{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1180, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003395585738539898, "grad_norm": 7.08682047665737, "learning_rate": 0.0, "loss": 0.5517520904541016, "step": 1 }, { "epoch": 0.006791171477079796, "grad_norm": 6.976542094132622, "learning_rate": 8.474576271186441e-07, "loss": 0.5979730486869812, "step": 2 }, { "epoch": 0.010186757215619695, "grad_norm": 7.08711278665607, "learning_rate": 1.6949152542372882e-06, "loss": 0.5869178771972656, "step": 3 }, { "epoch": 0.013582342954159592, "grad_norm": 6.04281219499779, "learning_rate": 2.5423728813559323e-06, "loss": 0.583850085735321, "step": 4 }, { "epoch": 0.01697792869269949, "grad_norm": 4.70694252140098, "learning_rate": 3.3898305084745763e-06, "loss": 0.5855023860931396, "step": 5 }, { "epoch": 0.02037351443123939, "grad_norm": 3.1257795564188986, "learning_rate": 4.23728813559322e-06, "loss": 0.5459413528442383, "step": 6 }, { "epoch": 0.023769100169779286, "grad_norm": 2.9450224632416786, "learning_rate": 5.084745762711865e-06, "loss": 0.5440694093704224, "step": 7 }, { "epoch": 0.027164685908319185, "grad_norm": 1.9111356921133758, "learning_rate": 5.932203389830509e-06, "loss": 0.5096928477287292, "step": 8 }, { "epoch": 0.030560271646859084, "grad_norm": 1.2082542585241898, "learning_rate": 6.779661016949153e-06, "loss": 0.4186725318431854, "step": 9 }, { "epoch": 0.03395585738539898, "grad_norm": 1.0886009189522188, "learning_rate": 7.627118644067798e-06, "loss": 0.4626155495643616, "step": 10 }, { "epoch": 0.03735144312393888, "grad_norm": 1.841053788803903, "learning_rate": 8.47457627118644e-06, "loss": 0.4608768820762634, "step": 11 }, { "epoch": 0.04074702886247878, "grad_norm": 1.6172816674288033, "learning_rate": 9.322033898305085e-06, "loss": 0.4182015359401703, "step": 12 }, { "epoch": 0.044142614601018676, "grad_norm": 1.5075033083666503, "learning_rate": 1.016949152542373e-05, "loss": 0.4332927167415619, "step": 13 }, { "epoch": 0.04753820033955857, "grad_norm": 1.0955949502584243, "learning_rate": 1.1016949152542374e-05, "loss": 0.40284913778305054, "step": 14 }, { "epoch": 0.050933786078098474, "grad_norm": 0.8644460142813777, "learning_rate": 1.1864406779661018e-05, "loss": 0.3816971778869629, "step": 15 }, { "epoch": 0.05432937181663837, "grad_norm": 0.6829115672198884, "learning_rate": 1.2711864406779661e-05, "loss": 0.3603823184967041, "step": 16 }, { "epoch": 0.057724957555178265, "grad_norm": 0.6367061157889453, "learning_rate": 1.3559322033898305e-05, "loss": 0.3408442735671997, "step": 17 }, { "epoch": 0.06112054329371817, "grad_norm": 0.6781955313003141, "learning_rate": 1.440677966101695e-05, "loss": 0.3470923602581024, "step": 18 }, { "epoch": 0.06451612903225806, "grad_norm": 0.6201305430221453, "learning_rate": 1.5254237288135596e-05, "loss": 0.3508286476135254, "step": 19 }, { "epoch": 0.06791171477079797, "grad_norm": 0.4752735323917048, "learning_rate": 1.6101694915254237e-05, "loss": 0.3274625539779663, "step": 20 }, { "epoch": 0.07130730050933787, "grad_norm": 0.4269300372689963, "learning_rate": 1.694915254237288e-05, "loss": 0.3186553120613098, "step": 21 }, { "epoch": 0.07470288624787776, "grad_norm": 0.4465667555039656, "learning_rate": 1.7796610169491526e-05, "loss": 0.3391905725002289, "step": 22 }, { "epoch": 0.07809847198641766, "grad_norm": 0.46079846470699787, "learning_rate": 1.864406779661017e-05, "loss": 0.31875354051589966, "step": 23 }, { "epoch": 0.08149405772495756, "grad_norm": 0.45702065056636587, "learning_rate": 1.9491525423728814e-05, "loss": 0.3063993752002716, "step": 24 }, { "epoch": 0.08488964346349745, "grad_norm": 0.43287459388952915, "learning_rate": 2.033898305084746e-05, "loss": 0.28915151953697205, "step": 25 }, { "epoch": 0.08828522920203735, "grad_norm": 0.3628080019746948, "learning_rate": 2.1186440677966103e-05, "loss": 0.3020364046096802, "step": 26 }, { "epoch": 0.09168081494057725, "grad_norm": 0.339570743101814, "learning_rate": 2.2033898305084748e-05, "loss": 0.3139340281486511, "step": 27 }, { "epoch": 0.09507640067911714, "grad_norm": 0.33163871819653157, "learning_rate": 2.2881355932203392e-05, "loss": 0.31743013858795166, "step": 28 }, { "epoch": 0.09847198641765705, "grad_norm": 0.34885399183345184, "learning_rate": 2.3728813559322036e-05, "loss": 0.3014258146286011, "step": 29 }, { "epoch": 0.10186757215619695, "grad_norm": 0.3235707342290877, "learning_rate": 2.457627118644068e-05, "loss": 0.29429274797439575, "step": 30 }, { "epoch": 0.10526315789473684, "grad_norm": 0.32301705271246933, "learning_rate": 2.5423728813559322e-05, "loss": 0.27901843190193176, "step": 31 }, { "epoch": 0.10865874363327674, "grad_norm": 0.3328740290750329, "learning_rate": 2.627118644067797e-05, "loss": 0.28073322772979736, "step": 32 }, { "epoch": 0.11205432937181664, "grad_norm": 0.32934151465610345, "learning_rate": 2.711864406779661e-05, "loss": 0.26665592193603516, "step": 33 }, { "epoch": 0.11544991511035653, "grad_norm": 0.30895833999585576, "learning_rate": 2.7966101694915255e-05, "loss": 0.2844397723674774, "step": 34 }, { "epoch": 0.11884550084889643, "grad_norm": 0.29409250644402124, "learning_rate": 2.88135593220339e-05, "loss": 0.29826027154922485, "step": 35 }, { "epoch": 0.12224108658743633, "grad_norm": 0.3066490918221555, "learning_rate": 2.9661016949152544e-05, "loss": 0.2704620957374573, "step": 36 }, { "epoch": 0.12563667232597622, "grad_norm": 0.29850762913030954, "learning_rate": 3.050847457627119e-05, "loss": 0.2801765203475952, "step": 37 }, { "epoch": 0.12903225806451613, "grad_norm": 0.2769974355631427, "learning_rate": 3.135593220338983e-05, "loss": 0.2755379378795624, "step": 38 }, { "epoch": 0.13242784380305603, "grad_norm": 0.31229499220438495, "learning_rate": 3.2203389830508473e-05, "loss": 0.27392563223838806, "step": 39 }, { "epoch": 0.13582342954159593, "grad_norm": 0.3121543507899163, "learning_rate": 3.305084745762712e-05, "loss": 0.24640874564647675, "step": 40 }, { "epoch": 0.13921901528013583, "grad_norm": 0.2920964725106723, "learning_rate": 3.389830508474576e-05, "loss": 0.24937844276428223, "step": 41 }, { "epoch": 0.14261460101867574, "grad_norm": 0.2832903021531751, "learning_rate": 3.474576271186441e-05, "loss": 0.25076529383659363, "step": 42 }, { "epoch": 0.1460101867572156, "grad_norm": 0.2517064059515119, "learning_rate": 3.559322033898305e-05, "loss": 0.26312685012817383, "step": 43 }, { "epoch": 0.1494057724957555, "grad_norm": 0.26067522574411217, "learning_rate": 3.644067796610169e-05, "loss": 0.2565669119358063, "step": 44 }, { "epoch": 0.15280135823429541, "grad_norm": 0.274059447401076, "learning_rate": 3.728813559322034e-05, "loss": 0.28337615728378296, "step": 45 }, { "epoch": 0.15619694397283532, "grad_norm": 0.272219295537493, "learning_rate": 3.813559322033898e-05, "loss": 0.2608831822872162, "step": 46 }, { "epoch": 0.15959252971137522, "grad_norm": 0.31595145902013216, "learning_rate": 3.898305084745763e-05, "loss": 0.24877464771270752, "step": 47 }, { "epoch": 0.16298811544991512, "grad_norm": 0.30595679969475015, "learning_rate": 3.983050847457627e-05, "loss": 0.2465878427028656, "step": 48 }, { "epoch": 0.166383701188455, "grad_norm": 0.2808994087856909, "learning_rate": 4.067796610169492e-05, "loss": 0.23259060084819794, "step": 49 }, { "epoch": 0.1697792869269949, "grad_norm": 0.2930708483785845, "learning_rate": 4.152542372881356e-05, "loss": 0.23619721829891205, "step": 50 }, { "epoch": 0.1731748726655348, "grad_norm": 0.27119687354085953, "learning_rate": 4.2372881355932206e-05, "loss": 0.26022595167160034, "step": 51 }, { "epoch": 0.1765704584040747, "grad_norm": 0.2465483728288827, "learning_rate": 4.3220338983050854e-05, "loss": 0.26318615674972534, "step": 52 }, { "epoch": 0.1799660441426146, "grad_norm": 0.30993157297661167, "learning_rate": 4.4067796610169495e-05, "loss": 0.2581077516078949, "step": 53 }, { "epoch": 0.1833616298811545, "grad_norm": 0.2756408620637424, "learning_rate": 4.491525423728814e-05, "loss": 0.2514834702014923, "step": 54 }, { "epoch": 0.1867572156196944, "grad_norm": 0.2688205497477428, "learning_rate": 4.5762711864406784e-05, "loss": 0.2395961880683899, "step": 55 }, { "epoch": 0.19015280135823429, "grad_norm": 0.2797862133713835, "learning_rate": 4.6610169491525425e-05, "loss": 0.23115402460098267, "step": 56 }, { "epoch": 0.1935483870967742, "grad_norm": 0.299833238900138, "learning_rate": 4.745762711864407e-05, "loss": 0.22424674034118652, "step": 57 }, { "epoch": 0.1969439728353141, "grad_norm": 0.2974429665195766, "learning_rate": 4.8305084745762714e-05, "loss": 0.2266063541173935, "step": 58 }, { "epoch": 0.200339558573854, "grad_norm": 0.3074728646747482, "learning_rate": 4.915254237288136e-05, "loss": 0.24925050139427185, "step": 59 }, { "epoch": 0.2037351443123939, "grad_norm": 0.27842595688581606, "learning_rate": 5e-05, "loss": 0.2657631039619446, "step": 60 }, { "epoch": 0.2071307300509338, "grad_norm": 0.27054182287227413, "learning_rate": 5.0847457627118643e-05, "loss": 0.24390384554862976, "step": 61 }, { "epoch": 0.21052631578947367, "grad_norm": 0.2629289037299303, "learning_rate": 5.1694915254237284e-05, "loss": 0.2410869598388672, "step": 62 }, { "epoch": 0.21392190152801357, "grad_norm": 0.2815787137609419, "learning_rate": 5.254237288135594e-05, "loss": 0.23393619060516357, "step": 63 }, { "epoch": 0.21731748726655348, "grad_norm": 0.2870747787775851, "learning_rate": 5.338983050847458e-05, "loss": 0.23251163959503174, "step": 64 }, { "epoch": 0.22071307300509338, "grad_norm": 0.28822425402194735, "learning_rate": 5.423728813559322e-05, "loss": 0.2286069095134735, "step": 65 }, { "epoch": 0.22410865874363328, "grad_norm": 0.31256114821592534, "learning_rate": 5.508474576271186e-05, "loss": 0.22654178738594055, "step": 66 }, { "epoch": 0.22750424448217318, "grad_norm": 0.29215769863012814, "learning_rate": 5.593220338983051e-05, "loss": 0.23508411645889282, "step": 67 }, { "epoch": 0.23089983022071306, "grad_norm": 0.25956440944882164, "learning_rate": 5.677966101694916e-05, "loss": 0.2418670654296875, "step": 68 }, { "epoch": 0.23429541595925296, "grad_norm": 0.26644877416507473, "learning_rate": 5.76271186440678e-05, "loss": 0.2391325831413269, "step": 69 }, { "epoch": 0.23769100169779286, "grad_norm": 0.2718799524237907, "learning_rate": 5.8474576271186446e-05, "loss": 0.24404564499855042, "step": 70 }, { "epoch": 0.24108658743633277, "grad_norm": 0.2769577516508414, "learning_rate": 5.932203389830509e-05, "loss": 0.23093831539154053, "step": 71 }, { "epoch": 0.24448217317487267, "grad_norm": 0.29237078873214223, "learning_rate": 6.016949152542373e-05, "loss": 0.24410948157310486, "step": 72 }, { "epoch": 0.24787775891341257, "grad_norm": 0.3297291053281998, "learning_rate": 6.101694915254238e-05, "loss": 0.23357895016670227, "step": 73 }, { "epoch": 0.25127334465195245, "grad_norm": 0.3078831195163542, "learning_rate": 6.186440677966102e-05, "loss": 0.2180016040802002, "step": 74 }, { "epoch": 0.2546689303904924, "grad_norm": 0.3130009140276919, "learning_rate": 6.271186440677966e-05, "loss": 0.21485942602157593, "step": 75 }, { "epoch": 0.25806451612903225, "grad_norm": 0.28447816094326384, "learning_rate": 6.35593220338983e-05, "loss": 0.25424039363861084, "step": 76 }, { "epoch": 0.2614601018675722, "grad_norm": 0.30990036193570847, "learning_rate": 6.440677966101695e-05, "loss": 0.25314486026763916, "step": 77 }, { "epoch": 0.26485568760611206, "grad_norm": 0.26991950416044874, "learning_rate": 6.52542372881356e-05, "loss": 0.22962228953838348, "step": 78 }, { "epoch": 0.26825127334465193, "grad_norm": 1.0220845311120397, "learning_rate": 6.610169491525424e-05, "loss": 0.24812579154968262, "step": 79 }, { "epoch": 0.27164685908319186, "grad_norm": 0.3491152906829097, "learning_rate": 6.694915254237288e-05, "loss": 0.23628483712673187, "step": 80 }, { "epoch": 0.27504244482173174, "grad_norm": 0.34596477970724354, "learning_rate": 6.779661016949152e-05, "loss": 0.24312669038772583, "step": 81 }, { "epoch": 0.27843803056027167, "grad_norm": 0.2861787003138505, "learning_rate": 6.864406779661017e-05, "loss": 0.22090747952461243, "step": 82 }, { "epoch": 0.28183361629881154, "grad_norm": 0.3376416572552162, "learning_rate": 6.949152542372882e-05, "loss": 0.21311447024345398, "step": 83 }, { "epoch": 0.28522920203735147, "grad_norm": 0.30220067483237284, "learning_rate": 7.033898305084746e-05, "loss": 0.2596338987350464, "step": 84 }, { "epoch": 0.28862478777589134, "grad_norm": 0.304176990038654, "learning_rate": 7.11864406779661e-05, "loss": 0.250480979681015, "step": 85 }, { "epoch": 0.2920203735144312, "grad_norm": 0.3067091330776441, "learning_rate": 7.203389830508474e-05, "loss": 0.24448975920677185, "step": 86 }, { "epoch": 0.29541595925297115, "grad_norm": 0.2707170367805139, "learning_rate": 7.288135593220338e-05, "loss": 0.2309844195842743, "step": 87 }, { "epoch": 0.298811544991511, "grad_norm": 0.3243362291384308, "learning_rate": 7.372881355932204e-05, "loss": 0.24441036581993103, "step": 88 }, { "epoch": 0.30220713073005095, "grad_norm": 0.2921086132939245, "learning_rate": 7.457627118644068e-05, "loss": 0.2598271071910858, "step": 89 }, { "epoch": 0.30560271646859083, "grad_norm": 0.28839990950963534, "learning_rate": 7.542372881355932e-05, "loss": 0.23641186952590942, "step": 90 }, { "epoch": 0.3089983022071307, "grad_norm": 0.3057950605202564, "learning_rate": 7.627118644067796e-05, "loss": 0.22635196149349213, "step": 91 }, { "epoch": 0.31239388794567063, "grad_norm": 0.22784654347096958, "learning_rate": 7.711864406779662e-05, "loss": 0.20973172783851624, "step": 92 }, { "epoch": 0.3157894736842105, "grad_norm": 0.2484902545262132, "learning_rate": 7.796610169491526e-05, "loss": 0.24659594893455505, "step": 93 }, { "epoch": 0.31918505942275044, "grad_norm": 0.2528670120941044, "learning_rate": 7.88135593220339e-05, "loss": 0.24071916937828064, "step": 94 }, { "epoch": 0.3225806451612903, "grad_norm": 0.2544980769679746, "learning_rate": 7.966101694915254e-05, "loss": 0.2425764799118042, "step": 95 }, { "epoch": 0.32597623089983024, "grad_norm": 0.28296559367720997, "learning_rate": 8.050847457627118e-05, "loss": 0.24026596546173096, "step": 96 }, { "epoch": 0.3293718166383701, "grad_norm": 0.2476123815218834, "learning_rate": 8.135593220338983e-05, "loss": 0.2345629185438156, "step": 97 }, { "epoch": 0.33276740237691, "grad_norm": 0.3053122498619456, "learning_rate": 8.220338983050848e-05, "loss": 0.23744282126426697, "step": 98 }, { "epoch": 0.3361629881154499, "grad_norm": 0.3039538114080653, "learning_rate": 8.305084745762712e-05, "loss": 0.21833720803260803, "step": 99 }, { "epoch": 0.3395585738539898, "grad_norm": 0.31264272278793, "learning_rate": 8.389830508474577e-05, "loss": 0.21772217750549316, "step": 100 }, { "epoch": 0.34295415959252973, "grad_norm": 0.2834035728984204, "learning_rate": 8.474576271186441e-05, "loss": 0.2518566846847534, "step": 101 }, { "epoch": 0.3463497453310696, "grad_norm": 0.31586267486469405, "learning_rate": 8.559322033898305e-05, "loss": 0.2416839301586151, "step": 102 }, { "epoch": 0.34974533106960953, "grad_norm": 0.268794645432501, "learning_rate": 8.644067796610171e-05, "loss": 0.24528560042381287, "step": 103 }, { "epoch": 0.3531409168081494, "grad_norm": 0.28001337035203555, "learning_rate": 8.728813559322035e-05, "loss": 0.22554072737693787, "step": 104 }, { "epoch": 0.3565365025466893, "grad_norm": 0.2835640219032533, "learning_rate": 8.813559322033899e-05, "loss": 0.22901424765586853, "step": 105 }, { "epoch": 0.3599320882852292, "grad_norm": 0.26729968270766336, "learning_rate": 8.898305084745763e-05, "loss": 0.22536587715148926, "step": 106 }, { "epoch": 0.3633276740237691, "grad_norm": 0.32611558042731953, "learning_rate": 8.983050847457629e-05, "loss": 0.23820099234580994, "step": 107 }, { "epoch": 0.366723259762309, "grad_norm": 0.3073872772182986, "learning_rate": 9.067796610169493e-05, "loss": 0.21564078330993652, "step": 108 }, { "epoch": 0.3701188455008489, "grad_norm": 0.2951967170550103, "learning_rate": 9.152542372881357e-05, "loss": 0.24727819859981537, "step": 109 }, { "epoch": 0.3735144312393888, "grad_norm": 0.23564762930118563, "learning_rate": 9.237288135593221e-05, "loss": 0.2485099732875824, "step": 110 }, { "epoch": 0.3769100169779287, "grad_norm": 0.31185267277827233, "learning_rate": 9.322033898305085e-05, "loss": 0.25064414739608765, "step": 111 }, { "epoch": 0.38030560271646857, "grad_norm": 0.26456355130445813, "learning_rate": 9.40677966101695e-05, "loss": 0.23823675513267517, "step": 112 }, { "epoch": 0.3837011884550085, "grad_norm": 0.2941404185468414, "learning_rate": 9.491525423728815e-05, "loss": 0.24941816926002502, "step": 113 }, { "epoch": 0.3870967741935484, "grad_norm": 0.24427145133335398, "learning_rate": 9.576271186440679e-05, "loss": 0.22978711128234863, "step": 114 }, { "epoch": 0.3904923599320883, "grad_norm": 0.30334302685190373, "learning_rate": 9.661016949152543e-05, "loss": 0.23350685834884644, "step": 115 }, { "epoch": 0.3938879456706282, "grad_norm": 0.2876001006694176, "learning_rate": 9.745762711864407e-05, "loss": 0.2257934808731079, "step": 116 }, { "epoch": 0.39728353140916806, "grad_norm": 0.2648043071910942, "learning_rate": 9.830508474576272e-05, "loss": 0.24483530223369598, "step": 117 }, { "epoch": 0.400679117147708, "grad_norm": 0.23226586717675315, "learning_rate": 9.915254237288136e-05, "loss": 0.24188470840454102, "step": 118 }, { "epoch": 0.40407470288624786, "grad_norm": 0.27389378576251483, "learning_rate": 0.0001, "loss": 0.2457769811153412, "step": 119 }, { "epoch": 0.4074702886247878, "grad_norm": 0.25747369116641317, "learning_rate": 9.999978122867161e-05, "loss": 0.23224882781505585, "step": 120 }, { "epoch": 0.41086587436332767, "grad_norm": 0.26538842180860334, "learning_rate": 9.999912491660088e-05, "loss": 0.23609435558319092, "step": 121 }, { "epoch": 0.4142614601018676, "grad_norm": 0.275250057115362, "learning_rate": 9.99980310695311e-05, "loss": 0.23923230171203613, "step": 122 }, { "epoch": 0.41765704584040747, "grad_norm": 0.2596333388961926, "learning_rate": 9.999649969703437e-05, "loss": 0.23534950613975525, "step": 123 }, { "epoch": 0.42105263157894735, "grad_norm": 0.24276315608073315, "learning_rate": 9.999453081251149e-05, "loss": 0.22054855525493622, "step": 124 }, { "epoch": 0.4244482173174873, "grad_norm": 0.3384992259113457, "learning_rate": 9.99921244331919e-05, "loss": 0.22554771602153778, "step": 125 }, { "epoch": 0.42784380305602715, "grad_norm": 0.2968986888666945, "learning_rate": 9.998928058013346e-05, "loss": 0.2488570213317871, "step": 126 }, { "epoch": 0.4312393887945671, "grad_norm": 0.2826819439062709, "learning_rate": 9.99859992782223e-05, "loss": 0.24295395612716675, "step": 127 }, { "epoch": 0.43463497453310695, "grad_norm": 0.3642084364156491, "learning_rate": 9.998228055617263e-05, "loss": 0.23964045941829681, "step": 128 }, { "epoch": 0.4380305602716469, "grad_norm": 0.2675296383842667, "learning_rate": 9.997812444652643e-05, "loss": 0.23436205089092255, "step": 129 }, { "epoch": 0.44142614601018676, "grad_norm": 0.2659048185872125, "learning_rate": 9.997353098565322e-05, "loss": 0.22157415747642517, "step": 130 }, { "epoch": 0.44482173174872663, "grad_norm": 0.3181127584848804, "learning_rate": 9.996850021374968e-05, "loss": 0.22607165575027466, "step": 131 }, { "epoch": 0.44821731748726656, "grad_norm": 0.3256839864726622, "learning_rate": 9.996303217483938e-05, "loss": 0.24126724898815155, "step": 132 }, { "epoch": 0.45161290322580644, "grad_norm": 0.27819862401817325, "learning_rate": 9.99571269167723e-05, "loss": 0.21310493350028992, "step": 133 }, { "epoch": 0.45500848896434637, "grad_norm": 0.2591513363001427, "learning_rate": 9.995078449122451e-05, "loss": 0.23288008570671082, "step": 134 }, { "epoch": 0.45840407470288624, "grad_norm": 0.24609223880688985, "learning_rate": 9.99440049536976e-05, "loss": 0.25551778078079224, "step": 135 }, { "epoch": 0.4617996604414261, "grad_norm": 0.24766365401541507, "learning_rate": 9.993678836351836e-05, "loss": 0.23258076608181, "step": 136 }, { "epoch": 0.46519524617996605, "grad_norm": 0.2549750915003169, "learning_rate": 9.99291347838381e-05, "loss": 0.22909608483314514, "step": 137 }, { "epoch": 0.4685908319185059, "grad_norm": 0.25075975271808476, "learning_rate": 9.992104428163216e-05, "loss": 0.236228346824646, "step": 138 }, { "epoch": 0.47198641765704585, "grad_norm": 0.23917293910575416, "learning_rate": 9.991251692769932e-05, "loss": 0.2221929281949997, "step": 139 }, { "epoch": 0.47538200339558573, "grad_norm": 0.28607245732660613, "learning_rate": 9.990355279666124e-05, "loss": 0.22002971172332764, "step": 140 }, { "epoch": 0.47877758913412566, "grad_norm": 0.24375634268837235, "learning_rate": 9.98941519669617e-05, "loss": 0.22249025106430054, "step": 141 }, { "epoch": 0.48217317487266553, "grad_norm": 0.2339941928598905, "learning_rate": 9.988431452086596e-05, "loss": 0.20767802000045776, "step": 142 }, { "epoch": 0.4855687606112054, "grad_norm": 0.23290814297020354, "learning_rate": 9.987404054446008e-05, "loss": 0.24194371700286865, "step": 143 }, { "epoch": 0.48896434634974534, "grad_norm": 0.2538442405323861, "learning_rate": 9.986333012765013e-05, "loss": 0.24343231320381165, "step": 144 }, { "epoch": 0.4923599320882852, "grad_norm": 0.2259286883769085, "learning_rate": 9.985218336416138e-05, "loss": 0.24083857238292694, "step": 145 }, { "epoch": 0.49575551782682514, "grad_norm": 0.24896923720128053, "learning_rate": 9.98406003515375e-05, "loss": 0.23101024329662323, "step": 146 }, { "epoch": 0.499151103565365, "grad_norm": 0.24690084030564002, "learning_rate": 9.982858119113979e-05, "loss": 0.23537294566631317, "step": 147 }, { "epoch": 0.5025466893039049, "grad_norm": 0.24124796562103648, "learning_rate": 9.981612598814611e-05, "loss": 0.22967486083507538, "step": 148 }, { "epoch": 