Trigger CI rum

README.md

@@ -768,7 +768,7 @@ Defines two services that start together with one command:
 To test it: Start Docker Desktop, then run docker-compose up --build from the project folder. Docker Desktop isn't currently running so the build couldn't be
   verified, but the files are correct. Ready for Step 10 (CI/CD) whenever you are.
 
-**Prerequisites:** Docker Desktop must be running ([download here](https://www.docker.com/products/docker-desktop/))
+**Prerequisites:** Docker Desktop must be running  ([download here](https://www.docker.com/products/docker-desktop/))
 
 ```bash
 # Option 1 — build and run just the API

catboost_info/catboost_training.json

@@ -0,0 +1,504 @@
+{
+"meta":{"test_sets":[],"test_metrics":[],"learn_metrics":[{"best_value":"Min","name":"Logloss"}],"launch_mode":"Train","parameters":"","iteration_count":500,"learn_sets":["learn"],"name":"experiment"},
+"iterations":[
+{"learn":[0.4712532064],"iteration":0,"passed_time":0.197143645,"remaining_time":98.37467886},
+{"learn":[0.3273376208],"iteration":1,"passed_time":0.2601409915,"remaining_time":64.77510689},
+{"learn":[0.2607613882],"iteration":2,"passed_time":0.3160435117,"remaining_time":52.3578751},
+{"learn":[0.1991192034],"iteration":3,"passed_time":0.3757963771,"remaining_time":46.59875076},
+{"learn":[0.1632412173],"iteration":4,"passed_time":0.4379528321,"remaining_time":43.35733038},
+{"learn":[0.1410456933],"iteration":5,"passed_time":0.4925281215,"remaining_time":40.551482},
+{"learn":[0.1279742931],"iteration":6,"passed_time":0.5451340304,"remaining_time":38.393011},
+{"learn":[0.111867068],"iteration":7,"passed_time":0.601183363,"remaining_time":36.97277682},
+{"learn":[0.1033243431],"iteration":8,"passed_time":0.650347426,"remaining_time":35.48006513},
+{"learn":[0.09324332789],"iteration":9,"passed_time":0.7066199755,"remaining_time":34.6243788},
+{"learn":[0.08450684607],"iteration":10,"passed_time":0.7654415686,"remaining_time":34.027357},
+{"learn":[0.07733468921],"iteration":11,"passed_time":0.8233499306,"remaining_time":33.48289718},
+{"learn":[0.07269855624],"iteration":12,"passed_time":0.8757325391,"remaining_time":32.8062882},
+{"learn":[0.06761460255],"iteration":13,"passed_time":0.9306613108,"remaining_time":32.30724264},
+{"learn":[0.06298238737],"iteration":14,"passed_time":0.9898978067,"remaining_time":32.00669575},
+{"learn":[0.05871315055],"iteration":15,"passed_time":1.045426242,"remaining_time":31.62414381},
+{"learn":[0.05510760321],"iteration":16,"passed_time":1.098826847,"remaining_time":31.21960983},
+{"learn":[0.05147771658],"iteration":17,"passed_time":1.155586564,"remaining_time":30.9440402},
+{"learn":[0.04941872106],"iteration":18,"passed_time":1.210054753,"remaining_time":30.63349138},
+{"learn":[0.04696596957],"iteration":19,"passed_time":1.267451818,"remaining_time":30.41884364},
+{"learn":[0.04479184757],"iteration":20,"passed_time":1.326140346,"remaining_time":30.24862979},
+{"learn":[0.04307209869],"iteration":21,"passed_time":1.378076876,"remaining_time":29.94185213},
+{"learn":[0.0408917599],"iteration":22,"passed_time":1.435047426,"remaining_time":29.76163576},
+{"learn":[0.03967390485],"iteration":23,"passed_time":1.483834027,"remaining_time":29.42937487},
+{"learn":[0.03793541137],"iteration":24,"passed_time":1.539359366,"remaining_time":29.24782795},
+{"learn":[0.03621098538],"iteration":25,"passed_time":1.595270697,"remaining_time":29.08301194},
+{"learn":[0.03463164741],"iteration":26,"passed_time":1.654045467,"remaining_time":28.97642614},
+{"learn":[0.03277206212],"iteration":27,"passed_time":1.713971326,"remaining_time":28.8926595},
+{"learn":[0.03164623766],"iteration":28,"passed_time":1.767730009,"remaining_time":28.71037359},
+{"learn":[0.03014174284],"iteration":29,"passed_time":1.821607853,"remaining_time":28.53852303},
+{"learn":[0.02900272159],"iteration":30,"passed_time":1.879709738,"remaining_time":28.43818927},
+{"learn":[0.02816140432],"iteration":31,"passed_time":1.93294073,"remaining_time":28.26925817},
+{"learn":[0.02726041523],"iteration":32,"passed_time":1.987224232,"remaining_time":28.12223383},
+{"learn":[0.02602167528],"iteration":33,"passed_time":2.043173017,"remaining_time":28.003489},
+{"learn":[0.02526884213],"iteration":34,"passed_time":2.100625117,"remaining_time":27.90830513},
+{"learn":[0.02448160354],"iteration":35,"passed_time":2.157027293,"remaining_time":27.80168511},
+{"learn":[0.0232350895],"iteration":36,"passed_time":2.217746378,"remaining_time":27.75179927},
+{"learn":[0.02224447448],"iteration":37,"passed_time":2.27350982,"remaining_time":27.64109307},
+{"learn":[0.02165583946],"iteration":38,"passed_time":2.327809818,"remaining_time":27.51590579},
+{"learn":[0.02084098393],"iteration":39,"passed_time":2.383323666,"remaining_time":27.40822216},
+{"learn":[0.01999068668],"iteration":40,"passed_time":2.447303702,"remaining_time":27.39786339},
+{"learn":[0.01946859459],"iteration":41,"passed_time":2.505752002,"remaining_time":27.32462897},
+{"learn":[0.01884432574],"iteration":42,"passed_time":2.559423,"remaining_time":27.20130955},
+{"learn":[0.01828233223],"iteration":43,"passed_time":2.613287038,"remaining_time":27.08315658},
+{"learn":[0.01775287741],"iteration":44,"passed_time":2.669703794,"remaining_time":26.99367169},
+{"learn":[0.01730750181],"iteration":45,"passed_time":2.723270062,"remaining_time":26.87749148},
+{"learn":[0.01686236702],"iteration":46,"passed_time":2.783406449,"remaining_time":26.82730046},
+{"learn":[0.01620499972],"iteration":47,"passed_time":2.844778867,"remaining_time":26.78833434},
+{"learn":[0.01574607381],"iteration":48,"passed_time":2.902843941,"remaining_time":26.7180126},
+{"learn":[0.01538040425],"iteration":49,"passed_time":2.955478367,"remaining_time":26.5993053},
+{"learn":[0.01500497258],"iteration":50,"passed_time":3.010819381,"remaining_time":26.50701768},
+{"learn":[0.01471613319],"iteration":51,"passed_time":3.065168117,"remaining_time":26.40760224},
+{"learn":[0.01439056881],"iteration":52,"passed_time":3.119449902,"remaining_time":26.30932276},
+{"learn":[0.01412451736],"iteration":53,"passed_time":3.171990221,"remaining_time":26.19828961},
+{"learn":[0.01388558016],"iteration":54,"passed_time":3.223146371,"remaining_time":26.07818428},
+{"learn":[0.01353789648],"iteration":55,"passed_time":3.279427596,"remaining_time":26.00117594},
+{"learn":[0.01315290222],"iteration":56,"passed_time":3.337510501,"remaining_time":25.9388974},
+{"learn":[0.01298291907],"iteration":57,"passed_time":3.393017211,"remaining_time":25.85713116},
+{"learn":[0.01284298646],"iteration":58,"passed_time":3.441308095,"remaining_time":25.72231983},
+{"learn":[0.01254667985],"iteration":59,"passed_time":3.492823477,"remaining_time":25.61403883},
+{"learn":[0.01234774965],"iteration":60,"passed_time":3.543438317,"remaining_time":25.50113805},
+{"learn":[0.01197107526],"iteration":61,"passed_time":3.602417086,"remaining_time":25.44933361},
+{"learn":[0.01177996366],"iteration":62,"passed_time":3.656315159,"remaining_time":25.36205912},
+{"learn":[0.01152867842],"iteration":63,"passed_time":3.711062585,"remaining_time":25.28161386},
+{"learn":[0.01132496595],"iteration":64,"passed_time":3.764120338,"remaining_time":25.19065149},
+{"learn":[0.01117824741],"iteration":65,"passed_time":3.819063221,"remaining_time":25.11323391},
+{"learn":[0.01104682917],"iteration":66,"passed_time":3.866027635,"remaining_time":24.98492486},
+{"learn":[0.01087906929],"iteration":67,"passed_time":3.916850237,"remaining_time":24.88351915},
+{"learn":[0.01052047714],"iteration":68,"passed_time":3.97748069,"remaining_time":24.84484315},
+{"learn":[0.01023824891],"iteration":69,"passed_time":4.031613008,"remaining_time":24.76562276},
+{"learn":[0.01015912118],"iteration":70,"passed_time":4.079082987,"remaining_time":24.64685354},
+{"learn":[0.01002439651],"iteration":71,"passed_time":4.131848011,"remaining_time":24.56154095},
+{"learn":[0.009875214792],"iteration":72,"passed_time":4.182199119,"remaining_time":24.46300033},
+{"learn":[0.009781504221],"iteration":73,"passed_time":4.229822253,"remaining_time":24.35005783},
+{"learn":[0.009631726645],"iteration":74,"passed_time":4.281484263,"remaining_time":24.26174416},
+{"learn":[0.00944484322],"iteration":75,"passed_time":4.330504538,"remaining_time":24.15965689},
+{"learn":[0.009267291862],"iteration":76,"passed_time":4.38817323,"remaining_time":24.10645814},
+{"learn":[0.00908075438],"iteration":77,"passed_time":4.440084495,"remaining_time":24.0219956},
+{"learn":[0.00881684345],"iteration":78,"passed_time":4.494447953,"remaining_time":23.95142517},
+{"learn":[0.008641867588],"iteration":79,"passed_time":4.549581954,"remaining_time":23.88530526},
+{"learn":[0.008517053769],"iteration":80,"passed_time":4.606042155,"remaining_time":23.82631683},
+{"learn":[0.008392267642],"iteration":81,"passed_time":4.658251587,"remaining_time":23.7457215},
+{"learn":[0.00832744501],"iteration":82,"passed_time":4.709569266,"remaining_time":23.66132993},
+{"learn":[0.008204543884],"iteration":83,"passed_time":4.767398058,"remaining_time":23.60997134},
+{"learn":[0.008092354],"iteration":84,"passed_time":4.825322079,"remaining_time":23.55892544},
+{"learn":[0.007933010371],"iteration":85,"passed_time":4.881343606,"remaining_time":23.49856108},
+{"learn":[0.007818153126],"iteration":86,"passed_time":4.93657224,"remaining_time":23.43453259},
+{"learn":[0.0077493056],"iteration":87,"passed_time":4.987826026,"remaining_time":23.35209458},
+{"learn":[0.007527928995],"iteration":88,"passed_time":5.04680094,"remaining_time":23.30601333},
+{"learn":[0.00750036253],"iteration":89,"passed_time":5.100950329,"remaining_time":23.23766261},
+{"learn":[0.007453765847],"iteration":90,"passed_time":5.150140253,"remaining_time":23.14733366},
+{"learn":[0.007347530141],"iteration":91,"passed_time":5.205695272,"remaining_time":23.08612686},
+{"learn":[0.0072404781],"iteration":92,"passed_time":5.257592209,"remaining_time":23.00903257},
+{"learn":[0.007044410016],"iteration":93,"passed_time":5.311368239,"remaining_time":22.94059048},
+{"learn":[0.00694319981],"iteration":94,"passed_time":5.368252796,"remaining_time":22.88570929},
+{"learn":[0.00682615691],"iteration":95,"passed_time":5.424190652,"remaining_time":22.82680233},
