adpretko's picture
Upload fine-tuned riscv-O2 model
fb67044 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9558615364817913,
"eval_steps": 500,
"global_step": 3800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0051473426843392095,
"grad_norm": 5.310028553009033,
"learning_rate": 4.6272493573264783e-07,
"loss": 0.5767,
"step": 10
},
{
"epoch": 0.010294685368678419,
"grad_norm": 3.2451159954071045,
"learning_rate": 9.768637532133676e-07,
"loss": 0.5436,
"step": 20
},
{
"epoch": 0.01544202805301763,
"grad_norm": 2.6238412857055664,
"learning_rate": 1.4910025706940876e-06,
"loss": 0.4248,
"step": 30
},
{
"epoch": 0.020589370737356838,
"grad_norm": 1.1435836553573608,
"learning_rate": 2.0051413881748076e-06,
"loss": 0.2565,
"step": 40
},
{
"epoch": 0.02573671342169605,
"grad_norm": 0.6369749307632446,
"learning_rate": 2.519280205655527e-06,
"loss": 0.1546,
"step": 50
},
{
"epoch": 0.03088405610603526,
"grad_norm": 0.31389811635017395,
"learning_rate": 3.033419023136247e-06,
"loss": 0.1188,
"step": 60
},
{
"epoch": 0.036031398790374466,
"grad_norm": 0.23692786693572998,
"learning_rate": 3.547557840616967e-06,
"loss": 0.1005,
"step": 70
},
{
"epoch": 0.041178741474713676,
"grad_norm": 0.17490938305854797,
"learning_rate": 4.0616966580976866e-06,
"loss": 0.0885,
"step": 80
},
{
"epoch": 0.04632608415905289,
"grad_norm": 0.16715744137763977,
"learning_rate": 4.575835475578407e-06,
"loss": 0.078,
"step": 90
},
{
"epoch": 0.0514734268433921,
"grad_norm": 0.168691024184227,
"learning_rate": 5.0899742930591265e-06,
"loss": 0.0728,
"step": 100
},
{
"epoch": 0.05662076952773131,
"grad_norm": 0.1685110628604889,
"learning_rate": 5.604113110539846e-06,
"loss": 0.0652,
"step": 110
},
{
"epoch": 0.06176811221207052,
"grad_norm": 0.14894704520702362,
"learning_rate": 6.1182519280205664e-06,
"loss": 0.0611,
"step": 120
},
{
"epoch": 0.06691545489640972,
"grad_norm": 0.17869767546653748,
"learning_rate": 6.632390745501286e-06,
"loss": 0.0578,
"step": 130
},
{
"epoch": 0.07206279758074893,
"grad_norm": 0.2117505520582199,
"learning_rate": 7.1465295629820055e-06,
"loss": 0.0565,
"step": 140
},
{
"epoch": 0.07721014026508814,
"grad_norm": 0.2170065939426422,
"learning_rate": 7.660668380462726e-06,
"loss": 0.0518,
"step": 150
},
{
"epoch": 0.08235748294942735,
"grad_norm": 0.20486794412136078,
"learning_rate": 8.174807197943445e-06,
"loss": 0.0506,
"step": 160
},
{
"epoch": 0.08750482563376656,
"grad_norm": 0.1600036472082138,
"learning_rate": 8.688946015424165e-06,
"loss": 0.0505,
"step": 170
},
{
"epoch": 0.09265216831810578,
"grad_norm": 0.18623106181621552,
"learning_rate": 9.203084832904885e-06,
"loss": 0.0454,
"step": 180
},
{
"epoch": 0.097799511002445,
"grad_norm": 0.16273102164268494,
"learning_rate": 9.717223650385606e-06,
"loss": 0.0443,
"step": 190
},
{
"epoch": 0.1029468536867842,
"grad_norm": 0.2154380977153778,
"learning_rate": 1.0231362467866324e-05,
"loss": 0.0421,
"step": 200
},
{
"epoch": 0.10809419637112341,
"grad_norm": 0.15672603249549866,
"learning_rate": 1.0745501285347045e-05,
"loss": 0.0413,
"step": 210
},
{
"epoch": 0.11324153905546262,
"grad_norm": 0.16729186475276947,
"learning_rate": 1.1259640102827764e-05,
"loss": 0.04,
"step": 220
},
{
"epoch": 0.11838888173980183,
"grad_norm": 0.17069196701049805,
"learning_rate": 1.1773778920308486e-05,
"loss": 0.04,
"step": 230
},
{
"epoch": 0.12353622442414104,
"grad_norm": 0.18878957629203796,
"learning_rate": 1.2287917737789203e-05,
"loss": 0.0379,
"step": 240
},
{
"epoch": 0.12868356710848025,
"grad_norm": 0.17584006488323212,
"learning_rate": 1.2802056555269925e-05,
"loss": 0.0361,
"step": 250
},
{
"epoch": 0.13383090979281945,
"grad_norm": 0.19568656384944916,
"learning_rate": 1.3316195372750644e-05,
"loss": 0.0348,
"step": 260
},
{
"epoch": 0.13897825247715867,
"grad_norm": 0.17687125504016876,
"learning_rate": 1.3830334190231362e-05,
"loss": 0.0344,
"step": 270
},
{
"epoch": 0.14412559516149787,
"grad_norm": 0.18790054321289062,
"learning_rate": 1.4344473007712083e-05,
"loss": 0.0334,
"step": 280
},
{
"epoch": 0.1492729378458371,
"grad_norm": 0.174034982919693,
"learning_rate": 1.4858611825192803e-05,
"loss": 0.0343,
"step": 290
},
{
"epoch": 0.15442028053017628,
"grad_norm": 0.17310510575771332,
"learning_rate": 1.5372750642673522e-05,
"loss": 0.033,
"step": 300
},
{
"epoch": 0.1595676232145155,
"grad_norm": 0.16747431457042694,
"learning_rate": 1.5886889460154242e-05,
"loss": 0.0321,
"step": 310
},
{
"epoch": 0.1647149658988547,
"grad_norm": 0.19836604595184326,
"learning_rate": 1.640102827763496e-05,
"loss": 0.0321,
"step": 320
},
{
"epoch": 0.16986230858319393,
"grad_norm": 0.16714957356452942,
"learning_rate": 1.6915167095115684e-05,
"loss": 0.0314,
"step": 330
},
{
"epoch": 0.17500965126753312,
"grad_norm": 0.15047457814216614,
"learning_rate": 1.74293059125964e-05,
"loss": 0.03,
"step": 340
},
{
"epoch": 0.18015699395187235,
"grad_norm": 0.153594508767128,
"learning_rate": 1.7943444730077123e-05,
"loss": 0.0307,
"step": 350
},
{
"epoch": 0.18530433663621157,
"grad_norm": 0.11620394140481949,
"learning_rate": 1.8457583547557843e-05,
"loss": 0.0288,
"step": 360
},
{
"epoch": 0.19045167932055077,
"grad_norm": 0.19321905076503754,
"learning_rate": 1.8971722365038563e-05,
"loss": 0.0295,
"step": 370
},
{
"epoch": 0.19559902200489,
"grad_norm": 0.15826652944087982,
"learning_rate": 1.9485861182519282e-05,
"loss": 0.0288,
"step": 380
},
{
"epoch": 0.20074636468922918,
"grad_norm": 0.1474819928407669,
"learning_rate": 2e-05,
"loss": 0.0287,
"step": 390
},
{
"epoch": 0.2058937073735684,
"grad_norm": 0.15279045701026917,
"learning_rate": 1.999959647024453e-05,
"loss": 0.0286,
"step": 400
},
{
"epoch": 0.2110410500579076,
"grad_norm": 0.1290847510099411,
"learning_rate": 1.999838591354537e-05,
"loss": 0.0269,
"step": 410
},
{
"epoch": 0.21618839274224683,
"grad_norm": 0.14468011260032654,
"learning_rate": 1.9996368427601652e-05,
"loss": 0.0272,
"step": 420
},
{
"epoch": 0.22133573542658602,
"grad_norm": 0.15097224712371826,
"learning_rate": 1.9993544175236498e-05,
"loss": 0.0263,
"step": 430
},
{
"epoch": 0.22648307811092525,
"grad_norm": 0.14941558241844177,
"learning_rate": 1.998991338438388e-05,
"loss": 0.0265,
"step": 440
},
{
"epoch": 0.23163042079526444,
"grad_norm": 0.12265824526548386,
"learning_rate": 1.9985476348070224e-05,
"loss": 0.0253,
"step": 450
},
{
"epoch": 0.23677776347960366,
"grad_norm": 0.13813571631908417,
"learning_rate": 1.9980233424390773e-05,
"loss": 0.0259,
"step": 460
},
{
"epoch": 0.24192510616394286,
"grad_norm": 0.13315853476524353,