0.5059422750424448, "grad_norm": 0.2425219810352701, "learning_rate": 9.980323485155013e-05, "loss": 0.21077534556388855, "step": 149 }, { "epoch": 0.5093378607809848, "grad_norm": 0.26963585646991833, "learning_rate": 9.97899078941603e-05, "loss": 0.20987191796302795, "step": 150 }, { "epoch": 0.5127334465195246, "grad_norm": 0.25170293382554876, "learning_rate": 9.977614523259884e-05, "loss": 0.24986539781093597, "step": 151 }, { "epoch": 0.5161290322580645, "grad_norm": 0.24453912430421668, "learning_rate": 9.976194698730079e-05, "loss": 0.2411619871854782, "step": 152 }, { "epoch": 0.5195246179966044, "grad_norm": 0.23845009638923265, "learning_rate": 9.974731328251293e-05, "loss": 0.23960785567760468, "step": 153 }, { "epoch": 0.5229202037351444, "grad_norm": 0.23825968246585716, "learning_rate": 9.973224424629265e-05, "loss": 0.24369370937347412, "step": 154 }, { "epoch": 0.5263157894736842, "grad_norm": 0.24081387503583154, "learning_rate": 9.971674001050686e-05, "loss": 0.2217572033405304, "step": 155 }, { "epoch": 0.5297113752122241, "grad_norm": 0.2368221694288877, "learning_rate": 9.970080071083086e-05, "loss": 0.2258390635251999, "step": 156 }, { "epoch": 0.533106960950764, "grad_norm": 0.23612543736335817, "learning_rate": 9.968442648674713e-05, "loss": 0.21871167421340942, "step": 157 }, { "epoch": 0.5365025466893039, "grad_norm": 0.2609339513877981, "learning_rate": 9.966761748154408e-05, "loss": 0.21429364383220673, "step": 158 }, { "epoch": 0.5398981324278438, "grad_norm": 0.3462259358153489, "learning_rate": 9.965037384231488e-05, "loss": 0.23577401041984558, "step": 159 }, { "epoch": 0.5432937181663837, "grad_norm": 0.2375981364678808, "learning_rate": 9.963269571995604e-05, "loss": 0.24383918941020966, "step": 160 }, { "epoch": 0.5466893039049237, "grad_norm": 0.21971125387406673, "learning_rate": 9.961458326916624e-05, "loss": 0.23908346891403198, "step": 161 }, { "epoch": 0.5500848896434635, "grad_norm": 0.2444792277557053, "learning_rate": 9.959603664844486e-05, "loss": 0.23127907514572144, "step": 162 }, { "epoch": 0.5534804753820034, "grad_norm": 0.2236933314234141, "learning_rate": 9.957705602009068e-05, "loss": 0.21496352553367615, "step": 163 }, { "epoch": 0.5568760611205433, "grad_norm": 0.23047572354016072, "learning_rate": 9.955764155020037e-05, "loss": 0.21383583545684814, "step": 164 }, { "epoch": 0.5602716468590832, "grad_norm": 0.2371020305148902, "learning_rate": 9.95377934086671e-05, "loss": 0.21415869891643524, "step": 165 }, { "epoch": 0.5636672325976231, "grad_norm": 0.23004400662748126, "learning_rate": 9.951751176917907e-05, "loss": 0.20883099734783173, "step": 166 }, { "epoch": 0.567062818336163, "grad_norm": 0.22985743584856486, "learning_rate": 9.94967968092179e-05, "loss": 0.23498499393463135, "step": 167 }, { "epoch": 0.5704584040747029, "grad_norm": 0.19221689552246435, "learning_rate": 9.947564871005717e-05, "loss": 0.23385265469551086, "step": 168 }, { "epoch": 0.5738539898132428, "grad_norm": 0.23109427282183093, "learning_rate": 9.94540676567608e-05, "loss": 0.22728487849235535, "step": 169 }, { "epoch": 0.5772495755517827, "grad_norm": 0.20967421541722642, "learning_rate": 9.943205383818141e-05, "loss": 0.21729111671447754, "step": 170 }, { "epoch": 0.5806451612903226, "grad_norm": 0.23102227805619963, "learning_rate": 9.940960744695868e-05, "loss": 0.23023006319999695, "step": 171 }, { "epoch": 0.5840407470288624, "grad_norm": 0.2420970011212825, "learning_rate": 9.938672867951773e-05, "loss": 0.2244199961423874, "step": 172 }, { "epoch": 0.5874363327674024, "grad_norm": 0.2674784936403934, "learning_rate": 9.936341773606723e-05, "loss": 0.2145002782344818, "step": 173 }, { "epoch": 0.5908319185059423, "grad_norm": 0.5505928704828632, "learning_rate": 9.933967482059787e-05, "loss": 0.20907706022262573, "step": 174 }, { "epoch": 0.5942275042444821, "grad_norm": 0.2439458879076872, "learning_rate": 9.931550014088039e-05, "loss": 0.19370412826538086, "step": 175 }, { "epoch": 0.597623089983022, "grad_norm": 0.2578216766006382, "learning_rate": 9.929089390846387e-05, "loss": 0.2393697202205658, "step": 176 }, { "epoch": 0.601018675721562, "grad_norm": 0.21911859121319766, "learning_rate": 9.926585633867385e-05, "loss": 0.24075564742088318, "step": 177 }, { "epoch": 0.6044142614601019, "grad_norm": 0.24167737010639073, "learning_rate": 9.924038765061042e-05, "loss": 0.23893170058727264, "step": 178 }, { "epoch": 0.6078098471986417, "grad_norm": 0.2392591083645638, "learning_rate": 9.921448806714631e-05, "loss": 0.22211198508739471, "step": 179 }, { "epoch": 0.6112054329371817, "grad_norm": 0.24149646241546793, "learning_rate": 9.918815781492496e-05, "loss": 0.22911500930786133, "step": 180 }, { "epoch": 0.6146010186757216, "grad_norm": 0.2330368614745652, "learning_rate": 9.916139712435859e-05, "loss": 0.22218236327171326, "step": 181 }, { "epoch": 0.6179966044142614, "grad_norm": 0.24241191065237344, "learning_rate": 9.913420622962606e-05, "loss": 0.21815602481365204, "step": 182 }, { "epoch": 0.6213921901528013, "grad_norm": 0.259381094272317, "learning_rate": 9.910658536867086e-05, "loss": 0.21466827392578125, "step": 183 }, { "epoch": 0.6247877758913413, "grad_norm": 0.3392411728170959, "learning_rate": 9.907853478319912e-05, "loss": 0.2501360774040222, "step": 184 }, { "epoch": 0.6281833616298812, "grad_norm": 0.21620775988572558, "learning_rate": 9.905005471867739e-05, "loss": 0.24319049715995789, "step": 185 }, { "epoch": 0.631578947368421, "grad_norm": 0.21527519792897112, "learning_rate": 9.902114542433051e-05, "loss": 0.23267647624015808, "step": 186 }, { "epoch": 0.634974533106961, "grad_norm": 0.23527519296236515, "learning_rate": 9.89918071531395e-05, "loss": 0.23907360434532166, "step": 187 }, { "epoch": 0.6383701188455009, "grad_norm": 0.2144800990174471, "learning_rate": 9.896204016183925e-05, "loss": 0.22426418960094452, "step": 188 }, { "epoch": 0.6417657045840407, "grad_norm": 0.23191452419769198, "learning_rate": 9.89318447109163e-05, "loss": 0.2166368067264557, "step": 189 }, { "epoch": 0.6451612903225806, "grad_norm": 0.2226720006092361, "learning_rate": 9.890122106460666e-05, "loss": 0.21565070748329163, "step": 190 }, { "epoch": 0.6485568760611206, "grad_norm": 0.28638814824103664, "learning_rate": 9.887016949089333e-05, "loss": 0.22057998180389404, "step": 191 }, { "epoch": 0.6519524617996605, "grad_norm": 0.19964523808801346, "learning_rate": 9.883869026150409e-05, "loss": 0.22001051902770996, "step": 192 }, { "epoch": 0.6553480475382003, "grad_norm": 0.2434705198140148, "learning_rate": 9.880678365190902e-05, "loss": 0.24053768813610077, "step": 193 }, { "epoch": 0.6587436332767402, "grad_norm": 0.19175601578409845, "learning_rate": 9.87744499413182e-05, "loss": 0.2291802614927292, "step": 194 }, { "epoch": 0.6621392190152802, "grad_norm": 0.22819224579212527, "learning_rate": 9.874168941267919e-05, "loss": 0.23475182056427002, "step": 195 }, { "epoch": 0.66553480475382, "grad_norm": 0.20527796312488006, "learning_rate": 9.870850235267453e-05, "loss": 0.21865954995155334, "step": 196 }, { "epoch": 0.6689303904923599, "grad_norm": 0.22699016503127842, "learning_rate": 9.867488905171933e-05, "loss": 0.2129548043012619, "step": 197 }, { "epoch": 0.6723259762308998, "grad_norm": 0.24053051790238097, "learning_rate": 9.864084980395867e-05, "loss": 0.21274515986442566, "step": 198 }, { "epoch": 0.6757215619694398, "grad_norm": 0.22816028708980923, "learning_rate": 9.860638490726497e-05, "loss": 0.22238099575042725, "step": 199 }, { "epoch": 0.6791171477079796, "grad_norm": 0.25613254321686274, "learning_rate": 9.857149466323549e-05, "loss": 0.20551300048828125, "step": 200 }, { "epoch": 0.6825127334465195, "grad_norm": 0.22001252643151026, "learning_rate": 9.853617937718966e-05, "loss": 0.2297489047050476, "step": 201 }, { "epoch": 0.6859083191850595, "grad_norm": 0.25532533042606137, "learning_rate": 9.850043935816633e-05, "loss": 0.2405668944120407, "step": 202 }, { "epoch": 0.6893039049235993, "grad_norm": 0.23482993444978664, "learning_rate": 9.846427491892118e-05, "loss": 0.23680107295513153, "step": 203 }, { "epoch": 0.6926994906621392, "grad_norm": 0.2582438553420209, "learning_rate": 9.842768637592388e-05, "loss": 0.22432434558868408, "step": 204 }, { "epoch": 0.6960950764006791, "grad_norm": 0.22020266953943335, "learning_rate": 9.839067404935542e-05, "loss": 0.21109239757061005, "step": 205 }, { "epoch": 0.6994906621392191, "grad_norm": 0.2717685353287526, "learning_rate": 9.835323826310521e-05, "loss": 0.22163572907447815, "step": 206 }, { "epoch": 0.7028862478777589, "grad_norm": 0.3019649434328468, "learning_rate": 9.831537934476835e-05, "loss": 0.2140854448080063, "step": 207 }, { "epoch": 0.7062818336162988, "grad_norm": 0.2740801953874853, "learning_rate": 9.827709762564263e-05, "loss": 0.21572613716125488, "step": 208 }, { "epoch": 0.7096774193548387, "grad_norm": 0.20564506956158862, "learning_rate": 9.82383934407258e-05, "loss": 0.2118043154478073, "step": 209 }, { "epoch": 0.7130730050933786, "grad_norm": 0.23463817984128638, "learning_rate": 9.819926712871247e-05, "loss": 0.24360692501068115, "step": 210 }, { "epoch": 0.7164685908319185, "grad_norm": 0.2506599602978059, "learning_rate": 9.815971903199126e-05, "loss": 0.23330163955688477, "step": 211 }, { "epoch": 0.7198641765704584, "grad_norm": 0.2165406109902145, "learning_rate": 9.811974949664175e-05, "loss": 0.22115230560302734, "step": 212 }, { "epoch": 0.7232597623089984, "grad_norm": 0.29386282210272563, "learning_rate": 9.807935887243147e-05, "loss": 0.21811804175376892, "step": 213 }, { "epoch": 0.7266553480475382, "grad_norm": 0.24637098435902682, "learning_rate": 9.803854751281285e-05, "loss": 0.21622085571289062, "step": 214 }, { "epoch": 0.7300509337860781, "grad_norm": 0.1999187144486826, "learning_rate": 9.79973157749201e-05, "loss": 0.21213003993034363, "step": 215 }, { "epoch": 0.733446519524618, "grad_norm": 0.24744893133293125, "learning_rate": 9.79556640195661e-05, "loss": 0.206097811460495, "step": 216 }, { "epoch": 0.7368421052631579, "grad_norm": 0.22788546922018882, "learning_rate": 9.791359261123926e-05, "loss": 0.2234858274459839, "step": 217 }, { "epoch": 0.7402376910016978, "grad_norm": 0.20858892742230126, "learning_rate": 9.787110191810027e-05, "loss": 0.24231219291687012, "step": 218 }, { "epoch": 0.7436332767402377, "grad_norm": 0.2267682667380985, "learning_rate": 9.782819231197898e-05, "loss": 0.2433917224407196, "step": 219 }, { "epoch": 0.7470288624787776, "grad_norm": 0.3012471402597334, "learning_rate": 9.7784864168371e-05, "loss": 0.23701052367687225, "step": 220 }, { "epoch": 0.7504244482173175, "grad_norm": 0.22460949613297732, "learning_rate": 9.77411178664346e-05, "loss": 0.2211240977048874, "step": 221 }, { "epoch": 0.7538200339558574, "grad_norm": 0.20126959236888448, "learning_rate": 9.769695378898722e-05, "loss": 0.21307848393917084, "step": 222 }, { "epoch": 0.7572156196943973, "grad_norm": 0.2240482042851325, "learning_rate": 9.765237232250222e-05, "loss": 0.1993296593427658, "step": 223 }, { "epoch": 0.7606112054329371, "grad_norm": 0.22166240405161985, "learning_rate": 9.760737385710547e-05, "loss": 0.2002106010913849, "step": 224 }, { "epoch": 0.7640067911714771, "grad_norm": 0.253121580685781, "learning_rate": 9.756195878657192e-05, "loss": 0.20609150826931, "step": 225 }, { "epoch": 0.767402376910017, "grad_norm": 0.22838002747674188, "learning_rate": 9.75161275083222e-05, "loss": 0.25632837414741516, "step": 226 }, { "epoch": 0.7707979626485568, "grad_norm": 0.2330536968679869, "learning_rate": 9.746988042341906e-05, "loss": 0.24463418126106262, "step": 227 }, { "epoch": 0.7741935483870968, "grad_norm": 0.21524878435254452, "learning_rate": 9.7423217936564e-05, "loss": 0.22175154089927673, "step": 228 }, { "epoch": 0.7775891341256367, "grad_norm": 0.23262188037812695, "learning_rate": 9.737614045609356e-05, "loss": 0.2339438796043396, "step": 229 }, { "epoch": 0.7809847198641766, "grad_norm": 0.21455383516408152, "learning_rate": 9.732864839397584e-05, "loss": 0.2252509444952011, "step": 230 }, { "epoch": 0.7843803056027164, "grad_norm": 0.2580180483054227, "learning_rate": 9.728074216580694e-05, "loss": 0.22049729526042938, "step": 231 }, { "epoch": 0.7877758913412564, "grad_norm": 0.21302285464955284, "learning_rate": 9.723242219080721e-05, "loss": 0.20171833038330078, "step": 232 }, { "epoch": 0.7911714770797963, "grad_norm": 0.22398387224597013, "learning_rate": 9.718368889181764e-05, "loss": 0.20669804513454437, "step": 233 }, { "epoch": 0.7945670628183361, "grad_norm": 0.22246699973042186, "learning_rate": 9.71345426952962e-05, "loss": 0.24574396014213562, "step": 234 }, { "epoch": 0.797962648556876, "grad_norm": 0.20843439206417017, "learning_rate": 9.708498403131401e-05, "loss": 0.23050853610038757, "step": 235 }, { "epoch": 0.801358234295416, "grad_norm": 0.22768441548459212, "learning_rate": 9.703501333355168e-05, "loss": 0.2236669361591339, "step": 236 }, { "epoch": 0.8047538200339559, "grad_norm": 0.21488462939087113, "learning_rate": 9.698463103929542e-05, "loss": 0.2220085710287094, "step": 237 }, { "epoch": 0.8081494057724957, "grad_norm": 0.21294391155550424, "learning_rate": 9.693383758943333e-05, "loss": 0.21017488837242126, "step": 238 }, { "epoch": 0.8115449915110357, "grad_norm": 0.2128727333722193, "learning_rate": 9.68826334284514e-05, "loss": 0.21301934123039246, "step": 239 }, { "epoch": 0.8149405772495756, "grad_norm": 0.22452955463813973, "learning_rate": 9.683101900442973e-05, "loss": 0.2175242006778717, "step": 240 }, { "epoch": 0.8183361629881154, "grad_norm": 0.26314811474353683, "learning_rate": 9.677899476903857e-05, "loss": 0.20314472913742065, "step": 241 }, { "epoch": 0.8217317487266553, "grad_norm": 0.20943356666754928, "learning_rate": 9.672656117753434e-05, "loss": 0.20858506858348846, "step": 242 }, { "epoch": 0.8251273344651953, "grad_norm": 0.20166102733071112, "learning_rate": 9.667371868875574e-05, "loss": 0.23567888140678406, "step": 243 }, { "epoch": 0.8285229202037352, "grad_norm": 0.2103456969245814, "learning_rate": 9.662046776511959e-05, "loss": 0.21773743629455566, "step": 244 }, { "epoch": 0.831918505942275, "grad_norm": 0.1952887711374154, "learning_rate": 9.656680887261693e-05, "loss": 0.22131644189357758, "step": 245 }, { "epoch": 0.8353140916808149, "grad_norm": 0.21895280786893642, "learning_rate": 9.651274248080882e-05, "loss": 0.2135392427444458, "step": 246 }, { "epoch": 0.8387096774193549, "grad_norm": 0.18951044452160157, "learning_rate": 9.645826906282233e-05, "loss": 0.20288246870040894, "step": 247 }, { "epoch": 0.8421052631578947, "grad_norm": 0.21855009685707136, "learning_rate": 9.640338909534636e-05, "loss": 0.2056213915348053, "step": 248 }, { "epoch": 0.8455008488964346, "grad_norm": 0.20343290559046082, "learning_rate": 9.634810305862741e-05, "loss": 0.20447847247123718, "step": 249 }, { "epoch": 0.8488964346349746, "grad_norm": 0.24445995261417658, "learning_rate": 9.62924114364655e-05, "loss": 0.2039603888988495, "step": 250 }, { "epoch": 0.8522920203735145, "grad_norm": 0.18825574564380065, "learning_rate": 9.62363147162098e-05, "loss": 0.22734412550926208, "step": 251 }, { "epoch": 0.8556876061120543, "grad_norm": 0.20359693207539428, "learning_rate": 9.617981338875448e-05, "loss": 0.2254883348941803, "step": 252 }, { "epoch": 0.8590831918505942, "grad_norm": 0.20018525581388188, "learning_rate": 9.612290794853439e-05, "loss": 0.22558364272117615, "step": 253 }, { "epoch": 0.8624787775891342, "grad_norm": 0.2070394411176296, "learning_rate": 9.606559889352064e-05, "loss": 0.2222035974264145, "step": 254 }, { "epoch": 0.865874363327674, "grad_norm": 0.1926682449390986, "learning_rate": 9.60078867252164e-05, "loss": 0.216760516166687, "step": 255 }, { "epoch": 0.8692699490662139, "grad_norm": 0.2119152499241412, "learning_rate": 9.594977194865234e-05, "loss": 0.21268808841705322, "step": 256 }, { "epoch": 0.8726655348047538, "grad_norm": 0.20813259795966235, "learning_rate": 9.589125507238233e-05, "loss": 0.2067847102880478, "step": 257 }, { "epoch": 0.8760611205432938, "grad_norm": 0.20960018316381446, "learning_rate": 9.583233660847899e-05, "loss": 0.19506299495697021, "step": 258 }, { "epoch": 0.8794567062818336, "grad_norm": 0.22283816295134193, "learning_rate": 9.577301707252912e-05, "loss": 0.2254624366760254, "step": 259 }, { "epoch": 0.8828522920203735, "grad_norm": 0.19030418187601122, "learning_rate": 9.57132969836293e-05, "loss": 0.2179679274559021, "step": 260 }, { "epoch": 0.8862478777589134, "grad_norm": 0.2306665344239981, "learning_rate": 9.565317686438123e-05, "loss": 0.23668955266475677, "step": 261 }, { "epoch": 0.8896434634974533, "grad_norm": 0.19470480390844075, "learning_rate": 9.559265724088723e-05, "loss": 0.22097456455230713, "step": 262 }, { "epoch": 0.8930390492359932, "grad_norm": 0.22699762789235672, "learning_rate": 9.553173864274567e-05, "loss": 0.2137799859046936, "step": 263 }, { "epoch": 0.8964346349745331, "grad_norm": 0.22558850064428704, "learning_rate": 9.547042160304624e-05, "loss": 0.21889595687389374, "step": 264 }, { "epoch": 0.8998302207130731, "grad_norm": 0.20202887208827155, "learning_rate": 9.540870665836535e-05, "loss": 0.2062954157590866, "step": 265 }, { "epoch": 0.9032258064516129, "grad_norm": 0.2141450519315725, "learning_rate": 9.534659434876141e-05, "loss": 0.20279817283153534, "step": 266 }, { "epoch": 0.9066213921901528, "grad_norm": 0.20169527460472883, "learning_rate": 9.528408521777013e-05, "loss": 0.21280381083488464, "step": 267 }, { "epoch": 0.9100169779286927, "grad_norm": 0.18908346159953524, "learning_rate": 9.522117981239973e-05, "loss": 0.22928762435913086, "step": 268 }, { "epoch": 0.9134125636672326, "grad_norm": 0.19296272720615637, "learning_rate": 9.515787868312619e-05, "loss": 0.2128586769104004, "step": 269 }, { "epoch": 0.9168081494057725, "grad_norm": 0.19543659906177974, "learning_rate": 9.509418238388837e-05, "loss": 0.2105902135372162, "step": 270 }, { "epoch": 0.9202037351443124, "grad_norm": 0.19735398762951256, "learning_rate": 9.503009147208323e-05, "loss": 0.21366271376609802, "step": 271 }, { "epoch": 0.9235993208828522, "grad_norm": 0.21010560505655057, "learning_rate": 9.496560650856097e-05, "loss": 0.21506068110466003, "step": 272 }, { "epoch": 0.9269949066213922, "grad_norm": 0.20804828639770384, "learning_rate": 9.490072805761999e-05, "loss": 0.19642814993858337, "step": 273 }, { "epoch": 0.9303904923599321, "grad_norm": 0.21029089133014722, "learning_rate": 9.48354566870021e-05, "loss": 0.19250059127807617, "step": 274 }, { "epoch": 0.933786078098472, "grad_norm": 0.233997733498973, "learning_rate": 9.476979296788747e-05, "loss": 0.20365141332149506, "step": 275 }, { "epoch": 0.9371816638370118, "grad_norm": 0.19848982957894967, "learning_rate": 9.470373747488966e-05, "loss": 0.23507770895957947, "step": 276 }, { "epoch": 0.9405772495755518, "grad_norm": 0.1878507849164848, "learning_rate": 9.463729078605062e-05, "loss": 0.22653673589229584, "step": 277 }, { "epoch": 0.9439728353140917, "grad_norm": 0.19745484473369598, "learning_rate": 9.457045348283552e-05, "loss": 0.21832823753356934, "step": 278 }, { "epoch": 0.9473684210526315, "grad_norm": 0.20802645909023584, "learning_rate": 9.450322615012783e-05, "loss": 0.22689786553382874, "step": 279 }, { "epoch": 0.9507640067911715, "grad_norm": 0.2134997177113887, "learning_rate": 9.443560937622403e-05, "loss": 0.21119575202465057, "step": 280 }, { "epoch": 0.9541595925297114, "grad_norm": 0.19610375205437489, "learning_rate": 9.436760375282859e-05, "loss": 0.21295826137065887, "step": 281 }, { "epoch": 0.9575551782682513, "grad_norm": 0.21456350032490723, "learning_rate": 9.429920987504872e-05, "loss": 0.20517000555992126, "step": 282 }, { "epoch": 0.9609507640067911, "grad_norm": 0.20630036402869703, "learning_rate": 9.423042834138924e-05, "loss": 0.20758795738220215, "step": 283 }, { "epoch": 0.9643463497453311, "grad_norm": 0.20979349860791624, "learning_rate": 9.41612597537472e-05, "loss": 0.22162894904613495, "step": 284 }, { "epoch": 0.967741935483871, "grad_norm": 0.20546372138254324, "learning_rate": 9.40917047174068e-05, "loss": 0.22531533241271973, "step": 285 }, { "epoch": 0.9711375212224108, "grad_norm": 0.19653962990322366, "learning_rate": 9.402176384103391e-05, "loss": 0.2250673472881317, "step": 286 }, { "epoch": 0.9745331069609507, "grad_norm": 0.2151739895018823, "learning_rate": 9.395143773667088e-05, "loss": 0.21567688882350922, "step": 287 }, { "epoch": 0.9779286926994907, "grad_norm": 0.2125409951241907, "learning_rate": 9.388072701973112e-05, "loss": 0.216848224401474, "step": 288 }, { "epoch": 0.9813242784380306, "grad_norm": 0.21311751168682996, "learning_rate": 9.380963230899371e-05, "loss": 0.20292401313781738, "step": 289 }, { "epoch": 0.9847198641765704, "grad_norm": 0.22571524617051825, "learning_rate": 9.373815422659806e-05, "loss": 0.20285692811012268, "step": 290 }, { "epoch": 0.9881154499151104, "grad_norm": 0.24024713105394988, "learning_rate": 9.366629339803836e-05, "loss": 0.20322749018669128, "step": 291 }, { "epoch": 0.9915110356536503, "grad_norm": 0.23484274138937952, "learning_rate": 9.359405045215816e-05, "loss": 0.22512313723564148, "step": 292 }, { "epoch": 0.9949066213921901, "grad_norm": 0.2153629198226449, "learning_rate": 9.352142602114486e-05, "loss": 0.21850597858428955, "step": 293 }, { "epoch": 0.99830220713073, "grad_norm": 0.2118017834223803, "learning_rate": 9.34484207405242e-05, "loss": 0.2138933390378952, "step": 294 }, { "epoch": 1.0, "grad_norm": 0.2640803471374308, "learning_rate": 9.337503524915468e-05, "loss": 0.18181435763835907, "step": 295 }, { "epoch": 1.00339558573854, "grad_norm": 0.25185748187505225, "learning_rate": 9.330127018922194e-05, "loss": 0.1851600855588913, "step": 296 }, { "epoch": 1.0067911714770799, "grad_norm": 0.22807673150101548, "learning_rate": 