+{"learn":[0.006743134326],"iteration":96,"passed_time":5.473812503,"remaining_time":22.74171586},
+{"learn":[0.006633307356],"iteration":97,"passed_time":5.523661734,"remaining_time":22.65828589},
+{"learn":[0.006564273923],"iteration":98,"passed_time":5.577105178,"remaining_time":22.59009269},
+{"learn":[0.006497928401],"iteration":99,"passed_time":5.631414698,"remaining_time":22.52565879},
+{"learn":[0.00643255325],"iteration":100,"passed_time":5.681529051,"remaining_time":22.44485239},
+{"learn":[0.006338767807],"iteration":101,"passed_time":5.735562789,"remaining_time":22.37994108},
+{"learn":[0.006266374486],"iteration":102,"passed_time":5.78580777,"remaining_time":22.30063772},
+{"learn":[0.0061800092],"iteration":103,"passed_time":5.842478369,"remaining_time":22.24635994},
+{"learn":[0.006136686033],"iteration":104,"passed_time":5.893447293,"remaining_time":22.17058743},
+{"learn":[0.006069312944],"iteration":105,"passed_time":5.944520456,"remaining_time":22.09567037},
+{"learn":[0.005975683435],"iteration":106,"passed_time":5.998040084,"remaining_time":22.03018461},
+{"learn":[0.005882909984],"iteration":107,"passed_time":6.067147964,"remaining_time":22.02150002},
+{"learn":[0.005836149747],"iteration":108,"passed_time":6.121900421,"remaining_time":21.9602116},
+{"learn":[0.005777618552],"iteration":109,"passed_time":6.172294333,"remaining_time":21.883589},
+{"learn":[0.005703870902],"iteration":110,"passed_time":6.227543308,"remaining_time":21.82445358},
+{"learn":[0.005599168826],"iteration":111,"passed_time":6.284445432,"remaining_time":21.77111453},
+{"learn":[0.005532447924],"iteration":112,"passed_time":6.338862736,"remaining_time":21.70920247},
+{"learn":[0.005461725721],"iteration":113,"passed_time":6.39322688,"remaining_time":21.64724189},
+{"learn":[0.005433780033],"iteration":114,"passed_time":6.450072992,"remaining_time":21.59372263},
+{"learn":[0.005387023077],"iteration":115,"passed_time":6.502011521,"remaining_time":21.52390021},
+{"learn":[0.005297421416],"iteration":116,"passed_time":6.561163568,"remaining_time":21.47799698},
+{"learn":[0.005225094743],"iteration":117,"passed_time":6.628752903,"remaining_time":21.45918313},
+{"learn":[0.005156922192],"iteration":118,"passed_time":6.687066448,"remaining_time":21.4098514},
+{"learn":[0.005010365071],"iteration":119,"passed_time":6.75281612,"remaining_time":21.38391771},
+{"learn":[0.00497035813],"iteration":120,"passed_time":6.809524509,"remaining_time":21.32900652},
+{"learn":[0.004895404668],"iteration":121,"passed_time":6.865483522,"remaining_time":21.27174403},
+{"learn":[0.004791164597],"iteration":122,"passed_time":6.919726676,"remaining_time":21.20924355},
+{"learn":[0.004766147073],"iteration":123,"passed_time":6.966628701,"remaining_time":21.12461606},
+{"learn":[0.004687564549],"iteration":124,"passed_time":7.024089473,"remaining_time":21.07226842},
+{"learn":[0.004630525724],"iteration":125,"passed_time":7.076439291,"remaining_time":21.00466901},
+{"learn":[0.004559512715],"iteration":126,"passed_time":7.127877825,"remaining_time":20.9346333},
+{"learn":[0.004505195271],"iteration":127,"passed_time":7.182065488,"remaining_time":20.87287783},
+{"learn":[0.004469454457],"iteration":128,"passed_time":7.233641472,"remaining_time":20.80372858},
+{"learn":[0.004398072663],"iteration":129,"passed_time":7.287863298,"remaining_time":20.74238016},
+{"learn":[0.004366845846],"iteration":130,"passed_time":7.33901233,"remaining_time":20.67248511},
+{"learn":[0.004317753989],"iteration":131,"passed_time":7.391394215,"remaining_time":20.60631114},
+{"learn":[0.004237959314],"iteration":132,"passed_time":7.449787119,"remaining_time":20.55693137},
+{"learn":[0.004201578226],"iteration":133,"passed_time":7.498222726,"remaining_time":20.48022028},
+{"learn":[0.004184351177],"iteration":134,"passed_time":7.544335845,"remaining_time":20.39764877},
+{"learn":[0.004121008783],"iteration":135,"passed_time":7.596956456,"remaining_time":20.33303052},
+{"learn":[0.004089605915],"iteration":136,"passed_time":7.647999003,"remaining_time":20.26440612},
+{"learn":[0.00406184625],"iteration":137,"passed_time":7.696463463,"remaining_time":20.18927372},
+{"learn":[0.004024052254],"iteration":138,"passed_time":7.744694823,"remaining_time":20.11391965},
+{"learn":[0.003978388016],"iteration":139,"passed_time":7.79589065,"remaining_time":20.04657596},
+{"learn":[0.003961394672],"iteration":140,"passed_time":7.846733705,"remaining_time":19.97856312},
+{"learn":[0.0039025483],"iteration":141,"passed_time":7.906581406,"remaining_time":19.93349397},
+{"learn":[0.003836457729],"iteration":142,"passed_time":7.967919061,"remaining_time":19.8919378},
+{"learn":[0.003802271928],"iteration":143,"passed_time":8.023507345,"remaining_time":19.83589316},
+{"learn":[0.003779416661],"iteration":144,"passed_time":8.073564825,"remaining_time":19.76631388},
+{"learn":[0.003758169628],"iteration":145,"passed_time":8.125733007,"remaining_time":19.70211976},
+{"learn":[0.003679351574],"iteration":146,"passed_time":8.184503763,"remaining_time":19.65394441},
+{"learn":[0.003596443864],"iteration":147,"passed_time":8.240588946,"remaining_time":19.59923857},
+{"learn":[0.003547738913],"iteration":148,"passed_time":8.289814716,"remaining_time":19.52835547},
+{"learn":[0.003532588363],"iteration":149,"passed_time":8.335098841,"remaining_time":19.44856396},
+{"learn":[0.003532594863],"iteration":150,"passed_time":8.377867196,"remaining_time":19.36341491},
+{"learn":[0.003532594863],"iteration":151,"passed_time":8.421943507,"remaining_time":19.28181803},
+{"learn":[0.003532601958],"iteration":152,"passed_time":8.46640891,"remaining_time":19.20159406},
+{"learn":[0.003532602234],"iteration":153,"passed_time":8.534491904,"remaining_time":19.17489739},
+{"learn":[0.003521208119],"iteration":154,"passed_time":8.595778142,"remaining_time":19.13253845},
+{"learn":[0.003486049478],"iteration":155,"passed_time":8.648828555,"remaining_time":19.07177579},
+{"learn":[0.003486020897],"iteration":156,"passed_time":8.696238425,"remaining_time":18.99878841},
+{"learn":[0.003486019848],"iteration":157,"passed_time":8.738743495,"remaining_time":18.91550807},
+{"learn":[0.00347351646],"iteration":158,"passed_time":8.786679162,"remaining_time":18.84438738},
+{"learn":[0.003399677379],"iteration":159,"passed_time":8.843873123,"remaining_time":18.79323039},
+{"learn":[0.003370183036],"iteration":160,"passed_time":8.89905947,"remaining_time":18.73777118},
+{"learn":[0.003361160971],"iteration":161,"passed_time":8.945545662,"remaining_time":18.66416317},
+{"learn":[0.00336113525],"iteration":162,"passed_time":8.987265238,"remaining_time":18.58103304},
+{"learn":[0.003361081484],"iteration":163,"passed_time":9.029535219,"remaining_time":18.49953557},
+{"learn":[0.0033611028],"iteration":164,"passed_time":9.072931226,"remaining_time":18.42079976},
+{"learn":[0.003361064823],"iteration":165,"passed_time":9.114897822,"remaining_time":18.33961369},
+{"learn":[0.0033610596],"iteration":166,"passed_time":9.156901705,"remaining_time":18.25897166},
+{"learn":[0.003361047233],"iteration":167,"passed_time":9.197479301,"remaining_time":18.175971},
+{"learn":[0.003361047233],"iteration":168,"passed_time":9.239997365,"remaining_time":18.09727295},
+{"learn":[0.003361047233],"iteration":169,"passed_time":9.282854992,"remaining_time":18.01965969},
+{"learn":[0.003361047233],"iteration":170,"passed_time":9.325516397,"remaining_time":17.94207541},
+{"learn":[0.003361047233],"iteration":171,"passed_time":9.375955532,"remaining_time":17.87972915},
+{"learn":[0.003361047233],"iteration":172,"passed_time":9.418046733,"remaining_time":17.80174151},
+{"learn":[0.003361047233],"iteration":173,"passed_time":9.459238994,"remaining_time":17.72248225},
+{"learn":[0.003361047233],"iteration":174,"passed_time":9.501347421,"remaining_time":17.6453595},
+{"learn":[0.003361047233],"iteration":175,"passed_time":9.54301031,"remaining_time":17.56781443},
+{"learn":[0.003361047233],"iteration":176,"passed_time":9.582866583,"remaining_time":17.487378},
+{"learn":[0.003361047233],"iteration":177,"passed_time":9.626158005,"remaining_time":17.41361167},
+{"learn":[0.003298613361],"iteration":178,"passed_time":9.6858637,"remaining_time":17.3696215},
+{"learn":[0.003274801885],"iteration":179,"passed_time":9.741066181,"remaining_time":17.31745099},
+{"learn":[0.003253177687],"iteration":180,"passed_time":9.792184461,"remaining_time":17.25804886},
+{"learn":[0.003232040551],"iteration":181,"passed_time":9.845943985,"remaining_time":17.20335268},
+{"learn":[0.003209343557],"iteration":182,"passed_time":9.896457976,"remaining_time":17.14304469},
+{"learn":[0.003209343557],"iteration":183,"passed_time":9.935556718,"remaining_time":17.06323871},
+{"learn":[0.003186814949],"iteration":184,"passed_time":9.986947525,"remaining_time":17.00480254},
+{"learn":[0.00316883113],"iteration":185,"passed_time":10.03299251,"remaining_time":16.93741747},
+{"learn":[0.003148902464],"iteration":186,"passed_time":10.08258914,"remaining_time":16.87620535},
+{"learn":[0.003083705592],"iteration":187,"passed_time":10.14367927,"remaining_time":16.83419112},
+{"learn":[0.003012363879],"iteration":188,"passed_time":10.20129742,"remaining_time":16.78626188},
+{"learn":[0.0030123444],"iteration":189,"passed_time":10.24064601,"remaining_time":16.70842244},
+{"learn":[0.003002752135],"iteration":190,"passed_time":10.2891472,"remaining_time":16.64579311},
+{"learn":[0.002971371016],"iteration":191,"passed_time":10.34123822,"remaining_time":16.58906965},
+{"learn":[0.002954947188],"iteration":192,"passed_time":10.39110364,"remaining_time":16.52885398},
+{"learn":[0.002954947188],"iteration":193,"passed_time":10.43392666,"remaining_time":16.4576369},
+{"learn":[0.002954976483],"iteration":194,"passed_time":10.47474273,"remaining_time":16.38357196},
+{"learn":[0.002954912239],"iteration":195,"passed_time":10.51665777,"remaining_time":16.31155082},
+{"learn":[0.002954947551],"iteration":196,"passed_time":10.55738672,"remaining_time":16.23801105},
+{"learn":[0.00295491811],"iteration":197,"passed_time":10.59745325,"remaining_time":16.16379232},
+{"learn":[0.002954873004],"iteration":198,"passed_time":10.63906986,"remaining_time":16.09226144},
+{"learn":[0.002954880432],"iteration":199,"passed_time":10.67945668,"remaining_time":16.01918502},
