{
  "best_metric": 0.7980687022209167,
  "best_model_checkpoint": "miner_id_24/checkpoint-1050",
  "epoch": 0.013958079235363127,
  "eval_steps": 150,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.329340879558393e-05,
      "eval_loss": 2.00691819190979,
      "eval_runtime": 2934.4159,
      "eval_samples_per_second": 43.176,
      "eval_steps_per_second": 10.794,
      "step": 1
    },
    {
      "epoch": 0.0001329340879558393,
      "grad_norm": 1.5657358169555664,
      "learning_rate": 2e-05,
      "loss": 1.2697,
      "step": 10
    },
    {
      "epoch": 0.0002658681759116786,
      "grad_norm": 1.3231450319290161,
      "learning_rate": 4e-05,
      "loss": 1.2549,
      "step": 20
    },
    {
      "epoch": 0.00039880226386751786,
      "grad_norm": 2.6863651275634766,
      "learning_rate": 6e-05,
      "loss": 1.043,
      "step": 30
    },
    {
      "epoch": 0.0005317363518233572,
      "grad_norm": 2.719365358352661,
      "learning_rate": 8e-05,
      "loss": 0.9829,
      "step": 40
    },
    {
      "epoch": 0.0006646704397791965,
      "grad_norm": 6.010656356811523,
      "learning_rate": 0.0001,
      "loss": 0.9896,
      "step": 50
    },
    {
      "epoch": 0.0007976045277350357,
      "grad_norm": 1.3875675201416016,
      "learning_rate": 9.999875400032707e-05,
      "loss": 0.942,
      "step": 60
    },
    {
      "epoch": 0.0009305386156908751,
      "grad_norm": 1.3019894361495972,
      "learning_rate": 9.999501606340891e-05,
      "loss": 0.9229,
      "step": 70
    },
    {
      "epoch": 0.0010634727036467144,
      "grad_norm": 1.3613632917404175,
      "learning_rate": 9.998878637554424e-05,
      "loss": 0.8867,
      "step": 80
    },
    {
      "epoch": 0.0011964067916025536,
      "grad_norm": 1.7349094152450562,
      "learning_rate": 9.998006524722059e-05,
      "loss": 0.7913,
      "step": 90
    },
    {
      "epoch": 0.001329340879558393,
      "grad_norm": 4.72564172744751,
      "learning_rate": 9.996885311309891e-05,
      "loss": 0.8381,
      "step": 100
    },
    {
      "epoch": 0.0014622749675142323,
      "grad_norm": 1.0643872022628784,
      "learning_rate": 9.995515053199182e-05,
      "loss": 0.9664,
      "step": 110
    },
    {
      "epoch": 0.0015952090554700715,
      "grad_norm": 1.1394284963607788,
      "learning_rate": 9.993895818683579e-05,
      "loss": 0.867,
      "step": 120
    },
    {
      "epoch": 0.0017281431434259108,
      "grad_norm": 1.412411093711853,
      "learning_rate": 9.992027688465707e-05,
      "loss": 0.8512,
      "step": 130
    },
    {
      "epoch": 0.0018610772313817502,
      "grad_norm": 2.1755828857421875,
      "learning_rate": 9.989910755653154e-05,
      "loss": 0.8609,
      "step": 140
    },
    {
      "epoch": 0.0019940113193375893,
      "grad_norm": 3.5878186225891113,
      "learning_rate": 9.987545125753819e-05,
      "loss": 0.8454,
      "step": 150
    },
    {
      "epoch": 0.0019940113193375893,
      "eval_loss": 0.9133399128913879,
      "eval_runtime": 2936.8352,
      "eval_samples_per_second": 43.14,
      "eval_steps_per_second": 10.785,
      "step": 150
    },
    {
      "epoch": 0.002126945407293429,
      "grad_norm": 0.8727161884307861,
      "learning_rate": 9.98493091667067e-05,
      "loss": 0.9236,
      "step": 160
    },
    {
      "epoch": 0.002259879495249268,