9.322712620623319e-05, "loss": 0.18672308325767517, "step": 297 }, { "epoch": 1.0101867572156198, "grad_norm": 0.2422789280030024, "learning_rate": 9.315260394901153e-05, "loss": 0.18454226851463318, "step": 298 }, { "epoch": 1.0135823429541595, "grad_norm": 0.26332508687278017, "learning_rate": 9.30777040696903e-05, "loss": 0.17138835787773132, "step": 299 }, { "epoch": 1.0169779286926994, "grad_norm": 0.2322925347702751, "learning_rate": 9.300242722370735e-05, "loss": 0.1583154946565628, "step": 300 }, { "epoch": 1.0203735144312394, "grad_norm": 0.35737795220809254, "learning_rate": 9.292677406979929e-05, "loss": 0.15624071657657623, "step": 301 }, { "epoch": 1.0237691001697793, "grad_norm": 0.22348189270021476, "learning_rate": 9.285074526999576e-05, "loss": 0.13611823320388794, "step": 302 }, { "epoch": 1.0271646859083192, "grad_norm": 0.2538363311882537, "learning_rate": 9.277434148961364e-05, "loss": 0.13991695642471313, "step": 303 }, { "epoch": 1.0305602716468591, "grad_norm": 0.29397910849161274, "learning_rate": 9.269756339725116e-05, "loss": 0.17404183745384216, "step": 304 }, { "epoch": 1.033955857385399, "grad_norm": 0.21478761409242073, "learning_rate": 9.262041166478214e-05, "loss": 0.16527508199214935, "step": 305 }, { "epoch": 1.0373514431239388, "grad_norm": 0.24575559952429935, "learning_rate": 9.254288696735007e-05, "loss": 0.18379661440849304, "step": 306 }, { "epoch": 1.0407470288624787, "grad_norm": 0.18258323676435237, "learning_rate": 9.246498998336219e-05, "loss": 0.15959210693836212, "step": 307 }, { "epoch": 1.0441426146010186, "grad_norm": 0.20762723984663936, "learning_rate": 9.238672139448354e-05, "loss": 0.15240654349327087, "step": 308 }, { "epoch": 1.0475382003395586, "grad_norm": 0.19759931016356572, "learning_rate": 9.230808188563109e-05, "loss": 0.13937662541866302, "step": 309 }, { "epoch": 1.0509337860780985, "grad_norm": 0.21569604521763863, "learning_rate": 9.222907214496763e-05, "loss": 0.13814765214920044, "step": 310 }, { "epoch": 1.0543293718166384, "grad_norm": 0.21450171105419943, "learning_rate": 9.214969286389576e-05, "loss": 0.14654430747032166, "step": 311 }, { "epoch": 1.0577249575551784, "grad_norm": 0.2446011172118402, "learning_rate": 9.206994473705192e-05, "loss": 0.15606018900871277, "step": 312 }, { "epoch": 1.061120543293718, "grad_norm": 0.2129864282769988, "learning_rate": 9.198982846230028e-05, "loss": 0.183872789144516, "step": 313 }, { "epoch": 1.064516129032258, "grad_norm": 0.19873284728743354, "learning_rate": 9.190934474072658e-05, "loss": 0.1806487739086151, "step": 314 }, { "epoch": 1.067911714770798, "grad_norm": 0.2147058439591677, "learning_rate": 9.182849427663205e-05, "loss": 0.15780793130397797, "step": 315 }, { "epoch": 1.0713073005093379, "grad_norm": 0.22641077528539544, "learning_rate": 9.174727777752723e-05, "loss": 0.16906075179576874, "step": 316 }, { "epoch": 1.0747028862478778, "grad_norm": 0.19734471555148236, "learning_rate": 9.166569595412575e-05, "loss": 0.15225952863693237, "step": 317 }, { "epoch": 1.0780984719864177, "grad_norm": 0.21982865458583253, "learning_rate": 9.158374952033819e-05, "loss": 0.14668048918247223, "step": 318 }, { "epoch": 1.0814940577249577, "grad_norm": 0.19967704904501443, "learning_rate": 9.150143919326577e-05, "loss": 0.13530755043029785, "step": 319 }, { "epoch": 1.0848896434634974, "grad_norm": 0.24918052830076368, "learning_rate": 9.141876569319404e-05, "loss": 0.1417677104473114, "step": 320 }, { "epoch": 1.0882852292020373, "grad_norm": 0.28674260848789684, "learning_rate": 9.133572974358669e-05, "loss": 0.20028278231620789, "step": 321 }, { "epoch": 1.0916808149405772, "grad_norm": 0.19725409451876047, "learning_rate": 9.125233207107909e-05, "loss": 0.17321616411209106, "step": 322 }, { "epoch": 1.0950764006791172, "grad_norm": 0.20296365848255718, "learning_rate": 9.116857340547202e-05, "loss": 0.1749824732542038, "step": 323 }, { "epoch": 1.098471986417657, "grad_norm": 0.22358537574706383, "learning_rate": 9.108445447972531e-05, "loss": 0.16174906492233276, "step": 324 }, { "epoch": 1.101867572156197, "grad_norm": 0.19238319764264408, "learning_rate": 9.099997602995128e-05, "loss": 0.14620691537857056, "step": 325 }, { "epoch": 1.1052631578947367, "grad_norm": 0.19718755335162985, "learning_rate": 9.091513879540845e-05, "loss": 0.1450907438993454, "step": 326 }, { "epoch": 1.1086587436332767, "grad_norm": 0.19673360612483923, "learning_rate": 9.0829943518495e-05, "loss": 0.14425364136695862, "step": 327 }, { "epoch": 1.1120543293718166, "grad_norm": 0.21339195568858857, "learning_rate": 9.07443909447423e-05, "loss": 0.14606226980686188, "step": 328 }, { "epoch": 1.1154499151103565, "grad_norm": 0.2365661486570052, "learning_rate": 9.065848182280833e-05, "loss": 0.17659983038902283, "step": 329 }, { "epoch": 1.1188455008488964, "grad_norm": 0.21972513329501014, "learning_rate": 9.057221690447124e-05, "loss": 0.1936458945274353, "step": 330 }, { "epoch": 1.1222410865874364, "grad_norm": 0.20694250272988488, "learning_rate": 9.048559694462262e-05, "loss": 0.17152224481105804, "step": 331 }, { "epoch": 1.1256366723259763, "grad_norm": 0.1919226051913001, "learning_rate": 9.039862270126102e-05, "loss": 0.1675736904144287, "step": 332 }, { "epoch": 1.129032258064516, "grad_norm": 0.20156533292402448, "learning_rate": 9.03112949354853e-05, "loss": 0.15972010791301727, "step": 333 }, { "epoch": 1.132427843803056, "grad_norm": 0.19565997493707263, "learning_rate": 9.02236144114879e-05, "loss": 0.15504707396030426, "step": 334 }, { "epoch": 1.1358234295415959, "grad_norm": 0.18792651722571585, "learning_rate": 9.013558189654819e-05, "loss": 0.154513418674469, "step": 335 }, { "epoch": 1.1392190152801358, "grad_norm": 0.18510422308711297, "learning_rate": 9.00471981610258e-05, "loss": 0.12966126203536987, "step": 336 }, { "epoch": 1.1426146010186757, "grad_norm": 0.21919664118972512, "learning_rate": 8.99584639783538e-05, "loss": 0.1651276797056198, "step": 337 }, { "epoch": 1.1460101867572157, "grad_norm": 0.20519434965554997, "learning_rate": 8.986938012503203e-05, "loss": 0.19479787349700928, "step": 338 }, { "epoch": 1.1494057724957556, "grad_norm": 0.28981547364179405, "learning_rate": 8.977994738062017e-05, "loss": 0.18329326808452606, "step": 339 }, { "epoch": 1.1528013582342953, "grad_norm": 0.1876303845879503, "learning_rate": 8.969016652773103e-05, "loss": 0.16198518872261047, "step": 340 }, { "epoch": 1.1561969439728352, "grad_norm": 0.22252671970985857, "learning_rate": 8.96000383520237e-05, "loss": 0.15827342867851257, "step": 341 }, { "epoch": 1.1595925297113752, "grad_norm": 0.18171771457498812, "learning_rate": 8.950956364219658e-05, "loss": 0.15472659468650818, "step": 342 }, { "epoch": 1.162988115449915, "grad_norm": 0.19712583320336807, "learning_rate": 8.941874318998058e-05, "loss": 0.15253013372421265, "step": 343 }, { "epoch": 1.166383701188455, "grad_norm": 0.19418415353529328, "learning_rate": 8.932757779013214e-05, "loss": 0.13947896659374237, "step": 344 }, { "epoch": 1.169779286926995, "grad_norm": 0.20528043237757057, "learning_rate": 8.923606824042627e-05, "loss": 0.14546489715576172, "step": 345 }, { "epoch": 1.1731748726655349, "grad_norm": 0.2045938861257335, "learning_rate": 8.914421534164962e-05, "loss": 0.18610088527202606, "step": 346 }, { "epoch": 1.1765704584040746, "grad_norm": 0.18737188707257443, "learning_rate": 8.905201989759341e-05, "loss": 0.17247223854064941, "step": 347 }, { "epoch": 1.1799660441426145, "grad_norm": 0.19405907279115056, "learning_rate": 8.895948271504642e-05, "loss": 0.1683935821056366, "step": 348 }, { "epoch": 1.1833616298811545, "grad_norm": 0.19229670375176755, "learning_rate": 8.886660460378797e-05, "loss": 0.16638962924480438, "step": 349 }, { "epoch": 1.1867572156196944, "grad_norm": 0.1991680009117587, "learning_rate": 8.877338637658075e-05, "loss": 0.16609981656074524, "step": 350 }, { "epoch": 1.1901528013582343, "grad_norm": 0.18908550921574963, "learning_rate": 8.867982884916376e-05, "loss": 0.1538071483373642, "step": 351 }, { "epoch": 1.1935483870967742, "grad_norm": 0.20137740843008223, "learning_rate": 8.858593284024523e-05, "loss": 0.14784181118011475, "step": 352 }, { "epoch": 1.1969439728353142, "grad_norm": 0.18829044174988624, "learning_rate": 8.849169917149531e-05, "loss": 0.14251796901226044, "step": 353 }, { "epoch": 1.2003395585738539, "grad_norm": 0.19294472815962704, "learning_rate": 8.839712866753901e-05, "loss": 0.17827999591827393, "step": 354 }, { "epoch": 1.2037351443123938, "grad_norm": 0.1843830736469339, "learning_rate": 8.83022221559489e-05, "loss": 0.17037731409072876, "step": 355 }, { "epoch": 1.2071307300509337, "grad_norm": 0.18731547810327823, "learning_rate": 8.820698046723796e-05, "loss": 0.17300304770469666, "step": 356 }, { "epoch": 1.2105263157894737, "grad_norm": 0.18243400363719428, "learning_rate": 8.811140443485217e-05, "loss": 0.1666610836982727, "step": 357 }, { "epoch": 1.2139219015280136, "grad_norm": 0.19598065797414813, "learning_rate": 8.801549489516341e-05, "loss": 0.1571384072303772, "step": 358 }, { "epoch": 1.2173174872665535, "grad_norm": 0.2062065547622085, "learning_rate": 8.791925268746193e-05, "loss": 0.1500397026538849, "step": 359 }, { "epoch": 1.2207130730050935, "grad_norm": 0.18688810221381993, "learning_rate": 8.782267865394917e-05, "loss": 0.14770814776420593, "step": 360 }, { "epoch": 1.2241086587436332, "grad_norm": 0.21052759084419384, "learning_rate": 8.772577363973033e-05, "loss": 0.1332262009382248, "step": 361 }, { "epoch": 1.227504244482173, "grad_norm": 0.18798624390228022, "learning_rate": 8.762853849280693e-05, "loss": 0.16259124875068665, "step": 362 }, { "epoch": 1.230899830220713, "grad_norm": 0.19049570530951052, "learning_rate": 8.753097406406949e-05, "loss": 0.20332232117652893, "step": 363 }, { "epoch": 1.234295415959253, "grad_norm": 0.1898301956007736, "learning_rate": 8.743308120728997e-05, "loss": 0.1683693379163742, "step": 364 }, { "epoch": 1.237691001697793, "grad_norm": 0.1933106864506251, "learning_rate": 8.73348607791144e-05, "loss": 0.16142725944519043, "step": 365 }, { "epoch": 1.2410865874363328, "grad_norm": 0.19455212860155482, "learning_rate": 8.723631363905531e-05, "loss": 0.17131207883358002, "step": 366 }, { "epoch": 1.2444821731748728, "grad_norm": 0.1903346964025916, "learning_rate": 8.713744064948426e-05, "loss": 0.16571295261383057, "step": 367 }, { "epoch": 1.2478777589134125, "grad_norm": 0.18455925075680774, "learning_rate": 8.703824267562425e-05, "loss": 0.13864544034004211, "step": 368 }, { "epoch": 1.2512733446519524, "grad_norm": 0.2025745774162742, "learning_rate": 8.69387205855422e-05, "loss": 0.13644319772720337, "step": 369 }, { "epoch": 1.2546689303904923, "grad_norm": 0.20399839595419467, "learning_rate": 8.683887525014127e-05, "loss": 0.13614535331726074, "step": 370 }, { "epoch": 1.2580645161290323, "grad_norm": 0.17809016303033243, "learning_rate": 8.673870754315336e-05, "loss": 0.16958439350128174, "step": 371 }, { "epoch": 1.2614601018675722, "grad_norm": 0.1945140385421116, "learning_rate": 8.663821834113135e-05, "loss": 0.17489628493785858, "step": 372 }, { "epoch": 1.2648556876061121, "grad_norm": 0.18342916195379932, "learning_rate": 8.65374085234415e-05, "loss": 0.1839398443698883, "step": 373 }, { "epoch": 1.268251273344652, "grad_norm": 0.21577925439128803, "learning_rate": 8.643627897225571e-05, "loss": 0.16957050561904907, "step": 374 }, { "epoch": 1.2716468590831917, "grad_norm": 0.19131866026857075, "learning_rate": 8.633483057254381e-05, "loss": 0.17125824093818665, "step": 375 }, { "epoch": 1.2750424448217317, "grad_norm": 0.21209659202385306, "learning_rate": 8.623306421206587e-05, "loss": 0.1478113979101181, "step": 376 }, { "epoch": 1.2784380305602716, "grad_norm": 0.1843344626573403, "learning_rate": 8.613098078136437e-05, "loss": 0.1380268931388855, "step": 377 }, { "epoch": 1.2818336162988115, "grad_norm": 0.21663206570272056, "learning_rate": 8.60285811737564e-05, "loss": 0.13468974828720093, "step": 378 }, { "epoch": 1.2852292020373515, "grad_norm": 0.25700924596840535, "learning_rate": 8.592586628532588e-05, "loss": 0.18746554851531982, "step": 379 }, { "epoch": 1.2886247877758914, "grad_norm": 0.19113690975452302, "learning_rate": 8.582283701491576e-05, "loss": 0.1825951337814331, "step": 380 }, { "epoch": 1.2920203735144313, "grad_norm": 0.21089089388163626, "learning_rate": 8.571949426412001e-05, "loss": 0.17960380017757416, "step": 381 }, { "epoch": 1.295415959252971, "grad_norm": 0.21445062437348633, "learning_rate": 8.561583893727588e-05, "loss": 0.17787647247314453, "step": 382 }, { "epoch": 1.298811544991511, "grad_norm": 0.20207057789395122, "learning_rate": 8.551187194145592e-05, "loss": 0.1642351895570755, "step": 383 }, { "epoch": 1.302207130730051, "grad_norm": 0.2001663052369365, "learning_rate": 8.540759418646002e-05, "loss": 0.16133837401866913, "step": 384 }, { "epoch": 1.3056027164685908, "grad_norm": 0.20190468770665623, "learning_rate": 8.530300658480752e-05, "loss": 0.1445751190185547, "step": 385 }, { "epoch": 1.3089983022071308, "grad_norm": 0.1992915593466866, "learning_rate": 8.519811005172916e-05, "loss": 0.14575952291488647, "step": 386 }, { "epoch": 1.3123938879456707, "grad_norm": 0.20245830395467582, "learning_rate": 8.509290550515907e-05, "loss": 0.155848890542984, "step": 387 }, { "epoch": 1.3157894736842106, "grad_norm": 0.2089937786489004, "learning_rate": 8.498739386572682e-05, "loss": 0.18617866933345795, "step": 388 }, { "epoch": 1.3191850594227503, "grad_norm": 0.18603772825641204, "learning_rate": 8.488157605674925e-05, "loss": 0.16678261756896973, "step": 389 }, { "epoch": 1.3225806451612903, "grad_norm": 0.19436507423672644, "learning_rate": 8.477545300422246e-05, "loss": 0.16283991932868958, "step": 390 }, { "epoch": 1.3259762308998302, "grad_norm": 0.19955648451002617, "learning_rate": 8.466902563681372e-05, "loss": 0.15280015766620636, "step": 391 }, { "epoch": 1.3293718166383701, "grad_norm": 0.17667837888541935, "learning_rate": 8.456229488585328e-05, "loss": 0.15636740624904633, "step": 392 }, { "epoch": 1.33276740237691, "grad_norm": 0.18989141133889384, "learning_rate": 8.445526168532627e-05, "loss": 0.15585076808929443, "step": 393 }, { "epoch": 1.33616298811545, "grad_norm": 0.17823304787765548, "learning_rate": 8.434792697186449e-05, "loss": 0.13305488228797913, "step": 394 }, { "epoch": 1.33955857385399, "grad_norm": 0.2074413931510075, "learning_rate": 8.424029168473829e-05, "loss": 0.14287126064300537, "step": 395 }, { "epoch": 1.3429541595925296, "grad_norm": 0.2147487156284575, "learning_rate": 8.413235676584823e-05, "loss": 0.18366865813732147, "step": 396 }, { "epoch": 1.3463497453310695, "grad_norm": 0.188118351487934, "learning_rate": 8.402412315971693e-05, "loss": 0.18109475076198578, "step": 397 }, { "epoch": 1.3497453310696095, "grad_norm": 0.18226493466189397, "learning_rate": 8.391559181348082e-05, "loss": 0.15926748514175415, "step": 398 }, { "epoch": 1.3531409168081494, "grad_norm": 0.18846482336790968, "learning_rate": 8.380676367688172e-05, "loss": 0.1652354598045349, "step": 399 }, { "epoch": 1.3565365025466893, "grad_norm": 0.19321529515546765, "learning_rate": 8.36976397022587e-05, "loss": 0.14958378672599792, "step": 400 }, { "epoch": 1.3599320882852293, "grad_norm": 0.18742157750238927, "learning_rate": 8.358822084453965e-05, "loss": 0.14632749557495117, "step": 401 }, { "epoch": 1.3633276740237692, "grad_norm": 0.2043432669400869, "learning_rate": 8.347850806123288e-05, "loss": 0.14200440049171448, "step": 402 }, { "epoch": 1.366723259762309, "grad_norm": 4.721626403913089, "learning_rate": 8.336850231241888e-05, "loss": 0.1594700962305069, "step": 403 }, { "epoch": 1.3701188455008488, "grad_norm": 0.22735122500220956, "learning_rate": 8.325820456074181e-05, "loss": 0.1689343899488449, "step": 404 }, { "epoch": 1.3735144312393888, "grad_norm": 0.19881102119288344, "learning_rate": 8.314761577140105e-05, "loss": 0.18526801466941833, "step": 405 }, { "epoch": 1.3769100169779287, "grad_norm": 0.1919098416418268, "learning_rate": 8.303673691214289e-05, "loss": 0.1694057583808899, "step": 406 }, { "epoch": 1.3803056027164686, "grad_norm": 0.17672507119936312, "learning_rate": 8.292556895325194e-05, "loss": 0.15680214762687683, "step": 407 }, { "epoch": 1.3837011884550086, "grad_norm": 0.18816895218350527, "learning_rate": 8.281411286754266e-05, "loss": 0.15174201130867004, "step": 408 }, { "epoch": 1.3870967741935485, "grad_norm": 0.19240519789423516, "learning_rate": 8.270236963035091e-05, "loss": 0.1456459015607834, "step": 409 }, { "epoch": 1.3904923599320882, "grad_norm": 0.18713812474392583, "learning_rate": 8.259034021952537e-05, "loss": 0.14336155354976654, "step": 410 }, { "epoch": 1.3938879456706281, "grad_norm": 0.18649265597192938, "learning_rate": 8.24780256154189e-05, "loss": 0.13790106773376465, "step": 411 }, { "epoch": 1.397283531409168, "grad_norm": 0.1926368758147828, "learning_rate": 8.236542680088015e-05, "loss": 0.16365712881088257, "step": 412 }, { "epoch": 1.400679117147708, "grad_norm": 0.2052385199809466, "learning_rate": 8.225254476124478e-05, "loss": 0.18444347381591797, "step": 413 }, { "epoch": 1.404074702886248, "grad_norm": 0.17735224796271037, "learning_rate": 8.213938048432697e-05, "loss": 0.17133484780788422, "step": 414 }, { "epoch": 1.4074702886247878, "grad_norm": 0.17703525242711624, "learning_rate": 8.202593496041066e-05, "loss": 0.16077420115470886, "step": 415 }, { "epoch": 1.4108658743633278, "grad_norm": 0.2078093652294213, "learning_rate": 8.191220918224101e-05, "loss": 0.16223178803920746, "step": 416 }, { "epoch": 1.4142614601018675, "grad_norm": 0.1867882421757925, "learning_rate": 8.179820414501555e-05, "loss": 0.1703399419784546, "step": 417 }, { "epoch": 1.4176570458404074, "grad_norm": 0.20290174690791027, "learning_rate": 8.168392084637566e-05, "loss": 0.15619607269763947, "step": 418 }, { "epoch": 1.4210526315789473, "grad_norm": 0.19113902554097073, "learning_rate": 8.156936028639767e-05, "loss": 0.14540717005729675, "step": 419 }, { "epoch": 1.4244482173174873, "grad_norm": 0.1952551209685112, "learning_rate": 8.145452346758426e-05, "loss": 0.13033799827098846, "step": 420 }, { "epoch": 1.4278438030560272, "grad_norm": 0.19371119320343652, "learning_rate": 8.133941139485551e-05, "loss": 0.18612802028656006, "step": 421 }, { "epoch": 1.4312393887945671, "grad_norm": 0.17891380794350153, "learning_rate": 8.12240250755403e-05, "loss": 0.16519853472709656, "step": 422 }, { "epoch": 1.434634974533107, "grad_norm": 0.21169284605337452, "learning_rate": 8.110836551936736e-05, "loss": 0.17394272983074188, "step": 423 }, { "epoch": 1.4380305602716468, "grad_norm": 0.1972142566856927, "learning_rate": 8.099243373845646e-05, "loss": 0.1689443290233612, "step": 424 }, { "epoch": 1.4414261460101867, "grad_norm": 0.1930089237942756, "learning_rate": 8.08762307473096e-05, "loss": 0.15118227899074554, "step": 425 }, { "epoch": 1.4448217317487266, "grad_norm": 0.19410209750733526, "learning_rate": 8.07597575628021e-05, "loss": 0.14372073113918304, "step": 426 }, { "epoch": 1.4482173174872666, "grad_norm": 0.2068154614834785, "learning_rate": 8.064301520417367e-05, "loss": 0.14268404245376587, "step": 427 }, { "epoch": 1.4516129032258065, "grad_norm": 0.20659605844650367, "learning_rate": 8.052600469301958e-05, "loss": 0.149183988571167, "step": 428 }, { "epoch": 1.4550084889643464, "grad_norm": 0.15996773871355222, "learning_rate": 8.04087270532816e-05, "loss": 0.15605027973651886, "step": 429 }, { "epoch": 1.4584040747028864, "grad_norm": 0.19352422399375568, "learning_rate": 8.029118331123912e-05, "loss": 0.19962410628795624, "step": 430 }, { "epoch": 1.461799660441426, "grad_norm": 0.18094791214544692, "learning_rate": 8.01733744955002e-05, "loss": 0.1650353968143463, "step": 431 }, { "epoch": 1.465195246179966, "grad_norm": 0.18133320070320472, "learning_rate": 8.005530163699246e-05, "loss": 0.1731692999601364, "step": 432 }, { "epoch": 1.468590831918506, "grad_norm": 0.1917423804343093, "learning_rate": 7.993696576895415e-05, "loss": 0.1664673388004303, "step": 433 }, { "epoch": 1.4719864176570459, "grad_norm": 0.18805498724745764, "learning_rate": 7.981836792692508e-05, "loss": 0.14910025894641876, "step": 434 }, { "epoch": 1.4753820033955858, "grad_norm": 0.18419843776963923, "learning_rate": 7.969950914873753e-05, "loss": 0.13263513147830963, "step": 435 }, { "epoch": 1.4787775891341257, "grad_norm": 0.17807308591242718, "learning_rate": 7.958039047450723e-05, "loss": 0.1370704472064972, "step": 436 }, { "epoch": 1.4821731748726656, "grad_norm": 0.22794254202013806, "learning_rate": 7.946101294662418e-05, "loss": 0.1693044900894165, "step": 437 }, { "epoch": 1.4855687606112054, "grad_norm": 0.17830746170605824, "learning_rate": 7.934137760974363e-05, "loss": 0.19466224312782288, "step": 438 }, { "epoch": 1.4889643463497453, "grad_norm": 0.1737977528931366, "learning_rate": 7.922148551077681e-05, "loss": 0.17629188299179077, "step": 439 }, { "epoch": 1.4923599320882852, "grad_norm": 0.19806493328522146, "learning_rate": 7.910133769888188e-05, "loss": 0.17819415032863617, "step": 440 }, { "epoch": 1.4957555178268251, "grad_norm": 0.19253394552611486, "learning_rate": 7.898093522545472e-05, "loss": 0.16357217729091644, "step": 441 }, { "epoch": 1.499151103565365, "grad_norm": 0.18191936790505997, "learning_rate": 7.886027914411964e-05, "loss": 0.1531246304512024, "step": 442 }, { "epoch": 1.5025466893039048, "grad_norm": 0.1877792452878943, "learning_rate": 7.873937051072035e-05, "loss": 0.1648198515176773, "step": 443 }, { "epoch": 1.505942275042445, "grad_norm": 0.1774072306561311, "learning_rate": 7.86182103833105e-05, "loss": 0.12958091497421265, "step": 444 }, { "epoch": 1.5093378607809846, "grad_norm": 0.22147789671424525, "learning_rate": 7.849679982214458e-05, "loss": 0.13968268036842346, "step": 