{ "model_dir": "models/openllama-3b", "distribution_id": "code_hard", "timestamp": "2023-10-20 01:20:54", "eval_loss": 0.6877474188804626, "eval_score": -0.24786555767059326, "eval_brier_score": 0.24786556860993772, "eval_average_probability": 0.5027546538511912, "eval_accuracy": 0.7186666666666667, "eval_probabilities": [ 0.5009541511535645, 0.4991297423839569, 0.4983240067958832, 0.5087032914161682, 0.49204862117767334, 0.49780744314193726, 0.5127522945404053, 0.537738025188446, 0.5129897594451904, 0.4946988523006439, 0.5210273265838623, 0.5165740251541138, 0.5326241254806519, 0.5320203900337219, 0.538191020488739, 0.5105686187744141, 0.49722591042518616, 0.500602662563324, 0.5088046789169312, 0.5222324132919312, 0.5222846865653992, 0.5215458869934082, 0.5273125171661377, 0.5239026546478271, 0.5180680155754089, 0.5171548128128052, 0.5182163715362549, 0.4816742539405823, 0.5175365805625916, 0.5185783505439758, 0.5064588785171509, 0.5059816241264343, 0.5055780410766602, 0.5049747228622437, 0.49865880608558655, 0.4988449215888977, 0.4645281732082367, 0.4676106572151184, 0.46278098225593567, 0.5043057203292847, 0.4943769574165344, 0.5004122853279114, 0.5273630619049072, 0.5257828235626221, 0.5250824093818665, 0.502755880355835, 0.5008992552757263, 0.5022150278091431, 0.497560054063797, 0.4999421536922455, 0.49749240279197693, 0.49787765741348267, 0.5040478706359863, 0.5004732012748718, 0.4814645051956177, 0.48159298300743103, 0.4803681969642639, 0.5009512901306152, 0.5041300058364868, 0.5024775266647339, 0.49850431084632874, 0.4990447163581848, 0.49794888496398926, 0.5074923038482666, 0.5016791820526123, 0.5057981610298157, 0.5112265944480896, 0.5133332014083862, 0.5052410960197449, 0.49512067437171936, 0.5103120803833008, 0.5034862160682678, 0.5173513293266296, 0.5241010189056396, 0.5216107368469238, 0.518986701965332, 0.5227066874504089, 0.5179375410079956, 0.5005595088005066, 0.5019857883453369, 0.5024380683898926, 0.509884238243103, 0.4989665448665619, 0.504818320274353, 0.5274378061294556, 0.5390399694442749, 0.5003756880760193, 0.49900031089782715, 0.5013948082923889, 0.5027642846107483, 0.5306578278541565, 0.53801029920578, 0.539126992225647, 0.4130994379520416, 0.41323211789131165, 0.413695365190506, 0.5053542256355286, 0.5053405165672302, 0.510122537612915, 0.5124260187149048, 0.49997439980506897, 0.49353447556495667, 0.4579092264175415, 0.45309770107269287, 0.457597017288208, 0.4992327094078064, 0.500151515007019, 0.49872878193855286, 0.5009836554527283, 0.5073531866073608, 0.50246661901474, 0.499522864818573, 0.5053948760032654, 0.5025132894515991, 0.498482882976532, 0.5021127462387085, 0.4961938261985779, 0.5284340977668762, 0.50554358959198, 0.5309867262840271, 0.5147180557250977, 0.5139132738113403, 0.515818178653717, 0.5150627493858337, 0.5176246762275696, 0.5144700407981873, 0.5147340893745422, 0.5224024057388306, 0.5248688459396362, 0.5149508118629456, 0.5184158682823181, 0.5285097360610962, 0.506483793258667, 0.5043370723724365, 0.5037827491760254, 0.49520227313041687, 0.4938935339450836, 0.4985451400279999, 0.4107288420200348, 0.4104059040546417, 0.41457319259643555, 0.5061694979667664, 0.50319904088974, 0.5005083680152893, 0.48186200857162476, 0.5035342574119568, 0.5004662871360779, 0.48729023337364197, 0.49482864141464233, 0.49021971225738525, 0.4230315387248993, 0.41954752802848816, 0.4286539852619171, 0.47959592938423157, 0.4741314649581909, 0.47467702627182007, 0.5192230939865112, 0.49911385774612427, 0.5170983076095581, 0.5246425867080688, 0.5104341506958008, 0.5108966827392578, 0.5005435943603516, 0.5069341063499451, 0.5085194706916809, 0.5048575401306152, 0.4997410178184509, 0.49683666229248047, 0.508003294467926, 0.5046340823173523, 0.5024315714836121, 0.4978286027908325, 0.5022167563438416, 0.5030627846717834, 0.4257031977176666, 0.4121972322463989, 0.42864999175071716, 0.5178281664848328, 0.5096238255500793, 0.49875542521476746, 0.5147284269332886, 0.5107414126396179, 0.5120668411254883, 0.49172186851501465, 0.4980837106704712, 0.5003341436386108, 0.4987697899341583, 0.5017468929290771, 0.5005198121070862, 0.5160881280899048, 0.5064770579338074, 0.5091634392738342, 0.501404345035553, 0.5005557537078857, 0.4995492994785309, 0.5156750082969666, 0.5013359785079956, 0.5037763118743896, 0.37886151671409607, 0.36857813596725464, 0.3738362193107605, 0.5422244668006897, 0.5702081322669983, 0.5897537469863892, 0.4989883601665497, 0.5039159655570984, 0.5019713044166565, 0.5147560238838196, 0.5157040357589722, 0.5080110430717468, 0.5076059699058533, 0.49975988268852234, 0.515874981880188, 0.4981813430786133, 0.5011470317840576, 0.5004943013191223, 0.5075818300247192, 0.5054045915603638, 0.50248783826828, 0.5244343280792236, 0.5255465507507324, 0.5256333351135254, 0.5008946657180786, 0.5051144361495972, 0.5134977698326111, 0.5037509799003601, 0.5007672309875488, 0.5059165358543396, 0.499546617269516, 0.4942046105861664, 0.4979848265647888, 0.5107523798942566, 0.5023475289344788, 0.5036648511886597, 0.5099871158599854, 0.5070180892944336, 0.5080859661102295, 0.4867812693119049, 0.4800567030906677, 0.48355263471603394, 0.501395583152771, 0.5036728978157043, 0.5023757219314575, 0.527726411819458, 0.5322823524475098, 0.5392914414405823, 0.5001704692840576, 0.5018320679664612, 0.5045567154884338, 0.5272818803787231, 0.5267221331596375, 0.522538423538208, 0.49949419498443604, 0.5005879402160645, 0.5038205981254578, 0.5007840394973755, 0.507729172706604, 0.5102759599685669, 0.502423882484436, 0.5064696669578552, 0.5019562840461731, 0.5233514904975891, 0.5232648253440857, 0.5319072604179382, 0.5009849071502686, 0.5034413933753967, 0.49993541836738586, 0.5297547578811646, 0.5304645299911499, 0.5332890748977661, 0.5135123133659363, 0.5201650261878967, 0.5182808041572571, 0.5025556683540344, 0.5095629692077637, 0.5061773061752319, 0.484458327293396, 0.5061435103416443, 0.5007451176643372, 0.5125772953033447, 0.5143836736679077, 0.5111652612686157, 0.5188631415367126, 0.5230873823165894, 0.5215491056442261, 0.528350830078125, 0.5358057618141174, 0.522598922252655, 0.4979894161224365, 0.49755680561065674, 0.4980669915676117, 0.4999699890613556, 0.5021787285804749, 0.5019017457962036, 0.5020527839660645, 0.4953957200050354, 0.5045327544212341, 0.5062636137008667, 0.49943286180496216, 0.5024356245994568, 0.5258026719093323, 0.5214945077896118, 0.5143948793411255, 0.5107553005218506, 0.5204503536224365, 0.5153393149375916, 0.5233345627784729, 0.5317865014076233, 0.5349575877189636, 0.5015318393707275, 0.5038819313049316, 0.5002246499061584, 0.5242816805839539, 0.5016770958900452, 0.5029898881912231, 0.5158433318138123, 0.5075637102127075, 0.5038635730743408, 0.4365612864494324, 0.4955875873565674, 0.5003886818885803, 0.5037612915039062, 0.5045397281646729, 0.5032064318656921, 0.5046544075012207, 0.5081546902656555, 0.506134569644928, 0.5346421003341675, 0.5159380435943604, 0.5262466669082642, 0.5019809603691101, 0.5080664753913879, 0.5009700059890747, 0.49661320447921753, 0.5048591494560242, 0.4994228184223175, 0.5004201531410217, 0.5004626512527466, 0.5004665851593018, 0.501192569732666, 0.5028157234191895, 0.5030494332313538, 0.5004416108131409, 0.5107994079589844, 0.5085605382919312, 0.4587014615535736, 0.45772749185562134, 0.4584256708621979, 0.5571109056472778, 0.5273408889770508, 0.527249276638031, 0.5180985331535339, 0.5105831027030945, 0.504063069820404, 0.5015424489974976, 0.5016186833381653, 0.5038890838623047, 0.5246437788009644, 0.5165879130363464, 0.5226777195930481, 0.5034899115562439, 0.49908989667892456, 0.5071726441383362, 0.502647876739502, 0.4989399015903473, 0.5035512447357178, 0.5127728581428528, 0.5077216029167175, 0.5082169771194458, 0.5193491578102112, 0.4990854561328888, 0.4990854561328888, 0.4908117353916168, 0.5026227831840515, 0.4980575144290924, 0.5041861534118652, 0.5024716258049011, 0.5029170513153076, 0.4921966791152954, 0.49953576922416687, 0.5005469918251038, 0.4507313072681427, 0.46941184997558594, 0.4645062983036041, 0.4951478838920593, 0.5046601295471191, 0.5020456910133362, 0.4997764825820923, 0.49987688660621643, 0.5016835927963257, 0.5057981610298157, 0.5063574314117432, 0.519572913646698, 0.5044342875480652, 0.5007914900779724, 0.504147469997406, 0.5051930546760559, 0.505500078201294, 0.49819451570510864, 0.5145785212516785, 0.5204763412475586, 0.5201772451400757, 0.5367105007171631, 0.5328570008277893, 0.5328800678253174, 0.529439389705658, 0.5339477062225342, 0.5322490334510803, 0.518363356590271, 0.5167111158370972, 0.5258252620697021, 0.5061048269271851, 0.5106028318405151, 0.5106737017631531, 0.5381652116775513, 0.5413077473640442, 0.5393857359886169, 0.4660997688770294, 0.4182272255420685, 0.45618513226509094, 0.5268338322639465, 0.5262309312820435, 0.5247222185134888, 0.4882727265357971, 0.5023645758628845, 0.4986720681190491, 0.42487382888793945, 0.42970842123031616, 0.4242590069770813, 0.5217719078063965, 0.5224560499191284, 0.5361471772193909, 0.5203791260719299, 0.5143694281578064, 0.5148425102233887, 0.505043625831604, 0.5138986110687256, 0.5416344404220581, 0.459038108587265, 0.46910107135772705, 0.4678616225719452, 0.5347440838813782, 0.5320515036582947, 0.5359301567077637, 0.5001460909843445, 0.4999200999736786, 0.5026781558990479, 0.4968556761741638, 0.5028875470161438, 0.5076910853385925, 0.5158545970916748, 0.5019733905792236, 0.49886375665664673, 0.5047823786735535, 0.5056302547454834, 0.5027822256088257, 0.5092668533325195, 0.5013504028320312, 0.5037813186645508, 0.5069150328636169, 0.5066774487495422, 0.5105799436569214, 0.5007753372192383, 0.5042945146560669, 0.5063353776931763, 0.5139327049255371, 0.5321759581565857, 0.5229036808013916, 0.49655574560165405, 0.4956997036933899, 0.49840429425239563, 0.5031301975250244, 0.50094074010849, 0.5014841556549072, 0.46834608912467957, 0.4612736999988556, 0.4592016041278839, 0.49960604310035706, 0.5014097094535828, 0.5008105039596558, 0.49892541766166687, 0.497993528842926, 0.5023998022079468, 0.49590054154396057, 0.4897083044052124, 0.49919137358665466, 0.5505585670471191, 0.5312770009040833, 0.5408290028572083, 0.503551185131073, 0.5023664832115173, 0.50800621509552, 0.49993959069252014, 0.49993959069252014, 0.4999386966228485, 0.5162038207054138, 0.5220046043395996, 0.5230036377906799, 0.49507734179496765, 0.494942307472229, 0.4916694760322571, 0.49950525164604187, 0.5078713893890381, 0.5082727074623108, 0.4962415397167206, 0.5, 0.5024387240409851, 0.39882469177246094, 0.4009437561035156, 0.40178948640823364, 0.4820476770401001, 0.47829508781433105, 0.47408002614974976, 0.4909660518169403, 0.4974615275859833, 0.4956236183643341, 0.5238876342773438, 0.5142295360565186, 0.512324869632721, 0.5047900676727295, 0.4915965795516968, 0.49543333053588867, 0.4848581850528717, 0.4848581850528717, 0.4873354732990265, 0.5037482976913452, 0.5028479695320129, 0.49165451526641846, 0.5119800567626953, 0.5181000232696533, 0.5111053586006165, 0.4936477839946747, 0.4972204864025116, 0.5018909573554993, 0.5, 0.5028125643730164, 0.504949152469635, 0.5071046352386475, 0.5094790458679199, 0.509076714515686, 0.5264836549758911, 0.5239436030387878, 0.5120601058006287, 0.5225600004196167, 0.5257136225700378, 0.5311734676361084, 0.49918535351753235, 0.5001807808876038, 0.5031403303146362, 0.4855404496192932, 0.507258951663971, 0.49724483489990234, 0.5, 0.5136678814888, 0.5091027617454529, 0.4983045756816864, 0.497130811214447, 0.4936565160751343, 0.5098475217819214, 0.5071225166320801, 0.5050577521324158, 0.5229678153991699, 0.5265181660652161, 