{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.836065573770492,
  "eval_steps": 500,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 2.1467645168304443,
      "learning_rate": 0.0004973224043715847,
      "loss": 5.4078,
      "step": 50
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.8721267580986023,
      "learning_rate": 0.0004945901639344262,
      "loss": 1.2654,
      "step": 100
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.8103071451187134,
      "learning_rate": 0.0004918579234972678,
      "loss": 1.0538,
      "step": 150
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1.3929318189620972,
      "learning_rate": 0.0004891256830601093,
      "loss": 1.0236,
      "step": 200
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.970960259437561,
      "learning_rate": 0.00048639344262295083,
      "loss": 1.075,
      "step": 250
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.9727946519851685,
      "learning_rate": 0.00048366120218579234,
      "loss": 1.0434,
      "step": 300
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.6411604285240173,
      "learning_rate": 0.0004809289617486339,
      "loss": 0.9285,
      "step": 350
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.8864787817001343,
      "learning_rate": 0.0004781967213114754,
      "loss": 0.9315,
      "step": 400
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.8886504173278809,
      "learning_rate": 0.0004754644808743169,
      "loss": 0.8818,
      "step": 450
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.7289233803749084,
      "learning_rate": 0.0004727322404371585,
      "loss": 0.92,
      "step": 500
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 1.0301029682159424,
      "learning_rate": 0.00047,
      "loss": 0.8222,
      "step": 550
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.808475136756897,
      "learning_rate": 0.00046726775956284155,
      "loss": 0.8767,
      "step": 600
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": 0.8232861161231995,
      "learning_rate": 0.0004645355191256831,
      "loss": 0.835,
      "step": 650
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 0.9552908539772034,
      "learning_rate": 0.0004618032786885246,
      "loss": 0.8203,
      "step": 700
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 0.7888686656951904,
      "learning_rate": 0.00045907103825136613,
      "loss": 0.8296,
      "step": 750
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.7473599910736084,
      "learning_rate": 0.0004563387978142077,
      "loss": 0.7801,
      "step": 800
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": 0.8543986678123474,
      "learning_rate": 0.0004536065573770492,
      "loss": 0.9248,
      "step": 850
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.7910193204879761,
      "learning_rate": 0.0004508743169398907,
      "loss": 0.8386,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6989373564720154,
      "eval_runtime": 35.1236,
      "eval_samples_per_second": 23.175,
      "eval_steps_per_second": 2.904,
      "step": 915
    },
    {
      "epoch": 1.0382513661202186,
      "grad_norm": 1.1451815366744995,
      "learning_rate": 0.00044814207650273227,
      "loss": 0.7198,
      "step": 950
    },
    {
      "epoch": 1.092896174863388,
      "grad_norm": 0.7096536755561829,
      "learning_rate": 0.0004454098360655738,
      "loss": 0.7374,
      "step": 1000
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 0.8436596393585205,
      "learning_rate": 0.0004426775956284153,
      "loss": 0.7471,
      "step": 1050
    },
    {
      "epoch": 1.2021857923497268,
      "grad_norm": 0.8844044208526611,
      "learning_rate": 0.00043994535519125685,
      "loss": 0.7072,
      "step": 1100
    },
    {
      "epoch": 1.2568306010928962,
      "grad_norm": 0.9547187089920044,
      "learning_rate": 0.00043721311475409836,
      "loss": 0.7618,
      "step": 1150
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.8470160961151123,
      "learning_rate": 0.00043448087431693987,
      "loss": 0.7719,