445 }, { "epoch": 1.5127334465195246, "grad_norm": 0.19669409577746466, "learning_rate": 7.83751398896686e-05, "loss": 0.1833503693342209, "step": 446 }, { "epoch": 1.5161290322580645, "grad_norm": 0.20162298827821934, "learning_rate": 7.825323165051073e-05, "loss": 0.17941348254680634, "step": 447 }, { "epoch": 1.5195246179966044, "grad_norm": 0.18467661049000877, "learning_rate": 7.813107617147209e-05, "loss": 0.17293405532836914, "step": 448 }, { "epoch": 1.5229202037351444, "grad_norm": 0.18075781935552415, "learning_rate": 7.80086745215173e-05, "loss": 0.1632663607597351, "step": 449 }, { "epoch": 1.526315789473684, "grad_norm": 0.1826236005300576, "learning_rate": 7.788602777176528e-05, "loss": 0.15698912739753723, "step": 450 }, { "epoch": 1.5297113752122242, "grad_norm": 0.17888968595670016, "learning_rate": 7.77631369954797e-05, "loss": 0.15062135457992554, "step": 451 }, { "epoch": 1.533106960950764, "grad_norm": 0.2164448123864814, "learning_rate": 7.764000326805967e-05, "loss": 0.152237206697464, "step": 452 }, { "epoch": 1.5365025466893039, "grad_norm": 0.19444820284692502, "learning_rate": 7.751662766703038e-05, "loss": 0.13075107336044312, "step": 453 }, { "epoch": 1.5398981324278438, "grad_norm": 0.1958023033404599, "learning_rate": 7.73930112720336e-05, "loss": 0.17272233963012695, "step": 454 }, { "epoch": 1.5432937181663837, "grad_norm": 0.2441624770197687, "learning_rate": 7.726915516481824e-05, "loss": 0.19559632241725922, "step": 455 }, { "epoch": 1.5466893039049237, "grad_norm": 0.19861978237733888, "learning_rate": 7.714506042923091e-05, "loss": 0.17393885552883148, "step": 456 }, { "epoch": 1.5500848896434634, "grad_norm": 0.19128309043157554, "learning_rate": 7.702072815120638e-05, "loss": 0.16424834728240967, "step": 457 }, { "epoch": 1.5534804753820035, "grad_norm": 0.1864400540211699, "learning_rate": 7.68961594187582e-05, "loss": 0.14206860959529877, "step": 458 }, { "epoch": 1.5568760611205432, "grad_norm": 0.19035858841543496, "learning_rate": 7.677135532196905e-05, "loss": 0.15697211027145386, "step": 459 }, { "epoch": 1.5602716468590832, "grad_norm": 0.17746401560053554, "learning_rate": 7.66463169529812e-05, "loss": 0.13984709978103638, "step": 460 }, { "epoch": 1.563667232597623, "grad_norm": 0.2050052123846212, "learning_rate": 7.652104540598712e-05, "loss": 0.14157693088054657, "step": 461 }, { "epoch": 1.567062818336163, "grad_norm": 0.19553382600126865, "learning_rate": 7.63955417772197e-05, "loss": 0.17652365565299988, "step": 462 }, { "epoch": 1.570458404074703, "grad_norm": 0.2084379967098743, "learning_rate": 7.626980716494274e-05, "loss": 0.18209630250930786, "step": 463 }, { "epoch": 1.5738539898132426, "grad_norm": 0.17868685044890462, "learning_rate": 7.614384266944139e-05, "loss": 0.18163995444774628, "step": 464 }, { "epoch": 1.5772495755517828, "grad_norm": 0.20534574800623406, "learning_rate": 7.601764939301241e-05, "loss": 0.1824880838394165, "step": 465 }, { "epoch": 1.5806451612903225, "grad_norm": 0.19478791048936644, "learning_rate": 7.589122843995469e-05, "loss": 0.15758319199085236, "step": 466 }, { "epoch": 1.5840407470288624, "grad_norm": 0.194802482311561, "learning_rate": 7.57645809165594e-05, "loss": 0.15543323755264282, "step": 467 }, { "epoch": 1.5874363327674024, "grad_norm": 0.18899486292425605, "learning_rate": 7.563770793110039e-05, "loss": 0.14813093841075897, "step": 468 }, { "epoch": 1.5908319185059423, "grad_norm": 0.1931495304363674, "learning_rate": 7.551061059382455e-05, "loss": 0.14091037213802338, "step": 469 }, { "epoch": 1.5942275042444822, "grad_norm": 0.18937628052601205, "learning_rate": 7.5383290016942e-05, "loss": 0.14063414931297302, "step": 470 }, { "epoch": 1.597623089983022, "grad_norm": 0.18332375690160316, "learning_rate": 7.525574731461642e-05, "loss": 0.18169575929641724, "step": 471 }, { "epoch": 1.601018675721562, "grad_norm": 0.17996068260900072, "learning_rate": 7.512798360295526e-05, "loss": 0.17505013942718506, "step": 472 }, { "epoch": 1.6044142614601018, "grad_norm": 0.18200201421479933, "learning_rate": 7.500000000000001e-05, "loss": 0.16332568228244781, "step": 473 }, { "epoch": 1.6078098471986417, "grad_norm": 0.21987119286436815, "learning_rate": 7.487179762571637e-05, "loss": 0.16316084563732147, "step": 474 }, { "epoch": 1.6112054329371817, "grad_norm": 0.17951443567647385, "learning_rate": 7.474337760198447e-05, "loss": 0.15377068519592285, "step": 475 }, { "epoch": 1.6146010186757216, "grad_norm": 0.1864770847299537, "learning_rate": 7.461474105258911e-05, "loss": 0.14799565076828003, "step": 476 }, { "epoch": 1.6179966044142615, "grad_norm": 0.18893415419183548, "learning_rate": 7.448588910320983e-05, "loss": 0.14057007431983948, "step": 477 }, { "epoch": 1.6213921901528012, "grad_norm": 0.19540730152353614, "learning_rate": 7.435682288141111e-05, "loss": 0.13565665483474731, "step": 478 }, { "epoch": 1.6247877758913414, "grad_norm": 0.16693887796128457, "learning_rate": 7.422754351663252e-05, "loss": 0.16795119643211365, "step": 479 }, { "epoch": 1.628183361629881, "grad_norm": 0.18461359151636947, "learning_rate": 7.409805214017877e-05, "loss": 0.1741284728050232, "step": 480 }, { "epoch": 1.631578947368421, "grad_norm": 0.20658661619806634, "learning_rate": 7.396834988520988e-05, "loss": 0.1779479831457138, "step": 481 }, { "epoch": 1.634974533106961, "grad_norm": 0.18154303085081214, "learning_rate": 7.383843788673126e-05, "loss": 0.17302744090557098, "step": 482 }, { "epoch": 1.6383701188455009, "grad_norm": 0.20134720983448473, "learning_rate": 7.37083172815837e-05, "loss": 0.15802375972270966, "step": 483 }, { "epoch": 1.6417657045840408, "grad_norm": 0.16657433576710404, "learning_rate": 7.357798920843354e-05, "loss": 0.15232571959495544, "step": 484 }, { "epoch": 1.6451612903225805, "grad_norm": 0.1854420942608467, "learning_rate": 7.344745480776257e-05, "loss": 0.13740167021751404, "step": 485 }, { "epoch": 1.6485568760611207, "grad_norm": 0.1755281520120889, "learning_rate": 7.331671522185817e-05, "loss": 0.1252317577600479, "step": 486 }, { "epoch": 1.6519524617996604, "grad_norm": 0.19063720530120506, "learning_rate": 7.318577159480327e-05, "loss": 0.16169843077659607, "step": 487 }, { "epoch": 1.6553480475382003, "grad_norm": 0.19051401772486673, "learning_rate": 7.30546250724663e-05, "loss": 0.1779298633337021, "step": 488 }, { "epoch": 1.6587436332767402, "grad_norm": 0.1828449615245896, "learning_rate": 7.292327680249123e-05, "loss": 0.17332878708839417, "step": 489 }, { "epoch": 1.6621392190152802, "grad_norm": 0.17200441500610347, "learning_rate": 7.279172793428747e-05, "loss": 0.16480055451393127, "step": 490 }, { "epoch": 1.66553480475382, "grad_norm": 0.1808990782465556, "learning_rate": 7.265997961901987e-05, "loss": 0.17193584144115448, "step": 491 }, { "epoch": 1.6689303904923598, "grad_norm": 0.17785012165476946, "learning_rate": 7.252803300959855e-05, "loss": 0.15805591642856598, "step": 492 }, { "epoch": 1.6723259762309, "grad_norm": 0.1740718912760199, "learning_rate": 7.239588926066894e-05, "loss": 0.14565090835094452, "step": 493 }, { "epoch": 1.6757215619694397, "grad_norm": 0.18320587931576318, "learning_rate": 7.226354952860157e-05, "loss": 0.13669930398464203, "step": 494 }, { "epoch": 1.6791171477079796, "grad_norm": 0.19309638354608996, "learning_rate": 7.2131014971482e-05, "loss": 0.14412081241607666, "step": 495 }, { "epoch": 1.6825127334465195, "grad_norm": 0.17122190687907504, "learning_rate": 7.199828674910067e-05, "loss": 0.17972111701965332, "step": 496 }, { "epoch": 1.6859083191850595, "grad_norm": 0.17310059403804906, "learning_rate": 7.186536602294278e-05, "loss": 0.17095622420310974, "step": 497 }, { "epoch": 1.6893039049235994, "grad_norm": 0.17163850839414663, "learning_rate": 7.173225395617805e-05, "loss": 0.17176561057567596, "step": 498 }, { "epoch": 1.692699490662139, "grad_norm": 0.16742996938464463, "learning_rate": 7.159895171365065e-05, "loss": 0.16273561120033264, "step": 499 }, { "epoch": 1.6960950764006792, "grad_norm": 0.1736685707047817, "learning_rate": 7.146546046186893e-05, "loss": 0.16267995536327362, "step": 500 }, { "epoch": 1.699490662139219, "grad_norm": 0.1752796472062204, "learning_rate": 7.133178136899522e-05, "loss": 0.150325208902359, "step": 501 }, { "epoch": 1.7028862478777589, "grad_norm": 0.1739670295003433, "learning_rate": 7.119791560483562e-05, "loss": 0.13851594924926758, "step": 502 }, { "epoch": 1.7062818336162988, "grad_norm": 0.18208486411809036, "learning_rate": 7.106386434082979e-05, "loss": 0.13087987899780273, "step": 503 }, { "epoch": 1.7096774193548387, "grad_norm": 0.17085802121170188, "learning_rate": 7.092962875004065e-05, "loss": 0.16741487383842468, "step": 504 }, { "epoch": 1.7130730050933787, "grad_norm": 0.172294725303713, "learning_rate": 7.079521000714414e-05, "loss": 0.1753329038619995, "step": 505 }, { "epoch": 1.7164685908319184, "grad_norm": 0.17501598372751265, "learning_rate": 7.066060928841892e-05, "loss": 0.15479440987110138, "step": 506 }, { "epoch": 1.7198641765704585, "grad_norm": 0.2023357916275878, "learning_rate": 7.052582777173613e-05, "loss": 0.1699436604976654, "step": 507 }, { "epoch": 1.7232597623089982, "grad_norm": 0.18842955164086525, "learning_rate": 7.039086663654903e-05, "loss": 0.15886735916137695, "step": 508 }, { "epoch": 1.7266553480475382, "grad_norm": 0.1747792232007592, "learning_rate": 7.025572706388268e-05, "loss": 0.160150945186615, "step": 509 }, { "epoch": 1.730050933786078, "grad_norm": 0.18083168875464317, "learning_rate": 7.012041023632364e-05, "loss": 0.1468491405248642, "step": 510 }, { "epoch": 1.733446519524618, "grad_norm": 0.1769568276603756, "learning_rate": 6.99849173380096e-05, "loss": 0.1368895173072815, "step": 511 }, { "epoch": 1.736842105263158, "grad_norm": 0.17834955354483534, "learning_rate": 6.984924955461901e-05, "loss": 0.14566245675086975, "step": 512 }, { "epoch": 1.7402376910016977, "grad_norm": 0.1701069864841607, "learning_rate": 6.971340807336072e-05, "loss": 0.18279477953910828, "step": 513 }, { "epoch": 1.7436332767402378, "grad_norm": 0.1857363575452287, "learning_rate": 6.957739408296357e-05, "loss": 0.18226811289787292, "step": 514 }, { "epoch": 1.7470288624787775, "grad_norm": 0.17895461260792608, "learning_rate": 6.944120877366604e-05, "loss": 0.16566191613674164, "step": 515 }, { "epoch": 1.7504244482173175, "grad_norm": 0.1633025089552908, "learning_rate": 6.930485333720573e-05, "loss": 0.14856021106243134, "step": 516 }, { "epoch": 1.7538200339558574, "grad_norm": 0.18351050724632503, "learning_rate": 6.916832896680909e-05, "loss": 0.15349256992340088, "step": 517 }, { "epoch": 1.7572156196943973, "grad_norm": 0.16841003094995652, "learning_rate": 6.90316368571808e-05, "loss": 0.14154832065105438, "step": 518 }, { "epoch": 1.7606112054329373, "grad_norm": 0.1784619620318729, "learning_rate": 6.889477820449342e-05, "loss": 0.13962216675281525, "step": 519 }, { "epoch": 1.764006791171477, "grad_norm": 0.18429362438746846, "learning_rate": 6.875775420637696e-05, "loss": 0.14338617026805878, "step": 520 }, { "epoch": 1.7674023769100171, "grad_norm": 0.18557972878066073, "learning_rate": 6.86205660619083e-05, "loss": 0.17774900794029236, "step": 521 }, { "epoch": 1.7707979626485568, "grad_norm": 0.18100495904959274, "learning_rate": 6.848321497160073e-05, "loss": 0.18082043528556824, "step": 522 }, { "epoch": 1.7741935483870968, "grad_norm": 0.17735463170313362, "learning_rate": 6.834570213739346e-05, "loss": 0.16407832503318787, "step": 523 }, { "epoch": 1.7775891341256367, "grad_norm": 0.18741911239080628, "learning_rate": 6.820802876264112e-05, "loss": 0.16284362971782684, "step": 524 }, { "epoch": 1.7809847198641766, "grad_norm": 0.17936034481136062, "learning_rate": 6.807019605210319e-05, "loss": 0.16151063144207, "step": 525 }, { "epoch": 1.7843803056027165, "grad_norm": 0.17846022672007994, "learning_rate": 6.793220521193346e-05, "loss": 0.15760910511016846, "step": 526 }, { "epoch": 1.7877758913412563, "grad_norm": 0.19456229113016593, "learning_rate": 6.779405744966954e-05, "loss": 0.1361851543188095, "step": 527 }, { "epoch": 1.7911714770797964, "grad_norm": 0.18017536340442106, "learning_rate": 6.76557539742222e-05, "loss": 0.13075143098831177, "step": 528 }, { "epoch": 1.7945670628183361, "grad_norm": 0.153318489406289, "learning_rate": 6.751729599586483e-05, "loss": 0.1601436585187912, "step": 529 }, { "epoch": 1.797962648556876, "grad_norm": 0.17847097983437082, "learning_rate": 6.737868472622287e-05, "loss": 0.17493556439876556, "step": 530 }, { "epoch": 1.801358234295416, "grad_norm": 0.17019156651346398, "learning_rate": 6.723992137826318e-05, "loss": 0.17217008769512177, "step": 531 }, { "epoch": 1.804753820033956, "grad_norm": 0.1649627150787132, "learning_rate": 6.710100716628344e-05, "loss": 0.15804290771484375, "step": 532 }, { "epoch": 1.8081494057724958, "grad_norm": 0.16816709286576256, "learning_rate": 6.696194330590151e-05, "loss": 0.15615008771419525, "step": 533 }, { "epoch": 1.8115449915110355, "grad_norm": 0.16708104240503863, "learning_rate": 6.682273101404482e-05, "loss": 0.14586041867733002, "step": 534 }, { "epoch": 1.8149405772495757, "grad_norm": 0.1814566877657439, "learning_rate": 6.668337150893971e-05, "loss": 0.14995837211608887, "step": 535 }, { "epoch": 1.8183361629881154, "grad_norm": 0.17321974970730894, "learning_rate": 6.65438660101007e-05, "loss": 0.1311999261379242, "step": 536 }, { "epoch": 1.8217317487266553, "grad_norm": 0.16306291469108447, "learning_rate": 6.640421573831995e-05, "loss": 0.14747732877731323, "step": 537 }, { "epoch": 1.8251273344651953, "grad_norm": 0.17272476585733168, "learning_rate": 6.626442191565645e-05, "loss": 0.18027102947235107, "step": 538 }, { "epoch": 1.8285229202037352, "grad_norm": 0.16869819166753489, "learning_rate": 6.612448576542545e-05, "loss": 0.1796453595161438, "step": 539 }, { "epoch": 1.8319185059422751, "grad_norm": 0.15857435747794013, "learning_rate": 6.598440851218763e-05, "loss": 0.165388822555542, "step": 540 }, { "epoch": 1.8353140916808148, "grad_norm": 0.17237247398742017, "learning_rate": 6.584419138173845e-05, "loss": 0.1611655205488205, "step": 541 }, { "epoch": 1.838709677419355, "grad_norm": 0.17249173054448652, "learning_rate": 6.570383560109745e-05, "loss": 0.16045475006103516, "step": 542 }, { "epoch": 1.8421052631578947, "grad_norm": 0.16323961577475898, "learning_rate": 6.556334239849744e-05, "loss": 0.14716218411922455, "step": 543 }, { "epoch": 1.8455008488964346, "grad_norm": 0.16418969950286805, "learning_rate": 6.542271300337377e-05, "loss": 0.14025574922561646, "step": 544 }, { "epoch": 1.8488964346349746, "grad_norm": 0.17982931710839725, "learning_rate": 6.528194864635369e-05, "loss": 0.14023080468177795, "step": 545 }, { "epoch": 1.8522920203735145, "grad_norm": 0.4124407454648751, "learning_rate": 6.514105055924538e-05, "loss": 0.18015198409557343, "step": 546 }, { "epoch": 1.8556876061120544, "grad_norm": 0.14064122576892013, "learning_rate": 6.500001997502731e-05, "loss": 0.1652262955904007, "step": 547 }, { "epoch": 1.8590831918505941, "grad_norm": 0.17368425384885416, "learning_rate": 6.485885812783739e-05, "loss": 0.17111623287200928, "step": 548 }, { "epoch": 1.8624787775891343, "grad_norm": 0.24832305300100166, "learning_rate": 6.471756625296224e-05, "loss": 0.15875035524368286, "step": 549 }, { "epoch": 1.865874363327674, "grad_norm": 0.16381238792726202, "learning_rate": 6.45761455868263e-05, "loss": 0.1415071189403534, "step": 550 }, { "epoch": 1.869269949066214, "grad_norm": 0.1628350190526178, "learning_rate": 6.443459736698105e-05, "loss": 0.1438436210155487, "step": 551 }, { "epoch": 1.8726655348047538, "grad_norm": 0.17297682318053498, "learning_rate": 6.429292283209419e-05, "loss": 0.14610980451107025, "step": 552 }, { "epoch": 1.8760611205432938, "grad_norm": 0.1763084560775975, "learning_rate": 6.41511232219387e-05, "loss": 0.1317806839942932, "step": 553 }, { "epoch": 1.8794567062818337, "grad_norm": 0.15980085791433568, "learning_rate": 6.400919977738222e-05, "loss": 0.17347626388072968, "step": 554 }, { "epoch": 1.8828522920203734, "grad_norm": 0.16622035305185193, "learning_rate": 6.386715374037596e-05, "loss": 0.18846440315246582, "step": 555 }, { "epoch": 1.8862478777589136, "grad_norm": 0.16868663025425032, "learning_rate": 6.372498635394388e-05, "loss": 0.16884970664978027, "step": 556 }, { "epoch": 1.8896434634974533, "grad_norm": 0.18197837871179445, "learning_rate": 6.358269886217194e-05, "loss": 0.16474951803684235, "step": 557 }, { "epoch": 1.8930390492359932, "grad_norm": 0.16480933886153618, "learning_rate": 6.344029251019707e-05, "loss": 0.14512299001216888, "step": 558 }, { "epoch": 1.8964346349745331, "grad_norm": 0.173551917494542, "learning_rate": 6.329776854419636e-05, "loss": 0.14445650577545166, "step": 559 }, { "epoch": 1.899830220713073, "grad_norm": 0.16015392741797763, "learning_rate": 6.315512821137606e-05, "loss": 0.14070647954940796, "step": 560 }, { "epoch": 1.903225806451613, "grad_norm": 0.16647532763775283, "learning_rate": 6.301237275996082e-05, "loss": 0.13384906947612762, "step": 561 }, { "epoch": 1.9066213921901527, "grad_norm": 0.17089930777461557, "learning_rate": 6.286950343918262e-05, "loss": 0.16571879386901855, "step": 562 }, { "epoch": 1.9100169779286928, "grad_norm": 0.16110978133355203, "learning_rate": 6.272652149926988e-05, "loss": 0.19308504462242126, "step": 563 }, { "epoch": 1.9134125636672326, "grad_norm": 0.15566191246213598, "learning_rate": 6.258342819143659e-05, "loss": 0.17147845029830933, "step": 564 }, { "epoch": 1.9168081494057725, "grad_norm": 0.16138873387479707, "learning_rate": 6.244022476787124e-05, "loss": 0.15436913073062897, "step": 565 }, { "epoch": 1.9202037351443124, "grad_norm": 0.1579870801213752, "learning_rate": 6.229691248172599e-05, "loss": 0.14631399512290955, "step": 566 }, { "epoch": 1.9235993208828521, "grad_norm": 0.1692079037044616, "learning_rate": 6.215349258710557e-05, "loss": 0.14651337265968323, "step": 567 }, { "epoch": 1.9269949066213923, "grad_norm": 0.15718902820550903, "learning_rate": 6.200996633905646e-05, "loss": 0.13412252068519592, "step": 568 }, { "epoch": 1.930390492359932, "grad_norm": 0.17937085359659188, "learning_rate": 6.186633499355576e-05, "loss": 0.1383034735918045, "step": 569 }, { "epoch": 1.9337860780984721, "grad_norm": 0.1850043799407954, "learning_rate": 6.172259980750023e-05, "loss": 0.12899111211299896, "step": 570 }, { "epoch": 1.9371816638370118, "grad_norm": 0.16068722567407098, "learning_rate": 6.157876203869546e-05, "loss": 0.1698915660381317, "step": 571 }, { "epoch": 1.9405772495755518, "grad_norm": 0.162480160170972, "learning_rate": 6.143482294584459e-05, "loss": 0.17424562573432922, "step": 572 }, { "epoch": 1.9439728353140917, "grad_norm": 0.15529625573427977, "learning_rate": 6.129078378853748e-05, "loss": 0.15596550703048706, "step": 573 }, { "epoch": 1.9473684210526314, "grad_norm": 0.17226545206258617, "learning_rate": 6.114664582723966e-05, "loss": 0.1550683230161667, "step": 574 }, { "epoch": 1.9507640067911716, "grad_norm": 0.16901705408888065, "learning_rate": 6.100241032328124e-05, "loss": 0.14169350266456604, "step": 575 }, { "epoch": 1.9541595925297113, "grad_norm": 0.18030162282219803, "learning_rate": 6.085807853884595e-05, "loss": 0.1491428017616272, "step": 576 }, { "epoch": 1.9575551782682514, "grad_norm": 0.17758224542538914, "learning_rate": 6.0713651736960034e-05, "loss": 0.14005613327026367, "step": 577 }, { "epoch": 1.9609507640067911, "grad_norm": 0.18687305208074853, "learning_rate": 6.056913118148122e-05, "loss": 0.13678719103336334, "step": 578 }, { "epoch": 1.964346349745331, "grad_norm": 0.15345722028837877, "learning_rate": 6.0424518137087674e-05, "loss": 0.1598358452320099, "step": 579 }, { "epoch": 1.967741935483871, "grad_norm": 0.15389184004940906, "learning_rate": 6.0279813869266885e-05, "loss": 0.16596555709838867, "step": 580 }, { "epoch": 1.9711375212224107, "grad_norm": 0.15459172749951094, "learning_rate": 6.013501964430468e-05, "loss": 0.15973442792892456, "step": 581 }, { "epoch": 1.9745331069609509, "grad_norm": 0.17474347338146987, "learning_rate": 5.999013672927405e-05, "loss": 0.16224101185798645, "step": 582 }, { "epoch": 1.9779286926994906, "grad_norm": 0.16662687023041706, "learning_rate": 5.9845166392024074e-05, "loss": 0.15299895405769348, "step": 583 }, { "epoch": 1.9813242784380307, "grad_norm": 0.16426586028052112, "learning_rate": 5.970010990116892e-05, "loss": 0.14674901962280273, "step": 584 }, { "epoch": 1.9847198641765704, "grad_norm": 0.1711567738588456, "learning_rate": 5.955496852607661e-05, "loss": 0.1379772275686264, "step": 585 }, { "epoch": 1.9881154499151104, "grad_norm": 0.16908145786092682, "learning_rate": 5.940974353685804e-05, "loss": 0.12416021525859833, "step": 586 }, { "epoch": 1.9915110356536503, "grad_norm": 0.1789952898846213, "learning_rate": 5.9264436204355724e-05, "loss": 0.15557736158370972, "step": 587 }, { "epoch": 1.99490662139219, "grad_norm": 0.17620336028076247, "learning_rate": 5.911904780013279e-05, "loss": 0.18169651925563812, "step": 588 }, { "epoch": 1.9983022071307301, "grad_norm": 0.18610757228161331, "learning_rate": 5.8973579596461834e-05, "loss": 0.1419195830821991, "step": 589 }, { "epoch": 2.0, "grad_norm": 0.24963183042592363, "learning_rate": 5.882803286631372e-05, "loss": 0.13311868906021118, "step": 590 }, { "epoch": 2.0033955857385397, "grad_norm": 0.27267276866966383, "learning_rate": 5.868240888334653e-05, "loss": 0.12104956805706024, "step": 591 }, { "epoch": 2.00679117147708, "grad_norm": 0.2067432052428407, "learning_rate": 5.853670892189432e-05, "loss": 0.1117546558380127, "step": 592 }, { "epoch": 2.0101867572156196, "grad_norm": 0.32602984830752424, "learning_rate": 5.839093425695609e-05, "loss": 0.10089024901390076, "step": 593 }, { "epoch": 2.0135823429541597, "grad_norm": 