diff --git "a/checkpoint-5875/trainer_state.json" "b/checkpoint-5875/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-5875/trainer_state.json" @@ -0,0 +1,4143 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.815991799077397, + "eval_steps": 500, + "global_step": 5875, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008119354511316351, + "grad_norm": 1.192345380783081, + "learning_rate": 2.7272727272727273e-05, + "loss": 1.3216888427734375, + "step": 10 + }, + { + "epoch": 0.016238709022632702, + "grad_norm": 1.2548257112503052, + "learning_rate": 5.757575757575758e-05, + "loss": 1.0566269874572753, + "step": 20 + }, + { + "epoch": 0.02435806353394905, + "grad_norm": 0.30806204676628113, + "learning_rate": 8.787878787878789e-05, + "loss": 0.6396953582763671, + "step": 30 + }, + { + "epoch": 0.032477418045265403, + "grad_norm": 0.25909167528152466, + "learning_rate": 0.0001181818181818182, + "loss": 0.5402174472808838, + "step": 40 + }, + { + "epoch": 0.04059677255658175, + "grad_norm": 0.21031738817691803, + "learning_rate": 0.00014848484848484849, + "loss": 0.5005859375, + "step": 50 + }, + { + "epoch": 0.0487161270678981, + "grad_norm": 0.18716108798980713, + "learning_rate": 0.0001787878787878788, + "loss": 0.537840461730957, + "step": 60 + }, + { + "epoch": 0.056835481579214454, + "grad_norm": 0.1792488396167755, + "learning_rate": 0.0001999990247348105, + "loss": 0.4450899600982666, + "step": 70 + }, + { + "epoch": 0.06495483609053081, + "grad_norm": 0.21492543816566467, + "learning_rate": 0.00019998168721618701, + "loss": 0.4202279090881348, + "step": 80 + }, + { + "epoch": 0.07307419060184715, + "grad_norm": 0.16661711037158966, + "learning_rate": 0.00019994268146276777, + "loss": 0.4485616207122803, + "step": 90 + }, + { + "epoch": 0.0811935451131635, + "grad_norm": 0.24056391417980194, + "learning_rate": 0.0001998820159279591, + "loss": 0.44878439903259276, + "step": 100 + }, + { + "epoch": 0.08931289962447986, + "grad_norm": 0.20612840354442596, + "learning_rate": 0.00019979970375931912, + "loss": 0.4974456787109375, + "step": 110 + }, + { + "epoch": 0.0974322541357962, + "grad_norm": 0.17296524345874786, + "learning_rate": 0.00019969576279570866, + "loss": 0.4231257438659668, + "step": 120 + }, + { + "epoch": 0.10555160864711255, + "grad_norm": 0.20717096328735352, + "learning_rate": 0.00019957021556342495, + "loss": 0.4275392532348633, + "step": 130 + }, + { + "epoch": 0.11367096315842891, + "grad_norm": 0.20023062825202942, + "learning_rate": 0.00019942308927131972, + "loss": 0.41733384132385254, + "step": 140 + }, + { + "epoch": 0.12179031766974525, + "grad_norm": 0.17242860794067383, + "learning_rate": 0.00019925441580490255, + "loss": 0.41766815185546874, + "step": 150 + }, + { + "epoch": 0.12990967218106161, + "grad_norm": 0.17718906700611115, + "learning_rate": 0.00019906423171943047, + "loss": 0.43944649696350097, + "step": 160 + }, + { + "epoch": 0.13802902669237796, + "grad_norm": 0.1699272096157074, + "learning_rate": 0.0001988525782319856, + "loss": 0.4246710777282715, + "step": 170 + }, + { + "epoch": 0.1461483812036943, + "grad_norm": 0.18154670298099518, + "learning_rate": 0.00019861950121254275, + "loss": 0.40392107963562013, + "step": 180 + }, + { + "epoch": 0.15426773571501065, + "grad_norm": 0.18973930180072784, + "learning_rate": 0.00019836505117402792, + "loss": 0.4155430316925049, + "step": 190 + }, + { + "epoch": 0.162387090226327, + "grad_norm": 0.15529297292232513, + "learning_rate": 0.00019808928326137156, + "loss": 0.430379581451416, + "step": 200 + }, + { + "epoch": 0.17050644473764337, + "grad_norm": 0.20729880034923553, + "learning_rate": 0.00019779225723955707, + "loss": 0.42681236267089845, + "step": 210 + }, + { + "epoch": 0.17862579924895972, + "grad_norm": 0.17007844150066376, + "learning_rate": 0.0001974740374806686, + "loss": 0.3926879644393921, + "step": 220 + }, + { + "epoch": 0.18674515376027606, + "grad_norm": 0.1643807291984558, + "learning_rate": 0.00019713469294994012, + "loss": 0.41318230628967284, + "step": 230 + }, + { + "epoch": 0.1948645082715924, + "grad_norm": 0.1504553258419037, + "learning_rate": 0.00019677429719080916, + "loss": 0.443330192565918, + "step": 240 + }, + { + "epoch": 0.20298386278290875, + "grad_norm": 0.17451228201389313, + "learning_rate": 0.00019639292830897837, + "loss": 0.4365452766418457, + "step": 250 + }, + { + "epoch": 0.2111032172942251, + "grad_norm": 0.16454367339611053, + "learning_rate": 0.0001959906689554881, + "loss": 0.45282588005065916, + "step": 260 + }, + { + "epoch": 0.21922257180554147, + "grad_norm": 0.15446598827838898, + "learning_rate": 0.0001955676063088045, + "loss": 0.46193952560424806, + "step": 270 + }, + { + "epoch": 0.22734192631685782, + "grad_norm": 0.17489995062351227, + "learning_rate": 0.00019512383205592552, + "loss": 0.46073436737060547, + "step": 280 + }, + { + "epoch": 0.23546128082817416, + "grad_norm": 0.1772591769695282, + "learning_rate": 0.00019465944237251071, + "loss": 0.38799960613250734, + "step": 290 + }, + { + "epoch": 0.2435806353394905, + "grad_norm": 0.11530005931854248, + "learning_rate": 0.00019417453790203772, + "loss": 0.4481969833374023, + "step": 300 + }, + { + "epoch": 0.2516999898508069, + "grad_norm": 0.1683167964220047, + "learning_rate": 0.0001936692237339905, + "loss": 0.41562438011169434, + "step": 310 + }, + { + "epoch": 0.25981934436212323, + "grad_norm": 0.16425232589244843, + "learning_rate": 0.00019314360938108425, + "loss": 0.40752553939819336, + "step": 320 + }, + { + "epoch": 0.2679386988734396, + "grad_norm": 0.16231301426887512, + "learning_rate": 0.0001925978087555316, + "loss": 0.3947896480560303, + "step": 330 + }, + { + "epoch": 0.2760580533847559, + "grad_norm": 0.17653369903564453, + "learning_rate": 0.00019203194014435525, + "loss": 0.4535045146942139, + "step": 340 + }, + { + "epoch": 0.28417740789607226, + "grad_norm": 0.15756867825984955, + "learning_rate": 0.0001914461261837526, + "loss": 0.4795684814453125, + "step": 350 + }, + { + "epoch": 0.2922967624073886, + "grad_norm": 0.1505475640296936, + "learning_rate": 0.00019084049383251783, + "loss": 0.4024923324584961, + "step": 360 + }, + { + "epoch": 0.30041611691870496, + "grad_norm": 0.16846773028373718, + "learning_rate": 0.00019021517434452702, + "loss": 0.42346930503845215, + "step": 370 + }, + { + "epoch": 0.3085354714300213, + "grad_norm": 0.17196664214134216, + "learning_rate": 0.0001895703032402926, + "loss": 0.38081505298614504, + "step": 380 + }, + { + "epoch": 0.31665482594133765, + "grad_norm": 0.18256904184818268, + "learning_rate": 0.00018890602027759313, + "loss": 0.37936599254608155, + "step": 390 + }, + { + "epoch": 0.324774180452654, + "grad_norm": 0.1385713666677475, + "learning_rate": 0.00018822246942118466, + "loss": 0.3991415977478027, + "step": 400 + }, + { + "epoch": 0.33289353496397034, + "grad_norm": 0.15789403021335602, + "learning_rate": 0.00018751979881160029, + "loss": 0.40332279205322263, + "step": 410 + }, + { + "epoch": 0.34101288947528674, + "grad_norm": 0.15686365962028503, + "learning_rate": 0.0001867981607330451, + "loss": 0.3878762722015381, + "step": 420 + }, + { + "epoch": 0.3491322439866031, + "grad_norm": 0.15789690613746643, + "learning_rate": 0.00018605771158039253, + "loss": 0.3754732131958008, + "step": 430 + }, + { + "epoch": 0.35725159849791943, + "grad_norm": 0.14583982527256012, + "learning_rate": 0.00018529861182529036, + "loss": 0.4119413375854492, + "step": 440 + }, + { + "epoch": 0.3653709530092358, + "grad_norm": 0.16271716356277466, + "learning_rate": 0.0001845210259813829, + "loss": 0.4371773719787598, + "step": 450 + }, + { + "epoch": 0.3734903075205521, + "grad_norm": 0.15252803266048431, + "learning_rate": 0.00018372512256865724, + "loss": 0.3985795021057129, + "step": 460 + }, + { + "epoch": 0.38160966203186847, + "grad_norm": 0.17694011330604553, + "learning_rate": 0.00018291107407692128, + "loss": 0.40482492446899415, + "step": 470 + }, + { + "epoch": 0.3897290165431848, + "grad_norm": 0.15677419304847717, + "learning_rate": 0.00018207905692842134, + "loss": 0.3925381898880005, + "step": 480 + }, + { + "epoch": 0.39784837105450116, + "grad_norm": 0.15828488767147064, + "learning_rate": 0.00018122925143960775, + "loss": 0.3869333028793335, + "step": 490 + }, + { + "epoch": 0.4059677255658175, + "grad_norm": 0.13660173118114471, + "learning_rate": 0.000180361841782056, + "loss": 0.4138071060180664, + "step": 500 + }, + { + "epoch": 0.41408708007713385, + "grad_norm": 0.164328932762146, + "learning_rate": 0.00017947701594255299, + "loss": 0.4766359806060791, + "step": 510 + }, + { + "epoch": 0.4222064345884502, + "grad_norm": 0.13619564473628998, + "learning_rate": 0.00017857496568235597, + "loss": 0.3740208625793457, + "step": 520 + }, + { + "epoch": 0.43032578909976654, + "grad_norm": 0.1389133632183075, + "learning_rate": 0.00017765588649563372, + "loss": 0.4194491386413574, + "step": 530 + }, + { + "epoch": 0.43844514361108294, + "grad_norm": 0.16105148196220398, + "learning_rate": 0.00017671997756709863, + "loss": 0.37844417095184324, + "step": 540 + }, + { + "epoch": 0.4465644981223993, + "grad_norm": 0.1176551878452301, + "learning_rate": 0.00017576744172883899, + "loss": 0.3884027719497681, + "step": 550 + }, + { + "epoch": 0.45468385263371563, + "grad_norm": 0.15062262117862701, + "learning_rate": 0.0001747984854163609, + "loss": 0.4128002643585205, + "step": 560 + }, + { + "epoch": 0.462803207145032, + "grad_norm": 0.14474593102931976, + "learning_rate": 0.00017381331862384894, + "loss": 0.37835040092468264, + "step": 570 + }, + { + "epoch": 0.4709225616563483, + "grad_norm": 0.11984218657016754, + "learning_rate": 0.00017281215485865603, + "loss": 0.3885404109954834, + "step": 580 + }, + { + "epoch": 0.47904191616766467, + "grad_norm": 0.11157386004924774, + "learning_rate": 0.00017179521109503146, + "loss": 0.41469721794128417, + "step": 590 + }, + { + "epoch": 0.487161270678981, + "grad_norm": 0.15861837565898895, + "learning_rate": 0.00017076270772709807, + "loss": 0.40916032791137696, + "step": 600 + }, + { + "epoch": 0.49528062519029736, + "grad_norm": 0.16919773817062378, + "learning_rate": 0.00016971486852108763, + "loss": 0.38907546997070314, + "step": 610 + }, + { + "epoch": 0.5033999797016138, + "grad_norm": 0.1534120887517929, + "learning_rate": 0.00016865192056684605, + "loss": 0.3835587978363037, + "step": 620 + }, + { + "epoch": 0.51151933421293, + "grad_norm": 0.1444127857685089, + "learning_rate": 0.00016757409422861802, + "loss": 0.41408615112304686, + "step": 630 + }, + { + "epoch": 0.5196386887242465, + "grad_norm": 0.16517969965934753, + "learning_rate": 0.00016648162309512173, + "loss": 0.3881347179412842, + "step": 640 + }, + { + "epoch": 0.5277580432355627, + "grad_norm": 0.16764643788337708, + "learning_rate": 0.00016537474392892528, + "loss": 0.36968770027160647, + "step": 650 + }, + { + "epoch": 0.5358773977468791, + "grad_norm": 0.15984776616096497, + "learning_rate": 0.0001642536966151349, + "loss": 0.4436800003051758, + "step": 660 + }, + { + "epoch": 0.5439967522581954, + "grad_norm": 0.15119516849517822, + "learning_rate": 0.00016311872410940676, + "loss": 0.36648738384246826, + "step": 670 + }, + { + "epoch": 0.5521161067695118, + "grad_norm": 0.17760701477527618, + "learning_rate": 0.00016197007238529277, + "loss": 0.43828520774841306, + "step": 680 + }, + { + "epoch": 0.5602354612808281, + "grad_norm": 0.15702351927757263, + "learning_rate": 0.00016080799038093311, + "loss": 0.39908370971679685, + "step": 690 + }, + { + "epoch": 0.5683548157921445, + "grad_norm": 0.16063162684440613, + "learning_rate": 0.0001596327299451054, + "loss": 0.3547415256500244, + "step": 700 + }, + { + "epoch": 0.5764741703034608, + "grad_norm": 0.15705077350139618, + "learning_rate": 0.000158444545782644, + "loss": 0.38064041137695315, + "step": 710 + }, + { + "epoch": 0.5845935248147772, + "grad_norm": 0.2802039086818695, + "learning_rate": 0.0001572436953992394, + "loss": 