      "step": 1200
    },
    {
      "epoch": 1.366120218579235,
      "grad_norm": 0.8797179460525513,
      "learning_rate": 0.00043174863387978143,
      "loss": 0.7172,
      "step": 1250
    },
    {
      "epoch": 1.4207650273224044,
      "grad_norm": 0.6831291317939758,
      "learning_rate": 0.00042901639344262294,
      "loss": 0.7254,
      "step": 1300
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.7458399534225464,
      "learning_rate": 0.00042628415300546445,
      "loss": 0.7219,
      "step": 1350
    },
    {
      "epoch": 1.530054644808743,
      "grad_norm": 0.7829724550247192,
      "learning_rate": 0.000423551912568306,
      "loss": 0.6969,
      "step": 1400
    },
    {
      "epoch": 1.5846994535519126,
      "grad_norm": 0.914277970790863,
      "learning_rate": 0.0004208196721311475,
      "loss": 0.7088,
      "step": 1450
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.9189252853393555,
      "learning_rate": 0.00041808743169398913,
      "loss": 0.7574,
      "step": 1500
    },
    {
      "epoch": 1.6939890710382515,
      "grad_norm": 0.8233757019042969,
      "learning_rate": 0.00041535519125683064,
      "loss": 0.7248,
      "step": 1550
    },
    {
      "epoch": 1.748633879781421,
      "grad_norm": 0.5294966101646423,
      "learning_rate": 0.00041262295081967215,
      "loss": 0.7173,
      "step": 1600
    },
    {
      "epoch": 1.8032786885245902,
      "grad_norm": 0.7432788014411926,
      "learning_rate": 0.0004098907103825137,
      "loss": 0.731,
      "step": 1650
    },
    {
      "epoch": 1.8579234972677594,
      "grad_norm": 0.9326347708702087,
      "learning_rate": 0.0004071584699453552,
      "loss": 0.6559,
      "step": 1700
    },
    {
      "epoch": 1.9125683060109289,
      "grad_norm": 0.6357129216194153,
      "learning_rate": 0.00040442622950819673,
      "loss": 0.7079,
      "step": 1750
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.6454396843910217,
      "learning_rate": 0.0004016939890710383,
      "loss": 0.6284,
      "step": 1800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6172024607658386,
      "eval_runtime": 34.4665,
      "eval_samples_per_second": 23.617,
      "eval_steps_per_second": 2.959,
      "step": 1830
    },
    {
      "epoch": 2.021857923497268,
      "grad_norm": 0.9404008388519287,
      "learning_rate": 0.0003989617486338798,
      "loss": 0.6996,
      "step": 1850
    },
    {
      "epoch": 2.0765027322404372,
      "grad_norm": 0.7585016489028931,
      "learning_rate": 0.0003962295081967213,
      "loss": 0.6634,
      "step": 1900
    },
    {
      "epoch": 2.1311475409836067,
      "grad_norm": 0.9319397807121277,
      "learning_rate": 0.00039349726775956287,
      "loss": 0.6439,
      "step": 1950
    },
    {
      "epoch": 2.185792349726776,
      "grad_norm": 0.7812663912773132,
      "learning_rate": 0.0003907650273224044,
      "loss": 0.6807,
      "step": 2000
    },
    {
      "epoch": 2.240437158469945,
      "grad_norm": 0.8016160726547241,
      "learning_rate": 0.0003880327868852459,
      "loss": 0.6121,
      "step": 2050
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 0.5846936106681824,
      "learning_rate": 0.00038530054644808745,
      "loss": 0.6501,
      "step": 2100
    },
    {
      "epoch": 2.349726775956284,
      "grad_norm": 0.6993207931518555,
      "learning_rate": 0.00038256830601092896,
      "loss": 0.6242,
      "step": 2150
    },
    {
      "epoch": 2.4043715846994536,
      "grad_norm": 0.5866222381591797,
      "learning_rate": 0.00037983606557377047,
      "loss": 0.5766,
      "step": 2200
    },
    {
      "epoch": 2.459016393442623,
      "grad_norm": 0.8375122547149658,
      "learning_rate": 0.00037710382513661203,
      "loss": 0.6395,
      "step": 2250
    },
    {
      "epoch": 2.5136612021857925,
      "grad_norm": 0.9567583799362183,
      "learning_rate": 0.00037437158469945354,
      "loss": 0.6829,
      "step": 2300
    },
    {
      "epoch": 2.5683060109289615,
      "grad_norm": 0.829088032245636,