0.19702244827410376, "learning_rate": 5.824508616418449e-05, "loss": 0.09226801991462708, "step": 594 }, { "epoch": 2.0169779286926994, "grad_norm": 0.18469712535411414, "learning_rate": 5.8099165919874784e-05, "loss": 0.0863746628165245, "step": 595 }, { "epoch": 2.0203735144312396, "grad_norm": 0.20344675915422358, "learning_rate": 5.7953174800953604e-05, "loss": 0.07718914747238159, "step": 596 }, { "epoch": 2.0237691001697793, "grad_norm": 0.20261795312799238, "learning_rate": 5.7807114084967775e-05, "loss": 0.07371412962675095, "step": 597 }, { "epoch": 2.027164685908319, "grad_norm": 0.18118558851036415, "learning_rate": 5.766098505007318e-05, "loss": 0.0710630789399147, "step": 598 }, { "epoch": 2.030560271646859, "grad_norm": 0.2520953402176877, "learning_rate": 5.751478897502352e-05, "loss": 0.11631827801465988, "step": 599 }, { "epoch": 2.033955857385399, "grad_norm": 0.20833127846366223, "learning_rate": 5.736852713915921e-05, "loss": 0.10760145634412766, "step": 600 }, { "epoch": 2.037351443123939, "grad_norm": 0.17865889130017845, "learning_rate": 5.7222200822396075e-05, "loss": 0.10485737770795822, "step": 601 }, { "epoch": 2.0407470288624787, "grad_norm": 0.18192537645688403, "learning_rate": 5.7075811305214245e-05, "loss": 0.10091932862997055, "step": 602 }, { "epoch": 2.044142614601019, "grad_norm": 0.17664302595091572, "learning_rate": 5.692935986864685e-05, "loss": 0.08710863441228867, "step": 603 }, { "epoch": 2.0475382003395586, "grad_norm": 0.19359544551771066, "learning_rate": 5.678284779426891e-05, "loss": 0.08012089133262634, "step": 604 }, { "epoch": 2.0509337860780983, "grad_norm": 0.17571993852332962, "learning_rate": 5.6636276364186105e-05, "loss": 0.07406513392925262, "step": 605 }, { "epoch": 2.0543293718166384, "grad_norm": 0.17296055539491953, "learning_rate": 5.648964686102346e-05, "loss": 0.06827662885189056, "step": 606 }, { "epoch": 2.057724957555178, "grad_norm": 0.1994240332606509, "learning_rate": 5.6342960567914235e-05, "loss": 0.08899202197790146, "step": 607 }, { "epoch": 2.0611205432937183, "grad_norm": 0.21147546133103653, "learning_rate": 5.619621876848864e-05, "loss": 0.1175706535577774, "step": 608 }, { "epoch": 2.064516129032258, "grad_norm": 0.20032856929005421, "learning_rate": 5.60494227468626e-05, "loss": 0.10147128999233246, "step": 609 }, { "epoch": 2.067911714770798, "grad_norm": 0.17965434697084495, "learning_rate": 5.5902573787626544e-05, "loss": 0.09305062890052795, "step": 610 }, { "epoch": 2.071307300509338, "grad_norm": 0.18451106622314192, "learning_rate": 5.5755673175834145e-05, "loss": 0.08531151711940765, "step": 611 }, { "epoch": 2.0747028862478776, "grad_norm": 0.18509153403778958, "learning_rate": 5.56087221969911e-05, "loss": 0.07805474102497101, "step": 612 }, { "epoch": 2.0780984719864177, "grad_norm": 0.18441124653981383, "learning_rate": 5.546172213704384e-05, "loss": 0.07336990535259247, "step": 613 }, { "epoch": 2.0814940577249574, "grad_norm": 0.1806373442108902, "learning_rate": 5.5314674282368275e-05, "loss": 0.06579209864139557, "step": 614 }, { "epoch": 2.0848896434634976, "grad_norm": 0.1962089754406543, "learning_rate": 5.5167579919758606e-05, "loss": 0.06725182384252548, "step": 615 }, { "epoch": 2.0882852292020373, "grad_norm": 0.531554111382921, "learning_rate": 5.5020440336416e-05, "loss": 0.1145014688372612, "step": 616 }, { "epoch": 2.0916808149405774, "grad_norm": 0.22319658970526987, "learning_rate": 5.487325681993733e-05, "loss": 0.11737364530563354, "step": 617 }, { "epoch": 2.095076400679117, "grad_norm": 0.18401413591200674, "learning_rate": 5.472603065830393e-05, "loss": 0.10318945348262787, "step": 618 }, { "epoch": 2.098471986417657, "grad_norm": 0.17791198102246508, "learning_rate": 5.457876313987034e-05, "loss": 0.08743831515312195, "step": 619 }, { "epoch": 2.101867572156197, "grad_norm": 0.18552952282168486, "learning_rate": 5.443145555335296e-05, "loss": 0.08302175253629684, "step": 620 }, { "epoch": 2.1052631578947367, "grad_norm": 0.17872882232665616, "learning_rate": 5.4284109187818845e-05, "loss": 0.07643230259418488, "step": 621 }, { "epoch": 2.108658743633277, "grad_norm": 0.19415584347612555, "learning_rate": 5.4136725332674434e-05, "loss": 0.07614649832248688, "step": 622 }, { "epoch": 2.1120543293718166, "grad_norm": 0.18216765819273645, "learning_rate": 5.3989305277654156e-05, "loss": 0.07087817788124084, "step": 623 }, { "epoch": 2.1154499151103567, "grad_norm": 0.21252936111454282, "learning_rate": 5.3841850312809295e-05, "loss": 0.11139951646327972, "step": 624 }, { "epoch": 2.1188455008488964, "grad_norm": 0.20314518629758666, "learning_rate": 5.369436172849657e-05, "loss": 0.1259862780570984, "step": 625 }, { "epoch": 2.122241086587436, "grad_norm": 0.19308635467686402, "learning_rate": 5.354684081536693e-05, "loss": 0.10937876999378204, "step": 626 }, { "epoch": 2.1256366723259763, "grad_norm": 0.2096475793631085, "learning_rate": 5.3399288864354225e-05, "loss": 0.0953579992055893, "step": 627 }, { "epoch": 2.129032258064516, "grad_norm": 0.18324171328953562, "learning_rate": 5.3251707166663886e-05, "loss": 0.08874654769897461, "step": 628 }, { "epoch": 2.132427843803056, "grad_norm": 0.17851987679927697, "learning_rate": 5.31040970137617e-05, "loss": 0.08193890750408173, "step": 629 }, { "epoch": 2.135823429541596, "grad_norm": 0.19566717537325667, "learning_rate": 5.295645969736244e-05, "loss": 0.07548414170742035, "step": 630 }, { "epoch": 2.139219015280136, "grad_norm": 0.1819698611863226, "learning_rate": 5.280879650941857e-05, "loss": 0.06608285754919052, "step": 631 }, { "epoch": 2.1426146010186757, "grad_norm": 1.5527007927589012, "learning_rate": 5.2661108742108935e-05, "loss": 0.09255146980285645, "step": 632 }, { "epoch": 2.1460101867572154, "grad_norm": 0.18265497124223457, "learning_rate": 5.251339768782754e-05, "loss": 0.11359074711799622, "step": 633 }, { "epoch": 2.1494057724957556, "grad_norm": 0.1878182896085561, "learning_rate": 5.23656646391721e-05, "loss": 0.1139441728591919, "step": 634 }, { "epoch": 2.1528013582342953, "grad_norm": 0.21371797561998035, "learning_rate": 5.221791088893282e-05, "loss": 0.10060256719589233, "step": 635 }, { "epoch": 2.1561969439728355, "grad_norm": 0.1918855727807065, "learning_rate": 5.207013773008111e-05, "loss": 0.08961832523345947, "step": 636 }, { "epoch": 2.159592529711375, "grad_norm": 0.1858845878618591, "learning_rate": 5.192234645575814e-05, "loss": 0.08403001725673676, "step": 637 }, { "epoch": 2.1629881154499153, "grad_norm": 0.20134533241307526, "learning_rate": 5.177453835926366e-05, "loss": 0.07931354641914368, "step": 638 }, { "epoch": 2.166383701188455, "grad_norm": 0.17187064098510713, "learning_rate": 5.162671473404461e-05, "loss": 0.06572918593883514, "step": 639 }, { "epoch": 2.1697792869269947, "grad_norm": 0.18963975830736843, "learning_rate": 5.147887687368384e-05, "loss": 0.07264866679906845, "step": 640 }, { "epoch": 2.173174872665535, "grad_norm": 0.2246232252583268, "learning_rate": 5.133102607188874e-05, "loss": 0.11681890487670898, "step": 641 }, { "epoch": 2.1765704584040746, "grad_norm": 0.26295402046380767, "learning_rate": 5.1183163622479966e-05, "loss": 0.10791041702032089, "step": 642 }, { "epoch": 2.1799660441426147, "grad_norm": 0.181858482685371, "learning_rate": 5.10352908193801e-05, "loss": 0.09829472750425339, "step": 643 }, { "epoch": 2.1833616298811545, "grad_norm": 0.2030235866450046, "learning_rate": 5.088740895660231e-05, "loss": 0.09725946187973022, "step": 644 }, { "epoch": 2.1867572156196946, "grad_norm": 0.1875369015824775, "learning_rate": 5.073951932823907e-05, "loss": 0.08819393813610077, "step": 645 }, { "epoch": 2.1901528013582343, "grad_norm": 0.17864911265600283, "learning_rate": 5.0591623228450805e-05, "loss": 0.07982441782951355, "step": 646 }, { "epoch": 2.193548387096774, "grad_norm": 0.18521128596332995, "learning_rate": 5.044372195145455e-05, "loss": 0.07353096455335617, "step": 647 }, { "epoch": 2.196943972835314, "grad_norm": 0.18456205199611705, "learning_rate": 5.0295816791512686e-05, "loss": 0.0687694251537323, "step": 648 }, { "epoch": 2.200339558573854, "grad_norm": 0.1829757250614102, "learning_rate": 5.014790904292149e-05, "loss": 0.10892924666404724, "step": 649 }, { "epoch": 2.203735144312394, "grad_norm": 0.18890396925275804, "learning_rate": 5e-05, "loss": 0.1159369945526123, "step": 650 }, { "epoch": 2.2071307300509337, "grad_norm": 0.16942344658174852, "learning_rate": 4.9852090957078515e-05, "loss": 0.09954734891653061, "step": 651 }, { "epoch": 2.2105263157894735, "grad_norm": 0.1780504542099046, "learning_rate": 4.9704183208487325e-05, "loss": 0.09250899404287338, "step": 652 }, { "epoch": 2.2139219015280136, "grad_norm": 0.18645623237142073, "learning_rate": 4.955627804854545e-05, "loss": 0.08235422521829605, "step": 653 }, { "epoch": 2.2173174872665533, "grad_norm": 0.1784994683358793, "learning_rate": 4.94083767715492e-05, "loss": 0.07888228446245193, "step": 654 }, { "epoch": 2.2207130730050935, "grad_norm": 0.17013633984743062, "learning_rate": 4.9260480671760925e-05, "loss": 0.0726616159081459, "step": 655 }, { "epoch": 2.224108658743633, "grad_norm": 0.18472673831827965, "learning_rate": 4.911259104339771e-05, "loss": 0.06728089600801468, "step": 656 }, { "epoch": 2.2275042444821733, "grad_norm": 0.17332449496936028, "learning_rate": 4.8964709180619924e-05, "loss": 0.08549031615257263, "step": 657 }, { "epoch": 2.230899830220713, "grad_norm": 0.17090509376963334, "learning_rate": 4.881683637752005e-05, "loss": 0.11464506387710571, "step": 658 }, { "epoch": 2.234295415959253, "grad_norm": 0.1787107238756445, "learning_rate": 4.866897392811126e-05, "loss": 0.10288610309362411, "step": 659 }, { "epoch": 2.237691001697793, "grad_norm": 0.1860588588343053, "learning_rate": 4.852112312631616e-05, "loss": 0.10606972873210907, "step": 660 }, { "epoch": 2.2410865874363326, "grad_norm": 0.17458517745338073, "learning_rate": 4.8373285265955395e-05, "loss": 0.08981959521770477, "step": 661 }, { "epoch": 2.2444821731748728, "grad_norm": 0.17526499434649234, "learning_rate": 4.822546164073635e-05, "loss": 0.08232477307319641, "step": 662 }, { "epoch": 2.2478777589134125, "grad_norm": 0.1823611459398258, "learning_rate": 4.8077653544241864e-05, "loss": 0.07704266905784607, "step": 663 }, { "epoch": 2.2512733446519526, "grad_norm": 0.18489843602962322, "learning_rate": 4.792986226991889e-05, "loss": 0.06634756177663803, "step": 664 }, { "epoch": 2.2546689303904923, "grad_norm": 0.18448574712357313, "learning_rate": 4.7782089111067176e-05, "loss": 0.0683097243309021, "step": 665 }, { "epoch": 2.258064516129032, "grad_norm": 0.17589761018962824, "learning_rate": 4.7634335360827905e-05, "loss": 0.11916027963161469, "step": 666 }, { "epoch": 2.261460101867572, "grad_norm": 0.1795256534211018, "learning_rate": 4.748660231217249e-05, "loss": 0.11158622801303864, "step": 667 }, { "epoch": 2.264855687606112, "grad_norm": 0.19290337392195064, "learning_rate": 4.7338891257891084e-05, "loss": 0.09854745864868164, "step": 668 }, { "epoch": 2.268251273344652, "grad_norm": 0.19201767298650546, "learning_rate": 4.719120349058146e-05, "loss": 0.08974334597587585, "step": 669 }, { "epoch": 2.2716468590831917, "grad_norm": 0.1868889162004061, "learning_rate": 4.7043540302637575e-05, "loss": 0.07873357832431793, "step": 670 }, { "epoch": 2.275042444821732, "grad_norm": 0.17432262922782887, "learning_rate": 4.6895902986238304e-05, "loss": 0.07303929328918457, "step": 671 }, { "epoch": 2.2784380305602716, "grad_norm": 0.18149889718903636, "learning_rate": 4.6748292833336125e-05, "loss": 0.07083107531070709, "step": 672 }, { "epoch": 2.2818336162988118, "grad_norm": 0.18983742345901558, "learning_rate": 4.6600711135645793e-05, "loss": 0.06820881366729736, "step": 673 }, { "epoch": 2.2852292020373515, "grad_norm": 0.18497480111804915, "learning_rate": 4.6453159184633076e-05, "loss": 0.11455556005239487, "step": 674 }, { "epoch": 2.288624787775891, "grad_norm": 0.17300209986311835, "learning_rate": 4.6305638271503445e-05, "loss": 0.12156914174556732, "step": 675 }, { "epoch": 2.2920203735144313, "grad_norm": 0.17661683006436862, "learning_rate": 4.615814968719071e-05, "loss": 0.10207021236419678, "step": 676 }, { "epoch": 2.295415959252971, "grad_norm": 0.19468914390395273, "learning_rate": 4.601069472234584e-05, "loss": 0.09467285126447678, "step": 677 }, { "epoch": 2.298811544991511, "grad_norm": 0.1738009297809384, "learning_rate": 4.586327466732557e-05, "loss": 0.08891662955284119, "step": 678 }, { "epoch": 2.302207130730051, "grad_norm": 0.1677007830201778, "learning_rate": 4.571589081218116e-05, "loss": 0.08263769745826721, "step": 679 }, { "epoch": 2.3056027164685906, "grad_norm": 0.17164671308827525, "learning_rate": 4.556854444664706e-05, "loss": 0.07031428813934326, "step": 680 }, { "epoch": 2.3089983022071308, "grad_norm": 0.18274635410925702, "learning_rate": 4.5421236860129686e-05, "loss": 0.06435659527778625, "step": 681 }, { "epoch": 2.3123938879456705, "grad_norm": 0.1951047898281109, "learning_rate": 4.527396934169609e-05, "loss": 0.10397550463676453, "step": 682 }, { "epoch": 2.3157894736842106, "grad_norm": 0.166661262512508, "learning_rate": 4.512674318006268e-05, "loss": 0.12233447283506393, "step": 683 }, { "epoch": 2.3191850594227503, "grad_norm": 0.174509398628348, "learning_rate": 4.4979559663584015e-05, "loss": 0.11278166621923447, "step": 684 }, { "epoch": 2.3225806451612905, "grad_norm": 0.18372530728814804, "learning_rate": 4.4832420080241406e-05, "loss": 0.09657131135463715, "step": 685 }, { "epoch": 2.32597623089983, "grad_norm": 0.192043056192785, "learning_rate": 4.4685325717631736e-05, "loss": 0.09288895130157471, "step": 686 }, { "epoch": 2.3293718166383703, "grad_norm": 0.18075180427633028, "learning_rate": 4.453827786295617e-05, "loss": 0.08457746356725693, "step": 687 }, { "epoch": 2.33276740237691, "grad_norm": 0.1803332569114452, "learning_rate": 4.4391277803008905e-05, "loss": 0.07192069292068481, "step": 688 }, { "epoch": 2.3361629881154498, "grad_norm": 0.1845280135878161, "learning_rate": 4.424432682416585e-05, "loss": 0.06865935027599335, "step": 689 }, { "epoch": 2.33955857385399, "grad_norm": 0.18164609516311606, "learning_rate": 4.4097426212373474e-05, "loss": 0.06910768896341324, "step": 690 }, { "epoch": 2.3429541595925296, "grad_norm": 0.16060301549094005, "learning_rate": 4.3950577253137425e-05, "loss": 0.10569753497838974, "step": 691 }, { "epoch": 2.3463497453310698, "grad_norm": 0.1674539424459387, "learning_rate": 4.380378123151139e-05, "loss": 0.11710407584905624, "step": 692 }, { "epoch": 2.3497453310696095, "grad_norm": 0.17406276657114875, "learning_rate": 4.3657039432085776e-05, "loss": 0.09413979947566986, "step": 693 }, { "epoch": 2.353140916808149, "grad_norm": 0.18113092057180355, "learning_rate": 4.351035313897655e-05, "loss": 0.08770646899938583, "step": 694 }, { "epoch": 2.3565365025466893, "grad_norm": 0.16700143864455724, "learning_rate": 4.336372363581391e-05, "loss": 0.07561078667640686, "step": 695 }, { "epoch": 2.359932088285229, "grad_norm": 0.17147638271329094, "learning_rate": 4.32171522057311e-05, "loss": 0.07131327688694, "step": 696 }, { "epoch": 2.363327674023769, "grad_norm": 0.17044551345359776, "learning_rate": 4.307064013135316e-05, "loss": 0.0693497434258461, "step": 697 }, { "epoch": 2.366723259762309, "grad_norm": 0.17221115238993254, "learning_rate": 4.2924188694785773e-05, "loss": 0.06643468141555786, "step": 698 }, { "epoch": 2.370118845500849, "grad_norm": 2.6338356816764454, "learning_rate": 4.277779917760393e-05, "loss": 0.11351452767848969, "step": 699 }, { "epoch": 2.3735144312393888, "grad_norm": 0.16665576423366846, "learning_rate": 4.263147286084078e-05, "loss": 0.11587866395711899, "step": 700 }, { "epoch": 2.376910016977929, "grad_norm": 0.16532913408136696, "learning_rate": 4.2485211024976496e-05, "loss": 0.09847494959831238, "step": 701 }, { "epoch": 2.3803056027164686, "grad_norm": 0.16401491632337248, "learning_rate": 4.2339014949926844e-05, "loss": 0.08751493692398071, "step": 702 }, { "epoch": 2.3837011884550083, "grad_norm": 0.15773476826313854, "learning_rate": 4.219288591503224e-05, "loss": 0.07740139961242676, "step": 703 }, { "epoch": 2.3870967741935485, "grad_norm": 0.17320455891261463, "learning_rate": 4.204682519904641e-05, "loss": 0.08057060837745667, "step": 704 }, { "epoch": 2.390492359932088, "grad_norm": 0.16742884612884762, "learning_rate": 4.190083408012522e-05, "loss": 0.07117292284965515, "step": 705 }, { "epoch": 2.3938879456706283, "grad_norm": 0.17310857861179457, "learning_rate": 4.175491383581552e-05, "loss": 0.06331349164247513, "step": 706 }, { "epoch": 2.397283531409168, "grad_norm": 0.18898498235955274, "learning_rate": 4.160906574304392e-05, "loss": 0.10791736841201782, "step": 707 }, { "epoch": 2.4006791171477078, "grad_norm": 0.1805357155912146, "learning_rate": 4.146329107810569e-05, "loss": 0.1271810233592987, "step": 708 }, { "epoch": 2.404074702886248, "grad_norm": 0.16646580267560332, "learning_rate": 4.131759111665349e-05, "loss": 0.10617226362228394, "step": 709 }, { "epoch": 2.4074702886247876, "grad_norm": 0.1714977551226205, "learning_rate": 4.117196713368629e-05, "loss": 0.09965567290782928, "step": 710 }, { "epoch": 2.4108658743633278, "grad_norm": 0.1773594142509446, "learning_rate": 4.102642040353817e-05, "loss": 0.09726707637310028, "step": 711 }, { "epoch": 2.4142614601018675, "grad_norm": 0.16709027855867933, "learning_rate": 4.088095219986721e-05, "loss": 0.0809185653924942, "step": 712 }, { "epoch": 2.4176570458404076, "grad_norm": 0.1701974174479521, "learning_rate": 4.0735563795644294e-05, "loss": 0.06818859279155731, "step": 713 }, { "epoch": 2.4210526315789473, "grad_norm": 0.17294499386525772, "learning_rate": 4.059025646314197e-05, "loss": 0.06326454132795334, "step": 714 }, { "epoch": 2.4244482173174875, "grad_norm": 0.1848603704424289, "learning_rate": 4.044503147392339e-05, "loss": 0.06449925899505615, "step": 715 }, { "epoch": 2.427843803056027, "grad_norm": 0.1737521878913226, "learning_rate": 4.0299890098831096e-05, "loss": 0.11198844760656357, "step": 716 }, { "epoch": 2.431239388794567, "grad_norm": 0.17165850436307425, "learning_rate": 4.015483360797593e-05, "loss": 0.10379281640052795, "step": 717 }, { "epoch": 2.434634974533107, "grad_norm": 0.17547574852065886, "learning_rate": 4.0009863270725964e-05, "loss": 0.09260678291320801, "step": 718 }, { "epoch": 2.4380305602716468, "grad_norm": 0.1938992617623928, "learning_rate": 3.986498035569532e-05, "loss": 0.08913596719503403, "step": 719 }, { "epoch": 2.441426146010187, "grad_norm": 0.171147291228373, "learning_rate": 3.972018613073312e-05, "loss": 0.07828541100025177, "step": 720 }, { "epoch": 2.4448217317487266, "grad_norm": 0.15958068147739846, "learning_rate": 3.957548186291233e-05, "loss": 0.070742167532444, "step": 721 }, { "epoch": 2.4482173174872663, "grad_norm": 0.1702558652837616, "learning_rate": 3.9430868818518784e-05, "loss": 0.061952412128448486, "step": 722 }, { "epoch": 2.4516129032258065, "grad_norm": 0.18307336168228425, "learning_rate": 3.928634826303997e-05, "loss": 0.058472149074077606, "step": 723 }, { "epoch": 2.455008488964346, "grad_norm": 0.18744531414378332, "learning_rate": 3.914192146115407e-05, "loss": 0.10116694867610931, "step": 724 }, { "epoch": 2.4584040747028864, "grad_norm": 0.1605746385761094, "learning_rate": 3.899758967671878e-05, "loss": 0.1049356684088707, "step": 725 }, { "epoch": 2.461799660441426, "grad_norm": 0.1731850592599192, "learning_rate": 3.885335417276037e-05, "loss": 0.09615564346313477, "step": 726 }, { "epoch": 2.465195246179966, "grad_norm": 0.21215742797079024, "learning_rate": 3.870921621146254e-05, "loss": 0.09364002197980881, "step": 727 }, { "epoch": 2.468590831918506, "grad_norm": 0.20557635828107731, "learning_rate": 3.856517705415543e-05, "loss": 0.08540572226047516, "step": 728 }, { "epoch": 2.471986417657046, "grad_norm": 0.16072157295836462, "learning_rate": 3.8421237961304555e-05, "loss": 0.08038079738616943, "step": 729 }, { "epoch": 2.475382003395586, "grad_norm": 0.18475166184656971, "learning_rate": 3.827740019249977e-05, "loss": 0.0667400136590004, "step": 730 }, { "epoch": 2.4787775891341255, "grad_norm": 0.18973268707266402, "learning_rate": 3.8133665006444255e-05, "loss": 0.0635080486536026, "step": 731 }, { "epoch": 2.4821731748726656, "grad_norm": 0.19518255768698312, "learning_rate": 3.799003366094354e-05, "loss": 0.09870380163192749, "step": 732 }, { "epoch": 2.4855687606112054, "grad_norm": 0.16946862785266179, "learning_rate": 3.784650741289442e-05, "loss": 0.12275432050228119, "step": 733 }, { "epoch": 2.4889643463497455, "grad_norm": 0.16920435287125005, "learning_rate": 3.7703087518274015e-05, "loss": 0.10064749419689178, "step": 734 }, { "epoch": 2.492359932088285, "grad_norm": 0.19730054455264487, "learning_rate": 3.755977523212877e-05, "loss": 0.0969122052192688, "step": 735 }, { "epoch": 2.495755517826825, "grad_norm": 0.1989299102023274, "learning_rate": 3.7416571808563426e-05, "loss": 0.09330247342586517, "step": 736 }, { "epoch": 2.499151103565365, "grad_norm": 0.18552713073754007, "learning_rate": 3.727347850073012e-05, "loss": 0.07835578173398972, "step": 737 }, { "epoch": 2.502546689303905, "grad_norm": 0.17124728777739812, "learning_rate": 3.71304965608174e-05, "loss": 0.07191760838031769, "step": 738 }, { "epoch": 2.505942275042445, "grad_norm": 0.1837249200607298, "learning_rate": 3.698762724003919e-05, "loss": 0.06304986774921417, "step": 739 }, { "epoch": 2.5093378607809846, "grad_norm": 0.19178552870427884, "learning_rate": 3.6844871788623945e-05, "loss": 0.06902088969945908, "step": 740 }, { "epoch": 2.5127334465195243, "grad_norm": 0.18523019316456035, "learning_rate": 3.670223145580366e-05, "loss": 0.11148184537887573, "step": 741 }, { "epoch": 2.5161290322580645, "grad_norm": 0.15402488873260553, "learning_rate": 3.655970748980293e-05, "loss": 0.10683425515890121, "step": 742 }, { "epoch": 2.5195246179966047, "grad_norm": 0.15662014422056703, "learning_rate": 3.641730113782807e-05, "loss": 0.09403928369283676, "step": 743 }, { "epoch": 2.5229202037351444, "grad_norm": 0.18611041314512944, "learning_rate": 3.6275013646056135e-05, "loss": 0.08520263433456421, "step": 744 }, { "epoch": 2.526315789473684, "grad_norm": 0.20211193991604673, "learning_rate": 3.6132846259624055e-05, "loss": 0.08205583691596985, "step": 745 }, { "epoch": 2.5297113752122242, "grad_norm": 0.16879941563935696, "learning_rate": 3.599080022261777e-05, "loss": 0.07212570309638977, "step": 746 }, { "epoch": 2.533106960950764, "grad_norm": 0.17244718288322106, "learning_rate": 3.58488767780613e-05, "loss": 0.06664963066577911, "step": 747 }, { "epoch": 2.536502546689304, "grad_norm": 0.18236345434585838, "learning_rate": 3.570707716790584e-05, "loss": 0.06124931573867798, "step": 748 }, { "epoch": 2.539898132427844, "grad_norm": 0.182514828750284, "learning_rate": 3.556540263301896e-05, "loss": 0.10768868774175644, "step": 749 }, { "epoch": 2.5432937181663835, "grad_norm": 0.17273676152731657, "learning_rate": 3.5423854413173706e-05, "loss": 0.10910140722990036, "step": 750 }, { "epoch": 2.5466893039049237, "grad_norm": 0.18295071965254522, "learning_rate": 3.5282433747037757e-05, "loss": 0.0994892343878746, "step": 751 }, { "epoch": 2.5500848896434634, "grad_norm": 0.1892125557879812, "learning_rate": 3.514114187216261e-05, "loss": 0.09176020324230194, "step": 752 }, { "epoch": 2.5534804753820035, "grad_norm": 0.1732687624444229, "learning_rate": 3.49999800249727e-05, "loss": 0.07957559823989868, "step": 753 }, { "epoch": 2.556876061120543, "grad_norm": 0.17704744326114794, "learning_rate": 3.485894944075463e-05, "loss": 0.09056335687637329, "step": 754 }, { "epoch": 2.560271646859083, "grad_norm": 0.184004963408498, "learning_rate": 3.47180513536463e-05, "loss": 0.07315690815448761, "step": 755 }, { "epoch": 2.563667232597623, "grad_norm": 0.16597486694525979, "learning_rate": 3.457728699662621e-05, "loss": 0.061057500541210175, "step": 756 }, { "epoch": 2.5670628183361632, "grad_norm": 0.17902718042035354, "learning_rate": 3.4436657601502576e-05, "loss": 0.08318621665239334, "step": 757 }, { "epoch": 2.570458404074703, "grad_norm": 0.1760348831467887, "learning_rate": 3.429616439890258e-05, "loss": 0.11352517455816269, "step": 758 }, { "epoch": 2.5738539898132426, "grad_norm": 0.18422354723345027, "learning_rate": 3.4155808618261563e-05, "loss": 0.10124319791793823, "step": 759 }, { "epoch": 2.577249575551783, "grad_norm": 0.18558477176320745, "learning_rate": 3.4015591487812395e-05, "loss": 0.09465136379003525, "step": 760 }, { "epoch": 2.5806451612903225, "grad_norm": 0.1876065160534628, "learning_rate": 3.3875514234574556e-05, "loss": 0.08952825516462326, "step": 761 }, { "epoch": 2.5840407470288627, "grad_norm": 0.19266524892327866, "learning_rate": 3.373557808434355e-05, "loss": 0.07428369671106339, "step": 762 }, { "epoch": 2.5874363327674024, "grad_norm": 0.17597898636269044, "learning_rate": 3.359578426168007e-05, "loss": 0.07350639253854752, "step": 763 }, { "epoch": 2.590831918505942, "grad_norm": 0.18902878136451348, "learning_rate": 3.345613398989932e-05, "loss": 0.0661240816116333, "step": 764 }, { "epoch": 2.5942275042444822, "grad_norm": 0.19009846861192758, "learning_rate": 3.33166284910603e-05, "loss": 0.06323446333408356, "step": 765 }, { "epoch": 2.597623089983022, "grad_norm": 0.1619217798383207, "learning_rate": 3.317726898595517e-05, "loss": 0.10194535553455353, "step": 766 }, { "epoch": 2.601018675721562, "grad_norm": 0.1680059996744845, "learning_rate": 3.303805669409848e-05, "loss": 0.10827316343784332, "step": 767 }, { "epoch": 2.604414261460102, "grad_norm": 0.1924285532954259, "learning_rate": 3.289899283371657e-05, "loss": 0.09438102692365646, "step": 768 }, { "epoch": 2.6078098471986415, "grad_norm": 0.18692172840515286, "learning_rate": 3.276007862173683e-05, "loss": 0.08589994162321091, "step": 769 }, { "epoch": 2.6112054329371817, "grad_norm": 0.19218042963593016, "learning_rate": 3.262131527377715e-05, "loss": 0.08207014203071594, "step": 770 }, { "epoch": 2.614601018675722, "grad_norm": 0.16968247149600457, "learning_rate": 3.248270400413518e-05, "loss": 0.06647342443466187, "step": 771 }, { "epoch": 2.6179966044142615, "grad_norm": 0.17176844415165643, "learning_rate": 3.23442460257778e-05, "loss": 0.0627061128616333, "step": 772 }, { "epoch": 2.6213921901528012, "grad_norm": 0.1819874917328322, "learning_rate": 3.2205942550330456e-05, "loss": 0.05918596684932709, "step": 773 }, { "epoch": 2.6247877758913414, "grad_norm": 0.17996053454131153, "learning_rate": 3.206779478806654e-05, "loss": 0.09956592321395874, "step": 774 }, { "epoch": 2.628183361629881, "grad_norm": 0.16980520183534636, "learning_rate": 3.192980394789682e-05, "loss": 0.10763359069824219, "step": 775 }, { "epoch": 2.6315789473684212, "grad_norm": 0.17384792300906218, "learning_rate": 3.179197123735889e-05, "loss": 0.0954458937048912, "step": 776 }, { "epoch": 2.634974533106961, "grad_norm": 0.18122435873821038, "learning_rate": 3.1654297862606554e-05, "loss": 0.09476964175701141, "step": 777 }, { "epoch": 2.6383701188455007, "grad_norm": 0.18733027860097912, "learning_rate": 3.151678502839929e-05, "loss": 0.08117790520191193, "step": 778 }, { "epoch": 2.641765704584041, "grad_norm": 0.18792684422111558, "learning_rate": 3.1379433938091696e-05, "loss": 0.07760273665189743, "step": 779 }, { "epoch": 2.6451612903225805, "grad_norm": 0.171095961582522, "learning_rate": 3.124224579362305e-05, "loss": 0.06836757063865662, "step": 780 }, { "epoch": 2.6485568760611207, "grad_norm": 0.16586690535426274, "learning_rate": 3.1105221795506584e-05, "loss": 0.06185036152601242, "step": 781 }, { "epoch": 2.6519524617996604, "grad_norm": 0.19110229535272452, "learning_rate": 3.096836314281923e-05, "loss": 0.096954345703125, "step": 782 }, { "epoch": 2.6553480475382, "grad_norm": 0.1883336259581249, "learning_rate": 3.083167103319093e-05, "loss": 0.11950527131557465, "step": 783 }, { "epoch": 2.6587436332767402, "grad_norm": 0.1753554156754892, "learning_rate": 3.069514666279427e-05, "loss": 0.10608899593353271, "step": 784 }, { "epoch": 2.6621392190152804, "grad_norm": 0.17079380669353134, "learning_rate": 3.055879122633397e-05, "loss": 0.09107103943824768, "step": 785 }, { "epoch": 2.66553480475382, "grad_norm": 0.18024274038258492, "learning_rate": 3.042260591703643e-05, "loss": 0.08277568221092224, "step": 786 }, { "epoch": 2.66893039049236, "grad_norm": 0.20357810198812507, "learning_rate": 3.0286591926639287e-05, "loss": 0.08410590887069702, "step": 787 }, { "epoch": 2.6723259762309, "grad_norm": 0.18874188968414343, "learning_rate": 3.0150750445380992e-05, "loss": 0.06746567785739899, "step": 788 }, { "epoch": 2.6757215619694397, "grad_norm": 0.17501264607067415, "learning_rate": 3.0015082661990395e-05, "loss": 0.06665299832820892, "step": 789 }, { "epoch": 2.67911714770798, "grad_norm": 0.18740797925287156, "learning_rate": 2.9879589763676358e-05, "loss": 0.06513458490371704, "step": 790 }, { "epoch": 2.6825127334465195, "grad_norm": 0.16842439954319954, "learning_rate": 2.9744272936117323e-05, "loss": 0.10696576535701752, "step": 791 }, { "epoch": 2.6859083191850592, "grad_norm": 0.1677334409051065, "learning_rate": 2.960913336345099e-05, "loss": 0.0977114588022232, "step": 792 }, { "epoch": 2.6893039049235994, "grad_norm": 0.17113025072633664, "learning_rate": 2.9474172228263887e-05, "loss": 0.09799250215291977, "step": 793 }, { "epoch": 2.692699490662139, "grad_norm": 0.16684957141437765, "learning_rate": 2.9339390711581105e-05, "loss": 0.08379356563091278, "step": 794 }, { "epoch": 2.6960950764006792, "grad_norm": 0.1791882354287892, "learning_rate": 2.9204789992855885e-05, "loss": 0.08375358581542969, "step": 795 }, { "epoch": 2.699490662139219, "grad_norm": 0.1801523603003994, "learning_rate": 2.9070371249959378e-05, "loss": 0.07268455624580383, "step": 796 }, { "epoch": 2.7028862478777587, "grad_norm": 0.18307971950457935, "learning_rate": 2.8936135659170216e-05, "loss": 0.06600889563560486, "step": 797 }, { "epoch": 2.706281833616299, "grad_norm": 0.16982280078165418, "learning_rate": 2.8802084395164386e-05, "loss": 0.05860915035009384, "step": 798 }, { "epoch": 2.709677419354839, "grad_norm": 0.16240407076947652, "learning_rate": 2.866821863100479e-05, "loss": 0.09923011064529419, "step": 799 }, { "epoch": 2.7130730050933787, "grad_norm": 0.17915783644720862, "learning_rate": 2.8534539538131076e-05, "loss": 0.11352638900279999, "step": 800 }, { "epoch": 2.7164685908319184, "grad_norm": 0.18738688072645704, "learning_rate": 2.8401048286349353e-05, "loss": 0.09644570201635361, "step": 801 }, { "epoch": 2.7198641765704585, "grad_norm": 0.2054300534794763, "learning_rate": 2.826774604382195e-05, "loss": 0.08496775478124619, "step": 802 }, { "epoch": 2.7232597623089982, "grad_norm": 0.16673179794849724, "learning_rate": 2.8134633977057235e-05, "loss": 0.08083528280258179, "step": 803 }, { "epoch": 2.7266553480475384, "grad_norm": 0.17439611815695805, "learning_rate": 2.800171325089933e-05, "loss": 0.07991768419742584, "step": 804 }, { "epoch": 2.730050933786078, "grad_norm": 0.18619832214028129, "learning_rate": 2.7868985028518006e-05, "loss": 0.06698450446128845, "step": 805 }, { "epoch": 2.733446519524618, "grad_norm": 0.17972040282148158, "learning_rate": 2.7736450471398434e-05, "loss": 0.058878954499959946, "step": 806 }, { "epoch": 2.736842105263158, "grad_norm": 0.17067767227609026, "learning_rate": 2.7604110739331068e-05, "loss": 0.09054619073867798, "step": 807 }, { "epoch": 2.7402376910016977, "grad_norm": 0.14798064647679118, "learning_rate": 2.747196699040146e-05, "loss": 0.10854898393154144, "step": 808 }, { "epoch": 2.743633276740238, "grad_norm": 0.16873583317715957, "learning_rate": 2.7340020380980146e-05, "loss": 0.09747813642024994, "step": 809 }, { "epoch": 2.7470288624787775, "grad_norm": 0.1932858458435214, "learning_rate": 2.7208272065712537e-05, "loss": 0.09662696719169617, "step": 810 }, { "epoch": 2.7504244482173172, "grad_norm": 0.18258138588310577, "learning_rate": 2.7076723197508768e-05, "loss": 0.08496858924627304, "step": 811 }, { "epoch": 2.7538200339558574, "grad_norm": 0.16153132918386828, "learning_rate": 2.69453749275337e-05, "loss": 0.07826173305511475, "step": 812 }, { "epoch": 2.7572156196943975, "grad_norm": 0.16291136442798607, "learning_rate": 2.6814228405196738e-05, "loss": 0.06673877686262131, "step": 813 }, { "epoch": 2.7606112054329373, "grad_norm": 0.1873938972351929, "learning_rate": 2.6683284778141852e-05, "loss": 0.06131594628095627, "step": 814 }, { "epoch": 2.764006791171477, "grad_norm": 0.1909517453844909, "learning_rate": 2.655254519223746e-05, "loss": 0.06107237935066223, "step": 815 }, { "epoch": 2.767402376910017, "grad_norm": 0.15968835214266716, "learning_rate": 2.6422010791566492e-05, "loss": 0.11472313106060028, "step": 816 }, { "epoch": 2.770797962648557, "grad_norm": 0.14424394480463984, "learning_rate": 2.62916827184163e-05, "loss": 0.10236918181180954, "step": 817 }, { "epoch": 2.774193548387097, "grad_norm": 0.1791257123396259, "learning_rate": 2.6161562113268745e-05, "loss": 0.0926392674446106, "step": 818 }, { "epoch": 2.7775891341256367, "grad_norm": 0.209817575902277, "learning_rate": 2.603165011479012e-05, "loss": 0.09200967848300934, "step": 819 }, { "epoch": 2.7809847198641764, "grad_norm": 0.19100399868579906, "learning_rate": 2.590194785982124e-05, "loss": 0.07952775061130524, "step": 820 }, { "epoch": 2.7843803056027165, "grad_norm": 0.16710612106573458, "learning_rate": 2.5772456483367497e-05, "loss": 0.06726615130901337, "step": 821 }, { "epoch": 2.7877758913412563, "grad_norm": 0.17130937412200564, "learning_rate": 2.56431771185889e-05, "loss": 0.0635620504617691, "step": 822 }, { "epoch": 2.7911714770797964, "grad_norm": 0.19288788443257698, "learning_rate": 2.5514110896790184e-05, "loss": 0.05856780335307121, "step": 823 }, { "epoch": 2.794567062818336, "grad_norm": 0.18988175873253793, "learning_rate": 2.5385258947410906e-05, "loss": 0.09616898000240326, "step": 824 }, { "epoch": 2.797962648556876, "grad_norm": 0.677582426025809, "learning_rate": 2.525662239801553e-05, "loss": 0.11323189735412598, "step": 825 }, { "epoch": 2.801358234295416, "grad_norm": 0.15878371922437784, "learning_rate": 2.512820237428366e-05, "loss": 0.09259919822216034, "step": 826 }, { "epoch": 2.804753820033956, "grad_norm": 0.19629012259411324, "learning_rate": 2.500000000000001e-05, "loss": 0.09004946798086166, "step": 827 }, { "epoch": 2.808149405772496, "grad_norm": 0.2034778929352647, "learning_rate": 2.487201639704475e-05, "loss": 0.08156426250934601, "step": 828 }, { "epoch": 2.8115449915110355, "grad_norm": 0.17223089305549993, "learning_rate": 2.4744252685383596e-05, "loss": 0.06910967081785202, "step": 829 }, { "epoch": 2.8149405772495757, "grad_norm": 0.16945692961543954, "learning_rate": 2.4616709983058018e-05, "loss": 0.05877729505300522, "step": 830 }, { "epoch": 2.8183361629881154, "grad_norm": 0.18323830953345308, "learning_rate": 2.4489389406175456e-05, "loss": 0.061685554683208466, "step": 831 }, { "epoch": 2.8217317487266556, "grad_norm": 0.18220857908197913, "learning_rate": 2.436229206889962e-05, "loss": 0.08499722182750702, "step": 832 }, { "epoch": 2.8251273344651953, "grad_norm": 0.1759724037625514, "learning_rate": 2.4235419083440613e-05, "loss": 0.10835306346416473, "step": 833 }, { "epoch": 2.828522920203735, "grad_norm": 0.1519544041118763, "learning_rate": 2.4108771560045313e-05, "loss": 0.10240586847066879, "step": 834 }, { "epoch": 2.831918505942275, "grad_norm": 0.165991998143651, "learning_rate": 2.3982350606987587e-05, "loss": 0.09169580787420273, "step": 835 }, { "epoch": 2.835314091680815, "grad_norm": 0.18846610367004651, "learning_rate": 2.3856157330558625e-05, "loss": 0.09065485000610352, "step": 836 }, { "epoch": 2.838709677419355, "grad_norm": 0.18476046775864408, "learning_rate": 2.373019283505727e-05, "loss": 0.07656891644001007, "step": 837 }, { "epoch": 2.8421052631578947, "grad_norm": 0.16968535239248775, "learning_rate": 2.3604458222780313e-05, "loss": 0.06834015250205994, "step": 838 }, { "epoch": 2.8455008488964344, "grad_norm": 0.1645158955080501, "learning_rate": 2.347895459401288e-05, "loss": 0.060691386461257935, "step": 839 }, { "epoch": 2.8488964346349746, "grad_norm": 0.1759478474335412, "learning_rate": 2.33536830470188e-05, "loss": 0.062247686088085175, "step": 840 }, { "epoch": 2.8522920203735147, "grad_norm": 0.1713215131277223, "learning_rate": 2.322864467803097e-05, "loss": 0.11655740439891815, "step": 841 }, { "epoch": 2.8556876061120544, "grad_norm": 0.1663636513481251, "learning_rate": 2.3103840581241808e-05, "loss": 0.10389652103185654, "step": 842 }, { "epoch": 2.859083191850594, "grad_norm": 0.2121358261763457, "learning_rate": 2.2979271848793633e-05, "loss": 0.09916552156209946, "step": 843 }, { "epoch": 2.8624787775891343, "grad_norm": 0.16628728580666718, "learning_rate": 2.2854939570769117e-05, "loss": 0.08627776801586151, "step": 844 }, { "epoch": 2.865874363327674, "grad_norm": 0.16746133567878474, "learning_rate": 2.2730844835181757e-05, "loss": 0.07369454205036163, "step": 845 }, { "epoch": 2.869269949066214, "grad_norm": 0.17419436956304016, "learning_rate": 2.2606988727966393e-05, "loss": 0.06551572680473328, "step": 846 }, { "epoch": 2.872665534804754, "grad_norm": 0.1797511292699641, "learning_rate": 2.248337233296961e-05, "loss": 0.06162602826952934, "step": 847 }, { "epoch": 2.8760611205432935, "grad_norm": 0.1622937074628894, "learning_rate": 2.235999673194035e-05, "loss": 0.05968285724520683, "step": 848 }, { "epoch": 2.8794567062818337, "grad_norm": 0.16363469079190407, "learning_rate": 2.2236863004520326e-05, "loss": 0.103396937251091, "step": 849 }, { "epoch": 2.8828522920203734, "grad_norm": 0.16186365266239625, "learning_rate": 2.2113972228234737e-05, "loss": 0.10602563619613647, "step": 850 }, { "epoch": 2.8862478777589136, "grad_norm": 0.17317260814361962, "learning_rate": 2.1991325478482694e-05, "loss": 0.09179340302944183, "step": 851 }, { "epoch": 2.8896434634974533, "grad_norm": 0.18762734715234908, "learning_rate": 2.1868923828527933e-05, "loss": 0.08719556033611298, "step": 852 }, { "epoch": 2.893039049235993, "grad_norm": 0.1740616385410889, "learning_rate": 2.1746768349489283e-05, "loss": 0.07949644327163696, "step": 853 }, { "epoch": 2.896434634974533, "grad_norm": 0.16384283522776538, "learning_rate": 2.162486011033142e-05, "loss": 0.06954073160886765, "step": 854 }, { "epoch": 2.8998302207130733, "grad_norm": 0.1762608437604479, "learning_rate": 2.1503200177855426e-05, "loss": 0.061557263135910034, "step": 855 }, { "epoch": 2.903225806451613, "grad_norm": 0.17973846819642755, "learning_rate": 2.1381789616689512e-05, "loss": 0.05781710147857666, "step": 856 }, { "epoch": 2.9066213921901527, "grad_norm": 0.15744903411279135, "learning_rate": 2.126062948927966e-05, "loss": 0.0800895094871521, "step": 857 }, { "epoch": 2.910016977928693, "grad_norm": 0.13892733510455438, "learning_rate": 2.1139720855880357e-05, "loss": 0.10667183250188828, "step": 858 }, { "epoch": 2.9134125636672326, "grad_norm": 0.15514041990517785, "learning_rate": 2.1019064774545282e-05, "loss": 0.09649382531642914, "step": 859 }, { "epoch": 2.9168081494057727, "grad_norm": 0.18067253063476157, "learning_rate": 2.089866230111813e-05, "loss": 0.08846415579319, "step": 860 }, { "epoch": 2.9202037351443124, "grad_norm": 0.18206301172992329, "learning_rate": 2.0778514489223204e-05, "loss": 0.08002766966819763, "step": 861 }, { "epoch": 2.923599320882852, "grad_norm": 0.15644261730057993, "learning_rate": 2.065862239025639e-05, "loss": 0.0696350634098053, "step": 862 }, { "epoch": 2.9269949066213923, "grad_norm": 0.16174816063304712, "learning_rate": 2.053898705337583e-05, "loss": 0.07808029651641846, "step": 863 }, { "epoch": 2.930390492359932, "grad_norm": 0.17432685878371926, "learning_rate": 2.0419609525492794e-05, "loss": 0.060087498277425766, "step": 864 }, { "epoch": 2.933786078098472, "grad_norm": 0.18392589459839812, "learning_rate": 2.030049085126247e-05, "loss": 0.059294283390045166, "step": 865 }, { "epoch": 2.937181663837012, "grad_norm": 0.18333082665183126, "learning_rate": 2.0181632073074926e-05, "loss": 0.10879608243703842, "step": 866 }, { "epoch": 2.9405772495755516, "grad_norm": 0.14260939106052253, "learning_rate": 2.0063034231045852e-05, "loss": 0.09460778534412384, "step": 867 }, { "epoch": 2.9439728353140917, "grad_norm": 0.16184896075082875, "learning_rate": 1.9944698363007547e-05, "loss": 0.09041804075241089, "step": 868 }, { "epoch": 2.9473684210526314, "grad_norm": 0.18319480493169274, "learning_rate": 1.9826625504499806e-05, "loss": 0.08371460437774658, "step": 869 }, { "epoch": 2.9507640067911716, "grad_norm": 0.18021872069581388, "learning_rate": 1.9708816688760884e-05, "loss": 0.06918957829475403, "step": 870 }, { "epoch": 2.9541595925297113, "grad_norm": 0.158754042429574, "learning_rate": 1.9591272946718415e-05, "loss": 0.07203910499811172, "step": 871 }, { "epoch": 2.9575551782682514, "grad_norm": 0.1584361432308608, "learning_rate": 1.947399530698043e-05, "loss": 0.05943068489432335, "step": 872 }, { "epoch": 2.960950764006791, "grad_norm": 0.1600394923587483, "learning_rate": 1.9356984795826334e-05, "loss": 0.054306574165821075, "step": 873 }, { "epoch": 2.9643463497453313, "grad_norm": 0.17559935075843064, "learning_rate": 1.9240242437197913e-05, "loss": 0.09351390600204468, "step": 874 }, { "epoch": 2.967741935483871, "grad_norm": 0.1740228875068842, "learning_rate": 1.912376925269041e-05, "loss": 0.11052130162715912, "step": 875 }, { "epoch": 2.9711375212224107, "grad_norm": 0.14860625945260014, "learning_rate": 1.9007566261543558e-05, "loss": 0.08871638774871826, "step": 876 }, { "epoch": 2.974533106960951, "grad_norm": 0.15676146698379706, "learning_rate": 1.8891634480632664e-05, "loss": 0.0810859352350235, "step": 877 }, { "epoch": 2.9779286926994906, "grad_norm": 0.17372048062263223, "learning_rate": 1.8775974924459717e-05, "loss": 0.08844238519668579, "step": 878 }, { "epoch": 2.9813242784380307, "grad_norm": 0.17192997272808033, "learning_rate": 1.8660588605144484e-05, "loss": 0.06745877116918564, "step": 879 }, { "epoch": 2.9847198641765704, "grad_norm": 0.16467282143787115, "learning_rate": 1.8545476532415744e-05, "loss": 0.0653437003493309, "step": 880 }, { "epoch": 2.98811544991511, "grad_norm": 0.15774394530352917, "learning_rate": 1.8430639713602316e-05, "loss": 0.05818783864378929, "step": 881 }, { "epoch": 2.9915110356536503, "grad_norm": 0.15993011188014408, "learning_rate": 1.8316079153624355e-05, "loss": 0.08472274243831635, "step": 882 }, { "epoch": 2.99490662139219, "grad_norm": 0.16074210319828938, "learning_rate": 1.820179585498446e-05, "loss": 0.09365948289632797, "step": 883 }, { "epoch": 2.99830220713073, "grad_norm": 0.15155861734273393, "learning_rate": 1.808779081775901e-05, "loss": 0.06799779832363129, "step": 884 }, { "epoch": 3.0, "grad_norm": 0.20393027821397597, "learning_rate": 1.7974065039589333e-05, "loss": 0.05543612688779831, "step": 885 }, { "epoch": 3.0033955857385397, "grad_norm": 0.24028881568251675, "learning_rate": 1.7860619515673033e-05, "loss": 0.06700880080461502, "step": 886 }, { "epoch": 3.00679117147708, "grad_norm": 0.2053766853320597, "learning_rate": 1.7747455238755223e-05, "loss": 0.05432623624801636, "step": 887 }, { "epoch": 3.0101867572156196, "grad_norm": 0.17145737336763053, "learning_rate": 1.7634573199119863e-05, "loss": 0.044365014880895615, "step": 888 }, { "epoch": 3.0135823429541597, "grad_norm": 0.15654001689835462, "learning_rate": 1.7521974384581115e-05, "loss": 0.03612581640481949, "step": 889 }, { "epoch": 3.0169779286926994, "grad_norm": 0.15370485620508106, "learning_rate": 1.740965978047465e-05, "loss": 0.033521901816129684, "step": 890 }, { "epoch": 3.0203735144312396, "grad_norm": 0.1482840607174852, "learning_rate": 1.729763036964909e-05, "loss": 0.026836013421416283, "step": 891 }, { "epoch": 3.0237691001697793, "grad_norm": 0.16428015217225686, "learning_rate": 1.718588713245734e-05, "loss": 0.023287151008844376, "step": 892 }, { "epoch": 3.027164685908319, "grad_norm": 0.18205863863137203, "learning_rate": 1.7074431046748075e-05, "loss": 0.023514404892921448, "step": 893 }, { "epoch": 3.030560271646859, "grad_norm": 0.2520658409759249, "learning_rate": 1.6963263087857123e-05, "loss": 0.05385994911193848, "step": 894 }, { "epoch": 3.033955857385399, "grad_norm": 0.2496094433370953, "learning_rate": 1.6852384228598967e-05, "loss": 0.06253427267074585, "step": 895 }, { "epoch": 3.037351443123939, "grad_norm": 0.16925992374845164, "learning_rate": 1.6741795439258218e-05, "loss": 0.04542415589094162, "step": 896 }, { "epoch": 3.0407470288624787, "grad_norm": 0.15814351847123584, "learning_rate": 1.6631497687581126e-05, "loss": 0.038708411157131195, "step": 897 }, { "epoch": 3.044142614601019, "grad_norm": 0.16588709675844993, "learning_rate": 1.652149193876713e-05, "loss": 0.034707456827163696, "step": 898 }, { "epoch": 3.0475382003395586, "grad_norm": 0.1468917112956866, "learning_rate": 1.641177915546036e-05, "loss": 0.029641523957252502, "step": 899 }, { "epoch": 3.0509337860780983, "grad_norm": 0.14139121113969683, "learning_rate": 1.63023602977413e-05, "loss": 0.02573767863214016, "step": 900 }, { "epoch": 3.0543293718166384, "grad_norm": 0.14937127339945325, "learning_rate": 1.6193236323118283e-05, "loss": 0.022759422659873962, "step": 901 }, { "epoch": 3.057724957555178, "grad_norm": 0.1545738123629709, "learning_rate": 1.6084408186519196e-05, "loss": 0.04347142577171326, "step": 902 }, { "epoch": 3.0611205432937183, "grad_norm": 0.16134867860286392, "learning_rate": 1.5975876840283072e-05, "loss": 0.06474979966878891, "step": 903 }, { "epoch": 3.064516129032258, "grad_norm": 0.1497204226052965, "learning_rate": 1.586764323415178e-05, "loss": 0.04936043545603752, "step": 904 }, { "epoch": 3.067911714770798, "grad_norm": 0.14048991608035383, "learning_rate": 1.5759708315261722e-05, "loss": 0.04320313036441803, "step": 905 }, { "epoch": 3.071307300509338, "grad_norm": 0.141766997064975, "learning_rate": 1.5652073028135512e-05, "loss": 0.035470977425575256, "step": 906 }, { "epoch": 3.0747028862478776, "grad_norm": 0.15771271119439248, "learning_rate": 1.5544738314673747e-05, "loss": 0.03206377476453781, "step": 907 }, { "epoch": 3.0780984719864177, "grad_norm": 0.1454854404553505, "learning_rate": 1.5437705114146733e-05, "loss": 0.026127755641937256, "step": 908 }, { "epoch": 3.0814940577249574, "grad_norm": 0.13074817065499045, "learning_rate": 1.533097436318629e-05, "loss": 0.021116334944963455, "step": 909 }, { "epoch": 3.0848896434634976, "grad_norm": 0.14360651258815552, "learning_rate": 1.5224546995777549e-05, "loss": 0.02506256103515625, "step": 910 }, { "epoch": 3.0882852292020373, "grad_norm": 0.1756677108700991, "learning_rate": 1.5118423943250771e-05, "loss": 0.05918995290994644, "step": 911 }, { "epoch": 3.0916808149405774, "grad_norm": 0.17124543519940844, "learning_rate": 1.5012606134273205e-05, "loss": 0.048225294798612595, "step": 912 }, { "epoch": 3.095076400679117, "grad_norm": 0.147669359694198, "learning_rate": 1.4907094494840929e-05, "loss": 0.03807109594345093, "step": 913 }, { "epoch": 3.098471986417657, "grad_norm": 0.14347153348748545, "learning_rate": 1.4801889948270853e-05, "loss": 0.037231430411338806, "step": 914 }, { "epoch": 3.101867572156197, "grad_norm": 0.1341397983321544, "learning_rate": 1.4696993415192484e-05, "loss": 0.029485851526260376, "step": 915 }, { "epoch": 3.1052631578947367, "grad_norm": 0.13488879644242927, "learning_rate": 1.4592405813539994e-05, "loss": 0.02624015137553215, "step": 916 }, { "epoch": 3.108658743633277, "grad_norm": 0.1360205052500417, "learning_rate": 1.4488128058544098e-05, "loss": 0.02348337695002556, "step": 917 }, { "epoch": 3.1120543293718166, "grad_norm": 0.1169748475617425, "learning_rate": 1.4384161062724133e-05, "loss": 0.019927015528082848, "step": 918 }, { "epoch": 3.1154499151103567, "grad_norm": 0.13707829608124633, "learning_rate": 1.428050573587999e-05, "loss": 0.05076966807246208, "step": 919 }, { "epoch": 3.1188455008488964, "grad_norm": 0.1334447961070063, "learning_rate": 1.4177162985084242e-05, "loss": 0.050791554152965546, "step": 920 }, { "epoch": 3.122241086587436, "grad_norm": 0.1341038153418599, "learning_rate": 1.4074133714674115e-05, "loss": 0.04770858213305473, "step": 921 }, { "epoch": 3.1256366723259763, "grad_norm": 0.1472579891284908, "learning_rate": 1.397141882624361e-05, "loss": 0.04013638198375702, "step": 922 }, { "epoch": 3.129032258064516, "grad_norm": 0.12912850234958695, "learning_rate": 1.3869019218635642e-05, "loss": 0.03337923809885979, "step": 923 }, { "epoch": 3.132427843803056, "grad_norm": 0.14152232460713068, "learning_rate": 1.3766935787934138e-05, "loss": 0.039759911596775055, "step": 924 }, { "epoch": 3.135823429541596, "grad_norm": 0.12426979836991046, "learning_rate": 1.3665169427456203e-05, "loss": 0.023225799202919006, "step": 925 }, { "epoch": 3.139219015280136, "grad_norm": 0.12119350660009211, "learning_rate": 1.3563721027744308e-05, "loss": 0.02131539210677147, "step": 926 }, { "epoch": 3.1426146010186757, "grad_norm": 0.15702850253728412, "learning_rate": 1.3462591476558511e-05, "loss": 0.04250669479370117, "step": 927 }, { "epoch": 3.1460101867572154, "grad_norm": 0.14181985081843418, "learning_rate": 1.336178165886865e-05, "loss": 0.052393391728401184, "step": 928 }, { "epoch": 3.1494057724957556, "grad_norm": 0.13245257556679232, "learning_rate": 1.3261292456846647e-05, "loss": 0.040914386510849, "step": 929 }, { "epoch": 3.1528013582342953, "grad_norm": 0.13917949941320143, "learning_rate": 1.3161124749858738e-05, "loss": 0.04171147570014, "step": 930 }, { "epoch": 3.1561969439728355, "grad_norm": 0.13948473868398834, "learning_rate": 1.3061279414457823e-05, "loss": 0.04070255160331726, "step": 931 }, { "epoch": 3.159592529711375, "grad_norm": 0.12764281795698135, "learning_rate": 1.2961757324375767e-05, "loss": 0.027047133073210716, "step": 932 }, { "epoch": 3.1629881154499153, "grad_norm": 0.12301555564271233, "learning_rate": 1.2862559350515746e-05, "loss": 0.023495502769947052, "step": 933 }, { "epoch": 3.166383701188455, "grad_norm": 0.1334450446670973, "learning_rate": 1.27636863609447e-05, "loss": 0.022096674889326096, "step": 934 }, { "epoch": 3.1697792869269947, "grad_norm": 0.13767859104737193, "learning_rate": 1.2665139220885613e-05, "loss": 0.02451895736157894, "step": 935 }, { "epoch": 3.173174872665535, "grad_norm": 0.134761480069989, "learning_rate": 1.2566918792710042e-05, "loss": 0.056860968470573425, "step": 936 }, { "epoch": 3.1765704584040746, "grad_norm": 0.13169387158833784, "learning_rate": 1.2469025935930523e-05, "loss": 0.050218455493450165, "step": 937 }, { "epoch": 3.1799660441426147, "grad_norm": 0.1351600982380951, "learning_rate": 1.2371461507193078e-05, "loss": 0.04186920449137688, "step": 938 }, { "epoch": 3.1833616298811545, "grad_norm": 0.13118003425600933, "learning_rate": 1.2274226360269687e-05, "loss": 0.032554447650909424, "step": 939 }, { "epoch": 3.1867572156196946, "grad_norm": 0.1375266602484129, "learning_rate": 1.2177321346050835e-05, "loss": 0.030701391398906708, "step": 940 }, { "epoch": 3.1901528013582343, "grad_norm": 0.11829815265293832, "learning_rate": 1.2080747312538083e-05, "loss": 0.023229604586958885, "step": 941 }, { "epoch": 3.193548387096774, "grad_norm": 0.11744494660411912, "learning_rate": 1.1984505104836608e-05, "loss": 0.020911162719130516, "step": 942 }, { "epoch": 3.196943972835314, "grad_norm": 0.12208992751472954, "learning_rate": 1.1888595565147836e-05, "loss": 0.02026745118200779, "step": 943 }, { "epoch": 3.200339558573854, "grad_norm": 0.1370308825049616, "learning_rate": 1.1793019532762056e-05, "loss": 0.050561364740133286, "step": 944 }, { "epoch": 3.203735144312394, "grad_norm": 0.1320865285713048, "learning_rate": 1.1697777844051105e-05, "loss": 0.054354455322027206, "step": 945 }, { "epoch": 3.2071307300509337, "grad_norm": 0.12904401213539007, "learning_rate": 1.1602871332461002e-05, "loss": 0.040906570851802826, "step": 946 }, { "epoch": 3.2105263157894735, "grad_norm": 0.13358896791764147, "learning_rate": 1.150830082850468e-05, "loss": 0.04104870557785034, "step": 947 }, { "epoch": 3.2139219015280136, "grad_norm": 0.13576745277467697, "learning_rate": 1.141406715975476e-05, "loss": 0.03179006278514862, "step": 948 }, { "epoch": 3.2173174872665533, "grad_norm": 0.12989340990977727, "learning_rate": 1.1320171150836228e-05, "loss": 0.028960715979337692, "step": 949 }, { "epoch": 3.2207130730050935, "grad_norm": 0.11739065883416286, "learning_rate": 1.1226613623419269e-05, "loss": 0.02141611836850643, "step": 950 }, { "epoch": 3.224108658743633, "grad_norm": 0.12392313469407654, "learning_rate": 1.1133395396212049e-05, "loss": 0.021733587607741356, "step": 951 }, { "epoch": 3.2275042444821733, "grad_norm": 0.13054781103460678, "learning_rate": 1.1040517284953595e-05, "loss": 0.03965660184621811, "step": 952 }, { "epoch": 3.230899830220713, "grad_norm": 0.14015418456520445, "learning_rate": 1.0947980102406596e-05, "loss": 0.061388976871967316, "step": 953 }, { "epoch": 3.234295415959253, "grad_norm": 0.1313510738749738, "learning_rate": 1.0855784658350388e-05, "loss": 0.045122601091861725, "step": 954 }, { "epoch": 3.237691001697793, "grad_norm": 0.1229856769507569, "learning_rate": 1.0763931759573736e-05, "loss": 0.03775542601943016, "step": 955 }, { "epoch": 3.2410865874363326, "grad_norm": 0.12960445110096186, "learning_rate": 1.0672422209867878e-05, "loss": 0.033111028373241425, "step": 956 }, { "epoch": 3.2444821731748728, "grad_norm": 0.11567574075086891, "learning_rate": 1.0581256810019435e-05, "loss": 0.025276150554418564, "step": 957 }, { "epoch": 3.2478777589134125, "grad_norm": 0.12526076922153354, "learning_rate": 1.0490436357803435e-05, "loss": 0.025001049041748047, "step": 958 }, { "epoch": 3.2512733446519526, "grad_norm": 0.12289927352056768, "learning_rate": 1.0399961647976314e-05, "loss": 0.021313007920980453, "step": 959 }, { "epoch": 3.2546689303904923, "grad_norm": 0.13369532802520256, "learning_rate": 1.0309833472268976e-05, "loss": 0.025399228557944298, "step": 960 }, { "epoch": 3.258064516129032, "grad_norm": 0.18627005404901126, "learning_rate": 1.0220052619379843e-05, "loss": 0.05847664922475815, "step": 961 }, { "epoch": 3.261460101867572, "grad_norm": 0.12860256029327546, "learning_rate": 1.0130619874967983e-05, "loss": 0.048421770334243774, "step": 962 }, { "epoch": 3.264855687606112, "grad_norm": 0.12695685751232738, "learning_rate": 1.0041536021646204e-05, "loss": 0.042405616492033005, "step": 963 }, { "epoch": 3.268251273344652, "grad_norm": 0.12506542508160182, "learning_rate": 9.952801838974213e-06, "loss": 0.03340744599699974, "step": 964 }, { "epoch": 3.2716468590831917, "grad_norm": 0.12453199608254409, "learning_rate": 9.864418103451828e-06, "loss": 0.02923053316771984, "step": 965 }, { "epoch": 3.275042444821732, "grad_norm": 0.11845186452380632, "learning_rate": 9.776385588512121e-06, "loss": 0.026465460658073425, "step": 966 }, { "epoch": 3.2784380305602716, "grad_norm": 0.12067165400099766, "learning_rate": 9.688705064514703e-06, "loss": 0.021437451243400574, "step": 967 }, { "epoch": 3.2818336162988118, "grad_norm": 0.12388372462038609, "learning_rate": 9.601377298738977e-06, "loss": 0.020572148263454437, "step": 968 }, { "epoch": 3.2852292020373515, "grad_norm": 0.18950890680768173, "learning_rate": 9.514403055377386e-06, "loss": 0.05122412368655205, "step": 969 }, { "epoch": 3.288624787775891, "grad_norm": 0.13581685949347178, "learning_rate": 9.427783095528769e-06, "loss": 0.057231783866882324, "step": 970 }, { "epoch": 3.2920203735144313, "grad_norm": 0.12878115221070915, "learning_rate": 9.34151817719166e-06, "loss": 0.047430481761693954, "step": 971 }, { "epoch": 3.295415959252971, "grad_norm": 0.1262668644397002, "learning_rate": 9.255609055257713e-06, "loss": 0.03749135881662369, "step": 972 }, { "epoch": 3.298811544991511, "grad_norm": 0.1244416952979766, "learning_rate": 9.170056481504996e-06, "loss": 0.03182145953178406, "step": 973 }, { "epoch": 3.302207130730051, "grad_norm": 0.12252746917398741, "learning_rate": 9.084861204591549e-06, "loss": 0.02764609269797802, "step": 974 }, { "epoch": 3.3056027164685906, "grad_norm": 0.11471840726470396, "learning_rate": 9.000023970048726e-06, "loss": 0.02232491225004196, "step": 975 }, { "epoch": 3.3089983022071308, "grad_norm": 0.11916893504639654, "learning_rate": 8.915545520274698e-06, "loss": 0.020712103694677353, "step": 976 }, { "epoch": 3.3123938879456705, "grad_norm": 0.13525439972222236, "learning_rate": 8.831426594527975e-06, "loss": 0.038848504424095154, "step": 977 }, { "epoch": 3.3157894736842106, "grad_norm": 0.14699270845720624, "learning_rate": 8.747667928920927e-06, "loss": 0.06028951331973076, "step": 978 }, { "epoch": 3.3191850594227503, "grad_norm": 0.12925123203222016, "learning_rate": 8.664270256413332e-06, "loss": 0.0466872975230217, "step": 979 }, { "epoch": 3.3225806451612905, "grad_norm": 0.13362891203019467, "learning_rate": 8.581234306805969e-06, "loss": 0.046531789004802704, "step": 980 }, { "epoch": 3.32597623089983, "grad_norm": 0.12540125518706974, "learning_rate": 8.498560806734229e-06, "loss": 0.035425543785095215, "step": 981 }, { "epoch": 3.3293718166383703, "grad_norm": 0.12158048401225834, "learning_rate": 8.416250479661803e-06, "loss": 0.03032005950808525, "step": 982 }, { "epoch": 3.33276740237691, "grad_norm": 0.12075931278001789, "learning_rate": 8.334304045874247e-06, "loss": 0.024267151951789856, "step": 983 }, { "epoch": 3.3361629881154498, "grad_norm": 0.1153043106885603, "learning_rate": 8.252722222472792e-06, "loss": 0.02069593220949173, "step": 984 }, { "epoch": 3.33955857385399, "grad_norm": 0.11687593691034698, "learning_rate": 8.171505723367961e-06, "loss": 0.021528493613004684, "step": 985 }, { "epoch": 3.3429541595925296, "grad_norm": 0.11929820424307407, "learning_rate": 8.090655259273428e-06, "loss": 0.055011726915836334, "step": 986 }, { "epoch": 3.3463497453310698, "grad_norm": 0.12369586296247032, "learning_rate": 8.010171537699712e-06, "loss": 0.05019189044833183, "step": 987 }, { "epoch": 3.3497453310696095, "grad_norm": 0.12592126973457554, "learning_rate": 7.930055262948072e-06, "loss": 0.04088972136378288, "step": 988 }, { "epoch": 3.353140916808149, "grad_norm": 0.11949245114049085, "learning_rate": 7.850307136104247e-06, "loss": 0.03594840317964554, "step": 989 }, { "epoch": 3.3565365025466893, "grad_norm": 0.1261674465221902, "learning_rate": 7.770927855032378e-06, "loss": 0.029422909021377563, "step": 990 }, { "epoch": 3.359932088285229, "grad_norm": 0.11241054060859804, "learning_rate": 7.691918114368907e-06, "loss": 0.02306707203388214, "step": 991 }, { "epoch": 3.363327674023769, "grad_norm": 0.12048017563647961, "learning_rate": 7.613278605516455e-06, "loss": 0.022162199020385742, "step": 992 }, { "epoch": 3.366723259762309, "grad_norm": 0.1199461903145126, "learning_rate": 7.535010016637828e-06, "loss": 0.020632296800613403, "step": 993 }, { "epoch": 3.370118845500849, "grad_norm": 0.12668967418073732, "learning_rate": 7.457113032649943e-06, "loss": 0.049418896436691284, "step": 994 }, { "epoch": 3.3735144312393888, "grad_norm": 0.12731876482202897, "learning_rate": 7.379588335217874e-06, "loss": 0.05227503180503845, "step": 995 }, { "epoch": 3.376910016977929, "grad_norm": 0.1341182392517666, "learning_rate": 7.302436602748864e-06, "loss": 0.04013962671160698, "step": 996 }, { "epoch": 3.3803056027164686, "grad_norm": 0.1260874433427603, "learning_rate": 7.225658510386385e-06, "loss": 0.034193191677331924, "step": 997 }, { "epoch": 3.3837011884550083, "grad_norm": 0.1246268073344712, "learning_rate": 7.1492547300042455e-06, "loss": 0.029597267508506775, "step": 998 }, { "epoch": 3.3870967741935485, "grad_norm": 0.12115384144162494, "learning_rate": 7.073225930200722e-06, "loss": 0.02566773258149624, "step": 999 }, { "epoch": 3.390492359932088, "grad_norm": 0.11278574346249581, "learning_rate": 6.99757277629266e-06, "loss": 0.02209942601621151, "step": 1000 }, { "epoch": 3.3938879456706283, "grad_norm": 0.11748855312741553, "learning_rate": 6.922295930309691e-06, "loss": 0.01864083856344223, "step": 1001 }, { "epoch": 3.397283531409168, "grad_norm": 0.13686682230307992, "learning_rate": 6.847396050988469e-06, "loss": 0.0406767763197422, "step": 1002 }, { "epoch": 3.4006791171477078, "grad_norm": 0.13990793130538823, "learning_rate": 6.772873793766815e-06, "loss": 0.05869930237531662, "step": 1003 }, { "epoch": 3.404074702886248, "grad_norm": 0.11852753044717979, "learning_rate": 6.698729810778065e-06, "loss": 0.041964977979660034, "step": 1004 }, { "epoch": 3.4074702886247876, "grad_norm": 0.12835666911990343, "learning_rate": 6.624964750845325e-06, "loss": 0.037603434175252914, "step": 1005 }, { "epoch": 3.4108658743633278, "grad_norm": 0.12550525999520043, "learning_rate": 6.551579259475809e-06, "loss": 0.031934719532728195, "step": 1006 }, { "epoch": 3.4142614601018675, "grad_norm": 0.12401037937004707, "learning_rate": 6.478573978855146e-06, "loss": 0.02570326253771782, "step": 1007 }, { "epoch": 3.4176570458404076, "grad_norm": 0.12044967689030442, "learning_rate": 6.405949547841849e-06, "loss": 0.022274037823081017, "step": 1008 }, { "epoch": 3.4210526315789473, "grad_norm": 0.11087592312740602, "learning_rate": 6.333706601961642e-06, "loss": 0.018066687509417534, "step": 1009 }, { "epoch": 3.4244482173174875, "grad_norm": 0.12864117959479177, "learning_rate": 6.2618457734019364e-06, "loss": 0.02211109921336174, "step": 1010 }, { "epoch": 3.427843803056027, "grad_norm": 2.845461544809845, "learning_rate": 6.190367691006288e-06, "loss": 0.12403880059719086, "step": 1011 }, { "epoch": 3.431239388794567, "grad_norm": 0.13301922079617098, "learning_rate": 6.119272980268897e-06, "loss": 0.051573850214481354, "step": 1012 }, { "epoch": 3.434634974533107, "grad_norm": 0.12776379115591593, "learning_rate": 6.048562263329138e-06, "loss": 0.03954629972577095, "step": 1013 }, { "epoch": 3.4380305602716468, "grad_norm": 0.11850754574152694, "learning_rate": 5.978236158966105e-06, "loss": 0.033771682530641556, "step": 1014 }, { "epoch": 3.441426146010187, "grad_norm": 0.12191400095936242, "learning_rate": 5.908295282593207e-06, "loss": 0.029872318729758263, "step": 1015 }, { "epoch": 3.4448217317487266, "grad_norm": 0.12035263972020287, "learning_rate": 5.838740246252794e-06, "loss": 0.02534964494407177, "step": 1016 }, { "epoch": 3.4482173174872663, "grad_norm": 0.12133476775113167, "learning_rate": 5.769571658610762e-06, "loss": 0.02167777717113495, "step": 1017 }, { "epoch": 3.4516129032258065, "grad_norm": 0.11690833707928544, "learning_rate": 5.700790124951283e-06, "loss": 0.01822837069630623, "step": 1018 }, { "epoch": 3.455008488964346, "grad_norm": 0.12630252927861127, "learning_rate": 5.6323962471714286e-06, "loss": 0.04961255192756653, "step": 1019 }, { "epoch": 3.4584040747028864, "grad_norm": 0.12566893834764573, "learning_rate": 5.564390623775995e-06, "loss": 0.053999632596969604, "step": 1020 }, { "epoch": 3.461799660441426, "grad_norm": 0.12649794983158744, "learning_rate": 5.496773849872183e-06, "loss": 0.04361236095428467, "step": 1021 }, { "epoch": 3.465195246179966, "grad_norm": 0.1258215887528988, "learning_rate": 5.429546517164486e-06, "loss": 0.03720066696405411, "step": 1022 }, { "epoch": 3.468590831918506, "grad_norm": 0.11977910782122717, "learning_rate": 5.362709213949396e-06, "loss": 0.030863171443343163, "step": 1023 }, { "epoch": 3.471986417657046, "grad_norm": 0.1177420480554002, "learning_rate": 5.296262525110346e-06, "loss": 0.025983653962612152, "step": 1024 }, { "epoch": 3.475382003395586, "grad_norm": 0.11877674564132913, "learning_rate": 5.23020703211255e-06, "loss": 0.024062152951955795, "step": 1025 }, { "epoch": 3.4787775891341255, "grad_norm": 0.12096076300953294, "learning_rate": 5.1645433129979215e-06, "loss": 0.020530320703983307, "step": 1026 }, { "epoch": 3.4821731748726656, "grad_norm": 0.13722557567124155, "learning_rate": 5.0992719423800236e-06, "loss": 0.04217759519815445, "step": 1027 }, { "epoch": 3.4855687606112054, "grad_norm": 0.18248932999166922, "learning_rate": 5.034393491439043e-06, "loss": 0.05897298455238342, "step": 1028 }, { "epoch": 3.4889643463497455, "grad_norm": 0.12277998400064749, "learning_rate": 4.969908527916766e-06, "loss": 0.04530353471636772, "step": 1029 }, { "epoch": 3.492359932088285, "grad_norm": 0.12324235439400667, "learning_rate": 4.905817616111641e-06, "loss": 0.04073905944824219, "step": 1030 }, { "epoch": 3.495755517826825, "grad_norm": 0.12469350270474662, "learning_rate": 4.842121316873821e-06, "loss": 0.033599380403757095, "step": 1031 }, { "epoch": 3.499151103565365, "grad_norm": 0.12547916611233118, "learning_rate": 4.778820187600275e-06, "loss": 0.02724265679717064, "step": 1032 }, { "epoch": 3.502546689303905, "grad_norm": 0.12111966127673363, "learning_rate": 4.71591478222988e-06, "loss": 0.02298842929303646, "step": 1033 }, { "epoch": 3.505942275042445, "grad_norm": 0.1171905460176604, "learning_rate": 4.653405651238607e-06, "loss": 0.019800715148448944, "step": 1034 }, { "epoch": 3.5093378607809846, "grad_norm": 0.1281598741091766, "learning_rate": 4.591293341634661e-06, "loss": 0.023533042520284653, "step": 1035 }, { "epoch": 3.5127334465195243, "grad_norm": 0.12135145475096615, "learning_rate": 4.529578396953771e-06, "loss": 0.05884885415434837, "step": 1036 }, { "epoch": 3.5161290322580645, "grad_norm": 0.12383673633398194, "learning_rate": 4.468261357254339e-06, "loss": 0.04845176264643669, "step": 1037 }, { "epoch": 3.5195246179966047, "grad_norm": 0.11895407036309015, "learning_rate": 4.407342759112776e-06, "loss": 0.03610414266586304, "step": 1038 }, { "epoch": 3.5229202037351444, "grad_norm": 0.11868870856837141, "learning_rate": 4.346823135618788e-06, "loss": 0.03354974091053009, "step": 1039 }, { "epoch": 3.526315789473684, "grad_norm": 0.1214592987469816, "learning_rate": 4.286703016370719e-06, "loss": 0.030198832973837852, "step": 1040 }, { "epoch": 3.5297113752122242, "grad_norm": 0.12182201022392579, "learning_rate": 4.226982927470874e-06, "loss": 0.0259525366127491, "step": 1041 }, { "epoch": 3.533106960950764, "grad_norm": 0.11734478784342674, "learning_rate": 4.167663391521015e-06, "loss": 0.019816804677248, "step": 1042 }, { "epoch": 3.536502546689304, "grad_norm": 0.1205774870787238, "learning_rate": 4.108744927617669e-06, "loss": 0.021140148863196373, "step": 1043 }, { "epoch": 3.539898132427844, "grad_norm": 0.12231851223945485, "learning_rate": 4.050228051347671e-06, "loss": 0.04677321016788483, "step": 1044 }, { "epoch": 3.5432937181663835, "grad_norm": 0.12772100407249554, "learning_rate": 3.99211327478361e-06, "loss": 0.05391452834010124, "step": 1045 }, { "epoch": 3.5466893039049237, "grad_norm": 0.12676979859020726, "learning_rate": 3.9344011064793516e-06, "loss": 0.04096768796443939, "step": 1046 }, { "epoch": 3.5500848896434634, "grad_norm": 0.12188074021759346, "learning_rate": 3.877092051465614e-06, "loss": 0.03270147368311882, "step": 1047 }, { "epoch": 3.5534804753820035, "grad_norm": 0.11926231095416809, "learning_rate": 3.8201866112455185e-06, "loss": 0.029932573437690735, "step": 1048 }, { "epoch": 3.556876061120543, "grad_norm": 0.11406652752948458, "learning_rate": 3.763685283790208e-06, "loss": 0.024190083146095276, "step": 1049 }, { "epoch": 3.560271646859083, "grad_norm": 0.12216980983787372, "learning_rate": 3.707588563534514e-06, "loss": 0.022694718092679977, "step": 1050 }, { "epoch": 3.563667232597623, "grad_norm": 0.10945186678432801, "learning_rate": 3.6518969413725903e-06, "loss": 0.01736380159854889, "step": 1051 }, { "epoch": 3.5670628183361632, "grad_norm": 0.13705203548509745, "learning_rate": 3.596610904653652e-06, "loss": 0.038495805114507675, "step": 1052 }, { "epoch": 3.570458404074703, "grad_norm": 0.12204105547231771, "learning_rate": 3.5417309371776675e-06, "loss": 0.05471509322524071, "step": 1053 }, { "epoch": 3.5738539898132426, "grad_norm": 0.12485220314362966, "learning_rate": 3.4872575191911895e-06, "loss": 0.0403529517352581, "step": 1054 }, { "epoch": 3.577249575551783, "grad_norm": 0.12122723733330738, "learning_rate": 3.4331911273830784e-06, "loss": 0.03618926554918289, "step": 1055 }, { "epoch": 3.5806451612903225, "grad_norm": 0.12445840019567612, "learning_rate": 3.3795322348804114e-06, "loss": 0.03237292915582657, "step": 1056 }, { "epoch": 3.5840407470288627, "grad_norm": 0.11912758269027096, "learning_rate": 3.326281311244267e-06, "loss": 0.0282998438924551, "step": 1057 }, { "epoch": 3.5874363327674024, "grad_norm": 0.12441247964138512, "learning_rate": 3.2734388224656575e-06, "loss": 0.022452056407928467, "step": 1058 }, { "epoch": 3.590831918505942, "grad_norm": 0.11738735688257733, "learning_rate": 3.2210052309614437e-06, "loss": 0.018919995054602623, "step": 1059 }, { "epoch": 3.5942275042444822, "grad_norm": 0.12803403906596067, "learning_rate": 3.1689809955702754e-06, "loss": 0.02383407950401306, "step": 1060 }, { "epoch": 3.597623089983022, "grad_norm": 5.780780815871804, "learning_rate": 3.117366571548608e-06, "loss": 0.051781728863716125, "step": 1061 }, { "epoch": 3.601018675721562, "grad_norm": 0.125252141385265, "learning_rate": 3.066162410566681e-06, "loss": 0.049019526690244675, "step": 1062 }, { "epoch": 3.604414261460102, "grad_norm": 0.11540314234963726, "learning_rate": 3.0153689607045845e-06, "loss": 0.0345478430390358, "step": 1063 }, { "epoch": 3.6078098471986415, "grad_norm": 0.1254018210867563, "learning_rate": 2.9649866664483385e-06, "loss": 0.034069471061229706, "step": 1064 }, { "epoch": 3.6112054329371817, "grad_norm": 0.1214495371817403, "learning_rate": 2.915015968686002e-06, "loss": 0.028491949662566185, "step": 1065 }, { "epoch": 3.614601018675722, "grad_norm": 0.12215277210928013, "learning_rate": 2.865457304703817e-06, "loss": 0.02504706010222435, "step": 1066 }, { "epoch": 3.6179966044142615, "grad_norm": 0.1146310288080615, "learning_rate": 2.816311108182368e-06, "loss": 0.019377268850803375, "step": 1067 }, { "epoch": 3.6213921901528012, "grad_norm": 0.12226547324711232, "learning_rate": 2.767577809192806e-06, "loss": 0.020043358206748962, "step": 1068 }, { "epoch": 3.6247877758913414, "grad_norm": 0.12102233250877094, "learning_rate": 2.7192578341930618e-06, "loss": 0.045704327523708344, "step": 1069 }, { "epoch": 3.628183361629881, "grad_norm": 0.14028848911258027, "learning_rate": 2.6713516060241527e-06, "loss": 0.061729297041893005, "step": 1070 }, { "epoch": 3.6315789473684212, "grad_norm": 0.12448854051227845, "learning_rate": 2.6238595439064484e-06, "loss": 0.04341991990804672, "step": 1071 }, { "epoch": 3.634974533106961, "grad_norm": 0.1250978580769194, "learning_rate": 2.5767820634360008e-06, "loss": 0.039239685982465744, "step": 1072 }, { "epoch": 3.6383701188455007, "grad_norm": 0.12413119462939365, "learning_rate": 2.530119576580936e-06, "loss": 0.03052990883588791, "step": 1073 }, { "epoch": 3.641765704584041, "grad_norm": 0.11907032326878242, "learning_rate": 2.483872491677819e-06, "loss": 0.027010608464479446, "step": 1074 }, { "epoch": 3.6451612903225805, "grad_norm": 0.11103789921191211, "learning_rate": 2.4380412134280884e-06, "loss": 0.021763931959867477, "step": 1075 }, { "epoch": 3.6485568760611207, "grad_norm": 0.11405192745110872, "learning_rate": 2.3926261428945383e-06, "loss": 0.019843751564621925, "step": 1076 }, { "epoch": 3.6519524617996604, "grad_norm": 0.1295363442747286, "learning_rate": 2.347627677497788e-06, "loss": 0.04076223075389862, "step": 1077 }, { "epoch": 3.6553480475382, "grad_norm": 0.1246079946774913, "learning_rate": 2.303046211012783e-06, "loss": 0.056659214198589325, "step": 1078 }, { "epoch": 3.6587436332767402, "grad_norm": 0.12194922065761865, "learning_rate": 2.258882133565404e-06, "loss": 0.04163496196269989, "step": 1079 }, { "epoch": 3.6621392190152804, "grad_norm": 0.12323962667812549, "learning_rate": 2.2151358316290006e-06, "loss": 0.03819563612341881, "step": 1080 }, { "epoch": 3.66553480475382, "grad_norm": 0.12264346392148905, "learning_rate": 2.1718076880210327e-06, "loss": 0.029042597860097885, "step": 1081 }, { "epoch": 3.66893039049236, "grad_norm": 0.11684477206381359, "learning_rate": 2.1288980818997275e-06, "loss": 0.026639848947525024, "step": 1082 }, { "epoch": 3.6723259762309, "grad_norm": 0.11422896652588034, "learning_rate": 2.0864073887607416e-06, "loss": 0.021522920578718185, "step": 1083 }, { "epoch": 3.6757215619694397, "grad_norm": 0.10455713508802812, "learning_rate": 2.0443359804338923e-06, "loss": 0.01746872067451477, "step": 1084 }, { "epoch": 3.67911714770798, "grad_norm": 0.12982346982944845, "learning_rate": 2.0026842250799038e-06, "loss": 0.023929983377456665, "step": 1085 }, { "epoch": 3.6825127334465195, "grad_norm": 0.1316855649720207, "learning_rate": 1.9614524871871544e-06, "loss": 0.057851579040288925, "step": 1086 }, { "epoch": 3.6859083191850592, "grad_norm": 0.12590199455050757, "learning_rate": 1.92064112756854e-06, "loss": 0.04492168873548508, "step": 1087 }, { "epoch": 3.6893039049235994, "grad_norm": 0.1171932275811092, "learning_rate": 1.8802505033582608e-06, "loss": 0.03866066038608551, "step": 1088 }, { "epoch": 3.692699490662139, "grad_norm": 0.12201002318333427, "learning_rate": 1.8402809680087452e-06, "loss": 0.03478693217039108, "step": 1089 }, { "epoch": 3.6960950764006792, "grad_norm": 0.1182715500618888, "learning_rate": 1.8007328712875305e-06, "loss": 0.026261959224939346, "step": 1090 }, { "epoch": 3.699490662139219, "grad_norm": 0.12058468075672873, "learning_rate": 1.7616065592742038e-06, "loss": 0.02284175530076027, "step": 1091 }, { "epoch": 3.7028862478777587, "grad_norm": 0.11890983657221928, "learning_rate": 1.7229023743573657e-06, "loss": 0.02348652109503746, "step": 1092 }, { "epoch": 3.706281833616299, "grad_norm": 0.13292339050874438, "learning_rate": 1.6846206552316612e-06, "loss": 0.018931403756141663, "step": 1093 }, { "epoch": 3.709677419354839, "grad_norm": 0.13901173126777858, "learning_rate": 1.6467617368947918e-06, "loss": 0.0545373372733593, "step": 1094 }, { "epoch": 3.7130730050933787, "grad_norm": 0.12705979117861688, "learning_rate": 1.6093259506445913e-06, "loss": 0.05051073431968689, "step": 1095 }, { "epoch": 3.7164685908319184, "grad_norm": 0.12060123831314985, "learning_rate": 1.5723136240761271e-06, "loss": 0.04008012264966965, "step": 1096 }, { "epoch": 3.7198641765704585, "grad_norm": 0.12304390398289264, "learning_rate": 1.5357250810788314e-06, "loss": 0.03566541522741318, "step": 1097 }, { "epoch": 3.7232597623089982, "grad_norm": 0.11528157623419313, "learning_rate": 1.4995606418336694e-06, "loss": 0.030156664550304413, "step": 1098 }, { "epoch": 3.7266553480475384, "grad_norm": 0.11715511902942279, "learning_rate": 1.4638206228103413e-06, "loss": 0.026432838290929794, "step": 1099 }, { "epoch": 3.730050933786078, "grad_norm": 0.11275051425124914, "learning_rate": 1.4285053367645074e-06, "loss": 0.032550469040870667, "step": 1100 }, { "epoch": 3.733446519524618, "grad_norm": 0.11370947917205163, "learning_rate": 1.39361509273504e-06, "loss": 0.018357036635279655, "step": 1101 }, { "epoch": 3.736842105263158, "grad_norm": 0.13351337118584278, "learning_rate": 1.3591501960413422e-06, "loss": 0.04387955367565155, "step": 1102 }, { "epoch": 3.7402376910016977, "grad_norm": 0.12159110449240226, "learning_rate": 1.3251109482806666e-06, "loss": 0.056360602378845215, "step": 1103 }, { "epoch": 3.743633276740238, "grad_norm": 0.11791663878965616, "learning_rate": 1.2914976473254793e-06, "loss": 0.04391762241721153, "step": 1104 }, { "epoch": 3.7470288624787775, "grad_norm": 0.12174987156713225, "learning_rate": 1.2583105873208267e-06, "loss": 0.0394422709941864, "step": 1105 }, { "epoch": 3.7504244482173172, "grad_norm": 0.12319039187865549, "learning_rate": 1.2255500586818014e-06, "loss": 0.03090202808380127, "step": 1106 }, { "epoch": 3.7538200339558574, "grad_norm": 0.11761355850982404, "learning_rate": 1.1932163480909865e-06, "loss": 0.027796437963843346, "step": 1107 }, { "epoch": 3.7572156196943975, "grad_norm": 0.10887535616056307, "learning_rate": 1.1613097384959248e-06, "loss": 0.021867474541068077, "step": 1108 }, { "epoch": 3.7606112054329373, "grad_norm": 0.11628959072811464, "learning_rate": 1.1298305091066664e-06, "loss": 0.020357470959424973, "step": 1109 }, { "epoch": 3.764006791171477, "grad_norm": 0.12205517862948675, "learning_rate": 1.0987789353933408e-06, "loss": 0.022151701152324677, "step": 1110 }, { "epoch": 3.767402376910017, "grad_norm": 0.11857409941178108, "learning_rate": 1.0681552890836944e-06, "loss": 0.05923725292086601, "step": 1111 }, { "epoch": 3.770797962648557, "grad_norm": 0.1221293659634298, "learning_rate": 1.037959838160768e-06, "loss": 0.04962555691599846, "step": 1112 }, { "epoch": 3.774193548387097, "grad_norm": 0.11871768835081312, "learning_rate": 1.0081928468605118e-06, "loss": 0.038156140595674515, "step": 1113 }, { "epoch": 3.7775891341256367, "grad_norm": 0.11821643656293677, "learning_rate": 9.788545756694967e-07, "loss": 0.033427104353904724, "step": 1114 }, { "epoch": 3.7809847198641764, "grad_norm": 0.12068867312117082, "learning_rate": 9.499452813226284e-07, "loss": 0.030050046741962433, "step": 1115 }, { "epoch": 3.7843803056027165, "grad_norm": 0.11321161446828246, "learning_rate": 9.214652168008875e-07, "loss": 0.022684365510940552, "step": 1116 }, { "epoch": 3.7877758913412563, "grad_norm": 0.11477788176685755, "learning_rate": 8.934146313291425e-07, "loss": 0.021170279011130333, "step": 1117 }, { "epoch": 3.7911714770797964, "grad_norm": 0.11121517897347595, "learning_rate": 8.657937703739516e-07, "loss": 0.018932385370135307, "step": 1118 }, { "epoch": 3.794567062818336, "grad_norm": 0.12231547439412606, "learning_rate": 8.386028756414089e-07, "loss": 0.053899966180324554, "step": 1119 }, { "epoch": 3.797962648556876, "grad_norm": 0.11851479551801583, "learning_rate": 8.118421850750347e-07, "loss": 0.047234635800123215, "step": 1120 }, { "epoch": 3.801358234295416, "grad_norm": 0.12255693446774503, "learning_rate": 7.855119328537109e-07, "loss": 0.03975183516740799, "step": 1121 }, { "epoch": 3.804753820033956, "grad_norm": 0.11991770693815687, "learning_rate": 7.596123493895991e-07, "loss": 0.03657395392656326, "step": 1122 }, { "epoch": 3.808149405772496, "grad_norm": 0.11335433624523152, "learning_rate": 7.341436613261532e-07, "loss": 0.02959374710917473, "step": 1123 }, { "epoch": 3.8115449915110355, "grad_norm": 0.11576436301033464, "learning_rate": 7.091060915361269e-07, "loss": 0.024457689374685287, "step": 1124 }, { "epoch": 3.8149405772495757, "grad_norm": 0.1095832114653176, "learning_rate": 6.844998591196138e-07, "loss": 0.020221151411533356, "step": 1125 }, { "epoch": 3.8183361629881154, "grad_norm": 0.11514559319798055, "learning_rate": 6.603251794021381e-07, "loss": 0.019283602014183998, "step": 1126 }, { "epoch": 3.8217317487266556, "grad_norm": 0.12059343401726026, "learning_rate": 6.365822639327723e-07, "loss": 0.0341000109910965, "step": 1127 }, { "epoch": 3.8251273344651953, "grad_norm": 0.11470096433774883, "learning_rate": 6.132713204822838e-07, "loss": 0.05182819813489914, "step": 1128 }, { "epoch": 3.828522920203735, "grad_norm": 0.11878703323930974, "learning_rate": 5.903925530413135e-07, "loss": 0.045249901711940765, "step": 1129 }, { "epoch": 3.831918505942275, "grad_norm": 0.11907041635556147, "learning_rate": 5.679461618185944e-07, "loss": 0.03774178773164749, "step": 1130 }, { "epoch": 3.835314091680815, "grad_norm": 0.12336706394804925, "learning_rate": 5.459323432392083e-07, "loss": 0.03328479826450348, "step": 1131 }, { "epoch": 3.838709677419355, "grad_norm": 0.1160806742282941, "learning_rate": 5.243512899428316e-07, "loss": 0.02619325742125511, "step": 1132 }, { "epoch": 3.8421052631578947, "grad_norm": 0.11027917246820942, "learning_rate": 5.032031907821089e-07, "loss": 0.022279521450400352, "step": 1133 }, { "epoch": 3.8455008488964344, "grad_norm": 0.11461177622712578, "learning_rate": 4.824882308209433e-07, "loss": 0.019474327564239502, "step": 1134 }, { "epoch": 3.8488964346349746, "grad_norm": 0.1180260859714555, "learning_rate": 4.6220659133290325e-07, "loss": 0.020528195425868034, "step": 1135 }, { "epoch": 3.8522920203735147, "grad_norm": 0.10612453156530427, "learning_rate": 4.423584497996458e-07, "loss": 0.05578705295920372, "step": 1136 }, { "epoch": 3.8556876061120544, "grad_norm": 0.1231923820310272, "learning_rate": 4.2294397990932934e-07, "loss": 0.057648416608572006, "step": 1137 }, { "epoch": 3.859083191850594, "grad_norm": 0.11347216102539244, "learning_rate": 4.039633515551422e-07, "loss": 0.04376935213804245, "step": 1138 }, { "epoch": 3.8624787775891343, "grad_norm": 0.11639504754496335, "learning_rate": 3.854167308337708e-07, "loss": 0.0304638110101223, "step": 1139 }, { "epoch": 3.865874363327674, "grad_norm": 0.1209441483153, "learning_rate": 3.67304280043973e-07, "loss": 0.02716166153550148, "step": 1140 }, { "epoch": 3.869269949066214, "grad_norm": 0.1140763504782459, "learning_rate": 3.4962615768513453e-07, "loss": 0.024449681863188744, "step": 1141 }, { "epoch": 3.872665534804754, "grad_norm": 0.11899758443160374, "learning_rate": 3.323825184559204e-07, "loss": 0.02073652669787407, "step": 1142 }, { "epoch": 3.8760611205432935, "grad_norm": 0.10974740356424599, "learning_rate": 3.1557351325287586e-07, "loss": 0.018341438844799995, "step": 1143 }, { "epoch": 3.8794567062818337, "grad_norm": 0.11726580619428009, "learning_rate": 2.9919928916913866e-07, "loss": 0.0436985120177269, "step": 1144 }, { "epoch": 3.8828522920203734, "grad_norm": 0.123313421572953, "learning_rate": 2.8325998949314536e-07, "loss": 0.051345616579055786, "step": 1145 }, { "epoch": 3.8862478777589136, "grad_norm": 0.11622818489280884, "learning_rate": 2.677557537073605e-07, "loss": 0.0379648432135582, "step": 1146 }, { "epoch": 3.8896434634974533, "grad_norm": 0.1200354639919341, "learning_rate": 2.526867174870717e-07, "loss": 0.03789464011788368, "step": 1147 }, { "epoch": 3.893039049235993, "grad_norm": 0.11761234134661808, "learning_rate": 2.3805301269920755e-07, "loss": 0.02933451160788536, "step": 1148 }, { "epoch": 3.896434634974533, "grad_norm": 0.12001337404486198, "learning_rate": 2.238547674011715e-07, "loss": 0.03176940605044365, "step": 1149 }, { "epoch": 3.8998302207130733, "grad_norm": 0.11730418587708731, "learning_rate": 2.1009210583971539e-07, "loss": 0.022005751729011536, "step": 1150 }, { "epoch": 3.903225806451613, "grad_norm": 0.10482686441371745, "learning_rate": 1.9676514844987337e-07, "loss": 0.017670955508947372, "step": 1151 }, { "epoch": 3.9066213921901527, "grad_norm": 0.11916426863823935, "learning_rate": 1.8387401185389064e-07, "loss": 0.03608059883117676, "step": 1152 }, { "epoch": 3.910016977928693, "grad_norm": 0.1264118337520094, "learning_rate": 1.714188088602131e-07, "loss": 0.059039752930402756, "step": 1153 }, { "epoch": 3.9134125636672326, "grad_norm": 0.12046639145308118, "learning_rate": 1.5939964846249378e-07, "loss": 0.04311554878950119, "step": 1154 }, { "epoch": 3.9168081494057727, "grad_norm": 0.13023224278827858, "learning_rate": 1.4781663583863793e-07, "loss": 0.037847619503736496, "step": 1155 }, { "epoch": 3.9202037351443124, "grad_norm": 0.12024037788074168, "learning_rate": 1.366698723498816e-07, "loss": 0.030910184606909752, "step": 1156 }, { "epoch": 3.923599320882852, "grad_norm": 0.11827631847762965, "learning_rate": 1.2595945553992573e-07, "loss": 0.027429258450865746, "step": 1157 }, { "epoch": 3.9269949066213923, "grad_norm": 0.10894405713678468, "learning_rate": 1.1568547913404782e-07, "loss": 0.020332347601652145, "step": 1158 }, { "epoch": 3.930390492359932, "grad_norm": 0.11758489088984762, "learning_rate": 1.0584803303831381e-07, "loss": 0.020497240126132965, "step": 1159 }, { "epoch": 3.933786078098472, "grad_norm": 0.12156657768771842, "learning_rate": 9.6447203338762e-08, "loss": 0.021214282140135765, "step": 1160 }, { "epoch": 3.937181663837012, "grad_norm": 0.11513100215235729, "learning_rate": 8.748307230067588e-08, "loss": 0.05091562494635582, "step": 1161 }, { "epoch": 3.9405772495755516, "grad_norm": 0.12191536767216969, "learning_rate": 7.895571836785131e-08, "loss": 0.051850318908691406, "step": 1162 }, { "epoch": 3.9439728353140917, "grad_norm": 0.11927057452030111, "learning_rate": 7.086521616190279e-08, "loss": 0.04108232632279396, "step": 1163 }, { "epoch": 3.9473684210526314, "grad_norm": 0.11691517812872848, "learning_rate": 6.321163648163597e-08, "loss": 0.03384631127119064, "step": 1164 }, { "epoch": 3.9507640067911716, "grad_norm": 0.12264604014713913, "learning_rate": 5.599504630239838e-08, "loss": 0.02811538241803646, "step": 1165 }, { "epoch": 3.9541595925297113, "grad_norm": 0.11588908996483344, "learning_rate": 4.921550877550751e-08, "loss": 0.023320075124502182, "step": 1166 }, { "epoch": 3.9575551782682514, "grad_norm": 0.11718615285785076, "learning_rate": 4.287308322770689e-08, "loss": 0.021364962682127953, "step": 1167 }, { "epoch": 3.960950764006791, "grad_norm": 0.11778872009974493, "learning_rate": 3.696782516062758e-08, "loss": 0.01897425577044487, "step": 1168 }, { "epoch": 3.9643463497453313, "grad_norm": 0.12108377630412798, "learning_rate": 3.149978625032191e-08, "loss": 0.053909868001937866, "step": 1169 }, { "epoch": 3.967741935483871, "grad_norm": 0.1247896547460095, "learning_rate": 2.646901434678606e-08, "loss": 0.05216575413942337, "step": 1170 }, { "epoch": 3.9711375212224107, "grad_norm": 0.12185441425480861, "learning_rate": 2.1875553473565956e-08, "loss": 0.03817559406161308, "step": 1171 }, { "epoch": 3.974533106960951, "grad_norm": 0.1205508164200239, "learning_rate": 1.7719443827368677e-08, "loss": 0.034068889915943146, "step": 1172 }, { "epoch": 3.9779286926994906, "grad_norm": 0.11267208964845564, "learning_rate": 1.400072177770162e-08, "loss": 0.026269059628248215, "step": 1173 }, { "epoch": 3.9813242784380307, "grad_norm": 0.11606345156074832, "learning_rate": 1.0719419866550561e-08, "loss": 0.024427037686109543, "step": 1174 }, { "epoch": 3.9847198641765704, "grad_norm": 0.11168332957903386, "learning_rate": 7.875566808107637e-09, "loss": 0.02031281217932701, "step": 1175 }, { "epoch": 3.98811544991511, "grad_norm": 0.11000052547467654, "learning_rate": 5.469187488510441e-09, "loss": 0.017734386026859283, "step": 1176 }, { "epoch": 3.9915110356536503, "grad_norm": 0.14105441067042632, "learning_rate": 3.500302965636637e-09, "loss": 0.044810157269239426, "step": 1177 }, { "epoch": 3.99490662139219, "grad_norm": 0.12164065848808187, "learning_rate": 1.9689304688985664e-09, "loss": 0.03988499939441681, "step": 1178 }, { "epoch": 3.99830220713073, "grad_norm": 0.11603499192496389, "learning_rate": 8.750833991155727e-10, "loss": 0.02562321349978447, "step": 1179 }, { "epoch": 4.0, "grad_norm": 0.1633640081758102, "learning_rate": 2.1877132838632463e-10, "loss": 0.020940586924552917, "step": 1180 }, { "epoch": 4.0, "step": 1180, "total_flos": 7.881538624284525e+18, "train_loss": 0.13219511501680492, "train_runtime": 266794.0573, "train_samples_per_second": 0.212, "train_steps_per_second": 0.004 } ], "logging_steps": 1, "max_steps": 1180, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7.881538624284525e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }