diff --git "a/log/debug_0.log" "b/log/debug_0.log" --- "a/log/debug_0.log" +++ "b/log/debug_0.log" @@ -39536,3 +39536,1009 @@ Use FP16 precision: False 02/26/2022 04:03:25 - INFO - codeparrot_training - Step 38998: {'lr': 6.206162678185817e-05, 'samples': 19967488, 'steps': 38998, 'loss/train': 1.4853224754333496} 02/26/2022 04:03:29 - INFO - codeparrot_training - Step 38999: {'lr': 6.205083705349965e-05, 'samples': 19968000, 'steps': 38999, 'loss/train': 1.7108924388885498} 02/26/2022 04:03:29 - INFO - codeparrot_training - Evaluating and saving model checkpoint +02/26/2022 04:03:47 - WARNING - huggingface_hub.repository - Several commits (39) will be pushed upstream. +02/26/2022 04:03:47 - WARNING - huggingface_hub.repository - The progress bars may be unreliable. +02/26/2022 04:04:24 - WARNING - huggingface_hub.repository - To https://huggingface.co/ncoop57/multi-code-clippy + e53c3e1..d2106d5 floral-grass-11 -> floral-grass-11 + +02/26/2022 04:04:30 - INFO - codeparrot_training - Step 39000: {'lr': 6.204004813025568e-05, 'samples': 19968512, 'steps': 39000, 'loss/train': 1.6747545003890991} +02/26/2022 04:04:34 - INFO - codeparrot_training - Step 39001: {'lr': 6.202926001217246e-05, 'samples': 19969024, 'steps': 39001, 'loss/train': 2.013767957687378} +02/26/2022 04:04:40 - INFO - codeparrot_training - Step 39002: {'lr': 6.201847269929612e-05, 'samples': 19969536, 'steps': 39002, 'loss/train': 1.7280240058898926} +02/26/2022 04:04:43 - INFO - codeparrot_training - Step 39003: {'lr': 6.200768619167301e-05, 'samples': 19970048, 'steps': 39003, 'loss/train': 1.1755962371826172} +02/26/2022 04:04:48 - INFO - codeparrot_training - Step 39004: {'lr': 6.199690048934933e-05, 'samples': 19970560, 'steps': 39004, 'loss/train': 2.298581123352051} +02/26/2022 04:04:52 - INFO - codeparrot_training - Step 39005: {'lr': 6.198611559237111e-05, 'samples': 19971072, 'steps': 39005, 'loss/train': 2.570070266723633} +02/26/2022 04:04:57 - INFO - codeparrot_training - Step 39006: {'lr': 6.197533150078483e-05, 'samples': 19971584, 'steps': 39006, 'loss/train': 0.574073851108551} +02/26/2022 04:05:01 - INFO - codeparrot_training - Step 39007: {'lr': 6.19645482146364e-05, 'samples': 19972096, 'steps': 39007, 'loss/train': 1.7723450660705566} +02/26/2022 04:05:08 - INFO - codeparrot_training - Step 39008: {'lr': 6.195376573397218e-05, 'samples': 19972608, 'steps': 39008, 'loss/train': 2.274547576904297} +02/26/2022 04:05:11 - INFO - codeparrot_training - Step 39009: {'lr': 6.194298405883825e-05, 'samples': 19973120, 'steps': 39009, 'loss/train': 1.4609389305114746} +02/26/2022 04:05:17 - INFO - codeparrot_training - Step 39010: {'lr': 6.193220318928102e-05, 'samples': 19973632, 'steps': 39010, 'loss/train': 2.611638069152832} +02/26/2022 04:05:20 - INFO - codeparrot_training - Step 39011: {'lr': 6.192142312534634e-05, 'samples': 19974144, 'steps': 39011, 'loss/train': 0.7639550566673279} +02/26/2022 04:05:26 - INFO - codeparrot_training - Step 39012: {'lr': 6.191064386708067e-05, 'samples': 19974656, 'steps': 39012, 'loss/train': 2.3598923683166504} +02/26/2022 04:05:29 - INFO - codeparrot_training - Step 39013: {'lr': 6.189986541453e-05, 'samples': 19975168, 'steps': 39013, 'loss/train': 2.697425603866577} +02/26/2022 04:05:35 - INFO - codeparrot_training - Step 39014: {'lr': 6.188908776774068e-05, 'samples': 19975680, 'steps': 39014, 'loss/train': 1.5055482387542725} +02/26/2022 04:05:38 - INFO - codeparrot_training - Step 39015: {'lr': 6.187831092675868e-05, 'samples': 19976192, 'steps': 39015, 'loss/train': 2.531839609146118} +02/26/2022 04:05:44 - INFO - codeparrot_training - Step 39016: {'lr': 6.186753489163033e-05, 'samples': 19976704, 'steps': 39016, 'loss/train': 1.9931358098983765} +02/26/2022 04:05:47 - INFO - codeparrot_training - Step 39017: {'lr': 6.185675966240161e-05, 'samples': 19977216, 'steps': 39017, 'loss/train': 1.963324785232544} +02/26/2022 04:05:54 - INFO - codeparrot_training - Step 39018: {'lr': 6.184598523911889e-05, 'samples': 19977728, 'steps': 39018, 'loss/train': 1.312903642654419} +02/26/2022 04:05:57 - INFO - codeparrot_training - Step 39019: {'lr': 6.183521162182824e-05, 'samples': 19978240, 'steps': 39019, 'loss/train': 2.381755828857422} +02/26/2022 04:06:03 - INFO - codeparrot_training - Step 39020: {'lr': 6.182443881057576e-05, 'samples': 19978752, 'steps': 39020, 'loss/train': 2.02602219581604} +02/26/2022 04:06:06 - INFO - codeparrot_training - Step 39021: {'lr': 6.181366680540756e-05, 'samples': 19979264, 'steps': 39021, 'loss/train': 1.2970889806747437} +02/26/2022 04:06:12 - INFO - codeparrot_training - Step 39022: {'lr': 6.180289560636995e-05, 'samples': 19979776, 'steps': 39022, 'loss/train': 3.331634521484375} +02/26/2022 04:06:15 - INFO - codeparrot_training - Step 39023: {'lr': 6.179212521350896e-05, 'samples': 19980288, 'steps': 39023, 'loss/train': 1.0699663162231445} +02/26/2022 04:06:21 - INFO - codeparrot_training - Step 39024: {'lr': 6.178135562687076e-05, 'samples': 19980800, 'steps': 39024, 'loss/train': 2.4809956550598145} +02/26/2022 04:06:24 - INFO - codeparrot_training - Step 39025: {'lr': 6.177058684650139e-05, 'samples': 19981312, 'steps': 39025, 'loss/train': 1.640254259109497} +02/26/2022 04:06:30 - INFO - codeparrot_training - Step 39026: {'lr': 6.175981887244711e-05, 'samples': 19981824, 'steps': 39026, 'loss/train': 0.6718084812164307} +02/26/2022 04:06:33 - INFO - codeparrot_training - Step 39027: {'lr': 6.174905170475401e-05, 'samples': 19982336, 'steps': 39027, 'loss/train': 1.9465161561965942} +02/26/2022 04:06:40 - INFO - codeparrot_training - Step 39028: {'lr': 6.17382853434682e-05, 'samples': 19982848, 'steps': 39028, 'loss/train': 1.8279520273208618} +02/26/2022 04:06:44 - INFO - codeparrot_training - Step 39029: {'lr': 6.172751978863572e-05, 'samples': 19983360, 'steps': 39029, 'loss/train': 2.2108936309814453} +02/26/2022 04:06:49 - INFO - codeparrot_training - Step 39030: {'lr': 6.171675504030283e-05, 'samples': 19983872, 'steps': 39030, 'loss/train': 1.1732641458511353} +02/26/2022 04:06:53 - INFO - codeparrot_training - Step 39031: {'lr': 6.170599109851549e-05, 'samples': 19984384, 'steps': 39031, 'loss/train': 1.1962976455688477} +02/26/2022 04:06:58 - INFO - codeparrot_training - Step 39032: {'lr': 6.169522796332005e-05, 'samples': 19984896, 'steps': 39032, 'loss/train': 1.1763854026794434} +02/26/2022 04:07:01 - INFO - codeparrot_training - Step 39033: {'lr': 6.168446563476232e-05, 'samples': 19985408, 'steps': 39033, 'loss/train': 1.3611056804656982} +02/26/2022 04:07:07 - INFO - codeparrot_training - Step 39034: {'lr': 6.167370411288862e-05, 'samples': 19985920, 'steps': 39034, 'loss/train': 1.4905256032943726} +02/26/2022 04:07:10 - INFO - codeparrot_training - Step 39035: {'lr': 6.166294339774489e-05, 'samples': 19986432, 'steps': 39035, 'loss/train': 1.3192150592803955} +02/26/2022 04:07:16 - INFO - codeparrot_training - Step 39036: {'lr': 6.165218348937746e-05, 'samples': 19986944, 'steps': 39036, 'loss/train': 2.604614734649658} +02/26/2022 04:07:19 - INFO - codeparrot_training - Step 39037: {'lr': 6.16414243878321e-05, 'samples': 19987456, 'steps': 39037, 'loss/train': 2.1776161193847656} +02/26/2022 04:07:26 - INFO - codeparrot_training - Step 39038: {'lr': 6.163066609315515e-05, 'samples': 19987968, 'steps': 39038, 'loss/train': 2.0572500228881836} +02/26/2022 04:07:29 - INFO - codeparrot_training - Step 39039: {'lr': 6.161990860539263e-05, 'samples': 19988480, 'steps': 39039, 'loss/train': 2.081935405731201} +02/26/2022 04:07:35 - INFO - codeparrot_training - Step 39040: {'lr': 6.160915192459057e-05, 'samples': 19988992, 'steps': 39040, 'loss/train': 1.36495041847229} +02/26/2022 04:07:38 - INFO - codeparrot_training - Step 39041: {'lr': 6.159839605079504e-05, 'samples': 19989504, 'steps': 39041, 'loss/train': 1.8949660062789917} +02/26/2022 04:07:44 - INFO - codeparrot_training - Step 39042: {'lr': 6.158764098405223e-05, 'samples': 19990016, 'steps': 39042, 'loss/train': 1.2063840627670288} +02/26/2022 04:07:47 - INFO - codeparrot_training - Step 39043: {'lr': 6.157688672440811e-05, 'samples': 19990528, 'steps': 39043, 'loss/train': 1.7869585752487183} +02/26/2022 04:07:53 - INFO - codeparrot_training - Step 39044: {'lr': 6.156613327190874e-05, 'samples': 19991040, 'steps': 39044, 'loss/train': 1.2570009231567383} +02/26/2022 04:07:58 - INFO - codeparrot_training - Step 39045: {'lr': 6.155538062660027e-05, 'samples': 19991552, 'steps': 39045, 'loss/train': 1.178591012954712} +02/26/2022 04:08:02 - INFO - codeparrot_training - Step 39046: {'lr': 6.154462878852874e-05, 'samples': 19992064, 'steps': 39046, 'loss/train': 1.2912369966506958} +02/26/2022 04:08:07 - INFO - codeparrot_training - Step 39047: {'lr': 6.153387775774013e-05, 'samples': 19992576, 'steps': 39047, 'loss/train': 0.7543942332267761} +02/26/2022 04:08:10 - INFO - codeparrot_training - Step 39048: {'lr': 6.152312753428049e-05, 'samples': 19993088, 'steps': 39048, 'loss/train': 1.7838596105575562} +02/26/2022 04:08:16 - INFO - codeparrot_training - Step 39049: {'lr': 6.151237811819602e-05, 'samples': 19993600, 'steps': 39049, 'loss/train': 1.394836664199829} +02/26/2022 04:08:20 - INFO - codeparrot_training - Step 39050: {'lr': 6.150162950953264e-05, 'samples': 19994112, 'steps': 39050, 'loss/train': 1.4068769216537476} +02/26/2022 04:08:25 - INFO - codeparrot_training - Step 39051: {'lr': 6.149088170833644e-05, 'samples': 19994624, 'steps': 39051, 'loss/train': 1.8832015991210938} +02/26/2022 04:08:28 - INFO - codeparrot_training - Step 39052: {'lr': 6.148013471465339e-05, 'samples': 19995136, 'steps': 39052, 'loss/train': 1.757644534111023} +02/26/2022 04:08:35 - INFO - codeparrot_training - Step 39053: {'lr': 6.146938852852962e-05, 'samples': 19995648, 'steps': 39053, 'loss/train': 0.8891740441322327} +02/26/2022 04:08:38 - INFO - codeparrot_training - Step 39054: {'lr': 6.145864315001115e-05, 'samples': 19996160, 'steps': 39054, 'loss/train': 0.5175991058349609} +02/26/2022 04:08:44 - INFO - codeparrot_training - Step 39055: {'lr': 6.144789857914395e-05, 'samples': 19996672, 'steps': 39055, 'loss/train': 2.0041868686676025} +02/26/2022 04:08:47 - INFO - codeparrot_training - Step 39056: {'lr': 6.143715481597403e-05, 'samples': 19997184, 'steps': 39056, 'loss/train': 0.5072973370552063} +02/26/2022 04:08:53 - INFO - codeparrot_training - Step 39057: {'lr': 6.142641186054754e-05, 'samples': 19997696, 'steps': 39057, 'loss/train': 2.1547584533691406} +02/26/2022 04:08:56 - INFO - codeparrot_training - Step 39058: {'lr': 6.141566971291043e-05, 'samples': 19998208, 'steps': 39058, 'loss/train': 0.5618374943733215} +02/26/2022 04:09:02 - INFO - codeparrot_training - Step 39059: {'lr': 6.140492837310868e-05, 'samples': 19998720, 'steps': 39059, 'loss/train': 1.1311376094818115} +02/26/2022 04:09:05 - INFO - codeparrot_training - Step 39060: {'lr': 6.139418784118827e-05, 'samples': 19999232, 'steps': 39060, 'loss/train': 2.414172887802124} +02/26/2022 04:09:11 - INFO - codeparrot_training - Step 39061: {'lr': 6.138344811719537e-05, 'samples': 19999744, 'steps': 39061, 'loss/train': 1.0803378820419312} +02/26/2022 04:09:14 - INFO - codeparrot_training - Step 39062: {'lr': 6.137270920117585e-05, 'samples': 20000256, 'steps': 39062, 'loss/train': 1.6616593599319458} +02/26/2022 04:09:20 - INFO - codeparrot_training - Step 39063: {'lr': 6.136197109317576e-05, 'samples': 20000768, 'steps': 39063, 'loss/train': 2.315521001815796} +02/26/2022 04:09:23 - INFO - codeparrot_training - Step 39064: {'lr': 6.135123379324104e-05, 'samples': 20001280, 'steps': 39064, 'loss/train': 1.2328269481658936} +02/26/2022 04:09:29 - INFO - codeparrot_training - Step 39065: {'lr': 6.134049730141777e-05, 'samples': 20001792, 'steps': 39065, 'loss/train': 2.0177531242370605} +02/26/2022 04:09:33 - INFO - codeparrot_training - Step 39066: {'lr': 6.132976161775184e-05, 'samples': 20002304, 'steps': 39066, 'loss/train': 2.2230148315429688} +02/26/2022 04:09:38 - INFO - codeparrot_training - Step 39067: {'lr': 6.131902674228945e-05, 'samples': 20002816, 'steps': 39067, 'loss/train': 2.1659538745880127} +02/26/2022 04:09:42 - INFO - codeparrot_training - Step 39068: {'lr': 6.130829267507629e-05, 'samples': 20003328, 'steps': 39068, 'loss/train': 1.5368413925170898} +02/26/2022 04:09:47 - INFO - codeparrot_training - Step 39069: {'lr': 6.129755941615856e-05, 'samples': 20003840, 'steps': 39069, 'loss/train': 1.3174980878829956} +02/26/2022 04:09:51 - INFO - codeparrot_training - Step 39070: {'lr': 6.128682696558208e-05, 'samples': 20004352, 'steps': 39070, 'loss/train': 3.0974884033203125} +02/26/2022 04:09:56 - INFO - codeparrot_training - Step 39071: {'lr': 6.127609532339306e-05, 'samples': 20004864, 'steps': 39071, 'loss/train': 1.7564198970794678} +02/26/2022 04:10:00 - INFO - codeparrot_training - Step 39072: {'lr': 6.126536448963718e-05, 'samples': 20005376, 'steps': 39072, 'loss/train': 1.2487951517105103} +02/26/2022 04:10:05 - INFO - codeparrot_training - Step 39073: {'lr': 6.125463446436064e-05, 'samples': 20005888, 'steps': 39073, 'loss/train': 2.3441574573516846} +02/26/2022 04:10:09 - INFO - codeparrot_training - Step 39074: {'lr': 6.124390524760922e-05, 'samples': 20006400, 'steps': 39074, 'loss/train': 0.940067708492279} +02/26/2022 04:10:15 - INFO - codeparrot_training - Step 39075: {'lr': 6.123317683942914e-05, 'samples': 20006912, 'steps': 39075, 'loss/train': 0.6586630940437317} +02/26/2022 04:10:19 - INFO - codeparrot_training - Step 39076: {'lr': 6.1222449239866e-05, 'samples': 20007424, 'steps': 39076, 'loss/train': 2.0088090896606445} +02/26/2022 04:10:24 - INFO - codeparrot_training - Step 39077: {'lr': 6.121172244896606e-05, 'samples': 20007936, 'steps': 39077, 'loss/train': 1.6931359767913818} +02/26/2022 04:10:27 - INFO - codeparrot_training - Step 39078: {'lr': 6.120099646677507e-05, 'samples': 20008448, 'steps': 39078, 'loss/train': 0.8467195630073547} +02/26/2022 04:10:33 - INFO - codeparrot_training - Step 39079: {'lr': 6.119027129333913e-05, 'samples': 20008960, 'steps': 39079, 'loss/train': 0.9533653259277344} +02/26/2022 04:10:37 - INFO - codeparrot_training - Step 39080: {'lr': 6.117954692870411e-05, 'samples': 20009472, 'steps': 39080, 'loss/train': 2.099364757537842} +02/26/2022 04:10:42 - INFO - codeparrot_training - Step 39081: {'lr': 6.116882337291596e-05, 'samples': 20009984, 'steps': 39081, 'loss/train': 0.2943916320800781} +02/26/2022 04:10:46 - INFO - codeparrot_training - Step 39082: {'lr': 6.115810062602054e-05, 'samples': 20010496, 'steps': 39082, 'loss/train': 1.418568730354309} +02/26/2022 04:10:51 - INFO - codeparrot_training - Step 39083: {'lr': 6.114737868806391e-05, 'samples': 20011008, 'steps': 39083, 'loss/train': 1.548271656036377} +02/26/2022 04:10:55 - INFO - codeparrot_training - Step 39084: {'lr': 6.113665755909195e-05, 'samples': 20011520, 'steps': 39084, 'loss/train': 1.1802722215652466} +02/26/2022 04:11:01 - INFO - codeparrot_training - Step 39085: {'lr': 6.112593723915058e-05, 'samples': 20012032, 'steps': 39085, 'loss/train': 1.373261570930481} +02/26/2022 04:11:04 - INFO - codeparrot_training - Step 39086: {'lr': 6.11152177282857e-05, 'samples': 20012544, 'steps': 39086, 'loss/train': 2.176295518875122} +02/26/2022 04:11:10 - INFO - codeparrot_training - Step 39087: {'lr': 6.110449902654322e-05, 'samples': 20013056, 'steps': 39087, 'loss/train': 0.8322294354438782} +02/26/2022 04:11:13 - INFO - codeparrot_training - Step 39088: {'lr': 6.109378113396913e-05, 'samples': 20013568, 'steps': 39088, 'loss/train': 1.8421934843063354} +02/26/2022 04:11:19 - INFO - codeparrot_training - Step 39089: {'lr': 6.108306405060931e-05, 'samples': 20014080, 'steps': 39089, 'loss/train': 1.0519932508468628} +02/26/2022 04:11:22 - INFO - codeparrot_training - Step 39090: {'lr': 6.107234777650963e-05, 'samples': 20014592, 'steps': 39090, 'loss/train': 1.990525245666504} +02/26/2022 04:11:28 - INFO - codeparrot_training - Step 39091: {'lr': 6.1061632311716e-05, 'samples': 20015104, 'steps': 39091, 'loss/train': 1.5158153772354126} +02/26/2022 04:11:31 - INFO - codeparrot_training - Step 39092: {'lr': 6.105091765627435e-05, 'samples': 20015616, 'steps': 39092, 'loss/train': 1.4494901895523071} +02/26/2022 04:11:37 - INFO - codeparrot_training - Step 39093: {'lr': 6.104020381023063e-05, 'samples': 20016128, 'steps': 39093, 'loss/train': 2.059077024459839} +02/26/2022 04:11:40 - INFO - codeparrot_training - Step 39094: {'lr': 6.1029490773630626e-05, 'samples': 20016640, 'steps': 39094, 'loss/train': 2.198873519897461} +02/26/2022 04:11:46 - INFO - codeparrot_training - Step 39095: {'lr': 6.1018778546520246e-05, 'samples': 20017152, 'steps': 39095, 'loss/train': 5.161421775817871} +02/26/2022 04:11:49 - INFO - codeparrot_training - Step 39096: {'lr': 6.100806712894544e-05, 'samples': 20017664, 'steps': 39096, 'loss/train': 1.4846274852752686} +02/26/2022 04:11:55 - INFO - codeparrot_training - Step 39097: {'lr': 6.099735652095209e-05, 'samples': 20018176, 'steps': 39097, 'loss/train': 0.45562854409217834} +02/26/2022 04:11:58 - INFO - codeparrot_training - Step 39098: {'lr': 6.0986646722586056e-05, 'samples': 20018688, 'steps': 39098, 'loss/train': 1.5801427364349365} +02/26/2022 04:12:04 - INFO - codeparrot_training - Step 39099: {'lr': 6.0975937733893125e-05, 'samples': 20019200, 'steps': 39099, 'loss/train': 1.6328351497650146} +02/26/2022 04:12:08 - INFO - codeparrot_training - Step 39100: {'lr': 6.0965229554919313e-05, 'samples': 20019712, 'steps': 39100, 'loss/train': 2.513152837753296} +02/26/2022 04:12:14 - INFO - codeparrot_training - Step 39101: {'lr': 6.09545221857104e-05, 'samples': 20020224, 'steps': 39101, 'loss/train': 2.6437675952911377} +02/26/2022 04:12:17 - INFO - codeparrot_training - Step 39102: {'lr': 6.09438156263124e-05, 'samples': 20020736, 'steps': 39102, 'loss/train': 3.066319704055786} +02/26/2022 04:12:22 - INFO - codeparrot_training - Step 39103: {'lr': 6.093310987677092e-05, 'samples': 20021248, 'steps': 39103, 'loss/train': 1.15779447555542} +02/26/2022 04:12:26 - INFO - codeparrot_training - Step 39104: {'lr': 6.0922404937132054e-05, 'samples': 20021760, 'steps': 39104, 'loss/train': 2.651045560836792} +02/26/2022 04:12:31 - INFO - codeparrot_training - Step 39105: {'lr': 6.0911700807441463e-05, 'samples': 20022272, 'steps': 39105, 'loss/train': 1.0412274599075317} +02/26/2022 04:12:37 - INFO - codeparrot_training - Step 39106: {'lr': 6.090099748774527e-05, 'samples': 20022784, 'steps': 39106, 'loss/train': 2.4487788677215576} +02/26/2022 04:12:40 - INFO - codeparrot_training - Step 39107: {'lr': 6.0890294978089014e-05, 'samples': 20023296, 'steps': 39107, 'loss/train': 1.915837049484253} +02/26/2022 04:12:46 - INFO - codeparrot_training - Step 39108: {'lr': 6.0879593278518744e-05, 'samples': 20023808, 'steps': 39108, 'loss/train': 2.437455654144287} +02/26/2022 04:12:49 - INFO - codeparrot_training - Step 39109: {'lr': 6.086889238908017e-05, 'samples': 20024320, 'steps': 39109, 'loss/train': 1.421085238456726} +02/26/2022 04:12:56 - INFO - codeparrot_training - Step 39110: {'lr': 6.085819230981934e-05, 'samples': 20024832, 'steps': 39110, 'loss/train': 1.716515302658081} +02/26/2022 04:12:59 - INFO - codeparrot_training - Step 39111: {'lr': 6.0847493040781855e-05, 'samples': 20025344, 'steps': 39111, 'loss/train': 2.38794207572937} +02/26/2022 04:13:05 - INFO - codeparrot_training - Step 39112: {'lr': 6.083679458201369e-05, 'samples': 20025856, 'steps': 39112, 'loss/train': 1.523942232131958} +02/26/2022 04:13:08 - INFO - codeparrot_training - Step 39113: {'lr': 6.082609693356056e-05, 'samples': 20026368, 'steps': 39113, 'loss/train': 0.8572320938110352} +02/26/2022 04:13:12 - INFO - codeparrot_training - Step 39114: {'lr': 6.0815400095468433e-05, 'samples': 20026880, 'steps': 39114, 'loss/train': 1.425020456314087} +02/26/2022 04:13:17 - INFO - codeparrot_training - Step 39115: {'lr': 6.080470406778305e-05, 'samples': 20027392, 'steps': 39115, 'loss/train': 1.7392770051956177} +02/26/2022 04:13:23 - INFO - codeparrot_training - Step 39116: {'lr': 6.079400885055025e-05, 'samples': 20027904, 'steps': 39116, 'loss/train': 1.9410251379013062} +02/26/2022 04:13:26 - INFO - codeparrot_training - Step 39117: {'lr': 6.078331444381577e-05, 'samples': 20028416, 'steps': 39117, 'loss/train': 0.9213608503341675} +02/26/2022 04:13:32 - INFO - codeparrot_training - Step 39118: {'lr': 6.0772620847625555e-05, 'samples': 20028928, 'steps': 39118, 'loss/train': 2.0220468044281006} +02/26/2022 04:13:35 - INFO - codeparrot_training - Step 39119: {'lr': 6.0761928062025324e-05, 'samples': 20029440, 'steps': 39119, 'loss/train': 1.5902371406555176} +02/26/2022 04:13:42 - INFO - codeparrot_training - Step 39120: {'lr': 6.075123608706093e-05, 'samples': 20029952, 'steps': 39120, 'loss/train': 2.356743097305298} +02/26/2022 04:13:45 - INFO - codeparrot_training - Step 39121: {'lr': 6.0740544922778055e-05, 'samples': 20030464, 'steps': 39121, 'loss/train': 1.110445499420166} +02/26/2022 04:13:48 - INFO - codeparrot_training - Step 39122: {'lr': 6.07298545692227e-05, 'samples': 20030976, 'steps': 39122, 'loss/train': 1.3796019554138184} +02/26/2022 04:13:54 - INFO - codeparrot_training - Step 39123: {'lr': 6.071916502644051e-05, 'samples': 20031488, 'steps': 39123, 'loss/train': 1.4902094602584839} +02/26/2022 04:13:57 - INFO - codeparrot_training - Step 39124: {'lr': 6.070847629447732e-05, 'samples': 20032000, 'steps': 39124, 'loss/train': 2.1751444339752197} +02/26/2022 04:14:03 - INFO - codeparrot_training - Step 39125: {'lr': 6.069778837337886e-05, 'samples': 20032512, 'steps': 39125, 'loss/train': 1.48564875125885} +02/26/2022 04:14:09 - INFO - codeparrot_training - Step 39126: {'lr': 6.068710126319102e-05, 'samples': 20033024, 'steps': 39126, 'loss/train': 1.5054903030395508} +02/26/2022 04:14:12 - INFO - codeparrot_training - Step 39127: {'lr': 6.067641496395951e-05, 'samples': 20033536, 'steps': 39127, 'loss/train': 1.8296412229537964} +02/26/2022 04:14:18 - INFO - codeparrot_training - Step 39128: {'lr': 6.066572947573015e-05, 'samples': 20034048, 'steps': 39128, 'loss/train': 1.9717140197753906} +02/26/2022 04:14:21 - INFO - codeparrot_training - Step 39129: {'lr': 6.065504479854858e-05, 'samples': 20034560, 'steps': 39129, 'loss/train': 2.417285680770874} +02/26/2022 04:14:27 - INFO - codeparrot_training - Step 39130: {'lr': 6.064436093246078e-05, 'samples': 20035072, 'steps': 39130, 'loss/train': 2.8860702514648438} +02/26/2022 04:14:31 - INFO - codeparrot_training - Step 39131: {'lr': 6.06336778775124e-05, 'samples': 20035584, 'steps': 39131, 'loss/train': 1.8716504573822021} +02/26/2022 04:14:36 - INFO - codeparrot_training - Step 39132: {'lr': 6.062299563374921e-05, 'samples': 20036096, 'steps': 39132, 'loss/train': 2.9836840629577637} +02/26/2022 04:14:40 - INFO - codeparrot_training - Step 39133: {'lr': 6.061231420121688e-05, 'samples': 20036608, 'steps': 39133, 'loss/train': 1.7031925916671753} +02/26/2022 04:14:45 - INFO - codeparrot_training - Step 39134: {'lr': 6.0601633579961375e-05, 'samples': 20037120, 'steps': 39134, 'loss/train': 2.1716651916503906} +02/26/2022 04:14:49 - INFO - codeparrot_training - Step 39135: {'lr': 6.0590953770028296e-05, 'samples': 20037632, 'steps': 39135, 'loss/train': 2.3985800743103027} +02/26/2022 04:14:54 - INFO - codeparrot_training - Step 39136: {'lr': 6.058027477146344e-05, 'samples': 20038144, 'steps': 39136, 'loss/train': 2.794325351715088} +02/26/2022 04:14:58 - INFO - codeparrot_training - Step 39137: {'lr': 6.056959658431252e-05, 'samples': 20038656, 'steps': 39137, 'loss/train': 1.6470996141433716} +02/26/2022 04:15:03 - INFO - codeparrot_training - Step 39138: {'lr': 6.0558919208621246e-05, 'samples': 20039168, 'steps': 39138, 'loss/train': 1.3356456756591797} +02/26/2022 04:15:07 - INFO - codeparrot_training - Step 39139: {'lr': 6.054824264443548e-05, 'samples': 20039680, 'steps': 39139, 'loss/train': 2.127650737762451} +02/26/2022 04:15:12 - INFO - codeparrot_training - Step 39140: {'lr': 6.0537566891800815e-05, 'samples': 20040192, 'steps': 39140, 'loss/train': 1.527857780456543} +02/26/2022 04:15:16 - INFO - codeparrot_training - Step 39141: {'lr': 6.052689195076319e-05, 'samples': 20040704, 'steps': 39141, 'loss/train': 1.3834233283996582} +02/26/2022 04:15:22 - INFO - codeparrot_training - Step 39142: {'lr': 6.051621782136804e-05, 'samples': 20041216, 'steps': 39142, 'loss/train': 0.9246218800544739} +02/26/2022 04:15:25 - INFO - codeparrot_training - Step 39143: {'lr': 6.050554450366133e-05, 'samples': 20041728, 'steps': 39143, 'loss/train': 2.255917549133301} +02/26/2022 04:15:31 - INFO - codeparrot_training - Step 39144: {'lr': 6.0494871997688636e-05, 'samples': 20042240, 'steps': 39144, 'loss/train': 1.8913518190383911} +02/26/2022 04:15:34 - INFO - codeparrot_training - Step 39145: {'lr': 6.0484200303495855e-05, 'samples': 20042752, 'steps': 39145, 'loss/train': 1.3118107318878174} +02/26/2022 04:15:40 - INFO - codeparrot_training - Step 39146: {'lr': 6.0473529421128466e-05, 'samples': 20043264, 'steps': 39146, 'loss/train': 0.20709088444709778} +02/26/2022 04:15:44 - INFO - codeparrot_training - Step 39147: {'lr': 6.046285935063234e-05, 'samples': 20043776, 'steps': 39147, 'loss/train': 0.9929444193840027} +02/26/2022 04:15:49 - INFO - codeparrot_training - Step 39148: {'lr': 6.045219009205308e-05, 'samples': 20044288, 'steps': 39148, 'loss/train': 1.2968947887420654} +02/26/2022 04:15:53 - INFO - codeparrot_training - Step 39149: {'lr': 6.044152164543659e-05, 'samples': 20044800, 'steps': 39149, 'loss/train': 1.6446397304534912} +02/26/2022 04:15:58 - INFO - codeparrot_training - Step 39150: {'lr': 6.043085401082829e-05, 'samples': 20045312, 'steps': 39150, 'loss/train': 1.9716802835464478} +02/26/2022 04:16:02 - INFO - codeparrot_training - Step 39151: {'lr': 6.042018718827408e-05, 'samples': 20045824, 'steps': 39151, 'loss/train': 2.2467217445373535} +02/26/2022 04:16:07 - INFO - codeparrot_training - Step 39152: {'lr': 6.040952117781953e-05, 'samples': 20046336, 'steps': 39152, 'loss/train': 1.6879045963287354} +02/26/2022 04:16:11 - INFO - codeparrot_training - Step 39153: {'lr': 6.039885597951045e-05, 'samples': 20046848, 'steps': 39153, 'loss/train': 1.7481259107589722} +02/26/2022 04:16:17 - INFO - codeparrot_training - Step 39154: {'lr': 6.038819159339248e-05, 'samples': 20047360, 'steps': 39154, 'loss/train': 1.6514978408813477} +02/26/2022 04:16:20 - INFO - codeparrot_training - Step 39155: {'lr': 6.037752801951127e-05, 'samples': 20047872, 'steps': 39155, 'loss/train': 1.8021762371063232} +02/26/2022 04:16:26 - INFO - codeparrot_training - Step 39156: {'lr': 6.036686525791246e-05, 'samples': 20048384, 'steps': 39156, 'loss/train': 2.1468286514282227} +02/26/2022 04:16:29 - INFO - codeparrot_training - Step 39157: {'lr': 6.035620330864183e-05, 'samples': 20048896, 'steps': 39157, 'loss/train': 1.4882481098175049} +02/26/2022 04:16:35 - INFO - codeparrot_training - Step 39158: {'lr': 6.034554217174504e-05, 'samples': 20049408, 'steps': 39158, 'loss/train': 1.5330560207366943} +02/26/2022 04:16:38 - INFO - codeparrot_training - Step 39159: {'lr': 6.033488184726771e-05, 'samples': 20049920, 'steps': 39159, 'loss/train': 1.8926385641098022} +02/26/2022 04:16:44 - INFO - codeparrot_training - Step 39160: {'lr': 6.0324222335255445e-05, 'samples': 20050432, 'steps': 39160, 'loss/train': 2.3933095932006836} +02/26/2022 04:16:48 - INFO - codeparrot_training - Step 39161: {'lr': 6.0313563635754074e-05, 'samples': 20050944, 'steps': 39161, 'loss/train': 1.404457926750183} +02/26/2022 04:16:53 - INFO - codeparrot_training - Step 39162: {'lr': 6.030290574880909e-05, 'samples': 20051456, 'steps': 39162, 'loss/train': 1.5727367401123047} +02/26/2022 04:16:56 - INFO - codeparrot_training - Step 39163: {'lr': 6.029224867446634e-05, 'samples': 20051968, 'steps': 39163, 'loss/train': 1.8429498672485352} +02/26/2022 04:17:02 - INFO - codeparrot_training - Step 39164: {'lr': 6.028159241277123e-05, 'samples': 20052480, 'steps': 39164, 'loss/train': 1.6968461275100708} +02/26/2022 04:17:05 - INFO - codeparrot_training - Step 39165: {'lr': 6.0270936963769616e-05, 'samples': 20052992, 'steps': 39165, 'loss/train': 2.4597506523132324} +02/26/2022 04:17:12 - INFO - codeparrot_training - Step 39166: {'lr': 6.026028232750696e-05, 'samples': 20053504, 'steps': 39166, 'loss/train': 2.032080888748169} +02/26/2022 04:17:15 - INFO - codeparrot_training - Step 39167: {'lr': 6.024962850402918e-05, 'samples': 20054016, 'steps': 39167, 'loss/train': 1.5263077020645142} +02/26/2022 04:17:21 - INFO - codeparrot_training - Step 39168: {'lr': 6.023897549338159e-05, 'samples': 20054528, 'steps': 39168, 'loss/train': 1.8026885986328125} +02/26/2022 04:17:24 - INFO - codeparrot_training - Step 39169: {'lr': 6.022832329561004e-05, 'samples': 20055040, 'steps': 39169, 'loss/train': 1.3546422719955444} +02/26/2022 04:17:30 - INFO - codeparrot_training - Step 39170: {'lr': 6.0217671910760106e-05, 'samples': 20055552, 'steps': 39170, 'loss/train': 1.0742846727371216} +02/26/2022 04:17:34 - INFO - codeparrot_training - Step 39171: {'lr': 6.0207021338877396e-05, 'samples': 20056064, 'steps': 39171, 'loss/train': 1.150915503501892} +02/26/2022 04:17:39 - INFO - codeparrot_training - Step 39172: {'lr': 6.0196371580007456e-05, 'samples': 20056576, 'steps': 39172, 'loss/train': 0.050631504505872726} +02/26/2022 04:17:43 - INFO - codeparrot_training - Step 39173: {'lr': 6.018572263419608e-05, 'samples': 20057088, 'steps': 39173, 'loss/train': 1.9853448867797852} +02/26/2022 04:17:48 - INFO - codeparrot_training - Step 39174: {'lr': 6.0175074501488765e-05, 'samples': 20057600, 'steps': 39174, 'loss/train': 1.737609624862671} +02/26/2022 04:17:52 - INFO - codeparrot_training - Step 39175: {'lr': 6.01644271819311e-05, 'samples': 20058112, 'steps': 39175, 'loss/train': 1.288604736328125} +02/26/2022 04:17:57 - INFO - codeparrot_training - Step 39176: {'lr': 6.015378067556884e-05, 'samples': 20058624, 'steps': 39176, 'loss/train': 1.0448052883148193} +02/26/2022 04:18:01 - INFO - codeparrot_training - Step 39177: {'lr': 6.014313498244747e-05, 'samples': 20059136, 'steps': 39177, 'loss/train': 1.7478086948394775} +02/26/2022 04:18:07 - INFO - codeparrot_training - Step 39178: {'lr': 6.0132490102612654e-05, 'samples': 20059648, 'steps': 39178, 'loss/train': 2.2179555892944336} +02/26/2022 04:18:11 - INFO - codeparrot_training - Step 39179: {'lr': 6.012184603610987e-05, 'samples': 20060160, 'steps': 39179, 'loss/train': 0.7077801823616028} +02/26/2022 04:18:14 - INFO - codeparrot_training - Step 39180: {'lr': 6.0111202782984876e-05, 'samples': 20060672, 'steps': 39180, 'loss/train': 1.6781692504882812} +02/26/2022 04:18:21 - INFO - codeparrot_training - Step 39181: {'lr': 6.0100560343283205e-05, 'samples': 20061184, 'steps': 39181, 'loss/train': 1.0841268301010132} +02/26/2022 04:18:25 - INFO - codeparrot_training - Step 39182: {'lr': 6.008991871705041e-05, 'samples': 20061696, 'steps': 39182, 'loss/train': 1.9873597621917725} +02/26/2022 04:18:30 - INFO - codeparrot_training - Step 39183: {'lr': 6.0079277904332066e-05, 'samples': 20062208, 'steps': 39183, 'loss/train': 2.6531574726104736} +02/26/2022 04:18:34 - INFO - codeparrot_training - Step 39184: {'lr': 6.0068637905173916e-05, 'samples': 20062720, 'steps': 39184, 'loss/train': 1.067253589630127} +02/26/2022 04:18:39 - INFO - codeparrot_training - Step 39185: {'lr': 6.0057998719621256e-05, 'samples': 20063232, 'steps': 39185, 'loss/train': 1.839909553527832} +02/26/2022 04:18:43 - INFO - codeparrot_training - Step 39186: {'lr': 6.0047360347719874e-05, 'samples': 20063744, 'steps': 39186, 'loss/train': 1.4952328205108643} +02/26/2022 04:18:48 - INFO - codeparrot_training - Step 39187: {'lr': 6.0036722789515244e-05, 'samples': 20064256, 'steps': 39187, 'loss/train': 1.8996855020523071} +02/26/2022 04:18:52 - INFO - codeparrot_training - Step 39188: {'lr': 6.0026086045053025e-05, 'samples': 20064768, 'steps': 39188, 'loss/train': 1.3404773473739624} +02/26/2022 04:18:57 - INFO - codeparrot_training - Step 39189: {'lr': 6.001545011437875e-05, 'samples': 20065280, 'steps': 39189, 'loss/train': 1.9518004655838013} +02/26/2022 04:19:01 - INFO - codeparrot_training - Step 39190: {'lr': 6.000481499753793e-05, 'samples': 20065792, 'steps': 39190, 'loss/train': 1.6301372051239014} +02/26/2022 04:19:07 - INFO - codeparrot_training - Step 39191: {'lr': 5.99941806945761e-05, 'samples': 20066304, 'steps': 39191, 'loss/train': 1.8701907396316528} +02/26/2022 04:19:11 - INFO - codeparrot_training - Step 39192: {'lr': 5.998354720553895e-05, 'samples': 20066816, 'steps': 39192, 'loss/train': 1.5031712055206299} +02/26/2022 04:19:16 - INFO - codeparrot_training - Step 39193: {'lr': 5.9972914530471935e-05, 'samples': 20067328, 'steps': 39193, 'loss/train': 1.1715377569198608} +02/26/2022 04:19:20 - INFO - codeparrot_training - Step 39194: {'lr': 5.996228266942061e-05, 'samples': 20067840, 'steps': 39194, 'loss/train': 2.02754545211792} +02/26/2022 04:19:25 - INFO - codeparrot_training - Step 39195: {'lr': 5.9951651622430435e-05, 'samples': 20068352, 'steps': 39195, 'loss/train': 2.533637046813965} +02/26/2022 04:19:29 - INFO - codeparrot_training - Step 39196: {'lr': 5.994102138954713e-05, 'samples': 20068864, 'steps': 39196, 'loss/train': 1.5374023914337158} +02/26/2022 04:19:34 - INFO - codeparrot_training - Step 39197: {'lr': 5.9930391970816153e-05, 'samples': 20069376, 'steps': 39197, 'loss/train': 2.2290003299713135} +02/26/2022 04:19:38 - INFO - codeparrot_training - Step 39198: {'lr': 5.991976336628299e-05, 'samples': 20069888, 'steps': 39198, 'loss/train': 1.6066607236862183} +02/26/2022 04:19:43 - INFO - codeparrot_training - Step 39199: {'lr': 5.9909135575993146e-05, 'samples': 20070400, 'steps': 39199, 'loss/train': 1.2327711582183838} +02/26/2022 04:19:47 - INFO - codeparrot_training - Step 39200: {'lr': 5.989850859999227e-05, 'samples': 20070912, 'steps': 39200, 'loss/train': 0.9524955153465271} +02/26/2022 04:19:52 - INFO - codeparrot_training - Step 39201: {'lr': 5.988788243832577e-05, 'samples': 20071424, 'steps': 39201, 'loss/train': 1.780321717262268} +02/26/2022 04:19:56 - INFO - codeparrot_training - Step 39202: {'lr': 5.987725709103933e-05, 'samples': 20071936, 'steps': 39202, 'loss/train': 2.4739410877227783} +02/26/2022 04:20:02 - INFO - codeparrot_training - Step 39203: {'lr': 5.986663255817823e-05, 'samples': 20072448, 'steps': 39203, 'loss/train': 2.1084718704223633} +02/26/2022 04:20:08 - INFO - codeparrot_training - Step 39204: {'lr': 5.9856008839788145e-05, 'samples': 20072960, 'steps': 39204, 'loss/train': 2.607719659805298} +02/26/2022 04:20:11 - INFO - codeparrot_training - Step 39205: {'lr': 5.9845385935914486e-05, 'samples': 20073472, 'steps': 39205, 'loss/train': 1.553194284439087} +02/26/2022 04:20:17 - INFO - codeparrot_training - Step 39206: {'lr': 5.983476384660297e-05, 'samples': 20073984, 'steps': 39206, 'loss/train': 0.08067571371793747} +02/26/2022 04:20:20 - INFO - codeparrot_training - Step 39207: {'lr': 5.9824142571898774e-05, 'samples': 20074496, 'steps': 39207, 'loss/train': 0.5256961584091187} +02/26/2022 04:20:26 - INFO - codeparrot_training - Step 39208: {'lr': 5.981352211184765e-05, 'samples': 20075008, 'steps': 39208, 'loss/train': 2.068943738937378} +02/26/2022 04:20:29 - INFO - codeparrot_training - Step 39209: {'lr': 5.980290246649495e-05, 'samples': 20075520, 'steps': 39209, 'loss/train': 2.2667617797851562} +02/26/2022 04:20:33 - INFO - codeparrot_training - Step 39210: {'lr': 5.979228363588626e-05, 'samples': 20076032, 'steps': 39210, 'loss/train': 2.1234488487243652} +02/26/2022 04:20:39 - INFO - codeparrot_training - Step 39211: {'lr': 5.9781665620067035e-05, 'samples': 20076544, 'steps': 39211, 'loss/train': 1.2851656675338745} +02/26/2022 04:20:42 - INFO - codeparrot_training - Step 39212: {'lr': 5.977104841908276e-05, 'samples': 20077056, 'steps': 39212, 'loss/train': 2.129596471786499} +02/26/2022 04:20:49 - INFO - codeparrot_training - Step 39213: {'lr': 5.976043203297885e-05, 'samples': 20077568, 'steps': 39213, 'loss/train': 0.2620987892150879} +02/26/2022 04:20:52 - INFO - codeparrot_training - Step 39214: {'lr': 5.9749816461800884e-05, 'samples': 20078080, 'steps': 39214, 'loss/train': 2.2618589401245117} +02/26/2022 04:20:57 - INFO - codeparrot_training - Step 39215: {'lr': 5.9739201705594323e-05, 'samples': 20078592, 'steps': 39215, 'loss/train': 1.6342507600784302} +02/26/2022 04:21:01 - INFO - codeparrot_training - Step 39216: {'lr': 5.97285877644046e-05, 'samples': 20079104, 'steps': 39216, 'loss/train': 1.6585915088653564} +02/26/2022 04:21:07 - INFO - codeparrot_training - Step 39217: {'lr': 5.971797463827716e-05, 'samples': 20079616, 'steps': 39217, 'loss/train': 0.9379733800888062} +02/26/2022 04:21:10 - INFO - codeparrot_training - Step 39218: {'lr': 5.970736232725746e-05, 'samples': 20080128, 'steps': 39218, 'loss/train': 1.3840649127960205} +02/26/2022 04:21:16 - INFO - codeparrot_training - Step 39219: {'lr': 5.969675083139106e-05, 'samples': 20080640, 'steps': 39219, 'loss/train': 2.2475056648254395} +02/26/2022 04:21:19 - INFO - codeparrot_training - Step 39220: {'lr': 5.968614015072335e-05, 'samples': 20081152, 'steps': 39220, 'loss/train': 2.007514476776123} +02/26/2022 04:21:25 - INFO - codeparrot_training - Step 39221: {'lr': 5.967553028529976e-05, 'samples': 20081664, 'steps': 39221, 'loss/train': 1.9549225568771362} +02/26/2022 04:21:28 - INFO - codeparrot_training - Step 39222: {'lr': 5.966492123516573e-05, 'samples': 20082176, 'steps': 39222, 'loss/train': 1.4100981950759888} +02/26/2022 04:21:35 - INFO - codeparrot_training - Step 39223: {'lr': 5.965431300036678e-05, 'samples': 20082688, 'steps': 39223, 'loss/train': 2.825514316558838} +02/26/2022 04:21:38 - INFO - codeparrot_training - Step 39224: {'lr': 5.964370558094831e-05, 'samples': 20083200, 'steps': 39224, 'loss/train': 2.0286624431610107} +02/26/2022 04:21:44 - INFO - codeparrot_training - Step 39225: {'lr': 5.963309897695579e-05, 'samples': 20083712, 'steps': 39225, 'loss/train': 1.9217307567596436} +02/26/2022 04:21:49 - INFO - codeparrot_training - Step 39226: {'lr': 5.962249318843455e-05, 'samples': 20084224, 'steps': 39226, 'loss/train': 0.926033616065979} +02/26/2022 04:21:53 - INFO - codeparrot_training - Step 39227: {'lr': 5.961188821543015e-05, 'samples': 20084736, 'steps': 39227, 'loss/train': 2.020341634750366} +02/26/2022 04:21:56 - INFO - codeparrot_training - Step 39228: {'lr': 5.9601284057987954e-05, 'samples': 20085248, 'steps': 39228, 'loss/train': 1.7333258390426636} +02/26/2022 04:22:02 - INFO - codeparrot_training - Step 39229: {'lr': 5.9590680716153425e-05, 'samples': 20085760, 'steps': 39229, 'loss/train': 1.9270201921463013} +02/26/2022 04:22:07 - INFO - codeparrot_training - Step 39230: {'lr': 5.958007818997188e-05, 'samples': 20086272, 'steps': 39230, 'loss/train': 1.4925305843353271} +02/26/2022 04:22:11 - INFO - codeparrot_training - Step 39231: {'lr': 5.956947647948888e-05, 'samples': 20086784, 'steps': 39231, 'loss/train': 1.597577452659607} +02/26/2022 04:22:16 - INFO - codeparrot_training - Step 39232: {'lr': 5.9558875584749786e-05, 'samples': 20087296, 'steps': 39232, 'loss/train': 1.6095819473266602} +02/26/2022 04:22:20 - INFO - codeparrot_training - Step 39233: {'lr': 5.95482755058e-05, 'samples': 20087808, 'steps': 39233, 'loss/train': 2.490502119064331} +02/26/2022 04:22:25 - INFO - codeparrot_training - Step 39234: {'lr': 5.953767624268483e-05, 'samples': 20088320, 'steps': 39234, 'loss/train': 2.119033098220825} +02/26/2022 04:22:29 - INFO - codeparrot_training - Step 39235: {'lr': 5.952707779544986e-05, 'samples': 20088832, 'steps': 39235, 'loss/train': 1.9056191444396973} +02/26/2022 04:22:35 - INFO - codeparrot_training - Step 39236: {'lr': 5.951648016414035e-05, 'samples': 20089344, 'steps': 39236, 'loss/train': 1.6329952478408813} +02/26/2022 04:22:38 - INFO - codeparrot_training - Step 39237: {'lr': 5.950588334880189e-05, 'samples': 20089856, 'steps': 39237, 'loss/train': 0.4335310757160187} +02/26/2022 04:22:42 - INFO - codeparrot_training - Step 39238: {'lr': 5.949528734947959e-05, 'samples': 20090368, 'steps': 39238, 'loss/train': 1.3485746383666992} +02/26/2022 04:22:49 - INFO - codeparrot_training - Step 39239: {'lr': 5.948469216621904e-05, 'samples': 20090880, 'steps': 39239, 'loss/train': 1.9692628383636475} +02/26/2022 04:22:52 - INFO - codeparrot_training - Step 39240: {'lr': 5.947409779906554e-05, 'samples': 20091392, 'steps': 39240, 'loss/train': 1.220459222793579} +02/26/2022 04:22:57 - INFO - codeparrot_training - Step 39241: {'lr': 5.9463504248064625e-05, 'samples': 20091904, 'steps': 39241, 'loss/train': 1.8257173299789429} +02/26/2022 04:23:01 - INFO - codeparrot_training - Step 39242: {'lr': 5.94529115132614e-05, 'samples': 20092416, 'steps': 39242, 'loss/train': 1.7604314088821411} +02/26/2022 04:23:07 - INFO - codeparrot_training - Step 39243: {'lr': 5.9442319594701504e-05, 'samples': 20092928, 'steps': 39243, 'loss/train': 1.203141689300537} +02/26/2022 04:23:10 - INFO - codeparrot_training - Step 39244: {'lr': 5.943172849243012e-05, 'samples': 20093440, 'steps': 39244, 'loss/train': 2.061610221862793} +02/26/2022 04:23:16 - INFO - codeparrot_training - Step 39245: {'lr': 5.9421138206492806e-05, 'samples': 20093952, 'steps': 39245, 'loss/train': 1.656941294670105} +02/26/2022 04:23:19 - INFO - codeparrot_training - Step 39246: {'lr': 5.941054873693472e-05, 'samples': 20094464, 'steps': 39246, 'loss/train': 1.434607744216919} +02/26/2022 04:23:25 - INFO - codeparrot_training - Step 39247: {'lr': 5.9399960083801385e-05, 'samples': 20094976, 'steps': 39247, 'loss/train': 2.743180751800537} +02/26/2022 04:23:28 - INFO - codeparrot_training - Step 39248: {'lr': 5.9389372247138004e-05, 'samples': 20095488, 'steps': 39248, 'loss/train': 0.854601263999939} +02/26/2022 04:23:35 - INFO - codeparrot_training - Step 39249: {'lr': 5.937878522699011e-05, 'samples': 20096000, 'steps': 39249, 'loss/train': 1.7251155376434326} +02/26/2022 04:23:38 - INFO - codeparrot_training - Step 39250: {'lr': 5.936819902340299e-05, 'samples': 20096512, 'steps': 39250, 'loss/train': 1.9975084066390991} +02/26/2022 04:23:43 - INFO - codeparrot_training - Step 39251: {'lr': 5.935761363642195e-05, 'samples': 20097024, 'steps': 39251, 'loss/train': 1.8870348930358887} +02/26/2022 04:23:47 - INFO - codeparrot_training - Step 39252: {'lr': 5.934702906609229e-05, 'samples': 20097536, 'steps': 39252, 'loss/train': 2.1907081604003906} +02/26/2022 04:23:52 - INFO - codeparrot_training - Step 39253: {'lr': 5.933644531245952e-05, 'samples': 20098048, 'steps': 39253, 'loss/train': 0.7847607135772705} +02/26/2022 04:23:56 - INFO - codeparrot_training - Step 39254: {'lr': 5.9325862375568835e-05, 'samples': 20098560, 'steps': 39254, 'loss/train': 1.7179933786392212} +02/26/2022 04:24:01 - INFO - codeparrot_training - Step 39255: {'lr': 5.931528025546565e-05, 'samples': 20099072, 'steps': 39255, 'loss/train': 1.0662907361984253} +02/26/2022 04:24:05 - INFO - codeparrot_training - Step 39256: {'lr': 5.9304698952195147e-05, 'samples': 20099584, 'steps': 39256, 'loss/train': 1.7633732557296753} +02/26/2022 04:24:10 - INFO - codeparrot_training - Step 39257: {'lr': 5.9294118465802847e-05, 'samples': 20100096, 'steps': 39257, 'loss/train': 0.9880204796791077} +02/26/2022 04:24:14 - INFO - codeparrot_training - Step 39258: {'lr': 5.9283538796334e-05, 'samples': 20100608, 'steps': 39258, 'loss/train': 1.5551226139068604} +02/26/2022 04:24:21 - INFO - codeparrot_training - Step 39259: {'lr': 5.9272959943833886e-05, 'samples': 20101120, 'steps': 39259, 'loss/train': 1.6984381675720215} +02/26/2022 04:24:26 - INFO - codeparrot_training - Step 39260: {'lr': 5.926238190834779e-05, 'samples': 20101632, 'steps': 39260, 'loss/train': 1.2085760831832886} +02/26/2022 04:24:30 - INFO - codeparrot_training - Step 39261: {'lr': 5.925180468992117e-05, 'samples': 20102144, 'steps': 39261, 'loss/train': 1.8080426454544067} +02/26/2022 04:24:35 - INFO - codeparrot_training - Step 39262: {'lr': 5.924122828859921e-05, 'samples': 20102656, 'steps': 39262, 'loss/train': 3.404402494430542} +02/26/2022 04:24:39 - INFO - codeparrot_training - Step 39263: {'lr': 5.923065270442729e-05, 'samples': 20103168, 'steps': 39263, 'loss/train': 1.4390474557876587} +02/26/2022 04:24:44 - INFO - codeparrot_training - Step 39264: {'lr': 5.922007793745068e-05, 'samples': 20103680, 'steps': 39264, 'loss/train': 2.132646322250366} +02/26/2022 04:24:48 - INFO - codeparrot_training - Step 39265: {'lr': 5.9209503987714574e-05, 'samples': 20104192, 'steps': 39265, 'loss/train': 1.136685848236084} +02/26/2022 04:24:53 - INFO - codeparrot_training - Step 39266: {'lr': 5.919893085526448e-05, 'samples': 20104704, 'steps': 39266, 'loss/train': 2.5582213401794434} +02/26/2022 04:24:57 - INFO - codeparrot_training - Step 39267: {'lr': 5.918835854014557e-05, 'samples': 20105216, 'steps': 39267, 'loss/train': 1.631758451461792} +02/26/2022 04:25:02 - INFO - codeparrot_training - Step 39268: {'lr': 5.917778704240312e-05, 'samples': 20105728, 'steps': 39268, 'loss/train': 1.1914089918136597} +02/26/2022 04:25:06 - INFO - codeparrot_training - Step 39269: {'lr': 5.916721636208239e-05, 'samples': 20106240, 'steps': 39269, 'loss/train': 0.9935445189476013} +02/26/2022 04:25:11 - INFO - codeparrot_training - Step 39270: {'lr': 5.915664649922875e-05, 'samples': 20106752, 'steps': 39270, 'loss/train': 0.8829196691513062} +02/26/2022 04:25:15 - INFO - codeparrot_training - Step 39271: {'lr': 5.914607745388739e-05, 'samples': 20107264, 'steps': 39271, 'loss/train': 0.5542932748794556} +02/26/2022 04:25:22 - INFO - codeparrot_training - Step 39272: {'lr': 5.913550922610378e-05, 'samples': 20107776, 'steps': 39272, 'loss/train': 2.1349236965179443} +02/26/2022 04:25:25 - INFO - codeparrot_training - Step 39273: {'lr': 5.912494181592287e-05, 'samples': 20108288, 'steps': 39273, 'loss/train': 1.980897307395935} +02/26/2022 04:25:31 - INFO - codeparrot_training - Step 39274: {'lr': 5.911437522339019e-05, 'samples': 20108800, 'steps': 39274, 'loss/train': 1.7240952253341675} +02/26/2022 04:25:34 - INFO - codeparrot_training - Step 39275: {'lr': 5.910380944855087e-05, 'samples': 20109312, 'steps': 39275, 'loss/train': 1.6117587089538574} +02/26/2022 04:25:40 - INFO - codeparrot_training - Step 39276: {'lr': 5.909324449145032e-05, 'samples': 20109824, 'steps': 39276, 'loss/train': 2.7535886764526367} +02/26/2022 04:25:43 - INFO - codeparrot_training - Step 39277: {'lr': 5.9082680352133546e-05, 'samples': 20110336, 'steps': 39277, 'loss/train': 2.589470863342285} +02/26/2022 04:25:49 - INFO - codeparrot_training - Step 39278: {'lr': 5.907211703064605e-05, 'samples': 20110848, 'steps': 39278, 'loss/train': 0.8415930271148682} +02/26/2022 04:25:53 - INFO - codeparrot_training - Step 39279: {'lr': 5.9061554527032876e-05, 'samples': 20111360, 'steps': 39279, 'loss/train': 7.042550086975098} +02/26/2022 04:25:56 - INFO - codeparrot_training - Step 39280: {'lr': 5.905099284133952e-05, 'samples': 20111872, 'steps': 39280, 'loss/train': 1.2340879440307617} +02/26/2022 04:26:02 - INFO - codeparrot_training - Step 39281: {'lr': 5.9040431973610945e-05, 'samples': 20112384, 'steps': 39281, 'loss/train': 2.5818324089050293} +02/26/2022 04:26:05 - INFO - codeparrot_training - Step 39282: {'lr': 5.9029871923892584e-05, 'samples': 20112896, 'steps': 39282, 'loss/train': 2.3087260723114014} +02/26/2022 04:26:11 - INFO - codeparrot_training - Step 39283: {'lr': 5.901931269222954e-05, 'samples': 20113408, 'steps': 39283, 'loss/train': 3.098461866378784} +02/26/2022 04:26:14 - INFO - codeparrot_training - Step 39284: {'lr': 5.9008754278667196e-05, 'samples': 20113920, 'steps': 39284, 'loss/train': 0.7448910474777222} +02/26/2022 04:26:21 - INFO - codeparrot_training - Step 39285: {'lr': 5.899819668325071e-05, 'samples': 20114432, 'steps': 39285, 'loss/train': 2.2561213970184326} +02/26/2022 04:26:24 - INFO - codeparrot_training - Step 39286: {'lr': 5.898763990602529e-05, 'samples': 20114944, 'steps': 39286, 'loss/train': 1.7975585460662842} +02/26/2022 04:26:30 - INFO - codeparrot_training - Step 39287: {'lr': 5.8977083947036105e-05, 'samples': 20115456, 'steps': 39287, 'loss/train': 1.4839191436767578} +02/26/2022 04:26:33 - INFO - codeparrot_training - Step 39288: {'lr': 5.8966528806328496e-05, 'samples': 20115968, 'steps': 39288, 'loss/train': 2.5699148178100586} +02/26/2022 04:26:39 - INFO - codeparrot_training - Step 39289: {'lr': 5.89559744839476e-05, 'samples': 20116480, 'steps': 39289, 'loss/train': 2.296220541000366} +02/26/2022 04:26:44 - INFO - codeparrot_training - Step 39290: {'lr': 5.8945420979938686e-05, 'samples': 20116992, 'steps': 39290, 'loss/train': 1.9628002643585205} +02/26/2022 04:26:48 - INFO - codeparrot_training - Step 39291: {'lr': 5.8934868294346825e-05, 'samples': 20117504, 'steps': 39291, 'loss/train': 0.9136307239532471} +02/26/2022 04:26:53 - INFO - codeparrot_training - Step 39292: {'lr': 5.8924316427217375e-05, 'samples': 20118016, 'steps': 39292, 'loss/train': 1.4834866523742676} +02/26/2022 04:26:57 - INFO - codeparrot_training - Step 39293: {'lr': 5.891376537859553e-05, 'samples': 20118528, 'steps': 39293, 'loss/train': 8.36025619506836} +02/26/2022 04:27:00 - INFO - codeparrot_training - Step 39294: {'lr': 5.89032151485264e-05, 'samples': 20119040, 'steps': 39294, 'loss/train': 1.8752689361572266} +02/26/2022 04:27:07 - INFO - codeparrot_training - Step 39295: {'lr': 5.889266573705515e-05, 'samples': 20119552, 'steps': 39295, 'loss/train': 1.0926858186721802} +02/26/2022 04:27:10 - INFO - codeparrot_training - Step 39296: {'lr': 5.8882117144227115e-05, 'samples': 20120064, 'steps': 39296, 'loss/train': 0.7730099558830261} +02/26/2022 04:27:16 - INFO - codeparrot_training - Step 39297: {'lr': 5.887156937008739e-05, 'samples': 20120576, 'steps': 39297, 'loss/train': 0.5640190839767456} +02/26/2022 04:27:22 - INFO - codeparrot_training - Step 39298: {'lr': 5.886102241468119e-05, 'samples': 20121088, 'steps': 39298, 'loss/train': 1.6185075044631958} +02/26/2022 04:27:25 - INFO - codeparrot_training - Step 39299: {'lr': 5.885047627805359e-05, 'samples': 20121600, 'steps': 39299, 'loss/train': 2.024411678314209} +02/26/2022 04:27:31 - INFO - codeparrot_training - Step 39300: {'lr': 5.883993096024992e-05, 'samples': 20122112, 'steps': 39300, 'loss/train': 2.4282212257385254} +02/26/2022 04:27:34 - INFO - codeparrot_training - Step 39301: {'lr': 5.88293864613153e-05, 'samples': 20122624, 'steps': 39301, 'loss/train': 2.111492395401001} +02/26/2022 04:27:40 - INFO - codeparrot_training - Step 39302: {'lr': 5.881884278129487e-05, 'samples': 20123136, 'steps': 39302, 'loss/train': 1.8113347291946411} +02/26/2022 04:27:43 - INFO - codeparrot_training - Step 39303: {'lr': 5.880829992023376e-05, 'samples': 20123648, 'steps': 39303, 'loss/train': 1.0204998254776} +02/26/2022 04:27:50 - INFO - codeparrot_training - Step 39304: {'lr': 5.8797757878177234e-05, 'samples': 20124160, 'steps': 39304, 'loss/train': 1.738308310508728} +02/26/2022 04:27:53 - INFO - codeparrot_training - Step 39305: {'lr': 5.8787216655170426e-05, 'samples': 20124672, 'steps': 39305, 'loss/train': 2.6062076091766357} +02/26/2022 04:27:59 - INFO - codeparrot_training - Step 39306: {'lr': 5.877667625125843e-05, 'samples': 20125184, 'steps': 39306, 'loss/train': 2.0921237468719482} +02/26/2022 04:28:02 - INFO - codeparrot_training - Step 39307: {'lr': 5.876613666648639e-05, 'samples': 20125696, 'steps': 39307, 'loss/train': 2.2125446796417236} +02/26/2022 04:28:08 - INFO - codeparrot_training - Step 39308: {'lr': 5.875559790089957e-05, 'samples': 20126208, 'steps': 39308, 'loss/train': 0.8944153785705566} +02/26/2022 04:28:11 - INFO - codeparrot_training - Step 39309: {'lr': 5.874505995454302e-05, 'samples': 20126720, 'steps': 39309, 'loss/train': 2.05277681350708} +02/26/2022 04:28:17 - INFO - codeparrot_training - Step 39310: {'lr': 5.8734522827461836e-05, 'samples': 20127232, 'steps': 39310, 'loss/train': 2.3895952701568604} +02/26/2022 04:28:20 - INFO - codeparrot_training - Step 39311: {'lr': 5.872398651970137e-05, 'samples': 20127744, 'steps': 39311, 'loss/train': 2.25655460357666} +02/26/2022 04:28:26 - INFO - codeparrot_training - Step 39312: {'lr': 5.871345103130646e-05, 'samples': 20128256, 'steps': 39312, 'loss/train': 1.6194692850112915} +02/26/2022 04:28:29 - INFO - codeparrot_training - Step 39313: {'lr': 5.870291636232247e-05, 'samples': 20128768, 'steps': 39313, 'loss/train': 1.6633578538894653} +02/26/2022 04:28:36 - INFO - codeparrot_training - Step 39314: {'lr': 5.869238251279438e-05, 'samples': 20129280, 'steps': 39314, 'loss/train': 1.8502283096313477} +02/26/2022 04:28:39 - INFO - codeparrot_training - Step 39315: {'lr': 5.8681849482767504e-05, 'samples': 20129792, 'steps': 39315, 'loss/train': 2.0411758422851562} +02/26/2022 04:28:45 - INFO - codeparrot_training - Step 39316: {'lr': 5.8671317272286664e-05, 'samples': 20130304, 'steps': 39316, 'loss/train': 2.1014180183410645} +02/26/2022 04:28:48 - INFO - codeparrot_training - Step 39317: {'lr': 5.8660785881397255e-05, 'samples': 20130816, 'steps': 39317, 'loss/train': 1.5701884031295776} +02/26/2022 04:28:54 - INFO - codeparrot_training - Step 39318: {'lr': 5.8650255310144204e-05, 'samples': 20131328, 'steps': 39318, 'loss/train': 1.7019730806350708} +02/26/2022 04:28:57 - INFO - codeparrot_training - Step 39319: {'lr': 5.8639725558572776e-05, 'samples': 20131840, 'steps': 39319, 'loss/train': 1.6158745288848877} +02/26/2022 04:29:03 - INFO - codeparrot_training - Step 39320: {'lr': 5.8629196626728e-05, 'samples': 20132352, 'steps': 39320, 'loss/train': 0.9566727876663208} +02/26/2022 04:29:06 - INFO - codeparrot_training - Step 39321: {'lr': 5.861866851465494e-05, 'samples': 20132864, 'steps': 39321, 'loss/train': 0.9225515723228455} +02/26/2022 04:29:12 - INFO - codeparrot_training - Step 39322: {'lr': 5.8608141222398717e-05, 'samples': 20133376, 'steps': 39322, 'loss/train': 1.4531960487365723} +02/26/2022 04:29:15 - INFO - codeparrot_training - Step 39323: {'lr': 5.859761475000447e-05, 'samples': 20133888, 'steps': 39323, 'loss/train': 1.919107437133789} +02/26/2022 04:29:21 - INFO - codeparrot_training - Step 39324: {'lr': 5.858708909751731e-05, 'samples': 20134400, 'steps': 39324, 'loss/train': 1.379542589187622} +02/26/2022 04:29:24 - INFO - codeparrot_training - Step 39325: {'lr': 5.857656426498223e-05, 'samples': 20134912, 'steps': 39325, 'loss/train': 0.8056464195251465} +02/26/2022 04:29:30 - INFO - codeparrot_training - Step 39326: {'lr': 5.856604025244433e-05, 'samples': 20135424, 'steps': 39326, 'loss/train': 1.9633475542068481} +02/26/2022 04:29:33 - INFO - codeparrot_training - Step 39327: {'lr': 5.8555517059948796e-05, 'samples': 20135936, 'steps': 39327, 'loss/train': 2.098339557647705} +02/26/2022 04:29:39 - INFO - codeparrot_training - Step 39328: {'lr': 5.854499468754063e-05, 'samples': 20136448, 'steps': 39328, 'loss/train': 1.830745816230774} +02/26/2022 04:29:42 - INFO - codeparrot_training - Step 39329: {'lr': 5.8534473135264886e-05, 'samples': 20136960, 'steps': 39329, 'loss/train': 2.612426519393921} +02/26/2022 04:29:47 - INFO - codeparrot_training - Step 39330: {'lr': 5.852395240316663e-05, 'samples': 20137472, 'steps': 39330, 'loss/train': 1.74697744846344} +02/26/2022 04:29:51 - INFO - codeparrot_training - Step 39331: {'lr': 5.851343249129101e-05, 'samples': 20137984, 'steps': 39331, 'loss/train': 1.3093727827072144} +02/26/2022 04:29:57 - INFO - codeparrot_training - Step 39332: {'lr': 5.850291339968297e-05, 'samples': 20138496, 'steps': 39332, 'loss/train': 0.5128688216209412} +02/26/2022 04:30:01 - INFO - codeparrot_training - Step 39333: {'lr': 5.84923951283878e-05, 'samples': 20139008, 'steps': 39333, 'loss/train': 1.4556185007095337} +02/26/2022 04:30:06 - INFO - codeparrot_training - Step 39334: {'lr': 5.848187767745025e-05, 'samples': 20139520, 'steps': 39334, 'loss/train': 2.0599207878112793} +02/26/2022 04:30:10 - INFO - codeparrot_training - Step 39335: {'lr': 5.847136104691558e-05, 'samples': 20140032, 'steps': 39335, 'loss/train': 0.5377969145774841} +02/26/2022 04:30:15 - INFO - codeparrot_training - Step 39336: {'lr': 5.8460845236828736e-05, 'samples': 20140544, 'steps': 39336, 'loss/train': 2.2448954582214355} +02/26/2022 04:30:19 - INFO - codeparrot_training - Step 39337: {'lr': 5.8450330247234925e-05, 'samples': 20141056, 'steps': 39337, 'loss/train': 1.9493519067764282} +02/26/2022 04:30:24 - INFO - codeparrot_training - Step 39338: {'lr': 5.8439816078178945e-05, 'samples': 20141568, 'steps': 39338, 'loss/train': 2.260248899459839} +02/26/2022 04:30:28 - INFO - codeparrot_training - Step 39339: {'lr': 5.8429302729706035e-05, 'samples': 20142080, 'steps': 39339, 'loss/train': 1.9130685329437256} +02/26/2022 04:30:35 - INFO - codeparrot_training - Step 39340: {'lr': 5.841879020186111e-05, 'samples': 20142592, 'steps': 39340, 'loss/train': 1.8006200790405273} +02/26/2022 04:30:38 - INFO - codeparrot_training - Step 39341: {'lr': 5.840827849468938e-05, 'samples': 20143104, 'steps': 39341, 'loss/train': 1.5545932054519653} +02/26/2022 04:30:44 - INFO - codeparrot_training - Step 39342: {'lr': 5.839776760823559e-05, 'samples': 20143616, 'steps': 39342, 'loss/train': 1.3660191297531128} +02/26/2022 04:30:47 - INFO - codeparrot_training - Step 39343: {'lr': 5.838725754254501e-05, 'samples': 20144128, 'steps': 39343, 'loss/train': 1.8794853687286377} +02/26/2022 04:30:53 - INFO - codeparrot_training - Step 39344: {'lr': 5.837674829766257e-05, 'samples': 20144640, 'steps': 39344, 'loss/train': 0.9432389140129089} +02/26/2022 04:30:56 - INFO - codeparrot_training - Step 39345: {'lr': 5.8366239873633235e-05, 'samples': 20145152, 'steps': 39345, 'loss/train': 1.6982903480529785} +02/26/2022 04:31:02 - INFO - codeparrot_training - Step 39346: {'lr': 5.835573227050214e-05, 'samples': 20145664, 'steps': 39346, 'loss/train': 1.7196199893951416} +02/26/2022 04:31:07 - INFO - codeparrot_training - Step 39347: {'lr': 5.834522548831422e-05, 'samples': 20146176, 'steps': 39347, 'loss/train': 0.8640785813331604} +02/26/2022 04:31:11 - INFO - codeparrot_training - Step 39348: {'lr': 5.8334719527114527e-05, 'samples': 20146688, 'steps': 39348, 'loss/train': 0.711805522441864} +02/26/2022 04:31:17 - INFO - codeparrot_training - Step 39349: {'lr': 5.832421438694793e-05, 'samples': 20147200, 'steps': 39349, 'loss/train': 1.9360721111297607} +02/26/2022 04:31:21 - INFO - codeparrot_training - Step 39350: {'lr': 5.831371006785963e-05, 'samples': 20147712, 'steps': 39350, 'loss/train': 1.4671344757080078} +02/26/2022 04:31:26 - INFO - codeparrot_training - Step 39351: {'lr': 5.830320656989452e-05, 'samples': 20148224, 'steps': 39351, 'loss/train': 0.11848215758800507} +02/26/2022 04:31:30 - INFO - codeparrot_training - Step 39352: {'lr': 5.829270389309763e-05, 'samples': 20148736, 'steps': 39352, 'loss/train': 0.18754246830940247} +02/26/2022 04:31:35 - INFO - codeparrot_training - Step 39353: {'lr': 5.82822020375138e-05, 'samples': 20149248, 'steps': 39353, 'loss/train': 1.3263994455337524} +02/26/2022 04:31:39 - INFO - codeparrot_training - Step 39354: {'lr': 5.8271701003188235e-05, 'samples': 20149760, 'steps': 39354, 'loss/train': 1.3562870025634766} +02/26/2022 04:31:44 - INFO - codeparrot_training - Step 39355: {'lr': 5.8261200790165836e-05, 'samples': 20150272, 'steps': 39355, 'loss/train': 1.4552899599075317} +02/26/2022 04:31:48 - INFO - codeparrot_training - Step 39356: {'lr': 5.825070139849156e-05, 'samples': 20150784, 'steps': 39356, 'loss/train': 0.9698016047477722} +02/26/2022 04:31:53 - INFO - codeparrot_training - Step 39357: {'lr': 5.824020282821033e-05, 'samples': 20151296, 'steps': 39357, 'loss/train': 2.542808771133423} +02/26/2022 04:31:57 - INFO - codeparrot_training - Step 39358: {'lr': 5.822970507936723e-05, 'samples': 20151808, 'steps': 39358, 'loss/train': 0.5101855397224426} +02/26/2022 04:32:02 - INFO - codeparrot_training - Step 39359: {'lr': 5.821920815200718e-05, 'samples': 20152320, 'steps': 39359, 'loss/train': 2.373020887374878} +02/26/2022 04:32:06 - INFO - codeparrot_training - Step 39360: {'lr': 5.8208712046175144e-05, 'samples': 20152832, 'steps': 39360, 'loss/train': 1.9011986255645752} +02/26/2022 04:32:12 - INFO - codeparrot_training - Step 39361: {'lr': 5.819821676191603e-05, 'samples': 20153344, 'steps': 39361, 'loss/train': 2.2148470878601074} +02/26/2022 04:32:15 - INFO - codeparrot_training - Step 39362: {'lr': 5.8187722299274906e-05, 'samples': 20153856, 'steps': 39362, 'loss/train': 1.9350521564483643} +02/26/2022 04:32:21 - INFO - codeparrot_training - Step 39363: {'lr': 5.817722865829669e-05, 'samples': 20154368, 'steps': 39363, 'loss/train': 1.215533971786499} +02/26/2022 04:32:24 - INFO - codeparrot_training - Step 39364: {'lr': 5.816673583902632e-05, 'samples': 20154880, 'steps': 39364, 'loss/train': 0.38346776366233826} +02/26/2022 04:32:30 - INFO - codeparrot_training - Step 39365: {'lr': 5.815624384150867e-05, 'samples': 20155392, 'steps': 39365, 'loss/train': 2.0341482162475586} +02/26/2022 04:32:33 - INFO - codeparrot_training - Step 39366: {'lr': 5.8145752665788785e-05, 'samples': 20155904, 'steps': 39366, 'loss/train': 1.2874284982681274} +02/26/2022 04:32:39 - INFO - codeparrot_training - Step 39367: {'lr': 5.813526231191155e-05, 'samples': 20156416, 'steps': 39367, 'loss/train': 1.7480957508087158} +02/26/2022 04:32:42 - INFO - codeparrot_training - Step 39368: {'lr': 5.812477277992204e-05, 'samples': 20156928, 'steps': 39368, 'loss/train': 0.8566776514053345} +02/26/2022 04:32:48 - INFO - codeparrot_training - Step 39369: {'lr': 5.8114284069864934e-05, 'samples': 20157440, 'steps': 39369, 'loss/train': 0.7865034341812134} +02/26/2022 04:32:51 - INFO - codeparrot_training - Step 39370: {'lr': 5.810379618178541e-05, 'samples': 20157952, 'steps': 39370, 'loss/train': 1.5552150011062622} +02/26/2022 04:32:58 - INFO - codeparrot_training - Step 39371: {'lr': 5.809330911572819e-05, 'samples': 20158464, 'steps': 39371, 'loss/train': 1.130629301071167} +02/26/2022 04:33:01 - INFO - codeparrot_training - Step 39372: {'lr': 5.808282287173844e-05, 'samples': 20158976, 'steps': 39372, 'loss/train': 1.0659348964691162} +02/26/2022 04:33:07 - INFO - codeparrot_training - Step 39373: {'lr': 5.807233744986079e-05, 'samples': 20159488, 'steps': 39373, 'loss/train': 0.5839967131614685} +02/26/2022 04:33:10 - INFO - codeparrot_training - Step 39374: {'lr': 5.8061852850140375e-05, 'samples': 20160000, 'steps': 39374, 'loss/train': 0.6007506251335144} +02/26/2022 04:33:16 - INFO - codeparrot_training - Step 39375: {'lr': 5.805136907262198e-05, 'samples': 20160512, 'steps': 39375, 'loss/train': 0.9831951260566711} +02/26/2022 04:33:19 - INFO - codeparrot_training - Step 39376: {'lr': 5.80408861173507e-05, 'samples': 20161024, 'steps': 39376, 'loss/train': 1.2300870418548584} +02/26/2022 04:33:25 - INFO - codeparrot_training - Step 39377: {'lr': 5.8030403984371175e-05, 'samples': 20161536, 'steps': 39377, 'loss/train': 1.255632996559143} +02/26/2022 04:33:28 - INFO - codeparrot_training - Step 39378: {'lr': 5.801992267372849e-05, 'samples': 20162048, 'steps': 39378, 'loss/train': 1.1090407371520996} +02/26/2022 04:33:34 - INFO - codeparrot_training - Step 39379: {'lr': 5.800944218546744e-05, 'samples': 20162560, 'steps': 39379, 'loss/train': 2.11875319480896} +02/26/2022 04:33:37 - INFO - codeparrot_training - Step 39380: {'lr': 5.799896251963305e-05, 'samples': 20163072, 'steps': 39380, 'loss/train': 0.767371416091919} +02/26/2022 04:33:43 - INFO - codeparrot_training - Step 39381: {'lr': 5.798848367627016e-05, 'samples': 20163584, 'steps': 39381, 'loss/train': 2.4251301288604736} +02/26/2022 04:33:46 - INFO - codeparrot_training - Step 39382: {'lr': 5.7978005655423605e-05, 'samples': 20164096, 'steps': 39382, 'loss/train': 1.3876231908798218} +02/26/2022 04:33:52 - INFO - codeparrot_training - Step 39383: {'lr': 5.7967528457138234e-05, 'samples': 20164608, 'steps': 39383, 'loss/train': 1.9034079313278198} +02/26/2022 04:33:55 - INFO - codeparrot_training - Step 39384: {'lr': 5.7957052081459074e-05, 'samples': 20165120, 'steps': 39384, 'loss/train': 1.6483125686645508} +02/26/2022 04:34:01 - INFO - codeparrot_training - Step 39385: {'lr': 5.794657652843091e-05, 'samples': 20165632, 'steps': 39385, 'loss/train': 1.4535356760025024} +02/26/2022 04:34:04 - INFO - codeparrot_training - Step 39386: {'lr': 5.793610179809863e-05, 'samples': 20166144, 'steps': 39386, 'loss/train': 1.7032256126403809} +02/26/2022 04:34:11 - INFO - codeparrot_training - Step 39387: {'lr': 5.7925627890507036e-05, 'samples': 20166656, 'steps': 39387, 'loss/train': 1.9047123193740845} +02/26/2022 04:34:14 - INFO - codeparrot_training - Step 39388: {'lr': 5.791515480570111e-05, 'samples': 20167168, 'steps': 39388, 'loss/train': 1.7393555641174316} +02/26/2022 04:34:20 - INFO - codeparrot_training - Step 39389: {'lr': 5.790468254372569e-05, 'samples': 20167680, 'steps': 39389, 'loss/train': 1.853602409362793} +02/26/2022 04:34:23 - INFO - codeparrot_training - Step 39390: {'lr': 5.7894211104625614e-05, 'samples': 20168192, 'steps': 39390, 'loss/train': 2.9697265625} +02/26/2022 04:34:29 - INFO - codeparrot_training - Step 39391: {'lr': 5.788374048844566e-05, 'samples': 20168704, 'steps': 39391, 'loss/train': 1.748284101486206} +02/26/2022 04:34:32 - INFO - codeparrot_training - Step 39392: {'lr': 5.787327069523085e-05, 'samples': 20169216, 'steps': 39392, 'loss/train': 1.6234177350997925} +02/26/2022 04:34:38 - INFO - codeparrot_training - Step 39393: {'lr': 5.786280172502592e-05, 'samples': 20169728, 'steps': 39393, 'loss/train': 1.5879952907562256} +02/26/2022 04:34:41 - INFO - codeparrot_training - Step 39394: {'lr': 5.7852333577875725e-05, 'samples': 20170240, 'steps': 39394, 'loss/train': 1.169845700263977} +02/26/2022 04:34:47 - INFO - codeparrot_training - Step 39395: {'lr': 5.7841866253825145e-05, 'samples': 20170752, 'steps': 39395, 'loss/train': 0.5379805564880371} +02/26/2022 04:34:50 - INFO - codeparrot_training - Step 39396: {'lr': 5.783139975291893e-05, 'samples': 20171264, 'steps': 39396, 'loss/train': 1.8642330169677734} +02/26/2022 04:34:57 - INFO - codeparrot_training - Step 39397: {'lr': 5.7820934075202005e-05, 'samples': 20171776, 'steps': 39397, 'loss/train': 2.3852691650390625} +02/26/2022 04:35:00 - INFO - codeparrot_training - Step 39398: {'lr': 5.781046922071922e-05, 'samples': 20172288, 'steps': 39398, 'loss/train': 2.105473518371582} +02/26/2022 04:35:06 - INFO - codeparrot_training - Step 39399: {'lr': 5.780000518951534e-05, 'samples': 20172800, 'steps': 39399, 'loss/train': 2.3800384998321533} +02/26/2022 04:35:11 - INFO - codeparrot_training - Step 39400: {'lr': 5.7789541981635134e-05, 'samples': 20173312, 'steps': 39400, 'loss/train': 2.753495216369629} +02/26/2022 04:35:15 - INFO - codeparrot_training - Step 39401: {'lr': 5.777907959712356e-05, 'samples': 20173824, 'steps': 39401, 'loss/train': 0.9524871110916138} +02/26/2022 04:35:20 - INFO - codeparrot_training - Step 39402: {'lr': 5.776861803602537e-05, 'samples': 20174336, 'steps': 39402, 'loss/train': 2.660076379776001} +02/26/2022 04:35:24 - INFO - codeparrot_training - Step 39403: {'lr': 5.77581572983854e-05, 'samples': 20174848, 'steps': 39403, 'loss/train': 2.8996992111206055} +02/26/2022 04:35:29 - INFO - codeparrot_training - Step 39404: {'lr': 5.774769738424837e-05, 'samples': 20175360, 'steps': 39404, 'loss/train': 1.8910436630249023} +02/26/2022 04:35:33 - INFO - codeparrot_training - Step 39405: {'lr': 5.7737238293659205e-05, 'samples': 20175872, 'steps': 39405, 'loss/train': 1.8484967947006226} +02/26/2022 04:35:40 - INFO - codeparrot_training - Step 39406: {'lr': 5.7726780026662594e-05, 'samples': 20176384, 'steps': 39406, 'loss/train': 2.237628936767578} +02/26/2022 04:35:43 - INFO - codeparrot_training - Step 39407: {'lr': 5.771632258330356e-05, 'samples': 20176896, 'steps': 39407, 'loss/train': 2.1191487312316895} +02/26/2022 04:35:49 - INFO - codeparrot_training - Step 39408: {'lr': 5.770586596362659e-05, 'samples': 20177408, 'steps': 39408, 'loss/train': 2.1390039920806885} +02/26/2022 04:35:52 - INFO - codeparrot_training - Step 39409: {'lr': 5.769541016767671e-05, 'samples': 20177920, 'steps': 39409, 'loss/train': 3.7390949726104736} +02/26/2022 04:35:58 - INFO - codeparrot_training - Step 39410: {'lr': 5.768495519549857e-05, 'samples': 20178432, 'steps': 39410, 'loss/train': 2.4449284076690674} +02/26/2022 04:36:01 - INFO - codeparrot_training - Step 39411: {'lr': 5.767450104713715e-05, 'samples': 20178944, 'steps': 39411, 'loss/train': 2.2156307697296143} +02/26/2022 04:36:07 - INFO - codeparrot_training - Step 39412: {'lr': 5.766404772263692e-05, 'samples': 20179456, 'steps': 39412, 'loss/train': 1.139458417892456} +02/26/2022 04:36:11 - INFO - codeparrot_training - Step 39413: {'lr': 5.7653595222042944e-05, 'samples': 20179968, 'steps': 39413, 'loss/train': 2.341097354888916} +02/26/2022 04:36:16 - INFO - codeparrot_training - Step 39414: {'lr': 5.764314354539982e-05, 'samples': 20180480, 'steps': 39414, 'loss/train': 0.0832589790225029} +02/26/2022 04:36:20 - INFO - codeparrot_training - Step 39415: {'lr': 5.763269269275251e-05, 'samples': 20180992, 'steps': 39415, 'loss/train': 1.841733694076538} +02/26/2022 04:36:27 - INFO - codeparrot_training - Step 39416: {'lr': 5.762224266414554e-05, 'samples': 20181504, 'steps': 39416, 'loss/train': 2.0044827461242676} +02/26/2022 04:36:30 - INFO - codeparrot_training - Step 39417: {'lr': 5.761179345962383e-05, 'samples': 20182016, 'steps': 39417, 'loss/train': 2.052302360534668} +02/26/2022 04:36:36 - INFO - codeparrot_training - Step 39418: {'lr': 5.760134507923206e-05, 'samples': 20182528, 'steps': 39418, 'loss/train': 1.4190049171447754} +02/26/2022 04:36:39 - INFO - codeparrot_training - Step 39419: {'lr': 5.7590897523015106e-05, 'samples': 20183040, 'steps': 39419, 'loss/train': 2.581770896911621} +02/26/2022 04:36:45 - INFO - codeparrot_training - Step 39420: {'lr': 5.758045079101765e-05, 'samples': 20183552, 'steps': 39420, 'loss/train': 1.4611321687698364} +02/26/2022 04:36:48 - INFO - codeparrot_training - Step 39421: {'lr': 5.757000488328446e-05, 'samples': 20184064, 'steps': 39421, 'loss/train': 2.043133020401001} +02/26/2022 04:36:54 - INFO - codeparrot_training - Step 39422: {'lr': 5.755955979986016e-05, 'samples': 20184576, 'steps': 39422, 'loss/train': 2.5207080841064453} +02/26/2022 04:36:57 - INFO - codeparrot_training - Step 39423: {'lr': 5.7549115540789705e-05, 'samples': 20185088, 'steps': 39423, 'loss/train': 1.8859179019927979} +02/26/2022 04:37:03 - INFO - codeparrot_training - Step 39424: {'lr': 5.753867210611771e-05, 'samples': 20185600, 'steps': 39424, 'loss/train': 0.813764750957489} +02/26/2022 04:37:06 - INFO - codeparrot_training - Step 39425: {'lr': 5.752822949588893e-05, 'samples': 20186112, 'steps': 39425, 'loss/train': 1.2927632331848145} +02/26/2022 04:37:12 - INFO - codeparrot_training - Step 39426: {'lr': 5.751778771014801e-05, 'samples': 20186624, 'steps': 39426, 'loss/train': 1.23225998878479} +02/26/2022 04:37:15 - INFO - codeparrot_training - Step 39427: {'lr': 5.750734674893987e-05, 'samples': 20187136, 'steps': 39427, 'loss/train': 1.6800318956375122} +02/26/2022 04:37:21 - INFO - codeparrot_training - Step 39428: {'lr': 5.749690661230914e-05, 'samples': 20187648, 'steps': 39428, 'loss/train': 2.3167762756347656} +02/26/2022 04:37:24 - INFO - codeparrot_training - Step 39429: {'lr': 5.748646730030049e-05, 'samples': 20188160, 'steps': 39429, 'loss/train': 0.8933626413345337} +02/26/2022 04:37:30 - INFO - codeparrot_training - Step 39430: {'lr': 5.747602881295866e-05, 'samples': 20188672, 'steps': 39430, 'loss/train': 2.0880558490753174} +02/26/2022 04:37:33 - INFO - codeparrot_training - Step 39431: {'lr': 5.746559115032843e-05, 'samples': 20189184, 'steps': 39431, 'loss/train': 1.8017241954803467} +02/26/2022 04:37:40 - INFO - codeparrot_training - Step 39432: {'lr': 5.745515431245449e-05, 'samples': 20189696, 'steps': 39432, 'loss/train': 1.7788697481155396} +02/26/2022 04:37:44 - INFO - codeparrot_training - Step 39433: {'lr': 5.7444718299381496e-05, 'samples': 20190208, 'steps': 39433, 'loss/train': 1.2854468822479248} +02/26/2022 04:37:49 - INFO - codeparrot_training - Step 39434: {'lr': 5.743428311115415e-05, 'samples': 20190720, 'steps': 39434, 'loss/train': 1.5779608488082886} +02/26/2022 04:37:53 - INFO - codeparrot_training - Step 39435: {'lr': 5.7423848747817256e-05, 'samples': 20191232, 'steps': 39435, 'loss/train': 1.9080621004104614} +02/26/2022 04:37:58 - INFO - codeparrot_training - Step 39436: {'lr': 5.741341520941543e-05, 'samples': 20191744, 'steps': 39436, 'loss/train': 1.552306890487671} +02/26/2022 04:38:02 - INFO - codeparrot_training - Step 39437: {'lr': 5.740298249599338e-05, 'samples': 20192256, 'steps': 39437, 'loss/train': 1.0564757585525513} +02/26/2022 04:38:07 - INFO - codeparrot_training - Step 39438: {'lr': 5.739255060759574e-05, 'samples': 20192768, 'steps': 39438, 'loss/train': 1.4067105054855347} +02/26/2022 04:38:11 - INFO - codeparrot_training - Step 39439: {'lr': 5.738211954426731e-05, 'samples': 20193280, 'steps': 39439, 'loss/train': 2.3647356033325195} +02/26/2022 04:38:16 - INFO - codeparrot_training - Step 39440: {'lr': 5.737168930605272e-05, 'samples': 20193792, 'steps': 39440, 'loss/train': 2.066711664199829} +02/26/2022 04:38:20 - INFO - codeparrot_training - Step 39441: {'lr': 5.736125989299659e-05, 'samples': 20194304, 'steps': 39441, 'loss/train': 1.963661551475525} +02/26/2022 04:38:27 - INFO - codeparrot_training - Step 39442: {'lr': 5.7350831305143766e-05, 'samples': 20194816, 'steps': 39442, 'loss/train': 0.5052897334098816} +02/26/2022 04:38:30 - INFO - codeparrot_training - Step 39443: {'lr': 5.7340403542538696e-05, 'samples': 20195328, 'steps': 39443, 'loss/train': 1.3866177797317505} +02/26/2022 04:38:36 - INFO - codeparrot_training - Step 39444: {'lr': 5.7329976605226206e-05, 'samples': 20195840, 'steps': 39444, 'loss/train': 2.0600945949554443} +02/26/2022 04:38:39 - INFO - codeparrot_training - Step 39445: {'lr': 5.7319550493250856e-05, 'samples': 20196352, 'steps': 39445, 'loss/train': 1.8887900114059448} +02/26/2022 04:38:45 - INFO - codeparrot_training - Step 39446: {'lr': 5.730912520665751e-05, 'samples': 20196864, 'steps': 39446, 'loss/train': 1.9036179780960083} +02/26/2022 04:38:48 - INFO - codeparrot_training - Step 39447: {'lr': 5.729870074549057e-05, 'samples': 20197376, 'steps': 39447, 'loss/train': 1.8594902753829956} +02/26/2022 04:38:54 - INFO - codeparrot_training - Step 39448: {'lr': 5.728827710979484e-05, 'samples': 20197888, 'steps': 39448, 'loss/train': 1.9182264804840088} +02/26/2022 04:38:57 - INFO - codeparrot_training - Step 39449: {'lr': 5.7277854299614876e-05, 'samples': 20198400, 'steps': 39449, 'loss/train': 1.698870062828064} +02/26/2022 04:39:03 - INFO - codeparrot_training - Step 39450: {'lr': 5.7267432314995535e-05, 'samples': 20198912, 'steps': 39450, 'loss/train': 2.3757519721984863} +02/26/2022 04:39:06 - INFO - codeparrot_training - Step 39451: {'lr': 5.725701115598117e-05, 'samples': 20199424, 'steps': 39451, 'loss/train': 0.23331354558467865} +02/26/2022 04:39:13 - INFO - codeparrot_training - Step 39452: {'lr': 5.7246590822616654e-05, 'samples': 20199936, 'steps': 39452, 'loss/train': 0.9359232187271118} +02/26/2022 04:39:16 - INFO - codeparrot_training - Step 39453: {'lr': 5.723617131494646e-05, 'samples': 20200448, 'steps': 39453, 'loss/train': 3.2734756469726562} +02/26/2022 04:39:22 - INFO - codeparrot_training - Step 39454: {'lr': 5.7225752633015354e-05, 'samples': 20200960, 'steps': 39454, 'loss/train': 2.4681668281555176} +02/26/2022 04:39:25 - INFO - codeparrot_training - Step 39455: {'lr': 5.721533477686791e-05, 'samples': 20201472, 'steps': 39455, 'loss/train': 2.2098896503448486} +02/26/2022 04:39:31 - INFO - codeparrot_training - Step 39456: {'lr': 5.720491774654876e-05, 'samples': 20201984, 'steps': 39456, 'loss/train': 2.2053308486938477} +02/26/2022 04:39:34 - INFO - codeparrot_training - Step 39457: {'lr': 5.7194501542102454e-05, 'samples': 20202496, 'steps': 39457, 'loss/train': 0.9811351895332336} +02/26/2022 04:39:40 - INFO - codeparrot_training - Step 39458: {'lr': 5.718408616357376e-05, 'samples': 20203008, 'steps': 39458, 'loss/train': 1.184763789176941} +02/26/2022 04:39:43 - INFO - codeparrot_training - Step 39459: {'lr': 5.717367161100723e-05, 'samples': 20203520, 'steps': 39459, 'loss/train': 1.5487140417099} +02/26/2022 04:39:49 - INFO - codeparrot_training - Step 39460: {'lr': 5.716325788444743e-05, 'samples': 20204032, 'steps': 39460, 'loss/train': 2.138392686843872} +02/26/2022 04:39:52 - INFO - codeparrot_training - Step 39461: {'lr': 5.7152844983938936e-05, 'samples': 20204544, 'steps': 39461, 'loss/train': 1.5722036361694336} +02/26/2022 04:39:58 - INFO - codeparrot_training - Step 39462: {'lr': 5.71424329095265e-05, 'samples': 20205056, 'steps': 39462, 'loss/train': 1.5240744352340698} +02/26/2022 04:40:01 - INFO - codeparrot_training - Step 39463: {'lr': 5.713202166125464e-05, 'samples': 20205568, 'steps': 39463, 'loss/train': 2.2927021980285645} +02/26/2022 04:40:07 - INFO - codeparrot_training - Step 39464: {'lr': 5.7121611239167954e-05, 'samples': 20206080, 'steps': 39464, 'loss/train': 0.7775042057037354} +02/26/2022 04:40:10 - INFO - codeparrot_training - Step 39465: {'lr': 5.711120164331096e-05, 'samples': 20206592, 'steps': 39465, 'loss/train': 1.3991249799728394} +02/26/2022 04:40:16 - INFO - codeparrot_training - Step 39466: {'lr': 5.710079287372841e-05, 'samples': 20207104, 'steps': 39466, 'loss/train': 2.436664342880249} +02/26/2022 04:40:20 - INFO - codeparrot_training - Step 39467: {'lr': 5.709038493046473e-05, 'samples': 20207616, 'steps': 39467, 'loss/train': 1.2326374053955078} +02/26/2022 04:40:26 - INFO - codeparrot_training - Step 39468: {'lr': 5.707997781356472e-05, 'samples': 20208128, 'steps': 39468, 'loss/train': 1.2545090913772583} +02/26/2022 04:40:30 - INFO - codeparrot_training - Step 39469: {'lr': 5.706957152307271e-05, 'samples': 20208640, 'steps': 39469, 'loss/train': 1.5603325366973877} +02/26/2022 04:40:35 - INFO - codeparrot_training - Step 39470: {'lr': 5.705916605903347e-05, 'samples': 20209152, 'steps': 39470, 'loss/train': 0.7118330597877502} +02/26/2022 04:40:39 - INFO - codeparrot_training - Step 39471: {'lr': 5.70487614214914e-05, 'samples': 20209664, 'steps': 39471, 'loss/train': 2.116262674331665} +02/26/2022 04:40:44 - INFO - codeparrot_training - Step 39472: {'lr': 5.703835761049131e-05, 'samples': 20210176, 'steps': 39472, 'loss/train': 1.6070528030395508} +02/26/2022 04:40:48 - INFO - codeparrot_training - Step 39473: {'lr': 5.702795462607749e-05, 'samples': 20210688, 'steps': 39473, 'loss/train': 1.1939600706100464} +02/26/2022 04:40:53 - INFO - codeparrot_training - Step 39474: {'lr': 5.701755246829471e-05, 'samples': 20211200, 'steps': 39474, 'loss/train': 2.164790391921997} +02/26/2022 04:40:57 - INFO - codeparrot_training - Step 39475: {'lr': 5.700715113718746e-05, 'samples': 20211712, 'steps': 39475, 'loss/train': 1.5403966903686523} +02/26/2022 04:41:02 - INFO - codeparrot_training - Step 39476: {'lr': 5.6996750632800215e-05, 'samples': 20212224, 'steps': 39476, 'loss/train': 2.2468080520629883} +02/26/2022 04:41:06 - INFO - codeparrot_training - Step 39477: {'lr': 5.698635095517768e-05, 'samples': 20212736, 'steps': 39477, 'loss/train': 2.535079002380371} +02/26/2022 04:41:13 - INFO - codeparrot_training - Step 39478: {'lr': 5.697595210436432e-05, 'samples': 20213248, 'steps': 39478, 'loss/train': 0.07792261987924576} +02/26/2022 04:41:16 - INFO - codeparrot_training - Step 39479: {'lr': 5.696555408040469e-05, 'samples': 20213760, 'steps': 39479, 'loss/train': 0.05075787007808685} +02/26/2022 04:41:22 - INFO - codeparrot_training - Step 39480: {'lr': 5.695515688334327e-05, 'samples': 20214272, 'steps': 39480, 'loss/train': 1.418874740600586} +02/26/2022 04:41:25 - INFO - codeparrot_training - Step 39481: {'lr': 5.6944760513224725e-05, 'samples': 20214784, 'steps': 39481, 'loss/train': 1.6823254823684692} +02/26/2022 04:41:31 - INFO - codeparrot_training - Step 39482: {'lr': 5.693436497009352e-05, 'samples': 20215296, 'steps': 39482, 'loss/train': 1.9608285427093506} +02/26/2022 04:41:34 - INFO - codeparrot_training - Step 39483: {'lr': 5.6923970253994176e-05, 'samples': 20215808, 'steps': 39483, 'loss/train': 1.87309730052948} +02/26/2022 04:41:40 - INFO - codeparrot_training - Step 39484: {'lr': 5.691357636497119e-05, 'samples': 20216320, 'steps': 39484, 'loss/train': 1.6646419763565063} +02/26/2022 04:41:43 - INFO - codeparrot_training - Step 39485: {'lr': 5.69031833030692e-05, 'samples': 20216832, 'steps': 39485, 'loss/train': 1.9159107208251953} +02/26/2022 04:41:49 - INFO - codeparrot_training - Step 39486: {'lr': 5.689279106833264e-05, 'samples': 20217344, 'steps': 39486, 'loss/train': 1.1292990446090698} +02/26/2022 04:41:52 - INFO - codeparrot_training - Step 39487: {'lr': 5.688239966080605e-05, 'samples': 20217856, 'steps': 39487, 'loss/train': 2.1154253482818604} +02/26/2022 04:41:59 - INFO - codeparrot_training - Step 39488: {'lr': 5.6872009080533885e-05, 'samples': 20218368, 'steps': 39488, 'loss/train': 1.952418327331543} +02/26/2022 04:42:02 - INFO - codeparrot_training - Step 39489: {'lr': 5.686161932756076e-05, 'samples': 20218880, 'steps': 39489, 'loss/train': 1.7327882051467896} +02/26/2022 04:42:08 - INFO - codeparrot_training - Step 39490: {'lr': 5.685123040193113e-05, 'samples': 20219392, 'steps': 39490, 'loss/train': 9.895872116088867} +02/26/2022 04:42:11 - INFO - codeparrot_training - Step 39491: {'lr': 5.684084230368952e-05, 'samples': 20219904, 'steps': 39491, 'loss/train': 2.5402824878692627} +02/26/2022 04:42:17 - INFO - codeparrot_training - Step 39492: {'lr': 5.6830455032880316e-05, 'samples': 20220416, 'steps': 39492, 'loss/train': 2.063387632369995} +02/26/2022 04:42:20 - INFO - codeparrot_training - Step 39493: {'lr': 5.6820068589548166e-05, 'samples': 20220928, 'steps': 39493, 'loss/train': 1.442240834236145} +02/26/2022 04:42:26 - INFO - codeparrot_training - Step 39494: {'lr': 5.680968297373754e-05, 'samples': 20221440, 'steps': 39494, 'loss/train': 2.397127628326416} +02/26/2022 04:42:29 - INFO - codeparrot_training - Step 39495: {'lr': 5.679929818549284e-05, 'samples': 20221952, 'steps': 39495, 'loss/train': 1.9233158826828003} +02/26/2022 04:42:35 - INFO - codeparrot_training - Step 39496: {'lr': 5.678891422485854e-05, 'samples': 20222464, 'steps': 39496, 'loss/train': 2.2014942169189453} +02/26/2022 04:42:38 - INFO - codeparrot_training - Step 39497: {'lr': 5.677853109187927e-05, 'samples': 20222976, 'steps': 39497, 'loss/train': 1.0298023223876953} +02/26/2022 04:42:45 - INFO - codeparrot_training - Step 39498: {'lr': 5.676814878659942e-05, 'samples': 20223488, 'steps': 39498, 'loss/train': 0.9240416288375854} +02/26/2022 04:42:48 - INFO - codeparrot_training - Step 39499: {'lr': 5.675776730906343e-05, 'samples': 20224000, 'steps': 39499, 'loss/train': 0.5989491939544678} +02/26/2022 04:42:54 - INFO - codeparrot_training - Step 39500: {'lr': 5.6747386659315755e-05, 'samples': 20224512, 'steps': 39500, 'loss/train': 1.4479424953460693} +02/26/2022 04:42:57 - INFO - codeparrot_training - Step 39501: {'lr': 5.673700683740099e-05, 'samples': 20225024, 'steps': 39501, 'loss/train': 1.8506078720092773} +02/26/2022 04:43:03 - INFO - codeparrot_training - Step 39502: {'lr': 5.672662784336344e-05, 'samples': 20225536, 'steps': 39502, 'loss/train': 2.0931456089019775} +02/26/2022 04:43:06 - INFO - codeparrot_training - Step 39503: {'lr': 5.6716249677247786e-05, 'samples': 20226048, 'steps': 39503, 'loss/train': 0.44452348351478577} +02/26/2022 04:43:12 - INFO - codeparrot_training - Step 39504: {'lr': 5.670587233909819e-05, 'samples': 20226560, 'steps': 39504, 'loss/train': 1.2021042108535767} +02/26/2022 04:43:15 - INFO - codeparrot_training - Step 39505: {'lr': 5.669549582895933e-05, 'samples': 20227072, 'steps': 39505, 'loss/train': 1.1801081895828247} +02/26/2022 04:43:21 - INFO - codeparrot_training - Step 39506: {'lr': 5.6685120146875545e-05, 'samples': 20227584, 'steps': 39506, 'loss/train': 1.5373822450637817} +02/26/2022 04:43:24 - INFO - codeparrot_training - Step 39507: {'lr': 5.6674745292891434e-05, 'samples': 20228096, 'steps': 39507, 'loss/train': 1.8907417058944702} +02/26/2022 04:43:31 - INFO - codeparrot_training - Step 39508: {'lr': 5.666437126705118e-05, 'samples': 20228608, 'steps': 39508, 'loss/train': 1.6787999868392944} +02/26/2022 04:43:34 - INFO - codeparrot_training - Step 39509: {'lr': 5.665399806939947e-05, 'samples': 20229120, 'steps': 39509, 'loss/train': 0.24926146864891052} +02/26/2022 04:43:40 - INFO - codeparrot_training - Step 39510: {'lr': 5.664362569998055e-05, 'samples': 20229632, 'steps': 39510, 'loss/train': 0.7358347177505493} +02/26/2022 04:43:44 - INFO - codeparrot_training - Step 39511: {'lr': 5.6633254158839074e-05, 'samples': 20230144, 'steps': 39511, 'loss/train': 1.1676466464996338} +02/26/2022 04:43:49 - INFO - codeparrot_training - Step 39512: {'lr': 5.662288344601921e-05, 'samples': 20230656, 'steps': 39512, 'loss/train': 1.6555445194244385} +02/26/2022 04:43:53 - INFO - codeparrot_training - Step 39513: {'lr': 5.6612513561565574e-05, 'samples': 20231168, 'steps': 39513, 'loss/train': 1.7136192321777344} +02/26/2022 04:43:58 - INFO - codeparrot_training - Step 39514: {'lr': 5.6602144505522455e-05, 'samples': 20231680, 'steps': 39514, 'loss/train': 2.512848138809204} +02/26/2022 04:44:02 - INFO - codeparrot_training - Step 39515: {'lr': 5.6591776277934383e-05, 'samples': 20232192, 'steps': 39515, 'loss/train': 1.4572277069091797} +02/26/2022 04:44:07 - INFO - codeparrot_training - Step 39516: {'lr': 5.6581408878845745e-05, 'samples': 20232704, 'steps': 39516, 'loss/train': 1.6925320625305176} +02/26/2022 04:44:13 - INFO - codeparrot_training - Step 39517: {'lr': 5.657104230830096e-05, 'samples': 20233216, 'steps': 39517, 'loss/train': 1.6385324001312256} +02/26/2022 04:44:16 - INFO - codeparrot_training - Step 39518: {'lr': 5.656067656634431e-05, 'samples': 20233728, 'steps': 39518, 'loss/train': 1.2513892650604248} +02/26/2022 04:44:22 - INFO - codeparrot_training - Step 39519: {'lr': 5.655031165302035e-05, 'samples': 20234240, 'steps': 39519, 'loss/train': 1.9805467128753662} +02/26/2022 04:44:25 - INFO - codeparrot_training - Step 39520: {'lr': 5.6539947568373466e-05, 'samples': 20234752, 'steps': 39520, 'loss/train': 1.527952790260315} +02/26/2022 04:44:31 - INFO - codeparrot_training - Step 39521: {'lr': 5.652958431244801e-05, 'samples': 20235264, 'steps': 39521, 'loss/train': 2.454334259033203} +02/26/2022 04:44:34 - INFO - codeparrot_training - Step 39522: {'lr': 5.6519221885288353e-05, 'samples': 20235776, 'steps': 39522, 'loss/train': 2.6586287021636963} +02/26/2022 04:44:41 - INFO - codeparrot_training - Step 39523: {'lr': 5.650886028693888e-05, 'samples': 20236288, 'steps': 39523, 'loss/train': 1.1758193969726562} +02/26/2022 04:44:45 - INFO - codeparrot_training - Step 39524: {'lr': 5.6498499517444044e-05, 'samples': 20236800, 'steps': 39524, 'loss/train': 1.6551343202590942} +02/26/2022 04:44:50 - INFO - codeparrot_training - Step 39525: {'lr': 5.6488139576848226e-05, 'samples': 20237312, 'steps': 39525, 'loss/train': 0.9471426010131836} +02/26/2022 04:44:54 - INFO - codeparrot_training - Step 39526: {'lr': 5.647778046519575e-05, 'samples': 20237824, 'steps': 39526, 'loss/train': 2.598798990249634} +02/26/2022 04:44:59 - INFO - codeparrot_training - Step 39527: {'lr': 5.646742218253095e-05, 'samples': 20238336, 'steps': 39527, 'loss/train': 1.8875553607940674} +02/26/2022 04:45:03 - INFO - codeparrot_training - Step 39528: {'lr': 5.645706472889833e-05, 'samples': 20238848, 'steps': 39528, 'loss/train': 0.7463963627815247} +02/26/2022 04:45:08 - INFO - codeparrot_training - Step 39529: {'lr': 5.6446708104342185e-05, 'samples': 20239360, 'steps': 39529, 'loss/train': 1.8360371589660645} +02/26/2022 04:45:12 - INFO - codeparrot_training - Step 39530: {'lr': 5.643635230890687e-05, 'samples': 20239872, 'steps': 39530, 'loss/train': 1.836422085762024} +02/26/2022 04:45:17 - INFO - codeparrot_training - Step 39531: {'lr': 5.64259973426367e-05, 'samples': 20240384, 'steps': 39531, 'loss/train': 2.352200508117676} +02/26/2022 04:45:21 - INFO - codeparrot_training - Step 39532: {'lr': 5.641564320557616e-05, 'samples': 20240896, 'steps': 39532, 'loss/train': 1.03348970413208} +02/26/2022 04:45:27 - INFO - codeparrot_training - Step 39533: {'lr': 5.6405289897769526e-05, 'samples': 20241408, 'steps': 39533, 'loss/train': 0.4009478986263275} +02/26/2022 04:45:31 - INFO - codeparrot_training - Step 39534: {'lr': 5.639493741926119e-05, 'samples': 20241920, 'steps': 39534, 'loss/train': 1.4194415807724} +02/26/2022 04:45:36 - INFO - codeparrot_training - Step 39535: {'lr': 5.638458577009537e-05, 'samples': 20242432, 'steps': 39535, 'loss/train': 2.4732158184051514} +02/26/2022 04:45:40 - INFO - codeparrot_training - Step 39536: {'lr': 5.637423495031657e-05, 'samples': 20242944, 'steps': 39536, 'loss/train': 1.328683853149414} +02/26/2022 04:45:45 - INFO - codeparrot_training - Step 39537: {'lr': 5.6363884959968996e-05, 'samples': 20243456, 'steps': 39537, 'loss/train': 2.2324206829071045} +02/26/2022 04:45:49 - INFO - codeparrot_training - Step 39538: {'lr': 5.635353579909719e-05, 'samples': 20243968, 'steps': 39538, 'loss/train': 0.16979217529296875} +02/26/2022 04:45:54 - INFO - codeparrot_training - Step 39539: {'lr': 5.6343187467745225e-05, 'samples': 20244480, 'steps': 39539, 'loss/train': 2.948667287826538} +02/26/2022 04:45:58 - INFO - codeparrot_training - Step 39540: {'lr': 5.633283996595762e-05, 'samples': 20244992, 'steps': 39540, 'loss/train': 1.7116411924362183} +02/26/2022 04:46:03 - INFO - codeparrot_training - Step 39541: {'lr': 5.6322493293778533e-05, 'samples': 20245504, 'steps': 39541, 'loss/train': 1.39324951171875} +02/26/2022 04:46:07 - INFO - codeparrot_training - Step 39542: {'lr': 5.631214745125254e-05, 'samples': 20246016, 'steps': 39542, 'loss/train': 1.6892502307891846} +02/26/2022 04:46:13 - INFO - codeparrot_training - Step 39543: {'lr': 5.63018024384237e-05, 'samples': 20246528, 'steps': 39543, 'loss/train': 1.9009425640106201} +02/26/2022 04:46:17 - INFO - codeparrot_training - Step 39544: {'lr': 5.629145825533646e-05, 'samples': 20247040, 'steps': 39544, 'loss/train': 0.9991382360458374} +02/26/2022 04:46:23 - INFO - codeparrot_training - Step 39545: {'lr': 5.628111490203505e-05, 'samples': 20247552, 'steps': 39545, 'loss/train': 1.6263071298599243} +02/26/2022 04:46:26 - INFO - codeparrot_training - Step 39546: {'lr': 5.6270772378563954e-05, 'samples': 20248064, 'steps': 39546, 'loss/train': 2.1895391941070557} +02/26/2022 04:46:32 - INFO - codeparrot_training - Step 39547: {'lr': 5.626043068496722e-05, 'samples': 20248576, 'steps': 39547, 'loss/train': 2.2050204277038574} +02/26/2022 04:46:35 - INFO - codeparrot_training - Step 39548: {'lr': 5.6250089821289375e-05, 'samples': 20249088, 'steps': 39548, 'loss/train': 1.783073902130127} +02/26/2022 04:46:41 - INFO - codeparrot_training - Step 39549: {'lr': 5.623974978757454e-05, 'samples': 20249600, 'steps': 39549, 'loss/train': 2.015637159347534} +02/26/2022 04:46:44 - INFO - codeparrot_training - Step 39550: {'lr': 5.622941058386716e-05, 'samples': 20250112, 'steps': 39550, 'loss/train': 2.2001965045928955} +02/26/2022 04:46:50 - INFO - codeparrot_training - Step 39551: {'lr': 5.621907221021144e-05, 'samples': 20250624, 'steps': 39551, 'loss/train': 0.774245023727417} +02/26/2022 04:46:54 - INFO - codeparrot_training - Step 39552: {'lr': 5.6208734666651686e-05, 'samples': 20251136, 'steps': 39552, 'loss/train': 1.522621989250183} +02/26/2022 04:46:59 - INFO - codeparrot_training - Step 39553: {'lr': 5.6198397953232114e-05, 'samples': 20251648, 'steps': 39553, 'loss/train': 1.6214483976364136} +02/26/2022 04:47:03 - INFO - codeparrot_training - Step 39554: {'lr': 5.618806206999716e-05, 'samples': 20252160, 'steps': 39554, 'loss/train': 1.1430423259735107} +02/26/2022 04:47:08 - INFO - codeparrot_training - Step 39555: {'lr': 5.6177727016990976e-05, 'samples': 20252672, 'steps': 39555, 'loss/train': 0.7819818258285522} +02/26/2022 04:47:12 - INFO - codeparrot_training - Step 39556: {'lr': 5.616739279425787e-05, 'samples': 20253184, 'steps': 39556, 'loss/train': 1.6150356531143188} +02/26/2022 04:47:17 - INFO - codeparrot_training - Step 39557: {'lr': 5.6157059401842045e-05, 'samples': 20253696, 'steps': 39557, 'loss/train': 1.6539686918258667} +02/26/2022 04:47:21 - INFO - codeparrot_training - Step 39558: {'lr': 5.614672683978789e-05, 'samples': 20254208, 'steps': 39558, 'loss/train': 1.4277534484863281} +02/26/2022 04:47:28 - INFO - codeparrot_training - Step 39559: {'lr': 5.6136395108139585e-05, 'samples': 20254720, 'steps': 39559, 'loss/train': 1.8054852485656738} +02/26/2022 04:47:31 - INFO - codeparrot_training - Step 39560: {'lr': 5.612606420694141e-05, 'samples': 20255232, 'steps': 39560, 'loss/train': 1.9222033023834229} +02/26/2022 04:47:37 - INFO - codeparrot_training - Step 39561: {'lr': 5.6115734136237554e-05, 'samples': 20255744, 'steps': 39561, 'loss/train': 2.471508026123047} +02/26/2022 04:47:40 - INFO - codeparrot_training - Step 39562: {'lr': 5.610540489607241e-05, 'samples': 20256256, 'steps': 39562, 'loss/train': 0.47053101658821106} +02/26/2022 04:47:45 - INFO - codeparrot_training - Step 39563: {'lr': 5.609507648649012e-05, 'samples': 20256768, 'steps': 39563, 'loss/train': 2.0279135704040527} +02/26/2022 04:47:49 - INFO - codeparrot_training - Step 39564: {'lr': 5.608474890753495e-05, 'samples': 20257280, 'steps': 39564, 'loss/train': 3.046379566192627} +02/26/2022 04:47:55 - INFO - codeparrot_training - Step 39565: {'lr': 5.60744221592511e-05, 'samples': 20257792, 'steps': 39565, 'loss/train': 1.2683528661727905} +02/26/2022 04:47:58 - INFO - codeparrot_training - Step 39566: {'lr': 5.606409624168291e-05, 'samples': 20258304, 'steps': 39566, 'loss/train': 1.5101704597473145} +02/26/2022 04:48:04 - INFO - codeparrot_training - Step 39567: {'lr': 5.6053771154874536e-05, 'samples': 20258816, 'steps': 39567, 'loss/train': 1.7682124376296997} +02/26/2022 04:48:07 - INFO - codeparrot_training - Step 39568: {'lr': 5.60434468988702e-05, 'samples': 20259328, 'steps': 39568, 'loss/train': 1.6780132055282593} +02/26/2022 04:48:14 - INFO - codeparrot_training - Step 39569: {'lr': 5.6033123473714174e-05, 'samples': 20259840, 'steps': 39569, 'loss/train': 1.5915560722351074} +02/26/2022 04:48:17 - INFO - codeparrot_training - Step 39570: {'lr': 5.602280087945058e-05, 'samples': 20260352, 'steps': 39570, 'loss/train': 1.4811367988586426} +02/26/2022 04:48:23 - INFO - codeparrot_training - Step 39571: {'lr': 5.601247911612381e-05, 'samples': 20260864, 'steps': 39571, 'loss/train': 2.1106085777282715} +02/26/2022 04:48:26 - INFO - codeparrot_training - Step 39572: {'lr': 5.6002158183777936e-05, 'samples': 20261376, 'steps': 39572, 'loss/train': 2.3033339977264404} +02/26/2022 04:48:32 - INFO - codeparrot_training - Step 39573: {'lr': 5.5991838082457253e-05, 'samples': 20261888, 'steps': 39573, 'loss/train': 0.6138990521430969} +02/26/2022 04:48:35 - INFO - codeparrot_training - Step 39574: {'lr': 5.598151881220584e-05, 'samples': 20262400, 'steps': 39574, 'loss/train': 1.1860277652740479} +02/26/2022 04:48:41 - INFO - codeparrot_training - Step 39575: {'lr': 5.5971200373068076e-05, 'samples': 20262912, 'steps': 39575, 'loss/train': 1.53574800491333} +02/26/2022 04:48:44 - INFO - codeparrot_training - Step 39576: {'lr': 5.5960882765087984e-05, 'samples': 20263424, 'steps': 39576, 'loss/train': 1.9003180265426636} +02/26/2022 04:48:50 - INFO - codeparrot_training - Step 39577: {'lr': 5.595056598831002e-05, 'samples': 20263936, 'steps': 39577, 'loss/train': 0.5860280990600586} +02/26/2022 04:48:53 - INFO - codeparrot_training - Step 39578: {'lr': 5.594025004277806e-05, 'samples': 20264448, 'steps': 39578, 'loss/train': 2.6915645599365234} +02/26/2022 04:48:59 - INFO - codeparrot_training - Step 39579: {'lr': 5.592993492853654e-05, 'samples': 20264960, 'steps': 39579, 'loss/train': 2.1316583156585693} +02/26/2022 04:49:03 - INFO - codeparrot_training - Step 39580: {'lr': 5.5919620645629445e-05, 'samples': 20265472, 'steps': 39580, 'loss/train': 5.451935768127441} +02/26/2022 04:49:09 - INFO - codeparrot_training - Step 39581: {'lr': 5.5909307194101255e-05, 'samples': 20265984, 'steps': 39581, 'loss/train': 1.6974302530288696} +02/26/2022 04:49:13 - INFO - codeparrot_training - Step 39582: {'lr': 5.589899457399578e-05, 'samples': 20266496, 'steps': 39582, 'loss/train': 3.507108449935913} +02/26/2022 04:49:18 - INFO - codeparrot_training - Step 39583: {'lr': 5.588868278535747e-05, 'samples': 20267008, 'steps': 39583, 'loss/train': 1.8848713636398315} +02/26/2022 04:49:22 - INFO - codeparrot_training - Step 39584: {'lr': 5.587837182823033e-05, 'samples': 20267520, 'steps': 39584, 'loss/train': 1.5594751834869385} +02/26/2022 04:49:27 - INFO - codeparrot_training - Step 39585: {'lr': 5.5868061702658676e-05, 'samples': 20268032, 'steps': 39585, 'loss/train': 2.2697362899780273} +02/26/2022 04:49:31 - INFO - codeparrot_training - Step 39586: {'lr': 5.5857752408686595e-05, 'samples': 20268544, 'steps': 39586, 'loss/train': 1.8169310092926025} +02/26/2022 04:49:36 - INFO - codeparrot_training - Step 39587: {'lr': 5.584744394635827e-05, 'samples': 20269056, 'steps': 39587, 'loss/train': 0.729655921459198} +02/26/2022 04:49:40 - INFO - codeparrot_training - Step 39588: {'lr': 5.583713631571777e-05, 'samples': 20269568, 'steps': 39588, 'loss/train': 1.6893389225006104} +02/26/2022 04:49:45 - INFO - codeparrot_training - Step 39589: {'lr': 5.58268295168094e-05, 'samples': 20270080, 'steps': 39589, 'loss/train': 1.3779979944229126} +02/26/2022 04:49:49 - INFO - codeparrot_training - Step 39590: {'lr': 5.5816523549677226e-05, 'samples': 20270592, 'steps': 39590, 'loss/train': 1.834897518157959} +02/26/2022 04:49:55 - INFO - codeparrot_training - Step 39591: {'lr': 5.58062184143654e-05, 'samples': 20271104, 'steps': 39591, 'loss/train': 1.8546406030654907} +02/26/2022 04:49:59 - INFO - codeparrot_training - Step 39592: {'lr': 5.5795914110918e-05, 'samples': 20271616, 'steps': 39592, 'loss/train': 1.0686100721359253} +02/26/2022 04:50:04 - INFO - codeparrot_training - Step 39593: {'lr': 5.5785610639379314e-05, 'samples': 20272128, 'steps': 39593, 'loss/train': 2.0364582538604736} +02/26/2022 04:50:08 - INFO - codeparrot_training - Step 39594: {'lr': 5.5775307999793415e-05, 'samples': 20272640, 'steps': 39594, 'loss/train': 2.130596399307251} +02/26/2022 04:50:13 - INFO - codeparrot_training - Step 39595: {'lr': 5.5765006192204395e-05, 'samples': 20273152, 'steps': 39595, 'loss/train': 0.9701781272888184} +02/26/2022 04:50:17 - INFO - codeparrot_training - Step 39596: {'lr': 5.5754705216656375e-05, 'samples': 20273664, 'steps': 39596, 'loss/train': 1.6545461416244507} +02/26/2022 04:50:22 - INFO - codeparrot_training - Step 39597: {'lr': 5.574440507319356e-05, 'samples': 20274176, 'steps': 39597, 'loss/train': 1.3062081336975098} +02/26/2022 04:50:26 - INFO - codeparrot_training - Step 39598: {'lr': 5.573410576185997e-05, 'samples': 20274688, 'steps': 39598, 'loss/train': 2.392810106277466} +02/26/2022 04:50:31 - INFO - codeparrot_training - Step 39599: {'lr': 5.572380728269993e-05, 'samples': 20275200, 'steps': 39599, 'loss/train': 7.505510330200195} +02/26/2022 04:50:35 - INFO - codeparrot_training - Step 39600: {'lr': 5.5713509635757274e-05, 'samples': 20275712, 'steps': 39600, 'loss/train': 2.972777843475342} +02/26/2022 04:50:41 - INFO - codeparrot_training - Step 39601: {'lr': 5.570321282107632e-05, 'samples': 20276224, 'steps': 39601, 'loss/train': 2.9780702590942383} +02/26/2022 04:50:45 - INFO - codeparrot_training - Step 39602: {'lr': 5.569291683870109e-05, 'samples': 20276736, 'steps': 39602, 'loss/train': 2.163320541381836} +02/26/2022 04:50:50 - INFO - codeparrot_training - Step 39603: {'lr': 5.568262168867572e-05, 'samples': 20277248, 'steps': 39603, 'loss/train': 2.3610901832580566} +02/26/2022 04:50:54 - INFO - codeparrot_training - Step 39604: {'lr': 5.567232737104422e-05, 'samples': 20277760, 'steps': 39604, 'loss/train': 1.554967999458313} +02/26/2022 04:50:59 - INFO - codeparrot_training - Step 39605: {'lr': 5.566203388585081e-05, 'samples': 20278272, 'steps': 39605, 'loss/train': 1.5985158681869507} +02/26/2022 04:51:03 - INFO - codeparrot_training - Step 39606: {'lr': 5.565174123313957e-05, 'samples': 20278784, 'steps': 39606, 'loss/train': 2.751771926879883} +02/26/2022 04:51:08 - INFO - codeparrot_training - Step 39607: {'lr': 5.564144941295454e-05, 'samples': 20279296, 'steps': 39607, 'loss/train': 1.0058128833770752} +02/26/2022 04:51:12 - INFO - codeparrot_training - Step 39608: {'lr': 5.563115842533978e-05, 'samples': 20279808, 'steps': 39608, 'loss/train': 2.8748834133148193} +02/26/2022 04:51:17 - INFO - codeparrot_training - Step 39609: {'lr': 5.562086827033946e-05, 'samples': 20280320, 'steps': 39609, 'loss/train': 1.484361171722412} +02/26/2022 04:51:21 - INFO - codeparrot_training - Step 39610: {'lr': 5.561057894799762e-05, 'samples': 20280832, 'steps': 39610, 'loss/train': 1.8666799068450928} +02/26/2022 04:51:26 - INFO - codeparrot_training - Step 39611: {'lr': 5.5600290458358296e-05, 'samples': 20281344, 'steps': 39611, 'loss/train': 1.147526741027832} +02/26/2022 04:51:30 - INFO - codeparrot_training - Step 39612: {'lr': 5.5590002801465645e-05, 'samples': 20281856, 'steps': 39612, 'loss/train': 0.5306660532951355} +02/26/2022 04:51:35 - INFO - codeparrot_training - Step 39613: {'lr': 5.557971597736369e-05, 'samples': 20282368, 'steps': 39613, 'loss/train': 2.113041400909424} +02/26/2022 04:51:38 - INFO - codeparrot_training - Step 39614: {'lr': 5.556942998609649e-05, 'samples': 20282880, 'steps': 39614, 'loss/train': 1.471741795539856} +02/26/2022 04:51:44 - INFO - codeparrot_training - Step 39615: {'lr': 5.555914482770805e-05, 'samples': 20283392, 'steps': 39615, 'loss/train': 1.3288798332214355} +02/26/2022 04:51:47 - INFO - codeparrot_training - Step 39616: {'lr': 5.554886050224256e-05, 'samples': 20283904, 'steps': 39616, 'loss/train': 0.5740442872047424} +02/26/2022 04:51:55 - INFO - codeparrot_training - Step 39617: {'lr': 5.553857700974402e-05, 'samples': 20284416, 'steps': 39617, 'loss/train': 0.944951593875885} +02/26/2022 04:51:58 - INFO - codeparrot_training - Step 39618: {'lr': 5.5528294350256443e-05, 'samples': 20284928, 'steps': 39618, 'loss/train': 2.2058258056640625} +02/26/2022 04:52:04 - INFO - codeparrot_training - Step 39619: {'lr': 5.551801252382385e-05, 'samples': 20285440, 'steps': 39619, 'loss/train': 1.2330358028411865} +02/26/2022 04:52:07 - INFO - codeparrot_training - Step 39620: {'lr': 5.550773153049046e-05, 'samples': 20285952, 'steps': 39620, 'loss/train': 0.3771727681159973} +02/26/2022 04:52:13 - INFO - codeparrot_training - Step 39621: {'lr': 5.549745137030007e-05, 'samples': 20286464, 'steps': 39621, 'loss/train': 1.0573660135269165} +02/26/2022 04:52:16 - INFO - codeparrot_training - Step 39622: {'lr': 5.54871720432969e-05, 'samples': 20286976, 'steps': 39622, 'loss/train': 1.3388012647628784} +02/26/2022 04:52:22 - INFO - codeparrot_training - Step 39623: {'lr': 5.547689354952484e-05, 'samples': 20287488, 'steps': 39623, 'loss/train': 0.615705668926239} +02/26/2022 04:52:25 - INFO - codeparrot_training - Step 39624: {'lr': 5.546661588902807e-05, 'samples': 20288000, 'steps': 39624, 'loss/train': 0.7831544280052185} +02/26/2022 04:52:31 - INFO - codeparrot_training - Step 39625: {'lr': 5.5456339061850576e-05, 'samples': 20288512, 'steps': 39625, 'loss/train': 1.7920844554901123} +02/26/2022 04:52:34 - INFO - codeparrot_training - Step 39626: {'lr': 5.544606306803632e-05, 'samples': 20289024, 'steps': 39626, 'loss/train': 2.372608184814453} +02/26/2022 04:52:41 - INFO - codeparrot_training - Step 39627: {'lr': 5.543578790762929e-05, 'samples': 20289536, 'steps': 39627, 'loss/train': 0.5385619401931763} +02/26/2022 04:52:45 - INFO - codeparrot_training - Step 39628: {'lr': 5.5425513580673634e-05, 'samples': 20290048, 'steps': 39628, 'loss/train': 2.880880832672119} +02/26/2022 04:52:50 - INFO - codeparrot_training - Step 39629: {'lr': 5.54152400872133e-05, 'samples': 20290560, 'steps': 39629, 'loss/train': 2.581942319869995} +02/26/2022 04:52:56 - INFO - codeparrot_training - Step 39630: {'lr': 5.540496742729229e-05, 'samples': 20291072, 'steps': 39630, 'loss/train': 1.8050655126571655} +02/26/2022 04:52:59 - INFO - codeparrot_training - Step 39631: {'lr': 5.53946956009545e-05, 'samples': 20291584, 'steps': 39631, 'loss/train': 1.3622560501098633} +02/26/2022 04:53:05 - INFO - codeparrot_training - Step 39632: {'lr': 5.5384424608244165e-05, 'samples': 20292096, 'steps': 39632, 'loss/train': 1.0495922565460205} +02/26/2022 04:53:08 - INFO - codeparrot_training - Step 39633: {'lr': 5.537415444920513e-05, 'samples': 20292608, 'steps': 39633, 'loss/train': 1.2890435457229614} +02/26/2022 04:53:14 - INFO - codeparrot_training - Step 39634: {'lr': 5.536388512388141e-05, 'samples': 20293120, 'steps': 39634, 'loss/train': 1.8021255731582642} +02/26/2022 04:53:17 - INFO - codeparrot_training - Step 39635: {'lr': 5.535361663231694e-05, 'samples': 20293632, 'steps': 39635, 'loss/train': 2.2562716007232666} +02/26/2022 04:53:21 - INFO - codeparrot_training - Step 39636: {'lr': 5.534334897455584e-05, 'samples': 20294144, 'steps': 39636, 'loss/train': 1.6376821994781494} +02/26/2022 04:53:27 - INFO - codeparrot_training - Step 39637: {'lr': 5.5333082150641975e-05, 'samples': 20294656, 'steps': 39637, 'loss/train': 1.8238276243209839} +02/26/2022 04:53:33 - INFO - codeparrot_training - Step 39638: {'lr': 5.5322816160619485e-05, 'samples': 20295168, 'steps': 39638, 'loss/train': 0.7472890615463257} +02/26/2022 04:53:37 - INFO - codeparrot_training - Step 39639: {'lr': 5.5312551004532116e-05, 'samples': 20295680, 'steps': 39639, 'loss/train': 1.3971142768859863} +02/26/2022 04:53:42 - INFO - codeparrot_training - Step 39640: {'lr': 5.5302286682424016e-05, 'samples': 20296192, 'steps': 39640, 'loss/train': 3.2534430027008057} +02/26/2022 04:53:45 - INFO - codeparrot_training - Step 39641: {'lr': 5.529202319433901e-05, 'samples': 20296704, 'steps': 39641, 'loss/train': 0.8869723677635193} +02/26/2022 04:53:51 - INFO - codeparrot_training - Step 39642: {'lr': 5.52817605403213e-05, 'samples': 20297216, 'steps': 39642, 'loss/train': 1.8182017803192139} +02/26/2022 04:53:55 - INFO - codeparrot_training - Step 39643: {'lr': 5.527149872041456e-05, 'samples': 20297728, 'steps': 39643, 'loss/train': 1.95842707157135} +02/26/2022 04:54:00 - INFO - codeparrot_training - Step 39644: {'lr': 5.526123773466296e-05, 'samples': 20298240, 'steps': 39644, 'loss/train': 2.507134437561035} +02/26/2022 04:54:04 - INFO - codeparrot_training - Step 39645: {'lr': 5.5250977583110316e-05, 'samples': 20298752, 'steps': 39645, 'loss/train': 0.7056419253349304} +02/26/2022 04:54:10 - INFO - codeparrot_training - Step 39646: {'lr': 5.524071826580071e-05, 'samples': 20299264, 'steps': 39646, 'loss/train': 1.2730189561843872} +02/26/2022 04:54:14 - INFO - codeparrot_training - Step 39647: {'lr': 5.523045978277802e-05, 'samples': 20299776, 'steps': 39647, 'loss/train': 1.396292805671692} +02/26/2022 04:54:19 - INFO - codeparrot_training - Step 39648: {'lr': 5.5220202134086185e-05, 'samples': 20300288, 'steps': 39648, 'loss/train': 2.679823637008667} +02/26/2022 04:54:23 - INFO - codeparrot_training - Step 39649: {'lr': 5.5209945319769166e-05, 'samples': 20300800, 'steps': 39649, 'loss/train': 0.8680575489997864} +02/26/2022 04:54:29 - INFO - codeparrot_training - Step 39650: {'lr': 5.519968933987082e-05, 'samples': 20301312, 'steps': 39650, 'loss/train': 1.508697509765625} +02/26/2022 04:54:32 - INFO - codeparrot_training - Step 39651: {'lr': 5.5189434194435204e-05, 'samples': 20301824, 'steps': 39651, 'loss/train': 1.804937720298767} +02/26/2022 04:54:36 - INFO - codeparrot_training - Step 39652: {'lr': 5.517917988350621e-05, 'samples': 20302336, 'steps': 39652, 'loss/train': 2.26228666305542} +02/26/2022 04:54:41 - INFO - codeparrot_training - Step 39653: {'lr': 5.516892640712776e-05, 'samples': 20302848, 'steps': 39653, 'loss/train': 1.994885802268982} +02/26/2022 04:54:45 - INFO - codeparrot_training - Step 39654: {'lr': 5.515867376534367e-05, 'samples': 20303360, 'steps': 39654, 'loss/train': 1.053203821182251} +02/26/2022 04:54:50 - INFO - codeparrot_training - Step 39655: {'lr': 5.5148421958198025e-05, 'samples': 20303872, 'steps': 39655, 'loss/train': 0.5563961863517761} +02/26/2022 04:54:54 - INFO - codeparrot_training - Step 39656: {'lr': 5.513817098573465e-05, 'samples': 20304384, 'steps': 39656, 'loss/train': 1.6732758283615112} +02/26/2022 04:54:59 - INFO - codeparrot_training - Step 39657: {'lr': 5.512792084799751e-05, 'samples': 20304896, 'steps': 39657, 'loss/train': 1.5255635976791382} +02/26/2022 04:55:05 - INFO - codeparrot_training - Step 39658: {'lr': 5.511767154503039e-05, 'samples': 20305408, 'steps': 39658, 'loss/train': 1.8469328880310059} +02/26/2022 04:55:08 - INFO - codeparrot_training - Step 39659: {'lr': 5.510742307687736e-05, 'samples': 20305920, 'steps': 39659, 'loss/train': 1.7309544086456299} +02/26/2022 04:55:14 - INFO - codeparrot_training - Step 39660: {'lr': 5.509717544358223e-05, 'samples': 20306432, 'steps': 39660, 'loss/train': 2.007723808288574} +02/26/2022 04:55:17 - INFO - codeparrot_training - Step 39661: {'lr': 5.508692864518891e-05, 'samples': 20306944, 'steps': 39661, 'loss/train': 1.743770718574524} +02/26/2022 04:55:21 - INFO - codeparrot_training - Step 39662: {'lr': 5.507668268174126e-05, 'samples': 20307456, 'steps': 39662, 'loss/train': 2.5784928798675537} +02/26/2022 04:55:28 - INFO - codeparrot_training - Step 39663: {'lr': 5.506643755328325e-05, 'samples': 20307968, 'steps': 39663, 'loss/train': 0.10176370292901993} +02/26/2022 04:55:33 - INFO - codeparrot_training - Step 39664: {'lr': 5.505619325985872e-05, 'samples': 20308480, 'steps': 39664, 'loss/train': 1.9804339408874512} +02/26/2022 04:55:37 - INFO - codeparrot_training - Step 39665: {'lr': 5.504594980151156e-05, 'samples': 20308992, 'steps': 39665, 'loss/train': 1.0873655080795288} +02/26/2022 04:55:40 - INFO - codeparrot_training - Step 39666: {'lr': 5.50357071782856e-05, 'samples': 20309504, 'steps': 39666, 'loss/train': 1.1225903034210205} +02/26/2022 04:55:46 - INFO - codeparrot_training - Step 39667: {'lr': 5.5025465390224794e-05, 'samples': 20310016, 'steps': 39667, 'loss/train': 1.82794189453125} +02/26/2022 04:55:49 - INFO - codeparrot_training - Step 39668: {'lr': 5.5015224437373005e-05, 'samples': 20310528, 'steps': 39668, 'loss/train': 4.054574966430664} +02/26/2022 04:55:55 - INFO - codeparrot_training - Step 39669: {'lr': 5.5004984319774076e-05, 'samples': 20311040, 'steps': 39669, 'loss/train': 1.000671625137329} +02/26/2022 04:55:58 - INFO - codeparrot_training - Step 39670: {'lr': 5.4994745037471816e-05, 'samples': 20311552, 'steps': 39670, 'loss/train': 1.4288913011550903} +02/26/2022 04:56:04 - INFO - codeparrot_training - Step 39671: {'lr': 5.498450659051018e-05, 'samples': 20312064, 'steps': 39671, 'loss/train': 1.8031368255615234} +02/26/2022 04:56:07 - INFO - codeparrot_training - Step 39672: {'lr': 5.497426897893296e-05, 'samples': 20312576, 'steps': 39672, 'loss/train': 2.184058904647827} +02/26/2022 04:56:14 - INFO - codeparrot_training - Step 39673: {'lr': 5.496403220278418e-05, 'samples': 20313088, 'steps': 39673, 'loss/train': 2.5792062282562256} +02/26/2022 04:56:20 - INFO - codeparrot_training - Step 39674: {'lr': 5.495379626210742e-05, 'samples': 20313600, 'steps': 39674, 'loss/train': 1.1711337566375732} +02/26/2022 04:56:23 - INFO - codeparrot_training - Step 39675: {'lr': 5.494356115694671e-05, 'samples': 20314112, 'steps': 39675, 'loss/train': 1.5987637042999268} +02/26/2022 04:56:29 - INFO - codeparrot_training - Step 39676: {'lr': 5.493332688734579e-05, 'samples': 20314624, 'steps': 39676, 'loss/train': 0.1176011860370636} +02/26/2022 04:56:33 - INFO - codeparrot_training - Step 39677: {'lr': 5.49230934533487e-05, 'samples': 20315136, 'steps': 39677, 'loss/train': 1.889054298400879} +02/26/2022 04:56:38 - INFO - codeparrot_training - Step 39678: {'lr': 5.4912860854999e-05, 'samples': 20315648, 'steps': 39678, 'loss/train': 2.9106810092926025} +02/26/2022 04:56:42 - INFO - codeparrot_training - Step 39679: {'lr': 5.49026290923407e-05, 'samples': 20316160, 'steps': 39679, 'loss/train': 2.006866216659546} +02/26/2022 04:56:47 - INFO - codeparrot_training - Step 39680: {'lr': 5.489239816541755e-05, 'samples': 20316672, 'steps': 39680, 'loss/train': 1.660393238067627} +02/26/2022 04:56:51 - INFO - codeparrot_training - Step 39681: {'lr': 5.4882168074273514e-05, 'samples': 20317184, 'steps': 39681, 'loss/train': 1.5633084774017334} +02/26/2022 04:56:54 - INFO - codeparrot_training - Step 39682: {'lr': 5.4871938818952195e-05, 'samples': 20317696, 'steps': 39682, 'loss/train': 1.2776139974594116} +02/26/2022 04:57:01 - INFO - codeparrot_training - Step 39683: {'lr': 5.486171039949761e-05, 'samples': 20318208, 'steps': 39683, 'loss/train': 2.2751355171203613} +02/26/2022 04:57:04 - INFO - codeparrot_training - Step 39684: {'lr': 5.4851482815953424e-05, 'samples': 20318720, 'steps': 39684, 'loss/train': 1.9149181842803955} +02/26/2022 04:57:10 - INFO - codeparrot_training - Step 39685: {'lr': 5.484125606836357e-05, 'samples': 20319232, 'steps': 39685, 'loss/train': 1.3627824783325195} +02/26/2022 04:57:13 - INFO - codeparrot_training - Step 39686: {'lr': 5.483103015677182e-05, 'samples': 20319744, 'steps': 39686, 'loss/train': 0.23077812790870667} +02/26/2022 04:57:19 - INFO - codeparrot_training - Step 39687: {'lr': 5.4820805081221944e-05, 'samples': 20320256, 'steps': 39687, 'loss/train': 2.1500403881073} +02/26/2022 04:57:24 - INFO - codeparrot_training - Step 39688: {'lr': 5.481058084175772e-05, 'samples': 20320768, 'steps': 39688, 'loss/train': 1.5449376106262207} +02/26/2022 04:57:28 - INFO - codeparrot_training - Step 39689: {'lr': 5.480035743842304e-05, 'samples': 20321280, 'steps': 39689, 'loss/train': 1.32004714012146} +02/26/2022 04:57:33 - INFO - codeparrot_training - Step 39690: {'lr': 5.4790134871261636e-05, 'samples': 20321792, 'steps': 39690, 'loss/train': 1.6051506996154785} +02/26/2022 04:57:37 - INFO - codeparrot_training - Step 39691: {'lr': 5.4779913140317326e-05, 'samples': 20322304, 'steps': 39691, 'loss/train': 0.8411818742752075} +02/26/2022 04:57:43 - INFO - codeparrot_training - Step 39692: {'lr': 5.476969224563383e-05, 'samples': 20322816, 'steps': 39692, 'loss/train': 1.7682324647903442} +02/26/2022 04:57:47 - INFO - codeparrot_training - Step 39693: {'lr': 5.4759472187255024e-05, 'samples': 20323328, 'steps': 39693, 'loss/train': 0.4707164466381073} +02/26/2022 04:57:52 - INFO - codeparrot_training - Step 39694: {'lr': 5.474925296522462e-05, 'samples': 20323840, 'steps': 39694, 'loss/train': 2.2049062252044678} +02/26/2022 04:57:56 - INFO - codeparrot_training - Step 39695: {'lr': 5.473903457958645e-05, 'samples': 20324352, 'steps': 39695, 'loss/train': 0.8677700161933899} +02/26/2022 04:58:01 - INFO - codeparrot_training - Step 39696: {'lr': 5.472881703038418e-05, 'samples': 20324864, 'steps': 39696, 'loss/train': 1.4744956493377686} +02/26/2022 04:58:05 - INFO - codeparrot_training - Step 39697: {'lr': 5.471860031766171e-05, 'samples': 20325376, 'steps': 39697, 'loss/train': 1.0862455368041992} +02/26/2022 04:58:08 - INFO - codeparrot_training - Step 39698: {'lr': 5.470838444146275e-05, 'samples': 20325888, 'steps': 39698, 'loss/train': 0.1650933474302292} +02/26/2022 04:58:14 - INFO - codeparrot_training - Step 39699: {'lr': 5.469816940183109e-05, 'samples': 20326400, 'steps': 39699, 'loss/train': 1.0252324342727661} +02/26/2022 04:58:19 - INFO - codeparrot_training - Step 39700: {'lr': 5.468795519881042e-05, 'samples': 20326912, 'steps': 39700, 'loss/train': 2.9577829837799072} +02/26/2022 04:58:23 - INFO - codeparrot_training - Step 39701: {'lr': 5.467774183244448e-05, 'samples': 20327424, 'steps': 39701, 'loss/train': 0.9262147545814514} +02/26/2022 04:58:30 - INFO - codeparrot_training - Step 39702: {'lr': 5.466752930277713e-05, 'samples': 20327936, 'steps': 39702, 'loss/train': 1.2280688285827637} +02/26/2022 04:58:34 - INFO - codeparrot_training - Step 39703: {'lr': 5.465731760985207e-05, 'samples': 20328448, 'steps': 39703, 'loss/train': 1.3474022150039673} +02/26/2022 04:58:39 - INFO - codeparrot_training - Step 39704: {'lr': 5.4647106753713014e-05, 'samples': 20328960, 'steps': 39704, 'loss/train': 0.9308189153671265} +02/26/2022 04:58:43 - INFO - codeparrot_training - Step 39705: {'lr': 5.463689673440367e-05, 'samples': 20329472, 'steps': 39705, 'loss/train': 1.720345139503479} +02/26/2022 04:58:48 - INFO - codeparrot_training - Step 39706: {'lr': 5.4626687551967896e-05, 'samples': 20329984, 'steps': 39706, 'loss/train': 1.885561227798462} +02/26/2022 04:58:52 - INFO - codeparrot_training - Step 39707: {'lr': 5.461647920644927e-05, 'samples': 20330496, 'steps': 39707, 'loss/train': 2.401057481765747} +02/26/2022 04:58:57 - INFO - codeparrot_training - Step 39708: {'lr': 5.4606271697891757e-05, 'samples': 20331008, 'steps': 39708, 'loss/train': 0.7946843504905701} +02/26/2022 04:59:01 - INFO - codeparrot_training - Step 39709: {'lr': 5.459606502633879e-05, 'samples': 20331520, 'steps': 39709, 'loss/train': 1.0909266471862793} +02/26/2022 04:59:06 - INFO - codeparrot_training - Step 39710: {'lr': 5.4585859191834284e-05, 'samples': 20332032, 'steps': 39710, 'loss/train': 0.4135775864124298} +02/26/2022 04:59:10 - INFO - codeparrot_training - Step 39711: {'lr': 5.457565419442187e-05, 'samples': 20332544, 'steps': 39711, 'loss/train': 2.2503304481506348} +02/26/2022 04:59:15 - INFO - codeparrot_training - Step 39712: {'lr': 5.4565450034145424e-05, 'samples': 20333056, 'steps': 39712, 'loss/train': 0.9864827990531921} +02/26/2022 04:59:18 - INFO - codeparrot_training - Step 39713: {'lr': 5.455524671104839e-05, 'samples': 20333568, 'steps': 39713, 'loss/train': 0.39865031838417053} +02/26/2022 04:59:26 - INFO - codeparrot_training - Step 39714: {'lr': 5.454504422517467e-05, 'samples': 20334080, 'steps': 39714, 'loss/train': 2.3310444355010986} +02/26/2022 04:59:29 - INFO - codeparrot_training - Step 39715: {'lr': 5.453484257656788e-05, 'samples': 20334592, 'steps': 39715, 'loss/train': 1.0801059007644653} +02/26/2022 04:59:35 - INFO - codeparrot_training - Step 39716: {'lr': 5.452464176527189e-05, 'samples': 20335104, 'steps': 39716, 'loss/train': 1.2765918970108032} +02/26/2022 04:59:38 - INFO - codeparrot_training - Step 39717: {'lr': 5.451444179133011e-05, 'samples': 20335616, 'steps': 39717, 'loss/train': 2.189959764480591} +02/26/2022 04:59:44 - INFO - codeparrot_training - Step 39718: {'lr': 5.4504242654786454e-05, 'samples': 20336128, 'steps': 39718, 'loss/train': 0.14243502914905548} +02/26/2022 04:59:47 - INFO - codeparrot_training - Step 39719: {'lr': 5.44940443556845e-05, 'samples': 20336640, 'steps': 39719, 'loss/train': 1.277060627937317} +02/26/2022 04:59:53 - INFO - codeparrot_training - Step 39720: {'lr': 5.4483846894068044e-05, 'samples': 20337152, 'steps': 39720, 'loss/train': 0.9580551385879517} +02/26/2022 04:59:56 - INFO - codeparrot_training - Step 39721: {'lr': 5.447365026998069e-05, 'samples': 20337664, 'steps': 39721, 'loss/train': 2.065368413925171} +02/26/2022 05:00:02 - INFO - codeparrot_training - Step 39722: {'lr': 5.4463454483466124e-05, 'samples': 20338176, 'steps': 39722, 'loss/train': 1.8422590494155884} +02/26/2022 05:00:05 - INFO - codeparrot_training - Step 39723: {'lr': 5.445325953456798e-05, 'samples': 20338688, 'steps': 39723, 'loss/train': 1.1569839715957642} +02/26/2022 05:00:13 - INFO - codeparrot_training - Step 39724: {'lr': 5.444306542333005e-05, 'samples': 20339200, 'steps': 39724, 'loss/train': 2.0523934364318848} +02/26/2022 05:00:16 - INFO - codeparrot_training - Step 39725: {'lr': 5.443287214979592e-05, 'samples': 20339712, 'steps': 39725, 'loss/train': 1.6092201471328735} +02/26/2022 05:00:22 - INFO - codeparrot_training - Step 39726: {'lr': 5.442267971400927e-05, 'samples': 20340224, 'steps': 39726, 'loss/train': 2.3666648864746094} +02/26/2022 05:00:25 - INFO - codeparrot_training - Step 39727: {'lr': 5.441248811601368e-05, 'samples': 20340736, 'steps': 39727, 'loss/train': 2.1323652267456055} +02/26/2022 05:00:30 - INFO - codeparrot_training - Step 39728: {'lr': 5.440229735585297e-05, 'samples': 20341248, 'steps': 39728, 'loss/train': 2.1372671127319336} +02/26/2022 05:00:34 - INFO - codeparrot_training - Step 39729: {'lr': 5.4392107433570704e-05, 'samples': 20341760, 'steps': 39729, 'loss/train': 1.4354342222213745} +02/26/2022 05:00:40 - INFO - codeparrot_training - Step 39730: {'lr': 5.4381918349210526e-05, 'samples': 20342272, 'steps': 39730, 'loss/train': 1.911924123764038} +02/26/2022 05:00:43 - INFO - codeparrot_training - Step 39731: {'lr': 5.437173010281604e-05, 'samples': 20342784, 'steps': 39731, 'loss/train': 2.8752458095550537} +02/26/2022 05:00:49 - INFO - codeparrot_training - Step 39732: {'lr': 5.4361542694430996e-05, 'samples': 20343296, 'steps': 39732, 'loss/train': 3.1536624431610107} +02/26/2022 05:00:52 - INFO - codeparrot_training - Step 39733: {'lr': 5.4351356124099e-05, 'samples': 20343808, 'steps': 39733, 'loss/train': 2.3629064559936523} +02/26/2022 05:00:59 - INFO - codeparrot_training - Step 39734: {'lr': 5.434117039186368e-05, 'samples': 20344320, 'steps': 39734, 'loss/train': 0.9162015914916992} +02/26/2022 05:01:03 - INFO - codeparrot_training - Step 39735: {'lr': 5.4330985497768545e-05, 'samples': 20344832, 'steps': 39735, 'loss/train': 1.1805990934371948} +02/26/2022 05:01:08 - INFO - codeparrot_training - Step 39736: {'lr': 5.432080144185744e-05, 'samples': 20345344, 'steps': 39736, 'loss/train': 1.0604205131530762} +02/26/2022 05:01:12 - INFO - codeparrot_training - Step 39737: {'lr': 5.431061822417388e-05, 'samples': 20345856, 'steps': 39737, 'loss/train': 2.219500780105591} +02/26/2022 05:01:17 - INFO - codeparrot_training - Step 39738: {'lr': 5.430043584476149e-05, 'samples': 20346368, 'steps': 39738, 'loss/train': 1.6543880701065063} +02/26/2022 05:01:21 - INFO - codeparrot_training - Step 39739: {'lr': 5.42902543036638e-05, 'samples': 20346880, 'steps': 39739, 'loss/train': 0.33507290482521057} +02/26/2022 05:01:27 - INFO - codeparrot_training - Step 39740: {'lr': 5.4280073600924626e-05, 'samples': 20347392, 'steps': 39740, 'loss/train': 8.76893424987793} +02/26/2022 05:01:30 - INFO - codeparrot_training - Step 39741: {'lr': 5.426989373658744e-05, 'samples': 20347904, 'steps': 39741, 'loss/train': 3.0817201137542725} +02/26/2022 05:01:36 - INFO - codeparrot_training - Step 39742: {'lr': 5.425971471069582e-05, 'samples': 20348416, 'steps': 39742, 'loss/train': 1.2712726593017578} +02/26/2022 05:01:39 - INFO - codeparrot_training - Step 39743: {'lr': 5.424953652329348e-05, 'samples': 20348928, 'steps': 39743, 'loss/train': 2.2463932037353516} +02/26/2022 05:01:46 - INFO - codeparrot_training - Step 39744: {'lr': 5.423935917442399e-05, 'samples': 20349440, 'steps': 39744, 'loss/train': 2.4513189792633057} +02/26/2022 05:01:50 - INFO - codeparrot_training - Step 39745: {'lr': 5.4229182664130904e-05, 'samples': 20349952, 'steps': 39745, 'loss/train': 1.9745986461639404} +02/26/2022 05:01:55 - INFO - codeparrot_training - Step 39746: {'lr': 5.42190069924578e-05, 'samples': 20350464, 'steps': 39746, 'loss/train': 1.25392746925354} +02/26/2022 05:01:59 - INFO - codeparrot_training - Step 39747: {'lr': 5.420883215944841e-05, 'samples': 20350976, 'steps': 39747, 'loss/train': 1.656606912612915} +02/26/2022 05:02:04 - INFO - codeparrot_training - Step 39748: {'lr': 5.419865816514607e-05, 'samples': 20351488, 'steps': 39748, 'loss/train': 2.42645525932312} +02/26/2022 05:02:08 - INFO - codeparrot_training - Step 39749: {'lr': 5.418848500959458e-05, 'samples': 20352000, 'steps': 39749, 'loss/train': 2.0131170749664307} +02/26/2022 05:02:13 - INFO - codeparrot_training - Step 39750: {'lr': 5.4178312692837405e-05, 'samples': 20352512, 'steps': 39750, 'loss/train': 1.3732068538665771} +02/26/2022 05:02:17 - INFO - codeparrot_training - Step 39751: {'lr': 5.416814121491825e-05, 'samples': 20353024, 'steps': 39751, 'loss/train': 1.518707275390625} +02/26/2022 05:02:22 - INFO - codeparrot_training - Step 39752: {'lr': 5.4157970575880486e-05, 'samples': 20353536, 'steps': 39752, 'loss/train': 1.727295160293579} +02/26/2022 05:02:26 - INFO - codeparrot_training - Step 39753: {'lr': 5.414780077576786e-05, 'samples': 20354048, 'steps': 39753, 'loss/train': 1.3572252988815308} +02/26/2022 05:02:31 - INFO - codeparrot_training - Step 39754: {'lr': 5.413763181462378e-05, 'samples': 20354560, 'steps': 39754, 'loss/train': 1.683567762374878} +02/26/2022 05:02:35 - INFO - codeparrot_training - Step 39755: {'lr': 5.412746369249197e-05, 'samples': 20355072, 'steps': 39755, 'loss/train': 1.8298965692520142} +02/26/2022 05:02:40 - INFO - codeparrot_training - Step 39756: {'lr': 5.41172964094159e-05, 'samples': 20355584, 'steps': 39756, 'loss/train': 1.5596152544021606} +02/26/2022 05:02:44 - INFO - codeparrot_training - Step 39757: {'lr': 5.410712996543915e-05, 'samples': 20356096, 'steps': 39757, 'loss/train': 2.074249505996704} +02/26/2022 05:02:49 - INFO - codeparrot_training - Step 39758: {'lr': 5.409696436060516e-05, 'samples': 20356608, 'steps': 39758, 'loss/train': 1.6563329696655273} +02/26/2022 05:02:53 - INFO - codeparrot_training - Step 39759: {'lr': 5.408679959495766e-05, 'samples': 20357120, 'steps': 39759, 'loss/train': 1.7762566804885864} +02/26/2022 05:03:00 - INFO - codeparrot_training - Step 39760: {'lr': 5.407663566854007e-05, 'samples': 20357632, 'steps': 39760, 'loss/train': 1.9043956995010376} +02/26/2022 05:03:03 - INFO - codeparrot_training - Step 39761: {'lr': 5.406647258139599e-05, 'samples': 20358144, 'steps': 39761, 'loss/train': 2.357501983642578} +02/26/2022 05:03:09 - INFO - codeparrot_training - Step 39762: {'lr': 5.405631033356884e-05, 'samples': 20358656, 'steps': 39762, 'loss/train': 0.3489668667316437} +02/26/2022 05:03:12 - INFO - codeparrot_training - Step 39763: {'lr': 5.4046148925102316e-05, 'samples': 20359168, 'steps': 39763, 'loss/train': 1.900965929031372} +02/26/2022 05:03:18 - INFO - codeparrot_training - Step 39764: {'lr': 5.4035988356039874e-05, 'samples': 20359680, 'steps': 39764, 'loss/train': 1.793460488319397} +02/26/2022 05:03:21 - INFO - codeparrot_training - Step 39765: {'lr': 5.402582862642502e-05, 'samples': 20360192, 'steps': 39765, 'loss/train': 1.7831315994262695} +02/26/2022 05:03:27 - INFO - codeparrot_training - Step 39766: {'lr': 5.4015669736301205e-05, 'samples': 20360704, 'steps': 39766, 'loss/train': 0.8137457370758057} +02/26/2022 05:03:30 - INFO - codeparrot_training - Step 39767: {'lr': 5.4005511685712134e-05, 'samples': 20361216, 'steps': 39767, 'loss/train': 1.6040894985198975} +02/26/2022 05:03:36 - INFO - codeparrot_training - Step 39768: {'lr': 5.399535447470111e-05, 'samples': 20361728, 'steps': 39768, 'loss/train': 1.795889973640442} +02/26/2022 05:03:39 - INFO - codeparrot_training - Step 39769: {'lr': 5.3985198103311925e-05, 'samples': 20362240, 'steps': 39769, 'loss/train': 1.8011457920074463} +02/26/2022 05:03:47 - INFO - codeparrot_training - Step 39770: {'lr': 5.397504257158775e-05, 'samples': 20362752, 'steps': 39770, 'loss/train': 2.3464174270629883} +02/26/2022 05:03:50 - INFO - codeparrot_training - Step 39771: {'lr': 5.3964887879572294e-05, 'samples': 20363264, 'steps': 39771, 'loss/train': 0.9428917169570923} +02/26/2022 05:03:55 - INFO - codeparrot_training - Step 39772: {'lr': 5.3954734027308966e-05, 'samples': 20363776, 'steps': 39772, 'loss/train': 2.6956887245178223} +02/26/2022 05:04:01 - INFO - codeparrot_training - Step 39773: {'lr': 5.3944581014841454e-05, 'samples': 20364288, 'steps': 39773, 'loss/train': 2.0494346618652344} +02/26/2022 05:04:04 - INFO - codeparrot_training - Step 39774: {'lr': 5.393442884221294e-05, 'samples': 20364800, 'steps': 39774, 'loss/train': 2.162763833999634} +02/26/2022 05:04:10 - INFO - codeparrot_training - Step 39775: {'lr': 5.3924277509467155e-05, 'samples': 20365312, 'steps': 39775, 'loss/train': 2.193805456161499} +02/26/2022 05:04:13 - INFO - codeparrot_training - Step 39776: {'lr': 5.391412701664744e-05, 'samples': 20365824, 'steps': 39776, 'loss/train': 2.1867339611053467} +02/26/2022 05:04:19 - INFO - codeparrot_training - Step 39777: {'lr': 5.390397736379749e-05, 'samples': 20366336, 'steps': 39777, 'loss/train': 1.8728506565093994} +02/26/2022 05:04:22 - INFO - codeparrot_training - Step 39778: {'lr': 5.389382855096048e-05, 'samples': 20366848, 'steps': 39778, 'loss/train': 0.4670170843601227} +02/26/2022 05:04:28 - INFO - codeparrot_training - Step 39779: {'lr': 5.388368057818011e-05, 'samples': 20367360, 'steps': 39779, 'loss/train': 2.3256709575653076} +02/26/2022 05:04:31 - INFO - codeparrot_training - Step 39780: {'lr': 5.387353344549978e-05, 'samples': 20367872, 'steps': 39780, 'loss/train': 1.5783545970916748} +02/26/2022 05:04:39 - INFO - codeparrot_training - Step 39781: {'lr': 5.3863387152962876e-05, 'samples': 20368384, 'steps': 39781, 'loss/train': 0.5226054787635803} +02/26/2022 05:04:42 - INFO - codeparrot_training - Step 39782: {'lr': 5.385324170061301e-05, 'samples': 20368896, 'steps': 39782, 'loss/train': 2.1844303607940674} +02/26/2022 05:04:48 - INFO - codeparrot_training - Step 39783: {'lr': 5.384309708849358e-05, 'samples': 20369408, 'steps': 39783, 'loss/train': 1.4209096431732178} +02/26/2022 05:04:51 - INFO - codeparrot_training - Step 39784: {'lr': 5.383295331664803e-05, 'samples': 20369920, 'steps': 39784, 'loss/train': 2.0249762535095215} +02/26/2022 05:04:57 - INFO - codeparrot_training - Step 39785: {'lr': 5.382281038511977e-05, 'samples': 20370432, 'steps': 39785, 'loss/train': 1.4781056642532349} +02/26/2022 05:05:00 - INFO - codeparrot_training - Step 39786: {'lr': 5.381266829395234e-05, 'samples': 20370944, 'steps': 39786, 'loss/train': 1.2523202896118164} +02/26/2022 05:05:05 - INFO - codeparrot_training - Step 39787: {'lr': 5.3802527043189166e-05, 'samples': 20371456, 'steps': 39787, 'loss/train': 2.046996593475342} +02/26/2022 05:05:09 - INFO - codeparrot_training - Step 39788: {'lr': 5.379238663287364e-05, 'samples': 20371968, 'steps': 39788, 'loss/train': 1.1402511596679688} +02/26/2022 05:05:14 - INFO - codeparrot_training - Step 39789: {'lr': 5.3782247063049185e-05, 'samples': 20372480, 'steps': 39789, 'loss/train': 2.7387282848358154} +02/26/2022 05:05:18 - INFO - codeparrot_training - Step 39790: {'lr': 5.3772108333759314e-05, 'samples': 20372992, 'steps': 39790, 'loss/train': 1.1888301372528076} +02/26/2022 05:05:25 - INFO - codeparrot_training - Step 39791: {'lr': 5.376197044504744e-05, 'samples': 20373504, 'steps': 39791, 'loss/train': 1.516459584236145} +02/26/2022 05:05:29 - INFO - codeparrot_training - Step 39792: {'lr': 5.375183339695697e-05, 'samples': 20374016, 'steps': 39792, 'loss/train': 2.8965492248535156} +02/26/2022 05:05:34 - INFO - codeparrot_training - Step 39793: {'lr': 5.374169718953126e-05, 'samples': 20374528, 'steps': 39793, 'loss/train': 1.5712018013000488} +02/26/2022 05:05:38 - INFO - codeparrot_training - Step 39794: {'lr': 5.373156182281388e-05, 'samples': 20375040, 'steps': 39794, 'loss/train': 2.4157755374908447} +02/26/2022 05:05:43 - INFO - codeparrot_training - Step 39795: {'lr': 5.372142729684815e-05, 'samples': 20375552, 'steps': 39795, 'loss/train': 1.7076926231384277} +02/26/2022 05:05:47 - INFO - codeparrot_training - Step 39796: {'lr': 5.371129361167751e-05, 'samples': 20376064, 'steps': 39796, 'loss/train': 2.3673014640808105} +02/26/2022 05:05:52 - INFO - codeparrot_training - Step 39797: {'lr': 5.37011607673453e-05, 'samples': 20376576, 'steps': 39797, 'loss/train': 2.1790261268615723} +02/26/2022 05:05:56 - INFO - codeparrot_training - Step 39798: {'lr': 5.369102876389503e-05, 'samples': 20377088, 'steps': 39798, 'loss/train': 2.948676824569702} +02/26/2022 05:06:01 - INFO - codeparrot_training - Step 39799: {'lr': 5.368089760137007e-05, 'samples': 20377600, 'steps': 39799, 'loss/train': 0.550044059753418} +02/26/2022 05:06:05 - INFO - codeparrot_training - Step 39800: {'lr': 5.367076727981382e-05, 'samples': 20378112, 'steps': 39800, 'loss/train': 2.8461899757385254} +02/26/2022 05:06:13 - INFO - codeparrot_training - Step 39801: {'lr': 5.366063779926958e-05, 'samples': 20378624, 'steps': 39801, 'loss/train': 3.3497750759124756} +02/26/2022 05:06:16 - INFO - codeparrot_training - Step 39802: {'lr': 5.3650509159780896e-05, 'samples': 20379136, 'steps': 39802, 'loss/train': 1.2837826013565063} +02/26/2022 05:06:20 - INFO - codeparrot_training - Step 39803: {'lr': 5.3640381361391015e-05, 'samples': 20379648, 'steps': 39803, 'loss/train': 2.0867919921875} +02/26/2022 05:06:25 - INFO - codeparrot_training - Step 39804: {'lr': 5.363025440414352e-05, 'samples': 20380160, 'steps': 39804, 'loss/train': 1.4675344228744507} +02/26/2022 05:06:28 - INFO - codeparrot_training - Step 39805: {'lr': 5.362012828808152e-05, 'samples': 20380672, 'steps': 39805, 'loss/train': 1.41089928150177} +02/26/2022 05:06:34 - INFO - codeparrot_training - Step 39806: {'lr': 5.361000301324859e-05, 'samples': 20381184, 'steps': 39806, 'loss/train': 2.1080501079559326} +02/26/2022 05:06:37 - INFO - codeparrot_training - Step 39807: {'lr': 5.359987857968801e-05, 'samples': 20381696, 'steps': 39807, 'loss/train': 1.9267653226852417} +02/26/2022 05:06:43 - INFO - codeparrot_training - Step 39808: {'lr': 5.358975498744331e-05, 'samples': 20382208, 'steps': 39808, 'loss/train': 2.1931066513061523} +02/26/2022 05:06:46 - INFO - codeparrot_training - Step 39809: {'lr': 5.35796322365576e-05, 'samples': 20382720, 'steps': 39809, 'loss/train': 1.9634737968444824} +02/26/2022 05:06:52 - INFO - codeparrot_training - Step 39810: {'lr': 5.356951032707441e-05, 'samples': 20383232, 'steps': 39810, 'loss/train': 1.4330230951309204} +02/26/2022 05:06:58 - INFO - codeparrot_training - Step 39811: {'lr': 5.3559389259037025e-05, 'samples': 20383744, 'steps': 39811, 'loss/train': 2.0131702423095703} +02/26/2022 05:07:01 - INFO - codeparrot_training - Step 39812: {'lr': 5.3549269032488966e-05, 'samples': 20384256, 'steps': 39812, 'loss/train': 1.5433257818222046} +02/26/2022 05:07:04 - INFO - codeparrot_training - Step 39813: {'lr': 5.353914964747333e-05, 'samples': 20384768, 'steps': 39813, 'loss/train': 1.7816805839538574} +02/26/2022 05:07:10 - INFO - codeparrot_training - Step 39814: {'lr': 5.352903110403368e-05, 'samples': 20385280, 'steps': 39814, 'loss/train': 0.8600420355796814} +02/26/2022 05:07:14 - INFO - codeparrot_training - Step 39815: {'lr': 5.3518913402213184e-05, 'samples': 20385792, 'steps': 39815, 'loss/train': 2.6810121536254883} +02/26/2022 05:07:21 - INFO - codeparrot_training - Step 39816: {'lr': 5.350879654205534e-05, 'samples': 20386304, 'steps': 39816, 'loss/train': 2.2573606967926025} +02/26/2022 05:07:24 - INFO - codeparrot_training - Step 39817: {'lr': 5.3498680523603406e-05, 'samples': 20386816, 'steps': 39817, 'loss/train': 1.8959447145462036} +02/26/2022 05:07:30 - INFO - codeparrot_training - Step 39818: {'lr': 5.348856534690075e-05, 'samples': 20387328, 'steps': 39818, 'loss/train': 1.5887534618377686} +02/26/2022 05:07:36 - INFO - codeparrot_training - Step 39819: {'lr': 5.347845101199061e-05, 'samples': 20387840, 'steps': 39819, 'loss/train': 2.023820400238037} +02/26/2022 05:07:39 - INFO - codeparrot_training - Step 39820: {'lr': 5.3468337518916445e-05, 'samples': 20388352, 'steps': 39820, 'loss/train': 1.3859535455703735} +02/26/2022 05:07:43 - INFO - codeparrot_training - Step 39821: {'lr': 5.345822486772153e-05, 'samples': 20388864, 'steps': 39821, 'loss/train': 0.5249124765396118} +02/26/2022 05:07:48 - INFO - codeparrot_training - Step 39822: {'lr': 5.344811305844915e-05, 'samples': 20389376, 'steps': 39822, 'loss/train': 1.6404755115509033} +02/26/2022 05:07:52 - INFO - codeparrot_training - Step 39823: {'lr': 5.343800209114258e-05, 'samples': 20389888, 'steps': 39823, 'loss/train': 1.5057337284088135} +02/26/2022 05:07:57 - INFO - codeparrot_training - Step 39824: {'lr': 5.342789196584527e-05, 'samples': 20390400, 'steps': 39824, 'loss/train': 0.6853026151657104} +02/26/2022 05:08:01 - INFO - codeparrot_training - Step 39825: {'lr': 5.3417782682600446e-05, 'samples': 20390912, 'steps': 39825, 'loss/train': 1.3691399097442627} +02/26/2022 05:08:06 - INFO - codeparrot_training - Step 39826: {'lr': 5.340767424145143e-05, 'samples': 20391424, 'steps': 39826, 'loss/train': 1.446277141571045} +02/26/2022 05:08:10 - INFO - codeparrot_training - Step 39827: {'lr': 5.3397566642441496e-05, 'samples': 20391936, 'steps': 39827, 'loss/train': 0.6511457562446594} +02/26/2022 05:08:17 - INFO - codeparrot_training - Step 39828: {'lr': 5.3387459885613886e-05, 'samples': 20392448, 'steps': 39828, 'loss/train': 1.8427156209945679} +02/26/2022 05:08:20 - INFO - codeparrot_training - Step 39829: {'lr': 5.337735397101207e-05, 'samples': 20392960, 'steps': 39829, 'loss/train': 1.8660967350006104} +02/26/2022 05:08:26 - INFO - codeparrot_training - Step 39830: {'lr': 5.336724889867919e-05, 'samples': 20393472, 'steps': 39830, 'loss/train': 2.286456823348999} +02/26/2022 05:08:29 - INFO - codeparrot_training - Step 39831: {'lr': 5.3357144668658594e-05, 'samples': 20393984, 'steps': 39831, 'loss/train': 1.088028073310852} +02/26/2022 05:08:35 - INFO - codeparrot_training - Step 39832: {'lr': 5.334704128099349e-05, 'samples': 20394496, 'steps': 39832, 'loss/train': 1.042543649673462} +02/26/2022 05:08:38 - INFO - codeparrot_training - Step 39833: {'lr': 5.333693873572729e-05, 'samples': 20395008, 'steps': 39833, 'loss/train': 1.624452829360962} +02/26/2022 05:08:44 - INFO - codeparrot_training - Step 39834: {'lr': 5.332683703290317e-05, 'samples': 20395520, 'steps': 39834, 'loss/train': 2.2484521865844727} +02/26/2022 05:08:47 - INFO - codeparrot_training - Step 39835: {'lr': 5.3316736172564466e-05, 'samples': 20396032, 'steps': 39835, 'loss/train': 2.118586301803589} +02/26/2022 05:08:53 - INFO - codeparrot_training - Step 39836: {'lr': 5.330663615475431e-05, 'samples': 20396544, 'steps': 39836, 'loss/train': 2.0278921127319336} +02/26/2022 05:08:56 - INFO - codeparrot_training - Step 39837: {'lr': 5.329653697951614e-05, 'samples': 20397056, 'steps': 39837, 'loss/train': 2.142737865447998} +02/26/2022 05:09:04 - INFO - codeparrot_training - Step 39838: {'lr': 5.328643864689317e-05, 'samples': 20397568, 'steps': 39838, 'loss/train': 0.24186043441295624} +02/26/2022 05:09:07 - INFO - codeparrot_training - Step 39839: {'lr': 5.327634115692862e-05, 'samples': 20398080, 'steps': 39839, 'loss/train': 1.9649680852890015} +02/26/2022 05:09:13 - INFO - codeparrot_training - Step 39840: {'lr': 5.326624450966569e-05, 'samples': 20398592, 'steps': 39840, 'loss/train': 1.2368621826171875} +02/26/2022 05:09:16 - INFO - codeparrot_training - Step 39841: {'lr': 5.325614870514775e-05, 'samples': 20399104, 'steps': 39841, 'loss/train': 1.774900197982788} +02/26/2022 05:09:22 - INFO - codeparrot_training - Step 39842: {'lr': 5.3246053743417924e-05, 'samples': 20399616, 'steps': 39842, 'loss/train': 1.5819013118743896} +02/26/2022 05:09:25 - INFO - codeparrot_training - Step 39843: {'lr': 5.323595962451969e-05, 'samples': 20400128, 'steps': 39843, 'loss/train': 1.3393691778182983} +02/26/2022 05:09:31 - INFO - codeparrot_training - Step 39844: {'lr': 5.3225866348495994e-05, 'samples': 20400640, 'steps': 39844, 'loss/train': 1.6038541793823242} +02/26/2022 05:09:34 - INFO - codeparrot_training - Step 39845: {'lr': 5.321577391539026e-05, 'samples': 20401152, 'steps': 39845, 'loss/train': 0.7268335819244385} +02/26/2022 05:09:40 - INFO - codeparrot_training - Step 39846: {'lr': 5.320568232524558e-05, 'samples': 20401664, 'steps': 39846, 'loss/train': 2.3017501831054688} +02/26/2022 05:09:43 - INFO - codeparrot_training - Step 39847: {'lr': 5.319559157810541e-05, 'samples': 20402176, 'steps': 39847, 'loss/train': 1.9190421104431152} +02/26/2022 05:09:49 - INFO - codeparrot_training - Step 39848: {'lr': 5.31855016740127e-05, 'samples': 20402688, 'steps': 39848, 'loss/train': 0.5984655022621155} +02/26/2022 05:09:52 - INFO - codeparrot_training - Step 39849: {'lr': 5.3175412613010895e-05, 'samples': 20403200, 'steps': 39849, 'loss/train': 1.1121525764465332} +02/26/2022 05:09:58 - INFO - codeparrot_training - Step 39850: {'lr': 5.316532439514304e-05, 'samples': 20403712, 'steps': 39850, 'loss/train': 1.1569085121154785} +02/26/2022 05:10:01 - INFO - codeparrot_training - Step 39851: {'lr': 5.3155237020452495e-05, 'samples': 20404224, 'steps': 39851, 'loss/train': 1.4745173454284668} +02/26/2022 05:10:07 - INFO - codeparrot_training - Step 39852: {'lr': 5.3145150488982414e-05, 'samples': 20404736, 'steps': 39852, 'loss/train': 2.1704354286193848} +02/26/2022 05:10:10 - INFO - codeparrot_training - Step 39853: {'lr': 5.3135064800775984e-05, 'samples': 20405248, 'steps': 39853, 'loss/train': 1.8462575674057007} +02/26/2022 05:10:18 - INFO - codeparrot_training - Step 39854: {'lr': 5.3124979955876396e-05, 'samples': 20405760, 'steps': 39854, 'loss/train': 2.3372702598571777} +02/26/2022 05:10:21 - INFO - codeparrot_training - Step 39855: {'lr': 5.311489595432692e-05, 'samples': 20406272, 'steps': 39855, 'loss/train': 0.8868804574012756} +02/26/2022 05:10:27 - INFO - codeparrot_training - Step 39856: {'lr': 5.310481279617071e-05, 'samples': 20406784, 'steps': 39856, 'loss/train': 2.015747308731079} +02/26/2022 05:10:30 - INFO - codeparrot_training - Step 39857: {'lr': 5.309473048145097e-05, 'samples': 20407296, 'steps': 39857, 'loss/train': 1.9868159294128418} +02/26/2022 05:10:36 - INFO - codeparrot_training - Step 39858: {'lr': 5.308464901021079e-05, 'samples': 20407808, 'steps': 39858, 'loss/train': 1.6486444473266602} +02/26/2022 05:10:39 - INFO - codeparrot_training - Step 39859: {'lr': 5.3074568382493524e-05, 'samples': 20408320, 'steps': 39859, 'loss/train': 1.1142995357513428} +02/26/2022 05:10:45 - INFO - codeparrot_training - Step 39860: {'lr': 5.3064488598342285e-05, 'samples': 20408832, 'steps': 39860, 'loss/train': 1.499235987663269} +02/26/2022 05:10:48 - INFO - codeparrot_training - Step 39861: {'lr': 5.3054409657800253e-05, 'samples': 20409344, 'steps': 39861, 'loss/train': 1.0868237018585205} +02/26/2022 05:10:54 - INFO - codeparrot_training - Step 39862: {'lr': 5.304433156091051e-05, 'samples': 20409856, 'steps': 39862, 'loss/train': 1.3696208000183105} +02/26/2022 05:11:01 - INFO - codeparrot_training - Step 39863: {'lr': 5.3034254307716386e-05, 'samples': 20410368, 'steps': 39863, 'loss/train': 2.6534674167633057} +02/26/2022 05:11:04 - INFO - codeparrot_training - Step 39864: {'lr': 5.3024177898260975e-05, 'samples': 20410880, 'steps': 39864, 'loss/train': 2.387263059616089} +02/26/2022 05:11:10 - INFO - codeparrot_training - Step 39865: {'lr': 5.3014102332587436e-05, 'samples': 20411392, 'steps': 39865, 'loss/train': 0.7505513429641724} +02/26/2022 05:11:13 - INFO - codeparrot_training - Step 39866: {'lr': 5.300402761073886e-05, 'samples': 20411904, 'steps': 39866, 'loss/train': 2.1400444507598877} +02/26/2022 05:11:20 - INFO - codeparrot_training - Step 39867: {'lr': 5.299395373275853e-05, 'samples': 20412416, 'steps': 39867, 'loss/train': 1.2390244007110596} +02/26/2022 05:11:23 - INFO - codeparrot_training - Step 39868: {'lr': 5.2983880698689565e-05, 'samples': 20412928, 'steps': 39868, 'loss/train': 1.8390448093414307} +02/26/2022 05:11:26 - INFO - codeparrot_training - Step 39869: {'lr': 5.297380850857508e-05, 'samples': 20413440, 'steps': 39869, 'loss/train': 1.5511404275894165} +02/26/2022 05:11:32 - INFO - codeparrot_training - Step 39870: {'lr': 5.29637371624582e-05, 'samples': 20413952, 'steps': 39870, 'loss/train': 0.892142117023468} +02/26/2022 05:11:35 - INFO - codeparrot_training - Step 39871: {'lr': 5.295366666038215e-05, 'samples': 20414464, 'steps': 39871, 'loss/train': 1.0398935079574585} +02/26/2022 05:11:41 - INFO - codeparrot_training - Step 39872: {'lr': 5.294359700239001e-05, 'samples': 20414976, 'steps': 39872, 'loss/train': 1.8959516286849976} +02/26/2022 05:11:44 - INFO - codeparrot_training - Step 39873: {'lr': 5.293352818852496e-05, 'samples': 20415488, 'steps': 39873, 'loss/train': 1.190548300743103} +02/26/2022 05:11:51 - INFO - codeparrot_training - Step 39874: {'lr': 5.2923460218830074e-05, 'samples': 20416000, 'steps': 39874, 'loss/train': 1.663425326347351} +02/26/2022 05:11:54 - INFO - codeparrot_training - Step 39875: {'lr': 5.2913393093348447e-05, 'samples': 20416512, 'steps': 39875, 'loss/train': 2.3053946495056152} +02/26/2022 05:12:00 - INFO - codeparrot_training - Step 39876: {'lr': 5.2903326812123314e-05, 'samples': 20417024, 'steps': 39876, 'loss/train': 2.026392936706543} +02/26/2022 05:12:03 - INFO - codeparrot_training - Step 39877: {'lr': 5.289326137519771e-05, 'samples': 20417536, 'steps': 39877, 'loss/train': 1.4735510349273682} +02/26/2022 05:12:09 - INFO - codeparrot_training - Step 39878: {'lr': 5.288319678261488e-05, 'samples': 20418048, 'steps': 39878, 'loss/train': 1.9659228324890137} +02/26/2022 05:12:12 - INFO - codeparrot_training - Step 39879: {'lr': 5.287313303441774e-05, 'samples': 20418560, 'steps': 39879, 'loss/train': 2.25028133392334} +02/26/2022 05:12:18 - INFO - codeparrot_training - Step 39880: {'lr': 5.286307013064956e-05, 'samples': 20419072, 'steps': 39880, 'loss/train': 1.6067264080047607} +02/26/2022 05:12:21 - INFO - codeparrot_training - Step 39881: {'lr': 5.285300807135332e-05, 'samples': 20419584, 'steps': 39881, 'loss/train': 1.510894775390625} +02/26/2022 05:12:27 - INFO - codeparrot_training - Step 39882: {'lr': 5.284294685657234e-05, 'samples': 20420096, 'steps': 39882, 'loss/train': 2.0477187633514404} +02/26/2022 05:12:30 - INFO - codeparrot_training - Step 39883: {'lr': 5.283288648634943e-05, 'samples': 20420608, 'steps': 39883, 'loss/train': 1.5893006324768066} +02/26/2022 05:12:36 - INFO - codeparrot_training - Step 39884: {'lr': 5.282282696072788e-05, 'samples': 20421120, 'steps': 39884, 'loss/train': 1.1562637090682983} +02/26/2022 05:12:40 - INFO - codeparrot_training - Step 39885: {'lr': 5.281276827975068e-05, 'samples': 20421632, 'steps': 39885, 'loss/train': 1.087403655052185} +02/26/2022 05:12:45 - INFO - codeparrot_training - Step 39886: {'lr': 5.280271044346108e-05, 'samples': 20422144, 'steps': 39886, 'loss/train': 2.4682846069335938} +02/26/2022 05:12:49 - INFO - codeparrot_training - Step 39887: {'lr': 5.279265345190193e-05, 'samples': 20422656, 'steps': 39887, 'loss/train': 1.378037691116333} +02/26/2022 05:12:54 - INFO - codeparrot_training - Step 39888: {'lr': 5.2782597305116504e-05, 'samples': 20423168, 'steps': 39888, 'loss/train': 1.7448939085006714} +02/26/2022 05:12:58 - INFO - codeparrot_training - Step 39889: {'lr': 5.277254200314774e-05, 'samples': 20423680, 'steps': 39889, 'loss/train': 1.8756383657455444} +02/26/2022 05:13:03 - INFO - codeparrot_training - Step 39890: {'lr': 5.2762487546038854e-05, 'samples': 20424192, 'steps': 39890, 'loss/train': 2.6077356338500977} +02/26/2022 05:13:07 - INFO - codeparrot_training - Step 39891: {'lr': 5.275243393383281e-05, 'samples': 20424704, 'steps': 39891, 'loss/train': 1.5853463411331177} +02/26/2022 05:13:12 - INFO - codeparrot_training - Step 39892: {'lr': 5.2742381166572735e-05, 'samples': 20425216, 'steps': 39892, 'loss/train': 1.5997183322906494} +02/26/2022 05:13:16 - INFO - codeparrot_training - Step 39893: {'lr': 5.273232924430158e-05, 'samples': 20425728, 'steps': 39893, 'loss/train': 2.2245750427246094} +02/26/2022 05:13:22 - INFO - codeparrot_training - Step 39894: {'lr': 5.272227816706257e-05, 'samples': 20426240, 'steps': 39894, 'loss/train': 2.6236751079559326} +02/26/2022 05:13:25 - INFO - codeparrot_training - Step 39895: {'lr': 5.271222793489866e-05, 'samples': 20426752, 'steps': 39895, 'loss/train': 1.755178451538086} +02/26/2022 05:13:31 - INFO - codeparrot_training - Step 39896: {'lr': 5.270217854785292e-05, 'samples': 20427264, 'steps': 39896, 'loss/train': 1.8808153867721558} +02/26/2022 05:13:35 - INFO - codeparrot_training - Step 39897: {'lr': 5.269213000596834e-05, 'samples': 20427776, 'steps': 39897, 'loss/train': 1.2185394763946533} +02/26/2022 05:13:40 - INFO - codeparrot_training - Step 39898: {'lr': 5.268208230928809e-05, 'samples': 20428288, 'steps': 39898, 'loss/train': 1.1425402164459229} +02/26/2022 05:13:44 - INFO - codeparrot_training - Step 39899: {'lr': 5.267203545785515e-05, 'samples': 20428800, 'steps': 39899, 'loss/train': 2.320765733718872} +02/26/2022 05:13:49 - INFO - codeparrot_training - Step 39900: {'lr': 5.266198945171252e-05, 'samples': 20429312, 'steps': 39900, 'loss/train': 1.8524881601333618} +02/26/2022 05:13:53 - INFO - codeparrot_training - Step 39901: {'lr': 5.2651944290903224e-05, 'samples': 20429824, 'steps': 39901, 'loss/train': 2.2199766635894775} +02/26/2022 05:13:58 - INFO - codeparrot_training - Step 39902: {'lr': 5.264189997547042e-05, 'samples': 20430336, 'steps': 39902, 'loss/train': 1.52739679813385} +02/26/2022 05:14:02 - INFO - codeparrot_training - Step 39903: {'lr': 5.2631856505456957e-05, 'samples': 20430848, 'steps': 39903, 'loss/train': 1.385076642036438} +02/26/2022 05:14:07 - INFO - codeparrot_training - Step 39904: {'lr': 5.262181388090609e-05, 'samples': 20431360, 'steps': 39904, 'loss/train': 1.4582237005233765} +02/26/2022 05:14:11 - INFO - codeparrot_training - Step 39905: {'lr': 5.261177210186055e-05, 'samples': 20431872, 'steps': 39905, 'loss/train': 3.2900726795196533} +02/26/2022 05:14:16 - INFO - codeparrot_training - Step 39906: {'lr': 5.260173116836356e-05, 'samples': 20432384, 'steps': 39906, 'loss/train': 2.355900287628174} +02/26/2022 05:14:20 - INFO - codeparrot_training - Step 39907: {'lr': 5.259169108045811e-05, 'samples': 20432896, 'steps': 39907, 'loss/train': 0.424358606338501} +02/26/2022 05:14:25 - INFO - codeparrot_training - Step 39908: {'lr': 5.2581651838187136e-05, 'samples': 20433408, 'steps': 39908, 'loss/train': 1.6566977500915527} +02/26/2022 05:14:29 - INFO - codeparrot_training - Step 39909: {'lr': 5.257161344159364e-05, 'samples': 20433920, 'steps': 39909, 'loss/train': 2.0595741271972656} +02/26/2022 05:14:35 - INFO - codeparrot_training - Step 39910: {'lr': 5.256157589072069e-05, 'samples': 20434432, 'steps': 39910, 'loss/train': 1.082891583442688} +02/26/2022 05:14:38 - INFO - codeparrot_training - Step 39911: {'lr': 5.2551539185611285e-05, 'samples': 20434944, 'steps': 39911, 'loss/train': 1.0988398790359497} +02/26/2022 05:14:45 - INFO - codeparrot_training - Step 39912: {'lr': 5.254150332630833e-05, 'samples': 20435456, 'steps': 39912, 'loss/train': 0.2989959418773651} +02/26/2022 05:14:48 - INFO - codeparrot_training - Step 39913: {'lr': 5.2531468312854935e-05, 'samples': 20435968, 'steps': 39913, 'loss/train': 1.5791479349136353} +02/26/2022 05:14:52 - INFO - codeparrot_training - Step 39914: {'lr': 5.252143414529401e-05, 'samples': 20436480, 'steps': 39914, 'loss/train': 0.8847836256027222} +02/26/2022 05:14:57 - INFO - codeparrot_training - Step 39915: {'lr': 5.251140082366857e-05, 'samples': 20436992, 'steps': 39915, 'loss/train': 0.7409181594848633} +02/26/2022 05:15:01 - INFO - codeparrot_training - Step 39916: {'lr': 5.2501368348021495e-05, 'samples': 20437504, 'steps': 39916, 'loss/train': 0.7507182955741882} +02/26/2022 05:15:06 - INFO - codeparrot_training - Step 39917: {'lr': 5.2491336718395926e-05, 'samples': 20438016, 'steps': 39917, 'loss/train': 0.03427466005086899} +02/26/2022 05:15:10 - INFO - codeparrot_training - Step 39918: {'lr': 5.2481305934834745e-05, 'samples': 20438528, 'steps': 39918, 'loss/train': 0.845059335231781} +02/26/2022 05:15:15 - INFO - codeparrot_training - Step 39919: {'lr': 5.247127599738094e-05, 'samples': 20439040, 'steps': 39919, 'loss/train': 3.348127841949463} +02/26/2022 05:15:19 - INFO - codeparrot_training - Step 39920: {'lr': 5.2461246906077396e-05, 'samples': 20439552, 'steps': 39920, 'loss/train': 2.5653140544891357} +02/26/2022 05:15:25 - INFO - codeparrot_training - Step 39921: {'lr': 5.245121866096722e-05, 'samples': 20440064, 'steps': 39921, 'loss/train': 0.905393123626709} +02/26/2022 05:15:28 - INFO - codeparrot_training - Step 39922: {'lr': 5.244119126209329e-05, 'samples': 20440576, 'steps': 39922, 'loss/train': 1.8390642404556274} +02/26/2022 05:15:34 - INFO - codeparrot_training - Step 39923: {'lr': 5.243116470949855e-05, 'samples': 20441088, 'steps': 39923, 'loss/train': 2.752764940261841} +02/26/2022 05:15:38 - INFO - codeparrot_training - Step 39924: {'lr': 5.24211390032259e-05, 'samples': 20441600, 'steps': 39924, 'loss/train': 1.442712426185608} +02/26/2022 05:15:43 - INFO - codeparrot_training - Step 39925: {'lr': 5.241111414331845e-05, 'samples': 20442112, 'steps': 39925, 'loss/train': 1.36506187915802} +02/26/2022 05:15:47 - INFO - codeparrot_training - Step 39926: {'lr': 5.2401090129819e-05, 'samples': 20442624, 'steps': 39926, 'loss/train': 1.8800948858261108} +02/26/2022 05:15:52 - INFO - codeparrot_training - Step 39927: {'lr': 5.2391066962770575e-05, 'samples': 20443136, 'steps': 39927, 'loss/train': 1.5546599626541138} +02/26/2022 05:15:56 - INFO - codeparrot_training - Step 39928: {'lr': 5.238104464221599e-05, 'samples': 20443648, 'steps': 39928, 'loss/train': 2.213608503341675} +02/26/2022 05:16:01 - INFO - codeparrot_training - Step 39929: {'lr': 5.237102316819831e-05, 'samples': 20444160, 'steps': 39929, 'loss/train': 2.7968904972076416} +02/26/2022 05:16:05 - INFO - codeparrot_training - Step 39930: {'lr': 5.236100254076043e-05, 'samples': 20444672, 'steps': 39930, 'loss/train': 1.476136326789856} +02/26/2022 05:16:12 - INFO - codeparrot_training - Step 39931: {'lr': 5.2350982759945266e-05, 'samples': 20445184, 'steps': 39931, 'loss/train': 1.0488280057907104} +02/26/2022 05:16:15 - INFO - codeparrot_training - Step 39932: {'lr': 5.234096382579565e-05, 'samples': 20445696, 'steps': 39932, 'loss/train': 1.8170726299285889} +02/26/2022 05:16:21 - INFO - codeparrot_training - Step 39933: {'lr': 5.233094573835464e-05, 'samples': 20446208, 'steps': 39933, 'loss/train': 1.8595818281173706} +02/26/2022 05:16:24 - INFO - codeparrot_training - Step 39934: {'lr': 5.232092849766509e-05, 'samples': 20446720, 'steps': 39934, 'loss/train': 1.4527502059936523} +02/26/2022 05:16:30 - INFO - codeparrot_training - Step 39935: {'lr': 5.2310912103769925e-05, 'samples': 20447232, 'steps': 39935, 'loss/train': 1.8730189800262451} +02/26/2022 05:16:33 - INFO - codeparrot_training - Step 39936: {'lr': 5.2300896556711966e-05, 'samples': 20447744, 'steps': 39936, 'loss/train': 1.5099983215332031} +02/26/2022 05:16:39 - INFO - codeparrot_training - Step 39937: {'lr': 5.229088185653427e-05, 'samples': 20448256, 'steps': 39937, 'loss/train': 1.108970284461975} +02/26/2022 05:16:42 - INFO - codeparrot_training - Step 39938: {'lr': 5.228086800327958e-05, 'samples': 20448768, 'steps': 39938, 'loss/train': 2.069016218185425} +02/26/2022 05:16:48 - INFO - codeparrot_training - Step 39939: {'lr': 5.2270854996991025e-05, 'samples': 20449280, 'steps': 39939, 'loss/train': 1.4826850891113281} +02/26/2022 05:16:51 - INFO - codeparrot_training - Step 39940: {'lr': 5.226084283771118e-05, 'samples': 20449792, 'steps': 39940, 'loss/train': 0.9875159859657288} +02/26/2022 05:16:57 - INFO - codeparrot_training - Step 39941: {'lr': 5.2250831525483156e-05, 'samples': 20450304, 'steps': 39941, 'loss/train': 1.9545085430145264} +02/26/2022 05:17:01 - INFO - codeparrot_training - Step 39942: {'lr': 5.224082106034972e-05, 'samples': 20450816, 'steps': 39942, 'loss/train': 1.7497848272323608} +02/26/2022 05:17:06 - INFO - codeparrot_training - Step 39943: {'lr': 5.223081144235395e-05, 'samples': 20451328, 'steps': 39943, 'loss/train': 1.555019497871399} +02/26/2022 05:17:10 - INFO - codeparrot_training - Step 39944: {'lr': 5.2220802671538446e-05, 'samples': 20451840, 'steps': 39944, 'loss/train': 0.8500522971153259} +02/26/2022 05:17:15 - INFO - codeparrot_training - Step 39945: {'lr': 5.2210794747946296e-05, 'samples': 20452352, 'steps': 39945, 'loss/train': 1.1895655393600464} +02/26/2022 05:17:19 - INFO - codeparrot_training - Step 39946: {'lr': 5.220078767162023e-05, 'samples': 20452864, 'steps': 39946, 'loss/train': 1.3385703563690186} +02/26/2022 05:17:25 - INFO - codeparrot_training - Step 39947: {'lr': 5.219078144260331e-05, 'samples': 20453376, 'steps': 39947, 'loss/train': 1.9422162771224976} +02/26/2022 05:17:29 - INFO - codeparrot_training - Step 39948: {'lr': 5.2180776060938126e-05, 'samples': 20453888, 'steps': 39948, 'loss/train': 1.648809552192688} +02/26/2022 05:17:34 - INFO - codeparrot_training - Step 39949: {'lr': 5.217077152666777e-05, 'samples': 20454400, 'steps': 39949, 'loss/train': 0.9245172142982483} +02/26/2022 05:17:40 - INFO - codeparrot_training - Step 39950: {'lr': 5.216076783983492e-05, 'samples': 20454912, 'steps': 39950, 'loss/train': 1.8229225873947144} +02/26/2022 05:17:43 - INFO - codeparrot_training - Step 39951: {'lr': 5.2150765000482605e-05, 'samples': 20455424, 'steps': 39951, 'loss/train': 0.5943360328674316} +02/26/2022 05:17:47 - INFO - codeparrot_training - Step 39952: {'lr': 5.2140763008653586e-05, 'samples': 20455936, 'steps': 39952, 'loss/train': 0.992263674736023} +02/26/2022 05:17:52 - INFO - codeparrot_training - Step 39953: {'lr': 5.21307618643907e-05, 'samples': 20456448, 'steps': 39953, 'loss/train': 1.3918200731277466} +02/26/2022 05:17:58 - INFO - codeparrot_training - Step 39954: {'lr': 5.212076156773673e-05, 'samples': 20456960, 'steps': 39954, 'loss/train': 1.640095591545105} +02/26/2022 05:18:01 - INFO - codeparrot_training - Step 39955: {'lr': 5.2110762118734665e-05, 'samples': 20457472, 'steps': 39955, 'loss/train': 1.9625239372253418} +02/26/2022 05:18:08 - INFO - codeparrot_training - Step 39956: {'lr': 5.210076351742726e-05, 'samples': 20457984, 'steps': 39956, 'loss/train': 0.7800009846687317} +02/26/2022 05:18:11 - INFO - codeparrot_training - Step 39957: {'lr': 5.209076576385735e-05, 'samples': 20458496, 'steps': 39957, 'loss/train': 1.860217809677124} +02/26/2022 05:18:17 - INFO - codeparrot_training - Step 39958: {'lr': 5.208076885806773e-05, 'samples': 20459008, 'steps': 39958, 'loss/train': 0.9180641174316406} +02/26/2022 05:18:20 - INFO - codeparrot_training - Step 39959: {'lr': 5.2070772800101196e-05, 'samples': 20459520, 'steps': 39959, 'loss/train': 2.3119800090789795} +02/26/2022 05:18:26 - INFO - codeparrot_training - Step 39960: {'lr': 5.206077759000069e-05, 'samples': 20460032, 'steps': 39960, 'loss/train': 1.6303881406784058} +02/26/2022 05:18:29 - INFO - codeparrot_training - Step 39961: {'lr': 5.2050783227808955e-05, 'samples': 20460544, 'steps': 39961, 'loss/train': 1.512158751487732} +02/26/2022 05:18:34 - INFO - codeparrot_training - Step 39962: {'lr': 5.204078971356882e-05, 'samples': 20461056, 'steps': 39962, 'loss/train': 0.6630454659461975} +02/26/2022 05:18:38 - INFO - codeparrot_training - Step 39963: {'lr': 5.203079704732303e-05, 'samples': 20461568, 'steps': 39963, 'loss/train': 2.811910390853882} +02/26/2022 05:18:43 - INFO - codeparrot_training - Step 39964: {'lr': 5.202080522911448e-05, 'samples': 20462080, 'steps': 39964, 'loss/train': 1.0674400329589844} +02/26/2022 05:18:47 - INFO - codeparrot_training - Step 39965: {'lr': 5.201081425898593e-05, 'samples': 20462592, 'steps': 39965, 'loss/train': 1.4454385042190552} +02/26/2022 05:18:53 - INFO - codeparrot_training - Step 39966: {'lr': 5.200082413698021e-05, 'samples': 20463104, 'steps': 39966, 'loss/train': 1.005170464515686} +02/26/2022 05:18:57 - INFO - codeparrot_training - Step 39967: {'lr': 5.199083486314002e-05, 'samples': 20463616, 'steps': 39967, 'loss/train': 2.5360870361328125} +02/26/2022 05:19:02 - INFO - codeparrot_training - Step 39968: {'lr': 5.198084643750825e-05, 'samples': 20464128, 'steps': 39968, 'loss/train': 1.8909685611724854} +02/26/2022 05:19:06 - INFO - codeparrot_training - Step 39969: {'lr': 5.19708588601277e-05, 'samples': 20464640, 'steps': 39969, 'loss/train': 2.437023162841797} +02/26/2022 05:19:11 - INFO - codeparrot_training - Step 39970: {'lr': 5.196087213104109e-05, 'samples': 20465152, 'steps': 39970, 'loss/train': 1.450929045677185} +02/26/2022 05:19:15 - INFO - codeparrot_training - Step 39971: {'lr': 5.1950886250291154e-05, 'samples': 20465664, 'steps': 39971, 'loss/train': 1.8635060787200928} +02/26/2022 05:19:20 - INFO - codeparrot_training - Step 39972: {'lr': 5.194090121792078e-05, 'samples': 20466176, 'steps': 39972, 'loss/train': 1.9153963327407837} +02/26/2022 05:19:24 - INFO - codeparrot_training - Step 39973: {'lr': 5.193091703397265e-05, 'samples': 20466688, 'steps': 39973, 'loss/train': 1.155573844909668} +02/26/2022 05:19:29 - INFO - codeparrot_training - Step 39974: {'lr': 5.192093369848971e-05, 'samples': 20467200, 'steps': 39974, 'loss/train': 2.5826423168182373} +02/26/2022 05:19:33 - INFO - codeparrot_training - Step 39975: {'lr': 5.191095121151446e-05, 'samples': 20467712, 'steps': 39975, 'loss/train': 2.0458474159240723} +02/26/2022 05:19:38 - INFO - codeparrot_training - Step 39976: {'lr': 5.1900969573089846e-05, 'samples': 20468224, 'steps': 39976, 'loss/train': 1.9865025281906128} +02/26/2022 05:19:42 - INFO - codeparrot_training - Step 39977: {'lr': 5.189098878325851e-05, 'samples': 20468736, 'steps': 39977, 'loss/train': 0.6222102046012878} +02/26/2022 05:19:47 - INFO - codeparrot_training - Step 39978: {'lr': 5.188100884206343e-05, 'samples': 20469248, 'steps': 39978, 'loss/train': 2.0489501953125} +02/26/2022 05:19:51 - INFO - codeparrot_training - Step 39979: {'lr': 5.187102974954705e-05, 'samples': 20469760, 'steps': 39979, 'loss/train': 2.1365416049957275} +02/26/2022 05:19:57 - INFO - codeparrot_training - Step 39980: {'lr': 5.1861051505752324e-05, 'samples': 20470272, 'steps': 39980, 'loss/train': 1.1082971096038818} +02/26/2022 05:20:00 - INFO - codeparrot_training - Step 39981: {'lr': 5.1851074110721875e-05, 'samples': 20470784, 'steps': 39981, 'loss/train': 1.1782704591751099} +02/26/2022 05:20:06 - INFO - codeparrot_training - Step 39982: {'lr': 5.184109756449865e-05, 'samples': 20471296, 'steps': 39982, 'loss/train': 1.077696681022644} +02/26/2022 05:20:10 - INFO - codeparrot_training - Step 39983: {'lr': 5.1831121867125074e-05, 'samples': 20471808, 'steps': 39983, 'loss/train': 1.541429877281189} +02/26/2022 05:20:15 - INFO - codeparrot_training - Step 39984: {'lr': 5.182114701864416e-05, 'samples': 20472320, 'steps': 39984, 'loss/train': 1.0684746503829956} +02/26/2022 05:20:19 - INFO - codeparrot_training - Step 39985: {'lr': 5.1811173019098434e-05, 'samples': 20472832, 'steps': 39985, 'loss/train': 1.7460517883300781} +02/26/2022 05:20:24 - INFO - codeparrot_training - Step 39986: {'lr': 5.180119986853077e-05, 'samples': 20473344, 'steps': 39986, 'loss/train': 2.0925605297088623} +02/26/2022 05:20:28 - INFO - codeparrot_training - Step 39987: {'lr': 5.1791227566983845e-05, 'samples': 20473856, 'steps': 39987, 'loss/train': 1.1940850019454956} +02/26/2022 05:20:33 - INFO - codeparrot_training - Step 39988: {'lr': 5.178125611450035e-05, 'samples': 20474368, 'steps': 39988, 'loss/train': 1.445656657218933} +02/26/2022 05:20:37 - INFO - codeparrot_training - Step 39989: {'lr': 5.177128551112295e-05, 'samples': 20474880, 'steps': 39989, 'loss/train': 1.4053744077682495} +02/26/2022 05:20:42 - INFO - codeparrot_training - Step 39990: {'lr': 5.176131575689447e-05, 'samples': 20475392, 'steps': 39990, 'loss/train': 1.9748722314834595} +02/26/2022 05:20:45 - INFO - codeparrot_training - Step 39991: {'lr': 5.175134685185759e-05, 'samples': 20475904, 'steps': 39991, 'loss/train': 1.6935545206069946} +02/26/2022 05:20:52 - INFO - codeparrot_training - Step 39992: {'lr': 5.174137879605498e-05, 'samples': 20476416, 'steps': 39992, 'loss/train': 1.3617392778396606} +02/26/2022 05:20:55 - INFO - codeparrot_training - Step 39993: {'lr': 5.1731411589529294e-05, 'samples': 20476928, 'steps': 39993, 'loss/train': 2.605715036392212} +02/26/2022 05:20:59 - INFO - codeparrot_training - Step 39994: {'lr': 5.1721445232323335e-05, 'samples': 20477440, 'steps': 39994, 'loss/train': 1.5338573455810547} +02/26/2022 05:21:04 - INFO - codeparrot_training - Step 39995: {'lr': 5.171147972447973e-05, 'samples': 20477952, 'steps': 39995, 'loss/train': 1.700262427330017} +02/26/2022 05:21:08 - INFO - codeparrot_training - Step 39996: {'lr': 5.170151506604121e-05, 'samples': 20478464, 'steps': 39996, 'loss/train': 1.9522618055343628} +02/26/2022 05:21:14 - INFO - codeparrot_training - Step 39997: {'lr': 5.169155125705036e-05, 'samples': 20478976, 'steps': 39997, 'loss/train': 0.7937091588973999} +02/26/2022 05:21:17 - INFO - codeparrot_training - Step 39998: {'lr': 5.1681588297549986e-05, 'samples': 20479488, 'steps': 39998, 'loss/train': 1.0893386602401733} +02/26/2022 05:21:23 - INFO - codeparrot_training - Step 39999: {'lr': 5.1671626187582723e-05, 'samples': 20480000, 'steps': 39999, 'loss/train': 2.366724729537964} +02/26/2022 05:21:23 - INFO - codeparrot_training - Evaluating and saving model checkpoint