"learning_rate": 1.9974185036480664e-05,
"loss": 0.025,
"step": 470
},
{
"epoch": 0.24707244884828208,
"grad_norm": 0.10484486818313599,
"learning_rate": 1.9967331672480798e-05,
"loss": 0.0253,
"step": 480
},
{
"epoch": 0.2522197915326213,
"grad_norm": 0.10516864061355591,
"learning_rate": 1.995967388549843e-05,
"loss": 0.0236,
"step": 490
},
{
"epoch": 0.2573671342169605,
"grad_norm": 0.13143527507781982,
"learning_rate": 1.9951212293562547e-05,
"loss": 0.0247,
"step": 500
},
{
"epoch": 0.2625144769012997,
"grad_norm": 0.11734788864850998,
"learning_rate": 1.994194757957397e-05,
"loss": 0.0239,
"step": 510
},
{
"epoch": 0.2676618195856389,
"grad_norm": 0.10932901501655579,
"learning_rate": 1.9931880491250263e-05,
"loss": 0.0237,
"step": 520
},
{
"epoch": 0.27280916226997814,
"grad_norm": 0.10849976539611816,
"learning_rate": 1.992101184106535e-05,
"loss": 0.0238,
"step": 530
},
{
"epoch": 0.27795650495431734,
"grad_norm": 0.10729847103357315,
"learning_rate": 1.990934250618399e-05,
"loss": 0.0247,
"step": 540
},
{
"epoch": 0.28310384763865654,
"grad_norm": 0.10003025084733963,
"learning_rate": 1.989687342839095e-05,
"loss": 0.0226,
"step": 550
},
{
"epoch": 0.28825119032299573,
"grad_norm": 0.1534651517868042,
"learning_rate": 1.9883605614015014e-05,
"loss": 0.0231,
"step": 560
},
{
"epoch": 0.293398533007335,
"grad_norm": 0.11108533293008804,
"learning_rate": 1.986954013384776e-05,
"loss": 0.0223,
"step": 570
},
{
"epoch": 0.2985458756916742,
"grad_norm": 0.11034880578517914,
"learning_rate": 1.9854678123057144e-05,
"loss": 0.0231,
"step": 580
},
{
"epoch": 0.3036932183760134,
"grad_norm": 0.1124214380979538,
"learning_rate": 1.9839020781095873e-05,
"loss": 0.0218,
"step": 590
},
{
"epoch": 0.30884056106035257,
"grad_norm": 0.10357758402824402,
"learning_rate": 1.9822569371604637e-05,
"loss": 0.0223,
"step": 600
},
{
"epoch": 0.3139879037446918,
"grad_norm": 0.10687187314033508,
"learning_rate": 1.9805325222310072e-05,
"loss": 0.0207,
"step": 610
},
{
"epoch": 0.319135246429031,
"grad_norm": 0.11198052763938904,
"learning_rate": 1.9787289724917657e-05,
"loss": 0.0217,
"step": 620
},
{
"epoch": 0.3242825891133702,
"grad_norm": 0.10764071345329285,
"learning_rate": 1.9768464334999352e-05,
"loss": 0.0203,
"step": 630
},
{
"epoch": 0.3294299317977094,
"grad_norm": 0.11469001322984695,
"learning_rate": 1.974885057187617e-05,
"loss": 0.0209,
"step": 640
},
{
"epoch": 0.33457727448204866,
"grad_norm": 0.10319452732801437,
"learning_rate": 1.9728450018495506e-05,
"loss": 0.0211,
"step": 650
},
{
"epoch": 0.33972461716638785,
"grad_norm": 0.1113303154706955,
"learning_rate": 1.9707264321303427e-05,
"loss": 0.021,
"step": 660
},
{
"epoch": 0.34487195985072705,
"grad_norm": 0.10461831837892532,
"learning_rate": 1.9685295190111777e-05,
"loss": 0.0204,
"step": 670
},
{
"epoch": 0.35001930253506625,
"grad_norm": 0.11531244963407516,
"learning_rate": 1.9662544397960182e-05,
"loss": 0.0202,
"step": 680
},
{
"epoch": 0.3551666452194055,
"grad_norm": 0.09318046271800995,
"learning_rate": 1.9639013780972958e-05,
"loss": 0.0205,
"step": 690
},
{
"epoch": 0.3603139879037447,
"grad_norm": 0.10880846530199051,
"learning_rate": 1.961470523821093e-05,
"loss": 0.0206,
"step": 700
},
{
"epoch": 0.3654613305880839,
"grad_norm": 0.1059744656085968,
"learning_rate": 1.9589620731518166e-05,
"loss": 0.02,
"step": 710
},
{
"epoch": 0.37060867327242314,
"grad_norm": 0.09044791013002396,
"learning_rate": 1.956376228536363e-05,
"loss": 0.0197,
"step": 720
},
{
"epoch": 0.37575601595676233,
"grad_norm": 0.08193252235651016,
"learning_rate": 1.953713198667782e-05,
"loss": 0.0203,
"step": 730
},
{
"epoch": 0.38090335864110153,
"grad_norm": 0.10840420424938202,
"learning_rate": 1.950973198468431e-05,
"loss": 0.0196,
"step": 740
},
{
"epoch": 0.3860507013254407,
"grad_norm": 0.10423741489648819,
"learning_rate": 1.9481564490726327e-05,
"loss": 0.0202,
"step": 750
},
{
"epoch": 0.39119804400978,
"grad_norm": 0.09768087416887283,
"learning_rate": 1.9452631778088262e-05,
"loss": 0.0192,
"step": 760
},
{
"epoch": 0.3963453866941192,
"grad_norm": 0.09175275266170502,
"learning_rate": 1.94229361818122e-05,
"loss": 0.0193,
"step": 770
},
{
"epoch": 0.40149272937845837,
"grad_norm": 0.10638079047203064,
"learning_rate": 1.9392480098509488e-05,
"loss": 0.0193,
"step": 780
},
{
"epoch": 0.40664007206279756,
"grad_norm": 0.0991005077958107,
"learning_rate": 1.9361265986167292e-05,
"loss": 0.0195,
"step": 790
},
{
"epoch": 0.4117874147471368,
"grad_norm": 0.09562570601701736,
"learning_rate": 1.9329296363950237e-05,
"loss": 0.0192,
"step": 800
},
{
"epoch": 0.416934757431476,
"grad_norm": 0.08249165862798691,
"learning_rate": 1.929657381199709e-05,
"loss": 0.0194,
"step": 810
},
{
"epoch": 0.4220821001158152,
"grad_norm": 0.08570217341184616,
"learning_rate": 1.9263100971212533e-05,
"loss": 0.0195,
"step": 820
},
{
"epoch": 0.4272294428001544,
"grad_norm": 0.09742734581232071,
"learning_rate": 1.922888054305401e-05,
"loss": 0.0192,
"step": 830
},
{
"epoch": 0.43237678548449365,
"grad_norm": 0.0958111509680748,
"learning_rate": 1.9193915289313726e-05,
"loss": 0.0186,
"step": 840
},
{
"epoch": 0.43752412816883285,
"grad_norm": 0.10406336188316345,
"learning_rate": 1.9158208031895738e-05,
"loss": 0.0182,
"step": 850
},
{
"epoch": 0.44267147085317204,
"grad_norm": 0.09037433564662933,
"learning_rate": 1.9121761652588217e-05,
"loss": 0.0188,
"step": 860
},
{
"epoch": 0.44781881353751124,
"grad_norm": 0.09204918146133423,
"learning_rate": 1.9084579092830873e-05,
"loss": 0.0182,
"step": 870
},
{
"epoch": 0.4529661562218505,
"grad_norm": 0.07945096492767334,
"learning_rate": 1.904666335347755e-05,
"loss": 0.017,
"step": 880
},
{
"epoch": 0.4581134989061897,
"grad_norm": 2.817049980163574,
"learning_rate": 1.900801749455406e-05,
"loss": 0.0223,
"step": 890
},
{
"epoch": 0.4632608415905289,
"grad_norm": 1.0506891012191772,
"learning_rate": 1.8968644635011192e-05,
"loss": 0.0434,
"step": 900
},
{
"epoch": 0.4684081842748681,
"grad_norm": 0.23307710886001587,
"learning_rate": 1.8928547952473037e-05,
"loss": 0.0308,
"step": 910
},
{
"epoch": 0.47355552695920733,
"grad_norm": 0.11467685550451279,
"learning_rate": 1.8887730682980484e-05,
"loss": 0.0234,
"step": 920
},
{
"epoch": 0.4787028696435465,
"grad_norm": 0.11315492540597916,
"learning_rate": 1.8846196120730095e-05,
"loss": 0.0222,
"step": 930
},
{
"epoch": 0.4838502123278857,
"grad_norm": 0.08601980656385422,
"learning_rate": 1.8803947617808217e-05,
"loss": 0.0219,
"step": 940
},
{
"epoch": 0.4889975550122249,
"grad_norm": 0.08733567595481873,