      "learning_rate": 0.00037163934426229505,
      "loss": 0.6138,
      "step": 2350
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.7738655805587769,
      "learning_rate": 0.00036890710382513666,
      "loss": 0.5961,
      "step": 2400
    },
    {
      "epoch": 2.6775956284153004,
      "grad_norm": 0.6849051117897034,
      "learning_rate": 0.00036617486338797817,
      "loss": 0.6158,
      "step": 2450
    },
    {
      "epoch": 2.73224043715847,
      "grad_norm": 0.6353682279586792,
      "learning_rate": 0.0003634426229508197,
      "loss": 0.6077,
      "step": 2500
    },
    {
      "epoch": 2.7868852459016393,
      "grad_norm": 0.6507243514060974,
      "learning_rate": 0.00036071038251366124,
      "loss": 0.5881,
      "step": 2550
    },
    {
      "epoch": 2.841530054644809,
      "grad_norm": 0.7680765390396118,
      "learning_rate": 0.00035797814207650275,
      "loss": 0.64,
      "step": 2600
    },
    {
      "epoch": 2.8961748633879782,
      "grad_norm": 0.8768549561500549,
      "learning_rate": 0.00035524590163934426,
      "loss": 0.5946,
      "step": 2650
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 0.9345018267631531,
      "learning_rate": 0.0003525136612021858,
      "loss": 0.5986,
      "step": 2700
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5772798657417297,
      "eval_runtime": 34.1537,
      "eval_samples_per_second": 23.833,
      "eval_steps_per_second": 2.986,
      "step": 2745
    },
    {
      "epoch": 3.0054644808743167,
      "grad_norm": 0.8109590411186218,
      "learning_rate": 0.00034978142076502733,
      "loss": 0.6056,
      "step": 2750
    },
    {
      "epoch": 3.060109289617486,
      "grad_norm": 1.1651564836502075,
      "learning_rate": 0.00034704918032786884,
      "loss": 0.5321,
      "step": 2800
    },
    {
      "epoch": 3.1147540983606556,
      "grad_norm": 0.9508790969848633,
      "learning_rate": 0.0003443169398907104,
      "loss": 0.5405,
      "step": 2850
    },
    {
      "epoch": 3.169398907103825,
      "grad_norm": 0.7765358686447144,
      "learning_rate": 0.0003415846994535519,
      "loss": 0.6053,
      "step": 2900
    },
    {
      "epoch": 3.2240437158469946,
      "grad_norm": 1.0186572074890137,
      "learning_rate": 0.0003388524590163934,
      "loss": 0.6171,
      "step": 2950
    },
    {
      "epoch": 3.278688524590164,
      "grad_norm": 0.9198819398880005,
      "learning_rate": 0.000336120218579235,
      "loss": 0.5755,
      "step": 3000
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 1.0580278635025024,
      "learning_rate": 0.0003333879781420765,
      "loss": 0.5521,
      "step": 3050
    },
    {
      "epoch": 3.387978142076503,
      "grad_norm": 0.637541651725769,
      "learning_rate": 0.00033065573770491805,
      "loss": 0.5288,
      "step": 3100
    },
    {
      "epoch": 3.442622950819672,
      "grad_norm": 1.3321665525436401,
      "learning_rate": 0.00032792349726775956,
      "loss": 0.57,
      "step": 3150
    },
    {
      "epoch": 3.4972677595628414,
      "grad_norm": 1.1390025615692139,
      "learning_rate": 0.00032519125683060107,
      "loss": 0.588,
      "step": 3200
    },
    {
      "epoch": 3.551912568306011,
      "grad_norm": 0.6929836273193359,
      "learning_rate": 0.00032245901639344263,
      "loss": 0.5508,
      "step": 3250
    },
    {
      "epoch": 3.6065573770491803,
      "grad_norm": 0.6794707179069519,
      "learning_rate": 0.00031972677595628414,
      "loss": 0.5284,
      "step": 3300
    },
    {
      "epoch": 3.66120218579235,
      "grad_norm": 0.7672021985054016,
      "learning_rate": 0.0003169945355191257,
      "loss": 0.5968,
      "step": 3350
    },
    {
      "epoch": 3.7158469945355193,
      "grad_norm": 1.0557798147201538,
      "learning_rate": 0.00031426229508196726,
      "loss": 0.5586,
      "step": 3400
    },
    {
      "epoch": 3.7704918032786887,
      "grad_norm": 0.7945201992988586,
      "learning_rate": 0.00031153005464480877,
      "loss": 0.5042,
      "step": 3450
    },
    {
      "epoch": 3.8251366120218577,