0.34356114864349363, + "step": 720 + }, + { + "epoch": 0.5927128793260936, + "grad_norm": 0.14802053570747375, + "learning_rate": 0.00015603043904563148, + "loss": 0.44878721237182617, + "step": 730 + }, + { + "epoch": 0.6008322338374099, + "grad_norm": 0.15852048993110657, + "learning_rate": 0.00015480503966120704, + "loss": 0.40053658485412597, + "step": 740 + }, + { + "epoch": 0.6089515883487263, + "grad_norm": 0.15426747500896454, + "learning_rate": 0.00015356776281701538, + "loss": 0.404225492477417, + "step": 750 + }, + { + "epoch": 0.6170709428600426, + "grad_norm": 0.1420115828514099, + "learning_rate": 0.000152318876658213, + "loss": 0.37903261184692383, + "step": 760 + }, + { + "epoch": 0.625190297371359, + "grad_norm": 0.13923387229442596, + "learning_rate": 0.00015105865184595073, + "loss": 0.35583546161651614, + "step": 770 + }, + { + "epoch": 0.6333096518826753, + "grad_norm": 0.14876466989517212, + "learning_rate": 0.00014978736149871545, + "loss": 0.3251772165298462, + "step": 780 + }, + { + "epoch": 0.6414290063939917, + "grad_norm": 0.17565123736858368, + "learning_rate": 0.0001485052811331393, + "loss": 0.39765985012054444, + "step": 790 + }, + { + "epoch": 0.649548360905308, + "grad_norm": 0.15443134307861328, + "learning_rate": 0.00014721268860428912, + "loss": 0.3529685020446777, + "step": 800 + }, + { + "epoch": 0.6576677154166244, + "grad_norm": 0.15266218781471252, + "learning_rate": 0.00014590986404544923, + "loss": 0.4115382194519043, + "step": 810 + }, + { + "epoch": 0.6657870699279407, + "grad_norm": 0.14183001220226288, + "learning_rate": 0.00014459708980741037, + "loss": 0.4038706302642822, + "step": 820 + }, + { + "epoch": 0.6739064244392571, + "grad_norm": 0.20107750594615936, + "learning_rate": 0.00014327465039727785, + "loss": 0.42904024124145507, + "step": 830 + }, + { + "epoch": 0.6820257789505735, + "grad_norm": 0.15056397020816803, + "learning_rate": 0.00014194283241681293, + "loss": 0.3807892084121704, + "step": 840 + }, + { + "epoch": 0.6901451334618898, + "grad_norm": 0.16432157158851624, + "learning_rate": 0.00014060192450031958, + "loss": 0.40647153854370116, + "step": 850 + }, + { + "epoch": 0.6982644879732062, + "grad_norm": 0.14384903013706207, + "learning_rate": 0.0001392522172520913, + "loss": 0.400847864151001, + "step": 860 + }, + { + "epoch": 0.7063838424845225, + "grad_norm": 0.16257992386817932, + "learning_rate": 0.00013789400318343068, + "loss": 0.4034707069396973, + "step": 870 + }, + { + "epoch": 0.7145031969958389, + "grad_norm": 0.1456725299358368, + "learning_rate": 0.00013652757664925572, + "loss": 0.3958974123001099, + "step": 880 + }, + { + "epoch": 0.7226225515071552, + "grad_norm": 0.1645933985710144, + "learning_rate": 0.00013515323378430664, + "loss": 0.39889843463897706, + "step": 890 + }, + { + "epoch": 0.7307419060184716, + "grad_norm": 0.14808154106140137, + "learning_rate": 0.00013377127243896706, + "loss": 0.39709608554840087, + "step": 900 + }, + { + "epoch": 0.7388612605297878, + "grad_norm": 0.15682613849639893, + "learning_rate": 0.00013238199211471305, + "loss": 0.3838841199874878, + "step": 910 + }, + { + "epoch": 0.7469806150411042, + "grad_norm": 0.15188175439834595, + "learning_rate": 0.00013098569389920488, + "loss": 0.4285408973693848, + "step": 920 + }, + { + "epoch": 0.7550999695524205, + "grad_norm": 0.16449961066246033, + "learning_rate": 0.00012958268040103434, + "loss": 0.37526252269744875, + "step": 930 + }, + { + "epoch": 0.7632193240637369, + "grad_norm": 0.1517837643623352, + "learning_rate": 0.00012817325568414297, + "loss": 0.40034284591674807, + "step": 940 + }, + { + "epoch": 0.7713386785750533, + "grad_norm": 0.18229644000530243, + "learning_rate": 0.00012675772520192476, + "loss": 0.37904250621795654, + "step": 950 + }, + { + "epoch": 0.7794580330863696, + "grad_norm": 0.15189775824546814, + "learning_rate": 0.00012533639573102754, + "loss": 0.4246711254119873, + "step": 960 + }, + { + "epoch": 0.787577387597686, + "grad_norm": 0.15175221860408783, + "learning_rate": 0.0001239095753048678, + "loss": 0.3818449735641479, + "step": 970 + }, + { + "epoch": 0.7956967421090023, + "grad_norm": 0.14126037061214447, + "learning_rate": 0.00012247757314687297, + "loss": 0.3847095251083374, + "step": 980 + }, + { + "epoch": 0.8038160966203187, + "grad_norm": 0.17514625191688538, + "learning_rate": 0.00012104069960346596, + "loss": 0.40877785682678225, + "step": 990 + }, + { + "epoch": 0.811935451131635, + "grad_norm": 0.1650720089673996, + "learning_rate": 0.00011959926607680639, + "loss": 0.40711078643798826, + "step": 1000 + }, + { + "epoch": 0.8200548056429514, + "grad_norm": 0.15258049964904785, + "learning_rate": 0.00011815358495730253, + "loss": 0.40592288970947266, + "step": 1010 + }, + { + "epoch": 0.8281741601542677, + "grad_norm": 0.14057976007461548, + "learning_rate": 0.00011670396955590974, + "loss": 0.3216592073440552, + "step": 1020 + }, + { + "epoch": 0.8362935146655841, + "grad_norm": 0.16660679876804352, + "learning_rate": 0.00011525073403622894, + "loss": 0.40019774436950684, + "step": 1030 + }, + { + "epoch": 0.8444128691769004, + "grad_norm": 0.17680172622203827, + "learning_rate": 0.0001137941933464204, + "loss": 0.4132580280303955, + "step": 1040 + }, + { + "epoch": 0.8525322236882168, + "grad_norm": 0.17041870951652527, + "learning_rate": 0.0001123346631509477, + "loss": 0.3415886878967285, + "step": 1050 + }, + { + "epoch": 0.8606515781995331, + "grad_norm": 0.15096868574619293, + "learning_rate": 0.00011087245976216607, + "loss": 0.4133938789367676, + "step": 1060 + }, + { + "epoch": 0.8687709327108495, + "grad_norm": 0.15110765397548676, + "learning_rate": 0.00010940790007177069, + "loss": 0.38502039909362795, + "step": 1070 + }, + { + "epoch": 0.8768902872221659, + "grad_norm": 0.1299409419298172, + "learning_rate": 0.00010794130148211918, + "loss": 0.36754612922668456, + "step": 1080 + }, + { + "epoch": 0.8850096417334822, + "grad_norm": 0.16098879277706146, + "learning_rate": 0.00010647298183744359, + "loss": 0.4300854206085205, + "step": 1090 + }, + { + "epoch": 0.8931289962447986, + "grad_norm": 0.18567131459712982, + "learning_rate": 0.00010500325935496654, + "loss": 0.4555531978607178, + "step": 1100 + }, + { + "epoch": 0.9012483507561149, + "grad_norm": 0.15725167095661163, + "learning_rate": 0.00010353245255593645, + "loss": 0.40347743034362793, + "step": 1110 + }, + { + "epoch": 0.9093677052674313, + "grad_norm": 0.18014128506183624, + "learning_rate": 0.0001020608801965971, + "loss": 0.43356914520263673, + "step": 1120 + }, + { + "epoch": 0.9174870597787476, + "grad_norm": 0.14646700024604797, + "learning_rate": 0.00010058886119910603, + "loss": 0.3579983949661255, + "step": 1130 + }, + { + "epoch": 0.925606414290064, + "grad_norm": 0.15054835379123688, + "learning_rate": 9.911671458241707e-05, + "loss": 0.412873363494873, + "step": 1140 + }, + { + "epoch": 0.9337257688013803, + "grad_norm": 0.1782434582710266, + "learning_rate": 9.764475939314199e-05, + "loss": 0.3661553144454956, + "step": 1150 + }, + { + "epoch": 0.9418451233126967, + "grad_norm": 0.14244233071804047, + "learning_rate": 9.6173314636406e-05, + "loss": 0.33595120906829834, + "step": 1160 + }, + { + "epoch": 0.9499644778240129, + "grad_norm": 0.15346868336200714, + "learning_rate": 9.470269920671242e-05, + "loss": 0.35301713943481444, + "step": 1170 + }, + { + "epoch": 0.9580838323353293, + "grad_norm": 0.17095577716827393, + "learning_rate": 9.323323181883093e-05, + "loss": 0.46831064224243163, + "step": 1180 + }, + { + "epoch": 0.9662031868466457, + "grad_norm": 0.16479066014289856, + "learning_rate": 9.176523093872545e-05, + "loss": 0.35177159309387207, + "step": 1190 + }, + { + "epoch": 0.974322541357962, + "grad_norm": 0.15938977897167206, + "learning_rate": 9.02990147145352e-05, + "loss": 0.40160298347473145, + "step": 1200 + }, + { + "epoch": 0.9824418958692784, + "grad_norm": 0.15273737907409668, + "learning_rate": 8.883490090762524e-05, + "loss": 0.3344574451446533, + "step": 1210 + }, + { + "epoch": 0.9905612503805947, + "grad_norm": 0.17632175981998444, + "learning_rate": 8.737320682372048e-05, + "loss": 0.3946251392364502, + "step": 1220 + }, + { + "epoch": 0.9986806048919111, + "grad_norm": 0.1546667516231537, + "learning_rate": 8.59142492441384e-05, + "loss": 0.38449108600616455, + "step": 1230 + }, + { + "epoch": 1.0064954836090532, + "grad_norm": 0.1582242101430893, + "learning_rate": 8.445834435713589e-05, + "loss": 0.35192313194274905, + "step": 1240 + }, + { + "epoch": 1.0146148381203695, + "grad_norm": 0.16060605645179749, + "learning_rate": 8.300580768938389e-05, + "loss": 0.3984487295150757, + "step": 1250 + }, + { + "epoch": 1.0227341926316857, + "grad_norm": 0.15913701057434082, + "learning_rate": 8.155695403758614e-05, + "loss": 0.3666527271270752, + "step": 1260 + }, + { + "epoch": 1.030853547143002, + "grad_norm": 0.2222735434770584, + "learning_rate": 8.011209740025568e-05, + "loss": 0.39426436424255373, + "step": 1270 + }, + { + "epoch": 1.0389729016543185, + "grad_norm": 0.14628788828849792, + "learning_rate": 7.867155090966429e-05, + "loss": 0.3448423147201538, + "step": 1280 + }, + { + "epoch": 1.0470922561656348, + "grad_norm": 0.1674235761165619, + "learning_rate": 7.723562676398017e-05, + "loss": 0.3735038280487061, + "step": 1290 + }, + { + "epoch": 1.0552116106769511, + "grad_norm": 0.1577482521533966, + "learning_rate": 7.580463615960731e-05, + "loss": 0.36143453121185304, + "step": 1300 + }, + { + "epoch": 1.0633309651882676, + "grad_norm": 0.15055105090141296, + "learning_rate": 7.437888922374276e-05, + "loss": 0.3465540647506714, + "step": 1310 + }, + { + "epoch": 1.071450319699584, + "grad_norm": 0.16190367937088013, + "learning_rate": 7.2958694947165e-05, + "loss": 0.3162075519561768, + "step": 1320 + }, + { + "epoch": 1.0795696742109002, + "grad_norm": 0.13373522460460663, + "learning_rate": 7.154436111726885e-05, + "loss": 0.2877171516418457, + "step": 1330 + }, + { + "epoch": 1.0876890287222165, + "grad_norm": 0.1537173092365265, + "learning_rate": 7.013619425136125e-05, + "loss": 0.371155834197998, + "step": 1340 + }, + { + "epoch": 1.095808383233533, + "grad_norm": 0.153018981218338, + "learning_rate": 6.873449953023205e-05, + "loss": 0.3403003454208374, + "step": 1350 + }, + { + "epoch": 1.1039277377448493, + "grad_norm": 0.14698824286460876, + "learning_rate": 6.733958073201484e-05, + "loss": 0.3563337802886963, + "step": 1360 + }, + { + "epoch": 1.1120470922561656, + "grad_norm": 0.17373280227184296, + "learning_rate": 6.595174016635132e-05, + "loss": 0.36922128200531007, + "step": 1370 + }, + { + "epoch": 1.120166446767482, + "grad_norm": 0.1971225142478943, + "learning_rate": 6.457127860887424e-05, + "loss": 0.40238251686096194, + "step": 1380 + }, + { + "epoch": 1.1282858012787984, + "grad_norm": 0.1588146984577179, + "learning_rate": 6.319849523602271e-05, + "loss": 0.38647644519805907, + "step": 1390 + }, + { + "epoch": 1.1364051557901147, + "grad_norm": 0.1998201310634613, + "learning_rate": 6.18336875602039e-05, + "loss": 0.3392190933227539, + "step": 1400 + }, + { + "epoch": 1.144524510301431, + "grad_norm": 0.1279604434967041, + "learning_rate": 6.047715136531587e-05, + "loss": 0.29073169231414797, + "step": 1410 + }, + { + "epoch": 1.1526438648127475, + "grad_norm": 0.17609012126922607, + "learning_rate": 5.9129180642644414e-05, + "loss": 0.3901878118515015, + "step": 1420 + }, + { + "epoch": 1.1607632193240638, + "grad_norm": 0.1663195639848709, + "learning_rate": 5.779006752714868e-05, + "loss": 0.3095200300216675, + "step": 1430 + }, + { + "epoch": 1.16888257383538, + "grad_norm": 0.14723604917526245, + "learning_rate": 5.646010223414924e-05, + "loss": 0.3879781007766724, + "step": 1440 + }, + { + "epoch": 1.1770019283466964, + "grad_norm": 0.19692786037921906, + "learning_rate": 5.513957299643194e-05, + "loss": 0.3436476469039917, + "step": 1450 + }, + { + "epoch": 1.1851212828580129, + "grad_norm": 0.14053191244602203, + "learning_rate": 