"learning_rate": 1.8760988583920457e-05,
"loss": 0.0197,
"step": 950
},
{
"epoch": 0.49414489769656417,
"grad_norm": 0.0972953736782074,
"learning_rate": 1.8717322486116513e-05,
"loss": 0.019,
"step": 960
},
{
"epoch": 0.49929224038090336,
"grad_norm": 0.08496998995542526,
"learning_rate": 1.867295284851033e-05,
"loss": 0.0186,
"step": 970
},
{
"epoch": 0.5044395830652426,
"grad_norm": 0.09595049172639847,
"learning_rate": 1.8627883251995712e-05,
"loss": 0.019,
"step": 980
},
{
"epoch": 0.5095869257495818,
"grad_norm": 0.10503372550010681,
"learning_rate": 1.858211733395731e-05,
"loss": 0.0175,
"step": 990
},
{
"epoch": 0.514734268433921,
"grad_norm": 0.07223546504974365,
"learning_rate": 1.8535658787977076e-05,
"loss": 0.0187,
"step": 1000
},
{
"epoch": 0.5198816111182601,
"grad_norm": 0.07786504924297333,
"learning_rate": 1.848851136353614e-05,
"loss": 0.0176,
"step": 1010
},
{
"epoch": 0.5250289538025994,
"grad_norm": 0.08368386328220367,
"learning_rate": 1.8440678865712237e-05,
"loss": 0.0171,
"step": 1020
},
{
"epoch": 0.5301762964869386,
"grad_norm": 0.08910104632377625,
"learning_rate": 1.8392165154872596e-05,
"loss": 0.0173,
"step": 1030
},
{
"epoch": 0.5353236391712778,
"grad_norm": 0.07958846539258957,
"learning_rate": 1.8342974146362397e-05,
"loss": 0.0171,
"step": 1040
},
{
"epoch": 0.540470981855617,
"grad_norm": 0.08344627916812897,
"learning_rate": 1.8293109810188756e-05,
"loss": 0.0179,
"step": 1050
},
{
"epoch": 0.5456183245399563,
"grad_norm": 0.09093711525201797,
"learning_rate": 1.8242576170700356e-05,
"loss": 0.0182,
"step": 1060
},
{
"epoch": 0.5507656672242954,
"grad_norm": 0.07439770549535751,
"learning_rate": 1.8191377306262635e-05,
"loss": 0.0177,
"step": 1070
},
{
"epoch": 0.5559130099086347,
"grad_norm": 0.07276415079832077,
"learning_rate": 1.813951734892864e-05,
"loss": 0.017,
"step": 1080
},
{
"epoch": 0.5610603525929739,
"grad_norm": 0.07302267104387283,
"learning_rate": 1.808700048410555e-05,
"loss": 0.0173,
"step": 1090
},
{
"epoch": 0.5662076952773131,
"grad_norm": 0.07959124445915222,
"learning_rate": 1.80338309502169e-05,
"loss": 0.0171,
"step": 1100
},
{
"epoch": 0.5713550379616523,
"grad_norm": 0.07042378187179565,
"learning_rate": 1.798001303836048e-05,
"loss": 0.0177,
"step": 1110
},
{
"epoch": 0.5765023806459915,
"grad_norm": 0.07214156538248062,
"learning_rate": 1.792555109196205e-05,
"loss": 0.0176,
"step": 1120
},
{
"epoch": 0.5816497233303307,
"grad_norm": 0.08310863375663757,
"learning_rate": 1.7870449506424802e-05,
"loss": 0.0168,
"step": 1130
},
{
"epoch": 0.58679706601467,
"grad_norm": 0.07772408425807953,
"learning_rate": 1.7814712728774602e-05,
"loss": 0.0161,
"step": 1140
},
{
"epoch": 0.5919444086990091,
"grad_norm": 0.07578866183757782,
"learning_rate": 1.7758345257301097e-05,
"loss": 0.0163,
"step": 1150
},
{
"epoch": 0.5970917513833484,
"grad_norm": 0.07637569308280945,
"learning_rate": 1.770135164119468e-05,
"loss": 0.017,
"step": 1160
},
{
"epoch": 0.6022390940676876,
"grad_norm": 0.07771653681993484,
"learning_rate": 1.7643736480179353e-05,
"loss": 0.0161,
"step": 1170
},
{
"epoch": 0.6073864367520267,
"grad_norm": 0.07540572434663773,
"learning_rate": 1.7585504424141483e-05,
"loss": 0.0162,
"step": 1180
},
{
"epoch": 0.612533779436366,
"grad_norm": 0.08060440421104431,
"learning_rate": 1.752666017275453e-05,
"loss": 0.0167,
"step": 1190
},
{
"epoch": 0.6176811221207051,
"grad_norm": 0.08262394368648529,
"learning_rate": 1.7467208475099777e-05,
"loss": 0.0164,
"step": 1200
},
{
"epoch": 0.6228284648050444,
"grad_norm": 0.09898388385772705,
"learning_rate": 1.740715412928302e-05,
"loss": 0.0161,
"step": 1210
},
{
"epoch": 0.6279758074893836,
"grad_norm": 0.08121711760759354,
"learning_rate": 1.734650198204736e-05,
"loss": 0.0158,
"step": 1220
},
{
"epoch": 0.6331231501737228,
"grad_norm": 0.08025297522544861,
"learning_rate": 1.7285256928382024e-05,
"loss": 0.0156,
"step": 1230
},
{
"epoch": 0.638270492858062,
"grad_norm": 0.07479096949100494,
"learning_rate": 1.7223423911127315e-05,
"loss": 0.0176,
"step": 1240
},
{
"epoch": 0.6434178355424013,
"grad_norm": 0.08772420138120651,
"learning_rate": 1.7161007920575705e-05,
"loss": 0.0156,
"step": 1250
},
{
"epoch": 0.6485651782267404,
"grad_norm": 0.07971519976854324,
"learning_rate": 1.709801399406907e-05,
"loss": 0.0154,
"step": 1260
},
{
"epoch": 0.6537125209110797,
"grad_norm": 0.07564999163150787,
"learning_rate": 1.7034447215592168e-05,
"loss": 0.0154,
"step": 1270
},
{
"epoch": 0.6588598635954188,
"grad_norm": 0.07267491519451141,
"learning_rate": 1.6970312715362304e-05,
"loss": 0.0159,
"step": 1280
},
{
"epoch": 0.6640072062797581,
"grad_norm": 0.07202299684286118,
"learning_rate": 1.6905615669415326e-05,
"loss": 0.0164,
"step": 1290
},
{
"epoch": 0.6691545489640973,
"grad_norm": 0.07982448488473892,
"learning_rate": 1.684036129918786e-05,
"loss": 0.0155,
"step": 1300
},
{
"epoch": 0.6743018916484365,
"grad_norm": 0.07582129538059235,
"learning_rate": 1.6774554871095918e-05,
"loss": 0.0153,
"step": 1310
},
{
"epoch": 0.6794492343327757,
"grad_norm": 0.08038461208343506,
"learning_rate": 1.6708201696109857e-05,
"loss": 0.0158,
"step": 1320
},
{
"epoch": 0.684596577017115,
"grad_norm": 0.07446227967739105,
"learning_rate": 1.6641307129325785e-05,
"loss": 0.0164,
"step": 1330
},
{
"epoch": 0.6897439197014541,
"grad_norm": 0.0867164209485054,
"learning_rate": 1.657387656953333e-05,
"loss": 0.016,
"step": 1340
},
{
"epoch": 0.6948912623857934,
"grad_norm": 0.07672440260648727,
"learning_rate": 1.6505915458779958e-05,
"loss": 0.0153,
"step": 1350
},
{
"epoch": 0.7000386050701325,
"grad_norm": 0.07314340770244598,
"learning_rate": 1.6437429281931744e-05,
"loss": 0.0145,
"step": 1360
},
{
"epoch": 0.7051859477544717,
"grad_norm": 0.07686632126569748,
"learning_rate": 1.636842356623073e-05,
"loss": 0.0152,
"step": 1370
},
{
"epoch": 0.710333290438811,
"grad_norm": 0.07814227044582367,
"learning_rate": 1.6298903880848836e-05,
"loss": 0.0155,
"step": 1380
},
{
"epoch": 0.7154806331231501,
"grad_norm": 0.07057350873947144,
"learning_rate": 1.6228875836438386e-05,
"loss": 0.0152,
"step": 1390
},
{
"epoch": 0.7206279758074894,
"grad_norm": 0.06801946461200714,
"learning_rate": 1.615834508467931e-05,
"loss": 0.0148,
"step": 1400
},
{
"epoch": 0.7257753184918286,
"grad_norm": 0.08162187039852142,
"learning_rate": 1.608731731782301e-05,
"loss": 0.0156,
"step": 1410
},
{
"epoch": 0.7309226611761678,
"grad_norm": 0.09547685086727142,
"learning_rate": 1.6015798268232964e-05,
"loss": 0.0158,
"step": 1420
},
{
"epoch": 0.736070003860507,