0.5259150266647339, 0.5057901740074158, 0.5061373114585876, 0.507921040058136, 0.4937571883201599, 0.4902033805847168, 0.55033940076828, 0.5232491493225098, 0.531272828578949, 0.522799551486969, 0.501308798789978, 0.5111252665519714, 0.516834020614624, 0.5025580525398254, 0.5028321743011475, 0.5016791224479675, 0.5116210579872131, 0.5112370848655701, 0.5029230117797852, 0.5229653716087341, 0.5095295906066895, 0.51495361328125, 0.5020527839660645, 0.5015379190444946, 0.5015674829483032, 0.482572078704834, 0.48323363065719604, 0.4817308187484741, 0.5031677484512329, 0.5068406462669373, 0.5013048052787781, 0.5000906586647034, 0.5064936280250549, 0.5075532793998718, 0.5281783938407898, 0.5255563855171204, 0.5231887102127075, 0.5028682947158813, 0.49438056349754333, 0.503026008605957, 0.5054842233657837, 0.5042405724525452, 0.5063852667808533, 0.5072040557861328, 0.5006740093231201, 0.503508448600769, 0.5047541260719299, 0.5162956714630127, 0.5036306381225586, 0.49859312176704407, 0.49943405389785767, 0.5004180073738098, 0.502506673336029, 0.502631425857544, 0.5022781491279602, 0.5017004013061523, 0.5046606659889221, 0.5034868717193604, 0.500732421875, 0.4993216097354889, 0.5012392401695251, 0.526041567325592, 0.5280998349189758, 0.5208909511566162, 0.4735313951969147, 0.5022531747817993, 0.5046836733818054, 0.5034245848655701, 0.5038003325462341, 0.5081883072853088, 0.5022950768470764, 0.5011173486709595, 0.5049695372581482, 0.498090535402298, 0.5038131475448608, 0.5084542632102966, 0.49966883659362793, 0.4991714656352997, 0.4992195665836334, 0.497189998626709, 0.5304344296455383, 0.5147782564163208, 0.4982161819934845, 0.5034466981887817, 0.5005354881286621, 0.49964529275894165, 0.4953494369983673, 0.4873664975166321, 0.5059751868247986, 0.5076417922973633, 0.5062074661254883, 0.4335992932319641, 0.43009260296821594, 0.43447551131248474, 0.5442053079605103, 0.5542563796043396, 0.5477290749549866, 0.510228157043457, 0.5035006999969482, 0.5023659467697144, 0.5197411775588989, 0.5173681378364563, 0.5146010518074036, 0.5027673840522766, 0.49884191155433655, 0.502178966999054, 0.5041917562484741, 0.502571165561676, 0.503524661064148, 0.5050333738327026, 0.5037442445755005, 0.5035388469696045, 0.499571830034256, 0.5013175010681152, 0.5023362040519714, 0.5000914335250854, 0.5011729598045349, 0.5011788010597229, 0.5191941857337952, 0.5197611451148987, 0.5191386342048645, 0.4999289810657501, 0.5038092732429504, 0.5040368437767029, 0.5236762166023254, 0.5101822018623352, 0.5058136582374573, 0.5094401240348816, 0.5053980946540833, 0.5058819651603699, 0.4947691559791565, 0.4953126609325409, 0.4969939589500427, 0.5340363383293152, 0.5448473691940308, 0.5440835356712341, 0.5091491341590881, 0.49445435404777527, 0.4987610876560211, 0.5212538838386536, 0.5199126601219177, 0.5200256705284119, 0.5023741722106934, 0.5029817819595337, 0.503196120262146, 0.5189456939697266, 0.5004532933235168, 0.519112229347229, 0.5039882063865662, 0.5127840638160706, 0.5045323967933655, 0.5000935196876526, 0.5040934085845947, 0.5084739327430725, 0.5046032667160034, 0.5038072466850281, 0.5069986581802368, 0.5188038349151611, 0.5276033282279968, 0.5202265381813049, 0.505096435546875, 0.5096435546875, 0.49902263283729553, 0.3428906798362732, 0.3589918613433838, 0.3601532578468323, 0.5052120685577393, 0.49895596504211426, 0.4957111179828644, 0.5006155371665955, 0.5015630722045898, 0.5041406154632568, 0.5005367398262024, 0.4999784231185913, 0.5002249479293823, 0.4723547697067261, 0.47603368759155273, 0.4988456964492798, 0.49953755736351013, 0.5, 0.5002236366271973, 0.5037704706192017, 0.5022208094596863, 0.5012670755386353, 0.47026702761650085, 0.47416388988494873, 0.4698916971683502 ], "eval_runtime": 69.9282, "eval_samples_per_second": 10.725, "eval_steps_per_second": 0.343, "eval_rms_calibration_error": 0.0005820668041037758 }