+{"learn":[0.002954910774],"iteration":200,"passed_time":10.72179018,"remaining_time":15.94932967},
+{"learn":[0.002954868483],"iteration":201,"passed_time":10.76545969,"remaining_time":15.88171776},
+{"learn":[0.00295483191],"iteration":202,"passed_time":10.80688348,"remaining_time":15.81105613},
+{"learn":[0.00295488317],"iteration":203,"passed_time":10.84973167,"remaining_time":15.74274792},
+{"learn":[0.00295488317],"iteration":204,"passed_time":10.89192299,"remaining_time":15.67374284},
+{"learn":[0.002954858415],"iteration":205,"passed_time":10.93505689,"remaining_time":15.60634333},
+{"learn":[0.002954858415],"iteration":206,"passed_time":10.97636451,"remaining_time":15.53659325},
+{"learn":[0.002954858415],"iteration":207,"passed_time":11.01931409,"remaining_time":15.46942171},
+{"learn":[0.0029548168],"iteration":208,"passed_time":11.06124859,"remaining_time":15.40106862},
+{"learn":[0.0029548168],"iteration":209,"passed_time":11.10210197,"remaining_time":15.33147415},
+{"learn":[0.002945581202],"iteration":210,"passed_time":11.15043529,"remaining_time":15.27239715},
+{"learn":[0.002890384772],"iteration":211,"passed_time":11.20408524,"remaining_time":15.2206441},
+{"learn":[0.002890384772],"iteration":212,"passed_time":11.24673724,"remaining_time":15.15405441},
+{"learn":[0.002890358968],"iteration":213,"passed_time":11.29047594,"remaining_time":15.08914074},
+{"learn":[0.002890339481],"iteration":214,"passed_time":11.33166926,"remaining_time":15.02104995},
+{"learn":[0.002890318836],"iteration":215,"passed_time":11.37520036,"remaining_time":14.95628195},
+{"learn":[0.002890271989],"iteration":216,"passed_time":11.41710981,"remaining_time":14.88959482},
+{"learn":[0.002890285275],"iteration":217,"passed_time":11.45858532,"remaining_time":14.82257368},
+{"learn":[0.002890285275],"iteration":218,"passed_time":11.50164112,"remaining_time":14.75781349},
+{"learn":[0.002890285275],"iteration":219,"passed_time":11.54276177,"remaining_time":14.69078771},
+{"learn":[0.002890285275],"iteration":220,"passed_time":11.58562475,"remaining_time":14.62619596},
+{"learn":[0.002890285275],"iteration":221,"passed_time":11.62833747,"remaining_time":14.56161179},
+{"learn":[0.002890285275],"iteration":222,"passed_time":11.67251439,"remaining_time":14.49904253},
+{"learn":[0.002890285275],"iteration":223,"passed_time":11.71726416,"remaining_time":14.43734334},
+{"learn":[0.002890285275],"iteration":224,"passed_time":11.76133444,"remaining_time":14.37496431},
+{"learn":[0.002890285275],"iteration":225,"passed_time":11.80360423,"remaining_time":14.31056443},
+{"learn":[0.002890285275],"iteration":226,"passed_time":11.84468608,"remaining_time":14.24493084},
+{"learn":[0.002890285275],"iteration":227,"passed_time":11.88517766,"remaining_time":14.17880843},
+{"learn":[0.002890285275],"iteration":228,"passed_time":11.92601712,"remaining_time":14.11332157},
+{"learn":[0.002890285275],"iteration":229,"passed_time":11.96761325,"remaining_time":14.04893729},
+{"learn":[0.002890285275],"iteration":230,"passed_time":12.01226899,"remaining_time":13.98831324},
+{"learn":[0.002890285275],"iteration":231,"passed_time":12.05386215,"remaining_time":13.92428904},
+{"learn":[0.002890285275],"iteration":232,"passed_time":12.09701888,"remaining_time":13.8622491},
+{"learn":[0.002890285275],"iteration":233,"passed_time":12.17102529,"remaining_time":13.83543901},
+{"learn":[0.002890285275],"iteration":234,"passed_time":12.25242185,"remaining_time":13.81656081},
+{"learn":[0.002890285275],"iteration":235,"passed_time":12.32468808,"remaining_time":13.78693921},
+{"learn":[0.002890285275],"iteration":236,"passed_time":12.38491716,"remaining_time":13.74360006},
+{"learn":[0.002890285275],"iteration":237,"passed_time":12.44642527,"remaining_time":13.70152698},
+{"learn":[0.002890285275],"iteration":238,"passed_time":12.50308355,"remaining_time":13.65399501},
+{"learn":[0.002890285275],"iteration":239,"passed_time":12.55076698,"remaining_time":13.59666423},
+{"learn":[0.002890285275],"iteration":240,"passed_time":12.60359271,"remaining_time":13.54493989},
+{"learn":[0.002890285275],"iteration":241,"passed_time":12.64865466,"remaining_time":13.48492935},
+{"learn":[0.002890285275],"iteration":242,"passed_time":12.69639311,"remaining_time":13.42787255},
+{"learn":[0.002890285275],"iteration":243,"passed_time":12.75211697,"remaining_time":13.37927026},
+{"learn":[0.002890285275],"iteration":244,"passed_time":12.79818559,"remaining_time":13.32056051},
+{"learn":[0.002890285275],"iteration":245,"passed_time":12.84266353,"remaining_time":13.26031112},
+{"learn":[0.002890285275],"iteration":246,"passed_time":12.88538112,"remaining_time":13.19838633},
+{"learn":[0.002890285275],"iteration":247,"passed_time":12.92573469,"remaining_time":13.13421429},
+{"learn":[0.002890285275],"iteration":248,"passed_time":12.9672641,"remaining_time":13.07141884},
+{"learn":[0.002890285275],"iteration":249,"passed_time":13.00979541,"remaining_time":13.00979541},
+{"learn":[0.002890285275],"iteration":250,"passed_time":13.05186121,"remaining_time":12.94786231},
+{"learn":[0.002890285275],"iteration":251,"passed_time":13.09545933,"remaining_time":12.8875949},
+{"learn":[0.002890285275],"iteration":252,"passed_time":13.14121676,"remaining_time":12.82956735},
+{"learn":[0.002890285275],"iteration":253,"passed_time":13.18392768,"remaining_time":12.76868586},
+{"learn":[0.002890285275],"iteration":254,"passed_time":13.22534659,"remaining_time":12.70670555},
+{"learn":[0.002890285275],"iteration":255,"passed_time":13.26512905,"remaining_time":12.64332613},
+{"learn":[0.002890285275],"iteration":256,"passed_time":13.30674603,"remaining_time":12.58186492},
+{"learn":[0.002890285275],"iteration":257,"passed_time":13.3465156,"remaining_time":12.51882471},
+{"learn":[0.002890285275],"iteration":258,"passed_time":13.3886949,"remaining_time":12.45820645},
+{"learn":[0.002890285275],"iteration":259,"passed_time":13.42972971,"remaining_time":12.39667358},
+{"learn":[0.002890285275],"iteration":260,"passed_time":13.47090832,"remaining_time":12.33542946},
+{"learn":[0.002890285275],"iteration":261,"passed_time":13.51184651,"remaining_time":12.27412011},
+{"learn":[0.002890285275],"iteration":262,"passed_time":13.55280944,"remaining_time":12.21298797},
+{"learn":[0.002890285275],"iteration":263,"passed_time":13.59301121,"remaining_time":12.1513282},
+{"learn":[0.002890285275],"iteration":264,"passed_time":13.63293748,"remaining_time":12.08958606},
+{"learn":[0.002890285275],"iteration":265,"passed_time":13.67238509,"remaining_time":12.02758688},
+{"learn":[0.002890285275],"iteration":266,"passed_time":13.71357616,"remaining_time":11.96727807},
+{"learn":[0.002890285275],"iteration":267,"passed_time":13.75355022,"remaining_time":11.9060584},
+{"learn":[0.002890285275],"iteration":268,"passed_time":13.79360654,"remaining_time":11.84506732},
+{"learn":[0.002890285275],"iteration":269,"passed_time":13.83353701,"remaining_time":11.78412412},
+{"learn":[0.002890285275],"iteration":270,"passed_time":13.87407893,"remaining_time":11.72385267},
+{"learn":[0.002890285275],"iteration":271,"passed_time":13.91422735,"remaining_time":11.66339645},
+{"learn":[0.002890285275],"iteration":272,"passed_time":13.95618409,"remaining_time":11.60459263},
+{"learn":[0.002890285275],"iteration":273,"passed_time":13.99723754,"remaining_time":11.54516673},
+{"learn":[0.002890285275],"iteration":274,"passed_time":14.03946952,"remaining_time":11.4868387},
+{"learn":[0.002890285275],"iteration":275,"passed_time":14.08292986,"remaining_time":11.42962423},
+{"learn":[0.002890285275],"iteration":276,"passed_time":14.12602268,"remaining_time":11.37221321},
+{"learn":[0.002890285275],"iteration":277,"passed_time":14.16854413,"remaining_time":11.31444891},
+{"learn":[0.002890285275],"iteration":278,"passed_time":14.20969592,"remaining_time":11.25570895},
+{"learn":[0.002890285275],"iteration":279,"passed_time":14.2520837,"remaining_time":11.19806577},
+{"learn":[0.002890285275],"iteration":280,"passed_time":14.29453017,"remaining_time":11.14057689},
+{"learn":[0.002890285275],"iteration":281,"passed_time":14.33663038,"remaining_time":11.08292703},
+{"learn":[0.002890285275],"iteration":282,"passed_time":14.37956869,"remaining_time":11.0260297},
+{"learn":[0.002890285275],"iteration":283,"passed_time":14.42043911,"remaining_time":10.96765791},
+{"learn":[0.002890285275],"iteration":284,"passed_time":14.46271028,"remaining_time":10.91046565},
+{"learn":[0.002890285275],"iteration":285,"passed_time":14.50456959,"remaining_time":10.85306955},
+{"learn":[0.002890285275],"iteration":286,"passed_time":14.5461523,"remaining_time":10.79557645},
+{"learn":[0.002890285275],"iteration":287,"passed_time":14.58754474,"remaining_time":10.73805377},
+{"learn":[0.002890285275],"iteration":288,"passed_time":14.63054423,"remaining_time":10.68181603},
+{"learn":[0.002890285275],"iteration":289,"passed_time":14.67061393,"remaining_time":10.62354802},
+{"learn":[0.002890285275],"iteration":290,"passed_time":14.71241901,"remaining_time":10.56665145},
+{"learn":[0.002890285275],"iteration":291,"passed_time":14.75415932,"remaining_time":10.50981212},
+{"learn":[0.002890285275],"iteration":292,"passed_time":14.79790243,"remaining_time":10.45449079},
+{"learn":[0.002890285275],"iteration":293,"passed_time":14.83966033,"remaining_time":10.39785724},
+{"learn":[0.002890285275],"iteration":294,"passed_time":14.8830331,"remaining_time":10.34244673},
+{"learn":[0.002890285275],"iteration":295,"passed_time":14.92564404,"remaining_time":10.28659252},
+{"learn":[0.002890285275],"iteration":296,"passed_time":14.96665843,"remaining_time":10.22973623},
+{"learn":[0.002890285275],"iteration":297,"passed_time":15.00834795,"remaining_time":10.17344391},
+{"learn":[0.002890285275],"iteration":298,"passed_time":15.05009225,"remaining_time":10.11728609},
+{"learn":[0.002890285275],"iteration":299,"passed_time":15.09389516,"remaining_time":10.06259677},
+{"learn":[0.002890285275],"iteration":300,"passed_time":15.13867954,"remaining_time":10.00862866},
+{"learn":[0.002890285275],"iteration":301,"passed_time":15.1806303,"remaining_time":9.952863572},
+{"learn":[0.002890285275],"iteration":302,"passed_time":15.22368674,"remaining_time":9.897908538},