"grad_norm": 0.07891667634248734,
"learning_rate": 1.5943793707922086e-05,
"loss": 0.0144,
"step": 1430
},
{
"epoch": 0.7412173465448463,
"grad_norm": 0.07318150252103806,
"learning_rate": 1.5871309448086903e-05,
"loss": 0.0158,
"step": 1440
},
{
"epoch": 0.7463646892291854,
"grad_norm": 0.06992822885513306,
"learning_rate": 1.5798351338638548e-05,
"loss": 0.0148,
"step": 1450
},
{
"epoch": 0.7515120319135247,
"grad_norm": 0.0747927725315094,
"learning_rate": 1.5724925267730625e-05,
"loss": 0.0156,
"step": 1460
},
{
"epoch": 0.7566593745978638,
"grad_norm": 0.06734950840473175,
"learning_rate": 1.5651037161284032e-05,
"loss": 0.0155,
"step": 1470
},
{
"epoch": 0.7618067172822031,
"grad_norm": 0.06667228043079376,
"learning_rate": 1.5576692982508665e-05,
"loss": 0.0149,
"step": 1480
},
{
"epoch": 0.7669540599665423,
"grad_norm": 0.07065103948116302,
"learning_rate": 1.550189873142219e-05,
"loss": 0.0149,
"step": 1490
},
{
"epoch": 0.7721014026508815,
"grad_norm": 0.07318428158760071,
"learning_rate": 1.542666044436577e-05,
"loss": 0.0147,
"step": 1500
},
{
"epoch": 0.7772487453352207,
"grad_norm": 0.06767120212316513,
"learning_rate": 1.5350984193516917e-05,
"loss": 0.0152,
"step": 1510
},
{
"epoch": 0.78239608801956,
"grad_norm": 0.08945749700069427,
"learning_rate": 1.5274876086399444e-05,
"loss": 0.0147,
"step": 1520
},
{
"epoch": 0.7875434307038991,
"grad_norm": 0.07100491225719452,
"learning_rate": 1.5198342265390511e-05,
"loss": 0.0144,
"step": 1530
},
{
"epoch": 0.7926907733882383,
"grad_norm": 0.06846942007541656,
"learning_rate": 1.512138890722494e-05,
"loss": 0.0148,
"step": 1540
},
{
"epoch": 0.7978381160725775,
"grad_norm": 0.07432665675878525,
"learning_rate": 1.5044022222496684e-05,
"loss": 0.0153,
"step": 1550
},
{
"epoch": 0.8029854587569167,
"grad_norm": 0.06611491739749908,
"learning_rate": 1.4966248455157622e-05,
"loss": 0.0143,
"step": 1560
},
{
"epoch": 0.808132801441256,
"grad_norm": 0.07415001094341278,
"learning_rate": 1.4888073882013616e-05,
"loss": 0.0143,
"step": 1570
},
{
"epoch": 0.8132801441255951,
"grad_norm": 0.06780339032411575,
"learning_rate": 1.480950481221795e-05,
"loss": 0.0145,
"step": 1580
},
{
"epoch": 0.8184274868099344,
"grad_norm": 0.07141536474227905,
"learning_rate": 1.4730547586762114e-05,
"loss": 0.0139,
"step": 1590
},
{
"epoch": 0.8235748294942736,
"grad_norm": 0.07404403388500214,
"learning_rate": 1.4651208577964099e-05,
"loss": 0.0149,
"step": 1600
},
{
"epoch": 0.8287221721786128,
"grad_norm": 0.07202573120594025,
"learning_rate": 1.4571494188954058e-05,
"loss": 0.0149,
"step": 1610
},
{
"epoch": 0.833869514862952,
"grad_norm": 0.055626142770051956,
"learning_rate": 1.4491410853157577e-05,
"loss": 0.014,
"step": 1620
},
{
"epoch": 0.8390168575472912,
"grad_norm": 0.06371673196554184,
"learning_rate": 1.4410965033776439e-05,
"loss": 0.0146,
"step": 1630
},
{
"epoch": 0.8441642002316304,
"grad_norm": 0.0604044534265995,
"learning_rate": 1.4330163223267005e-05,
"loss": 0.0147,
"step": 1640
},
{
"epoch": 0.8493115429159697,
"grad_norm": 0.07098476588726044,
"learning_rate": 1.4249011942816245e-05,
"loss": 0.0148,
"step": 1650
},
{
"epoch": 0.8544588856003088,
"grad_norm": 0.06837648898363113,
"learning_rate": 1.416751774181543e-05,
"loss": 0.0144,
"step": 1660
},
{
"epoch": 0.859606228284648,
"grad_norm": 0.06875620782375336,
"learning_rate": 1.4085687197331559e-05,
"loss": 0.0143,
"step": 1670
},
{
"epoch": 0.8647535709689873,
"grad_norm": 0.0676610991358757,
"learning_rate": 1.4003526913576555e-05,
"loss": 0.0152,
"step": 1680
},
{
"epoch": 0.8699009136533264,
"grad_norm": 0.06219542399048805,
"learning_rate": 1.392104352137426e-05,
"loss": 0.0137,
"step": 1690
},
{
"epoch": 0.8750482563376657,
"grad_norm": 0.06112512946128845,
"learning_rate": 1.3838243677625292e-05,
"loss": 0.0145,
"step": 1700
},
{
"epoch": 0.8801955990220048,
"grad_norm": 0.07453671842813492,
"learning_rate": 1.3755134064769788e-05,
"loss": 0.0144,
"step": 1710
},
{
"epoch": 0.8853429417063441,
"grad_norm": 0.07224484533071518,
"learning_rate": 1.36717213902481e-05,
"loss": 0.0138,
"step": 1720
},
{
"epoch": 0.8904902843906833,
"grad_norm": 0.06484848260879517,
"learning_rate": 1.3588012385959464e-05,
"loss": 0.0148,
"step": 1730
},
{
"epoch": 0.8956376270750225,
"grad_norm": 0.06340837478637695,
"learning_rate": 1.350401380771868e-05,
"loss": 0.014,
"step": 1740
},
{
"epoch": 0.9007849697593617,
"grad_norm": 0.06442750245332718,
"learning_rate": 1.3419732434710895e-05,
"loss": 0.0134,
"step": 1750
},
{
"epoch": 0.905932312443701,
"grad_norm": 0.06431768089532852,
"learning_rate": 1.333517506894448e-05,
"loss": 0.0144,
"step": 1760
},
{
"epoch": 0.9110796551280401,
"grad_norm": 0.06857169419527054,
"learning_rate": 1.3250348534702063e-05,
"loss": 0.0141,
"step": 1770
},
{
"epoch": 0.9162269978123794,
"grad_norm": 0.07051096856594086,
"learning_rate": 1.316525967798976e-05,
"loss": 0.0141,
"step": 1780
},
{
"epoch": 0.9213743404967185,
"grad_norm": 0.07205208390951157,
"learning_rate": 1.307991536598469e-05,
"loss": 0.0146,
"step": 1790
},
{
"epoch": 0.9265216831810578,
"grad_norm": 0.07224377989768982,
"learning_rate": 1.2994322486480716e-05,
"loss": 0.0137,
"step": 1800
},
{
"epoch": 0.931669025865397,
"grad_norm": 0.0663972795009613,
"learning_rate": 1.2908487947332588e-05,
"loss": 0.0135,
"step": 1810
},
{
"epoch": 0.9368163685497362,
"grad_norm": 0.06685107946395874,
"learning_rate": 1.2822418675898428e-05,
"loss": 0.0146,
"step": 1820
},
{
"epoch": 0.9419637112340754,
"grad_norm": 0.07378830760717392,
"learning_rate": 1.273612161848064e-05,
"loss": 0.0137,
"step": 1830
},
{
"epoch": 0.9471110539184147,
"grad_norm": 0.07926513254642487,
"learning_rate": 1.2649603739765323e-05,
"loss": 0.0134,
"step": 1840
},
{
"epoch": 0.9522583966027538,
"grad_norm": 0.060047443956136703,
"learning_rate": 1.2562872022260168e-05,
"loss": 0.0142,
"step": 1850
},
{
"epoch": 0.957405739287093,
"grad_norm": 0.07245929539203644,
"learning_rate": 1.2475933465730923e-05,
"loss": 0.0134,
"step": 1860
},
{
"epoch": 0.9625530819714323,
"grad_norm": 0.06252739578485489,
"learning_rate": 1.238879508663648e-05,
"loss": 0.0136,
"step": 1870
},
{
"epoch": 0.9677004246557714,
"grad_norm": 0.07423530519008636,
"learning_rate": 1.2301463917562602e-05,
"loss": 0.0138,
"step": 1880
},
{
"epoch": 0.9728477673401107,
"grad_norm": 0.06203414499759674,
"learning_rate": 1.2213947006654347e-05,
"loss": 0.0136,
"step": 1890
},
{
"epoch": 0.9779951100244498,
"grad_norm": 0.06526093184947968,
"learning_rate": 1.212625141704725e-05,
"loss": 0.0144,