      "grad_norm": 0.49171268939971924,
      "learning_rate": 0.0003087978142076503,
      "loss": 0.5695,
      "step": 3500
    },
    {
      "epoch": 3.879781420765027,
      "grad_norm": 1.0232176780700684,
      "learning_rate": 0.00030606557377049184,
      "loss": 0.5511,
      "step": 3550
    },
    {
      "epoch": 3.9344262295081966,
      "grad_norm": 0.6561440229415894,
      "learning_rate": 0.00030333333333333335,
      "loss": 0.5256,
      "step": 3600
    },
    {
      "epoch": 3.989071038251366,
      "grad_norm": 0.6772050261497498,
      "learning_rate": 0.00030060109289617486,
      "loss": 0.5752,
      "step": 3650
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5453636050224304,
      "eval_runtime": 18.8015,
      "eval_samples_per_second": 43.294,
      "eval_steps_per_second": 5.425,
      "step": 3660
    },
    {
      "epoch": 4.043715846994536,
      "grad_norm": 0.9626933336257935,
      "learning_rate": 0.0002978688524590164,
      "loss": 0.5659,
      "step": 3700
    },
    {
      "epoch": 4.098360655737705,
      "grad_norm": 0.6350908875465393,
      "learning_rate": 0.00029513661202185793,
      "loss": 0.4663,
      "step": 3750
    },
    {
      "epoch": 4.1530054644808745,
      "grad_norm": 0.862783670425415,
      "learning_rate": 0.00029240437158469944,
      "loss": 0.5265,
      "step": 3800
    },
    {
      "epoch": 4.2076502732240435,
      "grad_norm": 0.845670223236084,
      "learning_rate": 0.000289672131147541,
      "loss": 0.5029,
      "step": 3850
    },
    {
      "epoch": 4.262295081967213,
      "grad_norm": 0.5551162958145142,
      "learning_rate": 0.0002869398907103825,
      "loss": 0.473,
      "step": 3900
    },
    {
      "epoch": 4.316939890710382,
      "grad_norm": 0.8691427707672119,
      "learning_rate": 0.000284207650273224,
      "loss": 0.5257,
      "step": 3950
    },
    {
      "epoch": 4.371584699453552,
      "grad_norm": 0.7771849036216736,
      "learning_rate": 0.0002814754098360656,
      "loss": 0.4816,
      "step": 4000
    },
    {
      "epoch": 4.426229508196721,
      "grad_norm": 0.8042870163917542,
      "learning_rate": 0.0002787431693989071,
      "loss": 0.5424,
      "step": 4050
    },
    {
      "epoch": 4.48087431693989,
      "grad_norm": 0.9805220365524292,
      "learning_rate": 0.0002760109289617486,
      "loss": 0.5323,
      "step": 4100
    },
    {
      "epoch": 4.53551912568306,
      "grad_norm": 0.7407246828079224,
      "learning_rate": 0.00027327868852459016,
      "loss": 0.5581,
      "step": 4150
    },
    {
      "epoch": 4.590163934426229,
      "grad_norm": 0.7939064502716064,
      "learning_rate": 0.00027054644808743167,
      "loss": 0.4608,
      "step": 4200
    },
    {
      "epoch": 4.644808743169399,
      "grad_norm": 0.8826588988304138,
      "learning_rate": 0.00026781420765027323,
      "loss": 0.5058,
      "step": 4250
    },
    {
      "epoch": 4.699453551912568,
      "grad_norm": 0.8143342137336731,
      "learning_rate": 0.0002650819672131148,
      "loss": 0.5476,
      "step": 4300
    },
    {
      "epoch": 4.754098360655737,
      "grad_norm": 0.6828013062477112,
      "learning_rate": 0.0002623497267759563,
      "loss": 0.5289,
      "step": 4350
    },
    {
      "epoch": 4.808743169398907,
      "grad_norm": 0.8838549256324768,
      "learning_rate": 0.0002596174863387978,
      "loss": 0.4789,
      "step": 4400
    },
    {
      "epoch": 4.863387978142076,
      "grad_norm": 1.089988350868225,
      "learning_rate": 0.0002568852459016394,
      "loss": 0.5388,
      "step": 4450
    },
    {
      "epoch": 4.918032786885246,
      "grad_norm": 0.7895328998565674,
      "learning_rate": 0.0002541530054644809,
      "loss": 0.4863,
      "step": 4500
    },
    {
      "epoch": 4.972677595628415,
      "grad_norm": 0.7219722270965576,
      "learning_rate": 0.00025142076502732244,
      "loss": 0.4884,
      "step": 4550
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5269655585289001,
      "eval_runtime": 82.4268,
      "eval_samples_per_second": 9.875,