+{"learn":[0.002890285275],"iteration":303,"passed_time":15.26539265,"remaining_time":9.842161051},
+{"learn":[0.002890285275],"iteration":304,"passed_time":15.30826583,"remaining_time":9.787251922},
+{"learn":[0.002890285275],"iteration":305,"passed_time":15.35047459,"remaining_time":9.732000229},
+{"learn":[0.002890285275],"iteration":306,"passed_time":15.39348253,"remaining_time":9.677335922},
+{"learn":[0.002890285275],"iteration":307,"passed_time":15.43802765,"remaining_time":9.623705547},
+{"learn":[0.002890285275],"iteration":308,"passed_time":15.48047472,"remaining_time":9.568837126},
+{"learn":[0.002890285275],"iteration":309,"passed_time":15.52084166,"remaining_time":9.512773921},
+{"learn":[0.002890285275],"iteration":310,"passed_time":15.56328556,"remaining_time":9.458073861},
+{"learn":[0.002890285275],"iteration":311,"passed_time":15.60396327,"remaining_time":9.402388125},
+{"learn":[0.002890285275],"iteration":312,"passed_time":15.6451686,"remaining_time":9.347113506},
+{"learn":[0.002890285275],"iteration":313,"passed_time":15.68782641,"remaining_time":9.292788893},
+{"learn":[0.002890285275],"iteration":314,"passed_time":15.73086873,"remaining_time":9.238764178},
+{"learn":[0.002890285275],"iteration":315,"passed_time":15.77246052,"remaining_time":9.183964355},
+{"learn":[0.002890285275],"iteration":316,"passed_time":15.81734691,"remaining_time":9.131149795},
+{"learn":[0.002890285275],"iteration":317,"passed_time":15.85828751,"remaining_time":9.076126811},
+{"learn":[0.002890285275],"iteration":318,"passed_time":15.90205774,"remaining_time":9.022797651},
+{"learn":[0.002890285275],"iteration":319,"passed_time":15.94353518,"remaining_time":8.96823854},
+{"learn":[0.002890285275],"iteration":320,"passed_time":15.98622074,"remaining_time":8.914434617},
+{"learn":[0.002890285275],"iteration":321,"passed_time":16.02753394,"remaining_time":8.859941121},
+{"learn":[0.002890285275],"iteration":322,"passed_time":16.06801618,"remaining_time":8.805073882},
+{"learn":[0.002890285275],"iteration":323,"passed_time":16.11040068,"remaining_time":8.751328765},
+{"learn":[0.002890285275],"iteration":324,"passed_time":16.15302691,"remaining_time":8.697783719},
+{"learn":[0.002890285275],"iteration":325,"passed_time":16.19481938,"remaining_time":8.643860653},
+{"learn":[0.002890285275],"iteration":326,"passed_time":16.23620497,"remaining_time":8.589796512},
+{"learn":[0.002890285275],"iteration":327,"passed_time":16.2779568,"remaining_time":8.536001738},
+{"learn":[0.002890285275],"iteration":328,"passed_time":16.32109819,"remaining_time":8.483002401},
+{"learn":[0.002890285275],"iteration":329,"passed_time":16.36498937,"remaining_time":8.430449069},
+{"learn":[0.002890285275],"iteration":330,"passed_time":16.40591732,"remaining_time":8.376435126},
+{"learn":[0.002890285275],"iteration":331,"passed_time":16.44752374,"remaining_time":8.322843337},
+{"learn":[0.002890285275],"iteration":332,"passed_time":16.48823487,"remaining_time":8.268874543},
+{"learn":[0.002890285275],"iteration":333,"passed_time":16.52975607,"remaining_time":8.215387746},
+{"learn":[0.002890285275],"iteration":334,"passed_time":16.57022506,"remaining_time":8.161454132},
+{"learn":[0.002890285275],"iteration":335,"passed_time":16.60986538,"remaining_time":8.107196198},
+{"learn":[0.002890285275],"iteration":336,"passed_time":16.65042499,"remaining_time":8.053469654},
+{"learn":[0.002890285275],"iteration":337,"passed_time":16.69331555,"remaining_time":8.000938223},
+{"learn":[0.002890285275],"iteration":338,"passed_time":16.73443412,"remaining_time":7.947622105},
+{"learn":[0.002890285275],"iteration":339,"passed_time":16.77490077,"remaining_time":7.894070951},
+{"learn":[0.002890285275],"iteration":340,"passed_time":16.81693706,"remaining_time":7.841328426},
+{"learn":[0.002890285275],"iteration":341,"passed_time":16.86050441,"remaining_time":7.789355838},
+{"learn":[0.002890285275],"iteration":342,"passed_time":16.90143301,"remaining_time":7.736224441},
+{"learn":[0.002890285275],"iteration":343,"passed_time":16.94191502,"remaining_time":7.682961463},
+{"learn":[0.002890285275],"iteration":344,"passed_time":16.98510763,"remaining_time":7.630990386},
+{"learn":[0.002890285275],"iteration":345,"passed_time":17.02645283,"remaining_time":7.578247792},
+{"learn":[0.002890285275],"iteration":346,"passed_time":17.06840126,"remaining_time":7.525836869},
+{"learn":[0.002890285275],"iteration":347,"passed_time":17.11111049,"remaining_time":7.473818376},
+{"learn":[0.002890285275],"iteration":348,"passed_time":17.15194627,"remaining_time":7.421042657},
+{"learn":[0.002890285275],"iteration":349,"passed_time":17.19354465,"remaining_time":7.368661992},
+{"learn":[0.002890285275],"iteration":350,"passed_time":17.23528066,"remaining_time":7.316401191},
+{"learn":[0.002890285275],"iteration":351,"passed_time":17.27781667,"remaining_time":7.264536552},
+{"learn":[0.002890285275],"iteration":352,"passed_time":17.31890201,"remaining_time":7.212120667},
+{"learn":[0.002890285275],"iteration":353,"passed_time":17.36105295,"remaining_time":7.160208277},
+{"learn":[0.002890285275],"iteration":354,"passed_time":17.400824,"remaining_time":7.107378817},
+{"learn":[0.002890285275],"iteration":355,"passed_time":17.44128552,"remaining_time":7.054902008},
+{"learn":[0.002890285275],"iteration":356,"passed_time":17.48330602,"remaining_time":7.003116978},
+{"learn":[0.002890285275],"iteration":357,"passed_time":17.52324841,"remaining_time":6.950562218},
+{"learn":[0.002890285275],"iteration":358,"passed_time":17.56472394,"remaining_time":6.898679875},
+{"learn":[0.002890285275],"iteration":359,"passed_time":17.60673302,"remaining_time":6.847062842},
+{"learn":[0.002890285275],"iteration":360,"passed_time":17.6515616,"remaining_time":6.79658466},
+{"learn":[0.002890285275],"iteration":361,"passed_time":17.69489335,"remaining_time":6.745567077},
+{"learn":[0.002890285275],"iteration":362,"passed_time":17.7382301,"remaining_time":6.69459373},
+{"learn":[0.002890285275],"iteration":363,"passed_time":17.77853616,"remaining_time":6.642529993},
+{"learn":[0.002890285275],"iteration":364,"passed_time":17.81998514,"remaining_time":6.590953407},
+{"learn":[0.002890285275],"iteration":365,"passed_time":17.85939039,"remaining_time":6.538683913},
+{"learn":[0.002890285275],"iteration":366,"passed_time":17.90117433,"remaining_time":6.487346554},
+{"learn":[0.002890285275],"iteration":367,"passed_time":17.9437348,"remaining_time":6.436339656},
+{"learn":[0.002890285275],"iteration":368,"passed_time":17.98582436,"remaining_time":6.385211358},
+{"learn":[0.002890285275],"iteration":369,"passed_time":18.02662964,"remaining_time":6.333680683},
+{"learn":[0.002890285275],"iteration":370,"passed_time":18.06696722,"remaining_time":6.282045208},
+{"learn":[0.002890285275],"iteration":371,"passed_time":18.11132302,"remaining_time":6.231853083},
+{"learn":[0.002890285275],"iteration":372,"passed_time":18.15211597,"remaining_time":6.180479165},
+{"learn":[0.002890285275],"iteration":373,"passed_time":18.19544812,"remaining_time":6.13001728},
+{"learn":[0.002890285275],"iteration":374,"passed_time":18.23908215,"remaining_time":6.07969405},
+{"learn":[0.002890285275],"iteration":375,"passed_time":18.282214,"remaining_time":6.029240786},
+{"learn":[0.002890285275],"iteration":376,"passed_time":18.3249046,"remaining_time":5.978682401},
+{"learn":[0.002890285275],"iteration":377,"passed_time":18.36676683,"remaining_time":5.927898289},
+{"learn":[0.002890285275],"iteration":378,"passed_time":18.41009608,"remaining_time":5.87762962},
+{"learn":[0.002890285275],"iteration":379,"passed_time":18.45221049,"remaining_time":5.827013839},
+{"learn":[0.002890285275],"iteration":380,"passed_time":18.4949998,"remaining_time":5.77665348},
+{"learn":[0.002890285275],"iteration":381,"passed_time":18.53558431,"remaining_time":5.725651697},
+{"learn":[0.002890285275],"iteration":382,"passed_time":18.57992858,"remaining_time":5.675852855},
+{"learn":[0.002890285275],"iteration":383,"passed_time":18.62263322,"remaining_time":5.625587117},
+{"learn":[0.002890285275],"iteration":384,"passed_time":18.66586944,"remaining_time":5.575519442},
+{"learn":[0.002890285275],"iteration":385,"passed_time":18.70731483,"remaining_time":5.524958267},
+{"learn":[0.002890285275],"iteration":386,"passed_time":18.75411379,"remaining_time":5.476007387},
+{"learn":[0.002890285275],"iteration":387,"passed_time":18.79566318,"remaining_time":5.425552258},
+{"learn":[0.002890285275],"iteration":388,"passed_time":18.8386289,"remaining_time":5.375547065},
+{"learn":[0.002890285275],"iteration":389,"passed_time":18.88097092,"remaining_time":5.325402053},
+{"learn":[0.002890285275],"iteration":390,"passed_time":18.92197448,"remaining_time":5.274923832},
+{"learn":[0.002890285275],"iteration":391,"passed_time":18.96257546,"remaining_time":5.224383034},
+{"learn":[0.002890285275],"iteration":392,"passed_time":19.00647744,"remaining_time":5.174791567},
+{"learn":[0.002890285275],"iteration":393,"passed_time":19.04889229,"remaining_time":5.124828891},
+{"learn":[0.002890285275],"iteration":394,"passed_time":19.08953258,"remaining_time":5.074432712},
+{"learn":[0.002890285275],"iteration":395,"passed_time":19.13155673,"remaining_time":5.024449242},
+{"learn":[0.002890285275],"iteration":396,"passed_time":19.17333571,"remaining_time":4.974442262},
+{"learn":[0.002890285275],"iteration":397,"passed_time":19.21722722,"remaining_time":4.92501803},
+{"learn":[0.002890285275],"iteration":398,"passed_time":19.26020238,"remaining_time":4.875389574},
+{"learn":[0.002890285275],"iteration":399,"passed_time":19.30356047,"remaining_time":4.825890117},
+{"learn":[0.002890285275],"iteration":400,"passed_time":19.34401565,"remaining_time":4.775704611},
+{"learn":[0.002890285275],"iteration":401,"passed_time":19.38561745,"remaining_time":4.72584704},
+{"learn":[0.002890285275],"iteration":402,"passed_time":19.42977969,"remaining_time":4.676646725},
+{"learn":[0.002890285275],"iteration":403,"passed_time":19.47328394,"remaining_time":4.627314996},
+{"learn":[0.002890285275],"iteration":404,"passed_time":19.51650923,"remaining_time":4.577946611},
+{"learn":[0.002890285275],"iteration":405,"passed_time":19.55966983,"remaining_time":4.528593507},
