diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -32567,3 +32567,2506 @@ Use FP16 precision: False
 12/26/2021 22:02:02 - INFO - codeparrot_training - Step 29999: {'lr': 0.00017381092781912783, 'samples': 15360000, 'steps': 29999, 'batch_loss/train': 0.6627156580798328}
 12/26/2021 22:02:02 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/26/2021 22:05:23 - INFO - codeparrot_training - Step 30000: {'loss/eval': 0.7671898603439331, 'perplexity': 2.153705596923828}
+12/26/2021 22:05:41 - WARNING - huggingface_hub.repository - Several commits (10) will be pushed upstream.
+12/26/2021 22:05:54 - INFO - codeparrot_training - Step 30000: {'lr': 0.000173795914682856, 'samples': 15360512, 'steps': 30000, 'batch_loss/train': 0.6741299910936505}
+12/26/2021 22:06:05 - INFO - codeparrot_training - Step 30001: {'lr': 0.00017378090184954275, 'samples': 15361024, 'steps': 30001, 'batch_loss/train': 0.734086737036705}
+12/26/2021 22:06:19 - INFO - codeparrot_training - Step 30002: {'lr': 0.000173765889319248, 'samples': 15361536, 'steps': 30002, 'batch_loss/train': 0.738006106344983}
+12/26/2021 22:06:29 - INFO - codeparrot_training - Step 30003: {'lr': 0.0001737508770920312, 'samples': 15362048, 'steps': 30003, 'batch_loss/train': 0.9215702582150698}
+12/26/2021 22:06:40 - INFO - codeparrot_training - Step 30004: {'lr': 0.00017373586516795218, 'samples': 15362560, 'steps': 30004, 'batch_loss/train': 0.7753298892639577}
+12/26/2021 22:06:52 - INFO - codeparrot_training - Step 30005: {'lr': 0.00017372085354707046, 'samples': 15363072, 'steps': 30005, 'batch_loss/train': 0.6623600504826754}
+12/26/2021 22:07:03 - INFO - codeparrot_training - Step 30006: {'lr': 0.00017370584222944584, 'samples': 15363584, 'steps': 30006, 'batch_loss/train': 1.3678796836175025}
+12/26/2021 22:07:13 - INFO - codeparrot_training - Step 30007: {'lr': 0.00017369083121513806, 'samples': 15364096, 'steps': 30007, 'batch_loss/train': 0.7491974392905831}
+12/26/2021 22:07:26 - INFO - codeparrot_training - Step 30008: {'lr': 0.00017367582050420669, 'samples': 15364608, 'steps': 30008, 'batch_loss/train': 0.621832494798582}
+12/26/2021 22:07:37 - INFO - codeparrot_training - Step 30009: {'lr': 0.00017366081009671135, 'samples': 15365120, 'steps': 30009, 'batch_loss/train': 0.7666941303759813}
+12/26/2021 22:07:47 - INFO - codeparrot_training - Step 30010: {'lr': 0.00017364579999271196, 'samples': 15365632, 'steps': 30010, 'batch_loss/train': 0.7723866398446262}
+12/26/2021 22:07:58 - INFO - codeparrot_training - Step 30011: {'lr': 0.000173630790192268, 'samples': 15366144, 'steps': 30011, 'batch_loss/train': 0.6190134166972712}
+12/26/2021 22:08:12 - INFO - codeparrot_training - Step 30012: {'lr': 0.0001736157806954391, 'samples': 15366656, 'steps': 30012, 'batch_loss/train': 0.7219861653866246}
+12/26/2021 22:08:23 - INFO - codeparrot_training - Step 30013: {'lr': 0.00017360077150228504, 'samples': 15367168, 'steps': 30013, 'batch_loss/train': 0.7434927065623924}
+12/26/2021 22:08:33 - INFO - codeparrot_training - Step 30014: {'lr': 0.00017358576261286554, 'samples': 15367680, 'steps': 30014, 'batch_loss/train': 0.7640785025432706}
+12/26/2021 22:08:45 - INFO - codeparrot_training - Step 30015: {'lr': 0.00017357075402724015, 'samples': 15368192, 'steps': 30015, 'batch_loss/train': 0.9167928621172905}
+12/26/2021 22:08:56 - INFO - codeparrot_training - Step 30016: {'lr': 0.0001735557457454685, 'samples': 15368704, 'steps': 30016, 'batch_loss/train': 0.8416248792782426}
+12/26/2021 22:09:07 - INFO - codeparrot_training - Step 30017: {'lr': 0.00017354073776761048, 'samples': 15369216, 'steps': 30017, 'batch_loss/train': 0.8706389958970249}
+12/26/2021 22:09:19 - INFO - codeparrot_training - Step 30018: {'lr': 0.00017352573009372552, 'samples': 15369728, 'steps': 30018, 'batch_loss/train': 0.79141865670681}
+12/26/2021 22:09:29 - INFO - codeparrot_training - Step 30019: {'lr': 0.00017351072272387346, 'samples': 15370240, 'steps': 30019, 'batch_loss/train': 0.8110535629093647}
+12/26/2021 22:09:40 - INFO - codeparrot_training - Step 30020: {'lr': 0.0001734957156581138, 'samples': 15370752, 'steps': 30020, 'batch_loss/train': 0.7980521563440561}
+12/26/2021 22:09:50 - INFO - codeparrot_training - Step 30021: {'lr': 0.00017348070889650636, 'samples': 15371264, 'steps': 30021, 'batch_loss/train': 0.8003891687840223}
+12/26/2021 22:10:04 - INFO - codeparrot_training - Step 30022: {'lr': 0.00017346570243911068, 'samples': 15371776, 'steps': 30022, 'batch_loss/train': 0.766948038013652}
+12/26/2021 22:10:15 - INFO - codeparrot_training - Step 30023: {'lr': 0.00017345069628598654, 'samples': 15372288, 'steps': 30023, 'batch_loss/train': 0.7598970904946327}
+12/26/2021 22:10:25 - INFO - codeparrot_training - Step 30024: {'lr': 0.00017343569043719342, 'samples': 15372800, 'steps': 30024, 'batch_loss/train': 0.6691847261972725}
+12/26/2021 22:10:38 - INFO - codeparrot_training - Step 30025: {'lr': 0.0001734206848927911, 'samples': 15373312, 'steps': 30025, 'batch_loss/train': 0.7270841198042035}
+12/26/2021 22:10:48 - INFO - codeparrot_training - Step 30026: {'lr': 0.0001734056796528393, 'samples': 15373824, 'steps': 30026, 'batch_loss/train': 0.7853860724717379}
+12/26/2021 22:10:59 - INFO - codeparrot_training - Step 30027: {'lr': 0.00017339067471739753, 'samples': 15374336, 'steps': 30027, 'batch_loss/train': 0.7010464081540704}
+12/26/2021 22:11:11 - INFO - codeparrot_training - Step 30028: {'lr': 0.00017337567008652555, 'samples': 15374848, 'steps': 30028, 'batch_loss/train': 0.8457832271233201}
+12/26/2021 22:11:22 - INFO - codeparrot_training - Step 30029: {'lr': 0.00017336066576028298, 'samples': 15375360, 'steps': 30029, 'batch_loss/train': 0.8015181734226644}
+12/26/2021 22:11:33 - INFO - codeparrot_training - Step 30030: {'lr': 0.0001733456617387295, 'samples': 15375872, 'steps': 30030, 'batch_loss/train': 0.7640859708189964}
+12/26/2021 22:11:43 - INFO - codeparrot_training - Step 30031: {'lr': 0.0001733306580219246, 'samples': 15376384, 'steps': 30031, 'batch_loss/train': 0.6884589660912752}
+12/26/2021 22:11:57 - INFO - codeparrot_training - Step 30032: {'lr': 0.00017331565460992812, 'samples': 15376896, 'steps': 30032, 'batch_loss/train': 0.7282989639788866}
+12/26/2021 22:12:08 - INFO - codeparrot_training - Step 30033: {'lr': 0.00017330065150279972, 'samples': 15377408, 'steps': 30033, 'batch_loss/train': 0.8217993099242449}
+12/26/2021 22:12:19 - INFO - codeparrot_training - Step 30034: {'lr': 0.00017328564870059887, 'samples': 15377920, 'steps': 30034, 'batch_loss/train': 0.8053731303662062}
+12/26/2021 22:12:31 - INFO - codeparrot_training - Step 30035: {'lr': 0.0001732706462033853, 'samples': 15378432, 'steps': 30035, 'batch_loss/train': 0.804332653991878}
+12/26/2021 22:12:41 - INFO - codeparrot_training - Step 30036: {'lr': 0.00017325564401121874, 'samples': 15378944, 'steps': 30036, 'batch_loss/train': 0.7638776050880551}
+12/26/2021 22:12:52 - INFO - codeparrot_training - Step 30037: {'lr': 0.00017324064212415874, 'samples': 15379456, 'steps': 30037, 'batch_loss/train': 0.6693581594154239}
+12/26/2021 22:13:04 - INFO - codeparrot_training - Step 30038: {'lr': 0.0001732256405422649, 'samples': 15379968, 'steps': 30038, 'batch_loss/train': 0.6732131012249738}
+12/26/2021 22:13:15 - INFO - codeparrot_training - Step 30039: {'lr': 0.000173210639265597, 'samples': 15380480, 'steps': 30039, 'batch_loss/train': 0.7626086929813027}
+12/26/2021 22:13:26 - INFO - codeparrot_training - Step 30040: {'lr': 0.00017319563829421464, 'samples': 15380992, 'steps': 30040, 'batch_loss/train': 0.6998994001187384}
+12/26/2021 22:13:36 - INFO - codeparrot_training - Step 30041: {'lr': 0.00017318063762817738, 'samples': 15381504, 'steps': 30041, 'batch_loss/train': 0.7567367167212069}
+12/26/2021 22:13:50 - INFO - codeparrot_training - Step 30042: {'lr': 0.0001731656372675448, 'samples': 15382016, 'steps': 30042, 'batch_loss/train': 0.8409196278080344}
+12/26/2021 22:14:01 - INFO - codeparrot_training - Step 30043: {'lr': 0.00017315063721237678, 'samples': 15382528, 'steps': 30043, 'batch_loss/train': 0.6762333190999925}
+12/26/2021 22:14:12 - INFO - codeparrot_training - Step 30044: {'lr': 0.00017313563746273273, 'samples': 15383040, 'steps': 30044, 'batch_loss/train': 0.7392363771796227}
+12/26/2021 22:14:24 - INFO - codeparrot_training - Step 30045: {'lr': 0.00017312063801867242, 'samples': 15383552, 'steps': 30045, 'batch_loss/train': 0.9839538093656301}
+12/26/2021 22:14:34 - INFO - codeparrot_training - Step 30046: {'lr': 0.00017310563888025532, 'samples': 15384064, 'steps': 30046, 'batch_loss/train': 0.7850812714314088}
+12/26/2021 22:14:45 - INFO - codeparrot_training - Step 30047: {'lr': 0.0001730906400475413, 'samples': 15384576, 'steps': 30047, 'batch_loss/train': 0.6211493818555027}
+12/26/2021 22:14:57 - INFO - codeparrot_training - Step 30048: {'lr': 0.00017307564152058976, 'samples': 15385088, 'steps': 30048, 'batch_loss/train': 0.8396371905691922}
+12/26/2021 22:15:08 - INFO - codeparrot_training - Step 30049: {'lr': 0.0001730606432994604, 'samples': 15385600, 'steps': 30049, 'batch_loss/train': 0.7791494959965348}
+12/26/2021 22:15:19 - INFO - codeparrot_training - Step 30050: {'lr': 0.00017304564538421296, 'samples': 15386112, 'steps': 30050, 'batch_loss/train': 0.8510519838891923}
+12/26/2021 22:15:32 - INFO - codeparrot_training - Step 30051: {'lr': 0.00017303064777490694, 'samples': 15386624, 'steps': 30051, 'batch_loss/train': 0.7835797714069486}
+12/26/2021 22:15:43 - INFO - codeparrot_training - Step 30052: {'lr': 0.00017301565047160206, 'samples': 15387136, 'steps': 30052, 'batch_loss/train': 0.8498518075793982}
+12/26/2021 22:15:54 - INFO - codeparrot_training - Step 30053: {'lr': 0.00017300065347435775, 'samples': 15387648, 'steps': 30053, 'batch_loss/train': 0.8227023310028017}
+12/26/2021 22:16:04 - INFO - codeparrot_training - Step 30054: {'lr': 0.00017298565678323385, 'samples': 15388160, 'steps': 30054, 'batch_loss/train': 0.7760849432088435}
+12/26/2021 22:16:17 - INFO - codeparrot_training - Step 30055: {'lr': 0.00017297066039828992, 'samples': 15388672, 'steps': 30055, 'batch_loss/train': 0.6745460024103522}
+12/26/2021 22:16:27 - INFO - codeparrot_training - Step 30056: {'lr': 0.0001729556643195856, 'samples': 15389184, 'steps': 30056, 'batch_loss/train': 0.7962581180036068}
+12/26/2021 22:16:38 - INFO - codeparrot_training - Step 30057: {'lr': 0.00017294066854718032, 'samples': 15389696, 'steps': 30057, 'batch_loss/train': 0.7219424182549119}
+12/26/2021 22:16:52 - INFO - codeparrot_training - Step 30058: {'lr': 0.00017292567308113395, 'samples': 15390208, 'steps': 30058, 'batch_loss/train': 0.8424452901817858}
+12/26/2021 22:17:02 - INFO - codeparrot_training - Step 30059: {'lr': 0.000172910677921506, 'samples': 15390720, 'steps': 30059, 'batch_loss/train': 0.74047726765275}
+12/26/2021 22:17:13 - INFO - codeparrot_training - Step 30060: {'lr': 0.00017289568306835606, 'samples': 15391232, 'steps': 30060, 'batch_loss/train': 0.7741753468289971}
+12/26/2021 22:17:25 - INFO - codeparrot_training - Step 30061: {'lr': 0.0001728806885217437, 'samples': 15391744, 'steps': 30061, 'batch_loss/train': 0.7326560192741454}
+12/26/2021 22:17:36 - INFO - codeparrot_training - Step 30062: {'lr': 0.00017286569428172875, 'samples': 15392256, 'steps': 30062, 'batch_loss/train': 0.9826996740885079}
+12/26/2021 22:17:46 - INFO - codeparrot_training - Step 30063: {'lr': 0.00017285070034837058, 'samples': 15392768, 'steps': 30063, 'batch_loss/train': 0.8089829701930285}
+12/26/2021 22:17:57 - INFO - codeparrot_training - Step 30064: {'lr': 0.0001728357067217289, 'samples': 15393280, 'steps': 30064, 'batch_loss/train': 0.8493360662832856}
+12/26/2021 22:18:09 - INFO - codeparrot_training - Step 30065: {'lr': 0.00017282071340186334, 'samples': 15393792, 'steps': 30065, 'batch_loss/train': 0.7486019311472774}
+12/26/2021 22:18:20 - INFO - codeparrot_training - Step 30066: {'lr': 0.00017280572038883352, 'samples': 15394304, 'steps': 30066, 'batch_loss/train': 1.0539588844403625}
+12/26/2021 22:18:30 - INFO - codeparrot_training - Step 30067: {'lr': 0.00017279072768269896, 'samples': 15394816, 'steps': 30067, 'batch_loss/train': 0.6918194266036153}
+12/26/2021 22:18:43 - INFO - codeparrot_training - Step 30068: {'lr': 0.00017277573528351925, 'samples': 15395328, 'steps': 30068, 'batch_loss/train': 0.7978560430929065}
+12/26/2021 22:18:53 - INFO - codeparrot_training - Step 30069: {'lr': 0.00017276074319135418, 'samples': 15395840, 'steps': 30069, 'batch_loss/train': 0.7362247407436371}
+12/26/2021 22:19:04 - INFO - codeparrot_training - Step 30070: {'lr': 0.00017274575140626317, 'samples': 15396352, 'steps': 30070, 'batch_loss/train': 0.7372299400158226}
+12/26/2021 22:19:18 - INFO - codeparrot_training - Step 30071: {'lr': 0.00017273075992830595, 'samples': 15396864, 'steps': 30071, 'batch_loss/train': 0.7451476529240608}
+12/26/2021 22:19:28 - INFO - codeparrot_training - Step 30072: {'lr': 0.0001727157687575419, 'samples': 15397376, 'steps': 30072, 'batch_loss/train': 0.7476471541449428}
+12/26/2021 22:19:39 - INFO - codeparrot_training - Step 30073: {'lr': 0.00017270077789403087, 'samples': 15397888, 'steps': 30073, 'batch_loss/train': 0.7450636811554432}
+12/26/2021 22:19:50 - INFO - codeparrot_training - Step 30074: {'lr': 0.00017268578733783239, 'samples': 15398400, 'steps': 30074, 'batch_loss/train': 0.7568363696336746}
+12/26/2021 22:20:02 - INFO - codeparrot_training - Step 30075: {'lr': 0.00017267079708900592, 'samples': 15398912, 'steps': 30075, 'batch_loss/train': 0.6913242950104177}
+12/26/2021 22:20:13 - INFO - codeparrot_training - Step 30076: {'lr': 0.00017265580714761127, 'samples': 15399424, 'steps': 30076, 'batch_loss/train': 0.8014904021983966}
+12/26/2021 22:20:23 - INFO - codeparrot_training - Step 30077: {'lr': 0.0001726408175137079, 'samples': 15399936, 'steps': 30077, 'batch_loss/train': 0.7292408989742398}
+12/26/2021 22:20:35 - INFO - codeparrot_training - Step 30078: {'lr': 0.00017262582818735545, 'samples': 15400448, 'steps': 30078, 'batch_loss/train': 0.8398302784189582}
+12/26/2021 22:20:46 - INFO - codeparrot_training - Step 30079: {'lr': 0.0001726108391686134, 'samples': 15400960, 'steps': 30079, 'batch_loss/train': 0.6699753239518031}
+12/26/2021 22:20:57 - INFO - codeparrot_training - Step 30080: {'lr': 0.0001725958504575415, 'samples': 15401472, 'steps': 30080, 'batch_loss/train': 0.7022940395399928}
+12/26/2021 22:21:10 - INFO - codeparrot_training - Step 30081: {'lr': 0.00017258086205419932, 'samples': 15401984, 'steps': 30081, 'batch_loss/train': 0.7528568576090038}
+12/26/2021 22:21:21 - INFO - codeparrot_training - Step 30082: {'lr': 0.00017256587395864632, 'samples': 15402496, 'steps': 30082, 'batch_loss/train': 0.8106545330956578}
+12/26/2021 22:21:32 - INFO - codeparrot_training - Step 30083: {'lr': 0.00017255088617094212, 'samples': 15403008, 'steps': 30083, 'batch_loss/train': 0.8102855207398534}
+12/26/2021 22:21:42 - INFO - codeparrot_training - Step 30084: {'lr': 0.00017253589869114648, 'samples': 15403520, 'steps': 30084, 'batch_loss/train': 0.8678870680741966}
+12/26/2021 22:21:55 - INFO - codeparrot_training - Step 30085: {'lr': 0.00017252091151931883, 'samples': 15404032, 'steps': 30085, 'batch_loss/train': 0.7671860898844898}
+12/26/2021 22:22:05 - INFO - codeparrot_training - Step 30086: {'lr': 0.0001725059246555187, 'samples': 15404544, 'steps': 30086, 'batch_loss/train': 0.6489957813173532}
+12/26/2021 22:22:16 - INFO - codeparrot_training - Step 30087: {'lr': 0.00017249093809980581, 'samples': 15405056, 'steps': 30087, 'batch_loss/train': 0.7567091472446918}
+12/26/2021 22:22:30 - INFO - codeparrot_training - Step 30088: {'lr': 0.00017247595185223972, 'samples': 15405568, 'steps': 30088, 'batch_loss/train': 0.7141801677644253}
+12/26/2021 22:22:41 - INFO - codeparrot_training - Step 30089: {'lr': 0.0001724609659128799, 'samples': 15406080, 'steps': 30089, 'batch_loss/train': 0.849186778999865}
+12/26/2021 22:22:51 - INFO - codeparrot_training - Step 30090: {'lr': 0.000172445980281786, 'samples': 15406592, 'steps': 30090, 'batch_loss/train': 0.7257679365575314}
+12/26/2021 22:23:03 - INFO - codeparrot_training - Step 30091: {'lr': 0.00017243099495901768, 'samples': 15407104, 'steps': 30091, 'batch_loss/train': 0.6953356581507251}
+12/26/2021 22:23:14 - INFO - codeparrot_training - Step 30092: {'lr': 0.00017241600994463444, 'samples': 15407616, 'steps': 30092, 'batch_loss/train': 0.7381041520275176}
+12/26/2021 22:23:25 - INFO - codeparrot_training - Step 30093: {'lr': 0.00017240102523869577, 'samples': 15408128, 'steps': 30093, 'batch_loss/train': 0.7892778916284442}
+12/26/2021 22:23:35 - INFO - codeparrot_training - Step 30094: {'lr': 0.0001723860408412613, 'samples': 15408640, 'steps': 30094, 'batch_loss/train': 0.7443556408397853}
+12/26/2021 22:23:47 - INFO - codeparrot_training - Step 30095: {'lr': 0.00017237105675239073, 'samples': 15409152, 'steps': 30095, 'batch_loss/train': 0.7885005749994889}
+12/26/2021 22:23:58 - INFO - codeparrot_training - Step 30096: {'lr': 0.00017235607297214344, 'samples': 15409664, 'steps': 30096, 'batch_loss/train': 0.6891096513718367}
+12/26/2021 22:24:09 - INFO - codeparrot_training - Step 30097: {'lr': 0.00017234108950057918, 'samples': 15410176, 'steps': 30097, 'batch_loss/train': 0.7976120794191957}
+12/26/2021 22:24:22 - INFO - codeparrot_training - Step 30098: {'lr': 0.0001723261063377573, 'samples': 15410688, 'steps': 30098, 'batch_loss/train': 0.8144163526594639}
+12/26/2021 22:24:33 - INFO - codeparrot_training - Step 30099: {'lr': 0.00017231112348373756, 'samples': 15411200, 'steps': 30099, 'batch_loss/train': 0.7131247983779758}
+12/26/2021 22:24:43 - INFO - codeparrot_training - Step 30100: {'lr': 0.00017229614093857952, 'samples': 15411712, 'steps': 30100, 'batch_loss/train': 0.6972510032355785}
+12/26/2021 22:24:56 - INFO - codeparrot_training - Step 30101: {'lr': 0.00017228115870234257, 'samples': 15412224, 'steps': 30101, 'batch_loss/train': 0.7893682749127038}
+12/26/2021 22:25:06 - INFO - codeparrot_training - Step 30102: {'lr': 0.00017226617677508648, 'samples': 15412736, 'steps': 30102, 'batch_loss/train': 0.7767848498187959}
+12/26/2021 22:25:17 - INFO - codeparrot_training - Step 30103: {'lr': 0.00017225119515687065, 'samples': 15413248, 'steps': 30103, 'batch_loss/train': 0.7849394087679684}
+12/26/2021 22:25:29 - INFO - codeparrot_training - Step 30104: {'lr': 0.00017223621384775478, 'samples': 15413760, 'steps': 30104, 'batch_loss/train': 0.837081694509834}
+12/26/2021 22:25:40 - INFO - codeparrot_training - Step 30105: {'lr': 0.00017222123284779827, 'samples': 15414272, 'steps': 30105, 'batch_loss/train': 0.8439938924275339}
+12/26/2021 22:25:50 - INFO - codeparrot_training - Step 30106: {'lr': 0.00017220625215706083, 'samples': 15414784, 'steps': 30106, 'batch_loss/train': 0.7008415329619311}
+12/26/2021 22:26:01 - INFO - codeparrot_training - Step 30107: {'lr': 0.000172191271775602, 'samples': 15415296, 'steps': 30107, 'batch_loss/train': 0.7134687842335552}
+12/26/2021 22:26:13 - INFO - codeparrot_training - Step 30108: {'lr': 0.00017217629170348123, 'samples': 15415808, 'steps': 30108, 'batch_loss/train': 0.8981254743412137}
+12/26/2021 22:26:24 - INFO - codeparrot_training - Step 30109: {'lr': 0.0001721613119407581, 'samples': 15416320, 'steps': 30109, 'batch_loss/train': 0.7550781164318323}
+12/26/2021 22:26:34 - INFO - codeparrot_training - Step 30110: {'lr': 0.0001721463324874923, 'samples': 15416832, 'steps': 30110, 'batch_loss/train': 0.8040883932262659}
+12/26/2021 22:26:48 - INFO - codeparrot_training - Step 30111: {'lr': 0.0001721313533437433, 'samples': 15417344, 'steps': 30111, 'batch_loss/train': 0.6994348773732781}
+12/26/2021 22:26:59 - INFO - codeparrot_training - Step 30112: {'lr': 0.0001721163745095705, 'samples': 15417856, 'steps': 30112, 'batch_loss/train': 0.7171628852374852}
+12/26/2021 22:27:09 - INFO - codeparrot_training - Step 30113: {'lr': 0.00017210139598503366, 'samples': 15418368, 'steps': 30113, 'batch_loss/train': 0.8213838301599026}
+12/26/2021 22:27:22 - INFO - codeparrot_training - Step 30114: {'lr': 0.0001720864177701923, 'samples': 15418880, 'steps': 30114, 'batch_loss/train': 0.793201123829931}
+12/26/2021 22:27:32 - INFO - codeparrot_training - Step 30115: {'lr': 0.00017207143986510586, 'samples': 15419392, 'steps': 30115, 'batch_loss/train': 0.7220549727790058}
+12/26/2021 22:27:43 - INFO - codeparrot_training - Step 30116: {'lr': 0.00017205646226983395, 'samples': 15419904, 'steps': 30116, 'batch_loss/train': 0.7124692564830184}
+12/26/2021 22:27:54 - INFO - codeparrot_training - Step 30117: {'lr': 0.00017204148498443616, 'samples': 15420416, 'steps': 30117, 'batch_loss/train': 0.7452107379212976}
+12/26/2021 22:28:08 - INFO - codeparrot_training - Step 30118: {'lr': 0.00017202650800897198, 'samples': 15420928, 'steps': 30118, 'batch_loss/train': 0.7143907658755779}
+12/26/2021 22:28:19 - INFO - codeparrot_training - Step 30119: {'lr': 0.000172011531343501, 'samples': 15421440, 'steps': 30119, 'batch_loss/train': 1.0864731697365642}
+12/26/2021 22:28:29 - INFO - codeparrot_training - Step 30120: {'lr': 0.00017199655498808262, 'samples': 15421952, 'steps': 30120, 'batch_loss/train': 0.7790592920500785}
+12/26/2021 22:28:41 - INFO - codeparrot_training - Step 30121: {'lr': 0.00017198157894277662, 'samples': 15422464, 'steps': 30121, 'batch_loss/train': 0.8677251469343901}
+12/26/2021 22:28:52 - INFO - codeparrot_training - Step 30122: {'lr': 0.0001719666032076423, 'samples': 15422976, 'steps': 30122, 'batch_loss/train': 0.6991434679366648}
+12/26/2021 22:29:03 - INFO - codeparrot_training - Step 30123: {'lr': 0.00017195162778273925, 'samples': 15423488, 'steps': 30123, 'batch_loss/train': 0.6238324551377445}
+12/26/2021 22:29:15 - INFO - codeparrot_training - Step 30124: {'lr': 0.0001719366526681272, 'samples': 15424000, 'steps': 30124, 'batch_loss/train': 0.7442104904912412}
+12/26/2021 22:29:25 - INFO - codeparrot_training - Step 30125: {'lr': 0.00017192167786386544, 'samples': 15424512, 'steps': 30125, 'batch_loss/train': 0.7090409314259887}
+12/26/2021 22:29:36 - INFO - codeparrot_training - Step 30126: {'lr': 0.0001719067033700137, 'samples': 15425024, 'steps': 30126, 'batch_loss/train': 0.7438466749154031}
+12/26/2021 22:29:47 - INFO - codeparrot_training - Step 30127: {'lr': 0.00017189172918663132, 'samples': 15425536, 'steps': 30127, 'batch_loss/train': 0.7487726705148816}
+12/26/2021 22:30:01 - INFO - codeparrot_training - Step 30128: {'lr': 0.000171876755313778, 'samples': 15426048, 'steps': 30128, 'batch_loss/train': 0.7240990828722715}
+12/26/2021 22:30:11 - INFO - codeparrot_training - Step 30129: {'lr': 0.00017186178175151317, 'samples': 15426560, 'steps': 30129, 'batch_loss/train': 0.8044574223458767}
+12/26/2021 22:30:22 - INFO - codeparrot_training - Step 30130: {'lr': 0.00017184680849989647, 'samples': 15427072, 'steps': 30130, 'batch_loss/train': 0.7138062501326203}
+12/26/2021 22:30:34 - INFO - codeparrot_training - Step 30131: {'lr': 0.00017183183555898724, 'samples': 15427584, 'steps': 30131, 'batch_loss/train': 0.7305234321393073}
+12/26/2021 22:30:45 - INFO - codeparrot_training - Step 30132: {'lr': 0.00017181686292884514, 'samples': 15428096, 'steps': 30132, 'batch_loss/train': 0.6973096441943198}
+12/26/2021 22:30:55 - INFO - codeparrot_training - Step 30133: {'lr': 0.00017180189060952972, 'samples': 15428608, 'steps': 30133, 'batch_loss/train': 0.7673983685672283}
+12/26/2021 22:31:09 - INFO - codeparrot_training - Step 30134: {'lr': 0.00017178691860110043, 'samples': 15429120, 'steps': 30134, 'batch_loss/train': 0.6476702867075801}
+12/26/2021 22:31:20 - INFO - codeparrot_training - Step 30135: {'lr': 0.00017177194690361675, 'samples': 15429632, 'steps': 30135, 'batch_loss/train': 0.7682532276958227}
+12/26/2021 22:31:30 - INFO - codeparrot_training - Step 30136: {'lr': 0.0001717569755171384, 'samples': 15430144, 'steps': 30136, 'batch_loss/train': 0.8033249387517571}
+12/26/2021 22:31:41 - INFO - codeparrot_training - Step 30137: {'lr': 0.00017174200444172478, 'samples': 15430656, 'steps': 30137, 'batch_loss/train': 0.8136797357583418}
+12/26/2021 22:31:53 - INFO - codeparrot_training - Step 30138: {'lr': 0.00017172703367743526, 'samples': 15431168, 'steps': 30138, 'batch_loss/train': 0.7859202641993761}
+12/26/2021 22:32:04 - INFO - codeparrot_training - Step 30139: {'lr': 0.00017171206322432955, 'samples': 15431680, 'steps': 30139, 'batch_loss/train': 0.7577421879395843}
+12/26/2021 22:32:14 - INFO - codeparrot_training - Step 30140: {'lr': 0.0001716970930824672, 'samples': 15432192, 'steps': 30140, 'batch_loss/train': 0.8617171067744493}
+12/26/2021 22:32:26 - INFO - codeparrot_training - Step 30141: {'lr': 0.00017168212325190758, 'samples': 15432704, 'steps': 30141, 'batch_loss/train': 1.3861628780141473}
+12/26/2021 22:32:37 - INFO - codeparrot_training - Step 30142: {'lr': 0.00017166715373271018, 'samples': 15433216, 'steps': 30142, 'batch_loss/train': 0.7858304166002199}
+12/26/2021 22:32:48 - INFO - codeparrot_training - Step 30143: {'lr': 0.00017165218452493475, 'samples': 15433728, 'steps': 30143, 'batch_loss/train': 0.731003588414751}
+12/26/2021 22:33:00 - INFO - codeparrot_training - Step 30144: {'lr': 0.00017163721562864058, 'samples': 15434240, 'steps': 30144, 'batch_loss/train': 0.7497860310832039}
+12/26/2021 22:33:10 - INFO - codeparrot_training - Step 30145: {'lr': 0.0001716222470438873, 'samples': 15434752, 'steps': 30145, 'batch_loss/train': 0.8268007491715252}
+12/26/2021 22:33:21 - INFO - codeparrot_training - Step 30146: {'lr': 0.00017160727877073428, 'samples': 15435264, 'steps': 30146, 'batch_loss/train': 0.7636476019397378}
+12/26/2021 22:33:32 - INFO - codeparrot_training - Step 30147: {'lr': 0.0001715923108092412, 'samples': 15435776, 'steps': 30147, 'batch_loss/train': 0.7605560589581728}
+12/26/2021 22:33:46 - INFO - codeparrot_training - Step 30148: {'lr': 0.00017157734315946746, 'samples': 15436288, 'steps': 30148, 'batch_loss/train': 0.7837179200723767}
+12/26/2021 22:33:56 - INFO - codeparrot_training - Step 30149: {'lr': 0.00017156237582147252, 'samples': 15436800, 'steps': 30149, 'batch_loss/train': 0.8282950611319393}
+12/26/2021 22:34:07 - INFO - codeparrot_training - Step 30150: {'lr': 0.00017154740879531607, 'samples': 15437312, 'steps': 30150, 'batch_loss/train': 0.7807195065543056}
+12/26/2021 22:34:19 - INFO - codeparrot_training - Step 30151: {'lr': 0.00017153244208105745, 'samples': 15437824, 'steps': 30151, 'batch_loss/train': 0.7551262527704239}
+12/26/2021 22:34:30 - INFO - codeparrot_training - Step 30152: {'lr': 0.00017151747567875625, 'samples': 15438336, 'steps': 30152, 'batch_loss/train': 0.7440205405000597}
+12/26/2021 22:34:40 - INFO - codeparrot_training - Step 30153: {'lr': 0.00017150250958847187, 'samples': 15438848, 'steps': 30153, 'batch_loss/train': 0.7390148888807744}
+12/26/2021 22:34:52 - INFO - codeparrot_training - Step 30154: {'lr': 0.0001714875438102639, 'samples': 15439360, 'steps': 30154, 'batch_loss/train': 0.7206031922250986}
+12/26/2021 22:35:03 - INFO - codeparrot_training - Step 30155: {'lr': 0.00017147257834419183, 'samples': 15439872, 'steps': 30155, 'batch_loss/train': 0.8251425996422768}
+12/26/2021 22:35:14 - INFO - codeparrot_training - Step 30156: {'lr': 0.0001714576131903152, 'samples': 15440384, 'steps': 30156, 'batch_loss/train': 0.7348489970900118}
+12/26/2021 22:35:27 - INFO - codeparrot_training - Step 30157: {'lr': 0.00017144264834869328, 'samples': 15440896, 'steps': 30157, 'batch_loss/train': 0.7628682423382998}
+12/26/2021 22:35:38 - INFO - codeparrot_training - Step 30158: {'lr': 0.00017142768381938584, 'samples': 15441408, 'steps': 30158, 'batch_loss/train': 0.8132486666436307}
+12/26/2021 22:35:49 - INFO - codeparrot_training - Step 30159: {'lr': 0.00017141271960245224, 'samples': 15441920, 'steps': 30159, 'batch_loss/train': 0.7918633022345603}
+12/26/2021 22:35:59 - INFO - codeparrot_training - Step 30160: {'lr': 0.00017139775569795197, 'samples': 15442432, 'steps': 30160, 'batch_loss/train': 0.6538411750807427}
+12/26/2021 22:36:11 - INFO - codeparrot_training - Step 30161: {'lr': 0.00017138279210594454, 'samples': 15442944, 'steps': 30161, 'batch_loss/train': 0.7439510705880821}
+12/26/2021 22:36:22 - INFO - codeparrot_training - Step 30162: {'lr': 0.0001713678288264895, 'samples': 15443456, 'steps': 30162, 'batch_loss/train': 0.7983887683367357}
+12/26/2021 22:36:33 - INFO - codeparrot_training - Step 30163: {'lr': 0.00017135286585964627, 'samples': 15443968, 'steps': 30163, 'batch_loss/train': 0.829889852553606}
+12/26/2021 22:36:45 - INFO - codeparrot_training - Step 30164: {'lr': 0.00017133790320547425, 'samples': 15444480, 'steps': 30164, 'batch_loss/train': 0.8182187136262655}
+12/26/2021 22:36:55 - INFO - codeparrot_training - Step 30165: {'lr': 0.00017132294086403315, 'samples': 15444992, 'steps': 30165, 'batch_loss/train': 0.8457002304494381}
+12/26/2021 22:37:06 - INFO - codeparrot_training - Step 30166: {'lr': 0.00017130797883538231, 'samples': 15445504, 'steps': 30166, 'batch_loss/train': 0.788476224988699}
+12/26/2021 22:37:20 - INFO - codeparrot_training - Step 30167: {'lr': 0.00017129301711958124, 'samples': 15446016, 'steps': 30167, 'batch_loss/train': 0.7380972653627396}
+12/26/2021 22:37:31 - INFO - codeparrot_training - Step 30168: {'lr': 0.00017127805571668931, 'samples': 15446528, 'steps': 30168, 'batch_loss/train': 0.6068593673408031}
+12/26/2021 22:37:41 - INFO - codeparrot_training - Step 30169: {'lr': 0.0001712630946267662, 'samples': 15447040, 'steps': 30169, 'batch_loss/train': 0.7379289530217648}
+12/26/2021 22:37:52 - INFO - codeparrot_training - Step 30170: {'lr': 0.00017124813384987125, 'samples': 15447552, 'steps': 30170, 'batch_loss/train': 0.7468526707962155}
+12/26/2021 22:38:04 - INFO - codeparrot_training - Step 30171: {'lr': 0.0001712331733860641, 'samples': 15448064, 'steps': 30171, 'batch_loss/train': 0.7052089986391366}
+12/26/2021 22:38:15 - INFO - codeparrot_training - Step 30172: {'lr': 0.00017121821323540394, 'samples': 15448576, 'steps': 30172, 'batch_loss/train': 0.7874707216396928}
+12/26/2021 22:38:25 - INFO - codeparrot_training - Step 30173: {'lr': 0.00017120325339795052, 'samples': 15449088, 'steps': 30173, 'batch_loss/train': 0.8724192650988698}
+12/26/2021 22:38:39 - INFO - codeparrot_training - Step 30174: {'lr': 0.00017118829387376323, 'samples': 15449600, 'steps': 30174, 'batch_loss/train': 0.7766593573614955}
+12/26/2021 22:38:50 - INFO - codeparrot_training - Step 30175: {'lr': 0.00017117333466290142, 'samples': 15450112, 'steps': 30175, 'batch_loss/train': 0.8448414076119661}
+12/26/2021 22:39:01 - INFO - codeparrot_training - Step 30176: {'lr': 0.00017115837576542475, 'samples': 15450624, 'steps': 30176, 'batch_loss/train': 0.7914546653628349}
+12/26/2021 22:39:13 - INFO - codeparrot_training - Step 30177: {'lr': 0.00017114341718139258, 'samples': 15451136, 'steps': 30177, 'batch_loss/train': 0.7464643048588187}
+12/26/2021 22:39:23 - INFO - codeparrot_training - Step 30178: {'lr': 0.0001711284589108645, 'samples': 15451648, 'steps': 30178, 'batch_loss/train': 0.8491006214171648}
+12/26/2021 22:39:34 - INFO - codeparrot_training - Step 30179: {'lr': 0.00017111350095389973, 'samples': 15452160, 'steps': 30179, 'batch_loss/train': 0.7780843521468341}
+12/26/2021 22:39:46 - INFO - codeparrot_training - Step 30180: {'lr': 0.00017109854331055795, 'samples': 15452672, 'steps': 30180, 'batch_loss/train': 0.8505377480760217}
+12/26/2021 22:39:57 - INFO - codeparrot_training - Step 30181: {'lr': 0.00017108358598089864, 'samples': 15453184, 'steps': 30181, 'batch_loss/train': 0.6658239359967411}
+12/26/2021 22:40:07 - INFO - codeparrot_training - Step 30182: {'lr': 0.0001710686289649812, 'samples': 15453696, 'steps': 30182, 'batch_loss/train': 0.8088411800563335}
+12/26/2021 22:40:18 - INFO - codeparrot_training - Step 30183: {'lr': 0.00017105367226286495, 'samples': 15454208, 'steps': 30183, 'batch_loss/train': 0.6911014914512634}
+12/26/2021 22:40:30 - INFO - codeparrot_training - Step 30184: {'lr': 0.00017103871587460958, 'samples': 15454720, 'steps': 30184, 'batch_loss/train': 0.7968331421725452}
+12/26/2021 22:40:41 - INFO - codeparrot_training - Step 30185: {'lr': 0.00017102375980027447, 'samples': 15455232, 'steps': 30185, 'batch_loss/train': 0.774537842720747}
+12/26/2021 22:40:51 - INFO - codeparrot_training - Step 30186: {'lr': 0.00017100880403991904, 'samples': 15455744, 'steps': 30186, 'batch_loss/train': 0.7611840171739459}
+12/26/2021 22:41:05 - INFO - codeparrot_training - Step 30187: {'lr': 0.00017099384859360276, 'samples': 15456256, 'steps': 30187, 'batch_loss/train': 0.5353598645306192}
+12/26/2021 22:41:16 - INFO - codeparrot_training - Step 30188: {'lr': 0.0001709788934613852, 'samples': 15456768, 'steps': 30188, 'batch_loss/train': 0.613200630992651}
+12/26/2021 22:41:27 - INFO - codeparrot_training - Step 30189: {'lr': 0.00017096393864332566, 'samples': 15457280, 'steps': 30189, 'batch_loss/train': 0.7450653046835214}
+12/26/2021 22:41:39 - INFO - codeparrot_training - Step 30190: {'lr': 0.00017094898413948356, 'samples': 15457792, 'steps': 30190, 'batch_loss/train': 0.8485537096858025}
+12/26/2021 22:41:49 - INFO - codeparrot_training - Step 30191: {'lr': 0.0001709340299499186, 'samples': 15458304, 'steps': 30191, 'batch_loss/train': 0.7984926765784621}
+12/26/2021 22:42:00 - INFO - codeparrot_training - Step 30192: {'lr': 0.0001709190760746901, 'samples': 15458816, 'steps': 30192, 'batch_loss/train': 0.7859768802300096}
+12/26/2021 22:42:11 - INFO - codeparrot_training - Step 30193: {'lr': 0.0001709041225138574, 'samples': 15459328, 'steps': 30193, 'batch_loss/train': 0.8240900293458253}
+12/26/2021 22:42:23 - INFO - codeparrot_training - Step 30194: {'lr': 0.00017088916926748, 'samples': 15459840, 'steps': 30194, 'batch_loss/train': 0.752422631951049}
+12/26/2021 22:42:33 - INFO - codeparrot_training - Step 30195: {'lr': 0.0001708742163356175, 'samples': 15460352, 'steps': 30195, 'batch_loss/train': 0.6084944438189268}
+12/26/2021 22:42:44 - INFO - codeparrot_training - Step 30196: {'lr': 0.00017085926371832922, 'samples': 15460864, 'steps': 30196, 'batch_loss/train': 0.7535654362291098}
+12/26/2021 22:42:57 - INFO - codeparrot_training - Step 30197: {'lr': 0.00017084431141567452, 'samples': 15461376, 'steps': 30197, 'batch_loss/train': 0.7973830096889287}
+12/26/2021 22:43:08 - INFO - codeparrot_training - Step 30198: {'lr': 0.0001708293594277131, 'samples': 15461888, 'steps': 30198, 'batch_loss/train': 0.7898166389204562}
+12/26/2021 22:43:18 - INFO - codeparrot_training - Step 30199: {'lr': 0.0001708144077545042, 'samples': 15462400, 'steps': 30199, 'batch_loss/train': 0.6952607102575712}
+12/26/2021 22:43:30 - INFO - codeparrot_training - Step 30200: {'lr': 0.00017079945639610734, 'samples': 15462912, 'steps': 30200, 'batch_loss/train': 0.7315352740697563}
+12/26/2021 22:43:41 - INFO - codeparrot_training - Step 30201: {'lr': 0.00017078450535258183, 'samples': 15463424, 'steps': 30201, 'batch_loss/train': 0.7384460099274293}
+12/26/2021 22:43:52 - INFO - codeparrot_training - Step 30202: {'lr': 0.00017076955462398734, 'samples': 15463936, 'steps': 30202, 'batch_loss/train': 0.780335180927068}
+12/26/2021 22:44:05 - INFO - codeparrot_training - Step 30203: {'lr': 0.0001707546042103831, 'samples': 15464448, 'steps': 30203, 'batch_loss/train': 0.6779464709106833}
+12/26/2021 22:44:16 - INFO - codeparrot_training - Step 30204: {'lr': 0.00017073965411182874, 'samples': 15464960, 'steps': 30204, 'batch_loss/train': 0.8255715789273381}
+12/26/2021 22:44:26 - INFO - codeparrot_training - Step 30205: {'lr': 0.00017072470432838343, 'samples': 15465472, 'steps': 30205, 'batch_loss/train': 0.8533568065613508}
+12/26/2021 22:44:37 - INFO - codeparrot_training - Step 30206: {'lr': 0.0001707097548601068, 'samples': 15465984, 'steps': 30206, 'batch_loss/train': 0.7405768660828471}
+12/26/2021 22:44:49 - INFO - codeparrot_training - Step 30207: {'lr': 0.00017069480570705835, 'samples': 15466496, 'steps': 30207, 'batch_loss/train': 0.811709119938314}
+12/26/2021 22:45:00 - INFO - codeparrot_training - Step 30208: {'lr': 0.00017067985686929736, 'samples': 15467008, 'steps': 30208, 'batch_loss/train': 0.7277418617159128}
+12/26/2021 22:45:10 - INFO - codeparrot_training - Step 30209: {'lr': 0.00017066490834688326, 'samples': 15467520, 'steps': 30209, 'batch_loss/train': 0.7405705503188074}
+12/26/2021 22:45:22 - INFO - codeparrot_training - Step 30210: {'lr': 0.00017064996013987558, 'samples': 15468032, 'steps': 30210, 'batch_loss/train': 0.8084484711289406}
+12/26/2021 22:45:33 - INFO - codeparrot_training - Step 30211: {'lr': 0.00017063501224833373, 'samples': 15468544, 'steps': 30211, 'batch_loss/train': 0.8048828365281224}
+12/26/2021 22:45:44 - INFO - codeparrot_training - Step 30212: {'lr': 0.000170620064672317, 'samples': 15469056, 'steps': 30212, 'batch_loss/train': 0.7058506393805146}
+12/26/2021 22:45:58 - INFO - codeparrot_training - Step 30213: {'lr': 0.00017060511741188495, 'samples': 15469568, 'steps': 30213, 'batch_loss/train': 0.8646960565820336}
+12/26/2021 22:46:08 - INFO - codeparrot_training - Step 30214: {'lr': 0.00017059017046709707, 'samples': 15470080, 'steps': 30214, 'batch_loss/train': 0.5803473198320717}
+12/26/2021 22:46:19 - INFO - codeparrot_training - Step 30215: {'lr': 0.00017057522383801262, 'samples': 15470592, 'steps': 30215, 'batch_loss/train': 0.5834137692581862}
+12/26/2021 22:46:29 - INFO - codeparrot_training - Step 30216: {'lr': 0.000170560277524691, 'samples': 15471104, 'steps': 30216, 'batch_loss/train': 0.7416657693684101}
+12/26/2021 22:46:41 - INFO - codeparrot_training - Step 30217: {'lr': 0.00017054533152719188, 'samples': 15471616, 'steps': 30217, 'batch_loss/train': 0.6904004840180278}
+12/26/2021 22:46:52 - INFO - codeparrot_training - Step 30218: {'lr': 0.0001705303858455745, 'samples': 15472128, 'steps': 30218, 'batch_loss/train': 0.7197460364550352}
+12/26/2021 22:47:03 - INFO - codeparrot_training - Step 30219: {'lr': 0.00017051544047989823, 'samples': 15472640, 'steps': 30219, 'batch_loss/train': 0.8537957901135087}
+12/26/2021 22:47:15 - INFO - codeparrot_training - Step 30220: {'lr': 0.0001705004954302225, 'samples': 15473152, 'steps': 30220, 'batch_loss/train': 0.6804219400510192}
+12/26/2021 22:47:26 - INFO - codeparrot_training - Step 30221: {'lr': 0.00017048555069660692, 'samples': 15473664, 'steps': 30221, 'batch_loss/train': 0.7659509279765189}
+12/26/2021 22:47:36 - INFO - codeparrot_training - Step 30222: {'lr': 0.0001704706062791107, 'samples': 15474176, 'steps': 30222, 'batch_loss/train': 0.7897807424888015}
+12/26/2021 22:47:50 - INFO - codeparrot_training - Step 30223: {'lr': 0.00017045566217779325, 'samples': 15474688, 'steps': 30223, 'batch_loss/train': 0.7224198309704661}
+12/26/2021 22:48:01 - INFO - codeparrot_training - Step 30224: {'lr': 0.0001704407183927142, 'samples': 15475200, 'steps': 30224, 'batch_loss/train': 0.8045733901672065}
+12/26/2021 22:48:11 - INFO - codeparrot_training - Step 30225: {'lr': 0.0001704257749239327, 'samples': 15475712, 'steps': 30225, 'batch_loss/train': 0.6225101761519909}
+12/26/2021 22:48:22 - INFO - codeparrot_training - Step 30226: {'lr': 0.00017041083177150838, 'samples': 15476224, 'steps': 30226, 'batch_loss/train': 0.7898276168853045}
+12/26/2021 22:48:34 - INFO - codeparrot_training - Step 30227: {'lr': 0.0001703958889355004, 'samples': 15476736, 'steps': 30227, 'batch_loss/train': 0.7054000068455935}
+12/26/2021 22:48:45 - INFO - codeparrot_training - Step 30228: {'lr': 0.00017038094641596847, 'samples': 15477248, 'steps': 30228, 'batch_loss/train': 0.5856531300232746}
+12/26/2021 22:48:55 - INFO - codeparrot_training - Step 30229: {'lr': 0.00017036600421297172, 'samples': 15477760, 'steps': 30229, 'batch_loss/train': 0.5302227712236345}
+12/26/2021 22:49:07 - INFO - codeparrot_training - Step 30230: {'lr': 0.00017035106232656972, 'samples': 15478272, 'steps': 30230, 'batch_loss/train': 0.8924488946795464}
+12/26/2021 22:49:18 - INFO - codeparrot_training - Step 30231: {'lr': 0.00017033612075682177, 'samples': 15478784, 'steps': 30231, 'batch_loss/train': 0.7294901590794325}
+12/26/2021 22:49:29 - INFO - codeparrot_training - Step 30232: {'lr': 0.00017032117950378735, 'samples': 15479296, 'steps': 30232, 'batch_loss/train': 0.7680020816624165}
+12/26/2021 22:49:43 - INFO - codeparrot_training - Step 30233: {'lr': 0.00017030623856752587, 'samples': 15479808, 'steps': 30233, 'batch_loss/train': 0.7604910479858518}
+12/26/2021 22:49:53 - INFO - codeparrot_training - Step 30234: {'lr': 0.0001702912979480966, 'samples': 15480320, 'steps': 30234, 'batch_loss/train': 0.7879368830472231}
+12/26/2021 22:50:04 - INFO - codeparrot_training - Step 30235: {'lr': 0.0001702763576455591, 'samples': 15480832, 'steps': 30235, 'batch_loss/train': 0.6841073200048413}
+12/26/2021 22:50:15 - INFO - codeparrot_training - Step 30236: {'lr': 0.00017026141765997272, 'samples': 15481344, 'steps': 30236, 'batch_loss/train': 0.7507742196321487}
+12/26/2021 22:50:27 - INFO - codeparrot_training - Step 30237: {'lr': 0.00017024647799139685, 'samples': 15481856, 'steps': 30237, 'batch_loss/train': 0.7999563859775662}
+12/26/2021 22:50:38 - INFO - codeparrot_training - Step 30238: {'lr': 0.00017023153863989076, 'samples': 15482368, 'steps': 30238, 'batch_loss/train': 0.8174186162650585}
+12/26/2021 22:50:48 - INFO - codeparrot_training - Step 30239: {'lr': 0.00017021659960551403, 'samples': 15482880, 'steps': 30239, 'batch_loss/train': 0.5905561039689928}
+12/26/2021 22:51:00 - INFO - codeparrot_training - Step 30240: {'lr': 0.000170201660888326, 'samples': 15483392, 'steps': 30240, 'batch_loss/train': 0.6552972113713622}
+12/26/2021 22:51:11 - INFO - codeparrot_training - Step 30241: {'lr': 0.00017018672248838603, 'samples': 15483904, 'steps': 30241, 'batch_loss/train': 0.7872807821258903}
+12/26/2021 22:51:22 - INFO - codeparrot_training - Step 30242: {'lr': 0.0001701717844057534, 'samples': 15484416, 'steps': 30242, 'batch_loss/train': 0.8112925784662366}
+12/26/2021 22:51:36 - INFO - codeparrot_training - Step 30243: {'lr': 0.00017015684664048775, 'samples': 15484928, 'steps': 30243, 'batch_loss/train': 0.6270186617039144}
+12/26/2021 22:51:46 - INFO - codeparrot_training - Step 30244: {'lr': 0.00017014190919264826, 'samples': 15485440, 'steps': 30244, 'batch_loss/train': 0.7511256919242442}
+12/26/2021 22:51:57 - INFO - codeparrot_training - Step 30245: {'lr': 0.00017012697206229436, 'samples': 15485952, 'steps': 30245, 'batch_loss/train': 0.7961480235680938}
+12/26/2021 22:52:08 - INFO - codeparrot_training - Step 30246: {'lr': 0.00017011203524948555, 'samples': 15486464, 'steps': 30246, 'batch_loss/train': 0.7098890114575624}
+12/26/2021 22:52:20 - INFO - codeparrot_training - Step 30247: {'lr': 0.00017009709875428114, 'samples': 15486976, 'steps': 30247, 'batch_loss/train': 0.42586302175186574}
+12/26/2021 22:52:31 - INFO - codeparrot_training - Step 30248: {'lr': 0.00017008216257674043, 'samples': 15487488, 'steps': 30248, 'batch_loss/train': 0.7573311687447131}
+12/26/2021 22:52:41 - INFO - codeparrot_training - Step 30249: {'lr': 0.0001700672267169228, 'samples': 15488000, 'steps': 30249, 'batch_loss/train': 0.7416502069681883}
+12/26/2021 22:52:53 - INFO - codeparrot_training - Step 30250: {'lr': 0.0001700522911748878, 'samples': 15488512, 'steps': 30250, 'batch_loss/train': 0.709998045116663}
+12/26/2021 22:53:04 - INFO - codeparrot_training - Step 30251: {'lr': 0.00017003735595069467, 'samples': 15489024, 'steps': 30251, 'batch_loss/train': 0.8271262859925628}
+12/26/2021 22:53:15 - INFO - codeparrot_training - Step 30252: {'lr': 0.00017002242104440285, 'samples': 15489536, 'steps': 30252, 'batch_loss/train': 0.7761383070610464}
+12/26/2021 22:53:25 - INFO - codeparrot_training - Step 30253: {'lr': 0.00017000748645607162, 'samples': 15490048, 'steps': 30253, 'batch_loss/train': 0.73658312484622}
+12/26/2021 22:53:37 - INFO - codeparrot_training - Step 30254: {'lr': 0.00016999255218576044, 'samples': 15490560, 'steps': 30254, 'batch_loss/train': 0.8929464863613248}
+12/26/2021 22:53:48 - INFO - codeparrot_training - Step 30255: {'lr': 0.00016997761823352872, 'samples': 15491072, 'steps': 30255, 'batch_loss/train': 0.7805014001205564}
+12/26/2021 22:53:59 - INFO - codeparrot_training - Step 30256: {'lr': 0.00016996268459943577, 'samples': 15491584, 'steps': 30256, 'batch_loss/train': 0.8488701209425926}
+12/26/2021 22:54:13 - INFO - codeparrot_training - Step 30257: {'lr': 0.0001699477512835409, 'samples': 15492096, 'steps': 30257, 'batch_loss/train': 0.8698488622903824}
+12/26/2021 22:54:23 - INFO - codeparrot_training - Step 30258: {'lr': 0.00016993281828590353, 'samples': 15492608, 'steps': 30258, 'batch_loss/train': 0.7501571774482727}
+12/26/2021 22:54:34 - INFO - codeparrot_training - Step 30259: {'lr': 0.00016991788560658314, 'samples': 15493120, 'steps': 30259, 'batch_loss/train': 1.1061141779646277}
+12/26/2021 22:54:45 - INFO - codeparrot_training - Step 30260: {'lr': 0.00016990295324563888, 'samples': 15493632, 'steps': 30260, 'batch_loss/train': 0.8007212905213237}
+12/26/2021 22:54:57 - INFO - codeparrot_training - Step 30261: {'lr': 0.0001698880212031303, 'samples': 15494144, 'steps': 30261, 'batch_loss/train': 0.7447588900104165}
+12/26/2021 22:55:08 - INFO - codeparrot_training - Step 30262: {'lr': 0.00016987308947911673, 'samples': 15494656, 'steps': 30262, 'batch_loss/train': 0.7841519140638411}
+12/26/2021 22:55:18 - INFO - codeparrot_training - Step 30263: {'lr': 0.00016985815807365752, 'samples': 15495168, 'steps': 30263, 'batch_loss/train': 0.7313377915415913}
+12/26/2021 22:55:32 - INFO - codeparrot_training - Step 30264: {'lr': 0.0001698432269868119, 'samples': 15495680, 'steps': 30264, 'batch_loss/train': 0.7227810202166438}
+12/26/2021 22:55:43 - INFO - codeparrot_training - Step 30265: {'lr': 0.0001698282962186394, 'samples': 15496192, 'steps': 30265, 'batch_loss/train': 0.7078095120377839}
+12/26/2021 22:55:53 - INFO - codeparrot_training - Step 30266: {'lr': 0.00016981336576919937, 'samples': 15496704, 'steps': 30266, 'batch_loss/train': 0.7943510878831148}
+12/26/2021 22:56:05 - INFO - codeparrot_training - Step 30267: {'lr': 0.0001697984356385511, 'samples': 15497216, 'steps': 30267, 'batch_loss/train': 0.7222013265127316}
+12/26/2021 22:56:16 - INFO - codeparrot_training - Step 30268: {'lr': 0.00016978350582675384, 'samples': 15497728, 'steps': 30268, 'batch_loss/train': 0.800003373529762}
+12/26/2021 22:56:27 - INFO - codeparrot_training - Step 30269: {'lr': 0.00016976857633386723, 'samples': 15498240, 'steps': 30269, 'batch_loss/train': 0.751267846673727}
+12/26/2021 22:56:39 - INFO - codeparrot_training - Step 30270: {'lr': 0.00016975364715995038, 'samples': 15498752, 'steps': 30270, 'batch_loss/train': 0.7717712474986911}
+12/26/2021 22:56:49 - INFO - codeparrot_training - Step 30271: {'lr': 0.00016973871830506274, 'samples': 15499264, 'steps': 30271, 'batch_loss/train': 0.8753399020060897}
+12/26/2021 22:57:00 - INFO - codeparrot_training - Step 30272: {'lr': 0.00016972378976926373, 'samples': 15499776, 'steps': 30272, 'batch_loss/train': 0.784490155056119}
+12/26/2021 22:57:11 - INFO - codeparrot_training - Step 30273: {'lr': 0.00016970886155261259, 'samples': 15500288, 'steps': 30273, 'batch_loss/train': 0.8296043896116316}
+12/26/2021 22:57:25 - INFO - codeparrot_training - Step 30274: {'lr': 0.00016969393365516867, 'samples': 15500800, 'steps': 30274, 'batch_loss/train': 0.7989545548334718}
+12/26/2021 22:57:35 - INFO - codeparrot_training - Step 30275: {'lr': 0.00016967900607699126, 'samples': 15501312, 'steps': 30275, 'batch_loss/train': 0.7553271669894457}
+12/26/2021 22:57:46 - INFO - codeparrot_training - Step 30276: {'lr': 0.00016966407881813996, 'samples': 15501824, 'steps': 30276, 'batch_loss/train': 0.7328490964137018}
+12/26/2021 22:57:58 - INFO - codeparrot_training - Step 30277: {'lr': 0.00016964915187867385, 'samples': 15502336, 'steps': 30277, 'batch_loss/train': 0.7438050553901121}
+12/26/2021 22:58:08 - INFO - codeparrot_training - Step 30278: {'lr': 0.00016963422525865247, 'samples': 15502848, 'steps': 30278, 'batch_loss/train': 0.7820229983190075}
+12/26/2021 22:58:19 - INFO - codeparrot_training - Step 30279: {'lr': 0.00016961929895813492, 'samples': 15503360, 'steps': 30279, 'batch_loss/train': 0.7693208917044103}
+12/26/2021 22:58:33 - INFO - codeparrot_training - Step 30280: {'lr': 0.00016960437297718073, 'samples': 15503872, 'steps': 30280, 'batch_loss/train': 0.719751438125968}
+12/26/2021 22:58:44 - INFO - codeparrot_training - Step 30281: {'lr': 0.0001695894473158493, 'samples': 15504384, 'steps': 30281, 'batch_loss/train': 0.8101354754762724}
+12/26/2021 22:58:54 - INFO - codeparrot_training - Step 30282: {'lr': 0.0001695745219741997, 'samples': 15504896, 'steps': 30282, 'batch_loss/train': 0.9863415732979774}
+12/26/2021 22:59:05 - INFO - codeparrot_training - Step 30283: {'lr': 0.0001695595969522916, 'samples': 15505408, 'steps': 30283, 'batch_loss/train': 0.8348743710666895}
+12/26/2021 22:59:17 - INFO - codeparrot_training - Step 30284: {'lr': 0.00016954467225018406, 'samples': 15505920, 'steps': 30284, 'batch_loss/train': 0.5992396213114262}
+12/26/2021 22:59:28 - INFO - codeparrot_training - Step 30285: {'lr': 0.00016952974786793663, 'samples': 15506432, 'steps': 30285, 'batch_loss/train': 0.7405585134401917}
+12/26/2021 22:59:39 - INFO - codeparrot_training - Step 30286: {'lr': 0.0001695148238056084, 'samples': 15506944, 'steps': 30286, 'batch_loss/train': 0.7648942917585373}
+12/26/2021 22:59:52 - INFO - codeparrot_training - Step 30287: {'lr': 0.00016949990006325888, 'samples': 15507456, 'steps': 30287, 'batch_loss/train': 0.7963621281087399}
+12/26/2021 23:00:02 - INFO - codeparrot_training - Step 30288: {'lr': 0.00016948497664094741, 'samples': 15507968, 'steps': 30288, 'batch_loss/train': 0.8158303452655673}
+12/26/2021 23:00:13 - INFO - codeparrot_training - Step 30289: {'lr': 0.00016947005353873328, 'samples': 15508480, 'steps': 30289, 'batch_loss/train': 0.7588244881480932}
+12/26/2021 23:00:24 - INFO - codeparrot_training - Step 30290: {'lr': 0.00016945513075667572, 'samples': 15508992, 'steps': 30290, 'batch_loss/train': 1.328205400146544}
+12/26/2021 23:00:36 - INFO - codeparrot_training - Step 30291: {'lr': 0.00016944020829483427, 'samples': 15509504, 'steps': 30291, 'batch_loss/train': 0.7488730769837275}
+12/26/2021 23:00:46 - INFO - codeparrot_training - Step 30292: {'lr': 0.00016942528615326808, 'samples': 15510016, 'steps': 30292, 'batch_loss/train': 0.7088473225012422}
+12/26/2021 23:00:57 - INFO - codeparrot_training - Step 30293: {'lr': 0.0001694103643320365, 'samples': 15510528, 'steps': 30293, 'batch_loss/train': 0.6422260177787393}
+12/26/2021 23:01:10 - INFO - codeparrot_training - Step 30294: {'lr': 0.00016939544283119885, 'samples': 15511040, 'steps': 30294, 'batch_loss/train': 0.7294866153970361}
+12/26/2021 23:01:21 - INFO - codeparrot_training - Step 30295: {'lr': 0.00016938052165081457, 'samples': 15511552, 'steps': 30295, 'batch_loss/train': 0.8018245710991323}
+12/26/2021 23:01:31 - INFO - codeparrot_training - Step 30296: {'lr': 0.00016936560079094286, 'samples': 15512064, 'steps': 30296, 'batch_loss/train': 0.6985211223363876}
+12/26/2021 23:01:43 - INFO - codeparrot_training - Step 30297: {'lr': 0.00016935068025164302, 'samples': 15512576, 'steps': 30297, 'batch_loss/train': 0.8240173105150461}
+12/26/2021 23:01:54 - INFO - codeparrot_training - Step 30298: {'lr': 0.00016933576003297452, 'samples': 15513088, 'steps': 30298, 'batch_loss/train': 0.7196063422597945}
+12/26/2021 23:02:05 - INFO - codeparrot_training - Step 30299: {'lr': 0.00016932084013499655, 'samples': 15513600, 'steps': 30299, 'batch_loss/train': 0.6981802491936833}
+12/26/2021 23:02:15 - INFO - codeparrot_training - Step 30300: {'lr': 0.0001693059205577685, 'samples': 15514112, 'steps': 30300, 'batch_loss/train': 0.6931999516673386}
+12/26/2021 23:02:27 - INFO - codeparrot_training - Step 30301: {'lr': 0.0001692910013013495, 'samples': 15514624, 'steps': 30301, 'batch_loss/train': 0.7850580052472651}
+12/26/2021 23:02:38 - INFO - codeparrot_training - Step 30302: {'lr': 0.00016927608236579916, 'samples': 15515136, 'steps': 30302, 'batch_loss/train': 0.7290357548044994}
+12/26/2021 23:02:49 - INFO - codeparrot_training - Step 30303: {'lr': 0.00016926116375117655, 'samples': 15515648, 'steps': 30303, 'batch_loss/train': 0.7403982819523662}
+12/26/2021 23:03:03 - INFO - codeparrot_training - Step 30304: {'lr': 0.00016924624545754113, 'samples': 15516160, 'steps': 30304, 'batch_loss/train': 0.6724852081388235}
+12/26/2021 23:03:13 - INFO - codeparrot_training - Step 30305: {'lr': 0.00016923132748495205, 'samples': 15516672, 'steps': 30305, 'batch_loss/train': 0.8020163818728179}
+12/26/2021 23:03:24 - INFO - codeparrot_training - Step 30306: {'lr': 0.00016921640983346876, 'samples': 15517184, 'steps': 30306, 'batch_loss/train': 0.777906057657674}
+12/26/2021 23:03:36 - INFO - codeparrot_training - Step 30307: {'lr': 0.00016920149250315055, 'samples': 15517696, 'steps': 30307, 'batch_loss/train': 0.85644262842834}
+12/26/2021 23:03:47 - INFO - codeparrot_training - Step 30308: {'lr': 0.00016918657549405664, 'samples': 15518208, 'steps': 30308, 'batch_loss/train': 0.7868274850770831}
+12/26/2021 23:03:57 - INFO - codeparrot_training - Step 30309: {'lr': 0.00016917165880624645, 'samples': 15518720, 'steps': 30309, 'batch_loss/train': 0.737827654927969}