      "eval_steps_per_second": 1.237,
      "step": 4575
    },
    {
      "epoch": 5.027322404371585,
      "grad_norm": 0.611998975276947,
      "learning_rate": 0.00024868852459016395,
      "loss": 0.5115,
      "step": 4600
    },
    {
      "epoch": 5.081967213114754,
      "grad_norm": 0.8524764776229858,
      "learning_rate": 0.00024595628415300546,
      "loss": 0.4502,
      "step": 4650
    },
    {
      "epoch": 5.136612021857924,
      "grad_norm": 1.2595255374908447,
      "learning_rate": 0.000243224043715847,
      "loss": 0.4866,
      "step": 4700
    },
    {
      "epoch": 5.191256830601093,
      "grad_norm": 0.887760579586029,
      "learning_rate": 0.00024049180327868853,
      "loss": 0.4813,
      "step": 4750
    },
    {
      "epoch": 5.245901639344262,
      "grad_norm": 0.6199231147766113,
      "learning_rate": 0.00023775956284153004,
      "loss": 0.476,
      "step": 4800
    },
    {
      "epoch": 5.300546448087432,
      "grad_norm": 0.8007299304008484,
      "learning_rate": 0.00023502732240437158,
      "loss": 0.4773,
      "step": 4850
    },
    {
      "epoch": 5.355191256830601,
      "grad_norm": 0.5639681816101074,
      "learning_rate": 0.0002322950819672131,
      "loss": 0.4903,
      "step": 4900
    },
    {
      "epoch": 5.409836065573771,
      "grad_norm": 0.980188250541687,
      "learning_rate": 0.00022956284153005467,
      "loss": 0.5212,
      "step": 4950
    },
    {
      "epoch": 5.46448087431694,
      "grad_norm": 0.8411896228790283,
      "learning_rate": 0.00022683060109289618,
      "loss": 0.4216,
      "step": 5000
    },
    {
      "epoch": 5.51912568306011,
      "grad_norm": 0.9759379029273987,
      "learning_rate": 0.00022409836065573772,
      "loss": 0.47,
      "step": 5050
    },
    {
      "epoch": 5.573770491803279,
      "grad_norm": 0.7654640674591064,
      "learning_rate": 0.00022136612021857925,
      "loss": 0.4756,
      "step": 5100
    },
    {
      "epoch": 5.628415300546449,
      "grad_norm": 0.6740959882736206,
      "learning_rate": 0.00021863387978142076,
      "loss": 0.4836,
      "step": 5150
    },
    {
      "epoch": 5.683060109289618,
      "grad_norm": 0.702583909034729,
      "learning_rate": 0.0002159016393442623,
      "loss": 0.4388,
      "step": 5200
    },
    {
      "epoch": 5.737704918032787,
      "grad_norm": 0.5787151455879211,
      "learning_rate": 0.00021316939890710383,
      "loss": 0.4364,
      "step": 5250
    },
    {
      "epoch": 5.7923497267759565,
      "grad_norm": 0.8957023620605469,
      "learning_rate": 0.00021043715846994534,
      "loss": 0.4574,
      "step": 5300
    },
    {
      "epoch": 5.8469945355191255,
      "grad_norm": 0.6572920680046082,
      "learning_rate": 0.00020770491803278688,
      "loss": 0.5049,
      "step": 5350
    },
    {
      "epoch": 5.901639344262295,
      "grad_norm": 0.7359984517097473,
      "learning_rate": 0.00020497267759562844,
      "loss": 0.4999,
      "step": 5400
    },
    {
      "epoch": 5.956284153005464,
      "grad_norm": 1.1582518815994263,
      "learning_rate": 0.00020224043715846995,
      "loss": 0.4899,
      "step": 5450
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.512095034122467,
      "eval_runtime": 18.8094,
      "eval_samples_per_second": 43.276,
      "eval_steps_per_second": 5.423,
      "step": 5490
    },
    {
      "epoch": 6.0109289617486334,
      "grad_norm": 0.8027153611183167,
      "learning_rate": 0.00019950819672131148,
      "loss": 0.4413,
      "step": 5500
    },
    {
      "epoch": 6.065573770491803,
      "grad_norm": 1.0127980709075928,
      "learning_rate": 0.00019677595628415302,
      "loss": 0.4161,
      "step": 5550
    },
    {
      "epoch": 6.120218579234972,
      "grad_norm": 0.6213232278823853,
      "learning_rate": 0.00019404371584699453,
      "loss": 0.4174,
      "step": 5600
    },
    {
      "epoch": 6.174863387978142,
      "grad_norm": 0.910073459148407,
      "learning_rate": 0.00019131147540983606,
      "loss": 0.4577,
      "step": 5650
    },
    {
      "epoch": 6.229508196721311,
      "grad_norm": 0.6484264135360718,
      "learning_rate": 0.0001885792349726776,
      "loss": 0.4764,
      "step": 5700
    },
    {
      "epoch": 6.284153005464481,
      "grad_norm": 0.6599116325378418,
      "learning_rate": 0.00018584699453551913,
      "loss": 0.4607,
      "step": 5750
    },
    {
      "epoch": 6.33879781420765,
      "grad_norm": 0.6737315058708191,
      "learning_rate": 0.00018311475409836064,
      "loss": 0.4512,
      "step": 5800
    },
    {
      "epoch": 6.39344262295082,
      "grad_norm": 0.798819363117218,
      "learning_rate": 0.0001803825136612022,
      "loss": 0.4477,
      "step": 5850
    },
    {
      "epoch": 6.448087431693989,
      "grad_norm": 0.8825194835662842,
      "learning_rate": 0.00017765027322404374,
      "loss": 0.4602,
      "step": 5900
    },
    {
      "epoch": 6.502732240437158,
      "grad_norm": 0.9620506167411804,
      "learning_rate": 0.00017491803278688525,
      "loss": 0.4387,
      "step": 5950
    },
    {
      "epoch": 6.557377049180328,
      "grad_norm": 0.6066147089004517,
      "learning_rate": 0.00017218579234972678,
      "loss": 0.4325,
      "step": 6000
    },
    {
      "epoch": 6.612021857923497,
      "grad_norm": 1.0289280414581299,
      "learning_rate": 0.00016945355191256832,
      "loss": 0.4678,
      "step": 6050
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.849380612373352,
      "learning_rate": 0.00016672131147540983,
      "loss": 0.4462,
      "step": 6100
    },
    {
      "epoch": 6.721311475409836,
      "grad_norm": 0.9880459904670715,
      "learning_rate": 0.00016398907103825136,
      "loss": 0.4425,
      "step": 6150
    },
    {
      "epoch": 6.775956284153006,
      "grad_norm": 0.5747489333152771,
      "learning_rate": 0.0001612568306010929,
      "loss": 0.4123,
      "step": 6200
    },
    {
      "epoch": 6.830601092896175,
      "grad_norm": 0.9202123880386353,
      "learning_rate": 0.0001585245901639344,
      "loss": 0.4367,
      "step": 6250
    },
    {
      "epoch": 6.885245901639344,
      "grad_norm": 0.812148928642273,
      "learning_rate": 0.00015579234972677597,
      "loss": 0.4147,
      "step": 6300
    },
    {
      "epoch": 6.939890710382514,
      "grad_norm": 0.8769338130950928,
      "learning_rate": 0.0001530601092896175,
      "loss": 0.4192,
      "step": 6350
    },
    {
      "epoch": 6.994535519125683,
      "grad_norm": 1.2912615537643433,
      "learning_rate": 0.000150327868852459,
      "loss": 0.4471,
      "step": 6400
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.5004224181175232,
      "eval_runtime": 20.3806,
      "eval_samples_per_second": 39.94,
      "eval_steps_per_second": 5.005,
      "step": 6405
    },
    {
      "epoch": 7.049180327868853,
      "grad_norm": 0.5414749979972839,
      "learning_rate": 0.00014759562841530055,
      "loss": 0.4265,
      "step": 6450
    },
    {
      "epoch": 7.103825136612022,
      "grad_norm": 0.7735195159912109,
      "learning_rate": 0.00014486338797814208,
      "loss": 0.4124,
      "step": 6500
    },
    {
      "epoch": 7.158469945355192,
      "grad_norm": 0.7762187123298645,
      "learning_rate": 0.00014213114754098362,
      "loss": 0.4004,
      "step": 6550
    },
    {
      "epoch": 7.213114754098361,
      "grad_norm": 0.6879094243049622,
      "learning_rate": 0.00013939890710382513,
      "loss": 0.4414,
      "step": 6600
    },
    {
      "epoch": 7.26775956284153,
      "grad_norm": 0.8285422921180725,
      "learning_rate": 0.00013666666666666666,
      "loss": 0.4629,
      "step": 6650
    },
    {
      "epoch": 7.3224043715847,
      "grad_norm": 0.8115780353546143,
      "learning_rate": 0.0001339344262295082,
      "loss": 0.3816,
      "step": 6700
    },
    {
      "epoch": 7.377049180327869,
      "grad_norm": 0.8859063386917114,
      "learning_rate": 0.00013120218579234973,
      "loss": 0.3816,
      "step": 6750
    },
    {
      "epoch": 7.4316939890710385,
      "grad_norm": 0.6960242986679077,
      "learning_rate": 0.00012846994535519127,
      "loss": 0.3909,