"step": 1900
},
{
"epoch": 0.9831424527087891,
"grad_norm": 0.05829852074384689,
"learning_rate": 1.2038384226297272e-05,
"loss": 0.0135,
"step": 1910
},
{
"epoch": 0.9882897953931283,
"grad_norm": 0.0650823563337326,
"learning_rate": 1.1950352525809619e-05,
"loss": 0.0134,
"step": 1920
},
{
"epoch": 0.9934371380774675,
"grad_norm": 0.07050953805446625,
"learning_rate": 1.18621634202664e-05,
"loss": 0.0136,
"step": 1930
},
{
"epoch": 0.9985844807618067,
"grad_norm": 0.05969216674566269,
"learning_rate": 1.1773824027053256e-05,
"loss": 0.0135,
"step": 1940
},
{
"epoch": 1.0036031398790375,
"grad_norm": 0.05986722931265831,
"learning_rate": 1.1685341475684935e-05,
"loss": 0.0123,
"step": 1950
},
{
"epoch": 1.0087504825633766,
"grad_norm": 0.06715232133865356,
"learning_rate": 1.15967229072299e-05,
"loss": 0.0125,
"step": 1960
},
{
"epoch": 1.0138978252477158,
"grad_norm": 0.05757083743810654,
"learning_rate": 1.1507975473734002e-05,
"loss": 0.0123,
"step": 1970
},
{
"epoch": 1.0190451679320551,
"grad_norm": 0.06696327775716782,
"learning_rate": 1.141910633764327e-05,
"loss": 0.0122,
"step": 1980
},
{
"epoch": 1.0241925106163943,
"grad_norm": 0.061676956713199615,
"learning_rate": 1.1330122671225855e-05,
"loss": 0.0125,
"step": 1990
},
{
"epoch": 1.0293398533007334,
"grad_norm": 0.07469218969345093,
"learning_rate": 1.1241031655993188e-05,
"loss": 0.0127,
"step": 2000
},
{
"epoch": 1.0344871959850728,
"grad_norm": 0.06639962643384933,
"learning_rate": 1.1151840482120386e-05,
"loss": 0.0126,
"step": 2010
},
{
"epoch": 1.039634538669412,
"grad_norm": 0.07054606825113297,
"learning_rate": 1.1062556347865967e-05,
"loss": 0.0127,
"step": 2020
},
{
"epoch": 1.044781881353751,
"grad_norm": 0.06040499359369278,
"learning_rate": 1.0973186458990902e-05,
"loss": 0.0119,
"step": 2030
},
{
"epoch": 1.0499292240380904,
"grad_norm": 0.0656294897198677,
"learning_rate": 1.0883738028177069e-05,
"loss": 0.0126,
"step": 2040
},
{
"epoch": 1.0550765667224296,
"grad_norm": 0.06062242388725281,
"learning_rate": 1.0794218274445155e-05,
"loss": 0.0128,
"step": 2050
},
{
"epoch": 1.0602239094067687,
"grad_norm": 0.06211702898144722,
"learning_rate": 1.0704634422572029e-05,
"loss": 0.0127,
"step": 2060
},
{
"epoch": 1.065371252091108,
"grad_norm": 0.05939929559826851,
"learning_rate": 1.0614993702507649e-05,
"loss": 0.0129,
"step": 2070
},
{
"epoch": 1.0705185947754472,
"grad_norm": 0.06660640239715576,
"learning_rate": 1.0525303348791599e-05,
"loss": 0.012,
"step": 2080
},
{
"epoch": 1.0756659374597863,
"grad_norm": 0.061506547033786774,
"learning_rate": 1.0435570599969168e-05,
"loss": 0.0126,
"step": 2090
},
{
"epoch": 1.0808132801441257,
"grad_norm": 0.05894378572702408,
"learning_rate": 1.0345802698007198e-05,
"loss": 0.0127,
"step": 2100
},
{
"epoch": 1.0859606228284648,
"grad_norm": 0.06136978417634964,
"learning_rate": 1.0256006887709593e-05,
"loss": 0.0115,
"step": 2110
},
{
"epoch": 1.091107965512804,
"grad_norm": 0.0651112049818039,
"learning_rate": 1.016619041613263e-05,
"loss": 0.0125,
"step": 2120
},
{
"epoch": 1.0962553081971431,
"grad_norm": 0.06708134710788727,
"learning_rate": 1.0076360532000069e-05,
"loss": 0.0126,
"step": 2130
},
{
"epoch": 1.1014026508814825,
"grad_norm": 0.0627651959657669,
"learning_rate": 9.986524485118152e-06,
"loss": 0.0119,
"step": 2140
},
{
"epoch": 1.1065499935658216,
"grad_norm": 0.060133691877126694,
"learning_rate": 9.896689525790474e-06,
"loss": 0.013,
"step": 2150
},
{
"epoch": 1.1116973362501608,
"grad_norm": 0.05978613346815109,
"learning_rate": 9.80686290423288e-06,
"loss": 0.0118,
"step": 2160
},
{
"epoch": 1.1168446789345001,
"grad_norm": 0.0568259134888649,
"learning_rate": 9.717051869988287e-06,
"loss": 0.0122,
"step": 2170
},
{
"epoch": 1.1219920216188393,
"grad_norm": 0.07073856145143509,
"learning_rate": 9.627263671341638e-06,
"loss": 0.012,
"step": 2180
},
{
"epoch": 1.1271393643031784,
"grad_norm": 0.0650116428732872,
"learning_rate": 9.537505554734901e-06,
"loss": 0.0126,
"step": 2190
},
{
"epoch": 1.1322867069875178,
"grad_norm": 0.06662643700838089,
"learning_rate": 9.447784764182247e-06,
"loss": 0.0121,
"step": 2200
},
{
"epoch": 1.137434049671857,
"grad_norm": 0.06186177209019661,
"learning_rate": 9.358108540685406e-06,
"loss": 0.0116,
"step": 2210
},
{
"epoch": 1.142581392356196,
"grad_norm": 0.06745568662881851,
"learning_rate": 9.268484121649289e-06,
"loss": 0.0126,
"step": 2220
},
{
"epoch": 1.1477287350405354,
"grad_norm": 0.0625823512673378,
"learning_rate": 9.178918740297877e-06,
"loss": 0.0135,
"step": 2230
},
{
"epoch": 1.1528760777248745,
"grad_norm": 0.05811070650815964,
"learning_rate": 9.08941962509045e-06,
"loss": 0.0122,
"step": 2240
},
{
"epoch": 1.1580234204092137,
"grad_norm": 0.06800320744514465,
"learning_rate": 8.999993999138227e-06,
"loss": 0.0128,
"step": 2250
},
{
"epoch": 1.1631707630935528,
"grad_norm": 0.061803579330444336,
"learning_rate": 8.91064907962141e-06,
"loss": 0.0116,
"step": 2260
},
{
"epoch": 1.1683181057778922,
"grad_norm": 0.056932009756565094,
"learning_rate": 8.821392077206695e-06,
"loss": 0.0123,
"step": 2270
},
{
"epoch": 1.1734654484622313,
"grad_norm": 0.0628976821899414,
"learning_rate": 8.732230195465353e-06,
"loss": 0.0119,
"step": 2280
},
{
"epoch": 1.1786127911465707,
"grad_norm": 0.0606074184179306,
"learning_rate": 8.64317063029186e-06,
"loss": 0.0121,
"step": 2290
},
{
"epoch": 1.1837601338309098,
"grad_norm": 0.06012739986181259,
"learning_rate": 8.554220569323117e-06,
"loss": 0.0123,
"step": 2300
},
{
"epoch": 1.188907476515249,
"grad_norm": 0.060469817370176315,
"learning_rate": 8.465387191358398e-06,
"loss": 0.0121,
"step": 2310
},
{
"epoch": 1.1940548191995881,
"grad_norm": 0.06011821702122688,
"learning_rate": 8.376677665779968e-06,
"loss": 0.0119,
"step": 2320
},
{
"epoch": 1.1992021618839275,
"grad_norm": 0.0587395578622818,
"learning_rate": 8.288099151974446e-06,
"loss": 0.0121,
"step": 2330
},
{
"epoch": 1.2043495045682666,
"grad_norm": 0.06356833130121231,
"learning_rate": 8.199658798755048e-06,
"loss": 0.0123,
"step": 2340
},
{
"epoch": 1.2094968472526058,
"grad_norm": 0.05952199548482895,
"learning_rate": 8.111363743784587e-06,
"loss": 0.0123,
"step": 2350
},
{
"epoch": 1.2146441899369451,
"grad_norm": 0.0687473863363266,
"learning_rate": 8.023221112999459e-06,
"loss": 0.0117,
"step": 2360
},
{
"epoch": 1.2197915326212843,
"grad_norm": 0.05651247128844261,
"learning_rate": 7.935238020034505e-06,
"loss": 0.0107,
"step": 2370
},
{
"epoch": 1.2249388753056234,
"grad_norm": 0.05863620713353157,
"learning_rate": 7.847421565648929e-06,