+12/26/2021 23:04:08 - INFO - codeparrot_training - Step 30310: {'lr': 0.00016915674243977918, 'samples': 15519232, 'steps': 30310, 'batch_loss/train': 0.7763118771836162}
+12/26/2021 23:04:22 - INFO - codeparrot_training - Step 30311: {'lr': 0.00016914182639471426, 'samples': 15519744, 'steps': 30311, 'batch_loss/train': 0.8282372038811445}
+12/26/2021 23:04:33 - INFO - codeparrot_training - Step 30312: {'lr': 0.0001691269106711108, 'samples': 15520256, 'steps': 30312, 'batch_loss/train': 0.7324341060593724}
+12/26/2021 23:04:43 - INFO - codeparrot_training - Step 30313: {'lr': 0.00016911199526902824, 'samples': 15520768, 'steps': 30313, 'batch_loss/train': 0.8489788360893726}
+12/26/2021 23:04:55 - INFO - codeparrot_training - Step 30314: {'lr': 0.0001690970801885259, 'samples': 15521280, 'steps': 30314, 'batch_loss/train': 0.8108050134032965}
+12/26/2021 23:05:06 - INFO - codeparrot_training - Step 30315: {'lr': 0.00016908216542966297, 'samples': 15521792, 'steps': 30315, 'batch_loss/train': 0.776255832053721}
+12/26/2021 23:05:17 - INFO - codeparrot_training - Step 30316: {'lr': 0.00016906725099249874, 'samples': 15522304, 'steps': 30316, 'batch_loss/train': 0.7113209548406303}
+12/26/2021 23:05:29 - INFO - codeparrot_training - Step 30317: {'lr': 0.00016905233687709268, 'samples': 15522816, 'steps': 30317, 'batch_loss/train': 0.7220376411569305}
+12/26/2021 23:05:40 - INFO - codeparrot_training - Step 30318: {'lr': 0.00016903742308350394, 'samples': 15523328, 'steps': 30318, 'batch_loss/train': 0.7391798719763756}
+12/26/2021 23:05:50 - INFO - codeparrot_training - Step 30319: {'lr': 0.00016902250961179177, 'samples': 15523840, 'steps': 30319, 'batch_loss/train': 0.7085179686546326}
+12/26/2021 23:06:01 - INFO - codeparrot_training - Step 30320: {'lr': 0.00016900759646201554, 'samples': 15524352, 'steps': 30320, 'batch_loss/train': 0.7047441517934203}
+12/26/2021 23:06:15 - INFO - codeparrot_training - Step 30321: {'lr': 0.0001689926836342346, 'samples': 15524864, 'steps': 30321, 'batch_loss/train': 0.7973251051735133}
+12/26/2021 23:06:25 - INFO - codeparrot_training - Step 30322: {'lr': 0.00016897777112850809, 'samples': 15525376, 'steps': 30322, 'batch_loss/train': 0.7721666395664215}
+12/26/2021 23:06:36 - INFO - codeparrot_training - Step 30323: {'lr': 0.00016896285894489534, 'samples': 15525888, 'steps': 30323, 'batch_loss/train': 0.7789962785318494}
+12/26/2021 23:06:48 - INFO - codeparrot_training - Step 30324: {'lr': 0.00016894794708345576, 'samples': 15526400, 'steps': 30324, 'batch_loss/train': 0.7131933788768947}
+12/26/2021 23:06:59 - INFO - codeparrot_training - Step 30325: {'lr': 0.0001689330355442485, 'samples': 15526912, 'steps': 30325, 'batch_loss/train': 0.776974068954587}
+12/26/2021 23:07:09 - INFO - codeparrot_training - Step 30326: {'lr': 0.00016891812432733288, 'samples': 15527424, 'steps': 30326, 'batch_loss/train': 0.7034314731135964}
+12/26/2021 23:07:23 - INFO - codeparrot_training - Step 30327: {'lr': 0.00016890321343276816, 'samples': 15527936, 'steps': 30327, 'batch_loss/train': 0.7511392049491405}
+12/26/2021 23:07:34 - INFO - codeparrot_training - Step 30328: {'lr': 0.0001688883028606137, 'samples': 15528448, 'steps': 30328, 'batch_loss/train': 0.7517673717811704}
+12/26/2021 23:07:44 - INFO - codeparrot_training - Step 30329: {'lr': 0.00016887339261092865, 'samples': 15528960, 'steps': 30329, 'batch_loss/train': 0.7526908391155303}
+12/26/2021 23:07:56 - INFO - codeparrot_training - Step 30330: {'lr': 0.00016885848268377243, 'samples': 15529472, 'steps': 30330, 'batch_loss/train': 0.734469898045063}
+12/26/2021 23:08:07 - INFO - codeparrot_training - Step 30331: {'lr': 0.00016884357307920414, 'samples': 15529984, 'steps': 30331, 'batch_loss/train': 0.7318243077024817}
+12/26/2021 23:08:18 - INFO - codeparrot_training - Step 30332: {'lr': 0.00016882866379728324, 'samples': 15530496, 'steps': 30332, 'batch_loss/train': 0.8138715210370719}
+12/26/2021 23:08:28 - INFO - codeparrot_training - Step 30333: {'lr': 0.00016881375483806892, 'samples': 15531008, 'steps': 30333, 'batch_loss/train': 0.7649172402452677}
+12/26/2021 23:08:41 - INFO - codeparrot_training - Step 30334: {'lr': 0.0001687988462016204, 'samples': 15531520, 'steps': 30334, 'batch_loss/train': 0.7446907706325874}
+12/26/2021 23:08:52 - INFO - codeparrot_training - Step 30335: {'lr': 0.00016878393788799704, 'samples': 15532032, 'steps': 30335, 'batch_loss/train': 0.8156741689890623}
+12/26/2021 23:09:02 - INFO - codeparrot_training - Step 30336: {'lr': 0.00016876902989725813, 'samples': 15532544, 'steps': 30336, 'batch_loss/train': 0.8527269996702671}
+12/26/2021 23:09:14 - INFO - codeparrot_training - Step 30337: {'lr': 0.0001687541222294629, 'samples': 15533056, 'steps': 30337, 'batch_loss/train': 0.4707522098906338}
+12/26/2021 23:09:25 - INFO - codeparrot_training - Step 30338: {'lr': 0.00016873921488467047, 'samples': 15533568, 'steps': 30338, 'batch_loss/train': 0.7123753689229488}
+12/26/2021 23:09:36 - INFO - codeparrot_training - Step 30339: {'lr': 0.0001687243078629403, 'samples': 15534080, 'steps': 30339, 'batch_loss/train': 0.7300927881151438}
+12/26/2021 23:09:46 - INFO - codeparrot_training - Step 30340: {'lr': 0.00016870940116433164, 'samples': 15534592, 'steps': 30340, 'batch_loss/train': 0.7324778120964766}
+12/26/2021 23:10:00 - INFO - codeparrot_training - Step 30341: {'lr': 0.0001686944947889037, 'samples': 15535104, 'steps': 30341, 'batch_loss/train': 0.7074102280894294}
+12/26/2021 23:10:11 - INFO - codeparrot_training - Step 30342: {'lr': 0.00016867958873671563, 'samples': 15535616, 'steps': 30342, 'batch_loss/train': 0.7517969692125916}
+12/26/2021 23:10:21 - INFO - codeparrot_training - Step 30343: {'lr': 0.00016866468300782696, 'samples': 15536128, 'steps': 30343, 'batch_loss/train': 0.6890024549793452}
+12/26/2021 23:10:34 - INFO - codeparrot_training - Step 30344: {'lr': 0.00016864977760229673, 'samples': 15536640, 'steps': 30344, 'batch_loss/train': 0.6734271494206041}
+12/26/2021 23:10:44 - INFO - codeparrot_training - Step 30345: {'lr': 0.00016863487252018422, 'samples': 15537152, 'steps': 30345, 'batch_loss/train': 0.7394433710724115}
+12/26/2021 23:10:55 - INFO - codeparrot_training - Step 30346: {'lr': 0.00016861996776154883, 'samples': 15537664, 'steps': 30346, 'batch_loss/train': 0.5770099712535739}
+12/26/2021 23:11:08 - INFO - codeparrot_training - Step 30347: {'lr': 0.00016860506332644977, 'samples': 15538176, 'steps': 30347, 'batch_loss/train': 0.6582098465878516}
+12/26/2021 23:11:18 - INFO - codeparrot_training - Step 30348: {'lr': 0.00016859015921494614, 'samples': 15538688, 'steps': 30348, 'batch_loss/train': 0.7780614672228694}
+12/26/2021 23:11:29 - INFO - codeparrot_training - Step 30349: {'lr': 0.00016857525542709722, 'samples': 15539200, 'steps': 30349, 'batch_loss/train': 0.7679492551833391}
+12/26/2021 23:11:40 - INFO - codeparrot_training - Step 30350: {'lr': 0.0001685603519629625, 'samples': 15539712, 'steps': 30350, 'batch_loss/train': 0.6860130322165787}
+12/26/2021 23:11:53 - INFO - codeparrot_training - Step 30351: {'lr': 0.000168545448822601, 'samples': 15540224, 'steps': 30351, 'batch_loss/train': 0.5020563171710819}
+12/26/2021 23:12:04 - INFO - codeparrot_training - Step 30352: {'lr': 0.0001685305460060721, 'samples': 15540736, 'steps': 30352, 'batch_loss/train': 0.7705603120848536}
+12/26/2021 23:12:14 - INFO - codeparrot_training - Step 30353: {'lr': 0.00016851564351343484, 'samples': 15541248, 'steps': 30353, 'batch_loss/train': 0.7334735421463847}
+12/26/2021 23:12:25 - INFO - codeparrot_training - Step 30354: {'lr': 0.00016850074134474878, 'samples': 15541760, 'steps': 30354, 'batch_loss/train': 0.7996252104640007}
+12/26/2021 23:12:37 - INFO - codeparrot_training - Step 30355: {'lr': 0.0001684858395000729, 'samples': 15542272, 'steps': 30355, 'batch_loss/train': 0.7450212640687823}
+12/26/2021 23:12:48 - INFO - codeparrot_training - Step 30356: {'lr': 0.00016847093797946652, 'samples': 15542784, 'steps': 30356, 'batch_loss/train': 0.7170653584762476}
+12/26/2021 23:12:58 - INFO - codeparrot_training - Step 30357: {'lr': 0.00016845603678298902, 'samples': 15543296, 'steps': 30357, 'batch_loss/train': 0.8102821819484234}
+12/26/2021 23:13:13 - INFO - codeparrot_training - Step 30358: {'lr': 0.00016844113591069944, 'samples': 15543808, 'steps': 30358, 'batch_loss/train': 0.7498789317905903}
+12/26/2021 23:13:23 - INFO - codeparrot_training - Step 30359: {'lr': 0.00016842623536265716, 'samples': 15544320, 'steps': 30359, 'batch_loss/train': 0.7817348474636674}
+12/26/2021 23:13:34 - INFO - codeparrot_training - Step 30360: {'lr': 0.00016841133513892132, 'samples': 15544832, 'steps': 30360, 'batch_loss/train': 1.0102986991405487}
+12/26/2021 23:13:46 - INFO - codeparrot_training - Step 30361: {'lr': 0.0001683964352395512, 'samples': 15545344, 'steps': 30361, 'batch_loss/train': 0.7489525116980076}
+12/26/2021 23:13:57 - INFO - codeparrot_training - Step 30362: {'lr': 0.00016838153566460612, 'samples': 15545856, 'steps': 30362, 'batch_loss/train': 0.7904896242544055}
+12/26/2021 23:14:07 - INFO - codeparrot_training - Step 30363: {'lr': 0.00016836663641414524, 'samples': 15546368, 'steps': 30363, 'batch_loss/train': 0.7904106536880136}
+12/26/2021 23:14:18 - INFO - codeparrot_training - Step 30364: {'lr': 0.00016835173748822765, 'samples': 15546880, 'steps': 30364, 'batch_loss/train': 0.7847065171226859}
+12/26/2021 23:14:30 - INFO - codeparrot_training - Step 30365: {'lr': 0.0001683368388869128, 'samples': 15547392, 'steps': 30365, 'batch_loss/train': 0.8193763294257224}
+12/26/2021 23:14:41 - INFO - codeparrot_training - Step 30366: {'lr': 0.0001683219406102599, 'samples': 15547904, 'steps': 30366, 'batch_loss/train': 0.8148705440107733}
+12/26/2021 23:14:51 - INFO - codeparrot_training - Step 30367: {'lr': 0.00016830704265832804, 'samples': 15548416, 'steps': 30367, 'batch_loss/train': 0.8123387405648828}
+12/26/2021 23:15:05 - INFO - codeparrot_training - Step 30368: {'lr': 0.0001682921450311765, 'samples': 15548928, 'steps': 30368, 'batch_loss/train': 0.7505918517708778}
+12/26/2021 23:15:16 - INFO - codeparrot_training - Step 30369: {'lr': 0.00016827724772886465, 'samples': 15549440, 'steps': 30369, 'batch_loss/train': 0.7471540346741676}
+12/26/2021 23:15:27 - INFO - codeparrot_training - Step 30370: {'lr': 0.0001682623507514516, 'samples': 15549952, 'steps': 30370, 'batch_loss/train': 0.8285234281793237}
+12/26/2021 23:15:39 - INFO - codeparrot_training - Step 30371: {'lr': 0.00016824745409899645, 'samples': 15550464, 'steps': 30371, 'batch_loss/train': 0.7738095661625266}
+12/26/2021 23:15:49 - INFO - codeparrot_training - Step 30372: {'lr': 0.00016823255777155872, 'samples': 15550976, 'steps': 30372, 'batch_loss/train': 0.8617900181561708}
+12/26/2021 23:16:00 - INFO - codeparrot_training - Step 30373: {'lr': 0.0001682176617691974, 'samples': 15551488, 'steps': 30373, 'batch_loss/train': 0.8115465901792049}
+12/26/2021 23:16:12 - INFO - codeparrot_training - Step 30374: {'lr': 0.00016820276609197176, 'samples': 15552000, 'steps': 30374, 'batch_loss/train': 0.7183247555512935}
+12/26/2021 23:16:23 - INFO - codeparrot_training - Step 30375: {'lr': 0.000168187870739941, 'samples': 15552512, 'steps': 30375, 'batch_loss/train': 0.7912985803559422}
+12/26/2021 23:16:33 - INFO - codeparrot_training - Step 30376: {'lr': 0.00016817297571316447, 'samples': 15553024, 'steps': 30376, 'batch_loss/train': 0.681115326937288}
+12/26/2021 23:16:44 - INFO - codeparrot_training - Step 30377: {'lr': 0.0001681580810117012, 'samples': 15553536, 'steps': 30377, 'batch_loss/train': 0.8016816191375256}
+12/26/2021 23:16:56 - INFO - codeparrot_training - Step 30378: {'lr': 0.00016814318663561063, 'samples': 15554048, 'steps': 30378, 'batch_loss/train': 0.8214237892534584}
+12/26/2021 23:17:07 - INFO - codeparrot_training - Step 30379: {'lr': 0.00016812829258495166, 'samples': 15554560, 'steps': 30379, 'batch_loss/train': 0.9423373104073107}
+12/26/2021 23:17:17 - INFO - codeparrot_training - Step 30380: {'lr': 0.00016811339885978378, 'samples': 15555072, 'steps': 30380, 'batch_loss/train': 0.7057053507305682}
+12/26/2021 23:17:32 - INFO - codeparrot_training - Step 30381: {'lr': 0.00016809850546016614, 'samples': 15555584, 'steps': 30381, 'batch_loss/train': 0.8247639765031636}
+12/26/2021 23:17:42 - INFO - codeparrot_training - Step 30382: {'lr': 0.0001680836123861578, 'samples': 15556096, 'steps': 30382, 'batch_loss/train': 0.787279230542481}
+12/26/2021 23:17:53 - INFO - codeparrot_training - Step 30383: {'lr': 0.00016806871963781823, 'samples': 15556608, 'steps': 30383, 'batch_loss/train': 0.7488685818389058}
+12/26/2021 23:18:05 - INFO - codeparrot_training - Step 30384: {'lr': 0.00016805382721520642, 'samples': 15557120, 'steps': 30384, 'batch_loss/train': 0.7944280819501728}
+12/26/2021 23:18:16 - INFO - codeparrot_training - Step 30385: {'lr': 0.0001680389351183817, 'samples': 15557632, 'steps': 30385, 'batch_loss/train': 0.712493835715577}
+12/26/2021 23:18:26 - INFO - codeparrot_training - Step 30386: {'lr': 0.00016802404334740316, 'samples': 15558144, 'steps': 30386, 'batch_loss/train': 0.8355588223785162}
+12/26/2021 23:18:37 - INFO - codeparrot_training - Step 30387: {'lr': 0.00016800915190233007, 'samples': 15558656, 'steps': 30387, 'batch_loss/train': 0.5986833041533828}
+12/26/2021 23:18:51 - INFO - codeparrot_training - Step 30388: {'lr': 0.0001679942607832217, 'samples': 15559168, 'steps': 30388, 'batch_loss/train': 0.6737103778868914}
+12/26/2021 23:19:02 - INFO - codeparrot_training - Step 30389: {'lr': 0.00016797936999013717, 'samples': 15559680, 'steps': 30389, 'batch_loss/train': 0.7401702785864472}
+12/26/2021 23:19:12 - INFO - codeparrot_training - Step 30390: {'lr': 0.0001679644795231356, 'samples': 15560192, 'steps': 30390, 'batch_loss/train': 1.0108242947608232}
+12/26/2021 23:19:24 - INFO - codeparrot_training - Step 30391: {'lr': 0.00016794958938227638, 'samples': 15560704, 'steps': 30391, 'batch_loss/train': 0.5847743379417807}
+12/26/2021 23:19:35 - INFO - codeparrot_training - Step 30392: {'lr': 0.00016793469956761863, 'samples': 15561216, 'steps': 30392, 'batch_loss/train': 0.8208916211733595}
+12/26/2021 23:19:46 - INFO - codeparrot_training - Step 30393: {'lr': 0.00016791981007922147, 'samples': 15561728, 'steps': 30393, 'batch_loss/train': 0.6985751749016345}
+12/26/2021 23:19:56 - INFO - codeparrot_training - Step 30394: {'lr': 0.00016790492091714416, 'samples': 15562240, 'steps': 30394, 'batch_loss/train': 0.7737347148358822}
+12/26/2021 23:20:09 - INFO - codeparrot_training - Step 30395: {'lr': 0.00016789003208144592, 'samples': 15562752, 'steps': 30395, 'batch_loss/train': 0.8400062536820769}
+12/26/2021 23:20:19 - INFO - codeparrot_training - Step 30396: {'lr': 0.00016787514357218588, 'samples': 15563264, 'steps': 30396, 'batch_loss/train': 0.7292717797681689}
+12/26/2021 23:20:30 - INFO - codeparrot_training - Step 30397: {'lr': 0.00016786025538942324, 'samples': 15563776, 'steps': 30397, 'batch_loss/train': 0.7670926628634334}
+12/26/2021 23:20:44 - INFO - codeparrot_training - Step 30398: {'lr': 0.00016784536753321726, 'samples': 15564288, 'steps': 30398, 'batch_loss/train': 0.7345486702397466}
+12/26/2021 23:20:55 - INFO - codeparrot_training - Step 30399: {'lr': 0.0001678304800036271, 'samples': 15564800, 'steps': 30399, 'batch_loss/train': 0.5688985696760938}
+12/26/2021 23:21:05 - INFO - codeparrot_training - Step 30400: {'lr': 0.00016781559280071184, 'samples': 15565312, 'steps': 30400, 'batch_loss/train': 0.7763326806016266}
+12/26/2021 23:21:17 - INFO - codeparrot_training - Step 30401: {'lr': 0.00016780070592453076, 'samples': 15565824, 'steps': 30401, 'batch_loss/train': 0.712107615545392}
+12/26/2021 23:21:28 - INFO - codeparrot_training - Step 30402: {'lr': 0.0001677858193751431, 'samples': 15566336, 'steps': 30402, 'batch_loss/train': 0.8241373589262366}
+12/26/2021 23:21:39 - INFO - codeparrot_training - Step 30403: {'lr': 0.00016777093315260795, 'samples': 15566848, 'steps': 30403, 'batch_loss/train': 0.7559393253177404}
+12/26/2021 23:21:51 - INFO - codeparrot_training - Step 30404: {'lr': 0.00016775604725698456, 'samples': 15567360, 'steps': 30404, 'batch_loss/train': 0.7411087965592742}
+12/26/2021 23:22:02 - INFO - codeparrot_training - Step 30405: {'lr': 0.00016774116168833197, 'samples': 15567872, 'steps': 30405, 'batch_loss/train': 0.6853297797497362}
+12/26/2021 23:22:12 - INFO - codeparrot_training - Step 30406: {'lr': 0.0001677262764467095, 'samples': 15568384, 'steps': 30406, 'batch_loss/train': 0.726391093339771}
+12/26/2021 23:22:23 - INFO - codeparrot_training - Step 30407: {'lr': 0.00016771139153217636, 'samples': 15568896, 'steps': 30407, 'batch_loss/train': 0.666979237110354}
+12/26/2021 23:22:37 - INFO - codeparrot_training - Step 30408: {'lr': 0.00016769650694479154, 'samples': 15569408, 'steps': 30408, 'batch_loss/train': 0.8520151400007308}
+12/26/2021 23:22:47 - INFO - codeparrot_training - Step 30409: {'lr': 0.00016768162268461447, 'samples': 15569920, 'steps': 30409, 'batch_loss/train': 0.7287234761752188}
+12/26/2021 23:22:58 - INFO - codeparrot_training - Step 30410: {'lr': 0.00016766673875170406, 'samples': 15570432, 'steps': 30410, 'batch_loss/train': 0.710415106615983}
+12/26/2021 23:23:10 - INFO - codeparrot_training - Step 30411: {'lr': 0.00016765185514611974, 'samples': 15570944, 'steps': 30411, 'batch_loss/train': 0.7998373750597239}
+12/26/2021 23:23:21 - INFO - codeparrot_training - Step 30412: {'lr': 0.00016763697186792043, 'samples': 15571456, 'steps': 30412, 'batch_loss/train': 0.8001595344394445}
+12/26/2021 23:23:31 - INFO - codeparrot_training - Step 30413: {'lr': 0.00016762208891716543, 'samples': 15571968, 'steps': 30413, 'batch_loss/train': 0.6736700907349586}
+12/26/2021 23:23:43 - INFO - codeparrot_training - Step 30414: {'lr': 0.00016760720629391398, 'samples': 15572480, 'steps': 30414, 'batch_loss/train': 0.6813257988542318}
+12/26/2021 23:23:54 - INFO - codeparrot_training - Step 30415: {'lr': 0.0001675923239982251, 'samples': 15572992, 'steps': 30415, 'batch_loss/train': 0.7733433274552226}
+12/26/2021 23:24:05 - INFO - codeparrot_training - Step 30416: {'lr': 0.000167577442030158, 'samples': 15573504, 'steps': 30416, 'batch_loss/train': 0.7530504707247019}
+12/26/2021 23:24:15 - INFO - codeparrot_training - Step 30417: {'lr': 0.00016756256038977197, 'samples': 15574016, 'steps': 30417, 'batch_loss/train': 0.7939586602151394}
+12/26/2021 23:24:27 - INFO - codeparrot_training - Step 30418: {'lr': 0.00016754767907712606, 'samples': 15574528, 'steps': 30418, 'batch_loss/train': 0.78902786411345}
+12/26/2021 23:24:38 - INFO - codeparrot_training - Step 30419: {'lr': 0.00016753279809227932, 'samples': 15575040, 'steps': 30419, 'batch_loss/train': 0.7901883223094046}
+12/26/2021 23:24:48 - INFO - codeparrot_training - Step 30420: {'lr': 0.00016751791743529112, 'samples': 15575552, 'steps': 30420, 'batch_loss/train': 0.7544458326883614}
+12/26/2021 23:25:02 - INFO - codeparrot_training - Step 30421: {'lr': 0.00016750303710622057, 'samples': 15576064, 'steps': 30421, 'batch_loss/train': 0.7267407760955393}
+12/26/2021 23:25:13 - INFO - codeparrot_training - Step 30422: {'lr': 0.00016748815710512677, 'samples': 15576576, 'steps': 30422, 'batch_loss/train': 0.7640627641230822}
+12/26/2021 23:25:23 - INFO - codeparrot_training - Step 30423: {'lr': 0.00016747327743206884, 'samples': 15577088, 'steps': 30423, 'batch_loss/train': 0.7210181271657348}
+12/26/2021 23:25:36 - INFO - codeparrot_training - Step 30424: {'lr': 0.00016745839808710608, 'samples': 15577600, 'steps': 30424, 'batch_loss/train': 0.8005913989618421}
+12/26/2021 23:25:46 - INFO - codeparrot_training - Step 30425: {'lr': 0.00016744351907029754, 'samples': 15578112, 'steps': 30425, 'batch_loss/train': 0.7619810588657856}
+12/26/2021 23:25:57 - INFO - codeparrot_training - Step 30426: {'lr': 0.0001674286403817024, 'samples': 15578624, 'steps': 30426, 'batch_loss/train': 0.6967713190242648}
+12/26/2021 23:26:11 - INFO - codeparrot_training - Step 30427: {'lr': 0.00016741376202137974, 'samples': 15579136, 'steps': 30427, 'batch_loss/train': 0.7998430440202355}
+12/26/2021 23:26:22 - INFO - codeparrot_training - Step 30428: {'lr': 0.0001673988839893889, 'samples': 15579648, 'steps': 30428, 'batch_loss/train': 0.7589839361608028}
+12/26/2021 23:26:32 - INFO - codeparrot_training - Step 30429: {'lr': 0.00016738400628578883, 'samples': 15580160, 'steps': 30429, 'batch_loss/train': 0.6821065288968384}
+12/26/2021 23:26:43 - INFO - codeparrot_training - Step 30430: {'lr': 0.0001673691289106387, 'samples': 15580672, 'steps': 30430, 'batch_loss/train': 0.8097657379694283}
+12/26/2021 23:26:55 - INFO - codeparrot_training - Step 30431: {'lr': 0.00016735425186399782, 'samples': 15581184, 'steps': 30431, 'batch_loss/train': 0.751464348519221}
+12/26/2021 23:27:06 - INFO - codeparrot_training - Step 30432: {'lr': 0.00016733937514592522, 'samples': 15581696, 'steps': 30432, 'batch_loss/train': 0.7272158656269312}
+12/26/2021 23:27:16 - INFO - codeparrot_training - Step 30433: {'lr': 0.00016732449875648007, 'samples': 15582208, 'steps': 30433, 'batch_loss/train': 0.8663795292377472}
+12/26/2021 23:27:28 - INFO - codeparrot_training - Step 30434: {'lr': 0.00016730962269572138, 'samples': 15582720, 'steps': 30434, 'batch_loss/train': 0.7927469653077424}
+12/26/2021 23:27:39 - INFO - codeparrot_training - Step 30435: {'lr': 0.00016729474696370849, 'samples': 15583232, 'steps': 30435, 'batch_loss/train': 0.8029588959179819}
+12/26/2021 23:27:50 - INFO - codeparrot_training - Step 30436: {'lr': 0.00016727987156050047, 'samples': 15583744, 'steps': 30436, 'batch_loss/train': 0.776198542676866}
+12/26/2021 23:28:03 - INFO - codeparrot_training - Step 30437: {'lr': 0.00016726499648615648, 'samples': 15584256, 'steps': 30437, 'batch_loss/train': 0.8480096980929375}
+12/26/2021 23:28:14 - INFO - codeparrot_training - Step 30438: {'lr': 0.0001672501217407355, 'samples': 15584768, 'steps': 30438, 'batch_loss/train': 0.7654904290102422}
+12/26/2021 23:28:25 - INFO - codeparrot_training - Step 30439: {'lr': 0.00016723524732429685, 'samples': 15585280, 'steps': 30439, 'batch_loss/train': 0.7022222420200706}
+12/26/2021 23:28:35 - INFO - codeparrot_training - Step 30440: {'lr': 0.00016722037323689965, 'samples': 15585792, 'steps': 30440, 'batch_loss/train': 0.6496235635131598}
+12/26/2021 23:28:47 - INFO - codeparrot_training - Step 30441: {'lr': 0.00016720549947860298, 'samples': 15586304, 'steps': 30441, 'batch_loss/train': 0.6743149543181062}
+12/26/2021 23:28:58 - INFO - codeparrot_training - Step 30442: {'lr': 0.00016719062604946588, 'samples': 15586816, 'steps': 30442, 'batch_loss/train': 0.64466555591207}
+12/26/2021 23:29:09 - INFO - codeparrot_training - Step 30443: {'lr': 0.0001671757529495477, 'samples': 15587328, 'steps': 30443, 'batch_loss/train': 0.7495721997693181}
+12/26/2021 23:29:23 - INFO - codeparrot_training - Step 30444: {'lr': 0.00016716088017890745, 'samples': 15587840, 'steps': 30444, 'batch_loss/train': 0.7318567750044167}
+12/26/2021 23:29:33 - INFO - codeparrot_training - Step 30445: {'lr': 0.0001671460077376042, 'samples': 15588352, 'steps': 30445, 'batch_loss/train': 0.642926600528881}
+12/26/2021 23:29:44 - INFO - codeparrot_training - Step 30446: {'lr': 0.0001671311356256971, 'samples': 15588864, 'steps': 30446, 'batch_loss/train': 0.7831369498744607}
+12/26/2021 23:29:56 - INFO - codeparrot_training - Step 30447: {'lr': 0.00016711626384324546, 'samples': 15589376, 'steps': 30447, 'batch_loss/train': 0.8400950599461794}
+12/26/2021 23:30:07 - INFO - codeparrot_training - Step 30448: {'lr': 0.00016710139239030816, 'samples': 15589888, 'steps': 30448, 'batch_loss/train': 0.8443474831874482}
+12/26/2021 23:30:17 - INFO - codeparrot_training - Step 30449: {'lr': 0.00016708652126694437, 'samples': 15590400, 'steps': 30449, 'batch_loss/train': 1.0454582823440433}
+12/26/2021 23:30:28 - INFO - codeparrot_training - Step 30450: {'lr': 0.00016707165047321338, 'samples': 15590912, 'steps': 30450, 'batch_loss/train': 0.7445238791406155}
+12/26/2021 23:30:40 - INFO - codeparrot_training - Step 30451: {'lr': 0.00016705678000917415, 'samples': 15591424, 'steps': 30451, 'batch_loss/train': 0.9690962387248874}
+12/26/2021 23:30:51 - INFO - codeparrot_training - Step 30452: {'lr': 0.00016704190987488587, 'samples': 15591936, 'steps': 30452, 'batch_loss/train': 0.7988529978320003}
+12/26/2021 23:31:01 - INFO - codeparrot_training - Step 30453: {'lr': 0.00016702704007040756, 'samples': 15592448, 'steps': 30453, 'batch_loss/train': 0.7540526804514229}
+12/26/2021 23:31:14 - INFO - codeparrot_training - Step 30454: {'lr': 0.0001670121705957985, 'samples': 15592960, 'steps': 30454, 'batch_loss/train': 0.7865419210866094}
+12/26/2021 23:31:24 - INFO - codeparrot_training - Step 30455: {'lr': 0.00016699730145111765, 'samples': 15593472, 'steps': 30455, 'batch_loss/train': 0.6928483406081796}
+12/26/2021 23:31:35 - INFO - codeparrot_training - Step 30456: {'lr': 0.00016698243263642414, 'samples': 15593984, 'steps': 30456, 'batch_loss/train': 0.7714017319958657}
+12/26/2021 23:31:49 - INFO - codeparrot_training - Step 30457: {'lr': 0.00016696756415177728, 'samples': 15594496, 'steps': 30457, 'batch_loss/train': 0.6110899240011349}
+12/26/2021 23:31:59 - INFO - codeparrot_training - Step 30458: {'lr': 0.00016695269599723594, 'samples': 15595008, 'steps': 30458, 'batch_loss/train': 0.726873129606247}
+12/26/2021 23:32:10 - INFO - codeparrot_training - Step 30459: {'lr': 0.00016693782817285937, 'samples': 15595520, 'steps': 30459, 'batch_loss/train': 0.7129095469135791}
+12/26/2021 23:32:20 - INFO - codeparrot_training - Step 30460: {'lr': 0.00016692296067870655, 'samples': 15596032, 'steps': 30460, 'batch_loss/train': 0.8127227071672678}
+12/26/2021 23:32:32 - INFO - codeparrot_training - Step 30461: {'lr': 0.00016690809351483672, 'samples': 15596544, 'steps': 30461, 'batch_loss/train': 0.7900870870798826}
+12/26/2021 23:32:43 - INFO - codeparrot_training - Step 30462: {'lr': 0.00016689322668130897, 'samples': 15597056, 'steps': 30462, 'batch_loss/train': 0.7312082047574222}
+12/26/2021 23:32:54 - INFO - codeparrot_training - Step 30463: {'lr': 0.00016687836017818236, 'samples': 15597568, 'steps': 30463, 'batch_loss/train': 0.7938750358298421}
+12/26/2021 23:33:06 - INFO - codeparrot_training - Step 30464: {'lr': 0.00016686349400551592, 'samples': 15598080, 'steps': 30464, 'batch_loss/train': 0.5672712509986013}
+12/26/2021 23:33:16 - INFO - codeparrot_training - Step 30465: {'lr': 0.0001668486281633689, 'samples': 15598592, 'steps': 30465, 'batch_loss/train': 0.8273929050192237}
+12/26/2021 23:33:27 - INFO - codeparrot_training - Step 30466: {'lr': 0.0001668337626518004, 'samples': 15599104, 'steps': 30466, 'batch_loss/train': 0.677532846108079}
+12/26/2021 23:33:41 - INFO - codeparrot_training - Step 30467: {'lr': 0.00016681889747086932, 'samples': 15599616, 'steps': 30467, 'batch_loss/train': 0.9333339212462306}
+12/26/2021 23:33:51 - INFO - codeparrot_training - Step 30468: {'lr': 0.00016680403262063495, 'samples': 15600128, 'steps': 30468, 'batch_loss/train': 0.8461117194965482}
+12/26/2021 23:34:02 - INFO - codeparrot_training - Step 30469: {'lr': 0.0001667891681011564, 'samples': 15600640, 'steps': 30469, 'batch_loss/train': 0.8172977520152926}
+12/26/2021 23:34:13 - INFO - codeparrot_training - Step 30470: {'lr': 0.00016677430391249265, 'samples': 15601152, 'steps': 30470, 'batch_loss/train': 0.7199551428493578}
+12/26/2021 23:34:25 - INFO - codeparrot_training - Step 30471: {'lr': 0.0001667594400547028, 'samples': 15601664, 'steps': 30471, 'batch_loss/train': 0.7095055533573031}
+12/26/2021 23:34:35 - INFO - codeparrot_training - Step 30472: {'lr': 0.00016674457652784605, 'samples': 15602176, 'steps': 30472, 'batch_loss/train': 0.7600930836051702}
+12/26/2021 23:34:46 - INFO - codeparrot_training - Step 30473: {'lr': 0.00016672971333198144, 'samples': 15602688, 'steps': 30473, 'batch_loss/train': 0.885420442558825}
+12/26/2021 23:35:00 - INFO - codeparrot_training - Step 30474: {'lr': 0.000166714850467168, 'samples': 15603200, 'steps': 30474, 'batch_loss/train': 0.7727569499984384}
+12/26/2021 23:35:11 - INFO - codeparrot_training - Step 30475: {'lr': 0.00016669998793346482, 'samples': 15603712, 'steps': 30475, 'batch_loss/train': 0.7679472751915455}
+12/26/2021 23:35:21 - INFO - codeparrot_training - Step 30476: {'lr': 0.00016668512573093114, 'samples': 15604224, 'steps': 30476, 'batch_loss/train': 0.9210673263296485}
+12/26/2021 23:35:34 - INFO - codeparrot_training - Step 30477: {'lr': 0.0001666702638596259, 'samples': 15604736, 'steps': 30477, 'batch_loss/train': 0.7888710550032556}
+12/26/2021 23:35:44 - INFO - codeparrot_training - Step 30478: {'lr': 0.00016665540231960827, 'samples': 15605248, 'steps': 30478, 'batch_loss/train': 0.6968195559456944}
+12/26/2021 23:35:55 - INFO - codeparrot_training - Step 30479: {'lr': 0.0001666405411109372, 'samples': 15605760, 'steps': 30479, 'batch_loss/train': 0.8031116253696382}
+12/26/2021 23:36:05 - INFO - codeparrot_training - Step 30480: {'lr': 0.00016662568023367188, 'samples': 15606272, 'steps': 30480, 'batch_loss/train': 0.7141737155616283}
+12/26/2021 23:36:18 - INFO - codeparrot_training - Step 30481: {'lr': 0.00016661081968787146, 'samples': 15606784, 'steps': 30481, 'batch_loss/train': 0.7285800736863166}
+12/26/2021 23:36:28 - INFO - codeparrot_training - Step 30482: {'lr': 0.0001665959594735948, 'samples': 15607296, 'steps': 30482, 'batch_loss/train': 0.7097166208550334}
+12/26/2021 23:36:39 - INFO - codeparrot_training - Step 30483: {'lr': 0.00016658109959090124, 'samples': 15607808, 'steps': 30483, 'batch_loss/train': 0.7637602312024683}
+12/26/2021 23:36:53 - INFO - codeparrot_training - Step 30484: {'lr': 0.00016656624003984967, 'samples': 15608320, 'steps': 30484, 'batch_loss/train': 0.752293320838362}
+12/26/2021 23:37:03 - INFO - codeparrot_training - Step 30485: {'lr': 0.0001665513808204993, 'samples': 15608832, 'steps': 30485, 'batch_loss/train': 0.7566982920980081}
+12/26/2021 23:37:14 - INFO - codeparrot_training - Step 30486: {'lr': 0.000166536521932909, 'samples': 15609344, 'steps': 30486, 'batch_loss/train': 0.7562190787866712}
+12/26/2021 23:37:26 - INFO - codeparrot_training - Step 30487: {'lr': 0.00016652166337713804, 'samples': 15609856, 'steps': 30487, 'batch_loss/train': 0.7546584326773882}
+12/26/2021 23:37:37 - INFO - codeparrot_training - Step 30488: {'lr': 0.00016650680515324545, 'samples': 15610368, 'steps': 30488, 'batch_loss/train': 0.7720594676211476}
+12/26/2021 23:37:47 - INFO - codeparrot_training - Step 30489: {'lr': 0.0001664919472612903, 'samples': 15610880, 'steps': 30489, 'batch_loss/train': 0.8496150011196733}
+12/26/2021 23:37:59 - INFO - codeparrot_training - Step 30490: {'lr': 0.00016647708970133154, 'samples': 15611392, 'steps': 30490, 'batch_loss/train': 0.7078951571602374}
+12/26/2021 23:38:10 - INFO - codeparrot_training - Step 30491: {'lr': 0.00016646223247342837, 'samples': 15611904, 'steps': 30491, 'batch_loss/train': 0.8080749213695526}
+12/26/2021 23:38:21 - INFO - codeparrot_training - Step 30492: {'lr': 0.00016644737557763988, 'samples': 15612416, 'steps': 30492, 'batch_loss/train': 0.738821295555681}
+12/26/2021 23:38:31 - INFO - codeparrot_training - Step 30493: {'lr': 0.00016643251901402498, 'samples': 15612928, 'steps': 30493, 'batch_loss/train': 0.7825767518952489}
+12/26/2021 23:38:43 - INFO - codeparrot_training - Step 30494: {'lr': 0.00016641766278264287, 'samples': 15613440, 'steps': 30494, 'batch_loss/train': 0.7771296501159668}
+12/26/2021 23:38:54 - INFO - codeparrot_training - Step 30495: {'lr': 0.00016640280688355263, 'samples': 15613952, 'steps': 30495, 'batch_loss/train': 0.7018483718857169}
+12/26/2021 23:39:05 - INFO - codeparrot_training - Step 30496: {'lr': 0.0001663879513168132, 'samples': 15614464, 'steps': 30496, 'batch_loss/train': 0.7980988165363669}
+12/26/2021 23:39:19 - INFO - codeparrot_training - Step 30497: {'lr': 0.0001663730960824837, 'samples': 15614976, 'steps': 30497, 'batch_loss/train': 0.6297385348298121}
+12/26/2021 23:39:29 - INFO - codeparrot_training - Step 30498: {'lr': 0.00016635824118062327, 'samples': 15615488, 'steps': 30498, 'batch_loss/train': 0.7581208101473749}
+12/26/2021 23:39:40 - INFO - codeparrot_training - Step 30499: {'lr': 0.00016634338661129086, 'samples': 15616000, 'steps': 30499, 'batch_loss/train': 0.8157514980994165}
+12/26/2021 23:39:52 - INFO - codeparrot_training - Step 30500: {'lr': 0.00016632853237454553, 'samples': 15616512, 'steps': 30500, 'batch_loss/train': 0.7329970365390182}
+12/26/2021 23:40:03 - INFO - codeparrot_training - Step 30501: {'lr': 0.00016631367847044632, 'samples': 15617024, 'steps': 30501, 'batch_loss/train': 0.7616530945524573}
+12/26/2021 23:40:13 - INFO - codeparrot_training - Step 30502: {'lr': 0.0001662988248990524, 'samples': 15617536, 'steps': 30502, 'batch_loss/train': 0.8316608276218176}
+12/26/2021 23:40:27 - INFO - codeparrot_training - Step 30503: {'lr': 0.00016628397166042276, 'samples': 15618048, 'steps': 30503, 'batch_loss/train': 0.7109505590051413}
+12/26/2021 23:40:38 - INFO - codeparrot_training - Step 30504: {'lr': 0.0001662691187546163, 'samples': 15618560, 'steps': 30504, 'batch_loss/train': 0.7271362829487771}
+12/26/2021 23:40:49 - INFO - codeparrot_training - Step 30505: {'lr': 0.00016625426618169237, 'samples': 15619072, 'steps': 30505, 'batch_loss/train': 0.7892314530909061}
+12/26/2021 23:40:59 - INFO - codeparrot_training - Step 30506: {'lr': 0.0001662394139417098, 'samples': 15619584, 'steps': 30506, 'batch_loss/train': 0.7760427799075842}
+12/26/2021 23:41:11 - INFO - codeparrot_training - Step 30507: {'lr': 0.00016622456203472773, 'samples': 15620096, 'steps': 30507, 'batch_loss/train': 0.7651226622983813}
+12/26/2021 23:41:22 - INFO - codeparrot_training - Step 30508: {'lr': 0.00016620971046080508, 'samples': 15620608, 'steps': 30508, 'batch_loss/train': 0.8186481632292271}
+12/26/2021 23:41:33 - INFO - codeparrot_training - Step 30509: {'lr': 0.00016619485922000104, 'samples': 15621120, 'steps': 30509, 'batch_loss/train': 0.7571031767874956}
+12/26/2021 23:41:45 - INFO - codeparrot_training - Step 30510: {'lr': 0.00016618000831237462, 'samples': 15621632, 'steps': 30510, 'batch_loss/train': 0.723425735719502}
+12/26/2021 23:41:55 - INFO - codeparrot_training - Step 30511: {'lr': 0.00016616515773798486, 'samples': 15622144, 'steps': 30511, 'batch_loss/train': 0.8259640750475228}
+12/26/2021 23:42:06 - INFO - codeparrot_training - Step 30512: {'lr': 0.00016615030749689063, 'samples': 15622656, 'steps': 30512, 'batch_loss/train': 0.707457063253969}
+12/26/2021 23:42:20 - INFO - codeparrot_training - Step 30513: {'lr': 0.00016613545758915123, 'samples': 15623168, 'steps': 30513, 'batch_loss/train': 0.6972046853043139}
+12/26/2021 23:42:31 - INFO - codeparrot_training - Step 30514: {'lr': 0.0001661206080148256, 'samples': 15623680, 'steps': 30514, 'batch_loss/train': 0.8264711005613208}
+12/26/2021 23:42:41 - INFO - codeparrot_training - Step 30515: {'lr': 0.0001661057587739727, 'samples': 15624192, 'steps': 30515, 'batch_loss/train': 0.6457669390365481}
+12/26/2021 23:42:52 - INFO - codeparrot_training - Step 30516: {'lr': 0.0001660909098666516, 'samples': 15624704, 'steps': 30516, 'batch_loss/train': 0.7880122531205416}
+12/26/2021 23:43:04 - INFO - codeparrot_training - Step 30517: {'lr': 0.00016607606129292148, 'samples': 15625216, 'steps': 30517, 'batch_loss/train': 0.8323951596394181}
+12/26/2021 23:43:15 - INFO - codeparrot_training - Step 30518: {'lr': 0.00016606121305284122, 'samples': 15625728, 'steps': 30518, 'batch_loss/train': 0.7508040834218264}
+12/26/2021 23:43:25 - INFO - codeparrot_training - Step 30519: {'lr': 0.0001660463651464698, 'samples': 15626240, 'steps': 30519, 'batch_loss/train': 0.7554784929379821}
+12/26/2021 23:43:37 - INFO - codeparrot_training - Step 30520: {'lr': 0.00016603151757386636, 'samples': 15626752, 'steps': 30520, 'batch_loss/train': 0.7923707459121943}
+12/26/2021 23:43:48 - INFO - codeparrot_training - Step 30521: {'lr': 0.00016601667033508996, 'samples': 15627264, 'steps': 30521, 'batch_loss/train': 0.6494198588188738}
+12/26/2021 23:43:59 - INFO - codeparrot_training - Step 30522: {'lr': 0.00016600182343019953, 'samples': 15627776, 'steps': 30522, 'batch_loss/train': 0.8244441758142784}
+12/26/2021 23:44:13 - INFO - codeparrot_training - Step 30523: {'lr': 0.00016598697685925407, 'samples': 15628288, 'steps': 30523, 'batch_loss/train': 0.7291449401527643}
+12/26/2021 23:44:23 - INFO - codeparrot_training - Step 30524: {'lr': 0.00016597213062231276, 'samples': 15628800, 'steps': 30524, 'batch_loss/train': 0.8263470539823174}
+12/26/2021 23:44:34 - INFO - codeparrot_training - Step 30525: {'lr': 0.0001659572847194345, 'samples': 15629312, 'steps': 30525, 'batch_loss/train': 0.7884634928777814}
+12/26/2021 23:44:45 - INFO - codeparrot_training - Step 30526: {'lr': 0.00016594243915067842, 'samples': 15629824, 'steps': 30526, 'batch_loss/train': 0.7860724618658423}
+12/26/2021 23:44:57 - INFO - codeparrot_training - Step 30527: {'lr': 0.0001659275939161033, 'samples': 15630336, 'steps': 30527, 'batch_loss/train': 0.975614276714623}
+12/26/2021 23:45:08 - INFO - codeparrot_training - Step 30528: {'lr': 0.00016591274901576848, 'samples': 15630848, 'steps': 30528, 'batch_loss/train': 0.7630142383277416}
+12/26/2021 23:45:18 - INFO - codeparrot_training - Step 30529: {'lr': 0.00016589790444973272, 'samples': 15631360, 'steps': 30529, 'batch_loss/train': 0.7673402444925159}
+12/26/2021 23:45:30 - INFO - codeparrot_training - Step 30530: {'lr': 0.0001658830602180551, 'samples': 15631872, 'steps': 30530, 'batch_loss/train': 0.754888859577477}
+12/26/2021 23:45:41 - INFO - codeparrot_training - Step 30531: {'lr': 0.0001658682163207948, 'samples': 15632384, 'steps': 30531, 'batch_loss/train': 0.6859216887387447}
+12/26/2021 23:45:52 - INFO - codeparrot_training - Step 30532: {'lr': 0.0001658533727580106, 'samples': 15632896, 'steps': 30532, 'batch_loss/train': 0.7559486776590347}
+12/26/2021 23:46:05 - INFO - codeparrot_training - Step 30533: {'lr': 0.00016583852952976172, 'samples': 15633408, 'steps': 30533, 'batch_loss/train': 0.7516771778464317}
+12/26/2021 23:46:16 - INFO - codeparrot_training - Step 30534: {'lr': 0.00016582368663610694, 'samples': 15633920, 'steps': 30534, 'batch_loss/train': 0.8068866138346493}
+12/26/2021 23:46:27 - INFO - codeparrot_training - Step 30535: {'lr': 0.0001658088440771055, 'samples': 15634432, 'steps': 30535, 'batch_loss/train': 0.6918726083822548}
+12/26/2021 23:46:37 - INFO - codeparrot_training - Step 30536: {'lr': 0.0001657940018528163, 'samples': 15634944, 'steps': 30536, 'batch_loss/train': 0.7127158502116799}
+12/26/2021 23:46:49 - INFO - codeparrot_training - Step 30537: {'lr': 0.00016577915996329834, 'samples': 15635456, 'steps': 30537, 'batch_loss/train': 0.7626612549647689}
+12/26/2021 23:47:00 - INFO - codeparrot_training - Step 30538: {'lr': 0.00016576431840861056, 'samples': 15635968, 'steps': 30538, 'batch_loss/train': 0.7229328724788502}
+12/26/2021 23:47:11 - INFO - codeparrot_training - Step 30539: {'lr': 0.00016574947718881212, 'samples': 15636480, 'steps': 30539, 'batch_loss/train': 0.6478317846776918}
+12/26/2021 23:47:23 - INFO - codeparrot_training - Step 30540: {'lr': 0.00016573463630396195, 'samples': 15636992, 'steps': 30540, 'batch_loss/train': 0.7974648009985685}
+12/26/2021 23:47:33 - INFO - codeparrot_training - Step 30541: {'lr': 0.000165719795754119, 'samples': 15637504, 'steps': 30541, 'batch_loss/train': 0.6562700891518034}
+12/26/2021 23:47:44 - INFO - codeparrot_training - Step 30542: {'lr': 0.00016570495553934234, 'samples': 15638016, 'steps': 30542, 'batch_loss/train': 0.6532367204781622}
+12/26/2021 23:47:58 - INFO - codeparrot_training - Step 30543: {'lr': 0.000165690115659691, 'samples': 15638528, 'steps': 30543, 'batch_loss/train': 0.714112572837621}
+12/26/2021 23:48:09 - INFO - codeparrot_training - Step 30544: {'lr': 0.00016567527611522392, 'samples': 15639040, 'steps': 30544, 'batch_loss/train': 0.7337025988381356}
+12/26/2021 23:48:19 - INFO - codeparrot_training - Step 30545: {'lr': 0.00016566043690600002, 'samples': 15639552, 'steps': 30545, 'batch_loss/train': 0.7547266306355596}
+12/26/2021 23:48:30 - INFO - codeparrot_training - Step 30546: {'lr': 0.00016564559803207844, 'samples': 15640064, 'steps': 30546, 'batch_loss/train': 0.6096406517899595}
+12/26/2021 23:48:42 - INFO - codeparrot_training - Step 30547: {'lr': 0.00016563075949351812, 'samples': 15640576, 'steps': 30547, 'batch_loss/train': 0.7833166387281381}
+12/26/2021 23:48:53 - INFO - codeparrot_training - Step 30548: {'lr': 0.00016561592129037803, 'samples': 15641088, 'steps': 30548, 'batch_loss/train': 0.7509008585475385}
+12/26/2021 23:49:03 - INFO - codeparrot_training - Step 30549: {'lr': 0.00016560108342271711, 'samples': 15641600, 'steps': 30549, 'batch_loss/train': 0.8010374333243817}
+12/26/2021 23:49:15 - INFO - codeparrot_training - Step 30550: {'lr': 0.00016558624589059452, 'samples': 15642112, 'steps': 30550, 'batch_loss/train': 0.78069659601897}
+12/26/2021 23:49:26 - INFO - codeparrot_training - Step 30551: {'lr': 0.00016557140869406908, 'samples': 15642624, 'steps': 30551, 'batch_loss/train': 0.7584557815571316}
+12/26/2021 23:49:37 - INFO - codeparrot_training - Step 30552: {'lr': 0.00016555657183319988, 'samples': 15643136, 'steps': 30552, 'batch_loss/train': 0.7605905525851995}
+12/26/2021 23:49:51 - INFO - codeparrot_training - Step 30553: {'lr': 0.00016554173530804582, 'samples': 15643648, 'steps': 30553, 'batch_loss/train': 0.7879759510979056}
+12/26/2021 23:50:01 - INFO - codeparrot_training - Step 30554: {'lr': 0.00016552689911866598, 'samples': 15644160, 'steps': 30554, 'batch_loss/train': 0.7540164571255445}
+12/26/2021 23:50:12 - INFO - codeparrot_training - Step 30555: {'lr': 0.00016551206326511926, 'samples': 15644672, 'steps': 30555, 'batch_loss/train': 0.7237034541321918}
+12/26/2021 23:50:24 - INFO - codeparrot_training - Step 30556: {'lr': 0.00016549722774746462, 'samples': 15645184, 'steps': 30556, 'batch_loss/train': 0.7816982325166464}
+12/26/2021 23:50:35 - INFO - codeparrot_training - Step 30557: {'lr': 0.0001654823925657612, 'samples': 15645696, 'steps': 30557, 'batch_loss/train': 0.748059808742255}
+12/26/2021 23:50:45 - INFO - codeparrot_training - Step 30558: {'lr': 0.00016546755772006783, 'samples': 15646208, 'steps': 30558, 'batch_loss/train': 0.8597570583224297}
+12/26/2021 23:50:56 - INFO - codeparrot_training - Step 30559: {'lr': 0.00016545272321044359, 'samples': 15646720, 'steps': 30559, 'batch_loss/train': 0.8099596640095115}
+12/26/2021 23:51:10 - INFO - codeparrot_training - Step 30560: {'lr': 0.00016543788903694725, 'samples': 15647232, 'steps': 30560, 'batch_loss/train': 0.6863399036228657}
+12/26/2021 23:51:21 - INFO - codeparrot_training - Step 30561: {'lr': 0.000165423055199638, 'samples': 15647744, 'steps': 30561, 'batch_loss/train': 0.825993447448127}
+12/26/2021 23:51:31 - INFO - codeparrot_training - Step 30562: {'lr': 0.00016540822169857483, 'samples': 15648256, 'steps': 30562, 'batch_loss/train': 0.8933410085737705}
+12/26/2021 23:51:43 - INFO - codeparrot_training - Step 30563: {'lr': 0.00016539338853381664, 'samples': 15648768, 'steps': 30563, 'batch_loss/train': 0.9282791432924569}
+12/26/2021 23:51:54 - INFO - codeparrot_training - Step 30564: {'lr': 0.00016537855570542226, 'samples': 15649280, 'steps': 30564, 'batch_loss/train': 0.7838929882273078}
+12/26/2021 23:52:05 - INFO - codeparrot_training - Step 30565: {'lr': 0.00016536372321345085, 'samples': 15649792, 'steps': 30565, 'batch_loss/train': 0.7055733827874064}
+12/26/2021 23:52:17 - INFO - codeparrot_training - Step 30566: {'lr': 0.00016534889105796136, 'samples': 15650304, 'steps': 30566, 'batch_loss/train': 0.7812752788886428}
+12/26/2021 23:52:27 - INFO - codeparrot_training - Step 30567: {'lr': 0.00016533405923901262, 'samples': 15650816, 'steps': 30567, 'batch_loss/train': 0.836799256503582}
+12/26/2021 23:52:38 - INFO - codeparrot_training - Step 30568: {'lr': 0.00016531922775666374, 'samples': 15651328, 'steps': 30568, 'batch_loss/train': 0.7327574114315212}
+12/26/2021 23:52:48 - INFO - codeparrot_training - Step 30569: {'lr': 0.00016530439661097368, 'samples': 15651840, 'steps': 30569, 'batch_loss/train': 0.62836500024423}
+12/26/2021 23:53:01 - INFO - codeparrot_training - Step 30570: {'lr': 0.00016528956580200138, 'samples': 15652352, 'steps': 30570, 'batch_loss/train': 0.8019597912207246}
+12/26/2021 23:53:11 - INFO - codeparrot_training - Step 30571: {'lr': 0.00016527473532980565, 'samples': 15652864, 'steps': 30571, 'batch_loss/train': 0.8015092797577381}
+12/26/2021 23:53:22 - INFO - codeparrot_training - Step 30572: {'lr': 0.00016525990519444567, 'samples': 15653376, 'steps': 30572, 'batch_loss/train': 0.7039557038806379}
+12/26/2021 23:53:36 - INFO - codeparrot_training - Step 30573: {'lr': 0.00016524507539598032, 'samples': 15653888, 'steps': 30573, 'batch_loss/train': 0.7812421293929219}
+12/26/2021 23:53:46 - INFO - codeparrot_training - Step 30574: {'lr': 0.00016523024593446853, 'samples': 15654400, 'steps': 30574, 'batch_loss/train': 0.767178145237267}
+12/26/2021 23:53:57 - INFO - codeparrot_training - Step 30575: {'lr': 0.0001652154168099692, 'samples': 15654912, 'steps': 30575, 'batch_loss/train': 0.83501638751477}
+12/26/2021 23:54:09 - INFO - codeparrot_training - Step 30576: {'lr': 0.00016520058802254147, 'samples': 15655424, 'steps': 30576, 'batch_loss/train': 0.6458901287987828}
+12/26/2021 23:54:20 - INFO - codeparrot_training - Step 30577: {'lr': 0.00016518575957224414, 'samples': 15655936, 'steps': 30577, 'batch_loss/train': 0.8007586263120174}
+12/26/2021 23:54:30 - INFO - codeparrot_training - Step 30578: {'lr': 0.00016517093145913613, 'samples': 15656448, 'steps': 30578, 'batch_loss/train': 0.7980684586800635}
+12/26/2021 23:54:41 - INFO - codeparrot_training - Step 30579: {'lr': 0.0001651561036832766, 'samples': 15656960, 'steps': 30579, 'batch_loss/train': 0.7237235470674932}
+12/26/2021 23:54:53 - INFO - codeparrot_training - Step 30580: {'lr': 0.00016514127624472436, 'samples': 15657472, 'steps': 30580, 'batch_loss/train': 0.7461907309480011}
+12/26/2021 23:55:03 - INFO - codeparrot_training - Step 30581: {'lr': 0.0001651264491435383, 'samples': 15657984, 'steps': 30581, 'batch_loss/train': 0.7080123984487727}
+12/26/2021 23:55:14 - INFO - codeparrot_training - Step 30582: {'lr': 0.0001651116223797774, 'samples': 15658496, 'steps': 30582, 'batch_loss/train': 1.0292422394268215}
+12/26/2021 23:55:27 - INFO - codeparrot_training - Step 30583: {'lr': 0.00016509679595350075, 'samples': 15659008, 'steps': 30583, 'batch_loss/train': 0.7324570929631591}
+12/26/2021 23:55:38 - INFO - codeparrot_training - Step 30584: {'lr': 0.00016508196986476708, 'samples': 15659520, 'steps': 30584, 'batch_loss/train': 0.6899360418319702}
+12/26/2021 23:55:49 - INFO - codeparrot_training - Step 30585: {'lr': 0.00016506714411363552, 'samples': 15660032, 'steps': 30585, 'batch_loss/train': 0.7563235173001885}
+12/26/2021 23:56:01 - INFO - codeparrot_training - Step 30586: {'lr': 0.0001650523187001648, 'samples': 15660544, 'steps': 30586, 'batch_loss/train': 0.7276992332190275}
+12/26/2021 23:56:11 - INFO - codeparrot_training - Step 30587: {'lr': 0.00016503749362441406, 'samples': 15661056, 'steps': 30587, 'batch_loss/train': 0.7898718304932117}
+12/26/2021 23:56:22 - INFO - codeparrot_training - Step 30588: {'lr': 0.0001650226688864422, 'samples': 15661568, 'steps': 30588, 'batch_loss/train': 0.7913267826661468}
+12/26/2021 23:56:32 - INFO - codeparrot_training - Step 30589: {'lr': 0.0001650078444863081, 'samples': 15662080, 'steps': 30589, 'batch_loss/train': 0.7904033865779638}
+12/26/2021 23:56:46 - INFO - codeparrot_training - Step 30590: {'lr': 0.0001649930204240707, 'samples': 15662592, 'steps': 30590, 'batch_loss/train': 0.7426213724538684}
+12/26/2021 23:56:57 - INFO - codeparrot_training - Step 30591: {'lr': 0.00016497819669978892, 'samples': 15663104, 'steps': 30591, 'batch_loss/train': 0.7175329250749201}
+12/26/2021 23:57:08 - INFO - codeparrot_training - Step 30592: {'lr': 0.00016496337331352185, 'samples': 15663616, 'steps': 30592, 'batch_loss/train': 0.6877839625813067}
+12/26/2021 23:57:20 - INFO - codeparrot_training - Step 30593: {'lr': 0.00016494855026532812, 'samples': 15664128, 'steps': 30593, 'batch_loss/train': 0.7173084244132042}
+12/26/2021 23:57:30 - INFO - codeparrot_training - Step 30594: {'lr': 0.00016493372755526693, 'samples': 15664640, 'steps': 30594, 'batch_loss/train': 0.8038392621092498}
+12/26/2021 23:57:41 - INFO - codeparrot_training - Step 30595: {'lr': 0.00016491890518339719, 'samples': 15665152, 'steps': 30595, 'batch_loss/train': 0.8194242818281054}
+12/26/2021 23:57:53 - INFO - codeparrot_training - Step 30596: {'lr': 0.00016490408314977768, 'samples': 15665664, 'steps': 30596, 'batch_loss/train': 0.8014969825744629}
+12/26/2021 23:58:04 - INFO - codeparrot_training - Step 30597: {'lr': 0.00016488926145446736, 'samples': 15666176, 'steps': 30597, 'batch_loss/train': 0.7432472105138004}
+12/26/2021 23:58:14 - INFO - codeparrot_training - Step 30598: {'lr': 0.00016487444009752528, 'samples': 15666688, 'steps': 30598, 'batch_loss/train': 0.7665765850106254}
+12/26/2021 23:58:25 - INFO - codeparrot_training - Step 30599: {'lr': 0.0001648596190790103, 'samples': 15667200, 'steps': 30599, 'batch_loss/train': 0.8175449501723051}
+12/26/2021 23:58:39 - INFO - codeparrot_training - Step 30600: {'lr': 0.0001648447983989813, 'samples': 15667712, 'steps': 30600, 'batch_loss/train': 0.6754542253911495}
+12/26/2021 23:58:50 - INFO - codeparrot_training - Step 30601: {'lr': 0.00016482997805749715, 'samples': 15668224, 'steps': 30601, 'batch_loss/train': 0.48433887981809676}
+12/26/2021 23:59:00 - INFO - codeparrot_training - Step 30602: {'lr': 0.00016481515805461693, 'samples': 15668736, 'steps': 30602, 'batch_loss/train': 0.597506923484616}
+12/26/2021 23:59:13 - INFO - codeparrot_training - Step 30603: {'lr': 0.0001648003383903995, 'samples': 15669248, 'steps': 30603, 'batch_loss/train': 0.7370040656533092}
+12/26/2021 23:59:23 - INFO - codeparrot_training - Step 30604: {'lr': 0.00016478551906490364, 'samples': 15669760, 'steps': 30604, 'batch_loss/train': 0.645355440035928}
+12/26/2021 23:59:34 - INFO - codeparrot_training - Step 30605: {'lr': 0.00016477070007818852, 'samples': 15670272, 'steps': 30605, 'batch_loss/train': 0.8864666409790516}
+12/26/2021 23:59:46 - INFO - codeparrot_training - Step 30606: {'lr': 0.00016475588143031282, 'samples': 15670784, 'steps': 30606, 'batch_loss/train': 0.808967188000679}
+12/26/2021 23:59:57 - INFO - codeparrot_training - Step 30607: {'lr': 0.00016474106312133562, 'samples': 15671296, 'steps': 30607, 'batch_loss/train': 0.9342397348955274}
+12/27/2021 00:00:07 - INFO - codeparrot_training - Step 30608: {'lr': 0.00016472624515131566, 'samples': 15671808, 'steps': 30608, 'batch_loss/train': 0.7565833814442158}
+12/27/2021 00:00:18 - INFO - codeparrot_training - Step 30609: {'lr': 0.00016471142752031204, 'samples': 15672320, 'steps': 30609, 'batch_loss/train': 0.7412891276180744}
+12/27/2021 00:00:32 - INFO - codeparrot_training - Step 30610: {'lr': 0.00016469661022838357, 'samples': 15672832, 'steps': 30610, 'batch_loss/train': 0.7930377947632223}
+12/27/2021 00:00:42 - INFO - codeparrot_training - Step 30611: {'lr': 0.0001646817932755892, 'samples': 15673344, 'steps': 30611, 'batch_loss/train': 0.7553656827658415}
+12/27/2021 00:00:53 - INFO - codeparrot_training - Step 30612: {'lr': 0.00016466697666198766, 'samples': 15673856, 'steps': 30612, 'batch_loss/train': 0.6915016373386607}
+12/27/2021 00:01:05 - INFO - codeparrot_training - Step 30613: {'lr': 0.0001646521603876381, 'samples': 15674368, 'steps': 30613, 'batch_loss/train': 0.819216487929225}
+12/27/2021 00:01:16 - INFO - codeparrot_training - Step 30614: {'lr': 0.00016463734445259937, 'samples': 15674880, 'steps': 30614, 'batch_loss/train': 0.7304168334230781}
+12/27/2021 00:01:26 - INFO - codeparrot_training - Step 30615: {'lr': 0.00016462252885693018, 'samples': 15675392, 'steps': 30615, 'batch_loss/train': 0.7064919555559754}
+12/27/2021 00:01:39 - INFO - codeparrot_training - Step 30616: {'lr': 0.00016460771360068973, 'samples': 15675904, 'steps': 30616, 'batch_loss/train': 0.6777270098682493}
+12/27/2021 00:01:49 - INFO - codeparrot_training - Step 30617: {'lr': 0.00016459289868393673, 'samples': 15676416, 'steps': 30617, 'batch_loss/train': 0.7308497936464846}
+12/27/2021 00:02:00 - INFO - codeparrot_training - Step 30618: {'lr': 0.00016457808410673015, 'samples': 15676928, 'steps': 30618, 'batch_loss/train': 0.8203815794549882}
+12/27/2021 00:02:14 - INFO - codeparrot_training - Step 30619: {'lr': 0.00016456326986912873, 'samples': 15677440, 'steps': 30619, 'batch_loss/train': 0.716071140486747}
+12/27/2021 00:02:24 - INFO - codeparrot_training - Step 30620: {'lr': 0.00016454845597119156, 'samples': 15677952, 'steps': 30620, 'batch_loss/train': 0.6438308507204056}
+12/27/2021 00:02:35 - INFO - codeparrot_training - Step 30621: {'lr': 0.00016453364241297746, 'samples': 15678464, 'steps': 30621, 'batch_loss/train': 0.7448357627727091}
+12/27/2021 00:02:46 - INFO - codeparrot_training - Step 30622: {'lr': 0.00016451882919454536, 'samples': 15678976, 'steps': 30622, 'batch_loss/train': 0.6836877157911658}