      "step": 6800
    },
    {
      "epoch": 7.4863387978142075,
      "grad_norm": 0.8247169852256775,
      "learning_rate": 0.0001257377049180328,
      "loss": 0.4111,
      "step": 6850
    },
    {
      "epoch": 7.540983606557377,
      "grad_norm": 0.5891773700714111,
      "learning_rate": 0.00012300546448087431,
      "loss": 0.4645,
      "step": 6900
    },
    {
      "epoch": 7.595628415300546,
      "grad_norm": 0.6889060139656067,
      "learning_rate": 0.00012027322404371585,
      "loss": 0.3781,
      "step": 6950
    },
    {
      "epoch": 7.6502732240437155,
      "grad_norm": 0.7287388443946838,
      "learning_rate": 0.00011754098360655737,
      "loss": 0.4184,
      "step": 7000
    },
    {
      "epoch": 7.704918032786885,
      "grad_norm": 0.5292376279830933,
      "learning_rate": 0.00011480874316939891,
      "loss": 0.4042,
      "step": 7050
    },
    {
      "epoch": 7.759562841530054,
      "grad_norm": 1.0296603441238403,
      "learning_rate": 0.00011207650273224044,
      "loss": 0.4092,
      "step": 7100
    },
    {
      "epoch": 7.814207650273224,
      "grad_norm": 0.7451539039611816,
      "learning_rate": 0.00010934426229508198,
      "loss": 0.4379,
      "step": 7150
    },
    {
      "epoch": 7.868852459016393,
      "grad_norm": 0.6021469831466675,
      "learning_rate": 0.0001066120218579235,
      "loss": 0.4015,
      "step": 7200
    },
    {
      "epoch": 7.923497267759563,
      "grad_norm": 0.6649101376533508,
      "learning_rate": 0.00010387978142076502,
      "loss": 0.4119,
      "step": 7250
    },
    {
      "epoch": 7.978142076502732,
      "grad_norm": 0.8819006681442261,
      "learning_rate": 0.00010114754098360656,
      "loss": 0.4503,
      "step": 7300
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4996373653411865,
      "eval_runtime": 38.3302,
      "eval_samples_per_second": 21.236,
      "eval_steps_per_second": 2.661,
      "step": 7320
    },
    {
      "epoch": 8.032786885245901,
      "grad_norm": 0.974883496761322,
      "learning_rate": 9.841530054644809e-05,
      "loss": 0.399,
      "step": 7350
    },
    {
      "epoch": 8.087431693989071,
      "grad_norm": 0.4739116132259369,
      "learning_rate": 9.568306010928961e-05,
      "loss": 0.4358,
      "step": 7400
    },
    {
      "epoch": 8.142076502732241,
      "grad_norm": 0.618143618106842,
      "learning_rate": 9.295081967213115e-05,
      "loss": 0.4221,
      "step": 7450
    },
    {
      "epoch": 8.19672131147541,
      "grad_norm": 0.9425492286682129,
      "learning_rate": 9.021857923497267e-05,
      "loss": 0.4056,
      "step": 7500
    },
    {
      "epoch": 8.251366120218579,
      "grad_norm": 0.8939974308013916,
      "learning_rate": 8.748633879781422e-05,
      "loss": 0.3748,
      "step": 7550
    },
    {
      "epoch": 8.306010928961749,
      "grad_norm": 0.7813948392868042,
      "learning_rate": 8.475409836065574e-05,
      "loss": 0.4347,
      "step": 7600
    },
    {
      "epoch": 8.360655737704919,
      "grad_norm": 0.6311246752738953,
      "learning_rate": 8.202185792349726e-05,
      "loss": 0.3925,
      "step": 7650
    },
    {
      "epoch": 8.415300546448087,
      "grad_norm": 0.8458578586578369,
      "learning_rate": 7.92896174863388e-05,
      "loss": 0.402,
      "step": 7700
    },
    {
      "epoch": 8.469945355191257,
      "grad_norm": 1.0656789541244507,
      "learning_rate": 7.655737704918032e-05,
      "loss": 0.3874,
      "step": 7750
    },
    {
      "epoch": 8.524590163934427,
      "grad_norm": 0.8404769897460938,
      "learning_rate": 7.382513661202187e-05,
      "loss": 0.3548,
      "step": 7800
    },
    {
      "epoch": 8.579234972677595,
      "grad_norm": 0.768875777721405,
      "learning_rate": 7.10928961748634e-05,
      "loss": 0.3789,
      "step": 7850
    },
    {
      "epoch": 8.633879781420765,
      "grad_norm": 0.7351892590522766,
      "learning_rate": 6.836065573770492e-05,
      "loss": 0.4191,
      "step": 7900
    },
    {
      "epoch": 8.688524590163935,
      "grad_norm": 0.36720535159111023,
      "learning_rate": 6.562841530054645e-05,
      "loss": 0.3632,
      "step": 7950
    },
    {
      "epoch": 8.743169398907105,
      "grad_norm": 0.6152942180633545,
      "learning_rate": 6.289617486338797e-05,
      "loss": 0.4119,
      "step": 8000
    },
    {
      "epoch": 8.797814207650273,
      "grad_norm": 0.857695996761322,
      "learning_rate": 6.016393442622951e-05,
      "loss": 0.3946,
      "step": 8050
    },
    {
      "epoch": 8.852459016393443,
      "grad_norm": 0.8226462006568909,
      "learning_rate": 5.7431693989071044e-05,
      "loss": 0.3918,
      "step": 8100
    },
    {
      "epoch": 8.907103825136613,
      "grad_norm": 0.85596764087677,
      "learning_rate": 5.4699453551912565e-05,
      "loss": 0.4091,
      "step": 8150
    },
    {
      "epoch": 8.96174863387978,
      "grad_norm": 1.0148135423660278,
      "learning_rate": 5.19672131147541e-05,
      "loss": 0.3967,
      "step": 8200
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.49434006214141846,
      "eval_runtime": 43.7664,
      "eval_samples_per_second": 18.599,
      "eval_steps_per_second": 2.331,
      "step": 8235
    },
    {
      "epoch": 9.01639344262295,
      "grad_norm": 0.7951825857162476,
      "learning_rate": 4.923497267759563e-05,
      "loss": 0.3775,
      "step": 8250
    },
    {
      "epoch": 9.07103825136612,
      "grad_norm": 0.8234446048736572,
      "learning_rate": 4.6502732240437165e-05,
      "loss": 0.3479,
      "step": 8300
    },
    {
      "epoch": 9.12568306010929,
      "grad_norm": 0.7355231642723083,
      "learning_rate": 4.377049180327869e-05,
      "loss": 0.3862,
      "step": 8350
    },
    {
      "epoch": 9.180327868852459,
      "grad_norm": 0.8501237630844116,
      "learning_rate": 4.1038251366120216e-05,
      "loss": 0.3809,
      "step": 8400
    },
    {
      "epoch": 9.234972677595628,
      "grad_norm": 0.5716586112976074,
      "learning_rate": 3.830601092896175e-05,
      "loss": 0.3662,
      "step": 8450
    },
    {
      "epoch": 9.289617486338798,
      "grad_norm": 0.8132263422012329,
      "learning_rate": 3.557377049180328e-05,
      "loss": 0.4051,
      "step": 8500
    },
    {
      "epoch": 9.344262295081966,
      "grad_norm": 0.8344842791557312,
      "learning_rate": 3.284153005464481e-05,
      "loss": 0.3836,
      "step": 8550
    },
    {
      "epoch": 9.398907103825136,
      "grad_norm": 1.00874924659729,
      "learning_rate": 3.0109289617486337e-05,
      "loss": 0.4073,
      "step": 8600
    },
    {
      "epoch": 9.453551912568306,
      "grad_norm": 0.8442609310150146,
      "learning_rate": 2.737704918032787e-05,
      "loss": 0.3672,
      "step": 8650
    },
    {
      "epoch": 9.508196721311476,
      "grad_norm": 0.647296667098999,
      "learning_rate": 2.4644808743169398e-05,
      "loss": 0.3479,
      "step": 8700
    },
    {
      "epoch": 9.562841530054644,
      "grad_norm": 0.8498296141624451,
      "learning_rate": 2.191256830601093e-05,
      "loss": 0.3899,
      "step": 8750
    },
    {
      "epoch": 9.617486338797814,
      "grad_norm": 0.848953127861023,
      "learning_rate": 1.918032786885246e-05,
      "loss": 0.3702,
      "step": 8800
    },
    {
      "epoch": 9.672131147540984,
      "grad_norm": 0.6039347648620605,
      "learning_rate": 1.644808743169399e-05,
      "loss": 0.4322,
      "step": 8850
    },
    {
      "epoch": 9.726775956284152,
      "grad_norm": 0.762699544429779,
      "learning_rate": 1.3715846994535518e-05,
      "loss": 0.4086,
      "step": 8900
    },
    {
      "epoch": 9.781420765027322,
      "grad_norm": 1.0003371238708496,
      "learning_rate": 1.0983606557377048e-05,
      "loss": 0.37,
      "step": 8950
    },
    {
      "epoch": 9.836065573770492,
      "grad_norm": 0.623757541179657,
      "learning_rate": 8.251366120218579e-06,
      "loss": 0.3427,
      "step": 9000
    }
  ],
  "logging_steps": 50,
  "max_steps": 9150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3384116338688e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}