"loss": 0.0119,
"step": 2380
},
{
"epoch": 1.2300862179899628,
"grad_norm": 0.06163261458277702,
"learning_rate": 7.759778837153205e-06,
"loss": 0.0125,
"step": 2390
},
{
"epoch": 1.235233560674302,
"grad_norm": 0.061220042407512665,
"learning_rate": 7.672316907837084e-06,
"loss": 0.0118,
"step": 2400
},
{
"epoch": 1.240380903358641,
"grad_norm": 0.06481561809778214,
"learning_rate": 7.585042836398763e-06,
"loss": 0.0118,
"step": 2410
},
{
"epoch": 1.2455282460429804,
"grad_norm": 0.06460854411125183,
"learning_rate": 7.497963666375185e-06,
"loss": 0.0124,
"step": 2420
},
{
"epoch": 1.2506755887273195,
"grad_norm": 0.0643194317817688,
"learning_rate": 7.411086425573584e-06,
"loss": 0.0119,
"step": 2430
},
{
"epoch": 1.2558229314116587,
"grad_norm": 0.0629289299249649,
"learning_rate": 7.324418125504305e-06,
"loss": 0.0123,
"step": 2440
},
{
"epoch": 1.2609702740959978,
"grad_norm": 0.06404928117990494,
"learning_rate": 7.23796576081494e-06,
"loss": 0.0122,
"step": 2450
},
{
"epoch": 1.2661176167803372,
"grad_norm": 0.06378574669361115,
"learning_rate": 7.151736308725802e-06,
"loss": 0.0114,
"step": 2460
},
{
"epoch": 1.2712649594646763,
"grad_norm": 0.06403859704732895,
"learning_rate": 7.065736728466832e-06,
"loss": 0.0117,
"step": 2470
},
{
"epoch": 1.2764123021490157,
"grad_norm": 0.06829800456762314,
"learning_rate": 6.979973960715958e-06,
"loss": 0.0124,
"step": 2480
},
{
"epoch": 1.2815596448333548,
"grad_norm": 0.059846751391887665,
"learning_rate": 6.894454927038907e-06,
"loss": 0.0113,
"step": 2490
},
{
"epoch": 1.286706987517694,
"grad_norm": 0.054608747363090515,
"learning_rate": 6.809186529330639e-06,
"loss": 0.012,
"step": 2500
},
{
"epoch": 1.291854330202033,
"grad_norm": 0.06600859761238098,
"learning_rate": 6.724175649258287e-06,
"loss": 0.0126,
"step": 2510
},
{
"epoch": 1.2970016728863725,
"grad_norm": 0.05849931016564369,
"learning_rate": 6.6394291477057736e-06,
"loss": 0.0116,
"step": 2520
},
{
"epoch": 1.3021490155707116,
"grad_norm": 0.06548711657524109,
"learning_rate": 6.554953864220115e-06,
"loss": 0.0121,
"step": 2530
},
{
"epoch": 1.3072963582550507,
"grad_norm": 0.05490358918905258,
"learning_rate": 6.4707566164594105e-06,
"loss": 0.0116,
"step": 2540
},
{
"epoch": 1.3124437009393901,
"grad_norm": 0.05758791044354439,
"learning_rate": 6.386844199642619e-06,
"loss": 0.0117,
"step": 2550
},
{
"epoch": 1.3175910436237293,
"grad_norm": 0.0644078403711319,
"learning_rate": 6.30322338600114e-06,
"loss": 0.0124,
"step": 2560
},
{
"epoch": 1.3227383863080684,
"grad_norm": 0.05672595277428627,
"learning_rate": 6.219900924232279e-06,
"loss": 0.011,
"step": 2570
},
{
"epoch": 1.3278857289924075,
"grad_norm": 0.058410342782735825,
"learning_rate": 6.136883538954561e-06,
"loss": 0.012,
"step": 2580
},
{
"epoch": 1.333033071676747,
"grad_norm": 0.05841913819313049,
"learning_rate": 6.054177930165017e-06,
"loss": 0.0111,
"step": 2590
},
{
"epoch": 1.338180414361086,
"grad_norm": 0.06315062940120697,
"learning_rate": 5.971790772698467e-06,
"loss": 0.0114,
"step": 2600
},
{
"epoch": 1.3433277570454254,
"grad_norm": 0.059485290199518204,
"learning_rate": 5.889728715688814e-06,
"loss": 0.0116,
"step": 2610
},
{
"epoch": 1.3484750997297645,
"grad_norm": 0.06330478936433792,
"learning_rate": 5.807998382032414e-06,
"loss": 0.0117,
"step": 2620
},
{
"epoch": 1.3536224424141037,
"grad_norm": 0.05869928374886513,
"learning_rate": 5.726606367853581e-06,
"loss": 0.0119,
"step": 2630
},
{
"epoch": 1.3587697850984428,
"grad_norm": 0.07355443388223648,
"learning_rate": 5.645559241972231e-06,
"loss": 0.0123,
"step": 2640
},
{
"epoch": 1.3639171277827822,
"grad_norm": 0.05870656296610832,
"learning_rate": 5.56486354537374e-06,
"loss": 0.0117,
"step": 2650
},
{
"epoch": 1.3690644704671213,
"grad_norm": 0.059707384556531906,
"learning_rate": 5.484525790681052e-06,
"loss": 0.0117,
"step": 2660
},
{
"epoch": 1.3742118131514607,
"grad_norm": 0.0809202715754509,
"learning_rate": 5.404552461629069e-06,
"loss": 0.0114,
"step": 2670
},
{
"epoch": 1.3793591558357998,
"grad_norm": 0.05704690143465996,
"learning_rate": 5.324950012541372e-06,
"loss": 0.0118,
"step": 2680
},
{
"epoch": 1.384506498520139,
"grad_norm": 0.06190679967403412,
"learning_rate": 5.245724867809326e-06,
"loss": 0.0116,
"step": 2690
},
{
"epoch": 1.389653841204478,
"grad_norm": 0.055938467383384705,
"learning_rate": 5.166883421373583e-06,
"loss": 0.0116,
"step": 2700
},
{
"epoch": 1.3948011838888175,
"grad_norm": 0.05830509215593338,
"learning_rate": 5.088432036208075e-06,
"loss": 0.0112,
"step": 2710
},
{
"epoch": 1.3999485265731566,
"grad_norm": 0.05540473014116287,
"learning_rate": 5.010377043806443e-06,
"loss": 0.0102,
"step": 2720
},
{
"epoch": 1.4050958692574957,
"grad_norm": 0.05529293790459633,
"learning_rate": 4.932724743671089e-06,
"loss": 0.0113,
"step": 2730
},
{
"epoch": 1.410243211941835,
"grad_norm": 0.062383200973272324,
"learning_rate": 4.8554814028047605e-06,
"loss": 0.0114,
"step": 2740
},
{
"epoch": 1.4153905546261742,
"grad_norm": 0.05733776092529297,
"learning_rate": 4.778653255204733e-06,
"loss": 0.012,
"step": 2750
},
{
"epoch": 1.4205378973105134,
"grad_norm": 0.05461714044213295,
"learning_rate": 4.702246501359739e-06,
"loss": 0.0108,
"step": 2760
},
{
"epoch": 1.4256852399948525,
"grad_norm": 0.05713033676147461,
"learning_rate": 4.626267307749519e-06,
"loss": 0.0113,
"step": 2770
},
{
"epoch": 1.4308325826791919,
"grad_norm": 0.066215381026268,
"learning_rate": 4.550721806347146e-06,
"loss": 0.0117,
"step": 2780
},
{
"epoch": 1.435979925363531,
"grad_norm": 0.05536945164203644,
"learning_rate": 4.475616094124171e-06,
"loss": 0.0114,
"step": 2790
},
{
"epoch": 1.4411272680478704,
"grad_norm": 0.05297793820500374,
"learning_rate": 4.40095623255853e-06,
"loss": 0.0111,
"step": 2800
},
{
"epoch": 1.4462746107322095,
"grad_norm": 0.05898694694042206,
"learning_rate": 4.3267482471453574e-06,
"loss": 0.0107,
"step": 2810
},
{
"epoch": 1.4514219534165487,
"grad_norm": 0.05825399234890938,
"learning_rate": 4.252998126910696e-06,
"loss": 0.01,
"step": 2820
},
{
"epoch": 1.4565692961008878,
"grad_norm": 0.05541868135333061,
"learning_rate": 4.179711823928141e-06,
"loss": 0.0104,
"step": 2830
},
{
"epoch": 1.4617166387852272,
"grad_norm": 0.061555661261081696,
"learning_rate": 4.106895252838478e-06,
"loss": 0.0108,
"step": 2840
},
{
"epoch": 1.4668639814695663,
"grad_norm": 0.05560790374875069,
"learning_rate": 4.034554290372332e-06,
"loss": 0.0113,
"step": 2850
},
{
"epoch": 1.4720113241539057,
"grad_norm": 0.06007440760731697,
"learning_rate": 3.96269477487588e-06,