      "grad_norm": 1.0465607643127441,
      "learning_rate": 9.982068258695853e-05,
      "loss": 0.9194,
      "step": 170
    },
    {
      "epoch": 0.002392813583205107,
      "grad_norm": 1.2130919694900513,
      "learning_rate": 9.978957294504203e-05,
      "loss": 0.8099,
      "step": 180
    },
    {
      "epoch": 0.0025257476711609468,
      "grad_norm": 1.7668389081954956,
      "learning_rate": 9.975598179146133e-05,
      "loss": 0.8385,
      "step": 190
    },
    {
      "epoch": 0.002658681759116786,
      "grad_norm": 3.149250030517578,
      "learning_rate": 9.97199108003991e-05,
      "loss": 0.7771,
      "step": 200
    },
    {
      "epoch": 0.002791615847072625,
      "grad_norm": 0.8131629228591919,
      "learning_rate": 9.968136176963307e-05,
      "loss": 0.9286,
      "step": 210
    },
    {
      "epoch": 0.0029245499350284646,
      "grad_norm": 1.1880844831466675,
      "learning_rate": 9.964033662044643e-05,
      "loss": 0.9057,
      "step": 220
    },
    {
      "epoch": 0.0030574840229843038,
      "grad_norm": 1.2871088981628418,
      "learning_rate": 9.959683739753207e-05,
      "loss": 0.832,
      "step": 230
    },
    {
      "epoch": 0.003190418110940143,
      "grad_norm": 1.6375112533569336,
      "learning_rate": 9.955086626889068e-05,
      "loss": 0.8537,
      "step": 240
    },
    {
      "epoch": 0.0033233521988959825,
      "grad_norm": 2.9762630462646484,
      "learning_rate": 9.950242552572271e-05,
      "loss": 0.7039,
      "step": 250
    },
    {
      "epoch": 0.0034562862868518216,
      "grad_norm": 0.8247011303901672,
      "learning_rate": 9.945151758231421e-05,
      "loss": 0.8845,
      "step": 260
    },
    {
      "epoch": 0.003589220374807661,
      "grad_norm": 1.1122963428497314,
      "learning_rate": 9.939814497591636e-05,
      "loss": 0.8893,
      "step": 270
    },
    {
      "epoch": 0.0037221544627635004,
      "grad_norm": 1.3245172500610352,
      "learning_rate": 9.934231036661919e-05,
      "loss": 0.8365,
      "step": 280
    },
    {
      "epoch": 0.0038550885507193395,
      "grad_norm": 1.5120258331298828,
      "learning_rate": 9.928401653721891e-05,
      "loss": 0.8092,
      "step": 290
    },
    {
      "epoch": 0.003988022638675179,
      "grad_norm": 2.8242909908294678,
      "learning_rate": 9.922326639307917e-05,
      "loss": 0.7748,
      "step": 300
    },
    {
      "epoch": 0.003988022638675179,
      "eval_loss": 0.8625452518463135,
      "eval_runtime": 2939.9371,
      "eval_samples_per_second": 43.095,
      "eval_steps_per_second": 10.774,
      "step": 300
    },
    {
      "epoch": 0.004120956726631018,
      "grad_norm": 0.8277641534805298,
      "learning_rate": 9.91600629619864e-05,
      "loss": 0.9275,
      "step": 310
    },
    {
      "epoch": 0.004253890814586858,
      "grad_norm": 1.0220091342926025,
      "learning_rate": 9.909440939399876e-05,
      "loss": 0.9069,
      "step": 320
    },
    {
      "epoch": 0.004386824902542697,
      "grad_norm": 1.2098453044891357,
      "learning_rate": 9.902630896128923e-05,
      "loss": 0.7785,
      "step": 330
    },
    {
      "epoch": 0.004519758990498536,
      "grad_norm": 1.39773428440094,
      "learning_rate": 9.895576505798248e-05,
      "loss": 0.7963,
      "step": 340
    },
    {
      "epoch": 0.004652693078454375,
      "grad_norm": 2.3860318660736084,