5.382876600178155e-05, + "loss": 0.32699582576751707, + "step": 1460 + }, + { + "epoch": 1.1932406373693292, + "grad_norm": 0.18614161014556885, + "learning_rate": 5.25279653309584e-05, + "loss": 0.3756012201309204, + "step": 1470 + }, + { + "epoch": 1.2013599918806455, + "grad_norm": 0.17593547701835632, + "learning_rate": 5.1237452896132067e-05, + "loss": 0.4036771297454834, + "step": 1480 + }, + { + "epoch": 1.2094793463919618, + "grad_norm": 0.1469552218914032, + "learning_rate": 4.9957508379784704e-05, + "loss": 0.35532774925231936, + "step": 1490 + }, + { + "epoch": 1.2175987009032783, + "grad_norm": 0.1465003490447998, + "learning_rate": 4.86884091740975e-05, + "loss": 0.3272955656051636, + "step": 1500 + }, + { + "epoch": 1.2257180554145946, + "grad_norm": 0.16992369294166565, + "learning_rate": 4.7430430320834e-05, + "loss": 0.3861941576004028, + "step": 1510 + }, + { + "epoch": 1.2338374099259108, + "grad_norm": 0.19381046295166016, + "learning_rate": 4.618384445173228e-05, + "loss": 0.36703226566314695, + "step": 1520 + }, + { + "epoch": 1.2419567644372274, + "grad_norm": 0.1563887596130371, + "learning_rate": 4.494892172941965e-05, + "loss": 0.40213809013366697, + "step": 1530 + }, + { + "epoch": 1.2500761189485436, + "grad_norm": 0.145489901304245, + "learning_rate": 4.372592978886254e-05, + "loss": 0.344010591506958, + "step": 1540 + }, + { + "epoch": 1.25819547345986, + "grad_norm": 0.16564379632472992, + "learning_rate": 4.2515133679364116e-05, + "loss": 0.3600982904434204, + "step": 1550 + }, + { + "epoch": 1.2663148279711762, + "grad_norm": 0.12342356890439987, + "learning_rate": 4.13167958071221e-05, + "loss": 0.32795798778533936, + "step": 1560 + }, + { + "epoch": 1.2744341824824925, + "grad_norm": 0.18176662921905518, + "learning_rate": 4.013117587835978e-05, + "loss": 0.36577463150024414, + "step": 1570 + }, + { + "epoch": 1.282553536993809, + "grad_norm": 0.1916268765926361, + "learning_rate": 3.895853084304176e-05, + "loss": 0.39234256744384766, + "step": 1580 + }, + { + "epoch": 1.2906728915051253, + "grad_norm": 0.1897222399711609, + "learning_rate": 3.779911483918739e-05, + "loss": 0.41258983612060546, + "step": 1590 + }, + { + "epoch": 1.2987922460164416, + "grad_norm": 0.15678349137306213, + "learning_rate": 3.665317913779337e-05, + "loss": 0.3665084600448608, + "step": 1600 + }, + { + "epoch": 1.3069116005277581, + "grad_norm": 0.16308161616325378, + "learning_rate": 3.552097208837775e-05, + "loss": 0.3931357622146606, + "step": 1610 + }, + { + "epoch": 1.3150309550390744, + "grad_norm": 0.1778445839881897, + "learning_rate": 3.4402739065157266e-05, + "loss": 0.3759305477142334, + "step": 1620 + }, + { + "epoch": 1.3231503095503907, + "grad_norm": 0.1780257523059845, + "learning_rate": 3.3298722413869155e-05, + "loss": 0.3472525358200073, + "step": 1630 + }, + { + "epoch": 1.3312696640617072, + "grad_norm": 0.14955449104309082, + "learning_rate": 3.2209161399249674e-05, + "loss": 0.34793896675109864, + "step": 1640 + }, + { + "epoch": 1.3393890185730235, + "grad_norm": 0.20207709074020386, + "learning_rate": 3.1134292153180056e-05, + "loss": 0.3454656362533569, + "step": 1650 + }, + { + "epoch": 1.3475083730843398, + "grad_norm": 0.18875418603420258, + "learning_rate": 3.007434762351147e-05, + "loss": 0.3456529140472412, + "step": 1660 + }, + { + "epoch": 1.355627727595656, + "grad_norm": 0.18712455034255981, + "learning_rate": 2.9029557523580253e-05, + "loss": 0.33401539325714114, + "step": 1670 + }, + { + "epoch": 1.3637470821069724, + "grad_norm": 0.16952762007713318, + "learning_rate": 2.800014828242381e-05, + "loss": 0.3649503231048584, + "step": 1680 + }, + { + "epoch": 1.3718664366182889, + "grad_norm": 0.19082432985305786, + "learning_rate": 2.698634299570857e-05, + "loss": 0.3909872770309448, + "step": 1690 + }, + { + "epoch": 1.3799857911296052, + "grad_norm": 0.16776010394096375, + "learning_rate": 2.5988361377380188e-05, + "loss": 0.3379994869232178, + "step": 1700 + }, + { + "epoch": 1.3881051456409215, + "grad_norm": 0.19785159826278687, + "learning_rate": 2.5006419712046636e-05, + "loss": 0.3403695821762085, + "step": 1710 + }, + { + "epoch": 1.396224500152238, + "grad_norm": 0.12651121616363525, + "learning_rate": 2.4040730808104706e-05, + "loss": 0.37059574127197265, + "step": 1720 + }, + { + "epoch": 1.4043438546635543, + "grad_norm": 0.18700380623340607, + "learning_rate": 2.3091503951619543e-05, + "loss": 0.4034583568572998, + "step": 1730 + }, + { + "epoch": 1.4124632091748706, + "grad_norm": 0.1756463646888733, + "learning_rate": 2.2158944860967946e-05, + "loss": 0.3308366060256958, + "step": 1740 + }, + { + "epoch": 1.420582563686187, + "grad_norm": 0.19831162691116333, + "learning_rate": 2.1243255642254578e-05, + "loss": 0.3691343069076538, + "step": 1750 + }, + { + "epoch": 1.4287019181975034, + "grad_norm": 0.1685105711221695, + "learning_rate": 2.0344634745511015e-05, + "loss": 0.3646685600280762, + "step": 1760 + }, + { + "epoch": 1.4368212727088197, + "grad_norm": 0.1513417512178421, + "learning_rate": 1.9463276921687458e-05, + "loss": 0.3358032464981079, + "step": 1770 + }, + { + "epoch": 1.444940627220136, + "grad_norm": 0.21079151332378387, + "learning_rate": 1.8599373180445688e-05, + "loss": 0.38408379554748534, + "step": 1780 + }, + { + "epoch": 1.4530599817314522, + "grad_norm": 0.1852787733078003, + "learning_rate": 1.775311074876329e-05, + "loss": 0.3572732925415039, + "step": 1790 + }, + { + "epoch": 1.4611793362427687, + "grad_norm": 0.18594121932983398, + "learning_rate": 1.6924673030357285e-05, + "loss": 0.34491288661956787, + "step": 1800 + }, + { + "epoch": 1.469298690754085, + "grad_norm": 0.16469211876392365, + "learning_rate": 1.6114239565936484e-05, + "loss": 0.3106041193008423, + "step": 1810 + }, + { + "epoch": 1.4774180452654013, + "grad_norm": 0.146048441529274, + "learning_rate": 1.532198599429122e-05, + "loss": 0.3674412965774536, + "step": 1820 + }, + { + "epoch": 1.4855373997767178, + "grad_norm": 0.18818271160125732, + "learning_rate": 1.454808401422837e-05, + "loss": 0.3938064336776733, + "step": 1830 + }, + { + "epoch": 1.4936567542880341, + "grad_norm": 0.20953674614429474, + "learning_rate": 1.379270134736057e-05, + "loss": 0.30992081165313723, + "step": 1840 + }, + { + "epoch": 1.5017761087993504, + "grad_norm": 0.21023158729076385, + "learning_rate": 1.3056001701757226e-05, + "loss": 0.3922957181930542, + "step": 1850 + }, + { + "epoch": 1.509895463310667, + "grad_norm": 0.18391859531402588, + "learning_rate": 1.233814473646524e-05, + "loss": 0.3312171459197998, + "step": 1860 + }, + { + "epoch": 1.518014817821983, + "grad_norm": 0.20905567705631256, + "learning_rate": 1.1639286026907581e-05, + "loss": 0.33843116760253905, + "step": 1870 + }, + { + "epoch": 1.5261341723332995, + "grad_norm": 0.2057563066482544, + "learning_rate": 1.0959577031166513e-05, + "loss": 0.32880287170410155, + "step": 1880 + }, + { + "epoch": 1.5342535268446158, + "grad_norm": 0.16004444658756256, + "learning_rate": 1.0299165057159332e-05, + "loss": 0.3609264850616455, + "step": 1890 + }, + { + "epoch": 1.542372881355932, + "grad_norm": 0.18283307552337646, + "learning_rate": 9.658193230713509e-06, + "loss": 0.36747682094573975, + "step": 1900 + }, + { + "epoch": 1.5504922358672486, + "grad_norm": 0.13987980782985687, + "learning_rate": 9.036800464548157e-06, + "loss": 0.3149809598922729, + "step": 1910 + }, + { + "epoch": 1.558611590378565, + "grad_norm": 0.20485147833824158, + "learning_rate": 8.435121428168613e-06, + "loss": 0.3814858436584473, + "step": 1920 + }, + { + "epoch": 1.5667309448898812, + "grad_norm": 0.19381378591060638, + "learning_rate": 7.853286518680503e-06, + "loss": 0.3389918565750122, + "step": 1930 + }, + { + "epoch": 1.5748502994011977, + "grad_norm": 0.1762656271457672, + "learning_rate": 7.291421832529921e-06, + "loss": 0.3758829355239868, + "step": 1940 + }, + { + "epoch": 1.582969653912514, + "grad_norm": 0.18566051125526428, + "learning_rate": 6.749649138175518e-06, + "loss": 0.361565375328064, + "step": 1950 + }, + { + "epoch": 1.5910890084238303, + "grad_norm": 0.1679965704679489, + "learning_rate": 6.228085849698495e-06, + "loss": 0.3467693567276001, + "step": 1960 + }, + { + "epoch": 1.5992083629351468, + "grad_norm": 0.19734881818294525, + "learning_rate": 5.726845001356573e-06, + "loss": 0.41715250015258787, + "step": 1970 + }, + { + "epoch": 1.6073277174464629, + "grad_norm": 0.20948296785354614, + "learning_rate": 5.246035223086821e-06, + "loss": 0.3086181879043579, + "step": 1980 + }, + { + "epoch": 1.6154470719577794, + "grad_norm": 0.2349746823310852, + "learning_rate": 4.785760716963205e-06, + "loss": 0.2819353580474854, + "step": 1990 + }, + { + "epoch": 1.6235664264690957, + "grad_norm": 0.15716052055358887, + "learning_rate": 4.346121234613732e-06, + "loss": 0.4032479763031006, + "step": 2000 + }, + { + "epoch": 1.631685780980412, + "grad_norm": 0.1870564967393875, + "learning_rate": 3.927212055602003e-06, + "loss": 0.3259021759033203, + "step": 2010 + }, + { + "epoch": 1.6398051354917285, + "grad_norm": 0.1917184740304947, + "learning_rate": 3.5291239667781253e-06, + "loss": 0.3619376182556152, + "step": 2020 + }, + { + "epoch": 1.6479244900030448, + "grad_norm": 0.15155203640460968, + "learning_rate": 3.1519432426031504e-06, + "loss": 0.3836283445358276, + "step": 2030 + }, + { + "epoch": 1.656043844514361, + "grad_norm": 0.18562212586402893, + "learning_rate": 2.7957516264514593e-06, + "loss": 0.35469727516174315, + "step": 2040 + }, + { + "epoch": 1.6641631990256776, + "grad_norm": 0.23471137881278992, + "learning_rate": 2.4606263128952646e-06, + "loss": 0.4092714309692383, + "step": 2050 + }, + { + "epoch": 1.6722825535369938, + "grad_norm": 0.19046807289123535, + "learning_rate": 2.1466399309747364e-06, + "loss": 0.37486720085144043, + "step": 2060 + }, + { + "epoch": 1.6804019080483101, + "grad_norm": 0.18093442916870117, + "learning_rate": 1.8538605284577848e-06, + "loss": 0.3519495248794556, + "step": 2070 + }, + { + "epoch": 1.6885212625596266, + "grad_norm": 0.17989413440227509, + "learning_rate": 1.5823515570925763e-06, + "loss": 0.36248462200164794, + "step": 2080 + }, + { + "epoch": 1.6966406170709427, + "grad_norm": 0.18000203371047974, + "learning_rate": 1.3321718588561128e-06, + "loss": 0.377717113494873, + "step": 2090 + }, + { + "epoch": 1.7047599715822592, + "grad_norm": 0.1857496201992035, + "learning_rate": 1.1033756532019102e-06, + "loss": 0.3373147964477539, + "step": 2100 + }, + { + "epoch": 1.7128793260935755, + "grad_norm": 0.15915660560131073, + "learning_rate": 8.96012525309442e-07, + "loss": 0.35358049869537356, + "step": 2110 + }, + { + "epoch": 1.7209986806048918, + "grad_norm": 0.18095794320106506, + "learning_rate": 7.101274153379244e-07, + "loss": 0.34168615341186526, + "step": 2120 + }, + { + "epoch": 1.7291180351162083, + "grad_norm": 0.13066989183425903, + "learning_rate": 5.457606086868406e-07, + "loss": 0.31731865406036375, + "step": 2130 + }, + { + "epoch": 1.7372373896275246, + "grad_norm": 0.15085873007774353, + "learning_rate": 4.0294772726511274e-07, + "loss": 0.3172720193862915, + "step": 2140 + }, + { + "epoch": 1.745356744138841, + "grad_norm": 0.1692853718996048, + "learning_rate": 2.817197217711565e-07, + "loss": 0.3663973808288574, + "step": 2150 + }, + { + "epoch": 1.7534760986501574, + "grad_norm": 0.1765965223312378, + "learning_rate": 1.8210286498512307e-07, + "loss": 0.3134049415588379, + "step": 2160 + }, + { + "epoch": 1.7615954531614737, + "grad_norm": 0.17754477262496948, + "learning_rate": 1.0411874607501038e-07, + "loss": 0.32787179946899414, + "step": 2170 + }, + { + "epoch": 1.76971480767279, + "grad_norm": 0.2181764841079712, + "learning_rate": 4.778426591781626e-08, + "loss": 0.40297679901123046, + "step": 2180 + }, + { + "epoch": 1.7778341621841065, + "grad_norm": 0.14845119416713715, + "learning_rate": 1.3111633436779791e-08, + "loss": 0.3253025054931641, + "step": 2190 + }, + { + "epoch": 