+12/27/2021 00:02:58 - INFO - codeparrot_training - Step 30623: {'lr': 0.000164504016315954, 'samples': 15679488, 'steps': 30623, 'batch_loss/train': 0.6715410231263377}
+12/27/2021 00:03:08 - INFO - codeparrot_training - Step 30624: {'lr': 0.00016448920377726256, 'samples': 15680000, 'steps': 30624, 'batch_loss/train': 0.7180749094113708}
+12/27/2021 00:03:19 - INFO - codeparrot_training - Step 30625: {'lr': 0.00016447439157852973, 'samples': 15680512, 'steps': 30625, 'batch_loss/train': 0.9870774019509554}
+12/27/2021 00:03:31 - INFO - codeparrot_training - Step 30626: {'lr': 0.00016445957971981435, 'samples': 15681024, 'steps': 30626, 'batch_loss/train': 0.8315054774284363}
+12/27/2021 00:03:42 - INFO - codeparrot_training - Step 30627: {'lr': 0.00016444476820117533, 'samples': 15681536, 'steps': 30627, 'batch_loss/train': 0.689970220439136}
+12/27/2021 00:03:52 - INFO - codeparrot_training - Step 30628: {'lr': 0.00016442995702267173, 'samples': 15682048, 'steps': 30628, 'batch_loss/train': 0.7069191108457744}
+12/27/2021 00:04:06 - INFO - codeparrot_training - Step 30629: {'lr': 0.00016441514618436225, 'samples': 15682560, 'steps': 30629, 'batch_loss/train': 0.7637327616102993}
+12/27/2021 00:04:17 - INFO - codeparrot_training - Step 30630: {'lr': 0.0001644003356863058, 'samples': 15683072, 'steps': 30630, 'batch_loss/train': 0.7515502593014389}
+12/27/2021 00:04:28 - INFO - codeparrot_training - Step 30631: {'lr': 0.0001643855255285614, 'samples': 15683584, 'steps': 30631, 'batch_loss/train': 0.8343311632052064}
+12/27/2021 00:04:38 - INFO - codeparrot_training - Step 30632: {'lr': 0.00016437071571118772, 'samples': 15684096, 'steps': 30632, 'batch_loss/train': 0.7845033146440983}
+12/27/2021 00:04:50 - INFO - codeparrot_training - Step 30633: {'lr': 0.00016435590623424385, 'samples': 15684608, 'steps': 30633, 'batch_loss/train': 0.7781083029694855}
+12/27/2021 00:05:01 - INFO - codeparrot_training - Step 30634: {'lr': 0.00016434109709778845, 'samples': 15685120, 'steps': 30634, 'batch_loss/train': 0.7876761127263308}
+12/27/2021 00:05:12 - INFO - codeparrot_training - Step 30635: {'lr': 0.00016432628830188056, 'samples': 15685632, 'steps': 30635, 'batch_loss/train': 0.7634504833258688}
+12/27/2021 00:05:26 - INFO - codeparrot_training - Step 30636: {'lr': 0.00016431147984657902, 'samples': 15686144, 'steps': 30636, 'batch_loss/train': 0.6915192960295826}
+12/27/2021 00:05:36 - INFO - codeparrot_training - Step 30637: {'lr': 0.0001642966717319427, 'samples': 15686656, 'steps': 30637, 'batch_loss/train': 0.8007270535454154}
+12/27/2021 00:05:47 - INFO - codeparrot_training - Step 30638: {'lr': 0.0001642818639580303, 'samples': 15687168, 'steps': 30638, 'batch_loss/train': 0.973015614785254}
+12/27/2021 00:05:59 - INFO - codeparrot_training - Step 30639: {'lr': 0.00016426705652490095, 'samples': 15687680, 'steps': 30639, 'batch_loss/train': 0.920708023943007}
+12/27/2021 00:06:10 - INFO - codeparrot_training - Step 30640: {'lr': 0.00016425224943261347, 'samples': 15688192, 'steps': 30640, 'batch_loss/train': 0.8099111579358578}
+12/27/2021 00:06:20 - INFO - codeparrot_training - Step 30641: {'lr': 0.00016423744268122652, 'samples': 15688704, 'steps': 30641, 'batch_loss/train': 0.8282647514715791}
+12/27/2021 00:06:31 - INFO - codeparrot_training - Step 30642: {'lr': 0.0001642226362707992, 'samples': 15689216, 'steps': 30642, 'batch_loss/train': 0.6294436082243919}
+12/27/2021 00:06:43 - INFO - codeparrot_training - Step 30643: {'lr': 0.00016420783020139036, 'samples': 15689728, 'steps': 30643, 'batch_loss/train': 0.8696349109522998}
+12/27/2021 00:06:54 - INFO - codeparrot_training - Step 30644: {'lr': 0.00016419302447305876, 'samples': 15690240, 'steps': 30644, 'batch_loss/train': 0.8386941161006689}
+12/27/2021 00:07:04 - INFO - codeparrot_training - Step 30645: {'lr': 0.0001641782190858632, 'samples': 15690752, 'steps': 30645, 'batch_loss/train': 0.7935496317222714}
+12/27/2021 00:07:17 - INFO - codeparrot_training - Step 30646: {'lr': 0.0001641634140398627, 'samples': 15691264, 'steps': 30646, 'batch_loss/train': 0.7868967191316187}
+12/27/2021 00:07:27 - INFO - codeparrot_training - Step 30647: {'lr': 0.00016414860933511608, 'samples': 15691776, 'steps': 30647, 'batch_loss/train': 0.8516339175403118}
+12/27/2021 00:07:38 - INFO - codeparrot_training - Step 30648: {'lr': 0.00016413380497168212, 'samples': 15692288, 'steps': 30648, 'batch_loss/train': 0.7968182768672705}
+12/27/2021 00:07:52 - INFO - codeparrot_training - Step 30649: {'lr': 0.0001641190009496197, 'samples': 15692800, 'steps': 30649, 'batch_loss/train': 0.7777708092471585}
+12/27/2021 00:08:02 - INFO - codeparrot_training - Step 30650: {'lr': 0.00016410419726898778, 'samples': 15693312, 'steps': 30650, 'batch_loss/train': 0.7401506868191063}
+12/27/2021 00:08:13 - INFO - codeparrot_training - Step 30651: {'lr': 0.00016408939392984512, 'samples': 15693824, 'steps': 30651, 'batch_loss/train': 0.8122078664600849}
+12/27/2021 00:08:23 - INFO - codeparrot_training - Step 30652: {'lr': 0.00016407459093225056, 'samples': 15694336, 'steps': 30652, 'batch_loss/train': 0.7899655774235725}
+12/27/2021 00:08:36 - INFO - codeparrot_training - Step 30653: {'lr': 0.00016405978827626307, 'samples': 15694848, 'steps': 30653, 'batch_loss/train': 0.9921443085186183}
+12/27/2021 00:08:46 - INFO - codeparrot_training - Step 30654: {'lr': 0.00016404498596194137, 'samples': 15695360, 'steps': 30654, 'batch_loss/train': 0.6335900048725307}
+12/27/2021 00:08:57 - INFO - codeparrot_training - Step 30655: {'lr': 0.00016403018398934434, 'samples': 15695872, 'steps': 30655, 'batch_loss/train': 0.7562210966134444}
+12/27/2021 00:09:09 - INFO - codeparrot_training - Step 30656: {'lr': 0.00016401538235853076, 'samples': 15696384, 'steps': 30656, 'batch_loss/train': 0.711921798530966}
+12/27/2021 00:09:20 - INFO - codeparrot_training - Step 30657: {'lr': 0.00016400058106955969, 'samples': 15696896, 'steps': 30657, 'batch_loss/train': 0.808349093887955}
+12/27/2021 00:09:30 - INFO - codeparrot_training - Step 30658: {'lr': 0.00016398578012248973, 'samples': 15697408, 'steps': 30658, 'batch_loss/train': 0.6860288185998797}
+12/27/2021 00:09:45 - INFO - codeparrot_training - Step 30659: {'lr': 0.00016397097951737993, 'samples': 15697920, 'steps': 30659, 'batch_loss/train': 0.7258026488125324}
+12/27/2021 00:09:55 - INFO - codeparrot_training - Step 30660: {'lr': 0.00016395617925428892, 'samples': 15698432, 'steps': 30660, 'batch_loss/train': 0.7601099401945248}
+12/27/2021 00:10:06 - INFO - codeparrot_training - Step 30661: {'lr': 0.00016394137933327575, 'samples': 15698944, 'steps': 30661, 'batch_loss/train': 0.6781169390305877}
+12/27/2021 00:10:18 - INFO - codeparrot_training - Step 30662: {'lr': 0.00016392657975439909, 'samples': 15699456, 'steps': 30662, 'batch_loss/train': 0.795491547207348}
+12/27/2021 00:10:29 - INFO - codeparrot_training - Step 30663: {'lr': 0.00016391178051771793, 'samples': 15699968, 'steps': 30663, 'batch_loss/train': 0.7274784548208117}
+12/27/2021 00:10:39 - INFO - codeparrot_training - Step 30664: {'lr': 0.00016389698162329092, 'samples': 15700480, 'steps': 30664, 'batch_loss/train': 0.8066432783380151}
+12/27/2021 00:10:50 - INFO - codeparrot_training - Step 30665: {'lr': 0.00016388218307117702, 'samples': 15700992, 'steps': 30665, 'batch_loss/train': 0.606018669786863}
+12/27/2021 00:11:02 - INFO - codeparrot_training - Step 30666: {'lr': 0.00016386738486143511, 'samples': 15701504, 'steps': 30666, 'batch_loss/train': 0.5948637470137328}
+12/27/2021 00:11:13 - INFO - codeparrot_training - Step 30667: {'lr': 0.00016385258699412386, 'samples': 15702016, 'steps': 30667, 'batch_loss/train': 0.6891128541901708}
+12/27/2021 00:11:23 - INFO - codeparrot_training - Step 30668: {'lr': 0.00016383778946930228, 'samples': 15702528, 'steps': 30668, 'batch_loss/train': 0.6824625106528401}
+12/27/2021 00:11:37 - INFO - codeparrot_training - Step 30669: {'lr': 0.00016382299228702912, 'samples': 15703040, 'steps': 30669, 'batch_loss/train': 0.8419821290299296}
+12/27/2021 00:11:48 - INFO - codeparrot_training - Step 30670: {'lr': 0.00016380819544736322, 'samples': 15703552, 'steps': 30670, 'batch_loss/train': 0.777962270192802}
+12/27/2021 00:11:58 - INFO - codeparrot_training - Step 30671: {'lr': 0.00016379339895036327, 'samples': 15704064, 'steps': 30671, 'batch_loss/train': 0.752974616130814}
+12/27/2021 00:12:11 - INFO - codeparrot_training - Step 30672: {'lr': 0.0001637786027960883, 'samples': 15704576, 'steps': 30672, 'batch_loss/train': 0.7670457467902452}
+12/27/2021 00:12:21 - INFO - codeparrot_training - Step 30673: {'lr': 0.00016376380698459708, 'samples': 15705088, 'steps': 30673, 'batch_loss/train': 0.714107563951984}
+12/27/2021 00:12:32 - INFO - codeparrot_training - Step 30674: {'lr': 0.00016374901151594833, 'samples': 15705600, 'steps': 30674, 'batch_loss/train': 0.7320686941966414}
+12/27/2021 00:12:42 - INFO - codeparrot_training - Step 30675: {'lr': 0.00016373421639020094, 'samples': 15706112, 'steps': 30675, 'batch_loss/train': 0.7192562588024884}
+12/27/2021 00:12:56 - INFO - codeparrot_training - Step 30676: {'lr': 0.00016371942160741383, 'samples': 15706624, 'steps': 30676, 'batch_loss/train': 0.7603801421355456}
+12/27/2021 00:13:07 - INFO - codeparrot_training - Step 30677: {'lr': 0.00016370462716764565, 'samples': 15707136, 'steps': 30677, 'batch_loss/train': 0.9963803472928703}
+12/27/2021 00:13:18 - INFO - codeparrot_training - Step 30678: {'lr': 0.00016368983307095522, 'samples': 15707648, 'steps': 30678, 'batch_loss/train': 0.7094229804351926}
+12/27/2021 00:13:30 - INFO - codeparrot_training - Step 30679: {'lr': 0.00016367503931740158, 'samples': 15708160, 'steps': 30679, 'batch_loss/train': 0.6663944693282247}
+12/27/2021 00:13:41 - INFO - codeparrot_training - Step 30680: {'lr': 0.0001636602459070433, 'samples': 15708672, 'steps': 30680, 'batch_loss/train': 0.8590273009613156}
+12/27/2021 00:13:51 - INFO - codeparrot_training - Step 30681: {'lr': 0.00016364545283993932, 'samples': 15709184, 'steps': 30681, 'batch_loss/train': 0.8413809025660157}
+12/27/2021 00:14:03 - INFO - codeparrot_training - Step 30682: {'lr': 0.00016363066011614832, 'samples': 15709696, 'steps': 30682, 'batch_loss/train': 0.8472917936742306}
+12/27/2021 00:14:14 - INFO - codeparrot_training - Step 30683: {'lr': 0.0001636158677357293, 'samples': 15710208, 'steps': 30683, 'batch_loss/train': 0.7693531550467014}
+12/27/2021 00:14:25 - INFO - codeparrot_training - Step 30684: {'lr': 0.00016360107569874093, 'samples': 15710720, 'steps': 30684, 'batch_loss/train': 0.6100525700021535}
+12/27/2021 00:14:37 - INFO - codeparrot_training - Step 30685: {'lr': 0.00016358628400524214, 'samples': 15711232, 'steps': 30685, 'batch_loss/train': 0.7896861517801881}
+12/27/2021 00:14:48 - INFO - codeparrot_training - Step 30686: {'lr': 0.00016357149265529153, 'samples': 15711744, 'steps': 30686, 'batch_loss/train': 0.8218743037432432}
+12/27/2021 00:14:58 - INFO - codeparrot_training - Step 30687: {'lr': 0.0001635567016489481, 'samples': 15712256, 'steps': 30687, 'batch_loss/train': 0.7702992677222937}
+12/27/2021 00:15:09 - INFO - codeparrot_training - Step 30688: {'lr': 0.0001635419109862706, 'samples': 15712768, 'steps': 30688, 'batch_loss/train': 0.7788527719676495}
+12/27/2021 00:15:22 - INFO - codeparrot_training - Step 30689: {'lr': 0.00016352712066731773, 'samples': 15713280, 'steps': 30689, 'batch_loss/train': 0.7354790144599974}
+12/27/2021 00:15:33 - INFO - codeparrot_training - Step 30690: {'lr': 0.00016351233069214849, 'samples': 15713792, 'steps': 30690, 'batch_loss/train': 0.7381614069454372}
+12/27/2021 00:15:44 - INFO - codeparrot_training - Step 30691: {'lr': 0.0001634975410608215, 'samples': 15714304, 'steps': 30691, 'batch_loss/train': 0.7937191287055612}
+12/27/2021 00:15:56 - INFO - codeparrot_training - Step 30692: {'lr': 0.00016348275177339566, 'samples': 15714816, 'steps': 30692, 'batch_loss/train': 0.7495193808572367}
+12/27/2021 00:16:06 - INFO - codeparrot_training - Step 30693: {'lr': 0.00016346796282992965, 'samples': 15715328, 'steps': 30693, 'batch_loss/train': 0.6835753032937646}
+12/27/2021 00:16:17 - INFO - codeparrot_training - Step 30694: {'lr': 0.00016345317423048243, 'samples': 15715840, 'steps': 30694, 'batch_loss/train': 0.7349508409388363}
+12/27/2021 00:16:29 - INFO - codeparrot_training - Step 30695: {'lr': 0.00016343838597511273, 'samples': 15716352, 'steps': 30695, 'batch_loss/train': 0.7574555147439241}
+12/27/2021 00:16:40 - INFO - codeparrot_training - Step 30696: {'lr': 0.00016342359806387923, 'samples': 15716864, 'steps': 30696, 'batch_loss/train': 0.7284579984843731}
+12/27/2021 00:16:50 - INFO - codeparrot_training - Step 30697: {'lr': 0.00016340881049684084, 'samples': 15717376, 'steps': 30697, 'batch_loss/train': 0.6621048506349325}
+12/27/2021 00:17:01 - INFO - codeparrot_training - Step 30698: {'lr': 0.0001633940232740564, 'samples': 15717888, 'steps': 30698, 'batch_loss/train': 0.6218259930610657}
+12/27/2021 00:17:15 - INFO - codeparrot_training - Step 30699: {'lr': 0.0001633792363955846, 'samples': 15718400, 'steps': 30699, 'batch_loss/train': 0.7929580514319241}
+12/27/2021 00:17:25 - INFO - codeparrot_training - Step 30700: {'lr': 0.0001633644498614842, 'samples': 15718912, 'steps': 30700, 'batch_loss/train': 0.7750376597978175}
+12/27/2021 00:17:36 - INFO - codeparrot_training - Step 30701: {'lr': 0.00016334966367181404, 'samples': 15719424, 'steps': 30701, 'batch_loss/train': 0.9509856104850769}
+12/27/2021 00:17:48 - INFO - codeparrot_training - Step 30702: {'lr': 0.00016333487782663292, 'samples': 15719936, 'steps': 30702, 'batch_loss/train': 0.8648104295134544}
+12/27/2021 00:17:59 - INFO - codeparrot_training - Step 30703: {'lr': 0.0001633200923259996, 'samples': 15720448, 'steps': 30703, 'batch_loss/train': 0.7686479613184929}
+12/27/2021 00:18:10 - INFO - codeparrot_training - Step 30704: {'lr': 0.0001633053071699728, 'samples': 15720960, 'steps': 30704, 'batch_loss/train': 0.664530704729259}
+12/27/2021 00:18:23 - INFO - codeparrot_training - Step 30705: {'lr': 0.00016329052235861146, 'samples': 15721472, 'steps': 30705, 'batch_loss/train': 0.839724762365222}
+12/27/2021 00:18:34 - INFO - codeparrot_training - Step 30706: {'lr': 0.00016327573789197427, 'samples': 15721984, 'steps': 30706, 'batch_loss/train': 0.6984200719743967}
+12/27/2021 00:18:45 - INFO - codeparrot_training - Step 30707: {'lr': 0.00016326095377011996, 'samples': 15722496, 'steps': 30707, 'batch_loss/train': 0.7811967087909579}
+12/27/2021 00:18:55 - INFO - codeparrot_training - Step 30708: {'lr': 0.0001632461699931073, 'samples': 15723008, 'steps': 30708, 'batch_loss/train': 0.6740872678346932}
+12/27/2021 00:19:07 - INFO - codeparrot_training - Step 30709: {'lr': 0.00016323138656099516, 'samples': 15723520, 'steps': 30709, 'batch_loss/train': 0.7913325112313032}
+12/27/2021 00:19:18 - INFO - codeparrot_training - Step 30710: {'lr': 0.00016321660347384226, 'samples': 15724032, 'steps': 30710, 'batch_loss/train': 0.7781145954504609}
+12/27/2021 00:19:29 - INFO - codeparrot_training - Step 30711: {'lr': 0.00016320182073170742, 'samples': 15724544, 'steps': 30711, 'batch_loss/train': 0.8135796496644616}
+12/27/2021 00:19:41 - INFO - codeparrot_training - Step 30712: {'lr': 0.00016318703833464925, 'samples': 15725056, 'steps': 30712, 'batch_loss/train': 0.9736356204375625}
+12/27/2021 00:19:51 - INFO - codeparrot_training - Step 30713: {'lr': 0.00016317225628272676, 'samples': 15725568, 'steps': 30713, 'batch_loss/train': 0.6943339044228196}
+12/27/2021 00:20:02 - INFO - codeparrot_training - Step 30714: {'lr': 0.00016315747457599855, 'samples': 15726080, 'steps': 30714, 'batch_loss/train': 0.8116454565897584}
+12/27/2021 00:20:16 - INFO - codeparrot_training - Step 30715: {'lr': 0.00016314269321452337, 'samples': 15726592, 'steps': 30715, 'batch_loss/train': 0.6794492965564132}
+12/27/2021 00:20:27 - INFO - codeparrot_training - Step 30716: {'lr': 0.00016312791219836014, 'samples': 15727104, 'steps': 30716, 'batch_loss/train': 0.8066911827772856}
+12/27/2021 00:20:38 - INFO - codeparrot_training - Step 30717: {'lr': 0.00016311313152756748, 'samples': 15727616, 'steps': 30717, 'batch_loss/train': 0.7490399368107319}
+12/27/2021 00:20:48 - INFO - codeparrot_training - Step 30718: {'lr': 0.00016309835120220428, 'samples': 15728128, 'steps': 30718, 'batch_loss/train': 0.5833171107806265}
+12/27/2021 00:21:00 - INFO - codeparrot_training - Step 30719: {'lr': 0.00016308357122232908, 'samples': 15728640, 'steps': 30719, 'batch_loss/train': 0.8767593218944967}
+12/27/2021 00:21:11 - INFO - codeparrot_training - Step 30720: {'lr': 0.00016306879158800087, 'samples': 15729152, 'steps': 30720, 'batch_loss/train': 0.7668367850128561}
+12/27/2021 00:21:22 - INFO - codeparrot_training - Step 30721: {'lr': 0.00016305401229927834, 'samples': 15729664, 'steps': 30721, 'batch_loss/train': 0.769505399512127}
+12/27/2021 00:21:34 - INFO - codeparrot_training - Step 30722: {'lr': 0.00016303923335622017, 'samples': 15730176, 'steps': 30722, 'batch_loss/train': 0.6662010657601058}
+12/27/2021 00:21:44 - INFO - codeparrot_training - Step 30723: {'lr': 0.00016302445475888517, 'samples': 15730688, 'steps': 30723, 'batch_loss/train': 0.4862563656643033}
+12/27/2021 00:21:55 - INFO - codeparrot_training - Step 30724: {'lr': 0.00016300967650733215, 'samples': 15731200, 'steps': 30724, 'batch_loss/train': 0.7248493866063654}
+12/27/2021 00:22:07 - INFO - codeparrot_training - Step 30725: {'lr': 0.0001629948986016198, 'samples': 15731712, 'steps': 30725, 'batch_loss/train': 0.753311253618449}
+12/27/2021 00:22:18 - INFO - codeparrot_training - Step 30726: {'lr': 0.00016298012104180683, 'samples': 15732224, 'steps': 30726, 'batch_loss/train': 0.6851329994387925}
+12/27/2021 00:22:28 - INFO - codeparrot_training - Step 30727: {'lr': 0.00016296534382795208, 'samples': 15732736, 'steps': 30727, 'batch_loss/train': 0.7255883254110813}
+12/27/2021 00:22:39 - INFO - codeparrot_training - Step 30728: {'lr': 0.00016295056696011428, 'samples': 15733248, 'steps': 30728, 'batch_loss/train': 0.8874179003760219}
+12/27/2021 00:22:53 - INFO - codeparrot_training - Step 30729: {'lr': 0.00016293579043835215, 'samples': 15733760, 'steps': 30729, 'batch_loss/train': 0.8322876477614045}
+12/27/2021 00:23:03 - INFO - codeparrot_training - Step 30730: {'lr': 0.00016292101426272436, 'samples': 15734272, 'steps': 30730, 'batch_loss/train': 0.7694784186314791}
+12/27/2021 00:23:14 - INFO - codeparrot_training - Step 30731: {'lr': 0.00016290623843328984, 'samples': 15734784, 'steps': 30731, 'batch_loss/train': 0.6983974915929139}
+12/27/2021 00:23:26 - INFO - codeparrot_training - Step 30732: {'lr': 0.0001628914629501072, 'samples': 15735296, 'steps': 30732, 'batch_loss/train': 0.6290706023573875}
+12/27/2021 00:23:37 - INFO - codeparrot_training - Step 30733: {'lr': 0.00016287668781323524, 'samples': 15735808, 'steps': 30733, 'batch_loss/train': 1.1383631052449346}
+12/27/2021 00:23:48 - INFO - codeparrot_training - Step 30734: {'lr': 0.0001628619130227326, 'samples': 15736320, 'steps': 30734, 'batch_loss/train': 0.7600749852135777}
+12/27/2021 00:23:58 - INFO - codeparrot_training - Step 30735: {'lr': 0.0001628471385786582, 'samples': 15736832, 'steps': 30735, 'batch_loss/train': 0.6916469964198768}
+12/27/2021 00:24:10 - INFO - codeparrot_training - Step 30736: {'lr': 0.00016283236448107058, 'samples': 15737344, 'steps': 30736, 'batch_loss/train': 0.8044495219364762}
+12/27/2021 00:24:21 - INFO - codeparrot_training - Step 30737: {'lr': 0.0001628175907300286, 'samples': 15737856, 'steps': 30737, 'batch_loss/train': 0.8046136777848005}
+12/27/2021 00:24:31 - INFO - codeparrot_training - Step 30738: {'lr': 0.00016280281732559092, 'samples': 15738368, 'steps': 30738, 'batch_loss/train': 0.6870739919831976}
+12/27/2021 00:24:46 - INFO - codeparrot_training - Step 30739: {'lr': 0.00016278804426781633, 'samples': 15738880, 'steps': 30739, 'batch_loss/train': 0.7778442117851228}
+12/27/2021 00:24:56 - INFO - codeparrot_training - Step 30740: {'lr': 0.00016277327155676358, 'samples': 15739392, 'steps': 30740, 'batch_loss/train': 0.7426081290468574}
+12/27/2021 00:25:07 - INFO - codeparrot_training - Step 30741: {'lr': 0.00016275849919249131, 'samples': 15739904, 'steps': 30741, 'batch_loss/train': 0.6952892089029774}
+12/27/2021 00:25:20 - INFO - codeparrot_training - Step 30742: {'lr': 0.0001627437271750583, 'samples': 15740416, 'steps': 30742, 'batch_loss/train': 0.6948827924206853}
+12/27/2021 00:25:31 - INFO - codeparrot_training - Step 30743: {'lr': 0.00016272895550452338, 'samples': 15740928, 'steps': 30743, 'batch_loss/train': 0.7573662605136633}
+12/27/2021 00:25:41 - INFO - codeparrot_training - Step 30744: {'lr': 0.00016271418418094518, 'samples': 15741440, 'steps': 30744, 'batch_loss/train': 1.0494047132087871}
+12/27/2021 00:25:52 - INFO - codeparrot_training - Step 30745: {'lr': 0.0001626994132043823, 'samples': 15741952, 'steps': 30745, 'batch_loss/train': 1.9626185595989227}
+12/27/2021 00:26:06 - INFO - codeparrot_training - Step 30746: {'lr': 0.00016268464257489367, 'samples': 15742464, 'steps': 30746, 'batch_loss/train': 1.1384495692327619}
+12/27/2021 00:26:17 - INFO - codeparrot_training - Step 30747: {'lr': 0.00016266987229253798, 'samples': 15742976, 'steps': 30747, 'batch_loss/train': 0.7080499958246946}
+12/27/2021 00:26:27 - INFO - codeparrot_training - Step 30748: {'lr': 0.00016265510235737382, 'samples': 15743488, 'steps': 30748, 'batch_loss/train': 0.8030439291615039}
+12/27/2021 00:26:39 - INFO - codeparrot_training - Step 30749: {'lr': 0.00016264033276945997, 'samples': 15744000, 'steps': 30749, 'batch_loss/train': 0.7787617789581418}
+12/27/2021 00:26:50 - INFO - codeparrot_training - Step 30750: {'lr': 0.00016262556352885526, 'samples': 15744512, 'steps': 30750, 'batch_loss/train': 0.7038614861667156}
+12/27/2021 00:27:01 - INFO - codeparrot_training - Step 30751: {'lr': 0.00016261079463561834, 'samples': 15745024, 'steps': 30751, 'batch_loss/train': 0.7629413893446326}
+12/27/2021 00:27:11 - INFO - codeparrot_training - Step 30752: {'lr': 0.0001625960260898078, 'samples': 15745536, 'steps': 30752, 'batch_loss/train': 0.7356947157531977}
+12/27/2021 00:27:23 - INFO - codeparrot_training - Step 30753: {'lr': 0.00016258125789148244, 'samples': 15746048, 'steps': 30753, 'batch_loss/train': 0.8345602694898844}
+12/27/2021 00:27:34 - INFO - codeparrot_training - Step 30754: {'lr': 0.0001625664900407011, 'samples': 15746560, 'steps': 30754, 'batch_loss/train': 0.7484917985275388}
+12/27/2021 00:27:45 - INFO - codeparrot_training - Step 30755: {'lr': 0.00016255172253752234, 'samples': 15747072, 'steps': 30755, 'batch_loss/train': 0.7298173727467656}
+12/27/2021 00:27:59 - INFO - codeparrot_training - Step 30756: {'lr': 0.00016253695538200486, 'samples': 15747584, 'steps': 30756, 'batch_loss/train': 0.8583465861156583}
+12/27/2021 00:28:09 - INFO - codeparrot_training - Step 30757: {'lr': 0.00016252218857420748, 'samples': 15748096, 'steps': 30757, 'batch_loss/train': 0.8300075652077794}
+12/27/2021 00:28:20 - INFO - codeparrot_training - Step 30758: {'lr': 0.00016250742211418884, 'samples': 15748608, 'steps': 30758, 'batch_loss/train': 0.8139081031549722}
+12/27/2021 00:28:32 - INFO - codeparrot_training - Step 30759: {'lr': 0.00016249265600200768, 'samples': 15749120, 'steps': 30759, 'batch_loss/train': 0.7976779462769628}
+12/27/2021 00:28:43 - INFO - codeparrot_training - Step 30760: {'lr': 0.00016247789023772258, 'samples': 15749632, 'steps': 30760, 'batch_loss/train': 0.795784049667418}
+12/27/2021 00:28:53 - INFO - codeparrot_training - Step 30761: {'lr': 0.00016246312482139246, 'samples': 15750144, 'steps': 30761, 'batch_loss/train': 0.776810348033905}
+12/27/2021 00:29:04 - INFO - codeparrot_training - Step 30762: {'lr': 0.00016244835975307587, 'samples': 15750656, 'steps': 30762, 'batch_loss/train': 0.8015978625044227}
+12/27/2021 00:29:18 - INFO - codeparrot_training - Step 30763: {'lr': 0.00016243359503283146, 'samples': 15751168, 'steps': 30763, 'batch_loss/train': 0.8141813455149531}
+12/27/2021 00:29:29 - INFO - codeparrot_training - Step 30764: {'lr': 0.0001624188306607181, 'samples': 15751680, 'steps': 30764, 'batch_loss/train': 0.6414330622646958}
+12/27/2021 00:29:40 - INFO - codeparrot_training - Step 30765: {'lr': 0.00016240406663679436, 'samples': 15752192, 'steps': 30765, 'batch_loss/train': 0.7387345200404525}
+12/27/2021 00:29:52 - INFO - codeparrot_training - Step 30766: {'lr': 0.00016238930296111903, 'samples': 15752704, 'steps': 30766, 'batch_loss/train': 1.0650580124929547}
+12/27/2021 00:30:03 - INFO - codeparrot_training - Step 30767: {'lr': 0.00016237453963375065, 'samples': 15753216, 'steps': 30767, 'batch_loss/train': 0.7682269169017673}
+12/27/2021 00:30:13 - INFO - codeparrot_training - Step 30768: {'lr': 0.0001623597766547481, 'samples': 15753728, 'steps': 30768, 'batch_loss/train': 0.7155738370493054}
+12/27/2021 00:30:24 - INFO - codeparrot_training - Step 30769: {'lr': 0.00016234501402417, 'samples': 15754240, 'steps': 30769, 'batch_loss/train': 0.8091745898127556}
+12/27/2021 00:30:36 - INFO - codeparrot_training - Step 30770: {'lr': 0.00016233025174207505, 'samples': 15754752, 'steps': 30770, 'batch_loss/train': 0.8596173236146569}
+12/27/2021 00:30:47 - INFO - codeparrot_training - Step 30771: {'lr': 0.0001623154898085218, 'samples': 15755264, 'steps': 30771, 'batch_loss/train': 0.7708400972187519}
+12/27/2021 00:30:57 - INFO - codeparrot_training - Step 30772: {'lr': 0.00016230072822356908, 'samples': 15755776, 'steps': 30772, 'batch_loss/train': 0.7056989758275449}
+12/27/2021 00:31:11 - INFO - codeparrot_training - Step 30773: {'lr': 0.00016228596698727562, 'samples': 15756288, 'steps': 30773, 'batch_loss/train': 0.7650093724951148}
+12/27/2021 00:31:22 - INFO - codeparrot_training - Step 30774: {'lr': 0.00016227120609970002, 'samples': 15756800, 'steps': 30774, 'batch_loss/train': 0.7275451808236539}
+12/27/2021 00:31:32 - INFO - codeparrot_training - Step 30775: {'lr': 0.00016225644556090086, 'samples': 15757312, 'steps': 30775, 'batch_loss/train': 0.8059558421373367}
+12/27/2021 00:31:45 - INFO - codeparrot_training - Step 30776: {'lr': 0.0001622416853709371, 'samples': 15757824, 'steps': 30776, 'batch_loss/train': 0.6486248095170595}
+12/27/2021 00:31:55 - INFO - codeparrot_training - Step 30777: {'lr': 0.00016222692552986717, 'samples': 15758336, 'steps': 30777, 'batch_loss/train': 0.8518314836546779}
+12/27/2021 00:32:06 - INFO - codeparrot_training - Step 30778: {'lr': 0.00016221216603774986, 'samples': 15758848, 'steps': 30778, 'batch_loss/train': 0.8023763683158904}
+12/27/2021 00:32:20 - INFO - codeparrot_training - Step 30779: {'lr': 0.00016219740689464384, 'samples': 15759360, 'steps': 30779, 'batch_loss/train': 0.8458361905068159}
+12/27/2021 00:32:30 - INFO - codeparrot_training - Step 30780: {'lr': 0.00016218264810060785, 'samples': 15759872, 'steps': 30780, 'batch_loss/train': 0.8002205602824688}
+12/27/2021 00:32:41 - INFO - codeparrot_training - Step 30781: {'lr': 0.0001621678896557004, 'samples': 15760384, 'steps': 30781, 'batch_loss/train': 0.716746041085571}
+12/27/2021 00:32:51 - INFO - codeparrot_training - Step 30782: {'lr': 0.00016215313155998023, 'samples': 15760896, 'steps': 30782, 'batch_loss/train': 0.8024417269043624}
+12/27/2021 00:33:03 - INFO - codeparrot_training - Step 30783: {'lr': 0.00016213837381350615, 'samples': 15761408, 'steps': 30783, 'batch_loss/train': 0.6863022106699646}
+12/27/2021 00:33:14 - INFO - codeparrot_training - Step 30784: {'lr': 0.00016212361641633664, 'samples': 15761920, 'steps': 30784, 'batch_loss/train': 0.7047581584192812}
+12/27/2021 00:33:25 - INFO - codeparrot_training - Step 30785: {'lr': 0.00016210885936853052, 'samples': 15762432, 'steps': 30785, 'batch_loss/train': 0.77451375965029}
+12/27/2021 00:33:37 - INFO - codeparrot_training - Step 30786: {'lr': 0.00016209410267014628, 'samples': 15762944, 'steps': 30786, 'batch_loss/train': 0.7358229744131677}
+12/27/2021 00:33:48 - INFO - codeparrot_training - Step 30787: {'lr': 0.00016207934632124274, 'samples': 15763456, 'steps': 30787, 'batch_loss/train': 0.7033231714740396}
+12/27/2021 00:33:58 - INFO - codeparrot_training - Step 30788: {'lr': 0.0001620645903218786, 'samples': 15763968, 'steps': 30788, 'batch_loss/train': 0.7743355995044112}
+12/27/2021 00:34:10 - INFO - codeparrot_training - Step 30789: {'lr': 0.00016204983467211232, 'samples': 15764480, 'steps': 30789, 'batch_loss/train': 0.7461689347401261}
+12/27/2021 00:34:21 - INFO - codeparrot_training - Step 30790: {'lr': 0.0001620350793720028, 'samples': 15764992, 'steps': 30790, 'batch_loss/train': 0.9490162804722786}
+12/27/2021 00:34:32 - INFO - codeparrot_training - Step 30791: {'lr': 0.00016202032442160853, 'samples': 15765504, 'steps': 30791, 'batch_loss/train': 0.7693260200321674}
+12/27/2021 00:34:42 - INFO - codeparrot_training - Step 30792: {'lr': 0.00016200556982098828, 'samples': 15766016, 'steps': 30792, 'batch_loss/train': 0.7252944828942418}
+12/27/2021 00:34:56 - INFO - codeparrot_training - Step 30793: {'lr': 0.00016199081557020055, 'samples': 15766528, 'steps': 30793, 'batch_loss/train': 0.7324328916147351}
+12/27/2021 00:35:07 - INFO - codeparrot_training - Step 30794: {'lr': 0.00016197606166930417, 'samples': 15767040, 'steps': 30794, 'batch_loss/train': 0.717556088231504}
+12/27/2021 00:35:17 - INFO - codeparrot_training - Step 30795: {'lr': 0.0001619613081183578, 'samples': 15767552, 'steps': 30795, 'batch_loss/train': 0.7924542678520083}
+12/27/2021 00:35:29 - INFO - codeparrot_training - Step 30796: {'lr': 0.00016194655491742, 'samples': 15768064, 'steps': 30796, 'batch_loss/train': 0.7862041450571269}
+12/27/2021 00:35:40 - INFO - codeparrot_training - Step 30797: {'lr': 0.00016193180206654933, 'samples': 15768576, 'steps': 30797, 'batch_loss/train': 0.7801267672330141}
+12/27/2021 00:35:51 - INFO - codeparrot_training - Step 30798: {'lr': 0.00016191704956580467, 'samples': 15769088, 'steps': 30798, 'batch_loss/train': 0.829815779812634}
+12/27/2021 00:36:03 - INFO - codeparrot_training - Step 30799: {'lr': 0.00016190229741524457, 'samples': 15769600, 'steps': 30799, 'batch_loss/train': 0.5454260711267125}
+12/27/2021 00:36:14 - INFO - codeparrot_training - Step 30800: {'lr': 0.00016188754561492758, 'samples': 15770112, 'steps': 30800, 'batch_loss/train': 0.8294669974711724}
+12/27/2021 00:36:25 - INFO - codeparrot_training - Step 30801: {'lr': 0.0001618727941649125, 'samples': 15770624, 'steps': 30801, 'batch_loss/train': 1.990128057077527}
+12/27/2021 00:36:35 - INFO - codeparrot_training - Step 30802: {'lr': 0.00016185804306525795, 'samples': 15771136, 'steps': 30802, 'batch_loss/train': 0.8283108780160546}
+12/27/2021 00:36:49 - INFO - codeparrot_training - Step 30803: {'lr': 0.0001618432923160225, 'samples': 15771648, 'steps': 30803, 'batch_loss/train': 0.833123330026865}
+12/27/2021 00:37:00 - INFO - codeparrot_training - Step 30804: {'lr': 0.00016182854191726476, 'samples': 15772160, 'steps': 30804, 'batch_loss/train': 0.7487641358748078}
+12/27/2021 00:37:10 - INFO - codeparrot_training - Step 30805: {'lr': 0.00016181379186904358, 'samples': 15772672, 'steps': 30805, 'batch_loss/train': 0.7339253854006529}
+12/27/2021 00:37:23 - INFO - codeparrot_training - Step 30806: {'lr': 0.00016179904217141744, 'samples': 15773184, 'steps': 30806, 'batch_loss/train': 0.7528280671685934}
+12/27/2021 00:37:33 - INFO - codeparrot_training - Step 30807: {'lr': 0.00016178429282444494, 'samples': 15773696, 'steps': 30807, 'batch_loss/train': 0.7540730383479968}
+12/27/2021 00:37:44 - INFO - codeparrot_training - Step 30808: {'lr': 0.0001617695438281848, 'samples': 15774208, 'steps': 30808, 'batch_loss/train': 0.7612901595421135}
+12/27/2021 00:37:56 - INFO - codeparrot_training - Step 30809: {'lr': 0.00016175479518269571, 'samples': 15774720, 'steps': 30809, 'batch_loss/train': 0.8382108071818948}
+12/27/2021 00:38:07 - INFO - codeparrot_training - Step 30810: {'lr': 0.00016174004688803616, 'samples': 15775232, 'steps': 30810, 'batch_loss/train': 0.6808730756747536}
+12/27/2021 00:38:17 - INFO - codeparrot_training - Step 30811: {'lr': 0.00016172529894426492, 'samples': 15775744, 'steps': 30811, 'batch_loss/train': 0.6773623232729733}
+12/27/2021 00:38:28 - INFO - codeparrot_training - Step 30812: {'lr': 0.00016171055135144044, 'samples': 15776256, 'steps': 30812, 'batch_loss/train': 0.6327231962932274}
+12/27/2021 00:38:42 - INFO - codeparrot_training - Step 30813: {'lr': 0.00016169580410962153, 'samples': 15776768, 'steps': 30813, 'batch_loss/train': 0.8337628608569503}
+12/27/2021 00:38:52 - INFO - codeparrot_training - Step 30814: {'lr': 0.00016168105721886682, 'samples': 15777280, 'steps': 30814, 'batch_loss/train': 0.8047929042950273}
+12/27/2021 00:39:03 - INFO - codeparrot_training - Step 30815: {'lr': 0.0001616663106792348, 'samples': 15777792, 'steps': 30815, 'batch_loss/train': 0.730521603487432}
+12/27/2021 00:39:15 - INFO - codeparrot_training - Step 30816: {'lr': 0.00016165156449078424, 'samples': 15778304, 'steps': 30816, 'batch_loss/train': 0.7217117673717439}
+12/27/2021 00:39:26 - INFO - codeparrot_training - Step 30817: {'lr': 0.00016163681865357366, 'samples': 15778816, 'steps': 30817, 'batch_loss/train': 0.8659359049052}
+12/27/2021 00:39:36 - INFO - codeparrot_training - Step 30818: {'lr': 0.0001616220731676618, 'samples': 15779328, 'steps': 30818, 'batch_loss/train': 0.6854172823950648}
+12/27/2021 00:39:50 - INFO - codeparrot_training - Step 30819: {'lr': 0.00016160732803310708, 'samples': 15779840, 'steps': 30819, 'batch_loss/train': 0.7937643304467201}
+12/27/2021 00:40:01 - INFO - codeparrot_training - Step 30820: {'lr': 0.0001615925832499683, 'samples': 15780352, 'steps': 30820, 'batch_loss/train': 0.7309375293552876}
+12/27/2021 00:40:11 - INFO - codeparrot_training - Step 30821: {'lr': 0.00016157783881830406, 'samples': 15780864, 'steps': 30821, 'batch_loss/train': 0.736822965554893}
+12/27/2021 00:40:22 - INFO - codeparrot_training - Step 30822: {'lr': 0.00016156309473817294, 'samples': 15781376, 'steps': 30822, 'batch_loss/train': 0.7149216327816248}
+12/27/2021 00:40:34 - INFO - codeparrot_training - Step 30823: {'lr': 0.0001615483510096335, 'samples': 15781888, 'steps': 30823, 'batch_loss/train': 0.7472240459173918}
+12/27/2021 00:40:45 - INFO - codeparrot_training - Step 30824: {'lr': 0.0001615336076327445, 'samples': 15782400, 'steps': 30824, 'batch_loss/train': 0.8456062995828688}
+12/27/2021 00:40:55 - INFO - codeparrot_training - Step 30825: {'lr': 0.00016151886460756448, 'samples': 15782912, 'steps': 30825, 'batch_loss/train': 0.7915514297783375}
+12/27/2021 00:41:07 - INFO - codeparrot_training - Step 30826: {'lr': 0.00016150412193415193, 'samples': 15783424, 'steps': 30826, 'batch_loss/train': 0.7283979726489633}
+12/27/2021 00:41:18 - INFO - codeparrot_training - Step 30827: {'lr': 0.00016148937961256565, 'samples': 15783936, 'steps': 30827, 'batch_loss/train': 0.6758827373851091}
+12/27/2021 00:41:28 - INFO - codeparrot_training - Step 30828: {'lr': 0.00016147463764286423, 'samples': 15784448, 'steps': 30828, 'batch_loss/train': 0.6607715612044558}
+12/27/2021 00:41:41 - INFO - codeparrot_training - Step 30829: {'lr': 0.00016145989602510616, 'samples': 15784960, 'steps': 30829, 'batch_loss/train': 0.7137435795739293}
+12/27/2021 00:41:51 - INFO - codeparrot_training - Step 30830: {'lr': 0.00016144515475935005, 'samples': 15785472, 'steps': 30830, 'batch_loss/train': 0.7008698731660843}
+12/27/2021 00:42:02 - INFO - codeparrot_training - Step 30831: {'lr': 0.00016143041384565472, 'samples': 15785984, 'steps': 30831, 'batch_loss/train': 0.6983389793895185}
+12/27/2021 00:42:16 - INFO - codeparrot_training - Step 30832: {'lr': 0.0001614156732840785, 'samples': 15786496, 'steps': 30832, 'batch_loss/train': 0.8212960474193096}
+12/27/2021 00:42:26 - INFO - codeparrot_training - Step 30833: {'lr': 0.00016140093307468023, 'samples': 15787008, 'steps': 30833, 'batch_loss/train': 0.7239554298575968}
+12/27/2021 00:42:37 - INFO - codeparrot_training - Step 30834: {'lr': 0.00016138619321751823, 'samples': 15787520, 'steps': 30834, 'batch_loss/train': 0.7665661289356649}
+12/27/2021 00:42:48 - INFO - codeparrot_training - Step 30835: {'lr': 0.00016137145371265143, 'samples': 15788032, 'steps': 30835, 'batch_loss/train': 0.7112649756018072}
+12/27/2021 00:43:00 - INFO - codeparrot_training - Step 30836: {'lr': 0.00016135671456013817, 'samples': 15788544, 'steps': 30836, 'batch_loss/train': 0.819144593551755}
+12/27/2021 00:43:11 - INFO - codeparrot_training - Step 30837: {'lr': 0.00016134197576003713, 'samples': 15789056, 'steps': 30837, 'batch_loss/train': 0.8204434663057327}
+12/27/2021 00:43:21 - INFO - codeparrot_training - Step 30838: {'lr': 0.000161327237312407, 'samples': 15789568, 'steps': 30838, 'batch_loss/train': 0.8251678440719843}
+12/27/2021 00:43:33 - INFO - codeparrot_training - Step 30839: {'lr': 0.00016131249921730624, 'samples': 15790080, 'steps': 30839, 'batch_loss/train': 0.6814272035844624}
+12/27/2021 00:43:44 - INFO - codeparrot_training - Step 30840: {'lr': 0.00016129776147479356, 'samples': 15790592, 'steps': 30840, 'batch_loss/train': 0.7852231403812766}
+12/27/2021 00:43:54 - INFO - codeparrot_training - Step 30841: {'lr': 0.00016128302408492738, 'samples': 15791104, 'steps': 30841, 'batch_loss/train': 0.8152106599882245}
+12/27/2021 00:44:08 - INFO - codeparrot_training - Step 30842: {'lr': 0.00016126828704776647, 'samples': 15791616, 'steps': 30842, 'batch_loss/train': 0.7442397754639387}
+12/27/2021 00:44:19 - INFO - codeparrot_training - Step 30843: {'lr': 0.00016125355036336934, 'samples': 15792128, 'steps': 30843, 'batch_loss/train': 0.7873721913201734}
+12/27/2021 00:44:30 - INFO - codeparrot_training - Step 30844: {'lr': 0.0001612388140317946, 'samples': 15792640, 'steps': 30844, 'batch_loss/train': 0.7654439928010106}
+12/27/2021 00:44:42 - INFO - codeparrot_training - Step 30845: {'lr': 0.00016122407805310075, 'samples': 15793152, 'steps': 30845, 'batch_loss/train': 0.8660440240055323}
+12/27/2021 00:44:52 - INFO - codeparrot_training - Step 30846: {'lr': 0.00016120934242734648, 'samples': 15793664, 'steps': 30846, 'batch_loss/train': 0.7122303145006299}
+12/27/2021 00:45:03 - INFO - codeparrot_training - Step 30847: {'lr': 0.0001611946071545904, 'samples': 15794176, 'steps': 30847, 'batch_loss/train': 0.7616346888244152}
+12/27/2021 00:45:14 - INFO - codeparrot_training - Step 30848: {'lr': 0.00016117987223489093, 'samples': 15794688, 'steps': 30848, 'batch_loss/train': 0.6411690707318485}
+12/27/2021 00:45:28 - INFO - codeparrot_training - Step 30849: {'lr': 0.00016116513766830677, 'samples': 15795200, 'steps': 30849, 'batch_loss/train': 0.7486068871803582}
+12/27/2021 00:45:38 - INFO - codeparrot_training - Step 30850: {'lr': 0.00016115040345489654, 'samples': 15795712, 'steps': 30850, 'batch_loss/train': 0.7476525702513754}
+12/27/2021 00:45:49 - INFO - codeparrot_training - Step 30851: {'lr': 0.00016113566959471875, 'samples': 15796224, 'steps': 30851, 'batch_loss/train': 0.8739882661029696}
+12/27/2021 00:46:01 - INFO - codeparrot_training - Step 30852: {'lr': 0.0001611209360878319, 'samples': 15796736, 'steps': 30852, 'batch_loss/train': 0.7135303956456482}
+12/27/2021 00:46:12 - INFO - codeparrot_training - Step 30853: {'lr': 0.00016110620293429472, 'samples': 15797248, 'steps': 30853, 'batch_loss/train': 1.4244527341797948}
+12/27/2021 00:46:22 - INFO - codeparrot_training - Step 30854: {'lr': 0.00016109147013416576, 'samples': 15797760, 'steps': 30854, 'batch_loss/train': 0.8129576286301017}
+12/27/2021 00:46:33 - INFO - codeparrot_training - Step 30855: {'lr': 0.00016107673768750346, 'samples': 15798272, 'steps': 30855, 'batch_loss/train': 0.6903572764713317}
+12/27/2021 00:46:45 - INFO - codeparrot_training - Step 30856: {'lr': 0.00016106200559436645, 'samples': 15798784, 'steps': 30856, 'batch_loss/train': 0.665244656149298}
+12/27/2021 00:46:55 - INFO - codeparrot_training - Step 30857: {'lr': 0.0001610472738548134, 'samples': 15799296, 'steps': 30857, 'batch_loss/train': 0.7328792768530548}
+12/27/2021 00:47:06 - INFO - codeparrot_training - Step 30858: {'lr': 0.00016103254246890278, 'samples': 15799808, 'steps': 30858, 'batch_loss/train': 0.7520218235440552}
+12/27/2021 00:47:20 - INFO - codeparrot_training - Step 30859: {'lr': 0.00016101781143669324, 'samples': 15800320, 'steps': 30859, 'batch_loss/train': 0.7866185316815972}
+12/27/2021 00:47:31 - INFO - codeparrot_training - Step 30860: {'lr': 0.00016100308075824314, 'samples': 15800832, 'steps': 30860, 'batch_loss/train': 0.6666816789656878}
+12/27/2021 00:47:41 - INFO - codeparrot_training - Step 30861: {'lr': 0.0001609883504336113, 'samples': 15801344, 'steps': 30861, 'batch_loss/train': 0.7371662762016058}
+12/27/2021 00:47:54 - INFO - codeparrot_training - Step 30862: {'lr': 0.00016097362046285613, 'samples': 15801856, 'steps': 30862, 'batch_loss/train': 0.6850643646903336}
+12/27/2021 00:48:04 - INFO - codeparrot_training - Step 30863: {'lr': 0.00016095889084603615, 'samples': 15802368, 'steps': 30863, 'batch_loss/train': 0.6809002519585192}
+12/27/2021 00:48:15 - INFO - codeparrot_training - Step 30864: {'lr': 0.00016094416158321016, 'samples': 15802880, 'steps': 30864, 'batch_loss/train': 0.7334612235426903}
+12/27/2021 00:48:25 - INFO - codeparrot_training - Step 30865: {'lr': 0.00016092943267443646, 'samples': 15803392, 'steps': 30865, 'batch_loss/train': 0.879188084974885}
+12/27/2021 00:48:38 - INFO - codeparrot_training - Step 30866: {'lr': 0.00016091470411977376, 'samples': 15803904, 'steps': 30866, 'batch_loss/train': 0.7382848744746298}
+12/27/2021 00:48:48 - INFO - codeparrot_training - Step 30867: {'lr': 0.00016089997591928047, 'samples': 15804416, 'steps': 30867, 'batch_loss/train': 0.6886414904147387}
+12/27/2021 00:48:59 - INFO - codeparrot_training - Step 30868: {'lr': 0.0001608852480730153, 'samples': 15804928, 'steps': 30868, 'batch_loss/train': 0.6908066663891077}
+12/27/2021 00:49:11 - INFO - codeparrot_training - Step 30869: {'lr': 0.00016087052058103674, 'samples': 15805440, 'steps': 30869, 'batch_loss/train': 0.7658298150636256}
+12/27/2021 00:49:22 - INFO - codeparrot_training - Step 30870: {'lr': 0.00016085579344340338, 'samples': 15805952, 'steps': 30870, 'batch_loss/train': 0.7357853669673204}
+12/27/2021 00:49:33 - INFO - codeparrot_training - Step 30871: {'lr': 0.00016084106666017358, 'samples': 15806464, 'steps': 30871, 'batch_loss/train': 0.7952696345746517}
+12/27/2021 00:49:46 - INFO - codeparrot_training - Step 30872: {'lr': 0.00016082634023140613, 'samples': 15806976, 'steps': 30872, 'batch_loss/train': 0.5207338219042867}
+12/27/2021 00:49:57 - INFO - codeparrot_training - Step 30873: {'lr': 0.0001608116141571595, 'samples': 15807488, 'steps': 30873, 'batch_loss/train': 0.8028752068057656}
+12/27/2021 00:50:08 - INFO - codeparrot_training - Step 30874: {'lr': 0.00016079688843749214, 'samples': 15808000, 'steps': 30874, 'batch_loss/train': 0.678417258663103}
+12/27/2021 00:50:18 - INFO - codeparrot_training - Step 30875: {'lr': 0.00016078216307246267, 'samples': 15808512, 'steps': 30875, 'batch_loss/train': 0.6784301674924791}
+12/27/2021 00:50:30 - INFO - codeparrot_training - Step 30876: {'lr': 0.00016076743806212973, 'samples': 15809024, 'steps': 30876, 'batch_loss/train': 0.69429388968274}
+12/27/2021 00:50:41 - INFO - codeparrot_training - Step 30877: {'lr': 0.00016075271340655172, 'samples': 15809536, 'steps': 30877, 'batch_loss/train': 0.7691114619374275}
+12/27/2021 00:50:52 - INFO - codeparrot_training - Step 30878: {'lr': 0.00016073798910578712, 'samples': 15810048, 'steps': 30878, 'batch_loss/train': 0.7139703719876707}
+12/27/2021 00:51:06 - INFO - codeparrot_training - Step 30879: {'lr': 0.0001607232651598947, 'samples': 15810560, 'steps': 30879, 'batch_loss/train': 0.8478558673523366}
+12/27/2021 00:51:17 - INFO - codeparrot_training - Step 30880: {'lr': 0.0001607085415689329, 'samples': 15811072, 'steps': 30880, 'batch_loss/train': 1.3108900068327785}
+12/27/2021 00:51:27 - INFO - codeparrot_training - Step 30881: {'lr': 0.00016069381833296015, 'samples': 15811584, 'steps': 30881, 'batch_loss/train': 1.0161505173891783}
+12/27/2021 00:51:38 - INFO - codeparrot_training - Step 30882: {'lr': 0.00016067909545203503, 'samples': 15812096, 'steps': 30882, 'batch_loss/train': 0.8232877617701888}
+12/27/2021 00:51:50 - INFO - codeparrot_training - Step 30883: {'lr': 0.00016066437292621617, 'samples': 15812608, 'steps': 30883, 'batch_loss/train': 0.6942473677918315}
+12/27/2021 00:52:01 - INFO - codeparrot_training - Step 30884: {'lr': 0.00016064965075556197, 'samples': 15813120, 'steps': 30884, 'batch_loss/train': 0.8192414678633213}
+12/27/2021 00:52:11 - INFO - codeparrot_training - Step 30885: {'lr': 0.0001606349289401311, 'samples': 15813632, 'steps': 30885, 'batch_loss/train': 0.7604305576533079}
+12/27/2021 00:52:24 - INFO - codeparrot_training - Step 30886: {'lr': 0.0001606202074799819, 'samples': 15814144, 'steps': 30886, 'batch_loss/train': 0.7469745650887489}
+12/27/2021 00:52:34 - INFO - codeparrot_training - Step 30887: {'lr': 0.00016060548637517307, 'samples': 15814656, 'steps': 30887, 'batch_loss/train': 0.7873178661684506}
+12/27/2021 00:52:45 - INFO - codeparrot_training - Step 30888: {'lr': 0.00016059076562576307, 'samples': 15815168, 'steps': 30888, 'batch_loss/train': 0.7897944343276322}
+12/27/2021 00:52:59 - INFO - codeparrot_training - Step 30889: {'lr': 0.00016057604523181035, 'samples': 15815680, 'steps': 30889, 'batch_loss/train': 0.8216747650876641}
+12/27/2021 00:53:09 - INFO - codeparrot_training - Step 30890: {'lr': 0.00016056132519337362, 'samples': 15816192, 'steps': 30890, 'batch_loss/train': 0.7547458657063544}
+12/27/2021 00:53:20 - INFO - codeparrot_training - Step 30891: {'lr': 0.00016054660551051127, 'samples': 15816704, 'steps': 30891, 'batch_loss/train': 0.6870410484261811}
+12/27/2021 00:53:31 - INFO - codeparrot_training - Step 30892: {'lr': 0.00016053188618328184, 'samples': 15817216, 'steps': 30892, 'batch_loss/train': 0.8114374820142984}
+12/27/2021 00:53:43 - INFO - codeparrot_training - Step 30893: {'lr': 0.00016051716721174377, 'samples': 15817728, 'steps': 30893, 'batch_loss/train': 0.6409935094416142}
+12/27/2021 00:53:53 - INFO - codeparrot_training - Step 30894: {'lr': 0.00016050244859595569, 'samples': 15818240, 'steps': 30894, 'batch_loss/train': 0.7669994505122304}
+12/27/2021 00:54:04 - INFO - codeparrot_training - Step 30895: {'lr': 0.0001604877303359762, 'samples': 15818752, 'steps': 30895, 'batch_loss/train': 0.7880333252251148}
+12/27/2021 00:54:18 - INFO - codeparrot_training - Step 30896: {'lr': 0.00016047301243186362, 'samples': 15819264, 'steps': 30896, 'batch_loss/train': 0.8211307800374925}
+12/27/2021 00:54:28 - INFO - codeparrot_training - Step 30897: {'lr': 0.00016045829488367647, 'samples': 15819776, 'steps': 30897, 'batch_loss/train': 0.7276456663385034}
+12/27/2021 00:54:39 - INFO - codeparrot_training - Step 30898: {'lr': 0.00016044357769147335, 'samples': 15820288, 'steps': 30898, 'batch_loss/train': 0.6687818779610097}
+12/27/2021 00:54:51 - INFO - codeparrot_training - Step 30899: {'lr': 0.00016042886085531282, 'samples': 15820800, 'steps': 30899, 'batch_loss/train': 0.719536473043263}
+12/27/2021 00:55:02 - INFO - codeparrot_training - Step 30900: {'lr': 0.00016041414437525323, 'samples': 15821312, 'steps': 30900, 'batch_loss/train': 0.9306612424552441}
+12/27/2021 00:55:12 - INFO - codeparrot_training - Step 30901: {'lr': 0.00016039942825135322, 'samples': 15821824, 'steps': 30901, 'batch_loss/train': 0.7413059789687395}
+12/27/2021 00:55:25 - INFO - codeparrot_training - Step 30902: {'lr': 0.0001603847124836713, 'samples': 15822336, 'steps': 30902, 'batch_loss/train': 0.8339521875604987}
+12/27/2021 00:55:35 - INFO - codeparrot_training - Step 30903: {'lr': 0.00016036999707226587, 'samples': 15822848, 'steps': 30903, 'batch_loss/train': 0.6866914411075413}
+12/27/2021 00:55:46 - INFO - codeparrot_training - Step 30904: {'lr': 0.00016035528201719545, 'samples': 15823360, 'steps': 30904, 'batch_loss/train': 0.7364457731600851}
+12/27/2021 00:55:57 - INFO - codeparrot_training - Step 30905: {'lr': 0.00016034056731851866, 'samples': 15823872, 'steps': 30905, 'batch_loss/train': 0.7413009302690625}
+12/27/2021 00:56:09 - INFO - codeparrot_training - Step 30906: {'lr': 0.00016032585297629393, 'samples': 15824384, 'steps': 30906, 'batch_loss/train': 0.47756398253841326}
+12/27/2021 00:56:20 - INFO - codeparrot_training - Step 30907: {'lr': 0.0001603111389905797, 'samples': 15824896, 'steps': 30907, 'batch_loss/train': 0.824321505613625}
+12/27/2021 00:56:30 - INFO - codeparrot_training - Step 30908: {'lr': 0.00016029642536143445, 'samples': 15825408, 'steps': 30908, 'batch_loss/train': 0.7077257158234715}
+12/27/2021 00:56:44 - INFO - codeparrot_training - Step 30909: {'lr': 0.0001602817120889169, 'samples': 15825920, 'steps': 30909, 'batch_loss/train': 0.7675416581332684}
+12/27/2021 00:56:55 - INFO - codeparrot_training - Step 30910: {'lr': 0.00016026699917308528, 'samples': 15826432, 'steps': 30910, 'batch_loss/train': 0.7258037290303037}
+12/27/2021 00:57:05 - INFO - codeparrot_training - Step 30911: {'lr': 0.00016025228661399816, 'samples': 15826944, 'steps': 30911, 'batch_loss/train': 0.7361184869660065}
+12/27/2021 00:57:17 - INFO - codeparrot_training - Step 30912: {'lr': 0.00016023757441171416, 'samples': 15827456, 'steps': 30912, 'batch_loss/train': 0.7204616377130151}
+12/27/2021 00:57:28 - INFO - codeparrot_training - Step 30913: {'lr': 0.0001602228625662916, 'samples': 15827968, 'steps': 30913, 'batch_loss/train': 0.6740610487759113}
+12/27/2021 00:57:39 - INFO - codeparrot_training - Step 30914: {'lr': 0.00016020815107778912, 'samples': 15828480, 'steps': 30914, 'batch_loss/train': 0.8304150709882379}
+12/27/2021 00:57:49 - INFO - codeparrot_training - Step 30915: {'lr': 0.000160193439946265, 'samples': 15828992, 'steps': 30915, 'batch_loss/train': 0.8102163830772042}
+12/27/2021 00:58:01 - INFO - codeparrot_training - Step 30916: {'lr': 0.00016017872917177797, 'samples': 15829504, 'steps': 30916, 'batch_loss/train': 0.7572794952429831}
+12/27/2021 00:58:12 - INFO - codeparrot_training - Step 30917: {'lr': 0.00016016401875438636, 'samples': 15830016, 'steps': 30917, 'batch_loss/train': 0.8058102810755372}
+12/27/2021 00:58:23 - INFO - codeparrot_training - Step 30918: {'lr': 0.00016014930869414872, 'samples': 15830528, 'steps': 30918, 'batch_loss/train': 0.7368296808563173}
+12/27/2021 00:58:37 - INFO - codeparrot_training - Step 30919: {'lr': 0.0001601345989911234, 'samples': 15831040, 'steps': 30919, 'batch_loss/train': 0.49313009955221787}
+12/27/2021 00:58:47 - INFO - codeparrot_training - Step 30920: {'lr': 0.00016011988964536905, 'samples': 15831552, 'steps': 30920, 'batch_loss/train': 0.7266494273208082}
+12/27/2021 00:58:58 - INFO - codeparrot_training - Step 30921: {'lr': 0.00016010518065694412, 'samples': 15832064, 'steps': 30921, 'batch_loss/train': 0.823487208224833}
+12/27/2021 00:59:10 - INFO - codeparrot_training - Step 30922: {'lr': 0.000160090472025907, 'samples': 15832576, 'steps': 30922, 'batch_loss/train': 0.736624522600323}
+12/27/2021 00:59:21 - INFO - codeparrot_training - Step 30923: {'lr': 0.00016007576375231617, 'samples': 15833088, 'steps': 30923, 'batch_loss/train': 0.6849812790751457}
+12/27/2021 00:59:31 - INFO - codeparrot_training - Step 30924: {'lr': 0.00016006105583623022, 'samples': 15833600, 'steps': 30924, 'batch_loss/train': 0.7833189701195806}
+12/27/2021 00:59:42 - INFO - codeparrot_training - Step 30925: {'lr': 0.0001600463482777076, 'samples': 15834112, 'steps': 30925, 'batch_loss/train': 0.7481093539390713}
+12/27/2021 00:59:56 - INFO - codeparrot_training - Step 30926: {'lr': 0.00016003164107680662, 'samples': 15834624, 'steps': 30926, 'batch_loss/train': 0.9055466183344834}
+12/27/2021 01:00:07 - INFO - codeparrot_training - Step 30927: {'lr': 0.00016001693423358589, 'samples': 15835136, 'steps': 30927, 'batch_loss/train': 0.5188769396045245}
+12/27/2021 01:00:17 - INFO - codeparrot_training - Step 30928: {'lr': 0.00016000222774810392, 'samples': 15835648, 'steps': 30928, 'batch_loss/train': 0.7371681754011661}
+12/27/2021 01:00:30 - INFO - codeparrot_training - Step 30929: {'lr': 0.00015998752162041908, 'samples': 15836160, 'steps': 30929, 'batch_loss/train': 0.7774777887389064}
+12/27/2021 01:00:41 - INFO - codeparrot_training - Step 30930: {'lr': 0.00015997281585058976, 'samples': 15836672, 'steps': 30930, 'batch_loss/train': 0.7090618601068854}
+12/27/2021 01:00:51 - INFO - codeparrot_training - Step 30931: {'lr': 0.0001599581104386747, 'samples': 15837184, 'steps': 30931, 'batch_loss/train': 0.6594168236479163}
+12/27/2021 01:01:02 - INFO - codeparrot_training - Step 30932: {'lr': 0.00015994340538473214, 'samples': 15837696, 'steps': 30932, 'batch_loss/train': 0.8727131478954107}
+12/27/2021 01:01:14 - INFO - codeparrot_training - Step 30933: {'lr': 0.00015992870068882057, 'samples': 15838208, 'steps': 30933, 'batch_loss/train': 0.846006229519844}
+12/27/2021 01:01:25 - INFO - codeparrot_training - Step 30934: {'lr': 0.0001599139963509984, 'samples': 15838720, 'steps': 30934, 'batch_loss/train': 0.7020608629100025}
+12/27/2021 01:01:35 - INFO - codeparrot_training - Step 30935: {'lr': 0.00015989929237132433, 'samples': 15839232, 'steps': 30935, 'batch_loss/train': 0.7135394860524684}
+12/27/2021 01:01:48 - INFO - codeparrot_training - Step 30936: {'lr': 0.00015988458874985657, 'samples': 15839744, 'steps': 30936, 'batch_loss/train': 0.6663407463347539}
+12/27/2021 01:01:58 - INFO - codeparrot_training - Step 30937: {'lr': 0.00015986988548665358, 'samples': 15840256, 'steps': 30937, 'batch_loss/train': 0.7518970984965563}
+12/27/2021 01:02:09 - INFO - codeparrot_training - Step 30938: {'lr': 0.000159855182581774, 'samples': 15840768, 'steps': 30938, 'batch_loss/train': 0.5478270481107756}
+12/27/2021 01:02:23 - INFO - codeparrot_training - Step 30939: {'lr': 0.00015984048003527617, 'samples': 15841280, 'steps': 30939, 'batch_loss/train': 0.6976400790736079}
+12/27/2021 01:02:33 - INFO - codeparrot_training - Step 30940: {'lr': 0.00015982577784721854, 'samples': 15841792, 'steps': 30940, 'batch_loss/train': 0.6728284736163914}
+12/27/2021 01:02:44 - INFO - codeparrot_training - Step 30941: {'lr': 0.00015981107601765953, 'samples': 15842304, 'steps': 30941, 'batch_loss/train': 0.7502237651497126}
+12/27/2021 01:02:55 - INFO - codeparrot_training - Step 30942: {'lr': 0.00015979637454665769, 'samples': 15842816, 'steps': 30942, 'batch_loss/train': 0.7428133487701416}
+12/27/2021 01:03:07 - INFO - codeparrot_training - Step 30943: {'lr': 0.00015978167343427135, 'samples': 15843328, 'steps': 30943, 'batch_loss/train': 0.730098273139447}
+12/27/2021 01:03:18 - INFO - codeparrot_training - Step 30944: {'lr': 0.00015976697268055905, 'samples': 15843840, 'steps': 30944, 'batch_loss/train': 0.7331927660852671}
+12/27/2021 01:03:28 - INFO - codeparrot_training - Step 30945: {'lr': 0.00015975227228557916, 'samples': 15844352, 'steps': 30945, 'batch_loss/train': 0.5741670379065908}
+12/27/2021 01:03:40 - INFO - codeparrot_training - Step 30946: {'lr': 0.00015973757224939015, 'samples': 15844864, 'steps': 30946, 'batch_loss/train': 0.7537467768415809}
+12/27/2021 01:03:51 - INFO - codeparrot_training - Step 30947: {'lr': 0.00015972287257205053, 'samples': 15845376, 'steps': 30947, 'batch_loss/train': 0.7854438167996705}
+12/27/2021 01:04:02 - INFO - codeparrot_training - Step 30948: {'lr': 0.0001597081732536186, 'samples': 15845888, 'steps': 30948, 'batch_loss/train': 0.7557224370539188}
+12/27/2021 01:04:15 - INFO - codeparrot_training - Step 30949: {'lr': 0.00015969347429415292, 'samples': 15846400, 'steps': 30949, 'batch_loss/train': 0.7996171759441495}
+12/27/2021 01:04:26 - INFO - codeparrot_training - Step 30950: {'lr': 0.0001596787756937119, 'samples': 15846912, 'steps': 30950, 'batch_loss/train': 0.7828426696360111}
+12/27/2021 01:04:37 - INFO - codeparrot_training - Step 30951: {'lr': 0.00015966407745235405, 'samples': 15847424, 'steps': 30951, 'batch_loss/train': 0.7825040945317596}
+12/27/2021 01:04:49 - INFO - codeparrot_training - Step 30952: {'lr': 0.00015964937957013757, 'samples': 15847936, 'steps': 30952, 'batch_loss/train': 0.7346310596913099}
+12/27/2021 01:05:00 - INFO - codeparrot_training - Step 30953: {'lr': 0.0001596346820471211, 'samples': 15848448, 'steps': 30953, 'batch_loss/train': 1.738952654413879}
+12/27/2021 01:05:10 - INFO - codeparrot_training - Step 30954: {'lr': 0.00015961998488336305, 'samples': 15848960, 'steps': 30954, 'batch_loss/train': 0.6818685964681208}
+12/27/2021 01:05:21 - INFO - codeparrot_training - Step 30955: {'lr': 0.00015960528807892178, 'samples': 15849472, 'steps': 30955, 'batch_loss/train': 0.7927789213135839}
+12/27/2021 01:05:35 - INFO - codeparrot_training - Step 30956: {'lr': 0.00015959059163385566, 'samples': 15849984, 'steps': 30956, 'batch_loss/train': 0.6690448473673314}
+12/27/2021 01:05:46 - INFO - codeparrot_training - Step 30957: {'lr': 0.00015957589554822335, 'samples': 15850496, 'steps': 30957, 'batch_loss/train': 0.5124068564036861}
+12/27/2021 01:05:56 - INFO - codeparrot_training - Step 30958: {'lr': 0.00015956119982208307, 'samples': 15851008, 'steps': 30958, 'batch_loss/train': 0.9607853747438639}
+12/27/2021 01:06:09 - INFO - codeparrot_training - Step 30959: {'lr': 0.0001595465044554934, 'samples': 15851520, 'steps': 30959, 'batch_loss/train': 0.8304897211492062}
+12/27/2021 01:06:19 - INFO - codeparrot_training - Step 30960: {'lr': 0.00015953180944851253, 'samples': 15852032, 'steps': 30960, 'batch_loss/train': 0.862902779597789}
+12/27/2021 01:06:30 - INFO - codeparrot_training - Step 30961: {'lr': 0.00015951711480119912, 'samples': 15852544, 'steps': 30961, 'batch_loss/train': 0.4621347379870713}
+12/27/2021 01:06:40 - INFO - codeparrot_training - Step 30962: {'lr': 0.00015950242051361149, 'samples': 15853056, 'steps': 30962, 'batch_loss/train': 0.8457566620782018}
+12/27/2021 01:06:53 - INFO - codeparrot_training - Step 30963: {'lr': 0.00015948772658580803, 'samples': 15853568, 'steps': 30963, 'batch_loss/train': 0.7852991092950106}
+12/27/2021 01:07:03 - INFO - codeparrot_training - Step 30964: {'lr': 0.0001594730330178472, 'samples': 15854080, 'steps': 30964, 'batch_loss/train': 0.7082541394047439}
+12/27/2021 01:07:14 - INFO - codeparrot_training - Step 30965: {'lr': 0.00015945833980978745, 'samples': 15854592, 'steps': 30965, 'batch_loss/train': 0.8534339899197221}
+12/27/2021 01:07:28 - INFO - codeparrot_training - Step 30966: {'lr': 0.00015944364696168718, 'samples': 15855104, 'steps': 30966, 'batch_loss/train': 0.7428147620521486}
+12/27/2021 01:07:38 - INFO - codeparrot_training - Step 30967: {'lr': 0.00015942895447360465, 'samples': 15855616, 'steps': 30967, 'batch_loss/train': 0.7817545551806688}
+12/27/2021 01:07:49 - INFO - codeparrot_training - Step 30968: {'lr': 0.00015941426234559853, 'samples': 15856128, 'steps': 30968, 'batch_loss/train': 0.8148624440655112}
+12/27/2021 01:08:01 - INFO - codeparrot_training - Step 30969: {'lr': 0.00015939957057772703, 'samples': 15856640, 'steps': 30969, 'batch_loss/train': 0.8212556215003133}
+12/27/2021 01:08:12 - INFO - codeparrot_training - Step 30970: {'lr': 0.00015938487917004868, 'samples': 15857152, 'steps': 30970, 'batch_loss/train': 0.8303335739765316}
+12/27/2021 01:08:22 - INFO - codeparrot_training - Step 30971: {'lr': 0.00015937018812262172, 'samples': 15857664, 'steps': 30971, 'batch_loss/train': 0.7534277830272913}
+12/27/2021 01:08:33 - INFO - codeparrot_training - Step 30972: {'lr': 0.00015935549743550476, 'samples': 15858176, 'steps': 30972, 'batch_loss/train': 0.7711659184424207}
+12/27/2021 01:08:45 - INFO - codeparrot_training - Step 30973: {'lr': 0.0001593408071087561, 'samples': 15858688, 'steps': 30973, 'batch_loss/train': 0.7370801018550992}
+12/27/2021 01:08:56 - INFO - codeparrot_training - Step 30974: {'lr': 0.00015932611714243413, 'samples': 15859200, 'steps': 30974, 'batch_loss/train': 0.7597909113392234}
+12/27/2021 01:09:07 - INFO - codeparrot_training - Step 30975: {'lr': 0.0001593114275365973, 'samples': 15859712, 'steps': 30975, 'batch_loss/train': 0.682334499899298}
+12/27/2021 01:09:19 - INFO - codeparrot_training - Step 30976: {'lr': 0.00015929673829130403, 'samples': 15860224, 'steps': 30976, 'batch_loss/train': 0.549232435412705}
+12/27/2021 01:09:29 - INFO - codeparrot_training - Step 30977: {'lr': 0.00015928204940661274, 'samples': 15860736, 'steps': 30977, 'batch_loss/train': 0.7913648537360132}
+12/27/2021 01:09:40 - INFO - codeparrot_training - Step 30978: {'lr': 0.0001592673608825816, 'samples': 15861248, 'steps': 30978, 'batch_loss/train': 0.8050692370161414}
+12/27/2021 01:09:54 - INFO - codeparrot_training - Step 30979: {'lr': 0.00015925267271926923, 'samples': 15861760, 'steps': 30979, 'batch_loss/train': 0.8311370899900794}
+12/27/2021 01:10:05 - INFO - codeparrot_training - Step 30980: {'lr': 0.0001592379849167341, 'samples': 15862272, 'steps': 30980, 'batch_loss/train': 0.6875535580329597}
+12/27/2021 01:10:15 - INFO - codeparrot_training - Step 30981: {'lr': 0.00015922329747503433, 'samples': 15862784, 'steps': 30981, 'batch_loss/train': 0.7542576342821121}
+12/27/2021 01:10:27 - INFO - codeparrot_training - Step 30982: {'lr': 0.0001592086103942284, 'samples': 15863296, 'steps': 30982, 'batch_loss/train': 0.7516611418686807}
+12/27/2021 01:10:38 - INFO - codeparrot_training - Step 30983: {'lr': 0.0001591939236743749, 'samples': 15863808, 'steps': 30983, 'batch_loss/train': 0.8088318761438131}
+12/27/2021 01:10:49 - INFO - codeparrot_training - Step 30984: {'lr': 0.00015917923731553201, 'samples': 15864320, 'steps': 30984, 'batch_loss/train': 0.8027662266977131}
+12/27/2021 01:10:59 - INFO - codeparrot_training - Step 30985: {'lr': 0.00015916455131775815, 'samples': 15864832, 'steps': 30985, 'batch_loss/train': 0.7696922766044736}
+12/27/2021 01:11:13 - INFO - codeparrot_training - Step 30986: {'lr': 0.0001591498656811118, 'samples': 15865344, 'steps': 30986, 'batch_loss/train': 0.8583994824439287}
+12/27/2021 01:11:24 - INFO - codeparrot_training - Step 30987: {'lr': 0.00015913518040565127, 'samples': 15865856, 'steps': 30987, 'batch_loss/train': 0.7270805677399039}
+12/27/2021 01:11:34 - INFO - codeparrot_training - Step 30988: {'lr': 0.00015912049549143495, 'samples': 15866368, 'steps': 30988, 'batch_loss/train': 0.852509081363678}
+12/27/2021 01:11:46 - INFO - codeparrot_training - Step 30989: {'lr': 0.00015910581093852116, 'samples': 15866880, 'steps': 30989, 'batch_loss/train': 0.764291487634182}
+12/27/2021 01:11:57 - INFO - codeparrot_training - Step 30990: {'lr': 0.00015909112674696843, 'samples': 15867392, 'steps': 30990, 'batch_loss/train': 0.7696849587373435}
+12/27/2021 01:12:08 - INFO - codeparrot_training - Step 30991: {'lr': 0.000159076442916835, 'samples': 15867904, 'steps': 30991, 'batch_loss/train': 0.7885394496843219}
+12/27/2021 01:12:20 - INFO - codeparrot_training - Step 30992: {'lr': 0.0001590617594481794, 'samples': 15868416, 'steps': 30992, 'batch_loss/train': 0.8254323662258685}
+12/27/2021 01:12:30 - INFO - codeparrot_training - Step 30993: {'lr': 0.00015904707634105975, 'samples': 15868928, 'steps': 30993, 'batch_loss/train': 0.6878603957593441}
+12/27/2021 01:12:41 - INFO - codeparrot_training - Step 30994: {'lr': 0.00015903239359553464, 'samples': 15869440, 'steps': 30994, 'batch_loss/train': 0.7539136596024036}
+12/27/2021 01:12:52 - INFO - codeparrot_training - Step 30995: {'lr': 0.00015901771121166247, 'samples': 15869952, 'steps': 30995, 'batch_loss/train': 0.6513620978221297}
+12/27/2021 01:13:06 - INFO - codeparrot_training - Step 30996: {'lr': 0.0001590030291895015, 'samples': 15870464, 'steps': 30996, 'batch_loss/train': 0.7256746403872967}
+12/27/2021 01:13:16 - INFO - codeparrot_training - Step 30997: {'lr': 0.00015898834752911, 'samples': 15870976, 'steps': 30997, 'batch_loss/train': 0.7668946729972959}
+12/27/2021 01:13:27 - INFO - codeparrot_training - Step 30998: {'lr': 0.00015897366623054656, 'samples': 15871488, 'steps': 30998, 'batch_loss/train': 0.7572177378460765}
+12/27/2021 01:13:39 - INFO - codeparrot_training - Step 30999: {'lr': 0.0001589589852938695, 'samples': 15872000, 'steps': 30999, 'batch_loss/train': 0.8741669611772522}
+12/27/2021 01:13:50 - INFO - codeparrot_training - Step 31000: {'lr': 0.00015894430471913705, 'samples': 15872512, 'steps': 31000, 'batch_loss/train': 0.7697173319756985}
+12/27/2021 01:14:00 - INFO - codeparrot_training - Step 31001: {'lr': 0.0001589296245064077, 'samples': 15873024, 'steps': 31001, 'batch_loss/train': 0.7213050005957484}
+12/27/2021 01:14:12 - INFO - codeparrot_training - Step 31002: {'lr': 0.0001589149446557398, 'samples': 15873536, 'steps': 31002, 'batch_loss/train': 0.8183126980438828}
+12/27/2021 01:14:23 - INFO - codeparrot_training - Step 31003: {'lr': 0.00015890026516719163, 'samples': 15874048, 'steps': 31003, 'batch_loss/train': 0.9556475915014744}
+12/27/2021 01:14:34 - INFO - codeparrot_training - Step 31004: {'lr': 0.0001588855860408216, 'samples': 15874560, 'steps': 31004, 'batch_loss/train': 0.7682319204322994}
+12/27/2021 01:14:44 - INFO - codeparrot_training - Step 31005: {'lr': 0.0001588709072766882, 'samples': 15875072, 'steps': 31005, 'batch_loss/train': 0.758257175097242}
+12/27/2021 01:14:58 - INFO - codeparrot_training - Step 31006: {'lr': 0.00015885622887484957, 'samples': 15875584, 'steps': 31006, 'batch_loss/train': 0.7207337520085275}
+12/27/2021 01:15:09 - INFO - codeparrot_training - Step 31007: {'lr': 0.00015884155083536417, 'samples': 15876096, 'steps': 31007, 'batch_loss/train': 0.7772744530811906}
+12/27/2021 01:15:19 - INFO - codeparrot_training - Step 31008: {'lr': 0.00015882687315829031, 'samples': 15876608, 'steps': 31008, 'batch_loss/train': 0.801705852150917}
+12/27/2021 01:15:31 - INFO - codeparrot_training - Step 31009: {'lr': 0.00015881219584368644, 'samples': 15877120, 'steps': 31009, 'batch_loss/train': 0.7727651530876756}
+12/27/2021 01:15:42 - INFO - codeparrot_training - Step 31010: {'lr': 0.00015879751889161082, 'samples': 15877632, 'steps': 31010, 'batch_loss/train': 0.7331004424486309}
+12/27/2021 01:15:53 - INFO - codeparrot_training - Step 31011: {'lr': 0.00015878284230212177, 'samples': 15878144, 'steps': 31011, 'batch_loss/train': 0.7579820598475635}
+12/27/2021 01:16:05 - INFO - codeparrot_training - Step 31012: {'lr': 0.00015876816607527777, 'samples': 15878656, 'steps': 31012, 'batch_loss/train': 0.7889898489229381}
+12/27/2021 01:16:15 - INFO - codeparrot_training - Step 31013: {'lr': 0.00015875349021113718, 'samples': 15879168, 'steps': 31013, 'batch_loss/train': 0.8108031437732279}
+12/27/2021 01:16:26 - INFO - codeparrot_training - Step 31014: {'lr': 0.0001587388147097581, 'samples': 15879680, 'steps': 31014, 'batch_loss/train': 0.6751331547275186}
+12/27/2021 01:16:38 - INFO - codeparrot_training - Step 31015: {'lr': 0.00015872413957119906, 'samples': 15880192, 'steps': 31015, 'batch_loss/train': 0.732411848148331}
+12/27/2021 01:16:49 - INFO - codeparrot_training - Step 31016: {'lr': 0.00015870946479551847, 'samples': 15880704, 'steps': 31016, 'batch_loss/train': 0.7265564613044262}
+12/27/2021 01:16:59 - INFO - codeparrot_training - Step 31017: {'lr': 0.0001586947903827745, 'samples': 15881216, 'steps': 31017, 'batch_loss/train': 0.8278833264485002}
+12/27/2021 01:17:10 - INFO - codeparrot_training - Step 31018: {'lr': 0.0001586801163330256, 'samples': 15881728, 'steps': 31018, 'batch_loss/train': 0.5832267695805058}
+12/27/2021 01:17:24 - INFO - codeparrot_training - Step 31019: {'lr': 0.00015866544264633002, 'samples': 15882240, 'steps': 31019, 'batch_loss/train': 0.7990945195779204}
+12/27/2021 01:17:35 - INFO - codeparrot_training - Step 31020: {'lr': 0.0001586507693227462, 'samples': 15882752, 'steps': 31020, 'batch_loss/train': 0.7605624864809215}
+12/27/2021 01:17:45 - INFO - codeparrot_training - Step 31021: {'lr': 0.00015863609636233245, 'samples': 15883264, 'steps': 31021, 'batch_loss/train': 0.7524601130280644}
+12/27/2021 01:17:57 - INFO - codeparrot_training - Step 31022: {'lr': 0.00015862142376514698, 'samples': 15883776, 'steps': 31022, 'batch_loss/train': 0.6837199702858925}
+12/27/2021 01:18:08 - INFO - codeparrot_training - Step 31023: {'lr': 0.00015860675153124839, 'samples': 15884288, 'steps': 31023, 'batch_loss/train': 0.6880010787863284}
+12/27/2021 01:18:19 - INFO - codeparrot_training - Step 31024: {'lr': 0.00015859207966069472, 'samples': 15884800, 'steps': 31024, 'batch_loss/train': 0.7273413834627718}
+12/27/2021 01:18:33 - INFO - codeparrot_training - Step 31025: {'lr': 0.0001585774081535445, 'samples': 15885312, 'steps': 31025, 'batch_loss/train': 0.7179328170605004}
+12/27/2021 01:18:43 - INFO - codeparrot_training - Step 31026: {'lr': 0.0001585627370098559, 'samples': 15885824, 'steps': 31026, 'batch_loss/train': 0.700245360378176}
+12/27/2021 01:18:54 - INFO - codeparrot_training - Step 31027: {'lr': 0.00015854806622968737, 'samples': 15886336, 'steps': 31027, 'batch_loss/train': 0.7488870299421251}
+12/27/2021 01:19:05 - INFO - codeparrot_training - Step 31028: {'lr': 0.00015853339581309729, 'samples': 15886848, 'steps': 31028, 'batch_loss/train': 1.5918220954481512}
+12/27/2021 01:19:17 - INFO - codeparrot_training - Step 31029: {'lr': 0.00015851872576014378, 'samples': 15887360, 'steps': 31029, 'batch_loss/train': 1.8955766917206347}
+12/27/2021 01:19:27 - INFO - codeparrot_training - Step 31030: {'lr': 0.00015850405607088525, 'samples': 15887872, 'steps': 31030, 'batch_loss/train': 0.7191026518121362}
+12/27/2021 01:19:38 - INFO - codeparrot_training - Step 31031: {'lr': 0.00015848938674538015, 'samples': 15888384, 'steps': 31031, 'batch_loss/train': 0.6433155378326774}
+12/27/2021 01:19:50 - INFO - codeparrot_training - Step 31032: {'lr': 0.00015847471778368668, 'samples': 15888896, 'steps': 31032, 'batch_loss/train': 0.712498658336699}
+12/27/2021 01:20:01 - INFO - codeparrot_training - Step 31033: {'lr': 0.00015846004918586314, 'samples': 15889408, 'steps': 31033, 'batch_loss/train': 0.7916928296908736}
+12/27/2021 01:20:11 - INFO - codeparrot_training - Step 31034: {'lr': 0.0001584453809519678, 'samples': 15889920, 'steps': 31034, 'batch_loss/train': 0.7859434729907662}
+12/27/2021 01:20:22 - INFO - codeparrot_training - Step 31035: {'lr': 0.0001584307130820592, 'samples': 15890432, 'steps': 31035, 'batch_loss/train': 0.7204895308241248}
+12/27/2021 01:20:36 - INFO - codeparrot_training - Step 31036: {'lr': 0.00015841604557619544, 'samples': 15890944, 'steps': 31036, 'batch_loss/train': 0.7029059105552733}
+12/27/2021 01:20:47 - INFO - codeparrot_training - Step 31037: {'lr': 0.00015840137843443487, 'samples': 15891456, 'steps': 31037, 'batch_loss/train': 0.7469586906954646}
+12/27/2021 01:20:57 - INFO - codeparrot_training - Step 31038: {'lr': 0.00015838671165683592, 'samples': 15891968, 'steps': 31038, 'batch_loss/train': 0.7669969452545047}
+12/27/2021 01:21:09 - INFO - codeparrot_training - Step 31039: {'lr': 0.00015837204524345673, 'samples': 15892480, 'steps': 31039, 'batch_loss/train': 0.8146183213684708}
+12/27/2021 01:21:20 - INFO - codeparrot_training - Step 31040: {'lr': 0.00015835737919435577, 'samples': 15892992, 'steps': 31040, 'batch_loss/train': 0.7469966653734446}
+12/27/2021 01:21:31 - INFO - codeparrot_training - Step 31041: {'lr': 0.00015834271350959118, 'samples': 15893504, 'steps': 31041, 'batch_loss/train': 0.8506253575906157}
+12/27/2021 01:21:45 - INFO - codeparrot_training - Step 31042: {'lr': 0.00015832804818922142, 'samples': 15894016, 'steps': 31042, 'batch_loss/train': 0.9154888219200075}
+12/27/2021 01:21:55 - INFO - codeparrot_training - Step 31043: {'lr': 0.00015831338323330472, 'samples': 15894528, 'steps': 31043, 'batch_loss/train': 0.730831696651876}
+12/27/2021 01:22:06 - INFO - codeparrot_training - Step 31044: {'lr': 0.0001582987186418994, 'samples': 15895040, 'steps': 31044, 'batch_loss/train': 0.7899353769607842}
+12/27/2021 01:22:18 - INFO - codeparrot_training - Step 31045: {'lr': 0.00015828405441506367, 'samples': 15895552, 'steps': 31045, 'batch_loss/train': 1.3094531260430813}
+12/27/2021 01:22:29 - INFO - codeparrot_training - Step 31046: {'lr': 0.00015826939055285595, 'samples': 15896064, 'steps': 31046, 'batch_loss/train': 0.8033779300749302}
+12/27/2021 01:22:39 - INFO - codeparrot_training - Step 31047: {'lr': 0.00015825472705533456, 'samples': 15896576, 'steps': 31047, 'batch_loss/train': 0.7734782425686717}
+12/27/2021 01:22:50 - INFO - codeparrot_training - Step 31048: {'lr': 0.00015824006392255763, 'samples': 15897088, 'steps': 31048, 'batch_loss/train': 0.7622476993128657}
+12/27/2021 01:23:02 - INFO - codeparrot_training - Step 31049: {'lr': 0.00015822540115458357, 'samples': 15897600, 'steps': 31049, 'batch_loss/train': 0.7161011388525367}
+12/27/2021 01:23:13 - INFO - codeparrot_training - Step 31050: {'lr': 0.00015821073875147074, 'samples': 15898112, 'steps': 31050, 'batch_loss/train': 0.779757421463728}
+12/27/2021 01:23:23 - INFO - codeparrot_training - Step 31051: {'lr': 0.00015819607671327737, 'samples': 15898624, 'steps': 31051, 'batch_loss/train': 0.7649510558694601}
+12/27/2021 01:23:36 - INFO - codeparrot_training - Step 31052: {'lr': 0.0001581814150400616, 'samples': 15899136, 'steps': 31052, 'batch_loss/train': 0.8092801524326205}
+12/27/2021 01:23:46 - INFO - codeparrot_training - Step 31053: {'lr': 0.00015816675373188195, 'samples': 15899648, 'steps': 31053, 'batch_loss/train': 0.7197168027050793}
+12/27/2021 01:23:57 - INFO - codeparrot_training - Step 31054: {'lr': 0.00015815209278879667, 'samples': 15900160, 'steps': 31054, 'batch_loss/train': 0.7696050852537155}
+12/27/2021 01:24:11 - INFO - codeparrot_training - Step 31055: {'lr': 0.0001581374322108639, 'samples': 15900672, 'steps': 31055, 'batch_loss/train': 0.8303708722814918}
+12/27/2021 01:24:22 - INFO - codeparrot_training - Step 31056: {'lr': 0.00015812277199814197, 'samples': 15901184, 'steps': 31056, 'batch_loss/train': 0.784689954482019}
+12/27/2021 01:24:32 - INFO - codeparrot_training - Step 31057: {'lr': 0.00015810811215068933, 'samples': 15901696, 'steps': 31057, 'batch_loss/train': 0.7952025244012475}
+12/27/2021 01:24:43 - INFO - codeparrot_training - Step 31058: {'lr': 0.00015809345266856408, 'samples': 15902208, 'steps': 31058, 'batch_loss/train': 0.6548025303054601}
+12/27/2021 01:24:55 - INFO - codeparrot_training - Step 31059: {'lr': 0.0001580787935518245, 'samples': 15902720, 'steps': 31059, 'batch_loss/train': 0.7742264997214079}
+12/27/2021 01:25:06 - INFO - codeparrot_training - Step 31060: {'lr': 0.000158064134800529, 'samples': 15903232, 'steps': 31060, 'batch_loss/train': 0.5705209944862872}
+12/27/2021 01:25:16 - INFO - codeparrot_training - Step 31061: {'lr': 0.0001580494764147358, 'samples': 15903744, 'steps': 31061, 'batch_loss/train': 0.7259818213060498}
+12/27/2021 01:25:29 - INFO - codeparrot_training - Step 31062: {'lr': 0.0001580348183945031, 'samples': 15904256, 'steps': 31062, 'batch_loss/train': 0.7433553063310683}
+12/27/2021 01:25:39 - INFO - codeparrot_training - Step 31063: {'lr': 0.00015802016073988923, 'samples': 15904768, 'steps': 31063, 'batch_loss/train': 0.7317376820137724}
+12/27/2021 01:25:50 - INFO - codeparrot_training - Step 31064: {'lr': 0.00015800550345095255, 'samples': 15905280, 'steps': 31064, 'batch_loss/train': 0.684568609111011}
+12/27/2021 01:26:04 - INFO - codeparrot_training - Step 31065: {'lr': 0.0001579908465277512, 'samples': 15905792, 'steps': 31065, 'batch_loss/train': 0.7620658784871921}
+12/27/2021 01:26:14 - INFO - codeparrot_training - Step 31066: {'lr': 0.00015797618997034357, 'samples': 15906304, 'steps': 31066, 'batch_loss/train': 0.711801796220243}
+12/27/2021 01:26:25 - INFO - codeparrot_training - Step 31067: {'lr': 0.00015796153377878775, 'samples': 15906816, 'steps': 31067, 'batch_loss/train': 0.7405852377414703}
+12/27/2021 01:26:36 - INFO - codeparrot_training - Step 31068: {'lr': 0.00015794687795314222, 'samples': 15907328, 'steps': 31068, 'batch_loss/train': 0.6956771545810625}
+12/27/2021 01:26:48 - INFO - codeparrot_training - Step 31069: {'lr': 0.00015793222249346512, 'samples': 15907840, 'steps': 31069, 'batch_loss/train': 0.7211243249475956}
+12/27/2021 01:26:58 - INFO - codeparrot_training - Step 31070: {'lr': 0.00015791756739981475, 'samples': 15908352, 'steps': 31070, 'batch_loss/train': 0.7164490483701229}
+12/27/2021 01:27:09 - INFO - codeparrot_training - Step 31071: {'lr': 0.00015790291267224927, 'samples': 15908864, 'steps': 31071, 'batch_loss/train': 0.8350698305293918}
+12/27/2021 01:27:23 - INFO - codeparrot_training - Step 31072: {'lr': 0.0001578882583108271, 'samples': 15909376, 'steps': 31072, 'batch_loss/train': 0.6381482316646725}
+12/27/2021 01:27:34 - INFO - codeparrot_training - Step 31073: {'lr': 0.00015787360431560648, 'samples': 15909888, 'steps': 31073, 'batch_loss/train': 0.6942046768963337}
+12/27/2021 01:27:44 - INFO - codeparrot_training - Step 31074: {'lr': 0.00015785895068664551, 'samples': 15910400, 'steps': 31074, 'batch_loss/train': 0.6580778206698596}
+12/27/2021 01:27:56 - INFO - codeparrot_training - Step 31075: {'lr': 0.00015784429742400264, 'samples': 15910912, 'steps': 31075, 'batch_loss/train': 0.8217186350375414}
+12/27/2021 01:28:07 - INFO - codeparrot_training - Step 31076: {'lr': 0.00015782964452773607, 'samples': 15911424, 'steps': 31076, 'batch_loss/train': 0.7915335008874536}
+12/27/2021 01:28:18 - INFO - codeparrot_training - Step 31077: {'lr': 0.00015781499199790406, 'samples': 15911936, 'steps': 31077, 'batch_loss/train': 0.6789219682104886}
+12/27/2021 01:28:28 - INFO - codeparrot_training - Step 31078: {'lr': 0.00015780033983456472, 'samples': 15912448, 'steps': 31078, 'batch_loss/train': 0.7360159286763519}
+12/27/2021 01:28:40 - INFO - codeparrot_training - Step 31079: {'lr': 0.00015778568803777643, 'samples': 15912960, 'steps': 31079, 'batch_loss/train': 1.6666910154744983}
+12/27/2021 01:28:51 - INFO - codeparrot_training - Step 31080: {'lr': 0.0001577710366075975, 'samples': 15913472, 'steps': 31080, 'batch_loss/train': 0.7727972315624356}
+12/27/2021 01:29:02 - INFO - codeparrot_training - Step 31081: {'lr': 0.00015775638554408608, 'samples': 15913984, 'steps': 31081, 'batch_loss/train': 0.6767517095431685}
+12/27/2021 01:29:15 - INFO - codeparrot_training - Step 31082: {'lr': 0.00015774173484730037, 'samples': 15914496, 'steps': 31082, 'batch_loss/train': 0.6733672328991815}
+12/27/2021 01:29:26 - INFO - codeparrot_training - Step 31083: {'lr': 0.0001577270845172988, 'samples': 15915008, 'steps': 31083, 'batch_loss/train': 0.787358509725891}
+12/27/2021 01:29:37 - INFO - codeparrot_training - Step 31084: {'lr': 0.00015771243455413943, 'samples': 15915520, 'steps': 31084, 'batch_loss/train': 0.7835597335360944}
+12/27/2021 01:29:49 - INFO - codeparrot_training - Step 31085: {'lr': 0.00015769778495788053, 'samples': 15916032, 'steps': 31085, 'batch_loss/train': 0.6757879303768277}
+12/27/2021 01:30:00 - INFO - codeparrot_training - Step 31086: {'lr': 0.00015768313572858052, 'samples': 15916544, 'steps': 31086, 'batch_loss/train': 0.6648219339549541}
+12/27/2021 01:30:10 - INFO - codeparrot_training - Step 31087: {'lr': 0.00015766848686629746, 'samples': 15917056, 'steps': 31087, 'batch_loss/train': 0.7525088414549828}
+12/27/2021 01:30:21 - INFO - codeparrot_training - Step 31088: {'lr': 0.0001576538383710896, 'samples': 15917568, 'steps': 31088, 'batch_loss/train': 0.6650817911140621}
+12/27/2021 01:30:33 - INFO - codeparrot_training - Step 31089: {'lr': 0.00015763919024301516, 'samples': 15918080, 'steps': 31089, 'batch_loss/train': 0.7717553027905524}
+12/27/2021 01:30:44 - INFO - codeparrot_training - Step 31090: {'lr': 0.00015762454248213252, 'samples': 15918592, 'steps': 31090, 'batch_loss/train': 0.7929167272523046}
+12/27/2021 01:30:54 - INFO - codeparrot_training - Step 31091: {'lr': 0.00015760989508849975, 'samples': 15919104, 'steps': 31091, 'batch_loss/train': 0.7265625628642738}
+12/27/2021 01:31:06 - INFO - codeparrot_training - Step 31092: {'lr': 0.00015759524806217522, 'samples': 15919616, 'steps': 31092, 'batch_loss/train': 0.8614545809105039}
+12/27/2021 01:31:17 - INFO - codeparrot_training - Step 31093: {'lr': 0.00015758060140321701, 'samples': 15920128, 'steps': 31093, 'batch_loss/train': 0.7450016504153609}
+12/27/2021 01:31:28 - INFO - codeparrot_training - Step 31094: {'lr': 0.00015756595511168348, 'samples': 15920640, 'steps': 31094, 'batch_loss/train': 0.7025021978188306}
+12/27/2021 01:31:41 - INFO - codeparrot_training - Step 31095: {'lr': 0.00015755130918763282, 'samples': 15921152, 'steps': 31095, 'batch_loss/train': 0.8859447566792369}
+12/27/2021 01:31:52 - INFO - codeparrot_training - Step 31096: {'lr': 0.00015753666363112318, 'samples': 15921664, 'steps': 31096, 'batch_loss/train': 0.7691970434971154}
+12/27/2021 01:32:02 - INFO - codeparrot_training - Step 31097: {'lr': 0.00015752201844221298, 'samples': 15922176, 'steps': 31097, 'batch_loss/train': 0.7445485973730683}
+12/27/2021 01:32:14 - INFO - codeparrot_training - Step 31098: {'lr': 0.00015750737362096024, 'samples': 15922688, 'steps': 31098, 'batch_loss/train': 0.7723862552084029}
+12/27/2021 01:32:25 - INFO - codeparrot_training - Step 31099: {'lr': 0.0001574927291674233, 'samples': 15923200, 'steps': 31099, 'batch_loss/train': 0.6814604771789163}
+12/27/2021 01:32:36 - INFO - codeparrot_training - Step 31100: {'lr': 0.00015747808508166024, 'samples': 15923712, 'steps': 31100, 'batch_loss/train': 0.6531933178193867}
+12/27/2021 01:32:46 - INFO - codeparrot_training - Step 31101: {'lr': 0.0001574634413637294, 'samples': 15924224, 'steps': 31101, 'batch_loss/train': 0.7394403466023505}
+12/27/2021 01:33:01 - INFO - codeparrot_training - Step 31102: {'lr': 0.0001574487980136891, 'samples': 15924736, 'steps': 31102, 'batch_loss/train': 0.7644406957551837}
+12/27/2021 01:33:11 - INFO - codeparrot_training - Step 31103: {'lr': 0.00015743415503159737, 'samples': 15925248, 'steps': 31103, 'batch_loss/train': 0.8644211678765714}
+12/27/2021 01:33:22 - INFO - codeparrot_training - Step 31104: {'lr': 0.0001574195124175124, 'samples': 15925760, 'steps': 31104, 'batch_loss/train': 0.7159216939471662}
+12/27/2021 01:33:34 - INFO - codeparrot_training - Step 31105: {'lr': 0.00015740487017149257, 'samples': 15926272, 'steps': 31105, 'batch_loss/train': 0.7707074121572077}
+12/27/2021 01:33:44 - INFO - codeparrot_training - Step 31106: {'lr': 0.00015739022829359606, 'samples': 15926784, 'steps': 31106, 'batch_loss/train': 0.7401857399381697}
+12/27/2021 01:33:55 - INFO - codeparrot_training - Step 31107: {'lr': 0.00015737558678388097, 'samples': 15927296, 'steps': 31107, 'batch_loss/train': 0.7640858640661463}
+12/27/2021 01:34:07 - INFO - codeparrot_training - Step 31108: {'lr': 0.0001573609456424055, 'samples': 15927808, 'steps': 31108, 'batch_loss/train': 0.7620543912053108}
+12/27/2021 01:34:18 - INFO - codeparrot_training - Step 31109: {'lr': 0.00015734630486922808, 'samples': 15928320, 'steps': 31109, 'batch_loss/train': 0.6650875471532345}
+12/27/2021 01:34:28 - INFO - codeparrot_training - Step 31110: {'lr': 0.00015733166446440668, 'samples': 15928832, 'steps': 31110, 'batch_loss/train': 0.7645098334178329}
+12/27/2021 01:34:39 - INFO - codeparrot_training - Step 31111: {'lr': 0.00015731702442799955, 'samples': 15929344, 'steps': 31111, 'batch_loss/train': 0.8596219988539815}
+12/27/2021 01:34:53 - INFO - codeparrot_training - Step 31112: {'lr': 0.00015730238476006504, 'samples': 15929856, 'steps': 31112, 'batch_loss/train': 0.6845508366823196}
+12/27/2021 01:35:03 - INFO - codeparrot_training - Step 31113: {'lr': 0.00015728774546066123, 'samples': 15930368, 'steps': 31113, 'batch_loss/train': 0.7467604796402156}
+12/27/2021 01:35:14 - INFO - codeparrot_training - Step 31114: {'lr': 0.00015727310652984634, 'samples': 15930880, 'steps': 31114, 'batch_loss/train': 0.8268289444968104}
+12/27/2021 01:35:26 - INFO - codeparrot_training - Step 31115: {'lr': 0.00015725846796767846, 'samples': 15931392, 'steps': 31115, 'batch_loss/train': 0.7537598800845444}
+12/27/2021 01:35:37 - INFO - codeparrot_training - Step 31116: {'lr': 0.00015724382977421602, 'samples': 15931904, 'steps': 31116, 'batch_loss/train': 0.7371206237003207}
+12/27/2021 01:35:47 - INFO - codeparrot_training - Step 31117: {'lr': 0.000157229191949517, 'samples': 15932416, 'steps': 31117, 'batch_loss/train': 0.7436909079551697}
+12/27/2021 01:35:59 - INFO - codeparrot_training - Step 31118: {'lr': 0.0001572145544936398, 'samples': 15932928, 'steps': 31118, 'batch_loss/train': 0.7120484746992588}
+12/27/2021 01:36:10 - INFO - codeparrot_training - Step 31119: {'lr': 0.00015719991740664236, 'samples': 15933440, 'steps': 31119, 'batch_loss/train': 0.7515906589105725}
+12/27/2021 01:36:21 - INFO - codeparrot_training - Step 31120: {'lr': 0.00015718528068858306, 'samples': 15933952, 'steps': 31120, 'batch_loss/train': 0.6975909236352891}
+12/27/2021 01:36:35 - INFO - codeparrot_training - Step 31121: {'lr': 0.00015717064433952007, 'samples': 15934464, 'steps': 31121, 'batch_loss/train': 0.7856069798581302}
+12/27/2021 01:36:45 - INFO - codeparrot_training - Step 31122: {'lr': 0.0001571560083595115, 'samples': 15934976, 'steps': 31122, 'batch_loss/train': 0.7270895512774587}
+12/27/2021 01:36:56 - INFO - codeparrot_training - Step 31123: {'lr': 0.00015714137274861563, 'samples': 15935488, 'steps': 31123, 'batch_loss/train': 0.7848384184762836}
+12/27/2021 01:37:06 - INFO - codeparrot_training - Step 31124: {'lr': 0.00015712673750689057, 'samples': 15936000, 'steps': 31124, 'batch_loss/train': 0.8055107239633799}
+12/27/2021 01:37:19 - INFO - codeparrot_training - Step 31125: {'lr': 0.00015711210263439458, 'samples': 15936512, 'steps': 31125, 'batch_loss/train': 0.7868521343916655}
+12/27/2021 01:37:30 - INFO - codeparrot_training - Step 31126: {'lr': 0.0001570974681311857, 'samples': 15937024, 'steps': 31126, 'batch_loss/train': 0.781474323477596}
+12/27/2021 01:37:40 - INFO - codeparrot_training - Step 31127: {'lr': 0.00015708283399732225, 'samples': 15937536, 'steps': 31127, 'batch_loss/train': 0.7688420478370972}
+12/27/2021 01:37:52 - INFO - codeparrot_training - Step 31128: {'lr': 0.00015706820023286244, 'samples': 15938048, 'steps': 31128, 'batch_loss/train': 0.5665921655599959}
+12/27/2021 01:38:03 - INFO - codeparrot_training - Step 31129: {'lr': 0.00015705356683786431, 'samples': 15938560, 'steps': 31129, 'batch_loss/train': 0.7205194933339953}
+12/27/2021 01:38:14 - INFO - codeparrot_training - Step 31130: {'lr': 0.00015703893381238608, 'samples': 15939072, 'steps': 31130, 'batch_loss/train': 0.8002591617405415}
+12/27/2021 01:38:28 - INFO - codeparrot_training - Step 31131: {'lr': 0.00015702430115648603, 'samples': 15939584, 'steps': 31131, 'batch_loss/train': 0.7140631170477718}
+12/27/2021 01:38:38 - INFO - codeparrot_training - Step 31132: {'lr': 0.00015700966887022223, 'samples': 15940096, 'steps': 31132, 'batch_loss/train': 0.7988921827636659}
+12/27/2021 01:38:49 - INFO - codeparrot_training - Step 31133: {'lr': 0.0001569950369536528, 'samples': 15940608, 'steps': 31133, 'batch_loss/train': 0.7371317185461521}
+12/27/2021 01:38:59 - INFO - codeparrot_training - Step 31134: {'lr': 0.00015698040540683604, 'samples': 15941120, 'steps': 31134, 'batch_loss/train': 0.7326097607146949}
+12/27/2021 01:39:11 - INFO - codeparrot_training - Step 31135: {'lr': 0.0001569657742298301, 'samples': 15941632, 'steps': 31135, 'batch_loss/train': 0.7098896112293005}
+12/27/2021 01:39:22 - INFO - codeparrot_training - Step 31136: {'lr': 0.00015695114342269306, 'samples': 15942144, 'steps': 31136, 'batch_loss/train': 0.7653290807502344}
+12/27/2021 01:39:33 - INFO - codeparrot_training - Step 31137: {'lr': 0.0001569365129854831, 'samples': 15942656, 'steps': 31137, 'batch_loss/train': 0.8244258612394333}
+12/27/2021 01:39:45 - INFO - codeparrot_training - Step 31138: {'lr': 0.00015692188291825852, 'samples': 15943168, 'steps': 31138, 'batch_loss/train': 0.6960319671779871}
+12/27/2021 01:39:56 - INFO - codeparrot_training - Step 31139: {'lr': 0.00015690725322107735, 'samples': 15943680, 'steps': 31139, 'batch_loss/train': 0.694034461863339}
+12/27/2021 01:40:06 - INFO - codeparrot_training - Step 31140: {'lr': 0.00015689262389399783, 'samples': 15944192, 'steps': 31140, 'batch_loss/train': 0.7197387469932437}
+12/27/2021 01:40:20 - INFO - codeparrot_training - Step 31141: {'lr': 0.000156877994937078, 'samples': 15944704, 'steps': 31141, 'batch_loss/train': 0.7380871213972569}
+12/27/2021 01:40:31 - INFO - codeparrot_training - Step 31142: {'lr': 0.00015686336635037615, 'samples': 15945216, 'steps': 31142, 'batch_loss/train': 0.7774759051389992}
+12/27/2021 01:40:41 - INFO - codeparrot_training - Step 31143: {'lr': 0.0001568487381339504, 'samples': 15945728, 'steps': 31143, 'batch_loss/train': 0.9161382341990247}
+12/27/2021 01:40:52 - INFO - codeparrot_training - Step 31144: {'lr': 0.00015683411028785888, 'samples': 15946240, 'steps': 31144, 'batch_loss/train': 0.828970336355269}
+12/27/2021 01:41:04 - INFO - codeparrot_training - Step 31145: {'lr': 0.0001568194828121597, 'samples': 15946752, 'steps': 31145, 'batch_loss/train': 0.8322256682440639}
+12/27/2021 01:41:15 - INFO - codeparrot_training - Step 31146: {'lr': 0.00015680485570691114, 'samples': 15947264, 'steps': 31146, 'batch_loss/train': 0.6286868585739285}
+12/27/2021 01:41:25 - INFO - codeparrot_training - Step 31147: {'lr': 0.00015679022897217132, 'samples': 15947776, 'steps': 31147, 'batch_loss/train': 0.7433146121911705}
+12/27/2021 01:41:37 - INFO - codeparrot_training - Step 31148: {'lr': 0.00015677560260799823, 'samples': 15948288, 'steps': 31148, 'batch_loss/train': 0.7570709661813453}
+12/27/2021 01:41:48 - INFO - codeparrot_training - Step 31149: {'lr': 0.00015676097661445026, 'samples': 15948800, 'steps': 31149, 'batch_loss/train': 0.7714064354076982}
+12/27/2021 01:41:59 - INFO - codeparrot_training - Step 31150: {'lr': 0.0001567463509915854, 'samples': 15949312, 'steps': 31150, 'batch_loss/train': 0.6722631268203259}
+12/27/2021 01:42:13 - INFO - codeparrot_training - Step 31151: {'lr': 0.00015673172573946187, 'samples': 15949824, 'steps': 31151, 'batch_loss/train': 0.7876556804403663}
+12/27/2021 01:42:23 - INFO - codeparrot_training - Step 31152: {'lr': 0.0001567171008581377, 'samples': 15950336, 'steps': 31152, 'batch_loss/train': 0.8222541594877839}
+12/27/2021 01:42:34 - INFO - codeparrot_training - Step 31153: {'lr': 0.00015670247634767115, 'samples': 15950848, 'steps': 31153, 'batch_loss/train': 0.7600433398038149}
+12/27/2021 01:42:46 - INFO - codeparrot_training - Step 31154: {'lr': 0.00015668785220812037, 'samples': 15951360, 'steps': 31154, 'batch_loss/train': 0.7501985551789403}
+12/27/2021 01:42:57 - INFO - codeparrot_training - Step 31155: {'lr': 0.00015667322843954345, 'samples': 15951872, 'steps': 31155, 'batch_loss/train': 0.6373902545310557}
+12/27/2021 01:43:07 - INFO - codeparrot_training - Step 31156: {'lr': 0.00015665860504199844, 'samples': 15952384, 'steps': 31156, 'batch_loss/train': 0.773982867365703}
+12/27/2021 01:43:18 - INFO - codeparrot_training - Step 31157: {'lr': 0.0001566439820155437, 'samples': 15952896, 'steps': 31157, 'batch_loss/train': 0.7516657533124089}
+12/27/2021 01:43:31 - INFO - codeparrot_training - Step 31158: {'lr': 0.0001566293593602372, 'samples': 15953408, 'steps': 31158, 'batch_loss/train': 0.7858112789690495}
+12/27/2021 01:43:41 - INFO - codeparrot_training - Step 31159: {'lr': 0.00015661473707613704, 'samples': 15953920, 'steps': 31159, 'batch_loss/train': 0.8427554285153747}
+12/27/2021 01:43:52 - INFO - codeparrot_training - Step 31160: {'lr': 0.00015660011516330146, 'samples': 15954432, 'steps': 31160, 'batch_loss/train': 0.7671202216297388}
+12/27/2021 01:44:04 - INFO - codeparrot_training - Step 31161: {'lr': 0.00015658549362178865, 'samples': 15954944, 'steps': 31161, 'batch_loss/train': 0.7890508873388171}
+12/27/2021 01:44:14 - INFO - codeparrot_training - Step 31162: {'lr': 0.00015657087245165655, 'samples': 15955456, 'steps': 31162, 'batch_loss/train': 0.7019515744177625}
+12/27/2021 01:44:25 - INFO - codeparrot_training - Step 31163: {'lr': 0.00015655625165296333, 'samples': 15955968, 'steps': 31163, 'batch_loss/train': 0.7778482546564192}
+12/27/2021 01:44:37 - INFO - codeparrot_training - Step 31164: {'lr': 0.0001565416312257673, 'samples': 15956480, 'steps': 31164, 'batch_loss/train': 0.6850563366897404}
+12/27/2021 01:44:48 - INFO - codeparrot_training - Step 31165: {'lr': 0.0001565270111701264, 'samples': 15956992, 'steps': 31165, 'batch_loss/train': 0.7352451207116246}
+12/27/2021 01:44:58 - INFO - codeparrot_training - Step 31166: {'lr': 0.00015651239148609886, 'samples': 15957504, 'steps': 31166, 'batch_loss/train': 0.7835873500443995}
+12/27/2021 01:45:09 - INFO - codeparrot_training - Step 31167: {'lr': 0.0001564977721737426, 'samples': 15958016, 'steps': 31167, 'batch_loss/train': 0.741925360634923}
+12/27/2021 01:45:21 - INFO - codeparrot_training - Step 31168: {'lr': 0.00015648315323311607, 'samples': 15958528, 'steps': 31168, 'batch_loss/train': 0.7515094624832273}
+12/27/2021 01:45:32 - INFO - codeparrot_training - Step 31169: {'lr': 0.00015646853466427712, 'samples': 15959040, 'steps': 31169, 'batch_loss/train': 0.6235052628908306}
+12/27/2021 01:45:43 - INFO - codeparrot_training - Step 31170: {'lr': 0.0001564539164672839, 'samples': 15959552, 'steps': 31170, 'batch_loss/train': 1.0512652667239308}
+12/27/2021 01:45:55 - INFO - codeparrot_training - Step 31171: {'lr': 0.0001564392986421947, 'samples': 15960064, 'steps': 31171, 'batch_loss/train': 0.6890686347614974}
+12/27/2021 01:46:06 - INFO - codeparrot_training - Step 31172: {'lr': 0.0001564246811890675, 'samples': 15960576, 'steps': 31172, 'batch_loss/train': 1.433008930645883}
+12/27/2021 01:46:17 - INFO - codeparrot_training - Step 31173: {'lr': 0.00015641006410796045, 'samples': 15961088, 'steps': 31173, 'batch_loss/train': 0.9381017759442329}
+12/27/2021 01:46:27 - INFO - codeparrot_training - Step 31174: {'lr': 0.00015639544739893158, 'samples': 15961600, 'steps': 31174, 'batch_loss/train': 0.8422728944569826}
+12/27/2021 01:46:39 - INFO - codeparrot_training - Step 31175: {'lr': 0.0001563808310620391, 'samples': 15962112, 'steps': 31175, 'batch_loss/train': 0.7596401730552316}
+12/27/2021 01:46:50 - INFO - codeparrot_training - Step 31176: {'lr': 0.0001563662150973411, 'samples': 15962624, 'steps': 31176, 'batch_loss/train': 0.8254927447997034}
+12/27/2021 01:47:01 - INFO - codeparrot_training - Step 31177: {'lr': 0.00015635159950489573, 'samples': 15963136, 'steps': 31177, 'batch_loss/train': 0.7170295035466552}
+12/27/2021 01:47:15 - INFO - codeparrot_training - Step 31178: {'lr': 0.0001563369842847609, 'samples': 15963648, 'steps': 31178, 'batch_loss/train': 1.0568512352183461}
+12/27/2021 01:47:26 - INFO - codeparrot_training - Step 31179: {'lr': 0.0001563223694369949, 'samples': 15964160, 'steps': 31179, 'batch_loss/train': 0.7001821435987949}
+12/27/2021 01:47:36 - INFO - codeparrot_training - Step 31180: {'lr': 0.0001563077549616559, 'samples': 15964672, 'steps': 31180, 'batch_loss/train': 0.6935852691531181}
+12/27/2021 01:47:48 - INFO - codeparrot_training - Step 31181: {'lr': 0.00015629314085880178, 'samples': 15965184, 'steps': 31181, 'batch_loss/train': 0.5917715223622508}
+12/27/2021 01:47:59 - INFO - codeparrot_training - Step 31182: {'lr': 0.00015627852712849072, 'samples': 15965696, 'steps': 31182, 'batch_loss/train': 0.7616368811577559}
+12/27/2021 01:48:10 - INFO - codeparrot_training - Step 31183: {'lr': 0.00015626391377078096, 'samples': 15966208, 'steps': 31183, 'batch_loss/train': 0.8391030067577958}
+12/27/2021 01:48:23 - INFO - codeparrot_training - Step 31184: {'lr': 0.0001562493007857304, 'samples': 15966720, 'steps': 31184, 'batch_loss/train': 0.7480639342684299}
+12/27/2021 01:48:34 - INFO - codeparrot_training - Step 31185: {'lr': 0.0001562346881733972, 'samples': 15967232, 'steps': 31185, 'batch_loss/train': 0.8480459693819284}
+12/27/2021 01:48:45 - INFO - codeparrot_training - Step 31186: {'lr': 0.00015622007593383958, 'samples': 15967744, 'steps': 31186, 'batch_loss/train': 0.7168179647997022}
+12/27/2021 01:48:55 - INFO - codeparrot_training - Step 31187: {'lr': 0.0001562054640671155, 'samples': 15968256, 'steps': 31187, 'batch_loss/train': 0.75635592546314}
+12/27/2021 01:49:08 - INFO - codeparrot_training - Step 31188: {'lr': 0.00015619085257328303, 'samples': 15968768, 'steps': 31188, 'batch_loss/train': 0.6197016406804323}
+12/27/2021 01:49:18 - INFO - codeparrot_training - Step 31189: {'lr': 0.00015617624145240029, 'samples': 15969280, 'steps': 31189, 'batch_loss/train': 0.770565687911585}
+12/27/2021 01:49:29 - INFO - codeparrot_training - Step 31190: {'lr': 0.00015616163070452548, 'samples': 15969792, 'steps': 31190, 'batch_loss/train': 0.7461546855047345}
+12/27/2021 01:49:41 - INFO - codeparrot_training - Step 31191: {'lr': 0.00015614702032971654, 'samples': 15970304, 'steps': 31191, 'batch_loss/train': 0.6935714257415384}
+12/27/2021 01:49:52 - INFO - codeparrot_training - Step 31192: {'lr': 0.00015613241032803166, 'samples': 15970816, 'steps': 31192, 'batch_loss/train': 0.6667155781760812}
+12/27/2021 01:50:02 - INFO - codeparrot_training - Step 31193: {'lr': 0.00015611780069952876, 'samples': 15971328, 'steps': 31193, 'batch_loss/train': 0.7096760114654899}
+12/27/2021 01:50:16 - INFO - codeparrot_training - Step 31194: {'lr': 0.00015610319144426617, 'samples': 15971840, 'steps': 31194, 'batch_loss/train': 0.708776168525219}
+12/27/2021 01:50:27 - INFO - codeparrot_training - Step 31195: {'lr': 0.00015608858256230173, 'samples': 15972352, 'steps': 31195, 'batch_loss/train': 0.7705657761543989}
+12/27/2021 01:50:37 - INFO - codeparrot_training - Step 31196: {'lr': 0.00015607397405369361, 'samples': 15972864, 'steps': 31196, 'batch_loss/train': 0.6498663043603301}
+12/27/2021 01:50:49 - INFO - codeparrot_training - Step 31197: {'lr': 0.0001560593659185, 'samples': 15973376, 'steps': 31197, 'batch_loss/train': 0.7073149774223566}
+12/27/2021 01:51:00 - INFO - codeparrot_training - Step 31198: {'lr': 0.00015604475815677882, 'samples': 15973888, 'steps': 31198, 'batch_loss/train': 0.8223716779612005}
+12/27/2021 01:51:11 - INFO - codeparrot_training - Step 31199: {'lr': 0.0001560301507685883, 'samples': 15974400, 'steps': 31199, 'batch_loss/train': 0.7116389106959105}
+12/27/2021 01:51:21 - INFO - codeparrot_training - Step 31200: {'lr': 0.00015601554375398627, 'samples': 15974912, 'steps': 31200, 'batch_loss/train': 0.658361317589879}
+12/27/2021 01:51:33 - INFO - codeparrot_training - Step 31201: {'lr': 0.000156000937113031, 'samples': 15975424, 'steps': 31201, 'batch_loss/train': 0.5731234189588577}
+12/27/2021 01:51:44 - INFO - codeparrot_training - Step 31202: {'lr': 0.0001559863308457806, 'samples': 15975936, 'steps': 31202, 'batch_loss/train': 0.6893653818406165}
+12/27/2021 01:51:55 - INFO - codeparrot_training - Step 31203: {'lr': 0.00015597172495229302, 'samples': 15976448, 'steps': 31203, 'batch_loss/train': 0.734826902858913}
+12/27/2021 01:52:09 - INFO - codeparrot_training - Step 31204: {'lr': 0.00015595711943262628, 'samples': 15976960, 'steps': 31204, 'batch_loss/train': 0.7738064546138048}
+12/27/2021 01:52:19 - INFO - codeparrot_training - Step 31205: {'lr': 0.00015594251428683857, 'samples': 15977472, 'steps': 31205, 'batch_loss/train': 0.6332427490269765}
+12/27/2021 01:52:30 - INFO - codeparrot_training - Step 31206: {'lr': 0.00015592790951498791, 'samples': 15977984, 'steps': 31206, 'batch_loss/train': 0.7848239261657}
+12/27/2021 01:52:42 - INFO - codeparrot_training - Step 31207: {'lr': 0.0001559133051171323, 'samples': 15978496, 'steps': 31207, 'batch_loss/train': 0.7676130421459675}
+12/27/2021 01:52:52 - INFO - codeparrot_training - Step 31208: {'lr': 0.00015589870109332992, 'samples': 15979008, 'steps': 31208, 'batch_loss/train': 0.7439386900514364}
+12/27/2021 01:53:03 - INFO - codeparrot_training - Step 31209: {'lr': 0.00015588409744363884, 'samples': 15979520, 'steps': 31209, 'batch_loss/train': 0.7905589742586017}
+12/27/2021 01:53:17 - INFO - codeparrot_training - Step 31210: {'lr': 0.00015586949416811696, 'samples': 15980032, 'steps': 31210, 'batch_loss/train': 0.6851076884195209}
+12/27/2021 01:53:27 - INFO - codeparrot_training - Step 31211: {'lr': 0.00015585489126682242, 'samples': 15980544, 'steps': 31211, 'batch_loss/train': 0.7202304974198341}
+12/27/2021 01:53:38 - INFO - codeparrot_training - Step 31212: {'lr': 0.00015584028873981336, 'samples': 15981056, 'steps': 31212, 'batch_loss/train': 0.6640660092234612}
+12/27/2021 01:53:49 - INFO - codeparrot_training - Step 31213: {'lr': 0.00015582568658714777, 'samples': 15981568, 'steps': 31213, 'batch_loss/train': 0.6995602557435632}
+12/27/2021 01:54:01 - INFO - codeparrot_training - Step 31214: {'lr': 0.0001558110848088836, 'samples': 15982080, 'steps': 31214, 'batch_loss/train': 0.7191937863826752}
+12/27/2021 01:54:11 - INFO - codeparrot_training - Step 31215: {'lr': 0.00015579648340507902, 'samples': 15982592, 'steps': 31215, 'batch_loss/train': 0.7133359448052943}
+12/27/2021 01:54:22 - INFO - codeparrot_training - Step 31216: {'lr': 0.0001557818823757921, 'samples': 15983104, 'steps': 31216, 'batch_loss/train': 0.7548217801377177}
+12/27/2021 01:54:34 - INFO - codeparrot_training - Step 31217: {'lr': 0.00015576728172108078, 'samples': 15983616, 'steps': 31217, 'batch_loss/train': 0.7344898218289018}
+12/27/2021 01:54:45 - INFO - codeparrot_training - Step 31218: {'lr': 0.00015575268144100323, 'samples': 15984128, 'steps': 31218, 'batch_loss/train': 0.7182461442425847}
+12/27/2021 01:54:55 - INFO - codeparrot_training - Step 31219: {'lr': 0.00015573808153561736, 'samples': 15984640, 'steps': 31219, 'batch_loss/train': 0.6519049028865993}
+12/27/2021 01:55:09 - INFO - codeparrot_training - Step 31220: {'lr': 0.0001557234820049813, 'samples': 15985152, 'steps': 31220, 'batch_loss/train': 0.6969852454494685}
+12/27/2021 01:55:20 - INFO - codeparrot_training - Step 31221: {'lr': 0.00015570888284915314, 'samples': 15985664, 'steps': 31221, 'batch_loss/train': 0.720598938409239}
+12/27/2021 01:55:30 - INFO - codeparrot_training - Step 31222: {'lr': 0.00015569428406819074, 'samples': 15986176, 'steps': 31222, 'batch_loss/train': 0.7881099372170866}
+12/27/2021 01:55:42 - INFO - codeparrot_training - Step 31223: {'lr': 0.0001556796856621524, 'samples': 15986688, 'steps': 31223, 'batch_loss/train': 0.7833489300683141}
+12/27/2021 01:55:53 - INFO - codeparrot_training - Step 31224: {'lr': 0.00015566508763109594, 'samples': 15987200, 'steps': 31224, 'batch_loss/train': 0.7094577087555081}
+12/27/2021 01:56:04 - INFO - codeparrot_training - Step 31225: {'lr': 0.00015565048997507951, 'samples': 15987712, 'steps': 31225, 'batch_loss/train': 0.6724015465006232}
+12/27/2021 01:56:14 - INFO - codeparrot_training - Step 31226: {'lr': 0.00015563589269416107, 'samples': 15988224, 'steps': 31226, 'batch_loss/train': 0.6971373530104756}
+12/27/2021 01:56:26 - INFO - codeparrot_training - Step 31227: {'lr': 0.00015562129578839868, 'samples': 15988736, 'steps': 31227, 'batch_loss/train': 0.7767620651284233}
+12/27/2021 01:56:37 - INFO - codeparrot_training - Step 31228: {'lr': 0.00015560669925785044, 'samples': 15989248, 'steps': 31228, 'batch_loss/train': 0.7260140459984541}
+12/27/2021 01:56:48 - INFO - codeparrot_training - Step 31229: {'lr': 0.00015559210310257427, 'samples': 15989760, 'steps': 31229, 'batch_loss/train': 0.6977221020497382}
+12/27/2021 01:57:02 - INFO - codeparrot_training - Step 31230: {'lr': 0.00015557750732262822, 'samples': 15990272, 'steps': 31230, 'batch_loss/train': 0.8050493160262704}
+12/27/2021 01:57:12 - INFO - codeparrot_training - Step 31231: {'lr': 0.00015556291191807042, 'samples': 15990784, 'steps': 31231, 'batch_loss/train': 0.7101543580647558}
+12/27/2021 01:57:23 - INFO - codeparrot_training - Step 31232: {'lr': 0.00015554831688895885, 'samples': 15991296, 'steps': 31232, 'batch_loss/train': 0.7424016129225492}
+12/27/2021 01:57:35 - INFO - codeparrot_training - Step 31233: {'lr': 0.0001555337222353514, 'samples': 15991808, 'steps': 31233, 'batch_loss/train': 0.6792374821379781}
+12/27/2021 01:57:46 - INFO - codeparrot_training - Step 31234: {'lr': 0.00015551912795730625, 'samples': 15992320, 'steps': 31234, 'batch_loss/train': 0.8984327954240143}
+12/27/2021 01:57:56 - INFO - codeparrot_training - Step 31235: {'lr': 0.00015550453405488142, 'samples': 15992832, 'steps': 31235, 'batch_loss/train': 0.7790385910193436}
+12/27/2021 01:58:07 - INFO - codeparrot_training - Step 31236: {'lr': 0.00015548994052813484, 'samples': 15993344, 'steps': 31236, 'batch_loss/train': 0.7173456251621246}
+12/27/2021 01:58:19 - INFO - codeparrot_training - Step 31237: {'lr': 0.00015547534737712449, 'samples': 15993856, 'steps': 31237, 'batch_loss/train': 0.5910374777740799}
+12/27/2021 01:58:30 - INFO - codeparrot_training - Step 31238: {'lr': 0.0001554607546019086, 'samples': 15994368, 'steps': 31238, 'batch_loss/train': 0.6181629025377333}
+12/27/2021 01:58:40 - INFO - codeparrot_training - Step 31239: {'lr': 0.00015544616220254507, 'samples': 15994880, 'steps': 31239, 'batch_loss/train': 0.6964071444235742}
+12/27/2021 01:58:54 - INFO - codeparrot_training - Step 31240: {'lr': 0.00015543157017909183, 'samples': 15995392, 'steps': 31240, 'batch_loss/train': 0.6350541392457671}
+12/27/2021 01:59:05 - INFO - codeparrot_training - Step 31241: {'lr': 0.0001554169785316069, 'samples': 15995904, 'steps': 31241, 'batch_loss/train': 0.7360039995983243}
+12/27/2021 01:59:15 - INFO - codeparrot_training - Step 31242: {'lr': 0.00015540238726014844, 'samples': 15996416, 'steps': 31242, 'batch_loss/train': 0.6966207064688206}
+12/27/2021 01:59:27 - INFO - codeparrot_training - Step 31243: {'lr': 0.00015538779636477436, 'samples': 15996928, 'steps': 31243, 'batch_loss/train': 0.7341013413388282}
+12/27/2021 01:59:38 - INFO - codeparrot_training - Step 31244: {'lr': 0.00015537320584554256, 'samples': 15997440, 'steps': 31244, 'batch_loss/train': 0.7187804756686091}
+12/27/2021 01:59:49 - INFO - codeparrot_training - Step 31245: {'lr': 0.0001553586157025113, 'samples': 15997952, 'steps': 31245, 'batch_loss/train': 0.7283897968009114}
+12/27/2021 02:00:01 - INFO - codeparrot_training - Step 31246: {'lr': 0.00015534402593573844, 'samples': 15998464, 'steps': 31246, 'batch_loss/train': 0.6330820638686419}
+12/27/2021 02:00:11 - INFO - codeparrot_training - Step 31247: {'lr': 0.00015532943654528197, 'samples': 15998976, 'steps': 31247, 'batch_loss/train': 0.6694566374644637}
+12/27/2021 02:00:22 - INFO - codeparrot_training - Step 31248: {'lr': 0.00015531484753119988, 'samples': 15999488, 'steps': 31248, 'batch_loss/train': 0.7139387684874237}
+12/27/2021 02:00:36 - INFO - codeparrot_training - Step 31249: {'lr': 0.00015530025889355027, 'samples': 16000000, 'steps': 31249, 'batch_loss/train': 0.8985593896359205}
+12/27/2021 02:00:46 - INFO - codeparrot_training - Step 31250: {'lr': 0.00015528567063239102, 'samples': 16000512, 'steps': 31250, 'batch_loss/train': 0.7342694578692317}
+12/27/2021 02:00:57 - INFO - codeparrot_training - Step 31251: {'lr': 0.00015527108274778024, 'samples': 16001024, 'steps': 31251, 'batch_loss/train': 0.6817827164195478}
+12/27/2021 02:01:08 - INFO - codeparrot_training - Step 31252: {'lr': 0.00015525649523977575, 'samples': 16001536, 'steps': 31252, 'batch_loss/train': 0.6423605300078634}
+12/27/2021 02:01:20 - INFO - codeparrot_training - Step 31253: {'lr': 0.00015524190810843575, 'samples': 16002048, 'steps': 31253, 'batch_loss/train': 0.726797659881413}
+12/27/2021 02:01:31 - INFO - codeparrot_training - Step 31254: {'lr': 0.00015522732135381817, 'samples': 16002560, 'steps': 31254, 'batch_loss/train': 0.7936034593731165}
+12/27/2021 02:01:41 - INFO - codeparrot_training - Step 31255: {'lr': 0.00015521273497598093, 'samples': 16003072, 'steps': 31255, 'batch_loss/train': 0.7979706954210997}
+12/27/2021 02:01:55 - INFO - codeparrot_training - Step 31256: {'lr': 0.00015519814897498198, 'samples': 16003584, 'steps': 31256, 'batch_loss/train': 0.76047316507902}
+12/27/2021 02:02:06 - INFO - codeparrot_training - Step 31257: {'lr': 0.00015518356335087952, 'samples': 16004096, 'steps': 31257, 'batch_loss/train': 0.625092735979706}
+12/27/2021 02:02:16 - INFO - codeparrot_training - Step 31258: {'lr': 0.00015516897810373143, 'samples': 16004608, 'steps': 31258, 'batch_loss/train': 0.8180119409225881}
+12/27/2021 02:02:28 - INFO - codeparrot_training - Step 31259: {'lr': 0.00015515439323359557, 'samples': 16005120, 'steps': 31259, 'batch_loss/train': 0.7036831108853221}
+12/27/2021 02:02:39 - INFO - codeparrot_training - Step 31260: {'lr': 0.00015513980874053008, 'samples': 16005632, 'steps': 31260, 'batch_loss/train': 0.7192430375143886}
+12/27/2021 02:02:49 - INFO - codeparrot_training - Step 31261: {'lr': 0.00015512522462459295, 'samples': 16006144, 'steps': 31261, 'batch_loss/train': 0.7916339715011418}
+12/27/2021 02:03:02 - INFO - codeparrot_training - Step 31262: {'lr': 0.000155110640885842, 'samples': 16006656, 'steps': 31262, 'batch_loss/train': 0.7462668046355247}
+12/27/2021 02:03:12 - INFO - codeparrot_training - Step 31263: {'lr': 0.0001550960575243353, 'samples': 16007168, 'steps': 31263, 'batch_loss/train': 0.8187322812154889}
+12/27/2021 02:03:23 - INFO - codeparrot_training - Step 31264: {'lr': 0.00015508147454013093, 'samples': 16007680, 'steps': 31264, 'batch_loss/train': 0.708149014506489}
+12/27/2021 02:03:33 - INFO - codeparrot_training - Step 31265: {'lr': 0.00015506689193328676, 'samples': 16008192, 'steps': 31265, 'batch_loss/train': 0.7305104015395045}
+12/27/2021 02:03:47 - INFO - codeparrot_training - Step 31266: {'lr': 0.00015505230970386082, 'samples': 16008704, 'steps': 31266, 'batch_loss/train': 0.6202785763889551}
+12/27/2021 02:03:58 - INFO - codeparrot_training - Step 31267: {'lr': 0.00015503772785191094, 'samples': 16009216, 'steps': 31267, 'batch_loss/train': 0.6569737754762173}
+12/27/2021 02:04:08 - INFO - codeparrot_training - Step 31268: {'lr': 0.00015502314637749529, 'samples': 16009728, 'steps': 31268, 'batch_loss/train': 0.7104355180636048}
+12/27/2021 02:04:21 - INFO - codeparrot_training - Step 31269: {'lr': 0.0001550085652806717, 'samples': 16010240, 'steps': 31269, 'batch_loss/train': 0.6751037536887452}
+12/27/2021 02:04:31 - INFO - codeparrot_training - Step 31270: {'lr': 0.00015499398456149816, 'samples': 16010752, 'steps': 31270, 'batch_loss/train': 0.7389004686847329}
+12/27/2021 02:04:42 - INFO - codeparrot_training - Step 31271: {'lr': 0.00015497940422003274, 'samples': 16011264, 'steps': 31271, 'batch_loss/train': 0.47883270122110844}
+12/27/2021 02:04:54 - INFO - codeparrot_training - Step 31272: {'lr': 0.0001549648242563333, 'samples': 16011776, 'steps': 31272, 'batch_loss/train': 0.66883041895926}
+12/27/2021 02:05:05 - INFO - codeparrot_training - Step 31273: {'lr': 0.00015495024467045786, 'samples': 16012288, 'steps': 31273, 'batch_loss/train': 0.7301327046006918}
+12/27/2021 02:05:15 - INFO - codeparrot_training - Step 31274: {'lr': 0.00015493566546246425, 'samples': 16012800, 'steps': 31274, 'batch_loss/train': 0.4981325544649735}
+12/27/2021 02:05:27 - INFO - codeparrot_training - Step 31275: {'lr': 0.0001549210866324106, 'samples': 16013312, 'steps': 31275, 'batch_loss/train': 0.5584777336916886}
+12/27/2021 02:05:38 - INFO - codeparrot_training - Step 31276: {'lr': 0.0001549065081803549, 'samples': 16013824, 'steps': 31276, 'batch_loss/train': 0.7164248167537153}
+12/27/2021 02:05:48 - INFO - codeparrot_training - Step 31277: {'lr': 0.00015489193010635496, 'samples': 16014336, 'steps': 31277, 'batch_loss/train': 0.7296941699460149}
+12/27/2021 02:05:59 - INFO - codeparrot_training - Step 31278: {'lr': 0.00015487735241046874, 'samples': 16014848, 'steps': 31278, 'batch_loss/train': 0.6835520723834634}
+12/27/2021 02:06:13 - INFO - codeparrot_training - Step 31279: {'lr': 0.00015486277509275427, 'samples': 16015360, 'steps': 31279, 'batch_loss/train': 0.6912011979147792}
+12/27/2021 02:06:24 - INFO - codeparrot_training - Step 31280: {'lr': 0.00015484819815326953, 'samples': 16015872, 'steps': 31280, 'batch_loss/train': 0.7223558188416064}
+12/27/2021 02:06:34 - INFO - codeparrot_training - Step 31281: {'lr': 0.00015483362159207236, 'samples': 16016384, 'steps': 31281, 'batch_loss/train': 0.6753521482460201}
+12/27/2021 02:06:46 - INFO - codeparrot_training - Step 31282: {'lr': 0.00015481904540922079, 'samples': 16016896, 'steps': 31282, 'batch_loss/train': 0.7678639376536012}
+12/27/2021 02:06:57 - INFO - codeparrot_training - Step 31283: {'lr': 0.00015480446960477282, 'samples': 16017408, 'steps': 31283, 'batch_loss/train': 0.5597793461638503}
+12/27/2021 02:07:08 - INFO - codeparrot_training - Step 31284: {'lr': 0.00015478989417878636, 'samples': 16017920, 'steps': 31284, 'batch_loss/train': 0.6410588688449934}
+12/27/2021 02:07:20 - INFO - codeparrot_training - Step 31285: {'lr': 0.0001547753191313192, 'samples': 16018432, 'steps': 31285, 'batch_loss/train': 0.798741802573204}
+12/27/2021 02:07:30 - INFO - codeparrot_training - Step 31286: {'lr': 0.00015476074446242946, 'samples': 16018944, 'steps': 31286, 'batch_loss/train': 0.7210889346897602}
+12/27/2021 02:07:41 - INFO - codeparrot_training - Step 31287: {'lr': 0.0001547461701721751, 'samples': 16019456, 'steps': 31287, 'batch_loss/train': 0.6415602487977594}
+12/27/2021 02:07:55 - INFO - codeparrot_training - Step 31288: {'lr': 0.00015473159626061396, 'samples': 16019968, 'steps': 31288, 'batch_loss/train': 0.6473033728543669}
+12/27/2021 02:08:05 - INFO - codeparrot_training - Step 31289: {'lr': 0.00015471702272780398, 'samples': 16020480, 'steps': 31289, 'batch_loss/train': 0.7110807308927178}
+12/27/2021 02:08:16 - INFO - codeparrot_training - Step 31290: {'lr': 0.0001547024495738032, 'samples': 16020992, 'steps': 31290, 'batch_loss/train': 0.6674098647199571}
+12/27/2021 02:08:27 - INFO - codeparrot_training - Step 31291: {'lr': 0.00015468787679866948, 'samples': 16021504, 'steps': 31291, 'batch_loss/train': 0.6123711504042149}
+12/27/2021 02:08:39 - INFO - codeparrot_training - Step 31292: {'lr': 0.0001546733044024608, 'samples': 16022016, 'steps': 31292, 'batch_loss/train': 0.7036696026334539}
+12/27/2021 02:08:49 - INFO - codeparrot_training - Step 31293: {'lr': 0.000154658732385235, 'samples': 16022528, 'steps': 31293, 'batch_loss/train': 0.674368146341294}
+12/27/2021 02:09:00 - INFO - codeparrot_training - Step 31294: {'lr': 0.00015464416074705017, 'samples': 16023040, 'steps': 31294, 'batch_loss/train': 0.6091129976557568}
+12/27/2021 02:09:14 - INFO - codeparrot_training - Step 31295: {'lr': 0.00015462958948796407, 'samples': 16023552, 'steps': 31295, 'batch_loss/train': 0.742903359234333}
+12/27/2021 02:09:24 - INFO - codeparrot_training - Step 31296: {'lr': 0.0001546150186080347, 'samples': 16024064, 'steps': 31296, 'batch_loss/train': 0.8050195770338178}
+12/27/2021 02:09:35 - INFO - codeparrot_training - Step 31297: {'lr': 0.0001546004481073201, 'samples': 16024576, 'steps': 31297, 'batch_loss/train': 0.728780671954155}
+12/27/2021 02:09:47 - INFO - codeparrot_training - Step 31298: {'lr': 0.00015458587798587804, 'samples': 16025088, 'steps': 31298, 'batch_loss/train': 0.7994769895449281}
+12/27/2021 02:09:58 - INFO - codeparrot_training - Step 31299: {'lr': 0.00015457130824376652, 'samples': 16025600, 'steps': 31299, 'batch_loss/train': 0.7149194912053645}
+12/27/2021 02:10:08 - INFO - codeparrot_training - Step 31300: {'lr': 0.00015455673888104337, 'samples': 16026112, 'steps': 31300, 'batch_loss/train': 0.7383509390056133}
+12/27/2021 02:10:20 - INFO - codeparrot_training - Step 31301: {'lr': 0.00015454216989776664, 'samples': 16026624, 'steps': 31301, 'batch_loss/train': 0.7110766796395183}
+12/27/2021 02:10:31 - INFO - codeparrot_training - Step 31302: {'lr': 0.00015452760129399428, 'samples': 16027136, 'steps': 31302, 'batch_loss/train': 0.7304291408509016}
+12/27/2021 02:10:41 - INFO - codeparrot_training - Step 31303: {'lr': 0.00015451303306978408, 'samples': 16027648, 'steps': 31303, 'batch_loss/train': 0.7224130425602198}
+12/27/2021 02:10:52 - INFO - codeparrot_training - Step 31304: {'lr': 0.00015449846522519396, 'samples': 16028160, 'steps': 31304, 'batch_loss/train': 0.7913840226829052}
+12/27/2021 02:11:06 - INFO - codeparrot_training - Step 31305: {'lr': 0.00015448389776028188, 'samples': 16028672, 'steps': 31305, 'batch_loss/train': 0.7463649660348892}
+12/27/2021 02:11:16 - INFO - codeparrot_training - Step 31306: {'lr': 0.00015446933067510583, 'samples': 16029184, 'steps': 31306, 'batch_loss/train': 0.6852632639929652}
+12/27/2021 02:11:27 - INFO - codeparrot_training - Step 31307: {'lr': 0.00015445476396972352, 'samples': 16029696, 'steps': 31307, 'batch_loss/train': 0.7481912723742425}
+12/27/2021 02:11:39 - INFO - codeparrot_training - Step 31308: {'lr': 0.0001544401976441931, 'samples': 16030208, 'steps': 31308, 'batch_loss/train': 0.661697531118989}
+12/27/2021 02:11:50 - INFO - codeparrot_training - Step 31309: {'lr': 0.00015442563169857238, 'samples': 16030720, 'steps': 31309, 'batch_loss/train': 0.6916296659037471}
+12/27/2021 02:12:00 - INFO - codeparrot_training - Step 31310: {'lr': 0.00015441106613291923, 'samples': 16031232, 'steps': 31310, 'batch_loss/train': 0.6466857155319303}
+12/27/2021 02:12:13 - INFO - codeparrot_training - Step 31311: {'lr': 0.0001543965009472915, 'samples': 16031744, 'steps': 31311, 'batch_loss/train': 0.6556397834792733}
+12/27/2021 02:12:24 - INFO - codeparrot_training - Step 31312: {'lr': 0.0001543819361417473, 'samples': 16032256, 'steps': 31312, 'batch_loss/train': 0.6169125941814855}
+12/27/2021 02:12:34 - INFO - codeparrot_training - Step 31313: {'lr': 0.00015436737171634443, 'samples': 16032768, 'steps': 31313, 'batch_loss/train': 0.9026902765035629}
+12/27/2021 02:12:47 - INFO - codeparrot_training - Step 31314: {'lr': 0.00015435280767114073, 'samples': 16033280, 'steps': 31314, 'batch_loss/train': 0.7764902161434293}
+12/27/2021 02:12:57 - INFO - codeparrot_training - Step 31315: {'lr': 0.00015433824400619411, 'samples': 16033792, 'steps': 31315, 'batch_loss/train': 0.7373222464229912}
+12/27/2021 02:13:08 - INFO - codeparrot_training - Step 31316: {'lr': 0.0001543236807215626, 'samples': 16034304, 'steps': 31316, 'batch_loss/train': 0.7882818104699254}
+12/27/2021 02:13:20 - INFO - codeparrot_training - Step 31317: {'lr': 0.00015430911781730394, 'samples': 16034816, 'steps': 31317, 'batch_loss/train': 0.7285517184063792}
+12/27/2021 02:13:30 - INFO - codeparrot_training - Step 31318: {'lr': 0.00015429455529347607, 'samples': 16035328, 'steps': 31318, 'batch_loss/train': 0.722235044464469}
+12/27/2021 02:13:41 - INFO - codeparrot_training - Step 31319: {'lr': 0.00015427999315013703, 'samples': 16035840, 'steps': 31319, 'batch_loss/train': 0.8063041428104043}
+12/27/2021 02:13:52 - INFO - codeparrot_training - Step 31320: {'lr': 0.0001542654313873445, 'samples': 16036352, 'steps': 31320, 'batch_loss/train': 0.6599353859201074}
+12/27/2021 02:14:04 - INFO - codeparrot_training - Step 31321: {'lr': 0.00015425087000515655, 'samples': 16036864, 'steps': 31321, 'batch_loss/train': 0.6970173018053174}
+12/27/2021 02:14:15 - INFO - codeparrot_training - Step 31322: {'lr': 0.0001542363090036309, 'samples': 16037376, 'steps': 31322, 'batch_loss/train': 0.8440124550834298}
+12/27/2021 02:14:25 - INFO - codeparrot_training - Step 31323: {'lr': 0.0001542217483828256, 'samples': 16037888, 'steps': 31323, 'batch_loss/train': 0.8674872359260917}
+12/27/2021 02:14:38 - INFO - codeparrot_training - Step 31324: {'lr': 0.00015420718814279842, 'samples': 16038400, 'steps': 31324, 'batch_loss/train': 0.5953059657767881}
+12/27/2021 02:14:49 - INFO - codeparrot_training - Step 31325: {'lr': 0.00015419262828360734, 'samples': 16038912, 'steps': 31325, 'batch_loss/train': 0.9329207418486476}
+12/27/2021 02:15:00 - INFO - codeparrot_training - Step 31326: {'lr': 0.0001541780688053101, 'samples': 16039424, 'steps': 31326, 'batch_loss/train': 0.7426380440592766}
+12/27/2021 02:15:12 - INFO - codeparrot_training - Step 31327: {'lr': 0.0001541635097079647, 'samples': 16039936, 'steps': 31327, 'batch_loss/train': 0.721134283579886}
+12/27/2021 02:15:22 - INFO - codeparrot_training - Step 31328: {'lr': 0.00015414895099162906, 'samples': 16040448, 'steps': 31328, 'batch_loss/train': 0.7194748157635331}
+12/27/2021 02:15:33 - INFO - codeparrot_training - Step 31329: {'lr': 0.00015413439265636104, 'samples': 16040960, 'steps': 31329, 'batch_loss/train': 0.7242075130343437}
+12/27/2021 02:15:43 - INFO - codeparrot_training - Step 31330: {'lr': 0.00015411983470221832, 'samples': 16041472, 'steps': 31330, 'batch_loss/train': 0.6902520656585693}
+12/27/2021 02:15:56 - INFO - codeparrot_training - Step 31331: {'lr': 0.00015410527712925902, 'samples': 16041984, 'steps': 31331, 'batch_loss/train': 0.7494861204177141}
+12/27/2021 02:16:06 - INFO - codeparrot_training - Step 31332: {'lr': 0.000154090719937541, 'samples': 16042496, 'steps': 31332, 'batch_loss/train': 0.8218966205604374}
+12/27/2021 02:16:17 - INFO - codeparrot_training - Step 31333: {'lr': 0.00015407616312712192, 'samples': 16043008, 'steps': 31333, 'batch_loss/train': 0.7168535124510527}
+12/27/2021 02:16:30 - INFO - codeparrot_training - Step 31334: {'lr': 0.00015406160669805986, 'samples': 16043520, 'steps': 31334, 'batch_loss/train': 0.5433488389244303}
+12/27/2021 02:16:40 - INFO - codeparrot_training - Step 31335: {'lr': 0.00015404705065041264, 'samples': 16044032, 'steps': 31335, 'batch_loss/train': 0.6933231581933796}
+12/27/2021 02:16:51 - INFO - codeparrot_training - Step 31336: {'lr': 0.0001540324949842381, 'samples': 16044544, 'steps': 31336, 'batch_loss/train': 0.8995597707107663}
+12/27/2021 02:17:03 - INFO - codeparrot_training - Step 31337: {'lr': 0.0001540179396995941, 'samples': 16045056, 'steps': 31337, 'batch_loss/train': 0.659222003800096}
+12/27/2021 02:17:14 - INFO - codeparrot_training - Step 31338: {'lr': 0.00015400338479653857, 'samples': 16045568, 'steps': 31338, 'batch_loss/train': 0.8208300874102861}
+12/27/2021 02:17:24 - INFO - codeparrot_training - Step 31339: {'lr': 0.0001539888302751294, 'samples': 16046080, 'steps': 31339, 'batch_loss/train': 0.7539726081886329}
+12/27/2021 02:17:37 - INFO - codeparrot_training - Step 31340: {'lr': 0.00015397427613542431, 'samples': 16046592, 'steps': 31340, 'batch_loss/train': 0.7268832204863429}
+12/27/2021 02:17:48 - INFO - codeparrot_training - Step 31341: {'lr': 0.0001539597223774812, 'samples': 16047104, 'steps': 31341, 'batch_loss/train': 0.6770823698025197}
+12/27/2021 02:17:58 - INFO - codeparrot_training - Step 31342: {'lr': 0.00015394516900135805, 'samples': 16047616, 'steps': 31342, 'batch_loss/train': 0.8147261301055551}
+12/27/2021 02:18:09 - INFO - codeparrot_training - Step 31343: {'lr': 0.0001539306160071126, 'samples': 16048128, 'steps': 31343, 'batch_loss/train': 0.6636506328359246}
+12/27/2021 02:18:21 - INFO - codeparrot_training - Step 31344: {'lr': 0.00015391606339480268, 'samples': 16048640, 'steps': 31344, 'batch_loss/train': 0.6456280023267027}
+12/27/2021 02:18:32 - INFO - codeparrot_training - Step 31345: {'lr': 0.00015390151116448635, 'samples': 16049152, 'steps': 31345, 'batch_loss/train': 0.6903989776037633}
+12/27/2021 02:18:42 - INFO - codeparrot_training - Step 31346: {'lr': 0.00015388695931622127, 'samples': 16049664, 'steps': 31346, 'batch_loss/train': 0.6778666623868048}
+12/27/2021 02:18:54 - INFO - codeparrot_training - Step 31347: {'lr': 0.00015387240785006537, 'samples': 16050176, 'steps': 31347, 'batch_loss/train': 0.7661455273628235}
+12/27/2021 02:19:05 - INFO - codeparrot_training - Step 31348: {'lr': 0.00015385785676607638, 'samples': 16050688, 'steps': 31348, 'batch_loss/train': 0.7072465685196221}
+12/27/2021 02:19:16 - INFO - codeparrot_training - Step 31349: {'lr': 0.00015384330606431237, 'samples': 16051200, 'steps': 31349, 'batch_loss/train': 0.7317456197924912}
+12/27/2021 02:19:28 - INFO - codeparrot_training - Step 31350: {'lr': 0.000153828755744831, 'samples': 16051712, 'steps': 31350, 'batch_loss/train': 0.6996677408460528}
+12/27/2021 02:19:39 - INFO - codeparrot_training - Step 31351: {'lr': 0.00015381420580769025, 'samples': 16052224, 'steps': 31351, 'batch_loss/train': 0.6903347400948405}
+12/27/2021 02:19:50 - INFO - codeparrot_training - Step 31352: {'lr': 0.00015379965625294777, 'samples': 16052736, 'steps': 31352, 'batch_loss/train': 0.8197744432836771}
+12/27/2021 02:20:02 - INFO - codeparrot_training - Step 31353: {'lr': 0.00015378510708066162, 'samples': 16053248, 'steps': 31353, 'batch_loss/train': 0.557360382808838}
+12/27/2021 02:20:12 - INFO - codeparrot_training - Step 31354: {'lr': 0.0001537705582908896, 'samples': 16053760, 'steps': 31354, 'batch_loss/train': 0.6941123176948167}
+12/27/2021 02:20:23 - INFO - codeparrot_training - Step 31355: {'lr': 0.0001537560098836894, 'samples': 16054272, 'steps': 31355, 'batch_loss/train': 0.6945116906426847}
+12/27/2021 02:20:34 - INFO - codeparrot_training - Step 31356: {'lr': 0.00015374146185911903, 'samples': 16054784, 'steps': 31356, 'batch_loss/train': 0.7458361135795712}
+12/27/2021 02:20:46 - INFO - codeparrot_training - Step 31357: {'lr': 0.00015372691421723628, 'samples': 16055296, 'steps': 31357, 'batch_loss/train': 0.7057629227638245}
+12/27/2021 02:20:56 - INFO - codeparrot_training - Step 31358: {'lr': 0.000153712366958099, 'samples': 16055808, 'steps': 31358, 'batch_loss/train': 0.6619936747010797}
+12/27/2021 02:21:07 - INFO - codeparrot_training - Step 31359: {'lr': 0.00015369782008176487, 'samples': 16056320, 'steps': 31359, 'batch_loss/train': 0.843850277364254}
+12/27/2021 02:21:20 - INFO - codeparrot_training - Step 31360: {'lr': 0.00015368327358829186, 'samples': 16056832, 'steps': 31360, 'batch_loss/train': 0.7112798197194934}
+12/27/2021 02:21:30 - INFO - codeparrot_training - Step 31361: {'lr': 0.00015366872747773791, 'samples': 16057344, 'steps': 31361, 'batch_loss/train': 0.7124923411756754}
+12/27/2021 02:21:41 - INFO - codeparrot_training - Step 31362: {'lr': 0.00015365418175016063, 'samples': 16057856, 'steps': 31362, 'batch_loss/train': 0.7313026748597622}
+12/27/2021 02:21:53 - INFO - codeparrot_training - Step 31363: {'lr': 0.0001536396364056179, 'samples': 16058368, 'steps': 31363, 'batch_loss/train': 0.7527172064874321}
+12/27/2021 02:22:04 - INFO - codeparrot_training - Step 31364: {'lr': 0.0001536250914441677, 'samples': 16058880, 'steps': 31364, 'batch_loss/train': 0.6772037725895643}
+12/27/2021 02:22:15 - INFO - codeparrot_training - Step 31365: {'lr': 0.0001536105468658677, 'samples': 16059392, 'steps': 31365, 'batch_loss/train': 0.6888483893126249}
+12/27/2021 02:22:27 - INFO - codeparrot_training - Step 31366: {'lr': 0.00015359600267077583, 'samples': 16059904, 'steps': 31366, 'batch_loss/train': 0.7323987488634884}
+12/27/2021 02:22:38 - INFO - codeparrot_training - Step 31367: {'lr': 0.00015358145885894972, 'samples': 16060416, 'steps': 31367, 'batch_loss/train': 0.6252516122185625}
+12/27/2021 02:22:48 - INFO - codeparrot_training - Step 31368: {'lr': 0.00015356691543044743, 'samples': 16060928, 'steps': 31368, 'batch_loss/train': 0.6793262840947136}
+12/27/2021 02:22:59 - INFO - codeparrot_training - Step 31369: {'lr': 0.00015355237238532665, 'samples': 16061440, 'steps': 31369, 'batch_loss/train': 0.7993590449914336}
+12/27/2021 02:23:11 - INFO - codeparrot_training - Step 31370: {'lr': 0.00015353782972364515, 'samples': 16061952, 'steps': 31370, 'batch_loss/train': 0.753980353474617}
+12/27/2021 02:23:22 - INFO - codeparrot_training - Step 31371: {'lr': 0.0001535232874454609, 'samples': 16062464, 'steps': 31371, 'batch_loss/train': 0.6860061786137521}
+12/27/2021 02:23:32 - INFO - codeparrot_training - Step 31372: {'lr': 0.0001535087455508316, 'samples': 16062976, 'steps': 31372, 'batch_loss/train': 0.7205528421327472}
+12/27/2021 02:23:44 - INFO - codeparrot_training - Step 31373: {'lr': 0.00015349420403981519, 'samples': 16063488, 'steps': 31373, 'batch_loss/train': 0.7876288061961532}
+12/27/2021 02:23:55 - INFO - codeparrot_training - Step 31374: {'lr': 0.00015347966291246923, 'samples': 16064000, 'steps': 31374, 'batch_loss/train': 0.7264855918474495}
+12/27/2021 02:24:06 - INFO - codeparrot_training - Step 31375: {'lr': 0.00015346512216885179, 'samples': 16064512, 'steps': 31375, 'batch_loss/train': 0.7497520996257663}
+12/27/2021 02:24:18 - INFO - codeparrot_training - Step 31376: {'lr': 0.00015345058180902052, 'samples': 16065024, 'steps': 31376, 'batch_loss/train': 0.7570459204725921}
+12/27/2021 02:24:29 - INFO - codeparrot_training - Step 31377: {'lr': 0.00015343604183303333, 'samples': 16065536, 'steps': 31377, 'batch_loss/train': 0.506314558268059}
+12/27/2021 02:24:40 - INFO - codeparrot_training - Step 31378: {'lr': 0.0001534215022409479, 'samples': 16066048, 'steps': 31378, 'batch_loss/train': 0.6373367641645018}
+12/27/2021 02:24:52 - INFO - codeparrot_training - Step 31379: {'lr': 0.00015340696303282214, 'samples': 16066560, 'steps': 31379, 'batch_loss/train': 0.6185096751432866}
+12/27/2021 02:25:03 - INFO - codeparrot_training - Step 31380: {'lr': 0.0001533924242087139, 'samples': 16067072, 'steps': 31380, 'batch_loss/train': 0.6869913963600993}
+12/27/2021 02:25:13 - INFO - codeparrot_training - Step 31381: {'lr': 0.0001533778857686808, 'samples': 16067584, 'steps': 31381, 'batch_loss/train': 0.7948316056281328}
+12/27/2021 02:25:24 - INFO - codeparrot_training - Step 31382: {'lr': 0.00015336334771278077, 'samples': 16068096, 'steps': 31382, 'batch_loss/train': 0.730217142845504}
+12/27/2021 02:25:36 - INFO - codeparrot_training - Step 31383: {'lr': 0.00015334881004107164, 'samples': 16068608, 'steps': 31383, 'batch_loss/train': 0.8126309998333454}
+12/27/2021 02:25:47 - INFO - codeparrot_training - Step 31384: {'lr': 0.00015333427275361113, 'samples': 16069120, 'steps': 31384, 'batch_loss/train': 0.7286208756268024}
+12/27/2021 02:25:57 - INFO - codeparrot_training - Step 31385: {'lr': 0.00015331973585045694, 'samples': 16069632, 'steps': 31385, 'batch_loss/train': 0.8926768624223769}
+12/27/2021 02:26:09 - INFO - codeparrot_training - Step 31386: {'lr': 0.0001533051993316671, 'samples': 16070144, 'steps': 31386, 'batch_loss/train': 0.7544528073631227}
+12/27/2021 02:26:20 - INFO - codeparrot_training - Step 31387: {'lr': 0.00015329066319729926, 'samples': 16070656, 'steps': 31387, 'batch_loss/train': 0.8013615668751299}
+12/27/2021 02:26:31 - INFO - codeparrot_training - Step 31388: {'lr': 0.0001532761274474112, 'samples': 16071168, 'steps': 31388, 'batch_loss/train': 0.7397567750886083}
+12/27/2021 02:26:44 - INFO - codeparrot_training - Step 31389: {'lr': 0.00015326159208206068, 'samples': 16071680, 'steps': 31389, 'batch_loss/train': 0.7619536137208343}
+12/27/2021 02:26:54 - INFO - codeparrot_training - Step 31390: {'lr': 0.00015324705710130566, 'samples': 16072192, 'steps': 31390, 'batch_loss/train': 0.6652904450893402}
+12/27/2021 02:27:05 - INFO - codeparrot_training - Step 31391: {'lr': 0.00015323252250520374, 'samples': 16072704, 'steps': 31391, 'batch_loss/train': 1.5972239151597023}
+12/27/2021 02:27:17 - INFO - codeparrot_training - Step 31392: {'lr': 0.00015321798829381273, 'samples': 16073216, 'steps': 31392, 'batch_loss/train': 0.7530344566330314}
+12/27/2021 02:27:28 - INFO - codeparrot_training - Step 31393: {'lr': 0.00015320345446719053, 'samples': 16073728, 'steps': 31393, 'batch_loss/train': 0.6935775491874665}
+12/27/2021 02:27:38 - INFO - codeparrot_training - Step 31394: {'lr': 0.00015318892102539488, 'samples': 16074240, 'steps': 31394, 'batch_loss/train': 0.7033118134131655}
+12/27/2021 02:27:49 - INFO - codeparrot_training - Step 31395: {'lr': 0.00015317438796848346, 'samples': 16074752, 'steps': 31395, 'batch_loss/train': 0.7913850070908666}
+12/27/2021 02:28:02 - INFO - codeparrot_training - Step 31396: {'lr': 0.00015315985529651405, 'samples': 16075264, 'steps': 31396, 'batch_loss/train': 0.6549664112972096}
+12/27/2021 02:28:12 - INFO - codeparrot_training - Step 31397: {'lr': 0.0001531453230095446, 'samples': 16075776, 'steps': 31397, 'batch_loss/train': 0.6659903349354863}
+12/27/2021 02:28:23 - INFO - codeparrot_training - Step 31398: {'lr': 0.00015313079110763274, 'samples': 16076288, 'steps': 31398, 'batch_loss/train': 0.7683227695524693}
+12/27/2021 02:28:35 - INFO - codeparrot_training - Step 31399: {'lr': 0.00015311625959083634, 'samples': 16076800, 'steps': 31399, 'batch_loss/train': 0.7181908823549747}
+12/27/2021 02:28:46 - INFO - codeparrot_training - Step 31400: {'lr': 0.000153101728459213, 'samples': 16077312, 'steps': 31400, 'batch_loss/train': 0.5962661541998386}
+12/27/2021 02:28:56 - INFO - codeparrot_training - Step 31401: {'lr': 0.0001530871977128206, 'samples': 16077824, 'steps': 31401, 'batch_loss/train': 0.5788312088989187}
+12/27/2021 02:29:09 - INFO - codeparrot_training - Step 31402: {'lr': 0.00015307266735171702, 'samples': 16078336, 'steps': 31402, 'batch_loss/train': 0.740003545768559}
+12/27/2021 02:29:19 - INFO - codeparrot_training - Step 31403: {'lr': 0.0001530581373759599, 'samples': 16078848, 'steps': 31403, 'batch_loss/train': 0.6374310236424208}
+12/27/2021 02:29:30 - INFO - codeparrot_training - Step 31404: {'lr': 0.00015304360778560692, 'samples': 16079360, 'steps': 31404, 'batch_loss/train': 0.6790181607939303}
+12/27/2021 02:29:40 - INFO - codeparrot_training - Step 31405: {'lr': 0.00015302907858071596, 'samples': 16079872, 'steps': 31405, 'batch_loss/train': 0.657290754839778}
+12/27/2021 02:29:53 - INFO - codeparrot_training - Step 31406: {'lr': 0.00015301454976134488, 'samples': 16080384, 'steps': 31406, 'batch_loss/train': 0.7152929436415434}
+12/27/2021 02:30:04 - INFO - codeparrot_training - Step 31407: {'lr': 0.0001530000213275512, 'samples': 16080896, 'steps': 31407, 'batch_loss/train': 0.7268308158963919}
+12/27/2021 02:30:15 - INFO - codeparrot_training - Step 31408: {'lr': 0.00015298549327939288, 'samples': 16081408, 'steps': 31408, 'batch_loss/train': 0.7238501030951738}
+12/27/2021 02:30:27 - INFO - codeparrot_training - Step 31409: {'lr': 0.0001529709656169276, 'samples': 16081920, 'steps': 31409, 'batch_loss/train': 0.5563080223510042}
+12/27/2021 02:30:38 - INFO - codeparrot_training - Step 31410: {'lr': 0.00015295643834021316, 'samples': 16082432, 'steps': 31410, 'batch_loss/train': 0.715206197462976}
+12/27/2021 02:30:48 - INFO - codeparrot_training - Step 31411: {'lr': 0.0001529419114493072, 'samples': 16082944, 'steps': 31411, 'batch_loss/train': 0.7437752243131399}
+12/27/2021 02:31:01 - INFO - codeparrot_training - Step 31412: {'lr': 0.0001529273849442676, 'samples': 16083456, 'steps': 31412, 'batch_loss/train': 0.699783431366086}
+12/27/2021 02:31:11 - INFO - codeparrot_training - Step 31413: {'lr': 0.0001529128588251521, 'samples': 16083968, 'steps': 31413, 'batch_loss/train': 0.7374707804992795}
+12/27/2021 02:31:22 - INFO - codeparrot_training - Step 31414: {'lr': 0.00015289833309201835, 'samples': 16084480, 'steps': 31414, 'batch_loss/train': 0.6016094719816465}
+12/27/2021 02:31:34 - INFO - codeparrot_training - Step 31415: {'lr': 0.0001528838077449241, 'samples': 16084992, 'steps': 31415, 'batch_loss/train': 0.6190495310293045}
+12/27/2021 02:31:45 - INFO - codeparrot_training - Step 31416: {'lr': 0.0001528692827839273, 'samples': 16085504, 'steps': 31416, 'batch_loss/train': 0.7923814784735441}
+12/27/2021 02:31:56 - INFO - codeparrot_training - Step 31417: {'lr': 0.0001528547582090855, 'samples': 16086016, 'steps': 31417, 'batch_loss/train': 0.652852586004883}
+12/27/2021 02:32:06 - INFO - codeparrot_training - Step 31418: {'lr': 0.00015284023402045645, 'samples': 16086528, 'steps': 31418, 'batch_loss/train': 0.6484762988984585}
+12/27/2021 02:32:19 - INFO - codeparrot_training - Step 31419: {'lr': 0.00015282571021809805, 'samples': 16087040, 'steps': 31419, 'batch_loss/train': 0.7060039136558771}
+12/27/2021 02:32:30 - INFO - codeparrot_training - Step 31420: {'lr': 0.0001528111868020679, 'samples': 16087552, 'steps': 31420, 'batch_loss/train': 0.6574824941344559}
+12/27/2021 02:32:40 - INFO - codeparrot_training - Step 31421: {'lr': 0.00015279666377242374, 'samples': 16088064, 'steps': 31421, 'batch_loss/train': 0.6841356151271611}
+12/27/2021 02:32:52 - INFO - codeparrot_training - Step 31422: {'lr': 0.0001527821411292233, 'samples': 16088576, 'steps': 31422, 'batch_loss/train': 0.667212750588078}
+12/27/2021 02:33:03 - INFO - codeparrot_training - Step 31423: {'lr': 0.00015276761887252446, 'samples': 16089088, 'steps': 31423, 'batch_loss/train': 0.7037957014981657}
+12/27/2021 02:33:14 - INFO - codeparrot_training - Step 31424: {'lr': 0.00015275309700238482, 'samples': 16089600, 'steps': 31424, 'batch_loss/train': 0.728162637911737}
+12/27/2021 02:33:27 - INFO - codeparrot_training - Step 31425: {'lr': 0.00015273857551886217, 'samples': 16090112, 'steps': 31425, 'batch_loss/train': 0.7412622040137649}
+12/27/2021 02:33:37 - INFO - codeparrot_training - Step 31426: {'lr': 0.00015272405442201415, 'samples': 16090624, 'steps': 31426, 'batch_loss/train': 0.6198385075258557}
+12/27/2021 02:33:48 - INFO - codeparrot_training - Step 31427: {'lr': 0.00015270953371189855, 'samples': 16091136, 'steps': 31427, 'batch_loss/train': 0.7468491579056717}
+12/27/2021 02:33:59 - INFO - codeparrot_training - Step 31428: {'lr': 0.0001526950133885732, 'samples': 16091648, 'steps': 31428, 'batch_loss/train': 0.7116808767896146}
+12/27/2021 02:34:11 - INFO - codeparrot_training - Step 31429: {'lr': 0.00015268049345209565, 'samples': 16092160, 'steps': 31429, 'batch_loss/train': 0.8158577280119061}
+12/27/2021 02:34:21 - INFO - codeparrot_training - Step 31430: {'lr': 0.0001526659739025238, 'samples': 16092672, 'steps': 31430, 'batch_loss/train': 0.6291690769139677}
+12/27/2021 02:34:32 - INFO - codeparrot_training - Step 31431: {'lr': 0.0001526514547399152, 'samples': 16093184, 'steps': 31431, 'batch_loss/train': 0.6905692927539349}
+12/27/2021 02:34:44 - INFO - codeparrot_training - Step 31432: {'lr': 0.00015263693596432776, 'samples': 16093696, 'steps': 31432, 'batch_loss/train': 0.624697970226407}
+12/27/2021 02:34:55 - INFO - codeparrot_training - Step 31433: {'lr': 0.00015262241757581896, 'samples': 16094208, 'steps': 31433, 'batch_loss/train': 0.47775574878323823}
+12/27/2021 02:35:05 - INFO - codeparrot_training - Step 31434: {'lr': 0.00015260789957444675, 'samples': 16094720, 'steps': 31434, 'batch_loss/train': 0.8996003028005362}
+12/27/2021 02:35:19 - INFO - codeparrot_training - Step 31435: {'lr': 0.00015259338196026877, 'samples': 16095232, 'steps': 31435, 'batch_loss/train': 0.7121553122997284}
+12/27/2021 02:35:29 - INFO - codeparrot_training - Step 31436: {'lr': 0.0001525788647333427, 'samples': 16095744, 'steps': 31436, 'batch_loss/train': 0.6188963684253395}
+12/27/2021 02:35:40 - INFO - codeparrot_training - Step 31437: {'lr': 0.0001525643478937262, 'samples': 16096256, 'steps': 31437, 'batch_loss/train': 0.7426007548347116}
+12/27/2021 02:35:52 - INFO - codeparrot_training - Step 31438: {'lr': 0.0001525498314414772, 'samples': 16096768, 'steps': 31438, 'batch_loss/train': 0.7272120942361653}
+12/27/2021 02:36:03 - INFO - codeparrot_training - Step 31439: {'lr': 0.00015253531537665323, 'samples': 16097280, 'steps': 31439, 'batch_loss/train': 0.9965296518057585}
+12/27/2021 02:36:14 - INFO - codeparrot_training - Step 31440: {'lr': 0.00015252079969931204, 'samples': 16097792, 'steps': 31440, 'batch_loss/train': 0.5572548629716039}
+12/27/2021 02:36:24 - INFO - codeparrot_training - Step 31441: {'lr': 0.00015250628440951125, 'samples': 16098304, 'steps': 31441, 'batch_loss/train': 0.6187423735391349}
+12/27/2021 02:36:36 - INFO - codeparrot_training - Step 31442: {'lr': 0.0001524917695073088, 'samples': 16098816, 'steps': 31442, 'batch_loss/train': 0.6476672918652184}
+12/27/2021 02:36:47 - INFO - codeparrot_training - Step 31443: {'lr': 0.0001524772549927622, 'samples': 16099328, 'steps': 31443, 'batch_loss/train': 0.7253275644034147}
+12/27/2021 02:36:58 - INFO - codeparrot_training - Step 31444: {'lr': 0.00015246274086592914, 'samples': 16099840, 'steps': 31444, 'batch_loss/train': 0.752673065289855}
+12/27/2021 02:37:11 - INFO - codeparrot_training - Step 31445: {'lr': 0.0001524482271268675, 'samples': 16100352, 'steps': 31445, 'batch_loss/train': 0.6029241657233797}
+12/27/2021 02:37:21 - INFO - codeparrot_training - Step 31446: {'lr': 0.00015243371377563487, 'samples': 16100864, 'steps': 31446, 'batch_loss/train': 0.6811741283163428}
+12/27/2021 02:37:32 - INFO - codeparrot_training - Step 31447: {'lr': 0.00015241920081228894, 'samples': 16101376, 'steps': 31447, 'batch_loss/train': 0.6016291776613798}
+12/27/2021 02:37:44 - INFO - codeparrot_training - Step 31448: {'lr': 0.00015240468823688735, 'samples': 16101888, 'steps': 31448, 'batch_loss/train': 0.7493951926007867}
+12/27/2021 02:37:55 - INFO - codeparrot_training - Step 31449: {'lr': 0.00015239017604948797, 'samples': 16102400, 'steps': 31449, 'batch_loss/train': 0.8252062508836389}
+12/27/2021 02:38:05 - INFO - codeparrot_training - Step 31450: {'lr': 0.00015237566425014832, 'samples': 16102912, 'steps': 31450, 'batch_loss/train': 0.7388798296451569}
+12/27/2021 02:38:16 - INFO - codeparrot_training - Step 31451: {'lr': 0.00015236115283892628, 'samples': 16103424, 'steps': 31451, 'batch_loss/train': 0.7227443149313331}
+12/27/2021 02:38:29 - INFO - codeparrot_training - Step 31452: {'lr': 0.00015234664181587926, 'samples': 16103936, 'steps': 31452, 'batch_loss/train': 0.7169483460020274}
+12/27/2021 02:38:39 - INFO - codeparrot_training - Step 31453: {'lr': 0.0001523321311810652, 'samples': 16104448, 'steps': 31453, 'batch_loss/train': 0.7166472496464849}
+12/27/2021 02:38:50 - INFO - codeparrot_training - Step 31454: {'lr': 0.00015231762093454178, 'samples': 16104960, 'steps': 31454, 'batch_loss/train': 0.5630936808884144}
+12/27/2021 02:39:02 - INFO - codeparrot_training - Step 31455: {'lr': 0.00015230311107636646, 'samples': 16105472, 'steps': 31455, 'batch_loss/train': 0.6408872394822538}
+12/27/2021 02:39:13 - INFO - codeparrot_training - Step 31456: {'lr': 0.0001522886016065972, 'samples': 16105984, 'steps': 31456, 'batch_loss/train': 0.7261606520041823}
+12/27/2021 02:39:23 - INFO - codeparrot_training - Step 31457: {'lr': 0.00015227409252529156, 'samples': 16106496, 'steps': 31457, 'batch_loss/train': 0.7113102530129254}
+12/27/2021 02:39:35 - INFO - codeparrot_training - Step 31458: {'lr': 0.00015225958383250724, 'samples': 16107008, 'steps': 31458, 'batch_loss/train': 0.5090793297276832}
+12/27/2021 02:39:46 - INFO - codeparrot_training - Step 31459: {'lr': 0.0001522450755283018, 'samples': 16107520, 'steps': 31459, 'batch_loss/train': 0.7473622761899605}
+12/27/2021 02:39:57 - INFO - codeparrot_training - Step 31460: {'lr': 0.0001522305676127331, 'samples': 16108032, 'steps': 31460, 'batch_loss/train': 0.6404742567101493}
+12/27/2021 02:40:09 - INFO - codeparrot_training - Step 31461: {'lr': 0.0001522160600858588, 'samples': 16108544, 'steps': 31461, 'batch_loss/train': 0.7027882996480912}
+12/27/2021 02:40:19 - INFO - codeparrot_training - Step 31462: {'lr': 0.00015220155294773646, 'samples': 16109056, 'steps': 31462, 'batch_loss/train': 0.6904643606394529}
+12/27/2021 02:40:30 - INFO - codeparrot_training - Step 31463: {'lr': 0.00015218704619842377, 'samples': 16109568, 'steps': 31463, 'batch_loss/train': 0.7433326467871666}
+12/27/2021 02:40:41 - INFO - codeparrot_training - Step 31464: {'lr': 0.00015217253983797858, 'samples': 16110080, 'steps': 31464, 'batch_loss/train': 0.7341283932328224}
+12/27/2021 02:40:54 - INFO - codeparrot_training - Step 31465: {'lr': 0.0001521580338664584, 'samples': 16110592, 'steps': 31465, 'batch_loss/train': 0.6866295222425833}
+12/27/2021 02:41:04 - INFO - codeparrot_training - Step 31466: {'lr': 0.0001521435282839208, 'samples': 16111104, 'steps': 31466, 'batch_loss/train': 0.7785090822726488}
+12/27/2021 02:41:15 - INFO - codeparrot_training - Step 31467: {'lr': 0.0001521290230904237, 'samples': 16111616, 'steps': 31467, 'batch_loss/train': 0.6328826197423041}
+12/27/2021 02:41:27 - INFO - codeparrot_training - Step 31468: {'lr': 0.00015211451828602468, 'samples': 16112128, 'steps': 31468, 'batch_loss/train': 0.6729566007852554}
+12/27/2021 02:41:38 - INFO - codeparrot_training - Step 31469: {'lr': 0.00015210001387078132, 'samples': 16112640, 'steps': 31469, 'batch_loss/train': 0.7594414316117764}
+12/27/2021 02:41:48 - INFO - codeparrot_training - Step 31470: {'lr': 0.0001520855098447513, 'samples': 16113152, 'steps': 31470, 'batch_loss/train': 0.7550814980641007}
+12/27/2021 02:42:01 - INFO - codeparrot_training - Step 31471: {'lr': 0.0001520710062079924, 'samples': 16113664, 'steps': 31471, 'batch_loss/train': 0.7066844720393419}
+12/27/2021 02:42:11 - INFO - codeparrot_training - Step 31472: {'lr': 0.00015205650296056216, 'samples': 16114176, 'steps': 31472, 'batch_loss/train': 0.6995956678874791}
+12/27/2021 02:42:22 - INFO - codeparrot_training - Step 31473: {'lr': 0.00015204200010251833, 'samples': 16114688, 'steps': 31473, 'batch_loss/train': 0.7848382368683815}
+12/27/2021 02:42:34 - INFO - codeparrot_training - Step 31474: {'lr': 0.00015202749763391842, 'samples': 16115200, 'steps': 31474, 'batch_loss/train': 0.6401720058638602}
+12/27/2021 02:42:45 - INFO - codeparrot_training - Step 31475: {'lr': 0.00015201299555482028, 'samples': 16115712, 'steps': 31475, 'batch_loss/train': 0.6189368153281976}
+12/27/2021 02:42:56 - INFO - codeparrot_training - Step 31476: {'lr': 0.00015199849386528144, 'samples': 16116224, 'steps': 31476, 'batch_loss/train': 0.5850978442467749}
+12/27/2021 02:43:06 - INFO - codeparrot_training - Step 31477: {'lr': 0.00015198399256535964, 'samples': 16116736, 'steps': 31477, 'batch_loss/train': 0.768613045103848}
+12/27/2021 02:43:19 - INFO - codeparrot_training - Step 31478: {'lr': 0.00015196949165511236, 'samples': 16117248, 'steps': 31478, 'batch_loss/train': 0.7738383379764855}
+12/27/2021 02:43:29 - INFO - codeparrot_training - Step 31479: {'lr': 0.00015195499113459742, 'samples': 16117760, 'steps': 31479, 'batch_loss/train': 0.6964362990111113}
+12/27/2021 02:43:40 - INFO - codeparrot_training - Step 31480: {'lr': 0.00015194049100387247, 'samples': 16118272, 'steps': 31480, 'batch_loss/train': 0.7328276028856635}
+12/27/2021 02:43:53 - INFO - codeparrot_training - Step 31481: {'lr': 0.000151925991262995, 'samples': 16118784, 'steps': 31481, 'batch_loss/train': 0.7583038443699479}
+12/27/2021 02:44:03 - INFO - codeparrot_training - Step 31482: {'lr': 0.0001519114919120228, 'samples': 16119296, 'steps': 31482, 'batch_loss/train': 0.6309347879141569}
+12/27/2021 02:44:14 - INFO - codeparrot_training - Step 31483: {'lr': 0.0001518969929510135, 'samples': 16119808, 'steps': 31483, 'batch_loss/train': 0.703783311881125}
+12/27/2021 02:44:26 - INFO - codeparrot_training - Step 31484: {'lr': 0.00015188249438002476, 'samples': 16120320, 'steps': 31484, 'batch_loss/train': 0.6927805099403486}
+12/27/2021 02:44:37 - INFO - codeparrot_training - Step 31485: {'lr': 0.00015186799619911403, 'samples': 16120832, 'steps': 31485, 'batch_loss/train': 0.8748905076645315}
+12/27/2021 02:44:47 - INFO - codeparrot_training - Step 31486: {'lr': 0.00015185349840833917, 'samples': 16121344, 'steps': 31486, 'batch_loss/train': 0.8289650953374803}
+12/27/2021 02:44:59 - INFO - codeparrot_training - Step 31487: {'lr': 0.0001518390010077578, 'samples': 16121856, 'steps': 31487, 'batch_loss/train': 0.7433943618088961}
+12/27/2021 02:45:10 - INFO - codeparrot_training - Step 31488: {'lr': 0.00015182450399742743, 'samples': 16122368, 'steps': 31488, 'batch_loss/train': 0.7184185329824686}
+12/27/2021 02:45:20 - INFO - codeparrot_training - Step 31489: {'lr': 0.00015181000737740573, 'samples': 16122880, 'steps': 31489, 'batch_loss/train': 0.6129598161205649}
+12/27/2021 02:45:31 - INFO - codeparrot_training - Step 31490: {'lr': 0.00015179551114775046, 'samples': 16123392, 'steps': 31490, 'batch_loss/train': 0.7467375372070819}
+12/27/2021 02:45:44 - INFO - codeparrot_training - Step 31491: {'lr': 0.0001517810153085191, 'samples': 16123904, 'steps': 31491, 'batch_loss/train': 0.7727363593876362}
+12/27/2021 02:45:54 - INFO - codeparrot_training - Step 31492: {'lr': 0.00015176651985976928, 'samples': 16124416, 'steps': 31492, 'batch_loss/train': 0.7054386329837143}
+12/27/2021 02:46:05 - INFO - codeparrot_training - Step 31493: {'lr': 0.00015175202480155882, 'samples': 16124928, 'steps': 31493, 'batch_loss/train': 0.7159635750576854}
+12/27/2021 02:46:17 - INFO - codeparrot_training - Step 31494: {'lr': 0.00015173753013394514, 'samples': 16125440, 'steps': 31494, 'batch_loss/train': 0.6832621422363445}
+12/27/2021 02:46:28 - INFO - codeparrot_training - Step 31495: {'lr': 0.00015172303585698596, 'samples': 16125952, 'steps': 31495, 'batch_loss/train': 0.7718106820248067}
+12/27/2021 02:46:38 - INFO - codeparrot_training - Step 31496: {'lr': 0.0001517085419707388, 'samples': 16126464, 'steps': 31496, 'batch_loss/train': 0.5990631942404434}
+12/27/2021 02:46:51 - INFO - codeparrot_training - Step 31497: {'lr': 0.00015169404847526147, 'samples': 16126976, 'steps': 31497, 'batch_loss/train': 0.7343331323936582}
+12/27/2021 02:47:02 - INFO - codeparrot_training - Step 31498: {'lr': 0.00015167955537061145, 'samples': 16127488, 'steps': 31498, 'batch_loss/train': 0.7331145964562893}
+12/27/2021 02:47:12 - INFO - codeparrot_training - Step 31499: {'lr': 0.00015166506265684642, 'samples': 16128000, 'steps': 31499, 'batch_loss/train': 0.6760934421326965}
+12/27/2021 02:47:24 - INFO - codeparrot_training - Step 31500: {'lr': 0.00015165057033402388, 'samples': 16128512, 'steps': 31500, 'batch_loss/train': 0.7103553544729948}
+12/27/2021 02:47:35 - INFO - codeparrot_training - Step 31501: {'lr': 0.0001516360784022016, 'samples': 16129024, 'steps': 31501, 'batch_loss/train': 0.706904532853514}
+12/27/2021 02:47:45 - INFO - codeparrot_training - Step 31502: {'lr': 0.00015162158686143716, 'samples': 16129536, 'steps': 31502, 'batch_loss/train': 0.5841919060912915}
+12/27/2021 02:47:56 - INFO - codeparrot_training - Step 31503: {'lr': 0.00015160709571178805, 'samples': 16130048, 'steps': 31503, 'batch_loss/train': 0.6139028932084329}
+12/27/2021 02:48:08 - INFO - codeparrot_training - Step 31504: {'lr': 0.00015159260495331206, 'samples': 16130560, 'steps': 31504, 'batch_loss/train': 0.6896583186462522}
+12/27/2021 02:48:19 - INFO - codeparrot_training - Step 31505: {'lr': 0.0001515781145860667, 'samples': 16131072, 'steps': 31505, 'batch_loss/train': 0.6065133341471665}
+12/27/2021 02:48:30 - INFO - codeparrot_training - Step 31506: {'lr': 0.0001515636246101096, 'samples': 16131584, 'steps': 31506, 'batch_loss/train': 0.5704595501883887}
+12/27/2021 02:48:42 - INFO - codeparrot_training - Step 31507: {'lr': 0.0001515491350254983, 'samples': 16132096, 'steps': 31507, 'batch_loss/train': 0.6552599861170165}
+12/27/2021 02:48:52 - INFO - codeparrot_training - Step 31508: {'lr': 0.0001515346458322905, 'samples': 16132608, 'steps': 31508, 'batch_loss/train': 0.686503151897341}
+12/27/2021 02:49:03 - INFO - codeparrot_training - Step 31509: {'lr': 0.00015152015703054383, 'samples': 16133120, 'steps': 31509, 'batch_loss/train': 0.7183635057881474}
+12/27/2021 02:49:16 - INFO - codeparrot_training - Step 31510: {'lr': 0.00015150566862031585, 'samples': 16133632, 'steps': 31510, 'batch_loss/train': 0.7410596385598183}
+12/27/2021 02:49:26 - INFO - codeparrot_training - Step 31511: {'lr': 0.000151491180601664, 'samples': 16134144, 'steps': 31511, 'batch_loss/train': 0.6397136354353279}
+12/27/2021 02:49:37 - INFO - codeparrot_training - Step 31512: {'lr': 0.00015147669297464606, 'samples': 16134656, 'steps': 31512, 'batch_loss/train': 0.7214510682970285}
+12/27/2021 02:49:49 - INFO - codeparrot_training - Step 31513: {'lr': 0.00015146220573931967, 'samples': 16135168, 'steps': 31513, 'batch_loss/train': 0.737498658709228}
+12/27/2021 02:49:59 - INFO - codeparrot_training - Step 31514: {'lr': 0.00015144771889574228, 'samples': 16135680, 'steps': 31514, 'batch_loss/train': 0.6294438873883337}
+12/27/2021 02:50:10 - INFO - codeparrot_training - Step 31515: {'lr': 0.0001514332324439715, 'samples': 16136192, 'steps': 31515, 'batch_loss/train': 0.6383352223783731}
+12/27/2021 02:50:21 - INFO - codeparrot_training - Step 31516: {'lr': 0.00015141874638406507, 'samples': 16136704, 'steps': 31516, 'batch_loss/train': 0.6964890863746405}
+12/27/2021 02:50:33 - INFO - codeparrot_training - Step 31517: {'lr': 0.00015140426071608043, 'samples': 16137216, 'steps': 31517, 'batch_loss/train': 0.7416737475432456}
+12/27/2021 02:50:43 - INFO - codeparrot_training - Step 31518: {'lr': 0.0001513897754400752, 'samples': 16137728, 'steps': 31518, 'batch_loss/train': 0.7244674609974027}
+12/27/2021 02:50:54 - INFO - codeparrot_training - Step 31519: {'lr': 0.00015137529055610704, 'samples': 16138240, 'steps': 31519, 'batch_loss/train': 0.7813706323504448}
+12/27/2021 02:51:07 - INFO - codeparrot_training - Step 31520: {'lr': 0.00015136080606423352, 'samples': 16138752, 'steps': 31520, 'batch_loss/train': 0.6413423191988841}
+12/27/2021 02:51:17 - INFO - codeparrot_training - Step 31521: {'lr': 0.00015134632196451214, 'samples': 16139264, 'steps': 31521, 'batch_loss/train': 0.5576433222740889}
+12/27/2021 02:51:28 - INFO - codeparrot_training - Step 31522: {'lr': 0.00015133183825700048, 'samples': 16139776, 'steps': 31522, 'batch_loss/train': 0.6848308630287647}
+12/27/2021 02:51:40 - INFO - codeparrot_training - Step 31523: {'lr': 0.00015131735494175629, 'samples': 16140288, 'steps': 31523, 'batch_loss/train': 0.6837809784337878}
+12/27/2021 02:51:51 - INFO - codeparrot_training - Step 31524: {'lr': 0.00015130287201883696, 'samples': 16140800, 'steps': 31524, 'batch_loss/train': 0.7010832452215254}
+12/27/2021 02:52:01 - INFO - codeparrot_training - Step 31525: {'lr': 0.0001512883894883002, 'samples': 16141312, 'steps': 31525, 'batch_loss/train': 0.690398509032093}
+12/27/2021 02:52:14 - INFO - codeparrot_training - Step 31526: {'lr': 0.0001512739073502034, 'samples': 16141824, 'steps': 31526, 'batch_loss/train': 0.7113946229219437}
+12/27/2021 02:52:25 - INFO - codeparrot_training - Step 31527: {'lr': 0.00015125942560460437, 'samples': 16142336, 'steps': 31527, 'batch_loss/train': 0.7750695394352078}
+12/27/2021 02:52:35 - INFO - codeparrot_training - Step 31528: {'lr': 0.0001512449442515606, 'samples': 16142848, 'steps': 31528, 'batch_loss/train': 0.827846510335803}
+12/27/2021 02:52:46 - INFO - codeparrot_training - Step 31529: {'lr': 0.00015123046329112955, 'samples': 16143360, 'steps': 31529, 'batch_loss/train': 0.6886011816095561}
+12/27/2021 02:52:58 - INFO - codeparrot_training - Step 31530: {'lr': 0.000151215982723369, 'samples': 16143872, 'steps': 31530, 'batch_loss/train': 0.7595715820789337}
+12/27/2021 02:53:09 - INFO - codeparrot_training - Step 31531: {'lr': 0.00015120150254833634, 'samples': 16144384, 'steps': 31531, 'batch_loss/train': 0.6852353151189163}
+12/27/2021 02:53:19 - INFO - codeparrot_training - Step 31532: {'lr': 0.00015118702276608925, 'samples': 16144896, 'steps': 31532, 'batch_loss/train': 0.7253406811505556}
+12/27/2021 02:53:32 - INFO - codeparrot_training - Step 31533: {'lr': 0.00015117254337668515, 'samples': 16145408, 'steps': 31533, 'batch_loss/train': 0.7702100090391468}
+12/27/2021 02:53:43 - INFO - codeparrot_training - Step 31534: {'lr': 0.00015115806438018175, 'samples': 16145920, 'steps': 31534, 'batch_loss/train': 0.671945808455348}
+12/27/2021 02:53:53 - INFO - codeparrot_training - Step 31535: {'lr': 0.00015114358577663663, 'samples': 16146432, 'steps': 31535, 'batch_loss/train': 0.750348842702806}
+12/27/2021 02:54:06 - INFO - codeparrot_training - Step 31536: {'lr': 0.0001511291075661072, 'samples': 16146944, 'steps': 31536, 'batch_loss/train': 0.65590674552368}
+12/27/2021 02:54:17 - INFO - codeparrot_training - Step 31537: {'lr': 0.00015111462974865108, 'samples': 16147456, 'steps': 31537, 'batch_loss/train': 0.7227046792395413}
+12/27/2021 02:54:27 - INFO - codeparrot_training - Step 31538: {'lr': 0.00015110015232432594, 'samples': 16147968, 'steps': 31538, 'batch_loss/train': 0.592062541982159}
+12/27/2021 02:54:38 - INFO - codeparrot_training - Step 31539: {'lr': 0.00015108567529318928, 'samples': 16148480, 'steps': 31539, 'batch_loss/train': 0.5439181718975306}
+12/27/2021 02:54:50 - INFO - codeparrot_training - Step 31540: {'lr': 0.0001510711986552985, 'samples': 16148992, 'steps': 31540, 'batch_loss/train': 0.7469077873975039}
+12/27/2021 02:55:01 - INFO - codeparrot_training - Step 31541: {'lr': 0.00015105672241071133, 'samples': 16149504, 'steps': 31541, 'batch_loss/train': 0.7096933517605066}
+12/27/2021 02:55:11 - INFO - codeparrot_training - Step 31542: {'lr': 0.00015104224655948533, 'samples': 16150016, 'steps': 31542, 'batch_loss/train': 0.6750988978892565}
+12/27/2021 02:55:23 - INFO - codeparrot_training - Step 31543: {'lr': 0.00015102777110167798, 'samples': 16150528, 'steps': 31543, 'batch_loss/train': 0.7328909016214311}
+12/27/2021 02:55:34 - INFO - codeparrot_training - Step 31544: {'lr': 0.00015101329603734676, 'samples': 16151040, 'steps': 31544, 'batch_loss/train': 0.7439754949882627}
+12/27/2021 02:55:45 - INFO - codeparrot_training - Step 31545: {'lr': 0.00015099882136654938, 'samples': 16151552, 'steps': 31545, 'batch_loss/train': 0.7246581744402647}
+12/27/2021 02:55:57 - INFO - codeparrot_training - Step 31546: {'lr': 0.00015098434708934333, 'samples': 16152064, 'steps': 31546, 'batch_loss/train': 0.7958050114102662}
+12/27/2021 02:56:07 - INFO - codeparrot_training - Step 31547: {'lr': 0.00015096987320578606, 'samples': 16152576, 'steps': 31547, 'batch_loss/train': 0.6317842246498913}
+12/27/2021 02:56:18 - INFO - codeparrot_training - Step 31548: {'lr': 0.00015095539971593514, 'samples': 16153088, 'steps': 31548, 'batch_loss/train': 0.6659115398069844}
+12/27/2021 02:56:32 - INFO - codeparrot_training - Step 31549: {'lr': 0.00015094092661984825, 'samples': 16153600, 'steps': 31549, 'batch_loss/train': 0.6573078613728285}
+12/27/2021 02:56:42 - INFO - codeparrot_training - Step 31550: {'lr': 0.0001509264539175828, 'samples': 16154112, 'steps': 31550, 'batch_loss/train': 0.5794845618656836}
+12/27/2021 02:56:53 - INFO - codeparrot_training - Step 31551: {'lr': 0.0001509119816091964, 'samples': 16154624, 'steps': 31551, 'batch_loss/train': 0.7186567434109747}
+12/27/2021 02:57:04 - INFO - codeparrot_training - Step 31552: {'lr': 0.0001508975096947464, 'samples': 16155136, 'steps': 31552, 'batch_loss/train': 0.6341042334679514}
+12/27/2021 02:57:16 - INFO - codeparrot_training - Step 31553: {'lr': 0.00015088303817429062, 'samples': 16155648, 'steps': 31553, 'batch_loss/train': 0.7286252825288102}
+12/27/2021 02:57:26 - INFO - codeparrot_training - Step 31554: {'lr': 0.00015086856704788642, 'samples': 16156160, 'steps': 31554, 'batch_loss/train': 0.5001787610235624}
+12/27/2021 02:57:37 - INFO - codeparrot_training - Step 31555: {'lr': 0.00015085409631559132, 'samples': 16156672, 'steps': 31555, 'batch_loss/train': 0.6694228057749569}
+12/27/2021 02:57:50 - INFO - codeparrot_training - Step 31556: {'lr': 0.00015083962597746298, 'samples': 16157184, 'steps': 31556, 'batch_loss/train': 0.668015081435442}
+12/27/2021 02:58:01 - INFO - codeparrot_training - Step 31557: {'lr': 0.00015082515603355882, 'samples': 16157696, 'steps': 31557, 'batch_loss/train': 0.7443045871332288}
+12/27/2021 02:58:11 - INFO - codeparrot_training - Step 31558: {'lr': 0.00015081068648393643, 'samples': 16158208, 'steps': 31558, 'batch_loss/train': 0.7621028728317469}
+12/27/2021 02:58:23 - INFO - codeparrot_training - Step 31559: {'lr': 0.00015079621732865317, 'samples': 16158720, 'steps': 31559, 'batch_loss/train': 0.6233878751809243}
+12/27/2021 02:58:34 - INFO - codeparrot_training - Step 31560: {'lr': 0.00015078174856776678, 'samples': 16159232, 'steps': 31560, 'batch_loss/train': 0.7353176893666387}
+12/27/2021 02:58:45 - INFO - codeparrot_training - Step 31561: {'lr': 0.00015076728020133474, 'samples': 16159744, 'steps': 31561, 'batch_loss/train': 0.6346353432163596}