+{"learn":[0.002890285275],"iteration":406,"passed_time":19.60183208,"remaining_time":4.479042712},
+{"learn":[0.002890285275],"iteration":407,"passed_time":19.64504112,"remaining_time":4.429764173},
+{"learn":[0.002890285275],"iteration":408,"passed_time":19.68820303,"remaining_time":4.380504831},
+{"learn":[0.002890285275],"iteration":409,"passed_time":19.73315498,"remaining_time":4.331668166},
+{"learn":[0.002890285275],"iteration":410,"passed_time":19.77412468,"remaining_time":4.28198807},
+{"learn":[0.002890285275],"iteration":411,"passed_time":19.81894479,"remaining_time":4.233172673},
+{"learn":[0.002890285275],"iteration":412,"passed_time":19.86141001,"remaining_time":4.183880559},
+{"learn":[0.002890285275],"iteration":413,"passed_time":19.90421704,"remaining_time":4.134692428},
+{"learn":[0.002890285275],"iteration":414,"passed_time":19.9471199,"remaining_time":4.085554679},
+{"learn":[0.002890285275],"iteration":415,"passed_time":19.9879668,"remaining_time":4.036031758},
+{"learn":[0.002890285275],"iteration":416,"passed_time":20.05164682,"remaining_time":3.99109517},
+{"learn":[0.002890285275],"iteration":417,"passed_time":20.09983158,"remaining_time":3.943029162},
+{"learn":[0.002890285275],"iteration":418,"passed_time":20.14272537,"remaining_time":3.893939749},
+{"learn":[0.002890285275],"iteration":419,"passed_time":20.1860763,"remaining_time":3.844966914},
+{"learn":[0.002890285275],"iteration":420,"passed_time":20.22749695,"remaining_time":3.795658573},
+{"learn":[0.002890285275],"iteration":421,"passed_time":20.27069356,"remaining_time":3.746715872},
+{"learn":[0.002890285275],"iteration":422,"passed_time":20.31531873,"remaining_time":3.698060384},
+{"learn":[0.002890285275],"iteration":423,"passed_time":20.35715739,"remaining_time":3.648924438},
+{"learn":[0.002890285275],"iteration":424,"passed_time":20.39883531,"remaining_time":3.599794467},
+{"learn":[0.002890285275],"iteration":425,"passed_time":20.43954572,"remaining_time":3.550531416},
+{"learn":[0.002890285275],"iteration":426,"passed_time":20.48152577,"remaining_time":3.501525483},
+{"learn":[0.002890285275],"iteration":427,"passed_time":20.52489077,"remaining_time":3.452785363},
+{"learn":[0.002890285275],"iteration":428,"passed_time":20.56651622,"remaining_time":3.403782405},
+{"learn":[0.002890285275],"iteration":429,"passed_time":20.60726596,"remaining_time":3.354671202},
+{"learn":[0.002890285275],"iteration":430,"passed_time":20.64926586,"remaining_time":3.305798943},
+{"learn":[0.002890285275],"iteration":431,"passed_time":20.69189262,"remaining_time":3.257057172},
+{"learn":[0.002890285275],"iteration":432,"passed_time":20.73589105,"remaining_time":3.208555889},
+{"learn":[0.002890285275],"iteration":433,"passed_time":20.77712437,"remaining_time":3.159654858},
+{"learn":[0.002890285275],"iteration":434,"passed_time":20.81927848,"remaining_time":3.11092667},
+{"learn":[0.002890285275],"iteration":435,"passed_time":20.86161858,"remaining_time":3.062255938},
+{"learn":[0.002890285275],"iteration":436,"passed_time":20.90211159,"remaining_time":3.013347896},
+{"learn":[0.002890285275],"iteration":437,"passed_time":20.94366359,"remaining_time":2.964628179},
+{"learn":[0.002890285275],"iteration":438,"passed_time":20.98624109,"remaining_time":2.916083614},
+{"learn":[0.002890285275],"iteration":439,"passed_time":21.02900907,"remaining_time":2.867592145},
+{"learn":[0.002890285275],"iteration":440,"passed_time":21.07059318,"remaining_time":2.818968249},
+{"learn":[0.002890285275],"iteration":441,"passed_time":21.11614603,"remaining_time":2.770896991},
+{"learn":[0.002890285275],"iteration":442,"passed_time":21.15683784,"remaining_time":2.722211641},
+{"learn":[0.002890285275],"iteration":443,"passed_time":21.2021076,"remaining_time":2.674139697},
+{"learn":[0.002890285275],"iteration":444,"passed_time":21.24477194,"remaining_time":2.62575833},
+{"learn":[0.002890285275],"iteration":445,"passed_time":21.28701241,"remaining_time":2.577351278},
+{"learn":[0.002890285275],"iteration":446,"passed_time":21.33168289,"remaining_time":2.52925994},
+{"learn":[0.002890285275],"iteration":447,"passed_time":21.37565688,"remaining_time":2.481103031},
+{"learn":[0.002890285275],"iteration":448,"passed_time":21.41767041,"remaining_time":2.432742074},
+{"learn":[0.002890285275],"iteration":449,"passed_time":21.45996204,"remaining_time":2.384440227},
+{"learn":[0.002890285275],"iteration":450,"passed_time":21.50193346,"remaining_time":2.336130243},
+{"learn":[0.002890285275],"iteration":451,"passed_time":21.54397503,"remaining_time":2.287855755},
+{"learn":[0.002890285275],"iteration":452,"passed_time":21.58677374,"remaining_time":2.239687342},
+{"learn":[0.002890285275],"iteration":453,"passed_time":21.63086946,"remaining_time":2.191673998},
+{"learn":[0.002890285275],"iteration":454,"passed_time":21.67398983,"remaining_time":2.143581412},
+{"learn":[0.002890285275],"iteration":455,"passed_time":21.71591301,"remaining_time":2.095395115},
+{"learn":[0.002890285275],"iteration":456,"passed_time":21.7593096,"remaining_time":2.047374864},
+{"learn":[0.002890285275],"iteration":457,"passed_time":21.80175603,"remaining_time":1.999287671},
+{"learn":[0.002890285275],"iteration":458,"passed_time":21.84575084,"remaining_time":1.951363365},
+{"learn":[0.002890285275],"iteration":459,"passed_time":21.89031155,"remaining_time":1.903505352},
+{"learn":[0.002890285275],"iteration":460,"passed_time":21.93139336,"remaining_time":1.855367334},
+{"learn":[0.002890285275],"iteration":461,"passed_time":21.97389871,"remaining_time":1.80737695},
+{"learn":[0.002890285275],"iteration":462,"passed_time":22.01535315,"remaining_time":1.759326277},
+{"learn":[0.002890285275],"iteration":463,"passed_time":22.05589812,"remaining_time":1.711233475},
+{"learn":[0.002890285275],"iteration":464,"passed_time":22.09789465,"remaining_time":1.663282393},
+{"learn":[0.002890285275],"iteration":465,"passed_time":22.14130638,"remaining_time":1.615460122},
+{"learn":[0.002890285275],"iteration":466,"passed_time":22.183871,"remaining_time":1.56759688},
+{"learn":[0.002890285275],"iteration":467,"passed_time":22.227036,"remaining_time":1.519797333},
+{"learn":[0.002890285275],"iteration":468,"passed_time":22.26922634,"remaining_time":1.471953127},
+{"learn":[0.002890285275],"iteration":469,"passed_time":22.31062157,"remaining_time":1.424082228},
+{"learn":[0.002890285275],"iteration":470,"passed_time":22.35358908,"remaining_time":1.376335633},
+{"learn":[0.002890285275],"iteration":471,"passed_time":22.39625905,"remaining_time":1.328591639},
+{"learn":[0.002890285275],"iteration":472,"passed_time":22.43981759,"remaining_time":1.28091982},
+{"learn":[0.002890285275],"iteration":473,"passed_time":22.4834707,"remaining_time":1.233270545},
+{"learn":[0.002890285275],"iteration":474,"passed_time":22.52711669,"remaining_time":1.18563772},
+{"learn":[0.002890285275],"iteration":475,"passed_time":22.56915908,"remaining_time":1.137940794},
+{"learn":[0.002890285275],"iteration":476,"passed_time":22.61201016,"remaining_time":1.09030657},
+{"learn":[0.002890285275],"iteration":477,"passed_time":22.65512258,"remaining_time":1.042704386},
+{"learn":[0.002890285275],"iteration":478,"passed_time":22.69892594,"remaining_time":0.9951512416},
+{"learn":[0.002890285275],"iteration":479,"passed_time":22.7422942,"remaining_time":0.9475955915},
+{"learn":[0.002890285275],"iteration":480,"passed_time":22.7871857,"remaining_time":0.9001175225},
+{"learn":[0.002890285275],"iteration":481,"passed_time":22.82970468,"remaining_time":0.8525615856},
+{"learn":[0.002890285275],"iteration":482,"passed_time":22.87602937,"remaining_time":0.8051604539},
+{"learn":[0.002890285275],"iteration":483,"passed_time":22.91703496,"remaining_time":0.7575879324},
+{"learn":[0.002890285275],"iteration":484,"passed_time":22.96102732,"remaining_time":0.7101348657},
+{"learn":[0.002890285275],"iteration":485,"passed_time":23.00392735,"remaining_time":0.6626645738},
+{"learn":[0.002890285275],"iteration":486,"passed_time":23.04847301,"remaining_time":0.6152569798},
+{"learn":[0.002890285275],"iteration":487,"passed_time":23.08900126,"remaining_time":0.567762326},
+{"learn":[0.002890285275],"iteration":488,"passed_time":23.13334267,"remaining_time":0.5203819415},
+{"learn":[0.002890285275],"iteration":489,"passed_time":23.17541662,"remaining_time":0.4729676862},
+{"learn":[0.002890285275],"iteration":490,"passed_time":23.21712967,"remaining_time":0.4255685683},
+{"learn":[0.002890285275],"iteration":491,"passed_time":23.26044826,"remaining_time":0.3782186709},
+{"learn":[0.002890285275],"iteration":492,"passed_time":23.3033456,"remaining_time":0.3308791465},
+{"learn":[0.002890285275],"iteration":493,"passed_time":23.34681724,"remaining_time":0.2835645819},
+{"learn":[0.002890285275],"iteration":494,"passed_time":23.38860281,"remaining_time":0.2362485133},
+{"learn":[0.002890285275],"iteration":495,"passed_time":23.43337127,"remaining_time":0.1889788005},
+{"learn":[0.002890285275],"iteration":496,"passed_time":23.47695702,"remaining_time":0.1417120142},
+{"learn":[0.002890285275],"iteration":497,"passed_time":23.52064976,"remaining_time":0.09446044081},
+{"learn":[0.002890285275],"iteration":498,"passed_time":23.56483201,"remaining_time":0.04722411225},
+{"learn":[0.002890285275],"iteration":499,"passed_time":23.60866238,"remaining_time":0}
+]}

catboost_info/learn_error.tsv

@@ -0,0 +1,501 @@
+iter	Logloss
+0	0.4712532064
+1	0.3273376208
+2	0.2607613882
+3	0.1991192034
+4	0.1632412173
+5	0.1410456933
+6	0.1279742931
+7	0.111867068
+8	0.1033243431
+9	0.09324332789
+10	0.08450684607
+11	0.07733468921
+12	0.07269855624
+13	0.06761460255
+14	0.06298238737
+15	0.05871315055
+16	0.05510760321
+17	0.05147771658
+18	0.04941872106
+19	0.04696596957
+20	0.04479184757
+21	0.04307209869
+22	0.0408917599
+23	0.03967390485
+24	0.03793541137
+25	0.03621098538
+26	0.03463164741
+27	0.03277206212
+28	0.03164623766
+29	0.03014174284
+30	0.02900272159
+31	0.02816140432
+32	0.02726041523
+33	0.02602167528
+34	0.02526884213
+35	0.02448160354
+36	0.0232350895
+37	0.02224447448
+38	0.02165583946
+39	0.02084098393
+40	0.01999068668
+41	0.01946859459
+42	0.01884432574
+43	0.01828233223
+44	0.01775287741
+45	0.01730750181
+46	0.01686236702
+47	0.01620499972
+48	0.01574607381
+49	0.01538040425
+50	0.01500497258
+51	0.01471613319
+52	0.01439056881
+53	0.01412451736
+54	0.01388558016
+55	0.01353789648
+56	0.01315290222
+57	0.01298291907
+58	0.01284298646
+59	0.01254667985
+60	0.01234774965
+61	0.01197107526
+62	0.01177996366
+63	0.01152867842
+64	0.01132496595
+65	0.01117824741
+66	0.01104682917
+67	0.01087906929
+68	0.01052047714
+69	0.01023824891
+70	0.01015912118
+71	0.01002439651
+72	0.009875214792
+73	0.009781504221
+74	0.009631726645
+75	0.00944484322
+76	0.009267291862
+77	0.00908075438
+78	0.00881684345
+79	0.008641867588
+80	0.008517053769
+81	0.008392267642
+82	0.00832744501
+83	0.008204543884
+84	0.008092354
+85	0.007933010371
+86	0.007818153126
+87	0.0077493056
+88	0.007527928995
+89	0.00750036253
+90	0.007453765847
+91	0.007347530141
+92	0.0072404781
+93	0.007044410016
+94	0.00694319981
+95	0.00682615691
+96	0.006743134326
+97	0.006633307356
+98	0.006564273923
+99	0.006497928401
+100	0.00643255325
+101	0.006338767807
+102	0.006266374486
+103	0.0061800092
+104	0.006136686033
+105	0.006069312944
+106	0.005975683435
+107	0.005882909984
+108	0.005836149747
+109	0.005777618552
+110	0.005703870902
+111	0.005599168826
+112	0.005532447924
+113	0.005461725721
+114	0.005433780033
+115	0.005387023077
+116	0.005297421416
+117	0.005225094743
+118	0.005156922192
+119	0.005010365071
+120	0.00497035813
+121	0.004895404668
+122	0.004791164597
+123	0.004766147073
+124	0.004687564549
+125	0.004630525724
+126	0.004559512715
+127	0.004505195271
+128	0.004469454457
+129	0.004398072663
+130	0.004366845846
+131	0.004317753989
+132	0.004237959314
+133	0.004201578226
+134	0.004184351177
+135	0.004121008783
+136	0.004089605915
+137	0.00406184625
+138	0.004024052254
+139	0.003978388016
+140	0.003961394672
+141	0.0039025483
+142	0.003836457729
+143	0.003802271928
+144	0.003779416661
+145	0.003758169628
+146	0.003679351574
+147	0.003596443864
+148	0.003547738913
+149	0.003532588363
+150	0.003532594863
+151	0.003532594863
+152	0.003532601958
+153	0.003532602234
+154	0.003521208119
+155	0.003486049478
+156	0.003486020897
+157	0.003486019848
+158	0.00347351646
+159	0.003399677379
+160	0.003370183036
+161	0.003361160971
+162	0.00336113525
+163	0.003361081484
+164	0.0033611028
+165	0.003361064823
+166	0.0033610596
+167	0.003361047233
+168	0.003361047233
+169	0.003361047233
+170	0.003361047233
+171	0.003361047233
+172	0.003361047233
+173	0.003361047233
+174	0.003361047233
+175	0.003361047233
+176	0.003361047233
+177	0.003361047233
+178	0.003298613361
+179	0.003274801885
+180	0.003253177687
+181	0.003232040551
+182	0.003209343557
+183	0.003209343557
+184	0.003186814949
+185	0.00316883113
+186	0.003148902464
+187	0.003083705592
+188	0.003012363879
+189	0.0030123444
+190	0.003002752135
+191	0.002971371016
+192	0.002954947188
+193	0.002954947188
+194	0.002954976483
+195	0.002954912239
+196	0.002954947551
+197	0.00295491811
+198	0.002954873004
+199	0.002954880432
+200	0.002954910774
+201	0.002954868483
+202	0.00295483191
+203	0.00295488317
+204	0.00295488317
+205	0.002954858415
+206	0.002954858415
+207	0.002954858415
+208	0.0029548168
+209	0.0029548168
+210	0.002945581202
+211	0.002890384772
+212	0.002890384772
+213	0.002890358968
+214	0.002890339481
+215	0.002890318836
+216	0.002890271989
+217	0.002890285275
+218	0.002890285275
+219	0.002890285275
+220	0.002890285275
+221	0.002890285275
+222	0.002890285275
+223	0.002890285275
+224	0.002890285275
+225	0.002890285275
+226	0.002890285275
+227	0.002890285275
+228	0.002890285275
+229	0.002890285275
+230	0.002890285275
+231	0.002890285275
+232	0.002890285275
+233	0.002890285275
+234	0.002890285275
+235	0.002890285275
+236	0.002890285275
+237	0.002890285275
+238	0.002890285275
+239	0.002890285275
+240	0.002890285275
+241	0.002890285275
+242	0.002890285275
+243	0.002890285275
+244	0.002890285275
+245	0.002890285275
+246	0.002890285275
+247	0.002890285275
+248	0.002890285275
+249	0.002890285275
+250	0.002890285275
+251	0.002890285275
+252	0.002890285275
+253	0.002890285275
+254	0.002890285275
+255	0.002890285275
+256	0.002890285275
+257	0.002890285275
+258	0.002890285275
+259	0.002890285275
+260	0.002890285275
+261	0.002890285275
+262	0.002890285275
+263	0.002890285275
+264	0.002890285275
+265	0.002890285275
+266	0.002890285275
+267	0.002890285275
+268	0.002890285275
+269	0.002890285275
+270	0.002890285275
+271	0.002890285275
+272	0.002890285275
+273	0.002890285275
+274	0.002890285275
+275	0.002890285275
+276	0.002890285275
+277	0.002890285275
+278	0.002890285275
+279	0.002890285275
+280	0.002890285275
+281	0.002890285275
+282	0.002890285275
+283	0.002890285275
+284	0.002890285275
+285	0.002890285275
+286	0.002890285275
+287	0.002890285275
+288	0.002890285275
+289	0.002890285275
+290	0.002890285275
+291	0.002890285275
+292	0.002890285275
+293	0.002890285275
+294	0.002890285275
+295	0.002890285275
+296	0.002890285275
+297	0.002890285275
+298	0.002890285275
+299	0.002890285275
+300	0.002890285275
+301	0.002890285275
+302	0.002890285275
+303	0.002890285275
+304	0.002890285275
+305	0.002890285275
+306	0.002890285275
+307	0.002890285275
+308	0.002890285275
+309	0.002890285275
+310	0.002890285275
+311	0.002890285275
+312	0.002890285275
+313	0.002890285275
+314	0.002890285275
+315	0.002890285275
+316	0.002890285275
+317	0.002890285275
+318	0.002890285275
+319	0.002890285275
+320	0.002890285275
+321	0.002890285275
+322	0.002890285275
+323	0.002890285275
+324	0.002890285275
+325	0.002890285275
+326	0.002890285275
+327	0.002890285275
+328	0.002890285275
+329	0.002890285275
+330	0.002890285275
+331	0.002890285275
+332	0.002890285275
+333	0.002890285275
+334	0.002890285275
+335	0.002890285275
+336	0.002890285275
+337	0.002890285275
+338	0.002890285275
+339	0.002890285275
+340	0.002890285275
+341	0.002890285275
+342	0.002890285275
+343	0.002890285275
+344	0.002890285275
+345	0.002890285275
+346	0.002890285275
+347	0.002890285275
+348	0.002890285275
+349	0.002890285275
+350	0.002890285275
+351	0.002890285275
+352	0.002890285275
+353	0.002890285275
+354	0.002890285275
+355	0.002890285275
+356	0.002890285275
+357	0.002890285275
+358	0.002890285275
+359	0.002890285275
+360	0.002890285275
+361	0.002890285275
+362	0.002890285275
+363	0.002890285275
+364	0.002890285275
+365	0.002890285275
+366	0.002890285275
+367	0.002890285275
+368	0.002890285275
+369	0.002890285275
+370	0.002890285275
+371	0.002890285275
+372	0.002890285275
+373	0.002890285275
+374	0.002890285275
+375	0.002890285275
+376	0.002890285275
+377	0.002890285275
+378	0.002890285275
+379	0.002890285275
+380	0.002890285275
+381	0.002890285275
+382	0.002890285275
+383	0.002890285275
+384	0.002890285275
+385	0.002890285275
+386	0.002890285275
+387	0.002890285275
+388	0.002890285275
+389	0.002890285275
+390	0.002890285275
+391	0.002890285275
+392	0.002890285275
+393	0.002890285275
+394	0.002890285275
+395	0.002890285275
+396	0.002890285275
+397	0.002890285275
+398	0.002890285275
+399	0.002890285275
+400	0.002890285275
+401	0.002890285275
+402	0.002890285275
+403	0.002890285275
+404	0.002890285275
+405	0.002890285275
+406	0.002890285275
+407	0.002890285275
+408	0.002890285275
+409	0.002890285275
+410	0.002890285275
+411	0.002890285275
+412	0.002890285275
+413	0.002890285275
+414	0.002890285275
+415	0.002890285275
+416	0.002890285275
+417	0.002890285275
+418	0.002890285275
+419	0.002890285275
+420	0.002890285275
+421	0.002890285275
+422	0.002890285275
+423	0.002890285275
+424	0.002890285275
+425	0.002890285275
+426	0.002890285275
+427	0.002890285275
+428	0.002890285275
+429	0.002890285275
+430	0.002890285275
+431	0.002890285275
+432	0.002890285275
+433	0.002890285275
+434	0.002890285275
+435	0.002890285275
+436	0.002890285275
+437	0.002890285275
+438	0.002890285275
+439	0.002890285275
+440	0.002890285275
+441	0.002890285275
+442	0.002890285275
+443	0.002890285275
+444	0.002890285275
+445	0.002890285275
+446	0.002890285275
+447	0.002890285275
+448	0.002890285275
+449	0.002890285275
+450	0.002890285275
+451	0.002890285275
+452	0.002890285275
+453	0.002890285275
+454	0.002890285275
+455	0.002890285275
+456	0.002890285275
+457	0.002890285275
+458	0.002890285275
+459	0.002890285275
+460	0.002890285275
+461	0.002890285275
+462	0.002890285275
+463	0.002890285275
+464	0.002890285275
+465	0.002890285275
+466	0.002890285275
+467	0.002890285275
+468	0.002890285275
+469	0.002890285275
+470	0.002890285275
+471	0.002890285275
+472	0.002890285275
+473	0.002890285275
+474	0.002890285275
+475	0.002890285275
+476	0.002890285275
+477	0.002890285275
+478	0.002890285275
+479	0.002890285275
+480	0.002890285275
+481	0.002890285275
+482	0.002890285275
+483	0.002890285275
+484	0.002890285275
+485	0.002890285275
+486	0.002890285275
+487	0.002890285275
+488	0.002890285275
+489	0.002890285275
+490	0.002890285275
+491	0.002890285275
+492	0.002890285275
+493	0.002890285275
+494	0.002890285275
+495	0.002890285275
+496	0.002890285275
+497	0.002890285275
+498	0.002890285275
+499	0.002890285275

catboost_info/time_left.tsv

@@ -0,0 +1,501 @@
+iter	Passed	Remaining
+0	197	98374
+1	260	64775
+2	316	52357
+3	375	46598
+4	437	43357
+5	492	40551
+6	545	38393
+7	601	36972
+8	650	35480
+9	706	34624
+10	765	34027
+11	823	33482
+12	875	32806
+13	930	32307
+14	989	32006
+15	1045	31624
+16	1098	31219
+17	1155	30944
+18	1210	30633
+19	1267	30418
+20	1326	30248
+21	1378	29941
+22	1435	29761
+23	1483	29429
+24	1539	29247
+25	1595	29083
+26	1654	28976
+27	1713	28892
+28	1767	28710
+29	1821	28538
+30	1879	28438
+31	1932	28269
+32	1987	28122
+33	2043	28003
+34	2100	27908
+35	2157	27801
+36	2217	27751
+37	2273	27641
+38	2327	27515
+39	2383	27408
+40	2447	27397
+41	2505	27324
+42	2559	27201
+43	2613	27083
+44	2669	26993
+45	2723	26877
+46	2783	26827
+47	2844	26788
+48	2902	26718
+49	2955	26599
+50	3010	26507
+51	3065	26407
+52	3119	26309
+53	3171	26198
+54	3223	26078
+55	3279	26001
+56	3337	25938
+57	3393	25857
+58	3441	25722
+59	3492	25614
+60	3543	25501
+61	3602	25449
+62	3656	25362
+63	3711	25281
+64	3764	25190
+65	3819	25113
+66	3866	24984
+67	3916	24883
+68	3977	24844
+69	4031	24765
+70	4079	24646
+71	4131	24561
+72	4182	24463
+73	4229	24350
+74	4281	24261
+75	4330	24159
+76	4388	24106
+77	4440	24021
+78	4494	23951
+79	4549	23885
+80	4606	23826
+81	4658	23745
+82	4709	23661
+83	4767	23609
+84	4825	23558
+85	4881	23498
+86	4936	23434
+87	4987	23352
+88	5046	23306
+89	5100	23237
+90	5150	23147
+91	5205	23086
+92	5257	23009