      "learning_rate": 9.888278119998573e-05,
      "loss": 0.8,
      "step": 350
    },
    {
      "epoch": 0.004785627166410214,
      "grad_norm": 0.750569224357605,
      "learning_rate": 9.88073610248135e-05,
      "loss": 0.9546,
      "step": 360
    },
    {
      "epoch": 0.004918561254366054,
      "grad_norm": 1.0606836080551147,
      "learning_rate": 9.872950829140633e-05,
      "loss": 0.8189,
      "step": 370
    },
    {
      "epoch": 0.0050514953423218935,
      "grad_norm": 1.0504099130630493,
      "learning_rate": 9.864922687994347e-05,
      "loss": 0.8399,
      "step": 380
    },
    {
      "epoch": 0.005184429430277733,
      "grad_norm": 1.452014446258545,
      "learning_rate": 9.856652079164937e-05,
      "loss": 0.7719,
      "step": 390
    },
    {
      "epoch": 0.005317363518233572,
      "grad_norm": 3.2478177547454834,
      "learning_rate": 9.848139414859441e-05,
      "loss": 0.7396,
      "step": 400
    },
    {
      "epoch": 0.005450297606189411,
      "grad_norm": 0.8162371516227722,
      "learning_rate": 9.839385119348937e-05,
      "loss": 0.8558,
      "step": 410
    },
    {
      "epoch": 0.00558323169414525,
      "grad_norm": 1.0164737701416016,
      "learning_rate": 9.830389628947398e-05,
      "loss": 0.87,
      "step": 420
    },
    {
      "epoch": 0.00571616578210109,
      "grad_norm": 1.1020488739013672,
      "learning_rate": 9.82115339198995e-05,
      "loss": 0.8376,
      "step": 430
    },
    {
      "epoch": 0.005849099870056929,
      "grad_norm": 1.4051620960235596,
      "learning_rate": 9.811676868810517e-05,
      "loss": 0.7677,
      "step": 440
    },
    {
      "epoch": 0.005982033958012768,
      "grad_norm": 2.896073818206787,
      "learning_rate": 9.801960531718896e-05,
      "loss": 0.7716,
      "step": 450
    },
    {
      "epoch": 0.005982033958012768,
      "eval_loss": 0.8369041681289673,
      "eval_runtime": 2939.1318,
      "eval_samples_per_second": 43.107,
      "eval_steps_per_second": 10.777,
      "step": 450
    },
    {
      "epoch": 0.0061149680459686075,
      "grad_norm": 0.8108513951301575,
      "learning_rate": 9.792004864977198e-05,
      "loss": 0.9265,
      "step": 460
    },
    {
      "epoch": 0.006247902133924447,
      "grad_norm": 1.0227642059326172,
      "learning_rate": 9.781810364775722e-05,
      "loss": 0.8598,
      "step": 470
    },
    {
      "epoch": 0.006380836221880286,
      "grad_norm": 1.1522070169448853,
      "learning_rate": 9.771377539208228e-05,
      "loss": 0.7888,
      "step": 480
    },
    {
      "epoch": 0.006513770309836126,
      "grad_norm": 1.5358163118362427,
      "learning_rate": 9.760706908246603e-05,
      "loss": 0.8415,
      "step": 490
    },
    {
      "epoch": 0.006646704397791965,
      "grad_norm": 2.9296483993530273,
      "learning_rate": 9.749799003714954e-05,
      "loss": 0.7869,
      "step": 500
    },
    {
      "epoch": 0.006779638485747804,
      "grad_norm": 0.7771769165992737,
      "learning_rate": 9.738654369263103e-05,
      "loss": 0.9162,
      "step": 510
    },
    {
      "epoch": 0.006912572573703643,
      "grad_norm": 0.8883762955665588,
      "learning_rate": 9.727273560339483e-05,
      "loss": 0.8822,
      "step": 520
    },
    {
      "epoch": 0.007045506661659482,
      "grad_norm": 1.1782065629959106,
      "learning_rate": 9.715657144163463e-05,
      "loss": 0.8331,
      "step": 530
    },
    {
      "epoch": 0.007178440749615322,
      "grad_norm": 1.5381768941879272,
      "learning_rate": 9.703805699697072e-05,
      "loss": 0.7452,
      "step": 540
    },
    {
      "epoch": 0.0073113748375711616,
      "grad_norm": 3.0118932723999023,
      "learning_rate": 9.691719817616147e-05,
      "loss": 0.8766,
      "step": 550
    },
    {
      "epoch": 0.007444308925527001,
      "grad_norm": 0.883840024471283,
      "learning_rate": 9.679400100280896e-05,
      "loss": 0.9095,
      "step": 560
    },
    {
      "epoch": 0.00757724301348284,
      "grad_norm": 0.9513404369354248,
      "learning_rate": 9.666847161705867e-05,
      "loss": 0.9024,
      "step": 570
    },
    {
      "epoch": 0.007710177101438679,
      "grad_norm": 0.9779698252677917,
      "learning_rate": 9.654061627529354e-05,
      "loss": 0.8098,
      "step": 580
    },
    {
      "epoch": 0.007843111189394519,
      "grad_norm": 1.8038041591644287,
      "learning_rate": 9.641044134982215e-05,
      "loss": 0.8517,
      "step": 590
    },
    {
      "epoch": 0.007976045277350357,
      "grad_norm": 2.9668469429016113,
      "learning_rate": 9.627795332856107e-05,
      "loss": 0.7795,
      "step": 600
    },
    {
      "epoch": 0.007976045277350357,
      "eval_loss": 0.821550190448761,
      "eval_runtime": 2935.4759,
      "eval_samples_per_second": 43.16,
      "eval_steps_per_second": 10.79,
      "step": 600
    },
    {
      "epoch": 0.008108979365306197,
      "grad_norm": 0.8701363801956177,
      "learning_rate": 9.614315881471154e-05,
      "loss": 0.9088,
      "step": 610
    },
    {
      "epoch": 0.008241913453262036,
      "grad_norm": 1.020605206489563,
      "learning_rate": 9.600606452643037e-05,
      "loss": 0.8598,
      "step": 620
    },
    {
      "epoch": 0.008374847541217876,
      "grad_norm": 1.118003010749817,
      "learning_rate": 9.586667729649513e-05,
      "loss": 0.8552,
      "step": 630
    },
    {
      "epoch": 0.008507781629173716,
      "grad_norm": 1.3862948417663574,
      "learning_rate": 9.572500407196348e-05,
      "loss": 0.7882,
      "step": 640
    },
    {
      "epoch": 0.008640715717129554,
      "grad_norm": 2.998286485671997,
      "learning_rate": 9.55810519138271e-05,
      "loss": 0.7784,
      "step": 650
    },
    {
      "epoch": 0.008773649805085394,
      "grad_norm": 0.9497479796409607,
      "learning_rate": 9.543482799665969e-05,
      "loss": 0.9353,
      "step": 660
    },
    {
      "epoch": 0.008906583893041232,
      "grad_norm": 0.9987872242927551,
      "learning_rate": 9.528633960825933e-05,
      "loss": 0.8585,
      "step": 670
    },
    {
      "epoch": 0.009039517980997072,
      "grad_norm": 1.2126046419143677,
      "learning_rate": 9.513559414928538e-05,
      "loss": 0.828,
      "step": 680
    },
    {
      "epoch": 0.009172452068952912,
      "grad_norm": 1.1770802736282349,
      "learning_rate": 9.498259913288953e-05,
      "loss": 0.8091,
      "step": 690
    },
    {
      "epoch": 0.00930538615690875,
      "grad_norm": 2.9725301265716553,
      "learning_rate": 9.482736218434143e-05,
      "loss": 0.7926,
      "step": 700
    },
    {
      "epoch": 0.00943832024486459,
      "grad_norm": 0.9037257432937622,
      "learning_rate": 9.466989104064853e-05,
      "loss": 0.8929,
      "step": 710
    },
    {
      "epoch": 0.009571254332820429,
      "grad_norm": 0.9316276907920837,
      "learning_rate": 9.451019355017056e-05,
      "loss": 0.9077,
      "step": 720
    },
    {
      "epoch": 0.009704188420776269,
      "grad_norm": 1.080407977104187,
      "learning_rate": 9.43482776722284e-05,
      "loss": 0.8093,
      "step": 730
    },
    {
      "epoch": 0.009837122508732109,
      "grad_norm": 1.2614948749542236,
      "learning_rate": 9.418415147670725e-05,
      "loss": 0.7689,
      "step": 740
    },
    {
      "epoch": 0.009970056596687947,
      "grad_norm": 2.555124521255493,
      "learning_rate": 9.401782314365457e-05,
      "loss": 0.802,
      "step": 750
    },
    {
      "epoch": 0.009970056596687947,
      "eval_loss": 0.8119913935661316,
      "eval_runtime": 2937.8069,
      "eval_samples_per_second": 43.126,
      "eval_steps_per_second": 10.782,
      "step": 750
    },
    {
      "epoch": 0.010102990684643787,
      "grad_norm": 0.8965262770652771,
      "learning_rate": 9.38493009628723e-05,
      "loss": 0.8909,
      "step": 760
    },
    {
      "epoch": 0.010235924772599625,
      "grad_norm": 1.1142463684082031,
      "learning_rate": 9.36785933335037e-05,
      "loss": 0.8622,
      "step": 770
    },
    {
      "epoch": 0.010368858860555465,
      "grad_norm": 1.1537195444107056,
      "learning_rate": 9.350570876361482e-05,
      "loss": 0.7657,
      "step": 780
    },
    {
      "epoch": 0.010501792948511304,
      "grad_norm": 1.629679560661316,
      "learning_rate": 9.333065586977035e-05,
      "loss": 0.7819,
      "step": 790
    },
    {
      "epoch": 0.010634727036467144,
      "grad_norm": 2.6244359016418457,
      "learning_rate": 9.315344337660421e-05,
      "loss": 0.778,
      "step": 800
    },
    {
      "epoch": 0.010767661124422984,
      "grad_norm": 0.7998455166816711,
      "learning_rate": 9.297408011638477e-05,
      "loss": 0.8324,
      "step": 810
    },
    {
      "epoch": 0.010900595212378822,
      "grad_norm": 0.9035855531692505,
      "learning_rate": 9.279257502857455e-05,
      "loss": 0.8705,
      "step": 820
    },
    {
      "epoch": 0.011033529300334662,
      "grad_norm": 1.1769347190856934,
      "learning_rate": 9.260893715938477e-05,
      "loss": 0.7977,
      "step": 830
    },
    {
      "epoch": 0.0111664633882905,
      "grad_norm": 1.4826371669769287,
      "learning_rate": 9.24231756613244e-05,
      "loss": 0.7626,
      "step": 840
    },
    {
      "epoch": 0.01129939747624634,
      "grad_norm": 3.1065542697906494,
      "learning_rate": 9.22352997927441e-05,
      "loss": 0.7633,
      "step": 850
    },
    {
      "epoch": 0.01143233156420218,
      "grad_norm": 0.872209370136261,
      "learning_rate": 9.20453189173747e-05,
      "loss": 0.916,
      "step": 860
    },
    {
      "epoch": 0.011565265652158018,
      "grad_norm": 0.9683641791343689,
      "learning_rate": 9.185324250386054e-05,
      "loss": 0.8759,
      "step": 870
    },
    {
      "epoch": 0.011698199740113858,
      "grad_norm": 1.2745503187179565,
      "learning_rate": 9.165908012528755e-05,
      "loss": 0.8134,
      "step": 880
    },
    {
      "epoch": 0.011831133828069697,
      "grad_norm": 1.3109657764434814,
      "learning_rate": 9.146284145870614e-05,
      "loss": 0.7875,
      "step": 890
    },
    {
      "epoch": 0.011964067916025537,
      "grad_norm": 2.3323986530303955,
      "learning_rate": 9.126453628464888e-05,
      "loss": 0.7521,
      "step": 900
    },
    {
      "epoch": 0.011964067916025537,
      "eval_loss": 0.8035673499107361,
      "eval_runtime": 2937.1699,
      "eval_samples_per_second": 43.135,
      "eval_steps_per_second": 10.784,
      "step": 900
    },
    {
      "epoch": 0.012097002003981377,
      "grad_norm": 0.820439338684082,
      "learning_rate": 9.106417448664306e-05,
      "loss": 0.8856,
      "step": 910
    },
    {
      "epoch": 0.012229936091937215,
      "grad_norm": 1.0313884019851685,
      "learning_rate": 9.086176605071805e-05,
      "loss": 0.8814,
      "step": 920
    },
    {
      "epoch": 0.012362870179893055,
      "grad_norm": 1.2534911632537842,
      "learning_rate": 9.06573210649077e-05,
      "loss": 0.8069,
      "step": 930
    },
    {
      "epoch": 0.012495804267848893,
      "grad_norm": 1.3286960124969482,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7651,
      "step": 940
    },
    {
      "epoch": 0.012628738355804733,
      "grad_norm": 3.241807460784912,
      "learning_rate": 9.024236230276629e-05,
      "loss": 0.8244,
      "step": 950
    },
    {
      "epoch": 0.012761672443760572,
      "grad_norm": 0.8718632459640503,
      "learning_rate": 9.003186920797452e-05,
      "loss": 0.8792,
      "step": 960
    },
    {
      "epoch": 0.012894606531716412,
      "grad_norm": 0.9083179235458374,
      "learning_rate": 8.981938092534517e-05,
      "loss": 0.8644,
      "step": 970
    },
    {
      "epoch": 0.013027540619672252,
      "grad_norm": 1.1338489055633545,
      "learning_rate": 8.960490804529144e-05,
      "loss": 0.8368,
      "step": 980
    },
    {
      "epoch": 0.01316047470762809,
      "grad_norm": 1.466839075088501,
      "learning_rate": 8.938846125713891e-05,
      "loss": 0.7183,
      "step": 990
    },
    {
      "epoch": 0.01329340879558393,
      "grad_norm": 2.3635900020599365,
      "learning_rate": 8.917005134859263e-05,
      "loss": 0.7475,
      "step": 1000
    },
    {
      "epoch": 0.013426342883539768,
      "grad_norm": 0.8753401041030884,
      "learning_rate": 8.894968920519959e-05,
      "loss": 0.9097,
      "step": 1010
    },
    {
      "epoch": 0.013559276971495608,
      "grad_norm": 1.0394352674484253,
      "learning_rate": 8.872738580980615e-05,
      "loss": 0.8533,
      "step": 1020
    },
    {
      "epoch": 0.013692211059451448,
      "grad_norm": 1.3622921705245972,
      "learning_rate": 8.850315224201063e-05,
      "loss": 0.8018,
      "step": 1030
    },
    {
      "epoch": 0.013825145147407287,
      "grad_norm": 1.4305646419525146,
      "learning_rate": 8.827699967761108e-05,
      "loss": 0.8168,
      "step": 1040
    },
    {
      "epoch": 0.013958079235363127,
      "grad_norm": 2.2436411380767822,
      "learning_rate": 8.80489393880484e-05,
      "loss": 0.7678,
      "step": 1050
    },
    {
      "epoch": 0.013958079235363127,
      "eval_loss": 0.7980687022209167,
      "eval_runtime": 2936.4148,
      "eval_samples_per_second": 43.146,
      "eval_steps_per_second": 10.787,
      "step": 1050
    }
  ],
  "logging_steps": 10,
  "max_steps": 4500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0206243314335744e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}