"loss": 0.0106,
"step": 2860
},
{
"epoch": 1.4771586668382448,
"grad_norm": 0.0683414563536644,
"learning_rate": 3.891322505839672e-06,
"loss": 0.0112,
"step": 2870
},
{
"epoch": 1.482306009522584,
"grad_norm": 0.06036698445677757,
"learning_rate": 3.820443243430555e-06,
"loss": 0.0113,
"step": 2880
},
{
"epoch": 1.487453352206923,
"grad_norm": 0.060313206166028976,
"learning_rate": 3.750062708026814e-06,
"loss": 0.0113,
"step": 2890
},
{
"epoch": 1.4926006948912625,
"grad_norm": 0.056533217430114746,
"learning_rate": 3.680186579756507e-06,
"loss": 0.0106,
"step": 2900
},
{
"epoch": 1.4977480375756016,
"grad_norm": 0.054458554834127426,
"learning_rate": 3.6108204980390116e-06,
"loss": 0.0102,
"step": 2910
},
{
"epoch": 1.502895380259941,
"grad_norm": 0.058249276131391525,
"learning_rate": 3.5419700611299356e-06,
"loss": 0.0108,
"step": 2920
},
{
"epoch": 1.50804272294428,
"grad_norm": 0.06064664199948311,
"learning_rate": 3.4736408256692757e-06,
"loss": 0.0105,
"step": 2930
},
{
"epoch": 1.5131900656286192,
"grad_norm": 0.06132345646619797,
"learning_rate": 3.4058383062329534e-06,
"loss": 0.0107,
"step": 2940
},
{
"epoch": 1.5183374083129584,
"grad_norm": 0.06465797871351242,
"learning_rate": 3.3385679748877996e-06,
"loss": 0.0106,
"step": 2950
},
{
"epoch": 1.5234847509972975,
"grad_norm": 0.05858945474028587,
"learning_rate": 3.2718352607498814e-06,
"loss": 0.0101,
"step": 2960
},
{
"epoch": 1.5286320936816369,
"grad_norm": 0.0577542670071125,
"learning_rate": 3.205645549546361e-06,
"loss": 0.0101,
"step": 2970
},
{
"epoch": 1.533779436365976,
"grad_norm": 0.05463823676109314,
"learning_rate": 3.140004183180837e-06,
"loss": 0.0103,
"step": 2980
},
{
"epoch": 1.5389267790503154,
"grad_norm": 0.05978240817785263,
"learning_rate": 3.074916459302211e-06,
"loss": 0.0105,
"step": 2990
},
{
"epoch": 1.5440741217346545,
"grad_norm": 0.059246134012937546,
"learning_rate": 3.010387630877142e-06,
"loss": 0.0109,
"step": 3000
},
{
"epoch": 1.5492214644189937,
"grad_norm": 0.05470456928014755,
"learning_rate": 2.946422905766103e-06,
"loss": 0.0105,
"step": 3010
},
{
"epoch": 1.5543688071033328,
"grad_norm": 0.05716393515467644,
"learning_rate": 2.8830274463030705e-06,
"loss": 0.0105,
"step": 3020
},
{
"epoch": 1.5595161497876722,
"grad_norm": 0.05379533767700195,
"learning_rate": 2.820206368878894e-06,
"loss": 0.0104,
"step": 3030
},
{
"epoch": 1.5646634924720113,
"grad_norm": 0.0554485023021698,
"learning_rate": 2.7579647435283773e-06,
"loss": 0.0106,
"step": 3040
},
{
"epoch": 1.5698108351563507,
"grad_norm": 0.061001092195510864,
"learning_rate": 2.696307593521088e-06,
"loss": 0.0107,
"step": 3050
},
{
"epoch": 1.5749581778406898,
"grad_norm": 0.05021286383271217,
"learning_rate": 2.6352398949559697e-06,
"loss": 0.0111,
"step": 3060
},
{
"epoch": 1.580105520525029,
"grad_norm": 0.057367950677871704,
"learning_rate": 2.5747665763597016e-06,
"loss": 0.0106,
"step": 3070
},
{
"epoch": 1.585252863209368,
"grad_norm": 0.054719775915145874,
"learning_rate": 2.514892518288988e-06,
"loss": 0.0097,
"step": 3080
},
{
"epoch": 1.5904002058937072,
"grad_norm": 0.05537039414048195,
"learning_rate": 2.4556225529366316e-06,
"loss": 0.0099,
"step": 3090
},
{
"epoch": 1.5955475485780466,
"grad_norm": 0.056724581867456436,
"learning_rate": 2.3969614637415474e-06,
"loss": 0.0107,
"step": 3100
},
{
"epoch": 1.600694891262386,
"grad_norm": 0.059857919812202454,
"learning_rate": 2.338913985002739e-06,
"loss": 0.0104,
"step": 3110
},
{
"epoch": 1.605842233946725,
"grad_norm": 0.06095413863658905,
"learning_rate": 2.281484801497186e-06,
"loss": 0.0099,
"step": 3120
},
{
"epoch": 1.6109895766310642,
"grad_norm": 0.056674227118492126,
"learning_rate": 2.224678548101762e-06,
"loss": 0.0104,
"step": 3130
},
{
"epoch": 1.6161369193154034,
"grad_norm": 0.05638737604022026,
"learning_rate": 2.168499809419177e-06,
"loss": 0.0102,
"step": 3140
},
{
"epoch": 1.6212842619997425,
"grad_norm": 0.06467755138874054,
"learning_rate": 2.1129531194079656e-06,
"loss": 0.0101,
"step": 3150
},
{
"epoch": 1.6264316046840819,
"grad_norm": 0.05878566950559616,
"learning_rate": 2.0580429610165763e-06,
"loss": 0.0102,
"step": 3160
},
{
"epoch": 1.631578947368421,
"grad_norm": 0.05528358370065689,
"learning_rate": 2.0037737658215684e-06,
"loss": 0.0098,
"step": 3170
},
{
"epoch": 1.6367262900527604,
"grad_norm": 0.057190001010894775,
"learning_rate": 1.950149913669953e-06,
"loss": 0.0115,
"step": 3180
},
{
"epoch": 1.6418736327370995,
"grad_norm": 0.05818023905158043,
"learning_rate": 1.89717573232572e-06,
"loss": 0.0097,
"step": 3190
},
{
"epoch": 1.6470209754214387,
"grad_norm": 0.050614483654499054,
"learning_rate": 1.844855497120558e-06,
"loss": 0.0098,
"step": 3200
},
{
"epoch": 1.6521683181057778,
"grad_norm": 0.05694177374243736,
"learning_rate": 1.7931934306088082e-06,
"loss": 0.0099,
"step": 3210
},
{
"epoch": 1.657315660790117,
"grad_norm": 0.05727734416723251,
"learning_rate": 1.7421937022266921e-06,
"loss": 0.0102,
"step": 3220
},
{
"epoch": 1.6624630034744563,
"grad_norm": 0.054520897567272186,
"learning_rate": 1.691860427955785e-06,
"loss": 0.0104,
"step": 3230
},
{
"epoch": 1.6676103461587957,
"grad_norm": 0.05534141883254051,
"learning_rate": 1.6421976699908636e-06,
"loss": 0.0102,
"step": 3240
},
{
"epoch": 1.6727576888431348,
"grad_norm": 0.05031333491206169,
"learning_rate": 1.5932094364120453e-06,
"loss": 0.0099,
"step": 3250
},
{
"epoch": 1.677905031527474,
"grad_norm": 0.05531871318817139,
"learning_rate": 1.544899680861306e-06,
"loss": 0.0099,
"step": 3260
},
{
"epoch": 1.683052374211813,
"grad_norm": 0.05327874794602394,
"learning_rate": 1.4972723022234214e-06,
"loss": 0.0106,
"step": 3270
},
{
"epoch": 1.6881997168961522,
"grad_norm": 0.0656590610742569,
"learning_rate": 1.45033114431128e-06,
"loss": 0.0104,
"step": 3280
},
{
"epoch": 1.6933470595804916,
"grad_norm": 0.05613217502832413,
"learning_rate": 1.4040799955556771e-06,
"loss": 0.0101,
"step": 3290
},
{
"epoch": 1.6984944022648307,
"grad_norm": 0.053455501794815063,
"learning_rate": 1.3585225886995613e-06,
"loss": 0.0095,
"step": 3300
},
{
"epoch": 1.70364174494917,
"grad_norm": 0.06014241278171539,
"learning_rate": 1.3136626004967834e-06,
"loss": 0.0098,
"step": 3310
},
{
"epoch": 1.7087890876335092,
"grad_norm": 0.053092245012521744,
"learning_rate": 1.2695036514153569e-06,
"loss": 0.0101,
"step": 3320
},
{
"epoch": 1.7139364303178484,
"grad_norm": 0.057713184505701065,
"learning_rate": 1.2260493053452672e-06,
"loss": 0.0104,
"step": 3330
},
{
"epoch": 1.7190837730021875,
"grad_norm": 0.05759907886385918,
"learning_rate": 1.1833030693108426e-06,
"loss": 0.0097,
"step": 3340
},
{
"epoch": 1.7242311156865269,
"grad_norm": 0.05587298423051834,
"learning_rate": 1.1412683931877177e-06,
"loss": 0.0096,
"step": 3350
},
{
"epoch": 1.729378458370866,
"grad_norm": 0.05066050961613655,
"learning_rate": 1.0999486694244087e-06,
"loss": 0.0104,
"step": 3360
},
{
"epoch": 1.7345258010552054,
"grad_norm": 0.05758954957127571,
"learning_rate": 1.0593472327685183e-06,
"loss": 0.01,
"step": 3370
},
{
"epoch": 1.7396731437395445,
"grad_norm": 0.05743640661239624,
"learning_rate": 1.0194673599976134e-06,
"loss": 0.0094,
"step": 3380
},
{
"epoch": 1.7448204864238837,
"grad_norm": 0.06300937384366989,
"learning_rate": 9.803122696547473e-07,
"loss": 0.0105,
"step": 3390
},
{
"epoch": 1.7499678291082228,
"grad_norm": 0.059773825109004974,
"learning_rate": 9.418851217887337e-07,
"loss": 0.0104,
"step": 3400
},
{
"epoch": 1.755115171792562,
"grad_norm": 0.05869515612721443,
"learning_rate": 9.041890176990876e-07,
"loss": 0.01,
"step": 3410
},
{
"epoch": 1.7602625144769013,
"grad_norm": 0.05758318305015564,
"learning_rate": 8.672269996857375e-07,
"loss": 0.0102,
"step": 3420
},
{
"epoch": 1.7654098571612407,
"grad_norm": 0.059089090675115585,
"learning_rate": 8.310020508035055e-07,
"loss": 0.0101,
"step": 3430
},
{
"epoch": 1.7705571998455798,
"grad_norm": 0.05819304287433624,
"learning_rate": 7.955170946213442e-07,
"loss": 0.0097,
"step": 3440
},
{
"epoch": 1.775704542529919,
"grad_norm": 0.05375674366950989,
"learning_rate": 7.607749949863907e-07,
"loss": 0.0099,
"step": 3450
},
{
"epoch": 1.780851885214258,
"grad_norm": 0.055159516632556915,
"learning_rate": 7.267785557928398e-07,
"loss": 0.0097,
"step": 3460
},
{
"epoch": 1.7859992278985972,
"grad_norm": 0.05335604399442673,
"learning_rate": 6.935305207556509e-07,
"loss": 0.0101,
"step": 3470
},
{
"epoch": 1.7911465705829366,
"grad_norm": 0.05733654648065567,
"learning_rate": 6.610335731891116e-07,
"loss": 0.0098,
"step": 3480
},
{
"epoch": 1.7962939132672757,
"grad_norm": 0.05677180364727974,
"learning_rate": 6.292903357902846e-07,
"loss": 0.0102,
"step": 3490
},
{
"epoch": 1.801441255951615,
"grad_norm": 0.05063822120428085,
"learning_rate": 5.983033704273355e-07,
"loss": 0.0099,
"step": 3500
},
{
"epoch": 1.8065885986359542,
"grad_norm": 0.05387408286333084,
"learning_rate": 5.680751779327742e-07,
"loss": 0.0095,
"step": 3510
},
{
"epoch": 1.8117359413202934,
"grad_norm": 0.053591515868902206,
"learning_rate": 5.386081979016256e-07,
"loss": 0.01,
"step": 3520
},
{
"epoch": 1.8168832840046325,
"grad_norm": 0.05464727059006691,
"learning_rate": 5.099048084945401e-07,
"loss": 0.0092,
"step": 3530
},
{
"epoch": 1.8220306266889719,
"grad_norm": 0.055579908192157745,
"learning_rate": 4.819673262458591e-07,
"loss": 0.01,
"step": 3540
},
{
"epoch": 1.827177969373311,
"grad_norm": 0.05614079535007477,
"learning_rate": 4.547980058766566e-07,
"loss": 0.0101,
"step": 3550
},
{
"epoch": 1.8323253120576504,
"grad_norm": 0.05531793087720871,
"learning_rate": 4.283990401127769e-07,
"loss": 0.0098,
"step": 3560
},
{
"epoch": 1.8374726547419895,
"grad_norm": 0.05819229036569595,
"learning_rate": 4.027725595078591e-07,
"loss": 0.0098,
"step": 3570
},
{
"epoch": 1.8426199974263286,
"grad_norm": 0.06295463442802429,
"learning_rate": 3.779206322713913e-07,
"loss": 0.0101,
"step": 3580
},
{
"epoch": 1.8477673401106678,
"grad_norm": 0.05543727055191994,
"learning_rate": 3.5384526410180085e-07,
"loss": 0.0101,
"step": 3590
},
{
"epoch": 1.852914682795007,
"grad_norm": 0.05354765057563782,
"learning_rate": 3.305483980245716e-07,
"loss": 0.0097,
"step": 3600
},
{
"epoch": 1.8580620254793463,
"grad_norm": 0.05514323711395264,
"learning_rate": 3.080319142354393e-07,
"loss": 0.0104,
"step": 3610
},
{
"epoch": 1.8632093681636857,
"grad_norm": 0.055874355137348175,
"learning_rate": 2.8629762994864195e-07,
"loss": 0.0104,
"step": 3620
},
{
"epoch": 1.8683567108480248,
"grad_norm": 0.04839755967259407,
"learning_rate": 2.653472992502648e-07,
"loss": 0.0096,
"step": 3630
},
{
"epoch": 1.873504053532364,
"grad_norm": 0.05774934962391853,
"learning_rate": 2.4518261295667255e-07,
"loss": 0.01,
"step": 3640
},
{
"epoch": 1.878651396216703,
"grad_norm": 0.05328024923801422,
"learning_rate": 2.2580519847805182e-07,
"loss": 0.0098,
"step": 3650
},
{
"epoch": 1.8837987389010422,
"grad_norm": 0.06098954752087593,
"learning_rate": 2.072166196870673e-07,
"loss": 0.01,
"step": 3660
},
{
"epoch": 1.8889460815853816,
"grad_norm": 0.05954898148775101,
"learning_rate": 1.894183767926494e-07,
"loss": 0.0099,
"step": 3670
},
{
"epoch": 1.8940934242697207,
"grad_norm": 0.05533028766512871,
"learning_rate": 1.724119062189189e-07,
"loss": 0.0101,
"step": 3680
},
{
"epoch": 1.89924076695406,
"grad_norm": 0.054454490542411804,
"learning_rate": 1.561985804892585e-07,
"loss": 0.0094,
"step": 3690
},
{
"epoch": 1.9043881096383992,
"grad_norm": 0.05790005996823311,
"learning_rate": 1.4077970811554153e-07,
"loss": 0.0095,
"step": 3700
},
{
"epoch": 1.9095354523227384,
"grad_norm": 0.05482661351561546,
"learning_rate": 1.2615653349252743e-07,
"loss": 0.0104,
"step": 3710
},
{
"epoch": 1.9146827950070775,
"grad_norm": 0.053785741329193115,
"learning_rate": 1.1233023679743326e-07,
"loss": 0.01,
"step": 3720
},
{
"epoch": 1.9198301376914169,
"grad_norm": 0.05585356056690216,
"learning_rate": 9.930193389468323e-08,
"loss": 0.0097,
"step": 3730
},
{
"epoch": 1.924977480375756,
"grad_norm": 0.055351871997117996,
"learning_rate": 8.707267624585292e-08,
"loss": 0.0101,
"step": 3740
},
{
"epoch": 1.9301248230600954,
"grad_norm": 0.05515802651643753,
"learning_rate": 7.564345082481383e-08,
"loss": 0.0099,
"step": 3750
},
{
"epoch": 1.9352721657444345,
"grad_norm": 0.056177496910095215,
"learning_rate": 6.501518003807272e-08,
"loss": 0.0099,
"step": 3760
},
{
"epoch": 1.9404195084287736,
"grad_norm": 0.0514858104288578,
"learning_rate": 5.518872165033329e-08,
"loss": 0.0097,
"step": 3770
},
{
"epoch": 1.9455668511131128,
"grad_norm": 0.054609816521406174,
"learning_rate": 4.6164868715263825e-08,
"loss": 0.0093,
"step": 3780
},
{
"epoch": 1.950714193797452,
"grad_norm": 0.05447670817375183,
"learning_rate": 3.79443495114995e-08,
"loss": 0.0104,
"step": 3790
},
{
"epoch": 1.9558615364817913,
"grad_norm": 0.0530201718211174,
"learning_rate": 3.052782748386052e-08,
"loss": 0.0094,
"step": 3800
}
],
"logging_steps": 10,
"max_steps": 3886,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.179443739110618e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}