+12/27/2021 02:58:55 - INFO - codeparrot_training - Step 31562: {'lr': 0.00015075281222941446, 'samples': 16160256, 'steps': 31562, 'batch_loss/train': 0.8508788356557488}
+12/27/2021 02:59:08 - INFO - codeparrot_training - Step 31563: {'lr': 0.00015073834465206346, 'samples': 16160768, 'steps': 31563, 'batch_loss/train': 0.5597165746148676}
+12/27/2021 02:59:18 - INFO - codeparrot_training - Step 31564: {'lr': 0.00015072387746933944, 'samples': 16161280, 'steps': 31564, 'batch_loss/train': 0.6651992439292371}
+12/27/2021 02:59:29 - INFO - codeparrot_training - Step 31565: {'lr': 0.0001507094106812998, 'samples': 16161792, 'steps': 31565, 'batch_loss/train': 0.6714837965555489}
+12/27/2021 02:59:42 - INFO - codeparrot_training - Step 31566: {'lr': 0.00015069494428800195, 'samples': 16162304, 'steps': 31566, 'batch_loss/train': 0.7104943976737559}
+12/27/2021 02:59:52 - INFO - codeparrot_training - Step 31567: {'lr': 0.00015068047828950353, 'samples': 16162816, 'steps': 31567, 'batch_loss/train': 0.7190822437405586}
+12/27/2021 03:00:03 - INFO - codeparrot_training - Step 31568: {'lr': 0.0001506660126858621, 'samples': 16163328, 'steps': 31568, 'batch_loss/train': 0.7021235595457256}
+12/27/2021 03:00:15 - INFO - codeparrot_training - Step 31569: {'lr': 0.00015065154747713504, 'samples': 16163840, 'steps': 31569, 'batch_loss/train': 0.7148955315351486}
+12/27/2021 03:00:26 - INFO - codeparrot_training - Step 31570: {'lr': 0.0001506370826633799, 'samples': 16164352, 'steps': 31570, 'batch_loss/train': 0.745745268650353}
+12/27/2021 03:00:37 - INFO - codeparrot_training - Step 31571: {'lr': 0.00015062261824465428, 'samples': 16164864, 'steps': 31571, 'batch_loss/train': 0.7024156204424798}
+12/27/2021 03:00:49 - INFO - codeparrot_training - Step 31572: {'lr': 0.00015060815422101553, 'samples': 16165376, 'steps': 31572, 'batch_loss/train': 0.7353322450071573}
+12/27/2021 03:00:59 - INFO - codeparrot_training - Step 31573: {'lr': 0.00015059369059252132, 'samples': 16165888, 'steps': 31573, 'batch_loss/train': 0.5243236672831699}
+12/27/2021 03:01:10 - INFO - codeparrot_training - Step 31574: {'lr': 0.00015057922735922893, 'samples': 16166400, 'steps': 31574, 'batch_loss/train': 1.3861316861584783}
+12/27/2021 03:01:21 - INFO - codeparrot_training - Step 31575: {'lr': 0.0001505647645211961, 'samples': 16166912, 'steps': 31575, 'batch_loss/train': 1.0312389680184424}
+12/27/2021 03:01:33 - INFO - codeparrot_training - Step 31576: {'lr': 0.0001505503020784802, 'samples': 16167424, 'steps': 31576, 'batch_loss/train': 0.6958817914128304}
+12/27/2021 03:01:44 - INFO - codeparrot_training - Step 31577: {'lr': 0.00015053584003113865, 'samples': 16167936, 'steps': 31577, 'batch_loss/train': 0.7642549141310155}
+12/27/2021 03:01:54 - INFO - codeparrot_training - Step 31578: {'lr': 0.00015052137837922918, 'samples': 16168448, 'steps': 31578, 'batch_loss/train': 0.6340053707244806}
+12/27/2021 03:02:07 - INFO - codeparrot_training - Step 31579: {'lr': 0.00015050691712280905, 'samples': 16168960, 'steps': 31579, 'batch_loss/train': 0.7128059146925807}
+12/27/2021 03:02:17 - INFO - codeparrot_training - Step 31580: {'lr': 0.00015049245626193598, 'samples': 16169472, 'steps': 31580, 'batch_loss/train': 0.7530551175586879}
+12/27/2021 03:02:28 - INFO - codeparrot_training - Step 31581: {'lr': 0.00015047799579666715, 'samples': 16169984, 'steps': 31581, 'batch_loss/train': 0.7077461765147746}
+12/27/2021 03:02:40 - INFO - codeparrot_training - Step 31582: {'lr': 0.00015046353572706033, 'samples': 16170496, 'steps': 31582, 'batch_loss/train': 0.6558126052841544}
+12/27/2021 03:02:51 - INFO - codeparrot_training - Step 31583: {'lr': 0.00015044907605317296, 'samples': 16171008, 'steps': 31583, 'batch_loss/train': 0.7271980112418532}
+12/27/2021 03:03:02 - INFO - codeparrot_training - Step 31584: {'lr': 0.00015043461677506246, 'samples': 16171520, 'steps': 31584, 'batch_loss/train': 0.6928527434356511}
+12/27/2021 03:03:12 - INFO - codeparrot_training - Step 31585: {'lr': 0.00015042015789278623, 'samples': 16172032, 'steps': 31585, 'batch_loss/train': 0.5899099740781821}
+12/27/2021 03:03:25 - INFO - codeparrot_training - Step 31586: {'lr': 0.0001504056994064019, 'samples': 16172544, 'steps': 31586, 'batch_loss/train': 0.8173958896659315}
+12/27/2021 03:03:36 - INFO - codeparrot_training - Step 31587: {'lr': 0.00015039124131596693, 'samples': 16173056, 'steps': 31587, 'batch_loss/train': 0.6790745826438069}
+12/27/2021 03:03:46 - INFO - codeparrot_training - Step 31588: {'lr': 0.00015037678362153878, 'samples': 16173568, 'steps': 31588, 'batch_loss/train': 0.7820536214858294}
+12/27/2021 03:03:58 - INFO - codeparrot_training - Step 31589: {'lr': 0.0001503623263231748, 'samples': 16174080, 'steps': 31589, 'batch_loss/train': 0.7491732453927398}
+12/27/2021 03:04:09 - INFO - codeparrot_training - Step 31590: {'lr': 0.00015034786942093277, 'samples': 16174592, 'steps': 31590, 'batch_loss/train': 0.7252370032365434}
+12/27/2021 03:04:19 - INFO - codeparrot_training - Step 31591: {'lr': 0.00015033341291486994, 'samples': 16175104, 'steps': 31591, 'batch_loss/train': 0.707928170915693}
+12/27/2021 03:04:30 - INFO - codeparrot_training - Step 31592: {'lr': 0.00015031895680504373, 'samples': 16175616, 'steps': 31592, 'batch_loss/train': 0.7474225480109453}
+12/27/2021 03:04:42 - INFO - codeparrot_training - Step 31593: {'lr': 0.00015030450109151177, 'samples': 16176128, 'steps': 31593, 'batch_loss/train': 0.6776969088241458}
+12/27/2021 03:04:53 - INFO - codeparrot_training - Step 31594: {'lr': 0.0001502900457743315, 'samples': 16176640, 'steps': 31594, 'batch_loss/train': 0.7043181923218071}
+12/27/2021 03:05:03 - INFO - codeparrot_training - Step 31595: {'lr': 0.0001502755908535603, 'samples': 16177152, 'steps': 31595, 'batch_loss/train': 0.6038160275202245}
+12/27/2021 03:05:16 - INFO - codeparrot_training - Step 31596: {'lr': 0.0001502611363292557, 'samples': 16177664, 'steps': 31596, 'batch_loss/train': 0.7187776565551758}
+12/27/2021 03:05:27 - INFO - codeparrot_training - Step 31597: {'lr': 0.00015024668220147523, 'samples': 16178176, 'steps': 31597, 'batch_loss/train': 0.6339523384522181}
+12/27/2021 03:05:37 - INFO - codeparrot_training - Step 31598: {'lr': 0.00015023222847027623, 'samples': 16178688, 'steps': 31598, 'batch_loss/train': 0.7122092814533971}
+12/27/2021 03:05:50 - INFO - codeparrot_training - Step 31599: {'lr': 0.00015021777513571626, 'samples': 16179200, 'steps': 31599, 'batch_loss/train': 0.721508227288723}
+12/27/2021 03:06:00 - INFO - codeparrot_training - Step 31600: {'lr': 0.00015020332219785267, 'samples': 16179712, 'steps': 31600, 'batch_loss/train': 0.675104558467865}
+12/27/2021 03:06:11 - INFO - codeparrot_training - Step 31601: {'lr': 0.00015018886965674304, 'samples': 16180224, 'steps': 31601, 'batch_loss/train': 0.6837186724878848}
+12/27/2021 03:06:23 - INFO - codeparrot_training - Step 31602: {'lr': 0.0001501744175124448, 'samples': 16180736, 'steps': 31602, 'batch_loss/train': 0.7423969674855471}
+12/27/2021 03:06:34 - INFO - codeparrot_training - Step 31603: {'lr': 0.0001501599657650153, 'samples': 16181248, 'steps': 31603, 'batch_loss/train': 0.7026722128503025}
+12/27/2021 03:06:45 - INFO - codeparrot_training - Step 31604: {'lr': 0.00015014551441451212, 'samples': 16181760, 'steps': 31604, 'batch_loss/train': 0.5620977662038058}
+12/27/2021 03:06:55 - INFO - codeparrot_training - Step 31605: {'lr': 0.0001501310634609927, 'samples': 16182272, 'steps': 31605, 'batch_loss/train': 0.6969141322188079}
+12/27/2021 03:07:08 - INFO - codeparrot_training - Step 31606: {'lr': 0.0001501166129045145, 'samples': 16182784, 'steps': 31606, 'batch_loss/train': 0.7348775779828429}
+12/27/2021 03:07:18 - INFO - codeparrot_training - Step 31607: {'lr': 0.0001501021627451348, 'samples': 16183296, 'steps': 31607, 'batch_loss/train': 0.7926487075164914}
+12/27/2021 03:07:29 - INFO - codeparrot_training - Step 31608: {'lr': 0.00015008771298291124, 'samples': 16183808, 'steps': 31608, 'batch_loss/train': 0.7718122014775872}
+12/27/2021 03:07:41 - INFO - codeparrot_training - Step 31609: {'lr': 0.00015007326361790127, 'samples': 16184320, 'steps': 31609, 'batch_loss/train': 0.6521721258759499}
+12/27/2021 03:07:52 - INFO - codeparrot_training - Step 31610: {'lr': 0.00015005881465016228, 'samples': 16184832, 'steps': 31610, 'batch_loss/train': 0.6884867339394987}
+12/27/2021 03:08:02 - INFO - codeparrot_training - Step 31611: {'lr': 0.00015004436607975158, 'samples': 16185344, 'steps': 31611, 'batch_loss/train': 0.7342792619019747}
+12/27/2021 03:08:14 - INFO - codeparrot_training - Step 31612: {'lr': 0.00015002991790672682, 'samples': 16185856, 'steps': 31612, 'batch_loss/train': 0.5459339949884452}
+12/27/2021 03:08:25 - INFO - codeparrot_training - Step 31613: {'lr': 0.0001500154701311454, 'samples': 16186368, 'steps': 31613, 'batch_loss/train': 0.6966313547454774}
+12/27/2021 03:08:36 - INFO - codeparrot_training - Step 31614: {'lr': 0.0001500010227530646, 'samples': 16186880, 'steps': 31614, 'batch_loss/train': 0.7025516852736473}
+12/27/2021 03:08:49 - INFO - codeparrot_training - Step 31615: {'lr': 0.00014998657577254204, 'samples': 16187392, 'steps': 31615, 'batch_loss/train': 0.8505585929378867}
+12/27/2021 03:09:00 - INFO - codeparrot_training - Step 31616: {'lr': 0.00014997212918963515, 'samples': 16187904, 'steps': 31616, 'batch_loss/train': 0.7607985464856029}
+12/27/2021 03:09:11 - INFO - codeparrot_training - Step 31617: {'lr': 0.0001499576830044012, 'samples': 16188416, 'steps': 31617, 'batch_loss/train': 0.7168494660872966}
+12/27/2021 03:09:21 - INFO - codeparrot_training - Step 31618: {'lr': 0.00014994323721689772, 'samples': 16188928, 'steps': 31618, 'batch_loss/train': 0.8339604260399938}
+12/27/2021 03:09:33 - INFO - codeparrot_training - Step 31619: {'lr': 0.00014992879182718226, 'samples': 16189440, 'steps': 31619, 'batch_loss/train': 0.850530524738133}
+12/27/2021 03:09:44 - INFO - codeparrot_training - Step 31620: {'lr': 0.00014991434683531214, 'samples': 16189952, 'steps': 31620, 'batch_loss/train': 0.6366600766777992}
+12/27/2021 03:09:54 - INFO - codeparrot_training - Step 31621: {'lr': 0.00014989990224134476, 'samples': 16190464, 'steps': 31621, 'batch_loss/train': 0.670459725195542}
+12/27/2021 03:10:06 - INFO - codeparrot_training - Step 31622: {'lr': 0.00014988545804533746, 'samples': 16190976, 'steps': 31622, 'batch_loss/train': 0.7775247478857636}
+12/27/2021 03:10:17 - INFO - codeparrot_training - Step 31623: {'lr': 0.0001498710142473479, 'samples': 16191488, 'steps': 31623, 'batch_loss/train': 0.7579837804660201}
+12/27/2021 03:10:28 - INFO - codeparrot_training - Step 31624: {'lr': 0.00014985657084743334, 'samples': 16192000, 'steps': 31624, 'batch_loss/train': 0.7948171626776457}
+12/27/2021 03:10:42 - INFO - codeparrot_training - Step 31625: {'lr': 0.00014984212784565127, 'samples': 16192512, 'steps': 31625, 'batch_loss/train': 0.7122698193415999}
+12/27/2021 03:10:52 - INFO - codeparrot_training - Step 31626: {'lr': 0.00014982768524205903, 'samples': 16193024, 'steps': 31626, 'batch_loss/train': 0.8272983375936747}
+12/27/2021 03:11:03 - INFO - codeparrot_training - Step 31627: {'lr': 0.0001498132430367141, 'samples': 16193536, 'steps': 31627, 'batch_loss/train': 0.6876924876123667}
+12/27/2021 03:11:15 - INFO - codeparrot_training - Step 31628: {'lr': 0.00014979880122967392, 'samples': 16194048, 'steps': 31628, 'batch_loss/train': 0.8077275669202209}
+12/27/2021 03:11:26 - INFO - codeparrot_training - Step 31629: {'lr': 0.0001497843598209958, 'samples': 16194560, 'steps': 31629, 'batch_loss/train': 0.7503146370872855}
+12/27/2021 03:11:36 - INFO - codeparrot_training - Step 31630: {'lr': 0.00014976991881073733, 'samples': 16195072, 'steps': 31630, 'batch_loss/train': 0.8021339299157262}
+12/27/2021 03:11:47 - INFO - codeparrot_training - Step 31631: {'lr': 0.00014975547819895575, 'samples': 16195584, 'steps': 31631, 'batch_loss/train': 0.7491267486475408}
+12/27/2021 03:12:01 - INFO - codeparrot_training - Step 31632: {'lr': 0.0001497410379857086, 'samples': 16196096, 'steps': 31632, 'batch_loss/train': 0.7394359367899597}
+12/27/2021 03:12:11 - INFO - codeparrot_training - Step 31633: {'lr': 0.00014972659817105312, 'samples': 16196608, 'steps': 31633, 'batch_loss/train': 0.7092770081944764}
+12/27/2021 03:12:22 - INFO - codeparrot_training - Step 31634: {'lr': 0.0001497121587550469, 'samples': 16197120, 'steps': 31634, 'batch_loss/train': 0.6842481223866343}
+12/27/2021 03:12:34 - INFO - codeparrot_training - Step 31635: {'lr': 0.00014969771973774725, 'samples': 16197632, 'steps': 31635, 'batch_loss/train': 0.787144185975194}
+12/27/2021 03:12:45 - INFO - codeparrot_training - Step 31636: {'lr': 0.00014968328111921166, 'samples': 16198144, 'steps': 31636, 'batch_loss/train': 0.7320106661645696}
+12/27/2021 03:12:55 - INFO - codeparrot_training - Step 31637: {'lr': 0.00014966884289949734, 'samples': 16198656, 'steps': 31637, 'batch_loss/train': 0.7585328221321106}
+12/27/2021 03:13:07 - INFO - codeparrot_training - Step 31638: {'lr': 0.0001496544050786619, 'samples': 16199168, 'steps': 31638, 'batch_loss/train': 0.7887696549296379}
+12/27/2021 03:13:18 - INFO - codeparrot_training - Step 31639: {'lr': 0.00014963996765676268, 'samples': 16199680, 'steps': 31639, 'batch_loss/train': 0.7991688712500036}
+12/27/2021 03:13:29 - INFO - codeparrot_training - Step 31640: {'lr': 0.00014962553063385694, 'samples': 16200192, 'steps': 31640, 'batch_loss/train': 0.8053356576710939}
+12/27/2021 03:13:39 - INFO - codeparrot_training - Step 31641: {'lr': 0.00014961109401000224, 'samples': 16200704, 'steps': 31641, 'batch_loss/train': 0.8155677216127515}
+12/27/2021 03:13:53 - INFO - codeparrot_training - Step 31642: {'lr': 0.000149596657785256, 'samples': 16201216, 'steps': 31642, 'batch_loss/train': 0.709837771137245}
+12/27/2021 03:14:04 - INFO - codeparrot_training - Step 31643: {'lr': 0.00014958222195967546, 'samples': 16201728, 'steps': 31643, 'batch_loss/train': 0.7332812553504482}
+12/27/2021 03:14:14 - INFO - codeparrot_training - Step 31644: {'lr': 0.0001495677865333181, 'samples': 16202240, 'steps': 31644, 'batch_loss/train': 0.7402179503696971}
+12/27/2021 03:14:27 - INFO - codeparrot_training - Step 31645: {'lr': 0.00014955335150624132, 'samples': 16202752, 'steps': 31645, 'batch_loss/train': 0.8030292051844299}
+12/27/2021 03:14:37 - INFO - codeparrot_training - Step 31646: {'lr': 0.00014953891687850251, 'samples': 16203264, 'steps': 31646, 'batch_loss/train': 0.7822386980988085}
+12/27/2021 03:14:48 - INFO - codeparrot_training - Step 31647: {'lr': 0.00014952448265015902, 'samples': 16203776, 'steps': 31647, 'batch_loss/train': 0.6835565872024745}
+12/27/2021 03:15:00 - INFO - codeparrot_training - Step 31648: {'lr': 0.00014951004882126818, 'samples': 16204288, 'steps': 31648, 'batch_loss/train': 0.783615087158978}
+12/27/2021 03:15:11 - INFO - codeparrot_training - Step 31649: {'lr': 0.00014949561539188755, 'samples': 16204800, 'steps': 31649, 'batch_loss/train': 0.8961152657866478}
+12/27/2021 03:15:21 - INFO - codeparrot_training - Step 31650: {'lr': 0.0001494811823620743, 'samples': 16205312, 'steps': 31650, 'batch_loss/train': 0.7123422183794901}
+12/27/2021 03:15:32 - INFO - codeparrot_training - Step 31651: {'lr': 0.00014946674973188593, 'samples': 16205824, 'steps': 31651, 'batch_loss/train': 0.7148691010661423}
+12/27/2021 03:15:46 - INFO - codeparrot_training - Step 31652: {'lr': 0.00014945231750137987, 'samples': 16206336, 'steps': 31652, 'batch_loss/train': 0.7745263804681599}
+12/27/2021 03:15:56 - INFO - codeparrot_training - Step 31653: {'lr': 0.00014943788567061339, 'samples': 16206848, 'steps': 31653, 'batch_loss/train': 0.7594144493341446}
+12/27/2021 03:16:07 - INFO - codeparrot_training - Step 31654: {'lr': 0.00014942345423964395, 'samples': 16207360, 'steps': 31654, 'batch_loss/train': 0.7718704855069518}
+12/27/2021 03:16:19 - INFO - codeparrot_training - Step 31655: {'lr': 0.00014940902320852877, 'samples': 16207872, 'steps': 31655, 'batch_loss/train': 0.8346535703167319}
+12/27/2021 03:16:30 - INFO - codeparrot_training - Step 31656: {'lr': 0.00014939459257732547, 'samples': 16208384, 'steps': 31656, 'batch_loss/train': 0.8215374713763595}
+12/27/2021 03:16:40 - INFO - codeparrot_training - Step 31657: {'lr': 0.0001493801623460912, 'samples': 16208896, 'steps': 31657, 'batch_loss/train': 0.7473504897207022}
+12/27/2021 03:16:53 - INFO - codeparrot_training - Step 31658: {'lr': 0.0001493657325148835, 'samples': 16209408, 'steps': 31658, 'batch_loss/train': 0.7797026708722115}
+12/27/2021 03:17:03 - INFO - codeparrot_training - Step 31659: {'lr': 0.0001493513030837595, 'samples': 16209920, 'steps': 31659, 'batch_loss/train': 0.7987078139558434}
+12/27/2021 03:17:14 - INFO - codeparrot_training - Step 31660: {'lr': 0.0001493368740527768, 'samples': 16210432, 'steps': 31660, 'batch_loss/train': 0.7118460603524}
+12/27/2021 03:17:28 - INFO - codeparrot_training - Step 31661: {'lr': 0.00014932244542199268, 'samples': 16210944, 'steps': 31661, 'batch_loss/train': 0.7848309138789773}
+12/27/2021 03:17:39 - INFO - codeparrot_training - Step 31662: {'lr': 0.00014930801719146452, 'samples': 16211456, 'steps': 31662, 'batch_loss/train': 0.7449708124622703}
+12/27/2021 03:17:49 - INFO - codeparrot_training - Step 31663: {'lr': 0.0001492935893612496, 'samples': 16211968, 'steps': 31663, 'batch_loss/train': 0.6416525086387992}
+12/27/2021 03:18:00 - INFO - codeparrot_training - Step 31664: {'lr': 0.0001492791619314054, 'samples': 16212480, 'steps': 31664, 'batch_loss/train': 0.8016207222826779}
+12/27/2021 03:18:12 - INFO - codeparrot_training - Step 31665: {'lr': 0.00014926473490198928, 'samples': 16212992, 'steps': 31665, 'batch_loss/train': 0.7805045119021088}
+12/27/2021 03:18:23 - INFO - codeparrot_training - Step 31666: {'lr': 0.0001492503082730584, 'samples': 16213504, 'steps': 31666, 'batch_loss/train': 0.5185206040041521}
+12/27/2021 03:18:33 - INFO - codeparrot_training - Step 31667: {'lr': 0.0001492358820446703, 'samples': 16214016, 'steps': 31667, 'batch_loss/train': 0.8296190658584237}
+12/27/2021 03:18:46 - INFO - codeparrot_training - Step 31668: {'lr': 0.00014922145621688233, 'samples': 16214528, 'steps': 31668, 'batch_loss/train': 0.7656819587573409}
+12/27/2021 03:18:56 - INFO - codeparrot_training - Step 31669: {'lr': 0.0001492070307897518, 'samples': 16215040, 'steps': 31669, 'batch_loss/train': 0.752427805098705}
+12/27/2021 03:19:07 - INFO - codeparrot_training - Step 31670: {'lr': 0.00014919260576333593, 'samples': 16215552, 'steps': 31670, 'batch_loss/train': 0.9490494597703218}
+12/27/2021 03:19:21 - INFO - codeparrot_training - Step 31671: {'lr': 0.00014917818113769233, 'samples': 16216064, 'steps': 31671, 'batch_loss/train': 0.6657813182100654}
+12/27/2021 03:19:31 - INFO - codeparrot_training - Step 31672: {'lr': 0.0001491637569128782, 'samples': 16216576, 'steps': 31672, 'batch_loss/train': 0.7524215709418058}
+12/27/2021 03:19:42 - INFO - codeparrot_training - Step 31673: {'lr': 0.0001491493330889509, 'samples': 16217088, 'steps': 31673, 'batch_loss/train': 0.7435899777337909}
+12/27/2021 03:19:52 - INFO - codeparrot_training - Step 31674: {'lr': 0.00014913490966596767, 'samples': 16217600, 'steps': 31674, 'batch_loss/train': 0.7103992803022265}
+12/27/2021 03:20:05 - INFO - codeparrot_training - Step 31675: {'lr': 0.00014912048664398608, 'samples': 16218112, 'steps': 31675, 'batch_loss/train': 0.6320135196438059}
+12/27/2021 03:20:15 - INFO - codeparrot_training - Step 31676: {'lr': 0.0001491060640230633, 'samples': 16218624, 'steps': 31676, 'batch_loss/train': 0.7509701596572995}
+12/27/2021 03:20:26 - INFO - codeparrot_training - Step 31677: {'lr': 0.00014909164180325663, 'samples': 16219136, 'steps': 31677, 'batch_loss/train': 0.7956889634951949}
+12/27/2021 03:20:40 - INFO - codeparrot_training - Step 31678: {'lr': 0.00014907721998462365, 'samples': 16219648, 'steps': 31678, 'batch_loss/train': 0.8251870041713119}
+12/27/2021 03:20:51 - INFO - codeparrot_training - Step 31679: {'lr': 0.00014906279856722143, 'samples': 16220160, 'steps': 31679, 'batch_loss/train': 0.5458209747448564}
+12/27/2021 03:21:01 - INFO - codeparrot_training - Step 31680: {'lr': 0.00014904837755110747, 'samples': 16220672, 'steps': 31680, 'batch_loss/train': 0.8088277231436223}
+12/27/2021 03:21:13 - INFO - codeparrot_training - Step 31681: {'lr': 0.00014903395693633895, 'samples': 16221184, 'steps': 31681, 'batch_loss/train': 0.7035886598750949}
+12/27/2021 03:21:24 - INFO - codeparrot_training - Step 31682: {'lr': 0.0001490195367229734, 'samples': 16221696, 'steps': 31682, 'batch_loss/train': 0.8019968699663877}
+12/27/2021 03:21:35 - INFO - codeparrot_training - Step 31683: {'lr': 0.000149005116911068, 'samples': 16222208, 'steps': 31683, 'batch_loss/train': 0.9524455554783344}
+12/27/2021 03:21:47 - INFO - codeparrot_training - Step 31684: {'lr': 0.00014899069750068015, 'samples': 16222720, 'steps': 31684, 'batch_loss/train': 0.9131941958330572}
+12/27/2021 03:21:57 - INFO - codeparrot_training - Step 31685: {'lr': 0.00014897627849186706, 'samples': 16223232, 'steps': 31685, 'batch_loss/train': 0.7217303784564137}
+12/27/2021 03:22:08 - INFO - codeparrot_training - Step 31686: {'lr': 0.00014896185988468619, 'samples': 16223744, 'steps': 31686, 'batch_loss/train': 0.8439891124144197}
+12/27/2021 03:22:19 - INFO - codeparrot_training - Step 31687: {'lr': 0.00014894744167919487, 'samples': 16224256, 'steps': 31687, 'batch_loss/train': 0.6808542096987367}
+12/27/2021 03:22:32 - INFO - codeparrot_training - Step 31688: {'lr': 0.00014893302387545025, 'samples': 16224768, 'steps': 31688, 'batch_loss/train': 0.7292704321444035}
+12/27/2021 03:22:43 - INFO - codeparrot_training - Step 31689: {'lr': 0.0001489186064735098, 'samples': 16225280, 'steps': 31689, 'batch_loss/train': 0.668515489436686}
+12/27/2021 03:22:54 - INFO - codeparrot_training - Step 31690: {'lr': 0.0001489041894734309, 'samples': 16225792, 'steps': 31690, 'batch_loss/train': 0.8133476856164634}
+12/27/2021 03:23:06 - INFO - codeparrot_training - Step 31691: {'lr': 0.00014888977287527073, 'samples': 16226304, 'steps': 31691, 'batch_loss/train': 0.7447798843495548}
+12/27/2021 03:23:16 - INFO - codeparrot_training - Step 31692: {'lr': 0.00014887535667908658, 'samples': 16226816, 'steps': 31692, 'batch_loss/train': 0.6655381498858333}
+12/27/2021 03:23:27 - INFO - codeparrot_training - Step 31693: {'lr': 0.00014886094088493583, 'samples': 16227328, 'steps': 31693, 'batch_loss/train': 1.056951131671667}
+12/27/2021 03:23:39 - INFO - codeparrot_training - Step 31694: {'lr': 0.00014884652549287592, 'samples': 16227840, 'steps': 31694, 'batch_loss/train': 0.7120602265931666}
+12/27/2021 03:23:50 - INFO - codeparrot_training - Step 31695: {'lr': 0.0001488321105029639, 'samples': 16228352, 'steps': 31695, 'batch_loss/train': 0.8751148879528046}
+12/27/2021 03:24:00 - INFO - codeparrot_training - Step 31696: {'lr': 0.0001488176959152572, 'samples': 16228864, 'steps': 31696, 'batch_loss/train': 0.6865968115162104}
+12/27/2021 03:24:11 - INFO - codeparrot_training - Step 31697: {'lr': 0.00014880328172981323, 'samples': 16229376, 'steps': 31697, 'batch_loss/train': 0.7452032589353621}
+12/27/2021 03:24:23 - INFO - codeparrot_training - Step 31698: {'lr': 0.00014878886794668917, 'samples': 16229888, 'steps': 31698, 'batch_loss/train': 0.7323186611756682}
+12/27/2021 03:24:34 - INFO - codeparrot_training - Step 31699: {'lr': 0.00014877445456594235, 'samples': 16230400, 'steps': 31699, 'batch_loss/train': 0.8630652893334627}
+12/27/2021 03:24:44 - INFO - codeparrot_training - Step 31700: {'lr': 0.00014876004158763002, 'samples': 16230912, 'steps': 31700, 'batch_loss/train': 0.828066770453006}
+12/27/2021 03:24:58 - INFO - codeparrot_training - Step 31701: {'lr': 0.00014874562901180967, 'samples': 16231424, 'steps': 31701, 'batch_loss/train': 0.7571679018437862}
+12/27/2021 03:25:09 - INFO - codeparrot_training - Step 31702: {'lr': 0.00014873121683853835, 'samples': 16231936, 'steps': 31702, 'batch_loss/train': 0.8093816619366407}
+12/27/2021 03:25:20 - INFO - codeparrot_training - Step 31703: {'lr': 0.00014871680506787344, 'samples': 16232448, 'steps': 31703, 'batch_loss/train': 0.7825202029198408}
+12/27/2021 03:25:32 - INFO - codeparrot_training - Step 31704: {'lr': 0.00014870239369987239, 'samples': 16232960, 'steps': 31704, 'batch_loss/train': 0.7030838737264276}
+12/27/2021 03:25:42 - INFO - codeparrot_training - Step 31705: {'lr': 0.00014868798273459232, 'samples': 16233472, 'steps': 31705, 'batch_loss/train': 0.5823993457888719}
+12/27/2021 03:25:53 - INFO - codeparrot_training - Step 31706: {'lr': 0.00014867357217209062, 'samples': 16233984, 'steps': 31706, 'batch_loss/train': 0.7130589609732851}
+12/27/2021 03:26:04 - INFO - codeparrot_training - Step 31707: {'lr': 0.00014865916201242443, 'samples': 16234496, 'steps': 31707, 'batch_loss/train': 0.6426851185970008}
+12/27/2021 03:26:16 - INFO - codeparrot_training - Step 31708: {'lr': 0.0001486447522556512, 'samples': 16235008, 'steps': 31708, 'batch_loss/train': 0.7915622061118484}
+12/27/2021 03:26:26 - INFO - codeparrot_training - Step 31709: {'lr': 0.00014863034290182826, 'samples': 16235520, 'steps': 31709, 'batch_loss/train': 0.7649353607557714}
+12/27/2021 03:26:37 - INFO - codeparrot_training - Step 31710: {'lr': 0.00014861593395101274, 'samples': 16236032, 'steps': 31710, 'batch_loss/train': 0.8822889509610832}
+12/27/2021 03:26:51 - INFO - codeparrot_training - Step 31711: {'lr': 0.0001486015254032619, 'samples': 16236544, 'steps': 31711, 'batch_loss/train': 0.8615020159631968}
+12/27/2021 03:27:01 - INFO - codeparrot_training - Step 31712: {'lr': 0.00014858711725863316, 'samples': 16237056, 'steps': 31712, 'batch_loss/train': 0.5967396515188739}
+12/27/2021 03:27:12 - INFO - codeparrot_training - Step 31713: {'lr': 0.00014857270951718383, 'samples': 16237568, 'steps': 31713, 'batch_loss/train': 0.7788412794470787}
+12/27/2021 03:27:24 - INFO - codeparrot_training - Step 31714: {'lr': 0.000148558302178971, 'samples': 16238080, 'steps': 31714, 'batch_loss/train': 0.8279923759400845}
+12/27/2021 03:27:35 - INFO - codeparrot_training - Step 31715: {'lr': 0.00014854389524405207, 'samples': 16238592, 'steps': 31715, 'batch_loss/train': 0.7971275905147195}
+12/27/2021 03:27:45 - INFO - codeparrot_training - Step 31716: {'lr': 0.0001485294887124844, 'samples': 16239104, 'steps': 31716, 'batch_loss/train': 0.6763803726062179}
+12/27/2021 03:27:59 - INFO - codeparrot_training - Step 31717: {'lr': 0.0001485150825843251, 'samples': 16239616, 'steps': 31717, 'batch_loss/train': 0.6625431397696957}
+12/27/2021 03:28:10 - INFO - codeparrot_training - Step 31718: {'lr': 0.00014850067685963142, 'samples': 16240128, 'steps': 31718, 'batch_loss/train': 0.7458411380648613}
+12/27/2021 03:28:20 - INFO - codeparrot_training - Step 31719: {'lr': 0.00014848627153846088, 'samples': 16240640, 'steps': 31719, 'batch_loss/train': 0.6833106358535588}
+12/27/2021 03:28:31 - INFO - codeparrot_training - Step 31720: {'lr': 0.0001484718666208706, 'samples': 16241152, 'steps': 31720, 'batch_loss/train': 0.7540038451552391}
+12/27/2021 03:28:43 - INFO - codeparrot_training - Step 31721: {'lr': 0.00014845746210691773, 'samples': 16241664, 'steps': 31721, 'batch_loss/train': 0.80637177079916}
+12/27/2021 03:28:54 - INFO - codeparrot_training - Step 31722: {'lr': 0.00014844305799665967, 'samples': 16242176, 'steps': 31722, 'batch_loss/train': 0.8535362305119634}
+12/27/2021 03:29:04 - INFO - codeparrot_training - Step 31723: {'lr': 0.00014842865429015372, 'samples': 16242688, 'steps': 31723, 'batch_loss/train': 0.8222441552206874}
+12/27/2021 03:29:16 - INFO - codeparrot_training - Step 31724: {'lr': 0.00014841425098745706, 'samples': 16243200, 'steps': 31724, 'batch_loss/train': 0.6701649494934827}
+12/27/2021 03:29:27 - INFO - codeparrot_training - Step 31725: {'lr': 0.00014839984808862693, 'samples': 16243712, 'steps': 31725, 'batch_loss/train': 0.7294413540512323}
+12/27/2021 03:29:37 - INFO - codeparrot_training - Step 31726: {'lr': 0.00014838544559372076, 'samples': 16244224, 'steps': 31726, 'batch_loss/train': 0.777249657548964}
+12/27/2021 03:29:51 - INFO - codeparrot_training - Step 31727: {'lr': 0.0001483710435027956, 'samples': 16244736, 'steps': 31727, 'batch_loss/train': 0.7059426745399833}
+12/27/2021 03:30:02 - INFO - codeparrot_training - Step 31728: {'lr': 0.00014835664181590886, 'samples': 16245248, 'steps': 31728, 'batch_loss/train': 0.7440544553101063}
+12/27/2021 03:30:13 - INFO - codeparrot_training - Step 31729: {'lr': 0.00014834224053311763, 'samples': 16245760, 'steps': 31729, 'batch_loss/train': 0.8080921405926347}
+12/27/2021 03:30:23 - INFO - codeparrot_training - Step 31730: {'lr': 0.00014832783965447937, 'samples': 16246272, 'steps': 31730, 'batch_loss/train': 0.7977205272763968}
+12/27/2021 03:30:36 - INFO - codeparrot_training - Step 31731: {'lr': 0.0001483134391800512, 'samples': 16246784, 'steps': 31731, 'batch_loss/train': 0.9062856948003173}
+12/27/2021 03:30:46 - INFO - codeparrot_training - Step 31732: {'lr': 0.00014829903910989039, 'samples': 16247296, 'steps': 31732, 'batch_loss/train': 1.1271203542128205}
+12/27/2021 03:30:57 - INFO - codeparrot_training - Step 31733: {'lr': 0.00014828463944405418, 'samples': 16247808, 'steps': 31733, 'batch_loss/train': 0.7566627925261855}
+12/27/2021 03:31:09 - INFO - codeparrot_training - Step 31734: {'lr': 0.00014827024018259982, 'samples': 16248320, 'steps': 31734, 'batch_loss/train': 1.00788001017645}
+12/27/2021 03:31:20 - INFO - codeparrot_training - Step 31735: {'lr': 0.00014825584132558466, 'samples': 16248832, 'steps': 31735, 'batch_loss/train': 0.6892585186287761}
+12/27/2021 03:31:30 - INFO - codeparrot_training - Step 31736: {'lr': 0.00014824144287306585, 'samples': 16249344, 'steps': 31736, 'batch_loss/train': 0.6940071559511125}
+12/27/2021 03:31:42 - INFO - codeparrot_training - Step 31737: {'lr': 0.00014822704482510057, 'samples': 16249856, 'steps': 31737, 'batch_loss/train': 0.8178597348742187}
+12/27/2021 03:31:53 - INFO - codeparrot_training - Step 31738: {'lr': 0.00014821264718174615, 'samples': 16250368, 'steps': 31738, 'batch_loss/train': 0.742019722238183}
+12/27/2021 03:32:03 - INFO - codeparrot_training - Step 31739: {'lr': 0.00014819824994305987, 'samples': 16250880, 'steps': 31739, 'batch_loss/train': 0.7447379338555038}
+12/27/2021 03:32:14 - INFO - codeparrot_training - Step 31740: {'lr': 0.0001481838531090988, 'samples': 16251392, 'steps': 31740, 'batch_loss/train': 0.7930385824292898}
+12/27/2021 03:32:28 - INFO - codeparrot_training - Step 31741: {'lr': 0.00014816945667992033, 'samples': 16251904, 'steps': 31741, 'batch_loss/train': 0.7752768516074866}
+12/27/2021 03:32:39 - INFO - codeparrot_training - Step 31742: {'lr': 0.0001481550606555817, 'samples': 16252416, 'steps': 31742, 'batch_loss/train': 0.6725230333395302}
+12/27/2021 03:32:49 - INFO - codeparrot_training - Step 31743: {'lr': 0.00014814066503614006, 'samples': 16252928, 'steps': 31743, 'batch_loss/train': 0.7175064971670508}
+12/27/2021 03:33:01 - INFO - codeparrot_training - Step 31744: {'lr': 0.00014812626982165262, 'samples': 16253440, 'steps': 31744, 'batch_loss/train': 0.7106685219332576}
+12/27/2021 03:33:12 - INFO - codeparrot_training - Step 31745: {'lr': 0.00014811187501217676, 'samples': 16253952, 'steps': 31745, 'batch_loss/train': 0.8797373194247484}
+12/27/2021 03:33:22 - INFO - codeparrot_training - Step 31746: {'lr': 0.00014809748060776962, 'samples': 16254464, 'steps': 31746, 'batch_loss/train': 0.78371995780617}
+12/27/2021 03:33:36 - INFO - codeparrot_training - Step 31747: {'lr': 0.0001480830866084884, 'samples': 16254976, 'steps': 31747, 'batch_loss/train': 0.836367683019489}
+12/27/2021 03:33:47 - INFO - codeparrot_training - Step 31748: {'lr': 0.00014806869301439024, 'samples': 16255488, 'steps': 31748, 'batch_loss/train': 0.7841380201280117}
+12/27/2021 03:33:57 - INFO - codeparrot_training - Step 31749: {'lr': 0.0001480542998255326, 'samples': 16256000, 'steps': 31749, 'batch_loss/train': 0.7750903917476535}
+12/27/2021 03:34:10 - INFO - codeparrot_training - Step 31750: {'lr': 0.00014803990704197252, 'samples': 16256512, 'steps': 31750, 'batch_loss/train': 0.7492283419705927}
+12/27/2021 03:34:20 - INFO - codeparrot_training - Step 31751: {'lr': 0.0001480255146637672, 'samples': 16257024, 'steps': 31751, 'batch_loss/train': 0.6940749790519476}
+12/27/2021 03:34:31 - INFO - codeparrot_training - Step 31752: {'lr': 0.00014801112269097406, 'samples': 16257536, 'steps': 31752, 'batch_loss/train': 0.7272526025772095}
+12/27/2021 03:34:42 - INFO - codeparrot_training - Step 31753: {'lr': 0.0001479967311236501, 'samples': 16258048, 'steps': 31753, 'batch_loss/train': 0.5883333316887729}
+12/27/2021 03:34:54 - INFO - codeparrot_training - Step 31754: {'lr': 0.00014798233996185273, 'samples': 16258560, 'steps': 31754, 'batch_loss/train': 0.7717536836862564}
+12/27/2021 03:35:05 - INFO - codeparrot_training - Step 31755: {'lr': 0.00014796794920563888, 'samples': 16259072, 'steps': 31755, 'batch_loss/train': 0.6680816453881562}
+12/27/2021 03:35:15 - INFO - codeparrot_training - Step 31756: {'lr': 0.0001479535588550661, 'samples': 16259584, 'steps': 31756, 'batch_loss/train': 0.7600958133116364}
+12/27/2021 03:35:29 - INFO - codeparrot_training - Step 31757: {'lr': 0.00014793916891019137, 'samples': 16260096, 'steps': 31757, 'batch_loss/train': 0.6905246968381107}
+12/27/2021 03:35:40 - INFO - codeparrot_training - Step 31758: {'lr': 0.000147924779371072, 'samples': 16260608, 'steps': 31758, 'batch_loss/train': 0.6729814801365137}
+12/27/2021 03:35:50 - INFO - codeparrot_training - Step 31759: {'lr': 0.0001479103902377651, 'samples': 16261120, 'steps': 31759, 'batch_loss/train': 0.7228317447006702}
+12/27/2021 03:36:03 - INFO - codeparrot_training - Step 31760: {'lr': 0.00014789600151032795, 'samples': 16261632, 'steps': 31760, 'batch_loss/train': 0.6921065129572526}
+12/27/2021 03:36:13 - INFO - codeparrot_training - Step 31761: {'lr': 0.00014788161318881783, 'samples': 16262144, 'steps': 31761, 'batch_loss/train': 0.7940711071714759}
+12/27/2021 03:36:24 - INFO - codeparrot_training - Step 31762: {'lr': 0.0001478672252732917, 'samples': 16262656, 'steps': 31762, 'batch_loss/train': 0.7277129460126162}
+12/27/2021 03:36:34 - INFO - codeparrot_training - Step 31763: {'lr': 0.00014785283776380702, 'samples': 16263168, 'steps': 31763, 'batch_loss/train': 0.9660350037738681}
+12/27/2021 03:36:47 - INFO - codeparrot_training - Step 31764: {'lr': 0.00014783845066042094, 'samples': 16263680, 'steps': 31764, 'batch_loss/train': 0.7470192485488951}
+12/27/2021 03:36:58 - INFO - codeparrot_training - Step 31765: {'lr': 0.00014782406396319058, 'samples': 16264192, 'steps': 31765, 'batch_loss/train': 0.8828006908297539}
+12/27/2021 03:37:08 - INFO - codeparrot_training - Step 31766: {'lr': 0.0001478096776721731, 'samples': 16264704, 'steps': 31766, 'batch_loss/train': 0.6793643324635923}
+12/27/2021 03:37:20 - INFO - codeparrot_training - Step 31767: {'lr': 0.00014779529178742578, 'samples': 16265216, 'steps': 31767, 'batch_loss/train': 0.8120659259147942}
+12/27/2021 03:37:31 - INFO - codeparrot_training - Step 31768: {'lr': 0.00014778090630900584, 'samples': 16265728, 'steps': 31768, 'batch_loss/train': 0.6179751014860813}
+12/27/2021 03:37:42 - INFO - codeparrot_training - Step 31769: {'lr': 0.00014776652123697038, 'samples': 16266240, 'steps': 31769, 'batch_loss/train': 0.8644246142357588}
+12/27/2021 03:37:54 - INFO - codeparrot_training - Step 31770: {'lr': 0.00014775213657137657, 'samples': 16266752, 'steps': 31770, 'batch_loss/train': 0.8037289590574801}
+12/27/2021 03:38:04 - INFO - codeparrot_training - Step 31771: {'lr': 0.00014773775231228175, 'samples': 16267264, 'steps': 31771, 'batch_loss/train': 0.7276228396221995}
+12/27/2021 03:38:15 - INFO - codeparrot_training - Step 31772: {'lr': 0.00014772336845974304, 'samples': 16267776, 'steps': 31772, 'batch_loss/train': 0.8344570277258754}
+12/27/2021 03:38:26 - INFO - codeparrot_training - Step 31773: {'lr': 0.00014770898501381753, 'samples': 16268288, 'steps': 31773, 'batch_loss/train': 0.7389940937282518}
+12/27/2021 03:38:38 - INFO - codeparrot_training - Step 31774: {'lr': 0.00014769460197456243, 'samples': 16268800, 'steps': 31774, 'batch_loss/train': 0.7734876908361912}
+12/27/2021 03:38:48 - INFO - codeparrot_training - Step 31775: {'lr': 0.00014768021934203504, 'samples': 16269312, 'steps': 31775, 'batch_loss/train': 0.7662241221405566}
+12/27/2021 03:38:59 - INFO - codeparrot_training - Step 31776: {'lr': 0.00014766583711629244, 'samples': 16269824, 'steps': 31776, 'batch_loss/train': 0.7375223878771067}
+12/27/2021 03:39:12 - INFO - codeparrot_training - Step 31777: {'lr': 0.00014765145529739177, 'samples': 16270336, 'steps': 31777, 'batch_loss/train': 0.6999512831680477}
+12/27/2021 03:39:22 - INFO - codeparrot_training - Step 31778: {'lr': 0.00014763707388539034, 'samples': 16270848, 'steps': 31778, 'batch_loss/train': 0.7523617250844836}
+12/27/2021 03:39:33 - INFO - codeparrot_training - Step 31779: {'lr': 0.00014762269288034525, 'samples': 16271360, 'steps': 31779, 'batch_loss/train': 0.8029182502068579}
+12/27/2021 03:39:45 - INFO - codeparrot_training - Step 31780: {'lr': 0.00014760831228231372, 'samples': 16271872, 'steps': 31780, 'batch_loss/train': 0.8113296162337065}
+12/27/2021 03:39:56 - INFO - codeparrot_training - Step 31781: {'lr': 0.00014759393209135276, 'samples': 16272384, 'steps': 31781, 'batch_loss/train': 0.7803838532418013}
+12/27/2021 03:40:06 - INFO - codeparrot_training - Step 31782: {'lr': 0.0001475795523075198, 'samples': 16272896, 'steps': 31782, 'batch_loss/train': 0.6792642939835787}
+12/27/2021 03:40:18 - INFO - codeparrot_training - Step 31783: {'lr': 0.00014756517293087177, 'samples': 16273408, 'steps': 31783, 'batch_loss/train': 0.8317977599799633}
+12/27/2021 03:40:29 - INFO - codeparrot_training - Step 31784: {'lr': 0.00014755079396146597, 'samples': 16273920, 'steps': 31784, 'batch_loss/train': 0.8894432339584455}
+12/27/2021 03:40:40 - INFO - codeparrot_training - Step 31785: {'lr': 0.00014753641539935947, 'samples': 16274432, 'steps': 31785, 'batch_loss/train': 0.7732839724048972}
+12/27/2021 03:40:50 - INFO - codeparrot_training - Step 31786: {'lr': 0.00014752203724460955, 'samples': 16274944, 'steps': 31786, 'batch_loss/train': 0.7276667198166251}
+12/27/2021 03:41:03 - INFO - codeparrot_training - Step 31787: {'lr': 0.00014750765949727334, 'samples': 16275456, 'steps': 31787, 'batch_loss/train': 0.5757452072575688}
+12/27/2021 03:41:14 - INFO - codeparrot_training - Step 31788: {'lr': 0.00014749328215740788, 'samples': 16275968, 'steps': 31788, 'batch_loss/train': 0.7184634902514517}
+12/27/2021 03:41:24 - INFO - codeparrot_training - Step 31789: {'lr': 0.00014747890522507048, 'samples': 16276480, 'steps': 31789, 'batch_loss/train': 0.7106884493259713}
+12/27/2021 03:41:36 - INFO - codeparrot_training - Step 31790: {'lr': 0.0001474645287003183, 'samples': 16276992, 'steps': 31790, 'batch_loss/train': 0.711998981423676}
+12/27/2021 03:41:47 - INFO - codeparrot_training - Step 31791: {'lr': 0.00014745015258320842, 'samples': 16277504, 'steps': 31791, 'batch_loss/train': 0.7504907064139843}
+12/27/2021 03:41:58 - INFO - codeparrot_training - Step 31792: {'lr': 0.00014743577687379794, 'samples': 16278016, 'steps': 31792, 'batch_loss/train': 0.7860930059105158}
+12/27/2021 03:42:10 - INFO - codeparrot_training - Step 31793: {'lr': 0.00014742140157214412, 'samples': 16278528, 'steps': 31793, 'batch_loss/train': 0.6986489426344633}
+12/27/2021 03:42:21 - INFO - codeparrot_training - Step 31794: {'lr': 0.00014740702667830413, 'samples': 16279040, 'steps': 31794, 'batch_loss/train': 0.823252015048638}
+12/27/2021 03:42:32 - INFO - codeparrot_training - Step 31795: {'lr': 0.000147392652192335, 'samples': 16279552, 'steps': 31795, 'batch_loss/train': 1.4886555215343833}
+12/27/2021 03:42:42 - INFO - codeparrot_training - Step 31796: {'lr': 0.0001473782781142939, 'samples': 16280064, 'steps': 31796, 'batch_loss/train': 0.7669469905085862}
+12/27/2021 03:42:54 - INFO - codeparrot_training - Step 31797: {'lr': 0.0001473639044442381, 'samples': 16280576, 'steps': 31797, 'batch_loss/train': 0.7204260984435678}
+12/27/2021 03:43:05 - INFO - codeparrot_training - Step 31798: {'lr': 0.00014734953118222466, 'samples': 16281088, 'steps': 31798, 'batch_loss/train': 0.777967946138233}
+12/27/2021 03:43:16 - INFO - codeparrot_training - Step 31799: {'lr': 0.00014733515832831062, 'samples': 16281600, 'steps': 31799, 'batch_loss/train': 0.7459743227809668}
+12/27/2021 03:43:28 - INFO - codeparrot_training - Step 31800: {'lr': 0.00014732078588255336, 'samples': 16282112, 'steps': 31800, 'batch_loss/train': 0.6618986083194613}
+12/27/2021 03:43:38 - INFO - codeparrot_training - Step 31801: {'lr': 0.00014730641384500987, 'samples': 16282624, 'steps': 31801, 'batch_loss/train': 0.7434786017984152}
+12/27/2021 03:43:49 - INFO - codeparrot_training - Step 31802: {'lr': 0.00014729204221573727, 'samples': 16283136, 'steps': 31802, 'batch_loss/train': 0.8470667889341712}
+12/27/2021 03:44:02 - INFO - codeparrot_training - Step 31803: {'lr': 0.00014727767099479268, 'samples': 16283648, 'steps': 31803, 'batch_loss/train': 0.7849399792030454}
+12/27/2021 03:44:12 - INFO - codeparrot_training - Step 31804: {'lr': 0.00014726330018223333, 'samples': 16284160, 'steps': 31804, 'batch_loss/train': 0.6796897798776627}
+12/27/2021 03:44:23 - INFO - codeparrot_training - Step 31805: {'lr': 0.0001472489297781163, 'samples': 16284672, 'steps': 31805, 'batch_loss/train': 0.6817664848640561}
+12/27/2021 03:44:34 - INFO - codeparrot_training - Step 31806: {'lr': 0.00014723455978249878, 'samples': 16285184, 'steps': 31806, 'batch_loss/train': 0.6494614311959594}
+12/27/2021 03:44:46 - INFO - codeparrot_training - Step 31807: {'lr': 0.00014722019019543776, 'samples': 16285696, 'steps': 31807, 'batch_loss/train': 0.8497034460306168}
+12/27/2021 03:44:56 - INFO - codeparrot_training - Step 31808: {'lr': 0.00014720582101699053, 'samples': 16286208, 'steps': 31808, 'batch_loss/train': 0.8771047024056315}
+12/27/2021 03:45:07 - INFO - codeparrot_training - Step 31809: {'lr': 0.0001471914522472141, 'samples': 16286720, 'steps': 31809, 'batch_loss/train': 0.8233612468466163}
+12/27/2021 03:45:20 - INFO - codeparrot_training - Step 31810: {'lr': 0.0001471770838861657, 'samples': 16287232, 'steps': 31810, 'batch_loss/train': 0.6766634145751595}
+12/27/2021 03:45:30 - INFO - codeparrot_training - Step 31811: {'lr': 0.00014716271593390228, 'samples': 16287744, 'steps': 31811, 'batch_loss/train': 0.7130514550954103}
+12/27/2021 03:45:41 - INFO - codeparrot_training - Step 31812: {'lr': 0.0001471483483904811, 'samples': 16288256, 'steps': 31812, 'batch_loss/train': 0.7606725795194507}
+12/27/2021 03:45:53 - INFO - codeparrot_training - Step 31813: {'lr': 0.00014713398125595933, 'samples': 16288768, 'steps': 31813, 'batch_loss/train': 0.7772129331715405}
+12/27/2021 03:46:04 - INFO - codeparrot_training - Step 31814: {'lr': 0.0001471196145303939, 'samples': 16289280, 'steps': 31814, 'batch_loss/train': 0.6653079318348318}
+12/27/2021 03:46:14 - INFO - codeparrot_training - Step 31815: {'lr': 0.00014710524821384208, 'samples': 16289792, 'steps': 31815, 'batch_loss/train': 0.9863593950867653}
+12/27/2021 03:46:25 - INFO - codeparrot_training - Step 31816: {'lr': 0.000147090882306361, 'samples': 16290304, 'steps': 31816, 'batch_loss/train': 0.8456998120527714}
+12/27/2021 03:46:37 - INFO - codeparrot_training - Step 31817: {'lr': 0.0001470765168080077, 'samples': 16290816, 'steps': 31817, 'batch_loss/train': 0.710507012438029}
+12/27/2021 03:46:48 - INFO - codeparrot_training - Step 31818: {'lr': 0.00014706215171883926, 'samples': 16291328, 'steps': 31818, 'batch_loss/train': 0.6500339657068253}
+12/27/2021 03:46:59 - INFO - codeparrot_training - Step 31819: {'lr': 0.0001470477870389128, 'samples': 16291840, 'steps': 31819, 'batch_loss/train': 0.7619247944094241}
+12/27/2021 03:47:11 - INFO - codeparrot_training - Step 31820: {'lr': 0.00014703342276828558, 'samples': 16292352, 'steps': 31820, 'batch_loss/train': 0.8098590113222599}
+12/27/2021 03:47:22 - INFO - codeparrot_training - Step 31821: {'lr': 0.0001470190589070145, 'samples': 16292864, 'steps': 31821, 'batch_loss/train': 0.5406850918370765}
+12/27/2021 03:47:32 - INFO - codeparrot_training - Step 31822: {'lr': 0.00014700469545515676, 'samples': 16293376, 'steps': 31822, 'batch_loss/train': 0.6650030773598701}
+12/27/2021 03:47:45 - INFO - codeparrot_training - Step 31823: {'lr': 0.00014699033241276954, 'samples': 16293888, 'steps': 31823, 'batch_loss/train': 0.7995863249525428}
+12/27/2021 03:47:55 - INFO - codeparrot_training - Step 31824: {'lr': 0.00014697596977990979, 'samples': 16294400, 'steps': 31824, 'batch_loss/train': 0.7086032410152256}
+12/27/2021 03:48:06 - INFO - codeparrot_training - Step 31825: {'lr': 0.00014696160755663465, 'samples': 16294912, 'steps': 31825, 'batch_loss/train': 0.6762685319408774}
+12/27/2021 03:48:17 - INFO - codeparrot_training - Step 31826: {'lr': 0.00014694724574300136, 'samples': 16295424, 'steps': 31826, 'batch_loss/train': 0.7346733435988426}
+12/27/2021 03:48:29 - INFO - codeparrot_training - Step 31827: {'lr': 0.0001469328843390669, 'samples': 16295936, 'steps': 31827, 'batch_loss/train': 0.8530834997072816}
+12/27/2021 03:48:39 - INFO - codeparrot_training - Step 31828: {'lr': 0.00014691852334488832, 'samples': 16296448, 'steps': 31828, 'batch_loss/train': 0.7092279838398099}
+12/27/2021 03:48:50 - INFO - codeparrot_training - Step 31829: {'lr': 0.00014690416276052273, 'samples': 16296960, 'steps': 31829, 'batch_loss/train': 0.7751464295433834}
+12/27/2021 03:49:02 - INFO - codeparrot_training - Step 31830: {'lr': 0.00014688980258602735, 'samples': 16297472, 'steps': 31830, 'batch_loss/train': 0.6414663014002144}
+12/27/2021 03:49:13 - INFO - codeparrot_training - Step 31831: {'lr': 0.00014687544282145914, 'samples': 16297984, 'steps': 31831, 'batch_loss/train': 0.8453071312978864}
+12/27/2021 03:49:23 - INFO - codeparrot_training - Step 31832: {'lr': 0.00014686108346687529, 'samples': 16298496, 'steps': 31832, 'batch_loss/train': 0.7563894763588905}
+12/27/2021 03:49:36 - INFO - codeparrot_training - Step 31833: {'lr': 0.0001468467245223327, 'samples': 16299008, 'steps': 31833, 'batch_loss/train': 0.8147904565557837}
+12/27/2021 03:49:47 - INFO - codeparrot_training - Step 31834: {'lr': 0.00014683236598788868, 'samples': 16299520, 'steps': 31834, 'batch_loss/train': 0.8050429481081665}
+12/27/2021 03:49:57 - INFO - codeparrot_training - Step 31835: {'lr': 0.00014681800786360026, 'samples': 16300032, 'steps': 31835, 'batch_loss/train': 0.7384370155632496}
+12/27/2021 03:50:10 - INFO - codeparrot_training - Step 31836: {'lr': 0.00014680365014952434, 'samples': 16300544, 'steps': 31836, 'batch_loss/train': 0.7763364547863603}
+12/27/2021 03:50:20 - INFO - codeparrot_training - Step 31837: {'lr': 0.0001467892928457183, 'samples': 16301056, 'steps': 31837, 'batch_loss/train': 0.7426579194143414}
+12/27/2021 03:50:31 - INFO - codeparrot_training - Step 31838: {'lr': 0.00014677493595223896, 'samples': 16301568, 'steps': 31838, 'batch_loss/train': 0.7647074116393924}
+12/27/2021 03:50:42 - INFO - codeparrot_training - Step 31839: {'lr': 0.00014676057946914355, 'samples': 16302080, 'steps': 31839, 'batch_loss/train': 0.8184208071324974}
+12/27/2021 03:50:54 - INFO - codeparrot_training - Step 31840: {'lr': 0.00014674622339648903, 'samples': 16302592, 'steps': 31840, 'batch_loss/train': 0.8736024396494031}
+12/27/2021 03:51:05 - INFO - codeparrot_training - Step 31841: {'lr': 0.00014673186773433256, 'samples': 16303104, 'steps': 31841, 'batch_loss/train': 0.8056481243111193}
+12/27/2021 03:51:16 - INFO - codeparrot_training - Step 31842: {'lr': 0.00014671751248273123, 'samples': 16303616, 'steps': 31842, 'batch_loss/train': 0.682413000613451}
+12/27/2021 03:51:28 - INFO - codeparrot_training - Step 31843: {'lr': 0.00014670315764174206, 'samples': 16304128, 'steps': 31843, 'batch_loss/train': 0.5934856978128664}
+12/27/2021 03:51:38 - INFO - codeparrot_training - Step 31844: {'lr': 0.00014668880321142206, 'samples': 16304640, 'steps': 31844, 'batch_loss/train': 0.7754579829052091}
+12/27/2021 03:51:49 - INFO - codeparrot_training - Step 31845: {'lr': 0.0001466744491918285, 'samples': 16305152, 'steps': 31845, 'batch_loss/train': 1.024993128143251}
+12/27/2021 03:52:01 - INFO - codeparrot_training - Step 31846: {'lr': 0.00014666009558301823, 'samples': 16305664, 'steps': 31846, 'batch_loss/train': 0.7702944269403815}
+12/27/2021 03:52:12 - INFO - codeparrot_training - Step 31847: {'lr': 0.00014664574238504844, 'samples': 16306176, 'steps': 31847, 'batch_loss/train': 0.7868547644466162}
+12/27/2021 03:52:23 - INFO - codeparrot_training - Step 31848: {'lr': 0.00014663138959797607, 'samples': 16306688, 'steps': 31848, 'batch_loss/train': 0.6642484983312897}
+12/27/2021 03:52:33 - INFO - codeparrot_training - Step 31849: {'lr': 0.00014661703722185836, 'samples': 16307200, 'steps': 31849, 'batch_loss/train': 0.6248986299615353}
+12/27/2021 03:52:46 - INFO - codeparrot_training - Step 31850: {'lr': 0.00014660268525675224, 'samples': 16307712, 'steps': 31850, 'batch_loss/train': 0.6798126986250281}
+12/27/2021 03:52:57 - INFO - codeparrot_training - Step 31851: {'lr': 0.00014658833370271473, 'samples': 16308224, 'steps': 31851, 'batch_loss/train': 0.7671913150697947}
+12/27/2021 03:53:07 - INFO - codeparrot_training - Step 31852: {'lr': 0.0001465739825598031, 'samples': 16308736, 'steps': 31852, 'batch_loss/train': 0.772369921207428}
+12/27/2021 03:53:20 - INFO - codeparrot_training - Step 31853: {'lr': 0.0001465596318280742, 'samples': 16309248, 'steps': 31853, 'batch_loss/train': 0.728679892141372}
+12/27/2021 03:53:31 - INFO - codeparrot_training - Step 31854: {'lr': 0.00014654528150758513, 'samples': 16309760, 'steps': 31854, 'batch_loss/train': 0.7942998632788658}
+12/27/2021 03:53:41 - INFO - codeparrot_training - Step 31855: {'lr': 0.00014653093159839293, 'samples': 16310272, 'steps': 31855, 'batch_loss/train': 0.706990098580718}
+12/27/2021 03:53:53 - INFO - codeparrot_training - Step 31856: {'lr': 0.00014651658210055473, 'samples': 16310784, 'steps': 31856, 'batch_loss/train': 1.1624716392252594}
+12/27/2021 03:54:04 - INFO - codeparrot_training - Step 31857: {'lr': 0.0001465022330141275, 'samples': 16311296, 'steps': 31857, 'batch_loss/train': 0.780224627815187}
+12/27/2021 03:54:15 - INFO - codeparrot_training - Step 31858: {'lr': 0.00014648788433916838, 'samples': 16311808, 'steps': 31858, 'batch_loss/train': 0.8894189577549696}
+12/27/2021 03:54:25 - INFO - codeparrot_training - Step 31859: {'lr': 0.00014647353607573422, 'samples': 16312320, 'steps': 31859, 'batch_loss/train': 0.7548011164180934}
+12/27/2021 03:54:37 - INFO - codeparrot_training - Step 31860: {'lr': 0.00014645918822388227, 'samples': 16312832, 'steps': 31860, 'batch_loss/train': 0.7251311384607106}
+12/27/2021 03:54:48 - INFO - codeparrot_training - Step 31861: {'lr': 0.00014644484078366952, 'samples': 16313344, 'steps': 31861, 'batch_loss/train': 0.7070825295522809}
+12/27/2021 03:54:59 - INFO - codeparrot_training - Step 31862: {'lr': 0.00014643049375515289, 'samples': 16313856, 'steps': 31862, 'batch_loss/train': 0.8560344823636115}
+12/27/2021 03:55:11 - INFO - codeparrot_training - Step 31863: {'lr': 0.00014641614713838957, 'samples': 16314368, 'steps': 31863, 'batch_loss/train': 0.8497227462939918}
+12/27/2021 03:55:22 - INFO - codeparrot_training - Step 31864: {'lr': 0.00014640180093343654, 'samples': 16314880, 'steps': 31864, 'batch_loss/train': 0.7192728687077761}
+12/27/2021 03:55:33 - INFO - codeparrot_training - Step 31865: {'lr': 0.00014638745514035088, 'samples': 16315392, 'steps': 31865, 'batch_loss/train': 0.7193884460721165}
+12/27/2021 03:55:45 - INFO - codeparrot_training - Step 31866: {'lr': 0.00014637310975918944, 'samples': 16315904, 'steps': 31866, 'batch_loss/train': 0.711571104824543}
+12/27/2021 03:55:56 - INFO - codeparrot_training - Step 31867: {'lr': 0.00014635876479000948, 'samples': 16316416, 'steps': 31867, 'batch_loss/train': 0.7574204029515386}
+12/27/2021 03:56:06 - INFO - codeparrot_training - Step 31868: {'lr': 0.00014634442023286797, 'samples': 16316928, 'steps': 31868, 'batch_loss/train': 0.7270896129775792}
+12/27/2021 03:56:17 - INFO - codeparrot_training - Step 31869: {'lr': 0.00014633007608782185, 'samples': 16317440, 'steps': 31869, 'batch_loss/train': 0.7042636479018256}
+12/27/2021 03:56:29 - INFO - codeparrot_training - Step 31870: {'lr': 0.00014631573235492814, 'samples': 16317952, 'steps': 31870, 'batch_loss/train': 0.7848080629482865}
+12/27/2021 03:56:40 - INFO - codeparrot_training - Step 31871: {'lr': 0.00014630138903424405, 'samples': 16318464, 'steps': 31871, 'batch_loss/train': 0.7599697194527835}
+12/27/2021 03:56:50 - INFO - codeparrot_training - Step 31872: {'lr': 0.00014628704612582648, 'samples': 16318976, 'steps': 31872, 'batch_loss/train': 0.781647764146328}
+12/27/2021 03:57:03 - INFO - codeparrot_training - Step 31873: {'lr': 0.00014627270362973236, 'samples': 16319488, 'steps': 31873, 'batch_loss/train': 0.7487312600715086}
+12/27/2021 03:57:14 - INFO - codeparrot_training - Step 31874: {'lr': 0.00014625836154601884, 'samples': 16320000, 'steps': 31874, 'batch_loss/train': 0.7714458405971527}
+12/27/2021 03:57:24 - INFO - codeparrot_training - Step 31875: {'lr': 0.00014624401987474296, 'samples': 16320512, 'steps': 31875, 'batch_loss/train': 0.9513601567596197}
+12/27/2021 03:57:37 - INFO - codeparrot_training - Step 31876: {'lr': 0.00014622967861596165, 'samples': 16321024, 'steps': 31876, 'batch_loss/train': 0.7000431376509368}
+12/27/2021 03:57:47 - INFO - codeparrot_training - Step 31877: {'lr': 0.00014621533776973186, 'samples': 16321536, 'steps': 31877, 'batch_loss/train': 0.7194643935654312}
+12/27/2021 03:57:58 - INFO - codeparrot_training - Step 31878: {'lr': 0.00014620099733611084, 'samples': 16322048, 'steps': 31878, 'batch_loss/train': 0.7721019824966788}
+12/27/2021 03:58:09 - INFO - codeparrot_training - Step 31879: {'lr': 0.0001461866573151554, 'samples': 16322560, 'steps': 31879, 'batch_loss/train': 0.5679656567517668}
+12/27/2021 03:58:21 - INFO - codeparrot_training - Step 31880: {'lr': 0.00014617231770692264, 'samples': 16323072, 'steps': 31880, 'batch_loss/train': 0.7106166505254805}
+12/27/2021 03:58:32 - INFO - codeparrot_training - Step 31881: {'lr': 0.00014615797851146945, 'samples': 16323584, 'steps': 31881, 'batch_loss/train': 0.7093262923881412}
+12/27/2021 03:58:42 - INFO - codeparrot_training - Step 31882: {'lr': 0.00014614363972885306, 'samples': 16324096, 'steps': 31882, 'batch_loss/train': 0.7116166427731514}
+12/27/2021 03:58:55 - INFO - codeparrot_training - Step 31883: {'lr': 0.00014612930135913027, 'samples': 16324608, 'steps': 31883, 'batch_loss/train': 0.7922893278300762}
+12/27/2021 03:59:05 - INFO - codeparrot_training - Step 31884: {'lr': 0.0001461149634023582, 'samples': 16325120, 'steps': 31884, 'batch_loss/train': 0.7382288193330169}
+12/27/2021 03:59:16 - INFO - codeparrot_training - Step 31885: {'lr': 0.00014610062585859374, 'samples': 16325632, 'steps': 31885, 'batch_loss/train': 0.8411637023091316}
+12/27/2021 03:59:28 - INFO - codeparrot_training - Step 31886: {'lr': 0.00014608628872789397, 'samples': 16326144, 'steps': 31886, 'batch_loss/train': 0.8442542399279773}
+12/27/2021 03:59:39 - INFO - codeparrot_training - Step 31887: {'lr': 0.00014607195201031596, 'samples': 16326656, 'steps': 31887, 'batch_loss/train': 0.8398930821567774}
+12/27/2021 03:59:49 - INFO - codeparrot_training - Step 31888: {'lr': 0.00014605761570591654, 'samples': 16327168, 'steps': 31888, 'batch_loss/train': 0.763575054705143}
+12/27/2021 04:00:00 - INFO - codeparrot_training - Step 31889: {'lr': 0.0001460432798147528, 'samples': 16327680, 'steps': 31889, 'batch_loss/train': 0.7098903129808605}
+12/27/2021 04:00:12 - INFO - codeparrot_training - Step 31890: {'lr': 0.0001460289443368818, 'samples': 16328192, 'steps': 31890, 'batch_loss/train': 0.6790118010248989}
+12/27/2021 04:00:23 - INFO - codeparrot_training - Step 31891: {'lr': 0.00014601460927236043, 'samples': 16328704, 'steps': 31891, 'batch_loss/train': 0.7472548792138696}
+12/27/2021 04:00:33 - INFO - codeparrot_training - Step 31892: {'lr': 0.00014600027462124566, 'samples': 16329216, 'steps': 31892, 'batch_loss/train': 0.6992622511461377}
+12/27/2021 04:00:46 - INFO - codeparrot_training - Step 31893: {'lr': 0.00014598594038359454, 'samples': 16329728, 'steps': 31893, 'batch_loss/train': 0.6979976161092054}
+12/27/2021 04:00:57 - INFO - codeparrot_training - Step 31894: {'lr': 0.00014597160655946412, 'samples': 16330240, 'steps': 31894, 'batch_loss/train': 0.7447692109271884}
+12/27/2021 04:01:07 - INFO - codeparrot_training - Step 31895: {'lr': 0.00014595727314891126, 'samples': 16330752, 'steps': 31895, 'batch_loss/train': 0.5916073407279328}
+12/27/2021 04:01:19 - INFO - codeparrot_training - Step 31896: {'lr': 0.00014594294015199297, 'samples': 16331264, 'steps': 31896, 'batch_loss/train': 0.7128315868321806}
+12/27/2021 04:01:30 - INFO - codeparrot_training - Step 31897: {'lr': 0.0001459286075687663, 'samples': 16331776, 'steps': 31897, 'batch_loss/train': 0.8143412685021758}
+12/27/2021 04:01:41 - INFO - codeparrot_training - Step 31898: {'lr': 0.00014591427539928814, 'samples': 16332288, 'steps': 31898, 'batch_loss/train': 0.6799070099368691}
+12/27/2021 04:01:53 - INFO - codeparrot_training - Step 31899: {'lr': 0.0001458999436436156, 'samples': 16332800, 'steps': 31899, 'batch_loss/train': 0.7802020125091076}
+12/27/2021 04:02:03 - INFO - codeparrot_training - Step 31900: {'lr': 0.0001458856123018055, 'samples': 16333312, 'steps': 31900, 'batch_loss/train': 0.7217562827281654}
+12/27/2021 04:02:14 - INFO - codeparrot_training - Step 31901: {'lr': 0.00014587128137391492, 'samples': 16333824, 'steps': 31901, 'batch_loss/train': 0.7216942110098898}
+12/27/2021 04:02:25 - INFO - codeparrot_training - Step 31902: {'lr': 0.00014585695086000088, 'samples': 16334336, 'steps': 31902, 'batch_loss/train': 0.6065724173095077}
+12/27/2021 04:02:37 - INFO - codeparrot_training - Step 31903: {'lr': 0.00014584262076012015, 'samples': 16334848, 'steps': 31903, 'batch_loss/train': 0.6974895792081952}
+12/27/2021 04:02:48 - INFO - codeparrot_training - Step 31904: {'lr': 0.00014582829107432987, 'samples': 16335360, 'steps': 31904, 'batch_loss/train': 0.7183791995048523}
+12/27/2021 04:02:58 - INFO - codeparrot_training - Step 31905: {'lr': 0.00014581396180268712, 'samples': 16335872, 'steps': 31905, 'batch_loss/train': 0.832825199700892}
+12/27/2021 04:03:11 - INFO - codeparrot_training - Step 31906: {'lr': 0.00014579963294524857, 'samples': 16336384, 'steps': 31906, 'batch_loss/train': 0.7168078317772597}
+12/27/2021 04:03:21 - INFO - codeparrot_training - Step 31907: {'lr': 0.0001457853045020713, 'samples': 16336896, 'steps': 31907, 'batch_loss/train': 0.7170864334329963}
+12/27/2021 04:03:32 - INFO - codeparrot_training - Step 31908: {'lr': 0.0001457709764732124, 'samples': 16337408, 'steps': 31908, 'batch_loss/train': 0.7776830308139324}
+12/27/2021 04:03:45 - INFO - codeparrot_training - Step 31909: {'lr': 0.00014575664885872874, 'samples': 16337920, 'steps': 31909, 'batch_loss/train': 0.7674722499214113}
+12/27/2021 04:03:55 - INFO - codeparrot_training - Step 31910: {'lr': 0.00014574232165867723, 'samples': 16338432, 'steps': 31910, 'batch_loss/train': 0.7922011539340019}
+12/27/2021 04:04:06 - INFO - codeparrot_training - Step 31911: {'lr': 0.00014572799487311492, 'samples': 16338944, 'steps': 31911, 'batch_loss/train': 0.6858602399006486}
+12/27/2021 04:04:17 - INFO - codeparrot_training - Step 31912: {'lr': 0.0001457136685020987, 'samples': 16339456, 'steps': 31912, 'batch_loss/train': 0.6687997803092003}
+12/27/2021 04:04:29 - INFO - codeparrot_training - Step 31913: {'lr': 0.00014569934254568558, 'samples': 16339968, 'steps': 31913, 'batch_loss/train': 0.8424835996702313}
+12/27/2021 04:04:39 - INFO - codeparrot_training - Step 31914: {'lr': 0.0001456850170039325, 'samples': 16340480, 'steps': 31914, 'batch_loss/train': 0.7690926534123719}
+12/27/2021 04:04:50 - INFO - codeparrot_training - Step 31915: {'lr': 0.00014567069187689638, 'samples': 16340992, 'steps': 31915, 'batch_loss/train': 0.67406477231998}
+12/27/2021 04:05:03 - INFO - codeparrot_training - Step 31916: {'lr': 0.0001456563671646342, 'samples': 16341504, 'steps': 31916, 'batch_loss/train': 0.7282918945420533}
+12/27/2021 04:05:13 - INFO - codeparrot_training - Step 31917: {'lr': 0.000145642042867203, 'samples': 16342016, 'steps': 31917, 'batch_loss/train': 0.7654187821317464}
+12/27/2021 04:05:24 - INFO - codeparrot_training - Step 31918: {'lr': 0.00014562771898465947, 'samples': 16342528, 'steps': 31918, 'batch_loss/train': 0.8673186041414738}
+12/27/2021 04:05:36 - INFO - codeparrot_training - Step 31919: {'lr': 0.00014561339551706086, 'samples': 16343040, 'steps': 31919, 'batch_loss/train': 0.5356267626048066}
+12/27/2021 04:05:47 - INFO - codeparrot_training - Step 31920: {'lr': 0.0001455990724644639, 'samples': 16343552, 'steps': 31920, 'batch_loss/train': 0.7468445715494454}
+12/27/2021 04:05:58 - INFO - codeparrot_training - Step 31921: {'lr': 0.00014558474982692566, 'samples': 16344064, 'steps': 31921, 'batch_loss/train': 0.7571802595630288}
+12/27/2021 04:06:10 - INFO - codeparrot_training - Step 31922: {'lr': 0.00014557042760450294, 'samples': 16344576, 'steps': 31922, 'batch_loss/train': 0.7310304092243314}
+12/27/2021 04:06:21 - INFO - codeparrot_training - Step 31923: {'lr': 0.00014555610579725285, 'samples': 16345088, 'steps': 31923, 'batch_loss/train': 0.7035038662143052}
+12/27/2021 04:06:31 - INFO - codeparrot_training - Step 31924: {'lr': 0.00014554178440523218, 'samples': 16345600, 'steps': 31924, 'batch_loss/train': 0.7212524614296854}
+12/27/2021 04:06:42 - INFO - codeparrot_training - Step 31925: {'lr': 0.00014552746342849797, 'samples': 16346112, 'steps': 31925, 'batch_loss/train': 0.8436366748064756}
+12/27/2021 04:06:54 - INFO - codeparrot_training - Step 31926: {'lr': 0.00014551314286710712, 'samples': 16346624, 'steps': 31926, 'batch_loss/train': 0.7359624085947871}
+12/27/2021 04:07:05 - INFO - codeparrot_training - Step 31927: {'lr': 0.00014549882272111656, 'samples': 16347136, 'steps': 31927, 'batch_loss/train': 0.6669484761077911}
+12/27/2021 04:07:16 - INFO - codeparrot_training - Step 31928: {'lr': 0.0001454845029905833, 'samples': 16347648, 'steps': 31928, 'batch_loss/train': 0.6063989468966611}
+12/27/2021 04:07:28 - INFO - codeparrot_training - Step 31929: {'lr': 0.00014547018367556402, 'samples': 16348160, 'steps': 31929, 'batch_loss/train': 0.718155836686492}
+12/27/2021 04:07:38 - INFO - codeparrot_training - Step 31930: {'lr': 0.0001454558647761159, 'samples': 16348672, 'steps': 31930, 'batch_loss/train': 0.7551941247656941}
+12/27/2021 04:07:49 - INFO - codeparrot_training - Step 31931: {'lr': 0.00014544154629229588, 'samples': 16349184, 'steps': 31931, 'batch_loss/train': 0.7434254363179207}
+12/27/2021 04:08:01 - INFO - codeparrot_training - Step 31932: {'lr': 0.00014542722822416074, 'samples': 16349696, 'steps': 31932, 'batch_loss/train': 0.7211455209180713}
+12/27/2021 04:08:12 - INFO - codeparrot_training - Step 31933: {'lr': 0.0001454129105717673, 'samples': 16350208, 'steps': 31933, 'batch_loss/train': 0.8136425279080868}
+12/27/2021 04:08:23 - INFO - codeparrot_training - Step 31934: {'lr': 0.00014539859333517288, 'samples': 16350720, 'steps': 31934, 'batch_loss/train': 0.694523562444374}
+12/27/2021 04:08:33 - INFO - codeparrot_training - Step 31935: {'lr': 0.00014538427651443402, 'samples': 16351232, 'steps': 31935, 'batch_loss/train': 0.7421758528798819}
+12/27/2021 04:08:46 - INFO - codeparrot_training - Step 31936: {'lr': 0.00014536996010960782, 'samples': 16351744, 'steps': 31936, 'batch_loss/train': 0.852515017206315}
+12/27/2021 04:08:56 - INFO - codeparrot_training - Step 31937: {'lr': 0.0001453556441207511, 'samples': 16352256, 'steps': 31937, 'batch_loss/train': 0.9033232172951102}
+12/27/2021 04:09:07 - INFO - codeparrot_training - Step 31938: {'lr': 0.00014534132854792086, 'samples': 16352768, 'steps': 31938, 'batch_loss/train': 0.7894304152578115}
+12/27/2021 04:09:19 - INFO - codeparrot_training - Step 31939: {'lr': 0.000145327013391174, 'samples': 16353280, 'steps': 31939, 'batch_loss/train': 0.8209690796211362}
+12/27/2021 04:09:30 - INFO - codeparrot_training - Step 31940: {'lr': 0.00014531269865056737, 'samples': 16353792, 'steps': 31940, 'batch_loss/train': 0.8715091785416007}
+12/27/2021 04:09:40 - INFO - codeparrot_training - Step 31941: {'lr': 0.00014529838432615795, 'samples': 16354304, 'steps': 31941, 'batch_loss/train': 0.7477897226344794}
+12/27/2021 04:09:53 - INFO - codeparrot_training - Step 31942: {'lr': 0.00014528407041800257, 'samples': 16354816, 'steps': 31942, 'batch_loss/train': 0.7067928593605757}
+12/27/2021 04:10:04 - INFO - codeparrot_training - Step 31943: {'lr': 0.00014526975692615834, 'samples': 16355328, 'steps': 31943, 'batch_loss/train': 0.6619329880923033}
+12/27/2021 04:10:14 - INFO - codeparrot_training - Step 31944: {'lr': 0.0001452554438506818, 'samples': 16355840, 'steps': 31944, 'batch_loss/train': 0.8168338229879737}
+12/27/2021 04:10:25 - INFO - codeparrot_training - Step 31945: {'lr': 0.00014524113119163023, 'samples': 16356352, 'steps': 31945, 'batch_loss/train': 0.7344493726268411}
+12/27/2021 04:10:37 - INFO - codeparrot_training - Step 31946: {'lr': 0.00014522681894906032, 'samples': 16356864, 'steps': 31946, 'batch_loss/train': 0.6771369376219809}
+12/27/2021 04:10:48 - INFO - codeparrot_training - Step 31947: {'lr': 0.00014521250712302888, 'samples': 16357376, 'steps': 31947, 'batch_loss/train': 0.8312897658906877}
+12/27/2021 04:10:58 - INFO - codeparrot_training - Step 31948: {'lr': 0.00014519819571359317, 'samples': 16357888, 'steps': 31948, 'batch_loss/train': 0.6991229438572191}
+12/27/2021 04:11:11 - INFO - codeparrot_training - Step 31949: {'lr': 0.00014518388472080972, 'samples': 16358400, 'steps': 31949, 'batch_loss/train': 0.721479722764343}
+12/27/2021 04:11:22 - INFO - codeparrot_training - Step 31950: {'lr': 0.00014516957414473564, 'samples': 16358912, 'steps': 31950, 'batch_loss/train': 0.8277254961431026}
+12/27/2021 04:11:32 - INFO - codeparrot_training - Step 31951: {'lr': 0.0001451552639854277, 'samples': 16359424, 'steps': 31951, 'batch_loss/train': 0.773600448621437}
+12/27/2021 04:11:45 - INFO - codeparrot_training - Step 31952: {'lr': 0.00014514095424294287, 'samples': 16359936, 'steps': 31952, 'batch_loss/train': 0.6513679935596883}
+12/27/2021 04:11:55 - INFO - codeparrot_training - Step 31953: {'lr': 0.00014512664491733796, 'samples': 16360448, 'steps': 31953, 'batch_loss/train': 0.7553668515756726}
+12/27/2021 04:12:06 - INFO - codeparrot_training - Step 31954: {'lr': 0.00014511233600867008, 'samples': 16360960, 'steps': 31954, 'batch_loss/train': 0.7141644963994622}
+12/27/2021 04:12:17 - INFO - codeparrot_training - Step 31955: {'lr': 0.00014509802751699568, 'samples': 16361472, 'steps': 31955, 'batch_loss/train': 1.023904161178507}
+12/27/2021 04:12:29 - INFO - codeparrot_training - Step 31956: {'lr': 0.00014508371944237206, 'samples': 16361984, 'steps': 31956, 'batch_loss/train': 0.7519565192051232}
+12/27/2021 04:12:40 - INFO - codeparrot_training - Step 31957: {'lr': 0.00014506941178485605, 'samples': 16362496, 'steps': 31957, 'batch_loss/train': 0.7882409440353513}
+12/27/2021 04:12:51 - INFO - codeparrot_training - Step 31958: {'lr': 0.00014505510454450432, 'samples': 16363008, 'steps': 31958, 'batch_loss/train': 0.7754185041412711}
+12/27/2021 04:13:03 - INFO - codeparrot_training - Step 31959: {'lr': 0.0001450407977213738, 'samples': 16363520, 'steps': 31959, 'batch_loss/train': 0.9079031273722649}
+12/27/2021 04:13:14 - INFO - codeparrot_training - Step 31960: {'lr': 0.00014502649131552158, 'samples': 16364032, 'steps': 31960, 'batch_loss/train': 0.8797187586314976}
+12/27/2021 04:13:24 - INFO - codeparrot_training - Step 31961: {'lr': 0.00014501218532700437, 'samples': 16364544, 'steps': 31961, 'batch_loss/train': 0.6584167894907296}
+12/27/2021 04:13:36 - INFO - codeparrot_training - Step 31962: {'lr': 0.0001449978797558789, 'samples': 16365056, 'steps': 31962, 'batch_loss/train': 0.5918694599531591}
+12/27/2021 04:13:47 - INFO - codeparrot_training - Step 31963: {'lr': 0.00014498357460220247, 'samples': 16365568, 'steps': 31963, 'batch_loss/train': 0.808854759670794}
+12/27/2021 04:13:58 - INFO - codeparrot_training - Step 31964: {'lr': 0.00014496926986603154, 'samples': 16366080, 'steps': 31964, 'batch_loss/train': 0.7099562641233206}
+12/27/2021 04:14:10 - INFO - codeparrot_training - Step 31965: {'lr': 0.0001449549655474232, 'samples': 16366592, 'steps': 31965, 'batch_loss/train': 0.7439971081912518}
+12/27/2021 04:14:20 - INFO - codeparrot_training - Step 31966: {'lr': 0.0001449406616464342, 'samples': 16367104, 'steps': 31966, 'batch_loss/train': 0.6718647326342762}
+12/27/2021 04:14:31 - INFO - codeparrot_training - Step 31967: {'lr': 0.0001449263581631215, 'samples': 16367616, 'steps': 31967, 'batch_loss/train': 0.8115277751348913}
+12/27/2021 04:14:42 - INFO - codeparrot_training - Step 31968: {'lr': 0.00014491205509754187, 'samples': 16368128, 'steps': 31968, 'batch_loss/train': 0.6705477278446779}
+12/27/2021 04:14:54 - INFO - codeparrot_training - Step 31969: {'lr': 0.00014489775244975236, 'samples': 16368640, 'steps': 31969, 'batch_loss/train': 0.5724111577728763}
+12/27/2021 04:15:05 - INFO - codeparrot_training - Step 31970: {'lr': 0.00014488345021980954, 'samples': 16369152, 'steps': 31970, 'batch_loss/train': 0.7230505216866732}
+12/27/2021 04:15:16 - INFO - codeparrot_training - Step 31971: {'lr': 0.00014486914840777058, 'samples': 16369664, 'steps': 31971, 'batch_loss/train': 0.8773024952970445}
+12/27/2021 04:15:28 - INFO - codeparrot_training - Step 31972: {'lr': 0.00014485484701369213, 'samples': 16370176, 'steps': 31972, 'batch_loss/train': 0.7467029644176364}
+12/27/2021 04:15:38 - INFO - codeparrot_training - Step 31973: {'lr': 0.00014484054603763094, 'samples': 16370688, 'steps': 31973, 'batch_loss/train': 0.7027703507337719}
+12/27/2021 04:15:49 - INFO - codeparrot_training - Step 31974: {'lr': 0.0001448262454796443, 'samples': 16371200, 'steps': 31974, 'batch_loss/train': 0.5603175391443074}
+12/27/2021 04:16:01 - INFO - codeparrot_training - Step 31975: {'lr': 0.00014481194533978863, 'samples': 16371712, 'steps': 31975, 'batch_loss/train': 0.762289198115468}
+12/27/2021 04:16:12 - INFO - codeparrot_training - Step 31976: {'lr': 0.000144797645618121, 'samples': 16372224, 'steps': 31976, 'batch_loss/train': 0.8408209783956409}
+12/27/2021 04:16:22 - INFO - codeparrot_training - Step 31977: {'lr': 0.0001447833463146982, 'samples': 16372736, 'steps': 31977, 'batch_loss/train': 0.7153506581671536}
+12/27/2021 04:16:33 - INFO - codeparrot_training - Step 31978: {'lr': 0.00014476904742957708, 'samples': 16373248, 'steps': 31978, 'batch_loss/train': 0.6531502353027463}
+12/27/2021 04:16:47 - INFO - codeparrot_training - Step 31979: {'lr': 0.0001447547489628145, 'samples': 16373760, 'steps': 31979, 'batch_loss/train': 0.8184443190693855}
+12/27/2021 04:16:57 - INFO - codeparrot_training - Step 31980: {'lr': 0.0001447404509144674, 'samples': 16374272, 'steps': 31980, 'batch_loss/train': 0.6546603161841631}
+12/27/2021 04:17:08 - INFO - codeparrot_training - Step 31981: {'lr': 0.00014472615328459232, 'samples': 16374784, 'steps': 31981, 'batch_loss/train': 0.6982567654922605}
+12/27/2021 04:17:20 - INFO - codeparrot_training - Step 31982: {'lr': 0.0001447118560732464, 'samples': 16375296, 'steps': 31982, 'batch_loss/train': 0.7658149469643831}
+12/27/2021 04:17:31 - INFO - codeparrot_training - Step 31983: {'lr': 0.0001446975592804865, 'samples': 16375808, 'steps': 31983, 'batch_loss/train': 0.6913008582778275}
+12/27/2021 04:17:41 - INFO - codeparrot_training - Step 31984: {'lr': 0.00014468326290636912, 'samples': 16376320, 'steps': 31984, 'batch_loss/train': 0.7507428070530295}
+12/27/2021 04:17:53 - INFO - codeparrot_training - Step 31985: {'lr': 0.00014466896695095144, 'samples': 16376832, 'steps': 31985, 'batch_loss/train': 0.9294863492250443}
+12/27/2021 04:18:04 - INFO - codeparrot_training - Step 31986: {'lr': 0.0001446546714142903, 'samples': 16377344, 'steps': 31986, 'batch_loss/train': 0.828424443025142}
+12/27/2021 04:18:15 - INFO - codeparrot_training - Step 31987: {'lr': 0.00014464037629644225, 'samples': 16377856, 'steps': 31987, 'batch_loss/train': 0.7560961013659835}
+12/27/2021 04:18:27 - INFO - codeparrot_training - Step 31988: {'lr': 0.0001446260815974642, 'samples': 16378368, 'steps': 31988, 'batch_loss/train': 0.6332122723106295}
+12/27/2021 04:18:38 - INFO - codeparrot_training - Step 31989: {'lr': 0.00014461178731741325, 'samples': 16378880, 'steps': 31989, 'batch_loss/train': 0.8544108366477303}
+12/27/2021 04:18:49 - INFO - codeparrot_training - Step 31990: {'lr': 0.000144597493456346, 'samples': 16379392, 'steps': 31990, 'batch_loss/train': 0.7099901484325528}
+12/27/2021 04:18:59 - INFO - codeparrot_training - Step 31991: {'lr': 0.00014458320001431926, 'samples': 16379904, 'steps': 31991, 'batch_loss/train': 0.832249200437218}
+12/27/2021 04:19:12 - INFO - codeparrot_training - Step 31992: {'lr': 0.00014456890699138995, 'samples': 16380416, 'steps': 31992, 'batch_loss/train': 1.6357176955789328}
+12/27/2021 04:19:22 - INFO - codeparrot_training - Step 31993: {'lr': 0.00014455461438761484, 'samples': 16380928, 'steps': 31993, 'batch_loss/train': 0.9067887160927057}
+12/27/2021 04:19:33 - INFO - codeparrot_training - Step 31994: {'lr': 0.00014454032220305075, 'samples': 16381440, 'steps': 31994, 'batch_loss/train': 0.8224053429439664}
+12/27/2021 04:19:46 - INFO - codeparrot_training - Step 31995: {'lr': 0.00014452603043775452, 'samples': 16381952, 'steps': 31995, 'batch_loss/train': 1.795152777864132}
+12/27/2021 04:19:56 - INFO - codeparrot_training - Step 31996: {'lr': 0.000144511739091783, 'samples': 16382464, 'steps': 31996, 'batch_loss/train': 0.7361714583821595}
+12/27/2021 04:20:07 - INFO - codeparrot_training - Step 31997: {'lr': 0.00014449744816519297, 'samples': 16382976, 'steps': 31997, 'batch_loss/train': 0.779631033539772}
+12/27/2021 04:20:19 - INFO - codeparrot_training - Step 31998: {'lr': 0.00014448315765804132, 'samples': 16383488, 'steps': 31998, 'batch_loss/train': 0.8314580013975501}
+12/27/2021 04:20:30 - INFO - codeparrot_training - Step 31999: {'lr': 0.00014446886757038462, 'samples': 16384000, 'steps': 31999, 'batch_loss/train': 0.8306775754317641}
+12/27/2021 04:20:40 - INFO - codeparrot_training - Step 32000: {'lr': 0.00014445457790228006, 'samples': 16384512, 'steps': 32000, 'batch_loss/train': 0.7902027629315853}
+12/27/2021 04:20:51 - INFO - codeparrot_training - Step 32001: {'lr': 0.0001444402886537841, 'samples': 16385024, 'steps': 32001, 'batch_loss/train': 0.7147384216077626}
+12/27/2021 04:21:03 - INFO - codeparrot_training - Step 32002: {'lr': 0.00014442599982495376, 'samples': 16385536, 'steps': 32002, 'batch_loss/train': 0.7440563533455133}
+12/27/2021 04:21:14 - INFO - codeparrot_training - Step 32003: {'lr': 0.00014441171141584575, 'samples': 16386048, 'steps': 32003, 'batch_loss/train': 0.8096453249454498}
+12/27/2021 04:21:24 - INFO - codeparrot_training - Step 32004: {'lr': 0.0001443974234265169, 'samples': 16386560, 'steps': 32004, 'batch_loss/train': 0.7984539461322129}
+12/27/2021 04:21:37 - INFO - codeparrot_training - Step 32005: {'lr': 0.00014438313585702403, 'samples': 16387072, 'steps': 32005, 'batch_loss/train': 0.7090642526745796}
+12/27/2021 04:21:48 - INFO - codeparrot_training - Step 32006: {'lr': 0.00014436884870742394, 'samples': 16387584, 'steps': 32006, 'batch_loss/train': 0.811488610226661}
+12/27/2021 04:21:59 - INFO - codeparrot_training - Step 32007: {'lr': 0.00014435456197777342, 'samples': 16388096, 'steps': 32007, 'batch_loss/train': 0.7773114405572414}
+12/27/2021 04:22:09 - INFO - codeparrot_training - Step 32008: {'lr': 0.00014434027566812924, 'samples': 16388608, 'steps': 32008, 'batch_loss/train': 0.7019176525063813}
+12/27/2021 04:22:22 - INFO - codeparrot_training - Step 32009: {'lr': 0.00014432598977854834, 'samples': 16389120, 'steps': 32009, 'batch_loss/train': 0.7707016887143254}
+12/27/2021 04:22:32 - INFO - codeparrot_training - Step 32010: {'lr': 0.00014431170430908726, 'samples': 16389632, 'steps': 32010, 'batch_loss/train': 0.7873198231682181}
+12/27/2021 04:22:43 - INFO - codeparrot_training - Step 32011: {'lr': 0.00014429741925980297, 'samples': 16390144, 'steps': 32011, 'batch_loss/train': 0.8362345859641209}
+12/27/2021 04:22:55 - INFO - codeparrot_training - Step 32012: {'lr': 0.00014428313463075236, 'samples': 16390656, 'steps': 32012, 'batch_loss/train': 0.9523573406040668}
+12/27/2021 04:23:06 - INFO - codeparrot_training - Step 32013: {'lr': 0.00014426885042199196, 'samples': 16391168, 'steps': 32013, 'batch_loss/train': 0.9361483342945576}
+12/27/2021 04:23:16 - INFO - codeparrot_training - Step 32014: {'lr': 0.00014425456663357862, 'samples': 16391680, 'steps': 32014, 'batch_loss/train': 0.7183908191509545}
+12/27/2021 04:23:28 - INFO - codeparrot_training - Step 32015: {'lr': 0.00014424028326556938, 'samples': 16392192, 'steps': 32015, 'batch_loss/train': 0.7678525168448687}
+12/27/2021 04:23:39 - INFO - codeparrot_training - Step 32016: {'lr': 0.00014422600031802074, 'samples': 16392704, 'steps': 32016, 'batch_loss/train': 0.7479820968583226}
+12/27/2021 04:23:50 - INFO - codeparrot_training - Step 32017: {'lr': 0.0001442117177909896, 'samples': 16393216, 'steps': 32017, 'batch_loss/train': 0.7566901003010571}
+12/27/2021 04:24:00 - INFO - codeparrot_training - Step 32018: {'lr': 0.00014419743568453268, 'samples': 16393728, 'steps': 32018, 'batch_loss/train': 0.8056121943518519}
+12/27/2021 04:24:13 - INFO - codeparrot_training - Step 32019: {'lr': 0.0001441831539987069, 'samples': 16394240, 'steps': 32019, 'batch_loss/train': 0.7711253399029374}
+12/27/2021 04:24:24 - INFO - codeparrot_training - Step 32020: {'lr': 0.0001441688727335689, 'samples': 16394752, 'steps': 32020, 'batch_loss/train': 0.6398999774828553}
+12/27/2021 04:24:34 - INFO - codeparrot_training - Step 32021: {'lr': 0.00014415459188917546, 'samples': 16395264, 'steps': 32021, 'batch_loss/train': 1.1589857544749975}
+12/27/2021 04:24:47 - INFO - codeparrot_training - Step 32022: {'lr': 0.00014414031146558343, 'samples': 16395776, 'steps': 32022, 'batch_loss/train': 0.7305793170817196}
+12/27/2021 04:24:57 - INFO - codeparrot_training - Step 32023: {'lr': 0.00014412603146284953, 'samples': 16396288, 'steps': 32023, 'batch_loss/train': 0.7443191993515939}
+12/27/2021 04:25:08 - INFO - codeparrot_training - Step 32024: {'lr': 0.00014411175188103068, 'samples': 16396800, 'steps': 32024, 'batch_loss/train': 0.614909537951462}
+12/27/2021 04:25:21 - INFO - codeparrot_training - Step 32025: {'lr': 0.0001440974727201833, 'samples': 16397312, 'steps': 32025, 'batch_loss/train': 0.7050760970450938}
+12/27/2021 04:25:32 - INFO - codeparrot_training - Step 32026: {'lr': 0.0001440831939803646, 'samples': 16397824, 'steps': 32026, 'batch_loss/train': 1.2226259396411479}
+12/27/2021 04:25:42 - INFO - codeparrot_training - Step 32027: {'lr': 0.00014406891566163103, 'samples': 16398336, 'steps': 32027, 'batch_loss/train': 0.4699362368846778}
+12/27/2021 04:25:53 - INFO - codeparrot_training - Step 32028: {'lr': 0.00014405463776403943, 'samples': 16398848, 'steps': 32028, 'batch_loss/train': 0.7054315218701959}
+12/27/2021 04:26:05 - INFO - codeparrot_training - Step 32029: {'lr': 0.00014404036028764662, 'samples': 16399360, 'steps': 32029, 'batch_loss/train': 0.8305226294323802}
+12/27/2021 04:26:15 - INFO - codeparrot_training - Step 32030: {'lr': 0.0001440260832325093, 'samples': 16399872, 'steps': 32030, 'batch_loss/train': 0.7652666755020618}
+12/27/2021 04:26:26 - INFO - codeparrot_training - Step 32031: {'lr': 0.00014401180659868423, 'samples': 16400384, 'steps': 32031, 'batch_loss/train': 0.797881587408483}
+12/27/2021 04:26:38 - INFO - codeparrot_training - Step 32032: {'lr': 0.00014399753038622825, 'samples': 16400896, 'steps': 32032, 'batch_loss/train': 0.8490724666044116}
+12/27/2021 04:26:49 - INFO - codeparrot_training - Step 32033: {'lr': 0.00014398325459519807, 'samples': 16401408, 'steps': 32033, 'batch_loss/train': 0.7470477148890495}
+12/27/2021 04:26:59 - INFO - codeparrot_training - Step 32034: {'lr': 0.00014396897922565042, 'samples': 16401920, 'steps': 32034, 'batch_loss/train': 0.6756067825481296}
+12/27/2021 04:27:12 - INFO - codeparrot_training - Step 32035: {'lr': 0.00014395470427764218, 'samples': 16402432, 'steps': 32035, 'batch_loss/train': 0.6628507194109261}
+12/27/2021 04:27:23 - INFO - codeparrot_training - Step 32036: {'lr': 0.00014394042975122978, 'samples': 16402944, 'steps': 32036, 'batch_loss/train': 0.7749318163841963}
+12/27/2021 04:27:33 - INFO - codeparrot_training - Step 32037: {'lr': 0.00014392615564647027, 'samples': 16403456, 'steps': 32037, 'batch_loss/train': 0.6599286147393286}
+12/27/2021 04:27:44 - INFO - codeparrot_training - Step 32038: {'lr': 0.00014391188196342044, 'samples': 16403968, 'steps': 32038, 'batch_loss/train': 0.7620538743212819}
+12/27/2021 04:27:56 - INFO - codeparrot_training - Step 32039: {'lr': 0.0001438976087021368, 'samples': 16404480, 'steps': 32039, 'batch_loss/train': 0.7309103289153427}
+12/27/2021 04:28:07 - INFO - codeparrot_training - Step 32040: {'lr': 0.0001438833358626761, 'samples': 16404992, 'steps': 32040, 'batch_loss/train': 0.7300708154216409}
+12/27/2021 04:28:17 - INFO - codeparrot_training - Step 32041: {'lr': 0.00014386906344509542, 'samples': 16405504, 'steps': 32041, 'batch_loss/train': 0.8374668788164854}
+12/27/2021 04:28:30 - INFO - codeparrot_training - Step 32042: {'lr': 0.00014385479144945112, 'samples': 16406016, 'steps': 32042, 'batch_loss/train': 0.9623431181535125}
+12/27/2021 04:28:40 - INFO - codeparrot_training - Step 32043: {'lr': 0.00014384051987580016, 'samples': 16406528, 'steps': 32043, 'batch_loss/train': 0.7005334938876331}
+12/27/2021 04:28:51 - INFO - codeparrot_training - Step 32044: {'lr': 0.00014382624872419914, 'samples': 16407040, 'steps': 32044, 'batch_loss/train': 0.6849117111414671}
+12/27/2021 04:29:03 - INFO - codeparrot_training - Step 32045: {'lr': 0.00014381197799470492, 'samples': 16407552, 'steps': 32045, 'batch_loss/train': 0.8269471779931337}
+12/27/2021 04:29:14 - INFO - codeparrot_training - Step 32046: {'lr': 0.00014379770768737412, 'samples': 16408064, 'steps': 32046, 'batch_loss/train': 0.6840331447310746}
+12/27/2021 04:29:25 - INFO - codeparrot_training - Step 32047: {'lr': 0.00014378343780226357, 'samples': 16408576, 'steps': 32047, 'batch_loss/train': 0.7290927558206022}
+12/27/2021 04:29:35 - INFO - codeparrot_training - Step 32048: {'lr': 0.00014376916833942999, 'samples': 16409088, 'steps': 32048, 'batch_loss/train': 0.6814772132784128}
+12/27/2021 04:29:49 - INFO - codeparrot_training - Step 32049: {'lr': 0.00014375489929893004, 'samples': 16409600, 'steps': 32049, 'batch_loss/train': 0.7796170525252819}
+12/27/2021 04:30:00 - INFO - codeparrot_training - Step 32050: {'lr': 0.0001437406306808206, 'samples': 16410112, 'steps': 32050, 'batch_loss/train': 0.7001647190190852}
+12/27/2021 04:30:10 - INFO - codeparrot_training - Step 32051: {'lr': 0.00014372636248515813, 'samples': 16410624, 'steps': 32051, 'batch_loss/train': 0.6083197426050901}
+12/27/2021 04:30:22 - INFO - codeparrot_training - Step 32052: {'lr': 0.00014371209471199966, 'samples': 16411136, 'steps': 32052, 'batch_loss/train': 0.7529731539543718}
+12/27/2021 04:30:33 - INFO - codeparrot_training - Step 32053: {'lr': 0.0001436978273614017, 'samples': 16411648, 'steps': 32053, 'batch_loss/train': 0.5923964397516102}
+12/27/2021 04:30:43 - INFO - codeparrot_training - Step 32054: {'lr': 0.00014368356043342105, 'samples': 16412160, 'steps': 32054, 'batch_loss/train': 0.7596370121464133}
+12/27/2021 04:30:54 - INFO - codeparrot_training - Step 32055: {'lr': 0.0001436692939281144, 'samples': 16412672, 'steps': 32055, 'batch_loss/train': 0.726387204718776}
+12/27/2021 04:31:06 - INFO - codeparrot_training - Step 32056: {'lr': 0.0001436550278455385, 'samples': 16413184, 'steps': 32056, 'batch_loss/train': 1.0850694347172976}
+12/27/2021 04:31:17 - INFO - codeparrot_training - Step 32057: {'lr': 0.00014364076218575006, 'samples': 16413696, 'steps': 32057, 'batch_loss/train': 0.6881679128855467}
+12/27/2021 04:31:27 - INFO - codeparrot_training - Step 32058: {'lr': 0.00014362649694880575, 'samples': 16414208, 'steps': 32058, 'batch_loss/train': 0.7856850964017212}
+12/27/2021 04:31:40 - INFO - codeparrot_training - Step 32059: {'lr': 0.0001436122321347624, 'samples': 16414720, 'steps': 32059, 'batch_loss/train': 0.7129621653584763}
+12/27/2021 04:31:51 - INFO - codeparrot_training - Step 32060: {'lr': 0.00014359796774367656, 'samples': 16415232, 'steps': 32060, 'batch_loss/train': 0.7604674687609076}
+12/27/2021 04:32:01 - INFO - codeparrot_training - Step 32061: {'lr': 0.00014358370377560517, 'samples': 16415744, 'steps': 32061, 'batch_loss/train': 0.7428207723423839}
+12/27/2021 04:32:14 - INFO - codeparrot_training - Step 32062: {'lr': 0.0001435694402306046, 'samples': 16416256, 'steps': 32062, 'batch_loss/train': 0.6768989665433764}
+12/27/2021 04:32:24 - INFO - codeparrot_training - Step 32063: {'lr': 0.00014355517710873183, 'samples': 16416768, 'steps': 32063, 'batch_loss/train': 0.7924026491236873}
+12/27/2021 04:32:35 - INFO - codeparrot_training - Step 32064: {'lr': 0.00014354091441004359, 'samples': 16417280, 'steps': 32064, 'batch_loss/train': 0.7453712224960327}
+12/27/2021 04:32:48 - INFO - codeparrot_training - Step 32065: {'lr': 0.00014352665213459637, 'samples': 16417792, 'steps': 32065, 'batch_loss/train': 0.8447694364003837}
+12/27/2021 04:32:58 - INFO - codeparrot_training - Step 32066: {'lr': 0.0001435123902824469, 'samples': 16418304, 'steps': 32066, 'batch_loss/train': 0.9305233092163689}
+12/27/2021 04:33:09 - INFO - codeparrot_training - Step 32067: {'lr': 0.0001434981288536521, 'samples': 16418816, 'steps': 32067, 'batch_loss/train': 0.7175712501630187}
+12/27/2021 04:33:20 - INFO - codeparrot_training - Step 32068: {'lr': 0.00014348386784826848, 'samples': 16419328, 'steps': 32068, 'batch_loss/train': 0.7373849279247224}
+12/27/2021 04:33:32 - INFO - codeparrot_training - Step 32069: {'lr': 0.00014346960726635267, 'samples': 16419840, 'steps': 32069, 'batch_loss/train': 0.7547628979664296}
+12/27/2021 04:33:42 - INFO - codeparrot_training - Step 32070: {'lr': 0.0001434553471079617, 'samples': 16420352, 'steps': 32070, 'batch_loss/train': 1.294735343195498}
+12/27/2021 04:33:53 - INFO - codeparrot_training - Step 32071: {'lr': 0.00014344108737315188, 'samples': 16420864, 'steps': 32071, 'batch_loss/train': 0.6694833161309361}
+12/27/2021 04:34:05 - INFO - codeparrot_training - Step 32072: {'lr': 0.0001434268280619801, 'samples': 16421376, 'steps': 32072, 'batch_loss/train': 0.9559012735262513}
+12/27/2021 04:34:16 - INFO - codeparrot_training - Step 32073: {'lr': 0.000143412569174503, 'samples': 16421888, 'steps': 32073, 'batch_loss/train': 0.7959235669113696}
+12/27/2021 04:34:26 - INFO - codeparrot_training - Step 32074: {'lr': 0.0001433983107107773, 'samples': 16422400, 'steps': 32074, 'batch_loss/train': 0.675749787595123}
+12/27/2021 04:34:39 - INFO - codeparrot_training - Step 32075: {'lr': 0.00014338405267085965, 'samples': 16422912, 'steps': 32075, 'batch_loss/train': 0.7334698680788279}
+12/27/2021 04:34:50 - INFO - codeparrot_training - Step 32076: {'lr': 0.00014336979505480686, 'samples': 16423424, 'steps': 32076, 'batch_loss/train': 0.7126283580437303}
+12/27/2021 04:35:00 - INFO - codeparrot_training - Step 32077: {'lr': 0.0001433555378626753, 'samples': 16423936, 'steps': 32077, 'batch_loss/train': 0.759138165274635}
+12/27/2021 04:35:11 - INFO - codeparrot_training - Step 32078: {'lr': 0.00014334128109452194, 'samples': 16424448, 'steps': 32078, 'batch_loss/train': 0.7521615056321025}
+12/27/2021 04:35:23 - INFO - codeparrot_training - Step 32079: {'lr': 0.0001433270247504035, 'samples': 16424960, 'steps': 32079, 'batch_loss/train': 0.6326209069229662}
+12/27/2021 04:35:34 - INFO - codeparrot_training - Step 32080: {'lr': 0.0001433127688303764, 'samples': 16425472, 'steps': 32080, 'batch_loss/train': 0.7256203959695995}
+12/27/2021 04:35:44 - INFO - codeparrot_training - Step 32081: {'lr': 0.00014329851333449748, 'samples': 16425984, 'steps': 32081, 'batch_loss/train': 0.7578574204817414}
+12/27/2021 04:35:57 - INFO - codeparrot_training - Step 32082: {'lr': 0.00014328425826282338, 'samples': 16426496, 'steps': 32082, 'batch_loss/train': 0.5367078290437348}
+12/27/2021 04:36:07 - INFO - codeparrot_training - Step 32083: {'lr': 0.00014327000361541076, 'samples': 16427008, 'steps': 32083, 'batch_loss/train': 0.7548322509974241}
+12/27/2021 04:36:18 - INFO - codeparrot_training - Step 32084: {'lr': 0.00014325574939231628, 'samples': 16427520, 'steps': 32084, 'batch_loss/train': 0.6794548742473125}
+12/27/2021 04:36:31 - INFO - codeparrot_training - Step 32085: {'lr': 0.00014324149559359666, 'samples': 16428032, 'steps': 32085, 'batch_loss/train': 0.6510281367227435}
+12/27/2021 04:36:41 - INFO - codeparrot_training - Step 32086: {'lr': 0.00014322724221930855, 'samples': 16428544, 'steps': 32086, 'batch_loss/train': 0.7874831389635801}
+12/27/2021 04:36:52 - INFO - codeparrot_training - Step 32087: {'lr': 0.0001432129892695086, 'samples': 16429056, 'steps': 32087, 'batch_loss/train': 0.6643449139082804}
+12/27/2021 04:37:04 - INFO - codeparrot_training - Step 32088: {'lr': 0.00014319873674425347, 'samples': 16429568, 'steps': 32088, 'batch_loss/train': 0.832916896790266}
+12/27/2021 04:37:15 - INFO - codeparrot_training - Step 32089: {'lr': 0.00014318448464359989, 'samples': 16430080, 'steps': 32089, 'batch_loss/train': 0.6767360335215926}
+12/27/2021 04:37:26 - INFO - codeparrot_training - Step 32090: {'lr': 0.00014317023296760452, 'samples': 16430592, 'steps': 32090, 'batch_loss/train': 0.6681750847492367}
+12/27/2021 04:37:36 - INFO - codeparrot_training - Step 32091: {'lr': 0.00014315598171632388, 'samples': 16431104, 'steps': 32091, 'batch_loss/train': 0.8043926213867962}
+12/27/2021 04:37:48 - INFO - codeparrot_training - Step 32092: {'lr': 0.0001431417308898146, 'samples': 16431616, 'steps': 32092, 'batch_loss/train': 0.8229221580550075}
+12/27/2021 04:37:59 - INFO - codeparrot_training - Step 32093: {'lr': 0.00014312748048813368, 'samples': 16432128, 'steps': 32093, 'batch_loss/train': 0.7497468311339617}
+12/27/2021 04:38:09 - INFO - codeparrot_training - Step 32094: {'lr': 0.0001431132305113374, 'samples': 16432640, 'steps': 32094, 'batch_loss/train': 0.7468500826507807}
+12/27/2021 04:38:22 - INFO - codeparrot_training - Step 32095: {'lr': 0.00014309898095948249, 'samples': 16433152, 'steps': 32095, 'batch_loss/train': 0.7528686467558146}
+12/27/2021 04:38:32 - INFO - codeparrot_training - Step 32096: {'lr': 0.00014308473183262589, 'samples': 16433664, 'steps': 32096, 'batch_loss/train': 0.6899444735608995}
+12/27/2021 04:38:43 - INFO - codeparrot_training - Step 32097: {'lr': 0.0001430704831308239, 'samples': 16434176, 'steps': 32097, 'batch_loss/train': 0.6677827476523817}
+12/27/2021 04:38:56 - INFO - codeparrot_training - Step 32098: {'lr': 0.00014305623485413326, 'samples': 16434688, 'steps': 32098, 'batch_loss/train': 0.8713530809618533}
+12/27/2021 04:39:06 - INFO - codeparrot_training - Step 32099: {'lr': 0.00014304198700261067, 'samples': 16435200, 'steps': 32099, 'batch_loss/train': 0.8635667869821191}
+12/27/2021 04:39:17 - INFO - codeparrot_training - Step 32100: {'lr': 0.00014302773957631276, 'samples': 16435712, 'steps': 32100, 'batch_loss/train': 0.7125907139852643}
+12/27/2021 04:39:27 - INFO - codeparrot_training - Step 32101: {'lr': 0.00014301349257529617, 'samples': 16436224, 'steps': 32101, 'batch_loss/train': 0.7214028714224696}
+12/27/2021 04:39:39 - INFO - codeparrot_training - Step 32102: {'lr': 0.00014299924599961764, 'samples': 16436736, 'steps': 32102, 'batch_loss/train': 0.7524868054315448}
+12/27/2021 04:39:50 - INFO - codeparrot_training - Step 32103: {'lr': 0.0001429849998493335, 'samples': 16437248, 'steps': 32103, 'batch_loss/train': 0.6344959632260725}
+12/27/2021 04:40:01 - INFO - codeparrot_training - Step 32104: {'lr': 0.00014297075412450072, 'samples': 16437760, 'steps': 32104, 'batch_loss/train': 0.6653016227646731}
+12/27/2021 04:40:13 - INFO - codeparrot_training - Step 32105: {'lr': 0.00014295650882517586, 'samples': 16438272, 'steps': 32105, 'batch_loss/train': 0.6578119631158188}
+12/27/2021 04:40:24 - INFO - codeparrot_training - Step 32106: {'lr': 0.00014294226395141535, 'samples': 16438784, 'steps': 32106, 'batch_loss/train': 0.7194399596191943}
+12/27/2021 04:40:35 - INFO - codeparrot_training - Step 32107: {'lr': 0.00014292801950327615, 'samples': 16439296, 'steps': 32107, 'batch_loss/train': 0.777302899514325}
+12/27/2021 04:40:47 - INFO - codeparrot_training - Step 32108: {'lr': 0.00014291377548081462, 'samples': 16439808, 'steps': 32108, 'batch_loss/train': 0.7586999703198671}
+12/27/2021 04:40:57 - INFO - codeparrot_training - Step 32109: {'lr': 0.00014289953188408746, 'samples': 16440320, 'steps': 32109, 'batch_loss/train': 0.9171146280132234}
+12/27/2021 04:41:08 - INFO - codeparrot_training - Step 32110: {'lr': 0.00014288528871315138, 'samples': 16440832, 'steps': 32110, 'batch_loss/train': 0.6477636899799109}
+12/27/2021 04:41:19 - INFO - codeparrot_training - Step 32111: {'lr': 0.0001428710459680629, 'samples': 16441344, 'steps': 32111, 'batch_loss/train': 0.662066325545311}
+12/27/2021 04:41:31 - INFO - codeparrot_training - Step 32112: {'lr': 0.0001428568036488787, 'samples': 16441856, 'steps': 32112, 'batch_loss/train': 0.7234137421473861}
+12/27/2021 04:41:41 - INFO - codeparrot_training - Step 32113: {'lr': 0.00014284256175565538, 'samples': 16442368, 'steps': 32113, 'batch_loss/train': 0.7457964213099331}
+12/27/2021 04:41:52 - INFO - codeparrot_training - Step 32114: {'lr': 0.0001428283202884496, 'samples': 16442880, 'steps': 32114, 'batch_loss/train': 0.7919500591233373}
+12/27/2021 04:42:05 - INFO - codeparrot_training - Step 32115: {'lr': 0.00014281407924731794, 'samples': 16443392, 'steps': 32115, 'batch_loss/train': 0.6608889484778047}
+12/27/2021 04:42:15 - INFO - codeparrot_training - Step 32116: {'lr': 0.00014279983863231711, 'samples': 16443904, 'steps': 32116, 'batch_loss/train': 0.6365120398113504}
+12/27/2021 04:42:26 - INFO - codeparrot_training - Step 32117: {'lr': 0.00014278559844350358, 'samples': 16444416, 'steps': 32117, 'batch_loss/train': 0.7556113145546988}
+12/27/2021 04:42:38 - INFO - codeparrot_training - Step 32118: {'lr': 0.00014277135868093392, 'samples': 16444928, 'steps': 32118, 'batch_loss/train': 0.6897818350698799}
+12/27/2021 04:42:49 - INFO - codeparrot_training - Step 32119: {'lr': 0.00014275711934466504, 'samples': 16445440, 'steps': 32119, 'batch_loss/train': 0.6941314907744527}
+12/27/2021 04:42:59 - INFO - codeparrot_training - Step 32120: {'lr': 0.00014274288043475324, 'samples': 16445952, 'steps': 32120, 'batch_loss/train': 0.7534670264576562}
+12/27/2021 04:43:10 - INFO - codeparrot_training - Step 32121: {'lr': 0.00014272864195125518, 'samples': 16446464, 'steps': 32121, 'batch_loss/train': 0.7814805838279426}
+12/27/2021 04:43:22 - INFO - codeparrot_training - Step 32122: {'lr': 0.00014271440389422774, 'samples': 16446976, 'steps': 32122, 'batch_loss/train': 0.6979315197095275}
+12/27/2021 04:43:33 - INFO - codeparrot_training - Step 32123: {'lr': 0.0001427001662637272, 'samples': 16447488, 'steps': 32123, 'batch_loss/train': 0.6089500530215446}
+12/27/2021 04:43:44 - INFO - codeparrot_training - Step 32124: {'lr': 0.0001426859290598103, 'samples': 16448000, 'steps': 32124, 'batch_loss/train': 0.7540907924994826}
+12/27/2021 04:43:56 - INFO - codeparrot_training - Step 32125: {'lr': 0.0001426716922825336, 'samples': 16448512, 'steps': 32125, 'batch_loss/train': 0.719371011480689}
+12/27/2021 04:44:06 - INFO - codeparrot_training - Step 32126: {'lr': 0.00014265745593195376, 'samples': 16449024, 'steps': 32126, 'batch_loss/train': 1.042520219925791}
+12/27/2021 04:44:17 - INFO - codeparrot_training - Step 32127: {'lr': 0.00014264322000812733, 'samples': 16449536, 'steps': 32127, 'batch_loss/train': 0.7057013250887394}
+12/27/2021 04:44:29 - INFO - codeparrot_training - Step 32128: {'lr': 0.000142628984511111, 'samples': 16450048, 'steps': 32128, 'batch_loss/train': 0.6506889648735523}
+12/27/2021 04:44:40 - INFO - codeparrot_training - Step 32129: {'lr': 0.00014261474944096109, 'samples': 16450560, 'steps': 32129, 'batch_loss/train': 0.781022671610117}
+12/27/2021 04:44:51 - INFO - codeparrot_training - Step 32130: {'lr': 0.0001426005147977345, 'samples': 16451072, 'steps': 32130, 'batch_loss/train': 0.8003670573234558}
+12/27/2021 04:45:03 - INFO - codeparrot_training - Step 32131: {'lr': 0.00014258628058148783, 'samples': 16451584, 'steps': 32131, 'batch_loss/train': 0.6593137104064226}
+12/27/2021 04:45:13 - INFO - codeparrot_training - Step 32132: {'lr': 0.00014257204679227734, 'samples': 16452096, 'steps': 32132, 'batch_loss/train': 0.7181751960888505}
+12/27/2021 04:45:24 - INFO - codeparrot_training - Step 32133: {'lr': 0.00014255781343015995, 'samples': 16452608, 'steps': 32133, 'batch_loss/train': 0.7596271568909287}
+12/27/2021 04:45:35 - INFO - codeparrot_training - Step 32134: {'lr': 0.00014254358049519216, 'samples': 16453120, 'steps': 32134, 'batch_loss/train': 0.7634360967203975}
+12/27/2021 04:45:47 - INFO - codeparrot_training - Step 32135: {'lr': 0.00014252934798743047, 'samples': 16453632, 'steps': 32135, 'batch_loss/train': 0.7818901548162103}
+12/27/2021 04:45:58 - INFO - codeparrot_training - Step 32136: {'lr': 0.0001425151159069315, 'samples': 16454144, 'steps': 32136, 'batch_loss/train': 0.8862715968862176}
+12/27/2021 04:46:09 - INFO - codeparrot_training - Step 32137: {'lr': 0.00014250088425375184, 'samples': 16454656, 'steps': 32137, 'batch_loss/train': 0.749318297021091}
+12/27/2021 04:46:21 - INFO - codeparrot_training - Step 32138: {'lr': 0.00014248665302794809, 'samples': 16455168, 'steps': 32138, 'batch_loss/train': 0.7290945509448647}
+12/27/2021 04:46:31 - INFO - codeparrot_training - Step 32139: {'lr': 0.00014247242222957678, 'samples': 16455680, 'steps': 32139, 'batch_loss/train': 0.7513828906230628}
+12/27/2021 04:46:42 - INFO - codeparrot_training - Step 32140: {'lr': 0.00014245819185869458, 'samples': 16456192, 'steps': 32140, 'batch_loss/train': 0.7510615614010021}
+12/27/2021 04:46:54 - INFO - codeparrot_training - Step 32141: {'lr': 0.00014244396191535793, 'samples': 16456704, 'steps': 32141, 'batch_loss/train': 0.7792044170200825}
+12/27/2021 04:47:05 - INFO - codeparrot_training - Step 32142: {'lr': 0.00014242973239962363, 'samples': 16457216, 'steps': 32142, 'batch_loss/train': 0.674945145030506}
+12/27/2021 04:47:16 - INFO - codeparrot_training - Step 32143: {'lr': 0.00014241550331154786, 'samples': 16457728, 'steps': 32143, 'batch_loss/train': 0.8262941930443048}
+12/27/2021 04:47:26 - INFO - codeparrot_training - Step 32144: {'lr': 0.00014240127465118754, 'samples': 16458240, 'steps': 32144, 'batch_loss/train': 0.7043214305303991}
+12/27/2021 04:47:39 - INFO - codeparrot_training - Step 32145: {'lr': 0.00014238704641859922, 'samples': 16458752, 'steps': 32145, 'batch_loss/train': 0.656287997495383}
+12/27/2021 04:47:49 - INFO - codeparrot_training - Step 32146: {'lr': 0.0001423728186138393, 'samples': 16459264, 'steps': 32146, 'batch_loss/train': 0.670390164013952}
+12/27/2021 04:48:00 - INFO - codeparrot_training - Step 32147: {'lr': 0.0001423585912369643, 'samples': 16459776, 'steps': 32147, 'batch_loss/train': 0.6942694594617933}
+12/27/2021 04:48:12 - INFO - codeparrot_training - Step 32148: {'lr': 0.0001423443642880311, 'samples': 16460288, 'steps': 32148, 'batch_loss/train': 0.7674919473938644}
+12/27/2021 04:48:23 - INFO - codeparrot_training - Step 32149: {'lr': 0.0001423301377670959, 'samples': 16460800, 'steps': 32149, 'batch_loss/train': 0.7353104525245726}
+12/27/2021 04:48:33 - INFO - codeparrot_training - Step 32150: {'lr': 0.00014231591167421549, 'samples': 16461312, 'steps': 32150, 'batch_loss/train': 0.6761416718363762}
+12/27/2021 04:48:47 - INFO - codeparrot_training - Step 32151: {'lr': 0.00014230168600944633, 'samples': 16461824, 'steps': 32151, 'batch_loss/train': 0.6971013648435473}
+12/27/2021 04:48:57 - INFO - codeparrot_training - Step 32152: {'lr': 0.00014228746077284498, 'samples': 16462336, 'steps': 32152, 'batch_loss/train': 0.752703882753849}
+12/27/2021 04:49:08 - INFO - codeparrot_training - Step 32153: {'lr': 0.00014227323596446807, 'samples': 16462848, 'steps': 32153, 'batch_loss/train': 0.7803296949714422}
+12/27/2021 04:49:18 - INFO - codeparrot_training - Step 32154: {'lr': 0.00014225901158437215, 'samples': 16463360, 'steps': 32154, 'batch_loss/train': 1.0385072557255626}
+12/27/2021 04:49:31 - INFO - codeparrot_training - Step 32155: {'lr': 0.00014224478763261356, 'samples': 16463872, 'steps': 32155, 'batch_loss/train': 0.860835547093302}
+12/27/2021 04:49:41 - INFO - codeparrot_training - Step 32156: {'lr': 0.00014223056410924906, 'samples': 16464384, 'steps': 32156, 'batch_loss/train': 0.7704247790388763}
+12/27/2021 04:49:52 - INFO - codeparrot_training - Step 32157: {'lr': 0.00014221634101433528, 'samples': 16464896, 'steps': 32157, 'batch_loss/train': 0.7543237525969744}
+12/27/2021 04:50:04 - INFO - codeparrot_training - Step 32158: {'lr': 0.0001422021183479284, 'samples': 16465408, 'steps': 32158, 'batch_loss/train': 0.8972427761182189}
+12/27/2021 04:50:15 - INFO - codeparrot_training - Step 32159: {'lr': 0.0001421878961100853, 'samples': 16465920, 'steps': 32159, 'batch_loss/train': 0.6142801374662668}
+12/27/2021 04:50:25 - INFO - codeparrot_training - Step 32160: {'lr': 0.00014217367430086254, 'samples': 16466432, 'steps': 32160, 'batch_loss/train': 0.8135367808863521}
+12/27/2021 04:50:37 - INFO - codeparrot_training - Step 32161: {'lr': 0.00014215945292031642, 'samples': 16466944, 'steps': 32161, 'batch_loss/train': 0.7092428961768746}
+12/27/2021 04:50:48 - INFO - codeparrot_training - Step 32162: {'lr': 0.00014214523196850358, 'samples': 16467456, 'steps': 32162, 'batch_loss/train': 0.6933655021712184}
+12/27/2021 04:50:58 - INFO - codeparrot_training - Step 32163: {'lr': 0.00014213101144548062, 'samples': 16467968, 'steps': 32163, 'batch_loss/train': 0.7092152631375939}
+12/27/2021 04:51:11 - INFO - codeparrot_training - Step 32164: {'lr': 0.000142116791351304, 'samples': 16468480, 'steps': 32164, 'batch_loss/train': 0.7825713781639934}
+12/27/2021 04:51:22 - INFO - codeparrot_training - Step 32165: {'lr': 0.0001421025716860303, 'samples': 16468992, 'steps': 32165, 'batch_loss/train': 0.7320784656330943}
+12/27/2021 04:51:32 - INFO - codeparrot_training - Step 32166: {'lr': 0.00014208835244971602, 'samples': 16469504, 'steps': 32166, 'batch_loss/train': 0.6672828306327574}
+12/27/2021 04:51:43 - INFO - codeparrot_training - Step 32167: {'lr': 0.0001420741336424177, 'samples': 16470016, 'steps': 32167, 'batch_loss/train': 0.8390267267823219}
+12/27/2021 04:51:56 - INFO - codeparrot_training - Step 32168: {'lr': 0.00014205991526419187, 'samples': 16470528, 'steps': 32168, 'batch_loss/train': 0.7378744222223759}
+12/27/2021 04:52:07 - INFO - codeparrot_training - Step 32169: {'lr': 0.00014204569731509508, 'samples': 16471040, 'steps': 32169, 'batch_loss/train': 0.7298314590007067}
+12/27/2021 04:52:17 - INFO - codeparrot_training - Step 32170: {'lr': 0.00014203147979518382, 'samples': 16471552, 'steps': 32170, 'batch_loss/train': 0.7943827286362648}
+12/27/2021 04:52:29 - INFO - codeparrot_training - Step 32171: {'lr': 0.00014201726270451472, 'samples': 16472064, 'steps': 32171, 'batch_loss/train': 0.6417138166725636}
+12/27/2021 04:52:40 - INFO - codeparrot_training - Step 32172: {'lr': 0.00014200304604314413, 'samples': 16472576, 'steps': 32172, 'batch_loss/train': 0.7467708699405193}
+12/27/2021 04:52:51 - INFO - codeparrot_training - Step 32173: {'lr': 0.00014198882981112854, 'samples': 16473088, 'steps': 32173, 'batch_loss/train': 0.7656828830949962}
+12/27/2021 04:53:01 - INFO - codeparrot_training - Step 32174: {'lr': 0.0001419746140085248, 'samples': 16473600, 'steps': 32174, 'batch_loss/train': 0.7040509782673325}
+12/27/2021 04:53:14 - INFO - codeparrot_training - Step 32175: {'lr': 0.0001419603986353891, 'samples': 16474112, 'steps': 32175, 'batch_loss/train': 0.7360111903399229}
+12/27/2021 04:53:25 - INFO - codeparrot_training - Step 32176: {'lr': 0.00014194618369177804, 'samples': 16474624, 'steps': 32176, 'batch_loss/train': 0.7857917854562402}
+12/27/2021 04:53:35 - INFO - codeparrot_training - Step 32177: {'lr': 0.00014193196917774818, 'samples': 16475136, 'steps': 32177, 'batch_loss/train': 0.7192990938201547}
+12/27/2021 04:53:48 - INFO - codeparrot_training - Step 32178: {'lr': 0.00014191775509335598, 'samples': 16475648, 'steps': 32178, 'batch_loss/train': 0.715227362466976}
+12/27/2021 04:53:58 - INFO - codeparrot_training - Step 32179: {'lr': 0.00014190354143865796, 'samples': 16476160, 'steps': 32179, 'batch_loss/train': 0.6661192501778714}
+12/27/2021 04:54:09 - INFO - codeparrot_training - Step 32180: {'lr': 0.0001418893282137107, 'samples': 16476672, 'steps': 32180, 'batch_loss/train': 0.7803647965192795}
+12/27/2021 04:54:22 - INFO - codeparrot_training - Step 32181: {'lr': 0.0001418751154185706, 'samples': 16477184, 'steps': 32181, 'batch_loss/train': 1.347253710089717}
+12/27/2021 04:54:33 - INFO - codeparrot_training - Step 32182: {'lr': 0.00014186090305329425, 'samples': 16477696, 'steps': 32182, 'batch_loss/train': 0.7609147471375763}
+12/27/2021 04:54:43 - INFO - codeparrot_training - Step 32183: {'lr': 0.00014184669111793818, 'samples': 16478208, 'steps': 32183, 'batch_loss/train': 0.7311585622373968}
+12/27/2021 04:54:54 - INFO - codeparrot_training - Step 32184: {'lr': 0.00014183247961255867, 'samples': 16478720, 'steps': 32184, 'batch_loss/train': 0.6708004353567958}
+12/27/2021 04:55:06 - INFO - codeparrot_training - Step 32185: {'lr': 0.00014181826853721248, 'samples': 16479232, 'steps': 32185, 'batch_loss/train': 0.7673129066824913}
+12/27/2021 04:55:17 - INFO - codeparrot_training - Step 32186: {'lr': 0.00014180405789195608, 'samples': 16479744, 'steps': 32186, 'batch_loss/train': 0.7414378123939969}
+12/27/2021 04:55:27 - INFO - codeparrot_training - Step 32187: {'lr': 0.00014178984767684578, 'samples': 16480256, 'steps': 32187, 'batch_loss/train': 0.7140732952393591}
+12/27/2021 04:55:39 - INFO - codeparrot_training - Step 32188: {'lr': 0.0001417756378919382, 'samples': 16480768, 'steps': 32188, 'batch_loss/train': 0.7050739550031722}
+12/27/2021 04:55:50 - INFO - codeparrot_training - Step 32189: {'lr': 0.00014176142853728984, 'samples': 16481280, 'steps': 32189, 'batch_loss/train': 0.7750973305664957}
+12/27/2021 04:56:00 - INFO - codeparrot_training - Step 32190: {'lr': 0.00014174721961295717, 'samples': 16481792, 'steps': 32190, 'batch_loss/train': 0.6859108693897724}
+12/27/2021 04:56:13 - INFO - codeparrot_training - Step 32191: {'lr': 0.00014173301111899668, 'samples': 16482304, 'steps': 32191, 'batch_loss/train': 0.7529450310394168}
+12/27/2021 04:56:24 - INFO - codeparrot_training - Step 32192: {'lr': 0.0001417188030554648, 'samples': 16482816, 'steps': 32192, 'batch_loss/train': 0.8447713954374194}
+12/27/2021 04:56:34 - INFO - codeparrot_training - Step 32193: {'lr': 0.00014170459542241814, 'samples': 16483328, 'steps': 32193, 'batch_loss/train': 0.741950151976198}
+12/27/2021 04:56:45 - INFO - codeparrot_training - Step 32194: {'lr': 0.0001416903882199131, 'samples': 16483840, 'steps': 32194, 'batch_loss/train': 0.7032777639105916}
+12/27/2021 04:56:57 - INFO - codeparrot_training - Step 32195: {'lr': 0.00014167618144800617, 'samples': 16484352, 'steps': 32195, 'batch_loss/train': 0.8060387915465981}
+12/27/2021 04:57:08 - INFO - codeparrot_training - Step 32196: {'lr': 0.00014166197510675384, 'samples': 16484864, 'steps': 32196, 'batch_loss/train': 0.6959010171703994}
+12/27/2021 04:57:18 - INFO - codeparrot_training - Step 32197: {'lr': 0.0001416477691962127, 'samples': 16485376, 'steps': 32197, 'batch_loss/train': 0.7002528982702643}
+12/27/2021 04:57:30 - INFO - codeparrot_training - Step 32198: {'lr': 0.00014163356371643904, 'samples': 16485888, 'steps': 32198, 'batch_loss/train': 0.8412300683557987}
+12/27/2021 04:57:41 - INFO - codeparrot_training - Step 32199: {'lr': 0.00014161935866748926, 'samples': 16486400, 'steps': 32199, 'batch_loss/train': 0.7334463535808027}
+12/27/2021 04:57:52 - INFO - codeparrot_training - Step 32200: {'lr': 0.00014160515404942024, 'samples': 16486912, 'steps': 32200, 'batch_loss/train': 0.7032351987436414}
+12/27/2021 04:58:04 - INFO - codeparrot_training - Step 32201: {'lr': 0.00014159094986228803, 'samples': 16487424, 'steps': 32201, 'batch_loss/train': 0.7727161776274443}
+12/27/2021 04:58:14 - INFO - codeparrot_training - Step 32202: {'lr': 0.00014157674610614936, 'samples': 16487936, 'steps': 32202, 'batch_loss/train': 0.652889487799257}
+12/27/2021 04:58:25 - INFO - codeparrot_training - Step 32203: {'lr': 0.00014156254278106057, 'samples': 16488448, 'steps': 32203, 'batch_loss/train': 0.7186842178925872}
+12/27/2021 04:58:38 - INFO - codeparrot_training - Step 32204: {'lr': 0.00014154833988707817, 'samples': 16488960, 'steps': 32204, 'batch_loss/train': 0.7048428151756525}
+12/27/2021 04:58:48 - INFO - codeparrot_training - Step 32205: {'lr': 0.00014153413742425857, 'samples': 16489472, 'steps': 32205, 'batch_loss/train': 0.7167224232107401}
+12/27/2021 04:58:59 - INFO - codeparrot_training - Step 32206: {'lr': 0.00014151993539265835, 'samples': 16489984, 'steps': 32206, 'batch_loss/train': 0.6723442273214459}
+12/27/2021 04:59:09 - INFO - codeparrot_training - Step 32207: {'lr': 0.00014150573379233386, 'samples': 16490496, 'steps': 32207, 'batch_loss/train': 0.7613435061648488}
+12/27/2021 04:59:22 - INFO - codeparrot_training - Step 32208: {'lr': 0.00014149153262334164, 'samples': 16491008, 'steps': 32208, 'batch_loss/train': 0.7208065101876855}
+12/27/2021 04:59:32 - INFO - codeparrot_training - Step 32209: {'lr': 0.0001414773318857382, 'samples': 16491520, 'steps': 32209, 'batch_loss/train': 0.7008938565850258}
+12/27/2021 04:59:43 - INFO - codeparrot_training - Step 32210: {'lr': 0.00014146313157957968, 'samples': 16492032, 'steps': 32210, 'batch_loss/train': 0.7205646671354771}
+12/27/2021 04:59:56 - INFO - codeparrot_training - Step 32211: {'lr': 0.00014144893170492292, 'samples': 16492544, 'steps': 32211, 'batch_loss/train': 0.6695821348112077}
+12/27/2021 05:00:06 - INFO - codeparrot_training - Step 32212: {'lr': 0.0001414347322618243, 'samples': 16493056, 'steps': 32212, 'batch_loss/train': 0.6424560244195163}
+12/27/2021 05:00:17 - INFO - codeparrot_training - Step 32213: {'lr': 0.0001414205332503401, 'samples': 16493568, 'steps': 32213, 'batch_loss/train': 0.6752178238821216}
+12/27/2021 05:00:29 - INFO - codeparrot_training - Step 32214: {'lr': 0.00014140633467052676, 'samples': 16494080, 'steps': 32214, 'batch_loss/train': 0.673171253874898}
+12/27/2021 05:00:39 - INFO - codeparrot_training - Step 32215: {'lr': 0.000141392136522441, 'samples': 16494592, 'steps': 32215, 'batch_loss/train': 0.8013190235942602}
+12/27/2021 05:00:50 - INFO - codeparrot_training - Step 32216: {'lr': 0.00014137793880613904, 'samples': 16495104, 'steps': 32216, 'batch_loss/train': 0.7517765467055142}
+12/27/2021 05:01:01 - INFO - codeparrot_training - Step 32217: {'lr': 0.00014136374152167735, 'samples': 16495616, 'steps': 32217, 'batch_loss/train': 0.7360608587041497}
+12/27/2021 05:01:13 - INFO - codeparrot_training - Step 32218: {'lr': 0.00014134954466911242, 'samples': 16496128, 'steps': 32218, 'batch_loss/train': 0.8172041983343661}
+12/27/2021 05:01:23 - INFO - codeparrot_training - Step 32219: {'lr': 0.0001413353482485007, 'samples': 16496640, 'steps': 32219, 'batch_loss/train': 0.5885238312184811}
+12/27/2021 05:01:34 - INFO - codeparrot_training - Step 32220: {'lr': 0.00014132115225989856, 'samples': 16497152, 'steps': 32220, 'batch_loss/train': 0.7939993436448276}
+12/27/2021 05:01:47 - INFO - codeparrot_training - Step 32221: {'lr': 0.0001413069567033625, 'samples': 16497664, 'steps': 32221, 'batch_loss/train': 0.6865488516632468}
+12/27/2021 05:01:57 - INFO - codeparrot_training - Step 32222: {'lr': 0.00014129276157894894, 'samples': 16498176, 'steps': 32222, 'batch_loss/train': 0.7393544414080679}
+12/27/2021 05:02:08 - INFO - codeparrot_training - Step 32223: {'lr': 0.0001412785668867143, 'samples': 16498688, 'steps': 32223, 'batch_loss/train': 0.66373236104846}
+12/27/2021 05:02:20 - INFO - codeparrot_training - Step 32224: {'lr': 0.00014126437262671515, 'samples': 16499200, 'steps': 32224, 'batch_loss/train': 0.6117088152095675}
+12/27/2021 05:02:31 - INFO - codeparrot_training - Step 32225: {'lr': 0.0001412501787990076, 'samples': 16499712, 'steps': 32225, 'batch_loss/train': 0.7418463006615639}
+12/27/2021 05:02:42 - INFO - codeparrot_training - Step 32226: {'lr': 0.00014123598540364846, 'samples': 16500224, 'steps': 32226, 'batch_loss/train': 0.5456150131067261}
+12/27/2021 05:02:54 - INFO - codeparrot_training - Step 32227: {'lr': 0.00014122179244069387, 'samples': 16500736, 'steps': 32227, 'batch_loss/train': 0.7089443574659526}
+12/27/2021 05:03:05 - INFO - codeparrot_training - Step 32228: {'lr': 0.0001412075999102004, 'samples': 16501248, 'steps': 32228, 'batch_loss/train': 0.8090895470231771}
+12/27/2021 05:03:16 - INFO - codeparrot_training - Step 32229: {'lr': 0.00014119340781222438, 'samples': 16501760, 'steps': 32229, 'batch_loss/train': 0.7077463157474995}
+12/27/2021 05:03:26 - INFO - codeparrot_training - Step 32230: {'lr': 0.00014117921614682227, 'samples': 16502272, 'steps': 32230, 'batch_loss/train': 0.7505989549681544}
+12/27/2021 05:03:38 - INFO - codeparrot_training - Step 32231: {'lr': 0.0001411650249140506, 'samples': 16502784, 'steps': 32231, 'batch_loss/train': 0.6914443150162697}
+12/27/2021 05:03:49 - INFO - codeparrot_training - Step 32232: {'lr': 0.00014115083411396563, 'samples': 16503296, 'steps': 32232, 'batch_loss/train': 0.6876529278233647}
+12/27/2021 05:03:59 - INFO - codeparrot_training - Step 32233: {'lr': 0.00014113664374662384, 'samples': 16503808, 'steps': 32233, 'batch_loss/train': 0.7608127021230757}
+12/27/2021 05:04:12 - INFO - codeparrot_training - Step 32234: {'lr': 0.00014112245381208167, 'samples': 16504320, 'steps': 32234, 'batch_loss/train': 0.8000100161880255}
+12/27/2021 05:04:22 - INFO - codeparrot_training - Step 32235: {'lr': 0.00014110826431039562, 'samples': 16504832, 'steps': 32235, 'batch_loss/train': 0.6675173491239548}
+12/27/2021 05:04:33 - INFO - codeparrot_training - Step 32236: {'lr': 0.00014109407524162177, 'samples': 16505344, 'steps': 32236, 'batch_loss/train': 0.6243846314027905}
+12/27/2021 05:04:45 - INFO - codeparrot_training - Step 32237: {'lr': 0.00014107988660581688, 'samples': 16505856, 'steps': 32237, 'batch_loss/train': 0.6929899465758353}
+12/27/2021 05:04:56 - INFO - codeparrot_training - Step 32238: {'lr': 0.0001410656984030373, 'samples': 16506368, 'steps': 32238, 'batch_loss/train': 0.753618320915848}
+12/27/2021 05:05:06 - INFO - codeparrot_training - Step 32239: {'lr': 0.00014105151063333933, 'samples': 16506880, 'steps': 32239, 'batch_loss/train': 0.6955355550162494}
+12/27/2021 05:05:18 - INFO - codeparrot_training - Step 32240: {'lr': 0.00014103732329677927, 'samples': 16507392, 'steps': 32240, 'batch_loss/train': 0.6712037334218621}
+12/27/2021 05:05:29 - INFO - codeparrot_training - Step 32241: {'lr': 0.00014102313639341386, 'samples': 16507904, 'steps': 32241, 'batch_loss/train': 0.6204511274117976}
+12/27/2021 05:05:40 - INFO - codeparrot_training - Step 32242: {'lr': 0.00014100894992329923, 'samples': 16508416, 'steps': 32242, 'batch_loss/train': 0.6209729824913666}
+12/27/2021 05:05:50 - INFO - codeparrot_training - Step 32243: {'lr': 0.00014099476388649187, 'samples': 16508928, 'steps': 32243, 'batch_loss/train': 0.7053787927143276}
+12/27/2021 05:06:03 - INFO - codeparrot_training - Step 32244: {'lr': 0.00014098057828304818, 'samples': 16509440, 'steps': 32244, 'batch_loss/train': 0.7640824615955353}
+12/27/2021 05:06:14 - INFO - codeparrot_training - Step 32245: {'lr': 0.00014096639311302452, 'samples': 16509952, 'steps': 32245, 'batch_loss/train': 0.7382045714184642}
+12/27/2021 05:06:24 - INFO - codeparrot_training - Step 32246: {'lr': 0.00014095220837647733, 'samples': 16510464, 'steps': 32246, 'batch_loss/train': 0.6433682451024652}
+12/27/2021 05:06:36 - INFO - codeparrot_training - Step 32247: {'lr': 0.000140938024073463, 'samples': 16510976, 'steps': 32247, 'batch_loss/train': 0.7096298718824983}
+12/27/2021 05:06:47 - INFO - codeparrot_training - Step 32248: {'lr': 0.00014092384020403787, 'samples': 16511488, 'steps': 32248, 'batch_loss/train': 0.6340147789160255}
+12/27/2021 05:06:58 - INFO - codeparrot_training - Step 32249: {'lr': 0.00014090965676825836, 'samples': 16512000, 'steps': 32249, 'batch_loss/train': 0.7777726221829653}
+12/27/2021 05:07:10 - INFO - codeparrot_training - Step 32250: {'lr': 0.000140895473766181, 'samples': 16512512, 'steps': 32250, 'batch_loss/train': 0.6772524868138134}
+12/27/2021 05:07:21 - INFO - codeparrot_training - Step 32251: {'lr': 0.0001408812911978618, 'samples': 16513024, 'steps': 32251, 'batch_loss/train': 0.683428649790585}
+12/27/2021 05:07:32 - INFO - codeparrot_training - Step 32252: {'lr': 0.00014086710906335763, 'samples': 16513536, 'steps': 32252, 'batch_loss/train': 0.7173400986939669}
+12/27/2021 05:07:42 - INFO - codeparrot_training - Step 32253: {'lr': 0.00014085292736272452, 'samples': 16514048, 'steps': 32253, 'batch_loss/train': 0.851617312990129}
+12/27/2021 05:07:54 - INFO - codeparrot_training - Step 32254: {'lr': 0.00014083874609601882, 'samples': 16514560, 'steps': 32254, 'batch_loss/train': 0.664437529630959}
+12/27/2021 05:08:05 - INFO - codeparrot_training - Step 32255: {'lr': 0.00014082456526329728, 'samples': 16515072, 'steps': 32255, 'batch_loss/train': 0.8386290315538645}
+12/27/2021 05:08:16 - INFO - codeparrot_training - Step 32256: {'lr': 0.00014081038486461595, 'samples': 16515584, 'steps': 32256, 'batch_loss/train': 0.7970191591884941}
+12/27/2021 05:08:28 - INFO - codeparrot_training - Step 32257: {'lr': 0.00014079620490003127, 'samples': 16516096, 'steps': 32257, 'batch_loss/train': 0.8231175349210389}
+12/27/2021 05:08:38 - INFO - codeparrot_training - Step 32258: {'lr': 0.00014078202536959967, 'samples': 16516608, 'steps': 32258, 'batch_loss/train': 0.6344115226529539}
+12/27/2021 05:08:49 - INFO - codeparrot_training - Step 32259: {'lr': 0.0001407678462733775, 'samples': 16517120, 'steps': 32259, 'batch_loss/train': 0.6986809694208205}
+12/27/2021 05:09:02 - INFO - codeparrot_training - Step 32260: {'lr': 0.00014075366761142111, 'samples': 16517632, 'steps': 32260, 'batch_loss/train': 0.6686365585774183}
+12/27/2021 05:09:12 - INFO - codeparrot_training - Step 32261: {'lr': 0.000140739489383787, 'samples': 16518144, 'steps': 32261, 'batch_loss/train': 0.7574848776566796}
+12/27/2021 05:09:23 - INFO - codeparrot_training - Step 32262: {'lr': 0.0001407253115905312, 'samples': 16518656, 'steps': 32262, 'batch_loss/train': 0.6909284089924768}
+12/27/2021 05:09:35 - INFO - codeparrot_training - Step 32263: {'lr': 0.00014071113423171045, 'samples': 16519168, 'steps': 32263, 'batch_loss/train': 0.7538660462014377}
+12/27/2021 05:09:46 - INFO - codeparrot_training - Step 32264: {'lr': 0.000140696957307381, 'samples': 16519680, 'steps': 32264, 'batch_loss/train': 0.6747748528141528}
+12/27/2021 05:09:56 - INFO - codeparrot_training - Step 32265: {'lr': 0.00014068278081759915, 'samples': 16520192, 'steps': 32265, 'batch_loss/train': 0.7267934088595212}
+12/27/2021 05:10:07 - INFO - codeparrot_training - Step 32266: {'lr': 0.00014066860476242115, 'samples': 16520704, 'steps': 32266, 'batch_loss/train': 0.653785171394702}
+12/27/2021 05:10:20 - INFO - codeparrot_training - Step 32267: {'lr': 0.0001406544291419037, 'samples': 16521216, 'steps': 32267, 'batch_loss/train': 0.7216460141353309}
+12/27/2021 05:10:31 - INFO - codeparrot_training - Step 32268: {'lr': 0.00014064025395610285, 'samples': 16521728, 'steps': 32268, 'batch_loss/train': 0.6871995311230421}
+12/27/2021 05:10:41 - INFO - codeparrot_training - Step 32269: {'lr': 0.00014062607920507499, 'samples': 16522240, 'steps': 32269, 'batch_loss/train': 0.673477269243449}
+12/27/2021 05:10:53 - INFO - codeparrot_training - Step 32270: {'lr': 0.00014061190488887668, 'samples': 16522752, 'steps': 32270, 'batch_loss/train': 0.6558797525940463}
+12/27/2021 05:11:04 - INFO - codeparrot_training - Step 32271: {'lr': 0.00014059773100756406, 'samples': 16523264, 'steps': 32271, 'batch_loss/train': 1.4619604954496026}
+12/27/2021 05:11:14 - INFO - codeparrot_training - Step 32272: {'lr': 0.00014058355756119356, 'samples': 16523776, 'steps': 32272, 'batch_loss/train': 0.7344227954745293}
+12/27/2021 05:11:26 - INFO - codeparrot_training - Step 32273: {'lr': 0.00014056938454982149, 'samples': 16524288, 'steps': 32273, 'batch_loss/train': 0.8013887545093894}
+12/27/2021 05:11:37 - INFO - codeparrot_training - Step 32274: {'lr': 0.00014055521197350426, 'samples': 16524800, 'steps': 32274, 'batch_loss/train': 0.7755100411595777}
+12/27/2021 05:11:48 - INFO - codeparrot_training - Step 32275: {'lr': 0.00014054103983229818, 'samples': 16525312, 'steps': 32275, 'batch_loss/train': 0.8104966445825994}
+12/27/2021 05:11:58 - INFO - codeparrot_training - Step 32276: {'lr': 0.0001405268681262597, 'samples': 16525824, 'steps': 32276, 'batch_loss/train': 0.6896214940352365}
+12/27/2021 05:12:11 - INFO - codeparrot_training - Step 32277: {'lr': 0.00014051269685544485, 'samples': 16526336, 'steps': 32277, 'batch_loss/train': 0.7028019819408655}
+12/27/2021 05:12:21 - INFO - codeparrot_training - Step 32278: {'lr': 0.00014049852601991038, 'samples': 16526848, 'steps': 32278, 'batch_loss/train': 0.7507393141277134}
+12/27/2021 05:12:32 - INFO - codeparrot_training - Step 32279: {'lr': 0.0001404843556197123, 'samples': 16527360, 'steps': 32279, 'batch_loss/train': 0.6852635028772056}
+12/27/2021 05:12:45 - INFO - codeparrot_training - Step 32280: {'lr': 0.000140470185654907, 'samples': 16527872, 'steps': 32280, 'batch_loss/train': 0.7707140631973743}
+12/27/2021 05:12:55 - INFO - codeparrot_training - Step 32281: {'lr': 0.0001404560161255511, 'samples': 16528384, 'steps': 32281, 'batch_loss/train': 0.7048487275606021}
+12/27/2021 05:13:06 - INFO - codeparrot_training - Step 32282: {'lr': 0.00014044184703170058, 'samples': 16528896, 'steps': 32282, 'batch_loss/train': 0.6588018386391923}
+12/27/2021 05:13:18 - INFO - codeparrot_training - Step 32283: {'lr': 0.0001404276783734119, 'samples': 16529408, 'steps': 32283, 'batch_loss/train': 0.6386478452477604}
+12/27/2021 05:13:29 - INFO - codeparrot_training - Step 32284: {'lr': 0.00014041351015074143, 'samples': 16529920, 'steps': 32284, 'batch_loss/train': 0.6294620789121836}
+12/27/2021 05:13:39 - INFO - codeparrot_training - Step 32285: {'lr': 0.00014039934236374546, 'samples': 16530432, 'steps': 32285, 'batch_loss/train': 0.5020782520296052}
+12/27/2021 05:13:50 - INFO - codeparrot_training - Step 32286: {'lr': 0.0001403851750124803, 'samples': 16530944, 'steps': 32286, 'batch_loss/train': 0.8720851298421621}
+12/27/2021 05:14:02 - INFO - codeparrot_training - Step 32287: {'lr': 0.00014037100809700243, 'samples': 16531456, 'steps': 32287, 'batch_loss/train': 0.7483430681750178}
+12/27/2021 05:14:13 - INFO - codeparrot_training - Step 32288: {'lr': 0.0001403568416173678, 'samples': 16531968, 'steps': 32288, 'batch_loss/train': 0.6981320797931403}
+12/27/2021 05:14:23 - INFO - codeparrot_training - Step 32289: {'lr': 0.0001403426755736331, 'samples': 16532480, 'steps': 32289, 'batch_loss/train': 0.7333119437098503}
+12/27/2021 05:14:36 - INFO - codeparrot_training - Step 32290: {'lr': 0.0001403285099658546, 'samples': 16532992, 'steps': 32290, 'batch_loss/train': 0.754728065803647}
+12/27/2021 05:14:47 - INFO - codeparrot_training - Step 32291: {'lr': 0.00014031434479408833, 'samples': 16533504, 'steps': 32291, 'batch_loss/train': 0.731094847433269}
+12/27/2021 05:14:57 - INFO - codeparrot_training - Step 32292: {'lr': 0.0001403001800583909, 'samples': 16534016, 'steps': 32292, 'batch_loss/train': 0.6082432887051255}
+12/27/2021 05:15:10 - INFO - codeparrot_training - Step 32293: {'lr': 0.00014028601575881867, 'samples': 16534528, 'steps': 32293, 'batch_loss/train': 0.7096018446609378}
+12/27/2021 05:15:20 - INFO - codeparrot_training - Step 32294: {'lr': 0.00014027185189542768, 'samples': 16535040, 'steps': 32294, 'batch_loss/train': 0.6473485995084047}
+12/27/2021 05:15:31 - INFO - codeparrot_training - Step 32295: {'lr': 0.0001402576884682743, 'samples': 16535552, 'steps': 32295, 'batch_loss/train': 0.8452915567904711}
+12/27/2021 05:15:41 - INFO - codeparrot_training - Step 32296: {'lr': 0.0001402435254774151, 'samples': 16536064, 'steps': 32296, 'batch_loss/train': 0.788308777846396}
+12/27/2021 05:15:54 - INFO - codeparrot_training - Step 32297: {'lr': 0.0001402293629229061, 'samples': 16536576, 'steps': 32297, 'batch_loss/train': 0.7010481357574463}
+12/27/2021 05:16:05 - INFO - codeparrot_training - Step 32298: {'lr': 0.0001402152008048037, 'samples': 16537088, 'steps': 32298, 'batch_loss/train': 0.7920894725248218}
+12/27/2021 05:16:16 - INFO - codeparrot_training - Step 32299: {'lr': 0.00014020103912316424, 'samples': 16537600, 'steps': 32299, 'batch_loss/train': 0.6913965749554336}
+12/27/2021 05:16:28 - INFO - codeparrot_training - Step 32300: {'lr': 0.00014018687787804396, 'samples': 16538112, 'steps': 32300, 'batch_loss/train': 0.7396945971995592}
+12/27/2021 05:16:39 - INFO - codeparrot_training - Step 32301: {'lr': 0.0001401727170694992, 'samples': 16538624, 'steps': 32301, 'batch_loss/train': 0.6422419087029994}
+12/27/2021 05:16:49 - INFO - codeparrot_training - Step 32302: {'lr': 0.00014015855669758634, 'samples': 16539136, 'steps': 32302, 'batch_loss/train': 0.8203388601541519}
+12/27/2021 05:17:02 - INFO - codeparrot_training - Step 32303: {'lr': 0.00014014439676236141, 'samples': 16539648, 'steps': 32303, 'batch_loss/train': 0.6303406322840601}
+12/27/2021 05:17:12 - INFO - codeparrot_training - Step 32304: {'lr': 0.00014013023726388093, 'samples': 16540160, 'steps': 32304, 'batch_loss/train': 0.7581426119431853}
+12/27/2021 05:17:23 - INFO - codeparrot_training - Step 32305: {'lr': 0.00014011607820220125, 'samples': 16540672, 'steps': 32305, 'batch_loss/train': 0.6641548555344343}
+12/27/2021 05:17:34 - INFO - codeparrot_training - Step 32306: {'lr': 0.0001401019195773784, 'samples': 16541184, 'steps': 32306, 'batch_loss/train': 0.7428359037730843}
+12/27/2021 05:17:46 - INFO - codeparrot_training - Step 32307: {'lr': 0.000140087761389469, 'samples': 16541696, 'steps': 32307, 'batch_loss/train': 0.7058635083958507}
+12/27/2021 05:17:57 - INFO - codeparrot_training - Step 32308: {'lr': 0.00014007360363852905, 'samples': 16542208, 'steps': 32308, 'batch_loss/train': 0.6930845654569566}
+12/27/2021 05:18:07 - INFO - codeparrot_training - Step 32309: {'lr': 0.00014005944632461493, 'samples': 16542720, 'steps': 32309, 'batch_loss/train': 0.5091306239482947}
+12/27/2021 05:18:20 - INFO - codeparrot_training - Step 32310: {'lr': 0.00014004528944778295, 'samples': 16543232, 'steps': 32310, 'batch_loss/train': 0.6600369763909839}
+12/27/2021 05:18:31 - INFO - codeparrot_training - Step 32311: {'lr': 0.0001400311330080894, 'samples': 16543744, 'steps': 32311, 'batch_loss/train': 0.7436795388348401}
+12/27/2021 05:18:41 - INFO - codeparrot_training - Step 32312: {'lr': 0.00014001697700559052, 'samples': 16544256, 'steps': 32312, 'batch_loss/train': 0.443354940158315}
+12/27/2021 05:18:54 - INFO - codeparrot_training - Step 32313: {'lr': 0.00014000282144034266, 'samples': 16544768, 'steps': 32313, 'batch_loss/train': 0.6823590728454292}
+12/27/2021 05:19:04 - INFO - codeparrot_training - Step 32314: {'lr': 0.00013998866631240197, 'samples': 16545280, 'steps': 32314, 'batch_loss/train': 0.7069672392681241}
+12/27/2021 05:19:15 - INFO - codeparrot_training - Step 32315: {'lr': 0.00013997451162182486, 'samples': 16545792, 'steps': 32315, 'batch_loss/train': 0.7410523823928088}
+12/27/2021 05:19:27 - INFO - codeparrot_training - Step 32316: {'lr': 0.00013996035736866763, 'samples': 16546304, 'steps': 32316, 'batch_loss/train': 0.7432721578516066}
+12/27/2021 05:19:38 - INFO - codeparrot_training - Step 32317: {'lr': 0.00013994620355298627, 'samples': 16546816, 'steps': 32317, 'batch_loss/train': 0.7362597666215152}
+12/27/2021 05:19:48 - INFO - codeparrot_training - Step 32318: {'lr': 0.00013993205017483735, 'samples': 16547328, 'steps': 32318, 'batch_loss/train': 0.8229704652912915}
+12/27/2021 05:19:59 - INFO - codeparrot_training - Step 32319: {'lr': 0.00013991789723427717, 'samples': 16547840, 'steps': 32319, 'batch_loss/train': 0.8080765102058649}
+12/27/2021 05:20:12 - INFO - codeparrot_training - Step 32320: {'lr': 0.0001399037447313617, 'samples': 16548352, 'steps': 32320, 'batch_loss/train': 0.848365587182343}
+12/27/2021 05:20:22 - INFO - codeparrot_training - Step 32321: {'lr': 0.0001398895926661473, 'samples': 16548864, 'steps': 32321, 'batch_loss/train': 0.6218033956829458}
+12/27/2021 05:20:33 - INFO - codeparrot_training - Step 32322: {'lr': 0.00013987544103869054, 'samples': 16549376, 'steps': 32322, 'batch_loss/train': 0.6698503410443664}
+12/27/2021 05:20:45 - INFO - codeparrot_training - Step 32323: {'lr': 0.00013986128984904732, 'samples': 16549888, 'steps': 32323, 'batch_loss/train': 0.7402838496491313}
+12/27/2021 05:20:56 - INFO - codeparrot_training - Step 32324: {'lr': 0.00013984713909727403, 'samples': 16550400, 'steps': 32324, 'batch_loss/train': 0.2110253483406268}
+12/27/2021 05:21:07 - INFO - codeparrot_training - Step 32325: {'lr': 0.0001398329887834269, 'samples': 16550912, 'steps': 32325, 'batch_loss/train': 0.7804268598556519}
+12/27/2021 05:21:19 - INFO - codeparrot_training - Step 32326: {'lr': 0.00013981883890756223, 'samples': 16551424, 'steps': 32326, 'batch_loss/train': 0.5265220301225781}
+12/27/2021 05:21:30 - INFO - codeparrot_training - Step 32327: {'lr': 0.00013980468946973623, 'samples': 16551936, 'steps': 32327, 'batch_loss/train': 0.7191035840660334}
+12/27/2021 05:21:41 - INFO - codeparrot_training - Step 32328: {'lr': 0.0001397905404700052, 'samples': 16552448, 'steps': 32328, 'batch_loss/train': 0.7231624163687229}
+12/27/2021 05:21:52 - INFO - codeparrot_training - Step 32329: {'lr': 0.00013977639190842535, 'samples': 16552960, 'steps': 32329, 'batch_loss/train': 0.6932185934856534}
+12/27/2021 05:22:03 - INFO - codeparrot_training - Step 32330: {'lr': 0.00013976224378505297, 'samples': 16553472, 'steps': 32330, 'batch_loss/train': 0.7417432125657797}
+12/27/2021 05:22:14 - INFO - codeparrot_training - Step 32331: {'lr': 0.00013974809609994439, 'samples': 16553984, 'steps': 32331, 'batch_loss/train': 0.7439419236034155}
+12/27/2021 05:22:24 - INFO - codeparrot_training - Step 32332: {'lr': 0.00013973394885315548, 'samples': 16554496, 'steps': 32332, 'batch_loss/train': 0.7626461442559958}
+12/27/2021 05:22:37 - INFO - codeparrot_training - Step 32333: {'lr': 0.00013971980204474305, 'samples': 16555008, 'steps': 32333, 'batch_loss/train': 0.7175390813499689}
+12/27/2021 05:22:47 - INFO - codeparrot_training - Step 32334: {'lr': 0.0001397056556747629, 'samples': 16555520, 'steps': 32334, 'batch_loss/train': 0.73565723747015}
+12/27/2021 05:22:58 - INFO - codeparrot_training - Step 32335: {'lr': 0.0001396915097432714, 'samples': 16556032, 'steps': 32335, 'batch_loss/train': 0.6494126156903803}
+12/27/2021 05:23:12 - INFO - codeparrot_training - Step 32336: {'lr': 0.00013967736425032483, 'samples': 16556544, 'steps': 32336, 'batch_loss/train': 0.7941952338442206}
+12/27/2021 05:23:22 - INFO - codeparrot_training - Step 32337: {'lr': 0.0001396632191959794, 'samples': 16557056, 'steps': 32337, 'batch_loss/train': 0.7518828478641808}
+12/27/2021 05:23:33 - INFO - codeparrot_training - Step 32338: {'lr': 0.00013964907458029137, 'samples': 16557568, 'steps': 32338, 'batch_loss/train': 0.8009118097834289}
+12/27/2021 05:23:45 - INFO - codeparrot_training - Step 32339: {'lr': 0.00013963493040331692, 'samples': 16558080, 'steps': 32339, 'batch_loss/train': 0.6985837467946112}
+12/27/2021 05:23:56 - INFO - codeparrot_training - Step 32340: {'lr': 0.00013962078666511233, 'samples': 16558592, 'steps': 32340, 'batch_loss/train': 0.7208583783358335}
+12/27/2021 05:24:06 - INFO - codeparrot_training - Step 32341: {'lr': 0.0001396066433657338, 'samples': 16559104, 'steps': 32341, 'batch_loss/train': 0.7429032474756241}
+12/27/2021 05:24:17 - INFO - codeparrot_training - Step 32342: {'lr': 0.0001395925005052377, 'samples': 16559616, 'steps': 32342, 'batch_loss/train': 0.6830298871500418}
+12/27/2021 05:24:29 - INFO - codeparrot_training - Step 32343: {'lr': 0.0001395783580836799, 'samples': 16560128, 'steps': 32343, 'batch_loss/train': 0.7842979421839118}
+12/27/2021 05:24:40 - INFO - codeparrot_training - Step 32344: {'lr': 0.00013956421610111696, 'samples': 16560640, 'steps': 32344, 'batch_loss/train': 0.699182879878208}
+12/27/2021 05:24:50 - INFO - codeparrot_training - Step 32345: {'lr': 0.00013955007455760513, 'samples': 16561152, 'steps': 32345, 'batch_loss/train': 0.6695302715525031}
+12/27/2021 05:25:03 - INFO - codeparrot_training - Step 32346: {'lr': 0.00013953593345320038, 'samples': 16561664, 'steps': 32346, 'batch_loss/train': 0.8325824243947864}
+12/27/2021 05:25:13 - INFO - codeparrot_training - Step 32347: {'lr': 0.00013952179278795896, 'samples': 16562176, 'steps': 32347, 'batch_loss/train': 0.6639157008030452}
+12/27/2021 05:25:24 - INFO - codeparrot_training - Step 32348: {'lr': 0.00013950765256193735, 'samples': 16562688, 'steps': 32348, 'batch_loss/train': 0.4879343523643911}
+12/27/2021 05:25:37 - INFO - codeparrot_training - Step 32349: {'lr': 0.0001394935127751915, 'samples': 16563200, 'steps': 32349, 'batch_loss/train': 0.7681866786442697}
+12/27/2021 05:25:47 - INFO - codeparrot_training - Step 32350: {'lr': 0.0001394793734277777, 'samples': 16563712, 'steps': 32350, 'batch_loss/train': 0.7373222107999027}
+12/27/2021 05:25:58 - INFO - codeparrot_training - Step 32351: {'lr': 0.00013946523451975224, 'samples': 16564224, 'steps': 32351, 'batch_loss/train': 0.8112887050956488}
+12/27/2021 05:26:10 - INFO - codeparrot_training - Step 32352: {'lr': 0.00013945109605117124, 'samples': 16564736, 'steps': 32352, 'batch_loss/train': 0.696663680661004}
+12/27/2021 05:26:21 - INFO - codeparrot_training - Step 32353: {'lr': 0.00013943695802209088, 'samples': 16565248, 'steps': 32353, 'batch_loss/train': 0.6448397925123572}
+12/27/2021 05:26:32 - INFO - codeparrot_training - Step 32354: {'lr': 0.00013942282043256753, 'samples': 16565760, 'steps': 32354, 'batch_loss/train': 0.683486474212259}
+12/27/2021 05:26:42 - INFO - codeparrot_training - Step 32355: {'lr': 0.00013940868328265722, 'samples': 16566272, 'steps': 32355, 'batch_loss/train': 0.6210959147429094}
+12/27/2021 05:26:54 - INFO - codeparrot_training - Step 32356: {'lr': 0.00013939454657241627, 'samples': 16566784, 'steps': 32356, 'batch_loss/train': 0.7643389538861811}
+12/27/2021 05:27:05 - INFO - codeparrot_training - Step 32357: {'lr': 0.00013938041030190092, 'samples': 16567296, 'steps': 32357, 'batch_loss/train': 0.7217443864792585}
+12/27/2021 05:27:15 - INFO - codeparrot_training - Step 32358: {'lr': 0.0001393662744711671, 'samples': 16567808, 'steps': 32358, 'batch_loss/train': 0.7136455690488219}
+12/27/2021 05:27:28 - INFO - codeparrot_training - Step 32359: {'lr': 0.00013935213908027128, 'samples': 16568320, 'steps': 32359, 'batch_loss/train': 0.7066012807190418}
+12/27/2021 05:27:39 - INFO - codeparrot_training - Step 32360: {'lr': 0.0001393380041292697, 'samples': 16568832, 'steps': 32360, 'batch_loss/train': 0.6906012678518891}
+12/27/2021 05:27:49 - INFO - codeparrot_training - Step 32361: {'lr': 0.0001393238696182183, 'samples': 16569344, 'steps': 32361, 'batch_loss/train': 0.6133220409974456}
+12/27/2021 05:28:02 - INFO - codeparrot_training - Step 32362: {'lr': 0.00013930973554717344, 'samples': 16569856, 'steps': 32362, 'batch_loss/train': 0.7559969611465931}
+12/27/2021 05:28:12 - INFO - codeparrot_training - Step 32363: {'lr': 0.00013929560191619126, 'samples': 16570368, 'steps': 32363, 'batch_loss/train': 0.7405283318366855}
+12/27/2021 05:28:23 - INFO - codeparrot_training - Step 32364: {'lr': 0.00013928146872532797, 'samples': 16570880, 'steps': 32364, 'batch_loss/train': 0.721204839181155}
+12/27/2021 05:28:36 - INFO - codeparrot_training - Step 32365: {'lr': 0.00013926733597463976, 'samples': 16571392, 'steps': 32365, 'batch_loss/train': 0.7201142306439579}
+12/27/2021 05:28:47 - INFO - codeparrot_training - Step 32366: {'lr': 0.00013925320366418278, 'samples': 16571904, 'steps': 32366, 'batch_loss/train': 0.6387135619297624}
+12/27/2021 05:28:57 - INFO - codeparrot_training - Step 32367: {'lr': 0.0001392390717940133, 'samples': 16572416, 'steps': 32367, 'batch_loss/train': 0.7856559292413294}
+12/27/2021 05:29:08 - INFO - codeparrot_training - Step 32368: {'lr': 0.00013922494036418747, 'samples': 16572928, 'steps': 32368, 'batch_loss/train': 0.768601288087666}
+12/27/2021 05:29:20 - INFO - codeparrot_training - Step 32369: {'lr': 0.00013921080937476132, 'samples': 16573440, 'steps': 32369, 'batch_loss/train': 0.7374382824636996}
+12/27/2021 05:29:31 - INFO - codeparrot_training - Step 32370: {'lr': 0.00013919667882579125, 'samples': 16573952, 'steps': 32370, 'batch_loss/train': 0.8219026615843177}
+12/27/2021 05:29:41 - INFO - codeparrot_training - Step 32371: {'lr': 0.00013918254871733344, 'samples': 16574464, 'steps': 32371, 'batch_loss/train': 0.5401793254422955}
+12/27/2021 05:29:53 - INFO - codeparrot_training - Step 32372: {'lr': 0.00013916841904944386, 'samples': 16574976, 'steps': 32372, 'batch_loss/train': 0.6908401395776309}
+12/27/2021 05:30:04 - INFO - codeparrot_training - Step 32373: {'lr': 0.0001391542898221787, 'samples': 16575488, 'steps': 32373, 'batch_loss/train': 0.8346827785135247}
+12/27/2021 05:30:15 - INFO - codeparrot_training - Step 32374: {'lr': 0.00013914016103559447, 'samples': 16576000, 'steps': 32374, 'batch_loss/train': 0.7283850042149425}
+12/27/2021 05:30:27 - INFO - codeparrot_training - Step 32375: {'lr': 0.00013912603268974693, 'samples': 16576512, 'steps': 32375, 'batch_loss/train': 0.7789133954793215}
+12/27/2021 05:30:38 - INFO - codeparrot_training - Step 32376: {'lr': 0.00013911190478469246, 'samples': 16577024, 'steps': 32376, 'batch_loss/train': 0.953929761890322}
+12/27/2021 05:30:49 - INFO - codeparrot_training - Step 32377: {'lr': 0.00013909777732048717, 'samples': 16577536, 'steps': 32377, 'batch_loss/train': 0.7046423451974988}
+12/27/2021 05:30:59 - INFO - codeparrot_training - Step 32378: {'lr': 0.00013908365029718727, 'samples': 16578048, 'steps': 32378, 'batch_loss/train': 0.6734427093761042}
+12/27/2021 05:31:11 - INFO - codeparrot_training - Step 32379: {'lr': 0.00013906952371484888, 'samples': 16578560, 'steps': 32379, 'batch_loss/train': 0.7410535831004381}
+12/27/2021 05:31:22 - INFO - codeparrot_training - Step 32380: {'lr': 0.0001390553975735282, 'samples': 16579072, 'steps': 32380, 'batch_loss/train': 0.6309030561242253}
+12/27/2021 05:31:33 - INFO - codeparrot_training - Step 32381: {'lr': 0.00013904127187328133, 'samples': 16579584, 'steps': 32381, 'batch_loss/train': 0.7413820698857307}
+12/27/2021 05:31:45 - INFO - codeparrot_training - Step 32382: {'lr': 0.0001390271466141645, 'samples': 16580096, 'steps': 32382, 'batch_loss/train': 0.7370264614000916}
+12/27/2021 05:31:55 - INFO - codeparrot_training - Step 32383: {'lr': 0.0001390130217962339, 'samples': 16580608, 'steps': 32383, 'batch_loss/train': 0.5851664608344436}
+12/27/2021 05:32:06 - INFO - codeparrot_training - Step 32384: {'lr': 0.00013899889741954543, 'samples': 16581120, 'steps': 32384, 'batch_loss/train': 0.6550396382808685}
+12/27/2021 05:32:18 - INFO - codeparrot_training - Step 32385: {'lr': 0.00013898477348415556, 'samples': 16581632, 'steps': 32385, 'batch_loss/train': 0.8114882009103894}
+12/27/2021 05:32:29 - INFO - codeparrot_training - Step 32386: {'lr': 0.00013897064999012038, 'samples': 16582144, 'steps': 32386, 'batch_loss/train': 0.7587218033149838}
+12/27/2021 05:32:39 - INFO - codeparrot_training - Step 32387: {'lr': 0.0001389565269374959, 'samples': 16582656, 'steps': 32387, 'batch_loss/train': 0.7428464675322175}
+12/27/2021 05:32:53 - INFO - codeparrot_training - Step 32388: {'lr': 0.0001389424043263383, 'samples': 16583168, 'steps': 32388, 'batch_loss/train': 0.8147524707019329}
+12/27/2021 05:33:03 - INFO - codeparrot_training - Step 32389: {'lr': 0.00013892828215670379, 'samples': 16583680, 'steps': 32389, 'batch_loss/train': 0.7617266097804531}
+12/27/2021 05:33:14 - INFO - codeparrot_training - Step 32390: {'lr': 0.0001389141604286485, 'samples': 16584192, 'steps': 32390, 'batch_loss/train': 0.8466346114873886}
+12/27/2021 05:33:24 - INFO - codeparrot_training - Step 32391: {'lr': 0.00013890003914222854, 'samples': 16584704, 'steps': 32391, 'batch_loss/train': 0.7170351557433605}
+12/27/2021 05:33:37 - INFO - codeparrot_training - Step 32392: {'lr': 0.00013888591829750008, 'samples': 16585216, 'steps': 32392, 'batch_loss/train': 0.495068369229557}
+12/27/2021 05:33:47 - INFO - codeparrot_training - Step 32393: {'lr': 0.00013887179789451927, 'samples': 16585728, 'steps': 32393, 'batch_loss/train': 0.7930173818022013}
+12/27/2021 05:33:58 - INFO - codeparrot_training - Step 32394: {'lr': 0.00013885767793334226, 'samples': 16586240, 'steps': 32394, 'batch_loss/train': 0.6963072149083018}
+12/27/2021 05:34:10 - INFO - codeparrot_training - Step 32395: {'lr': 0.0001388435584140251, 'samples': 16586752, 'steps': 32395, 'batch_loss/train': 0.7602996407076716}
+12/27/2021 05:34:21 - INFO - codeparrot_training - Step 32396: {'lr': 0.000138829439336624, 'samples': 16587264, 'steps': 32396, 'batch_loss/train': 0.7176498537883162}
+12/27/2021 05:34:32 - INFO - codeparrot_training - Step 32397: {'lr': 0.00013881532070119518, 'samples': 16587776, 'steps': 32397, 'batch_loss/train': 0.7548332056030631}
+12/27/2021 05:34:44 - INFO - codeparrot_training - Step 32398: {'lr': 0.00013880120250779455, 'samples': 16588288, 'steps': 32398, 'batch_loss/train': 1.5376355491462164}
+12/27/2021 05:34:55 - INFO - codeparrot_training - Step 32399: {'lr': 0.00013878708475647828, 'samples': 16588800, 'steps': 32399, 'batch_loss/train': 0.789752337615937}
+12/27/2021 05:35:05 - INFO - codeparrot_training - Step 32400: {'lr': 0.00013877296744730272, 'samples': 16589312, 'steps': 32400, 'batch_loss/train': 0.714497294742614}
+12/27/2021 05:35:16 - INFO - codeparrot_training - Step 32401: {'lr': 0.0001387588505803238, 'samples': 16589824, 'steps': 32401, 'batch_loss/train': 0.7001133184821811}
+12/27/2021 05:35:29 - INFO - codeparrot_training - Step 32402: {'lr': 0.00013874473415559753, 'samples': 16590336, 'steps': 32402, 'batch_loss/train': 0.6017447697231546}
+12/27/2021 05:35:39 - INFO - codeparrot_training - Step 32403: {'lr': 0.00013873061817318045, 'samples': 16590848, 'steps': 32403, 'batch_loss/train': 0.7502701710909605}
+12/27/2021 05:35:50 - INFO - codeparrot_training - Step 32404: {'lr': 0.00013871650263312828, 'samples': 16591360, 'steps': 32404, 'batch_loss/train': 1.0415718303993344}
+12/27/2021 05:36:03 - INFO - codeparrot_training - Step 32405: {'lr': 0.00013870238753549728, 'samples': 16591872, 'steps': 32405, 'batch_loss/train': 0.810288674198091}
+12/27/2021 05:36:13 - INFO - codeparrot_training - Step 32406: {'lr': 0.00013868827288034355, 'samples': 16592384, 'steps': 32406, 'batch_loss/train': 1.4429555293172598}
+12/27/2021 05:36:24 - INFO - codeparrot_training - Step 32407: {'lr': 0.00013867415866772325, 'samples': 16592896, 'steps': 32407, 'batch_loss/train': 0.8011913076043129}
+12/27/2021 05:36:34 - INFO - codeparrot_training - Step 32408: {'lr': 0.00013866004489769242, 'samples': 16593408, 'steps': 32408, 'batch_loss/train': 0.5983671038411558}
+12/27/2021 05:36:47 - INFO - codeparrot_training - Step 32409: {'lr': 0.00013864593157030737, 'samples': 16593920, 'steps': 32409, 'batch_loss/train': 0.8532659986522049}
+12/27/2021 05:36:57 - INFO - codeparrot_training - Step 32410: {'lr': 0.0001386318186856238, 'samples': 16594432, 'steps': 32410, 'batch_loss/train': 0.5224180004152004}
+12/27/2021 05:37:08 - INFO - codeparrot_training - Step 32411: {'lr': 0.00013861770624369818, 'samples': 16594944, 'steps': 32411, 'batch_loss/train': 0.781175076495856}
+12/27/2021 05:37:21 - INFO - codeparrot_training - Step 32412: {'lr': 0.0001386035942445866, 'samples': 16595456, 'steps': 32412, 'batch_loss/train': 0.751599351875484}
+12/27/2021 05:37:32 - INFO - codeparrot_training - Step 32413: {'lr': 0.000138589482688345, 'samples': 16595968, 'steps': 32413, 'batch_loss/train': 0.6962300566956401}
+12/27/2021 05:37:42 - INFO - codeparrot_training - Step 32414: {'lr': 0.0001385753715750295, 'samples': 16596480, 'steps': 32414, 'batch_loss/train': 0.6928810020908713}
+12/27/2021 05:37:54 - INFO - codeparrot_training - Step 32415: {'lr': 0.00013856126090469628, 'samples': 16596992, 'steps': 32415, 'batch_loss/train': 0.5085188393713906}
+12/27/2021 05:38:05 - INFO - codeparrot_training - Step 32416: {'lr': 0.0001385471506774014, 'samples': 16597504, 'steps': 32416, 'batch_loss/train': 0.7534496751613915}
+12/27/2021 05:38:16 - INFO - codeparrot_training - Step 32417: {'lr': 0.00013853304089320094, 'samples': 16598016, 'steps': 32417, 'batch_loss/train': 0.704179780150298}
+12/27/2021 05:38:26 - INFO - codeparrot_training - Step 32418: {'lr': 0.00013851893155215106, 'samples': 16598528, 'steps': 32418, 'batch_loss/train': 0.7507332526147366}
+12/27/2021 05:38:39 - INFO - codeparrot_training - Step 32419: {'lr': 0.0001385048226543078, 'samples': 16599040, 'steps': 32419, 'batch_loss/train': 0.8217652537859976}
+12/27/2021 05:38:49 - INFO - codeparrot_training - Step 32420: {'lr': 0.0001384907141997273, 'samples': 16599552, 'steps': 32420, 'batch_loss/train': 0.4734814161201939}
+12/27/2021 05:39:00 - INFO - codeparrot_training - Step 32421: {'lr': 0.0001384766061884656, 'samples': 16600064, 'steps': 32421, 'batch_loss/train': 0.7484965904732235}
+12/27/2021 05:39:12 - INFO - codeparrot_training - Step 32422: {'lr': 0.00013846249862057878, 'samples': 16600576, 'steps': 32422, 'batch_loss/train': 0.8086684960871935}
+12/27/2021 05:39:23 - INFO - codeparrot_training - Step 32423: {'lr': 0.00013844839149612304, 'samples': 16601088, 'steps': 32423, 'batch_loss/train': 0.7137076877988875}
+12/27/2021 05:39:33 - INFO - codeparrot_training - Step 32424: {'lr': 0.00013843428481515429, 'samples': 16601600, 'steps': 32424, 'batch_loss/train': 0.7386652203276753}
+12/27/2021 05:39:46 - INFO - codeparrot_training - Step 32425: {'lr': 0.00013842017857772863, 'samples': 16602112, 'steps': 32425, 'batch_loss/train': 0.7639040334615856}
+12/27/2021 05:39:57 - INFO - codeparrot_training - Step 32426: {'lr': 0.00013840607278390238, 'samples': 16602624, 'steps': 32426, 'batch_loss/train': 0.6574268760159612}
+12/27/2021 05:40:07 - INFO - codeparrot_training - Step 32427: {'lr': 0.00013839196743373135, 'samples': 16603136, 'steps': 32427, 'batch_loss/train': 0.7259528385475278}
+12/27/2021 05:40:18 - INFO - codeparrot_training - Step 32428: {'lr': 0.00013837786252727163, 'samples': 16603648, 'steps': 32428, 'batch_loss/train': 0.8341601993888617}
+12/27/2021 05:40:30 - INFO - codeparrot_training - Step 32429: {'lr': 0.00013836375806457958, 'samples': 16604160, 'steps': 32429, 'batch_loss/train': 0.8033705744892359}
+12/27/2021 05:40:41 - INFO - codeparrot_training - Step 32430: {'lr': 0.00013834965404571091, 'samples': 16604672, 'steps': 32430, 'batch_loss/train': 0.766113568097353}
+12/27/2021 05:40:51 - INFO - codeparrot_training - Step 32431: {'lr': 0.00013833555047072194, 'samples': 16605184, 'steps': 32431, 'batch_loss/train': 0.6236517236102372}
+12/27/2021 05:41:04 - INFO - codeparrot_training - Step 32432: {'lr': 0.00013832144733966865, 'samples': 16605696, 'steps': 32432, 'batch_loss/train': 0.5811746741528623}
+12/27/2021 05:41:14 - INFO - codeparrot_training - Step 32433: {'lr': 0.00013830734465260707, 'samples': 16606208, 'steps': 32433, 'batch_loss/train': 0.7484292471781373}
+12/27/2021 05:41:25 - INFO - codeparrot_training - Step 32434: {'lr': 0.00013829324240959335, 'samples': 16606720, 'steps': 32434, 'batch_loss/train': 0.612607421935536}
+12/27/2021 05:41:38 - INFO - codeparrot_training - Step 32435: {'lr': 0.00013827914061068363, 'samples': 16607232, 'steps': 32435, 'batch_loss/train': 0.705434713861905}
+12/27/2021 05:41:48 - INFO - codeparrot_training - Step 32436: {'lr': 0.00013826503925593365, 'samples': 16607744, 'steps': 32436, 'batch_loss/train': 0.7532886583358049}
+12/27/2021 05:41:59 - INFO - codeparrot_training - Step 32437: {'lr': 0.00013825093834539975, 'samples': 16608256, 'steps': 32437, 'batch_loss/train': 0.7443896476179361}
+12/27/2021 05:42:11 - INFO - codeparrot_training - Step 32438: {'lr': 0.00013823683787913808, 'samples': 16608768, 'steps': 32438, 'batch_loss/train': 0.671644221059978}
+12/27/2021 05:42:22 - INFO - codeparrot_training - Step 32439: {'lr': 0.00013822273785720428, 'samples': 16609280, 'steps': 32439, 'batch_loss/train': 0.6642408790066838}
+12/27/2021 05:42:32 - INFO - codeparrot_training - Step 32440: {'lr': 0.00013820863827965484, 'samples': 16609792, 'steps': 32440, 'batch_loss/train': 0.7788570588454604}
+12/27/2021 05:42:43 - INFO - codeparrot_training - Step 32441: {'lr': 0.00013819453914654573, 'samples': 16610304, 'steps': 32441, 'batch_loss/train': 0.728126322850585}
+12/27/2021 05:42:56 - INFO - codeparrot_training - Step 32442: {'lr': 0.00013818044045793278, 'samples': 16610816, 'steps': 32442, 'batch_loss/train': 0.8227411694824696}
+12/27/2021 05:43:07 - INFO - codeparrot_training - Step 32443: {'lr': 0.0001381663422138722, 'samples': 16611328, 'steps': 32443, 'batch_loss/train': 0.7742307484149933}
+12/27/2021 05:43:17 - INFO - codeparrot_training - Step 32444: {'lr': 0.00013815224441442, 'samples': 16611840, 'steps': 32444, 'batch_loss/train': 0.7940793074667454}
+12/27/2021 05:43:29 - INFO - codeparrot_training - Step 32445: {'lr': 0.00013813814705963224, 'samples': 16612352, 'steps': 32445, 'batch_loss/train': 0.7053366787731647}
+12/27/2021 05:43:40 - INFO - codeparrot_training - Step 32446: {'lr': 0.00013812405014956497, 'samples': 16612864, 'steps': 32446, 'batch_loss/train': 0.676638004835695}
+12/27/2021 05:43:51 - INFO - codeparrot_training - Step 32447: {'lr': 0.00013810995368427427, 'samples': 16613376, 'steps': 32447, 'batch_loss/train': 0.5985388248227537}
+12/27/2021 05:44:03 - INFO - codeparrot_training - Step 32448: {'lr': 0.0001380958576638161, 'samples': 16613888, 'steps': 32448, 'batch_loss/train': 0.7153349751606584}
+12/27/2021 05:44:13 - INFO - codeparrot_training - Step 32449: {'lr': 0.0001380817620882467, 'samples': 16614400, 'steps': 32449, 'batch_loss/train': 0.6915714247152209}
+12/27/2021 05:44:24 - INFO - codeparrot_training - Step 32450: {'lr': 0.00013806766695762183, 'samples': 16614912, 'steps': 32450, 'batch_loss/train': 0.6816259303595871}
+12/27/2021 05:44:36 - INFO - codeparrot_training - Step 32451: {'lr': 0.00013805357227199755, 'samples': 16615424, 'steps': 32451, 'batch_loss/train': 0.6785509377950802}
+12/27/2021 05:44:47 - INFO - codeparrot_training - Step 32452: {'lr': 0.00013803947803143018, 'samples': 16615936, 'steps': 32452, 'batch_loss/train': 0.7248928765766323}
+12/27/2021 05:44:57 - INFO - codeparrot_training - Step 32453: {'lr': 0.00013802538423597548, 'samples': 16616448, 'steps': 32453, 'batch_loss/train': 0.9132445277646184}
+12/27/2021 05:45:08 - INFO - codeparrot_training - Step 32454: {'lr': 0.00013801129088568948, 'samples': 16616960, 'steps': 32454, 'batch_loss/train': 0.6215811809524894}
+12/27/2021 05:45:21 - INFO - codeparrot_training - Step 32455: {'lr': 0.00013799719798062847, 'samples': 16617472, 'steps': 32455, 'batch_loss/train': 0.6927280491217971}
+12/27/2021 05:45:31 - INFO - codeparrot_training - Step 32456: {'lr': 0.00013798310552084827, 'samples': 16617984, 'steps': 32456, 'batch_loss/train': 0.7068889955990016}
+12/27/2021 05:45:42 - INFO - codeparrot_training - Step 32457: {'lr': 0.00013796901350640492, 'samples': 16618496, 'steps': 32457, 'batch_loss/train': 0.7138373600319028}
+12/27/2021 05:45:54 - INFO - codeparrot_training - Step 32458: {'lr': 0.00013795492193735448, 'samples': 16619008, 'steps': 32458, 'batch_loss/train': 0.6901852479204535}
+12/27/2021 05:46:05 - INFO - codeparrot_training - Step 32459: {'lr': 0.00013794083081375294, 'samples': 16619520, 'steps': 32459, 'batch_loss/train': 0.7198220230638981}
+12/27/2021 05:46:15 - INFO - codeparrot_training - Step 32460: {'lr': 0.00013792674013565637, 'samples': 16620032, 'steps': 32460, 'batch_loss/train': 0.6757111614570022}
+12/27/2021 05:46:27 - INFO - codeparrot_training - Step 32461: {'lr': 0.00013791264990312084, 'samples': 16620544, 'steps': 32461, 'batch_loss/train': 0.6527447723783553}
+12/27/2021 05:46:38 - INFO - codeparrot_training - Step 32462: {'lr': 0.0001378985601162021, 'samples': 16621056, 'steps': 32462, 'batch_loss/train': 0.7372813150286674}
+12/27/2021 05:46:49 - INFO - codeparrot_training - Step 32463: {'lr': 0.00013788447077495646, 'samples': 16621568, 'steps': 32463, 'batch_loss/train': 0.638128784543369}
+12/27/2021 05:47:02 - INFO - codeparrot_training - Step 32464: {'lr': 0.00013787038187943991, 'samples': 16622080, 'steps': 32464, 'batch_loss/train': 0.7169531243853271}
+12/27/2021 05:47:12 - INFO - codeparrot_training - Step 32465: {'lr': 0.00013785629342970824, 'samples': 16622592, 'steps': 32465, 'batch_loss/train': 0.7599275065585971}
+12/27/2021 05:47:23 - INFO - codeparrot_training - Step 32466: {'lr': 0.00013784220542581766, 'samples': 16623104, 'steps': 32466, 'batch_loss/train': 0.7788556346204132}
+12/27/2021 05:47:34 - INFO - codeparrot_training - Step 32467: {'lr': 0.00013782811786782422, 'samples': 16623616, 'steps': 32467, 'batch_loss/train': 0.553601078921929}
+12/27/2021 05:47:46 - INFO - codeparrot_training - Step 32468: {'lr': 0.00013781403075578374, 'samples': 16624128, 'steps': 32468, 'batch_loss/train': 0.7659071842208505}
+12/27/2021 05:47:57 - INFO - codeparrot_training - Step 32469: {'lr': 0.0001377999440897523, 'samples': 16624640, 'steps': 32469, 'batch_loss/train': 0.6591085472609848}
+12/27/2021 05:48:07 - INFO - codeparrot_training - Step 32470: {'lr': 0.00013778585786978592, 'samples': 16625152, 'steps': 32470, 'batch_loss/train': 0.5613021455646958}
+12/27/2021 05:48:20 - INFO - codeparrot_training - Step 32471: {'lr': 0.00013777177209594061, 'samples': 16625664, 'steps': 32471, 'batch_loss/train': 0.7297030960326083}
+12/27/2021 05:48:31 - INFO - codeparrot_training - Step 32472: {'lr': 0.00013775768676827237, 'samples': 16626176, 'steps': 32472, 'batch_loss/train': 0.6705396577599458}
+12/27/2021 05:48:41 - INFO - codeparrot_training - Step 32473: {'lr': 0.00013774360188683715, 'samples': 16626688, 'steps': 32473, 'batch_loss/train': 0.7812702525407076}
+12/27/2021 05:48:53 - INFO - codeparrot_training - Step 32474: {'lr': 0.00013772951745169102, 'samples': 16627200, 'steps': 32474, 'batch_loss/train': 0.7529483459657058}
+12/27/2021 05:49:04 - INFO - codeparrot_training - Step 32475: {'lr': 0.0001377154334628899, 'samples': 16627712, 'steps': 32475, 'batch_loss/train': 0.7927341302856803}
+12/27/2021 05:49:15 - INFO - codeparrot_training - Step 32476: {'lr': 0.00013770134992048986, 'samples': 16628224, 'steps': 32476, 'batch_loss/train': 0.7769243735820055}
+12/27/2021 05:49:27 - INFO - codeparrot_training - Step 32477: {'lr': 0.00013768726682454683, 'samples': 16628736, 'steps': 32477, 'batch_loss/train': 0.6747968327254057}
+12/27/2021 05:49:37 - INFO - codeparrot_training - Step 32478: {'lr': 0.00013767318417511694, 'samples': 16629248, 'steps': 32478, 'batch_loss/train': 0.7257094540400431}
+12/27/2021 05:49:48 - INFO - codeparrot_training - Step 32479: {'lr': 0.00013765910197225593, 'samples': 16629760, 'steps': 32479, 'batch_loss/train': 0.831925161415711}
+12/27/2021 05:49:59 - INFO - codeparrot_training - Step 32480: {'lr': 0.00013764502021601982, 'samples': 16630272, 'steps': 32480, 'batch_loss/train': 0.7881812911946326}
+12/27/2021 05:50:12 - INFO - codeparrot_training - Step 32481: {'lr': 0.00013763093890646489, 'samples': 16630784, 'steps': 32481, 'batch_loss/train': 0.802687874995172}
+12/27/2021 05:50:23 - INFO - codeparrot_training - Step 32482: {'lr': 0.00013761685804364681, 'samples': 16631296, 'steps': 32482, 'batch_loss/train': 0.8430116111412644}
+12/27/2021 05:50:33 - INFO - codeparrot_training - Step 32483: {'lr': 0.00013760277762762165, 'samples': 16631808, 'steps': 32483, 'batch_loss/train': 0.6907042318489403}
+12/27/2021 05:50:45 - INFO - codeparrot_training - Step 32484: {'lr': 0.00013758869765844546, 'samples': 16632320, 'steps': 32484, 'batch_loss/train': 0.5471556948905345}
+12/27/2021 05:50:56 - INFO - codeparrot_training - Step 32485: {'lr': 0.00013757461813617412, 'samples': 16632832, 'steps': 32485, 'batch_loss/train': 0.827866998501122}
+12/27/2021 05:51:07 - INFO - codeparrot_training - Step 32486: {'lr': 0.00013756053906086363, 'samples': 16633344, 'steps': 32486, 'batch_loss/train': 0.7250346280634403}
+12/27/2021 05:51:19 - INFO - codeparrot_training - Step 32487: {'lr': 0.00013754646043257014, 'samples': 16633856, 'steps': 32487, 'batch_loss/train': 0.6856287503615022}
+12/27/2021 05:51:29 - INFO - codeparrot_training - Step 32488: {'lr': 0.00013753238225134922, 'samples': 16634368, 'steps': 32488, 'batch_loss/train': 0.7769987247884274}
+12/27/2021 05:51:40 - INFO - codeparrot_training - Step 32489: {'lr': 0.00013751830451725722, 'samples': 16634880, 'steps': 32489, 'batch_loss/train': 0.6275716994423419}
+12/27/2021 05:51:51 - INFO - codeparrot_training - Step 32490: {'lr': 0.00013750422723035003, 'samples': 16635392, 'steps': 32490, 'batch_loss/train': 0.5762830912135541}
+12/27/2021 05:52:03 - INFO - codeparrot_training - Step 32491: {'lr': 0.00013749015039068335, 'samples': 16635904, 'steps': 32491, 'batch_loss/train': 0.8496203701943159}
+12/27/2021 05:52:13 - INFO - codeparrot_training - Step 32492: {'lr': 0.00013747607399831348, 'samples': 16636416, 'steps': 32492, 'batch_loss/train': 0.7157357486430556}
+12/27/2021 05:52:24 - INFO - codeparrot_training - Step 32493: {'lr': 0.00013746199805329636, 'samples': 16636928, 'steps': 32493, 'batch_loss/train': 0.7555425718892366}
+12/27/2021 05:52:37 - INFO - codeparrot_training - Step 32494: {'lr': 0.00013744792255568773, 'samples': 16637440, 'steps': 32494, 'batch_loss/train': 0.7542116555268876}
+12/27/2021 05:52:48 - INFO - codeparrot_training - Step 32495: {'lr': 0.00013743384750554367, 'samples': 16637952, 'steps': 32495, 'batch_loss/train': 0.6957337207859382}
+12/27/2021 05:52:58 - INFO - codeparrot_training - Step 32496: {'lr': 0.00013741977290292008, 'samples': 16638464, 'steps': 32496, 'batch_loss/train': 0.7453595474362373}
+12/27/2021 05:53:10 - INFO - codeparrot_training - Step 32497: {'lr': 0.00013740569874787302, 'samples': 16638976, 'steps': 32497, 'batch_loss/train': 0.7514802729710937}
+12/27/2021 05:53:21 - INFO - codeparrot_training - Step 32498: {'lr': 0.00013739162504045838, 'samples': 16639488, 'steps': 32498, 'batch_loss/train': 0.7322430461645126}
+12/27/2021 05:53:31 - INFO - codeparrot_training - Step 32499: {'lr': 0.00013737755178073208, 'samples': 16640000, 'steps': 32499, 'batch_loss/train': 0.6620134976692498}
+12/27/2021 05:53:31 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+12/27/2021 05:56:54 - INFO - codeparrot_training - Step 32500: {'loss/eval': 0.7624319195747375, 'perplexity': 2.1434826850891113}