diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -15045,3 +15045,2506 @@ Use FP16 precision: False
 12/24/2021 14:59:31 - INFO - codeparrot_training - Step 12499: {'lr': 0.0004282446197415785, 'samples': 6400000, 'steps': 12499, 'batch_loss/train': 0.745213175425306}
 12/24/2021 14:59:31 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/24/2021 15:02:52 - INFO - codeparrot_training - Step 12500: {'loss/eval': 0.8193633556365967, 'perplexity': 2.269054889678955}
+12/24/2021 15:03:09 - WARNING - huggingface_hub.repository - Several commits (3) will be pushed upstream.
+12/24/2021 15:03:24 - INFO - codeparrot_training - Step 12500: {'lr': 0.00042823356649955265, 'samples': 6400512, 'steps': 12500, 'batch_loss/train': 0.8593634327407926}
+12/24/2021 15:03:35 - INFO - codeparrot_training - Step 12501: {'lr': 0.0004282225125489374, 'samples': 6401024, 'steps': 12501, 'batch_loss/train': 0.7067815940827131}
+12/24/2021 15:03:45 - INFO - codeparrot_training - Step 12502: {'lr': 0.0004282114578897767, 'samples': 6401536, 'steps': 12502, 'batch_loss/train': 0.7497427952475846}
+12/24/2021 15:04:00 - INFO - codeparrot_training - Step 12503: {'lr': 0.00042820040252211454, 'samples': 6402048, 'steps': 12503, 'batch_loss/train': 0.8325769518269226}
+12/24/2021 15:04:10 - INFO - codeparrot_training - Step 12504: {'lr': 0.00042818934644599493, 'samples': 6402560, 'steps': 12504, 'batch_loss/train': 0.7711407681927085}
+12/24/2021 15:04:21 - INFO - codeparrot_training - Step 12505: {'lr': 0.00042817828966146173, 'samples': 6403072, 'steps': 12505, 'batch_loss/train': 0.5320454495376907}
+12/24/2021 15:04:33 - INFO - codeparrot_training - Step 12506: {'lr': 0.0004281672321685589, 'samples': 6403584, 'steps': 12506, 'batch_loss/train': 0.754804483614862}
+12/24/2021 15:04:44 - INFO - codeparrot_training - Step 12507: {'lr': 0.0004281561739673304, 'samples': 6404096, 'steps': 12507, 'batch_loss/train': 0.8037345167249441}
+12/24/2021 15:04:54 - INFO - codeparrot_training - Step 12508: {'lr': 0.0004281451150578203, 'samples': 6404608, 'steps': 12508, 'batch_loss/train': 0.7624505225103348}
+12/24/2021 15:05:07 - INFO - codeparrot_training - Step 12509: {'lr': 0.00042813405544007245, 'samples': 6405120, 'steps': 12509, 'batch_loss/train': 0.836041453294456}
+12/24/2021 15:05:17 - INFO - codeparrot_training - Step 12510: {'lr': 0.00042812299511413087, 'samples': 6405632, 'steps': 12510, 'batch_loss/train': 0.7718489300459623}
+12/24/2021 15:05:28 - INFO - codeparrot_training - Step 12511: {'lr': 0.00042811193408003956, 'samples': 6406144, 'steps': 12511, 'batch_loss/train': 0.7994400281459093}
+12/24/2021 15:05:39 - INFO - codeparrot_training - Step 12512: {'lr': 0.00042810087233784237, 'samples': 6406656, 'steps': 12512, 'batch_loss/train': 0.8050190825015306}
+12/24/2021 15:05:51 - INFO - codeparrot_training - Step 12513: {'lr': 0.0004280898098875834, 'samples': 6407168, 'steps': 12513, 'batch_loss/train': 0.6992241148836911}
+12/24/2021 15:06:01 - INFO - codeparrot_training - Step 12514: {'lr': 0.00042807874672930657, 'samples': 6407680, 'steps': 12514, 'batch_loss/train': 0.71758639998734}
+12/24/2021 15:06:12 - INFO - codeparrot_training - Step 12515: {'lr': 0.00042806768286305594, 'samples': 6408192, 'steps': 12515, 'batch_loss/train': 0.7814584905281663}
+12/24/2021 15:06:26 - INFO - codeparrot_training - Step 12516: {'lr': 0.0004280566182888754, 'samples': 6408704, 'steps': 12516, 'batch_loss/train': 0.8314587259665132}
+12/24/2021 15:06:36 - INFO - codeparrot_training - Step 12517: {'lr': 0.0004280455530068089, 'samples': 6409216, 'steps': 12517, 'batch_loss/train': 0.9352252334356308}
+12/24/2021 15:06:47 - INFO - codeparrot_training - Step 12518: {'lr': 0.00042803448701690065, 'samples': 6409728, 'steps': 12518, 'batch_loss/train': 0.8647064417600632}
+12/24/2021 15:06:58 - INFO - codeparrot_training - Step 12519: {'lr': 0.0004280234203191944, 'samples': 6410240, 'steps': 12519, 'batch_loss/train': 0.9176020724698901}
+12/24/2021 15:07:10 - INFO - codeparrot_training - Step 12520: {'lr': 0.0004280123529137343, 'samples': 6410752, 'steps': 12520, 'batch_loss/train': 0.7387919737957418}
+12/24/2021 15:07:20 - INFO - codeparrot_training - Step 12521: {'lr': 0.0004280012848005643, 'samples': 6411264, 'steps': 12521, 'batch_loss/train': 0.7734425188973546}
+12/24/2021 15:07:31 - INFO - codeparrot_training - Step 12522: {'lr': 0.0004279902159797283, 'samples': 6411776, 'steps': 12522, 'batch_loss/train': 0.7120393645018339}
+12/24/2021 15:07:45 - INFO - codeparrot_training - Step 12523: {'lr': 0.0004279791464512706, 'samples': 6412288, 'steps': 12523, 'batch_loss/train': 0.9026863630861044}
+12/24/2021 15:07:55 - INFO - codeparrot_training - Step 12524: {'lr': 0.0004279680762152349, 'samples': 6412800, 'steps': 12524, 'batch_loss/train': 0.9006065241992474}
+12/24/2021 15:08:06 - INFO - codeparrot_training - Step 12525: {'lr': 0.00042795700527166523, 'samples': 6413312, 'steps': 12525, 'batch_loss/train': 0.7988934030290693}
+12/24/2021 15:08:18 - INFO - codeparrot_training - Step 12526: {'lr': 0.00042794593362060584, 'samples': 6413824, 'steps': 12526, 'batch_loss/train': 0.8117581093683839}
+12/24/2021 15:08:29 - INFO - codeparrot_training - Step 12527: {'lr': 0.00042793486126210063, 'samples': 6414336, 'steps': 12527, 'batch_loss/train': 0.7496100584976375}
+12/24/2021 15:08:39 - INFO - codeparrot_training - Step 12528: {'lr': 0.0004279237881961935, 'samples': 6414848, 'steps': 12528, 'batch_loss/train': 0.8645166782662272}
+12/24/2021 15:08:50 - INFO - codeparrot_training - Step 12529: {'lr': 0.00042791271442292866, 'samples': 6415360, 'steps': 12529, 'batch_loss/train': 0.8367462414316833}
+12/24/2021 15:09:02 - INFO - codeparrot_training - Step 12530: {'lr': 0.00042790163994235, 'samples': 6415872, 'steps': 12530, 'batch_loss/train': 1.0348610579967499}
+12/24/2021 15:09:12 - INFO - codeparrot_training - Step 12531: {'lr': 0.00042789056475450157, 'samples': 6416384, 'steps': 12531, 'batch_loss/train': 0.7822382273152471}
+12/24/2021 15:09:23 - INFO - codeparrot_training - Step 12532: {'lr': 0.0004278794888594274, 'samples': 6416896, 'steps': 12532, 'batch_loss/train': 0.936638574115932}
+12/24/2021 15:09:37 - INFO - codeparrot_training - Step 12533: {'lr': 0.00042786841225717163, 'samples': 6417408, 'steps': 12533, 'batch_loss/train': 0.7991258660331368}
+12/24/2021 15:09:47 - INFO - codeparrot_training - Step 12534: {'lr': 0.0004278573349477782, 'samples': 6417920, 'steps': 12534, 'batch_loss/train': 0.8300980255007744}
+12/24/2021 15:09:58 - INFO - codeparrot_training - Step 12535: {'lr': 0.0004278462569312911, 'samples': 6418432, 'steps': 12535, 'batch_loss/train': 0.7783073745667934}
+12/24/2021 15:10:10 - INFO - codeparrot_training - Step 12536: {'lr': 0.0004278351782077545, 'samples': 6418944, 'steps': 12536, 'batch_loss/train': 0.788862157613039}
+12/24/2021 15:10:21 - INFO - codeparrot_training - Step 12537: {'lr': 0.0004278240987772123, 'samples': 6419456, 'steps': 12537, 'batch_loss/train': 0.788922606036067}
+12/24/2021 15:10:31 - INFO - codeparrot_training - Step 12538: {'lr': 0.0004278130186397087, 'samples': 6419968, 'steps': 12538, 'batch_loss/train': 0.8325432632118464}
+12/24/2021 15:10:44 - INFO - codeparrot_training - Step 12539: {'lr': 0.00042780193779528767, 'samples': 6420480, 'steps': 12539, 'batch_loss/train': 0.7274671760387719}
+12/24/2021 15:10:54 - INFO - codeparrot_training - Step 12540: {'lr': 0.0004277908562439933, 'samples': 6420992, 'steps': 12540, 'batch_loss/train': 0.7741058515384793}
+12/24/2021 15:11:05 - INFO - codeparrot_training - Step 12541: {'lr': 0.0004277797739858695, 'samples': 6421504, 'steps': 12541, 'batch_loss/train': 0.7834247495047748}
+12/24/2021 15:11:15 - INFO - codeparrot_training - Step 12542: {'lr': 0.0004277686910209605, 'samples': 6422016, 'steps': 12542, 'batch_loss/train': 0.5988394973683171}
+12/24/2021 15:11:28 - INFO - codeparrot_training - Step 12543: {'lr': 0.00042775760734931035, 'samples': 6422528, 'steps': 12543, 'batch_loss/train': 0.8744842577725649}
+12/24/2021 15:11:38 - INFO - codeparrot_training - Step 12544: {'lr': 0.00042774652297096304, 'samples': 6423040, 'steps': 12544, 'batch_loss/train': 0.7917586546391249}
+12/24/2021 15:11:49 - INFO - codeparrot_training - Step 12545: {'lr': 0.0004277354378859627, 'samples': 6423552, 'steps': 12545, 'batch_loss/train': 0.7943313712021336}
+12/24/2021 15:12:03 - INFO - codeparrot_training - Step 12546: {'lr': 0.00042772435209435333, 'samples': 6424064, 'steps': 12546, 'batch_loss/train': 0.8008491066284478}
+12/24/2021 15:12:13 - INFO - codeparrot_training - Step 12547: {'lr': 0.0004277132655961791, 'samples': 6424576, 'steps': 12547, 'batch_loss/train': 0.7708990881219506}
+12/24/2021 15:12:24 - INFO - codeparrot_training - Step 12548: {'lr': 0.00042770217839148395, 'samples': 6425088, 'steps': 12548, 'batch_loss/train': 1.0026995101943612}
+12/24/2021 15:12:36 - INFO - codeparrot_training - Step 12549: {'lr': 0.00042769109048031205, 'samples': 6425600, 'steps': 12549, 'batch_loss/train': 0.881767921615392}
+12/24/2021 15:12:47 - INFO - codeparrot_training - Step 12550: {'lr': 0.0004276800018627075, 'samples': 6426112, 'steps': 12550, 'batch_loss/train': 0.7471167128533125}
+12/24/2021 15:12:57 - INFO - codeparrot_training - Step 12551: {'lr': 0.0004276689125387143, 'samples': 6426624, 'steps': 12551, 'batch_loss/train': 0.7414843237493187}
+12/24/2021 15:13:08 - INFO - codeparrot_training - Step 12552: {'lr': 0.00042765782250837664, 'samples': 6427136, 'steps': 12552, 'batch_loss/train': 0.8894875384867191}
+12/24/2021 15:13:21 - INFO - codeparrot_training - Step 12553: {'lr': 0.0004276467317717386, 'samples': 6427648, 'steps': 12553, 'batch_loss/train': 0.8328850325196981}
+12/24/2021 15:13:32 - INFO - codeparrot_training - Step 12554: {'lr': 0.00042763564032884414, 'samples': 6428160, 'steps': 12554, 'batch_loss/train': 0.8170148031786084}
+12/24/2021 15:13:43 - INFO - codeparrot_training - Step 12555: {'lr': 0.0004276245481797375, 'samples': 6428672, 'steps': 12555, 'batch_loss/train': 0.8414353891275823}
+12/24/2021 15:13:55 - INFO - codeparrot_training - Step 12556: {'lr': 0.00042761345532446273, 'samples': 6429184, 'steps': 12556, 'batch_loss/train': 0.8538457024842501}
+12/24/2021 15:14:05 - INFO - codeparrot_training - Step 12557: {'lr': 0.0004276023617630639, 'samples': 6429696, 'steps': 12557, 'batch_loss/train': 0.8339118333533406}
+12/24/2021 15:14:16 - INFO - codeparrot_training - Step 12558: {'lr': 0.00042759126749558515, 'samples': 6430208, 'steps': 12558, 'batch_loss/train': 0.8530780868604779}
+12/24/2021 15:14:28 - INFO - codeparrot_training - Step 12559: {'lr': 0.0004275801725220705, 'samples': 6430720, 'steps': 12559, 'batch_loss/train': 0.8244136100402102}
+12/24/2021 15:14:39 - INFO - codeparrot_training - Step 12560: {'lr': 0.0004275690768425643, 'samples': 6431232, 'steps': 12560, 'batch_loss/train': 0.8316478095948696}
+12/24/2021 15:14:49 - INFO - codeparrot_training - Step 12561: {'lr': 0.00042755798045711037, 'samples': 6431744, 'steps': 12561, 'batch_loss/train': 0.833941025659442}
+12/24/2021 15:15:03 - INFO - codeparrot_training - Step 12562: {'lr': 0.000427546883365753, 'samples': 6432256, 'steps': 12562, 'batch_loss/train': 0.7276930769439787}
+12/24/2021 15:15:14 - INFO - codeparrot_training - Step 12563: {'lr': 0.0004275357855685362, 'samples': 6432768, 'steps': 12563, 'batch_loss/train': 1.7352975346148014}
+12/24/2021 15:15:25 - INFO - codeparrot_training - Step 12564: {'lr': 0.0004275246870655043, 'samples': 6433280, 'steps': 12564, 'batch_loss/train': 0.8410628056153655}
+12/24/2021 15:15:35 - INFO - codeparrot_training - Step 12565: {'lr': 0.0004275135878567011, 'samples': 6433792, 'steps': 12565, 'batch_loss/train': 1.4730480615980923}
+12/24/2021 15:15:47 - INFO - codeparrot_training - Step 12566: {'lr': 0.000427502487942171, 'samples': 6434304, 'steps': 12566, 'batch_loss/train': 0.8459376911632717}
+12/24/2021 15:15:58 - INFO - codeparrot_training - Step 12567: {'lr': 0.00042749138732195804, 'samples': 6434816, 'steps': 12567, 'batch_loss/train': 0.8043190236203372}
+12/24/2021 15:16:08 - INFO - codeparrot_training - Step 12568: {'lr': 0.0004274802859961063, 'samples': 6435328, 'steps': 12568, 'batch_loss/train': 0.8507891995832324}
+12/24/2021 15:16:22 - INFO - codeparrot_training - Step 12569: {'lr': 0.00042746918396465995, 'samples': 6435840, 'steps': 12569, 'batch_loss/train': 0.80434625223279}
+12/24/2021 15:16:33 - INFO - codeparrot_training - Step 12570: {'lr': 0.0004274580812276632, 'samples': 6436352, 'steps': 12570, 'batch_loss/train': 0.7979062153026462}
+12/24/2021 15:16:44 - INFO - codeparrot_training - Step 12571: {'lr': 0.0004274469777851601, 'samples': 6436864, 'steps': 12571, 'batch_loss/train': 0.9130801339633763}
+12/24/2021 15:16:54 - INFO - codeparrot_training - Step 12572: {'lr': 0.0004274358736371947, 'samples': 6437376, 'steps': 12572, 'batch_loss/train': 0.8188600828871131}
+12/24/2021 15:17:06 - INFO - codeparrot_training - Step 12573: {'lr': 0.00042742476878381144, 'samples': 6437888, 'steps': 12573, 'batch_loss/train': 0.7786412108689547}
+12/24/2021 15:17:17 - INFO - codeparrot_training - Step 12574: {'lr': 0.00042741366322505416, 'samples': 6438400, 'steps': 12574, 'batch_loss/train': 0.9284954508766532}
+12/24/2021 15:17:28 - INFO - codeparrot_training - Step 12575: {'lr': 0.0004274025569609672, 'samples': 6438912, 'steps': 12575, 'batch_loss/train': 0.7526645252946764}
+12/24/2021 15:17:40 - INFO - codeparrot_training - Step 12576: {'lr': 0.0004273914499915946, 'samples': 6439424, 'steps': 12576, 'batch_loss/train': 0.7894351202994585}
+12/24/2021 15:17:50 - INFO - codeparrot_training - Step 12577: {'lr': 0.00042738034231698063, 'samples': 6439936, 'steps': 12577, 'batch_loss/train': 0.7836560728028417}
+12/24/2021 15:18:01 - INFO - codeparrot_training - Step 12578: {'lr': 0.0004273692339371694, 'samples': 6440448, 'steps': 12578, 'batch_loss/train': 0.7091091936454177}
+12/24/2021 15:18:15 - INFO - codeparrot_training - Step 12579: {'lr': 0.00042735812485220504, 'samples': 6440960, 'steps': 12579, 'batch_loss/train': 0.8197984588332474}
+12/24/2021 15:18:26 - INFO - codeparrot_training - Step 12580: {'lr': 0.0004273470150621318, 'samples': 6441472, 'steps': 12580, 'batch_loss/train': 0.8144944543018937}
+12/24/2021 15:18:36 - INFO - codeparrot_training - Step 12581: {'lr': 0.0004273359045669938, 'samples': 6441984, 'steps': 12581, 'batch_loss/train': 0.8112665330991149}
+12/24/2021 15:18:47 - INFO - codeparrot_training - Step 12582: {'lr': 0.00042732479336683515, 'samples': 6442496, 'steps': 12582, 'batch_loss/train': 0.8013476715423167}
+12/24/2021 15:18:59 - INFO - codeparrot_training - Step 12583: {'lr': 0.0004273136814617, 'samples': 6443008, 'steps': 12583, 'batch_loss/train': 0.6059524192241952}
+12/24/2021 15:19:10 - INFO - codeparrot_training - Step 12584: {'lr': 0.00042730256885163275, 'samples': 6443520, 'steps': 12584, 'batch_loss/train': 0.8411729331128299}
+12/24/2021 15:19:20 - INFO - codeparrot_training - Step 12585: {'lr': 0.0004272914555366774, 'samples': 6444032, 'steps': 12585, 'batch_loss/train': 0.893549625761807}
+12/24/2021 15:19:33 - INFO - codeparrot_training - Step 12586: {'lr': 0.00042728034151687813, 'samples': 6444544, 'steps': 12586, 'batch_loss/train': 0.7435586103238165}
+12/24/2021 15:19:43 - INFO - codeparrot_training - Step 12587: {'lr': 0.00042726922679227916, 'samples': 6445056, 'steps': 12587, 'batch_loss/train': 0.7921226331964135}
+12/24/2021 15:19:54 - INFO - codeparrot_training - Step 12588: {'lr': 0.0004272581113629247, 'samples': 6445568, 'steps': 12588, 'batch_loss/train': 0.921039080247283}
+12/24/2021 15:20:06 - INFO - codeparrot_training - Step 12589: {'lr': 0.0004272469952288589, 'samples': 6446080, 'steps': 12589, 'batch_loss/train': 0.6759250807808712}
+12/24/2021 15:20:17 - INFO - codeparrot_training - Step 12590: {'lr': 0.000427235878390126, 'samples': 6446592, 'steps': 12590, 'batch_loss/train': 0.8440966885536909}
+12/24/2021 15:20:27 - INFO - codeparrot_training - Step 12591: {'lr': 0.0004272247608467701, 'samples': 6447104, 'steps': 12591, 'batch_loss/train': 0.877419629599899}
+12/24/2021 15:20:38 - INFO - codeparrot_training - Step 12592: {'lr': 0.00042721364259883554, 'samples': 6447616, 'steps': 12592, 'batch_loss/train': 0.8526618042960763}
+12/24/2021 15:20:52 - INFO - codeparrot_training - Step 12593: {'lr': 0.00042720252364636635, 'samples': 6448128, 'steps': 12593, 'batch_loss/train': 0.8771097280550748}
+12/24/2021 15:21:02 - INFO - codeparrot_training - Step 12594: {'lr': 0.000427191403989407, 'samples': 6448640, 'steps': 12594, 'batch_loss/train': 0.7811001027002931}
+12/24/2021 15:21:13 - INFO - codeparrot_training - Step 12595: {'lr': 0.00042718028362800144, 'samples': 6449152, 'steps': 12595, 'batch_loss/train': 0.7772481930442154}
+12/24/2021 15:21:25 - INFO - codeparrot_training - Step 12596: {'lr': 0.00042716916256219393, 'samples': 6449664, 'steps': 12596, 'batch_loss/train': 0.8449200331233442}
+12/24/2021 15:21:36 - INFO - codeparrot_training - Step 12597: {'lr': 0.0004271580407920288, 'samples': 6450176, 'steps': 12597, 'batch_loss/train': 0.7910690953722224}
+12/24/2021 15:21:46 - INFO - codeparrot_training - Step 12598: {'lr': 0.00042714691831755014, 'samples': 6450688, 'steps': 12598, 'batch_loss/train': 0.6939439445268363}
+12/24/2021 15:22:00 - INFO - codeparrot_training - Step 12599: {'lr': 0.0004271357951388023, 'samples': 6451200, 'steps': 12599, 'batch_loss/train': 0.8071074280887842}
+12/24/2021 15:22:11 - INFO - codeparrot_training - Step 12600: {'lr': 0.0004271246712558293, 'samples': 6451712, 'steps': 12600, 'batch_loss/train': 0.6413073476869613}
+12/24/2021 15:22:22 - INFO - codeparrot_training - Step 12601: {'lr': 0.00042711354666867557, 'samples': 6452224, 'steps': 12601, 'batch_loss/train': 0.7591525570023805}
+12/24/2021 15:22:32 - INFO - codeparrot_training - Step 12602: {'lr': 0.0004271024213773853, 'samples': 6452736, 'steps': 12602, 'batch_loss/train': 0.790421596262604}
+12/24/2021 15:22:44 - INFO - codeparrot_training - Step 12603: {'lr': 0.0004270912953820026, 'samples': 6453248, 'steps': 12603, 'batch_loss/train': 0.851144996471703}
+12/24/2021 15:22:55 - INFO - codeparrot_training - Step 12604: {'lr': 0.0004270801686825717, 'samples': 6453760, 'steps': 12604, 'batch_loss/train': 0.7764520337805152}
+12/24/2021 15:23:05 - INFO - codeparrot_training - Step 12605: {'lr': 0.00042706904127913704, 'samples': 6454272, 'steps': 12605, 'batch_loss/train': 0.7731544822454453}
+12/24/2021 15:23:17 - INFO - codeparrot_training - Step 12606: {'lr': 0.0004270579131717427, 'samples': 6454784, 'steps': 12606, 'batch_loss/train': 0.7640663693891838}
+12/24/2021 15:23:28 - INFO - codeparrot_training - Step 12607: {'lr': 0.000427046784360433, 'samples': 6455296, 'steps': 12607, 'batch_loss/train': 0.8692188682034612}
+12/24/2021 15:23:39 - INFO - codeparrot_training - Step 12608: {'lr': 0.000427035654845252, 'samples': 6455808, 'steps': 12608, 'batch_loss/train': 0.9442226234823465}
+12/24/2021 15:23:52 - INFO - codeparrot_training - Step 12609: {'lr': 0.0004270245246262442, 'samples': 6456320, 'steps': 12609, 'batch_loss/train': 0.855852272361517}
+12/24/2021 15:24:03 - INFO - codeparrot_training - Step 12610: {'lr': 0.0004270133937034537, 'samples': 6456832, 'steps': 12610, 'batch_loss/train': 0.8145561208948493}
+12/24/2021 15:24:14 - INFO - codeparrot_training - Step 12611: {'lr': 0.0004270022620769248, 'samples': 6457344, 'steps': 12611, 'batch_loss/train': 0.8343264537397772}
+12/24/2021 15:24:24 - INFO - codeparrot_training - Step 12612: {'lr': 0.00042699112974670166, 'samples': 6457856, 'steps': 12612, 'batch_loss/train': 0.8086019335314631}
+12/24/2021 15:24:37 - INFO - codeparrot_training - Step 12613: {'lr': 0.0004269799967128287, 'samples': 6458368, 'steps': 12613, 'batch_loss/train': 0.8558925767429173}
+12/24/2021 15:24:47 - INFO - codeparrot_training - Step 12614: {'lr': 0.0004269688629753501, 'samples': 6458880, 'steps': 12614, 'batch_loss/train': 0.7844953574240208}
+12/24/2021 15:24:58 - INFO - codeparrot_training - Step 12615: {'lr': 0.0004269577285343101, 'samples': 6459392, 'steps': 12615, 'batch_loss/train': 0.7611038484610617}
+12/24/2021 15:25:10 - INFO - codeparrot_training - Step 12616: {'lr': 0.00042694659338975296, 'samples': 6459904, 'steps': 12616, 'batch_loss/train': 0.7625792613252997}
+12/24/2021 15:25:21 - INFO - codeparrot_training - Step 12617: {'lr': 0.000426935457541723, 'samples': 6460416, 'steps': 12617, 'batch_loss/train': 0.8155375448986888}
+12/24/2021 15:25:32 - INFO - codeparrot_training - Step 12618: {'lr': 0.00042692432099026445, 'samples': 6460928, 'steps': 12618, 'batch_loss/train': 0.7241238900460303}
+12/24/2021 15:25:42 - INFO - codeparrot_training - Step 12619: {'lr': 0.00042691318373542164, 'samples': 6461440, 'steps': 12619, 'batch_loss/train': 0.9593733809888363}
+12/24/2021 15:25:54 - INFO - codeparrot_training - Step 12620: {'lr': 0.00042690204577723877, 'samples': 6461952, 'steps': 12620, 'batch_loss/train': 0.9320247764699161}
+12/24/2021 15:26:05 - INFO - codeparrot_training - Step 12621: {'lr': 0.00042689090711576025, 'samples': 6462464, 'steps': 12621, 'batch_loss/train': 0.7988232458010316}
+12/24/2021 15:26:16 - INFO - codeparrot_training - Step 12622: {'lr': 0.0004268797677510302, 'samples': 6462976, 'steps': 12622, 'batch_loss/train': 0.9186774916015565}
+12/24/2021 15:26:29 - INFO - codeparrot_training - Step 12623: {'lr': 0.00042686862768309295, 'samples': 6463488, 'steps': 12623, 'batch_loss/train': 0.8664492834359407}
+12/24/2021 15:26:40 - INFO - codeparrot_training - Step 12624: {'lr': 0.00042685748691199287, 'samples': 6464000, 'steps': 12624, 'batch_loss/train': 0.7460404895246029}
+12/24/2021 15:26:51 - INFO - codeparrot_training - Step 12625: {'lr': 0.00042684634543777424, 'samples': 6464512, 'steps': 12625, 'batch_loss/train': 0.92150027025491}
+12/24/2021 15:27:03 - INFO - codeparrot_training - Step 12626: {'lr': 0.0004268352032604812, 'samples': 6465024, 'steps': 12626, 'batch_loss/train': 0.8366102380678058}
+12/24/2021 15:27:14 - INFO - codeparrot_training - Step 12627: {'lr': 0.00042682406038015825, 'samples': 6465536, 'steps': 12627, 'batch_loss/train': 0.8040793659165502}
+12/24/2021 15:27:24 - INFO - codeparrot_training - Step 12628: {'lr': 0.0004268129167968496, 'samples': 6466048, 'steps': 12628, 'batch_loss/train': 0.8458579108119011}
+12/24/2021 15:27:35 - INFO - codeparrot_training - Step 12629: {'lr': 0.00042680177251059947, 'samples': 6466560, 'steps': 12629, 'batch_loss/train': 0.9221493825316429}
+12/24/2021 15:27:49 - INFO - codeparrot_training - Step 12630: {'lr': 0.00042679062752145236, 'samples': 6467072, 'steps': 12630, 'batch_loss/train': 2.394324777647853}
+12/24/2021 15:28:00 - INFO - codeparrot_training - Step 12631: {'lr': 0.0004267794818294525, 'samples': 6467584, 'steps': 12631, 'batch_loss/train': 0.8000651281327009}
+12/24/2021 15:28:10 - INFO - codeparrot_training - Step 12632: {'lr': 0.000426768335434644, 'samples': 6468096, 'steps': 12632, 'batch_loss/train': 0.8566823611035943}
+12/24/2021 15:28:22 - INFO - codeparrot_training - Step 12633: {'lr': 0.00042675718833707146, 'samples': 6468608, 'steps': 12633, 'batch_loss/train': 0.8347082762047648}
+12/24/2021 15:28:33 - INFO - codeparrot_training - Step 12634: {'lr': 0.00042674604053677905, 'samples': 6469120, 'steps': 12634, 'batch_loss/train': 0.8318511140532792}
+12/24/2021 15:28:44 - INFO - codeparrot_training - Step 12635: {'lr': 0.0004267348920338111, 'samples': 6469632, 'steps': 12635, 'batch_loss/train': 0.8622719384729862}
+12/24/2021 15:28:54 - INFO - codeparrot_training - Step 12636: {'lr': 0.00042672374282821203, 'samples': 6470144, 'steps': 12636, 'batch_loss/train': 0.7548525109887123}
+12/24/2021 15:29:06 - INFO - codeparrot_training - Step 12637: {'lr': 0.000426712592920026, 'samples': 6470656, 'steps': 12637, 'batch_loss/train': 0.8233505475800484}
+12/24/2021 15:29:17 - INFO - codeparrot_training - Step 12638: {'lr': 0.00042670144230929746, 'samples': 6471168, 'steps': 12638, 'batch_loss/train': 0.8472527214325964}
+12/24/2021 15:29:27 - INFO - codeparrot_training - Step 12639: {'lr': 0.0004266902909960707, 'samples': 6471680, 'steps': 12639, 'batch_loss/train': 0.9356502238661051}
+12/24/2021 15:29:41 - INFO - codeparrot_training - Step 12640: {'lr': 0.00042667913898039014, 'samples': 6472192, 'steps': 12640, 'batch_loss/train': 0.7816589353606105}
+12/24/2021 15:29:52 - INFO - codeparrot_training - Step 12641: {'lr': 0.0004266679862622999, 'samples': 6472704, 'steps': 12641, 'batch_loss/train': 0.8311442490667105}
+12/24/2021 15:30:03 - INFO - codeparrot_training - Step 12642: {'lr': 0.0004266568328418445, 'samples': 6473216, 'steps': 12642, 'batch_loss/train': 0.7273613173747435}
+12/24/2021 15:30:15 - INFO - codeparrot_training - Step 12643: {'lr': 0.0004266456787190682, 'samples': 6473728, 'steps': 12643, 'batch_loss/train': 0.9173296145163476}
+12/24/2021 15:30:26 - INFO - codeparrot_training - Step 12644: {'lr': 0.00042663452389401547, 'samples': 6474240, 'steps': 12644, 'batch_loss/train': 0.7772900313138962}
+12/24/2021 15:30:36 - INFO - codeparrot_training - Step 12645: {'lr': 0.00042662336836673056, 'samples': 6474752, 'steps': 12645, 'batch_loss/train': 1.0938143348321319}
+12/24/2021 15:30:50 - INFO - codeparrot_training - Step 12646: {'lr': 0.00042661221213725783, 'samples': 6475264, 'steps': 12646, 'batch_loss/train': 0.8102797737810761}
+12/24/2021 15:31:01 - INFO - codeparrot_training - Step 12647: {'lr': 0.0004266010552056416, 'samples': 6475776, 'steps': 12647, 'batch_loss/train': 0.849279472604394}
+12/24/2021 15:31:11 - INFO - codeparrot_training - Step 12648: {'lr': 0.00042658989757192624, 'samples': 6476288, 'steps': 12648, 'batch_loss/train': 1.0747971422970295}
+12/24/2021 15:31:22 - INFO - codeparrot_training - Step 12649: {'lr': 0.00042657873923615606, 'samples': 6476800, 'steps': 12649, 'batch_loss/train': 0.8088468257337809}
+12/24/2021 15:31:34 - INFO - codeparrot_training - Step 12650: {'lr': 0.0004265675801983756, 'samples': 6477312, 'steps': 12650, 'batch_loss/train': 0.8456621773075312}
+12/24/2021 15:31:45 - INFO - codeparrot_training - Step 12651: {'lr': 0.0004265564204586291, 'samples': 6477824, 'steps': 12651, 'batch_loss/train': 0.863393499981612}
+12/24/2021 15:31:55 - INFO - codeparrot_training - Step 12652: {'lr': 0.00042654526001696094, 'samples': 6478336, 'steps': 12652, 'batch_loss/train': 0.9086840711534023}
+12/24/2021 15:32:07 - INFO - codeparrot_training - Step 12653: {'lr': 0.00042653409887341543, 'samples': 6478848, 'steps': 12653, 'batch_loss/train': 0.7863477990031242}
+12/24/2021 15:32:18 - INFO - codeparrot_training - Step 12654: {'lr': 0.000426522937028037, 'samples': 6479360, 'steps': 12654, 'batch_loss/train': 0.820214862935245}
+12/24/2021 15:32:29 - INFO - codeparrot_training - Step 12655: {'lr': 0.0004265117744808701, 'samples': 6479872, 'steps': 12655, 'batch_loss/train': 0.8802738226950169}
+12/24/2021 15:32:42 - INFO - codeparrot_training - Step 12656: {'lr': 0.00042650061123195894, 'samples': 6480384, 'steps': 12656, 'batch_loss/train': 0.8391699083149433}
+12/24/2021 15:32:53 - INFO - codeparrot_training - Step 12657: {'lr': 0.0004264894472813481, 'samples': 6480896, 'steps': 12657, 'batch_loss/train': 0.8960793800652027}
+12/24/2021 15:33:04 - INFO - codeparrot_training - Step 12658: {'lr': 0.00042647828262908175, 'samples': 6481408, 'steps': 12658, 'batch_loss/train': 0.8040118655189872}
+12/24/2021 15:33:14 - INFO - codeparrot_training - Step 12659: {'lr': 0.00042646711727520445, 'samples': 6481920, 'steps': 12659, 'batch_loss/train': 0.8710431689396501}
+12/24/2021 15:33:27 - INFO - codeparrot_training - Step 12660: {'lr': 0.0004264559512197605, 'samples': 6482432, 'steps': 12660, 'batch_loss/train': 0.8073851075023413}
+12/24/2021 15:33:37 - INFO - codeparrot_training - Step 12661: {'lr': 0.00042644478446279426, 'samples': 6482944, 'steps': 12661, 'batch_loss/train': 0.8246556045487523}
+12/24/2021 15:33:48 - INFO - codeparrot_training - Step 12662: {'lr': 0.0004264336170043502, 'samples': 6483456, 'steps': 12662, 'batch_loss/train': 0.8643769966438413}
+12/24/2021 15:34:00 - INFO - codeparrot_training - Step 12663: {'lr': 0.0004264224488444728, 'samples': 6483968, 'steps': 12663, 'batch_loss/train': 0.8250672835856676}
+12/24/2021 15:34:11 - INFO - codeparrot_training - Step 12664: {'lr': 0.0004264112799832063, 'samples': 6484480, 'steps': 12664, 'batch_loss/train': 0.8980627553537488}
+12/24/2021 15:34:21 - INFO - codeparrot_training - Step 12665: {'lr': 0.0004264001104205951, 'samples': 6484992, 'steps': 12665, 'batch_loss/train': 0.8328432757407427}
+12/24/2021 15:34:33 - INFO - codeparrot_training - Step 12666: {'lr': 0.0004263889401566838, 'samples': 6485504, 'steps': 12666, 'batch_loss/train': 0.7941936503630131}
+12/24/2021 15:34:44 - INFO - codeparrot_training - Step 12667: {'lr': 0.0004263777691915166, 'samples': 6486016, 'steps': 12667, 'batch_loss/train': 0.7961399145424366}
+12/24/2021 15:34:54 - INFO - codeparrot_training - Step 12668: {'lr': 0.00042636659752513795, 'samples': 6486528, 'steps': 12668, 'batch_loss/train': 0.7109446451067924}
+12/24/2021 15:35:05 - INFO - codeparrot_training - Step 12669: {'lr': 0.00042635542515759235, 'samples': 6487040, 'steps': 12669, 'batch_loss/train': 0.8301319610327482}
+12/24/2021 15:35:19 - INFO - codeparrot_training - Step 12670: {'lr': 0.0004263442520889241, 'samples': 6487552, 'steps': 12670, 'batch_loss/train': 0.8594667594879866}
+12/24/2021 15:35:30 - INFO - codeparrot_training - Step 12671: {'lr': 0.0004263330783191778, 'samples': 6488064, 'steps': 12671, 'batch_loss/train': 0.8265599743463099}
+12/24/2021 15:35:40 - INFO - codeparrot_training - Step 12672: {'lr': 0.00042632190384839767, 'samples': 6488576, 'steps': 12672, 'batch_loss/train': 0.9004784114658833}
+12/24/2021 15:35:52 - INFO - codeparrot_training - Step 12673: {'lr': 0.00042631072867662837, 'samples': 6489088, 'steps': 12673, 'batch_loss/train': 0.8903949270024896}
+12/24/2021 15:36:03 - INFO - codeparrot_training - Step 12674: {'lr': 0.00042629955280391396, 'samples': 6489600, 'steps': 12674, 'batch_loss/train': 0.9640490128658712}
+12/24/2021 15:36:13 - INFO - codeparrot_training - Step 12675: {'lr': 0.0004262883762302993, 'samples': 6490112, 'steps': 12675, 'batch_loss/train': 0.7534837296698242}
+12/24/2021 15:36:26 - INFO - codeparrot_training - Step 12676: {'lr': 0.0004262771989558285, 'samples': 6490624, 'steps': 12676, 'batch_loss/train': 0.8838881365954876}
+12/24/2021 15:36:36 - INFO - codeparrot_training - Step 12677: {'lr': 0.00042626602098054615, 'samples': 6491136, 'steps': 12677, 'batch_loss/train': 0.8567611183971167}
+12/24/2021 15:36:47 - INFO - codeparrot_training - Step 12678: {'lr': 0.00042625484230449665, 'samples': 6491648, 'steps': 12678, 'batch_loss/train': 0.7626380105502903}
+12/24/2021 15:37:01 - INFO - codeparrot_training - Step 12679: {'lr': 0.00042624366292772447, 'samples': 6492160, 'steps': 12679, 'batch_loss/train': 0.6806810586713254}
+12/24/2021 15:37:12 - INFO - codeparrot_training - Step 12680: {'lr': 0.000426232482850274, 'samples': 6492672, 'steps': 12680, 'batch_loss/train': 0.7608084445819259}
+12/24/2021 15:37:22 - INFO - codeparrot_training - Step 12681: {'lr': 0.0004262213020721898, 'samples': 6493184, 'steps': 12681, 'batch_loss/train': 0.8114660084247589}
+12/24/2021 15:37:33 - INFO - codeparrot_training - Step 12682: {'lr': 0.0004262101205935162, 'samples': 6493696, 'steps': 12682, 'batch_loss/train': 0.6110063777305186}
+12/24/2021 15:37:45 - INFO - codeparrot_training - Step 12683: {'lr': 0.0004261989384142976, 'samples': 6494208, 'steps': 12683, 'batch_loss/train': 0.8294248105958104}
+12/24/2021 15:37:55 - INFO - codeparrot_training - Step 12684: {'lr': 0.00042618775553457866, 'samples': 6494720, 'steps': 12684, 'batch_loss/train': 0.7517662858590484}
+12/24/2021 15:38:06 - INFO - codeparrot_training - Step 12685: {'lr': 0.0004261765719544036, 'samples': 6495232, 'steps': 12685, 'batch_loss/train': 0.919594987295568}
+12/24/2021 15:38:20 - INFO - codeparrot_training - Step 12686: {'lr': 0.0004261653876738172, 'samples': 6495744, 'steps': 12686, 'batch_loss/train': 0.7763039005221799}
+12/24/2021 15:38:30 - INFO - codeparrot_training - Step 12687: {'lr': 0.00042615420269286367, 'samples': 6496256, 'steps': 12687, 'batch_loss/train': 0.8003615217749029}
+12/24/2021 15:38:41 - INFO - codeparrot_training - Step 12688: {'lr': 0.0004261430170115875, 'samples': 6496768, 'steps': 12688, 'batch_loss/train': 0.8178893560543656}
+12/24/2021 15:38:54 - INFO - codeparrot_training - Step 12689: {'lr': 0.0004261318306300332, 'samples': 6497280, 'steps': 12689, 'batch_loss/train': 0.8015596193727106}
+12/24/2021 15:39:04 - INFO - codeparrot_training - Step 12690: {'lr': 0.00042612064354824523, 'samples': 6497792, 'steps': 12690, 'batch_loss/train': 0.7825410077348351}
+12/24/2021 15:39:15 - INFO - codeparrot_training - Step 12691: {'lr': 0.00042610945576626813, 'samples': 6498304, 'steps': 12691, 'batch_loss/train': 1.1071297666057944}
+12/24/2021 15:39:25 - INFO - codeparrot_training - Step 12692: {'lr': 0.00042609826728414634, 'samples': 6498816, 'steps': 12692, 'batch_loss/train': 0.917801265604794}
+12/24/2021 15:39:37 - INFO - codeparrot_training - Step 12693: {'lr': 0.00042608707810192425, 'samples': 6499328, 'steps': 12693, 'batch_loss/train': 0.7874202290549874}
+12/24/2021 15:39:48 - INFO - codeparrot_training - Step 12694: {'lr': 0.00042607588821964653, 'samples': 6499840, 'steps': 12694, 'batch_loss/train': 0.8696433985605836}
+12/24/2021 15:39:59 - INFO - codeparrot_training - Step 12695: {'lr': 0.0004260646976373576, 'samples': 6500352, 'steps': 12695, 'batch_loss/train': 0.6950437125051394}
+12/24/2021 15:40:12 - INFO - codeparrot_training - Step 12696: {'lr': 0.00042605350635510175, 'samples': 6500864, 'steps': 12696, 'batch_loss/train': 0.8192175021395087}
+12/24/2021 15:40:23 - INFO - codeparrot_training - Step 12697: {'lr': 0.00042604231437292375, 'samples': 6501376, 'steps': 12697, 'batch_loss/train': 0.7752391751855612}
+12/24/2021 15:40:34 - INFO - codeparrot_training - Step 12698: {'lr': 0.0004260311216908679, 'samples': 6501888, 'steps': 12698, 'batch_loss/train': 0.7753578573465347}
+12/24/2021 15:40:46 - INFO - codeparrot_training - Step 12699: {'lr': 0.00042601992830897887, 'samples': 6502400, 'steps': 12699, 'batch_loss/train': 0.8408265884499997}
+12/24/2021 15:40:56 - INFO - codeparrot_training - Step 12700: {'lr': 0.00042600873422730094, 'samples': 6502912, 'steps': 12700, 'batch_loss/train': 0.6720321490429342}
+12/24/2021 15:41:07 - INFO - codeparrot_training - Step 12701: {'lr': 0.0004259975394458788, 'samples': 6503424, 'steps': 12701, 'batch_loss/train': 0.7840562369674444}
+12/24/2021 15:41:18 - INFO - codeparrot_training - Step 12702: {'lr': 0.000425986343964757, 'samples': 6503936, 'steps': 12702, 'batch_loss/train': 0.8313891720026731}
+12/24/2021 15:41:30 - INFO - codeparrot_training - Step 12703: {'lr': 0.0004259751477839798, 'samples': 6504448, 'steps': 12703, 'batch_loss/train': 0.9774435837753117}
+12/24/2021 15:41:40 - INFO - codeparrot_training - Step 12704: {'lr': 0.000425963950903592, 'samples': 6504960, 'steps': 12704, 'batch_loss/train': 0.8382281444501132}
+12/24/2021 15:41:51 - INFO - codeparrot_training - Step 12705: {'lr': 0.00042595275332363785, 'samples': 6505472, 'steps': 12705, 'batch_loss/train': 0.7529152799397707}
+12/24/2021 15:42:05 - INFO - codeparrot_training - Step 12706: {'lr': 0.000425941555044162, 'samples': 6505984, 'steps': 12706, 'batch_loss/train': 0.7596880234777927}
+12/24/2021 15:42:16 - INFO - codeparrot_training - Step 12707: {'lr': 0.00042593035606520904, 'samples': 6506496, 'steps': 12707, 'batch_loss/train': 0.8207313334569335}
+12/24/2021 15:42:26 - INFO - codeparrot_training - Step 12708: {'lr': 0.00042591915638682333, 'samples': 6507008, 'steps': 12708, 'batch_loss/train': 0.8979011261835694}
+12/24/2021 15:42:38 - INFO - codeparrot_training - Step 12709: {'lr': 0.00042590795600904954, 'samples': 6507520, 'steps': 12709, 'batch_loss/train': 0.6501489887014031}
+12/24/2021 15:42:49 - INFO - codeparrot_training - Step 12710: {'lr': 0.0004258967549319321, 'samples': 6508032, 'steps': 12710, 'batch_loss/train': 0.7392860548570752}
+12/24/2021 15:42:59 - INFO - codeparrot_training - Step 12711: {'lr': 0.00042588555315551557, 'samples': 6508544, 'steps': 12711, 'batch_loss/train': 0.9209254134912044}
+12/24/2021 15:43:12 - INFO - codeparrot_training - Step 12712: {'lr': 0.00042587435067984456, 'samples': 6509056, 'steps': 12712, 'batch_loss/train': 0.8230609287275001}
+12/24/2021 15:43:22 - INFO - codeparrot_training - Step 12713: {'lr': 0.00042586314750496344, 'samples': 6509568, 'steps': 12713, 'batch_loss/train': 0.7564549492672086}
+12/24/2021 15:43:33 - INFO - codeparrot_training - Step 12714: {'lr': 0.00042585194363091693, 'samples': 6510080, 'steps': 12714, 'batch_loss/train': 0.709659906104207}
+12/24/2021 15:43:44 - INFO - codeparrot_training - Step 12715: {'lr': 0.00042584073905774944, 'samples': 6510592, 'steps': 12715, 'batch_loss/train': 0.7618708619847894}
+12/24/2021 15:43:58 - INFO - codeparrot_training - Step 12716: {'lr': 0.0004258295337855056, 'samples': 6511104, 'steps': 12716, 'batch_loss/train': 0.8756120847538114}
+12/24/2021 15:44:08 - INFO - codeparrot_training - Step 12717: {'lr': 0.0004258183278142299, 'samples': 6511616, 'steps': 12717, 'batch_loss/train': 0.7428342083003372}
+12/24/2021 15:44:19 - INFO - codeparrot_training - Step 12718: {'lr': 0.000425807121143967, 'samples': 6512128, 'steps': 12718, 'batch_loss/train': 0.8353196093812585}
+12/24/2021 15:44:31 - INFO - codeparrot_training - Step 12719: {'lr': 0.00042579591377476123, 'samples': 6512640, 'steps': 12719, 'batch_loss/train': 0.8151398524641991}
+12/24/2021 15:44:42 - INFO - codeparrot_training - Step 12720: {'lr': 0.0004257847057066574, 'samples': 6513152, 'steps': 12720, 'batch_loss/train': 0.673821653239429}
+12/24/2021 15:44:52 - INFO - codeparrot_training - Step 12721: {'lr': 0.0004257734969396999, 'samples': 6513664, 'steps': 12721, 'batch_loss/train': 0.8814121698960662}
+12/24/2021 15:45:04 - INFO - codeparrot_training - Step 12722: {'lr': 0.0004257622874739333, 'samples': 6514176, 'steps': 12722, 'batch_loss/train': 0.7826341334730387}
+12/24/2021 15:45:15 - INFO - codeparrot_training - Step 12723: {'lr': 0.0004257510773094023, 'samples': 6514688, 'steps': 12723, 'batch_loss/train': 0.8300854614935815}
+12/24/2021 15:45:26 - INFO - codeparrot_training - Step 12724: {'lr': 0.00042573986644615133, 'samples': 6515200, 'steps': 12724, 'batch_loss/train': 0.7651649974286556}
+12/24/2021 15:45:36 - INFO - codeparrot_training - Step 12725: {'lr': 0.000425728654884225, 'samples': 6515712, 'steps': 12725, 'batch_loss/train': 0.9484895491041243}
+12/24/2021 15:45:50 - INFO - codeparrot_training - Step 12726: {'lr': 0.0004257174426236679, 'samples': 6516224, 'steps': 12726, 'batch_loss/train': 0.8161309584975243}
+12/24/2021 15:46:01 - INFO - codeparrot_training - Step 12727: {'lr': 0.0004257062296645247, 'samples': 6516736, 'steps': 12727, 'batch_loss/train': 0.7853889411780983}
+12/24/2021 15:46:11 - INFO - codeparrot_training - Step 12728: {'lr': 0.0004256950160068397, 'samples': 6517248, 'steps': 12728, 'batch_loss/train': 1.9278644304722548}
+12/24/2021 15:46:23 - INFO - codeparrot_training - Step 12729: {'lr': 0.00042568380165065774, 'samples': 6517760, 'steps': 12729, 'batch_loss/train': 0.8399738287553191}
+12/24/2021 15:46:34 - INFO - codeparrot_training - Step 12730: {'lr': 0.00042567258659602326, 'samples': 6518272, 'steps': 12730, 'batch_loss/train': 0.8110517105087638}
+12/24/2021 15:46:45 - INFO - codeparrot_training - Step 12731: {'lr': 0.00042566137084298103, 'samples': 6518784, 'steps': 12731, 'batch_loss/train': 0.8210046254098415}
+12/24/2021 15:46:58 - INFO - codeparrot_training - Step 12732: {'lr': 0.0004256501543915754, 'samples': 6519296, 'steps': 12732, 'batch_loss/train': 0.8385020447894931}
+12/24/2021 15:47:09 - INFO - codeparrot_training - Step 12733: {'lr': 0.0004256389372418511, 'samples': 6519808, 'steps': 12733, 'batch_loss/train': 0.909946602769196}
+12/24/2021 15:47:20 - INFO - codeparrot_training - Step 12734: {'lr': 0.0004256277193938528, 'samples': 6520320, 'steps': 12734, 'batch_loss/train': 0.8419289598241448}
+12/24/2021 15:47:30 - INFO - codeparrot_training - Step 12735: {'lr': 0.00042561650084762496, 'samples': 6520832, 'steps': 12735, 'batch_loss/train': 0.8131282413378358}
+12/24/2021 15:47:42 - INFO - codeparrot_training - Step 12736: {'lr': 0.00042560528160321217, 'samples': 6521344, 'steps': 12736, 'batch_loss/train': 0.8101909919641912}
+12/24/2021 15:47:53 - INFO - codeparrot_training - Step 12737: {'lr': 0.00042559406166065906, 'samples': 6521856, 'steps': 12737, 'batch_loss/train': 0.7043209981638938}
+12/24/2021 15:48:03 - INFO - codeparrot_training - Step 12738: {'lr': 0.00042558284102001034, 'samples': 6522368, 'steps': 12738, 'batch_loss/train': 0.7476955850142986}
+12/24/2021 15:48:16 - INFO - codeparrot_training - Step 12739: {'lr': 0.0004255716196813105, 'samples': 6522880, 'steps': 12739, 'batch_loss/train': 0.9167607808485627}
+12/24/2021 15:48:26 - INFO - codeparrot_training - Step 12740: {'lr': 0.00042556039764460427, 'samples': 6523392, 'steps': 12740, 'batch_loss/train': 0.7797140325419605}
+12/24/2021 15:48:37 - INFO - codeparrot_training - Step 12741: {'lr': 0.00042554917490993604, 'samples': 6523904, 'steps': 12741, 'batch_loss/train': 0.7089812071062624}
+12/24/2021 15:48:51 - INFO - codeparrot_training - Step 12742: {'lr': 0.00042553795147735077, 'samples': 6524416, 'steps': 12742, 'batch_loss/train': 0.6982485051266849}
+12/24/2021 15:49:02 - INFO - codeparrot_training - Step 12743: {'lr': 0.0004255267273468927, 'samples': 6524928, 'steps': 12743, 'batch_loss/train': 0.77466229069978}
+12/24/2021 15:49:13 - INFO - codeparrot_training - Step 12744: {'lr': 0.00042551550251860676, 'samples': 6525440, 'steps': 12744, 'batch_loss/train': 0.7350398725830019}
+12/24/2021 15:49:23 - INFO - codeparrot_training - Step 12745: {'lr': 0.00042550427699253736, 'samples': 6525952, 'steps': 12745, 'batch_loss/train': 0.8042952544055879}
+12/24/2021 15:49:35 - INFO - codeparrot_training - Step 12746: {'lr': 0.00042549305076872927, 'samples': 6526464, 'steps': 12746, 'batch_loss/train': 1.0275668017566204}
+12/24/2021 15:49:46 - INFO - codeparrot_training - Step 12747: {'lr': 0.0004254818238472271, 'samples': 6526976, 'steps': 12747, 'batch_loss/train': 0.8515878701582551}
+12/24/2021 15:49:57 - INFO - codeparrot_training - Step 12748: {'lr': 0.00042547059622807543, 'samples': 6527488, 'steps': 12748, 'batch_loss/train': 0.8016918962821364}
+12/24/2021 15:50:10 - INFO - codeparrot_training - Step 12749: {'lr': 0.000425459367911319, 'samples': 6528000, 'steps': 12749, 'batch_loss/train': 0.7291825793217868}
+12/24/2021 15:50:21 - INFO - codeparrot_training - Step 12750: {'lr': 0.0004254481388970022, 'samples': 6528512, 'steps': 12750, 'batch_loss/train': 0.788270459510386}
+12/24/2021 15:50:32 - INFO - codeparrot_training - Step 12751: {'lr': 0.00042543690918517, 'samples': 6529024, 'steps': 12751, 'batch_loss/train': 0.814669125713408}
+12/24/2021 15:50:44 - INFO - codeparrot_training - Step 12752: {'lr': 0.00042542567877586684, 'samples': 6529536, 'steps': 12752, 'batch_loss/train': 0.8347485233098269}
+12/24/2021 15:50:55 - INFO - codeparrot_training - Step 12753: {'lr': 0.0004254144476691374, 'samples': 6530048, 'steps': 12753, 'batch_loss/train': 0.7812588871456683}
+12/24/2021 15:51:05 - INFO - codeparrot_training - Step 12754: {'lr': 0.0004254032158650264, 'samples': 6530560, 'steps': 12754, 'batch_loss/train': 0.8233502148650587}
+12/24/2021 15:51:16 - INFO - codeparrot_training - Step 12755: {'lr': 0.00042539198336357845, 'samples': 6531072, 'steps': 12755, 'batch_loss/train': 0.5994498632499017}
+12/24/2021 15:51:28 - INFO - codeparrot_training - Step 12756: {'lr': 0.0004253807501648381, 'samples': 6531584, 'steps': 12756, 'batch_loss/train': 0.8200299479067326}
+12/24/2021 15:51:38 - INFO - codeparrot_training - Step 12757: {'lr': 0.00042536951626885025, 'samples': 6532096, 'steps': 12757, 'batch_loss/train': 0.8660965692251921}
+12/24/2021 15:51:49 - INFO - codeparrot_training - Step 12758: {'lr': 0.0004253582816756593, 'samples': 6532608, 'steps': 12758, 'batch_loss/train': 0.7224141941405833}
+12/24/2021 15:52:03 - INFO - codeparrot_training - Step 12759: {'lr': 0.00042534704638531005, 'samples': 6533120, 'steps': 12759, 'batch_loss/train': 0.8657286437228322}
+12/24/2021 15:52:14 - INFO - codeparrot_training - Step 12760: {'lr': 0.0004253358103978472, 'samples': 6533632, 'steps': 12760, 'batch_loss/train': 0.7427330582868308}
+12/24/2021 15:52:24 - INFO - codeparrot_training - Step 12761: {'lr': 0.00042532457371331534, 'samples': 6534144, 'steps': 12761, 'batch_loss/train': 0.725032807327807}
+12/24/2021 15:52:35 - INFO - codeparrot_training - Step 12762: {'lr': 0.0004253133363317592, 'samples': 6534656, 'steps': 12762, 'batch_loss/train': 0.9207190806046128}
+12/24/2021 15:52:47 - INFO - codeparrot_training - Step 12763: {'lr': 0.0004253020982532234, 'samples': 6535168, 'steps': 12763, 'batch_loss/train': 0.7935615945607424}
+12/24/2021 15:52:57 - INFO - codeparrot_training - Step 12764: {'lr': 0.0004252908594777527, 'samples': 6535680, 'steps': 12764, 'batch_loss/train': 0.7802359769120812}
+12/24/2021 15:53:08 - INFO - codeparrot_training - Step 12765: {'lr': 0.0004252796200053917, 'samples': 6536192, 'steps': 12765, 'batch_loss/train': 0.8010279815644026}
+12/24/2021 15:53:20 - INFO - codeparrot_training - Step 12766: {'lr': 0.0004252683798361851, 'samples': 6536704, 'steps': 12766, 'batch_loss/train': 0.8574970979243517}
+12/24/2021 15:53:31 - INFO - codeparrot_training - Step 12767: {'lr': 0.0004252571389701776, 'samples': 6537216, 'steps': 12767, 'batch_loss/train': 0.8903798819519579}
+12/24/2021 15:53:41 - INFO - codeparrot_training - Step 12768: {'lr': 0.00042524589740741394, 'samples': 6537728, 'steps': 12768, 'batch_loss/train': 0.8013594676740468}
+12/24/2021 15:53:56 - INFO - codeparrot_training - Step 12769: {'lr': 0.0004252346551479387, 'samples': 6538240, 'steps': 12769, 'batch_loss/train': 0.7794401561841369}
+12/24/2021 15:54:06 - INFO - codeparrot_training - Step 12770: {'lr': 0.0004252234121917966, 'samples': 6538752, 'steps': 12770, 'batch_loss/train': 1.5623252354562283}
+12/24/2021 15:54:17 - INFO - codeparrot_training - Step 12771: {'lr': 0.0004252121685390325, 'samples': 6539264, 'steps': 12771, 'batch_loss/train': 0.7665633629076183}
+12/24/2021 15:54:29 - INFO - codeparrot_training - Step 12772: {'lr': 0.0004252009241896909, 'samples': 6539776, 'steps': 12772, 'batch_loss/train': 0.8329424569383264}
+12/24/2021 15:54:40 - INFO - codeparrot_training - Step 12773: {'lr': 0.00042518967914381657, 'samples': 6540288, 'steps': 12773, 'batch_loss/train': 0.8265408724546432}
+12/24/2021 15:54:50 - INFO - codeparrot_training - Step 12774: {'lr': 0.0004251784334014542, 'samples': 6540800, 'steps': 12774, 'batch_loss/train': 0.8363358052447438}
+12/24/2021 15:55:01 - INFO - codeparrot_training - Step 12775: {'lr': 0.00042516718696264865, 'samples': 6541312, 'steps': 12775, 'batch_loss/train': 0.9082498261705041}
+12/24/2021 15:55:13 - INFO - codeparrot_training - Step 12776: {'lr': 0.00042515593982744436, 'samples': 6541824, 'steps': 12776, 'batch_loss/train': 0.8303805682808161}
+12/24/2021 15:55:24 - INFO - codeparrot_training - Step 12777: {'lr': 0.00042514469199588634, 'samples': 6542336, 'steps': 12777, 'batch_loss/train': 0.39812382258241996}
+12/24/2021 15:55:34 - INFO - codeparrot_training - Step 12778: {'lr': 0.00042513344346801904, 'samples': 6542848, 'steps': 12778, 'batch_loss/train': 0.9018856538459659}
+12/24/2021 15:55:48 - INFO - codeparrot_training - Step 12779: {'lr': 0.0004251221942438873, 'samples': 6543360, 'steps': 12779, 'batch_loss/train': 0.8950139163061976}
+12/24/2021 15:55:59 - INFO - codeparrot_training - Step 12780: {'lr': 0.00042511094432353584, 'samples': 6543872, 'steps': 12780, 'batch_loss/train': 0.8873281383421272}
+12/24/2021 15:56:10 - INFO - codeparrot_training - Step 12781: {'lr': 0.00042509969370700944, 'samples': 6544384, 'steps': 12781, 'batch_loss/train': 0.9058304224163294}
+12/24/2021 15:56:22 - INFO - codeparrot_training - Step 12782: {'lr': 0.0004250884423943527, 'samples': 6544896, 'steps': 12782, 'batch_loss/train': 0.7441819603554904}
+12/24/2021 15:56:32 - INFO - codeparrot_training - Step 12783: {'lr': 0.00042507719038561054, 'samples': 6545408, 'steps': 12783, 'batch_loss/train': 0.7923362869769335}
+12/24/2021 15:56:43 - INFO - codeparrot_training - Step 12784: {'lr': 0.0004250659376808275, 'samples': 6545920, 'steps': 12784, 'batch_loss/train': 0.8717459570616484}
+12/24/2021 15:56:54 - INFO - codeparrot_training - Step 12785: {'lr': 0.00042505468428004833, 'samples': 6546432, 'steps': 12785, 'batch_loss/train': 0.8286224843468517}
+12/24/2021 15:57:06 - INFO - codeparrot_training - Step 12786: {'lr': 0.000425043430183318, 'samples': 6546944, 'steps': 12786, 'batch_loss/train': 0.794399737729691}
+12/24/2021 15:57:16 - INFO - codeparrot_training - Step 12787: {'lr': 0.000425032175390681, 'samples': 6547456, 'steps': 12787, 'batch_loss/train': 0.802183295134455}
+12/24/2021 15:57:27 - INFO - codeparrot_training - Step 12788: {'lr': 0.00042502091990218206, 'samples': 6547968, 'steps': 12788, 'batch_loss/train': 0.9288619412109256}
+12/24/2021 15:57:41 - INFO - codeparrot_training - Step 12789: {'lr': 0.00042500966371786616, 'samples': 6548480, 'steps': 12789, 'batch_loss/train': 0.7333228255156428}
+12/24/2021 15:57:52 - INFO - codeparrot_training - Step 12790: {'lr': 0.00042499840683777793, 'samples': 6548992, 'steps': 12790, 'batch_loss/train': 0.8084307704120874}
+12/24/2021 15:58:02 - INFO - codeparrot_training - Step 12791: {'lr': 0.00042498714926196205, 'samples': 6549504, 'steps': 12791, 'batch_loss/train': 0.8325918009504676}
+12/24/2021 15:58:14 - INFO - codeparrot_training - Step 12792: {'lr': 0.0004249758909904633, 'samples': 6550016, 'steps': 12792, 'batch_loss/train': 0.6749343434348702}
+12/24/2021 15:58:25 - INFO - codeparrot_training - Step 12793: {'lr': 0.0004249646320233265, 'samples': 6550528, 'steps': 12793, 'batch_loss/train': 0.7739299070090055}
+12/24/2021 15:58:36 - INFO - codeparrot_training - Step 12794: {'lr': 0.0004249533723605964, 'samples': 6551040, 'steps': 12794, 'batch_loss/train': 0.8691810043528676}
+12/24/2021 15:58:46 - INFO - codeparrot_training - Step 12795: {'lr': 0.0004249421120023177, 'samples': 6551552, 'steps': 12795, 'batch_loss/train': 0.8210790152661502}
+12/24/2021 15:58:59 - INFO - codeparrot_training - Step 12796: {'lr': 0.00042493085094853534, 'samples': 6552064, 'steps': 12796, 'batch_loss/train': 0.8595274081453681}
+12/24/2021 15:59:10 - INFO - codeparrot_training - Step 12797: {'lr': 0.00042491958919929385, 'samples': 6552576, 'steps': 12797, 'batch_loss/train': 0.8257254608906806}
+12/24/2021 15:59:20 - INFO - codeparrot_training - Step 12798: {'lr': 0.0004249083267546382, 'samples': 6553088, 'steps': 12798, 'batch_loss/train': 1.073230025358498}
+12/24/2021 15:59:34 - INFO - codeparrot_training - Step 12799: {'lr': 0.0004248970636146131, 'samples': 6553600, 'steps': 12799, 'batch_loss/train': 1.1721860617399216}
+12/24/2021 15:59:45 - INFO - codeparrot_training - Step 12800: {'lr': 0.0004248857997792632, 'samples': 6554112, 'steps': 12800, 'batch_loss/train': 0.8692452553659678}
+12/24/2021 15:59:55 - INFO - codeparrot_training - Step 12801: {'lr': 0.0004248745352486335, 'samples': 6554624, 'steps': 12801, 'batch_loss/train': 0.8132470529526472}
+12/24/2021 16:00:06 - INFO - codeparrot_training - Step 12802: {'lr': 0.0004248632700227686, 'samples': 6555136, 'steps': 12802, 'batch_loss/train': 0.8837095377966762}
+12/24/2021 16:00:18 - INFO - codeparrot_training - Step 12803: {'lr': 0.0004248520041017134, 'samples': 6555648, 'steps': 12803, 'batch_loss/train': 0.871555722784251}
+12/24/2021 16:00:29 - INFO - codeparrot_training - Step 12804: {'lr': 0.0004248407374855127, 'samples': 6556160, 'steps': 12804, 'batch_loss/train': 0.7545436061918736}
+12/24/2021 16:00:40 - INFO - codeparrot_training - Step 12805: {'lr': 0.00042482947017421125, 'samples': 6556672, 'steps': 12805, 'batch_loss/train': 0.8418841515667737}
+12/24/2021 16:00:53 - INFO - codeparrot_training - Step 12806: {'lr': 0.0004248182021678538, 'samples': 6557184, 'steps': 12806, 'batch_loss/train': 0.9695285316556692}
+12/24/2021 16:01:04 - INFO - codeparrot_training - Step 12807: {'lr': 0.0004248069334664851, 'samples': 6557696, 'steps': 12807, 'batch_loss/train': 0.7371480215806514}
+12/24/2021 16:01:15 - INFO - codeparrot_training - Step 12808: {'lr': 0.0004247956640701502, 'samples': 6558208, 'steps': 12808, 'batch_loss/train': 0.8456141427159309}
+12/24/2021 16:01:27 - INFO - codeparrot_training - Step 12809: {'lr': 0.0004247843939788936, 'samples': 6558720, 'steps': 12809, 'batch_loss/train': 0.8769786106422544}
+12/24/2021 16:01:37 - INFO - codeparrot_training - Step 12810: {'lr': 0.00042477312319276033, 'samples': 6559232, 'steps': 12810, 'batch_loss/train': 0.7933020000346005}
+12/24/2021 16:01:48 - INFO - codeparrot_training - Step 12811: {'lr': 0.0004247618517117951, 'samples': 6559744, 'steps': 12811, 'batch_loss/train': 0.7833170474041253}
+12/24/2021 16:02:00 - INFO - codeparrot_training - Step 12812: {'lr': 0.00042475057953604274, 'samples': 6560256, 'steps': 12812, 'batch_loss/train': 0.8756840396672487}
+12/24/2021 16:02:10 - INFO - codeparrot_training - Step 12813: {'lr': 0.00042473930666554803, 'samples': 6560768, 'steps': 12813, 'batch_loss/train': 0.875840462744236}
+12/24/2021 16:02:21 - INFO - codeparrot_training - Step 12814: {'lr': 0.0004247280331003559, 'samples': 6561280, 'steps': 12814, 'batch_loss/train': 0.8746453253552318}
+12/24/2021 16:02:32 - INFO - codeparrot_training - Step 12815: {'lr': 0.000424716758840511, 'samples': 6561792, 'steps': 12815, 'batch_loss/train': 0.9115716628730297}
+12/24/2021 16:02:44 - INFO - codeparrot_training - Step 12816: {'lr': 0.0004247054838860582, 'samples': 6562304, 'steps': 12816, 'batch_loss/train': 0.7310405457392335}
+12/24/2021 16:02:54 - INFO - codeparrot_training - Step 12817: {'lr': 0.0004246942082370424, 'samples': 6562816, 'steps': 12817, 'batch_loss/train': 0.7861380120739341}
+12/24/2021 16:03:05 - INFO - codeparrot_training - Step 12818: {'lr': 0.00042468293189350844, 'samples': 6563328, 'steps': 12818, 'batch_loss/train': 0.8692785315215588}
+12/24/2021 16:03:19 - INFO - codeparrot_training - Step 12819: {'lr': 0.0004246716548555011, 'samples': 6563840, 'steps': 12819, 'batch_loss/train': 0.7535063019022346}
+12/24/2021 16:03:29 - INFO - codeparrot_training - Step 12820: {'lr': 0.0004246603771230651, 'samples': 6564352, 'steps': 12820, 'batch_loss/train': 0.7090701311826706}
+12/24/2021 16:03:40 - INFO - codeparrot_training - Step 12821: {'lr': 0.00042464909869624544, 'samples': 6564864, 'steps': 12821, 'batch_loss/train': 0.8412591709056869}
+12/24/2021 16:03:52 - INFO - codeparrot_training - Step 12822: {'lr': 0.00042463781957508695, 'samples': 6565376, 'steps': 12822, 'batch_loss/train': 0.7924729147925973}
+12/24/2021 16:04:03 - INFO - codeparrot_training - Step 12823: {'lr': 0.0004246265397596345, 'samples': 6565888, 'steps': 12823, 'batch_loss/train': 0.6617266838438809}
+12/24/2021 16:04:14 - INFO - codeparrot_training - Step 12824: {'lr': 0.0004246152592499327, 'samples': 6566400, 'steps': 12824, 'batch_loss/train': 0.7435141829773784}
+12/24/2021 16:04:24 - INFO - codeparrot_training - Step 12825: {'lr': 0.00042460397804602667, 'samples': 6566912, 'steps': 12825, 'batch_loss/train': 0.887202775105834}
+12/24/2021 16:04:36 - INFO - codeparrot_training - Step 12826: {'lr': 0.00042459269614796117, 'samples': 6567424, 'steps': 12826, 'batch_loss/train': 0.9623308554291725}
+12/24/2021 16:04:47 - INFO - codeparrot_training - Step 12827: {'lr': 0.0004245814135557809, 'samples': 6567936, 'steps': 12827, 'batch_loss/train': 0.8751085568219423}
+12/24/2021 16:04:57 - INFO - codeparrot_training - Step 12828: {'lr': 0.00042457013026953093, 'samples': 6568448, 'steps': 12828, 'batch_loss/train': 0.8285783343017101}
+12/24/2021 16:05:11 - INFO - codeparrot_training - Step 12829: {'lr': 0.00042455884628925613, 'samples': 6568960, 'steps': 12829, 'batch_loss/train': 0.7740848795510828}
+12/24/2021 16:05:22 - INFO - codeparrot_training - Step 12830: {'lr': 0.00042454756161500114, 'samples': 6569472, 'steps': 12830, 'batch_loss/train': 0.7670541357947513}
+12/24/2021 16:05:33 - INFO - codeparrot_training - Step 12831: {'lr': 0.000424536276246811, 'samples': 6569984, 'steps': 12831, 'batch_loss/train': 0.6500386586412787}
+12/24/2021 16:05:45 - INFO - codeparrot_training - Step 12832: {'lr': 0.00042452499018473056, 'samples': 6570496, 'steps': 12832, 'batch_loss/train': 0.7886459876317531}
+12/24/2021 16:05:56 - INFO - codeparrot_training - Step 12833: {'lr': 0.0004245137034288046, 'samples': 6571008, 'steps': 12833, 'batch_loss/train': 0.8753083618357778}
+12/24/2021 16:06:06 - INFO - codeparrot_training - Step 12834: {'lr': 0.00042450241597907806, 'samples': 6571520, 'steps': 12834, 'batch_loss/train': 0.8468303941190243}
+12/24/2021 16:06:17 - INFO - codeparrot_training - Step 12835: {'lr': 0.00042449112783559577, 'samples': 6572032, 'steps': 12835, 'batch_loss/train': 0.7751929583027959}
+12/24/2021 16:06:31 - INFO - codeparrot_training - Step 12836: {'lr': 0.0004244798389984027, 'samples': 6572544, 'steps': 12836, 'batch_loss/train': 0.7530256072059274}
+12/24/2021 16:06:41 - INFO - codeparrot_training - Step 12837: {'lr': 0.0004244685494675437, 'samples': 6573056, 'steps': 12837, 'batch_loss/train': 0.5218226362485439}
+12/24/2021 16:06:52 - INFO - codeparrot_training - Step 12838: {'lr': 0.00042445725924306353, 'samples': 6573568, 'steps': 12838, 'batch_loss/train': 0.7315205556806177}
+12/24/2021 16:07:04 - INFO - codeparrot_training - Step 12839: {'lr': 0.0004244459683250073, 'samples': 6574080, 'steps': 12839, 'batch_loss/train': 0.71277996012941}
+12/24/2021 16:07:15 - INFO - codeparrot_training - Step 12840: {'lr': 0.00042443467671341963, 'samples': 6574592, 'steps': 12840, 'batch_loss/train': 0.7733085071668029}
+12/24/2021 16:07:25 - INFO - codeparrot_training - Step 12841: {'lr': 0.0004244233844083456, 'samples': 6575104, 'steps': 12841, 'batch_loss/train': 0.8253549213986844}
+12/24/2021 16:07:37 - INFO - codeparrot_training - Step 12842: {'lr': 0.00042441209140983005, 'samples': 6575616, 'steps': 12842, 'batch_loss/train': 0.857629369944334}
+12/24/2021 16:07:48 - INFO - codeparrot_training - Step 12843: {'lr': 0.00042440079771791783, 'samples': 6576128, 'steps': 12843, 'batch_loss/train': 0.7988179917447269}
+12/24/2021 16:07:58 - INFO - codeparrot_training - Step 12844: {'lr': 0.00042438950333265404, 'samples': 6576640, 'steps': 12844, 'batch_loss/train': 0.8076379294507205}
+12/24/2021 16:08:09 - INFO - codeparrot_training - Step 12845: {'lr': 0.0004243782082540833, 'samples': 6577152, 'steps': 12845, 'batch_loss/train': 0.7710771028650925}
+12/24/2021 16:08:23 - INFO - codeparrot_training - Step 12846: {'lr': 0.0004243669124822507, 'samples': 6577664, 'steps': 12846, 'batch_loss/train': 0.5990145090036094}
+12/24/2021 16:08:34 - INFO - codeparrot_training - Step 12847: {'lr': 0.0004243556160172011, 'samples': 6578176, 'steps': 12847, 'batch_loss/train': 0.8161477211397141}
+12/24/2021 16:08:44 - INFO - codeparrot_training - Step 12848: {'lr': 0.0004243443188589793, 'samples': 6578688, 'steps': 12848, 'batch_loss/train': 0.7905095323221758}
+12/24/2021 16:08:57 - INFO - codeparrot_training - Step 12849: {'lr': 0.00042433302100763047, 'samples': 6579200, 'steps': 12849, 'batch_loss/train': 0.8251441931352019}
+12/24/2021 16:09:08 - INFO - codeparrot_training - Step 12850: {'lr': 0.00042432172246319926, 'samples': 6579712, 'steps': 12850, 'batch_loss/train': 0.8701100486796349}
+12/24/2021 16:09:18 - INFO - codeparrot_training - Step 12851: {'lr': 0.0004243104232257308, 'samples': 6580224, 'steps': 12851, 'batch_loss/train': 0.9728533320594579}
+12/24/2021 16:09:30 - INFO - codeparrot_training - Step 12852: {'lr': 0.0004242991232952699, 'samples': 6580736, 'steps': 12852, 'batch_loss/train': 0.8231268348172307}
+12/24/2021 16:09:41 - INFO - codeparrot_training - Step 12853: {'lr': 0.0004242878226718614, 'samples': 6581248, 'steps': 12853, 'batch_loss/train': 0.8407412227243185}
+12/24/2021 16:09:51 - INFO - codeparrot_training - Step 12854: {'lr': 0.0004242765213555504, 'samples': 6581760, 'steps': 12854, 'batch_loss/train': 0.7935853274539113}
+12/24/2021 16:10:02 - INFO - codeparrot_training - Step 12855: {'lr': 0.0004242652193463817, 'samples': 6582272, 'steps': 12855, 'batch_loss/train': 0.7893967612180859}
+12/24/2021 16:10:14 - INFO - codeparrot_training - Step 12856: {'lr': 0.0004242539166444004, 'samples': 6582784, 'steps': 12856, 'batch_loss/train': 0.8717006323859096}
+12/24/2021 16:10:25 - INFO - codeparrot_training - Step 12857: {'lr': 0.00042424261324965117, 'samples': 6583296, 'steps': 12857, 'batch_loss/train': 0.7725236427504569}
+12/24/2021 16:10:35 - INFO - codeparrot_training - Step 12858: {'lr': 0.0004242313091621792, 'samples': 6583808, 'steps': 12858, 'batch_loss/train': 0.8630127932410687}
+12/24/2021 16:10:49 - INFO - codeparrot_training - Step 12859: {'lr': 0.00042422000438202935, 'samples': 6584320, 'steps': 12859, 'batch_loss/train': 0.8358451439999044}
+12/24/2021 16:11:00 - INFO - codeparrot_training - Step 12860: {'lr': 0.00042420869890924653, 'samples': 6584832, 'steps': 12860, 'batch_loss/train': 0.8723146729171276}
+12/24/2021 16:11:10 - INFO - codeparrot_training - Step 12861: {'lr': 0.0004241973927438757, 'samples': 6585344, 'steps': 12861, 'batch_loss/train': 0.9047963423654437}
+12/24/2021 16:11:23 - INFO - codeparrot_training - Step 12862: {'lr': 0.0004241860858859618, 'samples': 6585856, 'steps': 12862, 'batch_loss/train': 0.8510332745499909}
+12/24/2021 16:11:34 - INFO - codeparrot_training - Step 12863: {'lr': 0.00042417477833554975, 'samples': 6586368, 'steps': 12863, 'batch_loss/train': 0.645011093467474}
+12/24/2021 16:11:45 - INFO - codeparrot_training - Step 12864: {'lr': 0.00042416347009268464, 'samples': 6586880, 'steps': 12864, 'batch_loss/train': 0.6720038597122766}
+12/24/2021 16:11:55 - INFO - codeparrot_training - Step 12865: {'lr': 0.00042415216115741127, 'samples': 6587392, 'steps': 12865, 'batch_loss/train': 1.670983268879354}
+12/24/2021 16:12:09 - INFO - codeparrot_training - Step 12866: {'lr': 0.0004241408515297747, 'samples': 6587904, 'steps': 12866, 'batch_loss/train': 0.8908951254561543}
+12/24/2021 16:12:20 - INFO - codeparrot_training - Step 12867: {'lr': 0.00042412954120981983, 'samples': 6588416, 'steps': 12867, 'batch_loss/train': 0.7524021058343351}
+12/24/2021 16:12:30 - INFO - codeparrot_training - Step 12868: {'lr': 0.00042411823019759164, 'samples': 6588928, 'steps': 12868, 'batch_loss/train': 0.7653742488473654}
+12/24/2021 16:12:42 - INFO - codeparrot_training - Step 12869: {'lr': 0.0004241069184931351, 'samples': 6589440, 'steps': 12869, 'batch_loss/train': 0.7920643562683836}
+12/24/2021 16:12:53 - INFO - codeparrot_training - Step 12870: {'lr': 0.00042409560609649524, 'samples': 6589952, 'steps': 12870, 'batch_loss/train': 0.7942575979977846}
+12/24/2021 16:13:04 - INFO - codeparrot_training - Step 12871: {'lr': 0.00042408429300771697, 'samples': 6590464, 'steps': 12871, 'batch_loss/train': 0.8007700052112341}
+12/24/2021 16:13:16 - INFO - codeparrot_training - Step 12872: {'lr': 0.00042407297922684523, 'samples': 6590976, 'steps': 12872, 'batch_loss/train': 0.8388366277795285}
+12/24/2021 16:13:27 - INFO - codeparrot_training - Step 12873: {'lr': 0.0004240616647539252, 'samples': 6591488, 'steps': 12873, 'batch_loss/train': 0.8070039581507444}
+12/24/2021 16:13:37 - INFO - codeparrot_training - Step 12874: {'lr': 0.0004240503495890015, 'samples': 6592000, 'steps': 12874, 'batch_loss/train': 0.8159436276182532}
+12/24/2021 16:13:48 - INFO - codeparrot_training - Step 12875: {'lr': 0.0004240390337321195, 'samples': 6592512, 'steps': 12875, 'batch_loss/train': 0.7678877813741565}
+12/24/2021 16:14:03 - INFO - codeparrot_training - Step 12876: {'lr': 0.0004240277171833239, 'samples': 6593024, 'steps': 12876, 'batch_loss/train': 0.8536263089627028}
+12/24/2021 16:14:13 - INFO - codeparrot_training - Step 12877: {'lr': 0.0004240163999426599, 'samples': 6593536, 'steps': 12877, 'batch_loss/train': 1.0798377469182014}
+12/24/2021 16:14:24 - INFO - codeparrot_training - Step 12878: {'lr': 0.0004240050820101724, 'samples': 6594048, 'steps': 12878, 'batch_loss/train': 0.8909198241308331}
+12/24/2021 16:14:36 - INFO - codeparrot_training - Step 12879: {'lr': 0.00042399376338590636, 'samples': 6594560, 'steps': 12879, 'batch_loss/train': 0.7922730674035847}
+12/24/2021 16:14:47 - INFO - codeparrot_training - Step 12880: {'lr': 0.0004239824440699068, 'samples': 6595072, 'steps': 12880, 'batch_loss/train': 0.8348797839134932}
+12/24/2021 16:14:57 - INFO - codeparrot_training - Step 12881: {'lr': 0.0004239711240622187, 'samples': 6595584, 'steps': 12881, 'batch_loss/train': 0.834947076626122}
+12/24/2021 16:15:08 - INFO - codeparrot_training - Step 12882: {'lr': 0.0004239598033628872, 'samples': 6596096, 'steps': 12882, 'batch_loss/train': 0.8637937535531819}
+12/24/2021 16:15:20 - INFO - codeparrot_training - Step 12883: {'lr': 0.00042394848197195714, 'samples': 6596608, 'steps': 12883, 'batch_loss/train': 0.8865162078291178}
+12/24/2021 16:15:31 - INFO - codeparrot_training - Step 12884: {'lr': 0.0004239371598894736, 'samples': 6597120, 'steps': 12884, 'batch_loss/train': 0.8915656581521034}
+12/24/2021 16:15:41 - INFO - codeparrot_training - Step 12885: {'lr': 0.0004239258371154816, 'samples': 6597632, 'steps': 12885, 'batch_loss/train': 0.7715214379131794}
+12/24/2021 16:15:54 - INFO - codeparrot_training - Step 12886: {'lr': 0.0004239145136500262, 'samples': 6598144, 'steps': 12886, 'batch_loss/train': 0.7916861004196107}
+12/24/2021 16:16:04 - INFO - codeparrot_training - Step 12887: {'lr': 0.0004239031894931523, 'samples': 6598656, 'steps': 12887, 'batch_loss/train': 0.7386882519349456}
+12/24/2021 16:16:15 - INFO - codeparrot_training - Step 12888: {'lr': 0.0004238918646449049, 'samples': 6599168, 'steps': 12888, 'batch_loss/train': 0.9849840514361858}
+12/24/2021 16:16:29 - INFO - codeparrot_training - Step 12889: {'lr': 0.00042388053910532924, 'samples': 6599680, 'steps': 12889, 'batch_loss/train': 0.8501082500442863}
+12/24/2021 16:16:39 - INFO - codeparrot_training - Step 12890: {'lr': 0.0004238692128744702, 'samples': 6600192, 'steps': 12890, 'batch_loss/train': 0.8690782925114036}
+12/24/2021 16:16:50 - INFO - codeparrot_training - Step 12891: {'lr': 0.00042385788595237275, 'samples': 6600704, 'steps': 12891, 'batch_loss/train': 0.8052077945321798}
+12/24/2021 16:17:01 - INFO - codeparrot_training - Step 12892: {'lr': 0.000423846558339082, 'samples': 6601216, 'steps': 12892, 'batch_loss/train': 0.8478165487758815}
+12/24/2021 16:17:13 - INFO - codeparrot_training - Step 12893: {'lr': 0.00042383523003464304, 'samples': 6601728, 'steps': 12893, 'batch_loss/train': 0.8770785238593817}
+12/24/2021 16:17:23 - INFO - codeparrot_training - Step 12894: {'lr': 0.0004238239010391008, 'samples': 6602240, 'steps': 12894, 'batch_loss/train': 0.9043105095624924}
+12/24/2021 16:17:34 - INFO - codeparrot_training - Step 12895: {'lr': 0.0004238125713525004, 'samples': 6602752, 'steps': 12895, 'batch_loss/train': 0.7998585114255548}
+12/24/2021 16:17:48 - INFO - codeparrot_training - Step 12896: {'lr': 0.0004238012409748868, 'samples': 6603264, 'steps': 12896, 'batch_loss/train': 0.7953733475878835}
+12/24/2021 16:17:59 - INFO - codeparrot_training - Step 12897: {'lr': 0.00042378990990630513, 'samples': 6603776, 'steps': 12897, 'batch_loss/train': 0.7621951913461089}
+12/24/2021 16:18:10 - INFO - codeparrot_training - Step 12898: {'lr': 0.0004237785781468003, 'samples': 6604288, 'steps': 12898, 'batch_loss/train': 0.9496196322143078}
+12/24/2021 16:18:22 - INFO - codeparrot_training - Step 12899: {'lr': 0.00042376724569641755, 'samples': 6604800, 'steps': 12899, 'batch_loss/train': 0.7285679820924997}
+12/24/2021 16:18:32 - INFO - codeparrot_training - Step 12900: {'lr': 0.00042375591255520187, 'samples': 6605312, 'steps': 12900, 'batch_loss/train': 0.6456664949655533}
+12/24/2021 16:18:43 - INFO - codeparrot_training - Step 12901: {'lr': 0.0004237445787231982, 'samples': 6605824, 'steps': 12901, 'batch_loss/train': 0.8336421232670546}
+12/24/2021 16:18:54 - INFO - codeparrot_training - Step 12902: {'lr': 0.0004237332442004518, 'samples': 6606336, 'steps': 12902, 'batch_loss/train': 0.7635426777414978}
+12/24/2021 16:19:06 - INFO - codeparrot_training - Step 12903: {'lr': 0.0004237219089870075, 'samples': 6606848, 'steps': 12903, 'batch_loss/train': 0.8602701369673014}
+12/24/2021 16:19:17 - INFO - codeparrot_training - Step 12904: {'lr': 0.00042371057308291055, 'samples': 6607360, 'steps': 12904, 'batch_loss/train': 0.8576609455049038}
+12/24/2021 16:19:27 - INFO - codeparrot_training - Step 12905: {'lr': 0.00042369923648820595, 'samples': 6607872, 'steps': 12905, 'batch_loss/train': 0.8462854092940688}
+12/24/2021 16:19:41 - INFO - codeparrot_training - Step 12906: {'lr': 0.0004236878992029387, 'samples': 6608384, 'steps': 12906, 'batch_loss/train': 0.7943619778379798}
+12/24/2021 16:19:52 - INFO - codeparrot_training - Step 12907: {'lr': 0.00042367656122715405, 'samples': 6608896, 'steps': 12907, 'batch_loss/train': 0.7403267612680793}
+12/24/2021 16:20:02 - INFO - codeparrot_training - Step 12908: {'lr': 0.0004236652225608969, 'samples': 6609408, 'steps': 12908, 'batch_loss/train': 0.8042130004614592}
+12/24/2021 16:20:14 - INFO - codeparrot_training - Step 12909: {'lr': 0.0004236538832042125, 'samples': 6609920, 'steps': 12909, 'batch_loss/train': 0.9341345317661762}
+12/24/2021 16:20:25 - INFO - codeparrot_training - Step 12910: {'lr': 0.00042364254315714573, 'samples': 6610432, 'steps': 12910, 'batch_loss/train': 0.8562896563671529}
+12/24/2021 16:20:36 - INFO - codeparrot_training - Step 12911: {'lr': 0.0004236312024197417, 'samples': 6610944, 'steps': 12911, 'batch_loss/train': 0.8190116416662931}
+12/24/2021 16:20:46 - INFO - codeparrot_training - Step 12912: {'lr': 0.00042361986099204575, 'samples': 6611456, 'steps': 12912, 'batch_loss/train': 0.7989669675007463}
+12/24/2021 16:20:58 - INFO - codeparrot_training - Step 12913: {'lr': 0.00042360851887410266, 'samples': 6611968, 'steps': 12913, 'batch_loss/train': 0.9435015814378858}
+12/24/2021 16:21:09 - INFO - codeparrot_training - Step 12914: {'lr': 0.00042359717606595777, 'samples': 6612480, 'steps': 12914, 'batch_loss/train': 0.7882572235539556}
+12/24/2021 16:21:19 - INFO - codeparrot_training - Step 12915: {'lr': 0.0004235858325676559, 'samples': 6612992, 'steps': 12915, 'batch_loss/train': 0.8400699933990836}
+12/24/2021 16:21:33 - INFO - codeparrot_training - Step 12916: {'lr': 0.0004235744883792425, 'samples': 6613504, 'steps': 12916, 'batch_loss/train': 0.8912825724110007}
+12/24/2021 16:21:44 - INFO - codeparrot_training - Step 12917: {'lr': 0.0004235631435007623, 'samples': 6614016, 'steps': 12917, 'batch_loss/train': 0.8114601764827967}
+12/24/2021 16:21:55 - INFO - codeparrot_training - Step 12918: {'lr': 0.0004235517979322606, 'samples': 6614528, 'steps': 12918, 'batch_loss/train': 0.8857047227211297}
+12/24/2021 16:22:07 - INFO - codeparrot_training - Step 12919: {'lr': 0.0004235404516737826, 'samples': 6615040, 'steps': 12919, 'batch_loss/train': 0.8208198649808764}
+12/24/2021 16:22:17 - INFO - codeparrot_training - Step 12920: {'lr': 0.0004235291047253732, 'samples': 6615552, 'steps': 12920, 'batch_loss/train': 0.962240731343627}
+12/24/2021 16:22:28 - INFO - codeparrot_training - Step 12921: {'lr': 0.00042351775708707764, 'samples': 6616064, 'steps': 12921, 'batch_loss/train': 0.9240679070353508}
+12/24/2021 16:22:39 - INFO - codeparrot_training - Step 12922: {'lr': 0.0004235064087589409, 'samples': 6616576, 'steps': 12922, 'batch_loss/train': 0.9372880132868886}
+12/24/2021 16:22:52 - INFO - codeparrot_training - Step 12923: {'lr': 0.00042349505974100833, 'samples': 6617088, 'steps': 12923, 'batch_loss/train': 0.7791684423573315}
+12/24/2021 16:23:03 - INFO - codeparrot_training - Step 12924: {'lr': 0.0004234837100333248, 'samples': 6617600, 'steps': 12924, 'batch_loss/train': 0.8185719531029463}
+12/24/2021 16:23:14 - INFO - codeparrot_training - Step 12925: {'lr': 0.00042347235963593555, 'samples': 6618112, 'steps': 12925, 'batch_loss/train': 0.753034558147192}
+12/24/2021 16:23:26 - INFO - codeparrot_training - Step 12926: {'lr': 0.00042346100854888575, 'samples': 6618624, 'steps': 12926, 'batch_loss/train': 0.8551320396363735}
+12/24/2021 16:23:36 - INFO - codeparrot_training - Step 12927: {'lr': 0.0004234496567722205, 'samples': 6619136, 'steps': 12927, 'batch_loss/train': 0.8448055284097791}
+12/24/2021 16:23:47 - INFO - codeparrot_training - Step 12928: {'lr': 0.00042343830430598486, 'samples': 6619648, 'steps': 12928, 'batch_loss/train': 0.7405439242720604}
+12/24/2021 16:23:59 - INFO - codeparrot_training - Step 12929: {'lr': 0.000423426951150224, 'samples': 6620160, 'steps': 12929, 'batch_loss/train': 0.8573675584048033}
+12/24/2021 16:24:10 - INFO - codeparrot_training - Step 12930: {'lr': 0.0004234155973049831, 'samples': 6620672, 'steps': 12930, 'batch_loss/train': 0.8770044185221195}
+12/24/2021 16:24:20 - INFO - codeparrot_training - Step 12931: {'lr': 0.0004234042427703072, 'samples': 6621184, 'steps': 12931, 'batch_loss/train': 0.8417053634766489}
+12/24/2021 16:24:31 - INFO - codeparrot_training - Step 12932: {'lr': 0.0004233928875462416, 'samples': 6621696, 'steps': 12932, 'batch_loss/train': 0.8311327574774623}
+12/24/2021 16:24:43 - INFO - codeparrot_training - Step 12933: {'lr': 0.00042338153163283125, 'samples': 6622208, 'steps': 12933, 'batch_loss/train': 0.7965037440881133}
+12/24/2021 16:24:54 - INFO - codeparrot_training - Step 12934: {'lr': 0.0004233701750301215, 'samples': 6622720, 'steps': 12934, 'batch_loss/train': 0.7580520557239652}
+12/24/2021 16:25:04 - INFO - codeparrot_training - Step 12935: {'lr': 0.00042335881773815733, 'samples': 6623232, 'steps': 12935, 'batch_loss/train': 0.8304054976906627}
+12/24/2021 16:25:19 - INFO - codeparrot_training - Step 12936: {'lr': 0.000423347459756984, 'samples': 6623744, 'steps': 12936, 'batch_loss/train': 0.7545634275302291}
+12/24/2021 16:25:29 - INFO - codeparrot_training - Step 12937: {'lr': 0.00042333610108664655, 'samples': 6624256, 'steps': 12937, 'batch_loss/train': 0.7333661860320717}
+12/24/2021 16:25:40 - INFO - codeparrot_training - Step 12938: {'lr': 0.0004233247417271903, 'samples': 6624768, 'steps': 12938, 'batch_loss/train': 0.8189774843631312}
+12/24/2021 16:25:52 - INFO - codeparrot_training - Step 12939: {'lr': 0.0004233133816786602, 'samples': 6625280, 'steps': 12939, 'batch_loss/train': 0.8388893138617277}
+12/24/2021 16:26:02 - INFO - codeparrot_training - Step 12940: {'lr': 0.0004233020209411017, 'samples': 6625792, 'steps': 12940, 'batch_loss/train': 0.6992448113160208}
+12/24/2021 16:26:13 - INFO - codeparrot_training - Step 12941: {'lr': 0.0004232906595145597, 'samples': 6626304, 'steps': 12941, 'batch_loss/train': 0.813586562871933}
+12/24/2021 16:26:24 - INFO - codeparrot_training - Step 12942: {'lr': 0.00042327929739907947, 'samples': 6626816, 'steps': 12942, 'batch_loss/train': 0.7618722589686513}
+12/24/2021 16:26:38 - INFO - codeparrot_training - Step 12943: {'lr': 0.0004232679345947062, 'samples': 6627328, 'steps': 12943, 'batch_loss/train': 0.7277508727274835}
+12/24/2021 16:26:48 - INFO - codeparrot_training - Step 12944: {'lr': 0.000423256571101485, 'samples': 6627840, 'steps': 12944, 'batch_loss/train': 0.7882340475916862}
+12/24/2021 16:26:59 - INFO - codeparrot_training - Step 12945: {'lr': 0.00042324520691946116, 'samples': 6628352, 'steps': 12945, 'batch_loss/train': 0.921651654643938}
+12/24/2021 16:27:11 - INFO - codeparrot_training - Step 12946: {'lr': 0.00042323384204867977, 'samples': 6628864, 'steps': 12946, 'batch_loss/train': 0.8580932421609759}
+12/24/2021 16:27:22 - INFO - codeparrot_training - Step 12947: {'lr': 0.00042322247648918606, 'samples': 6629376, 'steps': 12947, 'batch_loss/train': 0.7443629554472864}
+12/24/2021 16:27:32 - INFO - codeparrot_training - Step 12948: {'lr': 0.0004232111102410251, 'samples': 6629888, 'steps': 12948, 'batch_loss/train': 0.7954574376344681}
+12/24/2021 16:27:45 - INFO - codeparrot_training - Step 12949: {'lr': 0.0004231997433042423, 'samples': 6630400, 'steps': 12949, 'batch_loss/train': 0.9307677503675222}
+12/24/2021 16:27:55 - INFO - codeparrot_training - Step 12950: {'lr': 0.00042318837567888255, 'samples': 6630912, 'steps': 12950, 'batch_loss/train': 0.810433529317379}
+12/24/2021 16:28:06 - INFO - codeparrot_training - Step 12951: {'lr': 0.0004231770073649914, 'samples': 6631424, 'steps': 12951, 'batch_loss/train': 0.8712178955320269}
+12/24/2021 16:28:20 - INFO - codeparrot_training - Step 12952: {'lr': 0.0004231656383626137, 'samples': 6631936, 'steps': 12952, 'batch_loss/train': 0.7995509002357721}
+12/24/2021 16:28:30 - INFO - codeparrot_training - Step 12953: {'lr': 0.0004231542686717949, 'samples': 6632448, 'steps': 12953, 'batch_loss/train': 0.7501424308866262}
+12/24/2021 16:28:41 - INFO - codeparrot_training - Step 12954: {'lr': 0.0004231428982925801, 'samples': 6632960, 'steps': 12954, 'batch_loss/train': 0.7359261745586991}
+12/24/2021 16:28:52 - INFO - codeparrot_training - Step 12955: {'lr': 0.00042313152722501444, 'samples': 6633472, 'steps': 12955, 'batch_loss/train': 0.92414107080549}
+12/24/2021 16:29:04 - INFO - codeparrot_training - Step 12956: {'lr': 0.0004231201554691433, 'samples': 6633984, 'steps': 12956, 'batch_loss/train': 0.8774133296683431}
+12/24/2021 16:29:14 - INFO - codeparrot_training - Step 12957: {'lr': 0.00042310878302501175, 'samples': 6634496, 'steps': 12957, 'batch_loss/train': 0.9773971885442734}
+12/24/2021 16:29:25 - INFO - codeparrot_training - Step 12958: {'lr': 0.000423097409892665, 'samples': 6635008, 'steps': 12958, 'batch_loss/train': 0.8849851721897721}
+12/24/2021 16:29:37 - INFO - codeparrot_training - Step 12959: {'lr': 0.00042308603607214834, 'samples': 6635520, 'steps': 12959, 'batch_loss/train': 0.8340517971664667}
+12/24/2021 16:29:48 - INFO - codeparrot_training - Step 12960: {'lr': 0.000423074661563507, 'samples': 6636032, 'steps': 12960, 'batch_loss/train': 0.7923588007688522}
+12/24/2021 16:29:58 - INFO - codeparrot_training - Step 12961: {'lr': 0.0004230632863667861, 'samples': 6636544, 'steps': 12961, 'batch_loss/train': 0.9344980455935001}
+12/24/2021 16:30:12 - INFO - codeparrot_training - Step 12962: {'lr': 0.00042305191048203094, 'samples': 6637056, 'steps': 12962, 'batch_loss/train': 0.8713934682309628}
+12/24/2021 16:30:23 - INFO - codeparrot_training - Step 12963: {'lr': 0.0004230405339092867, 'samples': 6637568, 'steps': 12963, 'batch_loss/train': 0.7460556310834363}
+12/24/2021 16:30:33 - INFO - codeparrot_training - Step 12964: {'lr': 0.00042302915664859867, 'samples': 6638080, 'steps': 12964, 'batch_loss/train': 0.8466383214108646}
+12/24/2021 16:30:44 - INFO - codeparrot_training - Step 12965: {'lr': 0.000423017778700012, 'samples': 6638592, 'steps': 12965, 'batch_loss/train': 0.9413957940414548}
+12/24/2021 16:30:56 - INFO - codeparrot_training - Step 12966: {'lr': 0.00042300640006357203, 'samples': 6639104, 'steps': 12966, 'batch_loss/train': 0.9890270158648491}
+12/24/2021 16:31:07 - INFO - codeparrot_training - Step 12967: {'lr': 0.00042299502073932395, 'samples': 6639616, 'steps': 12967, 'batch_loss/train': 0.8127199485898018}
+12/24/2021 16:31:17 - INFO - codeparrot_training - Step 12968: {'lr': 0.0004229836407273129, 'samples': 6640128, 'steps': 12968, 'batch_loss/train': 0.8018375718966126}
+12/24/2021 16:31:31 - INFO - codeparrot_training - Step 12969: {'lr': 0.0004229722600275843, 'samples': 6640640, 'steps': 12969, 'batch_loss/train': 0.5608920340891927}
+12/24/2021 16:31:42 - INFO - codeparrot_training - Step 12970: {'lr': 0.0004229608786401832, 'samples': 6641152, 'steps': 12970, 'batch_loss/train': 0.7730783838778734}
+12/24/2021 16:31:53 - INFO - codeparrot_training - Step 12971: {'lr': 0.00042294949656515504, 'samples': 6641664, 'steps': 12971, 'batch_loss/train': 0.8355894018895924}
+12/24/2021 16:32:05 - INFO - codeparrot_training - Step 12972: {'lr': 0.000422938113802545, 'samples': 6642176, 'steps': 12972, 'batch_loss/train': 0.7861653240397573}
+12/24/2021 16:32:16 - INFO - codeparrot_training - Step 12973: {'lr': 0.00042292673035239825, 'samples': 6642688, 'steps': 12973, 'batch_loss/train': 1.1248339572921395}
+12/24/2021 16:32:26 - INFO - codeparrot_training - Step 12974: {'lr': 0.00042291534621476015, 'samples': 6643200, 'steps': 12974, 'batch_loss/train': 0.814558366779238}
+12/24/2021 16:32:37 - INFO - codeparrot_training - Step 12975: {'lr': 0.0004229039613896759, 'samples': 6643712, 'steps': 12975, 'batch_loss/train': 0.8070625215768814}
+12/24/2021 16:32:49 - INFO - codeparrot_training - Step 12976: {'lr': 0.00042289257587719084, 'samples': 6644224, 'steps': 12976, 'batch_loss/train': 0.7938446374610066}
+12/24/2021 16:33:00 - INFO - codeparrot_training - Step 12977: {'lr': 0.0004228811896773501, 'samples': 6644736, 'steps': 12977, 'batch_loss/train': 0.8234686926007271}
+12/24/2021 16:33:10 - INFO - codeparrot_training - Step 12978: {'lr': 0.0004228698027901991, 'samples': 6645248, 'steps': 12978, 'batch_loss/train': 0.7840134901925921}
+12/24/2021 16:33:22 - INFO - codeparrot_training - Step 12979: {'lr': 0.00042285841521578306, 'samples': 6645760, 'steps': 12979, 'batch_loss/train': 0.7938153930008411}
+12/24/2021 16:33:33 - INFO - codeparrot_training - Step 12980: {'lr': 0.0004228470269541471, 'samples': 6646272, 'steps': 12980, 'batch_loss/train': 0.8854358643293381}
+12/24/2021 16:33:44 - INFO - codeparrot_training - Step 12981: {'lr': 0.00042283563800533675, 'samples': 6646784, 'steps': 12981, 'batch_loss/train': 0.8268008991144598}
+12/24/2021 16:33:57 - INFO - codeparrot_training - Step 12982: {'lr': 0.0004228242483693971, 'samples': 6647296, 'steps': 12982, 'batch_loss/train': 0.8235091126989573}
+12/24/2021 16:34:08 - INFO - codeparrot_training - Step 12983: {'lr': 0.0004228128580463735, 'samples': 6647808, 'steps': 12983, 'batch_loss/train': 0.829069378785789}
+12/24/2021 16:34:19 - INFO - codeparrot_training - Step 12984: {'lr': 0.00042280146703631126, 'samples': 6648320, 'steps': 12984, 'batch_loss/train': 0.8653337145224214}
+12/24/2021 16:34:31 - INFO - codeparrot_training - Step 12985: {'lr': 0.0004227900753392556, 'samples': 6648832, 'steps': 12985, 'batch_loss/train': 0.7965043929871172}
+12/24/2021 16:34:41 - INFO - codeparrot_training - Step 12986: {'lr': 0.0004227786829552519, 'samples': 6649344, 'steps': 12986, 'batch_loss/train': 0.8376366160809994}
+12/24/2021 16:34:52 - INFO - codeparrot_training - Step 12987: {'lr': 0.0004227672898843453, 'samples': 6649856, 'steps': 12987, 'batch_loss/train': 0.8670059777796268}
+12/24/2021 16:35:03 - INFO - codeparrot_training - Step 12988: {'lr': 0.0004227558961265813, 'samples': 6650368, 'steps': 12988, 'batch_loss/train': 0.7635803883895278}
+12/24/2021 16:35:15 - INFO - codeparrot_training - Step 12989: {'lr': 0.00042274450168200493, 'samples': 6650880, 'steps': 12989, 'batch_loss/train': 1.117776634171605}
+12/24/2021 16:35:25 - INFO - codeparrot_training - Step 12990: {'lr': 0.00042273310655066185, 'samples': 6651392, 'steps': 12990, 'batch_loss/train': 0.8456959133036435}
+12/24/2021 16:35:36 - INFO - codeparrot_training - Step 12991: {'lr': 0.000422721710732597, 'samples': 6651904, 'steps': 12991, 'batch_loss/train': 0.7946229944936931}
+12/24/2021 16:35:50 - INFO - codeparrot_training - Step 12992: {'lr': 0.0004227103142278559, 'samples': 6652416, 'steps': 12992, 'batch_loss/train': 0.8751590171596035}
+12/24/2021 16:36:01 - INFO - codeparrot_training - Step 12993: {'lr': 0.00042269891703648386, 'samples': 6652928, 'steps': 12993, 'batch_loss/train': 0.8767042635008693}
+12/24/2021 16:36:11 - INFO - codeparrot_training - Step 12994: {'lr': 0.00042268751915852605, 'samples': 6653440, 'steps': 12994, 'batch_loss/train': 0.840452398173511}
+12/24/2021 16:36:22 - INFO - codeparrot_training - Step 12995: {'lr': 0.00042267612059402796, 'samples': 6653952, 'steps': 12995, 'batch_loss/train': 0.8565544402226806}
+12/24/2021 16:36:34 - INFO - codeparrot_training - Step 12996: {'lr': 0.0004226647213430347, 'samples': 6654464, 'steps': 12996, 'batch_loss/train': 0.8668846189975739}
+12/24/2021 16:36:44 - INFO - codeparrot_training - Step 12997: {'lr': 0.00042265332140559175, 'samples': 6654976, 'steps': 12997, 'batch_loss/train': 0.8541797064244747}
+12/24/2021 16:36:55 - INFO - codeparrot_training - Step 12998: {'lr': 0.0004226419207817444, 'samples': 6655488, 'steps': 12998, 'batch_loss/train': 0.8081822261447087}
+12/24/2021 16:37:09 - INFO - codeparrot_training - Step 12999: {'lr': 0.00042263051947153795, 'samples': 6656000, 'steps': 12999, 'batch_loss/train': 0.6979994125431404}
+12/24/2021 16:37:20 - INFO - codeparrot_training - Step 13000: {'lr': 0.00042261911747501767, 'samples': 6656512, 'steps': 13000, 'batch_loss/train': 1.042100409977138}
+12/24/2021 16:37:30 - INFO - codeparrot_training - Step 13001: {'lr': 0.00042260771479222907, 'samples': 6657024, 'steps': 13001, 'batch_loss/train': 0.8218228998593986}
+12/24/2021 16:37:42 - INFO - codeparrot_training - Step 13002: {'lr': 0.0004225963114232173, 'samples': 6657536, 'steps': 13002, 'batch_loss/train': 0.8825387079268694}
+12/24/2021 16:37:53 - INFO - codeparrot_training - Step 13003: {'lr': 0.0004225849073680279, 'samples': 6658048, 'steps': 13003, 'batch_loss/train': 0.8849582988768816}
+12/24/2021 16:38:03 - INFO - codeparrot_training - Step 13004: {'lr': 0.0004225735026267059, 'samples': 6658560, 'steps': 13004, 'batch_loss/train': 0.8320559058338404}
+12/24/2021 16:38:14 - INFO - codeparrot_training - Step 13005: {'lr': 0.0004225620971992968, 'samples': 6659072, 'steps': 13005, 'batch_loss/train': 1.014697226230055}
+12/24/2021 16:38:26 - INFO - codeparrot_training - Step 13006: {'lr': 0.0004225506910858461, 'samples': 6659584, 'steps': 13006, 'batch_loss/train': 0.8912302805110812}
+12/24/2021 16:38:37 - INFO - codeparrot_training - Step 13007: {'lr': 0.000422539284286399, 'samples': 6660096, 'steps': 13007, 'batch_loss/train': 0.7969660256057978}
+12/24/2021 16:38:47 - INFO - codeparrot_training - Step 13008: {'lr': 0.0004225278768010008, 'samples': 6660608, 'steps': 13008, 'batch_loss/train': 0.8367911288514733}
+12/24/2021 16:39:01 - INFO - codeparrot_training - Step 13009: {'lr': 0.00042251646862969685, 'samples': 6661120, 'steps': 13009, 'batch_loss/train': 0.807616968639195}
+12/24/2021 16:39:12 - INFO - codeparrot_training - Step 13010: {'lr': 0.0004225050597725326, 'samples': 6661632, 'steps': 13010, 'batch_loss/train': 0.9081397503614426}
+12/24/2021 16:39:22 - INFO - codeparrot_training - Step 13011: {'lr': 0.00042249365022955344, 'samples': 6662144, 'steps': 13011, 'batch_loss/train': 0.790582480840385}
+12/24/2021 16:39:35 - INFO - codeparrot_training - Step 13012: {'lr': 0.0004224822400008046, 'samples': 6662656, 'steps': 13012, 'batch_loss/train': 0.9067452680319548}
+12/24/2021 16:39:45 - INFO - codeparrot_training - Step 13013: {'lr': 0.0004224708290863315, 'samples': 6663168, 'steps': 13013, 'batch_loss/train': 0.8366348496638238}
+12/24/2021 16:39:56 - INFO - codeparrot_training - Step 13014: {'lr': 0.0004224594174861795, 'samples': 6663680, 'steps': 13014, 'batch_loss/train': 0.814844858366996}
+12/24/2021 16:40:08 - INFO - codeparrot_training - Step 13015: {'lr': 0.00042244800520039395, 'samples': 6664192, 'steps': 13015, 'batch_loss/train': 0.8299070438370109}
+12/24/2021 16:40:19 - INFO - codeparrot_training - Step 13016: {'lr': 0.0004224365922290203, 'samples': 6664704, 'steps': 13016, 'batch_loss/train': 0.8946619965136051}
+12/24/2021 16:40:29 - INFO - codeparrot_training - Step 13017: {'lr': 0.0004224251785721038, 'samples': 6665216, 'steps': 13017, 'batch_loss/train': 0.898843658156693}
+12/24/2021 16:40:40 - INFO - codeparrot_training - Step 13018: {'lr': 0.00042241376422968996, 'samples': 6665728, 'steps': 13018, 'batch_loss/train': 0.8849222734570503}
+12/24/2021 16:40:52 - INFO - codeparrot_training - Step 13019: {'lr': 0.0004224023492018241, 'samples': 6666240, 'steps': 13019, 'batch_loss/train': 0.8875184264034033}
+12/24/2021 16:41:02 - INFO - codeparrot_training - Step 13020: {'lr': 0.00042239093348855157, 'samples': 6666752, 'steps': 13020, 'batch_loss/train': 0.8142429143190384}
+12/24/2021 16:41:13 - INFO - codeparrot_training - Step 13021: {'lr': 0.0004223795170899178, 'samples': 6667264, 'steps': 13021, 'batch_loss/train': 0.712556635029614}
+12/24/2021 16:41:27 - INFO - codeparrot_training - Step 13022: {'lr': 0.00042236810000596814, 'samples': 6667776, 'steps': 13022, 'batch_loss/train': 0.7989917658269405}
+12/24/2021 16:41:37 - INFO - codeparrot_training - Step 13023: {'lr': 0.000422356682236748, 'samples': 6668288, 'steps': 13023, 'batch_loss/train': 0.7957085063681006}
+12/24/2021 16:41:48 - INFO - codeparrot_training - Step 13024: {'lr': 0.00042234526378230277, 'samples': 6668800, 'steps': 13024, 'batch_loss/train': 0.6589626700151712}
+12/24/2021 16:42:00 - INFO - codeparrot_training - Step 13025: {'lr': 0.0004223338446426779, 'samples': 6669312, 'steps': 13025, 'batch_loss/train': 0.7192874809261411}
+12/24/2021 16:42:11 - INFO - codeparrot_training - Step 13026: {'lr': 0.0004223224248179186, 'samples': 6669824, 'steps': 13026, 'batch_loss/train': 0.8128350535407662}
+12/24/2021 16:42:21 - INFO - codeparrot_training - Step 13027: {'lr': 0.00042231100430807053, 'samples': 6670336, 'steps': 13027, 'batch_loss/train': 0.7505819397047162}
+12/24/2021 16:42:36 - INFO - codeparrot_training - Step 13028: {'lr': 0.0004222995831131789, 'samples': 6670848, 'steps': 13028, 'batch_loss/train': 0.8713273471221328}
+12/24/2021 16:42:46 - INFO - codeparrot_training - Step 13029: {'lr': 0.0004222881612332892, 'samples': 6671360, 'steps': 13029, 'batch_loss/train': 0.8348371647298336}
+12/24/2021 16:42:57 - INFO - codeparrot_training - Step 13030: {'lr': 0.00042227673866844685, 'samples': 6671872, 'steps': 13030, 'batch_loss/train': 0.5584628558717668}
+12/24/2021 16:43:07 - INFO - codeparrot_training - Step 13031: {'lr': 0.0004222653154186972, 'samples': 6672384, 'steps': 13031, 'batch_loss/train': 0.8696496095508337}
+12/24/2021 16:43:20 - INFO - codeparrot_training - Step 13032: {'lr': 0.0004222538914840857, 'samples': 6672896, 'steps': 13032, 'batch_loss/train': 0.7789918419439346}
+12/24/2021 16:43:30 - INFO - codeparrot_training - Step 13033: {'lr': 0.00042224246686465785, 'samples': 6673408, 'steps': 13033, 'batch_loss/train': 0.7508451219182462}
+12/24/2021 16:43:41 - INFO - codeparrot_training - Step 13034: {'lr': 0.00042223104156045887, 'samples': 6673920, 'steps': 13034, 'batch_loss/train': 0.7919189482927322}
+12/24/2021 16:43:53 - INFO - codeparrot_training - Step 13035: {'lr': 0.0004222196155715344, 'samples': 6674432, 'steps': 13035, 'batch_loss/train': 0.7666469966061413}
+12/24/2021 16:44:04 - INFO - codeparrot_training - Step 13036: {'lr': 0.00042220818889792967, 'samples': 6674944, 'steps': 13036, 'batch_loss/train': 0.8327909549698234}
+12/24/2021 16:44:14 - INFO - codeparrot_training - Step 13037: {'lr': 0.00042219676153969026, 'samples': 6675456, 'steps': 13037, 'batch_loss/train': 0.8984936960041523}
+12/24/2021 16:44:28 - INFO - codeparrot_training - Step 13038: {'lr': 0.00042218533349686163, 'samples': 6675968, 'steps': 13038, 'batch_loss/train': 0.797020610421896}
+12/24/2021 16:44:39 - INFO - codeparrot_training - Step 13039: {'lr': 0.00042217390476948896, 'samples': 6676480, 'steps': 13039, 'batch_loss/train': 0.8313870327547193}
+12/24/2021 16:44:49 - INFO - codeparrot_training - Step 13040: {'lr': 0.000422162475357618, 'samples': 6676992, 'steps': 13040, 'batch_loss/train': 0.9251939682289958}
+12/24/2021 16:45:00 - INFO - codeparrot_training - Step 13041: {'lr': 0.00042215104526129396, 'samples': 6677504, 'steps': 13041, 'batch_loss/train': 0.7407164219766855}
+12/24/2021 16:45:12 - INFO - codeparrot_training - Step 13042: {'lr': 0.0004221396144805624, 'samples': 6678016, 'steps': 13042, 'batch_loss/train': 0.7497866554185748}
+12/24/2021 16:45:23 - INFO - codeparrot_training - Step 13043: {'lr': 0.0004221281830154687, 'samples': 6678528, 'steps': 13043, 'batch_loss/train': 0.6723706083139405}
+12/24/2021 16:45:33 - INFO - codeparrot_training - Step 13044: {'lr': 0.0004221167508660583, 'samples': 6679040, 'steps': 13044, 'batch_loss/train': 0.8112401450052857}
+12/24/2021 16:45:45 - INFO - codeparrot_training - Step 13045: {'lr': 0.00042210531803237673, 'samples': 6679552, 'steps': 13045, 'batch_loss/train': 0.8690565046854317}
+12/24/2021 16:45:56 - INFO - codeparrot_training - Step 13046: {'lr': 0.00042209388451446944, 'samples': 6680064, 'steps': 13046, 'batch_loss/train': 0.8057667752727866}
+12/24/2021 16:46:07 - INFO - codeparrot_training - Step 13047: {'lr': 0.0004220824503123818, 'samples': 6680576, 'steps': 13047, 'batch_loss/train': 0.8355517974123359}
+12/24/2021 16:46:21 - INFO - codeparrot_training - Step 13048: {'lr': 0.0004220710154261593, 'samples': 6681088, 'steps': 13048, 'batch_loss/train': 0.7158059785142541}
+12/24/2021 16:46:31 - INFO - codeparrot_training - Step 13049: {'lr': 0.00042205957985584755, 'samples': 6681600, 'steps': 13049, 'batch_loss/train': 0.9339654054492712}
+12/24/2021 16:46:42 - INFO - codeparrot_training - Step 13050: {'lr': 0.0004220481436014917, 'samples': 6682112, 'steps': 13050, 'batch_loss/train': 0.8802523007616401}
+12/24/2021 16:46:52 - INFO - codeparrot_training - Step 13051: {'lr': 0.0004220367066631375, 'samples': 6682624, 'steps': 13051, 'batch_loss/train': 0.8858281802386045}
+12/24/2021 16:47:05 - INFO - codeparrot_training - Step 13052: {'lr': 0.0004220252690408303, 'samples': 6683136, 'steps': 13052, 'batch_loss/train': 0.9059086898341775}
+12/24/2021 16:47:15 - INFO - codeparrot_training - Step 13053: {'lr': 0.00042201383073461554, 'samples': 6683648, 'steps': 13053, 'batch_loss/train': 0.7837138865143061}
+12/24/2021 16:47:26 - INFO - codeparrot_training - Step 13054: {'lr': 0.00042200239174453876, 'samples': 6684160, 'steps': 13054, 'batch_loss/train': 0.824236567132175}
+12/24/2021 16:47:38 - INFO - codeparrot_training - Step 13055: {'lr': 0.00042199095207064543, 'samples': 6684672, 'steps': 13055, 'batch_loss/train': 0.8167127736378461}
+12/24/2021 16:47:48 - INFO - codeparrot_training - Step 13056: {'lr': 0.00042197951171298097, 'samples': 6685184, 'steps': 13056, 'batch_loss/train': 0.7987996125593781}
+12/24/2021 16:47:59 - INFO - codeparrot_training - Step 13057: {'lr': 0.0004219680706715909, 'samples': 6685696, 'steps': 13057, 'batch_loss/train': 0.8129761908203363}
+12/24/2021 16:48:13 - INFO - codeparrot_training - Step 13058: {'lr': 0.0004219566289465208, 'samples': 6686208, 'steps': 13058, 'batch_loss/train': 0.8367360085248947}
+12/24/2021 16:48:24 - INFO - codeparrot_training - Step 13059: {'lr': 0.00042194518653781597, 'samples': 6686720, 'steps': 13059, 'batch_loss/train': 0.7538531725294888}
+12/24/2021 16:48:34 - INFO - codeparrot_training - Step 13060: {'lr': 0.00042193374344552215, 'samples': 6687232, 'steps': 13060, 'batch_loss/train': 0.8887944733723998}
+12/24/2021 16:48:45 - INFO - codeparrot_training - Step 13061: {'lr': 0.00042192229966968455, 'samples': 6687744, 'steps': 13061, 'batch_loss/train': 0.7824779665097594}
+12/24/2021 16:48:57 - INFO - codeparrot_training - Step 13062: {'lr': 0.0004219108552103489, 'samples': 6688256, 'steps': 13062, 'batch_loss/train': 0.6332334568724036}
+12/24/2021 16:49:08 - INFO - codeparrot_training - Step 13063: {'lr': 0.0004218994100675605, 'samples': 6688768, 'steps': 13063, 'batch_loss/train': 0.7438715272583067}
+12/24/2021 16:49:18 - INFO - codeparrot_training - Step 13064: {'lr': 0.000421887964241365, 'samples': 6689280, 'steps': 13064, 'batch_loss/train': 0.8649081652984023}
+12/24/2021 16:49:30 - INFO - codeparrot_training - Step 13065: {'lr': 0.0004218765177318079, 'samples': 6689792, 'steps': 13065, 'batch_loss/train': 0.7449036955367774}
+12/24/2021 16:49:41 - INFO - codeparrot_training - Step 13066: {'lr': 0.00042186507053893456, 'samples': 6690304, 'steps': 13066, 'batch_loss/train': 0.861285739345476}
+12/24/2021 16:49:51 - INFO - codeparrot_training - Step 13067: {'lr': 0.0004218536226627907, 'samples': 6690816, 'steps': 13067, 'batch_loss/train': 0.8224632360506803}
+12/24/2021 16:50:05 - INFO - codeparrot_training - Step 13068: {'lr': 0.00042184217410342164, 'samples': 6691328, 'steps': 13068, 'batch_loss/train': 0.8836798593401909}
+12/24/2021 16:50:16 - INFO - codeparrot_training - Step 13069: {'lr': 0.00042183072486087303, 'samples': 6691840, 'steps': 13069, 'batch_loss/train': 0.8200494545744732}
+12/24/2021 16:50:26 - INFO - codeparrot_training - Step 13070: {'lr': 0.0004218192749351903, 'samples': 6692352, 'steps': 13070, 'batch_loss/train': 0.7909489534795284}
+12/24/2021 16:50:38 - INFO - codeparrot_training - Step 13071: {'lr': 0.0004218078243264191, 'samples': 6692864, 'steps': 13071, 'batch_loss/train': 0.8447822220623493}
+12/24/2021 16:50:49 - INFO - codeparrot_training - Step 13072: {'lr': 0.0004217963730346048, 'samples': 6693376, 'steps': 13072, 'batch_loss/train': 0.8061314676888287}
+12/24/2021 16:51:00 - INFO - codeparrot_training - Step 13073: {'lr': 0.0004217849210597929, 'samples': 6693888, 'steps': 13073, 'batch_loss/train': 0.8490304304286838}
+12/24/2021 16:51:10 - INFO - codeparrot_training - Step 13074: {'lr': 0.0004217734684020292, 'samples': 6694400, 'steps': 13074, 'batch_loss/train': 0.9232624350115657}
+12/24/2021 16:51:22 - INFO - codeparrot_training - Step 13075: {'lr': 0.0004217620150613589, 'samples': 6694912, 'steps': 13075, 'batch_loss/train': 0.7579597264993936}
+12/24/2021 16:51:33 - INFO - codeparrot_training - Step 13076: {'lr': 0.0004217505610378277, 'samples': 6695424, 'steps': 13076, 'batch_loss/train': 0.8566374685615301}
+12/24/2021 16:51:44 - INFO - codeparrot_training - Step 13077: {'lr': 0.0004217391063314813, 'samples': 6695936, 'steps': 13077, 'batch_loss/train': 0.8428273824974895}
+12/24/2021 16:51:57 - INFO - codeparrot_training - Step 13078: {'lr': 0.0004217276509423649, 'samples': 6696448, 'steps': 13078, 'batch_loss/train': 0.8802339620888233}
+12/24/2021 16:52:08 - INFO - codeparrot_training - Step 13079: {'lr': 0.00042171619487052416, 'samples': 6696960, 'steps': 13079, 'batch_loss/train': 0.7408670908771455}
+12/24/2021 16:52:19 - INFO - codeparrot_training - Step 13080: {'lr': 0.00042170473811600475, 'samples': 6697472, 'steps': 13080, 'batch_loss/train': 0.7662916025146842}
+12/24/2021 16:52:31 - INFO - codeparrot_training - Step 13081: {'lr': 0.000421693280678852, 'samples': 6697984, 'steps': 13081, 'batch_loss/train': 0.6994417998939753}
+12/24/2021 16:52:42 - INFO - codeparrot_training - Step 13082: {'lr': 0.0004216818225591118, 'samples': 6698496, 'steps': 13082, 'batch_loss/train': 0.7425871398299932}
+12/24/2021 16:52:52 - INFO - codeparrot_training - Step 13083: {'lr': 0.00042167036375682937, 'samples': 6699008, 'steps': 13083, 'batch_loss/train': 0.7254088125191629}
+12/24/2021 16:53:03 - INFO - codeparrot_training - Step 13084: {'lr': 0.00042165890427205046, 'samples': 6699520, 'steps': 13084, 'batch_loss/train': 0.768653488252312}
+12/24/2021 16:53:17 - INFO - codeparrot_training - Step 13085: {'lr': 0.0004216474441048205, 'samples': 6700032, 'steps': 13085, 'batch_loss/train': 0.8007477829232812}
+12/24/2021 16:53:27 - INFO - codeparrot_training - Step 13086: {'lr': 0.00042163598325518513, 'samples': 6700544, 'steps': 13086, 'batch_loss/train': 0.9080955665558577}
+12/24/2021 16:53:38 - INFO - codeparrot_training - Step 13087: {'lr': 0.00042162452172318993, 'samples': 6701056, 'steps': 13087, 'batch_loss/train': 0.7961451306473464}
+12/24/2021 16:53:50 - INFO - codeparrot_training - Step 13088: {'lr': 0.00042161305950888045, 'samples': 6701568, 'steps': 13088, 'batch_loss/train': 0.8136374466121197}
+12/24/2021 16:54:01 - INFO - codeparrot_training - Step 13089: {'lr': 0.00042160159661230217, 'samples': 6702080, 'steps': 13089, 'batch_loss/train': 1.648950087837875}
+12/24/2021 16:54:12 - INFO - codeparrot_training - Step 13090: {'lr': 0.0004215901330335008, 'samples': 6702592, 'steps': 13090, 'batch_loss/train': 0.7735862487461418}
+12/24/2021 16:54:22 - INFO - codeparrot_training - Step 13091: {'lr': 0.0004215786687725218, 'samples': 6703104, 'steps': 13091, 'batch_loss/train': 0.7598436083644629}
+12/24/2021 16:54:34 - INFO - codeparrot_training - Step 13092: {'lr': 0.00042156720382941084, 'samples': 6703616, 'steps': 13092, 'batch_loss/train': 0.6827410813421011}
+12/24/2021 16:54:45 - INFO - codeparrot_training - Step 13093: {'lr': 0.00042155573820421347, 'samples': 6704128, 'steps': 13093, 'batch_loss/train': 0.8204029169864953}
+12/24/2021 16:54:55 - INFO - codeparrot_training - Step 13094: {'lr': 0.0004215442718969752, 'samples': 6704640, 'steps': 13094, 'batch_loss/train': 0.8206214485689998}
+12/24/2021 16:55:10 - INFO - codeparrot_training - Step 13095: {'lr': 0.0004215328049077417, 'samples': 6705152, 'steps': 13095, 'batch_loss/train': 1.7788200648501515}
+12/24/2021 16:55:20 - INFO - codeparrot_training - Step 13096: {'lr': 0.0004215213372365586, 'samples': 6705664, 'steps': 13096, 'batch_loss/train': 0.8699695970863104}
+12/24/2021 16:55:31 - INFO - codeparrot_training - Step 13097: {'lr': 0.0004215098688834714, 'samples': 6706176, 'steps': 13097, 'batch_loss/train': 0.8947219327092171}
+12/24/2021 16:55:43 - INFO - codeparrot_training - Step 13098: {'lr': 0.0004214983998485257, 'samples': 6706688, 'steps': 13098, 'batch_loss/train': 0.7787996651604772}
+12/24/2021 16:55:54 - INFO - codeparrot_training - Step 13099: {'lr': 0.00042148693013176707, 'samples': 6707200, 'steps': 13099, 'batch_loss/train': 0.9528190204873681}
+12/24/2021 16:56:04 - INFO - codeparrot_training - Step 13100: {'lr': 0.0004214754597332412, 'samples': 6707712, 'steps': 13100, 'batch_loss/train': 0.6809896575286984}
+12/24/2021 16:56:15 - INFO - codeparrot_training - Step 13101: {'lr': 0.0004214639886529937, 'samples': 6708224, 'steps': 13101, 'batch_loss/train': 0.8001194875687361}
+12/24/2021 16:56:27 - INFO - codeparrot_training - Step 13102: {'lr': 0.00042145251689107, 'samples': 6708736, 'steps': 13102, 'batch_loss/train': 0.7701521813869476}
+12/24/2021 16:56:38 - INFO - codeparrot_training - Step 13103: {'lr': 0.0004214410444475159, 'samples': 6709248, 'steps': 13103, 'batch_loss/train': 0.8042446027975529}
+12/24/2021 16:56:48 - INFO - codeparrot_training - Step 13104: {'lr': 0.00042142957132237696, 'samples': 6709760, 'steps': 13104, 'batch_loss/train': 0.9083388913422823}
+12/24/2021 16:57:00 - INFO - codeparrot_training - Step 13105: {'lr': 0.00042141809751569876, 'samples': 6710272, 'steps': 13105, 'batch_loss/train': 0.876733418321237}
+12/24/2021 16:57:11 - INFO - codeparrot_training - Step 13106: {'lr': 0.00042140662302752696, 'samples': 6710784, 'steps': 13106, 'batch_loss/train': 0.9210051447153091}
+12/24/2021 16:57:22 - INFO - codeparrot_training - Step 13107: {'lr': 0.0004213951478579071, 'samples': 6711296, 'steps': 13107, 'batch_loss/train': 0.8606929956004024}
+12/24/2021 16:57:36 - INFO - codeparrot_training - Step 13108: {'lr': 0.00042138367200688487, 'samples': 6711808, 'steps': 13108, 'batch_loss/train': 0.8006187113933265}
+12/24/2021 16:57:46 - INFO - codeparrot_training - Step 13109: {'lr': 0.0004213721954745058, 'samples': 6712320, 'steps': 13109, 'batch_loss/train': 0.9175910842604935}
+12/24/2021 16:57:57 - INFO - codeparrot_training - Step 13110: {'lr': 0.0004213607182608157, 'samples': 6712832, 'steps': 13110, 'batch_loss/train': 0.8409126475453377}
+12/24/2021 16:58:07 - INFO - codeparrot_training - Step 13111: {'lr': 0.0004213492403658601, 'samples': 6713344, 'steps': 13111, 'batch_loss/train': 0.8381201233714819}
+12/24/2021 16:58:20 - INFO - codeparrot_training - Step 13112: {'lr': 0.00042133776178968454, 'samples': 6713856, 'steps': 13112, 'batch_loss/train': 0.8473222041502595}
+12/24/2021 16:58:30 - INFO - codeparrot_training - Step 13113: {'lr': 0.00042132628253233474, 'samples': 6714368, 'steps': 13113, 'batch_loss/train': 0.7532546450383961}
+12/24/2021 16:58:41 - INFO - codeparrot_training - Step 13114: {'lr': 0.00042131480259385634, 'samples': 6714880, 'steps': 13114, 'batch_loss/train': 0.6967521458864212}
+12/24/2021 16:58:55 - INFO - codeparrot_training - Step 13115: {'lr': 0.000421303321974295, 'samples': 6715392, 'steps': 13115, 'batch_loss/train': 0.820867155212909}
+12/24/2021 16:59:05 - INFO - codeparrot_training - Step 13116: {'lr': 0.0004212918406736963, 'samples': 6715904, 'steps': 13116, 'batch_loss/train': 0.7943852748721838}
+12/24/2021 16:59:16 - INFO - codeparrot_training - Step 13117: {'lr': 0.0004212803586921059, 'samples': 6716416, 'steps': 13117, 'batch_loss/train': 0.8732364354655147}
+12/24/2021 16:59:28 - INFO - codeparrot_training - Step 13118: {'lr': 0.0004212688760295695, 'samples': 6716928, 'steps': 13118, 'batch_loss/train': 0.9149840781465173}
+12/24/2021 16:59:39 - INFO - codeparrot_training - Step 13119: {'lr': 0.0004212573926861327, 'samples': 6717440, 'steps': 13119, 'batch_loss/train': 0.7117884964682162}
+12/24/2021 16:59:49 - INFO - codeparrot_training - Step 13120: {'lr': 0.0004212459086618412, 'samples': 6717952, 'steps': 13120, 'batch_loss/train': 0.8240248709917068}
+12/24/2021 17:00:00 - INFO - codeparrot_training - Step 13121: {'lr': 0.00042123442395674063, 'samples': 6718464, 'steps': 13121, 'batch_loss/train': 0.7553907157853246}
+12/24/2021 17:00:12 - INFO - codeparrot_training - Step 13122: {'lr': 0.00042122293857087663, 'samples': 6718976, 'steps': 13122, 'batch_loss/train': 0.8174107396043837}
+12/24/2021 17:00:23 - INFO - codeparrot_training - Step 13123: {'lr': 0.0004212114525042949, 'samples': 6719488, 'steps': 13123, 'batch_loss/train': 0.8471985463984311}
+12/24/2021 17:00:33 - INFO - codeparrot_training - Step 13124: {'lr': 0.000421199965757041, 'samples': 6720000, 'steps': 13124, 'batch_loss/train': 0.8777696965262294}
+12/24/2021 17:00:47 - INFO - codeparrot_training - Step 13125: {'lr': 0.00042118847832916075, 'samples': 6720512, 'steps': 13125, 'batch_loss/train': 0.8086504535749555}
+12/24/2021 17:00:58 - INFO - codeparrot_training - Step 13126: {'lr': 0.0004211769902206997, 'samples': 6721024, 'steps': 13126, 'batch_loss/train': 0.8186282245442271}
+12/24/2021 17:01:08 - INFO - codeparrot_training - Step 13127: {'lr': 0.0004211655014317036, 'samples': 6721536, 'steps': 13127, 'batch_loss/train': 0.7929616752080619}
+12/24/2021 17:01:20 - INFO - codeparrot_training - Step 13128: {'lr': 0.00042115401196221814, 'samples': 6722048, 'steps': 13128, 'batch_loss/train': 0.7859851950779557}
+12/24/2021 17:01:31 - INFO - codeparrot_training - Step 13129: {'lr': 0.0004211425218122889, 'samples': 6722560, 'steps': 13129, 'batch_loss/train': 0.7358655240386724}
+12/24/2021 17:01:42 - INFO - codeparrot_training - Step 13130: {'lr': 0.00042113103098196167, 'samples': 6723072, 'steps': 13130, 'batch_loss/train': 0.8902473300695419}
+12/24/2021 17:01:54 - INFO - codeparrot_training - Step 13131: {'lr': 0.000421119539471282, 'samples': 6723584, 'steps': 13131, 'batch_loss/train': 0.7605984611436725}
+12/24/2021 17:02:04 - INFO - codeparrot_training - Step 13132: {'lr': 0.00042110804728029573, 'samples': 6724096, 'steps': 13132, 'batch_loss/train': 0.7795050721615553}
+12/24/2021 17:02:15 - INFO - codeparrot_training - Step 13133: {'lr': 0.0004210965544090484, 'samples': 6724608, 'steps': 13133, 'batch_loss/train': 0.8133056019432843}
+12/24/2021 17:02:25 - INFO - codeparrot_training - Step 13134: {'lr': 0.0004210850608575858, 'samples': 6725120, 'steps': 13134, 'batch_loss/train': 0.7581839985214174}
+12/24/2021 17:02:39 - INFO - codeparrot_training - Step 13135: {'lr': 0.0004210735666259536, 'samples': 6725632, 'steps': 13135, 'batch_loss/train': 0.7936996873468161}
+12/24/2021 17:02:50 - INFO - codeparrot_training - Step 13136: {'lr': 0.0004210620717141975, 'samples': 6726144, 'steps': 13136, 'batch_loss/train': 0.8584145000204444}
+12/24/2021 17:03:01 - INFO - codeparrot_training - Step 13137: {'lr': 0.0004210505761223632, 'samples': 6726656, 'steps': 13137, 'batch_loss/train': 0.7955347178503871}
+12/24/2021 17:03:13 - INFO - codeparrot_training - Step 13138: {'lr': 0.0004210390798504964, 'samples': 6727168, 'steps': 13138, 'batch_loss/train': 0.8258552616462111}
+12/24/2021 17:03:23 - INFO - codeparrot_training - Step 13139: {'lr': 0.00042102758289864274, 'samples': 6727680, 'steps': 13139, 'batch_loss/train': 0.8441900098696351}
+12/24/2021 17:03:34 - INFO - codeparrot_training - Step 13140: {'lr': 0.000421016085266848, 'samples': 6728192, 'steps': 13140, 'batch_loss/train': 0.8016094556078315}
+12/24/2021 17:03:46 - INFO - codeparrot_training - Step 13141: {'lr': 0.000421004586955158, 'samples': 6728704, 'steps': 13141, 'batch_loss/train': 0.7931282571516931}
+12/24/2021 17:03:57 - INFO - codeparrot_training - Step 13142: {'lr': 0.00042099308796361825, 'samples': 6729216, 'steps': 13142, 'batch_loss/train': 0.9046736750751734}
+12/24/2021 17:04:08 - INFO - codeparrot_training - Step 13143: {'lr': 0.0004209815882922745, 'samples': 6729728, 'steps': 13143, 'batch_loss/train': 0.7448652876773849}
+12/24/2021 17:04:18 - INFO - codeparrot_training - Step 13144: {'lr': 0.0004209700879411725, 'samples': 6730240, 'steps': 13144, 'batch_loss/train': 0.8598833531141281}
+12/24/2021 17:04:32 - INFO - codeparrot_training - Step 13145: {'lr': 0.00042095858691035807, 'samples': 6730752, 'steps': 13145, 'batch_loss/train': 0.7562524392269552}
+12/24/2021 17:04:43 - INFO - codeparrot_training - Step 13146: {'lr': 0.00042094708519987685, 'samples': 6731264, 'steps': 13146, 'batch_loss/train': 0.7780975312925875}
+12/24/2021 17:04:53 - INFO - codeparrot_training - Step 13147: {'lr': 0.0004209355828097745, 'samples': 6731776, 'steps': 13147, 'batch_loss/train': 0.8267309288494289}
+12/24/2021 17:05:05 - INFO - codeparrot_training - Step 13148: {'lr': 0.0004209240797400969, 'samples': 6732288, 'steps': 13148, 'batch_loss/train': 0.7949872203171253}
+12/24/2021 17:05:16 - INFO - codeparrot_training - Step 13149: {'lr': 0.0004209125759908896, 'samples': 6732800, 'steps': 13149, 'batch_loss/train': 1.6677916990593076}
+12/24/2021 17:05:27 - INFO - codeparrot_training - Step 13150: {'lr': 0.0004209010715621985, 'samples': 6733312, 'steps': 13150, 'batch_loss/train': 0.9607327671255916}
+12/24/2021 17:05:39 - INFO - codeparrot_training - Step 13151: {'lr': 0.0004208895664540693, 'samples': 6733824, 'steps': 13151, 'batch_loss/train': 0.7455375869758427}
+12/24/2021 17:05:50 - INFO - codeparrot_training - Step 13152: {'lr': 0.00042087806066654765, 'samples': 6734336, 'steps': 13152, 'batch_loss/train': 0.8654231792315841}
+12/24/2021 17:06:00 - INFO - codeparrot_training - Step 13153: {'lr': 0.00042086655419967936, 'samples': 6734848, 'steps': 13153, 'batch_loss/train': 0.7539959447458386}
+12/24/2021 17:06:11 - INFO - codeparrot_training - Step 13154: {'lr': 0.0004208550470535102, 'samples': 6735360, 'steps': 13154, 'batch_loss/train': 0.7595639815554023}
+12/24/2021 17:06:25 - INFO - codeparrot_training - Step 13155: {'lr': 0.00042084353922808575, 'samples': 6735872, 'steps': 13155, 'batch_loss/train': 0.754623148823157}
+12/24/2021 17:06:36 - INFO - codeparrot_training - Step 13156: {'lr': 0.00042083203072345205, 'samples': 6736384, 'steps': 13156, 'batch_loss/train': 0.6780898203141987}
+12/24/2021 17:06:46 - INFO - codeparrot_training - Step 13157: {'lr': 0.00042082052153965464, 'samples': 6736896, 'steps': 13157, 'batch_loss/train': 0.6764449521433562}
+12/24/2021 17:06:59 - INFO - codeparrot_training - Step 13158: {'lr': 0.00042080901167673934, 'samples': 6737408, 'steps': 13158, 'batch_loss/train': 0.8008964778855443}
+12/24/2021 17:07:09 - INFO - codeparrot_training - Step 13159: {'lr': 0.0004207975011347519, 'samples': 6737920, 'steps': 13159, 'batch_loss/train': 0.8585302941501141}
+12/24/2021 17:07:20 - INFO - codeparrot_training - Step 13160: {'lr': 0.00042078598991373813, 'samples': 6738432, 'steps': 13160, 'batch_loss/train': 0.8295428650453687}
+12/24/2021 17:07:32 - INFO - codeparrot_training - Step 13161: {'lr': 0.00042077447801374367, 'samples': 6738944, 'steps': 13161, 'batch_loss/train': 0.8740113712847233}
+12/24/2021 17:07:43 - INFO - codeparrot_training - Step 13162: {'lr': 0.0004207629654348145, 'samples': 6739456, 'steps': 13162, 'batch_loss/train': 0.8759404812008142}
+12/24/2021 17:07:53 - INFO - codeparrot_training - Step 13163: {'lr': 0.0004207514521769961, 'samples': 6739968, 'steps': 13163, 'batch_loss/train': 0.7964446407277137}
+12/24/2021 17:08:04 - INFO - codeparrot_training - Step 13164: {'lr': 0.00042073993824033454, 'samples': 6740480, 'steps': 13164, 'batch_loss/train': 0.7669547580881044}
+12/24/2021 17:08:17 - INFO - codeparrot_training - Step 13165: {'lr': 0.0004207284236248753, 'samples': 6740992, 'steps': 13165, 'batch_loss/train': 0.8292675539851189}
+12/24/2021 17:08:28 - INFO - codeparrot_training - Step 13166: {'lr': 0.00042071690833066444, 'samples': 6741504, 'steps': 13166, 'batch_loss/train': 0.7647723373956978}
+12/24/2021 17:08:39 - INFO - codeparrot_training - Step 13167: {'lr': 0.0004207053923577476, 'samples': 6742016, 'steps': 13167, 'batch_loss/train': 0.8224443276412785}
+12/24/2021 17:08:51 - INFO - codeparrot_training - Step 13168: {'lr': 0.0004206938757061705, 'samples': 6742528, 'steps': 13168, 'batch_loss/train': 0.8203578346874565}
+12/24/2021 17:09:02 - INFO - codeparrot_training - Step 13169: {'lr': 0.0004206823583759791, 'samples': 6743040, 'steps': 13169, 'batch_loss/train': 0.8630714854225516}
+12/24/2021 17:09:12 - INFO - codeparrot_training - Step 13170: {'lr': 0.00042067084036721895, 'samples': 6743552, 'steps': 13170, 'batch_loss/train': 0.6003166257869452}
+12/24/2021 17:09:24 - INFO - codeparrot_training - Step 13171: {'lr': 0.00042065932167993615, 'samples': 6744064, 'steps': 13171, 'batch_loss/train': 0.7873190985992551}
+12/24/2021 17:09:35 - INFO - codeparrot_training - Step 13172: {'lr': 0.0004206478023141762, 'samples': 6744576, 'steps': 13172, 'batch_loss/train': 0.712820737157017}
+12/24/2021 17:09:45 - INFO - codeparrot_training - Step 13173: {'lr': 0.00042063628226998506, 'samples': 6745088, 'steps': 13173, 'batch_loss/train': 0.7872478519566357}
+12/24/2021 17:09:56 - INFO - codeparrot_training - Step 13174: {'lr': 0.0004206247615474085, 'samples': 6745600, 'steps': 13174, 'batch_loss/train': 0.7385636568069458}
+12/24/2021 17:10:11 - INFO - codeparrot_training - Step 13175: {'lr': 0.00042061324014649234, 'samples': 6746112, 'steps': 13175, 'batch_loss/train': 0.851138062775135}
+12/24/2021 17:10:21 - INFO - codeparrot_training - Step 13176: {'lr': 0.00042060171806728233, 'samples': 6746624, 'steps': 13176, 'batch_loss/train': 0.7606805134564638}
+12/24/2021 17:10:32 - INFO - codeparrot_training - Step 13177: {'lr': 0.00042059019530982423, 'samples': 6747136, 'steps': 13177, 'batch_loss/train': 0.7792458129115403}
+12/24/2021 17:10:44 - INFO - codeparrot_training - Step 13178: {'lr': 0.00042057867187416406, 'samples': 6747648, 'steps': 13178, 'batch_loss/train': 0.7666065362282097}
+12/24/2021 17:10:55 - INFO - codeparrot_training - Step 13179: {'lr': 0.0004205671477603474, 'samples': 6748160, 'steps': 13179, 'batch_loss/train': 0.8250810289755464}
+12/24/2021 17:11:05 - INFO - codeparrot_training - Step 13180: {'lr': 0.0004205556229684202, 'samples': 6748672, 'steps': 13180, 'batch_loss/train': 0.8443933548405766}
+12/24/2021 17:11:20 - INFO - codeparrot_training - Step 13181: {'lr': 0.00042054409749842824, 'samples': 6749184, 'steps': 13181, 'batch_loss/train': 0.8561663711443543}
+12/24/2021 17:11:31 - INFO - codeparrot_training - Step 13182: {'lr': 0.0004205325713504174, 'samples': 6749696, 'steps': 13182, 'batch_loss/train': 0.7828223360702395}
+12/24/2021 17:11:41 - INFO - codeparrot_training - Step 13183: {'lr': 0.0004205210445244334, 'samples': 6750208, 'steps': 13183, 'batch_loss/train': 0.773463205434382}
+12/24/2021 17:11:52 - INFO - codeparrot_training - Step 13184: {'lr': 0.0004205095170205221, 'samples': 6750720, 'steps': 13184, 'batch_loss/train': 0.6466374862939119}
+12/24/2021 17:12:04 - INFO - codeparrot_training - Step 13185: {'lr': 0.00042049798883872936, 'samples': 6751232, 'steps': 13185, 'batch_loss/train': 0.9124206686392426}
+12/24/2021 17:12:14 - INFO - codeparrot_training - Step 13186: {'lr': 0.00042048645997910095, 'samples': 6751744, 'steps': 13186, 'batch_loss/train': 0.8038037652149796}
+12/24/2021 17:12:25 - INFO - codeparrot_training - Step 13187: {'lr': 0.00042047493044168285, 'samples': 6752256, 'steps': 13187, 'batch_loss/train': 0.922662565484643}
+12/24/2021 17:12:37 - INFO - codeparrot_training - Step 13188: {'lr': 0.00042046340022652075, 'samples': 6752768, 'steps': 13188, 'batch_loss/train': 0.7041425784118474}
+12/24/2021 17:12:48 - INFO - codeparrot_training - Step 13189: {'lr': 0.0004204518693336604, 'samples': 6753280, 'steps': 13189, 'batch_loss/train': 0.8429762180894613}
+12/24/2021 17:12:58 - INFO - codeparrot_training - Step 13190: {'lr': 0.0004204403377631479, 'samples': 6753792, 'steps': 13190, 'batch_loss/train': 0.9573446903377771}
+12/24/2021 17:13:12 - INFO - codeparrot_training - Step 13191: {'lr': 0.00042042880551502906, 'samples': 6754304, 'steps': 13191, 'batch_loss/train': 0.8361318558454514}
+12/24/2021 17:13:23 - INFO - codeparrot_training - Step 13192: {'lr': 0.0004204172725893495, 'samples': 6754816, 'steps': 13192, 'batch_loss/train': 0.9040102055296302}
+12/24/2021 17:13:33 - INFO - codeparrot_training - Step 13193: {'lr': 0.00042040573898615525, 'samples': 6755328, 'steps': 13193, 'batch_loss/train': 0.7336675287224352}
+12/24/2021 17:13:44 - INFO - codeparrot_training - Step 13194: {'lr': 0.00042039420470549213, 'samples': 6755840, 'steps': 13194, 'batch_loss/train': 0.7916770880110562}
+12/24/2021 17:13:56 - INFO - codeparrot_training - Step 13195: {'lr': 0.00042038266974740604, 'samples': 6756352, 'steps': 13195, 'batch_loss/train': 0.819748766720295}
+12/24/2021 17:14:07 - INFO - codeparrot_training - Step 13196: {'lr': 0.00042037113411194275, 'samples': 6756864, 'steps': 13196, 'batch_loss/train': 0.775233889464289}
+12/24/2021 17:14:17 - INFO - codeparrot_training - Step 13197: {'lr': 0.0004203595977991481, 'samples': 6757376, 'steps': 13197, 'batch_loss/train': 0.8552856640890241}
+12/24/2021 17:14:31 - INFO - codeparrot_training - Step 13198: {'lr': 0.0004203480608090681, 'samples': 6757888, 'steps': 13198, 'batch_loss/train': 0.6801711132284254}
+12/24/2021 17:14:42 - INFO - codeparrot_training - Step 13199: {'lr': 0.00042033652314174845, 'samples': 6758400, 'steps': 13199, 'batch_loss/train': 0.8157510804012418}
+12/24/2021 17:14:52 - INFO - codeparrot_training - Step 13200: {'lr': 0.00042032498479723516, 'samples': 6758912, 'steps': 13200, 'batch_loss/train': 0.9044127142988145}
+12/24/2021 17:15:04 - INFO - codeparrot_training - Step 13201: {'lr': 0.00042031344577557407, 'samples': 6759424, 'steps': 13201, 'batch_loss/train': 0.8240072159096599}
+12/24/2021 17:15:15 - INFO - codeparrot_training - Step 13202: {'lr': 0.00042030190607681095, 'samples': 6759936, 'steps': 13202, 'batch_loss/train': 0.797450901940465}
+12/24/2021 17:15:26 - INFO - codeparrot_training - Step 13203: {'lr': 0.00042029036570099176, 'samples': 6760448, 'steps': 13203, 'batch_loss/train': 0.8776646926999092}
+12/24/2021 17:15:38 - INFO - codeparrot_training - Step 13204: {'lr': 0.0004202788246481625, 'samples': 6760960, 'steps': 13204, 'batch_loss/train': 0.7455227500759065}
+12/24/2021 17:15:48 - INFO - codeparrot_training - Step 13205: {'lr': 0.00042026728291836874, 'samples': 6761472, 'steps': 13205, 'batch_loss/train': 0.7987164817750454}
+12/24/2021 17:15:59 - INFO - codeparrot_training - Step 13206: {'lr': 0.00042025574051165673, 'samples': 6761984, 'steps': 13206, 'batch_loss/train': 0.7251236925367266}
+12/24/2021 17:16:09 - INFO - codeparrot_training - Step 13207: {'lr': 0.00042024419742807206, 'samples': 6762496, 'steps': 13207, 'batch_loss/train': 0.8656305363401771}
+12/24/2021 17:16:22 - INFO - codeparrot_training - Step 13208: {'lr': 0.0004202326536676608, 'samples': 6763008, 'steps': 13208, 'batch_loss/train': 0.7224058164283633}
+12/24/2021 17:16:32 - INFO - codeparrot_training - Step 13209: {'lr': 0.0004202211092304687, 'samples': 6763520, 'steps': 13209, 'batch_loss/train': 0.7434908912982792}
+12/24/2021 17:16:43 - INFO - codeparrot_training - Step 13210: {'lr': 0.0004202095641165419, 'samples': 6764032, 'steps': 13210, 'batch_loss/train': 0.8964906767942011}
+12/24/2021 17:16:57 - INFO - codeparrot_training - Step 13211: {'lr': 0.000420198018325926, 'samples': 6764544, 'steps': 13211, 'batch_loss/train': 0.9036046036053449}
+12/24/2021 17:17:07 - INFO - codeparrot_training - Step 13212: {'lr': 0.0004201864718586671, 'samples': 6765056, 'steps': 13212, 'batch_loss/train': 0.8115497333928943}
+12/24/2021 17:17:18 - INFO - codeparrot_training - Step 13213: {'lr': 0.000420174924714811, 'samples': 6765568, 'steps': 13213, 'batch_loss/train': 0.7471444895491004}
+12/24/2021 17:17:30 - INFO - codeparrot_training - Step 13214: {'lr': 0.00042016337689440374, 'samples': 6766080, 'steps': 13214, 'batch_loss/train': 0.8473425358533859}
+12/24/2021 17:17:41 - INFO - codeparrot_training - Step 13215: {'lr': 0.00042015182839749113, 'samples': 6766592, 'steps': 13215, 'batch_loss/train': 0.7608842412009835}
+12/24/2021 17:17:51 - INFO - codeparrot_training - Step 13216: {'lr': 0.00042014027922411903, 'samples': 6767104, 'steps': 13216, 'batch_loss/train': 0.7013066569343209}
+12/24/2021 17:18:02 - INFO - codeparrot_training - Step 13217: {'lr': 0.00042012872937433347, 'samples': 6767616, 'steps': 13217, 'batch_loss/train': 0.742322466801852}
+12/24/2021 17:18:14 - INFO - codeparrot_training - Step 13218: {'lr': 0.00042011717884818037, 'samples': 6768128, 'steps': 13218, 'batch_loss/train': 0.7789000226184726}
+12/24/2021 17:18:24 - INFO - codeparrot_training - Step 13219: {'lr': 0.0004201056276457055, 'samples': 6768640, 'steps': 13219, 'batch_loss/train': 0.7577952770516276}
+12/24/2021 17:18:35 - INFO - codeparrot_training - Step 13220: {'lr': 0.0004200940757669549, 'samples': 6769152, 'steps': 13220, 'batch_loss/train': 1.5286987030413002}
+12/24/2021 17:18:49 - INFO - codeparrot_training - Step 13221: {'lr': 0.00042008252321197457, 'samples': 6769664, 'steps': 13221, 'batch_loss/train': 0.8726291283965111}
+12/24/2021 17:19:00 - INFO - codeparrot_training - Step 13222: {'lr': 0.0004200709699808103, 'samples': 6770176, 'steps': 13222, 'batch_loss/train': 0.7807420853059739}
+12/24/2021 17:19:11 - INFO - codeparrot_training - Step 13223: {'lr': 0.0004200594160735081, 'samples': 6770688, 'steps': 13223, 'batch_loss/train': 0.9366481369361281}
+12/24/2021 17:19:23 - INFO - codeparrot_training - Step 13224: {'lr': 0.0004200478614901138, 'samples': 6771200, 'steps': 13224, 'batch_loss/train': 0.8520561046898365}
+12/24/2021 17:19:33 - INFO - codeparrot_training - Step 13225: {'lr': 0.00042003630623067346, 'samples': 6771712, 'steps': 13225, 'batch_loss/train': 0.8370273830369115}
+12/24/2021 17:19:44 - INFO - codeparrot_training - Step 13226: {'lr': 0.0004200247502952329, 'samples': 6772224, 'steps': 13226, 'batch_loss/train': 0.7792091674637049}
+12/24/2021 17:19:58 - INFO - codeparrot_training - Step 13227: {'lr': 0.0004200131936838382, 'samples': 6772736, 'steps': 13227, 'batch_loss/train': 0.8585053854621947}
+12/24/2021 17:20:08 - INFO - codeparrot_training - Step 13228: {'lr': 0.0004200016363965352, 'samples': 6773248, 'steps': 13228, 'batch_loss/train': 0.8052849899977446}
+12/24/2021 17:20:19 - INFO - codeparrot_training - Step 13229: {'lr': 0.0004199900784333699, 'samples': 6773760, 'steps': 13229, 'batch_loss/train': 0.8036480685696006}
+12/24/2021 17:20:29 - INFO - codeparrot_training - Step 13230: {'lr': 0.0004199785197943883, 'samples': 6774272, 'steps': 13230, 'batch_loss/train': 1.8355634207837284}
+12/24/2021 17:20:41 - INFO - codeparrot_training - Step 13231: {'lr': 0.0004199669604796361, 'samples': 6774784, 'steps': 13231, 'batch_loss/train': 0.818474655970931}
+12/24/2021 17:20:52 - INFO - codeparrot_training - Step 13232: {'lr': 0.00041995540048915964, 'samples': 6775296, 'steps': 13232, 'batch_loss/train': 0.8032191414386034}
+12/24/2021 17:21:03 - INFO - codeparrot_training - Step 13233: {'lr': 0.00041994383982300453, 'samples': 6775808, 'steps': 13233, 'batch_loss/train': 0.8257854050025344}
+12/24/2021 17:21:15 - INFO - codeparrot_training - Step 13234: {'lr': 0.000419932278481217, 'samples': 6776320, 'steps': 13234, 'batch_loss/train': 0.8169780680909753}
+12/24/2021 17:21:26 - INFO - codeparrot_training - Step 13235: {'lr': 0.0004199207164638429, 'samples': 6776832, 'steps': 13235, 'batch_loss/train': 0.6918790945783257}
+12/24/2021 17:21:36 - INFO - codeparrot_training - Step 13236: {'lr': 0.0004199091537709281, 'samples': 6777344, 'steps': 13236, 'batch_loss/train': 0.7978520188480616}
+12/24/2021 17:21:50 - INFO - codeparrot_training - Step 13237: {'lr': 0.0004198975904025187, 'samples': 6777856, 'steps': 13237, 'batch_loss/train': 0.9272961686365306}
+12/24/2021 17:22:01 - INFO - codeparrot_training - Step 13238: {'lr': 0.0004198860263586607, 'samples': 6778368, 'steps': 13238, 'batch_loss/train': 0.8610140793025494}
+12/24/2021 17:22:11 - INFO - codeparrot_training - Step 13239: {'lr': 0.0004198744616393999, 'samples': 6778880, 'steps': 13239, 'batch_loss/train': 1.0166155565530062}
+12/24/2021 17:22:22 - INFO - codeparrot_training - Step 13240: {'lr': 0.00041986289624478234, 'samples': 6779392, 'steps': 13240, 'batch_loss/train': 0.9031170625239611}
+12/24/2021 17:22:34 - INFO - codeparrot_training - Step 13241: {'lr': 0.0004198513301748542, 'samples': 6779904, 'steps': 13241, 'batch_loss/train': 0.8386277128010988}
+12/24/2021 17:22:45 - INFO - codeparrot_training - Step 13242: {'lr': 0.00041983976342966126, 'samples': 6780416, 'steps': 13242, 'batch_loss/train': 0.9529253551736474}
+12/24/2021 17:22:56 - INFO - codeparrot_training - Step 13243: {'lr': 0.0004198281960092495, 'samples': 6780928, 'steps': 13243, 'batch_loss/train': 0.8206408582627773}
+12/24/2021 17:23:08 - INFO - codeparrot_training - Step 13244: {'lr': 0.0004198166279136649, 'samples': 6781440, 'steps': 13244, 'batch_loss/train': 0.7052513130474836}
+12/24/2021 17:23:19 - INFO - codeparrot_training - Step 13245: {'lr': 0.00041980505914295365, 'samples': 6781952, 'steps': 13245, 'batch_loss/train': 0.8615616867318749}
+12/24/2021 17:23:29 - INFO - codeparrot_training - Step 13246: {'lr': 0.0004197934896971615, 'samples': 6782464, 'steps': 13246, 'batch_loss/train': 0.8064258699305356}
+12/24/2021 17:23:41 - INFO - codeparrot_training - Step 13247: {'lr': 0.0004197819195763346, 'samples': 6782976, 'steps': 13247, 'batch_loss/train': 0.7359414137899876}
+12/24/2021 17:23:52 - INFO - codeparrot_training - Step 13248: {'lr': 0.00041977034878051887, 'samples': 6783488, 'steps': 13248, 'batch_loss/train': 0.8326709279790521}
+12/24/2021 17:24:03 - INFO - codeparrot_training - Step 13249: {'lr': 0.00041975877730976034, 'samples': 6784000, 'steps': 13249, 'batch_loss/train': 1.1424960168078542}
+12/24/2021 17:24:13 - INFO - codeparrot_training - Step 13250: {'lr': 0.00041974720516410504, 'samples': 6784512, 'steps': 13250, 'batch_loss/train': 0.9345102943480015}
+12/24/2021 17:24:27 - INFO - codeparrot_training - Step 13251: {'lr': 0.0004197356323435989, 'samples': 6785024, 'steps': 13251, 'batch_loss/train': 0.716802439186722}
+12/24/2021 17:24:38 - INFO - codeparrot_training - Step 13252: {'lr': 0.000419724058848288, 'samples': 6785536, 'steps': 13252, 'batch_loss/train': 0.8231111750937998}
+12/24/2021 17:24:48 - INFO - codeparrot_training - Step 13253: {'lr': 0.00041971248467821833, 'samples': 6786048, 'steps': 13253, 'batch_loss/train': 0.8548115501180291}
+12/24/2021 17:25:00 - INFO - codeparrot_training - Step 13254: {'lr': 0.00041970090983343587, 'samples': 6786560, 'steps': 13254, 'batch_loss/train': 0.8501289011910558}
+12/24/2021 17:25:11 - INFO - codeparrot_training - Step 13255: {'lr': 0.0004196893343139867, 'samples': 6787072, 'steps': 13255, 'batch_loss/train': 0.6921546200755984}
+12/24/2021 17:25:21 - INFO - codeparrot_training - Step 13256: {'lr': 0.0004196777581199168, 'samples': 6787584, 'steps': 13256, 'batch_loss/train': 0.7871983805671334}
+12/24/2021 17:25:36 - INFO - codeparrot_training - Step 13257: {'lr': 0.0004196661812512722, 'samples': 6788096, 'steps': 13257, 'batch_loss/train': 0.7923246412537992}
+12/24/2021 17:25:46 - INFO - codeparrot_training - Step 13258: {'lr': 0.0004196546037080989, 'samples': 6788608, 'steps': 13258, 'batch_loss/train': 0.8318671612069011}
+12/24/2021 17:25:57 - INFO - codeparrot_training - Step 13259: {'lr': 0.00041964302549044296, 'samples': 6789120, 'steps': 13259, 'batch_loss/train': 0.7719853976741433}
+12/24/2021 17:26:08 - INFO - codeparrot_training - Step 13260: {'lr': 0.0004196314465983505, 'samples': 6789632, 'steps': 13260, 'batch_loss/train': 0.7263758017215878}
+12/24/2021 17:26:20 - INFO - codeparrot_training - Step 13261: {'lr': 0.0004196198670318674, 'samples': 6790144, 'steps': 13261, 'batch_loss/train': 0.7636184627190232}
+12/24/2021 17:26:30 - INFO - codeparrot_training - Step 13262: {'lr': 0.0004196082867910397, 'samples': 6790656, 'steps': 13262, 'batch_loss/train': 0.7440125392749906}
+12/24/2021 17:26:41 - INFO - codeparrot_training - Step 13263: {'lr': 0.00041959670587591355, 'samples': 6791168, 'steps': 13263, 'batch_loss/train': 0.7965268651023507}
+12/24/2021 17:26:53 - INFO - codeparrot_training - Step 13264: {'lr': 0.0004195851242865349, 'samples': 6791680, 'steps': 13264, 'batch_loss/train': 0.6420968394959345}
+12/24/2021 17:27:04 - INFO - codeparrot_training - Step 13265: {'lr': 0.0004195735420229498, 'samples': 6792192, 'steps': 13265, 'batch_loss/train': 0.8301542485132813}
+12/24/2021 17:27:14 - INFO - codeparrot_training - Step 13266: {'lr': 0.0004195619590852045, 'samples': 6792704, 'steps': 13266, 'batch_loss/train': 0.7865244783461094}
+12/24/2021 17:27:25 - INFO - codeparrot_training - Step 13267: {'lr': 0.0004195503754733447, 'samples': 6793216, 'steps': 13267, 'batch_loss/train': 0.8419237041380256}
+12/24/2021 17:27:39 - INFO - codeparrot_training - Step 13268: {'lr': 0.00041953879118741664, 'samples': 6793728, 'steps': 13268, 'batch_loss/train': 0.822650546208024}
+12/24/2021 17:27:50 - INFO - codeparrot_training - Step 13269: {'lr': 0.0004195272062274664, 'samples': 6794240, 'steps': 13269, 'batch_loss/train': 0.7038432052358985}
+12/24/2021 17:28:01 - INFO - codeparrot_training - Step 13270: {'lr': 0.00041951562059353996, 'samples': 6794752, 'steps': 13270, 'batch_loss/train': 1.0804718043655157}
+12/24/2021 17:28:12 - INFO - codeparrot_training - Step 13271: {'lr': 0.0004195040342856835, 'samples': 6795264, 'steps': 13271, 'batch_loss/train': 0.5876227328553796}
+12/24/2021 17:28:23 - INFO - codeparrot_training - Step 13272: {'lr': 0.000419492447303943, 'samples': 6795776, 'steps': 13272, 'batch_loss/train': 0.9046404212713242}
+12/24/2021 17:28:34 - INFO - codeparrot_training - Step 13273: {'lr': 0.00041948085964836444, 'samples': 6796288, 'steps': 13273, 'batch_loss/train': 0.9339744411408901}
+12/24/2021 17:28:44 - INFO - codeparrot_training - Step 13274: {'lr': 0.000419469271318994, 'samples': 6796800, 'steps': 13274, 'batch_loss/train': 0.8228378109633923}
+12/24/2021 17:28:56 - INFO - codeparrot_training - Step 13275: {'lr': 0.00041945768231587777, 'samples': 6797312, 'steps': 13275, 'batch_loss/train': 0.8863197742030025}
+12/24/2021 17:29:07 - INFO - codeparrot_training - Step 13276: {'lr': 0.00041944609263906175, 'samples': 6797824, 'steps': 13276, 'batch_loss/train': 0.8466470362618566}
+12/24/2021 17:29:18 - INFO - codeparrot_training - Step 13277: {'lr': 0.000419434502288592, 'samples': 6798336, 'steps': 13277, 'batch_loss/train': 0.7285827847663313}
+12/24/2021 17:29:32 - INFO - codeparrot_training - Step 13278: {'lr': 0.0004194229112645148, 'samples': 6798848, 'steps': 13278, 'batch_loss/train': 0.812964313197881}
+12/24/2021 17:29:42 - INFO - codeparrot_training - Step 13279: {'lr': 0.00041941131956687596, 'samples': 6799360, 'steps': 13279, 'batch_loss/train': 1.5197123121470213}
+12/24/2021 17:29:53 - INFO - codeparrot_training - Step 13280: {'lr': 0.0004193997271957217, 'samples': 6799872, 'steps': 13280, 'batch_loss/train': 0.8432503836229444}
+12/24/2021 17:30:04 - INFO - codeparrot_training - Step 13281: {'lr': 0.00041938813415109803, 'samples': 6800384, 'steps': 13281, 'batch_loss/train': 0.8109947703778744}
+12/24/2021 17:30:16 - INFO - codeparrot_training - Step 13282: {'lr': 0.0004193765404330512, 'samples': 6800896, 'steps': 13282, 'batch_loss/train': 0.8635568963363767}
+12/24/2021 17:30:26 - INFO - codeparrot_training - Step 13283: {'lr': 0.0004193649460416271, 'samples': 6801408, 'steps': 13283, 'batch_loss/train': 0.8430218491703272}
+12/24/2021 17:30:37 - INFO - codeparrot_training - Step 13284: {'lr': 0.000419353350976872, 'samples': 6801920, 'steps': 13284, 'batch_loss/train': 0.7463191552087665}
+12/24/2021 17:30:49 - INFO - codeparrot_training - Step 13285: {'lr': 0.00041934175523883186, 'samples': 6802432, 'steps': 13285, 'batch_loss/train': 0.8257656851783395}
+12/24/2021 17:31:00 - INFO - codeparrot_training - Step 13286: {'lr': 0.00041933015882755293, 'samples': 6802944, 'steps': 13286, 'batch_loss/train': 0.6541245197877288}
+12/24/2021 17:31:10 - INFO - codeparrot_training - Step 13287: {'lr': 0.00041931856174308115, 'samples': 6803456, 'steps': 13287, 'batch_loss/train': 0.8294146803673357}
+12/24/2021 17:31:24 - INFO - codeparrot_training - Step 13288: {'lr': 0.00041930696398546273, 'samples': 6803968, 'steps': 13288, 'batch_loss/train': 0.7950731101445854}
+12/24/2021 17:31:35 - INFO - codeparrot_training - Step 13289: {'lr': 0.00041929536555474373, 'samples': 6804480, 'steps': 13289, 'batch_loss/train': 0.8013875912874937}
+12/24/2021 17:31:45 - INFO - codeparrot_training - Step 13290: {'lr': 0.00041928376645097035, 'samples': 6804992, 'steps': 13290, 'batch_loss/train': 0.7737386012449861}
+12/24/2021 17:31:56 - INFO - codeparrot_training - Step 13291: {'lr': 0.00041927216667418855, 'samples': 6805504, 'steps': 13291, 'batch_loss/train': 0.8003901885822415}
+12/24/2021 17:32:08 - INFO - codeparrot_training - Step 13292: {'lr': 0.0004192605662244445, 'samples': 6806016, 'steps': 13292, 'batch_loss/train': 0.6707771243527532}
+12/24/2021 17:32:19 - INFO - codeparrot_training - Step 13293: {'lr': 0.00041924896510178445, 'samples': 6806528, 'steps': 13293, 'batch_loss/train': 0.7174275789875537}
+12/24/2021 17:32:29 - INFO - codeparrot_training - Step 13294: {'lr': 0.00041923736330625437, 'samples': 6807040, 'steps': 13294, 'batch_loss/train': 0.7700326316989958}
+12/24/2021 17:32:41 - INFO - codeparrot_training - Step 13295: {'lr': 0.00041922576083790045, 'samples': 6807552, 'steps': 13295, 'batch_loss/train': 0.6872891215607524}
+12/24/2021 17:32:52 - INFO - codeparrot_training - Step 13296: {'lr': 0.00041921415769676873, 'samples': 6808064, 'steps': 13296, 'batch_loss/train': 0.6190993885975331}
+12/24/2021 17:33:03 - INFO - codeparrot_training - Step 13297: {'lr': 0.0004192025538829055, 'samples': 6808576, 'steps': 13297, 'batch_loss/train': 0.7996860444545746}
+12/24/2021 17:33:17 - INFO - codeparrot_training - Step 13298: {'lr': 0.00041919094939635684, 'samples': 6809088, 'steps': 13298, 'batch_loss/train': 0.9172459095716476}
+12/24/2021 17:33:27 - INFO - codeparrot_training - Step 13299: {'lr': 0.00041917934423716876, 'samples': 6809600, 'steps': 13299, 'batch_loss/train': 0.9185072458349168}
+12/24/2021 17:33:38 - INFO - codeparrot_training - Step 13300: {'lr': 0.00041916773840538753, 'samples': 6810112, 'steps': 13300, 'batch_loss/train': 0.8052965914830565}
+12/24/2021 17:33:49 - INFO - codeparrot_training - Step 13301: {'lr': 0.00041915613190105915, 'samples': 6810624, 'steps': 13301, 'batch_loss/train': 0.8304195990785956}
+12/24/2021 17:34:01 - INFO - codeparrot_training - Step 13302: {'lr': 0.00041914452472423003, 'samples': 6811136, 'steps': 13302, 'batch_loss/train': 0.8278103922493756}
+12/24/2021 17:34:11 - INFO - codeparrot_training - Step 13303: {'lr': 0.00041913291687494604, 'samples': 6811648, 'steps': 13303, 'batch_loss/train': 0.8680481966584921}
+12/24/2021 17:34:22 - INFO - codeparrot_training - Step 13304: {'lr': 0.00041912130835325347, 'samples': 6812160, 'steps': 13304, 'batch_loss/train': 0.8712839563377202}
+12/24/2021 17:34:36 - INFO - codeparrot_training - Step 13305: {'lr': 0.0004191096991591984, 'samples': 6812672, 'steps': 13305, 'batch_loss/train': 0.8498088205233216}
+12/24/2021 17:34:46 - INFO - codeparrot_training - Step 13306: {'lr': 0.00041909808929282706, 'samples': 6813184, 'steps': 13306, 'batch_loss/train': 0.807948412373662}
+12/24/2021 17:34:57 - INFO - codeparrot_training - Step 13307: {'lr': 0.0004190864787541855, 'samples': 6813696, 'steps': 13307, 'batch_loss/train': 0.856605876237154}
+12/24/2021 17:35:09 - INFO - codeparrot_training - Step 13308: {'lr': 0.00041907486754332, 'samples': 6814208, 'steps': 13308, 'batch_loss/train': 0.8302074614912271}
+12/24/2021 17:35:20 - INFO - codeparrot_training - Step 13309: {'lr': 0.0004190632556602767, 'samples': 6814720, 'steps': 13309, 'batch_loss/train': 0.7285954039543867}
+12/24/2021 17:35:30 - INFO - codeparrot_training - Step 13310: {'lr': 0.0004190516431051017, 'samples': 6815232, 'steps': 13310, 'batch_loss/train': 0.7418063841760159}
+12/24/2021 17:35:41 - INFO - codeparrot_training - Step 13311: {'lr': 0.00041904002987784117, 'samples': 6815744, 'steps': 13311, 'batch_loss/train': 0.7928233630955219}
+12/24/2021 17:35:53 - INFO - codeparrot_training - Step 13312: {'lr': 0.0004190284159785413, 'samples': 6816256, 'steps': 13312, 'batch_loss/train': 0.9133796067908406}
+12/24/2021 17:36:04 - INFO - codeparrot_training - Step 13313: {'lr': 0.0004190168014072483, 'samples': 6816768, 'steps': 13313, 'batch_loss/train': 0.8735930770635605}
+12/24/2021 17:36:14 - INFO - codeparrot_training - Step 13314: {'lr': 0.00041900518616400827, 'samples': 6817280, 'steps': 13314, 'batch_loss/train': 0.6894259739201516}
+12/24/2021 17:36:27 - INFO - codeparrot_training - Step 13315: {'lr': 0.00041899357024886754, 'samples': 6817792, 'steps': 13315, 'batch_loss/train': 0.7608071370050311}
+12/24/2021 17:36:37 - INFO - codeparrot_training - Step 13316: {'lr': 0.0004189819536618721, 'samples': 6818304, 'steps': 13316, 'batch_loss/train': 0.7466223938390613}
+12/24/2021 17:36:48 - INFO - codeparrot_training - Step 13317: {'lr': 0.0004189703364030683, 'samples': 6818816, 'steps': 13317, 'batch_loss/train': 0.8331453334540129}
+12/24/2021 17:37:02 - INFO - codeparrot_training - Step 13318: {'lr': 0.0004189587184725021, 'samples': 6819328, 'steps': 13318, 'batch_loss/train': 0.6060700166854076}
+12/24/2021 17:37:12 - INFO - codeparrot_training - Step 13319: {'lr': 0.00041894709987022, 'samples': 6819840, 'steps': 13319, 'batch_loss/train': 0.9940622511785477}
+12/24/2021 17:37:23 - INFO - codeparrot_training - Step 13320: {'lr': 0.00041893548059626786, 'samples': 6820352, 'steps': 13320, 'batch_loss/train': 0.9877703925594687}
+12/24/2021 17:37:34 - INFO - codeparrot_training - Step 13321: {'lr': 0.0004189238606506921, 'samples': 6820864, 'steps': 13321, 'batch_loss/train': 0.8252851944416761}
+12/24/2021 17:37:46 - INFO - codeparrot_training - Step 13322: {'lr': 0.00041891224003353885, 'samples': 6821376, 'steps': 13322, 'batch_loss/train': 1.49789622053504}
+12/24/2021 17:37:57 - INFO - codeparrot_training - Step 13323: {'lr': 0.0004189006187448543, 'samples': 6821888, 'steps': 13323, 'batch_loss/train': 0.8329881355166435}
+12/24/2021 17:38:07 - INFO - codeparrot_training - Step 13324: {'lr': 0.0004188889967846847, 'samples': 6822400, 'steps': 13324, 'batch_loss/train': 0.8335860809311271}
+12/24/2021 17:38:20 - INFO - codeparrot_training - Step 13325: {'lr': 0.0004188773741530762, 'samples': 6822912, 'steps': 13325, 'batch_loss/train': 0.7524183467030525}
+12/24/2021 17:38:31 - INFO - codeparrot_training - Step 13326: {'lr': 0.0004188657508500751, 'samples': 6823424, 'steps': 13326, 'batch_loss/train': 1.3128201309591532}
+12/24/2021 17:38:42 - INFO - codeparrot_training - Step 13327: {'lr': 0.00041885412687572745, 'samples': 6823936, 'steps': 13327, 'batch_loss/train': 0.8415225767530501}
+12/24/2021 17:38:55 - INFO - codeparrot_training - Step 13328: {'lr': 0.00041884250223007957, 'samples': 6824448, 'steps': 13328, 'batch_loss/train': 0.8406263990327716}
+12/24/2021 17:39:06 - INFO - codeparrot_training - Step 13329: {'lr': 0.0004188308769131777, 'samples': 6824960, 'steps': 13329, 'batch_loss/train': 0.8336712580639869}
+12/24/2021 17:39:17 - INFO - codeparrot_training - Step 13330: {'lr': 0.0004188192509250679, 'samples': 6825472, 'steps': 13330, 'batch_loss/train': 0.8500007721595466}
+12/24/2021 17:39:27 - INFO - codeparrot_training - Step 13331: {'lr': 0.00041880762426579654, 'samples': 6825984, 'steps': 13331, 'batch_loss/train': 0.7913707671687007}
+12/24/2021 17:39:39 - INFO - codeparrot_training - Step 13332: {'lr': 0.0004187959969354099, 'samples': 6826496, 'steps': 13332, 'batch_loss/train': 0.8297595670446754}
+12/24/2021 17:39:50 - INFO - codeparrot_training - Step 13333: {'lr': 0.000418784368933954, 'samples': 6827008, 'steps': 13333, 'batch_loss/train': 0.8408014131709933}
+12/24/2021 17:40:00 - INFO - codeparrot_training - Step 13334: {'lr': 0.00041877274026147525, 'samples': 6827520, 'steps': 13334, 'batch_loss/train': 0.7653535848949105}
+12/24/2021 17:40:13 - INFO - codeparrot_training - Step 13335: {'lr': 0.0004187611109180197, 'samples': 6828032, 'steps': 13335, 'batch_loss/train': 0.8307512337341905}
+12/24/2021 17:40:23 - INFO - codeparrot_training - Step 13336: {'lr': 0.00041874948090363386, 'samples': 6828544, 'steps': 13336, 'batch_loss/train': 0.7472973740659654}
+12/24/2021 17:40:34 - INFO - codeparrot_training - Step 13337: {'lr': 0.0004187378502183637, 'samples': 6829056, 'steps': 13337, 'batch_loss/train': 0.8492257352918386}
+12/24/2021 17:40:48 - INFO - codeparrot_training - Step 13338: {'lr': 0.0004187262188622556, 'samples': 6829568, 'steps': 13338, 'batch_loss/train': 0.7791922183241695}
+12/24/2021 17:40:58 - INFO - codeparrot_training - Step 13339: {'lr': 0.0004187145868353557, 'samples': 6830080, 'steps': 13339, 'batch_loss/train': 0.8387351459823549}
+12/24/2021 17:41:09 - INFO - codeparrot_training - Step 13340: {'lr': 0.0004187029541377103, 'samples': 6830592, 'steps': 13340, 'batch_loss/train': 0.8349424367770553}
+12/24/2021 17:41:20 - INFO - codeparrot_training - Step 13341: {'lr': 0.0004186913207693658, 'samples': 6831104, 'steps': 13341, 'batch_loss/train': 0.7070877784863114}
+12/24/2021 17:41:32 - INFO - codeparrot_training - Step 13342: {'lr': 0.00041867968673036814, 'samples': 6831616, 'steps': 13342, 'batch_loss/train': 0.8450437178835273}
+12/24/2021 17:41:42 - INFO - codeparrot_training - Step 13343: {'lr': 0.00041866805202076386, 'samples': 6832128, 'steps': 13343, 'batch_loss/train': 0.8562998804263771}
+12/24/2021 17:41:53 - INFO - codeparrot_training - Step 13344: {'lr': 0.000418656416640599, 'samples': 6832640, 'steps': 13344, 'batch_loss/train': 0.7734531089663506}
+12/24/2021 17:42:07 - INFO - codeparrot_training - Step 13345: {'lr': 0.00041864478058991993, 'samples': 6833152, 'steps': 13345, 'batch_loss/train': 0.8757303152233362}
+12/24/2021 17:42:18 - INFO - codeparrot_training - Step 13346: {'lr': 0.0004186331438687729, 'samples': 6833664, 'steps': 13346, 'batch_loss/train': 0.8191946353763342}
+12/24/2021 17:42:28 - INFO - codeparrot_training - Step 13347: {'lr': 0.0004186215064772042, 'samples': 6834176, 'steps': 13347, 'batch_loss/train': 0.6873598594684154}
+12/24/2021 17:42:41 - INFO - codeparrot_training - Step 13348: {'lr': 0.0004186098684152601, 'samples': 6834688, 'steps': 13348, 'batch_loss/train': 0.8036960307508707}
+12/24/2021 17:42:52 - INFO - codeparrot_training - Step 13349: {'lr': 0.00041859822968298667, 'samples': 6835200, 'steps': 13349, 'batch_loss/train': 0.6913217566907406}
+12/24/2021 17:43:02 - INFO - codeparrot_training - Step 13350: {'lr': 0.00041858659028043047, 'samples': 6835712, 'steps': 13350, 'batch_loss/train': 0.8616676316596568}
+12/24/2021 17:43:13 - INFO - codeparrot_training - Step 13351: {'lr': 0.00041857495020763757, 'samples': 6836224, 'steps': 13351, 'batch_loss/train': 0.8809795812703669}
+12/24/2021 17:43:25 - INFO - codeparrot_training - Step 13352: {'lr': 0.00041856330946465437, 'samples': 6836736, 'steps': 13352, 'batch_loss/train': 0.7497248114086688}
+12/24/2021 17:43:35 - INFO - codeparrot_training - Step 13353: {'lr': 0.000418551668051527, 'samples': 6837248, 'steps': 13353, 'batch_loss/train': 0.8533205271232873}
+12/24/2021 17:43:46 - INFO - codeparrot_training - Step 13354: {'lr': 0.00041854002596830196, 'samples': 6837760, 'steps': 13354, 'batch_loss/train': 0.7701509715989232}
+12/24/2021 17:43:58 - INFO - codeparrot_training - Step 13355: {'lr': 0.0004185283832150254, 'samples': 6838272, 'steps': 13355, 'batch_loss/train': 0.7721464815549552}
+12/24/2021 17:44:09 - INFO - codeparrot_training - Step 13356: {'lr': 0.0004185167397917436, 'samples': 6838784, 'steps': 13356, 'batch_loss/train': 0.8191412430023775}
+12/24/2021 17:44:19 - INFO - codeparrot_training - Step 13357: {'lr': 0.00041850509569850284, 'samples': 6839296, 'steps': 13357, 'batch_loss/train': 0.6810070211067796}
+12/24/2021 17:44:33 - INFO - codeparrot_training - Step 13358: {'lr': 0.0004184934509353495, 'samples': 6839808, 'steps': 13358, 'batch_loss/train': 0.76257219677791}
+12/24/2021 17:44:44 - INFO - codeparrot_training - Step 13359: {'lr': 0.0004184818055023297, 'samples': 6840320, 'steps': 13359, 'batch_loss/train': 0.765519677195698}
+12/24/2021 17:44:54 - INFO - codeparrot_training - Step 13360: {'lr': 0.00041847015939949, 'samples': 6840832, 'steps': 13360, 'batch_loss/train': 0.9343729726970196}
+12/24/2021 17:45:05 - INFO - codeparrot_training - Step 13361: {'lr': 0.0004184585126268765, 'samples': 6841344, 'steps': 13361, 'batch_loss/train': 0.8133214060217142}
+12/24/2021 17:45:17 - INFO - codeparrot_training - Step 13362: {'lr': 0.00041844686518453556, 'samples': 6841856, 'steps': 13362, 'batch_loss/train': 0.7686606161296368}
+12/24/2021 17:45:28 - INFO - codeparrot_training - Step 13363: {'lr': 0.00041843521707251354, 'samples': 6842368, 'steps': 13363, 'batch_loss/train': 0.7544627776369452}
+12/24/2021 17:45:38 - INFO - codeparrot_training - Step 13364: {'lr': 0.0004184235682908566, 'samples': 6842880, 'steps': 13364, 'batch_loss/train': 0.8090066853910685}
+12/24/2021 17:45:50 - INFO - codeparrot_training - Step 13365: {'lr': 0.0004184119188396112, 'samples': 6843392, 'steps': 13365, 'batch_loss/train': 0.8371434365399182}
+12/24/2021 17:46:01 - INFO - codeparrot_training - Step 13366: {'lr': 0.0004184002687188236, 'samples': 6843904, 'steps': 13366, 'batch_loss/train': 0.8754458893090487}
+12/24/2021 17:46:12 - INFO - codeparrot_training - Step 13367: {'lr': 0.0004183886179285401, 'samples': 6844416, 'steps': 13367, 'batch_loss/train': 0.8907420560717583}
+12/24/2021 17:46:25 - INFO - codeparrot_training - Step 13368: {'lr': 0.0004183769664688071, 'samples': 6844928, 'steps': 13368, 'batch_loss/train': 0.8635064223781228}
+12/24/2021 17:46:36 - INFO - codeparrot_training - Step 13369: {'lr': 0.0004183653143396708, 'samples': 6845440, 'steps': 13369, 'batch_loss/train': 0.7956645516678691}
+12/24/2021 17:46:47 - INFO - codeparrot_training - Step 13370: {'lr': 0.0004183536615411775, 'samples': 6845952, 'steps': 13370, 'batch_loss/train': 0.8054405869916081}
+12/24/2021 17:46:57 - INFO - codeparrot_training - Step 13371: {'lr': 0.00041834200807337377, 'samples': 6846464, 'steps': 13371, 'batch_loss/train': 0.8345984816551208}
+12/24/2021 17:47:10 - INFO - codeparrot_training - Step 13372: {'lr': 0.0004183303539363057, 'samples': 6846976, 'steps': 13372, 'batch_loss/train': 0.7045520239043981}
+12/24/2021 17:47:20 - INFO - codeparrot_training - Step 13373: {'lr': 0.00041831869913001976, 'samples': 6847488, 'steps': 13373, 'batch_loss/train': 0.9016745518893003}
+12/24/2021 17:47:31 - INFO - codeparrot_training - Step 13374: {'lr': 0.00041830704365456215, 'samples': 6848000, 'steps': 13374, 'batch_loss/train': 0.8175651987548918}
+12/24/2021 17:47:45 - INFO - codeparrot_training - Step 13375: {'lr': 0.0004182953875099793, 'samples': 6848512, 'steps': 13375, 'batch_loss/train': 0.9010699614882469}
+12/24/2021 17:47:55 - INFO - codeparrot_training - Step 13376: {'lr': 0.00041828373069631756, 'samples': 6849024, 'steps': 13376, 'batch_loss/train': 0.7926432113163173}
+12/24/2021 17:48:06 - INFO - codeparrot_training - Step 13377: {'lr': 0.00041827207321362323, 'samples': 6849536, 'steps': 13377, 'batch_loss/train': 0.8869187328964472}
+12/24/2021 17:48:18 - INFO - codeparrot_training - Step 13378: {'lr': 0.00041826041506194266, 'samples': 6850048, 'steps': 13378, 'batch_loss/train': 0.8356825411319733}
+12/24/2021 17:48:29 - INFO - codeparrot_training - Step 13379: {'lr': 0.00041824875624132225, 'samples': 6850560, 'steps': 13379, 'batch_loss/train': 0.7507787146605551}
+12/24/2021 17:48:39 - INFO - codeparrot_training - Step 13380: {'lr': 0.00041823709675180835, 'samples': 6851072, 'steps': 13380, 'batch_loss/train': 0.7026171020697802}
+12/24/2021 17:48:50 - INFO - codeparrot_training - Step 13381: {'lr': 0.00041822543659344715, 'samples': 6851584, 'steps': 13381, 'batch_loss/train': 0.7332087230170146}
+12/24/2021 17:49:02 - INFO - codeparrot_training - Step 13382: {'lr': 0.0004182137757662852, 'samples': 6852096, 'steps': 13382, 'batch_loss/train': 0.8823283137753606}
+12/24/2021 17:49:13 - INFO - codeparrot_training - Step 13383: {'lr': 0.0004182021142703688, 'samples': 6852608, 'steps': 13383, 'batch_loss/train': 0.8496929779648781}
+12/24/2021 17:49:23 - INFO - codeparrot_training - Step 13384: {'lr': 0.00041819045210574437, 'samples': 6853120, 'steps': 13384, 'batch_loss/train': 0.7568288557231426}
+12/24/2021 17:49:37 - INFO - codeparrot_training - Step 13385: {'lr': 0.0004181787892724581, 'samples': 6853632, 'steps': 13385, 'batch_loss/train': 0.8010180708952248}
+12/24/2021 17:49:48 - INFO - codeparrot_training - Step 13386: {'lr': 0.0004181671257705565, 'samples': 6854144, 'steps': 13386, 'batch_loss/train': 0.8819185774773359}
+12/24/2021 17:49:59 - INFO - codeparrot_training - Step 13387: {'lr': 0.00041815546160008587, 'samples': 6854656, 'steps': 13387, 'batch_loss/train': 0.7572279986925423}
+12/24/2021 17:50:11 - INFO - codeparrot_training - Step 13388: {'lr': 0.0004181437967610927, 'samples': 6855168, 'steps': 13388, 'batch_loss/train': 0.8902539378032088}
+12/24/2021 17:50:21 - INFO - codeparrot_training - Step 13389: {'lr': 0.00041813213125362325, 'samples': 6855680, 'steps': 13389, 'batch_loss/train': 0.7840015487745404}
+12/24/2021 17:50:32 - INFO - codeparrot_training - Step 13390: {'lr': 0.00041812046507772396, 'samples': 6856192, 'steps': 13390, 'batch_loss/train': 0.8718201937153935}
+12/24/2021 17:50:43 - INFO - codeparrot_training - Step 13391: {'lr': 0.0004181087982334411, 'samples': 6856704, 'steps': 13391, 'batch_loss/train': 0.7378954140003771}
+12/24/2021 17:50:55 - INFO - codeparrot_training - Step 13392: {'lr': 0.0004180971307208212, 'samples': 6857216, 'steps': 13392, 'batch_loss/train': 0.7407225521747023}
+12/24/2021 17:51:06 - INFO - codeparrot_training - Step 13393: {'lr': 0.0004180854625399105, 'samples': 6857728, 'steps': 13393, 'batch_loss/train': 0.9035733994096518}
+12/24/2021 17:51:16 - INFO - codeparrot_training - Step 13394: {'lr': 0.00041807379369075557, 'samples': 6858240, 'steps': 13394, 'batch_loss/train': 0.7611780995503068}
+12/24/2021 17:51:28 - INFO - codeparrot_training - Step 13395: {'lr': 0.00041806212417340265, 'samples': 6858752, 'steps': 13395, 'batch_loss/train': 0.7739942250773311}
+12/24/2021 17:51:39 - INFO - codeparrot_training - Step 13396: {'lr': 0.0004180504539878982, 'samples': 6859264, 'steps': 13396, 'batch_loss/train': 0.8764342637732625}
+12/24/2021 17:51:50 - INFO - codeparrot_training - Step 13397: {'lr': 0.00041803878313428856, 'samples': 6859776, 'steps': 13397, 'batch_loss/train': 0.8011249527335167}
+12/24/2021 17:52:03 - INFO - codeparrot_training - Step 13398: {'lr': 0.0004180271116126202, 'samples': 6860288, 'steps': 13398, 'batch_loss/train': 0.8016375675797462}
+12/24/2021 17:52:14 - INFO - codeparrot_training - Step 13399: {'lr': 0.0004180154394229395, 'samples': 6860800, 'steps': 13399, 'batch_loss/train': 0.8022057870402932}
+12/24/2021 17:52:25 - INFO - codeparrot_training - Step 13400: {'lr': 0.0004180037665652928, 'samples': 6861312, 'steps': 13400, 'batch_loss/train': 0.6648685880936682}
+12/24/2021 17:52:37 - INFO - codeparrot_training - Step 13401: {'lr': 0.0004179920930397266, 'samples': 6861824, 'steps': 13401, 'batch_loss/train': 0.8426976129412651}
+12/24/2021 17:52:47 - INFO - codeparrot_training - Step 13402: {'lr': 0.0004179804188462872, 'samples': 6862336, 'steps': 13402, 'batch_loss/train': 0.7290635666577145}
+12/24/2021 17:52:58 - INFO - codeparrot_training - Step 13403: {'lr': 0.00041796874398502117, 'samples': 6862848, 'steps': 13403, 'batch_loss/train': 0.8328350745141506}
+12/24/2021 17:53:08 - INFO - codeparrot_training - Step 13404: {'lr': 0.0004179570684559749, 'samples': 6863360, 'steps': 13404, 'batch_loss/train': 0.8729202635586262}
+12/24/2021 17:53:21 - INFO - codeparrot_training - Step 13405: {'lr': 0.0004179453922591946, 'samples': 6863872, 'steps': 13405, 'batch_loss/train': 0.7957298546098173}
+12/24/2021 17:53:31 - INFO - codeparrot_training - Step 13406: {'lr': 0.0004179337153947269, 'samples': 6864384, 'steps': 13406, 'batch_loss/train': 0.8176814126782119}
+12/24/2021 17:53:42 - INFO - codeparrot_training - Step 13407: {'lr': 0.00041792203786261814, 'samples': 6864896, 'steps': 13407, 'batch_loss/train': 0.9412024901248515}
+12/24/2021 17:53:55 - INFO - codeparrot_training - Step 13408: {'lr': 0.0004179103596629148, 'samples': 6865408, 'steps': 13408, 'batch_loss/train': 0.8411218301625922}
+12/24/2021 17:54:06 - INFO - codeparrot_training - Step 13409: {'lr': 0.00041789868079566316, 'samples': 6865920, 'steps': 13409, 'batch_loss/train': 0.8496462875045836}
+12/24/2021 17:54:17 - INFO - codeparrot_training - Step 13410: {'lr': 0.0004178870012609099, 'samples': 6866432, 'steps': 13410, 'batch_loss/train': 0.8245499702170491}
+12/24/2021 17:54:29 - INFO - codeparrot_training - Step 13411: {'lr': 0.0004178753210587012, 'samples': 6866944, 'steps': 13411, 'batch_loss/train': 0.8328776822891086}
+12/24/2021 17:54:39 - INFO - codeparrot_training - Step 13412: {'lr': 0.0004178636401890837, 'samples': 6867456, 'steps': 13412, 'batch_loss/train': 0.848421691916883}
+12/24/2021 17:54:50 - INFO - codeparrot_training - Step 13413: {'lr': 0.0004178519586521037, 'samples': 6867968, 'steps': 13413, 'batch_loss/train': 0.8031352516263723}
+12/24/2021 17:55:01 - INFO - codeparrot_training - Step 13414: {'lr': 0.0004178402764478077, 'samples': 6868480, 'steps': 13414, 'batch_loss/train': 0.7918480960652232}
+12/24/2021 17:55:15 - INFO - codeparrot_training - Step 13415: {'lr': 0.00041782859357624217, 'samples': 6868992, 'steps': 13415, 'batch_loss/train': 0.7259304998442531}
+12/24/2021 17:55:25 - INFO - codeparrot_training - Step 13416: {'lr': 0.0004178169100374535, 'samples': 6869504, 'steps': 13416, 'batch_loss/train': 0.8813172243535519}
+12/24/2021 17:55:36 - INFO - codeparrot_training - Step 13417: {'lr': 0.00041780522583148816, 'samples': 6870016, 'steps': 13417, 'batch_loss/train': 0.8207487808540463}
+12/24/2021 17:55:48 - INFO - codeparrot_training - Step 13418: {'lr': 0.00041779354095839257, 'samples': 6870528, 'steps': 13418, 'batch_loss/train': 0.7831490007229149}
+12/24/2021 17:55:59 - INFO - codeparrot_training - Step 13419: {'lr': 0.00041778185541821325, 'samples': 6871040, 'steps': 13419, 'batch_loss/train': 0.8219869141466916}
+12/24/2021 17:56:09 - INFO - codeparrot_training - Step 13420: {'lr': 0.0004177701692109966, 'samples': 6871552, 'steps': 13420, 'batch_loss/train': 0.6229864414199255}
+12/24/2021 17:56:21 - INFO - codeparrot_training - Step 13421: {'lr': 0.00041775848233678917, 'samples': 6872064, 'steps': 13421, 'batch_loss/train': 0.8627431849017739}
+12/24/2021 17:56:32 - INFO - codeparrot_training - Step 13422: {'lr': 0.00041774679479563727, 'samples': 6872576, 'steps': 13422, 'batch_loss/train': 0.8289665686897933}
+12/24/2021 17:56:43 - INFO - codeparrot_training - Step 13423: {'lr': 0.0004177351065875875, 'samples': 6873088, 'steps': 13423, 'batch_loss/train': 0.8349010618403554}
+12/24/2021 17:56:57 - INFO - codeparrot_training - Step 13424: {'lr': 0.00041772341771268627, 'samples': 6873600, 'steps': 13424, 'batch_loss/train': 0.8185014012269676}
+12/24/2021 17:57:07 - INFO - codeparrot_training - Step 13425: {'lr': 0.00041771172817098003, 'samples': 6874112, 'steps': 13425, 'batch_loss/train': 0.7164841839112341}
+12/24/2021 17:57:18 - INFO - codeparrot_training - Step 13426: {'lr': 0.0004177000379625153, 'samples': 6874624, 'steps': 13426, 'batch_loss/train': 0.8300656527280807}
+12/24/2021 17:57:28 - INFO - codeparrot_training - Step 13427: {'lr': 0.0004176883470873386, 'samples': 6875136, 'steps': 13427, 'batch_loss/train': 0.7777676025871187}
+12/24/2021 17:57:41 - INFO - codeparrot_training - Step 13428: {'lr': 0.00041767665554549627, 'samples': 6875648, 'steps': 13428, 'batch_loss/train': 0.8375170149374753}
+12/24/2021 17:57:51 - INFO - codeparrot_training - Step 13429: {'lr': 0.00041766496333703497, 'samples': 6876160, 'steps': 13429, 'batch_loss/train': 0.7536641955375671}
+12/24/2021 17:58:02 - INFO - codeparrot_training - Step 13430: {'lr': 0.000417653270462001, 'samples': 6876672, 'steps': 13430, 'batch_loss/train': 0.7740793759003282}
+12/24/2021 17:58:15 - INFO - codeparrot_training - Step 13431: {'lr': 0.0004176415769204409, 'samples': 6877184, 'steps': 13431, 'batch_loss/train': 0.8555116085335612}
+12/24/2021 17:58:26 - INFO - codeparrot_training - Step 13432: {'lr': 0.0004176298827124013, 'samples': 6877696, 'steps': 13432, 'batch_loss/train': 0.8157337317243218}
+12/24/2021 17:58:36 - INFO - codeparrot_training - Step 13433: {'lr': 0.0004176181878379285, 'samples': 6878208, 'steps': 13433, 'batch_loss/train': 0.8766613742336631}
+12/24/2021 17:58:47 - INFO - codeparrot_training - Step 13434: {'lr': 0.0004176064922970691, 'samples': 6878720, 'steps': 13434, 'batch_loss/train': 1.316168317105621}
+12/24/2021 17:59:00 - INFO - codeparrot_training - Step 13435: {'lr': 0.0004175947960898696, 'samples': 6879232, 'steps': 13435, 'batch_loss/train': 0.8376758471131325}
+12/24/2021 17:59:11 - INFO - codeparrot_training - Step 13436: {'lr': 0.0004175830992163764, 'samples': 6879744, 'steps': 13436, 'batch_loss/train': 0.8476493777707219}
+12/24/2021 17:59:22 - INFO - codeparrot_training - Step 13437: {'lr': 0.0004175714016766361, 'samples': 6880256, 'steps': 13437, 'batch_loss/train': 0.7847469444386661}
+12/24/2021 17:59:34 - INFO - codeparrot_training - Step 13438: {'lr': 0.0004175597034706952, 'samples': 6880768, 'steps': 13438, 'batch_loss/train': 0.6914884564466774}
+12/24/2021 17:59:44 - INFO - codeparrot_training - Step 13439: {'lr': 0.0004175480045986002, 'samples': 6881280, 'steps': 13439, 'batch_loss/train': 0.844203433021903}
+12/24/2021 17:59:55 - INFO - codeparrot_training - Step 13440: {'lr': 0.0004175363050603976, 'samples': 6881792, 'steps': 13440, 'batch_loss/train': 0.8065213989466429}
+12/24/2021 18:00:07 - INFO - codeparrot_training - Step 13441: {'lr': 0.0004175246048561339, 'samples': 6882304, 'steps': 13441, 'batch_loss/train': 0.8238637167960405}
+12/24/2021 18:00:18 - INFO - codeparrot_training - Step 13442: {'lr': 0.0004175129039858556, 'samples': 6882816, 'steps': 13442, 'batch_loss/train': 0.8412407729774714}
+12/24/2021 18:00:28 - INFO - codeparrot_training - Step 13443: {'lr': 0.00041750120244960924, 'samples': 6883328, 'steps': 13443, 'batch_loss/train': 0.7507714862003922}
+12/24/2021 18:00:39 - INFO - codeparrot_training - Step 13444: {'lr': 0.00041748950024744134, 'samples': 6883840, 'steps': 13444, 'batch_loss/train': 0.7733234157785773}
+12/24/2021 18:00:53 - INFO - codeparrot_training - Step 13445: {'lr': 0.0004174777973793985, 'samples': 6884352, 'steps': 13445, 'batch_loss/train': 0.8829414653591812}
+12/24/2021 18:01:03 - INFO - codeparrot_training - Step 13446: {'lr': 0.0004174660938455271, 'samples': 6884864, 'steps': 13446, 'batch_loss/train': 0.823197865858674}
+12/24/2021 18:01:14 - INFO - codeparrot_training - Step 13447: {'lr': 0.00041745438964587377, 'samples': 6885376, 'steps': 13447, 'batch_loss/train': 0.797347885556519}
+12/24/2021 18:01:26 - INFO - codeparrot_training - Step 13448: {'lr': 0.00041744268478048505, 'samples': 6885888, 'steps': 13448, 'batch_loss/train': 0.7927600429393351}
+12/24/2021 18:01:37 - INFO - codeparrot_training - Step 13449: {'lr': 0.0004174309792494073, 'samples': 6886400, 'steps': 13449, 'batch_loss/train': 0.8191743725910783}
+12/24/2021 18:01:47 - INFO - codeparrot_training - Step 13450: {'lr': 0.0004174192730526874, 'samples': 6886912, 'steps': 13450, 'batch_loss/train': 0.7274933671578765}
+12/24/2021 18:01:59 - INFO - codeparrot_training - Step 13451: {'lr': 0.00041740756619037156, 'samples': 6887424, 'steps': 13451, 'batch_loss/train': 0.8235009191557765}
+12/24/2021 18:02:10 - INFO - codeparrot_training - Step 13452: {'lr': 0.00041739585866250653, 'samples': 6887936, 'steps': 13452, 'batch_loss/train': 0.8182401545345783}
+12/24/2021 18:02:21 - INFO - codeparrot_training - Step 13453: {'lr': 0.0004173841504691387, 'samples': 6888448, 'steps': 13453, 'batch_loss/train': 0.8768950831145048}
+12/24/2021 18:02:31 - INFO - codeparrot_training - Step 13454: {'lr': 0.00041737244161031467, 'samples': 6888960, 'steps': 13454, 'batch_loss/train': 0.8934615729376674}
+12/24/2021 18:02:45 - INFO - codeparrot_training - Step 13455: {'lr': 0.0004173607320860811, 'samples': 6889472, 'steps': 13455, 'batch_loss/train': 0.8441444272175431}
+12/24/2021 18:02:56 - INFO - codeparrot_training - Step 13456: {'lr': 0.0004173490218964844, 'samples': 6889984, 'steps': 13456, 'batch_loss/train': 0.7794137524906546}
+12/24/2021 18:03:07 - INFO - codeparrot_training - Step 13457: {'lr': 0.0004173373110415711, 'samples': 6890496, 'steps': 13457, 'batch_loss/train': 0.8137453380040824}
+12/24/2021 18:03:19 - INFO - codeparrot_training - Step 13458: {'lr': 0.00041732559952138796, 'samples': 6891008, 'steps': 13458, 'batch_loss/train': 0.7862089965492487}
+12/24/2021 18:03:29 - INFO - codeparrot_training - Step 13459: {'lr': 0.0004173138873359813, 'samples': 6891520, 'steps': 13459, 'batch_loss/train': 0.7879939554259181}
+12/24/2021 18:03:40 - INFO - codeparrot_training - Step 13460: {'lr': 0.0004173021744853979, 'samples': 6892032, 'steps': 13460, 'batch_loss/train': 0.7839152151718736}
+12/24/2021 18:03:54 - INFO - codeparrot_training - Step 13461: {'lr': 0.0004172904609696842, 'samples': 6892544, 'steps': 13461, 'batch_loss/train': 0.8495272658765316}
+12/24/2021 18:04:04 - INFO - codeparrot_training - Step 13462: {'lr': 0.0004172787467888868, 'samples': 6893056, 'steps': 13462, 'batch_loss/train': 0.7569084241986275}
+12/24/2021 18:04:15 - INFO - codeparrot_training - Step 13463: {'lr': 0.0004172670319430523, 'samples': 6893568, 'steps': 13463, 'batch_loss/train': 0.8081970158964396}
+12/24/2021 18:04:26 - INFO - codeparrot_training - Step 13464: {'lr': 0.00041725531643222716, 'samples': 6894080, 'steps': 13464, 'batch_loss/train': 0.8522781739011407}
+12/24/2021 18:04:38 - INFO - codeparrot_training - Step 13465: {'lr': 0.000417243600256458, 'samples': 6894592, 'steps': 13465, 'batch_loss/train': 0.7486175802769139}
+12/24/2021 18:04:48 - INFO - codeparrot_training - Step 13466: {'lr': 0.00041723188341579153, 'samples': 6895104, 'steps': 13466, 'batch_loss/train': 0.8573319837450981}
+12/24/2021 18:04:59 - INFO - codeparrot_training - Step 13467: {'lr': 0.00041722016591027423, 'samples': 6895616, 'steps': 13467, 'batch_loss/train': 0.8864365788176656}
+12/24/2021 18:05:11 - INFO - codeparrot_training - Step 13468: {'lr': 0.0004172084477399526, 'samples': 6896128, 'steps': 13468, 'batch_loss/train': 0.8727437341585755}
+12/24/2021 18:05:22 - INFO - codeparrot_training - Step 13469: {'lr': 0.0004171967289048734, 'samples': 6896640, 'steps': 13469, 'batch_loss/train': 0.6809875041944906}
+12/24/2021 18:05:32 - INFO - codeparrot_training - Step 13470: {'lr': 0.0004171850094050831, 'samples': 6897152, 'steps': 13470, 'batch_loss/train': 0.8569710375741124}
+12/24/2021 18:05:45 - INFO - codeparrot_training - Step 13471: {'lr': 0.00041717328924062837, 'samples': 6897664, 'steps': 13471, 'batch_loss/train': 0.7467970867874101}
+12/24/2021 18:05:55 - INFO - codeparrot_training - Step 13472: {'lr': 0.0004171615684115557, 'samples': 6898176, 'steps': 13472, 'batch_loss/train': 0.5932987760170363}
+12/24/2021 18:06:06 - INFO - codeparrot_training - Step 13473: {'lr': 0.0004171498469179118, 'samples': 6898688, 'steps': 13473, 'batch_loss/train': 0.8325558914802969}
+12/24/2021 18:06:20 - INFO - codeparrot_training - Step 13474: {'lr': 0.00041713812475974323, 'samples': 6899200, 'steps': 13474, 'batch_loss/train': 0.7193480203859508}
+12/24/2021 18:06:31 - INFO - codeparrot_training - Step 13475: {'lr': 0.00041712640193709654, 'samples': 6899712, 'steps': 13475, 'batch_loss/train': 0.8736268309876323}
+12/24/2021 18:06:41 - INFO - codeparrot_training - Step 13476: {'lr': 0.0004171146784500185, 'samples': 6900224, 'steps': 13476, 'batch_loss/train': 0.9661603420972824}
+12/24/2021 18:06:52 - INFO - codeparrot_training - Step 13477: {'lr': 0.0004171029542985554, 'samples': 6900736, 'steps': 13477, 'batch_loss/train': 1.1155674736946821}
+12/24/2021 18:07:04 - INFO - codeparrot_training - Step 13478: {'lr': 0.0004170912294827542, 'samples': 6901248, 'steps': 13478, 'batch_loss/train': 0.7038574302569032}
+12/24/2021 18:07:15 - INFO - codeparrot_training - Step 13479: {'lr': 0.0004170795040026614, 'samples': 6901760, 'steps': 13479, 'batch_loss/train': 0.7300950079225004}
+12/24/2021 18:07:25 - INFO - codeparrot_training - Step 13480: {'lr': 0.00041706777785832346, 'samples': 6902272, 'steps': 13480, 'batch_loss/train': 0.8460462652146816}
+12/24/2021 18:07:37 - INFO - codeparrot_training - Step 13481: {'lr': 0.0004170560510497872, 'samples': 6902784, 'steps': 13481, 'batch_loss/train': 0.66613624477759}
+12/24/2021 18:07:48 - INFO - codeparrot_training - Step 13482: {'lr': 0.0004170443235770991, 'samples': 6903296, 'steps': 13482, 'batch_loss/train': 0.74916025204584}
+12/24/2021 18:07:59 - INFO - codeparrot_training - Step 13483: {'lr': 0.0004170325954403058, 'samples': 6903808, 'steps': 13483, 'batch_loss/train': 0.8341453336179256}
+12/24/2021 18:08:12 - INFO - codeparrot_training - Step 13484: {'lr': 0.00041702086663945404, 'samples': 6904320, 'steps': 13484, 'batch_loss/train': 0.8342033205553889}
+12/24/2021 18:08:23 - INFO - codeparrot_training - Step 13485: {'lr': 0.00041700913717459035, 'samples': 6904832, 'steps': 13485, 'batch_loss/train': 0.7946330029517412}
+12/24/2021 18:08:34 - INFO - codeparrot_training - Step 13486: {'lr': 0.0004169974070457614, 'samples': 6905344, 'steps': 13486, 'batch_loss/train': 0.9165064059197903}
+12/24/2021 18:08:44 - INFO - codeparrot_training - Step 13487: {'lr': 0.00041698567625301385, 'samples': 6905856, 'steps': 13487, 'batch_loss/train': 0.9000625032931566}
+12/24/2021 18:08:57 - INFO - codeparrot_training - Step 13488: {'lr': 0.0004169739447963943, 'samples': 6906368, 'steps': 13488, 'batch_loss/train': 0.967975964769721}
+12/24/2021 18:09:07 - INFO - codeparrot_training - Step 13489: {'lr': 0.0004169622126759494, 'samples': 6906880, 'steps': 13489, 'batch_loss/train': 0.7822508821263909}
+12/24/2021 18:09:18 - INFO - codeparrot_training - Step 13490: {'lr': 0.00041695047989172567, 'samples': 6907392, 'steps': 13490, 'batch_loss/train': 0.6566777806729078}
+12/24/2021 18:09:32 - INFO - codeparrot_training - Step 13491: {'lr': 0.00041693874644376997, 'samples': 6907904, 'steps': 13491, 'batch_loss/train': 0.7683784570544958}
+12/24/2021 18:09:43 - INFO - codeparrot_training - Step 13492: {'lr': 0.0004169270123321288, 'samples': 6908416, 'steps': 13492, 'batch_loss/train': 0.808711014688015}
+12/24/2021 18:09:53 - INFO - codeparrot_training - Step 13493: {'lr': 0.00041691527755684894, 'samples': 6908928, 'steps': 13493, 'batch_loss/train': 0.8252057433128357}
+12/24/2021 18:10:05 - INFO - codeparrot_training - Step 13494: {'lr': 0.00041690354211797686, 'samples': 6909440, 'steps': 13494, 'batch_loss/train': 0.7961625498719513}
+12/24/2021 18:10:16 - INFO - codeparrot_training - Step 13495: {'lr': 0.00041689180601555943, 'samples': 6909952, 'steps': 13495, 'batch_loss/train': 0.7735111592337489}
+12/24/2021 18:10:27 - INFO - codeparrot_training - Step 13496: {'lr': 0.00041688006924964314, 'samples': 6910464, 'steps': 13496, 'batch_loss/train': 0.7838389207608998}
+12/24/2021 18:10:37 - INFO - codeparrot_training - Step 13497: {'lr': 0.00041686833182027463, 'samples': 6910976, 'steps': 13497, 'batch_loss/train': 0.8607270494103432}
+12/24/2021 18:10:49 - INFO - codeparrot_training - Step 13498: {'lr': 0.0004168565937275007, 'samples': 6911488, 'steps': 13498, 'batch_loss/train': 0.8828485663980246}
+12/24/2021 18:11:00 - INFO - codeparrot_training - Step 13499: {'lr': 0.00041684485497136804, 'samples': 6912000, 'steps': 13499, 'batch_loss/train': 0.957943425513804}
+12/24/2021 18:11:11 - INFO - codeparrot_training - Step 13500: {'lr': 0.00041683311555192314, 'samples': 6912512, 'steps': 13500, 'batch_loss/train': 0.7643457055091858}
+12/24/2021 18:11:23 - INFO - codeparrot_training - Step 13501: {'lr': 0.00041682137546921274, 'samples': 6913024, 'steps': 13501, 'batch_loss/train': 0.806865626713261}
+12/24/2021 18:11:33 - INFO - codeparrot_training - Step 13502: {'lr': 0.0004168096347232836, 'samples': 6913536, 'steps': 13502, 'batch_loss/train': 0.8002302469685674}
+12/24/2021 18:11:44 - INFO - codeparrot_training - Step 13503: {'lr': 0.00041679789331418234, 'samples': 6914048, 'steps': 13503, 'batch_loss/train': 0.8567804843187332}
+12/24/2021 18:11:58 - INFO - codeparrot_training - Step 13504: {'lr': 0.00041678615124195564, 'samples': 6914560, 'steps': 13504, 'batch_loss/train': 0.7756170593202114}
+12/24/2021 18:12:08 - INFO - codeparrot_training - Step 13505: {'lr': 0.0004167744085066502, 'samples': 6915072, 'steps': 13505, 'batch_loss/train': 0.8307293020188808}
+12/24/2021 18:12:19 - INFO - codeparrot_training - Step 13506: {'lr': 0.0004167626651083126, 'samples': 6915584, 'steps': 13506, 'batch_loss/train': 0.7335264547728002}
+12/24/2021 18:12:30 - INFO - codeparrot_training - Step 13507: {'lr': 0.0004167509210469896, 'samples': 6916096, 'steps': 13507, 'batch_loss/train': 0.8580498928204179}
+12/24/2021 18:12:42 - INFO - codeparrot_training - Step 13508: {'lr': 0.000416739176322728, 'samples': 6916608, 'steps': 13508, 'batch_loss/train': 0.7321929335594177}
+12/24/2021 18:12:53 - INFO - codeparrot_training - Step 13509: {'lr': 0.0004167274309355743, 'samples': 6917120, 'steps': 13509, 'batch_loss/train': 0.8430396215990186}
+12/24/2021 18:13:03 - INFO - codeparrot_training - Step 13510: {'lr': 0.0004167156848855753, 'samples': 6917632, 'steps': 13510, 'batch_loss/train': 0.8778301689308137}
+12/24/2021 18:13:15 - INFO - codeparrot_training - Step 13511: {'lr': 0.0004167039381727778, 'samples': 6918144, 'steps': 13511, 'batch_loss/train': 0.8345812894403934}
+12/24/2021 18:13:26 - INFO - codeparrot_training - Step 13512: {'lr': 0.0004166921907972283, 'samples': 6918656, 'steps': 13512, 'batch_loss/train': 0.6932782281655818}
+12/24/2021 18:13:36 - INFO - codeparrot_training - Step 13513: {'lr': 0.0004166804427589736, 'samples': 6919168, 'steps': 13513, 'batch_loss/train': 0.7686655893921852}
+12/24/2021 18:13:50 - INFO - codeparrot_training - Step 13514: {'lr': 0.0004166686940580604, 'samples': 6919680, 'steps': 13514, 'batch_loss/train': 0.7660488232504576}
+12/24/2021 18:14:01 - INFO - codeparrot_training - Step 13515: {'lr': 0.00041665694469453544, 'samples': 6920192, 'steps': 13515, 'batch_loss/train': 0.8607385698705912}
+12/24/2021 18:14:12 - INFO - codeparrot_training - Step 13516: {'lr': 0.0004166451946684453, 'samples': 6920704, 'steps': 13516, 'batch_loss/train': 0.6800875917542726}
+12/24/2021 18:14:24 - INFO - codeparrot_training - Step 13517: {'lr': 0.0004166334439798368, 'samples': 6921216, 'steps': 13517, 'batch_loss/train': 0.7620429182425141}
+12/24/2021 18:14:34 - INFO - codeparrot_training - Step 13518: {'lr': 0.0004166216926287567, 'samples': 6921728, 'steps': 13518, 'batch_loss/train': 0.8660935582593083}
+12/24/2021 18:14:45 - INFO - codeparrot_training - Step 13519: {'lr': 0.0004166099406152517, 'samples': 6922240, 'steps': 13519, 'batch_loss/train': 0.832039772765711}
+12/24/2021 18:14:55 - INFO - codeparrot_training - Step 13520: {'lr': 0.00041659818793936845, 'samples': 6922752, 'steps': 13520, 'batch_loss/train': 0.8911683410406113}
+12/24/2021 18:15:09 - INFO - codeparrot_training - Step 13521: {'lr': 0.00041658643460115366, 'samples': 6923264, 'steps': 13521, 'batch_loss/train': 0.8742270432412624}
+12/24/2021 18:15:20 - INFO - codeparrot_training - Step 13522: {'lr': 0.00041657468060065414, 'samples': 6923776, 'steps': 13522, 'batch_loss/train': 0.892209294019267}
+12/24/2021 18:15:31 - INFO - codeparrot_training - Step 13523: {'lr': 0.00041656292593791655, 'samples': 6924288, 'steps': 13523, 'batch_loss/train': 0.7969346344470978}
+12/24/2021 18:15:43 - INFO - codeparrot_training - Step 13524: {'lr': 0.00041655117061298774, 'samples': 6924800, 'steps': 13524, 'batch_loss/train': 0.8883431719150394}
+12/24/2021 18:15:53 - INFO - codeparrot_training - Step 13525: {'lr': 0.0004165394146259143, 'samples': 6925312, 'steps': 13525, 'batch_loss/train': 0.7722043972462416}
+12/24/2021 18:16:04 - INFO - codeparrot_training - Step 13526: {'lr': 0.00041652765797674306, 'samples': 6925824, 'steps': 13526, 'batch_loss/train': 0.8182902177795768}
+12/24/2021 18:16:16 - INFO - codeparrot_training - Step 13527: {'lr': 0.0004165159006655207, 'samples': 6926336, 'steps': 13527, 'batch_loss/train': 0.8291089567355812}
+12/24/2021 18:16:27 - INFO - codeparrot_training - Step 13528: {'lr': 0.000416504142692294, 'samples': 6926848, 'steps': 13528, 'batch_loss/train': 0.8431429513730109}
+12/24/2021 18:16:37 - INFO - codeparrot_training - Step 13529: {'lr': 0.00041649238405710976, 'samples': 6927360, 'steps': 13529, 'batch_loss/train': 0.7660315232351422}
+12/24/2021 18:16:48 - INFO - codeparrot_training - Step 13530: {'lr': 0.0004164806247600146, 'samples': 6927872, 'steps': 13530, 'batch_loss/train': 0.8278312152251601}
+12/24/2021 18:17:02 - INFO - codeparrot_training - Step 13531: {'lr': 0.0004164688648010554, 'samples': 6928384, 'steps': 13531, 'batch_loss/train': 0.905308123677969}
+12/24/2021 18:17:12 - INFO - codeparrot_training - Step 13532: {'lr': 0.0004164571041802788, 'samples': 6928896, 'steps': 13532, 'batch_loss/train': 0.7631172575056553}
+12/24/2021 18:17:23 - INFO - codeparrot_training - Step 13533: {'lr': 0.00041644534289773157, 'samples': 6929408, 'steps': 13533, 'batch_loss/train': 0.8230935633182526}
+12/24/2021 18:17:35 - INFO - codeparrot_training - Step 13534: {'lr': 0.0004164335809534605, 'samples': 6929920, 'steps': 13534, 'batch_loss/train': 0.8858921630308032}
+12/24/2021 18:17:46 - INFO - codeparrot_training - Step 13535: {'lr': 0.00041642181834751247, 'samples': 6930432, 'steps': 13535, 'batch_loss/train': 0.6871832953765988}
+12/24/2021 18:17:56 - INFO - codeparrot_training - Step 13536: {'lr': 0.00041641005507993403, 'samples': 6930944, 'steps': 13536, 'batch_loss/train': 0.7912917165085673}
+12/24/2021 18:18:09 - INFO - codeparrot_training - Step 13537: {'lr': 0.0004163982911507721, 'samples': 6931456, 'steps': 13537, 'batch_loss/train': 0.7571589183062315}
+12/24/2021 18:18:19 - INFO - codeparrot_training - Step 13538: {'lr': 0.0004163865265600733, 'samples': 6931968, 'steps': 13538, 'batch_loss/train': 1.1577836433425546}
+12/24/2021 18:18:30 - INFO - codeparrot_training - Step 13539: {'lr': 0.0004163747613078846, 'samples': 6932480, 'steps': 13539, 'batch_loss/train': 0.8656878378242254}
+12/24/2021 18:18:41 - INFO - codeparrot_training - Step 13540: {'lr': 0.0004163629953942526, 'samples': 6932992, 'steps': 13540, 'batch_loss/train': 0.7274064254015684}
+12/24/2021 18:18:53 - INFO - codeparrot_training - Step 13541: {'lr': 0.00041635122881922423, 'samples': 6933504, 'steps': 13541, 'batch_loss/train': 0.7746416749432683}
+12/24/2021 18:19:03 - INFO - codeparrot_training - Step 13542: {'lr': 0.00041633946158284605, 'samples': 6934016, 'steps': 13542, 'batch_loss/train': 0.7561235805042088}
+12/24/2021 18:19:14 - INFO - codeparrot_training - Step 13543: {'lr': 0.0004163276936851651, 'samples': 6934528, 'steps': 13543, 'batch_loss/train': 0.7302806712687016}
+12/24/2021 18:19:28 - INFO - codeparrot_training - Step 13544: {'lr': 0.000416315925126228, 'samples': 6935040, 'steps': 13544, 'batch_loss/train': 0.7187257376499474}
+12/24/2021 18:19:39 - INFO - codeparrot_training - Step 13545: {'lr': 0.0004163041559060816, 'samples': 6935552, 'steps': 13545, 'batch_loss/train': 0.808296175673604}
+12/24/2021 18:19:49 - INFO - codeparrot_training - Step 13546: {'lr': 0.00041629238602477266, 'samples': 6936064, 'steps': 13546, 'batch_loss/train': 0.8431949052028358}
+12/24/2021 18:20:01 - INFO - codeparrot_training - Step 13547: {'lr': 0.00041628061548234797, 'samples': 6936576, 'steps': 13547, 'batch_loss/train': 0.7906867447309196}
+12/24/2021 18:20:12 - INFO - codeparrot_training - Step 13548: {'lr': 0.00041626884427885437, 'samples': 6937088, 'steps': 13548, 'batch_loss/train': 0.7996720841620117}
+12/24/2021 18:20:23 - INFO - codeparrot_training - Step 13549: {'lr': 0.0004162570724143386, 'samples': 6937600, 'steps': 13549, 'batch_loss/train': 0.8480516914278269}
+12/24/2021 18:20:33 - INFO - codeparrot_training - Step 13550: {'lr': 0.0004162452998888475, 'samples': 6938112, 'steps': 13550, 'batch_loss/train': 0.8501515774987638}
+12/24/2021 18:20:47 - INFO - codeparrot_training - Step 13551: {'lr': 0.0004162335267024278, 'samples': 6938624, 'steps': 13551, 'batch_loss/train': 0.6762274018255994}
+12/24/2021 18:20:58 - INFO - codeparrot_training - Step 13552: {'lr': 0.0004162217528551264, 'samples': 6939136, 'steps': 13552, 'batch_loss/train': 0.7632704516872764}
+12/24/2021 18:21:09 - INFO - codeparrot_training - Step 13553: {'lr': 0.0004162099783469901, 'samples': 6939648, 'steps': 13553, 'batch_loss/train': 0.8442970439791679}
+12/24/2021 18:21:20 - INFO - codeparrot_training - Step 13554: {'lr': 0.0004161982031780657, 'samples': 6940160, 'steps': 13554, 'batch_loss/train': 0.805717951618135}
+12/24/2021 18:21:31 - INFO - codeparrot_training - Step 13555: {'lr': 0.00041618642734839997, 'samples': 6940672, 'steps': 13555, 'batch_loss/train': 0.7349476516246796}
+12/24/2021 18:21:42 - INFO - codeparrot_training - Step 13556: {'lr': 0.0004161746508580397, 'samples': 6941184, 'steps': 13556, 'batch_loss/train': 0.8336070696823299}
+12/24/2021 18:21:54 - INFO - codeparrot_training - Step 13557: {'lr': 0.0004161628737070319, 'samples': 6941696, 'steps': 13557, 'batch_loss/train': 0.8172261312138289}
+12/24/2021 18:22:05 - INFO - codeparrot_training - Step 13558: {'lr': 0.0004161510958954231, 'samples': 6942208, 'steps': 13558, 'batch_loss/train': 0.797247963026166}
+12/24/2021 18:22:15 - INFO - codeparrot_training - Step 13559: {'lr': 0.0004161393174232604, 'samples': 6942720, 'steps': 13559, 'batch_loss/train': 0.8284044377505779}
+12/24/2021 18:22:29 - INFO - codeparrot_training - Step 13560: {'lr': 0.0004161275382905904, 'samples': 6943232, 'steps': 13560, 'batch_loss/train': 0.852595305070281}
+12/24/2021 18:22:40 - INFO - codeparrot_training - Step 13561: {'lr': 0.0004161157584974601, 'samples': 6943744, 'steps': 13561, 'batch_loss/train': 0.8503582179546356}
+12/24/2021 18:22:50 - INFO - codeparrot_training - Step 13562: {'lr': 0.00041610397804391633, 'samples': 6944256, 'steps': 13562, 'batch_loss/train': 0.7518537547439337}
+12/24/2021 18:23:01 - INFO - codeparrot_training - Step 13563: {'lr': 0.0004160921969300058, 'samples': 6944768, 'steps': 13563, 'batch_loss/train': 0.7942410269752145}
+12/24/2021 18:23:13 - INFO - codeparrot_training - Step 13564: {'lr': 0.0004160804151557753, 'samples': 6945280, 'steps': 13564, 'batch_loss/train': 0.7812806433066726}
+12/24/2021 18:23:24 - INFO - codeparrot_training - Step 13565: {'lr': 0.00041606863272127193, 'samples': 6945792, 'steps': 13565, 'batch_loss/train': 0.7502692146226764}
+12/24/2021 18:23:34 - INFO - codeparrot_training - Step 13566: {'lr': 0.00041605684962654234, 'samples': 6946304, 'steps': 13566, 'batch_loss/train': 0.8206184215378016}
+12/24/2021 18:23:46 - INFO - codeparrot_training - Step 13567: {'lr': 0.0004160450658716334, 'samples': 6946816, 'steps': 13567, 'batch_loss/train': 0.7317204936407506}
+12/24/2021 18:23:57 - INFO - codeparrot_training - Step 13568: {'lr': 0.0004160332814565919, 'samples': 6947328, 'steps': 13568, 'batch_loss/train': 0.8107765773311257}
+12/24/2021 18:24:07 - INFO - codeparrot_training - Step 13569: {'lr': 0.00041602149638146494, 'samples': 6947840, 'steps': 13569, 'batch_loss/train': 0.8233556877821684}
+12/24/2021 18:24:21 - INFO - codeparrot_training - Step 13570: {'lr': 0.00041600971064629903, 'samples': 6948352, 'steps': 13570, 'batch_loss/train': 0.79493148624897}
+12/24/2021 18:24:32 - INFO - codeparrot_training - Step 13571: {'lr': 0.00041599792425114126, 'samples': 6948864, 'steps': 13571, 'batch_loss/train': 0.7601630084682256}
+12/24/2021 18:24:42 - INFO - codeparrot_training - Step 13572: {'lr': 0.00041598613719603846, 'samples': 6949376, 'steps': 13572, 'batch_loss/train': 0.8443589173257351}
+12/24/2021 18:24:53 - INFO - codeparrot_training - Step 13573: {'lr': 0.0004159743494810374, 'samples': 6949888, 'steps': 13573, 'batch_loss/train': 0.6615303644211963}
+12/24/2021 18:25:05 - INFO - codeparrot_training - Step 13574: {'lr': 0.00041596256110618503, 'samples': 6950400, 'steps': 13574, 'batch_loss/train': 0.907196993008256}
+12/24/2021 18:25:16 - INFO - codeparrot_training - Step 13575: {'lr': 0.00041595077207152813, 'samples': 6950912, 'steps': 13575, 'batch_loss/train': 0.9993758499622345}
+12/24/2021 18:25:26 - INFO - codeparrot_training - Step 13576: {'lr': 0.0004159389823771137, 'samples': 6951424, 'steps': 13576, 'batch_loss/train': 0.7420989573001862}
+12/24/2021 18:25:38 - INFO - codeparrot_training - Step 13577: {'lr': 0.00041592719202298846, 'samples': 6951936, 'steps': 13577, 'batch_loss/train': 0.8297704339493066}
+12/24/2021 18:25:49 - INFO - codeparrot_training - Step 13578: {'lr': 0.00041591540100919947, 'samples': 6952448, 'steps': 13578, 'batch_loss/train': 0.8221791572868824}
+12/24/2021 18:26:00 - INFO - codeparrot_training - Step 13579: {'lr': 0.0004159036093357934, 'samples': 6952960, 'steps': 13579, 'batch_loss/train': 0.797499518841505}
+12/24/2021 18:26:13 - INFO - codeparrot_training - Step 13580: {'lr': 0.00041589181700281717, 'samples': 6953472, 'steps': 13580, 'batch_loss/train': 0.7871373433154076}
+12/24/2021 18:26:24 - INFO - codeparrot_training - Step 13581: {'lr': 0.00041588002401031775, 'samples': 6953984, 'steps': 13581, 'batch_loss/train': 0.7627917525824159}
+12/24/2021 18:26:35 - INFO - codeparrot_training - Step 13582: {'lr': 0.0004158682303583421, 'samples': 6954496, 'steps': 13582, 'batch_loss/train': 0.9050031621009111}
+12/24/2021 18:26:45 - INFO - codeparrot_training - Step 13583: {'lr': 0.0004158564360469368, 'samples': 6955008, 'steps': 13583, 'batch_loss/train': 0.8953026542440057}
+12/24/2021 18:26:57 - INFO - codeparrot_training - Step 13584: {'lr': 0.00041584464107614905, 'samples': 6955520, 'steps': 13584, 'batch_loss/train': 0.8781520901247859}
+12/24/2021 18:27:08 - INFO - codeparrot_training - Step 13585: {'lr': 0.0004158328454460257, 'samples': 6956032, 'steps': 13585, 'batch_loss/train': 0.8078726553358138}
+12/24/2021 18:27:18 - INFO - codeparrot_training - Step 13586: {'lr': 0.00041582104915661343, 'samples': 6956544, 'steps': 13586, 'batch_loss/train': 0.8386942148208618}
+12/24/2021 18:27:31 - INFO - codeparrot_training - Step 13587: {'lr': 0.0004158092522079594, 'samples': 6957056, 'steps': 13587, 'batch_loss/train': 0.8247412638738751}
+12/24/2021 18:27:41 - INFO - codeparrot_training - Step 13588: {'lr': 0.0004157974546001103, 'samples': 6957568, 'steps': 13588, 'batch_loss/train': 0.8546771369874477}
+12/24/2021 18:27:52 - INFO - codeparrot_training - Step 13589: {'lr': 0.00041578565633311313, 'samples': 6958080, 'steps': 13589, 'batch_loss/train': 0.8126274775713682}
+12/24/2021 18:28:06 - INFO - codeparrot_training - Step 13590: {'lr': 0.00041577385740701483, 'samples': 6958592, 'steps': 13590, 'batch_loss/train': 0.7123595825396478}
+12/24/2021 18:28:16 - INFO - codeparrot_training - Step 13591: {'lr': 0.0004157620578218623, 'samples': 6959104, 'steps': 13591, 'batch_loss/train': 0.7426079995930195}
+12/24/2021 18:28:27 - INFO - codeparrot_training - Step 13592: {'lr': 0.0004157502575777023, 'samples': 6959616, 'steps': 13592, 'batch_loss/train': 0.7773772475775331}
+12/24/2021 18:28:39 - INFO - codeparrot_training - Step 13593: {'lr': 0.00041573845667458196, 'samples': 6960128, 'steps': 13593, 'batch_loss/train': 0.7342138603562489}
+12/24/2021 18:28:50 - INFO - codeparrot_training - Step 13594: {'lr': 0.0004157266551125481, 'samples': 6960640, 'steps': 13594, 'batch_loss/train': 0.7890412475680932}
+12/24/2021 18:29:00 - INFO - codeparrot_training - Step 13595: {'lr': 0.00041571485289164763, 'samples': 6961152, 'steps': 13595, 'batch_loss/train': 0.7613468486815691}
+12/24/2021 18:29:11 - INFO - codeparrot_training - Step 13596: {'lr': 0.00041570305001192745, 'samples': 6961664, 'steps': 13596, 'batch_loss/train': 0.6747157517820597}
+12/24/2021 18:29:23 - INFO - codeparrot_training - Step 13597: {'lr': 0.0004156912464734345, 'samples': 6962176, 'steps': 13597, 'batch_loss/train': 0.5618223410565406}
+12/24/2021 18:29:34 - INFO - codeparrot_training - Step 13598: {'lr': 0.00041567944227621567, 'samples': 6962688, 'steps': 13598, 'batch_loss/train': 1.2834808812476695}
+12/24/2021 18:29:44 - INFO - codeparrot_training - Step 13599: {'lr': 0.000415667637420318, 'samples': 6963200, 'steps': 13599, 'batch_loss/train': 0.8605329317506403}
+12/24/2021 18:29:58 - INFO - codeparrot_training - Step 13600: {'lr': 0.00041565583190578836, 'samples': 6963712, 'steps': 13600, 'batch_loss/train': 0.8286610064096749}
+12/24/2021 18:30:09 - INFO - codeparrot_training - Step 13601: {'lr': 0.0004156440257326737, 'samples': 6964224, 'steps': 13601, 'batch_loss/train': 0.7679252438247204}
+12/24/2021 18:30:19 - INFO - codeparrot_training - Step 13602: {'lr': 0.0004156322189010209, 'samples': 6964736, 'steps': 13602, 'batch_loss/train': 0.8736072815954685}
+12/24/2021 18:30:32 - INFO - codeparrot_training - Step 13603: {'lr': 0.00041562041141087695, 'samples': 6965248, 'steps': 13603, 'batch_loss/train': 0.9162763254716992}
+12/24/2021 18:30:42 - INFO - codeparrot_training - Step 13604: {'lr': 0.0004156086032622888, 'samples': 6965760, 'steps': 13604, 'batch_loss/train': 0.8754878863692284}
+12/24/2021 18:30:53 - INFO - codeparrot_training - Step 13605: {'lr': 0.0004155967944553033, 'samples': 6966272, 'steps': 13605, 'batch_loss/train': 0.8162585999816656}
+12/24/2021 18:31:03 - INFO - codeparrot_training - Step 13606: {'lr': 0.00041558498498996756, 'samples': 6966784, 'steps': 13606, 'batch_loss/train': 0.7420970080420375}
+12/24/2021 18:31:18 - INFO - codeparrot_training - Step 13607: {'lr': 0.0004155731748663284, 'samples': 6967296, 'steps': 13607, 'batch_loss/train': 0.8076087161898613}
+12/24/2021 18:31:28 - INFO - codeparrot_training - Step 13608: {'lr': 0.0004155613640844328, 'samples': 6967808, 'steps': 13608, 'batch_loss/train': 1.5994646856561303}
+12/24/2021 18:31:39 - INFO - codeparrot_training - Step 13609: {'lr': 0.00041554955264432774, 'samples': 6968320, 'steps': 13609, 'batch_loss/train': 0.8448003521189094}
+12/24/2021 18:31:50 - INFO - codeparrot_training - Step 13610: {'lr': 0.0004155377405460602, 'samples': 6968832, 'steps': 13610, 'batch_loss/train': 1.0527706816792488}
+12/24/2021 18:32:02 - INFO - codeparrot_training - Step 13611: {'lr': 0.00041552592778967715, 'samples': 6969344, 'steps': 13611, 'batch_loss/train': 0.9617097899317741}
+12/24/2021 18:32:12 - INFO - codeparrot_training - Step 13612: {'lr': 0.0004155141143752254, 'samples': 6969856, 'steps': 13612, 'batch_loss/train': 0.8335088947787881}
+12/24/2021 18:32:23 - INFO - codeparrot_training - Step 13613: {'lr': 0.00041550230030275206, 'samples': 6970368, 'steps': 13613, 'batch_loss/train': 0.7734317518770695}
+12/24/2021 18:32:35 - INFO - codeparrot_training - Step 13614: {'lr': 0.00041549048557230407, 'samples': 6970880, 'steps': 13614, 'batch_loss/train': 0.7767074825242162}
+12/24/2021 18:32:46 - INFO - codeparrot_training - Step 13615: {'lr': 0.0004154786701839284, 'samples': 6971392, 'steps': 13615, 'batch_loss/train': 0.8982709851115942}
+12/24/2021 18:32:57 - INFO - codeparrot_training - Step 13616: {'lr': 0.00041546685413767207, 'samples': 6971904, 'steps': 13616, 'batch_loss/train': 0.7459296784363687}
+12/24/2021 18:33:11 - INFO - codeparrot_training - Step 13617: {'lr': 0.0004154550374335819, 'samples': 6972416, 'steps': 13617, 'batch_loss/train': 0.8025864227674901}
+12/24/2021 18:33:22 - INFO - codeparrot_training - Step 13618: {'lr': 0.0004154432200717051, 'samples': 6972928, 'steps': 13618, 'batch_loss/train': 0.8186353500932455}
+12/24/2021 18:33:32 - INFO - codeparrot_training - Step 13619: {'lr': 0.00041543140205208847, 'samples': 6973440, 'steps': 13619, 'batch_loss/train': 0.8373757395893335}
+12/24/2021 18:33:44 - INFO - codeparrot_training - Step 13620: {'lr': 0.00041541958337477903, 'samples': 6973952, 'steps': 13620, 'batch_loss/train': 0.8270373838022351}
+12/24/2021 18:33:55 - INFO - codeparrot_training - Step 13621: {'lr': 0.0004154077640398238, 'samples': 6974464, 'steps': 13621, 'batch_loss/train': 0.8414728604257107}
+12/24/2021 18:34:05 - INFO - codeparrot_training - Step 13622: {'lr': 0.00041539594404726976, 'samples': 6974976, 'steps': 13622, 'batch_loss/train': 0.7877097204327583}
+12/24/2021 18:34:16 - INFO - codeparrot_training - Step 13623: {'lr': 0.0004153841233971639, 'samples': 6975488, 'steps': 13623, 'batch_loss/train': 0.8000831445679069}
+12/24/2021 18:34:30 - INFO - codeparrot_training - Step 13624: {'lr': 0.0004153723020895532, 'samples': 6976000, 'steps': 13624, 'batch_loss/train': 0.8378220936283469}
+12/24/2021 18:34:41 - INFO - codeparrot_training - Step 13625: {'lr': 0.00041536048012448464, 'samples': 6976512, 'steps': 13625, 'batch_loss/train': 0.7665108414366841}
+12/24/2021 18:34:51 - INFO - codeparrot_training - Step 13626: {'lr': 0.0004153486575020053, 'samples': 6977024, 'steps': 13626, 'batch_loss/train': 0.6879871636629105}
+12/24/2021 18:35:04 - INFO - codeparrot_training - Step 13627: {'lr': 0.0004153368342221621, 'samples': 6977536, 'steps': 13627, 'batch_loss/train': 0.8053453015163541}
+12/24/2021 18:35:14 - INFO - codeparrot_training - Step 13628: {'lr': 0.00041532501028500215, 'samples': 6978048, 'steps': 13628, 'batch_loss/train': 0.771147623192519}
+12/24/2021 18:35:25 - INFO - codeparrot_training - Step 13629: {'lr': 0.0004153131856905723, 'samples': 6978560, 'steps': 13629, 'batch_loss/train': 0.7066908853594214}
+12/24/2021 18:35:37 - INFO - codeparrot_training - Step 13630: {'lr': 0.0004153013604389196, 'samples': 6979072, 'steps': 13630, 'batch_loss/train': 0.6941221880260855}
+12/24/2021 18:35:48 - INFO - codeparrot_training - Step 13631: {'lr': 0.0004152895345300912, 'samples': 6979584, 'steps': 13631, 'batch_loss/train': 0.7088221539743245}
+12/24/2021 18:35:58 - INFO - codeparrot_training - Step 13632: {'lr': 0.000415277707964134, 'samples': 6980096, 'steps': 13632, 'batch_loss/train': 0.8061456470750272}
+12/24/2021 18:36:12 - INFO - codeparrot_training - Step 13633: {'lr': 0.0004152658807410951, 'samples': 6980608, 'steps': 13633, 'batch_loss/train': 0.8245454579591751}
+12/24/2021 18:36:23 - INFO - codeparrot_training - Step 13634: {'lr': 0.0004152540528610214, 'samples': 6981120, 'steps': 13634, 'batch_loss/train': 0.7408408988267183}
+12/24/2021 18:36:33 - INFO - codeparrot_training - Step 13635: {'lr': 0.0004152422243239599, 'samples': 6981632, 'steps': 13635, 'batch_loss/train': 0.8544167056679726}
+12/24/2021 18:36:44 - INFO - codeparrot_training - Step 13636: {'lr': 0.00041523039512995777, 'samples': 6982144, 'steps': 13636, 'batch_loss/train': 0.8134855362586677}
+12/24/2021 18:36:56 - INFO - codeparrot_training - Step 13637: {'lr': 0.00041521856527906197, 'samples': 6982656, 'steps': 13637, 'batch_loss/train': 0.7779782065190375}
+12/24/2021 18:37:06 - INFO - codeparrot_training - Step 13638: {'lr': 0.0004152067347713196, 'samples': 6983168, 'steps': 13638, 'batch_loss/train': 0.7503496606368572}
+12/24/2021 18:37:17 - INFO - codeparrot_training - Step 13639: {'lr': 0.0004151949036067776, 'samples': 6983680, 'steps': 13639, 'batch_loss/train': 0.7322690435685217}
+12/24/2021 18:37:31 - INFO - codeparrot_training - Step 13640: {'lr': 0.00041518307178548306, 'samples': 6984192, 'steps': 13640, 'batch_loss/train': 0.5727132566971704}
+12/24/2021 18:37:42 - INFO - codeparrot_training - Step 13641: {'lr': 0.00041517123930748294, 'samples': 6984704, 'steps': 13641, 'batch_loss/train': 0.7602025484666228}
+12/24/2021 18:37:52 - INFO - codeparrot_training - Step 13642: {'lr': 0.0004151594061728244, 'samples': 6985216, 'steps': 13642, 'batch_loss/train': 0.616954448632896}
+12/24/2021 18:38:04 - INFO - codeparrot_training - Step 13643: {'lr': 0.00041514757238155436, 'samples': 6985728, 'steps': 13643, 'batch_loss/train': 0.7560896258801222}
+12/24/2021 18:38:15 - INFO - codeparrot_training - Step 13644: {'lr': 0.00041513573793371995, 'samples': 6986240, 'steps': 13644, 'batch_loss/train': 0.6395050549181178}
+12/24/2021 18:38:25 - INFO - codeparrot_training - Step 13645: {'lr': 0.00041512390282936817, 'samples': 6986752, 'steps': 13645, 'batch_loss/train': 0.6964522725902498}
+12/24/2021 18:38:36 - INFO - codeparrot_training - Step 13646: {'lr': 0.0004151120670685462, 'samples': 6987264, 'steps': 13646, 'batch_loss/train': 0.6883084822911769}
+12/24/2021 18:38:48 - INFO - codeparrot_training - Step 13647: {'lr': 0.0004151002306513009, 'samples': 6987776, 'steps': 13647, 'batch_loss/train': 0.8000080175697803}
+12/24/2021 18:38:59 - INFO - codeparrot_training - Step 13648: {'lr': 0.0004150883935776795, 'samples': 6988288, 'steps': 13648, 'batch_loss/train': 0.5171181011828594}
+12/24/2021 18:39:09 - INFO - codeparrot_training - Step 13649: {'lr': 0.00041507655584772896, 'samples': 6988800, 'steps': 13649, 'batch_loss/train': 0.866093622520566}
+12/24/2021 18:39:22 - INFO - codeparrot_training - Step 13650: {'lr': 0.00041506471746149634, 'samples': 6989312, 'steps': 13650, 'batch_loss/train': 0.7229694500565529}
+12/24/2021 18:39:32 - INFO - codeparrot_training - Step 13651: {'lr': 0.0004150528784190287, 'samples': 6989824, 'steps': 13651, 'batch_loss/train': 0.7149697262793779}
+12/24/2021 18:39:43 - INFO - codeparrot_training - Step 13652: {'lr': 0.00041504103872037326, 'samples': 6990336, 'steps': 13652, 'batch_loss/train': 0.8414313551038504}
+12/24/2021 18:39:57 - INFO - codeparrot_training - Step 13653: {'lr': 0.0004150291983655768, 'samples': 6990848, 'steps': 13653, 'batch_loss/train': 0.822242493275553}
+12/24/2021 18:40:07 - INFO - codeparrot_training - Step 13654: {'lr': 0.00041501735735468664, 'samples': 6991360, 'steps': 13654, 'batch_loss/train': 0.6815868830308318}
+12/24/2021 18:40:18 - INFO - codeparrot_training - Step 13655: {'lr': 0.0004150055156877498, 'samples': 6991872, 'steps': 13655, 'batch_loss/train': 0.8054414838552475}
+12/24/2021 18:40:30 - INFO - codeparrot_training - Step 13656: {'lr': 0.0004149936733648133, 'samples': 6992384, 'steps': 13656, 'batch_loss/train': 0.8378195278346539}
+12/24/2021 18:40:40 - INFO - codeparrot_training - Step 13657: {'lr': 0.0004149818303859243, 'samples': 6992896, 'steps': 13657, 'batch_loss/train': 0.7690370213240385}
+12/24/2021 18:40:51 - INFO - codeparrot_training - Step 13658: {'lr': 0.00041496998675112976, 'samples': 6993408, 'steps': 13658, 'batch_loss/train': 0.7681764317676425}
+12/24/2021 18:41:02 - INFO - codeparrot_training - Step 13659: {'lr': 0.00041495814246047684, 'samples': 6993920, 'steps': 13659, 'batch_loss/train': 0.8496627351269126}
+12/24/2021 18:41:14 - INFO - codeparrot_training - Step 13660: {'lr': 0.0004149462975140127, 'samples': 6994432, 'steps': 13660, 'batch_loss/train': 0.7705060271546245}
+12/24/2021 18:41:24 - INFO - codeparrot_training - Step 13661: {'lr': 0.00041493445191178436, 'samples': 6994944, 'steps': 13661, 'batch_loss/train': 0.779621466062963}
+12/24/2021 18:41:35 - INFO - codeparrot_training - Step 13662: {'lr': 0.0004149226056538389, 'samples': 6995456, 'steps': 13662, 'batch_loss/train': 0.8515476898755878}
+12/24/2021 18:41:49 - INFO - codeparrot_training - Step 13663: {'lr': 0.0004149107587402234, 'samples': 6995968, 'steps': 13663, 'batch_loss/train': 0.8078048098832369}
+12/24/2021 18:41:59 - INFO - codeparrot_training - Step 13664: {'lr': 0.000414898911170985, 'samples': 6996480, 'steps': 13664, 'batch_loss/train': 0.7279259655624628}
+12/24/2021 18:42:10 - INFO - codeparrot_training - Step 13665: {'lr': 0.00041488706294617086, 'samples': 6996992, 'steps': 13665, 'batch_loss/train': 0.66089813481085}
+12/24/2021 18:42:22 - INFO - codeparrot_training - Step 13666: {'lr': 0.0004148752140658279, 'samples': 6997504, 'steps': 13666, 'batch_loss/train': 0.9951891526579857}
+12/24/2021 18:42:33 - INFO - codeparrot_training - Step 13667: {'lr': 0.0004148633645300034, 'samples': 6998016, 'steps': 13667, 'batch_loss/train': 0.8146980693563819}
+12/24/2021 18:42:43 - INFO - codeparrot_training - Step 13668: {'lr': 0.00041485151433874444, 'samples': 6998528, 'steps': 13668, 'batch_loss/train': 0.9112509777769446}
+12/24/2021 18:42:58 - INFO - codeparrot_training - Step 13669: {'lr': 0.00041483966349209814, 'samples': 6999040, 'steps': 13669, 'batch_loss/train': 0.6775628785253502}
+12/24/2021 18:43:08 - INFO - codeparrot_training - Step 13670: {'lr': 0.0004148278119901114, 'samples': 6999552, 'steps': 13670, 'batch_loss/train': 0.8585020517930388}
+12/24/2021 18:43:19 - INFO - codeparrot_training - Step 13671: {'lr': 0.0004148159598328317, 'samples': 7000064, 'steps': 13671, 'batch_loss/train': 0.8119877362623811}
+12/24/2021 18:43:29 - INFO - codeparrot_training - Step 13672: {'lr': 0.00041480410702030593, 'samples': 7000576, 'steps': 13672, 'batch_loss/train': 0.7146873185411096}
+12/24/2021 18:43:41 - INFO - codeparrot_training - Step 13673: {'lr': 0.0004147922535525812, 'samples': 7001088, 'steps': 13673, 'batch_loss/train': 0.8589732346590608}
+12/24/2021 18:43:52 - INFO - codeparrot_training - Step 13674: {'lr': 0.0004147803994297048, 'samples': 7001600, 'steps': 13674, 'batch_loss/train': 0.7894395207986236}
+12/24/2021 18:44:03 - INFO - codeparrot_training - Step 13675: {'lr': 0.00041476854465172366, 'samples': 7002112, 'steps': 13675, 'batch_loss/train': 0.7312543778680265}
+12/24/2021 18:44:15 - INFO - codeparrot_training - Step 13676: {'lr': 0.000414756689218685, 'samples': 7002624, 'steps': 13676, 'batch_loss/train': 0.816523902118206}
+12/24/2021 18:44:25 - INFO - codeparrot_training - Step 13677: {'lr': 0.00041474483313063597, 'samples': 7003136, 'steps': 13677, 'batch_loss/train': 0.6221683954936452}
+12/24/2021 18:44:36 - INFO - codeparrot_training - Step 13678: {'lr': 0.00041473297638762376, 'samples': 7003648, 'steps': 13678, 'batch_loss/train': 0.819923160597682}
+12/24/2021 18:44:50 - INFO - codeparrot_training - Step 13679: {'lr': 0.0004147211189896953, 'samples': 7004160, 'steps': 13679, 'batch_loss/train': 0.755083053605631}
+12/24/2021 18:45:00 - INFO - codeparrot_training - Step 13680: {'lr': 0.000414709260936898, 'samples': 7004672, 'steps': 13680, 'batch_loss/train': 0.7362191779538989}
+12/24/2021 18:45:11 - INFO - codeparrot_training - Step 13681: {'lr': 0.0004146974022292788, 'samples': 7005184, 'steps': 13681, 'batch_loss/train': 0.6980527229025029}
+12/24/2021 18:45:22 - INFO - codeparrot_training - Step 13682: {'lr': 0.00041468554286688494, 'samples': 7005696, 'steps': 13682, 'batch_loss/train': 0.7809050139039755}
+12/24/2021 18:45:34 - INFO - codeparrot_training - Step 13683: {'lr': 0.0004146736828497635, 'samples': 7006208, 'steps': 13683, 'batch_loss/train': 0.7738628190709278}
+12/24/2021 18:45:44 - INFO - codeparrot_training - Step 13684: {'lr': 0.0004146618221779617, 'samples': 7006720, 'steps': 13684, 'batch_loss/train': 0.8167421203106642}
+12/24/2021 18:45:55 - INFO - codeparrot_training - Step 13685: {'lr': 0.0004146499608515267, 'samples': 7007232, 'steps': 13685, 'batch_loss/train': 0.8444514884613454}
+12/24/2021 18:46:07 - INFO - codeparrot_training - Step 13686: {'lr': 0.00041463809887050564, 'samples': 7007744, 'steps': 13686, 'batch_loss/train': 0.8419130739057437}
+12/24/2021 18:46:18 - INFO - codeparrot_training - Step 13687: {'lr': 0.0004146262362349456, 'samples': 7008256, 'steps': 13687, 'batch_loss/train': 0.7723642699420452}
+12/24/2021 18:46:28 - INFO - codeparrot_training - Step 13688: {'lr': 0.00041461437294489377, 'samples': 7008768, 'steps': 13688, 'batch_loss/train': 0.8000844828784466}
+12/24/2021 18:46:40 - INFO - codeparrot_training - Step 13689: {'lr': 0.0004146025090003975, 'samples': 7009280, 'steps': 13689, 'batch_loss/train': 0.8232099590823054}
+12/24/2021 18:46:51 - INFO - codeparrot_training - Step 13690: {'lr': 0.0004145906444015037, 'samples': 7009792, 'steps': 13690, 'batch_loss/train': 0.824959154240787}
+12/24/2021 18:47:01 - INFO - codeparrot_training - Step 13691: {'lr': 0.0004145787791482597, 'samples': 7010304, 'steps': 13691, 'batch_loss/train': 0.6821286793565378}
+12/24/2021 18:47:16 - INFO - codeparrot_training - Step 13692: {'lr': 0.0004145669132407125, 'samples': 7010816, 'steps': 13692, 'batch_loss/train': 0.7573491861112416}
+12/24/2021 18:47:26 - INFO - codeparrot_training - Step 13693: {'lr': 0.00041455504667890953, 'samples': 7011328, 'steps': 13693, 'batch_loss/train': 0.7247601402923465}
+12/24/2021 18:47:37 - INFO - codeparrot_training - Step 13694: {'lr': 0.0004145431794628978, 'samples': 7011840, 'steps': 13694, 'batch_loss/train': 0.5414795642718673}
+12/24/2021 18:47:47 - INFO - codeparrot_training - Step 13695: {'lr': 0.0004145313115927244, 'samples': 7012352, 'steps': 13695, 'batch_loss/train': 0.5723126069642603}
+12/24/2021 18:47:59 - INFO - codeparrot_training - Step 13696: {'lr': 0.0004145194430684367, 'samples': 7012864, 'steps': 13696, 'batch_loss/train': 0.7723208030220121}
+12/24/2021 18:48:10 - INFO - codeparrot_training - Step 13697: {'lr': 0.0004145075738900819, 'samples': 7013376, 'steps': 13697, 'batch_loss/train': 0.7757347812876105}
+12/24/2021 18:48:21 - INFO - codeparrot_training - Step 13698: {'lr': 0.00041449570405770696, 'samples': 7013888, 'steps': 13698, 'batch_loss/train': 0.7542486554011703}
+12/24/2021 18:48:33 - INFO - codeparrot_training - Step 13699: {'lr': 0.00041448383357135934, 'samples': 7014400, 'steps': 13699, 'batch_loss/train': 0.7780963629484177}
+12/24/2021 18:48:43 - INFO - codeparrot_training - Step 13700: {'lr': 0.000414471962431086, 'samples': 7014912, 'steps': 13700, 'batch_loss/train': 0.8019173555076122}
+12/24/2021 18:48:54 - INFO - codeparrot_training - Step 13701: {'lr': 0.0004144600906369343, 'samples': 7015424, 'steps': 13701, 'batch_loss/train': 0.6196174866636284}
+12/24/2021 18:49:08 - INFO - codeparrot_training - Step 13702: {'lr': 0.0004144482181889514, 'samples': 7015936, 'steps': 13702, 'batch_loss/train': 0.7423722818493843}
+12/24/2021 18:49:18 - INFO - codeparrot_training - Step 13703: {'lr': 0.00041443634508718443, 'samples': 7016448, 'steps': 13703, 'batch_loss/train': 0.5910641030641273}
+12/24/2021 18:49:29 - INFO - codeparrot_training - Step 13704: {'lr': 0.00041442447133168065, 'samples': 7016960, 'steps': 13704, 'batch_loss/train': 0.8018735032528639}
+12/24/2021 18:49:41 - INFO - codeparrot_training - Step 13705: {'lr': 0.0004144125969224872, 'samples': 7017472, 'steps': 13705, 'batch_loss/train': 0.7842907197773457}
+12/24/2021 18:49:52 - INFO - codeparrot_training - Step 13706: {'lr': 0.00041440072185965147, 'samples': 7017984, 'steps': 13706, 'batch_loss/train': 0.7329177493229508}
+12/24/2021 18:50:02 - INFO - codeparrot_training - Step 13707: {'lr': 0.0004143888461432205, 'samples': 7018496, 'steps': 13707, 'batch_loss/train': 0.7898299028165638}
+12/24/2021 18:50:13 - INFO - codeparrot_training - Step 13708: {'lr': 0.00041437696977324147, 'samples': 7019008, 'steps': 13708, 'batch_loss/train': 0.7254409631714225}
+12/24/2021 18:50:27 - INFO - codeparrot_training - Step 13709: {'lr': 0.00041436509274976174, 'samples': 7019520, 'steps': 13709, 'batch_loss/train': 0.8507406148128211}
+12/24/2021 18:50:37 - INFO - codeparrot_training - Step 13710: {'lr': 0.0004143532150728285, 'samples': 7020032, 'steps': 13710, 'batch_loss/train': 0.7709641717374325}
+12/24/2021 18:50:48 - INFO - codeparrot_training - Step 13711: {'lr': 0.00041434133674248886, 'samples': 7020544, 'steps': 13711, 'batch_loss/train': 0.7490430531324819}
+12/24/2021 18:51:00 - INFO - codeparrot_training - Step 13712: {'lr': 0.00041432945775879014, 'samples': 7021056, 'steps': 13712, 'batch_loss/train': 0.8391087293857709}
+12/24/2021 18:51:11 - INFO - codeparrot_training - Step 13713: {'lr': 0.00041431757812177954, 'samples': 7021568, 'steps': 13713, 'batch_loss/train': 0.8657533032819629}
+12/24/2021 18:51:21 - INFO - codeparrot_training - Step 13714: {'lr': 0.0004143056978315043, 'samples': 7022080, 'steps': 13714, 'batch_loss/train': 0.8324931645765901}
+12/24/2021 18:51:34 - INFO - codeparrot_training - Step 13715: {'lr': 0.0004142938168880117, 'samples': 7022592, 'steps': 13715, 'batch_loss/train': 0.7390142614021897}
+12/24/2021 18:51:44 - INFO - codeparrot_training - Step 13716: {'lr': 0.00041428193529134883, 'samples': 7023104, 'steps': 13716, 'batch_loss/train': 0.8528866451233625}
+12/24/2021 18:51:55 - INFO - codeparrot_training - Step 13717: {'lr': 0.00041427005304156306, 'samples': 7023616, 'steps': 13717, 'batch_loss/train': 0.8304711235687137}
+12/24/2021 18:52:09 - INFO - codeparrot_training - Step 13718: {'lr': 0.0004142581701387016, 'samples': 7024128, 'steps': 13718, 'batch_loss/train': 0.7579422313719988}
+12/24/2021 18:52:19 - INFO - codeparrot_training - Step 13719: {'lr': 0.00041424628658281163, 'samples': 7024640, 'steps': 13719, 'batch_loss/train': 0.8063094979152083}
+12/24/2021 18:52:30 - INFO - codeparrot_training - Step 13720: {'lr': 0.0004142344023739405, 'samples': 7025152, 'steps': 13720, 'batch_loss/train': 0.7543291477486491}
+12/24/2021 18:52:40 - INFO - codeparrot_training - Step 13721: {'lr': 0.00041422251751213536, 'samples': 7025664, 'steps': 13721, 'batch_loss/train': 0.845734991133213}
+12/24/2021 18:52:53 - INFO - codeparrot_training - Step 13722: {'lr': 0.00041421063199744345, 'samples': 7026176, 'steps': 13722, 'batch_loss/train': 0.6845304323360324}
+12/24/2021 18:53:04 - INFO - codeparrot_training - Step 13723: {'lr': 0.0004141987458299121, 'samples': 7026688, 'steps': 13723, 'batch_loss/train': 0.824881193228066}
+12/24/2021 18:53:14 - INFO - codeparrot_training - Step 13724: {'lr': 0.00041418685900958865, 'samples': 7027200, 'steps': 13724, 'batch_loss/train': 1.102796956896782}
+12/24/2021 18:53:28 - INFO - codeparrot_training - Step 13725: {'lr': 0.00041417497153652013, 'samples': 7027712, 'steps': 13725, 'batch_loss/train': 0.7118276503169909}
+12/24/2021 18:53:39 - INFO - codeparrot_training - Step 13726: {'lr': 0.00041416308341075394, 'samples': 7028224, 'steps': 13726, 'batch_loss/train': 0.9084341879934072}
+12/24/2021 18:53:49 - INFO - codeparrot_training - Step 13727: {'lr': 0.0004141511946323373, 'samples': 7028736, 'steps': 13727, 'batch_loss/train': 1.6263319330755621}
+12/24/2021 18:54:01 - INFO - codeparrot_training - Step 13728: {'lr': 0.0004141393052013175, 'samples': 7029248, 'steps': 13728, 'batch_loss/train': 0.83491116669029}
+12/24/2021 18:54:12 - INFO - codeparrot_training - Step 13729: {'lr': 0.0004141274151177418, 'samples': 7029760, 'steps': 13729, 'batch_loss/train': 0.7719694809056818}
+12/24/2021 18:54:23 - INFO - codeparrot_training - Step 13730: {'lr': 0.0004141155243816575, 'samples': 7030272, 'steps': 13730, 'batch_loss/train': 0.8388674193993211}
+12/24/2021 18:54:33 - INFO - codeparrot_training - Step 13731: {'lr': 0.00041410363299311184, 'samples': 7030784, 'steps': 13731, 'batch_loss/train': 0.6981899528764188}
+12/24/2021 18:54:45 - INFO - codeparrot_training - Step 13732: {'lr': 0.000414091740952152, 'samples': 7031296, 'steps': 13732, 'batch_loss/train': 0.7887698905542493}
+12/24/2021 18:54:56 - INFO - codeparrot_training - Step 13733: {'lr': 0.0004140798482588255, 'samples': 7031808, 'steps': 13733, 'batch_loss/train': 0.8351681074127555}
+12/24/2021 18:55:06 - INFO - codeparrot_training - Step 13734: {'lr': 0.0004140679549131794, 'samples': 7032320, 'steps': 13734, 'batch_loss/train': 0.7311671525822021}
+12/24/2021 18:55:19 - INFO - codeparrot_training - Step 13735: {'lr': 0.00041405606091526106, 'samples': 7032832, 'steps': 13735, 'batch_loss/train': 0.7369772981619462}
+12/24/2021 18:55:29 - INFO - codeparrot_training - Step 13736: {'lr': 0.00041404416626511774, 'samples': 7033344, 'steps': 13736, 'batch_loss/train': 0.7665149951353669}
+12/24/2021 18:55:40 - INFO - codeparrot_training - Step 13737: {'lr': 0.00041403227096279685, 'samples': 7033856, 'steps': 13737, 'batch_loss/train': 0.5664254012517631}
+12/24/2021 18:55:58 - INFO - codeparrot_training - Step 13738: {'lr': 0.00041402037500834547, 'samples': 7034368, 'steps': 13738, 'batch_loss/train': 0.8143429988995194}
+12/24/2021 18:56:08 - INFO - codeparrot_training - Step 13739: {'lr': 0.0004140084784018111, 'samples': 7034880, 'steps': 13739, 'batch_loss/train': 0.7422681129537523}
+12/24/2021 18:56:19 - INFO - codeparrot_training - Step 13740: {'lr': 0.0004139965811432409, 'samples': 7035392, 'steps': 13740, 'batch_loss/train': 0.8327446104958653}
+12/24/2021 18:56:31 - INFO - codeparrot_training - Step 13741: {'lr': 0.00041398468323268224, 'samples': 7035904, 'steps': 13741, 'batch_loss/train': 0.807286012917757}
+12/24/2021 18:56:42 - INFO - codeparrot_training - Step 13742: {'lr': 0.0004139727846701824, 'samples': 7036416, 'steps': 13742, 'batch_loss/train': 0.5721896469476633}
+12/24/2021 18:56:52 - INFO - codeparrot_training - Step 13743: {'lr': 0.0004139608854557887, 'samples': 7036928, 'steps': 13743, 'batch_loss/train': 0.7039823178201914}
+12/24/2021 18:57:03 - INFO - codeparrot_training - Step 13744: {'lr': 0.0004139489855895484, 'samples': 7037440, 'steps': 13744, 'batch_loss/train': 0.8394855805672705}
+12/24/2021 18:57:15 - INFO - codeparrot_training - Step 13745: {'lr': 0.0004139370850715088, 'samples': 7037952, 'steps': 13745, 'batch_loss/train': 0.7994116768240929}
+12/24/2021 18:57:26 - INFO - codeparrot_training - Step 13746: {'lr': 0.0004139251839017173, 'samples': 7038464, 'steps': 13746, 'batch_loss/train': 0.8983790781348944}
+12/24/2021 18:57:36 - INFO - codeparrot_training - Step 13747: {'lr': 0.0004139132820802212, 'samples': 7038976, 'steps': 13747, 'batch_loss/train': 0.47267161414492875}
+12/24/2021 18:57:50 - INFO - codeparrot_training - Step 13748: {'lr': 0.00041390137960706767, 'samples': 7039488, 'steps': 13748, 'batch_loss/train': 0.6873089817818254}
+12/24/2021 18:58:01 - INFO - codeparrot_training - Step 13749: {'lr': 0.00041388947648230426, 'samples': 7040000, 'steps': 13749, 'batch_loss/train': 0.7105399006977677}
+12/24/2021 18:58:11 - INFO - codeparrot_training - Step 13750: {'lr': 0.00041387757270597807, 'samples': 7040512, 'steps': 13750, 'batch_loss/train': 0.8636395689100027}
+12/24/2021 18:58:23 - INFO - codeparrot_training - Step 13751: {'lr': 0.0004138656682781365, 'samples': 7041024, 'steps': 13751, 'batch_loss/train': 0.7472064206376672}
+12/24/2021 18:58:34 - INFO - codeparrot_training - Step 13752: {'lr': 0.00041385376319882705, 'samples': 7041536, 'steps': 13752, 'batch_loss/train': 0.7574474830180407}
+12/24/2021 18:58:45 - INFO - codeparrot_training - Step 13753: {'lr': 0.0004138418574680969, 'samples': 7042048, 'steps': 13753, 'batch_loss/train': 0.8692765822634101}
+12/24/2021 18:58:59 - INFO - codeparrot_training - Step 13754: {'lr': 0.0004138299510859933, 'samples': 7042560, 'steps': 13754, 'batch_loss/train': 0.8347559403628111}
+12/24/2021 18:59:09 - INFO - codeparrot_training - Step 13755: {'lr': 0.0004138180440525637, 'samples': 7043072, 'steps': 13755, 'batch_loss/train': 0.7110188116785139}
+12/24/2021 18:59:20 - INFO - codeparrot_training - Step 13756: {'lr': 0.00041380613636785534, 'samples': 7043584, 'steps': 13756, 'batch_loss/train': 0.5543778762221336}
+12/24/2021 18:59:31 - INFO - codeparrot_training - Step 13757: {'lr': 0.0004137942280319158, 'samples': 7044096, 'steps': 13757, 'batch_loss/train': 0.7029660665430129}
+12/24/2021 18:59:43 - INFO - codeparrot_training - Step 13758: {'lr': 0.0004137823190447921, 'samples': 7044608, 'steps': 13758, 'batch_loss/train': 0.8327977927401662}
+12/24/2021 18:59:53 - INFO - codeparrot_training - Step 13759: {'lr': 0.0004137704094065319, 'samples': 7045120, 'steps': 13759, 'batch_loss/train': 0.7297650510445237}
+12/24/2021 19:00:04 - INFO - codeparrot_training - Step 13760: {'lr': 0.00041375849911718223, 'samples': 7045632, 'steps': 13760, 'batch_loss/train': 0.6714879022911191}
+12/24/2021 19:00:16 - INFO - codeparrot_training - Step 13761: {'lr': 0.0004137465881767907, 'samples': 7046144, 'steps': 13761, 'batch_loss/train': 0.8099147165194154}
+12/24/2021 19:00:27 - INFO - codeparrot_training - Step 13762: {'lr': 0.00041373467658540453, 'samples': 7046656, 'steps': 13762, 'batch_loss/train': 0.7030640514567494}
+12/24/2021 19:00:37 - INFO - codeparrot_training - Step 13763: {'lr': 0.0004137227643430711, 'samples': 7047168, 'steps': 13763, 'batch_loss/train': 0.8173875032225624}
+12/24/2021 19:00:51 - INFO - codeparrot_training - Step 13764: {'lr': 0.0004137108514498378, 'samples': 7047680, 'steps': 13764, 'batch_loss/train': 0.7252163379453123}
+12/24/2021 19:01:02 - INFO - codeparrot_training - Step 13765: {'lr': 0.000413698937905752, 'samples': 7048192, 'steps': 13765, 'batch_loss/train': 0.7321086304727942}
+12/24/2021 19:01:12 - INFO - codeparrot_training - Step 13766: {'lr': 0.0004136870237108609, 'samples': 7048704, 'steps': 13766, 'batch_loss/train': 0.7876685298979282}
+12/24/2021 19:01:24 - INFO - codeparrot_training - Step 13767: {'lr': 0.00041367510886521216, 'samples': 7049216, 'steps': 13767, 'batch_loss/train': 0.7364500996191055}
+12/24/2021 19:01:35 - INFO - codeparrot_training - Step 13768: {'lr': 0.00041366319336885287, 'samples': 7049728, 'steps': 13768, 'batch_loss/train': 0.8186225444078445}
+12/24/2021 19:01:46 - INFO - codeparrot_training - Step 13769: {'lr': 0.0004136512772218305, 'samples': 7050240, 'steps': 13769, 'batch_loss/train': 0.804456191137433}
+12/24/2021 19:01:56 - INFO - codeparrot_training - Step 13770: {'lr': 0.0004136393604241926, 'samples': 7050752, 'steps': 13770, 'batch_loss/train': 0.7949732150882483}
+12/24/2021 19:02:08 - INFO - codeparrot_training - Step 13771: {'lr': 0.0004136274429759863, 'samples': 7051264, 'steps': 13771, 'batch_loss/train': 0.77310883870814}
+12/24/2021 19:02:19 - INFO - codeparrot_training - Step 13772: {'lr': 0.00041361552487725905, 'samples': 7051776, 'steps': 13772, 'batch_loss/train': 0.850149161182344}
+12/24/2021 19:02:30 - INFO - codeparrot_training - Step 13773: {'lr': 0.00041360360612805824, 'samples': 7052288, 'steps': 13773, 'batch_loss/train': 0.7344567750114948}
+12/24/2021 19:02:42 - INFO - codeparrot_training - Step 13774: {'lr': 0.0004135916867284314, 'samples': 7052800, 'steps': 13774, 'batch_loss/train': 0.8862059488892555}
+12/24/2021 19:02:52 - INFO - codeparrot_training - Step 13775: {'lr': 0.0004135797666784257, 'samples': 7053312, 'steps': 13775, 'batch_loss/train': 0.8259107945486903}
+12/24/2021 19:03:03 - INFO - codeparrot_training - Step 13776: {'lr': 0.00041356784597808857, 'samples': 7053824, 'steps': 13776, 'batch_loss/train': 0.6449545131181367}
+12/24/2021 19:03:17 - INFO - codeparrot_training - Step 13777: {'lr': 0.00041355592462746744, 'samples': 7054336, 'steps': 13777, 'batch_loss/train': 0.8018773994408548}
+12/24/2021 19:03:27 - INFO - codeparrot_training - Step 13778: {'lr': 0.0004135440026266097, 'samples': 7054848, 'steps': 13778, 'batch_loss/train': 0.7598493844270706}
+12/24/2021 19:03:38 - INFO - codeparrot_training - Step 13779: {'lr': 0.00041353207997556283, 'samples': 7055360, 'steps': 13779, 'batch_loss/train': 0.7611016016453505}
+12/24/2021 19:03:48 - INFO - codeparrot_training - Step 13780: {'lr': 0.00041352015667437417, 'samples': 7055872, 'steps': 13780, 'batch_loss/train': 0.8139701951295137}
+12/24/2021 19:04:01 - INFO - codeparrot_training - Step 13781: {'lr': 0.000413508232723091, 'samples': 7056384, 'steps': 13781, 'batch_loss/train': 0.8054298779461533}
+12/24/2021 19:04:12 - INFO - codeparrot_training - Step 13782: {'lr': 0.0004134963081217609, 'samples': 7056896, 'steps': 13782, 'batch_loss/train': 0.7181649958947673}
+12/24/2021 19:04:22 - INFO - codeparrot_training - Step 13783: {'lr': 0.00041348438287043126, 'samples': 7057408, 'steps': 13783, 'batch_loss/train': 1.254366279579699}
+12/24/2021 19:04:36 - INFO - codeparrot_training - Step 13784: {'lr': 0.0004134724569691494, 'samples': 7057920, 'steps': 13784, 'batch_loss/train': 0.8452668786048889}
+12/24/2021 19:04:47 - INFO - codeparrot_training - Step 13785: {'lr': 0.0004134605304179628, 'samples': 7058432, 'steps': 13785, 'batch_loss/train': 0.8826300539076328}
+12/24/2021 19:04:57 - INFO - codeparrot_training - Step 13786: {'lr': 0.0004134486032169188, 'samples': 7058944, 'steps': 13786, 'batch_loss/train': 0.6541162537178025}
+12/24/2021 19:05:09 - INFO - codeparrot_training - Step 13787: {'lr': 0.0004134366753660649, 'samples': 7059456, 'steps': 13787, 'batch_loss/train': 0.8040604181587696}
+12/24/2021 19:05:20 - INFO - codeparrot_training - Step 13788: {'lr': 0.0004134247468654485, 'samples': 7059968, 'steps': 13788, 'batch_loss/train': 0.7409105292754248}
+12/24/2021 19:05:31 - INFO - codeparrot_training - Step 13789: {'lr': 0.00041341281771511696, 'samples': 7060480, 'steps': 13789, 'batch_loss/train': 0.588150198047515}
+12/24/2021 19:05:41 - INFO - codeparrot_training - Step 13790: {'lr': 0.0004134008879151178, 'samples': 7060992, 'steps': 13790, 'batch_loss/train': 0.7603881377726793}
+12/24/2021 19:05:54 - INFO - codeparrot_training - Step 13791: {'lr': 0.0004133889574654984, 'samples': 7061504, 'steps': 13791, 'batch_loss/train': 0.7656506458297372}
+12/24/2021 19:06:04 - INFO - codeparrot_training - Step 13792: {'lr': 0.00041337702636630626, 'samples': 7062016, 'steps': 13792, 'batch_loss/train': 0.6573046429548413}
+12/24/2021 19:06:15 - INFO - codeparrot_training - Step 13793: {'lr': 0.0004133650946175886, 'samples': 7062528, 'steps': 13793, 'batch_loss/train': 0.8574365223757923}
+12/24/2021 19:06:29 - INFO - codeparrot_training - Step 13794: {'lr': 0.0004133531622193932, 'samples': 7063040, 'steps': 13794, 'batch_loss/train': 0.7609620625153184}
+12/24/2021 19:06:39 - INFO - codeparrot_training - Step 13795: {'lr': 0.0004133412291717672, 'samples': 7063552, 'steps': 13795, 'batch_loss/train': 0.7340179816819727}
+12/24/2021 19:06:50 - INFO - codeparrot_training - Step 13796: {'lr': 0.00041332929547475814, 'samples': 7064064, 'steps': 13796, 'batch_loss/train': 0.7534839473664761}
+12/24/2021 19:07:02 - INFO - codeparrot_training - Step 13797: {'lr': 0.00041331736112841343, 'samples': 7064576, 'steps': 13797, 'batch_loss/train': 0.6740753091289662}
+12/24/2021 19:07:13 - INFO - codeparrot_training - Step 13798: {'lr': 0.00041330542613278063, 'samples': 7065088, 'steps': 13798, 'batch_loss/train': 0.8201344264671206}
+12/24/2021 19:07:23 - INFO - codeparrot_training - Step 13799: {'lr': 0.00041329349048790714, 'samples': 7065600, 'steps': 13799, 'batch_loss/train': 0.8119339402765036}
+12/24/2021 19:07:35 - INFO - codeparrot_training - Step 13800: {'lr': 0.0004132815541938404, 'samples': 7066112, 'steps': 13800, 'batch_loss/train': 0.8328267401084304}
+12/24/2021 19:07:46 - INFO - codeparrot_training - Step 13801: {'lr': 0.00041326961725062774, 'samples': 7066624, 'steps': 13801, 'batch_loss/train': 0.8421200728043914}
+12/24/2021 19:07:56 - INFO - codeparrot_training - Step 13802: {'lr': 0.00041325767965831687, 'samples': 7067136, 'steps': 13802, 'batch_loss/train': 0.821764625608921}
+12/24/2021 19:08:07 - INFO - codeparrot_training - Step 13803: {'lr': 0.00041324574141695503, 'samples': 7067648, 'steps': 13803, 'batch_loss/train': 0.7783314744010568}
+12/24/2021 19:08:21 - INFO - codeparrot_training - Step 13804: {'lr': 0.00041323380252658977, 'samples': 7068160, 'steps': 13804, 'batch_loss/train': 0.6536838025785983}
+12/24/2021 19:08:32 - INFO - codeparrot_training - Step 13805: {'lr': 0.00041322186298726847, 'samples': 7068672, 'steps': 13805, 'batch_loss/train': 0.7722303494811058}
+12/24/2021 19:08:42 - INFO - codeparrot_training - Step 13806: {'lr': 0.0004132099227990388, 'samples': 7069184, 'steps': 13806, 'batch_loss/train': 1.6551284750457853}
+12/24/2021 19:08:54 - INFO - codeparrot_training - Step 13807: {'lr': 0.00041319798196194803, 'samples': 7069696, 'steps': 13807, 'batch_loss/train': 0.8546575368382037}
+12/24/2021 19:09:05 - INFO - codeparrot_training - Step 13808: {'lr': 0.0004131860404760437, 'samples': 7070208, 'steps': 13808, 'batch_loss/train': 0.6782859904924408}
+12/24/2021 19:09:16 - INFO - codeparrot_training - Step 13809: {'lr': 0.00041317409834137333, 'samples': 7070720, 'steps': 13809, 'batch_loss/train': 0.6992060746997595}
+12/24/2021 19:09:28 - INFO - codeparrot_training - Step 13810: {'lr': 0.00041316215555798437, 'samples': 7071232, 'steps': 13810, 'batch_loss/train': 0.7432420841942076}
+12/24/2021 19:09:38 - INFO - codeparrot_training - Step 13811: {'lr': 0.0004131502121259243, 'samples': 7071744, 'steps': 13811, 'batch_loss/train': 0.8000726504251361}
+12/24/2021 19:09:49 - INFO - codeparrot_training - Step 13812: {'lr': 0.00041313826804524053, 'samples': 7072256, 'steps': 13812, 'batch_loss/train': 0.6671086917631328}
+12/24/2021 19:10:03 - INFO - codeparrot_training - Step 13813: {'lr': 0.00041312632331598064, 'samples': 7072768, 'steps': 13813, 'batch_loss/train': 0.8069752398878336}
+12/24/2021 19:10:13 - INFO - codeparrot_training - Step 13814: {'lr': 0.000413114377938192, 'samples': 7073280, 'steps': 13814, 'batch_loss/train': 0.5336777325719595}
+12/24/2021 19:10:24 - INFO - codeparrot_training - Step 13815: {'lr': 0.00041310243191192234, 'samples': 7073792, 'steps': 13815, 'batch_loss/train': 0.8123653624206781}
+12/24/2021 19:10:35 - INFO - codeparrot_training - Step 13816: {'lr': 0.0004130904852372188, 'samples': 7074304, 'steps': 13816, 'batch_loss/train': 0.8205056395381689}
+12/24/2021 19:10:47 - INFO - codeparrot_training - Step 13817: {'lr': 0.0004130785379141292, 'samples': 7074816, 'steps': 13817, 'batch_loss/train': 0.6982385264709592}
+12/24/2021 19:10:57 - INFO - codeparrot_training - Step 13818: {'lr': 0.0004130665899427009, 'samples': 7075328, 'steps': 13818, 'batch_loss/train': 0.7416854574694298}
+12/24/2021 19:11:08 - INFO - codeparrot_training - Step 13819: {'lr': 0.00041305464132298137, 'samples': 7075840, 'steps': 13819, 'batch_loss/train': 0.8176624048501253}
+12/24/2021 19:11:20 - INFO - codeparrot_training - Step 13820: {'lr': 0.0004130426920550182, 'samples': 7076352, 'steps': 13820, 'batch_loss/train': 0.8363923761062324}
+12/24/2021 19:11:31 - INFO - codeparrot_training - Step 13821: {'lr': 0.0004130307421388588, 'samples': 7076864, 'steps': 13821, 'batch_loss/train': 0.7054522428661585}
+12/24/2021 19:11:41 - INFO - codeparrot_training - Step 13822: {'lr': 0.0004130187915745508, 'samples': 7077376, 'steps': 13822, 'batch_loss/train': 0.6923885527648963}
+12/24/2021 19:11:55 - INFO - codeparrot_training - Step 13823: {'lr': 0.0004130068403621416, 'samples': 7077888, 'steps': 13823, 'batch_loss/train': 0.7390890698879957}
+12/24/2021 19:12:06 - INFO - codeparrot_training - Step 13824: {'lr': 0.0004129948885016788, 'samples': 7078400, 'steps': 13824, 'batch_loss/train': 0.8712930865585804}
+12/24/2021 19:12:16 - INFO - codeparrot_training - Step 13825: {'lr': 0.00041298293599320975, 'samples': 7078912, 'steps': 13825, 'batch_loss/train': 0.711054421029985}
+12/24/2021 19:12:27 - INFO - codeparrot_training - Step 13826: {'lr': 0.00041297098283678215, 'samples': 7079424, 'steps': 13826, 'batch_loss/train': 0.7081672102212906}
+12/24/2021 19:12:39 - INFO - codeparrot_training - Step 13827: {'lr': 0.0004129590290324434, 'samples': 7079936, 'steps': 13827, 'batch_loss/train': 0.8310264572501183}
+12/24/2021 19:12:50 - INFO - codeparrot_training - Step 13828: {'lr': 0.0004129470745802412, 'samples': 7080448, 'steps': 13828, 'batch_loss/train': 0.7231151815503836}
+12/24/2021 19:13:00 - INFO - codeparrot_training - Step 13829: {'lr': 0.0004129351194802229, 'samples': 7080960, 'steps': 13829, 'batch_loss/train': 0.5560917900002096}
+12/24/2021 19:13:13 - INFO - codeparrot_training - Step 13830: {'lr': 0.00041292316373243613, 'samples': 7081472, 'steps': 13830, 'batch_loss/train': 0.6821587373851798}
+12/24/2021 19:13:24 - INFO - codeparrot_training - Step 13831: {'lr': 0.0004129112073369283, 'samples': 7081984, 'steps': 13831, 'batch_loss/train': 0.7934941085986793}
+12/24/2021 19:13:34 - INFO - codeparrot_training - Step 13832: {'lr': 0.000412899250293747, 'samples': 7082496, 'steps': 13832, 'batch_loss/train': 0.787737812846899}
+12/24/2021 19:13:48 - INFO - codeparrot_training - Step 13833: {'lr': 0.0004128872926029399, 'samples': 7083008, 'steps': 13833, 'batch_loss/train': 0.7046836782246828}
+12/24/2021 19:13:59 - INFO - codeparrot_training - Step 13834: {'lr': 0.00041287533426455434, 'samples': 7083520, 'steps': 13834, 'batch_loss/train': 0.7218586192466319}
+12/24/2021 19:14:09 - INFO - codeparrot_training - Step 13835: {'lr': 0.000412863375278638, 'samples': 7084032, 'steps': 13835, 'batch_loss/train': 0.7680007279850543}
+12/24/2021 19:14:21 - INFO - codeparrot_training - Step 13836: {'lr': 0.00041285141564523833, 'samples': 7084544, 'steps': 13836, 'batch_loss/train': 0.7419218700379133}
+12/24/2021 19:14:32 - INFO - codeparrot_training - Step 13837: {'lr': 0.000412839455364403, 'samples': 7085056, 'steps': 13837, 'batch_loss/train': 0.7094696526182815}
+12/24/2021 19:14:43 - INFO - codeparrot_training - Step 13838: {'lr': 0.0004128274944361794, 'samples': 7085568, 'steps': 13838, 'batch_loss/train': 1.5229622810147703}
+12/24/2021 19:14:53 - INFO - codeparrot_training - Step 13839: {'lr': 0.00041281553286061525, 'samples': 7086080, 'steps': 13839, 'batch_loss/train': 0.7207257116679102}
+12/24/2021 19:15:07 - INFO - codeparrot_training - Step 13840: {'lr': 0.00041280357063775786, 'samples': 7086592, 'steps': 13840, 'batch_loss/train': 0.7817963939160109}
+12/24/2021 19:15:17 - INFO - codeparrot_training - Step 13841: {'lr': 0.00041279160776765513, 'samples': 7087104, 'steps': 13841, 'batch_loss/train': 0.6269746905309148}
+12/24/2021 19:15:28 - INFO - codeparrot_training - Step 13842: {'lr': 0.0004127796442503543, 'samples': 7087616, 'steps': 13842, 'batch_loss/train': 0.7492403733776882}
+12/24/2021 19:15:40 - INFO - codeparrot_training - Step 13843: {'lr': 0.00041276768008590315, 'samples': 7088128, 'steps': 13843, 'batch_loss/train': 0.7393173091113567}
+12/24/2021 19:15:51 - INFO - codeparrot_training - Step 13844: {'lr': 0.0004127557152743491, 'samples': 7088640, 'steps': 13844, 'batch_loss/train': 0.7269350872375071}
+12/24/2021 19:16:01 - INFO - codeparrot_training - Step 13845: {'lr': 0.0004127437498157398, 'samples': 7089152, 'steps': 13845, 'batch_loss/train': 0.9026270033791661}
+12/24/2021 19:16:14 - INFO - codeparrot_training - Step 13846: {'lr': 0.00041273178371012284, 'samples': 7089664, 'steps': 13846, 'batch_loss/train': 0.7188053233548999}
+12/24/2021 19:16:24 - INFO - codeparrot_training - Step 13847: {'lr': 0.0004127198169575457, 'samples': 7090176, 'steps': 13847, 'batch_loss/train': 0.7137117060483433}
+12/24/2021 19:16:35 - INFO - codeparrot_training - Step 13848: {'lr': 0.00041270784955805607, 'samples': 7090688, 'steps': 13848, 'batch_loss/train': 0.8657901147380471}
+12/24/2021 19:16:45 - INFO - codeparrot_training - Step 13849: {'lr': 0.0004126958815117014, 'samples': 7091200, 'steps': 13849, 'batch_loss/train': 0.7976212091743946}
+12/24/2021 19:16:58 - INFO - codeparrot_training - Step 13850: {'lr': 0.00041268391281852943, 'samples': 7091712, 'steps': 13850, 'batch_loss/train': 0.8473435062915087}
+12/24/2021 19:17:08 - INFO - codeparrot_training - Step 13851: {'lr': 0.00041267194347858755, 'samples': 7092224, 'steps': 13851, 'batch_loss/train': 0.8161035836674273}
+12/24/2021 19:17:19 - INFO - codeparrot_training - Step 13852: {'lr': 0.00041265997349192353, 'samples': 7092736, 'steps': 13852, 'batch_loss/train': 0.6923118841368705}
+12/24/2021 19:17:33 - INFO - codeparrot_training - Step 13853: {'lr': 0.00041264800285858473, 'samples': 7093248, 'steps': 13853, 'batch_loss/train': 0.7879116013646126}
+12/24/2021 19:17:44 - INFO - codeparrot_training - Step 13854: {'lr': 0.0004126360315786191, 'samples': 7093760, 'steps': 13854, 'batch_loss/train': 0.8251137644983828}
+12/24/2021 19:17:54 - INFO - codeparrot_training - Step 13855: {'lr': 0.00041262405965207386, 'samples': 7094272, 'steps': 13855, 'batch_loss/train': 0.7922248980030417}
+12/24/2021 19:18:06 - INFO - codeparrot_training - Step 13856: {'lr': 0.00041261208707899676, 'samples': 7094784, 'steps': 13856, 'batch_loss/train': 0.5713498702971265}
+12/24/2021 19:18:17 - INFO - codeparrot_training - Step 13857: {'lr': 0.0004126001138594354, 'samples': 7095296, 'steps': 13857, 'batch_loss/train': 0.7829071450978518}
+12/24/2021 19:18:28 - INFO - codeparrot_training - Step 13858: {'lr': 0.0004125881399934375, 'samples': 7095808, 'steps': 13858, 'batch_loss/train': 0.8107706811279058}
+12/24/2021 19:18:38 - INFO - codeparrot_training - Step 13859: {'lr': 0.0004125761654810504, 'samples': 7096320, 'steps': 13859, 'batch_loss/train': 0.8227475108578801}
+12/24/2021 19:18:50 - INFO - codeparrot_training - Step 13860: {'lr': 0.00041256419032232195, 'samples': 7096832, 'steps': 13860, 'batch_loss/train': 0.8826451729983091}
+12/24/2021 19:19:01 - INFO - codeparrot_training - Step 13861: {'lr': 0.00041255221451729965, 'samples': 7097344, 'steps': 13861, 'batch_loss/train': 0.7966415546834469}
+12/24/2021 19:19:12 - INFO - codeparrot_training - Step 13862: {'lr': 0.0004125402380660311, 'samples': 7097856, 'steps': 13862, 'batch_loss/train': 0.7238206492038444}
+12/24/2021 19:19:25 - INFO - codeparrot_training - Step 13863: {'lr': 0.000412528260968564, 'samples': 7098368, 'steps': 13863, 'batch_loss/train': 0.7158109792508185}
+12/24/2021 19:19:36 - INFO - codeparrot_training - Step 13864: {'lr': 0.00041251628322494575, 'samples': 7098880, 'steps': 13864, 'batch_loss/train': 0.6837175348773599}
+12/24/2021 19:19:47 - INFO - codeparrot_training - Step 13865: {'lr': 0.0004125043048352243, 'samples': 7099392, 'steps': 13865, 'batch_loss/train': 0.729366144631058}
+12/24/2021 19:19:59 - INFO - codeparrot_training - Step 13866: {'lr': 0.00041249232579944697, 'samples': 7099904, 'steps': 13866, 'batch_loss/train': 0.8408379824832082}
+12/24/2021 19:20:09 - INFO - codeparrot_training - Step 13867: {'lr': 0.0004124803461176615, 'samples': 7100416, 'steps': 13867, 'batch_loss/train': 0.8124661212787032}
+12/24/2021 19:20:20 - INFO - codeparrot_training - Step 13868: {'lr': 0.00041246836578991565, 'samples': 7100928, 'steps': 13868, 'batch_loss/train': 0.7492935814661905}
+12/24/2021 19:20:32 - INFO - codeparrot_training - Step 13869: {'lr': 0.0004124563848162568, 'samples': 7101440, 'steps': 13869, 'batch_loss/train': 0.7596230180934072}
+12/24/2021 19:20:43 - INFO - codeparrot_training - Step 13870: {'lr': 0.0004124444031967328, 'samples': 7101952, 'steps': 13870, 'batch_loss/train': 0.8455656040459871}
+12/24/2021 19:20:54 - INFO - codeparrot_training - Step 13871: {'lr': 0.0004124324209313911, 'samples': 7102464, 'steps': 13871, 'batch_loss/train': 0.7423830169718713}
+12/24/2021 19:21:04 - INFO - codeparrot_training - Step 13872: {'lr': 0.0004124204380202795, 'samples': 7102976, 'steps': 13872, 'batch_loss/train': 0.7052617112058215}
+12/24/2021 19:21:18 - INFO - codeparrot_training - Step 13873: {'lr': 0.0004124084544634455, 'samples': 7103488, 'steps': 13873, 'batch_loss/train': 0.5409138493123464}
+12/24/2021 19:21:29 - INFO - codeparrot_training - Step 13874: {'lr': 0.00041239647026093684, 'samples': 7104000, 'steps': 13874, 'batch_loss/train': 0.826431043446064}
+12/24/2021 19:21:39 - INFO - codeparrot_training - Step 13875: {'lr': 0.00041238448541280117, 'samples': 7104512, 'steps': 13875, 'batch_loss/train': 0.7790813045576215}
+12/24/2021 19:21:51 - INFO - codeparrot_training - Step 13876: {'lr': 0.00041237249991908604, 'samples': 7105024, 'steps': 13876, 'batch_loss/train': 0.7998730465769768}
+12/24/2021 19:22:02 - INFO - codeparrot_training - Step 13877: {'lr': 0.00041236051377983916, 'samples': 7105536, 'steps': 13877, 'batch_loss/train': 0.7523517006775364}
+12/24/2021 19:22:12 - INFO - codeparrot_training - Step 13878: {'lr': 0.0004123485269951083, 'samples': 7106048, 'steps': 13878, 'batch_loss/train': 0.7682518009096384}
+12/24/2021 19:22:26 - INFO - codeparrot_training - Step 13879: {'lr': 0.0004123365395649408, 'samples': 7106560, 'steps': 13879, 'batch_loss/train': 0.7962389052845538}
+12/24/2021 19:22:37 - INFO - codeparrot_training - Step 13880: {'lr': 0.00041232455148938464, 'samples': 7107072, 'steps': 13880, 'batch_loss/train': 0.5892719498369843}
+12/24/2021 19:22:48 - INFO - codeparrot_training - Step 13881: {'lr': 0.0004123125627684874, 'samples': 7107584, 'steps': 13881, 'batch_loss/train': 0.832256143912673}
+12/24/2021 19:22:58 - INFO - codeparrot_training - Step 13882: {'lr': 0.00041230057340229656, 'samples': 7108096, 'steps': 13882, 'batch_loss/train': 0.8257887233048677}
+12/24/2021 19:23:11 - INFO - codeparrot_training - Step 13883: {'lr': 0.00041228858339086, 'samples': 7108608, 'steps': 13883, 'batch_loss/train': 0.8291447944939137}
+12/24/2021 19:23:21 - INFO - codeparrot_training - Step 13884: {'lr': 0.0004122765927342253, 'samples': 7109120, 'steps': 13884, 'batch_loss/train': 0.5774636511923745}
+12/24/2021 19:23:32 - INFO - codeparrot_training - Step 13885: {'lr': 0.00041226460143244017, 'samples': 7109632, 'steps': 13885, 'batch_loss/train': 0.8914419384673238}
+12/24/2021 19:23:44 - INFO - codeparrot_training - Step 13886: {'lr': 0.0004122526094855522, 'samples': 7110144, 'steps': 13886, 'batch_loss/train': 0.6644128388725221}
+12/24/2021 19:23:55 - INFO - codeparrot_training - Step 13887: {'lr': 0.00041224061689360914, 'samples': 7110656, 'steps': 13887, 'batch_loss/train': 0.9055015463382006}
+12/24/2021 19:24:05 - INFO - codeparrot_training - Step 13888: {'lr': 0.0004122286236566587, 'samples': 7111168, 'steps': 13888, 'batch_loss/train': 0.7438381639658473}
+12/24/2021 19:24:20 - INFO - codeparrot_training - Step 13889: {'lr': 0.00041221662977474844, 'samples': 7111680, 'steps': 13889, 'batch_loss/train': 0.6994635771261528}
+12/24/2021 19:24:30 - INFO - codeparrot_training - Step 13890: {'lr': 0.00041220463524792604, 'samples': 7112192, 'steps': 13890, 'batch_loss/train': 0.8810921711847186}
+12/24/2021 19:24:41 - INFO - codeparrot_training - Step 13891: {'lr': 0.00041219264007623943, 'samples': 7112704, 'steps': 13891, 'batch_loss/train': 1.6836614892818034}
+12/24/2021 19:24:52 - INFO - codeparrot_training - Step 13892: {'lr': 0.000412180644259736, 'samples': 7113216, 'steps': 13892, 'batch_loss/train': 0.8163724625483155}
+12/24/2021 19:25:04 - INFO - codeparrot_training - Step 13893: {'lr': 0.00041216864779846366, 'samples': 7113728, 'steps': 13893, 'batch_loss/train': 0.8661471856757998}
+12/24/2021 19:25:14 - INFO - codeparrot_training - Step 13894: {'lr': 0.00041215665069246996, 'samples': 7114240, 'steps': 13894, 'batch_loss/train': 0.8577881581149995}
+12/24/2021 19:25:25 - INFO - codeparrot_training - Step 13895: {'lr': 0.0004121446529418026, 'samples': 7114752, 'steps': 13895, 'batch_loss/train': 0.8635135681251995}
+12/24/2021 19:25:37 - INFO - codeparrot_training - Step 13896: {'lr': 0.0004121326545465094, 'samples': 7115264, 'steps': 13896, 'batch_loss/train': 0.5714422440505587}
+12/24/2021 19:25:48 - INFO - codeparrot_training - Step 13897: {'lr': 0.00041212065550663793, 'samples': 7115776, 'steps': 13897, 'batch_loss/train': 0.7325993133708835}
+12/24/2021 19:25:58 - INFO - codeparrot_training - Step 13898: {'lr': 0.000412108655822236, 'samples': 7116288, 'steps': 13898, 'batch_loss/train': 0.7717183511704206}
+12/24/2021 19:26:12 - INFO - codeparrot_training - Step 13899: {'lr': 0.0004120966554933512, 'samples': 7116800, 'steps': 13899, 'batch_loss/train': 0.6340821543126367}
+12/24/2021 19:26:23 - INFO - codeparrot_training - Step 13900: {'lr': 0.0004120846545200313, 'samples': 7117312, 'steps': 13900, 'batch_loss/train': 0.8131558392196894}
+12/24/2021 19:26:33 - INFO - codeparrot_training - Step 13901: {'lr': 0.0004120726529023241, 'samples': 7117824, 'steps': 13901, 'batch_loss/train': 0.8128682803362608}
+12/24/2021 19:26:45 - INFO - codeparrot_training - Step 13902: {'lr': 0.0004120606506402772, 'samples': 7118336, 'steps': 13902, 'batch_loss/train': 0.8131849518977106}
+12/24/2021 19:26:56 - INFO - codeparrot_training - Step 13903: {'lr': 0.00041204864773393825, 'samples': 7118848, 'steps': 13903, 'batch_loss/train': 0.8673683982342482}
+12/24/2021 19:27:07 - INFO - codeparrot_training - Step 13904: {'lr': 0.0004120366441833551, 'samples': 7119360, 'steps': 13904, 'batch_loss/train': 0.7107691017445177}
+12/24/2021 19:27:17 - INFO - codeparrot_training - Step 13905: {'lr': 0.0004120246399885755, 'samples': 7119872, 'steps': 13905, 'batch_loss/train': 0.6990752932615578}
+12/24/2021 19:27:29 - INFO - codeparrot_training - Step 13906: {'lr': 0.0004120126351496471, 'samples': 7120384, 'steps': 13906, 'batch_loss/train': 0.7233710014261305}
+12/24/2021 19:27:40 - INFO - codeparrot_training - Step 13907: {'lr': 0.00041200062966661766, 'samples': 7120896, 'steps': 13907, 'batch_loss/train': 0.7338734278455377}
+12/24/2021 19:27:51 - INFO - codeparrot_training - Step 13908: {'lr': 0.0004119886235395348, 'samples': 7121408, 'steps': 13908, 'batch_loss/train': 0.7287185871973634}
+12/24/2021 19:28:04 - INFO - codeparrot_training - Step 13909: {'lr': 0.0004119766167684464, 'samples': 7121920, 'steps': 13909, 'batch_loss/train': 0.8099658545106649}
+12/24/2021 19:28:15 - INFO - codeparrot_training - Step 13910: {'lr': 0.00041196460935340006, 'samples': 7122432, 'steps': 13910, 'batch_loss/train': 0.7518203910440207}
+12/24/2021 19:28:26 - INFO - codeparrot_training - Step 13911: {'lr': 0.0004119526012944437, 'samples': 7122944, 'steps': 13911, 'batch_loss/train': 0.7432790687307715}
+12/24/2021 19:28:38 - INFO - codeparrot_training - Step 13912: {'lr': 0.0004119405925916249, 'samples': 7123456, 'steps': 13912, 'batch_loss/train': 0.7531077340245247}
+12/24/2021 19:28:48 - INFO - codeparrot_training - Step 13913: {'lr': 0.0004119285832449914, 'samples': 7123968, 'steps': 13913, 'batch_loss/train': 0.7231715171365067}
+12/24/2021 19:28:59 - INFO - codeparrot_training - Step 13914: {'lr': 0.00041191657325459106, 'samples': 7124480, 'steps': 13914, 'batch_loss/train': 0.7240879312157631}
+12/24/2021 19:29:11 - INFO - codeparrot_training - Step 13915: {'lr': 0.00041190456262047147, 'samples': 7124992, 'steps': 13915, 'batch_loss/train': 0.75280727352947}
+12/24/2021 19:29:22 - INFO - codeparrot_training - Step 13916: {'lr': 0.00041189255134268057, 'samples': 7125504, 'steps': 13916, 'batch_loss/train': 0.756965477950871}
+12/24/2021 19:29:32 - INFO - codeparrot_training - Step 13917: {'lr': 0.00041188053942126595, 'samples': 7126016, 'steps': 13917, 'batch_loss/train': 0.7368351048789918}
+12/24/2021 19:29:43 - INFO - codeparrot_training - Step 13918: {'lr': 0.00041186852685627553, 'samples': 7126528, 'steps': 13918, 'batch_loss/train': 0.8117497656494379}
+12/24/2021 19:29:57 - INFO - codeparrot_training - Step 13919: {'lr': 0.0004118565136477568, 'samples': 7127040, 'steps': 13919, 'batch_loss/train': 0.5958026023581624}
+12/24/2021 19:30:08 - INFO - codeparrot_training - Step 13920: {'lr': 0.00041184449979575786, 'samples': 7127552, 'steps': 13920, 'batch_loss/train': 0.7007558700861409}
+12/24/2021 19:30:18 - INFO - codeparrot_training - Step 13921: {'lr': 0.0004118324853003262, 'samples': 7128064, 'steps': 13921, 'batch_loss/train': 0.6878484301269054}
+12/24/2021 19:30:30 - INFO - codeparrot_training - Step 13922: {'lr': 0.0004118204701615097, 'samples': 7128576, 'steps': 13922, 'batch_loss/train': 0.8642453588545322}
+12/24/2021 19:30:41 - INFO - codeparrot_training - Step 13923: {'lr': 0.0004118084543793561, 'samples': 7129088, 'steps': 13923, 'batch_loss/train': 0.7895752554759383}
+12/24/2021 19:30:51 - INFO - codeparrot_training - Step 13924: {'lr': 0.0004117964379539132, 'samples': 7129600, 'steps': 13924, 'batch_loss/train': 0.7869997974485159}
+12/24/2021 19:31:05 - INFO - codeparrot_training - Step 13925: {'lr': 0.0004117844208852288, 'samples': 7130112, 'steps': 13925, 'batch_loss/train': 0.7850196645595133}
+12/24/2021 19:31:16 - INFO - codeparrot_training - Step 13926: {'lr': 0.0004117724031733506, 'samples': 7130624, 'steps': 13926, 'batch_loss/train': 0.775435988791287}
+12/24/2021 19:31:27 - INFO - codeparrot_training - Step 13927: {'lr': 0.00041176038481832635, 'samples': 7131136, 'steps': 13927, 'batch_loss/train': 0.8554649790748954}
+12/24/2021 19:31:39 - INFO - codeparrot_training - Step 13928: {'lr': 0.0004117483658202039, 'samples': 7131648, 'steps': 13928, 'batch_loss/train': 0.8903634222224355}
+12/24/2021 19:31:49 - INFO - codeparrot_training - Step 13929: {'lr': 0.0004117363461790311, 'samples': 7132160, 'steps': 13929, 'batch_loss/train': 0.7546544759534299}
+12/24/2021 19:32:00 - INFO - codeparrot_training - Step 13930: {'lr': 0.0004117243258948555, 'samples': 7132672, 'steps': 13930, 'batch_loss/train': 0.7029049132252112}
+12/24/2021 19:32:11 - INFO - codeparrot_training - Step 13931: {'lr': 0.0004117123049677253, 'samples': 7133184, 'steps': 13931, 'batch_loss/train': 0.7112559049855918}
+12/24/2021 19:32:23 - INFO - codeparrot_training - Step 13932: {'lr': 0.00041170028339768784, 'samples': 7133696, 'steps': 13932, 'batch_loss/train': 0.745105360285379}
+12/24/2021 19:32:33 - INFO - codeparrot_training - Step 13933: {'lr': 0.0004116882611847912, 'samples': 7134208, 'steps': 13933, 'batch_loss/train': 0.8006752240471542}
+12/24/2021 19:32:44 - INFO - codeparrot_training - Step 13934: {'lr': 0.00041167623832908296, 'samples': 7134720, 'steps': 13934, 'batch_loss/train': 0.8043532008305192}
+12/24/2021 19:32:56 - INFO - codeparrot_training - Step 13935: {'lr': 0.0004116642148306111, 'samples': 7135232, 'steps': 13935, 'batch_loss/train': 0.8331430535763502}
+12/24/2021 19:33:07 - INFO - codeparrot_training - Step 13936: {'lr': 0.00041165219068942343, 'samples': 7135744, 'steps': 13936, 'batch_loss/train': 0.8339579286985099}
+12/24/2021 19:33:17 - INFO - codeparrot_training - Step 13937: {'lr': 0.0004116401659055676, 'samples': 7136256, 'steps': 13937, 'batch_loss/train': 0.6731277249054983}
+12/24/2021 19:33:31 - INFO - codeparrot_training - Step 13938: {'lr': 0.00041162814047909156, 'samples': 7136768, 'steps': 13938, 'batch_loss/train': 0.7882440134417266}
+12/24/2021 19:33:42 - INFO - codeparrot_training - Step 13939: {'lr': 0.0004116161144100431, 'samples': 7137280, 'steps': 13939, 'batch_loss/train': 0.7255773618817329}
+12/24/2021 19:33:53 - INFO - codeparrot_training - Step 13940: {'lr': 0.0004116040876984699, 'samples': 7137792, 'steps': 13940, 'batch_loss/train': 0.7576815681532025}
+12/24/2021 19:34:03 - INFO - codeparrot_training - Step 13941: {'lr': 0.0004115920603444199, 'samples': 7138304, 'steps': 13941, 'batch_loss/train': 0.7593799885362387}
+12/24/2021 19:34:15 - INFO - codeparrot_training - Step 13942: {'lr': 0.00041158003234794094, 'samples': 7138816, 'steps': 13942, 'batch_loss/train': 0.8055243836715817}
+12/24/2021 19:34:26 - INFO - codeparrot_training - Step 13943: {'lr': 0.00041156800370908075, 'samples': 7139328, 'steps': 13943, 'batch_loss/train': 0.7637424366548657}
+12/24/2021 19:34:36 - INFO - codeparrot_training - Step 13944: {'lr': 0.00041155597442788715, 'samples': 7139840, 'steps': 13944, 'batch_loss/train': 0.6354571045958437}
+12/24/2021 19:34:49 - INFO - codeparrot_training - Step 13945: {'lr': 0.000411543944504408, 'samples': 7140352, 'steps': 13945, 'batch_loss/train': 0.7756950249895453}
+12/24/2021 19:34:59 - INFO - codeparrot_training - Step 13946: {'lr': 0.00041153191393869114, 'samples': 7140864, 'steps': 13946, 'batch_loss/train': 0.7994091277942061}
+12/24/2021 19:35:10 - INFO - codeparrot_training - Step 13947: {'lr': 0.0004115198827307844, 'samples': 7141376, 'steps': 13947, 'batch_loss/train': 0.775285454466939}
+12/24/2021 19:35:24 - INFO - codeparrot_training - Step 13948: {'lr': 0.00041150785088073564, 'samples': 7141888, 'steps': 13948, 'batch_loss/train': 0.8141383100301027}
+12/24/2021 19:35:34 - INFO - codeparrot_training - Step 13949: {'lr': 0.0004114958183885925, 'samples': 7142400, 'steps': 13949, 'batch_loss/train': 0.8275740873068571}
+12/24/2021 19:35:45 - INFO - codeparrot_training - Step 13950: {'lr': 0.0004114837852544031, 'samples': 7142912, 'steps': 13950, 'batch_loss/train': 0.7098526963964105}
+12/24/2021 19:35:57 - INFO - codeparrot_training - Step 13951: {'lr': 0.00041147175147821505, 'samples': 7143424, 'steps': 13951, 'batch_loss/train': 0.8021522685885429}
+12/24/2021 19:36:08 - INFO - codeparrot_training - Step 13952: {'lr': 0.00041145971706007633, 'samples': 7143936, 'steps': 13952, 'batch_loss/train': 0.7627892135642469}
+12/24/2021 19:36:18 - INFO - codeparrot_training - Step 13953: {'lr': 0.00041144768200003474, 'samples': 7144448, 'steps': 13953, 'batch_loss/train': 0.7356639923527837}
+12/24/2021 19:36:29 - INFO - codeparrot_training - Step 13954: {'lr': 0.00041143564629813814, 'samples': 7144960, 'steps': 13954, 'batch_loss/train': 0.8613860569894314}
+12/24/2021 19:36:43 - INFO - codeparrot_training - Step 13955: {'lr': 0.00041142360995443435, 'samples': 7145472, 'steps': 13955, 'batch_loss/train': 0.7789567415602505}
+12/24/2021 19:36:53 - INFO - codeparrot_training - Step 13956: {'lr': 0.00041141157296897124, 'samples': 7145984, 'steps': 13956, 'batch_loss/train': 0.7483404912054539}
+12/24/2021 19:37:04 - INFO - codeparrot_training - Step 13957: {'lr': 0.0004113995353417966, 'samples': 7146496, 'steps': 13957, 'batch_loss/train': 0.7338802739977837}
+12/24/2021 19:37:16 - INFO - codeparrot_training - Step 13958: {'lr': 0.0004113874970729584, 'samples': 7147008, 'steps': 13958, 'batch_loss/train': 0.7805010955780745}
+12/24/2021 19:37:26 - INFO - codeparrot_training - Step 13959: {'lr': 0.00041137545816250453, 'samples': 7147520, 'steps': 13959, 'batch_loss/train': 0.8014207938686013}
+12/24/2021 19:37:37 - INFO - codeparrot_training - Step 13960: {'lr': 0.00041136341861048263, 'samples': 7148032, 'steps': 13960, 'batch_loss/train': 0.622970447584521}
+12/24/2021 19:37:49 - INFO - codeparrot_training - Step 13961: {'lr': 0.0004113513784169408, 'samples': 7148544, 'steps': 13961, 'batch_loss/train': 0.574941924714949}
+12/24/2021 19:38:00 - INFO - codeparrot_training - Step 13962: {'lr': 0.00041133933758192675, 'samples': 7149056, 'steps': 13962, 'batch_loss/train': 0.7517035251948982}
+12/24/2021 19:38:10 - INFO - codeparrot_training - Step 13963: {'lr': 0.0004113272961054885, 'samples': 7149568, 'steps': 13963, 'batch_loss/train': 0.6952986119431444}
+12/24/2021 19:38:24 - INFO - codeparrot_training - Step 13964: {'lr': 0.00041131525398767376, 'samples': 7150080, 'steps': 13964, 'batch_loss/train': 0.7622777394717559}
+12/24/2021 19:38:35 - INFO - codeparrot_training - Step 13965: {'lr': 0.00041130321122853056, 'samples': 7150592, 'steps': 13965, 'batch_loss/train': 0.85027090087533}
+12/24/2021 19:38:46 - INFO - codeparrot_training - Step 13966: {'lr': 0.0004112911678281066, 'samples': 7151104, 'steps': 13966, 'batch_loss/train': 0.7995479786768556}
+12/24/2021 19:38:56 - INFO - codeparrot_training - Step 13967: {'lr': 0.0004112791237864499, 'samples': 7151616, 'steps': 13967, 'batch_loss/train': 0.8043054859153926}
+12/24/2021 19:39:08 - INFO - codeparrot_training - Step 13968: {'lr': 0.0004112670791036083, 'samples': 7152128, 'steps': 13968, 'batch_loss/train': 0.8312921114265919}
+12/24/2021 19:39:19 - INFO - codeparrot_training - Step 13969: {'lr': 0.0004112550337796297, 'samples': 7152640, 'steps': 13969, 'batch_loss/train': 0.8016615780070424}
+12/24/2021 19:39:30 - INFO - codeparrot_training - Step 13970: {'lr': 0.00041124298781456206, 'samples': 7153152, 'steps': 13970, 'batch_loss/train': 0.8084822967648506}
+12/24/2021 19:39:41 - INFO - codeparrot_training - Step 13971: {'lr': 0.000411230941208453, 'samples': 7153664, 'steps': 13971, 'batch_loss/train': 0.81635542656295}
+12/24/2021 19:39:52 - INFO - codeparrot_training - Step 13972: {'lr': 0.0004112188939613507, 'samples': 7154176, 'steps': 13972, 'batch_loss/train': 0.833665503654629}
+12/24/2021 19:40:03 - INFO - codeparrot_training - Step 13973: {'lr': 0.00041120684607330295, 'samples': 7154688, 'steps': 13973, 'batch_loss/train': 0.851745905354619}
+12/24/2021 19:40:16 - INFO - codeparrot_training - Step 13974: {'lr': 0.00041119479754435763, 'samples': 7155200, 'steps': 13974, 'batch_loss/train': 0.8028105106204748}
+12/24/2021 19:40:27 - INFO - codeparrot_training - Step 13975: {'lr': 0.00041118274837456263, 'samples': 7155712, 'steps': 13975, 'batch_loss/train': 0.7516265958547592}
+12/24/2021 19:40:38 - INFO - codeparrot_training - Step 13976: {'lr': 0.00041117069856396593, 'samples': 7156224, 'steps': 13976, 'batch_loss/train': 0.788801888236776}
+12/24/2021 19:40:50 - INFO - codeparrot_training - Step 13977: {'lr': 0.0004111586481126154, 'samples': 7156736, 'steps': 13977, 'batch_loss/train': 0.7451761099509895}
+12/24/2021 19:41:01 - INFO - codeparrot_training - Step 13978: {'lr': 0.0004111465970205589, 'samples': 7157248, 'steps': 13978, 'batch_loss/train': 0.7992221610620618}
+12/24/2021 19:41:11 - INFO - codeparrot_training - Step 13979: {'lr': 0.0004111345452878444, 'samples': 7157760, 'steps': 13979, 'batch_loss/train': 0.7731765392236412}
+12/24/2021 19:41:23 - INFO - codeparrot_training - Step 13980: {'lr': 0.00041112249291451973, 'samples': 7158272, 'steps': 13980, 'batch_loss/train': 0.7843627939000726}
+12/24/2021 19:41:34 - INFO - codeparrot_training - Step 13981: {'lr': 0.0004111104399006329, 'samples': 7158784, 'steps': 13981, 'batch_loss/train': 0.7495027398690581}
+12/24/2021 19:41:44 - INFO - codeparrot_training - Step 13982: {'lr': 0.00041109838624623187, 'samples': 7159296, 'steps': 13982, 'batch_loss/train': 0.7196072184015065}
+12/24/2021 19:41:55 - INFO - codeparrot_training - Step 13983: {'lr': 0.0004110863319513644, 'samples': 7159808, 'steps': 13983, 'batch_loss/train': 0.8414551597088575}
+12/24/2021 19:42:07 - INFO - codeparrot_training - Step 13984: {'lr': 0.00041107427701607847, 'samples': 7160320, 'steps': 13984, 'batch_loss/train': 2.7947718827053905}
+12/24/2021 19:42:18 - INFO - codeparrot_training - Step 13985: {'lr': 0.00041106222144042217, 'samples': 7160832, 'steps': 13985, 'batch_loss/train': 0.8259323509410024}
+12/24/2021 19:42:29 - INFO - codeparrot_training - Step 13986: {'lr': 0.00041105016522444317, 'samples': 7161344, 'steps': 13986, 'batch_loss/train': 0.7863217790145427}
+12/24/2021 19:42:43 - INFO - codeparrot_training - Step 13987: {'lr': 0.00041103810836818955, 'samples': 7161856, 'steps': 13987, 'batch_loss/train': 0.7929088985547423}
+12/24/2021 19:42:53 - INFO - codeparrot_training - Step 13988: {'lr': 0.0004110260508717092, 'samples': 7162368, 'steps': 13988, 'batch_loss/train': 0.7943822648376226}
+12/24/2021 19:43:04 - INFO - codeparrot_training - Step 13989: {'lr': 0.00041101399273505015, 'samples': 7162880, 'steps': 13989, 'batch_loss/train': 0.7463091788813472}
+12/24/2021 19:43:16 - INFO - codeparrot_training - Step 13990: {'lr': 0.0004110019339582602, 'samples': 7163392, 'steps': 13990, 'batch_loss/train': 0.6905973094981164}
+12/24/2021 19:43:27 - INFO - codeparrot_training - Step 13991: {'lr': 0.0004109898745413874, 'samples': 7163904, 'steps': 13991, 'batch_loss/train': 0.7841538959182799}
+12/24/2021 19:43:37 - INFO - codeparrot_training - Step 13992: {'lr': 0.00041097781448447957, 'samples': 7164416, 'steps': 13992, 'batch_loss/train': 0.8576564802788198}
+12/24/2021 19:43:48 - INFO - codeparrot_training - Step 13993: {'lr': 0.0004109657537875847, 'samples': 7164928, 'steps': 13993, 'batch_loss/train': 0.6257255235686898}
+12/24/2021 19:44:02 - INFO - codeparrot_training - Step 13994: {'lr': 0.00041095369245075085, 'samples': 7165440, 'steps': 13994, 'batch_loss/train': 0.8077971367165446}
+12/24/2021 19:44:13 - INFO - codeparrot_training - Step 13995: {'lr': 0.00041094163047402586, 'samples': 7165952, 'steps': 13995, 'batch_loss/train': 0.7517152586951852}
+12/24/2021 19:44:23 - INFO - codeparrot_training - Step 13996: {'lr': 0.0004109295678574578, 'samples': 7166464, 'steps': 13996, 'batch_loss/train': 0.7959950855001807}
+12/24/2021 19:44:35 - INFO - codeparrot_training - Step 13997: {'lr': 0.0004109175046010944, 'samples': 7166976, 'steps': 13997, 'batch_loss/train': 0.8046049668919295}
+12/24/2021 19:44:46 - INFO - codeparrot_training - Step 13998: {'lr': 0.00041090544070498394, 'samples': 7167488, 'steps': 13998, 'batch_loss/train': 0.7995187342166901}
+12/24/2021 19:44:57 - INFO - codeparrot_training - Step 13999: {'lr': 0.0004108933761691741, 'samples': 7168000, 'steps': 13999, 'batch_loss/train': 0.7244901661761105}
+12/24/2021 19:45:09 - INFO - codeparrot_training - Step 14000: {'lr': 0.00041088131099371297, 'samples': 7168512, 'steps': 14000, 'batch_loss/train': 0.7847578818909824}
+12/24/2021 19:45:19 - INFO - codeparrot_training - Step 14001: {'lr': 0.0004108692451786485, 'samples': 7169024, 'steps': 14001, 'batch_loss/train': 0.760838049929589}
+12/24/2021 19:45:30 - INFO - codeparrot_training - Step 14002: {'lr': 0.0004108571787240286, 'samples': 7169536, 'steps': 14002, 'batch_loss/train': 0.6755525299813598}
+12/24/2021 19:45:40 - INFO - codeparrot_training - Step 14003: {'lr': 0.00041084511162990135, 'samples': 7170048, 'steps': 14003, 'batch_loss/train': 0.8030363521538675}
+12/24/2021 19:45:54 - INFO - codeparrot_training - Step 14004: {'lr': 0.0004108330438963146, 'samples': 7170560, 'steps': 14004, 'batch_loss/train': 0.8462497442960739}
+12/24/2021 19:46:05 - INFO - codeparrot_training - Step 14005: {'lr': 0.0004108209755233165, 'samples': 7171072, 'steps': 14005, 'batch_loss/train': 0.7949494593776762}
+12/24/2021 19:46:16 - INFO - codeparrot_training - Step 14006: {'lr': 0.0004108089065109548, 'samples': 7171584, 'steps': 14006, 'batch_loss/train': 0.8325726203620434}
+12/24/2021 19:46:28 - INFO - codeparrot_training - Step 14007: {'lr': 0.00041079683685927773, 'samples': 7172096, 'steps': 14007, 'batch_loss/train': 0.7496057087555528}
+12/24/2021 19:46:39 - INFO - codeparrot_training - Step 14008: {'lr': 0.0004107847665683331, 'samples': 7172608, 'steps': 14008, 'batch_loss/train': 0.8517486620694399}
+12/24/2021 19:46:49 - INFO - codeparrot_training - Step 14009: {'lr': 0.000410772695638169, 'samples': 7173120, 'steps': 14009, 'batch_loss/train': 0.8007533731870353}
+12/24/2021 19:47:03 - INFO - codeparrot_training - Step 14010: {'lr': 0.00041076062406883326, 'samples': 7173632, 'steps': 14010, 'batch_loss/train': 0.715678779524751}
+12/24/2021 19:47:14 - INFO - codeparrot_training - Step 14011: {'lr': 0.000410748551860374, 'samples': 7174144, 'steps': 14011, 'batch_loss/train': 1.0619625765830278}
+12/24/2021 19:47:25 - INFO - codeparrot_training - Step 14012: {'lr': 0.0004107364790128393, 'samples': 7174656, 'steps': 14012, 'batch_loss/train': 0.5922567581292242}
+12/24/2021 19:47:35 - INFO - codeparrot_training - Step 14013: {'lr': 0.00041072440552627695, 'samples': 7175168, 'steps': 14013, 'batch_loss/train': 0.8731426503509283}
+12/24/2021 19:47:47 - INFO - codeparrot_training - Step 14014: {'lr': 0.00041071233140073507, 'samples': 7175680, 'steps': 14014, 'batch_loss/train': 0.7490117596462369}
+12/24/2021 19:47:58 - INFO - codeparrot_training - Step 14015: {'lr': 0.00041070025663626157, 'samples': 7176192, 'steps': 14015, 'batch_loss/train': 0.8013992328196764}
+12/24/2021 19:48:08 - INFO - codeparrot_training - Step 14016: {'lr': 0.00041068818123290464, 'samples': 7176704, 'steps': 14016, 'batch_loss/train': 0.7276998027227819}
+12/24/2021 19:48:20 - INFO - codeparrot_training - Step 14017: {'lr': 0.0004106761051907122, 'samples': 7177216, 'steps': 14017, 'batch_loss/train': 0.821045970544219}
+12/24/2021 19:48:31 - INFO - codeparrot_training - Step 14018: {'lr': 0.00041066402850973216, 'samples': 7177728, 'steps': 14018, 'batch_loss/train': 0.776848113629967}
+12/24/2021 19:48:42 - INFO - codeparrot_training - Step 14019: {'lr': 0.00041065195119001266, 'samples': 7178240, 'steps': 14019, 'batch_loss/train': 0.8276777165010571}
+12/24/2021 19:48:54 - INFO - codeparrot_training - Step 14020: {'lr': 0.0004106398732316016, 'samples': 7178752, 'steps': 14020, 'batch_loss/train': 0.798963051638566}
+12/24/2021 19:49:04 - INFO - codeparrot_training - Step 14021: {'lr': 0.000410627794634547, 'samples': 7179264, 'steps': 14021, 'batch_loss/train': 0.6916033100569621}
+12/24/2021 19:49:15 - INFO - codeparrot_training - Step 14022: {'lr': 0.0004106157153988971, 'samples': 7179776, 'steps': 14022, 'batch_loss/train': 0.8705926267430186}
+12/24/2021 19:49:29 - INFO - codeparrot_training - Step 14023: {'lr': 0.0004106036355246997, 'samples': 7180288, 'steps': 14023, 'batch_loss/train': 0.7666177619248629}
+12/24/2021 19:49:40 - INFO - codeparrot_training - Step 14024: {'lr': 0.00041059155501200285, 'samples': 7180800, 'steps': 14024, 'batch_loss/train': 0.5735791793558747}
+12/24/2021 19:49:50 - INFO - codeparrot_training - Step 14025: {'lr': 0.0004105794738608546, 'samples': 7181312, 'steps': 14025, 'batch_loss/train': 0.7323762244195677}
+12/24/2021 19:50:01 - INFO - codeparrot_training - Step 14026: {'lr': 0.00041056739207130313, 'samples': 7181824, 'steps': 14026, 'batch_loss/train': 0.7950607314705849}
+12/24/2021 19:50:13 - INFO - codeparrot_training - Step 14027: {'lr': 0.00041055530964339616, 'samples': 7182336, 'steps': 14027, 'batch_loss/train': 0.7942894101142883}
+12/24/2021 19:50:23 - INFO - codeparrot_training - Step 14028: {'lr': 0.00041054322657718196, 'samples': 7182848, 'steps': 14028, 'batch_loss/train': 0.8391943201422691}
+12/24/2021 19:50:34 - INFO - codeparrot_training - Step 14029: {'lr': 0.00041053114287270857, 'samples': 7183360, 'steps': 14029, 'batch_loss/train': 0.8328424021601677}
+12/24/2021 19:50:46 - INFO - codeparrot_training - Step 14030: {'lr': 0.0004105190585300239, 'samples': 7183872, 'steps': 14030, 'batch_loss/train': 0.7934282119385898}
+12/24/2021 19:50:57 - INFO - codeparrot_training - Step 14031: {'lr': 0.0004105069735491761, 'samples': 7184384, 'steps': 14031, 'batch_loss/train': 0.7938456488773227}
+12/24/2021 19:51:07 - INFO - codeparrot_training - Step 14032: {'lr': 0.00041049488793021315, 'samples': 7184896, 'steps': 14032, 'batch_loss/train': 0.8413038873113692}
+12/24/2021 19:51:21 - INFO - codeparrot_training - Step 14033: {'lr': 0.0004104828016731832, 'samples': 7185408, 'steps': 14033, 'batch_loss/train': 0.715989341493696}
+12/24/2021 19:51:32 - INFO - codeparrot_training - Step 14034: {'lr': 0.00041047071477813416, 'samples': 7185920, 'steps': 14034, 'batch_loss/train': 0.6463325400254689}
+12/24/2021 19:51:42 - INFO - codeparrot_training - Step 14035: {'lr': 0.0004104586272451142, 'samples': 7186432, 'steps': 14035, 'batch_loss/train': 0.7646285081282258}
+12/24/2021 19:51:54 - INFO - codeparrot_training - Step 14036: {'lr': 0.0004104465390741713, 'samples': 7186944, 'steps': 14036, 'batch_loss/train': 0.8008784870617092}
+12/24/2021 19:52:05 - INFO - codeparrot_training - Step 14037: {'lr': 0.00041043445026535353, 'samples': 7187456, 'steps': 14037, 'batch_loss/train': 0.7819372015073895}
+12/24/2021 19:52:16 - INFO - codeparrot_training - Step 14038: {'lr': 0.0004104223608187089, 'samples': 7187968, 'steps': 14038, 'batch_loss/train': 0.9120669336989522}
+12/24/2021 19:52:26 - INFO - codeparrot_training - Step 14039: {'lr': 0.0004104102707342856, 'samples': 7188480, 'steps': 14039, 'batch_loss/train': 0.811393903568387}
+12/24/2021 19:52:40 - INFO - codeparrot_training - Step 14040: {'lr': 0.00041039818001213164, 'samples': 7188992, 'steps': 14040, 'batch_loss/train': 0.7627051658928394}
+12/24/2021 19:52:51 - INFO - codeparrot_training - Step 14041: {'lr': 0.0004103860886522951, 'samples': 7189504, 'steps': 14041, 'batch_loss/train': 0.706456414074637}
+12/24/2021 19:53:01 - INFO - codeparrot_training - Step 14042: {'lr': 0.000410373996654824, 'samples': 7190016, 'steps': 14042, 'batch_loss/train': 0.8067855667322874}
+12/24/2021 19:53:13 - INFO - codeparrot_training - Step 14043: {'lr': 0.00041036190401976647, 'samples': 7190528, 'steps': 14043, 'batch_loss/train': 0.7703754790127277}
+12/24/2021 19:53:24 - INFO - codeparrot_training - Step 14044: {'lr': 0.00041034981074717053, 'samples': 7191040, 'steps': 14044, 'batch_loss/train': 0.7125793821178377}
+12/24/2021 19:53:35 - INFO - codeparrot_training - Step 14045: {'lr': 0.00041033771683708425, 'samples': 7191552, 'steps': 14045, 'batch_loss/train': 0.8026843816041946}
+12/24/2021 19:53:47 - INFO - codeparrot_training - Step 14046: {'lr': 0.00041032562228955584, 'samples': 7192064, 'steps': 14046, 'batch_loss/train': 0.7613607458770275}
+12/24/2021 19:53:57 - INFO - codeparrot_training - Step 14047: {'lr': 0.0004103135271046332, 'samples': 7192576, 'steps': 14047, 'batch_loss/train': 0.7608857830055058}
+12/24/2021 19:54:08 - INFO - codeparrot_training - Step 14048: {'lr': 0.00041030143128236465, 'samples': 7193088, 'steps': 14048, 'batch_loss/train': 0.7914261408150196}
+12/24/2021 19:54:22 - INFO - codeparrot_training - Step 14049: {'lr': 0.00041028933482279795, 'samples': 7193600, 'steps': 14049, 'batch_loss/train': 0.8004131467314437}
+12/24/2021 19:54:32 - INFO - codeparrot_training - Step 14050: {'lr': 0.00041027723772598155, 'samples': 7194112, 'steps': 14050, 'batch_loss/train': 0.6950438290368766}
+12/24/2021 19:54:43 - INFO - codeparrot_training - Step 14051: {'lr': 0.00041026513999196327, 'samples': 7194624, 'steps': 14051, 'batch_loss/train': 0.7212957831216045}
+12/24/2021 19:54:54 - INFO - codeparrot_training - Step 14052: {'lr': 0.0004102530416207913, 'samples': 7195136, 'steps': 14052, 'batch_loss/train': 0.7901826556189917}
+12/24/2021 19:55:06 - INFO - codeparrot_training - Step 14053: {'lr': 0.0004102409426125138, 'samples': 7195648, 'steps': 14053, 'batch_loss/train': 0.8061887472867966}
+12/24/2021 19:55:17 - INFO - codeparrot_training - Step 14054: {'lr': 0.00041022884296717876, 'samples': 7196160, 'steps': 14054, 'batch_loss/train': 0.7862129518762231}
+12/24/2021 19:55:27 - INFO - codeparrot_training - Step 14055: {'lr': 0.00041021674268483445, 'samples': 7196672, 'steps': 14055, 'batch_loss/train': 0.6609127585252281}
+12/24/2021 19:55:39 - INFO - codeparrot_training - Step 14056: {'lr': 0.00041020464176552875, 'samples': 7197184, 'steps': 14056, 'batch_loss/train': 0.7881434278097004}
+12/24/2021 19:55:50 - INFO - codeparrot_training - Step 14057: {'lr': 0.00041019254020930993, 'samples': 7197696, 'steps': 14057, 'batch_loss/train': 0.8012278127716854}
+12/24/2021 19:56:00 - INFO - codeparrot_training - Step 14058: {'lr': 0.000410180438016226, 'samples': 7198208, 'steps': 14058, 'batch_loss/train': 0.7957572788000107}
+12/24/2021 19:56:14 - INFO - codeparrot_training - Step 14059: {'lr': 0.00041016833518632524, 'samples': 7198720, 'steps': 14059, 'batch_loss/train': 0.7421736361575313}
+12/24/2021 19:56:25 - INFO - codeparrot_training - Step 14060: {'lr': 0.00041015623171965557, 'samples': 7199232, 'steps': 14060, 'batch_loss/train': 0.820157153531909}
+12/24/2021 19:56:35 - INFO - codeparrot_training - Step 14061: {'lr': 0.00041014412761626525, 'samples': 7199744, 'steps': 14061, 'batch_loss/train': 0.909615270793438}
+12/24/2021 19:56:50 - INFO - codeparrot_training - Step 14062: {'lr': 0.00041013202287620235, 'samples': 7200256, 'steps': 14062, 'batch_loss/train': 0.7349101467989385}
+12/24/2021 19:57:00 - INFO - codeparrot_training - Step 14063: {'lr': 0.0004101199174995149, 'samples': 7200768, 'steps': 14063, 'batch_loss/train': 0.7495371940312907}
+12/24/2021 19:57:11 - INFO - codeparrot_training - Step 14064: {'lr': 0.0004101078114862512, 'samples': 7201280, 'steps': 14064, 'batch_loss/train': 0.6547567481175065}
+12/24/2021 19:57:22 - INFO - codeparrot_training - Step 14065: {'lr': 0.00041009570483645924, 'samples': 7201792, 'steps': 14065, 'batch_loss/train': 0.8014970822259784}
+12/24/2021 19:57:33 - INFO - codeparrot_training - Step 14066: {'lr': 0.0004100835975501873, 'samples': 7202304, 'steps': 14066, 'batch_loss/train': 0.7888337066397071}
+12/24/2021 19:57:44 - INFO - codeparrot_training - Step 14067: {'lr': 0.00041007148962748333, 'samples': 7202816, 'steps': 14067, 'batch_loss/train': 0.772339534945786}
+12/24/2021 19:57:55 - INFO - codeparrot_training - Step 14068: {'lr': 0.0004100593810683956, 'samples': 7203328, 'steps': 14068, 'batch_loss/train': 0.7338426066562533}
+12/24/2021 19:58:07 - INFO - codeparrot_training - Step 14069: {'lr': 0.0004100472718729722, 'samples': 7203840, 'steps': 14069, 'batch_loss/train': 0.7766570611856878}
+12/24/2021 19:58:18 - INFO - codeparrot_training - Step 14070: {'lr': 0.0004100351620412612, 'samples': 7204352, 'steps': 14070, 'batch_loss/train': 0.7847294025123119}
+12/24/2021 19:58:28 - INFO - codeparrot_training - Step 14071: {'lr': 0.0004100230515733109, 'samples': 7204864, 'steps': 14071, 'batch_loss/train': 0.8807678716257215}
+12/24/2021 19:58:42 - INFO - codeparrot_training - Step 14072: {'lr': 0.00041001094046916943, 'samples': 7205376, 'steps': 14072, 'batch_loss/train': 0.8835269594565034}
+12/24/2021 19:58:52 - INFO - codeparrot_training - Step 14073: {'lr': 0.00040999882872888485, 'samples': 7205888, 'steps': 14073, 'batch_loss/train': 0.7462989906780422}
+12/24/2021 19:59:03 - INFO - codeparrot_training - Step 14074: {'lr': 0.0004099867163525053, 'samples': 7206400, 'steps': 14074, 'batch_loss/train': 0.7411756068468094}
+12/24/2021 19:59:14 - INFO - codeparrot_training - Step 14075: {'lr': 0.000409974603340079, 'samples': 7206912, 'steps': 14075, 'batch_loss/train': 0.8305881302803755}
+12/24/2021 19:59:26 - INFO - codeparrot_training - Step 14076: {'lr': 0.0004099624896916541, 'samples': 7207424, 'steps': 14076, 'batch_loss/train': 0.8827858865261078}
+12/24/2021 19:59:37 - INFO - codeparrot_training - Step 14077: {'lr': 0.00040995037540727863, 'samples': 7207936, 'steps': 14077, 'batch_loss/train': 0.7368094949051738}
+12/24/2021 19:59:47 - INFO - codeparrot_training - Step 14078: {'lr': 0.0004099382604870009, 'samples': 7208448, 'steps': 14078, 'batch_loss/train': 0.7392447423189878}
+12/24/2021 19:59:59 - INFO - codeparrot_training - Step 14079: {'lr': 0.0004099261449308691, 'samples': 7208960, 'steps': 14079, 'batch_loss/train': 0.8063699887134135}
+12/24/2021 20:00:10 - INFO - codeparrot_training - Step 14080: {'lr': 0.00040991402873893126, 'samples': 7209472, 'steps': 14080, 'batch_loss/train': 0.9096806878224015}
+12/24/2021 20:00:20 - INFO - codeparrot_training - Step 14081: {'lr': 0.0004099019119112357, 'samples': 7209984, 'steps': 14081, 'batch_loss/train': 0.8129604021087289}
+12/24/2021 20:00:34 - INFO - codeparrot_training - Step 14082: {'lr': 0.00040988979444783047, 'samples': 7210496, 'steps': 14082, 'batch_loss/train': 0.7635708246380091}
+12/24/2021 20:00:45 - INFO - codeparrot_training - Step 14083: {'lr': 0.00040987767634876384, 'samples': 7211008, 'steps': 14083, 'batch_loss/train': 0.7330233221873641}
+12/24/2021 20:00:56 - INFO - codeparrot_training - Step 14084: {'lr': 0.00040986555761408385, 'samples': 7211520, 'steps': 14084, 'batch_loss/train': 0.7771141218254343}
+12/24/2021 20:01:06 - INFO - codeparrot_training - Step 14085: {'lr': 0.0004098534382438388, 'samples': 7212032, 'steps': 14085, 'batch_loss/train': 0.7814133095089346}
+12/24/2021 20:01:18 - INFO - codeparrot_training - Step 14086: {'lr': 0.00040984131823807693, 'samples': 7212544, 'steps': 14086, 'batch_loss/train': 0.8256251979619265}
+12/24/2021 20:01:29 - INFO - codeparrot_training - Step 14087: {'lr': 0.00040982919759684623, 'samples': 7213056, 'steps': 14087, 'batch_loss/train': 0.8067771075293422}
+12/24/2021 20:01:40 - INFO - codeparrot_training - Step 14088: {'lr': 0.000409817076320195, 'samples': 7213568, 'steps': 14088, 'batch_loss/train': 0.7376611909130588}
+12/24/2021 20:01:53 - INFO - codeparrot_training - Step 14089: {'lr': 0.0004098049544081714, 'samples': 7214080, 'steps': 14089, 'batch_loss/train': 0.7373716356232762}
+12/24/2021 20:02:04 - INFO - codeparrot_training - Step 14090: {'lr': 0.00040979283186082374, 'samples': 7214592, 'steps': 14090, 'batch_loss/train': 0.8836178127676249}
+12/24/2021 20:02:15 - INFO - codeparrot_training - Step 14091: {'lr': 0.0004097807086782, 'samples': 7215104, 'steps': 14091, 'batch_loss/train': 0.6901006888365373}
+12/24/2021 20:02:27 - INFO - codeparrot_training - Step 14092: {'lr': 0.0004097685848603485, 'samples': 7215616, 'steps': 14092, 'batch_loss/train': 0.7082422156818211}
+12/24/2021 20:02:37 - INFO - codeparrot_training - Step 14093: {'lr': 0.0004097564604073175, 'samples': 7216128, 'steps': 14093, 'batch_loss/train': 0.7008565003052354}
+12/24/2021 20:02:48 - INFO - codeparrot_training - Step 14094: {'lr': 0.0004097443353191551, 'samples': 7216640, 'steps': 14094, 'batch_loss/train': 0.8609400410205126}
+12/24/2021 20:03:00 - INFO - codeparrot_training - Step 14095: {'lr': 0.00040973220959590964, 'samples': 7217152, 'steps': 14095, 'batch_loss/train': 1.0982046108692884}
+12/24/2021 20:03:11 - INFO - codeparrot_training - Step 14096: {'lr': 0.0004097200832376291, 'samples': 7217664, 'steps': 14096, 'batch_loss/train': 0.7326824790798128}
+12/24/2021 20:03:22 - INFO - codeparrot_training - Step 14097: {'lr': 0.00040970795624436184, 'samples': 7218176, 'steps': 14097, 'batch_loss/train': 0.6975506080780178}
+12/24/2021 20:03:32 - INFO - codeparrot_training - Step 14098: {'lr': 0.00040969582861615606, 'samples': 7218688, 'steps': 14098, 'batch_loss/train': 0.5968134280119557}
+12/24/2021 20:03:45 - INFO - codeparrot_training - Step 14099: {'lr': 0.00040968370035306004, 'samples': 7219200, 'steps': 14099, 'batch_loss/train': 0.7338516684249043}
+12/24/2021 20:03:55 - INFO - codeparrot_training - Step 14100: {'lr': 0.0004096715714551218, 'samples': 7219712, 'steps': 14100, 'batch_loss/train': 0.8346553631126881}
+12/24/2021 20:04:06 - INFO - codeparrot_training - Step 14101: {'lr': 0.00040965944192238973, 'samples': 7220224, 'steps': 14101, 'batch_loss/train': 0.8026429433375597}
+12/24/2021 20:04:20 - INFO - codeparrot_training - Step 14102: {'lr': 0.000409647311754912, 'samples': 7220736, 'steps': 14102, 'batch_loss/train': 0.9185064183548093}
+12/24/2021 20:04:30 - INFO - codeparrot_training - Step 14103: {'lr': 0.00040963518095273683, 'samples': 7221248, 'steps': 14103, 'batch_loss/train': 0.7733487877994776}
+12/24/2021 20:04:41 - INFO - codeparrot_training - Step 14104: {'lr': 0.00040962304951591244, 'samples': 7221760, 'steps': 14104, 'batch_loss/train': 0.7222949415445328}
+12/24/2021 20:04:53 - INFO - codeparrot_training - Step 14105: {'lr': 0.0004096109174444872, 'samples': 7222272, 'steps': 14105, 'batch_loss/train': 0.7994396630674601}
+12/24/2021 20:05:04 - INFO - codeparrot_training - Step 14106: {'lr': 0.0004095987847385091, 'samples': 7222784, 'steps': 14106, 'batch_loss/train': 0.769797375658527}
+12/24/2021 20:05:14 - INFO - codeparrot_training - Step 14107: {'lr': 0.00040958665139802653, 'samples': 7223296, 'steps': 14107, 'batch_loss/train': 0.8747116532176733}
+12/24/2021 20:05:25 - INFO - codeparrot_training - Step 14108: {'lr': 0.0004095745174230876, 'samples': 7223808, 'steps': 14108, 'batch_loss/train': 0.697512713028118}
+12/24/2021 20:05:37 - INFO - codeparrot_training - Step 14109: {'lr': 0.0004095623828137408, 'samples': 7224320, 'steps': 14109, 'batch_loss/train': 0.8060676995664835}
+12/24/2021 20:05:48 - INFO - codeparrot_training - Step 14110: {'lr': 0.00040955024757003414, 'samples': 7224832, 'steps': 14110, 'batch_loss/train': 0.7904270123690367}
+12/24/2021 20:05:58 - INFO - codeparrot_training - Step 14111: {'lr': 0.0004095381116920159, 'samples': 7225344, 'steps': 14111, 'batch_loss/train': 0.7515649958513677}
+12/24/2021 20:06:12 - INFO - codeparrot_training - Step 14112: {'lr': 0.00040952597517973443, 'samples': 7225856, 'steps': 14112, 'batch_loss/train': 0.5038019128260203}
+12/24/2021 20:06:23 - INFO - codeparrot_training - Step 14113: {'lr': 0.00040951383803323793, 'samples': 7226368, 'steps': 14113, 'batch_loss/train': 0.849129959475249}
+12/24/2021 20:06:34 - INFO - codeparrot_training - Step 14114: {'lr': 0.0004095017002525746, 'samples': 7226880, 'steps': 14114, 'batch_loss/train': 0.8465683949179947}
+12/24/2021 20:06:46 - INFO - codeparrot_training - Step 14115: {'lr': 0.0004094895618377927, 'samples': 7227392, 'steps': 14115, 'batch_loss/train': 0.7482229573652148}
+12/24/2021 20:06:56 - INFO - codeparrot_training - Step 14116: {'lr': 0.0004094774227889405, 'samples': 7227904, 'steps': 14116, 'batch_loss/train': 0.7891454817727208}
+12/24/2021 20:07:07 - INFO - codeparrot_training - Step 14117: {'lr': 0.0004094652831060664, 'samples': 7228416, 'steps': 14117, 'batch_loss/train': 0.8256255020387471}
+12/24/2021 20:07:21 - INFO - codeparrot_training - Step 14118: {'lr': 0.00040945314278921854, 'samples': 7228928, 'steps': 14118, 'batch_loss/train': 0.8587329108268023}
+12/24/2021 20:07:31 - INFO - codeparrot_training - Step 14119: {'lr': 0.0004094410018384451, 'samples': 7229440, 'steps': 14119, 'batch_loss/train': 0.6968080988153815}
+12/24/2021 20:07:42 - INFO - codeparrot_training - Step 14120: {'lr': 0.0004094288602537945, 'samples': 7229952, 'steps': 14120, 'batch_loss/train': 0.7365560214966536}
+12/24/2021 20:07:53 - INFO - codeparrot_training - Step 14121: {'lr': 0.00040941671803531487, 'samples': 7230464, 'steps': 14121, 'batch_loss/train': 0.882798632606864}
+12/24/2021 20:08:05 - INFO - codeparrot_training - Step 14122: {'lr': 0.0004094045751830547, 'samples': 7230976, 'steps': 14122, 'batch_loss/train': 0.8106290800496936}
+12/24/2021 20:08:15 - INFO - codeparrot_training - Step 14123: {'lr': 0.00040939243169706195, 'samples': 7231488, 'steps': 14123, 'batch_loss/train': 0.7590055200271308}
+12/24/2021 20:08:26 - INFO - codeparrot_training - Step 14124: {'lr': 0.00040938028757738523, 'samples': 7232000, 'steps': 14124, 'batch_loss/train': 0.7384843118488789}
+12/24/2021 20:08:38 - INFO - codeparrot_training - Step 14125: {'lr': 0.0004093681428240726, 'samples': 7232512, 'steps': 14125, 'batch_loss/train': 0.8105757031589746}
+12/24/2021 20:08:49 - INFO - codeparrot_training - Step 14126: {'lr': 0.00040935599743717243, 'samples': 7233024, 'steps': 14126, 'batch_loss/train': 0.6496426229714416}
+12/24/2021 20:08:59 - INFO - codeparrot_training - Step 14127: {'lr': 0.000409343851416733, 'samples': 7233536, 'steps': 14127, 'batch_loss/train': 0.7339321379549801}
+12/24/2021 20:09:13 - INFO - codeparrot_training - Step 14128: {'lr': 0.00040933170476280256, 'samples': 7234048, 'steps': 14128, 'batch_loss/train': 0.7774470248259604}
+12/24/2021 20:09:24 - INFO - codeparrot_training - Step 14129: {'lr': 0.0004093195574754294, 'samples': 7234560, 'steps': 14129, 'batch_loss/train': 0.7736155712045729}
+12/24/2021 20:09:34 - INFO - codeparrot_training - Step 14130: {'lr': 0.00040930740955466186, 'samples': 7235072, 'steps': 14130, 'batch_loss/train': 0.8196102287620306}
+12/24/2021 20:09:47 - INFO - codeparrot_training - Step 14131: {'lr': 0.00040929526100054827, 'samples': 7235584, 'steps': 14131, 'batch_loss/train': 0.7714681960642338}
+12/24/2021 20:09:57 - INFO - codeparrot_training - Step 14132: {'lr': 0.00040928311181313674, 'samples': 7236096, 'steps': 14132, 'batch_loss/train': 0.7496281713247299}
+12/24/2021 20:10:08 - INFO - codeparrot_training - Step 14133: {'lr': 0.0004092709619924758, 'samples': 7236608, 'steps': 14133, 'batch_loss/train': 0.8534570019692183}
+12/24/2021 20:10:19 - INFO - codeparrot_training - Step 14134: {'lr': 0.0004092588115386136, 'samples': 7237120, 'steps': 14134, 'batch_loss/train': 0.7490087235346437}
+12/24/2021 20:10:31 - INFO - codeparrot_training - Step 14135: {'lr': 0.0004092466604515985, 'samples': 7237632, 'steps': 14135, 'batch_loss/train': 0.826731524663046}
+12/24/2021 20:10:41 - INFO - codeparrot_training - Step 14136: {'lr': 0.0004092345087314789, 'samples': 7238144, 'steps': 14136, 'batch_loss/train': 0.8175032990984619}
+12/24/2021 20:10:52 - INFO - codeparrot_training - Step 14137: {'lr': 0.00040922235637830295, 'samples': 7238656, 'steps': 14137, 'batch_loss/train': 0.8048050818033516}
+12/24/2021 20:11:04 - INFO - codeparrot_training - Step 14138: {'lr': 0.00040921020339211903, 'samples': 7239168, 'steps': 14138, 'batch_loss/train': 0.6270486218854785}
+12/24/2021 20:11:15 - INFO - codeparrot_training - Step 14139: {'lr': 0.00040919804977297534, 'samples': 7239680, 'steps': 14139, 'batch_loss/train': 0.7753886543214321}
+12/24/2021 20:11:25 - INFO - codeparrot_training - Step 14140: {'lr': 0.00040918589552092055, 'samples': 7240192, 'steps': 14140, 'batch_loss/train': 0.8668060833588243}
+12/24/2021 20:11:39 - INFO - codeparrot_training - Step 14141: {'lr': 0.00040917374063600254, 'samples': 7240704, 'steps': 14141, 'batch_loss/train': 0.8039778508245945}
+12/24/2021 20:11:50 - INFO - codeparrot_training - Step 14142: {'lr': 0.00040916158511827, 'samples': 7241216, 'steps': 14142, 'batch_loss/train': 0.8245840454474092}
+12/24/2021 20:12:00 - INFO - codeparrot_training - Step 14143: {'lr': 0.00040914942896777095, 'samples': 7241728, 'steps': 14143, 'batch_loss/train': 0.7397364298813045}
+12/24/2021 20:12:11 - INFO - codeparrot_training - Step 14144: {'lr': 0.000409137272184554, 'samples': 7242240, 'steps': 14144, 'batch_loss/train': 0.7973557831719518}
+12/24/2021 20:12:23 - INFO - codeparrot_training - Step 14145: {'lr': 0.00040912511476866726, 'samples': 7242752, 'steps': 14145, 'batch_loss/train': 0.8044205158948898}
+12/24/2021 20:12:34 - INFO - codeparrot_training - Step 14146: {'lr': 0.0004091129567201592, 'samples': 7243264, 'steps': 14146, 'batch_loss/train': 0.8200795063748956}
+12/24/2021 20:12:44 - INFO - codeparrot_training - Step 14147: {'lr': 0.0004091007980390781, 'samples': 7243776, 'steps': 14147, 'batch_loss/train': 0.7113238926976919}
+12/24/2021 20:12:58 - INFO - codeparrot_training - Step 14148: {'lr': 0.0004090886387254722, 'samples': 7244288, 'steps': 14148, 'batch_loss/train': 0.857639379799366}
+12/24/2021 20:13:09 - INFO - codeparrot_training - Step 14149: {'lr': 0.00040907647877939, 'samples': 7244800, 'steps': 14149, 'batch_loss/train': 0.7679396970197558}
+12/24/2021 20:13:19 - INFO - codeparrot_training - Step 14150: {'lr': 0.00040906431820087987, 'samples': 7245312, 'steps': 14150, 'batch_loss/train': 0.7621099806856364}
+12/24/2021 20:13:31 - INFO - codeparrot_training - Step 14151: {'lr': 0.00040905215698999, 'samples': 7245824, 'steps': 14151, 'batch_loss/train': 0.9140664953738451}
+12/24/2021 20:13:42 - INFO - codeparrot_training - Step 14152: {'lr': 0.0004090399951467687, 'samples': 7246336, 'steps': 14152, 'batch_loss/train': 0.7170029813423753}
+12/24/2021 20:13:53 - INFO - codeparrot_training - Step 14153: {'lr': 0.0004090278326712646, 'samples': 7246848, 'steps': 14153, 'batch_loss/train': 0.786207596771419}
+12/24/2021 20:14:04 - INFO - codeparrot_training - Step 14154: {'lr': 0.00040901566956352576, 'samples': 7247360, 'steps': 14154, 'batch_loss/train': 0.798956316895783}
+12/24/2021 20:14:15 - INFO - codeparrot_training - Step 14155: {'lr': 0.0004090035058236008, 'samples': 7247872, 'steps': 14155, 'batch_loss/train': 0.7238874617032707}
+12/24/2021 20:14:26 - INFO - codeparrot_training - Step 14156: {'lr': 0.0004089913414515378, 'samples': 7248384, 'steps': 14156, 'batch_loss/train': 0.8156622909009457}
+12/24/2021 20:14:36 - INFO - codeparrot_training - Step 14157: {'lr': 0.00040897917644738536, 'samples': 7248896, 'steps': 14157, 'batch_loss/train': 0.7405556766316295}
+12/24/2021 20:14:50 - INFO - codeparrot_training - Step 14158: {'lr': 0.0004089670108111917, 'samples': 7249408, 'steps': 14158, 'batch_loss/train': 0.753852279856801}
+12/24/2021 20:15:01 - INFO - codeparrot_training - Step 14159: {'lr': 0.00040895484454300525, 'samples': 7249920, 'steps': 14159, 'batch_loss/train': 0.841150576248765}
+12/24/2021 20:15:12 - INFO - codeparrot_training - Step 14160: {'lr': 0.0004089426776428743, 'samples': 7250432, 'steps': 14160, 'batch_loss/train': 0.8365287035703659}
+12/24/2021 20:15:24 - INFO - codeparrot_training - Step 14161: {'lr': 0.0004089305101108474, 'samples': 7250944, 'steps': 14161, 'batch_loss/train': 0.7837501866742969}
+12/24/2021 20:15:34 - INFO - codeparrot_training - Step 14162: {'lr': 0.0004089183419469726, 'samples': 7251456, 'steps': 14162, 'batch_loss/train': 0.7640772147569805}
+12/24/2021 20:15:45 - INFO - codeparrot_training - Step 14163: {'lr': 0.00040890617315129864, 'samples': 7251968, 'steps': 14163, 'batch_loss/train': 0.7964846240356565}
+12/24/2021 20:15:57 - INFO - codeparrot_training - Step 14164: {'lr': 0.00040889400372387367, 'samples': 7252480, 'steps': 14164, 'batch_loss/train': 0.775511578656733}
+12/24/2021 20:16:08 - INFO - codeparrot_training - Step 14165: {'lr': 0.00040888183366474617, 'samples': 7252992, 'steps': 14165, 'batch_loss/train': 0.7397130709141493}
+12/24/2021 20:16:18 - INFO - codeparrot_training - Step 14166: {'lr': 0.00040886966297396443, 'samples': 7253504, 'steps': 14166, 'batch_loss/train': 0.7880379185080528}
+12/24/2021 20:16:29 - INFO - codeparrot_training - Step 14167: {'lr': 0.000408857491651577, 'samples': 7254016, 'steps': 14167, 'batch_loss/train': 0.8227582294493914}
+12/24/2021 20:16:42 - INFO - codeparrot_training - Step 14168: {'lr': 0.0004088453196976321, 'samples': 7254528, 'steps': 14168, 'batch_loss/train': 0.7094215587712824}
+12/24/2021 20:16:53 - INFO - codeparrot_training - Step 14169: {'lr': 0.00040883314711217823, 'samples': 7255040, 'steps': 14169, 'batch_loss/train': 0.8144409307278693}
+12/24/2021 20:17:04 - INFO - codeparrot_training - Step 14170: {'lr': 0.0004088209738952637, 'samples': 7255552, 'steps': 14170, 'batch_loss/train': 0.7449844377115369}
+12/24/2021 20:17:16 - INFO - codeparrot_training - Step 14171: {'lr': 0.0004088088000469369, 'samples': 7256064, 'steps': 14171, 'batch_loss/train': 0.8071022699587047}
+12/24/2021 20:17:26 - INFO - codeparrot_training - Step 14172: {'lr': 0.0004087966255672464, 'samples': 7256576, 'steps': 14172, 'batch_loss/train': 0.6717624788579997}
+12/24/2021 20:17:37 - INFO - codeparrot_training - Step 14173: {'lr': 0.0004087844504562404, 'samples': 7257088, 'steps': 14173, 'batch_loss/train': 0.8161356905475259}
+12/24/2021 20:17:49 - INFO - codeparrot_training - Step 14174: {'lr': 0.0004087722747139674, 'samples': 7257600, 'steps': 14174, 'batch_loss/train': 0.8115293411538005}
+12/24/2021 20:18:00 - INFO - codeparrot_training - Step 14175: {'lr': 0.0004087600983404757, 'samples': 7258112, 'steps': 14175, 'batch_loss/train': 0.7828636169433594}
+12/24/2021 20:18:10 - INFO - codeparrot_training - Step 14176: {'lr': 0.00040874792133581384, 'samples': 7258624, 'steps': 14176, 'batch_loss/train': 0.7721194886835292}
+12/24/2021 20:18:24 - INFO - codeparrot_training - Step 14177: {'lr': 0.00040873574370003024, 'samples': 7259136, 'steps': 14177, 'batch_loss/train': 0.7624199977144599}
+12/24/2021 20:18:35 - INFO - codeparrot_training - Step 14178: {'lr': 0.00040872356543317326, 'samples': 7259648, 'steps': 14178, 'batch_loss/train': 0.7657391289249063}
+12/24/2021 20:18:45 - INFO - codeparrot_training - Step 14179: {'lr': 0.00040871138653529127, 'samples': 7260160, 'steps': 14179, 'batch_loss/train': 0.8235079981386662}
+12/24/2021 20:18:56 - INFO - codeparrot_training - Step 14180: {'lr': 0.0004086992070064327, 'samples': 7260672, 'steps': 14180, 'batch_loss/train': 0.8613769179210067}
+12/24/2021 20:19:08 - INFO - codeparrot_training - Step 14181: {'lr': 0.0004086870268466461, 'samples': 7261184, 'steps': 14181, 'batch_loss/train': 0.7020208723843098}
+12/24/2021 20:19:19 - INFO - codeparrot_training - Step 14182: {'lr': 0.00040867484605597976, 'samples': 7261696, 'steps': 14182, 'batch_loss/train': 0.8931556548923254}
+12/24/2021 20:19:29 - INFO - codeparrot_training - Step 14183: {'lr': 0.0004086626646344822, 'samples': 7262208, 'steps': 14183, 'batch_loss/train': 0.6277901870198548}
+12/24/2021 20:19:42 - INFO - codeparrot_training - Step 14184: {'lr': 0.0004086504825822016, 'samples': 7262720, 'steps': 14184, 'batch_loss/train': 0.6421396975056268}
+12/24/2021 20:19:52 - INFO - codeparrot_training - Step 14185: {'lr': 0.00040863829989918677, 'samples': 7263232, 'steps': 14185, 'batch_loss/train': 0.8069097362458706}
+12/24/2021 20:20:03 - INFO - codeparrot_training - Step 14186: {'lr': 0.00040862611658548594, 'samples': 7263744, 'steps': 14186, 'batch_loss/train': 0.7651180964894593}
+12/24/2021 20:20:17 - INFO - codeparrot_training - Step 14187: {'lr': 0.0004086139326411475, 'samples': 7264256, 'steps': 14187, 'batch_loss/train': 0.7465059558162466}
+12/24/2021 20:20:27 - INFO - codeparrot_training - Step 14188: {'lr': 0.00040860174806621994, 'samples': 7264768, 'steps': 14188, 'batch_loss/train': 0.8732327520847321}
+12/24/2021 20:20:38 - INFO - codeparrot_training - Step 14189: {'lr': 0.00040858956286075177, 'samples': 7265280, 'steps': 14189, 'batch_loss/train': 0.8552466062828898}
+12/24/2021 20:20:50 - INFO - codeparrot_training - Step 14190: {'lr': 0.00040857737702479146, 'samples': 7265792, 'steps': 14190, 'batch_loss/train': 0.8440984962508082}
+12/24/2021 20:21:01 - INFO - codeparrot_training - Step 14191: {'lr': 0.00040856519055838727, 'samples': 7266304, 'steps': 14191, 'batch_loss/train': 0.7954618521034718}
+12/24/2021 20:21:11 - INFO - codeparrot_training - Step 14192: {'lr': 0.00040855300346158776, 'samples': 7266816, 'steps': 14192, 'batch_loss/train': 0.7428499041125178}
+12/24/2021 20:21:22 - INFO - codeparrot_training - Step 14193: {'lr': 0.00040854081573444135, 'samples': 7267328, 'steps': 14193, 'batch_loss/train': 0.8593726791441441}
+12/24/2021 20:21:34 - INFO - codeparrot_training - Step 14194: {'lr': 0.00040852862737699656, 'samples': 7267840, 'steps': 14194, 'batch_loss/train': 0.820599090307951}
+12/24/2021 20:21:44 - INFO - codeparrot_training - Step 14195: {'lr': 0.00040851643838930185, 'samples': 7268352, 'steps': 14195, 'batch_loss/train': 0.8116918564774096}
+12/24/2021 20:21:55 - INFO - codeparrot_training - Step 14196: {'lr': 0.00040850424877140557, 'samples': 7268864, 'steps': 14196, 'batch_loss/train': 0.9033478377386928}
+12/24/2021 20:22:09 - INFO - codeparrot_training - Step 14197: {'lr': 0.00040849205852335624, 'samples': 7269376, 'steps': 14197, 'batch_loss/train': 0.668145720846951}
+12/24/2021 20:22:19 - INFO - codeparrot_training - Step 14198: {'lr': 0.0004084798676452024, 'samples': 7269888, 'steps': 14198, 'batch_loss/train': 0.7250907635316253}
+12/24/2021 20:22:30 - INFO - codeparrot_training - Step 14199: {'lr': 0.00040846767613699235, 'samples': 7270400, 'steps': 14199, 'batch_loss/train': 0.7495850310660899}
+12/24/2021 20:22:42 - INFO - codeparrot_training - Step 14200: {'lr': 0.00040845548399877477, 'samples': 7270912, 'steps': 14200, 'batch_loss/train': 0.8211204813560471}
+12/24/2021 20:22:53 - INFO - codeparrot_training - Step 14201: {'lr': 0.0004084432912305979, 'samples': 7271424, 'steps': 14201, 'batch_loss/train': 0.83620441891253}
+12/24/2021 20:23:03 - INFO - codeparrot_training - Step 14202: {'lr': 0.0004084310978325104, 'samples': 7271936, 'steps': 14202, 'batch_loss/train': 0.9357540383934975}
+12/24/2021 20:23:14 - INFO - codeparrot_training - Step 14203: {'lr': 0.00040841890380456067, 'samples': 7272448, 'steps': 14203, 'batch_loss/train': 0.730705738067627}
+12/24/2021 20:23:28 - INFO - codeparrot_training - Step 14204: {'lr': 0.0004084067091467971, 'samples': 7272960, 'steps': 14204, 'batch_loss/train': 0.7364543434232473}
+12/24/2021 20:23:39 - INFO - codeparrot_training - Step 14205: {'lr': 0.0004083945138592684, 'samples': 7273472, 'steps': 14205, 'batch_loss/train': 0.7516931015998125}
+12/24/2021 20:23:49 - INFO - codeparrot_training - Step 14206: {'lr': 0.00040838231794202286, 'samples': 7273984, 'steps': 14206, 'batch_loss/train': 0.7806793553754687}
+12/24/2021 20:24:01 - INFO - codeparrot_training - Step 14207: {'lr': 0.00040837012139510905, 'samples': 7274496, 'steps': 14207, 'batch_loss/train': 0.8574721999466419}
+12/24/2021 20:24:12 - INFO - codeparrot_training - Step 14208: {'lr': 0.0004083579242185754, 'samples': 7275008, 'steps': 14208, 'batch_loss/train': 0.7220795904286206}
+12/24/2021 20:24:22 - INFO - codeparrot_training - Step 14209: {'lr': 0.0004083457264124705, 'samples': 7275520, 'steps': 14209, 'batch_loss/train': 0.8207021877169609}
+12/24/2021 20:24:34 - INFO - codeparrot_training - Step 14210: {'lr': 0.0004083335279768426, 'samples': 7276032, 'steps': 14210, 'batch_loss/train': 0.7830867017619312}
+12/24/2021 20:24:45 - INFO - codeparrot_training - Step 14211: {'lr': 0.0004083213289117406, 'samples': 7276544, 'steps': 14211, 'batch_loss/train': 0.6638002007966861}
+12/24/2021 20:24:56 - INFO - codeparrot_training - Step 14212: {'lr': 0.0004083091292172127, 'samples': 7277056, 'steps': 14212, 'batch_loss/train': 0.8658229857683182}
+12/24/2021 20:25:06 - INFO - codeparrot_training - Step 14213: {'lr': 0.00040829692889330743, 'samples': 7277568, 'steps': 14213, 'batch_loss/train': 0.8006741218268871}
+12/24/2021 20:25:18 - INFO - codeparrot_training - Step 14214: {'lr': 0.0004082847279400734, 'samples': 7278080, 'steps': 14214, 'batch_loss/train': 0.7397617711685598}
+12/24/2021 20:25:29 - INFO - codeparrot_training - Step 14215: {'lr': 0.000408272526357559, 'samples': 7278592, 'steps': 14215, 'batch_loss/train': 0.6702103691641241}
+12/24/2021 20:25:40 - INFO - codeparrot_training - Step 14216: {'lr': 0.00040826032414581286, 'samples': 7279104, 'steps': 14216, 'batch_loss/train': 0.7101637991145253}
+12/24/2021 20:25:54 - INFO - codeparrot_training - Step 14217: {'lr': 0.0004082481213048834, 'samples': 7279616, 'steps': 14217, 'batch_loss/train': 0.8430973803624511}
+12/24/2021 20:26:04 - INFO - codeparrot_training - Step 14218: {'lr': 0.00040823591783481917, 'samples': 7280128, 'steps': 14218, 'batch_loss/train': 0.8430909896269441}
+12/24/2021 20:26:15 - INFO - codeparrot_training - Step 14219: {'lr': 0.0004082237137356687, 'samples': 7280640, 'steps': 14219, 'batch_loss/train': 0.8324483365286142}
+12/24/2021 20:26:27 - INFO - codeparrot_training - Step 14220: {'lr': 0.00040821150900748044, 'samples': 7281152, 'steps': 14220, 'batch_loss/train': 1.1485723936930299}
+12/24/2021 20:26:38 - INFO - codeparrot_training - Step 14221: {'lr': 0.000408199303650303, 'samples': 7281664, 'steps': 14221, 'batch_loss/train': 0.8540010182186961}
+12/24/2021 20:26:48 - INFO - codeparrot_training - Step 14222: {'lr': 0.0004081870976641848, 'samples': 7282176, 'steps': 14222, 'batch_loss/train': 0.7661696722498164}
+12/24/2021 20:26:59 - INFO - codeparrot_training - Step 14223: {'lr': 0.00040817489104917447, 'samples': 7282688, 'steps': 14223, 'batch_loss/train': 0.806489902548492}
+12/24/2021 20:27:11 - INFO - codeparrot_training - Step 14224: {'lr': 0.0004081626838053205, 'samples': 7283200, 'steps': 14224, 'batch_loss/train': 0.8409593179821968}
+12/24/2021 20:27:22 - INFO - codeparrot_training - Step 14225: {'lr': 0.0004081504759326714, 'samples': 7283712, 'steps': 14225, 'batch_loss/train': 0.9127850234508514}
+12/24/2021 20:27:32 - INFO - codeparrot_training - Step 14226: {'lr': 0.00040813826743127575, 'samples': 7284224, 'steps': 14226, 'batch_loss/train': 0.8927137460559607}
+12/24/2021 20:27:46 - INFO - codeparrot_training - Step 14227: {'lr': 0.0004081260583011821, 'samples': 7284736, 'steps': 14227, 'batch_loss/train': 0.7269861723762006}
+12/24/2021 20:27:57 - INFO - codeparrot_training - Step 14228: {'lr': 0.00040811384854243883, 'samples': 7285248, 'steps': 14228, 'batch_loss/train': 0.8607850887347013}
+12/24/2021 20:28:07 - INFO - codeparrot_training - Step 14229: {'lr': 0.0004081016381550947, 'samples': 7285760, 'steps': 14229, 'batch_loss/train': 0.7037463122978806}
+12/24/2021 20:28:19 - INFO - codeparrot_training - Step 14230: {'lr': 0.00040808942713919813, 'samples': 7286272, 'steps': 14230, 'batch_loss/train': 0.7550274822860956}
+12/24/2021 20:28:30 - INFO - codeparrot_training - Step 14231: {'lr': 0.00040807721549479764, 'samples': 7286784, 'steps': 14231, 'batch_loss/train': 0.757731375284493}
+12/24/2021 20:28:41 - INFO - codeparrot_training - Step 14232: {'lr': 0.00040806500322194186, 'samples': 7287296, 'steps': 14232, 'batch_loss/train': 0.8208673158660531}
+12/24/2021 20:28:54 - INFO - codeparrot_training - Step 14233: {'lr': 0.00040805279032067935, 'samples': 7287808, 'steps': 14233, 'batch_loss/train': 0.8181716143153608}
+12/24/2021 20:29:05 - INFO - codeparrot_training - Step 14234: {'lr': 0.0004080405767910585, 'samples': 7288320, 'steps': 14234, 'batch_loss/train': 0.8410442429594696}
+12/24/2021 20:29:16 - INFO - codeparrot_training - Step 14235: {'lr': 0.0004080283626331282, 'samples': 7288832, 'steps': 14235, 'batch_loss/train': 0.9518751678988338}
+12/24/2021 20:29:26 - INFO - codeparrot_training - Step 14236: {'lr': 0.00040801614784693666, 'samples': 7289344, 'steps': 14236, 'batch_loss/train': 0.8394506215117872}
+12/24/2021 20:29:38 - INFO - codeparrot_training - Step 14237: {'lr': 0.0004080039324325326, 'samples': 7289856, 'steps': 14237, 'batch_loss/train': 0.7108169868588448}
+12/24/2021 20:29:49 - INFO - codeparrot_training - Step 14238: {'lr': 0.00040799171638996457, 'samples': 7290368, 'steps': 14238, 'batch_loss/train': 0.7122271408443339}
+12/24/2021 20:30:00 - INFO - codeparrot_training - Step 14239: {'lr': 0.00040797949971928103, 'samples': 7290880, 'steps': 14239, 'batch_loss/train': 0.7405793752986938}
+12/24/2021 20:30:12 - INFO - codeparrot_training - Step 14240: {'lr': 0.00040796728242053083, 'samples': 7291392, 'steps': 14240, 'batch_loss/train': 0.9127914309501648}
+12/24/2021 20:30:23 - INFO - codeparrot_training - Step 14241: {'lr': 0.0004079550644937623, 'samples': 7291904, 'steps': 14241, 'batch_loss/train': 1.0051098086405545}
+12/24/2021 20:30:34 - INFO - codeparrot_training - Step 14242: {'lr': 0.000407942845939024, 'samples': 7292416, 'steps': 14242, 'batch_loss/train': 0.6784502449445426}
+12/24/2021 20:30:44 - INFO - codeparrot_training - Step 14243: {'lr': 0.00040793062675636467, 'samples': 7292928, 'steps': 14243, 'batch_loss/train': 0.80370142031461}
+12/24/2021 20:30:58 - INFO - codeparrot_training - Step 14244: {'lr': 0.0004079184069458328, 'samples': 7293440, 'steps': 14244, 'batch_loss/train': 0.7817684458568692}
+12/24/2021 20:31:09 - INFO - codeparrot_training - Step 14245: {'lr': 0.0004079061865074769, 'samples': 7293952, 'steps': 14245, 'batch_loss/train': 0.6905032468494028}
+12/24/2021 20:31:19 - INFO - codeparrot_training - Step 14246: {'lr': 0.00040789396544134573, 'samples': 7294464, 'steps': 14246, 'batch_loss/train': 0.8237797152251005}
+12/24/2021 20:31:31 - INFO - codeparrot_training - Step 14247: {'lr': 0.00040788174374748766, 'samples': 7294976, 'steps': 14247, 'batch_loss/train': 0.7603100598789752}
+12/24/2021 20:31:42 - INFO - codeparrot_training - Step 14248: {'lr': 0.00040786952142595146, 'samples': 7295488, 'steps': 14248, 'batch_loss/train': 0.8774069817736745}
+12/24/2021 20:31:52 - INFO - codeparrot_training - Step 14249: {'lr': 0.0004078572984767855, 'samples': 7296000, 'steps': 14249, 'batch_loss/train': 0.8117302786558867}
+12/24/2021 20:32:05 - INFO - codeparrot_training - Step 14250: {'lr': 0.00040784507490003875, 'samples': 7296512, 'steps': 14250, 'batch_loss/train': 0.886431235470809}
+12/24/2021 20:32:15 - INFO - codeparrot_training - Step 14251: {'lr': 0.0004078328506957595, 'samples': 7297024, 'steps': 14251, 'batch_loss/train': 0.8625734075903893}
+12/24/2021 20:32:26 - INFO - codeparrot_training - Step 14252: {'lr': 0.00040782062586399635, 'samples': 7297536, 'steps': 14252, 'batch_loss/train': 0.7727146437391639}
+12/24/2021 20:32:36 - INFO - codeparrot_training - Step 14253: {'lr': 0.0004078084004047981, 'samples': 7298048, 'steps': 14253, 'batch_loss/train': 0.8114218674600124}
+12/24/2021 20:32:48 - INFO - codeparrot_training - Step 14254: {'lr': 0.00040779617431821317, 'samples': 7298560, 'steps': 14254, 'batch_loss/train': 0.7393130538985133}
+12/24/2021 20:32:59 - INFO - codeparrot_training - Step 14255: {'lr': 0.0004077839476042903, 'samples': 7299072, 'steps': 14255, 'batch_loss/train': 0.8065955750644207}
+12/24/2021 20:33:09 - INFO - codeparrot_training - Step 14256: {'lr': 0.00040777172026307794, 'samples': 7299584, 'steps': 14256, 'batch_loss/train': 0.6928978185169399}
+12/24/2021 20:33:24 - INFO - codeparrot_training - Step 14257: {'lr': 0.0004077594922946248, 'samples': 7300096, 'steps': 14257, 'batch_loss/train': 0.7926750890910625}
+12/24/2021 20:33:34 - INFO - codeparrot_training - Step 14258: {'lr': 0.0004077472636989795, 'samples': 7300608, 'steps': 14258, 'batch_loss/train': 0.7970528153236955}
+12/24/2021 20:33:45 - INFO - codeparrot_training - Step 14259: {'lr': 0.0004077350344761908, 'samples': 7301120, 'steps': 14259, 'batch_loss/train': 0.6630721702240407}
+12/24/2021 20:33:57 - INFO - codeparrot_training - Step 14260: {'lr': 0.00040772280462630695, 'samples': 7301632, 'steps': 14260, 'batch_loss/train': 0.6785494980867952}
+12/24/2021 20:34:07 - INFO - codeparrot_training - Step 14261: {'lr': 0.00040771057414937684, 'samples': 7302144, 'steps': 14261, 'batch_loss/train': 0.8476568101905286}
+12/24/2021 20:34:18 - INFO - codeparrot_training - Step 14262: {'lr': 0.00040769834304544905, 'samples': 7302656, 'steps': 14262, 'batch_loss/train': 0.7798189846798778}
+12/24/2021 20:34:29 - INFO - codeparrot_training - Step 14263: {'lr': 0.0004076861113145722, 'samples': 7303168, 'steps': 14263, 'batch_loss/train': 0.7683620238676667}
+12/24/2021 20:34:43 - INFO - codeparrot_training - Step 14264: {'lr': 0.0004076738789567949, 'samples': 7303680, 'steps': 14264, 'batch_loss/train': 0.7504128526197746}
+12/24/2021 20:34:53 - INFO - codeparrot_training - Step 14265: {'lr': 0.00040766164597216576, 'samples': 7304192, 'steps': 14265, 'batch_loss/train': 0.8290198147296906}
+12/24/2021 20:35:04 - INFO - codeparrot_training - Step 14266: {'lr': 0.0004076494123607335, 'samples': 7304704, 'steps': 14266, 'batch_loss/train': 0.8140048859640956}
+12/24/2021 20:35:16 - INFO - codeparrot_training - Step 14267: {'lr': 0.0004076371781225467, 'samples': 7305216, 'steps': 14267, 'batch_loss/train': 0.721267007291317}
+12/24/2021 20:35:27 - INFO - codeparrot_training - Step 14268: {'lr': 0.000407624943257654, 'samples': 7305728, 'steps': 14268, 'batch_loss/train': 0.80481799505651}
+12/24/2021 20:35:37 - INFO - codeparrot_training - Step 14269: {'lr': 0.00040761270776610404, 'samples': 7306240, 'steps': 14269, 'batch_loss/train': 0.8436556118540466}
+12/24/2021 20:35:49 - INFO - codeparrot_training - Step 14270: {'lr': 0.00040760047164794546, 'samples': 7306752, 'steps': 14270, 'batch_loss/train': 0.737927345559001}
+12/24/2021 20:36:00 - INFO - codeparrot_training - Step 14271: {'lr': 0.0004075882349032269, 'samples': 7307264, 'steps': 14271, 'batch_loss/train': 0.774925182107836}
+12/24/2021 20:36:10 - INFO - codeparrot_training - Step 14272: {'lr': 0.00040757599753199703, 'samples': 7307776, 'steps': 14272, 'batch_loss/train': 0.7151597184129059}
+12/24/2021 20:36:21 - INFO - codeparrot_training - Step 14273: {'lr': 0.0004075637595343045, 'samples': 7308288, 'steps': 14273, 'batch_loss/train': 0.8395281368866563}
+12/24/2021 20:36:35 - INFO - codeparrot_training - Step 14274: {'lr': 0.00040755152091019787, 'samples': 7308800, 'steps': 14274, 'batch_loss/train': 0.745793903246522}
+12/24/2021 20:36:46 - INFO - codeparrot_training - Step 14275: {'lr': 0.000407539281659726, 'samples': 7309312, 'steps': 14275, 'batch_loss/train': 0.722167759668082}
+12/24/2021 20:36:56 - INFO - codeparrot_training - Step 14276: {'lr': 0.00040752704178293744, 'samples': 7309824, 'steps': 14276, 'batch_loss/train': 0.7461062986403704}
+12/24/2021 20:37:08 - INFO - codeparrot_training - Step 14277: {'lr': 0.0004075148012798807, 'samples': 7310336, 'steps': 14277, 'batch_loss/train': 0.7330661043524742}
+12/24/2021 20:37:19 - INFO - codeparrot_training - Step 14278: {'lr': 0.00040750256015060474, 'samples': 7310848, 'steps': 14278, 'batch_loss/train': 0.7695222431793809}
+12/24/2021 20:37:30 - INFO - codeparrot_training - Step 14279: {'lr': 0.000407490318395158, 'samples': 7311360, 'steps': 14279, 'batch_loss/train': 0.6530494157341309}
+12/24/2021 20:37:42 - INFO - codeparrot_training - Step 14280: {'lr': 0.0004074780760135892, 'samples': 7311872, 'steps': 14280, 'batch_loss/train': 0.7521150358952582}
+12/24/2021 20:37:52 - INFO - codeparrot_training - Step 14281: {'lr': 0.0004074658330059471, 'samples': 7312384, 'steps': 14281, 'batch_loss/train': 0.8218121195677668}
+12/24/2021 20:38:03 - INFO - codeparrot_training - Step 14282: {'lr': 0.00040745358937228026, 'samples': 7312896, 'steps': 14282, 'batch_loss/train': 0.6141473844763823}
+12/24/2021 20:38:17 - INFO - codeparrot_training - Step 14283: {'lr': 0.0004074413451126374, 'samples': 7313408, 'steps': 14283, 'batch_loss/train': 0.7565831667743623}
+12/24/2021 20:38:27 - INFO - codeparrot_training - Step 14284: {'lr': 0.00040742910022706716, 'samples': 7313920, 'steps': 14284, 'batch_loss/train': 0.7297872398048639}
+12/24/2021 20:38:38 - INFO - codeparrot_training - Step 14285: {'lr': 0.0004074168547156184, 'samples': 7314432, 'steps': 14285, 'batch_loss/train': 0.6750283711589873}
+12/24/2021 20:38:49 - INFO - codeparrot_training - Step 14286: {'lr': 0.0004074046085783395, 'samples': 7314944, 'steps': 14286, 'batch_loss/train': 0.7528380386065692}
+12/24/2021 20:39:01 - INFO - codeparrot_training - Step 14287: {'lr': 0.00040739236181527936, 'samples': 7315456, 'steps': 14287, 'batch_loss/train': 0.6303626339649782}
+12/24/2021 20:39:12 - INFO - codeparrot_training - Step 14288: {'lr': 0.0004073801144264867, 'samples': 7315968, 'steps': 14288, 'batch_loss/train': 0.7771528512239456}
+12/24/2021 20:39:22 - INFO - codeparrot_training - Step 14289: {'lr': 0.00040736786641201, 'samples': 7316480, 'steps': 14289, 'batch_loss/train': 0.7955869548022747}
+12/24/2021 20:39:34 - INFO - codeparrot_training - Step 14290: {'lr': 0.00040735561777189823, 'samples': 7316992, 'steps': 14290, 'batch_loss/train': 0.6547762549598701}
+12/24/2021 20:39:45 - INFO - codeparrot_training - Step 14291: {'lr': 0.0004073433685061998, 'samples': 7317504, 'steps': 14291, 'batch_loss/train': 0.9104081047698855}
+12/24/2021 20:39:56 - INFO - codeparrot_training - Step 14292: {'lr': 0.00040733111861496364, 'samples': 7318016, 'steps': 14292, 'batch_loss/train': 0.8211538596078753}
+12/24/2021 20:40:09 - INFO - codeparrot_training - Step 14293: {'lr': 0.00040731886809823825, 'samples': 7318528, 'steps': 14293, 'batch_loss/train': 0.7718511000275612}
+12/24/2021 20:40:20 - INFO - codeparrot_training - Step 14294: {'lr': 0.00040730661695607257, 'samples': 7319040, 'steps': 14294, 'batch_loss/train': 0.7908499927725643}
+12/24/2021 20:40:31 - INFO - codeparrot_training - Step 14295: {'lr': 0.00040729436518851516, 'samples': 7319552, 'steps': 14295, 'batch_loss/train': 0.8040943476371467}
+12/24/2021 20:40:41 - INFO - codeparrot_training - Step 14296: {'lr': 0.00040728211279561467, 'samples': 7320064, 'steps': 14296, 'batch_loss/train': 0.8509047888219357}
+12/24/2021 20:40:53 - INFO - codeparrot_training - Step 14297: {'lr': 0.0004072698597774199, 'samples': 7320576, 'steps': 14297, 'batch_loss/train': 0.6713111757999286}
+12/24/2021 20:41:04 - INFO - codeparrot_training - Step 14298: {'lr': 0.00040725760613397966, 'samples': 7321088, 'steps': 14298, 'batch_loss/train': 0.6694465749897063}
+12/24/2021 20:41:14 - INFO - codeparrot_training - Step 14299: {'lr': 0.0004072453518653424, 'samples': 7321600, 'steps': 14299, 'batch_loss/train': 0.7325177020393312}
+12/24/2021 20:41:27 - INFO - codeparrot_training - Step 14300: {'lr': 0.0004072330969715571, 'samples': 7322112, 'steps': 14300, 'batch_loss/train': 0.7073480949620716}
+12/24/2021 20:41:37 - INFO - codeparrot_training - Step 14301: {'lr': 0.00040722084145267237, 'samples': 7322624, 'steps': 14301, 'batch_loss/train': 0.829408855875954}
+12/24/2021 20:41:48 - INFO - codeparrot_training - Step 14302: {'lr': 0.00040720858530873686, 'samples': 7323136, 'steps': 14302, 'batch_loss/train': 0.8231947598978877}
+12/24/2021 20:42:02 - INFO - codeparrot_training - Step 14303: {'lr': 0.0004071963285397995, 'samples': 7323648, 'steps': 14303, 'batch_loss/train': 0.8291209014132619}
+12/24/2021 20:42:12 - INFO - codeparrot_training - Step 14304: {'lr': 0.0004071840711459087, 'samples': 7324160, 'steps': 14304, 'batch_loss/train': 0.773192759603262}
+12/24/2021 20:42:23 - INFO - codeparrot_training - Step 14305: {'lr': 0.0004071718131271136, 'samples': 7324672, 'steps': 14305, 'batch_loss/train': 0.8420504359528422}
+12/24/2021 20:42:35 - INFO - codeparrot_training - Step 14306: {'lr': 0.0004071595544834626, 'samples': 7325184, 'steps': 14306, 'batch_loss/train': 0.750297780148685}
+12/24/2021 20:42:46 - INFO - codeparrot_training - Step 14307: {'lr': 0.0004071472952150046, 'samples': 7325696, 'steps': 14307, 'batch_loss/train': 0.7428242852911353}
+12/24/2021 20:42:56 - INFO - codeparrot_training - Step 14308: {'lr': 0.0004071350353217882, 'samples': 7326208, 'steps': 14308, 'batch_loss/train': 0.5401429663761519}
+12/24/2021 20:43:07 - INFO - codeparrot_training - Step 14309: {'lr': 0.00040712277480386234, 'samples': 7326720, 'steps': 14309, 'batch_loss/train': 0.8020009929314256}
+12/24/2021 20:43:19 - INFO - codeparrot_training - Step 14310: {'lr': 0.0004071105136612756, 'samples': 7327232, 'steps': 14310, 'batch_loss/train': 0.7200181894004345}
+12/24/2021 20:43:29 - INFO - codeparrot_training - Step 14311: {'lr': 0.0004070982518940768, 'samples': 7327744, 'steps': 14311, 'batch_loss/train': 0.7831822540611029}
+12/24/2021 20:43:40 - INFO - codeparrot_training - Step 14312: {'lr': 0.0004070859895023146, 'samples': 7328256, 'steps': 14312, 'batch_loss/train': 0.7719675274565816}
+12/24/2021 20:43:54 - INFO - codeparrot_training - Step 14313: {'lr': 0.0004070737264860379, 'samples': 7328768, 'steps': 14313, 'batch_loss/train': 1.4753432204015553}
+12/24/2021 20:44:05 - INFO - codeparrot_training - Step 14314: {'lr': 0.0004070614628452953, 'samples': 7329280, 'steps': 14314, 'batch_loss/train': 0.8944761361926794}
+12/24/2021 20:44:15 - INFO - codeparrot_training - Step 14315: {'lr': 0.0004070491985801357, 'samples': 7329792, 'steps': 14315, 'batch_loss/train': 0.7941536232829094}
+12/24/2021 20:44:27 - INFO - codeparrot_training - Step 14316: {'lr': 0.0004070369336906078, 'samples': 7330304, 'steps': 14316, 'batch_loss/train': 0.7853873383719474}
+12/24/2021 20:44:38 - INFO - codeparrot_training - Step 14317: {'lr': 0.0004070246681767603, 'samples': 7330816, 'steps': 14317, 'batch_loss/train': 0.8705396996811032}
+12/24/2021 20:44:49 - INFO - codeparrot_training - Step 14318: {'lr': 0.000407012402038642, 'samples': 7331328, 'steps': 14318, 'batch_loss/train': 0.7665174310095608}
+12/24/2021 20:44:59 - INFO - codeparrot_training - Step 14319: {'lr': 0.00040700013527630174, 'samples': 7331840, 'steps': 14319, 'batch_loss/train': 0.8156115703750402}
+12/24/2021 20:45:13 - INFO - codeparrot_training - Step 14320: {'lr': 0.0004069878678897881, 'samples': 7332352, 'steps': 14320, 'batch_loss/train': 0.8373958133161068}
+12/24/2021 20:45:24 - INFO - codeparrot_training - Step 14321: {'lr': 0.0004069755998791501, 'samples': 7332864, 'steps': 14321, 'batch_loss/train': 0.8537029828876257}
+12/24/2021 20:45:34 - INFO - codeparrot_training - Step 14322: {'lr': 0.00040696333124443643, 'samples': 7333376, 'steps': 14322, 'batch_loss/train': 0.7166109117679298}
+12/24/2021 20:45:46 - INFO - codeparrot_training - Step 14323: {'lr': 0.00040695106198569567, 'samples': 7333888, 'steps': 14323, 'batch_loss/train': 0.8212225837633014}
+12/24/2021 20:45:57 - INFO - codeparrot_training - Step 14324: {'lr': 0.00040693879210297677, 'samples': 7334400, 'steps': 14324, 'batch_loss/train': 0.7919746628031135}
+12/24/2021 20:46:07 - INFO - codeparrot_training - Step 14325: {'lr': 0.0004069265215963285, 'samples': 7334912, 'steps': 14325, 'batch_loss/train': 0.8389196745119989}
+12/24/2021 20:46:19 - INFO - codeparrot_training - Step 14326: {'lr': 0.00040691425046579966, 'samples': 7335424, 'steps': 14326, 'batch_loss/train': 0.6447340575396083}
+12/24/2021 20:46:30 - INFO - codeparrot_training - Step 14327: {'lr': 0.0004069019787114391, 'samples': 7335936, 'steps': 14327, 'batch_loss/train': 0.7932939818128943}
+12/24/2021 20:46:41 - INFO - codeparrot_training - Step 14328: {'lr': 0.00040688970633329536, 'samples': 7336448, 'steps': 14328, 'batch_loss/train': 0.8296339986845851}
+12/24/2021 20:46:53 - INFO - codeparrot_training - Step 14329: {'lr': 0.00040687743333141745, 'samples': 7336960, 'steps': 14329, 'batch_loss/train': 0.8597945431247354}
+12/24/2021 20:47:04 - INFO - codeparrot_training - Step 14330: {'lr': 0.00040686515970585413, 'samples': 7337472, 'steps': 14330, 'batch_loss/train': 0.8818600727245212}
+12/24/2021 20:47:15 - INFO - codeparrot_training - Step 14331: {'lr': 0.00040685288545665415, 'samples': 7337984, 'steps': 14331, 'batch_loss/train': 1.2538460846990347}
+12/24/2021 20:47:25 - INFO - codeparrot_training - Step 14332: {'lr': 0.00040684061058386635, 'samples': 7338496, 'steps': 14332, 'batch_loss/train': 0.7989172330126166}
+12/24/2021 20:47:39 - INFO - codeparrot_training - Step 14333: {'lr': 0.00040682833508753945, 'samples': 7339008, 'steps': 14333, 'batch_loss/train': 0.723459176835604}
+12/24/2021 20:47:50 - INFO - codeparrot_training - Step 14334: {'lr': 0.0004068160589677223, 'samples': 7339520, 'steps': 14334, 'batch_loss/train': 0.8259889148175716}
+12/24/2021 20:48:00 - INFO - codeparrot_training - Step 14335: {'lr': 0.00040680378222446377, 'samples': 7340032, 'steps': 14335, 'batch_loss/train': 0.786514900624752}
+12/24/2021 20:48:12 - INFO - codeparrot_training - Step 14336: {'lr': 0.0004067915048578125, 'samples': 7340544, 'steps': 14336, 'batch_loss/train': 0.789344544056803}
+12/24/2021 20:48:23 - INFO - codeparrot_training - Step 14337: {'lr': 0.00040677922686781746, 'samples': 7341056, 'steps': 14337, 'batch_loss/train': 0.8179225400090218}
+12/24/2021 20:48:33 - INFO - codeparrot_training - Step 14338: {'lr': 0.0004067669482545275, 'samples': 7341568, 'steps': 14338, 'batch_loss/train': 0.7652892866171896}
+12/24/2021 20:48:45 - INFO - codeparrot_training - Step 14339: {'lr': 0.0004067546690179913, 'samples': 7342080, 'steps': 14339, 'batch_loss/train': 0.8232034924440086}
+12/24/2021 20:48:56 - INFO - codeparrot_training - Step 14340: {'lr': 0.0004067423891582577, 'samples': 7342592, 'steps': 14340, 'batch_loss/train': 0.8265803401591256}
+12/24/2021 20:49:07 - INFO - codeparrot_training - Step 14341: {'lr': 0.0004067301086753755, 'samples': 7343104, 'steps': 14341, 'batch_loss/train': 0.770349288941361}
+12/24/2021 20:49:17 - INFO - codeparrot_training - Step 14342: {'lr': 0.0004067178275693936, 'samples': 7343616, 'steps': 14342, 'batch_loss/train': 0.8449778454378247}
+12/24/2021 20:49:31 - INFO - codeparrot_training - Step 14343: {'lr': 0.0004067055458403608, 'samples': 7344128, 'steps': 14343, 'batch_loss/train': 0.8214195249602199}
+12/24/2021 20:49:42 - INFO - codeparrot_training - Step 14344: {'lr': 0.00040669326348832596, 'samples': 7344640, 'steps': 14344, 'batch_loss/train': 0.7833186108618975}
+12/24/2021 20:49:52 - INFO - codeparrot_training - Step 14345: {'lr': 0.0004066809805133378, 'samples': 7345152, 'steps': 14345, 'batch_loss/train': 0.8221320817247033}
+12/24/2021 20:50:04 - INFO - codeparrot_training - Step 14346: {'lr': 0.0004066686969154453, 'samples': 7345664, 'steps': 14346, 'batch_loss/train': 0.7837064553750679}
+12/24/2021 20:50:15 - INFO - codeparrot_training - Step 14347: {'lr': 0.00040665641269469713, 'samples': 7346176, 'steps': 14347, 'batch_loss/train': 0.7309074411168694}
+12/24/2021 20:50:26 - INFO - codeparrot_training - Step 14348: {'lr': 0.0004066441278511422, 'samples': 7346688, 'steps': 14348, 'batch_loss/train': 0.8982451381161809}
+12/24/2021 20:50:40 - INFO - codeparrot_training - Step 14349: {'lr': 0.00040663184238482955, 'samples': 7347200, 'steps': 14349, 'batch_loss/train': 0.7791677988134325}
+12/24/2021 20:50:50 - INFO - codeparrot_training - Step 14350: {'lr': 0.00040661955629580764, 'samples': 7347712, 'steps': 14350, 'batch_loss/train': 0.7063709188951179}
+12/24/2021 20:51:01 - INFO - codeparrot_training - Step 14351: {'lr': 0.00040660726958412566, 'samples': 7348224, 'steps': 14351, 'batch_loss/train': 0.7622749167494476}
+12/24/2021 20:51:11 - INFO - codeparrot_training - Step 14352: {'lr': 0.0004065949822498322, 'samples': 7348736, 'steps': 14352, 'batch_loss/train': 0.6751569795887917}
+12/24/2021 20:51:24 - INFO - codeparrot_training - Step 14353: {'lr': 0.00040658269429297625, 'samples': 7349248, 'steps': 14353, 'batch_loss/train': 0.5513375150039792}
+12/24/2021 20:51:34 - INFO - codeparrot_training - Step 14354: {'lr': 0.00040657040571360657, 'samples': 7349760, 'steps': 14354, 'batch_loss/train': 0.681512679962907}
+12/24/2021 20:51:45 - INFO - codeparrot_training - Step 14355: {'lr': 0.00040655811651177213, 'samples': 7350272, 'steps': 14355, 'batch_loss/train': 0.6066668545245193}
+12/24/2021 20:51:57 - INFO - codeparrot_training - Step 14356: {'lr': 0.0004065458266875218, 'samples': 7350784, 'steps': 14356, 'batch_loss/train': 0.660497963661328}
+12/24/2021 20:52:07 - INFO - codeparrot_training - Step 14357: {'lr': 0.00040653353624090427, 'samples': 7351296, 'steps': 14357, 'batch_loss/train': 0.629343444830738}
+12/24/2021 20:52:18 - INFO - codeparrot_training - Step 14358: {'lr': 0.0004065212451719685, 'samples': 7351808, 'steps': 14358, 'batch_loss/train': 0.8514356147497892}
+12/24/2021 20:52:30 - INFO - codeparrot_training - Step 14359: {'lr': 0.00040650895348076345, 'samples': 7352320, 'steps': 14359, 'batch_loss/train': 0.7420325763523579}
+12/24/2021 20:52:41 - INFO - codeparrot_training - Step 14360: {'lr': 0.00040649666116733784, 'samples': 7352832, 'steps': 14360, 'batch_loss/train': 0.7140755311120301}
+12/24/2021 20:52:51 - INFO - codeparrot_training - Step 14361: {'lr': 0.0004064843682317406, 'samples': 7353344, 'steps': 14361, 'batch_loss/train': 0.6681561913574114}
+12/24/2021 20:53:05 - INFO - codeparrot_training - Step 14362: {'lr': 0.0004064720746740206, 'samples': 7353856, 'steps': 14362, 'batch_loss/train': 0.8321587573736906}
+12/24/2021 20:53:16 - INFO - codeparrot_training - Step 14363: {'lr': 0.0004064597804942267, 'samples': 7354368, 'steps': 14363, 'batch_loss/train': 0.7165713491849601}
+12/24/2021 20:53:27 - INFO - codeparrot_training - Step 14364: {'lr': 0.00040644748569240783, 'samples': 7354880, 'steps': 14364, 'batch_loss/train': 0.7727621709927917}
+12/24/2021 20:53:37 - INFO - codeparrot_training - Step 14365: {'lr': 0.00040643519026861274, 'samples': 7355392, 'steps': 14365, 'batch_loss/train': 0.7886540177278221}
+12/24/2021 20:53:49 - INFO - codeparrot_training - Step 14366: {'lr': 0.0004064228942228906, 'samples': 7355904, 'steps': 14366, 'batch_loss/train': 0.8207669202238321}
+12/24/2021 20:54:00 - INFO - codeparrot_training - Step 14367: {'lr': 0.00040641059755528987, 'samples': 7356416, 'steps': 14367, 'batch_loss/train': 0.7243892289698124}
+12/24/2021 20:54:10 - INFO - codeparrot_training - Step 14368: {'lr': 0.0004063983002658598, 'samples': 7356928, 'steps': 14368, 'batch_loss/train': 0.8269480438902974}
+12/24/2021 20:54:22 - INFO - codeparrot_training - Step 14369: {'lr': 0.0004063860023546491, 'samples': 7357440, 'steps': 14369, 'batch_loss/train': 0.745899316854775}
+12/24/2021 20:54:33 - INFO - codeparrot_training - Step 14370: {'lr': 0.00040637370382170667, 'samples': 7357952, 'steps': 14370, 'batch_loss/train': 0.5914999585947953}
+12/24/2021 20:54:44 - INFO - codeparrot_training - Step 14371: {'lr': 0.00040636140466708147, 'samples': 7358464, 'steps': 14371, 'batch_loss/train': 0.8597923330962658}
+12/24/2021 20:54:57 - INFO - codeparrot_training - Step 14372: {'lr': 0.00040634910489082234, 'samples': 7358976, 'steps': 14372, 'batch_loss/train': 0.8541155429556966}
+12/24/2021 20:55:08 - INFO - codeparrot_training - Step 14373: {'lr': 0.0004063368044929783, 'samples': 7359488, 'steps': 14373, 'batch_loss/train': 0.7342601106502116}
+12/24/2021 20:55:19 - INFO - codeparrot_training - Step 14374: {'lr': 0.00040632450347359805, 'samples': 7360000, 'steps': 14374, 'batch_loss/train': 0.8001265237107873}
+12/24/2021 20:55:31 - INFO - codeparrot_training - Step 14375: {'lr': 0.00040631220183273063, 'samples': 7360512, 'steps': 14375, 'batch_loss/train': 0.7714180091861635}
+12/24/2021 20:55:41 - INFO - codeparrot_training - Step 14376: {'lr': 0.0004062998995704249, 'samples': 7361024, 'steps': 14376, 'batch_loss/train': 0.7871728148311377}
+12/24/2021 20:55:52 - INFO - codeparrot_training - Step 14377: {'lr': 0.00040628759668672983, 'samples': 7361536, 'steps': 14377, 'batch_loss/train': 0.6693661054596305}
+12/24/2021 20:56:03 - INFO - codeparrot_training - Step 14378: {'lr': 0.0004062752931816942, 'samples': 7362048, 'steps': 14378, 'batch_loss/train': 0.7243287408491597}
+12/24/2021 20:56:15 - INFO - codeparrot_training - Step 14379: {'lr': 0.00040626298905536713, 'samples': 7362560, 'steps': 14379, 'batch_loss/train': 0.840857190079987}
+12/24/2021 20:56:25 - INFO - codeparrot_training - Step 14380: {'lr': 0.0004062506843077973, 'samples': 7363072, 'steps': 14380, 'batch_loss/train': 0.7972024958580732}
+12/24/2021 20:56:36 - INFO - codeparrot_training - Step 14381: {'lr': 0.00040623837893903386, 'samples': 7363584, 'steps': 14381, 'batch_loss/train': 0.6530896725598723}
+12/24/2021 20:56:50 - INFO - codeparrot_training - Step 14382: {'lr': 0.00040622607294912556, 'samples': 7364096, 'steps': 14382, 'batch_loss/train': 0.784143315278925}
+12/24/2021 20:57:00 - INFO - codeparrot_training - Step 14383: {'lr': 0.00040621376633812143, 'samples': 7364608, 'steps': 14383, 'batch_loss/train': 0.6975715907756239}
+12/24/2021 20:57:11 - INFO - codeparrot_training - Step 14384: {'lr': 0.0004062014591060703, 'samples': 7365120, 'steps': 14384, 'batch_loss/train': 0.9049372989684343}
+12/24/2021 20:57:23 - INFO - codeparrot_training - Step 14385: {'lr': 0.0004061891512530211, 'samples': 7365632, 'steps': 14385, 'batch_loss/train': 0.659433924825862}
+12/24/2021 20:57:34 - INFO - codeparrot_training - Step 14386: {'lr': 0.0004061768427790229, 'samples': 7366144, 'steps': 14386, 'batch_loss/train': 0.9216384636238217}
+12/24/2021 20:57:44 - INFO - codeparrot_training - Step 14387: {'lr': 0.00040616453368412454, 'samples': 7366656, 'steps': 14387, 'batch_loss/train': 0.7939587980508804}
+12/24/2021 20:57:55 - INFO - codeparrot_training - Step 14388: {'lr': 0.00040615222396837494, 'samples': 7367168, 'steps': 14388, 'batch_loss/train': 1.0023083174601197}
+12/24/2021 20:58:09 - INFO - codeparrot_training - Step 14389: {'lr': 0.000406139913631823, 'samples': 7367680, 'steps': 14389, 'batch_loss/train': 0.7222729837521911}
+12/24/2021 20:58:19 - INFO - codeparrot_training - Step 14390: {'lr': 0.00040612760267451776, 'samples': 7368192, 'steps': 14390, 'batch_loss/train': 0.756210420280695}
+12/24/2021 20:58:30 - INFO - codeparrot_training - Step 14391: {'lr': 0.00040611529109650814, 'samples': 7368704, 'steps': 14391, 'batch_loss/train': 0.8094795513898134}
+12/24/2021 20:58:42 - INFO - codeparrot_training - Step 14392: {'lr': 0.0004061029788978431, 'samples': 7369216, 'steps': 14392, 'batch_loss/train': 0.8046063678339124}
+12/24/2021 20:58:52 - INFO - codeparrot_training - Step 14393: {'lr': 0.0004060906660785715, 'samples': 7369728, 'steps': 14393, 'batch_loss/train': 0.7926086313091218}
+12/24/2021 20:59:03 - INFO - codeparrot_training - Step 14394: {'lr': 0.00040607835263874236, 'samples': 7370240, 'steps': 14394, 'batch_loss/train': 0.8430774984881282}
+12/24/2021 20:59:15 - INFO - codeparrot_training - Step 14395: {'lr': 0.00040606603857840464, 'samples': 7370752, 'steps': 14395, 'batch_loss/train': 0.7586956219747663}
+12/24/2021 20:59:26 - INFO - codeparrot_training - Step 14396: {'lr': 0.0004060537238976073, 'samples': 7371264, 'steps': 14396, 'batch_loss/train': 0.8319260831922293}
+12/24/2021 20:59:36 - INFO - codeparrot_training - Step 14397: {'lr': 0.00040604140859639917, 'samples': 7371776, 'steps': 14397, 'batch_loss/train': 0.7976538436487317}
+12/24/2021 20:59:47 - INFO - codeparrot_training - Step 14398: {'lr': 0.0004060290926748294, 'samples': 7372288, 'steps': 14398, 'batch_loss/train': 0.7616070611402392}
+12/24/2021 20:59:59 - INFO - codeparrot_training - Step 14399: {'lr': 0.00040601677613294685, 'samples': 7372800, 'steps': 14399, 'batch_loss/train': 0.7436474654823542}
+12/24/2021 21:00:09 - INFO - codeparrot_training - Step 14400: {'lr': 0.0004060044589708005, 'samples': 7373312, 'steps': 14400, 'batch_loss/train': 0.765016702003777}
+12/24/2021 21:00:20 - INFO - codeparrot_training - Step 14401: {'lr': 0.0004059921411884394, 'samples': 7373824, 'steps': 14401, 'batch_loss/train': 0.7874116702005267}
+12/24/2021 21:00:34 - INFO - codeparrot_training - Step 14402: {'lr': 0.00040597982278591237, 'samples': 7374336, 'steps': 14402, 'batch_loss/train': 0.7543824990279973}
+12/24/2021 21:00:45 - INFO - codeparrot_training - Step 14403: {'lr': 0.00040596750376326854, 'samples': 7374848, 'steps': 14403, 'batch_loss/train': 0.8271801867522299}
+12/24/2021 21:00:55 - INFO - codeparrot_training - Step 14404: {'lr': 0.00040595518412055674, 'samples': 7375360, 'steps': 14404, 'batch_loss/train': 0.8070313036441803}
+12/24/2021 21:01:07 - INFO - codeparrot_training - Step 14405: {'lr': 0.00040594286385782605, 'samples': 7375872, 'steps': 14405, 'batch_loss/train': 0.8165835151448846}
+12/24/2021 21:01:18 - INFO - codeparrot_training - Step 14406: {'lr': 0.0004059305429751254, 'samples': 7376384, 'steps': 14406, 'batch_loss/train': 0.5629420534241945}
+12/24/2021 21:01:29 - INFO - codeparrot_training - Step 14407: {'lr': 0.0004059182214725038, 'samples': 7376896, 'steps': 14407, 'batch_loss/train': 0.8440208183601499}
+12/24/2021 21:01:41 - INFO - codeparrot_training - Step 14408: {'lr': 0.0004059058993500102, 'samples': 7377408, 'steps': 14408, 'batch_loss/train': 0.7572104558348656}
+12/24/2021 21:01:51 - INFO - codeparrot_training - Step 14409: {'lr': 0.00040589357660769356, 'samples': 7377920, 'steps': 14409, 'batch_loss/train': 0.7743108496069908}
+12/24/2021 21:02:02 - INFO - codeparrot_training - Step 14410: {'lr': 0.000405881253245603, 'samples': 7378432, 'steps': 14410, 'batch_loss/train': 0.7802382949739695}
+12/24/2021 21:02:13 - INFO - codeparrot_training - Step 14411: {'lr': 0.0004058689292637874, 'samples': 7378944, 'steps': 14411, 'batch_loss/train': 0.8228210303932428}
+12/24/2021 21:02:26 - INFO - codeparrot_training - Step 14412: {'lr': 0.0004058566046622958, 'samples': 7379456, 'steps': 14412, 'batch_loss/train': 0.7692320761270821}
+12/24/2021 21:02:37 - INFO - codeparrot_training - Step 14413: {'lr': 0.0004058442794411772, 'samples': 7379968, 'steps': 14413, 'batch_loss/train': 0.8544259583577514}
+12/24/2021 21:02:48 - INFO - codeparrot_training - Step 14414: {'lr': 0.00040583195360048064, 'samples': 7380480, 'steps': 14414, 'batch_loss/train': 0.7756724515929818}
+12/24/2021 21:03:00 - INFO - codeparrot_training - Step 14415: {'lr': 0.000405819627140255, 'samples': 7380992, 'steps': 14415, 'batch_loss/train': 0.8199131153523922}
+12/24/2021 21:03:10 - INFO - codeparrot_training - Step 14416: {'lr': 0.0004058073000605493, 'samples': 7381504, 'steps': 14416, 'batch_loss/train': 0.7609236361458898}
+12/24/2021 21:03:21 - INFO - codeparrot_training - Step 14417: {'lr': 0.0004057949723614127, 'samples': 7382016, 'steps': 14417, 'batch_loss/train': 0.7696857322007418}
+12/24/2021 21:03:35 - INFO - codeparrot_training - Step 14418: {'lr': 0.0004057826440428941, 'samples': 7382528, 'steps': 14418, 'batch_loss/train': 0.8580714724957943}
+12/24/2021 21:03:45 - INFO - codeparrot_training - Step 14419: {'lr': 0.0004057703151050426, 'samples': 7383040, 'steps': 14419, 'batch_loss/train': 0.6969712261925451}
+12/24/2021 21:03:56 - INFO - codeparrot_training - Step 14420: {'lr': 0.00040575798554790704, 'samples': 7383552, 'steps': 14420, 'batch_loss/train': 0.7922532535158098}
+12/24/2021 21:04:08 - INFO - codeparrot_training - Step 14421: {'lr': 0.00040574565537153655, 'samples': 7384064, 'steps': 14421, 'batch_loss/train': 0.7026864956133068}
+12/24/2021 21:04:18 - INFO - codeparrot_training - Step 14422: {'lr': 0.0004057333245759801, 'samples': 7384576, 'steps': 14422, 'batch_loss/train': 0.7750430807936937}
+12/24/2021 21:04:29 - INFO - codeparrot_training - Step 14423: {'lr': 0.00040572099316128687, 'samples': 7385088, 'steps': 14423, 'batch_loss/train': 0.6753226849250495}
+12/24/2021 21:04:40 - INFO - codeparrot_training - Step 14424: {'lr': 0.0004057086611275057, 'samples': 7385600, 'steps': 14424, 'batch_loss/train': 0.7686782237142324}
+12/24/2021 21:04:52 - INFO - codeparrot_training - Step 14425: {'lr': 0.00040569632847468575, 'samples': 7386112, 'steps': 14425, 'batch_loss/train': 0.738016399089247}
+12/24/2021 21:05:02 - INFO - codeparrot_training - Step 14426: {'lr': 0.0004056839952028759, 'samples': 7386624, 'steps': 14426, 'batch_loss/train': 0.697270252276212}
+12/24/2021 21:05:13 - INFO - codeparrot_training - Step 14427: {'lr': 0.0004056716613121253, 'samples': 7387136, 'steps': 14427, 'batch_loss/train': 1.7606603652238846}
+12/24/2021 21:05:27 - INFO - codeparrot_training - Step 14428: {'lr': 0.00040565932680248297, 'samples': 7387648, 'steps': 14428, 'batch_loss/train': 0.7046131719835103}
+12/24/2021 21:05:37 - INFO - codeparrot_training - Step 14429: {'lr': 0.000405646991673998, 'samples': 7388160, 'steps': 14429, 'batch_loss/train': 0.876697420142591}
+12/24/2021 21:05:48 - INFO - codeparrot_training - Step 14430: {'lr': 0.00040563465592671923, 'samples': 7388672, 'steps': 14430, 'batch_loss/train': 0.8342354092746973}
+12/24/2021 21:06:00 - INFO - codeparrot_training - Step 14431: {'lr': 0.0004056223195606959, 'samples': 7389184, 'steps': 14431, 'batch_loss/train': 0.7949042366817594}
+12/24/2021 21:06:11 - INFO - codeparrot_training - Step 14432: {'lr': 0.00040560998257597693, 'samples': 7389696, 'steps': 14432, 'batch_loss/train': 0.7923786672763526}
+12/24/2021 21:06:21 - INFO - codeparrot_training - Step 14433: {'lr': 0.00040559764497261156, 'samples': 7390208, 'steps': 14433, 'batch_loss/train': 0.7645766119239852}
+12/24/2021 21:06:32 - INFO - codeparrot_training - Step 14434: {'lr': 0.0004055853067506485, 'samples': 7390720, 'steps': 14434, 'batch_loss/train': 0.8497481131926179}
+12/24/2021 21:06:44 - INFO - codeparrot_training - Step 14435: {'lr': 0.00040557296791013717, 'samples': 7391232, 'steps': 14435, 'batch_loss/train': 0.7813273291103542}
+12/24/2021 21:06:55 - INFO - codeparrot_training - Step 14436: {'lr': 0.0004055606284511264, 'samples': 7391744, 'steps': 14436, 'batch_loss/train': 0.850170599296689}
+12/24/2021 21:07:05 - INFO - codeparrot_training - Step 14437: {'lr': 0.0004055482883736653, 'samples': 7392256, 'steps': 14437, 'batch_loss/train': 0.7952681118622422}
+12/24/2021 21:07:18 - INFO - codeparrot_training - Step 14438: {'lr': 0.000405535947677803, 'samples': 7392768, 'steps': 14438, 'batch_loss/train': 0.8147792816162109}
+12/24/2021 21:07:28 - INFO - codeparrot_training - Step 14439: {'lr': 0.00040552360636358844, 'samples': 7393280, 'steps': 14439, 'batch_loss/train': 0.7802589861676097}
+12/24/2021 21:07:39 - INFO - codeparrot_training - Step 14440: {'lr': 0.0004055112644310708, 'samples': 7393792, 'steps': 14440, 'batch_loss/train': 0.6766338543966413}
+12/24/2021 21:07:53 - INFO - codeparrot_training - Step 14441: {'lr': 0.000405498921880299, 'samples': 7394304, 'steps': 14441, 'batch_loss/train': 0.8081174492835999}
+12/24/2021 21:08:03 - INFO - codeparrot_training - Step 14442: {'lr': 0.00040548657871132234, 'samples': 7394816, 'steps': 14442, 'batch_loss/train': 0.8362015290185809}
+12/24/2021 21:08:14 - INFO - codeparrot_training - Step 14443: {'lr': 0.0004054742349241896, 'samples': 7395328, 'steps': 14443, 'batch_loss/train': 0.7607070347294211}
+12/24/2021 21:08:24 - INFO - codeparrot_training - Step 14444: {'lr': 0.0004054618905189501, 'samples': 7395840, 'steps': 14444, 'batch_loss/train': 0.7140958642121404}
+12/24/2021 21:08:37 - INFO - codeparrot_training - Step 14445: {'lr': 0.0004054495454956528, 'samples': 7396352, 'steps': 14445, 'batch_loss/train': 0.7482699556276202}
+12/24/2021 21:08:47 - INFO - codeparrot_training - Step 14446: {'lr': 0.0004054371998543468, 'samples': 7396864, 'steps': 14446, 'batch_loss/train': 0.9408856919035316}
+12/24/2021 21:08:58 - INFO - codeparrot_training - Step 14447: {'lr': 0.0004054248535950812, 'samples': 7397376, 'steps': 14447, 'batch_loss/train': 0.8490971475839615}
+12/24/2021 21:09:10 - INFO - codeparrot_training - Step 14448: {'lr': 0.000405412506717905, 'samples': 7397888, 'steps': 14448, 'batch_loss/train': 0.7894862918183208}
+12/24/2021 21:09:20 - INFO - codeparrot_training - Step 14449: {'lr': 0.00040540015922286746, 'samples': 7398400, 'steps': 14449, 'batch_loss/train': 0.7831326867453754}
+12/24/2021 21:09:31 - INFO - codeparrot_training - Step 14450: {'lr': 0.00040538781111001753, 'samples': 7398912, 'steps': 14450, 'batch_loss/train': 0.7940477705560625}
+12/24/2021 21:09:45 - INFO - codeparrot_training - Step 14451: {'lr': 0.0004053754623794043, 'samples': 7399424, 'steps': 14451, 'batch_loss/train': 0.7632901519536972}
+12/24/2021 21:09:55 - INFO - codeparrot_training - Step 14452: {'lr': 0.0004053631130310769, 'samples': 7399936, 'steps': 14452, 'batch_loss/train': 0.8291241135448217}
+12/24/2021 21:10:06 - INFO - codeparrot_training - Step 14453: {'lr': 0.00040535076306508444, 'samples': 7400448, 'steps': 14453, 'batch_loss/train': 0.7774081956595182}
+12/24/2021 21:10:17 - INFO - codeparrot_training - Step 14454: {'lr': 0.000405338412481476, 'samples': 7400960, 'steps': 14454, 'batch_loss/train': 1.723494753241539}
+12/24/2021 21:10:29 - INFO - codeparrot_training - Step 14455: {'lr': 0.0004053260612803007, 'samples': 7401472, 'steps': 14455, 'batch_loss/train': 0.8344197850674391}
+12/24/2021 21:10:39 - INFO - codeparrot_training - Step 14456: {'lr': 0.0004053137094616076, 'samples': 7401984, 'steps': 14456, 'batch_loss/train': 0.8360478105023503}
+12/24/2021 21:10:50 - INFO - codeparrot_training - Step 14457: {'lr': 0.0004053013570254459, 'samples': 7402496, 'steps': 14457, 'batch_loss/train': 0.8614283357746899}
+12/24/2021 21:11:04 - INFO - codeparrot_training - Step 14458: {'lr': 0.00040528900397186464, 'samples': 7403008, 'steps': 14458, 'batch_loss/train': 0.8023588084615767}
+12/24/2021 21:11:14 - INFO - codeparrot_training - Step 14459: {'lr': 0.0004052766503009129, 'samples': 7403520, 'steps': 14459, 'batch_loss/train': 0.800335356965661}
+12/24/2021 21:11:25 - INFO - codeparrot_training - Step 14460: {'lr': 0.0004052642960126398, 'samples': 7404032, 'steps': 14460, 'batch_loss/train': 0.8864487195387483}
+12/24/2021 21:11:37 - INFO - codeparrot_training - Step 14461: {'lr': 0.0004052519411070945, 'samples': 7404544, 'steps': 14461, 'batch_loss/train': 0.7907833433710039}
+12/24/2021 21:11:48 - INFO - codeparrot_training - Step 14462: {'lr': 0.0004052395855843261, 'samples': 7405056, 'steps': 14462, 'batch_loss/train': 0.7736672139726579}
+12/24/2021 21:11:58 - INFO - codeparrot_training - Step 14463: {'lr': 0.0004052272294443837, 'samples': 7405568, 'steps': 14463, 'batch_loss/train': 0.7443662602454424}
+12/24/2021 21:12:10 - INFO - codeparrot_training - Step 14464: {'lr': 0.00040521487268731655, 'samples': 7406080, 'steps': 14464, 'batch_loss/train': 0.7715516202151775}
+12/24/2021 21:12:21 - INFO - codeparrot_training - Step 14465: {'lr': 0.00040520251531317355, 'samples': 7406592, 'steps': 14465, 'batch_loss/train': 0.9143158011138439}
+12/24/2021 21:12:31 - INFO - codeparrot_training - Step 14466: {'lr': 0.00040519015732200404, 'samples': 7407104, 'steps': 14466, 'batch_loss/train': 0.8553401045501232}
+12/24/2021 21:12:42 - INFO - codeparrot_training - Step 14467: {'lr': 0.0004051777987138571, 'samples': 7407616, 'steps': 14467, 'batch_loss/train': 0.8076601540669799}
+12/24/2021 21:12:56 - INFO - codeparrot_training - Step 14468: {'lr': 0.0004051654394887817, 'samples': 7408128, 'steps': 14468, 'batch_loss/train': 0.7534263795241714}
+12/24/2021 21:13:06 - INFO - codeparrot_training - Step 14469: {'lr': 0.0004051530796468271, 'samples': 7408640, 'steps': 14469, 'batch_loss/train': 0.7380002615973353}
+12/24/2021 21:13:17 - INFO - codeparrot_training - Step 14470: {'lr': 0.0004051407191880426, 'samples': 7409152, 'steps': 14470, 'batch_loss/train': 0.8548561858478934}
+12/24/2021 21:13:29 - INFO - codeparrot_training - Step 14471: {'lr': 0.00040512835811247705, 'samples': 7409664, 'steps': 14471, 'batch_loss/train': 0.829748303629458}
+12/24/2021 21:13:40 - INFO - codeparrot_training - Step 14472: {'lr': 0.0004051159964201797, 'samples': 7410176, 'steps': 14472, 'batch_loss/train': 0.7177524211583659}
+12/24/2021 21:13:50 - INFO - codeparrot_training - Step 14473: {'lr': 0.0004051036341111998, 'samples': 7410688, 'steps': 14473, 'batch_loss/train': 0.7052846199367195}
+12/24/2021 21:14:04 - INFO - codeparrot_training - Step 14474: {'lr': 0.00040509127118558636, 'samples': 7411200, 'steps': 14474, 'batch_loss/train': 0.7871590792201459}
+12/24/2021 21:14:15 - INFO - codeparrot_training - Step 14475: {'lr': 0.00040507890764338863, 'samples': 7411712, 'steps': 14475, 'batch_loss/train': 0.8317597033455968}
+12/24/2021 21:14:25 - INFO - codeparrot_training - Step 14476: {'lr': 0.00040506654348465565, 'samples': 7412224, 'steps': 14476, 'batch_loss/train': 0.9397415351122618}
+12/24/2021 21:14:38 - INFO - codeparrot_training - Step 14477: {'lr': 0.00040505417870943675, 'samples': 7412736, 'steps': 14477, 'batch_loss/train': 0.794648103415966}
+12/24/2021 21:14:48 - INFO - codeparrot_training - Step 14478: {'lr': 0.0004050418133177809, 'samples': 7413248, 'steps': 14478, 'batch_loss/train': 0.8141411207616329}
+12/24/2021 21:14:59 - INFO - codeparrot_training - Step 14479: {'lr': 0.0004050294473097373, 'samples': 7413760, 'steps': 14479, 'batch_loss/train': 1.0222084252163768}
+12/24/2021 21:15:09 - INFO - codeparrot_training - Step 14480: {'lr': 0.00040501708068535524, 'samples': 7414272, 'steps': 14480, 'batch_loss/train': 0.7162191388197243}
+12/24/2021 21:15:22 - INFO - codeparrot_training - Step 14481: {'lr': 0.0004050047134446838, 'samples': 7414784, 'steps': 14481, 'batch_loss/train': 0.7546407417394221}
+12/24/2021 21:15:32 - INFO - codeparrot_training - Step 14482: {'lr': 0.0004049923455877721, 'samples': 7415296, 'steps': 14482, 'batch_loss/train': 0.7985744497273117}
+12/24/2021 21:15:43 - INFO - codeparrot_training - Step 14483: {'lr': 0.00040497997711466937, 'samples': 7415808, 'steps': 14483, 'batch_loss/train': 0.8330721776001155}
+12/24/2021 21:15:55 - INFO - codeparrot_training - Step 14484: {'lr': 0.0004049676080254248, 'samples': 7416320, 'steps': 14484, 'batch_loss/train': 0.7047268128953874}
+12/24/2021 21:16:06 - INFO - codeparrot_training - Step 14485: {'lr': 0.0004049552383200875, 'samples': 7416832, 'steps': 14485, 'batch_loss/train': 0.78544981777668}
+12/24/2021 21:16:16 - INFO - codeparrot_training - Step 14486: {'lr': 0.0004049428679987067, 'samples': 7417344, 'steps': 14486, 'batch_loss/train': 0.8239551442675292}
+12/24/2021 21:16:30 - INFO - codeparrot_training - Step 14487: {'lr': 0.00040493049706133156, 'samples': 7417856, 'steps': 14487, 'batch_loss/train': 0.8231672011315823}
+12/24/2021 21:16:41 - INFO - codeparrot_training - Step 14488: {'lr': 0.0004049181255080113, 'samples': 7418368, 'steps': 14488, 'batch_loss/train': 0.9033278157003224}
+12/24/2021 21:16:51 - INFO - codeparrot_training - Step 14489: {'lr': 0.000404905753338795, 'samples': 7418880, 'steps': 14489, 'batch_loss/train': 0.8578813103958964}
+12/24/2021 21:17:02 - INFO - codeparrot_training - Step 14490: {'lr': 0.00040489338055373195, 'samples': 7419392, 'steps': 14490, 'batch_loss/train': 0.7298800591379404}
+12/24/2021 21:17:14 - INFO - codeparrot_training - Step 14491: {'lr': 0.00040488100715287123, 'samples': 7419904, 'steps': 14491, 'batch_loss/train': 0.8715792894363403}
+12/24/2021 21:17:24 - INFO - codeparrot_training - Step 14492: {'lr': 0.0004048686331362623, 'samples': 7420416, 'steps': 14492, 'batch_loss/train': 0.7645857213065028}
+12/24/2021 21:17:35 - INFO - codeparrot_training - Step 14493: {'lr': 0.00040485625850395396, 'samples': 7420928, 'steps': 14493, 'batch_loss/train': 0.7197452606633306}
+12/24/2021 21:17:47 - INFO - codeparrot_training - Step 14494: {'lr': 0.0004048438832559957, 'samples': 7421440, 'steps': 14494, 'batch_loss/train': 0.8186878236010671}
+12/24/2021 21:17:58 - INFO - codeparrot_training - Step 14495: {'lr': 0.0004048315073924366, 'samples': 7421952, 'steps': 14495, 'batch_loss/train': 0.7725222473964095}
+12/24/2021 21:18:08 - INFO - codeparrot_training - Step 14496: {'lr': 0.0004048191309133259, 'samples': 7422464, 'steps': 14496, 'batch_loss/train': 0.8178280902793631}
+12/24/2021 21:18:22 - INFO - codeparrot_training - Step 14497: {'lr': 0.0004048067538187128, 'samples': 7422976, 'steps': 14497, 'batch_loss/train': 0.7897657649591565}
+12/24/2021 21:18:33 - INFO - codeparrot_training - Step 14498: {'lr': 0.00040479437610864644, 'samples': 7423488, 'steps': 14498, 'batch_loss/train': 0.7959894272498786}
+12/24/2021 21:18:43 - INFO - codeparrot_training - Step 14499: {'lr': 0.0004047819977831761, 'samples': 7424000, 'steps': 14499, 'batch_loss/train': 0.746421517804265}
+12/24/2021 21:18:55 - INFO - codeparrot_training - Step 14500: {'lr': 0.0004047696188423511, 'samples': 7424512, 'steps': 14500, 'batch_loss/train': 0.8268796298652887}
+12/24/2021 21:19:06 - INFO - codeparrot_training - Step 14501: {'lr': 0.00040475723928622045, 'samples': 7425024, 'steps': 14501, 'batch_loss/train': 0.6409639795310795}
+12/24/2021 21:19:17 - INFO - codeparrot_training - Step 14502: {'lr': 0.00040474485911483343, 'samples': 7425536, 'steps': 14502, 'batch_loss/train': 0.8077704403549433}
+12/24/2021 21:19:27 - INFO - codeparrot_training - Step 14503: {'lr': 0.00040473247832823936, 'samples': 7426048, 'steps': 14503, 'batch_loss/train': 0.8073315555229783}
+12/24/2021 21:19:41 - INFO - codeparrot_training - Step 14504: {'lr': 0.00040472009692648725, 'samples': 7426560, 'steps': 14504, 'batch_loss/train': 0.7771367463283241}
+12/24/2021 21:19:51 - INFO - codeparrot_training - Step 14505: {'lr': 0.00040470771490962653, 'samples': 7427072, 'steps': 14505, 'batch_loss/train': 0.7759137470275164}
+12/24/2021 21:20:02 - INFO - codeparrot_training - Step 14506: {'lr': 0.0004046953322777064, 'samples': 7427584, 'steps': 14506, 'batch_loss/train': 0.8157443013042212}
+12/24/2021 21:20:14 - INFO - codeparrot_training - Step 14507: {'lr': 0.00040468294903077596, 'samples': 7428096, 'steps': 14507, 'batch_loss/train': 0.8753816806711257}
+12/24/2021 21:20:25 - INFO - codeparrot_training - Step 14508: {'lr': 0.00040467056516888455, 'samples': 7428608, 'steps': 14508, 'batch_loss/train': 0.7813797183334827}
+12/24/2021 21:20:35 - INFO - codeparrot_training - Step 14509: {'lr': 0.0004046581806920814, 'samples': 7429120, 'steps': 14509, 'batch_loss/train': 0.7999724131077528}
+12/24/2021 21:20:46 - INFO - codeparrot_training - Step 14510: {'lr': 0.00040464579560041565, 'samples': 7429632, 'steps': 14510, 'batch_loss/train': 0.7055282741785049}
+12/24/2021 21:21:00 - INFO - codeparrot_training - Step 14511: {'lr': 0.00040463340989393666, 'samples': 7430144, 'steps': 14511, 'batch_loss/train': 0.7527643274515867}
+12/24/2021 21:21:11 - INFO - codeparrot_training - Step 14512: {'lr': 0.0004046210235726936, 'samples': 7430656, 'steps': 14512, 'batch_loss/train': 0.8780729696154594}
+12/24/2021 21:21:21 - INFO - codeparrot_training - Step 14513: {'lr': 0.0004046086366367358, 'samples': 7431168, 'steps': 14513, 'batch_loss/train': 0.7858016239479184}
+12/24/2021 21:21:33 - INFO - codeparrot_training - Step 14514: {'lr': 0.00040459624908611237, 'samples': 7431680, 'steps': 14514, 'batch_loss/train': 0.7888796348124743}
+12/24/2021 21:21:44 - INFO - codeparrot_training - Step 14515: {'lr': 0.00040458386092087265, 'samples': 7432192, 'steps': 14515, 'batch_loss/train': 0.7124688038602471}
+12/24/2021 21:21:55 - INFO - codeparrot_training - Step 14516: {'lr': 0.0004045714721410658, 'samples': 7432704, 'steps': 14516, 'batch_loss/train': 0.8292450793087482}
+12/24/2021 21:22:07 - INFO - codeparrot_training - Step 14517: {'lr': 0.0004045590827467412, 'samples': 7433216, 'steps': 14517, 'batch_loss/train': 0.7938361028209329}
+12/24/2021 21:22:17 - INFO - codeparrot_training - Step 14518: {'lr': 0.0004045466927379481, 'samples': 7433728, 'steps': 14518, 'batch_loss/train': 0.8147512190043926}
+12/24/2021 21:22:28 - INFO - codeparrot_training - Step 14519: {'lr': 0.00040453430211473564, 'samples': 7434240, 'steps': 14519, 'batch_loss/train': 0.7829461582005024}
+12/24/2021 21:22:42 - INFO - codeparrot_training - Step 14520: {'lr': 0.00040452191087715314, 'samples': 7434752, 'steps': 14520, 'batch_loss/train': 0.7936670864000916}
+12/24/2021 21:22:52 - INFO - codeparrot_training - Step 14521: {'lr': 0.0004045095190252499, 'samples': 7435264, 'steps': 14521, 'batch_loss/train': 0.8160509457811713}
+12/24/2021 21:23:03 - INFO - codeparrot_training - Step 14522: {'lr': 0.0004044971265590751, 'samples': 7435776, 'steps': 14522, 'batch_loss/train': 0.7609271751716733}
+12/24/2021 21:23:14 - INFO - codeparrot_training - Step 14523: {'lr': 0.0004044847334786781, 'samples': 7436288, 'steps': 14523, 'batch_loss/train': 0.9109337767586112}
+12/24/2021 21:23:26 - INFO - codeparrot_training - Step 14524: {'lr': 0.00040447233978410814, 'samples': 7436800, 'steps': 14524, 'batch_loss/train': 0.8418207569047809}
+12/24/2021 21:23:37 - INFO - codeparrot_training - Step 14525: {'lr': 0.0004044599454754144, 'samples': 7437312, 'steps': 14525, 'batch_loss/train': 0.8197522228583694}
+12/24/2021 21:23:47 - INFO - codeparrot_training - Step 14526: {'lr': 0.0004044475505526464, 'samples': 7437824, 'steps': 14526, 'batch_loss/train': 1.0450520738959312}
+12/24/2021 21:24:01 - INFO - codeparrot_training - Step 14527: {'lr': 0.00040443515501585315, 'samples': 7438336, 'steps': 14527, 'batch_loss/train': 0.8251100000925362}
+12/24/2021 21:24:12 - INFO - codeparrot_training - Step 14528: {'lr': 0.000404422758865084, 'samples': 7438848, 'steps': 14528, 'batch_loss/train': 0.771146728657186}
+12/24/2021 21:24:22 - INFO - codeparrot_training - Step 14529: {'lr': 0.0004044103621003883, 'samples': 7439360, 'steps': 14529, 'batch_loss/train': 0.8224132545292377}
+12/24/2021 21:24:34 - INFO - codeparrot_training - Step 14530: {'lr': 0.0004043979647218153, 'samples': 7439872, 'steps': 14530, 'batch_loss/train': 0.793625402264297}
+12/24/2021 21:24:45 - INFO - codeparrot_training - Step 14531: {'lr': 0.0004043855667294144, 'samples': 7440384, 'steps': 14531, 'batch_loss/train': 0.7698456692742184}
+12/24/2021 21:24:56 - INFO - codeparrot_training - Step 14532: {'lr': 0.00040437316812323465, 'samples': 7440896, 'steps': 14532, 'batch_loss/train': 0.733096657320857}
+12/24/2021 21:25:06 - INFO - codeparrot_training - Step 14533: {'lr': 0.0004043607689033255, 'samples': 7441408, 'steps': 14533, 'batch_loss/train': 0.8685655393637717}
+12/24/2021 21:25:18 - INFO - codeparrot_training - Step 14534: {'lr': 0.00040434836906973626, 'samples': 7441920, 'steps': 14534, 'batch_loss/train': 0.7888433029875159}
+12/24/2021 21:25:29 - INFO - codeparrot_training - Step 14535: {'lr': 0.0004043359686225161, 'samples': 7442432, 'steps': 14535, 'batch_loss/train': 0.7533476836979389}
+12/24/2021 21:25:40 - INFO - codeparrot_training - Step 14536: {'lr': 0.00040432356756171453, 'samples': 7442944, 'steps': 14536, 'batch_loss/train': 0.8257367052137852}
+12/24/2021 21:25:54 - INFO - codeparrot_training - Step 14537: {'lr': 0.00040431116588738057, 'samples': 7443456, 'steps': 14537, 'batch_loss/train': 0.6066584931686521}
+12/24/2021 21:26:05 - INFO - codeparrot_training - Step 14538: {'lr': 0.0004042987635995639, 'samples': 7443968, 'steps': 14538, 'batch_loss/train': 0.8582726761233062}
+12/24/2021 21:26:15 - INFO - codeparrot_training - Step 14539: {'lr': 0.00040428636069831335, 'samples': 7444480, 'steps': 14539, 'batch_loss/train': 1.2410197705030441}
+12/24/2021 21:26:26 - INFO - codeparrot_training - Step 14540: {'lr': 0.00040427395718367864, 'samples': 7444992, 'steps': 14540, 'batch_loss/train': 0.8568713590502739}
+12/24/2021 21:26:38 - INFO - codeparrot_training - Step 14541: {'lr': 0.00040426155305570887, 'samples': 7445504, 'steps': 14541, 'batch_loss/train': 0.8312932522967458}
+12/24/2021 21:26:48 - INFO - codeparrot_training - Step 14542: {'lr': 0.00040424914831445346, 'samples': 7446016, 'steps': 14542, 'batch_loss/train': 0.8890148410573602}
+12/24/2021 21:26:59 - INFO - codeparrot_training - Step 14543: {'lr': 0.0004042367429599617, 'samples': 7446528, 'steps': 14543, 'batch_loss/train': 0.769819799810648}
+12/24/2021 21:27:13 - INFO - codeparrot_training - Step 14544: {'lr': 0.00040422433699228283, 'samples': 7447040, 'steps': 14544, 'batch_loss/train': 0.766990203410387}
+12/24/2021 21:27:24 - INFO - codeparrot_training - Step 14545: {'lr': 0.00040421193041146626, 'samples': 7447552, 'steps': 14545, 'batch_loss/train': 0.841575366910547}
+12/24/2021 21:27:34 - INFO - codeparrot_training - Step 14546: {'lr': 0.00040419952321756123, 'samples': 7448064, 'steps': 14546, 'batch_loss/train': 0.7757745208218694}
+12/24/2021 21:27:46 - INFO - codeparrot_training - Step 14547: {'lr': 0.0004041871154106172, 'samples': 7448576, 'steps': 14547, 'batch_loss/train': 0.7619125072378665}
+12/24/2021 21:27:57 - INFO - codeparrot_training - Step 14548: {'lr': 0.0004041747069906834, 'samples': 7449088, 'steps': 14548, 'batch_loss/train': 0.6649721707217395}
+12/24/2021 21:28:07 - INFO - codeparrot_training - Step 14549: {'lr': 0.0004041622979578091, 'samples': 7449600, 'steps': 14549, 'batch_loss/train': 0.7963699079118669}
+12/24/2021 21:28:18 - INFO - codeparrot_training - Step 14550: {'lr': 0.0004041498883120438, 'samples': 7450112, 'steps': 14550, 'batch_loss/train': 0.7421456566080451}
+12/24/2021 21:28:30 - INFO - codeparrot_training - Step 14551: {'lr': 0.0004041374780534367, 'samples': 7450624, 'steps': 14551, 'batch_loss/train': 0.8041170306969434}
+12/24/2021 21:28:41 - INFO - codeparrot_training - Step 14552: {'lr': 0.00040412506718203725, 'samples': 7451136, 'steps': 14552, 'batch_loss/train': 0.9684199746698141}
+12/24/2021 21:28:51 - INFO - codeparrot_training - Step 14553: {'lr': 0.0004041126556978946, 'samples': 7451648, 'steps': 14553, 'batch_loss/train': 0.7940661013126373}
+12/24/2021 21:29:04 - INFO - codeparrot_training - Step 14554: {'lr': 0.00040410024360105834, 'samples': 7452160, 'steps': 14554, 'batch_loss/train': 0.8970004618167877}
+12/24/2021 21:29:14 - INFO - codeparrot_training - Step 14555: {'lr': 0.0004040878308915776, 'samples': 7452672, 'steps': 14555, 'batch_loss/train': 0.698346015997231}
+12/24/2021 21:29:25 - INFO - codeparrot_training - Step 14556: {'lr': 0.0004040754175695019, 'samples': 7453184, 'steps': 14556, 'batch_loss/train': 0.6728684189729393}
+12/24/2021 21:29:39 - INFO - codeparrot_training - Step 14557: {'lr': 0.0004040630036348805, 'samples': 7453696, 'steps': 14557, 'batch_loss/train': 0.7551039564423263}
+12/24/2021 21:29:50 - INFO - codeparrot_training - Step 14558: {'lr': 0.0004040505890877628, 'samples': 7454208, 'steps': 14558, 'batch_loss/train': 0.7986617586575449}
+12/24/2021 21:30:00 - INFO - codeparrot_training - Step 14559: {'lr': 0.0004040381739281981, 'samples': 7454720, 'steps': 14559, 'batch_loss/train': 0.824303669272922}
+12/24/2021 21:30:12 - INFO - codeparrot_training - Step 14560: {'lr': 0.0004040257581562358, 'samples': 7455232, 'steps': 14560, 'batch_loss/train': 0.7590979798696935}
+12/24/2021 21:30:23 - INFO - codeparrot_training - Step 14561: {'lr': 0.00040401334177192516, 'samples': 7455744, 'steps': 14561, 'batch_loss/train': 0.7899989051511511}
+12/24/2021 21:30:34 - INFO - codeparrot_training - Step 14562: {'lr': 0.0004040009247753157, 'samples': 7456256, 'steps': 14562, 'batch_loss/train': 0.760648949071765}
+12/24/2021 21:30:44 - INFO - codeparrot_training - Step 14563: {'lr': 0.00040398850716645676, 'samples': 7456768, 'steps': 14563, 'batch_loss/train': 0.8485035374760628}
+12/24/2021 21:30:56 - INFO - codeparrot_training - Step 14564: {'lr': 0.00040397608894539755, 'samples': 7457280, 'steps': 14564, 'batch_loss/train': 0.8137924997135997}
+12/24/2021 21:31:07 - INFO - codeparrot_training - Step 14565: {'lr': 0.0004039636701121876, 'samples': 7457792, 'steps': 14565, 'batch_loss/train': 0.8754673525691032}
+12/24/2021 21:31:18 - INFO - codeparrot_training - Step 14566: {'lr': 0.00040395125066687625, 'samples': 7458304, 'steps': 14566, 'batch_loss/train': 0.8997135902754962}
+12/24/2021 21:31:32 - INFO - codeparrot_training - Step 14567: {'lr': 0.0004039388306095128, 'samples': 7458816, 'steps': 14567, 'batch_loss/train': 0.8499926966615021}
+12/24/2021 21:31:42 - INFO - codeparrot_training - Step 14568: {'lr': 0.00040392640994014675, 'samples': 7459328, 'steps': 14568, 'batch_loss/train': 0.8714629160240293}
+12/24/2021 21:31:53 - INFO - codeparrot_training - Step 14569: {'lr': 0.0004039139886588274, 'samples': 7459840, 'steps': 14569, 'batch_loss/train': 0.9056868515908718}
+12/24/2021 21:32:05 - INFO - codeparrot_training - Step 14570: {'lr': 0.0004039015667656041, 'samples': 7460352, 'steps': 14570, 'batch_loss/train': 0.8453264003619552}
+12/24/2021 21:32:16 - INFO - codeparrot_training - Step 14571: {'lr': 0.00040388914426052637, 'samples': 7460864, 'steps': 14571, 'batch_loss/train': 0.716292129131034}
+12/24/2021 21:32:26 - INFO - codeparrot_training - Step 14572: {'lr': 0.0004038767211436434, 'samples': 7461376, 'steps': 14572, 'batch_loss/train': 0.8655237276107073}
+12/24/2021 21:32:37 - INFO - codeparrot_training - Step 14573: {'lr': 0.00040386429741500477, 'samples': 7461888, 'steps': 14573, 'batch_loss/train': 0.8225331245921552}
+12/24/2021 21:32:51 - INFO - codeparrot_training - Step 14574: {'lr': 0.00040385187307465976, 'samples': 7462400, 'steps': 14574, 'batch_loss/train': 0.9576403154060245}
+12/24/2021 21:33:01 - INFO - codeparrot_training - Step 14575: {'lr': 0.0004038394481226578, 'samples': 7462912, 'steps': 14575, 'batch_loss/train': 0.8233979064971209}
+12/24/2021 21:33:12 - INFO - codeparrot_training - Step 14576: {'lr': 0.00040382702255904827, 'samples': 7463424, 'steps': 14576, 'batch_loss/train': 0.7850408768281341}
+12/24/2021 21:33:24 - INFO - codeparrot_training - Step 14577: {'lr': 0.00040381459638388065, 'samples': 7463936, 'steps': 14577, 'batch_loss/train': 0.7895810091868043}
+12/24/2021 21:33:34 - INFO - codeparrot_training - Step 14578: {'lr': 0.00040380216959720415, 'samples': 7464448, 'steps': 14578, 'batch_loss/train': 0.7064187587238848}
+12/24/2021 21:33:45 - INFO - codeparrot_training - Step 14579: {'lr': 0.00040378974219906836, 'samples': 7464960, 'steps': 14579, 'batch_loss/train': 0.8725610454566777}
+12/24/2021 21:33:57 - INFO - codeparrot_training - Step 14580: {'lr': 0.0004037773141895226, 'samples': 7465472, 'steps': 14580, 'batch_loss/train': 0.8897393238730729}
+12/24/2021 21:34:08 - INFO - codeparrot_training - Step 14581: {'lr': 0.00040376488556861635, 'samples': 7465984, 'steps': 14581, 'batch_loss/train': 0.8103339613880962}
+12/24/2021 21:34:18 - INFO - codeparrot_training - Step 14582: {'lr': 0.00040375245633639896, 'samples': 7466496, 'steps': 14582, 'batch_loss/train': 0.8898217019159347}
+12/24/2021 21:34:29 - INFO - codeparrot_training - Step 14583: {'lr': 0.00040374002649291987, 'samples': 7467008, 'steps': 14583, 'batch_loss/train': 0.7659333236515522}
+12/24/2021 21:34:43 - INFO - codeparrot_training - Step 14584: {'lr': 0.0004037275960382285, 'samples': 7467520, 'steps': 14584, 'batch_loss/train': 0.701867675408721}
+12/24/2021 21:34:53 - INFO - codeparrot_training - Step 14585: {'lr': 0.00040371516497237416, 'samples': 7468032, 'steps': 14585, 'batch_loss/train': 0.7863708473742008}
+12/24/2021 21:35:04 - INFO - codeparrot_training - Step 14586: {'lr': 0.0004037027332954064, 'samples': 7468544, 'steps': 14586, 'batch_loss/train': 0.8043652372434735}
+12/24/2021 21:35:16 - INFO - codeparrot_training - Step 14587: {'lr': 0.00040369030100737463, 'samples': 7469056, 'steps': 14587, 'batch_loss/train': 0.7700865329243243}
+12/24/2021 21:35:27 - INFO - codeparrot_training - Step 14588: {'lr': 0.0004036778681083283, 'samples': 7469568, 'steps': 14588, 'batch_loss/train': 0.7773967040702701}
+12/24/2021 21:35:38 - INFO - codeparrot_training - Step 14589: {'lr': 0.00040366543459831674, 'samples': 7470080, 'steps': 14589, 'batch_loss/train': 0.6707971030846238}
+12/24/2021 21:35:50 - INFO - codeparrot_training - Step 14590: {'lr': 0.00040365300047738947, 'samples': 7470592, 'steps': 14590, 'batch_loss/train': 0.8184917871840298}
+12/24/2021 21:36:00 - INFO - codeparrot_training - Step 14591: {'lr': 0.0004036405657455958, 'samples': 7471104, 'steps': 14591, 'batch_loss/train': 0.8367636390030384}
+12/24/2021 21:36:11 - INFO - codeparrot_training - Step 14592: {'lr': 0.00040362813040298534, 'samples': 7471616, 'steps': 14592, 'batch_loss/train': 0.8385505238547921}
+12/24/2021 21:36:21 - INFO - codeparrot_training - Step 14593: {'lr': 0.0004036156944496074, 'samples': 7472128, 'steps': 14593, 'batch_loss/train': 0.8278913744725287}
+12/24/2021 21:36:33 - INFO - codeparrot_training - Step 14594: {'lr': 0.00040360325788551144, 'samples': 7472640, 'steps': 14594, 'batch_loss/train': 0.8313835365697742}
+12/24/2021 21:36:44 - INFO - codeparrot_training - Step 14595: {'lr': 0.00040359082071074703, 'samples': 7473152, 'steps': 14595, 'batch_loss/train': 0.8190669601899572}
+12/24/2021 21:36:55 - INFO - codeparrot_training - Step 14596: {'lr': 0.00040357838292536343, 'samples': 7473664, 'steps': 14596, 'batch_loss/train': 0.7751601226627827}
+12/24/2021 21:37:08 - INFO - codeparrot_training - Step 14597: {'lr': 0.0004035659445294102, 'samples': 7474176, 'steps': 14597, 'batch_loss/train': 0.8301773127168417}
+12/24/2021 21:37:19 - INFO - codeparrot_training - Step 14598: {'lr': 0.0004035535055229367, 'samples': 7474688, 'steps': 14598, 'batch_loss/train': 0.7630405388772488}
+12/24/2021 21:37:30 - INFO - codeparrot_training - Step 14599: {'lr': 0.0004035410659059925, 'samples': 7475200, 'steps': 14599, 'batch_loss/train': 0.7815540349110961}
+12/24/2021 21:37:42 - INFO - codeparrot_training - Step 14600: {'lr': 0.0004035286256786269, 'samples': 7475712, 'steps': 14600, 'batch_loss/train': 0.7653406602330506}
+12/24/2021 21:37:52 - INFO - codeparrot_training - Step 14601: {'lr': 0.0004035161848408896, 'samples': 7476224, 'steps': 14601, 'batch_loss/train': 0.7147982083261013}
+12/24/2021 21:38:03 - INFO - codeparrot_training - Step 14602: {'lr': 0.0004035037433928298, 'samples': 7476736, 'steps': 14602, 'batch_loss/train': 0.912590678781271}
+12/24/2021 21:38:13 - INFO - codeparrot_training - Step 14603: {'lr': 0.0004034913013344972, 'samples': 7477248, 'steps': 14603, 'batch_loss/train': 0.8001081068068743}
+12/24/2021 21:38:27 - INFO - codeparrot_training - Step 14604: {'lr': 0.000403478858665941, 'samples': 7477760, 'steps': 14604, 'batch_loss/train': 0.7987002303125337}
+12/24/2021 21:38:38 - INFO - codeparrot_training - Step 14605: {'lr': 0.0004034664153872109, 'samples': 7478272, 'steps': 14605, 'batch_loss/train': 0.8290638970211148}
+12/24/2021 21:38:49 - INFO - codeparrot_training - Step 14606: {'lr': 0.0004034539714983563, 'samples': 7478784, 'steps': 14606, 'batch_loss/train': 0.7457584007643163}
+12/24/2021 21:39:01 - INFO - codeparrot_training - Step 14607: {'lr': 0.00040344152699942656, 'samples': 7479296, 'steps': 14607, 'batch_loss/train': 0.7755988594144583}
+12/24/2021 21:39:12 - INFO - codeparrot_training - Step 14608: {'lr': 0.0004034290818904713, 'samples': 7479808, 'steps': 14608, 'batch_loss/train': 0.7539607470389456}
+12/24/2021 21:39:22 - INFO - codeparrot_training - Step 14609: {'lr': 0.0004034166361715399, 'samples': 7480320, 'steps': 14609, 'batch_loss/train': 0.8808780759572983}
+12/24/2021 21:39:34 - INFO - codeparrot_training - Step 14610: {'lr': 0.0004034041898426819, 'samples': 7480832, 'steps': 14610, 'batch_loss/train': 0.8753639664500952}
+12/24/2021 21:39:45 - INFO - codeparrot_training - Step 14611: {'lr': 0.00040339174290394676, 'samples': 7481344, 'steps': 14611, 'batch_loss/train': 0.7702323636040092}
+12/24/2021 21:39:56 - INFO - codeparrot_training - Step 14612: {'lr': 0.000403379295355384, 'samples': 7481856, 'steps': 14612, 'batch_loss/train': 0.9027400254271924}
+12/24/2021 21:40:06 - INFO - codeparrot_training - Step 14613: {'lr': 0.0004033668471970431, 'samples': 7482368, 'steps': 14613, 'batch_loss/train': 0.7685903124511242}
+12/24/2021 21:40:20 - INFO - codeparrot_training - Step 14614: {'lr': 0.0004033543984289735, 'samples': 7482880, 'steps': 14614, 'batch_loss/train': 0.7418541247025132}
+12/24/2021 21:40:31 - INFO - codeparrot_training - Step 14615: {'lr': 0.0004033419490512247, 'samples': 7483392, 'steps': 14615, 'batch_loss/train': 0.7779615707695484}
+12/24/2021 21:40:41 - INFO - codeparrot_training - Step 14616: {'lr': 0.0004033294990638462, 'samples': 7483904, 'steps': 14616, 'batch_loss/train': 0.9161662005353719}
+12/24/2021 21:40:54 - INFO - codeparrot_training - Step 14617: {'lr': 0.00040331704846688755, 'samples': 7484416, 'steps': 14617, 'batch_loss/train': 0.7740978267975152}
+12/24/2021 21:41:04 - INFO - codeparrot_training - Step 14618: {'lr': 0.00040330459726039815, 'samples': 7484928, 'steps': 14618, 'batch_loss/train': 0.6939873769879341}
+12/24/2021 21:41:15 - INFO - codeparrot_training - Step 14619: {'lr': 0.0004032921454444276, 'samples': 7485440, 'steps': 14619, 'batch_loss/train': 0.7895460072904825}
+12/24/2021 21:41:27 - INFO - codeparrot_training - Step 14620: {'lr': 0.00040327969301902534, 'samples': 7485952, 'steps': 14620, 'batch_loss/train': 0.8766858843155205}
+12/24/2021 21:41:38 - INFO - codeparrot_training - Step 14621: {'lr': 0.0004032672399842409, 'samples': 7486464, 'steps': 14621, 'batch_loss/train': 0.7995488932356238}
+12/24/2021 21:41:48 - INFO - codeparrot_training - Step 14622: {'lr': 0.00040325478634012374, 'samples': 7486976, 'steps': 14622, 'batch_loss/train': 0.8814340000972152}
+12/24/2021 21:41:59 - INFO - codeparrot_training - Step 14623: {'lr': 0.0004032423320867235, 'samples': 7487488, 'steps': 14623, 'batch_loss/train': 0.7904592324048281}
+12/24/2021 21:42:13 - INFO - codeparrot_training - Step 14624: {'lr': 0.00040322987722408955, 'samples': 7488000, 'steps': 14624, 'batch_loss/train': 0.7924273842945695}
+12/24/2021 21:42:24 - INFO - codeparrot_training - Step 14625: {'lr': 0.0004032174217522715, 'samples': 7488512, 'steps': 14625, 'batch_loss/train': 0.7049997246358544}
+12/24/2021 21:42:34 - INFO - codeparrot_training - Step 14626: {'lr': 0.00040320496567131884, 'samples': 7489024, 'steps': 14626, 'batch_loss/train': 0.8478294983506203}
+12/24/2021 21:42:46 - INFO - codeparrot_training - Step 14627: {'lr': 0.0004031925089812811, 'samples': 7489536, 'steps': 14627, 'batch_loss/train': 0.8927136786514893}
+12/24/2021 21:42:57 - INFO - codeparrot_training - Step 14628: {'lr': 0.0004031800516822077, 'samples': 7490048, 'steps': 14628, 'batch_loss/train': 0.7886912731919438}
+12/24/2021 21:43:07 - INFO - codeparrot_training - Step 14629: {'lr': 0.00040316759377414835, 'samples': 7490560, 'steps': 14629, 'batch_loss/train': 0.8446077187545598}
+12/24/2021 21:43:19 - INFO - codeparrot_training - Step 14630: {'lr': 0.0004031551352571524, 'samples': 7491072, 'steps': 14630, 'batch_loss/train': 0.7636511917226017}
+12/24/2021 21:43:30 - INFO - codeparrot_training - Step 14631: {'lr': 0.0004031426761312695, 'samples': 7491584, 'steps': 14631, 'batch_loss/train': 0.7932222243398428}
+12/24/2021 21:43:41 - INFO - codeparrot_training - Step 14632: {'lr': 0.00040313021639654914, 'samples': 7492096, 'steps': 14632, 'batch_loss/train': 0.8905920786783099}
+12/24/2021 21:43:51 - INFO - codeparrot_training - Step 14633: {'lr': 0.0004031177560530409, 'samples': 7492608, 'steps': 14633, 'batch_loss/train': 0.8923349380493164}
+12/24/2021 21:44:05 - INFO - codeparrot_training - Step 14634: {'lr': 0.0004031052951007942, 'samples': 7493120, 'steps': 14634, 'batch_loss/train': 0.8332614516839385}
+12/24/2021 21:44:16 - INFO - codeparrot_training - Step 14635: {'lr': 0.0004030928335398587, 'samples': 7493632, 'steps': 14635, 'batch_loss/train': 0.770465200766921}
+12/24/2021 21:44:26 - INFO - codeparrot_training - Step 14636: {'lr': 0.0004030803713702839, 'samples': 7494144, 'steps': 14636, 'batch_loss/train': 0.8384248511865735}
+12/24/2021 21:44:39 - INFO - codeparrot_training - Step 14637: {'lr': 0.00040306790859211936, 'samples': 7494656, 'steps': 14637, 'batch_loss/train': 0.7342606505844742}
+12/24/2021 21:44:49 - INFO - codeparrot_training - Step 14638: {'lr': 0.0004030554452054146, 'samples': 7495168, 'steps': 14638, 'batch_loss/train': 0.7777777884621173}
+12/24/2021 21:45:00 - INFO - codeparrot_training - Step 14639: {'lr': 0.00040304298121021914, 'samples': 7495680, 'steps': 14639, 'batch_loss/train': 0.6442889912286773}
+12/24/2021 21:45:12 - INFO - codeparrot_training - Step 14640: {'lr': 0.0004030305166065826, 'samples': 7496192, 'steps': 14640, 'batch_loss/train': 0.8641754714772105}
+12/24/2021 21:45:23 - INFO - codeparrot_training - Step 14641: {'lr': 0.0004030180513945545, 'samples': 7496704, 'steps': 14641, 'batch_loss/train': 0.776433426886797}
+12/24/2021 21:45:34 - INFO - codeparrot_training - Step 14642: {'lr': 0.0004030055855741845, 'samples': 7497216, 'steps': 14642, 'batch_loss/train': 2.4252782594412565}
+12/24/2021 21:45:44 - INFO - codeparrot_training - Step 14643: {'lr': 0.00040299311914552194, 'samples': 7497728, 'steps': 14643, 'batch_loss/train': 0.9243030790239573}
+12/24/2021 21:45:58 - INFO - codeparrot_training - Step 14644: {'lr': 0.00040298065210861656, 'samples': 7498240, 'steps': 14644, 'batch_loss/train': 0.7998006660491228}
+12/24/2021 21:46:09 - INFO - codeparrot_training - Step 14645: {'lr': 0.00040296818446351783, 'samples': 7498752, 'steps': 14645, 'batch_loss/train': 0.8106344761326909}
+12/24/2021 21:46:19 - INFO - codeparrot_training - Step 14646: {'lr': 0.00040295571621027537, 'samples': 7499264, 'steps': 14646, 'batch_loss/train': 0.8896235972642899}
+12/24/2021 21:46:31 - INFO - codeparrot_training - Step 14647: {'lr': 0.0004029432473489388, 'samples': 7499776, 'steps': 14647, 'batch_loss/train': 0.81540038716048}
+12/24/2021 21:46:42 - INFO - codeparrot_training - Step 14648: {'lr': 0.00040293077787955755, 'samples': 7500288, 'steps': 14648, 'batch_loss/train': 0.7576495683752}
+12/24/2021 21:46:53 - INFO - codeparrot_training - Step 14649: {'lr': 0.0004029183078021813, 'samples': 7500800, 'steps': 14649, 'batch_loss/train': 0.8076618192717433}
+12/24/2021 21:47:05 - INFO - codeparrot_training - Step 14650: {'lr': 0.0004029058371168596, 'samples': 7501312, 'steps': 14650, 'batch_loss/train': 0.8425707661081105}
+12/24/2021 21:47:15 - INFO - codeparrot_training - Step 14651: {'lr': 0.00040289336582364214, 'samples': 7501824, 'steps': 14651, 'batch_loss/train': 0.7769680125638843}
+12/24/2021 21:47:26 - INFO - codeparrot_training - Step 14652: {'lr': 0.0004028808939225782, 'samples': 7502336, 'steps': 14652, 'batch_loss/train': 0.8413285445421934}
+12/24/2021 21:47:37 - INFO - codeparrot_training - Step 14653: {'lr': 0.00040286842141371763, 'samples': 7502848, 'steps': 14653, 'batch_loss/train': 0.7409617621451616}
+12/24/2021 21:47:51 - INFO - codeparrot_training - Step 14654: {'lr': 0.0004028559482971099, 'samples': 7503360, 'steps': 14654, 'batch_loss/train': 0.8566116055008024}
+12/24/2021 21:48:01 - INFO - codeparrot_training - Step 14655: {'lr': 0.0004028434745728047, 'samples': 7503872, 'steps': 14655, 'batch_loss/train': 0.7707671616226435}
+12/24/2021 21:48:12 - INFO - codeparrot_training - Step 14656: {'lr': 0.00040283100024085153, 'samples': 7504384, 'steps': 14656, 'batch_loss/train': 0.7474158178083599}
+12/24/2021 21:48:24 - INFO - codeparrot_training - Step 14657: {'lr': 0.0004028185253013, 'samples': 7504896, 'steps': 14657, 'batch_loss/train': 0.7722333716228604}
+12/24/2021 21:48:35 - INFO - codeparrot_training - Step 14658: {'lr': 0.00040280604975419975, 'samples': 7505408, 'steps': 14658, 'batch_loss/train': 0.8418080592527986}
+12/24/2021 21:48:45 - INFO - codeparrot_training - Step 14659: {'lr': 0.0004027935735996003, 'samples': 7505920, 'steps': 14659, 'batch_loss/train': 0.8281535031273961}
+12/24/2021 21:48:59 - INFO - codeparrot_training - Step 14660: {'lr': 0.00040278109683755133, 'samples': 7506432, 'steps': 14660, 'batch_loss/train': 0.8595015809405595}
+12/24/2021 21:49:10 - INFO - codeparrot_training - Step 14661: {'lr': 0.0004027686194681023, 'samples': 7506944, 'steps': 14661, 'batch_loss/train': 0.832519329385832}
+12/24/2021 21:49:20 - INFO - codeparrot_training - Step 14662: {'lr': 0.0004027561414913031, 'samples': 7507456, 'steps': 14662, 'batch_loss/train': 0.8198362239636481}
+12/24/2021 21:49:31 - INFO - codeparrot_training - Step 14663: {'lr': 0.00040274366290720304, 'samples': 7507968, 'steps': 14663, 'batch_loss/train': 0.771451243199408}
+12/24/2021 21:49:43 - INFO - codeparrot_training - Step 14664: {'lr': 0.00040273118371585186, 'samples': 7508480, 'steps': 14664, 'batch_loss/train': 0.7829523887485266}
+12/24/2021 21:49:54 - INFO - codeparrot_training - Step 14665: {'lr': 0.0004027187039172992, 'samples': 7508992, 'steps': 14665, 'batch_loss/train': 0.7813259558752179}
+12/24/2021 21:50:04 - INFO - codeparrot_training - Step 14666: {'lr': 0.0004027062235115946, 'samples': 7509504, 'steps': 14666, 'batch_loss/train': 0.8141427123919129}
+12/24/2021 21:50:16 - INFO - codeparrot_training - Step 14667: {'lr': 0.00040269374249878774, 'samples': 7510016, 'steps': 14667, 'batch_loss/train': 1.1692237919196486}
+12/24/2021 21:50:27 - INFO - codeparrot_training - Step 14668: {'lr': 0.0004026812608789282, 'samples': 7510528, 'steps': 14668, 'batch_loss/train': 0.7247258508577943}
+12/24/2021 21:50:38 - INFO - codeparrot_training - Step 14669: {'lr': 0.00040266877865206564, 'samples': 7511040, 'steps': 14669, 'batch_loss/train': 0.78247433854267}
+12/24/2021 21:50:51 - INFO - codeparrot_training - Step 14670: {'lr': 0.00040265629581824966, 'samples': 7511552, 'steps': 14670, 'batch_loss/train': 0.9570004073902965}
+12/24/2021 21:51:02 - INFO - codeparrot_training - Step 14671: {'lr': 0.0004026438123775299, 'samples': 7512064, 'steps': 14671, 'batch_loss/train': 0.7685965381097049}
+12/24/2021 21:51:12 - INFO - codeparrot_training - Step 14672: {'lr': 0.0004026313283299559, 'samples': 7512576, 'steps': 14672, 'batch_loss/train': 0.8519279453903437}
+12/24/2021 21:51:23 - INFO - codeparrot_training - Step 14673: {'lr': 0.00040261884367557747, 'samples': 7513088, 'steps': 14673, 'batch_loss/train': 0.8525078697130084}
+12/24/2021 21:51:35 - INFO - codeparrot_training - Step 14674: {'lr': 0.000402606358414444, 'samples': 7513600, 'steps': 14674, 'batch_loss/train': 0.7494188183918595}
+12/24/2021 21:51:46 - INFO - codeparrot_training - Step 14675: {'lr': 0.00040259387254660547, 'samples': 7514112, 'steps': 14675, 'batch_loss/train': 0.8471954734995961}
+12/24/2021 21:51:56 - INFO - codeparrot_training - Step 14676: {'lr': 0.0004025813860721112, 'samples': 7514624, 'steps': 14676, 'batch_loss/train': 0.8501309119164944}
+12/24/2021 21:52:08 - INFO - codeparrot_training - Step 14677: {'lr': 0.000402568898991011, 'samples': 7515136, 'steps': 14677, 'batch_loss/train': 0.8709222609177232}
+12/24/2021 21:52:19 - INFO - codeparrot_training - Step 14678: {'lr': 0.0004025564113033544, 'samples': 7515648, 'steps': 14678, 'batch_loss/train': 0.7778072720393538}
+12/24/2021 21:52:30 - INFO - codeparrot_training - Step 14679: {'lr': 0.00040254392300919116, 'samples': 7516160, 'steps': 14679, 'batch_loss/train': 0.8305049641057849}
+12/24/2021 21:52:42 - INFO - codeparrot_training - Step 14680: {'lr': 0.00040253143410857084, 'samples': 7516672, 'steps': 14680, 'batch_loss/train': 0.8162033329717815}
+12/24/2021 21:52:53 - INFO - codeparrot_training - Step 14681: {'lr': 0.00040251894460154313, 'samples': 7517184, 'steps': 14681, 'batch_loss/train': 0.8003407586365938}
+12/24/2021 21:53:03 - INFO - codeparrot_training - Step 14682: {'lr': 0.00040250645448815773, 'samples': 7517696, 'steps': 14682, 'batch_loss/train': 0.7438982841558754}
+12/24/2021 21:53:14 - INFO - codeparrot_training - Step 14683: {'lr': 0.00040249396376846426, 'samples': 7518208, 'steps': 14683, 'batch_loss/train': 1.2223894894123077}
+12/24/2021 21:53:28 - INFO - codeparrot_training - Step 14684: {'lr': 0.0004024814724425123, 'samples': 7518720, 'steps': 14684, 'batch_loss/train': 0.6957352580502629}
+12/24/2021 21:53:38 - INFO - codeparrot_training - Step 14685: {'lr': 0.00040246898051035163, 'samples': 7519232, 'steps': 14685, 'batch_loss/train': 0.6984557002433576}
+12/24/2021 21:53:49 - INFO - codeparrot_training - Step 14686: {'lr': 0.00040245648797203196, 'samples': 7519744, 'steps': 14686, 'batch_loss/train': 0.7833325816318393}
+12/24/2021 21:54:01 - INFO - codeparrot_training - Step 14687: {'lr': 0.00040244399482760267, 'samples': 7520256, 'steps': 14687, 'batch_loss/train': 0.8580555943772197}
+12/24/2021 21:54:12 - INFO - codeparrot_training - Step 14688: {'lr': 0.00040243150107711374, 'samples': 7520768, 'steps': 14688, 'batch_loss/train': 0.791399285197258}
+12/24/2021 21:54:22 - INFO - codeparrot_training - Step 14689: {'lr': 0.00040241900672061473, 'samples': 7521280, 'steps': 14689, 'batch_loss/train': 0.839608071371913}
+12/24/2021 21:54:36 - INFO - codeparrot_training - Step 14690: {'lr': 0.00040240651175815523, 'samples': 7521792, 'steps': 14690, 'batch_loss/train': 0.8449339848011732}
+12/24/2021 21:54:47 - INFO - codeparrot_training - Step 14691: {'lr': 0.000402394016189785, 'samples': 7522304, 'steps': 14691, 'batch_loss/train': 0.901790140196681}
+12/24/2021 21:54:57 - INFO - codeparrot_training - Step 14692: {'lr': 0.0004023815200155537, 'samples': 7522816, 'steps': 14692, 'batch_loss/train': 0.9180742623284459}
+12/24/2021 21:55:08 - INFO - codeparrot_training - Step 14693: {'lr': 0.00040236902323551103, 'samples': 7523328, 'steps': 14693, 'batch_loss/train': 0.7606714167632163}
+12/24/2021 21:55:20 - INFO - codeparrot_training - Step 14694: {'lr': 0.0004023565258497066, 'samples': 7523840, 'steps': 14694, 'batch_loss/train': 0.9124003704637289}
+12/24/2021 21:55:31 - INFO - codeparrot_training - Step 14695: {'lr': 0.00040234402785819026, 'samples': 7524352, 'steps': 14695, 'batch_loss/train': 0.8864890905097127}
+12/24/2021 21:55:41 - INFO - codeparrot_training - Step 14696: {'lr': 0.0004023315292610115, 'samples': 7524864, 'steps': 14696, 'batch_loss/train': 0.7856913227587938}
+12/24/2021 21:55:53 - INFO - codeparrot_training - Step 14697: {'lr': 0.0004023190300582201, 'samples': 7525376, 'steps': 14697, 'batch_loss/train': 0.8222546172328293}
+12/24/2021 21:56:04 - INFO - codeparrot_training - Step 14698: {'lr': 0.0004023065302498658, 'samples': 7525888, 'steps': 14698, 'batch_loss/train': 0.987383687403053}
+12/24/2021 21:56:15 - INFO - codeparrot_training - Step 14699: {'lr': 0.0004022940298359983, 'samples': 7526400, 'steps': 14699, 'batch_loss/train': 0.8651194218546152}
+12/24/2021 21:56:25 - INFO - codeparrot_training - Step 14700: {'lr': 0.00040228152881666715, 'samples': 7526912, 'steps': 14700, 'batch_loss/train': 0.8914685919880867}
+12/24/2021 21:56:40 - INFO - codeparrot_training - Step 14701: {'lr': 0.00040226902719192213, 'samples': 7527424, 'steps': 14701, 'batch_loss/train': 0.7007809979841113}
+12/24/2021 21:56:51 - INFO - codeparrot_training - Step 14702: {'lr': 0.000402256524961813, 'samples': 7527936, 'steps': 14702, 'batch_loss/train': 0.7637762001249939}
+12/24/2021 21:57:01 - INFO - codeparrot_training - Step 14703: {'lr': 0.0004022440221263894, 'samples': 7528448, 'steps': 14703, 'batch_loss/train': 1.6005335003137589}
+12/24/2021 21:57:13 - INFO - codeparrot_training - Step 14704: {'lr': 0.00040223151868570096, 'samples': 7528960, 'steps': 14704, 'batch_loss/train': 1.3203336261212826}
+12/24/2021 21:57:24 - INFO - codeparrot_training - Step 14705: {'lr': 0.0004022190146397976, 'samples': 7529472, 'steps': 14705, 'batch_loss/train': 0.8572336575016379}
+12/24/2021 21:57:35 - INFO - codeparrot_training - Step 14706: {'lr': 0.0004022065099887289, 'samples': 7529984, 'steps': 14706, 'batch_loss/train': 0.8424673723056912}
+12/24/2021 21:57:45 - INFO - codeparrot_training - Step 14707: {'lr': 0.0004021940047325445, 'samples': 7530496, 'steps': 14707, 'batch_loss/train': 0.8102518925443292}
+12/24/2021 21:57:59 - INFO - codeparrot_training - Step 14708: {'lr': 0.00040218149887129436, 'samples': 7531008, 'steps': 14708, 'batch_loss/train': 0.7859471691772342}
+12/24/2021 21:58:10 - INFO - codeparrot_training - Step 14709: {'lr': 0.0004021689924050279, 'samples': 7531520, 'steps': 14709, 'batch_loss/train': 0.9628745624795556}
+12/24/2021 21:58:20 - INFO - codeparrot_training - Step 14710: {'lr': 0.0004021564853337951, 'samples': 7532032, 'steps': 14710, 'batch_loss/train': 0.9495108285918832}
+12/24/2021 21:58:32 - INFO - codeparrot_training - Step 14711: {'lr': 0.0004021439776576454, 'samples': 7532544, 'steps': 14711, 'batch_loss/train': 0.9006870593875647}
+12/24/2021 21:58:43 - INFO - codeparrot_training - Step 14712: {'lr': 0.00040213146937662894, 'samples': 7533056, 'steps': 14712, 'batch_loss/train': 0.7905729562044144}
+12/24/2021 21:58:54 - INFO - codeparrot_training - Step 14713: {'lr': 0.000402118960490795, 'samples': 7533568, 'steps': 14713, 'batch_loss/train': 0.7598259625956416}
+12/24/2021 21:59:06 - INFO - codeparrot_training - Step 14714: {'lr': 0.00040210645100019363, 'samples': 7534080, 'steps': 14714, 'batch_loss/train': 0.8467762069776654}
+12/24/2021 21:59:16 - INFO - codeparrot_training - Step 14715: {'lr': 0.0004020939409048743, 'samples': 7534592, 'steps': 14715, 'batch_loss/train': 0.8124277796596289}
+12/24/2021 21:59:27 - INFO - codeparrot_training - Step 14716: {'lr': 0.000402081430204887, 'samples': 7535104, 'steps': 14716, 'batch_loss/train': 0.8355035055428743}
+12/24/2021 21:59:37 - INFO - codeparrot_training - Step 14717: {'lr': 0.0004020689189002813, 'samples': 7535616, 'steps': 14717, 'batch_loss/train': 0.8335599424317479}
+12/24/2021 21:59:50 - INFO - codeparrot_training - Step 14718: {'lr': 0.000402056406991107, 'samples': 7536128, 'steps': 14718, 'batch_loss/train': 0.8779905049595982}
+12/24/2021 22:00:00 - INFO - codeparrot_training - Step 14719: {'lr': 0.0004020438944774139, 'samples': 7536640, 'steps': 14719, 'batch_loss/train': 0.7282224111258984}
+12/24/2021 22:00:11 - INFO - codeparrot_training - Step 14720: {'lr': 0.00040203138135925165, 'samples': 7537152, 'steps': 14720, 'batch_loss/train': 0.718089078553021}
+12/24/2021 22:00:25 - INFO - codeparrot_training - Step 14721: {'lr': 0.00040201886763667006, 'samples': 7537664, 'steps': 14721, 'batch_loss/train': 0.9969516415148973}
+12/24/2021 22:00:36 - INFO - codeparrot_training - Step 14722: {'lr': 0.0004020063533097188, 'samples': 7538176, 'steps': 14722, 'batch_loss/train': 0.8725247969850898}
+12/24/2021 22:00:46 - INFO - codeparrot_training - Step 14723: {'lr': 0.00040199383837844773, 'samples': 7538688, 'steps': 14723, 'batch_loss/train': 0.744363805744797}
+12/24/2021 22:00:58 - INFO - codeparrot_training - Step 14724: {'lr': 0.00040198132284290653, 'samples': 7539200, 'steps': 14724, 'batch_loss/train': 0.8182488223537803}
+12/24/2021 22:01:09 - INFO - codeparrot_training - Step 14725: {'lr': 0.00040196880670314493, 'samples': 7539712, 'steps': 14725, 'batch_loss/train': 0.8497895654290915}
+12/24/2021 22:01:20 - INFO - codeparrot_training - Step 14726: {'lr': 0.0004019562899592128, 'samples': 7540224, 'steps': 14726, 'batch_loss/train': 0.8007540460675955}
+12/24/2021 22:01:30 - INFO - codeparrot_training - Step 14727: {'lr': 0.00040194377261115977, 'samples': 7540736, 'steps': 14727, 'batch_loss/train': 0.8043962195515633}
+12/24/2021 22:01:42 - INFO - codeparrot_training - Step 14728: {'lr': 0.00040193125465903573, 'samples': 7541248, 'steps': 14728, 'batch_loss/train': 0.7338452736148611}
+12/24/2021 22:01:53 - INFO - codeparrot_training - Step 14729: {'lr': 0.0004019187361028904, 'samples': 7541760, 'steps': 14729, 'batch_loss/train': 0.7572613246738911}
+12/24/2021 22:02:03 - INFO - codeparrot_training - Step 14730: {'lr': 0.00040190621694277353, 'samples': 7542272, 'steps': 14730, 'batch_loss/train': 0.8842874085530639}
+12/24/2021 22:02:17 - INFO - codeparrot_training - Step 14731: {'lr': 0.0004018936971787348, 'samples': 7542784, 'steps': 14731, 'batch_loss/train': 0.7325809765607119}
+12/24/2021 22:02:28 - INFO - codeparrot_training - Step 14732: {'lr': 0.0004018811768108242, 'samples': 7543296, 'steps': 14732, 'batch_loss/train': 0.6752582401968539}
+12/24/2021 22:02:38 - INFO - codeparrot_training - Step 14733: {'lr': 0.0004018686558390913, 'samples': 7543808, 'steps': 14733, 'batch_loss/train': 0.7781572537496686}
+12/24/2021 22:02:51 - INFO - codeparrot_training - Step 14734: {'lr': 0.00040185613426358606, 'samples': 7544320, 'steps': 14734, 'batch_loss/train': 0.928446221165359}
+12/24/2021 22:03:01 - INFO - codeparrot_training - Step 14735: {'lr': 0.0004018436120843581, 'samples': 7544832, 'steps': 14735, 'batch_loss/train': 0.7900923150591552}
+12/24/2021 22:03:12 - INFO - codeparrot_training - Step 14736: {'lr': 0.00040183108930145735, 'samples': 7545344, 'steps': 14736, 'batch_loss/train': 0.8397740502841771}
+12/24/2021 22:03:22 - INFO - codeparrot_training - Step 14737: {'lr': 0.0004018185659149334, 'samples': 7545856, 'steps': 14737, 'batch_loss/train': 0.8531016670167446}
+12/24/2021 22:03:36 - INFO - codeparrot_training - Step 14738: {'lr': 0.00040180604192483626, 'samples': 7546368, 'steps': 14738, 'batch_loss/train': 0.8185305339284241}
+12/24/2021 22:03:47 - INFO - codeparrot_training - Step 14739: {'lr': 0.00040179351733121563, 'samples': 7546880, 'steps': 14739, 'batch_loss/train': 0.7432420197874308}
+12/24/2021 22:03:57 - INFO - codeparrot_training - Step 14740: {'lr': 0.00040178099213412124, 'samples': 7547392, 'steps': 14740, 'batch_loss/train': 0.9690715614706278}
+12/24/2021 22:04:10 - INFO - codeparrot_training - Step 14741: {'lr': 0.00040176846633360286, 'samples': 7547904, 'steps': 14741, 'batch_loss/train': 0.7629574341699481}
+12/24/2021 22:04:20 - INFO - codeparrot_training - Step 14742: {'lr': 0.00040175593992971046, 'samples': 7548416, 'steps': 14742, 'batch_loss/train': 0.7295037524309009}
+12/24/2021 22:04:31 - INFO - codeparrot_training - Step 14743: {'lr': 0.0004017434129224937, 'samples': 7548928, 'steps': 14743, 'batch_loss/train': 0.7478513839887455}
+12/24/2021 22:04:43 - INFO - codeparrot_training - Step 14744: {'lr': 0.00040173088531200246, 'samples': 7549440, 'steps': 14744, 'batch_loss/train': 0.709140264429152}
+12/24/2021 22:04:54 - INFO - codeparrot_training - Step 14745: {'lr': 0.0004017183570982865, 'samples': 7549952, 'steps': 14745, 'batch_loss/train': 0.743111508898437}
+12/24/2021 22:05:04 - INFO - codeparrot_training - Step 14746: {'lr': 0.0004017058282813957, 'samples': 7550464, 'steps': 14746, 'batch_loss/train': 0.6991888168267906}
+12/24/2021 22:05:16 - INFO - codeparrot_training - Step 14747: {'lr': 0.0004016932988613797, 'samples': 7550976, 'steps': 14747, 'batch_loss/train': 0.8043817104771733}
+12/24/2021 22:05:27 - INFO - codeparrot_training - Step 14748: {'lr': 0.0004016807688382884, 'samples': 7551488, 'steps': 14748, 'batch_loss/train': 0.8419307917356491}
+12/24/2021 22:05:38 - INFO - codeparrot_training - Step 14749: {'lr': 0.0004016682382121718, 'samples': 7552000, 'steps': 14749, 'batch_loss/train': 0.7979575032368302}
+12/24/2021 22:05:48 - INFO - codeparrot_training - Step 14750: {'lr': 0.0004016557069830794, 'samples': 7552512, 'steps': 14750, 'batch_loss/train': 0.8107557399198413}
+12/24/2021 22:06:02 - INFO - codeparrot_training - Step 14751: {'lr': 0.00040164317515106133, 'samples': 7553024, 'steps': 14751, 'batch_loss/train': 0.8797395492438227}
+12/24/2021 22:06:13 - INFO - codeparrot_training - Step 14752: {'lr': 0.0004016306427161671, 'samples': 7553536, 'steps': 14752, 'batch_loss/train': 0.7289293417707086}
+12/24/2021 22:06:23 - INFO - codeparrot_training - Step 14753: {'lr': 0.0004016181096784467, 'samples': 7554048, 'steps': 14753, 'batch_loss/train': 0.8381202085874975}
+12/24/2021 22:06:35 - INFO - codeparrot_training - Step 14754: {'lr': 0.00040160557603795, 'samples': 7554560, 'steps': 14754, 'batch_loss/train': 0.7448510839603841}
+12/24/2021 22:06:46 - INFO - codeparrot_training - Step 14755: {'lr': 0.00040159304179472675, 'samples': 7555072, 'steps': 14755, 'batch_loss/train': 0.8684057397767901}
+12/24/2021 22:06:57 - INFO - codeparrot_training - Step 14756: {'lr': 0.0004015805069488268, 'samples': 7555584, 'steps': 14756, 'batch_loss/train': 0.9861093750223517}
+12/24/2021 22:07:09 - INFO - codeparrot_training - Step 14757: {'lr': 0.0004015679715003, 'samples': 7556096, 'steps': 14757, 'batch_loss/train': 0.7571808276697993}
+12/24/2021 22:07:19 - INFO - codeparrot_training - Step 14758: {'lr': 0.0004015554354491962, 'samples': 7556608, 'steps': 14758, 'batch_loss/train': 0.9296991126611829}
+12/24/2021 22:07:30 - INFO - codeparrot_training - Step 14759: {'lr': 0.00040154289879556517, 'samples': 7557120, 'steps': 14759, 'batch_loss/train': 0.6475030835717916}
+12/24/2021 22:07:40 - INFO - codeparrot_training - Step 14760: {'lr': 0.0004015303615394569, 'samples': 7557632, 'steps': 14760, 'batch_loss/train': 0.8902539489790797}
+12/24/2021 22:07:54 - INFO - codeparrot_training - Step 14761: {'lr': 0.00040151782368092094, 'samples': 7558144, 'steps': 14761, 'batch_loss/train': 0.7532916201744229}
+12/24/2021 22:08:05 - INFO - codeparrot_training - Step 14762: {'lr': 0.0004015052852200075, 'samples': 7558656, 'steps': 14762, 'batch_loss/train': 0.775721188634634}
+12/24/2021 22:08:16 - INFO - codeparrot_training - Step 14763: {'lr': 0.00040149274615676613, 'samples': 7559168, 'steps': 14763, 'batch_loss/train': 0.8039434894453734}
+12/24/2021 22:08:28 - INFO - codeparrot_training - Step 14764: {'lr': 0.0004014802064912469, 'samples': 7559680, 'steps': 14764, 'batch_loss/train': 0.7805453431792557}
+12/24/2021 22:08:39 - INFO - codeparrot_training - Step 14765: {'lr': 0.0004014676662234995, 'samples': 7560192, 'steps': 14765, 'batch_loss/train': 0.8478530710563064}
+12/24/2021 22:08:49 - INFO - codeparrot_training - Step 14766: {'lr': 0.00040145512535357387, 'samples': 7560704, 'steps': 14766, 'batch_loss/train': 0.7502506170421839}
+12/24/2021 22:09:03 - INFO - codeparrot_training - Step 14767: {'lr': 0.0004014425838815198, 'samples': 7561216, 'steps': 14767, 'batch_loss/train': 0.8349290792830288}
+12/24/2021 22:09:14 - INFO - codeparrot_training - Step 14768: {'lr': 0.0004014300418073873, 'samples': 7561728, 'steps': 14768, 'batch_loss/train': 0.8687594896182418}
+12/24/2021 22:09:24 - INFO - codeparrot_training - Step 14769: {'lr': 0.00040141749913122604, 'samples': 7562240, 'steps': 14769, 'batch_loss/train': 0.8419452169910073}
+12/24/2021 22:09:35 - INFO - codeparrot_training - Step 14770: {'lr': 0.000401404955853086, 'samples': 7562752, 'steps': 14770, 'batch_loss/train': 0.8517233012244105}
+12/24/2021 22:09:47 - INFO - codeparrot_training - Step 14771: {'lr': 0.00040139241197301715, 'samples': 7563264, 'steps': 14771, 'batch_loss/train': 0.8110721465200186}
+12/24/2021 22:09:57 - INFO - codeparrot_training - Step 14772: {'lr': 0.00040137986749106904, 'samples': 7563776, 'steps': 14772, 'batch_loss/train': 0.8260789783671498}
+12/24/2021 22:10:08 - INFO - codeparrot_training - Step 14773: {'lr': 0.00040136732240729186, 'samples': 7564288, 'steps': 14773, 'batch_loss/train': 0.6609376836568117}
+12/24/2021 22:10:20 - INFO - codeparrot_training - Step 14774: {'lr': 0.00040135477672173525, 'samples': 7564800, 'steps': 14774, 'batch_loss/train': 0.770225047133863}
+12/24/2021 22:10:31 - INFO - codeparrot_training - Step 14775: {'lr': 0.0004013422304344493, 'samples': 7565312, 'steps': 14775, 'batch_loss/train': 0.7926526321098208}
+12/24/2021 22:10:41 - INFO - codeparrot_training - Step 14776: {'lr': 0.00040132968354548374, 'samples': 7565824, 'steps': 14776, 'batch_loss/train': 0.7241932116448879}
+12/24/2021 22:10:55 - INFO - codeparrot_training - Step 14777: {'lr': 0.00040131713605488854, 'samples': 7566336, 'steps': 14777, 'batch_loss/train': 0.8546199640259147}
+12/24/2021 22:11:06 - INFO - codeparrot_training - Step 14778: {'lr': 0.0004013045879627135, 'samples': 7566848, 'steps': 14778, 'batch_loss/train': 0.8242675373330712}
+12/24/2021 22:11:16 - INFO - codeparrot_training - Step 14779: {'lr': 0.0004012920392690086, 'samples': 7567360, 'steps': 14779, 'batch_loss/train': 0.8311926331371069}
+12/24/2021 22:11:27 - INFO - codeparrot_training - Step 14780: {'lr': 0.00040127948997382355, 'samples': 7567872, 'steps': 14780, 'batch_loss/train': 0.8115632841363549}
+12/24/2021 22:11:39 - INFO - codeparrot_training - Step 14781: {'lr': 0.0004012669400772085, 'samples': 7568384, 'steps': 14781, 'batch_loss/train': 0.849894504994154}
+12/24/2021 22:11:50 - INFO - codeparrot_training - Step 14782: {'lr': 0.0004012543895792132, 'samples': 7568896, 'steps': 14782, 'batch_loss/train': 0.7833979772403836}
+12/24/2021 22:12:00 - INFO - codeparrot_training - Step 14783: {'lr': 0.0004012418384798875, 'samples': 7569408, 'steps': 14783, 'batch_loss/train': 0.979450412094593}
+12/24/2021 22:12:12 - INFO - codeparrot_training - Step 14784: {'lr': 0.0004012292867792814, 'samples': 7569920, 'steps': 14784, 'batch_loss/train': 0.8685245225206017}
+12/24/2021 22:12:23 - INFO - codeparrot_training - Step 14785: {'lr': 0.0004012167344774447, 'samples': 7570432, 'steps': 14785, 'batch_loss/train': 0.8927674684673548}
+12/24/2021 22:12:33 - INFO - codeparrot_training - Step 14786: {'lr': 0.0004012041815744275, 'samples': 7570944, 'steps': 14786, 'batch_loss/train': 0.9062859397381544}
+12/24/2021 22:12:46 - INFO - codeparrot_training - Step 14787: {'lr': 0.00040119162807027945, 'samples': 7571456, 'steps': 14787, 'batch_loss/train': 0.9237598236650229}
+12/24/2021 22:12:56 - INFO - codeparrot_training - Step 14788: {'lr': 0.0004011790739650506, 'samples': 7571968, 'steps': 14788, 'batch_loss/train': 0.7106257025152445}
+12/24/2021 22:13:07 - INFO - codeparrot_training - Step 14789: {'lr': 0.00040116651925879075, 'samples': 7572480, 'steps': 14789, 'batch_loss/train': 0.8307496686466038}
+12/24/2021 22:13:21 - INFO - codeparrot_training - Step 14790: {'lr': 0.00040115396395155, 'samples': 7572992, 'steps': 14790, 'batch_loss/train': 0.8290072530508041}
+12/24/2021 22:13:32 - INFO - codeparrot_training - Step 14791: {'lr': 0.00040114140804337815, 'samples': 7573504, 'steps': 14791, 'batch_loss/train': 0.8805717076174915}
+12/24/2021 22:13:42 - INFO - codeparrot_training - Step 14792: {'lr': 0.0004011288515343251, 'samples': 7574016, 'steps': 14792, 'batch_loss/train': 0.840916465036571}
+12/24/2021 22:13:53 - INFO - codeparrot_training - Step 14793: {'lr': 0.00040111629442444085, 'samples': 7574528, 'steps': 14793, 'batch_loss/train': 0.7815494351089001}
+12/24/2021 22:14:05 - INFO - codeparrot_training - Step 14794: {'lr': 0.00040110373671377526, 'samples': 7575040, 'steps': 14794, 'batch_loss/train': 0.8226264868862927}
+12/24/2021 22:14:16 - INFO - codeparrot_training - Step 14795: {'lr': 0.0004010911784023782, 'samples': 7575552, 'steps': 14795, 'batch_loss/train': 0.8212643876904622}
+12/24/2021 22:14:27 - INFO - codeparrot_training - Step 14796: {'lr': 0.0004010786194902998, 'samples': 7576064, 'steps': 14796, 'batch_loss/train': 0.8094999364111573}
+12/24/2021 22:14:39 - INFO - codeparrot_training - Step 14797: {'lr': 0.00040106605997758973, 'samples': 7576576, 'steps': 14797, 'batch_loss/train': 0.7515414047520608}
+12/24/2021 22:14:49 - INFO - codeparrot_training - Step 14798: {'lr': 0.0004010534998642981, 'samples': 7577088, 'steps': 14798, 'batch_loss/train': 0.8203367255628109}
+12/24/2021 22:15:00 - INFO - codeparrot_training - Step 14799: {'lr': 0.0004010409391504748, 'samples': 7577600, 'steps': 14799, 'batch_loss/train': 0.7644413465168327}
+12/24/2021 22:15:10 - INFO - codeparrot_training - Step 14800: {'lr': 0.0004010283778361697, 'samples': 7578112, 'steps': 14800, 'batch_loss/train': 0.8560554499272257}
+12/24/2021 22:15:24 - INFO - codeparrot_training - Step 14801: {'lr': 0.0004010158159214328, 'samples': 7578624, 'steps': 14801, 'batch_loss/train': 0.8593790698796511}
+12/24/2021 22:15:35 - INFO - codeparrot_training - Step 14802: {'lr': 0.0004010032534063141, 'samples': 7579136, 'steps': 14802, 'batch_loss/train': 0.7521167425438762}
+12/24/2021 22:15:46 - INFO - codeparrot_training - Step 14803: {'lr': 0.0004009906902908634, 'samples': 7579648, 'steps': 14803, 'batch_loss/train': 0.7800775719806552}
+12/24/2021 22:15:58 - INFO - codeparrot_training - Step 14804: {'lr': 0.0004009781265751308, 'samples': 7580160, 'steps': 14804, 'batch_loss/train': 0.7598210019059479}
+12/24/2021 22:16:08 - INFO - codeparrot_training - Step 14805: {'lr': 0.0004009655622591661, 'samples': 7580672, 'steps': 14805, 'batch_loss/train': 0.891825657337904}
+12/24/2021 22:16:19 - INFO - codeparrot_training - Step 14806: {'lr': 0.0004009529973430194, 'samples': 7581184, 'steps': 14806, 'batch_loss/train': 0.7223222032189369}
+12/24/2021 22:16:33 - INFO - codeparrot_training - Step 14807: {'lr': 0.00040094043182674056, 'samples': 7581696, 'steps': 14807, 'batch_loss/train': 0.8287630979903042}
+12/24/2021 22:16:43 - INFO - codeparrot_training - Step 14808: {'lr': 0.0004009278657103796, 'samples': 7582208, 'steps': 14808, 'batch_loss/train': 0.8132887948304415}
+12/24/2021 22:16:54 - INFO - codeparrot_training - Step 14809: {'lr': 0.00040091529899398637, 'samples': 7582720, 'steps': 14809, 'batch_loss/train': 1.4020000686869025}
+12/24/2021 22:17:04 - INFO - codeparrot_training - Step 14810: {'lr': 0.00040090273167761093, 'samples': 7583232, 'steps': 14810, 'batch_loss/train': 1.1368119465187192}
+12/24/2021 22:17:17 - INFO - codeparrot_training - Step 14811: {'lr': 0.0004008901637613032, 'samples': 7583744, 'steps': 14811, 'batch_loss/train': 0.7732313359156251}
+12/24/2021 22:17:27 - INFO - codeparrot_training - Step 14812: {'lr': 0.00040087759524511313, 'samples': 7584256, 'steps': 14812, 'batch_loss/train': 0.7297165528871119}
+12/24/2021 22:17:38 - INFO - codeparrot_training - Step 14813: {'lr': 0.00040086502612909073, 'samples': 7584768, 'steps': 14813, 'batch_loss/train': 0.8917263466864824}
+12/24/2021 22:17:50 - INFO - codeparrot_training - Step 14814: {'lr': 0.00040085245641328595, 'samples': 7585280, 'steps': 14814, 'batch_loss/train': 0.7104241019114852}
+12/24/2021 22:18:01 - INFO - codeparrot_training - Step 14815: {'lr': 0.0004008398860977487, 'samples': 7585792, 'steps': 14815, 'batch_loss/train': 0.8470465801656246}
+12/24/2021 22:18:12 - INFO - codeparrot_training - Step 14816: {'lr': 0.0004008273151825291, 'samples': 7586304, 'steps': 14816, 'batch_loss/train': 1.0927011175081134}
+12/24/2021 22:18:25 - INFO - codeparrot_training - Step 14817: {'lr': 0.000400814743667677, 'samples': 7586816, 'steps': 14817, 'batch_loss/train': 0.8689357065595686}
+12/24/2021 22:18:36 - INFO - codeparrot_training - Step 14818: {'lr': 0.00040080217155324244, 'samples': 7587328, 'steps': 14818, 'batch_loss/train': 0.7834439263679087}
+12/24/2021 22:18:47 - INFO - codeparrot_training - Step 14819: {'lr': 0.00040078959883927545, 'samples': 7587840, 'steps': 14819, 'batch_loss/train': 0.8272016411647201}
+12/24/2021 22:18:57 - INFO - codeparrot_training - Step 14820: {'lr': 0.00040077702552582587, 'samples': 7588352, 'steps': 14820, 'batch_loss/train': 0.7530165971256793}
+12/24/2021 22:19:09 - INFO - codeparrot_training - Step 14821: {'lr': 0.0004007644516129438, 'samples': 7588864, 'steps': 14821, 'batch_loss/train': 0.8085882337763906}
+12/24/2021 22:19:20 - INFO - codeparrot_training - Step 14822: {'lr': 0.00040075187710067917, 'samples': 7589376, 'steps': 14822, 'batch_loss/train': 0.9034493928775191}
+12/24/2021 22:19:31 - INFO - codeparrot_training - Step 14823: {'lr': 0.000400739301989082, 'samples': 7589888, 'steps': 14823, 'batch_loss/train': 0.7958934297785163}
+12/24/2021 22:19:44 - INFO - codeparrot_training - Step 14824: {'lr': 0.0004007267262782023, 'samples': 7590400, 'steps': 14824, 'batch_loss/train': 1.5059992801398039}
+12/24/2021 22:19:55 - INFO - codeparrot_training - Step 14825: {'lr': 0.00040071414996809007, 'samples': 7590912, 'steps': 14825, 'batch_loss/train': 0.8437318587675691}
+12/24/2021 22:20:06 - INFO - codeparrot_training - Step 14826: {'lr': 0.00040070157305879524, 'samples': 7591424, 'steps': 14826, 'batch_loss/train': 0.859690835699439}
+12/24/2021 22:20:18 - INFO - codeparrot_training - Step 14827: {'lr': 0.00040068899555036785, 'samples': 7591936, 'steps': 14827, 'batch_loss/train': 0.7792858814354986}
+12/24/2021 22:20:29 - INFO - codeparrot_training - Step 14828: {'lr': 0.000400676417442858, 'samples': 7592448, 'steps': 14828, 'batch_loss/train': 0.8596856170333922}
+12/24/2021 22:20:39 - INFO - codeparrot_training - Step 14829: {'lr': 0.00040066383873631553, 'samples': 7592960, 'steps': 14829, 'batch_loss/train': 0.8437265520915389}
+12/24/2021 22:20:50 - INFO - codeparrot_training - Step 14830: {'lr': 0.0004006512594307905, 'samples': 7593472, 'steps': 14830, 'batch_loss/train': 0.9952767066424713}
+12/24/2021 22:21:02 - INFO - codeparrot_training - Step 14831: {'lr': 0.000400638679526333, 'samples': 7593984, 'steps': 14831, 'batch_loss/train': 0.7796980463899672}
+12/24/2021 22:21:12 - INFO - codeparrot_training - Step 14832: {'lr': 0.000400626099022993, 'samples': 7594496, 'steps': 14832, 'batch_loss/train': 0.8017937773838639}
+12/24/2021 22:21:23 - INFO - codeparrot_training - Step 14833: {'lr': 0.00040061351792082046, 'samples': 7595008, 'steps': 14833, 'batch_loss/train': 0.7646425175480545}
+12/24/2021 22:21:35 - INFO - codeparrot_training - Step 14834: {'lr': 0.0004006009362198655, 'samples': 7595520, 'steps': 14834, 'batch_loss/train': 0.8063022396527231}
+12/24/2021 22:21:46 - INFO - codeparrot_training - Step 14835: {'lr': 0.000400588353920178, 'samples': 7596032, 'steps': 14835, 'batch_loss/train': 0.7533129518851638}
+12/24/2021 22:21:56 - INFO - codeparrot_training - Step 14836: {'lr': 0.0004005757710218082, 'samples': 7596544, 'steps': 14836, 'batch_loss/train': 0.7866422403603792}
+12/24/2021 22:22:10 - INFO - codeparrot_training - Step 14837: {'lr': 0.00040056318752480584, 'samples': 7597056, 'steps': 14837, 'batch_loss/train': 0.6565287751145661}
+12/24/2021 22:22:21 - INFO - codeparrot_training - Step 14838: {'lr': 0.0004005506034292212, 'samples': 7597568, 'steps': 14838, 'batch_loss/train': 0.9078730633482337}
+12/24/2021 22:22:32 - INFO - codeparrot_training - Step 14839: {'lr': 0.00040053801873510416, 'samples': 7598080, 'steps': 14839, 'batch_loss/train': 0.6661032875999808}
+12/24/2021 22:22:42 - INFO - codeparrot_training - Step 14840: {'lr': 0.0004005254334425048, 'samples': 7598592, 'steps': 14840, 'batch_loss/train': 0.8580302838236094}
+12/24/2021 22:22:54 - INFO - codeparrot_training - Step 14841: {'lr': 0.0004005128475514732, 'samples': 7599104, 'steps': 14841, 'batch_loss/train': 0.8213707860559225}
+12/24/2021 22:23:05 - INFO - codeparrot_training - Step 14842: {'lr': 0.00040050026106205926, 'samples': 7599616, 'steps': 14842, 'batch_loss/train': 0.8812612863257527}
+12/24/2021 22:23:15 - INFO - codeparrot_training - Step 14843: {'lr': 0.0004004876739743132, 'samples': 7600128, 'steps': 14843, 'batch_loss/train': 0.8590751877054572}
+12/24/2021 22:23:27 - INFO - codeparrot_training - Step 14844: {'lr': 0.0004004750862882849, 'samples': 7600640, 'steps': 14844, 'batch_loss/train': 0.7665859599364921}
+12/24/2021 22:23:38 - INFO - codeparrot_training - Step 14845: {'lr': 0.0004004624980040245, 'samples': 7601152, 'steps': 14845, 'batch_loss/train': 0.8229421116411686}
+12/24/2021 22:23:49 - INFO - codeparrot_training - Step 14846: {'lr': 0.00040044990912158204, 'samples': 7601664, 'steps': 14846, 'batch_loss/train': 0.730053863953799}
+12/24/2021 22:24:02 - INFO - codeparrot_training - Step 14847: {'lr': 0.00040043731964100747, 'samples': 7602176, 'steps': 14847, 'batch_loss/train': 0.8180617094039917}
+12/24/2021 22:24:13 - INFO - codeparrot_training - Step 14848: {'lr': 0.000400424729562351, 'samples': 7602688, 'steps': 14848, 'batch_loss/train': 0.7661726045189425}
+12/24/2021 22:24:24 - INFO - codeparrot_training - Step 14849: {'lr': 0.00040041213888566263, 'samples': 7603200, 'steps': 14849, 'batch_loss/train': 0.7981159146875143}
+12/24/2021 22:24:34 - INFO - codeparrot_training - Step 14850: {'lr': 0.00040039954761099226, 'samples': 7603712, 'steps': 14850, 'batch_loss/train': 0.7678952448768541}
+12/24/2021 22:24:46 - INFO - codeparrot_training - Step 14851: {'lr': 0.00040038695573839026, 'samples': 7604224, 'steps': 14851, 'batch_loss/train': 0.8113216292113066}
+12/24/2021 22:24:57 - INFO - codeparrot_training - Step 14852: {'lr': 0.0004003743632679063, 'samples': 7604736, 'steps': 14852, 'batch_loss/train': 0.7680471939966083}
+12/24/2021 22:25:07 - INFO - codeparrot_training - Step 14853: {'lr': 0.0004003617701995908, 'samples': 7605248, 'steps': 14853, 'batch_loss/train': 0.7215701953973621}
+12/24/2021 22:25:21 - INFO - codeparrot_training - Step 14854: {'lr': 0.0004003491765334937, 'samples': 7605760, 'steps': 14854, 'batch_loss/train': 0.6879022109205835}
+12/24/2021 22:25:32 - INFO - codeparrot_training - Step 14855: {'lr': 0.0004003365822696649, 'samples': 7606272, 'steps': 14855, 'batch_loss/train': 0.8165665538981557}
+12/24/2021 22:25:42 - INFO - codeparrot_training - Step 14856: {'lr': 0.0004003239874081547, 'samples': 7606784, 'steps': 14856, 'batch_loss/train': 0.8529785564169288}
+12/24/2021 22:25:54 - INFO - codeparrot_training - Step 14857: {'lr': 0.0004003113919490131, 'samples': 7607296, 'steps': 14857, 'batch_loss/train': 0.7673701131716371}
+12/24/2021 22:26:05 - INFO - codeparrot_training - Step 14858: {'lr': 0.0004002987958922901, 'samples': 7607808, 'steps': 14858, 'batch_loss/train': 0.8257623799145222}
+12/24/2021 22:26:15 - INFO - codeparrot_training - Step 14859: {'lr': 0.00040028619923803587, 'samples': 7608320, 'steps': 14859, 'batch_loss/train': 0.7897538165561855}
+12/24/2021 22:26:27 - INFO - codeparrot_training - Step 14860: {'lr': 0.0004002736019863005, 'samples': 7608832, 'steps': 14860, 'batch_loss/train': 0.8202797323465347}
+12/24/2021 22:26:38 - INFO - codeparrot_training - Step 14861: {'lr': 0.000400261004137134, 'samples': 7609344, 'steps': 14861, 'batch_loss/train': 0.8010152019560337}
+12/24/2021 22:26:48 - INFO - codeparrot_training - Step 14862: {'lr': 0.0004002484056905865, 'samples': 7609856, 'steps': 14862, 'batch_loss/train': 0.8140564800705761}
+12/24/2021 22:26:59 - INFO - codeparrot_training - Step 14863: {'lr': 0.000400235806646708, 'samples': 7610368, 'steps': 14863, 'batch_loss/train': 0.8490180997177958}
+12/24/2021 22:27:13 - INFO - codeparrot_training - Step 14864: {'lr': 0.0004002232070055488, 'samples': 7610880, 'steps': 14864, 'batch_loss/train': 0.7839597379788756}
+12/24/2021 22:27:24 - INFO - codeparrot_training - Step 14865: {'lr': 0.0004002106067671587, 'samples': 7611392, 'steps': 14865, 'batch_loss/train': 0.7881908644922078}
+12/24/2021 22:27:34 - INFO - codeparrot_training - Step 14866: {'lr': 0.000400198005931588, 'samples': 7611904, 'steps': 14866, 'batch_loss/train': 0.7450574864633381}
+12/24/2021 22:27:46 - INFO - codeparrot_training - Step 14867: {'lr': 0.00040018540449888676, 'samples': 7612416, 'steps': 14867, 'batch_loss/train': 0.7937466034200042}
+12/24/2021 22:27:57 - INFO - codeparrot_training - Step 14868: {'lr': 0.000400172802469105, 'samples': 7612928, 'steps': 14868, 'batch_loss/train': 0.7303532278165221}
+12/24/2021 22:28:07 - INFO - codeparrot_training - Step 14869: {'lr': 0.00040016019984229304, 'samples': 7613440, 'steps': 14869, 'batch_loss/train': 0.7804905446246266}
+12/24/2021 22:28:19 - INFO - codeparrot_training - Step 14870: {'lr': 0.00040014759661850065, 'samples': 7613952, 'steps': 14870, 'batch_loss/train': 0.8562190802767873}
+12/24/2021 22:28:30 - INFO - codeparrot_training - Step 14871: {'lr': 0.0004001349927977782, 'samples': 7614464, 'steps': 14871, 'batch_loss/train': 0.8433669060468674}
+12/24/2021 22:28:41 - INFO - codeparrot_training - Step 14872: {'lr': 0.00040012238838017566, 'samples': 7614976, 'steps': 14872, 'batch_loss/train': 0.8049775357358158}
+12/24/2021 22:28:51 - INFO - codeparrot_training - Step 14873: {'lr': 0.0004001097833657432, 'samples': 7615488, 'steps': 14873, 'batch_loss/train': 0.887266818434}
+12/24/2021 22:29:03 - INFO - codeparrot_training - Step 14874: {'lr': 0.0004000971777545309, 'samples': 7616000, 'steps': 14874, 'batch_loss/train': 0.7063533149193972}
+12/24/2021 22:29:14 - INFO - codeparrot_training - Step 14875: {'lr': 0.00040008457154658896, 'samples': 7616512, 'steps': 14875, 'batch_loss/train': 0.8169862143695354}
+12/24/2021 22:29:25 - INFO - codeparrot_training - Step 14876: {'lr': 0.0004000719647419674, 'samples': 7617024, 'steps': 14876, 'batch_loss/train': 0.802849605679512}
+12/24/2021 22:29:38 - INFO - codeparrot_training - Step 14877: {'lr': 0.00040005935734071634, 'samples': 7617536, 'steps': 14877, 'batch_loss/train': 0.7765915418276563}
+12/24/2021 22:29:49 - INFO - codeparrot_training - Step 14878: {'lr': 0.000400046749342886, 'samples': 7618048, 'steps': 14878, 'batch_loss/train': 0.8169589564204216}
+12/24/2021 22:30:00 - INFO - codeparrot_training - Step 14879: {'lr': 0.00040003414074852634, 'samples': 7618560, 'steps': 14879, 'batch_loss/train': 0.8262485032901168}
+12/24/2021 22:30:12 - INFO - codeparrot_training - Step 14880: {'lr': 0.00040002153155768765, 'samples': 7619072, 'steps': 14880, 'batch_loss/train': 0.7724743662402034}
+12/24/2021 22:30:22 - INFO - codeparrot_training - Step 14881: {'lr': 0.00040000892177042, 'samples': 7619584, 'steps': 14881, 'batch_loss/train': 0.8182650813832879}
+12/24/2021 22:30:33 - INFO - codeparrot_training - Step 14882: {'lr': 0.0003999963113867735, 'samples': 7620096, 'steps': 14882, 'batch_loss/train': 0.6956731197424233}
+12/24/2021 22:30:43 - INFO - codeparrot_training - Step 14883: {'lr': 0.00039998370040679834, 'samples': 7620608, 'steps': 14883, 'batch_loss/train': 0.8173117274418473}
+12/24/2021 22:30:57 - INFO - codeparrot_training - Step 14884: {'lr': 0.00039997108883054464, 'samples': 7621120, 'steps': 14884, 'batch_loss/train': 0.8768704673275352}
+12/24/2021 22:31:08 - INFO - codeparrot_training - Step 14885: {'lr': 0.0003999584766580624, 'samples': 7621632, 'steps': 14885, 'batch_loss/train': 0.8246625391766429}
+12/24/2021 22:31:18 - INFO - codeparrot_training - Step 14886: {'lr': 0.00039994586388940204, 'samples': 7622144, 'steps': 14886, 'batch_loss/train': 0.7943075348157436}
+12/24/2021 22:31:30 - INFO - codeparrot_training - Step 14887: {'lr': 0.00039993325052461336, 'samples': 7622656, 'steps': 14887, 'batch_loss/train': 0.7713945617433637}
+12/24/2021 22:31:41 - INFO - codeparrot_training - Step 14888: {'lr': 0.0003999206365637468, 'samples': 7623168, 'steps': 14888, 'batch_loss/train': 0.8313033310696483}
+12/24/2021 22:31:52 - INFO - codeparrot_training - Step 14889: {'lr': 0.0003999080220068524, 'samples': 7623680, 'steps': 14889, 'batch_loss/train': 0.7187997926957905}
+12/24/2021 22:32:04 - INFO - codeparrot_training - Step 14890: {'lr': 0.0003998954068539803, 'samples': 7624192, 'steps': 14890, 'batch_loss/train': 0.8642866935115308}
+12/24/2021 22:32:14 - INFO - codeparrot_training - Step 14891: {'lr': 0.00039988279110518066, 'samples': 7624704, 'steps': 14891, 'batch_loss/train': 0.7275898745283484}
+12/24/2021 22:32:25 - INFO - codeparrot_training - Step 14892: {'lr': 0.00039987017476050357, 'samples': 7625216, 'steps': 14892, 'batch_loss/train': 0.8561246804893017}
+12/24/2021 22:32:39 - INFO - codeparrot_training - Step 14893: {'lr': 0.00039985755781999933, 'samples': 7625728, 'steps': 14893, 'batch_loss/train': 0.8180895773693919}
+12/24/2021 22:32:49 - INFO - codeparrot_training - Step 14894: {'lr': 0.00039984494028371797, 'samples': 7626240, 'steps': 14894, 'batch_loss/train': 0.7310387641191483}
+12/24/2021 22:33:00 - INFO - codeparrot_training - Step 14895: {'lr': 0.0003998323221517098, 'samples': 7626752, 'steps': 14895, 'batch_loss/train': 0.8623589952476323}
+12/24/2021 22:33:10 - INFO - codeparrot_training - Step 14896: {'lr': 0.00039981970342402485, 'samples': 7627264, 'steps': 14896, 'batch_loss/train': 0.9010824132710695}
+12/24/2021 22:33:23 - INFO - codeparrot_training - Step 14897: {'lr': 0.00039980708410071333, 'samples': 7627776, 'steps': 14897, 'batch_loss/train': 0.9831913104280829}
+12/24/2021 22:33:34 - INFO - codeparrot_training - Step 14898: {'lr': 0.0003997944641818253, 'samples': 7628288, 'steps': 14898, 'batch_loss/train': 0.948082908289507}
+12/24/2021 22:33:44 - INFO - codeparrot_training - Step 14899: {'lr': 0.0003997818436674112, 'samples': 7628800, 'steps': 14899, 'batch_loss/train': 0.8376731583848596}
+12/24/2021 22:33:56 - INFO - codeparrot_training - Step 14900: {'lr': 0.00039976922255752093, 'samples': 7629312, 'steps': 14900, 'batch_loss/train': 0.8369915243238211}
+12/24/2021 22:34:07 - INFO - codeparrot_training - Step 14901: {'lr': 0.0003997566008522048, 'samples': 7629824, 'steps': 14901, 'batch_loss/train': 0.9597814227454364}
+12/24/2021 22:34:17 - INFO - codeparrot_training - Step 14902: {'lr': 0.000399743978551513, 'samples': 7630336, 'steps': 14902, 'batch_loss/train': 0.8145941118709743}
+12/24/2021 22:34:28 - INFO - codeparrot_training - Step 14903: {'lr': 0.0003997313556554957, 'samples': 7630848, 'steps': 14903, 'batch_loss/train': 0.7989378133788705}
+12/24/2021 22:34:42 - INFO - codeparrot_training - Step 14904: {'lr': 0.0003997187321642031, 'samples': 7631360, 'steps': 14904, 'batch_loss/train': 0.7855122238397598}
+12/24/2021 22:34:52 - INFO - codeparrot_training - Step 14905: {'lr': 0.00039970610807768525, 'samples': 7631872, 'steps': 14905, 'batch_loss/train': 0.8552204556763172}
+12/24/2021 22:35:03 - INFO - codeparrot_training - Step 14906: {'lr': 0.00039969348339599246, 'samples': 7632384, 'steps': 14906, 'batch_loss/train': 0.7772174868732691}
+12/24/2021 22:35:15 - INFO - codeparrot_training - Step 14907: {'lr': 0.00039968085811917497, 'samples': 7632896, 'steps': 14907, 'batch_loss/train': 0.8056781715713441}
+12/24/2021 22:35:26 - INFO - codeparrot_training - Step 14908: {'lr': 0.00039966823224728287, 'samples': 7633408, 'steps': 14908, 'batch_loss/train': 0.9317420329898596}
+12/24/2021 22:35:36 - INFO - codeparrot_training - Step 14909: {'lr': 0.0003996556057803664, 'samples': 7633920, 'steps': 14909, 'batch_loss/train': 0.7913907701149583}
+12/24/2021 22:35:48 - INFO - codeparrot_training - Step 14910: {'lr': 0.00039964297871847575, 'samples': 7634432, 'steps': 14910, 'batch_loss/train': 0.7517104977741838}
+12/24/2021 22:35:59 - INFO - codeparrot_training - Step 14911: {'lr': 0.00039963035106166107, 'samples': 7634944, 'steps': 14911, 'batch_loss/train': 0.9379186378791928}
+12/24/2021 22:36:10 - INFO - codeparrot_training - Step 14912: {'lr': 0.00039961772280997263, 'samples': 7635456, 'steps': 14912, 'batch_loss/train': 0.7479285253211856}
+12/24/2021 22:36:22 - INFO - codeparrot_training - Step 14913: {'lr': 0.0003996050939634607, 'samples': 7635968, 'steps': 14913, 'batch_loss/train': 0.840595243498683}
+12/24/2021 22:36:32 - INFO - codeparrot_training - Step 14914: {'lr': 0.00039959246452217533, 'samples': 7636480, 'steps': 14914, 'batch_loss/train': 0.8410772574134171}
+12/24/2021 22:36:43 - INFO - codeparrot_training - Step 14915: {'lr': 0.0003995798344861668, 'samples': 7636992, 'steps': 14915, 'batch_loss/train': 0.7583388611674309}
+12/24/2021 22:36:54 - INFO - codeparrot_training - Step 14916: {'lr': 0.00039956720385548526, 'samples': 7637504, 'steps': 14916, 'batch_loss/train': 0.7782814704114571}
+12/24/2021 22:37:07 - INFO - codeparrot_training - Step 14917: {'lr': 0.0003995545726301811, 'samples': 7638016, 'steps': 14917, 'batch_loss/train': 0.7786327949725091}
+12/24/2021 22:37:18 - INFO - codeparrot_training - Step 14918: {'lr': 0.00039954194081030445, 'samples': 7638528, 'steps': 14918, 'batch_loss/train': 0.8110890993848443}
+12/24/2021 22:37:29 - INFO - codeparrot_training - Step 14919: {'lr': 0.00039952930839590547, 'samples': 7639040, 'steps': 14919, 'batch_loss/train': 0.782548317569308}
+12/24/2021 22:37:41 - INFO - codeparrot_training - Step 14920: {'lr': 0.0003995166753870344, 'samples': 7639552, 'steps': 14920, 'batch_loss/train': 0.7225279211997986}
+12/24/2021 22:37:52 - INFO - codeparrot_training - Step 14921: {'lr': 0.0003995040417837415, 'samples': 7640064, 'steps': 14921, 'batch_loss/train': 0.7985578309744596}
+12/24/2021 22:38:02 - INFO - codeparrot_training - Step 14922: {'lr': 0.000399491407586077, 'samples': 7640576, 'steps': 14922, 'batch_loss/train': 0.8664869396016002}
+12/24/2021 22:38:16 - INFO - codeparrot_training - Step 14923: {'lr': 0.0003994787727940911, 'samples': 7641088, 'steps': 14923, 'batch_loss/train': 0.7197042619809508}
+12/24/2021 22:38:27 - INFO - codeparrot_training - Step 14924: {'lr': 0.000399466137407834, 'samples': 7641600, 'steps': 14924, 'batch_loss/train': 0.8584628775715828}
+12/24/2021 22:38:37 - INFO - codeparrot_training - Step 14925: {'lr': 0.00039945350142735604, 'samples': 7642112, 'steps': 14925, 'batch_loss/train': 0.7831713948398829}
+12/24/2021 22:38:48 - INFO - codeparrot_training - Step 14926: {'lr': 0.0003994408648527073, 'samples': 7642624, 'steps': 14926, 'batch_loss/train': 0.7987029626965523}
+12/24/2021 22:39:00 - INFO - codeparrot_training - Step 14927: {'lr': 0.0003994282276839382, 'samples': 7643136, 'steps': 14927, 'batch_loss/train': 0.9441551715135574}
+12/24/2021 22:39:11 - INFO - codeparrot_training - Step 14928: {'lr': 0.0003994155899210988, 'samples': 7643648, 'steps': 14928, 'batch_loss/train': 0.658662679605186}
+12/24/2021 22:39:21 - INFO - codeparrot_training - Step 14929: {'lr': 0.00039940295156423944, 'samples': 7644160, 'steps': 14929, 'batch_loss/train': 0.8753558411262929}
+12/24/2021 22:39:34 - INFO - codeparrot_training - Step 14930: {'lr': 0.00039939031261341043, 'samples': 7644672, 'steps': 14930, 'batch_loss/train': 0.8455679705366492}
+12/24/2021 22:39:44 - INFO - codeparrot_training - Step 14931: {'lr': 0.0003993776730686619, 'samples': 7645184, 'steps': 14931, 'batch_loss/train': 0.8144983602687716}
+12/24/2021 22:39:55 - INFO - codeparrot_training - Step 14932: {'lr': 0.00039936503293004416, 'samples': 7645696, 'steps': 14932, 'batch_loss/train': 0.5203846454387531}
+12/24/2021 22:40:08 - INFO - codeparrot_training - Step 14933: {'lr': 0.00039935239219760746, 'samples': 7646208, 'steps': 14933, 'batch_loss/train': 0.7989084664732218}
+12/24/2021 22:40:18 - INFO - codeparrot_training - Step 14934: {'lr': 0.0003993397508714021, 'samples': 7646720, 'steps': 14934, 'batch_loss/train': 0.7818194208666682}
+12/24/2021 22:40:29 - INFO - codeparrot_training - Step 14935: {'lr': 0.0003993271089514781, 'samples': 7647232, 'steps': 14935, 'batch_loss/train': 0.6784079452045262}
+12/24/2021 22:40:39 - INFO - codeparrot_training - Step 14936: {'lr': 0.00039931446643788604, 'samples': 7647744, 'steps': 14936, 'batch_loss/train': 0.7971495534293354}
+12/24/2021 22:40:54 - INFO - codeparrot_training - Step 14937: {'lr': 0.000399301823330676, 'samples': 7648256, 'steps': 14937, 'batch_loss/train': 0.8062593387439847}
+12/24/2021 22:41:05 - INFO - codeparrot_training - Step 14938: {'lr': 0.0003992891796298983, 'samples': 7648768, 'steps': 14938, 'batch_loss/train': 0.8546439072815701}
+12/24/2021 22:41:15 - INFO - codeparrot_training - Step 14939: {'lr': 0.00039927653533560316, 'samples': 7649280, 'steps': 14939, 'batch_loss/train': 0.7384168040007353}
+12/24/2021 22:41:27 - INFO - codeparrot_training - Step 14940: {'lr': 0.00039926389044784086, 'samples': 7649792, 'steps': 14940, 'batch_loss/train': 0.7761679757386446}
+12/24/2021 22:41:38 - INFO - codeparrot_training - Step 14941: {'lr': 0.00039925124496666175, 'samples': 7650304, 'steps': 14941, 'batch_loss/train': 0.8224639587569982}
+12/24/2021 22:41:49 - INFO - codeparrot_training - Step 14942: {'lr': 0.000399238598892116, 'samples': 7650816, 'steps': 14942, 'batch_loss/train': 0.7289525454398245}
+12/24/2021 22:42:03 - INFO - codeparrot_training - Step 14943: {'lr': 0.00039922595222425394, 'samples': 7651328, 'steps': 14943, 'batch_loss/train': 0.9488638639450073}
+12/24/2021 22:42:13 - INFO - codeparrot_training - Step 14944: {'lr': 0.0003992133049631259, 'samples': 7651840, 'steps': 14944, 'batch_loss/train': 0.886180782224983}
+12/24/2021 22:42:24 - INFO - codeparrot_training - Step 14945: {'lr': 0.00039920065710878205, 'samples': 7652352, 'steps': 14945, 'batch_loss/train': 0.6940825453493744}
+12/24/2021 22:42:34 - INFO - codeparrot_training - Step 14946: {'lr': 0.0003991880086612727, 'samples': 7652864, 'steps': 14946, 'batch_loss/train': 0.7763613378629088}
+12/24/2021 22:42:47 - INFO - codeparrot_training - Step 14947: {'lr': 0.00039917535962064824, 'samples': 7653376, 'steps': 14947, 'batch_loss/train': 0.7274105120450258}
+12/24/2021 22:42:58 - INFO - codeparrot_training - Step 14948: {'lr': 0.0003991627099869588, 'samples': 7653888, 'steps': 14948, 'batch_loss/train': 0.7751791313057765}
+12/24/2021 22:43:08 - INFO - codeparrot_training - Step 14949: {'lr': 0.00039915005976025477, 'samples': 7654400, 'steps': 14949, 'batch_loss/train': 1.1046269834041595}
+12/24/2021 22:43:20 - INFO - codeparrot_training - Step 14950: {'lr': 0.0003991374089405864, 'samples': 7654912, 'steps': 14950, 'batch_loss/train': 0.7606855486519635}
+12/24/2021 22:43:31 - INFO - codeparrot_training - Step 14951: {'lr': 0.000399124757528004, 'samples': 7655424, 'steps': 14951, 'batch_loss/train': 0.8064826531335711}
+12/24/2021 22:43:41 - INFO - codeparrot_training - Step 14952: {'lr': 0.00039911210552255795, 'samples': 7655936, 'steps': 14952, 'batch_loss/train': 0.7880838735727593}
+12/24/2021 22:43:55 - INFO - codeparrot_training - Step 14953: {'lr': 0.00039909945292429836, 'samples': 7656448, 'steps': 14953, 'batch_loss/train': 0.7198272217065096}
+12/24/2021 22:44:06 - INFO - codeparrot_training - Step 14954: {'lr': 0.0003990867997332758, 'samples': 7656960, 'steps': 14954, 'batch_loss/train': 0.8193459170870483}
+12/24/2021 22:44:17 - INFO - codeparrot_training - Step 14955: {'lr': 0.0003990741459495403, 'samples': 7657472, 'steps': 14955, 'batch_loss/train': 0.8289420870132744}
+12/24/2021 22:44:27 - INFO - codeparrot_training - Step 14956: {'lr': 0.00039906149157314225, 'samples': 7657984, 'steps': 14956, 'batch_loss/train': 0.9309912407770753}
+12/24/2021 22:44:39 - INFO - codeparrot_training - Step 14957: {'lr': 0.00039904883660413205, 'samples': 7658496, 'steps': 14957, 'batch_loss/train': 0.8533587232232094}
+12/24/2021 22:44:50 - INFO - codeparrot_training - Step 14958: {'lr': 0.00039903618104256, 'samples': 7659008, 'steps': 14958, 'batch_loss/train': 0.6924831725191325}
+12/24/2021 22:45:01 - INFO - codeparrot_training - Step 14959: {'lr': 0.00039902352488847625, 'samples': 7659520, 'steps': 14959, 'batch_loss/train': 0.9944223209749907}
+12/24/2021 22:45:13 - INFO - codeparrot_training - Step 14960: {'lr': 0.0003990108681419313, 'samples': 7660032, 'steps': 14960, 'batch_loss/train': 0.7691072570160031}
+12/24/2021 22:45:23 - INFO - codeparrot_training - Step 14961: {'lr': 0.0003989982108029754, 'samples': 7660544, 'steps': 14961, 'batch_loss/train': 0.8569365860894322}
+12/24/2021 22:45:34 - INFO - codeparrot_training - Step 14962: {'lr': 0.00039898555287165897, 'samples': 7661056, 'steps': 14962, 'batch_loss/train': 0.7216180141549557}
+12/24/2021 22:45:48 - INFO - codeparrot_training - Step 14963: {'lr': 0.0003989728943480321, 'samples': 7661568, 'steps': 14963, 'batch_loss/train': 0.8912443136796355}
+12/24/2021 22:45:58 - INFO - codeparrot_training - Step 14964: {'lr': 0.00039896023523214525, 'samples': 7662080, 'steps': 14964, 'batch_loss/train': 0.7967049318831414}
+12/24/2021 22:46:09 - INFO - codeparrot_training - Step 14965: {'lr': 0.0003989475755240488, 'samples': 7662592, 'steps': 14965, 'batch_loss/train': 0.835612652823329}
+12/24/2021 22:46:20 - INFO - codeparrot_training - Step 14966: {'lr': 0.000398934915223793, 'samples': 7663104, 'steps': 14966, 'batch_loss/train': 0.7750417930074036}
+12/24/2021 22:46:32 - INFO - codeparrot_training - Step 14967: {'lr': 0.00039892225433142827, 'samples': 7663616, 'steps': 14967, 'batch_loss/train': 0.8652515388093889}
+12/24/2021 22:46:42 - INFO - codeparrot_training - Step 14968: {'lr': 0.00039890959284700486, 'samples': 7664128, 'steps': 14968, 'batch_loss/train': 0.8014767728745937}
+12/24/2021 22:46:53 - INFO - codeparrot_training - Step 14969: {'lr': 0.0003988969307705731, 'samples': 7664640, 'steps': 14969, 'batch_loss/train': 0.8777642250061035}
+12/24/2021 22:47:05 - INFO - codeparrot_training - Step 14970: {'lr': 0.0003988842681021834, 'samples': 7665152, 'steps': 14970, 'batch_loss/train': 0.8367453264072537}
+12/24/2021 22:47:16 - INFO - codeparrot_training - Step 14971: {'lr': 0.0003988716048418861, 'samples': 7665664, 'steps': 14971, 'batch_loss/train': 0.8290500291623175}
+12/24/2021 22:47:26 - INFO - codeparrot_training - Step 14972: {'lr': 0.00039885894098973143, 'samples': 7666176, 'steps': 14972, 'batch_loss/train': 0.7725702449679375}
+12/24/2021 22:47:40 - INFO - codeparrot_training - Step 14973: {'lr': 0.00039884627654576985, 'samples': 7666688, 'steps': 14973, 'batch_loss/train': 0.8569014258682728}
+12/24/2021 22:47:51 - INFO - codeparrot_training - Step 14974: {'lr': 0.0003988336115100517, 'samples': 7667200, 'steps': 14974, 'batch_loss/train': 0.8242682134732604}
+12/24/2021 22:48:01 - INFO - codeparrot_training - Step 14975: {'lr': 0.0003988209458826273, 'samples': 7667712, 'steps': 14975, 'batch_loss/train': 0.8479360193014145}
+12/24/2021 22:48:12 - INFO - codeparrot_training - Step 14976: {'lr': 0.00039880827966354705, 'samples': 7668224, 'steps': 14976, 'batch_loss/train': 0.7561071803793311}
+12/24/2021 22:48:24 - INFO - codeparrot_training - Step 14977: {'lr': 0.00039879561285286114, 'samples': 7668736, 'steps': 14977, 'batch_loss/train': 0.8227624869905412}
+12/24/2021 22:48:35 - INFO - codeparrot_training - Step 14978: {'lr': 0.0003987829454506202, 'samples': 7669248, 'steps': 14978, 'batch_loss/train': 0.8530326834879816}
+12/24/2021 22:48:45 - INFO - codeparrot_training - Step 14979: {'lr': 0.0003987702774568743, 'samples': 7669760, 'steps': 14979, 'batch_loss/train': 0.8644650019705296}
+12/24/2021 22:48:57 - INFO - codeparrot_training - Step 14980: {'lr': 0.0003987576088716741, 'samples': 7670272, 'steps': 14980, 'batch_loss/train': 0.8709141761064529}
+12/24/2021 22:49:08 - INFO - codeparrot_training - Step 14981: {'lr': 0.0003987449396950698, 'samples': 7670784, 'steps': 14981, 'batch_loss/train': 0.8841860480606556}
+12/24/2021 22:49:19 - INFO - codeparrot_training - Step 14982: {'lr': 0.0003987322699271117, 'samples': 7671296, 'steps': 14982, 'batch_loss/train': 0.839030846953392}
+12/24/2021 22:49:33 - INFO - codeparrot_training - Step 14983: {'lr': 0.0003987195995678503, 'samples': 7671808, 'steps': 14983, 'batch_loss/train': 0.8072294876910746}
+12/24/2021 22:49:43 - INFO - codeparrot_training - Step 14984: {'lr': 0.00039870692861733594, 'samples': 7672320, 'steps': 14984, 'batch_loss/train': 0.6850467405747622}
+12/24/2021 22:49:54 - INFO - codeparrot_training - Step 14985: {'lr': 0.0003986942570756189, 'samples': 7672832, 'steps': 14985, 'batch_loss/train': 0.7369942953810096}
+12/24/2021 22:50:05 - INFO - codeparrot_training - Step 14986: {'lr': 0.00039868158494274974, 'samples': 7673344, 'steps': 14986, 'batch_loss/train': 0.8134306538850069}
+12/24/2021 22:50:17 - INFO - codeparrot_training - Step 14987: {'lr': 0.0003986689122187787, 'samples': 7673856, 'steps': 14987, 'batch_loss/train': 0.8122547334060073}
+12/24/2021 22:50:27 - INFO - codeparrot_training - Step 14988: {'lr': 0.0003986562389037562, 'samples': 7674368, 'steps': 14988, 'batch_loss/train': 0.966645794454962}
+12/24/2021 22:50:38 - INFO - codeparrot_training - Step 14989: {'lr': 0.0003986435649977326, 'samples': 7674880, 'steps': 14989, 'batch_loss/train': 0.49386740755289793}
+12/24/2021 22:50:50 - INFO - codeparrot_training - Step 14990: {'lr': 0.0003986308905007583, 'samples': 7675392, 'steps': 14990, 'batch_loss/train': 0.7801290457136929}
+12/24/2021 22:51:01 - INFO - codeparrot_training - Step 14991: {'lr': 0.00039861821541288376, 'samples': 7675904, 'steps': 14991, 'batch_loss/train': 0.8083182186819613}
+12/24/2021 22:51:11 - INFO - codeparrot_training - Step 14992: {'lr': 0.00039860553973415923, 'samples': 7676416, 'steps': 14992, 'batch_loss/train': 0.8115547096822411}
+12/24/2021 22:51:25 - INFO - codeparrot_training - Step 14993: {'lr': 0.0003985928634646353, 'samples': 7676928, 'steps': 14993, 'batch_loss/train': 0.9199220193549991}
+12/24/2021 22:51:36 - INFO - codeparrot_training - Step 14994: {'lr': 0.00039858018660436217, 'samples': 7677440, 'steps': 14994, 'batch_loss/train': 0.8914810419082642}
+12/24/2021 22:51:47 - INFO - codeparrot_training - Step 14995: {'lr': 0.00039856750915339036, 'samples': 7677952, 'steps': 14995, 'batch_loss/train': 0.7796540134586394}
+12/24/2021 22:51:57 - INFO - codeparrot_training - Step 14996: {'lr': 0.0003985548311117702, 'samples': 7678464, 'steps': 14996, 'batch_loss/train': 0.9431326556950808}
+12/24/2021 22:52:09 - INFO - codeparrot_training - Step 14997: {'lr': 0.00039854215247955214, 'samples': 7678976, 'steps': 14997, 'batch_loss/train': 0.8029667832888663}
+12/24/2021 22:52:20 - INFO - codeparrot_training - Step 14998: {'lr': 0.0003985294732567866, 'samples': 7679488, 'steps': 14998, 'batch_loss/train': 0.8013834027806297}
+12/24/2021 22:52:30 - INFO - codeparrot_training - Step 14999: {'lr': 0.00039851679344352385, 'samples': 7680000, 'steps': 14999, 'batch_loss/train': 0.8290996924042702}
+12/24/2021 22:52:30 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+12/24/2021 22:55:51 - INFO - codeparrot_training - Step 15000: {'loss/eval': 0.8110089898109436, 'perplexity': 2.2501771450042725}