1.7859535166954226, + "grad_norm": 0.16625212132930756, + "learning_rate": 1.083629553977339e-10, + "loss": 0.3306998014450073, + "step": 2200 + }, + { + "epoch": 0.8465405793631793, + "grad_norm": 0.31709548830986023, + "learning_rate": 0.0001457833924251086, + "loss": 0.6895709991455078, + "step": 2210 + }, + { + "epoch": 0.8503710797222888, + "grad_norm": 0.22089441120624542, + "learning_rate": 0.0001453028317991183, + "loss": 0.6232875347137451, + "step": 2220 + }, + { + "epoch": 0.8542015800813981, + "grad_norm": 0.22472961246967316, + "learning_rate": 0.00014482095116054422, + "loss": 0.580645751953125, + "step": 2230 + }, + { + "epoch": 0.8580320804405075, + "grad_norm": 0.18781282007694244, + "learning_rate": 0.0001443377645501975, + "loss": 0.5852691173553467, + "step": 2240 + }, + { + "epoch": 0.861862580799617, + "grad_norm": 0.3779642581939697, + "learning_rate": 0.00014385328604694212, + "loss": 0.5722718238830566, + "step": 2250 + }, + { + "epoch": 0.8656930811587263, + "grad_norm": 0.23427145183086395, + "learning_rate": 0.0001433675297672846, + "loss": 0.566037940979004, + "step": 2260 + }, + { + "epoch": 0.8695235815178358, + "grad_norm": 0.2183203548192978, + "learning_rate": 0.00014288050986496268, + "loss": 0.6243879795074463, + "step": 2270 + }, + { + "epoch": 0.8733540818769452, + "grad_norm": 0.2532879412174225, + "learning_rate": 0.00014239224053053302, + "loss": 0.5365942001342774, + "step": 2280 + }, + { + "epoch": 0.8771845822360546, + "grad_norm": 0.20788337290287018, + "learning_rate": 0.00014190273599095762, + "loss": 0.5467002868652344, + "step": 2290 + }, + { + "epoch": 0.881015082595164, + "grad_norm": 0.2582492232322693, + "learning_rate": 0.00014141201050918922, + "loss": 0.567399263381958, + "step": 2300 + }, + { + "epoch": 0.8848455829542734, + "grad_norm": 0.19094614684581757, + "learning_rate": 0.00014092007838375592, + "loss": 0.563731336593628, + "step": 2310 + }, + { + "epoch": 0.8886760833133828, + "grad_norm": 0.24398261308670044, + "learning_rate": 0.00014042695394834436, + "loss": 0.5930374145507813, + "step": 2320 + }, + { + "epoch": 0.8925065836724922, + "grad_norm": 0.1616758406162262, + "learning_rate": 0.0001399326515713822, + "loss": 0.5320866584777832, + "step": 2330 + }, + { + "epoch": 0.8963370840316016, + "grad_norm": 0.19463369250297546, + "learning_rate": 0.00013943718565561936, + "loss": 0.5593301296234131, + "step": 2340 + }, + { + "epoch": 0.900167584390711, + "grad_norm": 0.2512662410736084, + "learning_rate": 0.0001389405706377084, + "loss": 0.5519943237304688, + "step": 2350 + }, + { + "epoch": 0.9039980847498205, + "grad_norm": 0.24107597768306732, + "learning_rate": 0.00013844282098778393, + "loss": 0.5739433765411377, + "step": 2360 + }, + { + "epoch": 0.9078285851089298, + "grad_norm": 0.18342378735542297, + "learning_rate": 0.00013794395120904089, + "loss": 0.5859064102172852, + "step": 2370 + }, + { + "epoch": 0.9116590854680393, + "grad_norm": 0.20521777868270874, + "learning_rate": 0.00013744397583731203, + "loss": 0.5629020214080811, + "step": 2380 + }, + { + "epoch": 0.9154895858271487, + "grad_norm": 0.17162705957889557, + "learning_rate": 0.00013694290944064435, + "loss": 0.5632124900817871, + "step": 2390 + }, + { + "epoch": 0.919320086186258, + "grad_norm": 0.18732701241970062, + "learning_rate": 0.00013644076661887452, + "loss": 0.5588642120361328, + "step": 2400 + }, + { + "epoch": 0.9231505865453675, + "grad_norm": 0.21033287048339844, + "learning_rate": 0.00013593756200320372, + "loss": 0.5421002864837646, + "step": 2410 + }, + { + "epoch": 0.9269810869044769, + "grad_norm": 0.18077102303504944, + "learning_rate": 0.0001354333102557712, + "loss": 0.5636842727661133, + "step": 2420 + }, + { + "epoch": 0.9308115872635863, + "grad_norm": 0.19449454545974731, + "learning_rate": 0.0001349280260692269, + "loss": 0.5634388446807861, + "step": 2430 + }, + { + "epoch": 0.9346420876226957, + "grad_norm": 0.21519041061401367, + "learning_rate": 0.00013442172416630355, + "loss": 0.552568769454956, + "step": 2440 + }, + { + "epoch": 0.9384725879818051, + "grad_norm": 0.21668848395347595, + "learning_rate": 0.0001339144192993876, + "loss": 0.5575977325439453, + "step": 2450 + }, + { + "epoch": 0.9423030883409146, + "grad_norm": 0.20259518921375275, + "learning_rate": 0.00013340612625008946, + "loss": 0.5953729629516602, + "step": 2460 + }, + { + "epoch": 0.946133588700024, + "grad_norm": 0.22012926638126373, + "learning_rate": 0.0001328968598288127, + "loss": 0.5506711006164551, + "step": 2470 + }, + { + "epoch": 0.9499640890591333, + "grad_norm": 0.18549343943595886, + "learning_rate": 0.0001323866348743225, + "loss": 0.5871614456176758, + "step": 2480 + }, + { + "epoch": 0.9537945894182428, + "grad_norm": 0.1908208429813385, + "learning_rate": 0.00013187546625331335, + "loss": 0.5431451320648193, + "step": 2490 + }, + { + "epoch": 0.9576250897773522, + "grad_norm": 0.18781603872776031, + "learning_rate": 0.0001313633688599759, + "loss": 0.5061774730682373, + "step": 2500 + }, + { + "epoch": 0.9614555901364615, + "grad_norm": 0.2165912687778473, + "learning_rate": 0.0001308503576155629, + "loss": 0.5560242652893066, + "step": 2510 + }, + { + "epoch": 0.965286090495571, + "grad_norm": 0.21473945677280426, + "learning_rate": 0.00013033644746795445, + "loss": 0.5335087776184082, + "step": 2520 + }, + { + "epoch": 0.9691165908546804, + "grad_norm": 0.2197163999080658, + "learning_rate": 0.00012982165339122246, + "loss": 0.5561465263366699, + "step": 2530 + }, + { + "epoch": 0.9729470912137897, + "grad_norm": 0.21780231595039368, + "learning_rate": 0.00012930599038519434, + "loss": 0.5662136554718018, + "step": 2540 + }, + { + "epoch": 0.9767775915728992, + "grad_norm": 0.1910906732082367, + "learning_rate": 0.00012878947347501606, + "loss": 0.5577693462371827, + "step": 2550 + }, + { + "epoch": 0.9806080919320086, + "grad_norm": 0.18059995770454407, + "learning_rate": 0.0001282721177107141, + "loss": 0.531907606124878, + "step": 2560 + }, + { + "epoch": 0.9844385922911181, + "grad_norm": 0.24920019507408142, + "learning_rate": 0.00012775393816675718, + "loss": 0.497232723236084, + "step": 2570 + }, + { + "epoch": 0.9882690926502274, + "grad_norm": 0.2506183385848999, + "learning_rate": 0.00012723494994161682, + "loss": 0.5702355384826661, + "step": 2580 + }, + { + "epoch": 0.9920995930093368, + "grad_norm": 0.207411989569664, + "learning_rate": 0.00012671516815732767, + "loss": 0.5431533813476562, + "step": 2590 + }, + { + "epoch": 0.9959300933684463, + "grad_norm": 0.20407091081142426, + "learning_rate": 0.00012619460795904657, + "loss": 0.5356565952301026, + "step": 2600 + }, + { + "epoch": 0.9997605937275557, + "grad_norm": 0.19829393923282623, + "learning_rate": 0.00012567328451461152, + "loss": 0.5477075576782227, + "step": 2610 + }, + { + "epoch": 1.0034474503231985, + "grad_norm": 0.2388325333595276, + "learning_rate": 0.0001251512130140996, + "loss": 0.6198837280273437, + "step": 2620 + }, + { + "epoch": 1.007277950682308, + "grad_norm": 0.18306539952754974, + "learning_rate": 0.00012462840866938436, + "loss": 0.5606157779693604, + "step": 2630 + }, + { + "epoch": 1.0111084510414172, + "grad_norm": 0.19269554316997528, + "learning_rate": 0.00012410488671369275, + "loss": 0.5489321231842041, + "step": 2640 + }, + { + "epoch": 1.0149389514005267, + "grad_norm": 0.21272292733192444, + "learning_rate": 0.00012358066240116092, + "loss": 0.5239657878875732, + "step": 2650 + }, + { + "epoch": 1.0187694517596362, + "grad_norm": 0.18628379702568054, + "learning_rate": 0.00012305575100639014, + "loss": 0.4884448528289795, + "step": 2660 + }, + { + "epoch": 1.0225999521187454, + "grad_norm": 0.20898866653442383, + "learning_rate": 0.00012253016782400148, + "loss": 0.5124496459960938, + "step": 2670 + }, + { + "epoch": 1.026430452477855, + "grad_norm": 0.20223310589790344, + "learning_rate": 0.00012200392816819022, + "loss": 0.5053596019744873, + "step": 2680 + }, + { + "epoch": 1.0302609528369644, + "grad_norm": 0.20589347183704376, + "learning_rate": 0.00012147704737227971, + "loss": 0.5432235717773437, + "step": 2690 + }, + { + "epoch": 1.0340914531960737, + "grad_norm": 0.19833305478096008, + "learning_rate": 0.0001209495407882746, + "loss": 0.507619047164917, + "step": 2700 + }, + { + "epoch": 1.0379219535551831, + "grad_norm": 0.21857035160064697, + "learning_rate": 0.0001204214237864133, + "loss": 0.5090025901794434, + "step": 2710 + }, + { + "epoch": 1.0417524539142926, + "grad_norm": 0.23668751120567322, + "learning_rate": 0.00011989271175472037, + "loss": 0.5485597610473633, + "step": 2720 + }, + { + "epoch": 1.0455829542734019, + "grad_norm": 0.19491468369960785, + "learning_rate": 0.00011936342009855805, + "loss": 0.5889732360839843, + "step": 2730 + }, + { + "epoch": 1.0494134546325113, + "grad_norm": 0.23975807428359985, + "learning_rate": 0.00011883356424017748, + "loss": 0.5385537624359131, + "step": 2740 + }, + { + "epoch": 1.0532439549916208, + "grad_norm": 0.22210931777954102, + "learning_rate": 0.00011830315961826917, + "loss": 0.5223836898803711, + "step": 2750 + }, + { + "epoch": 1.05707445535073, + "grad_norm": 0.23908647894859314, + "learning_rate": 0.00011777222168751325, + "loss": 0.5172951221466064, + "step": 2760 + }, + { + "epoch": 1.0609049557098396, + "grad_norm": 0.19327178597450256, + "learning_rate": 0.00011724076591812918, + "loss": 0.5314321517944336, + "step": 2770 + }, + { + "epoch": 1.064735456068949, + "grad_norm": 0.1691632866859436, + "learning_rate": 0.00011670880779542495, + "loss": 0.5226422786712647, + "step": 2780 + }, + { + "epoch": 1.0685659564280585, + "grad_norm": 0.21012499928474426, + "learning_rate": 0.00011617636281934592, + "loss": 0.5367197513580322, + "step": 2790 + }, + { + "epoch": 1.0723964567871678, + "grad_norm": 0.22527191042900085, + "learning_rate": 0.0001156434465040231, + "loss": 0.5030739784240723, + "step": 2800 + }, + { + "epoch": 1.0762269571462773, + "grad_norm": 0.2014586478471756, + "learning_rate": 0.00011511007437732117, + "loss": 0.5275944232940674, + "step": 2810 + }, + { + "epoch": 1.0800574575053867, + "grad_norm": 0.21319256722927094, + "learning_rate": 0.00011457626198038604, + "loss": 0.5280105113983155, + "step": 2820 + }, + { + "epoch": 1.083887957864496, + "grad_norm": 0.20912741124629974, + "learning_rate": 0.00011404202486719205, + "loss": 0.5142996311187744, + "step": 2830 + }, + { + "epoch": 1.0877184582236055, + "grad_norm": 0.2093651294708252, + "learning_rate": 0.00011350737860408864, + "loss": 0.539802885055542, + "step": 2840 + }, + { + "epoch": 1.091548958582715, + "grad_norm": 0.23947930335998535, + "learning_rate": 0.0001129723387693469, + "loss": 0.5196691036224366, + "step": 2850 + }, + { + "epoch": 1.0953794589418242, + "grad_norm": 0.21143850684165955, + "learning_rate": 0.00011243692095270564, + "loss": 0.5398859500885009, + "step": 2860 + }, + { + "epoch": 1.0992099593009337, + "grad_norm": 0.27163559198379517, + "learning_rate": 0.00011190114075491709, + "loss": 0.5032851696014404, + "step": 2870 + }, + { + "epoch": 1.1030404596600432, + "grad_norm": 0.1733262985944748, + "learning_rate": 0.00011136501378729248, + "loss": 0.539389181137085, + "step": 2880 + }, + { + "epoch": 1.1068709600191524, + "grad_norm": 0.17658951878547668, + "learning_rate": 0.00011082855567124692, + "loss": 0.5478601455688477, + "step": 2890 + }, + { + "epoch": 1.110701460378262, + "grad_norm": 0.19091221690177917, + "learning_rate": 0.00011029178203784443, + "loss": 0.5334963321685791, + "step": 2900 + }, + { + "epoch": 1.1145319607373714, + "grad_norm": 0.21165837347507477, + "learning_rate": 0.00010975470852734242, + "loss": 0.554966926574707, + "step": 2910 + }, + { + "epoch": 1.1183624610964806, + "grad_norm": 0.19263046979904175, + "learning_rate": 0.00010921735078873598, + "loss": 0.5330226421356201, + "step": 2920 + }, + { + "epoch": 1.12219296145559, + "grad_norm": 0.18461711704730988, + "learning_rate": 0.00010867972447930193, + "loss": 