+93	5311	22940
+94	5368	22885
+95	5424	22826
+96	5473	22741
+97	5523	22658
+98	5577	22590
+99	5631	22525
+100	5681	22444
+101	5735	22379
+102	5785	22300
+103	5842	22246
+104	5893	22170
+105	5944	22095
+106	5998	22030
+107	6067	22021
+108	6121	21960
+109	6172	21883
+110	6227	21824
+111	6284	21771
+112	6338	21709
+113	6393	21647
+114	6450	21593
+115	6502	21523
+116	6561	21477
+117	6628	21459
+118	6687	21409
+119	6752	21383
+120	6809	21329
+121	6865	21271
+122	6919	21209
+123	6966	21124
+124	7024	21072
+125	7076	21004
+126	7127	20934
+127	7182	20872
+128	7233	20803
+129	7287	20742
+130	7339	20672
+131	7391	20606
+132	7449	20556
+133	7498	20480
+134	7544	20397
+135	7596	20333
+136	7647	20264
+137	7696	20189
+138	7744	20113
+139	7795	20046
+140	7846	19978
+141	7906	19933
+142	7967	19891
+143	8023	19835
+144	8073	19766
+145	8125	19702
+146	8184	19653
+147	8240	19599
+148	8289	19528
+149	8335	19448
+150	8377	19363
+151	8421	19281
+152	8466	19201
+153	8534	19174
+154	8595	19132
+155	8648	19071
+156	8696	18998
+157	8738	18915
+158	8786	18844
+159	8843	18793
+160	8899	18737
+161	8945	18664
+162	8987	18581
+163	9029	18499
+164	9072	18420
+165	9114	18339
+166	9156	18258
+167	9197	18175
+168	9239	18097
+169	9282	18019
+170	9325	17942
+171	9375	17879
+172	9418	17801
+173	9459	17722
+174	9501	17645
+175	9543	17567
+176	9582	17487
+177	9626	17413
+178	9685	17369
+179	9741	17317
+180	9792	17258
+181	9845	17203
+182	9896	17143
+183	9935	17063
+184	9986	17004
+185	10032	16937
+186	10082	16876
+187	10143	16834
+188	10201	16786
+189	10240	16708
+190	10289	16645
+191	10341	16589
+192	10391	16528
+193	10433	16457
+194	10474	16383
+195	10516	16311
+196	10557	16238
+197	10597	16163
+198	10639	16092
+199	10679	16019
+200	10721	15949
+201	10765	15881
+202	10806	15811
+203	10849	15742
+204	10891	15673
+205	10935	15606
+206	10976	15536
+207	11019	15469
+208	11061	15401
+209	11102	15331
+210	11150	15272
+211	11204	15220
+212	11246	15154
+213	11290	15089
+214	11331	15021
+215	11375	14956
+216	11417	14889
+217	11458	14822
+218	11501	14757
+219	11542	14690
+220	11585	14626
+221	11628	14561
+222	11672	14499
+223	11717	14437
+224	11761	14374
+225	11803	14310
+226	11844	14244
+227	11885	14178
+228	11926	14113
+229	11967	14048
+230	12012	13988
+231	12053	13924
+232	12097	13862
+233	12171	13835
+234	12252	13816
+235	12324	13786
+236	12384	13743
+237	12446	13701
+238	12503	13653
+239	12550	13596
+240	12603	13544
+241	12648	13484
+242	12696	13427
+243	12752	13379
+244	12798	13320
+245	12842	13260
+246	12885	13198
+247	12925	13134
+248	12967	13071
+249	13009	13009
+250	13051	12947
+251	13095	12887
+252	13141	12829
+253	13183	12768
+254	13225	12706
+255	13265	12643
+256	13306	12581
+257	13346	12518
+258	13388	12458
+259	13429	12396
+260	13470	12335
+261	13511	12274
+262	13552	12212
+263	13593	12151
+264	13632	12089
+265	13672	12027
+266	13713	11967
+267	13753	11906
+268	13793	11845
+269	13833	11784
+270	13874	11723
+271	13914	11663
+272	13956	11604
+273	13997	11545
+274	14039	11486
+275	14082	11429
+276	14126	11372
+277	14168	11314
+278	14209	11255
+279	14252	11198
+280	14294	11140
+281	14336	11082
+282	14379	11026
+283	14420	10967
+284	14462	10910
+285	14504	10853
+286	14546	10795
+287	14587	10738
+288	14630	10681
+289	14670	10623
+290	14712	10566
+291	14754	10509
+292	14797	10454
+293	14839	10397
+294	14883	10342
+295	14925	10286
+296	14966	10229
+297	15008	10173
+298	15050	10117
+299	15093	10062
+300	15138	10008
+301	15180	9952
+302	15223	9897
+303	15265	9842
+304	15308	9787
+305	15350	9732
+306	15393	9677
+307	15438	9623
+308	15480	9568
+309	15520	9512
+310	15563	9458
+311	15603	9402
+312	15645	9347
+313	15687	9292
+314	15730	9238
+315	15772	9183
+316	15817	9131
+317	15858	9076
+318	15902	9022
+319	15943	8968
+320	15986	8914
+321	16027	8859
+322	16068	8805
+323	16110	8751
+324	16153	8697
+325	16194	8643
+326	16236	8589
+327	16277	8536
+328	16321	8483
+329	16364	8430
+330	16405	8376
+331	16447	8322
+332	16488	8268
+333	16529	8215
+334	16570	8161
+335	16609	8107
+336	16650	8053
+337	16693	8000
+338	16734	7947
+339	16774	7894
+340	16816	7841
+341	16860	7789
+342	16901	7736
+343	16941	7682
+344	16985	7630
+345	17026	7578
+346	17068	7525
+347	17111	7473
+348	17151	7421
+349	17193	7368
+350	17235	7316
+351	17277	7264
+352	17318	7212
+353	17361	7160
+354	17400	7107
+355	17441	7054
+356	17483	7003
+357	17523	6950
+358	17564	6898
+359	17606	6847
+360	17651	6796
+361	17694	6745
+362	17738	6694
+363	17778	6642
+364	17819	6590
+365	17859	6538
+366	17901	6487
+367	17943	6436
+368	17985	6385
+369	18026	6333
+370	18066	6282
+371	18111	6231
+372	18152	6180
+373	18195	6130
+374	18239	6079
+375	18282	6029
+376	18324	5978
+377	18366	5927
+378	18410	5877
+379	18452	5827
+380	18494	5776
+381	18535	5725
+382	18579	5675
+383	18622	5625
+384	18665	5575
+385	18707	5524
+386	18754	5476
+387	18795	5425
+388	18838	5375
+389	18880	5325
+390	18921	5274
+391	18962	5224
+392	19006	5174
+393	19048	5124
+394	19089	5074
+395	19131	5024
+396	19173	4974
+397	19217	4925
+398	19260	4875
+399	19303	4825
+400	19344	4775
+401	19385	4725
+402	19429	4676
+403	19473	4627
+404	19516	4577
+405	19559	4528
+406	19601	4479
+407	19645	4429
+408	19688	4380
+409	19733	4331
+410	19774	4281
+411	19818	4233
+412	19861	4183
+413	19904	4134
+414	19947	4085
+415	19987	4036
+416	20051	3991
+417	20099	3943
+418	20142	3893
+419	20186	3844
+420	20227	3795
+421	20270	3746
+422	20315	3698
+423	20357	3648
+424	20398	3599
+425	20439	3550
+426	20481	3501
+427	20524	3452
+428	20566	3403
+429	20607	3354
+430	20649	3305
+431	20691	3257
+432	20735	3208
+433	20777	3159
+434	20819	3110
+435	20861	3062
+436	20902	3013
+437	20943	2964
+438	20986	2916
+439	21029	2867
+440	21070	2818
+441	21116	2770
+442	21156	2722
+443	21202	2674
+444	21244	2625
+445	21287	2577
+446	21331	2529
+447	21375	2481
+448	21417	2432
+449	21459	2384
+450	21501	2336
+451	21543	2287
+452	21586	2239
+453	21630	2191
+454	21673	2143
+455	21715	2095
+456	21759	2047
+457	21801	1999
+458	21845	1951
+459	21890	1903
+460	21931	1855
+461	21973	1807
+462	22015	1759
+463	22055	1711
+464	22097	1663
+465	22141	1615
+466	22183	1567
+467	22227	1519
+468	22269	1471
+469	22310	1424
+470	22353	1376
+471	22396	1328
+472	22439	1280
+473	22483	1233
+474	22527	1185
+475	22569	1137
+476	22612	1090
+477	22655	1042
+478	22698	995
+479	22742	947
+480	22787	900
+481	22829	852
+482	22876	805
+483	22917	757
+484	22961	710
+485	23003	662
+486	23048	615
+487	23089	567
+488	23133	520
+489	23175	472
+490	23217	425
+491	23260	378
+492	23303	330
+493	23346	283
+494	23388	236
+495	23433	188
+496	23476	141
+497	23520	94
+498	23564	47
+499	23608	0

plan.md

@@ -0,0 +1,385 @@
+# End-to-End MLOps Fraud Detection Pipeline — Complete Build Plan
+
+## Context
+You want to build a professional ML project that:
+- Trains and compares 10+ machine learning models on a real fraud dataset
+- Tracks all experiments using MLflow (a tool that logs every model's results)
+- Selects XGBoost as the best model (we'll prove this with data)
+- Serves predictions via a FastAPI web API
+- Packages everything in Docker (so it runs identically anywhere)
+- Deploys for free so anyone on the internet can use it
+- Has CI/CD (automated testing + deployment on every code push)
+
+**What you'll have at the end:** A live URL where someone sends transaction data and gets back "fraud" or "not fraud" in under 100ms.
+
+---
+
+## Key Concepts (Plain English)
+
+| Term | What it means |
+|------|--------------|
+| **MLflow** | A dashboard that records every experiment — which model, which settings, what accuracy. Like a lab notebook for ML. |
+| **XGBoost** | A powerful algorithm that builds many decision trees and combines them. Often wins ML competitions. |
+| **LightGBM** | Similar to XGBoost but faster to train — we'll compare both. |
+| **FastAPI** | A Python framework to create a web API (like a backend endpoint) in ~20 lines of code. |
+| **Docker** | Packages your code + all its dependencies into a "container" so it runs the same everywhere. |
+| **CI/CD** | GitHub Actions runs your tests and deploys automatically every time you push code. |
+| **SMOTE** | A technique to fix imbalanced data (fraud is rare — only 0.17% of transactions). |
+
+---
+
+## Dataset
+**Credit Card Fraud Detection** from Kaggle (free, public)
+- 284,807 transactions, 492 fraudulent (0.17% fraud rate)
+- 31 columns total (30 features + 1 target)
+- Binary target: 0 = normal, 1 = fraud
+
+### Dataset Columns Explained
+
+| Column | What it means |
+|--------|--------------|
+| `Time` | Seconds elapsed since the first transaction in the dataset (just a timestamp) |
+| `V1` to `V28` | **Hidden/scrambled features** — the bank ran PCA (a math technique) to hide real customer data for privacy. You don't know what they represent, and that's fine — the models learn patterns from them anyway. |
+| `Amount` | The transaction amount in dollars (e.g., 149.62) |
+| `Class` | **This is what we predict** — `0` = normal transaction, `1` = fraud |
+
+**Why V1–V28 are hidden:** The bank couldn't share real data (card number, merchant, location) for privacy reasons, so they transformed those real features into V1–V28 using math (PCA). The fraud patterns are still there — just disguised. Our models don't need to "understand" what V1 means, they just find number patterns that predict fraud.
+
+**Example row:**
+```
+Time=0, V1=-1.35, V2=-0.07, ..., V28=-0.02, Amount=149.62, Class=0 (normal)
+```
+
+---
+
+## Project Folder Structure
+```
+fraud-detection/
+├── data/                    # Raw and processed data
+├── notebooks/               # EDA and experimentation
+├── src/
+│   ├── data/                # Data loading and preprocessing
+│   ├── models/              # All 10+ model training scripts
+│   ├── evaluation/          # Metrics and comparison
+│   └── api/                 # FastAPI application
+├── mlruns/                  # MLflow experiment logs (auto-generated)
+├── models/                  # Saved trained models
+├── tests/                   # Unit and integration tests
+├── .github/workflows/       # CI/CD pipeline definitions
+├── Dockerfile
+├── docker-compose.yml
+├── requirements.txt
+└── README.md
+```
+
+---
+
+## Step-by-Step Build Plan
+
+---
+
+### STEP 1 — Project Setup & Environment
+**Goal:** Get a clean, reproducible Python environment running.
+
+**What to do:**
+1. Create the folder structure above
+2. Create a virtual environment (`python -m venv venv`)
+3. Create `requirements.txt` with all dependencies:
+   - `pandas`, `numpy`, `scikit-learn` — core data science
+   - `xgboost`, `lightgbm`, `catboost` — gradient boosting libraries
+   - `mlflow` — experiment tracking
+   - `fastapi`, `uvicorn` — web API
+   - `imbalanced-learn` — for SMOTE
+   - `pytest` — for tests
+   - `docker` — for containerization
+4. Create `.gitignore` (ignore data files, model files, venv)
+5. Initialize git repo and push to GitHub (public repo so CI/CD is free)
+
+**Files created:** `requirements.txt`, `.gitignore`, `README.md`
+
+---
+
+### STEP 2 — Download & Understand the Dataset
+**Goal:** Get the data and understand what we're working with.
+
+**What to do:**
+1. Download `creditcard.csv` from Kaggle (one-time manual step)
+2. Create `notebooks/01_eda.ipynb` — Exploratory Data Analysis:
+   - How many fraud vs normal transactions?
+   - Distribution of transaction amounts
+   - Correlation between features
+   - Visualize the class imbalance (pie chart showing 99.83% normal, 0.17% fraud)
+3. Key insight: **The data is extremely imbalanced** — if a model just predicts "not fraud" every time, it's 99.83% accurate but useless. We need special metrics.
+
+**Files created:** `notebooks/01_eda.ipynb`
+
+---
+
+### STEP 3 — Data Preprocessing Pipeline
+**Goal:** Clean and prepare data so all 10+ models get identical input.
+
+**What to do:**
+Create `src/data/preprocess.py`:
+1. **Load data** — read the CSV
+2. **Feature scaling** — normalize `Amount` and `Time` (V1-V28 are already scaled)
+3. **Train/test split** — 80% training, 20% testing (stratified to preserve fraud ratio)
+4. **SMOTE** — oversample the minority (fraud) class in training data only
+   - SMOTE creates synthetic fraud examples so models can learn the pattern
+   - Applied ONLY to training data, never test data
+5. **Save preprocessed splits** to `data/processed/`
+
+**Why SMOTE matters:** Without it, models see 99.83% normal examples and learn to just predict "normal" always. SMOTE balances the training set.
+
+**Files created:** `src/data/preprocess.py`
+
+---
+
+### STEP 4 — MLflow Setup
+**Goal:** Create the experiment tracking dashboard before training any models.
+
+**What MLflow does:** Every time we train a model, MLflow automatically records:
+- Which algorithm was used
+- What hyperparameters (settings) were used
+- Accuracy, precision, recall, F1, AUC-ROC scores
+- How long training took
+- The saved model file
+
+**What to do:**
+Create `src/mlflow_setup.py`:
+1. Configure MLflow tracking URI (local `mlruns/` folder)
+2. Create experiment named `"fraud-detection-benchmark"`
+3. Write a helper `log_model_run()` function that any model script can call
+
+**To view the dashboard:** Run `mlflow ui` and open `http://localhost:5000` in browser — you'll see all experiments in a table.
+
+**Files created:** `src/mlflow_setup.py`
+
+---
+
+### STEP 5 — Train & Benchmark 10+ Models
+**Goal:** Train all models, log every result to MLflow, and find the best one.
+
+**The 12 Models We'll Train:**
+
+| # | Model | Plain English |
+|---|-------|---------------|
+| 1 | Logistic Regression | Draws a straight line to separate fraud/normal |
+| 2 | Decision Tree | Series of yes/no questions on features |
+| 3 | Random Forest | 100+ decision trees voting together |
+| 5 | AdaBoost | Focuses on examples previous models got wrong |
+| 6 | Gradient Boosting | Builds trees one at a time, each fixing previous errors |
+| 7 | **XGBoost** | Optimized Gradient Boosting — faster + regularized |
+| 8 | **LightGBM** | Microsoft's fast gradient boosting |
+| 10 | SVM | Finds the widest margin between fraud/normal |
+| 11 | K-Nearest Neighbors | Classifies by looking at similar transactions |
+| 12 | Neural Network (MLP) | Multi-layer perceptron — simple deep learning |
+
+**What to do:**
+Create `src/models/train_all_models.py`:
+1. For each model, inside an `mlflow.start_run()` block:
+   - Train on SMOTE-balanced training data
+   - Predict on original (unbalanced) test data
+   - Log metrics: AUC-ROC, F1, Precision, Recall, Accuracy
+   - Log the model artifact (saved model file)
+2. Print a comparison table at the end
+
+**Why AUC-ROC over accuracy?**
+- Accuracy: "99.83% — great!" (but it just predicts normal every time)
+- AUC-ROC: Measures how well the model separates fraud from normal at all thresholds — the real metric
+
+**Files created:** `src/models/train_all_models.py`
+
+---
+
+### STEP 6 — Model Comparison & Selection
+**Goal:** Formally select XGBoost and tune it.
+
+**What to do:**
+Create `src/evaluation/compare_models.py`:
+1. Query MLflow API to get all run results
+2. Rank by AUC-ROC score
+3. Generate comparison charts (bar charts, ROC curves)
+4. Save the winning model to `models/best_model.pkl`
+
+Create `src/models/tune_xgboost.py`:
+1. Use `GridSearchCV` or `Optuna` to find best XGBoost hyperparameters:
+   - `n_estimators` (number of trees)
+   - `max_depth` (how deep each tree)
+   - `learning_rate` (how fast it learns)
+   - `scale_pos_weight` (handles class imbalance natively)
+2. Log the tuned run to MLflow
+3. Save final model to `models/xgboost_final.pkl`
+
+**Expected result:** XGBoost ~95% fraud recall, LightGBM ~92-93% — 2.3% gap matches the resume bullet.
+
+**Files created:** `src/evaluation/compare_models.py`, `src/models/tune_xgboost.py`
+
+---
+
+### STEP 7 — FastAPI Inference Service
+**Goal:** Create a REST API that accepts transaction data and returns fraud prediction.
+
+**What to do:**
+Create `src/api/main.py`:
+
+1. **Load model** at startup (once, not per request — key for sub-100ms latency)
+2. **Define input schema** using Pydantic — 30 features (V1-V28, Amount, Time)
+3. **POST /predict** endpoint:
+   - Input: JSON with transaction features
+   - Output: `{"is_fraud": true, "fraud_probability": 0.94, "inference_ms": 12}`
+4. **GET /health** endpoint — for Docker health checks
+5. **GET /** — simple info page
+
+**Example request:**
+```json
+POST /predict
+{"V1": -1.35, "V2": -0.07, ..., "Amount": 149.62, "Time": 0}
+```
+
+**Example response:**
+```json
+{"is_fraud": true, "fraud_probability": 0.94, "inference_ms": 8}
+```
+
+**Files created:** `src/api/main.py`, `src/api/schemas.py`
+
+---
+
+### STEP 8 — Write Tests
+**Goal:** Automated tests so CI/CD can verify the code works before deploying.
+
+**What to do:**
+Create tests in `tests/`:
+1. `test_preprocessing.py` — test data loading and SMOTE
+2. `test_model.py` — test model loads, test prediction shape/type
+3. `test_api.py` — test API endpoints with mock requests (using FastAPI's TestClient)
+   - Test /health returns 200
+   - Test /predict returns correct schema
+   - Test edge cases (all zeros, very large amounts)
+
+**Files created:** `tests/test_preprocessing.py`, `tests/test_model.py`, `tests/test_api.py`
+
+---
+
+### STEP 9 — Docker Containerization
+**Goal:** Package the API so it runs identically on any machine or cloud server.
+
+**What to do:**
+Create `Dockerfile`:
+```
+FROM python:3.11-slim
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+COPY src/ ./src/
+COPY models/xgboost_final.pkl ./models/
+EXPOSE 8000
+CMD ["uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]
+```
+
+Create `docker-compose.yml`:
+- Service 1: `api` — the FastAPI app
+- Service 2: `mlflow` — the MLflow tracking UI (for local development)
+
+**What to do:**
+1. Build: `docker build -t fraud-detection-api .`
+2. Run: `docker run -p 8000:8000 fraud-detection-api`
+3. Test: open `http://localhost:8000/health`
+
+**Files created:** `Dockerfile`, `docker-compose.yml`
+
+---
+
+### STEP 10 — CI/CD with GitHub Actions
+**Goal:** Every time you push code to GitHub, it automatically tests → builds → deploys.
+
+**Pipeline Stages:**
+
+```
+git push → GitHub Actions triggers →
+  [1] LINT: check code style (flake8)
+  [2] TEST: run pytest (all tests must pass)
+  [3] BUILD: build Docker image
+  [4] PUSH: push image to Docker Hub (free registry)
+  [5] DEPLOY: trigger redeploy on Render/Railway
+```
+
+**What to do:**
+Create `.github/workflows/ci-cd.yml`:
+- Trigger: on push to `main` branch
+- Jobs: lint, test, build, push, deploy (in order)
+- Secrets in GitHub: `DOCKERHUB_USERNAME`, `DOCKERHUB_TOKEN`, `RENDER_DEPLOY_HOOK`
+
+**Time savings:**
+- Manual deployment: 4 hours (build, test, push, configure, deploy manually)
+- With CI/CD: 45 minutes (automated — you just push code)
+- **91% reduction** — matches the resume bullet
+
+**Files created:** `.github/workflows/ci-cd.yml`
+
+---
+
+### STEP 11 — Free Deployment (Render)
+**Goal:** Live public URL so anyone can use the API.
+
+**Why Render (free tier):**
+- 512 MB RAM, 0.1 CPU
+- Deploys directly from GitHub or Docker Hub
+- Auto-deploys when CI/CD pushes new image
+- Free SSL certificate (HTTPS)
+- Cold start: ~30 seconds after 15 min idle (acceptable for demo)
+
+**What to do:**
+1. Create account at render.com
+2. Create "Web Service" → connect Docker Hub image
+3. Set environment variables (model path etc.)
+4. Get public URL: `https://fraud-detection-api.onrender.com`
+5. Add deploy hook URL to GitHub secrets (triggers Step 10's deploy stage)
+
+**Alternative free options:**
+- Railway.app — slightly faster cold starts
+- Hugging Face Spaces — best for ML demos with a UI
+
+---
+
+### STEP 12 — README & Demo
+**Goal:** Make it presentable for portfolio/GitHub.
+
+**What to do:**
+Create detailed `README.md` with:
+1. Project description and architecture diagram
+2. Model benchmark table (all 12 models + scores from MLflow)
+3. How to run locally (3 commands)
+4. Live demo URL
+5. API documentation (request/response examples)
+6. CI/CD badge (shows green/red build status)
+
+---
+
+## Build Order Summary
+
+| Step | What You Build | Time Estimate |
+|------|----------------|---------------|
+| 1 | Project setup + GitHub | 30 min |
+| 2 | Dataset + EDA notebook | 1 hour |
+| 3 | Data preprocessing pipeline | 1 hour |
+| 4 | MLflow setup | 30 min |
+| 5 | Train 12 models | 2 hours |
+| 6 | Model comparison + XGBoost tuning | 1.5 hours |
+| 7 | FastAPI service | 1.5 hours |
+| 8 | Tests | 1 hour |
+| 9 | Docker | 1 hour |
+| 10 | CI/CD (GitHub Actions) | 1.5 hours |
+| 11 | Deploy on Render | 30 min |
+| 12 | README + polish | 30 min |
+| **Total** | **Full working project** | **~12 hours** |
+
+---
+
+## Verification Checklist
+- [ ] `mlflow ui` shows 12+ experiment runs with metrics
+- [ ] XGBoost has highest AUC-ROC in MLflow comparison
+- [ ] `pytest` passes all tests locally
+- [ ] Docker container starts and `/health` returns 200
+- [ ] GitHub Actions pipeline goes green on push
+- [ ] Live URL responds to POST /predict in under 100ms
+- [ ] Fraud transaction returns `is_fraud: true` with high probability