0.5291602611541748, + "step": 2930 + }, + { + "epoch": 1.1260234618146996, + "grad_norm": 0.18377310037612915, + "learning_rate": 0.0001081418452641425, + "loss": 0.5406131267547607, + "step": 2940 + }, + { + "epoch": 1.1298539621738088, + "grad_norm": 0.23681478202342987, + "learning_rate": 0.00010760372881572905, + "loss": 0.5551674365997314, + "step": 2950 + }, + { + "epoch": 1.1336844625329183, + "grad_norm": 0.19873519241809845, + "learning_rate": 0.00010706539081344529, + "loss": 0.5545490264892579, + "step": 2960 + }, + { + "epoch": 1.1375149628920278, + "grad_norm": 0.17395852506160736, + "learning_rate": 0.00010652684694313051, + "loss": 0.5141590118408204, + "step": 2970 + }, + { + "epoch": 1.1413454632511373, + "grad_norm": 0.21609513461589813, + "learning_rate": 0.00010598811289662243, + "loss": 0.49283924102783205, + "step": 2980 + }, + { + "epoch": 1.1451759636102465, + "grad_norm": 0.23576237261295319, + "learning_rate": 0.00010544920437130003, + "loss": 0.5531333446502685, + "step": 2990 + }, + { + "epoch": 1.149006463969356, + "grad_norm": 0.20940575003623962, + "learning_rate": 0.00010491013706962622, + "loss": 0.5683028221130371, + "step": 3000 + }, + { + "epoch": 1.1528369643284655, + "grad_norm": 0.24417303502559662, + "learning_rate": 0.00010437092669869024, + "loss": 0.5033949851989746, + "step": 3010 + }, + { + "epoch": 1.1566674646875748, + "grad_norm": 0.18906274437904358, + "learning_rate": 0.00010383158896974998, + "loss": 0.5204009532928466, + "step": 3020 + }, + { + "epoch": 1.1604979650466842, + "grad_norm": 0.20773115754127502, + "learning_rate": 0.00010329213959777431, + "loss": 0.5497435092926025, + "step": 3030 + }, + { + "epoch": 1.1643284654057937, + "grad_norm": 0.21606457233428955, + "learning_rate": 0.000102752594300985, + "loss": 0.5554033279418945, + "step": 3040 + }, + { + "epoch": 1.168158965764903, + "grad_norm": 0.24872884154319763, + "learning_rate": 0.00010221296880039888, + "loss": 0.520789384841919, + "step": 3050 + }, + { + "epoch": 1.1719894661240124, + "grad_norm": 0.23239879310131073, + "learning_rate": 0.00010167327881936979, + "loss": 0.554888916015625, + "step": 3060 + }, + { + "epoch": 1.175819966483122, + "grad_norm": 0.194828063249588, + "learning_rate": 0.00010113354008313025, + "loss": 0.5161662101745605, + "step": 3070 + }, + { + "epoch": 1.1796504668422312, + "grad_norm": 0.19345180690288544, + "learning_rate": 0.00010059376831833347, + "loss": 0.5281338691711426, + "step": 3080 + }, + { + "epoch": 1.1834809672013407, + "grad_norm": 0.2391313910484314, + "learning_rate": 0.00010005397925259496, + "loss": 0.5351935863494873, + "step": 3090 + }, + { + "epoch": 1.1873114675604501, + "grad_norm": 0.1873185932636261, + "learning_rate": 9.95141886140344e-05, + "loss": 0.47800097465515134, + "step": 3100 + }, + { + "epoch": 1.1911419679195594, + "grad_norm": 0.21092236042022705, + "learning_rate": 9.89744121308173e-05, + "loss": 0.5321640014648438, + "step": 3110 + }, + { + "epoch": 1.1949724682786689, + "grad_norm": 0.1895597130060196, + "learning_rate": 9.843466553069666e-05, + "loss": 0.5259033679962158, + "step": 3120 + }, + { + "epoch": 1.1988029686377784, + "grad_norm": 0.22822576761245728, + "learning_rate": 9.789496454055482e-05, + "loss": 0.5021588325500488, + "step": 3130 + }, + { + "epoch": 1.2026334689968876, + "grad_norm": 0.1812424212694168, + "learning_rate": 9.735532488594507e-05, + "loss": 0.5383275032043457, + "step": 3140 + }, + { + "epoch": 1.206463969355997, + "grad_norm": 0.21432311832904816, + "learning_rate": 9.681576229063369e-05, + "loss": 0.4902031898498535, + "step": 3150 + }, + { + "epoch": 1.2102944697151066, + "grad_norm": 0.2118760645389557, + "learning_rate": 9.627629247614152e-05, + "loss": 0.5405004978179931, + "step": 3160 + }, + { + "epoch": 1.214124970074216, + "grad_norm": 0.17781169712543488, + "learning_rate": 9.5736931161286e-05, + "loss": 0.5332688808441162, + "step": 3170 + }, + { + "epoch": 1.2179554704333253, + "grad_norm": 0.19811245799064636, + "learning_rate": 9.519769406172315e-05, + "loss": 0.5008315563201904, + "step": 3180 + }, + { + "epoch": 1.2217859707924348, + "grad_norm": 0.21972911059856415, + "learning_rate": 9.465859688948977e-05, + "loss": 0.5292376518249512, + "step": 3190 + }, + { + "epoch": 1.2256164711515443, + "grad_norm": 0.23009081184864044, + "learning_rate": 9.411965535254541e-05, + "loss": 0.5621660709381103, + "step": 3200 + }, + { + "epoch": 1.2294469715106535, + "grad_norm": 0.21291089057922363, + "learning_rate": 9.358088515431487e-05, + "loss": 0.5500400543212891, + "step": 3210 + }, + { + "epoch": 1.233277471869763, + "grad_norm": 0.19430555403232574, + "learning_rate": 9.304230199323049e-05, + "loss": 0.5366146564483643, + "step": 3220 + }, + { + "epoch": 1.2371079722288725, + "grad_norm": 0.18103627860546112, + "learning_rate": 9.250392156227489e-05, + "loss": 0.5162454128265381, + "step": 3230 + }, + { + "epoch": 1.2409384725879817, + "grad_norm": 0.1706976294517517, + "learning_rate": 9.196575954852351e-05, + "loss": 0.5634176731109619, + "step": 3240 + }, + { + "epoch": 1.2447689729470912, + "grad_norm": 0.1886712908744812, + "learning_rate": 9.142783163268781e-05, + "loss": 0.5125929832458496, + "step": 3250 + }, + { + "epoch": 1.2485994733062007, + "grad_norm": 0.2378716766834259, + "learning_rate": 9.089015348865811e-05, + "loss": 0.5268106460571289, + "step": 3260 + }, + { + "epoch": 1.25242997366531, + "grad_norm": 0.21824203431606293, + "learning_rate": 9.035274078304702e-05, + "loss": 0.5469632148742676, + "step": 3270 + }, + { + "epoch": 1.2562604740244194, + "grad_norm": 0.19580702483654022, + "learning_rate": 8.981560917473293e-05, + "loss": 0.5463891983032226, + "step": 3280 + }, + { + "epoch": 1.260090974383529, + "grad_norm": 0.24418896436691284, + "learning_rate": 8.92787743144038e-05, + "loss": 0.4903553485870361, + "step": 3290 + }, + { + "epoch": 1.2639214747426384, + "grad_norm": 0.1831478625535965, + "learning_rate": 8.874225184410098e-05, + "loss": 0.545778226852417, + "step": 3300 + }, + { + "epoch": 1.2677519751017476, + "grad_norm": 0.1959410458803177, + "learning_rate": 8.820605739676363e-05, + "loss": 0.49173221588134763, + "step": 3310 + }, + { + "epoch": 1.2715824754608571, + "grad_norm": 0.2172957807779312, + "learning_rate": 8.76702065957731e-05, + "loss": 0.5537460327148438, + "step": 3320 + }, + { + "epoch": 1.2754129758199664, + "grad_norm": 0.23475711047649384, + "learning_rate": 8.71347150544978e-05, + "loss": 0.5206586837768554, + "step": 3330 + }, + { + "epoch": 1.2792434761790759, + "grad_norm": 0.17950321733951569, + "learning_rate": 8.659959837583807e-05, + "loss": 0.5183176517486572, + "step": 3340 + }, + { + "epoch": 1.2830739765381853, + "grad_norm": 0.26022428274154663, + "learning_rate": 8.60648721517718e-05, + "loss": 0.5329340934753418, + "step": 3350 + }, + { + "epoch": 1.2869044768972948, + "grad_norm": 0.21860136091709137, + "learning_rate": 8.553055196289992e-05, + "loss": 0.5420422554016113, + "step": 3360 + }, + { + "epoch": 1.290734977256404, + "grad_norm": 0.20065219700336456, + "learning_rate": 8.499665337799254e-05, + "loss": 0.4903436183929443, + "step": 3370 + }, + { + "epoch": 1.2945654776155135, + "grad_norm": 0.2057187706232071, + "learning_rate": 8.446319195353524e-05, + "loss": 0.5572310447692871, + "step": 3380 + }, + { + "epoch": 1.2983959779746228, + "grad_norm": 0.17702226340770721, + "learning_rate": 8.393018323327591e-05, + "loss": 0.5058128833770752, + "step": 3390 + }, + { + "epoch": 1.3022264783337323, + "grad_norm": 0.19724802672863007, + "learning_rate": 8.339764274777165e-05, + "loss": 0.5044569969177246, + "step": 3400 + }, + { + "epoch": 1.3060569786928418, + "grad_norm": 0.1853686422109604, + "learning_rate": 8.286558601393642e-05, + "loss": 0.5192684173583985, + "step": 3410 + }, + { + "epoch": 1.3098874790519512, + "grad_norm": 0.2165904939174652, + "learning_rate": 8.233402853458877e-05, + "loss": 0.5493855476379395, + "step": 3420 + }, + { + "epoch": 1.3137179794110605, + "grad_norm": 0.18439316749572754, + "learning_rate": 8.180298579800035e-05, + "loss": 0.500330924987793, + "step": 3430 + }, + { + "epoch": 1.31754847977017, + "grad_norm": 0.1958782970905304, + "learning_rate": 8.127247327744434e-05, + "loss": 0.5382319450378418, + "step": 3440 + }, + { + "epoch": 1.3213789801292795, + "grad_norm": 0.1947711557149887, + "learning_rate": 8.074250643074484e-05, + "loss": 0.5128917217254638, + "step": 3450 + }, + { + "epoch": 1.3252094804883887, + "grad_norm": 0.17371414601802826, + "learning_rate": 8.021310069982624e-05, + "loss": 0.5215467929840087, + "step": 3460 + }, + { + "epoch": 1.3290399808474982, + "grad_norm": 0.19855856895446777, + "learning_rate": 7.968427151026355e-05, + "loss": 0.5010844230651855, + "step": 3470 + }, + { + "epoch": 1.3328704812066077, + "grad_norm": 0.18040011823177338, + "learning_rate": 7.915603427083268e-05, + "loss": 0.51223783493042, + "step": 3480 + }, + { + "epoch": 1.3367009815657172, + "grad_norm": 0.21727366745471954, + "learning_rate": 7.862840437306165e-05, + "loss": 0.5380761623382568, + "step": 3490 + }, + { + "epoch": 1.3405314819248264, + "grad_norm": 0.17868368327617645, + "learning_rate": 7.810139719078195e-05, + "loss": 0.543517017364502, + "step": 3500 + }, + { + "epoch": 1.3443619822839359, + "grad_norm": 0.23797963559627533, + "learning_rate": 7.757502807968075e-05, + "loss": 0.5299440860748291, + "step": 3510 + }, + { + "epoch": 1.3481924826430451, + "grad_norm": 0.20597504079341888, + "learning_rate": 7.704931237685342e-05, + "loss": 0.5269464969635009, + "step": 3520 + }, + { + "epoch": 1.3520229830021546, + "grad_norm": 0.21105614304542542, + "learning_rate": 7.652426540035657e-05, + "loss": 0.5518492221832275, + "step": 3530 + }, + { + "epoch": 1.355853483361264, + "grad_norm": 0.2271437793970108, + "learning_rate": 7.599990244876183e-05, + "loss": 0.5539456844329834, + "step": 3540 + }, + { + "epoch": 1.3596839837203736, + "grad_norm": 0.20776766538619995, + "learning_rate": 7.547623880070993e-05, + "loss": 0.5296282291412353, + "step": 3550 + }, + { + "epoch": 1.3079467156637574, + "grad_norm": 0.2367064505815506, + "learning_rate": 7.495328971446578e-05, + "loss": 0.6062966346740722, + "step": 3560 + }, + { + "epoch": 1.3116214974735876, + "grad_norm": 0.2572702169418335, + "learning_rate": 7.44310704274736e-05, + "loss": 0.6122443199157714, + "step": 3570 + }, + { + "epoch": 1.3152962792834175, + "grad_norm": 0.19573259353637695, + "learning_rate": 7.390959615591316e-05, + "loss": 0.6494469165802002, + "step": 3580 + }, + { + "epoch": 1.3189710610932477, + "grad_norm": 0.22986537218093872, + "learning_rate": 7.338888209425622e-05, + "loss": 0.6188368797302246, + "step": 3590 + }, + { + "epoch": 1.3226458429030776, + "grad_norm": 0.22328007221221924, + "learning_rate": 7.286894341482397e-05, + "loss": 0.6440567970275879, + "step": 3600 + }, + { + "epoch": 1.3263206247129076, + "grad_norm": 0.21681271493434906, + "learning_rate": 7.234979526734482e-05, + "loss": 0.6130101680755615, + "step": 3610 + }, + { + "epoch": 1.3299954065227377, + "grad_norm": 0.23429043591022491, + "learning_rate": 7.183145277851313e-05, + "loss": 0.5713854312896729, + "step": 3620 + }, + { + "epoch": 1.3336701883325677, + "grad_norm": 0.22499820590019226, + "learning_rate": 7.131393105154826e-05, + "loss": 0.6435183048248291, + "step": 3630 + }, + { + "epoch": 1.3373449701423978, + "grad_norm": 0.23204010725021362, + "learning_rate": 7.079724516575466e-05, + "loss": 0.5970840930938721, + "step": 3640 + }, + { + "epoch": 1.3410197519522278, + "grad_norm": 0.22594687342643738, + "learning_rate": 7.028141017608234e-05, + "loss": 0.6086468696594238, + "step": 3650 + }, + { + "epoch": 1.344694533762058, + "grad_norm": 0.23983144760131836, + "learning_rate": 6.976644111268845e-05, + "loss": 0.6677327632904053, + "step": 3660 + }, + { + "epoch": 1.3483693155718879, + "grad_norm": 0.2365673929452896, + "learning_rate": 6.925235298049906e-05, + "loss": 0.6098092555999756, + "step": 3670 + }, + { + "epoch": 1.352044097381718, + "grad_norm": 0.24905718863010406, + "learning_rate": 6.873916075877216e-05, + "loss": 0.6216807842254639, + "step": 3680 + }, + { + "epoch": 1.355718879191548, + "grad_norm": 0.23672564327716827, + "learning_rate": 6.822687940066102e-05, + "loss": 0.6090316295623779, + "step": 3690 + }, + { + "epoch": 1.359393661001378, + "grad_norm": 0.20575745403766632, + "learning_rate": 6.771552383277875e-05, + "loss": 0.6467265129089356, + "step": 3700 + }, + { + "epoch": 1.363068442811208, + "grad_norm": 0.23861850798130035, + "learning_rate": 6.720510895476309e-05, + "loss": 0.5875473022460938, + "step": 3710 + }, + { + "epoch": 1.3667432246210383, + "grad_norm": 0.2574703097343445, + "learning_rate": 6.669564963884245e-05, + "loss": 0.622504186630249, + "step": 3720 + }, + { + "epoch": 1.3704180064308682, + "grad_norm": 0.25036099553108215, + "learning_rate": 6.618716072940248e-05, + "loss": 0.6222783088684082, + "step": 3730 + }, + { + "epoch": 1.3740927882406981, + "grad_norm": 0.23848992586135864, + "learning_rate": 6.56796570425537e-05, + "loss": 0.6142213821411133, + "step": 3740 + }, + { + "epoch": 1.3777675700505283, + "grad_norm": 0.22312362492084503, + "learning_rate": 6.517315336569953e-05, + "loss": 0.633341121673584, + "step": 3750 + }, + { + "epoch": 1.3814423518603582, + "grad_norm": 0.24296629428863525, + "learning_rate": 6.466766445710568e-05, + "loss": 0.6525699138641358, + "step": 3760 + }, + { + "epoch": 1.3851171336701884, + "grad_norm": 0.2250729650259018, + "learning_rate": 6.416320504546997e-05, + "loss": 0.6627958297729493, + "step": 3770 + }, + { + "epoch": 1.3887919154800183, + "grad_norm": 0.2684767246246338, + "learning_rate": 6.365978982949324e-05, + "loss": 0.6367505550384521, + "step": 3780 + }, + { + "epoch": 1.3924666972898483, + "grad_norm": 0.21995939314365387, + "learning_rate": 6.315743347745097e-05, + "loss": 0.6509771347045898, + "step": 3790 + }, + { + "epoch": 1.3961414790996785, + "grad_norm": 0.24876751005649567, + "learning_rate": 6.265615062676612e-05, + "loss": 0.588352108001709, + "step": 3800 + }, + { + "epoch": 1.3998162609095086, + "grad_norm": 0.2845150828361511, + "learning_rate": 6.215595588358233e-05, + "loss": 0.5724838733673095, + "step": 3810 + }, + { + "epoch": 1.4034910427193386, + "grad_norm": 0.22122569382190704, + "learning_rate": 6.165686382233855e-05, + "loss": 0.621783971786499, + "step": 3820 + }, + { + "epoch": 1.4071658245291685, + "grad_norm": 0.23665687441825867, + "learning_rate": 6.115888898534427e-05, + "loss": 0.5714973449707031, + "step": 3830 + }, + { + "epoch": 1.4108406063389987, + "grad_norm": 0.26456931233406067, + "learning_rate": 6.066204588235585e-05, + "loss": 0.5998946189880371, + "step": 3840 + }, + { + "epoch": 1.4145153881488286, + "grad_norm": 0.21921156346797943, + "learning_rate": 6.016634899015369e-05, + "loss": 0.6019998550415039, + "step": 3850 + }, + { + "epoch": 1.4181901699586588, + "grad_norm": 0.2688063681125641, + "learning_rate": 5.967181275212046e-05, + "loss": 0.584591293334961, + "step": 3860 + }, + { + "epoch": 1.4218649517684887, + "grad_norm": 0.26307207345962524, + "learning_rate": 5.917845157782025e-05, + "loss": 0.592690896987915, + "step": 3870 + }, + { + "epoch": 1.4255397335783189, + "grad_norm": 0.28062573075294495, + "learning_rate": 5.8686279842578615e-05, + "loss": 0.5952250480651855, + "step": 3880 + }, + { + "epoch": 1.4292145153881488, + "grad_norm": 0.24920772016048431, + "learning_rate": 5.819531188706393e-05, + "loss": 0.6023118972778321, + "step": 3890 + }, + { + "epoch": 1.432889297197979, + "grad_norm": 0.2551993429660797, + "learning_rate": 5.770556201686927e-05, + "loss": 0.5991564750671386, + "step": 3900 + }, + { + "epoch": 1.436564079007809, + "grad_norm": 0.225216805934906, + "learning_rate": 5.7217044502095806e-05, + "loss": 0.5858877182006836, + "step": 3910 + }, + { + "epoch": 1.4402388608176389, + "grad_norm": 0.24253210425376892, + "learning_rate": 5.6729773576936874e-05, + "loss": 0.5954824924468994, + "step": 3920 + }, + { + "epoch": 1.443913642627469, + "grad_norm": 0.22022658586502075, + "learning_rate": 5.624376343926332e-05, + "loss": 0.625191593170166, + "step": 3930 + }, + { + "epoch": 1.447588424437299, + "grad_norm": 0.22758881747722626, + "learning_rate": 5.575902825020962e-05, + "loss": 0.5991941928863526, + "step": 3940 + }, + { + "epoch": 1.4512632062471291, + "grad_norm": 0.22000859677791595, + "learning_rate": 5.527558213376161e-05, + "loss": 0.6294786930084229, + "step": 3950 + }, + { + "epoch": 1.454937988056959, + "grad_norm": 0.22377276420593262, + "learning_rate": 5.479343917634451e-05, + "loss": 0.6242120742797852, + "step": 3960 + }, + { + "epoch": 1.4586127698667892, + "grad_norm": 0.27151235938072205, + "learning_rate": 5.431261342641286e-05, + "loss": 0.5964043617248536, + "step": 3970 + }, + { + "epoch": 1.4622875516766192, + "grad_norm": 0.22597825527191162, + "learning_rate": 5.383311889404103e-05, + "loss": 0.6154329299926757, + "step": 3980 + }, + { + "epoch": 1.4659623334864493, + "grad_norm": 0.21540269255638123, + "learning_rate": 5.3354969550514856e-05, + "loss": 0.6018314361572266, + "step": 3990 + }, + { + "epoch": 1.4696371152962793, + "grad_norm": 0.23756641149520874, + "learning_rate": 5.287817932792485e-05, + "loss": 0.6373420715332031, + "step": 4000 + }, + { + "epoch": 1.4733118971061092, + "grad_norm": 0.24588297307491302, + "learning_rate": 5.240276211876005e-05, + "loss": 0.6303625583648682, + "step": 4010 + }, + { + "epoch": 1.4769866789159394, + "grad_norm": 0.23921391367912292, + "learning_rate": 5.192873177550321e-05, + "loss": 0.6234454154968262, + "step": 4020 + }, + { + "epoch": 1.4806614607257695, + "grad_norm": 0.268675833940506, + "learning_rate": 5.1456102110227375e-05, + "loss": 0.5861053943634034, + "step": 4030 + }, + { + "epoch": 1.4843362425355995, + "grad_norm": 0.23049448430538177, + "learning_rate": 5.098488689419313e-05, + "loss": 0.6783847332000732, + "step": 4040 + }, + { + "epoch": 1.4880110243454294, + "grad_norm": 0.2512610852718353, + "learning_rate": 5.0515099857447615e-05, + "loss": 0.6114784717559815, + "step": 4050 + }, + { + "epoch": 1.4916858061552596, + "grad_norm": 0.21778461337089539, + "learning_rate": 5.004675468842436e-05, + "loss": 0.6642892360687256, + "step": 4060 + }, + { + "epoch": 1.4953605879650895, + "grad_norm": 0.2870982885360718, + "learning_rate": 4.957986503354433e-05, + "loss": 0.6069085121154785, + "step": 4070 + }, + { + "epoch": 1.4990353697749197, + "grad_norm": 0.2539427876472473, + "learning_rate": 4.91144444968185e-05, + "loss": 0.5883574485778809, + "step": 4080 + }, + { + "epoch": 1.5027101515847496, + "grad_norm": 0.2666284739971161, + "learning_rate": 4.865050663945139e-05, + "loss": 0.64878249168396, + "step": 4090 + }, + { + "epoch": 1.5063849333945796, + "grad_norm": 0.2161935567855835, + "learning_rate": 4.818806497944575e-05, + "loss": 0.6164711952209473, + "step": 4100 + }, + { + "epoch": 1.5100597152044097, + "grad_norm": 0.270613431930542, + "learning_rate": 4.772713299120909e-05, + "loss": 0.5953383922576905, + "step": 4110 + }, + { + "epoch": 1.51373449701424, + "grad_norm": 0.22387981414794922, + "learning_rate": 4.726772410516055e-05, + "loss": 0.6686501026153564, + "step": 4120 + }, + { + "epoch": 1.5174092788240698, + "grad_norm": 0.21915844082832336, + "learning_rate": 4.680985170734005e-05, + "loss": 0.6070637702941895, + "step": 4130 + }, + { + "epoch": 1.5210840606338998, + "grad_norm": 0.25814303755760193, + "learning_rate": 4.635352913901785e-05, + "loss": 0.5802205562591553, + "step": 4140 + }, + { + "epoch": 1.52475884244373, + "grad_norm": 0.2502751648426056, + "learning_rate": 4.5898769696306155e-05, + "loss": 0.606569766998291, + "step": 4150 + }, + { + "epoch": 1.52843362425356, + "grad_norm": 0.29439958930015564, + "learning_rate": 4.544558662977154e-05, + "loss": 0.5848165988922119, + "step": 4160 + }, + { + "epoch": 1.53210840606339, + "grad_norm": 0.2533748745918274, + "learning_rate": 4.499399314404874e-05, + "loss": 0.6226361751556396, + "step": 4170 + }, + { + "epoch": 1.53578318787322, + "grad_norm": 0.20448249578475952, + "learning_rate": 4.454400239745619e-05, + "loss": 0.6301614284515381, + "step": 4180 + }, + { + "epoch": 1.53945796968305, + "grad_norm": 0.21227025985717773, + "learning_rate": 4.4095627501612416e-05, + "loss": 0.635749626159668, + "step": 4190 + }, + { + "epoch": 1.54313275149288, + "grad_norm": 0.23682698607444763, + "learning_rate": 4.364888152105397e-05, + "loss": 0.6260458946228027, + "step": 4200 + }, + { + "epoch": 1.5468075333027103, + "grad_norm": 0.19529347121715546, + "learning_rate": 4.320377747285497e-05, + "loss": 0.6009593963623047, + "step": 4210 + }, + { + "epoch": 1.5504823151125402, + "grad_norm": 0.2707568109035492, + "learning_rate": 4.2760328326247534e-05, + "loss": 0.5838070869445801, + "step": 4220 + }, + { + "epoch": 1.5541570969223701, + "grad_norm": 0.26869723200798035, + "learning_rate": 4.231854700224417e-05, + "loss": 0.5800216674804688, + "step": 4230 + }, + { + "epoch": 1.5578318787322003, + "grad_norm": 0.2252606600522995, + "learning_rate": 4.18784463732611e-05, + "loss": 0.6049102306365967, + "step": 4240 + }, + { + "epoch": 1.5615066605420305, + "grad_norm": 0.2604488730430603, + "learning_rate": 4.1440039262743227e-05, + "loss": 0.6492654323577881, + "step": 4250 + }, + { + "epoch": 1.5651814423518604, + "grad_norm": 0.25955140590667725, + "learning_rate": 4.100333844479055e-05, + "loss": 0.5918104171752929, + "step": 4260 + }, + { + "epoch": 1.5688562241616903, + "grad_norm": 0.2388666868209839, + "learning_rate": 4.0568356643785856e-05, + "loss": 0.6321864128112793, + "step": 4270 + }, + { + "epoch": 1.5725310059715203, + "grad_norm": 0.26732930541038513, + "learning_rate": 4.0135106534024056e-05, + "loss": 0.6065220832824707, + "step": 4280 + }, + { + "epoch": 1.5762057877813505, + "grad_norm": 0.2281692773103714, + "learning_rate": 3.9703600739342985e-05, + "loss": 0.5991446495056152, + "step": 4290 + }, + { + "epoch": 1.5798805695911806, + "grad_norm": 0.23855754733085632, + "learning_rate": 3.9273851832755214e-05, + "loss": 0.5810461044311523, + "step": 4300 + }, + { + "epoch": 1.5835553514010106, + "grad_norm": 0.30157583951950073, + "learning_rate": 3.8845872336082125e-05, + "loss": 0.5769465923309326, + "step": 4310 + }, + { + "epoch": 1.5872301332108405, + "grad_norm": 0.2254714071750641, + "learning_rate": 3.8419674719588725e-05, + "loss": 0.6204625129699707, + "step": 4320 + }, + { + "epoch": 1.5909049150206707, + "grad_norm": 0.22155548632144928, + "learning_rate": 3.799527140162055e-05, + "loss": 0.583667516708374, + "step": 4330 + }, + { + "epoch": 1.5945796968305008, + "grad_norm": 0.24007032811641693, + "learning_rate": 3.7572674748241674e-05, + "loss": 0.6734154224395752, + "step": 4340 + }, + { + "epoch": 1.5982544786403308, + "grad_norm": 0.24698472023010254, + "learning_rate": 3.715189707287436e-05, + "loss": 0.5612778663635254, + "step": 4350 + }, + { + "epoch": 1.6019292604501607, + "grad_norm": 0.23125363886356354, + "learning_rate": 3.673295063594049e-05, + "loss": 0.6097794532775879, + "step": 4360 + }, + { + "epoch": 1.6056040422599906, + "grad_norm": 0.2623499035835266, + "learning_rate": 3.631584764450402e-05, + "loss": 0.6135641098022461, + "step": 4370 + }, + { + "epoch": 1.6092788240698208, + "grad_norm": 0.3083759844303131, + "learning_rate": 3.590060025191556e-05, + "loss": 0.623767614364624, + "step": 4380 + }, + { + "epoch": 1.612953605879651, + "grad_norm": 0.21405094861984253, + "learning_rate": 3.5487220557458176e-05, + "loss": 0.580271863937378, + "step": 4390 + }, + { + "epoch": 1.616628387689481, + "grad_norm": 0.27044427394866943, + "learning_rate": 3.507572060599471e-05, + "loss": 0.60565185546875, + "step": 4400 + }, + { + "epoch": 1.6203031694993109, + "grad_norm": 0.2213546633720398, + "learning_rate": 3.4666112387617045e-05, + "loss": 0.6188304424285889, + "step": 4410 + }, + { + "epoch": 1.623977951309141, + "grad_norm": 0.236136794090271, + "learning_rate": 3.425840783729664e-05, + "loss": 0.5975236892700195, + "step": 4420 + }, + { + "epoch": 1.6276527331189712, + "grad_norm": 0.2937586009502411, + "learning_rate": 3.385261883453664e-05, + "loss": 0.6132159233093262, + "step": 4430 + }, + { + "epoch": 1.6313275149288011, + "grad_norm": 0.26236283779144287, + "learning_rate": 3.344875720302604e-05, + "loss": 0.6577489852905274, + "step": 4440 + }, + { + "epoch": 1.635002296738631, + "grad_norm": 0.21058732271194458, + "learning_rate": 3.304683471029485e-05, + "loss": 0.630679988861084, + "step": 4450 + }, + { + "epoch": 1.6386770785484612, + "grad_norm": 0.24456511437892914, + "learning_rate": 3.264686306737147e-05, + "loss": 0.5711773872375489, + "step": 4460 + }, + { + "epoch": 1.6423518603582912, + "grad_norm": 0.28906679153442383, + "learning_rate": 3.2248853928441304e-05, + "loss": 0.6463574409484864, + "step": 4470 + }, + { + "epoch": 1.6460266421681213, + "grad_norm": 0.2541700005531311, + "learning_rate": 3.185281889050725e-05, + "loss": 0.5943029880523681, + "step": 4480 + }, + { + "epoch": 1.6497014239779513, + "grad_norm": 0.20259977877140045, + "learning_rate": 3.1458769493051854e-05, + "loss": 0.5949666023254394, + "step": 4490 + }, + { + "epoch": 1.6533762057877812, + "grad_norm": 0.20865267515182495, + "learning_rate": 3.1066717217700835e-05, + "loss": 0.622490930557251, + "step": 4500 + }, + { + "epoch": 1.6570509875976114, + "grad_norm": 0.2103072702884674, + "learning_rate": 3.067667348788885e-05, + "loss": 0.596876859664917, + "step": 4510 + }, + { + "epoch": 1.6607257694074415, + "grad_norm": 0.2789931297302246, + "learning_rate": 3.0288649668526504e-05, + "loss": 0.6100345134735108, + "step": 4520 + }, + { + "epoch": 1.6644005512172715, + "grad_norm": 0.2407047599554062, + "learning_rate": 2.9902657065669082e-05, + "loss": 0.5866603374481201, + "step": 4530 + }, + { + "epoch": 1.6680753330271014, + "grad_norm": 0.23293636739253998, + "learning_rate": 2.951870692618739e-05, + "loss": 0.6044306755065918, + "step": 4540 + }, + { + "epoch": 1.6717501148369316, + "grad_norm": 0.26319974660873413, + "learning_rate": 2.9136810437439743e-05, + "loss": 0.6011191844940186, + "step": 4550 + }, + { + "epoch": 1.6754248966467618, + "grad_norm": 0.266152024269104, + "learning_rate": 2.8756978726946283e-05, + "loss": 0.6181775569915772, + "step": 4560 + }, + { + "epoch": 1.6790996784565917, + "grad_norm": 0.22137150168418884, + "learning_rate": 2.8379222862064568e-05, + "loss": 0.5735309600830079, + "step": 4570 + }, + { + "epoch": 1.6827744602664216, + "grad_norm": 0.19313573837280273, + "learning_rate": 2.8003553849667097e-05, + "loss": 0.5909959316253662, + "step": 4580 + }, + { + "epoch": 1.6864492420762516, + "grad_norm": 0.2427615523338318, + "learning_rate": 2.7629982635820707e-05, + "loss": 0.6190264225006104, + "step": 4590 + }, + { + "epoch": 1.6901240238860817, + "grad_norm": 0.2528453469276428, + "learning_rate": 2.7258520105467567e-05, + "loss": 0.5556782245635986, + "step": 4600 + }, + { + "epoch": 1.693798805695912, + "grad_norm": 0.21333430707454681, + "learning_rate": 2.6889177082107942e-05, + "loss": 0.6259308815002441, + "step": 4610 + }, + { + "epoch": 1.6974735875057418, + "grad_norm": 0.2462078183889389, + "learning_rate": 2.6521964327485017e-05, + "loss": 0.6408613681793213, + "step": 4620 + }, + { + "epoch": 1.7011483693155718, + "grad_norm": 0.22960656881332397, + "learning_rate": 2.6156892541271084e-05, + "loss": 0.5830319881439209, + "step": 4630 + }, + { + "epoch": 1.704823151125402, + "grad_norm": 0.23370933532714844, + "learning_rate": 2.5793972360756002e-05, + "loss": 0.6464344978332519, + "step": 4640 + }, + { + "epoch": 1.708497932935232, + "grad_norm": 0.25368574261665344, + "learning_rate": 2.543321436053713e-05, + "loss": 0.5802364826202393, + "step": 4650 + }, + { + "epoch": 1.712172714745062, + "grad_norm": 0.23351016640663147, + "learning_rate": 2.5074629052211217e-05, + "loss": 0.6773637294769287, + "step": 4660 + }, + { + "epoch": 1.715847496554892, + "grad_norm": 0.23634305596351624, + "learning_rate": 2.4718226884068187e-05, + "loss": 0.6070538997650147, + "step": 4670 + }, + { + "epoch": 1.719522278364722, + "grad_norm": 0.23648826777935028, + "learning_rate": 2.4364018240786546e-05, + "loss": 0.63211030960083, + "step": 4680 + }, + { + "epoch": 1.723197060174552, + "grad_norm": 0.2305329442024231, + "learning_rate": 2.401201344313102e-05, + "loss": 0.5770946502685547, + "step": 4690 + }, + { + "epoch": 1.7268718419843823, + "grad_norm": 0.20384910702705383, + "learning_rate": 2.3662222747651695e-05, + "loss": 0.578916597366333, + "step": 4700 + }, + { + "epoch": 1.7305466237942122, + "grad_norm": 0.21320855617523193, + "learning_rate": 2.3314656346385134e-05, + "loss": 0.5877019882202148, + "step": 4710 + }, + { + "epoch": 1.7342214056040421, + "grad_norm": 0.24065816402435303, + "learning_rate": 2.2969324366557522e-05, + "loss": 0.6320582866668701, + "step": 4720 + }, + { + "epoch": 1.7378961874138723, + "grad_norm": 0.21492637693881989, + "learning_rate": 2.2626236870289452e-05, + "loss": 0.6050594806671142, + "step": 4730 + }, + { + "epoch": 1.7415709692237025, + "grad_norm": 0.23171354830265045, + "learning_rate": 2.2285403854302912e-05, + "loss": 0.6136460304260254, + "step": 4740 + }, + { + "epoch": 1.7452457510335324, + "grad_norm": 0.23479370772838593, + "learning_rate": 2.194683524962986e-05, + "loss": 0.5907188892364502, + "step": 4750 + }, + { + "epoch": 1.7489205328433624, + "grad_norm": 0.21812178194522858, + "learning_rate": 2.161054092132284e-05, + "loss": 0.6049327850341797, + "step": 4760 + }, + { + "epoch": 1.7525953146531925, + "grad_norm": 0.22398284077644348, + "learning_rate": 2.1276530668167728e-05, + "loss": 0.6184739112854004, + "step": 4770 + }, + { + "epoch": 1.7562700964630225, + "grad_norm": 0.28541100025177, + "learning_rate": 2.0944814222397944e-05, + "loss": 0.594030237197876, + "step": 4780 + }, + { + "epoch": 1.7599448782728526, + "grad_norm": 0.2562128007411957, + "learning_rate": 2.061540124941117e-05, + "loss": 0.6142899513244628, + "step": 4790 + }, + { + "epoch": 1.7636196600826826, + "grad_norm": 0.2420058250427246, + "learning_rate": 2.0288301347487528e-05, + "loss": 0.6153490543365479, + "step": 4800 + }, + { + "epoch": 1.7672944418925125, + "grad_norm": 0.30034923553466797, + "learning_rate": 1.9963524047509897e-05, + "loss": 0.5961874008178711, + "step": 4810 + }, + { + "epoch": 1.7709692237023427, + "grad_norm": 0.3149788975715637, + "learning_rate": 1.9641078812686375e-05, + "loss": 0.6012597560882569, + "step": 4820 + }, + { + "epoch": 1.7746440055121728, + "grad_norm": 0.2160654366016388, + "learning_rate": 1.9320975038274402e-05, + "loss": 0.5875374794006347, + "step": 4830 + }, + { + "epoch": 1.7783187873220028, + "grad_norm": 0.25491863489151, + "learning_rate": 1.9003222051307047e-05, + "loss": 0.5735582828521728, + "step": 4840 + }, + { + "epoch": 1.7819935691318327, + "grad_norm": 0.2498500943183899, + "learning_rate": 1.8687829110321254e-05, + "loss": 0.6238004684448242, + "step": 4850 + }, + { + "epoch": 1.7856683509416629, + "grad_norm": 0.23228974640369415, + "learning_rate": 1.8374805405088014e-05, + "loss": 0.6190362930297851, + "step": 4860 + }, + { + "epoch": 1.789343132751493, + "grad_norm": 0.248588427901268, + "learning_rate": 1.8064160056344716e-05, + "loss": 0.6250235080718994, + "step": 4870 + }, + { + "epoch": 1.793017914561323, + "grad_norm": 0.22170130908489227, + "learning_rate": 1.7755902115529222e-05, + "loss": 0.6499590873718262, + "step": 4880 + }, + { + "epoch": 1.796692696371153, + "grad_norm": 0.242046058177948, + "learning_rate": 1.7450040564516322e-05, + "loss": 0.6411127567291259, + "step": 4890 + }, + { + "epoch": 1.8003674781809829, + "grad_norm": 0.24742132425308228, + "learning_rate": 1.7146584315355885e-05, + "loss": 0.5813017368316651, + "step": 4900 + }, + { + "epoch": 1.804042259990813, + "grad_norm": 0.25267845392227173, + "learning_rate": 1.6845542210013198e-05, + "loss": 0.5960687637329102, + "step": 4910 + }, + { + "epoch": 1.8077170418006432, + "grad_norm": 0.23756426572799683, + "learning_rate": 1.6546923020111417e-05, + "loss": 0.5912890911102295, + "step": 4920 + }, + { + "epoch": 1.8113918236104731, + "grad_norm": 0.22568336129188538, + "learning_rate": 1.6250735446675912e-05, + "loss": 0.6352333068847656, + "step": 4930 + }, + { + "epoch": 1.815066605420303, + "grad_norm": 0.24231384694576263, + "learning_rate": 1.5956988119880712e-05, + "loss": 0.6327116966247559, + "step": 4940 + }, + { + "epoch": 1.8187413872301332, + "grad_norm": 0.2860916554927826, + "learning_rate": 1.5665689598797174e-05, + "loss": 0.6136715888977051, + "step": 4950 + }, + { + "epoch": 1.8224161690399634, + "grad_norm": 0.27555617690086365, + "learning_rate": 1.5376848371144402e-05, + "loss": 0.6523287773132325, + "step": 4960 + }, + { + "epoch": 1.8260909508497933, + "grad_norm": 0.23608949780464172, + "learning_rate": 1.5090472853042137e-05, + "loss": 0.5987821578979492, + "step": 4970 + }, + { + "epoch": 1.8297657326596233, + "grad_norm": 0.26431113481521606, + "learning_rate": 1.48065713887654e-05, + "loss": 0.6213451385498047, + "step": 4980 + }, + { + "epoch": 1.8334405144694532, + "grad_norm": 0.26088884472846985, + "learning_rate": 1.4525152250501361e-05, + "loss": 0.6668256282806396, + "step": 4990 + }, + { + "epoch": 1.8371152962792834, + "grad_norm": 0.2662504017353058, + "learning_rate": 1.424622363810838e-05, + "loss": 0.6278341770172119, + "step": 5000 + }, + { + "epoch": 1.8407900780891135, + "grad_norm": 0.2490486353635788, + "learning_rate": 1.3969793678877075e-05, + "loss": 0.5880495071411133, + "step": 5010 + }, + { + "epoch": 1.8444648598989435, + "grad_norm": 0.23027367889881134, + "learning_rate": 1.369587042729341e-05, + "loss": 0.5670716285705566, + "step": 5020 + }, + { + "epoch": 1.8481396417087734, + "grad_norm": 0.25596269965171814, + "learning_rate": 1.3424461864804183e-05, + "loss": 0.6119084358215332, + "step": 5030 + }, + { + "epoch": 1.8518144235186036, + "grad_norm": 0.24995382130146027, + "learning_rate": 1.3155575899584226e-05, + "loss": 0.5778251647949219, + "step": 5040 + }, + { + "epoch": 1.8554892053284338, + "grad_norm": 0.22746507823467255, + "learning_rate": 1.2889220366306276e-05, + "loss": 0.6088578701019287, + "step": 5050 + }, + { + "epoch": 1.8591639871382637, + "grad_norm": 0.25209841132164, + "learning_rate": 1.2625403025912397e-05, + "loss": 0.6049771785736084, + "step": 5060 + }, + { + "epoch": 1.8628387689480936, + "grad_norm": 0.21623386442661285, + "learning_rate": 1.2364131565388059e-05, + "loss": 0.6542551517486572, + "step": 5070 + }, + { + "epoch": 1.8665135507579238, + "grad_norm": 0.2937711179256439, + "learning_rate": 1.2105413597538107e-05, + "loss": 0.6242814540863038, + "step": 5080 + }, + { + "epoch": 1.8701883325677537, + "grad_norm": 0.22145850956439972, + "learning_rate": 1.1849256660764829e-05, + "loss": 0.6305468082427979, + "step": 5090 + }, + { + "epoch": 1.873863114377584, + "grad_norm": 0.2406489998102188, + "learning_rate": 1.1595668218848466e-05, + "loss": 0.5648299217224121, + "step": 5100 + }, + { + "epoch": 1.8185053380782918, + "grad_norm": 0.5347191095352173, + "learning_rate": 1.1344655660729675e-05, + "loss": 0.9309283256530761, + "step": 5110 + }, + { + "epoch": 1.8220640569395017, + "grad_norm": 0.3157309591770172, + "learning_rate": 1.1096226300294144e-05, + "loss": 0.8174578666687011, + "step": 5120 + }, + { + "epoch": 1.8256227758007118, + "grad_norm": 0.39881300926208496, + "learning_rate": 1.0850387376159666e-05, + "loss": 0.688888692855835, + "step": 5130 + }, + { + "epoch": 1.8291814946619218, + "grad_norm": 0.39760011434555054, + "learning_rate": 1.0607146051465012e-05, + "loss": 0.6008673667907715, + "step": 5140 + }, + { + "epoch": 1.8327402135231317, + "grad_norm": 0.2301214188337326, + "learning_rate": 1.0366509413661407e-05, + "loss": 0.5371044158935547, + "step": 5150 + }, + { + "epoch": 1.8362989323843415, + "grad_norm": 0.268571138381958, + "learning_rate": 1.0128484474305932e-05, + "loss": 0.5456399917602539, + "step": 5160 + }, + { + "epoch": 1.8398576512455516, + "grad_norm": 0.2829780876636505, + "learning_rate": 9.893078168857173e-06, + "loss": 0.6310898780822753, + "step": 5170 + }, + { + "epoch": 1.8434163701067616, + "grad_norm": 0.23199482262134552, + "learning_rate": 9.660297356473246e-06, + "loss": 0.5056358337402344, + "step": 5180 + }, + { + "epoch": 1.8469750889679717, + "grad_norm": 0.18909375369548798, + "learning_rate": 9.430148819811813e-06, + "loss": 0.591670560836792, + "step": 5190 + }, + { + "epoch": 1.8505338078291815, + "grad_norm": 0.21808627247810364, + "learning_rate": 9.202639264832668e-06, + "loss": 0.522268533706665, + "step": 5200 + }, + { + "epoch": 1.8540925266903914, + "grad_norm": 0.1928812861442566, + "learning_rate": 8.977775320602044e-06, + "loss": 0.5216116428375244, + "step": 5210 + }, + { + "epoch": 1.8576512455516014, + "grad_norm": 0.23067593574523926, + "learning_rate": 8.755563539099688e-06, + "loss": 0.5356510639190674, + "step": 5220 + }, + { + "epoch": 1.8612099644128115, + "grad_norm": 0.22381772100925446, + "learning_rate": 8.536010395027904e-06, + "loss": 0.5457266807556153, + "step": 5230 + }, + { + "epoch": 1.8647686832740213, + "grad_norm": 0.19332070648670197, + "learning_rate": 8.319122285622793e-06, + "loss": 0.5373063564300538, + "step": 5240 + }, + { + "epoch": 1.8683274021352312, + "grad_norm": 0.2347511649131775, + "learning_rate": 8.104905530467988e-06, + "loss": 0.5520383358001709, + "step": 5250 + }, + { + "epoch": 1.8718861209964412, + "grad_norm": 0.2347835898399353, + "learning_rate": 7.893366371310462e-06, + "loss": 0.6185570240020752, + "step": 5260 + }, + { + "epoch": 1.8754448398576513, + "grad_norm": 0.1947682499885559, + "learning_rate": 7.684510971878612e-06, + "loss": 0.49200053215026857, + "step": 5270 + }, + { + "epoch": 1.8790035587188612, + "grad_norm": 0.20180030167102814, + "learning_rate": 7.4783454177027705e-06, + "loss": 0.46091561317443847, + "step": 5280 + }, + { + "epoch": 1.8825622775800712, + "grad_norm": 0.22945503890514374, + "learning_rate": 7.274875715937746e-06, + "loss": 0.5818113327026367, + "step": 5290 + }, + { + "epoch": 1.886120996441281, + "grad_norm": 0.17361043393611908, + "learning_rate": 7.074107795187923e-06, + "loss": 0.5041025638580322, + "step": 5300 + }, + { + "epoch": 1.8896797153024911, + "grad_norm": 0.19834654033184052, + "learning_rate": 6.876047505334482e-06, + "loss": 0.4940037727355957, + "step": 5310 + }, + { + "epoch": 1.8932384341637012, + "grad_norm": 0.1980016976594925, + "learning_rate": 6.680700617364877e-06, + "loss": 0.5819048881530762, + "step": 5320 + }, + { + "epoch": 1.896797153024911, + "grad_norm": 0.2092839926481247, + "learning_rate": 6.488072823204749e-06, + "loss": 0.5352010726928711, + "step": 5330 + }, + { + "epoch": 1.9003558718861209, + "grad_norm": 0.1931697428226471, + "learning_rate": 6.298169735552095e-06, + "loss": 0.5835151672363281, + "step": 5340 + }, + { + "epoch": 1.903914590747331, + "grad_norm": 0.20344269275665283, + "learning_rate": 6.110996887713661e-06, + "loss": 0.528069543838501, + "step": 5350 + }, + { + "epoch": 1.907473309608541, + "grad_norm": 0.2120201289653778, + "learning_rate": 5.92655973344377e-06, + "loss": 0.6034663677215576, + "step": 5360 + }, + { + "epoch": 1.9110320284697508, + "grad_norm": 0.18206527829170227, + "learning_rate": 5.744863646785359e-06, + "loss": 0.4821772575378418, + "step": 5370 + }, + { + "epoch": 1.914590747330961, + "grad_norm": 0.20323292911052704, + "learning_rate": 5.565913921913513e-06, + "loss": 0.5498052120208741, + "step": 5380 + }, + { + "epoch": 1.9181494661921707, + "grad_norm": 0.20763012766838074, + "learning_rate": 5.389715772981008e-06, + "loss": 0.5417836666107178, + "step": 5390 + }, + { + "epoch": 1.9217081850533808, + "grad_norm": 0.18934236466884613, + "learning_rate": 5.216274333966587e-06, + "loss": 0.5138674736022949, + "step": 5400 + }, + { + "epoch": 1.9252669039145909, + "grad_norm": 0.20865601301193237, + "learning_rate": 5.045594658525232e-06, + "loss": 0.5408785820007325, + "step": 5410 + }, + { + "epoch": 1.9288256227758007, + "grad_norm": 0.21466206014156342, + "learning_rate": 4.877681719840954e-06, + "loss": 0.5956434726715087, + "step": 5420 + }, + { + "epoch": 1.9323843416370106, + "grad_norm": 0.2258831411600113, + "learning_rate": 4.7125404104819245e-06, + "loss": 0.5089565277099609, + "step": 5430 + }, + { + "epoch": 1.9359430604982206, + "grad_norm": 0.20672915875911713, + "learning_rate": 4.550175542257862e-06, + "loss": 0.4947202682495117, + "step": 5440 + }, + { + "epoch": 1.9395017793594307, + "grad_norm": 0.17640693485736847, + "learning_rate": 4.390591846079839e-06, + "loss": 0.5234504222869873, + "step": 5450 + }, + { + "epoch": 1.9430604982206405, + "grad_norm": 0.25858819484710693, + "learning_rate": 4.233793971822475e-06, + "loss": 0.5606400966644287, + "step": 5460 + }, + { + "epoch": 1.9466192170818504, + "grad_norm": 0.2583085596561432, + "learning_rate": 4.0797864881883975e-06, + "loss": 0.562528419494629, + "step": 5470 + }, + { + "epoch": 1.9501779359430604, + "grad_norm": 0.20404495298862457, + "learning_rate": 3.92857388257516e-06, + "loss": 0.528929328918457, + "step": 5480 + }, + { + "epoch": 1.9537366548042705, + "grad_norm": 0.20115692913532257, + "learning_rate": 3.780160560944479e-06, + "loss": 0.5270949363708496, + "step": 5490 + }, + { + "epoch": 1.9572953736654806, + "grad_norm": 0.22428476810455322, + "learning_rate": 3.6345508476938297e-06, + "loss": 0.5581763744354248, + "step": 5500 + }, + { + "epoch": 4.516658124038955, + "grad_norm": 0.26195743680000305, + "learning_rate": 3.4917489855305074e-06, + "loss": 1.5826950073242188, + "step": 5510 + }, + { + "epoch": 4.524859046642748, + "grad_norm": 0.28879228234291077, + "learning_rate": 3.3517591353479094e-06, + "loss": 1.5269113540649415, + "step": 5520 + }, + { + "epoch": 4.5330599692465405, + "grad_norm": 0.24640367925167084, + "learning_rate": 3.214585376104384e-06, + "loss": 1.4506096839904785, + "step": 5530 + }, + { + "epoch": 4.541260891850333, + "grad_norm": 0.23131071031093597, + "learning_rate": 3.0802317047043837e-06, + "loss": 1.442794418334961, + "step": 5540 + }, + { + "epoch": 4.549461814454126, + "grad_norm": 0.19850678741931915, + "learning_rate": 2.9487020358818673e-06, + "loss": 1.449783992767334, + "step": 5550 + }, + { + "epoch": 4.557662737057919, + "grad_norm": 0.20797349512577057, + "learning_rate": 2.820000202086459e-06, + "loss": 1.4503040313720703, + "step": 5560 + }, + { + "epoch": 4.565863659661712, + "grad_norm": 0.22960826754570007, + "learning_rate": 2.69412995337156e-06, + "loss": 1.438700008392334, + "step": 5570 + }, + { + "epoch": 4.574064582265505, + "grad_norm": 0.2156728059053421, + "learning_rate": 2.5710949572852363e-06, + "loss": 1.462771224975586, + "step": 5580 + }, + { + "epoch": 4.582265504869298, + "grad_norm": 0.20963099598884583, + "learning_rate": 2.450898798763268e-06, + "loss": 1.4643362998962401, + "step": 5590 + }, + { + "epoch": 4.590466427473091, + "grad_norm": 0.20916540920734406, + "learning_rate": 2.3335449800247265e-06, + "loss": 1.3959227561950684, + "step": 5600 + }, + { + "epoch": 4.598667350076884, + "grad_norm": 0.23627620935440063, + "learning_rate": 2.2190369204699525e-06, + "loss": 1.4502220153808594, + "step": 5610 + }, + { + "epoch": 4.606868272680677, + "grad_norm": 0.2292768359184265, + "learning_rate": 2.107377956580847e-06, + "loss": 1.355497455596924, + "step": 5620 + }, + { + "epoch": 4.61506919528447, + "grad_norm": 0.22735118865966797, + "learning_rate": 1.9985713418237407e-06, + "loss": 1.411573314666748, + "step": 5630 + }, + { + "epoch": 4.6232701178882625, + "grad_norm": 0.23649324476718903, + "learning_rate": 1.892620246554555e-06, + "loss": 1.498843002319336, + "step": 5640 + }, + { + "epoch": 4.631471040492055, + "grad_norm": 0.21309642493724823, + "learning_rate": 1.7895277579264014e-06, + "loss": 1.4190632820129394, + "step": 5650 + }, + { + "epoch": 4.639671963095848, + "grad_norm": 0.20090609788894653, + "learning_rate": 1.6892968797996955e-06, + "loss": 1.5616422653198243, + "step": 5660 + }, + { + "epoch": 4.647872885699641, + "grad_norm": 0.1834453046321869, + "learning_rate": 1.591930532654573e-06, + "loss": 1.4625298500061035, + "step": 5670 + }, + { + "epoch": 4.656073808303434, + "grad_norm": 0.24359364807605743, + "learning_rate": 1.4974315535058015e-06, + "loss": 1.5805925369262694, + "step": 5680 + }, + { + "epoch": 4.664274730907227, + "grad_norm": 0.2116386741399765, + "learning_rate": 1.4058026958201465e-06, + "loss": 1.4265759468078614, + "step": 5690 + }, + { + "epoch": 4.67247565351102, + "grad_norm": 0.2073894888162613, + "learning_rate": 1.317046629436136e-06, + "loss": 1.4648627281188964, + "step": 5700 + }, + { + "epoch": 4.680676576114813, + "grad_norm": 0.20656034350395203, + "learning_rate": 1.231165940486234e-06, + "loss": 1.4101587295532227, + "step": 5710 + }, + { + "epoch": 4.688877498718606, + "grad_norm": 0.21959076821804047, + "learning_rate": 1.1481631313215223e-06, + "loss": 1.459317398071289, + "step": 5720 + }, + { + "epoch": 4.697078421322399, + "grad_norm": 0.21213866770267487, + "learning_rate": 1.0680406204387704e-06, + "loss": 1.4261064529418945, + "step": 5730 + }, + { + "epoch": 4.7052793439261915, + "grad_norm": 0.20413118600845337, + "learning_rate": 9.90800742410003e-07, + "loss": 1.4091854095458984, + "step": 5740 + }, + { + "epoch": 4.713480266529984, + "grad_norm": 0.20361439883708954, + "learning_rate": 9.164457478143873e-07, + "loss": 1.4002375602722168, + "step": 5750 + }, + { + "epoch": 4.721681189133777, + "grad_norm": 0.26386862993240356, + "learning_rate": 8.44977803172775e-07, + "loss": 1.3728976249694824, + "step": 5760 + }, + { + "epoch": 4.72988211173757, + "grad_norm": 0.21209527552127838, + "learning_rate": 7.763989908844749e-07, + "loss": 1.4790589332580566, + "step": 5770 + }, + { + "epoch": 4.738083034341363, + "grad_norm": 0.22729259729385376, + "learning_rate": 7.10711309166634e-07, + "loss": 1.4757543563842774, + "step": 5780 + }, + { + "epoch": 4.746283956945156, + "grad_norm": 0.20996031165122986, + "learning_rate": 6.479166719959962e-07, + "loss": 1.5113654136657715, + "step": 5790 + }, + { + "epoch": 4.754484879548949, + "grad_norm": 0.19377897679805756, + "learning_rate": 5.880169090531351e-07, + "loss": 1.4255532264709472, + "step": 5800 + }, + { + "epoch": 4.762685802152742, + "grad_norm": 0.1967298835515976, + "learning_rate": 5.310137656691306e-07, + "loss": 1.3477745056152344, + "step": 5810 + }, + { + "epoch": 4.770886724756535, + "grad_norm": 0.21067732572555542, + "learning_rate": 4.769089027747641e-07, + "loss": 1.5181450843811035, + "step": 5820 + }, + { + "epoch": 4.779087647360328, + "grad_norm": 0.20564958453178406, + "learning_rate": 4.257038968520366e-07, + "loss": 1.4333147048950194, + "step": 5830 + }, + { + "epoch": 4.7872885699641206, + "grad_norm": 0.20786744356155396, + "learning_rate": 3.774002398883036e-07, + "loss": 1.59590425491333, + "step": 5840 + }, + { + "epoch": 4.7954894925679135, + "grad_norm": 0.19587092101573944, + "learning_rate": 3.319993393327891e-07, + "loss": 1.486422634124756, + "step": 5850 + }, + { + "epoch": 4.803690415171706, + "grad_norm": 0.19629155099391937, + "learning_rate": 2.8950251805553997e-07, + "loss": 1.4627803802490233, + "step": 5860 + }, + { + "epoch": 4.811891337775499, + "grad_norm": 0.18955595791339874, + "learning_rate": 2.499110143089567e-07, + "loss": 1.3632481575012207, + "step": 5870 + } + ], + "logging_steps": 10, + "max_steps": 6000, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 25, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.261735626342892e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +}