{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998204667863555,
  "eval_steps": 500,
  "global_step": 2505,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011968880909634948,
      "grad_norm": 26.500904248426494,
      "learning_rate": 5e-06,
      "loss": 1.0918,
      "step": 10
    },
    {
      "epoch": 0.023937761819269897,
      "grad_norm": 2.050351070135692,
      "learning_rate": 5e-06,
      "loss": 0.9643,
      "step": 20
    },
    {
      "epoch": 0.03590664272890485,
      "grad_norm": 1.5804902490894754,
      "learning_rate": 5e-06,
      "loss": 0.8994,
      "step": 30
    },
    {
      "epoch": 0.047875523638539794,
      "grad_norm": 1.3296407219003534,
      "learning_rate": 5e-06,
      "loss": 0.8624,
      "step": 40
    },
    {
      "epoch": 0.059844404548174746,
      "grad_norm": 1.2478037629085867,
      "learning_rate": 5e-06,
      "loss": 0.8386,
      "step": 50
    },
    {
      "epoch": 0.0718132854578097,
      "grad_norm": 1.5244344651863047,
      "learning_rate": 5e-06,
      "loss": 0.8163,
      "step": 60
    },
    {
      "epoch": 0.08378216636744465,
      "grad_norm": 1.4588200289873845,
      "learning_rate": 5e-06,
      "loss": 0.8072,
      "step": 70
    },
    {
      "epoch": 0.09575104727707959,
      "grad_norm": 1.0982027372762801,
      "learning_rate": 5e-06,
      "loss": 0.793,
      "step": 80
    },
    {
      "epoch": 0.10771992818671454,
      "grad_norm": 0.8816222607041236,
      "learning_rate": 5e-06,
      "loss": 0.7803,
      "step": 90
    },
    {
      "epoch": 0.11968880909634949,
      "grad_norm": 0.756880071100982,
      "learning_rate": 5e-06,
      "loss": 0.7751,
      "step": 100
    },
    {
      "epoch": 0.13165769000598443,
      "grad_norm": 1.055426572397012,
      "learning_rate": 5e-06,
      "loss": 0.7709,
      "step": 110
    },
    {
      "epoch": 0.1436265709156194,
      "grad_norm": 0.6572909169517717,
      "learning_rate": 5e-06,
      "loss": 0.7696,
      "step": 120
    },
    {
      "epoch": 0.15559545182525433,
      "grad_norm": 0.9133460033726442,
      "learning_rate": 5e-06,
      "loss": 0.7674,
      "step": 130
    },
    {
      "epoch": 0.1675643327348893,
      "grad_norm": 1.3148870123285326,
      "learning_rate": 5e-06,
      "loss": 0.7689,
      "step": 140
    },
    {
      "epoch": 0.17953321364452424,
      "grad_norm": 1.2147160089970106,
      "learning_rate": 5e-06,
      "loss": 0.7629,
      "step": 150
    },
    {
      "epoch": 0.19150209455415917,
      "grad_norm": 1.0090571814802656,
      "learning_rate": 5e-06,
      "loss": 0.7539,
      "step": 160
    },
    {
      "epoch": 0.20347097546379414,
      "grad_norm": 0.6786427727932486,
      "learning_rate": 5e-06,
      "loss": 0.7581,
      "step": 170
    },
    {
      "epoch": 0.21543985637342908,
      "grad_norm": 0.6292227320745046,
      "learning_rate": 5e-06,
      "loss": 0.7586,
      "step": 180
    },
    {
      "epoch": 0.22740873728306404,
      "grad_norm": 0.7713241812517966,
      "learning_rate": 5e-06,
      "loss": 0.7502,
      "step": 190
    },
    {
      "epoch": 0.23937761819269898,
      "grad_norm": 0.7205115952689147,
      "learning_rate": 5e-06,
      "loss": 0.7547,
      "step": 200
    },
    {
      "epoch": 0.2513464991023339,
      "grad_norm": 0.6517310095502118,
      "learning_rate": 5e-06,
      "loss": 0.7483,
      "step": 210
    },
    {
      "epoch": 0.26331538001196886,
      "grad_norm": 0.9369409311428439,
      "learning_rate": 5e-06,
      "loss": 0.746,
      "step": 220
    },
    {
      "epoch": 0.27528426092160385,
      "grad_norm": 0.6858210048955122,
      "learning_rate": 5e-06,
      "loss": 0.7441,
      "step": 230
    },
    {
      "epoch": 0.2872531418312388,
      "grad_norm": 0.7081095639219623,
      "learning_rate": 5e-06,
      "loss": 0.7445,
      "step": 240
    },
    {
      "epoch": 0.2992220227408737,
      "grad_norm": 0.8305808826463342,
      "learning_rate": 5e-06,
      "loss": 0.7422,
      "step": 250
    },
    {
      "epoch": 0.31119090365050867,
      "grad_norm": 0.641119207471586,
      "learning_rate": 5e-06,
      "loss": 0.7436,
      "step": 260
    },
    {
      "epoch": 0.3231597845601436,
      "grad_norm": 0.6092200095597452,
      "learning_rate": 5e-06,
      "loss": 0.742,
      "step": 270
    },
    {
      "epoch": 0.3351286654697786,
      "grad_norm": 0.7329815044595642,
      "learning_rate": 5e-06,
      "loss": 0.7446,
      "step": 280
    },
    {
      "epoch": 0.34709754637941354,
      "grad_norm": 0.837913540141014,
      "learning_rate": 5e-06,
      "loss": 0.7405,
      "step": 290
    },
    {
      "epoch": 0.3590664272890485,
      "grad_norm": 0.7796180622052511,
      "learning_rate": 5e-06,
      "loss": 0.7361,
      "step": 300
    },
    {
      "epoch": 0.3710353081986834,
      "grad_norm": 0.6206194415830822,
      "learning_rate": 5e-06,
      "loss": 0.7385,
      "step": 310
    },
    {
      "epoch": 0.38300418910831835,
      "grad_norm": 0.807676253948667,
      "learning_rate": 5e-06,
      "loss": 0.7354,
      "step": 320
    },
    {
      "epoch": 0.39497307001795334,
      "grad_norm": 0.6508042723489613,
      "learning_rate": 5e-06,
      "loss": 0.7342,
      "step": 330
    },
    {
      "epoch": 0.4069419509275883,
      "grad_norm": 1.127544531436106,
      "learning_rate": 5e-06,
      "loss": 0.7393,
      "step": 340
    },
    {
      "epoch": 0.4189108318372232,
      "grad_norm": 0.7264448945571097,
      "learning_rate": 5e-06,
      "loss": 0.7335,
      "step": 350
    },
    {
      "epoch": 0.43087971274685816,
      "grad_norm": 0.7993530026874973,
      "learning_rate": 5e-06,
      "loss": 0.7367,
      "step": 360
    },
    {
      "epoch": 0.4428485936564931,
      "grad_norm": 0.9608462791926143,
      "learning_rate": 5e-06,
      "loss": 0.7402,
      "step": 370
    },
    {
      "epoch": 0.4548174745661281,
      "grad_norm": 0.7292313869577105,
      "learning_rate": 5e-06,
      "loss": 0.7346,
      "step": 380
    },
    {
      "epoch": 0.466786355475763,
      "grad_norm": 1.047700429826994,
      "learning_rate": 5e-06,
      "loss": 0.7306,
      "step": 390
    },
    {
      "epoch": 0.47875523638539796,
      "grad_norm": 0.7162891952015032,
      "learning_rate": 5e-06,
      "loss": 0.7298,
      "step": 400
    },
    {
      "epoch": 0.4907241172950329,
      "grad_norm": 0.8782360080252781,
      "learning_rate": 5e-06,
      "loss": 0.7313,
      "step": 410
    },
    {
      "epoch": 0.5026929982046678,
      "grad_norm": 0.6666343216734302,
      "learning_rate": 5e-06,
      "loss": 0.7314,
      "step": 420
    },
    {
      "epoch": 0.5146618791143028,
      "grad_norm": 0.8384501076164775,
      "learning_rate": 5e-06,
      "loss": 0.7355,
      "step": 430
    },
    {
      "epoch": 0.5266307600239377,
      "grad_norm": 0.6150369560469455,
      "learning_rate": 5e-06,
      "loss": 0.7298,
      "step": 440
    },
    {
      "epoch": 0.5385996409335727,
      "grad_norm": 0.6124319945799728,
      "learning_rate": 5e-06,
      "loss": 0.7292,
      "step": 450
    },
    {
      "epoch": 0.5505685218432077,
      "grad_norm": 0.6189565248445754,
      "learning_rate": 5e-06,
      "loss": 0.7263,
      "step": 460
    },
    {
      "epoch": 0.5625374027528426,
      "grad_norm": 0.6421927415859262,
      "learning_rate": 5e-06,
      "loss": 0.7299,
      "step": 470
    },
    {
      "epoch": 0.5745062836624776,
      "grad_norm": 0.7163639686041191,
      "learning_rate": 5e-06,
      "loss": 0.7288,
      "step": 480
    },
    {
      "epoch": 0.5864751645721125,
      "grad_norm": 0.7901780871296374,
      "learning_rate": 5e-06,
      "loss": 0.7233,
      "step": 490
    },
    {
      "epoch": 0.5984440454817475,
      "grad_norm": 0.6075768057357427,
      "learning_rate": 5e-06,
      "loss": 0.7285,
      "step": 500
    },
    {
      "epoch": 0.6104129263913824,
      "grad_norm": 0.7432513250953633,
      "learning_rate": 5e-06,
      "loss": 0.7255,
      "step": 510
    },
    {
      "epoch": 0.6223818073010173,
      "grad_norm": 0.6882126061650138,
      "learning_rate": 5e-06,
      "loss": 0.7228,
      "step": 520
    },
    {
      "epoch": 0.6343506882106523,
      "grad_norm": 0.6444331452668448,
      "learning_rate": 5e-06,
      "loss": 0.7208,
      "step": 530
    },
    {
      "epoch": 0.6463195691202872,
      "grad_norm": 0.6113206044775283,
      "learning_rate": 5e-06,
      "loss": 0.725,
      "step": 540
    },
    {
      "epoch": 0.6582884500299222,
      "grad_norm": 0.6186132585168679,
      "learning_rate": 5e-06,
      "loss": 0.7237,
      "step": 550
    },
    {
      "epoch": 0.6702573309395572,
      "grad_norm": 0.8008035313826654,
      "learning_rate": 5e-06,
      "loss": 0.7214,
      "step": 560
    },
    {
      "epoch": 0.6822262118491921,
      "grad_norm": 0.7712979616981473,
      "learning_rate": 5e-06,
      "loss": 0.7201,
      "step": 570
    },
    {
      "epoch": 0.6941950927588271,
      "grad_norm": 0.771784813198081,
      "learning_rate": 5e-06,
      "loss": 0.712,
      "step": 580
    },
    {
      "epoch": 0.706163973668462,
      "grad_norm": 0.7490151127607958,
      "learning_rate": 5e-06,
      "loss": 0.7186,
      "step": 590
    },
    {
      "epoch": 0.718132854578097,
      "grad_norm": 0.7472145149920045,
      "learning_rate": 5e-06,
      "loss": 0.7215,
      "step": 600
    },
    {
      "epoch": 0.7301017354877319,
      "grad_norm": 0.669766192904856,
      "learning_rate": 5e-06,
      "loss": 0.7203,
      "step": 610
    },
    {
      "epoch": 0.7420706163973668,
      "grad_norm": 0.7074773906209623,
      "learning_rate": 5e-06,
      "loss": 0.7206,
      "step": 620
    },
    {
      "epoch": 0.7540394973070018,
      "grad_norm": 0.6359019991344024,
      "learning_rate": 5e-06,
      "loss": 0.7173,
      "step": 630
    },
    {
      "epoch": 0.7660083782166367,
      "grad_norm": 0.7248185956514057,
      "learning_rate": 5e-06,
      "loss": 0.715,
      "step": 640
    },
    {
      "epoch": 0.7779772591262717,
      "grad_norm": 0.5916566575834068,
      "learning_rate": 5e-06,
      "loss": 0.7153,
      "step": 650
    },
    {
      "epoch": 0.7899461400359067,
      "grad_norm": 0.9435696828561574,
      "learning_rate": 5e-06,
      "loss": 0.7132,
      "step": 660
    },
    {
      "epoch": 0.8019150209455416,
      "grad_norm": 1.043671294723693,
      "learning_rate": 5e-06,
      "loss": 0.7208,
      "step": 670
    },
    {
      "epoch": 0.8138839018551766,
      "grad_norm": 0.6012906477211288,
      "learning_rate": 5e-06,
      "loss": 0.7169,
      "step": 680
    },
    {
      "epoch": 0.8258527827648114,
      "grad_norm": 0.6760825364942948,
      "learning_rate": 5e-06,
      "loss": 0.7099,
      "step": 690
    },
    {
      "epoch": 0.8378216636744464,
      "grad_norm": 0.6518956331777058,
      "learning_rate": 5e-06,
      "loss": 0.7148,
      "step": 700
    },
    {
      "epoch": 0.8497905445840814,
      "grad_norm": 0.7071013655191297,
      "learning_rate": 5e-06,
      "loss": 0.714,
      "step": 710
    },
    {
      "epoch": 0.8617594254937163,
      "grad_norm": 0.6247282830782587,
      "learning_rate": 5e-06,
      "loss": 0.7147,
      "step": 720
    },
    {
      "epoch": 0.8737283064033513,
      "grad_norm": 0.6919222170502861,
      "learning_rate": 5e-06,
      "loss": 0.7128,
      "step": 730
    },
    {
      "epoch": 0.8856971873129862,
      "grad_norm": 0.6537145672155599,
      "learning_rate": 5e-06,
      "loss": 0.7162,
      "step": 740
    },
    {
      "epoch": 0.8976660682226212,
      "grad_norm": 0.68375157978155,
      "learning_rate": 5e-06,
      "loss": 0.7147,
      "step": 750
    },
    {
      "epoch": 0.9096349491322562,
      "grad_norm": 0.6647354124963691,
      "learning_rate": 5e-06,
      "loss": 0.7126,
      "step": 760
    },
    {
      "epoch": 0.9216038300418911,
      "grad_norm": 0.5977043002608496,
      "learning_rate": 5e-06,
      "loss": 0.7149,
      "step": 770
    },
    {
      "epoch": 0.933572710951526,
      "grad_norm": 0.5976562834062398,
      "learning_rate": 5e-06,
      "loss": 0.715,
      "step": 780
    },
    {
      "epoch": 0.9455415918611609,
      "grad_norm": 0.6047572754156897,
      "learning_rate": 5e-06,
      "loss": 0.7098,
      "step": 790
    },
    {
      "epoch": 0.9575104727707959,
      "grad_norm": 0.7904694447754029,
      "learning_rate": 5e-06,
      "loss": 0.7144,
      "step": 800
    },
    {
      "epoch": 0.9694793536804309,
      "grad_norm": 0.5807742093881076,
      "learning_rate": 5e-06,
      "loss": 0.7101,
      "step": 810
    },
    {
      "epoch": 0.9814482345900658,
      "grad_norm": 0.7039850599689602,
      "learning_rate": 5e-06,
      "loss": 0.7148,
      "step": 820
    },
    {
      "epoch": 0.9934171154997008,
      "grad_norm": 0.6174865022883058,
      "learning_rate": 5e-06,
      "loss": 0.7062,
      "step": 830
    },
    {
      "epoch": 0.9994015559545183,
      "eval_loss": 0.7114372849464417,
      "eval_runtime": 147.5298,
      "eval_samples_per_second": 152.606,
      "eval_steps_per_second": 0.596,
      "step": 835
    },
    {
      "epoch": 1.0053859964093357,
      "grad_norm": 0.8962593548100513,
      "learning_rate": 5e-06,
      "loss": 0.728,
      "step": 840
    },
    {
      "epoch": 1.0173548773189707,
      "grad_norm": 0.7772228818285795,
      "learning_rate": 5e-06,
      "loss": 0.6687,
      "step": 850
    },
    {
      "epoch": 1.0293237582286057,
      "grad_norm": 0.7166716512779154,
      "learning_rate": 5e-06,
      "loss": 0.6638,
      "step": 860
    },
    {
      "epoch": 1.0412926391382407,
      "grad_norm": 0.6621044482167691,
      "learning_rate": 5e-06,
      "loss": 0.6701,
      "step": 870
    },
    {
      "epoch": 1.0532615200478754,
      "grad_norm": 0.6053908490954104,
      "learning_rate": 5e-06,
      "loss": 0.6647,
      "step": 880
    },
    {
      "epoch": 1.0652304009575104,
      "grad_norm": 0.6887973939100516,
      "learning_rate": 5e-06,
      "loss": 0.6638,
      "step": 890
    },
    {
      "epoch": 1.0771992818671454,
      "grad_norm": 0.702826603937809,
      "learning_rate": 5e-06,
      "loss": 0.6683,
      "step": 900
    },
    {
      "epoch": 1.0891681627767804,
      "grad_norm": 0.7995617189411401,
      "learning_rate": 5e-06,
      "loss": 0.6661,
      "step": 910
    },
    {
      "epoch": 1.1011370436864154,
      "grad_norm": 0.6519665847110662,
      "learning_rate": 5e-06,
      "loss": 0.6656,
      "step": 920
    },
    {
      "epoch": 1.1131059245960502,
      "grad_norm": 0.6273625611261167,
      "learning_rate": 5e-06,
      "loss": 0.6642,
      "step": 930
    },
    {
      "epoch": 1.1250748055056852,
      "grad_norm": 0.7185612601640737,
      "learning_rate": 5e-06,
      "loss": 0.6655,
      "step": 940
    },
    {
      "epoch": 1.1370436864153202,
      "grad_norm": 0.6572849791275432,
      "learning_rate": 5e-06,
      "loss": 0.6694,
      "step": 950
    },
    {
      "epoch": 1.1490125673249552,
      "grad_norm": 0.6670384809386003,
      "learning_rate": 5e-06,
      "loss": 0.6702,
      "step": 960
    },
    {
      "epoch": 1.1609814482345902,
      "grad_norm": 0.6742291672674092,
      "learning_rate": 5e-06,
      "loss": 0.6694,
      "step": 970
    },
    {
      "epoch": 1.172950329144225,
      "grad_norm": 0.7341117675868765,
      "learning_rate": 5e-06,
      "loss": 0.6661,
      "step": 980
    },
    {
      "epoch": 1.18491921005386,
      "grad_norm": 0.647754764205428,
      "learning_rate": 5e-06,
      "loss": 0.6626,
      "step": 990
    },
    {
      "epoch": 1.196888090963495,
      "grad_norm": 0.6349210444739344,
      "learning_rate": 5e-06,
      "loss": 0.673,
      "step": 1000
    },
    {
      "epoch": 1.20885697187313,
      "grad_norm": 0.7055438799763827,
      "learning_rate": 5e-06,
      "loss": 0.6678,
      "step": 1010
    },
    {
      "epoch": 1.220825852782765,
      "grad_norm": 0.5932598557482555,
      "learning_rate": 5e-06,
      "loss": 0.6636,
      "step": 1020
    },
    {
      "epoch": 1.2327947336923997,
      "grad_norm": 0.5945872005782129,
      "learning_rate": 5e-06,
      "loss": 0.6734,
      "step": 1030
    },
    {
      "epoch": 1.2447636146020347,
      "grad_norm": 0.6634460553155971,
      "learning_rate": 5e-06,
      "loss": 0.6686,
      "step": 1040
    },
    {
      "epoch": 1.2567324955116697,
      "grad_norm": 0.6119696190494924,
      "learning_rate": 5e-06,
      "loss": 0.6632,
      "step": 1050
    },
    {
      "epoch": 1.2687013764213046,
      "grad_norm": 0.5680998374934575,
      "learning_rate": 5e-06,
      "loss": 0.6639,
      "step": 1060
    },
    {
      "epoch": 1.2806702573309394,
      "grad_norm": 0.7632716086431686,
      "learning_rate": 5e-06,
      "loss": 0.6707,
      "step": 1070
    },
    {
      "epoch": 1.2926391382405744,
      "grad_norm": 0.5773596573256996,
      "learning_rate": 5e-06,
      "loss": 0.667,
      "step": 1080
    },
    {
      "epoch": 1.3046080191502094,
      "grad_norm": 0.7249658131418688,
      "learning_rate": 5e-06,
      "loss": 0.6627,
      "step": 1090
    },
    {
      "epoch": 1.3165769000598444,
      "grad_norm": 0.6627381756172364,
      "learning_rate": 5e-06,
      "loss": 0.67,
      "step": 1100
    },
    {
      "epoch": 1.3285457809694794,
      "grad_norm": 0.5614593187441069,
      "learning_rate": 5e-06,
      "loss": 0.6647,
      "step": 1110
    },
    {
      "epoch": 1.3405146618791144,
      "grad_norm": 0.582853382816816,
      "learning_rate": 5e-06,
      "loss": 0.6669,
      "step": 1120
    },
    {
      "epoch": 1.3524835427887494,
      "grad_norm": 0.7100796913546954,
      "learning_rate": 5e-06,
      "loss": 0.6726,
      "step": 1130
    },
    {
      "epoch": 1.3644524236983842,
      "grad_norm": 0.6440445846779764,
      "learning_rate": 5e-06,
      "loss": 0.6645,
      "step": 1140
    },
    {
      "epoch": 1.3764213046080191,
      "grad_norm": 0.6414609210769443,
      "learning_rate": 5e-06,
      "loss": 0.6649,
      "step": 1150
    },
    {
      "epoch": 1.3883901855176541,
      "grad_norm": 0.6066442073205667,
      "learning_rate": 5e-06,
      "loss": 0.6671,
      "step": 1160
    },
    {
      "epoch": 1.400359066427289,
      "grad_norm": 0.5517122631957174,
      "learning_rate": 5e-06,
      "loss": 0.6676,
      "step": 1170
    },
    {
      "epoch": 1.412327947336924,
      "grad_norm": 0.6431261043778982,
      "learning_rate": 5e-06,
      "loss": 0.6639,
      "step": 1180
    },
    {
      "epoch": 1.424296828246559,
      "grad_norm": 0.7260721545398744,
      "learning_rate": 5e-06,
      "loss": 0.6701,
      "step": 1190
    },
    {
      "epoch": 1.436265709156194,
      "grad_norm": 0.7161457181189081,
      "learning_rate": 5e-06,
      "loss": 0.6559,
      "step": 1200
    },
    {
      "epoch": 1.4482345900658289,
      "grad_norm": 0.6352035083119371,
      "learning_rate": 5e-06,
      "loss": 0.6681,
      "step": 1210
    },
    {
      "epoch": 1.4602034709754639,
      "grad_norm": 0.7063524982241797,
      "learning_rate": 5e-06,
      "loss": 0.6654,
      "step": 1220
    },
    {
      "epoch": 1.4721723518850989,
      "grad_norm": 0.6879403956072693,
      "learning_rate": 5e-06,
      "loss": 0.6694,
      "step": 1230
    },
    {
      "epoch": 1.4841412327947336,
      "grad_norm": 0.6783332447999513,
      "learning_rate": 5e-06,
      "loss": 0.6666,
      "step": 1240
    },
    {
      "epoch": 1.4961101137043686,
      "grad_norm": 0.6478235600361606,
      "learning_rate": 5e-06,
      "loss": 0.6675,
      "step": 1250
    },
    {
      "epoch": 1.5080789946140036,
      "grad_norm": 0.5883450422091347,
      "learning_rate": 5e-06,
      "loss": 0.6645,
      "step": 1260
    },
    {
      "epoch": 1.5200478755236384,
      "grad_norm": 0.6660437650036387,
      "learning_rate": 5e-06,
      "loss": 0.6611,
      "step": 1270
    },
    {
      "epoch": 1.5320167564332734,
      "grad_norm": 0.5948419571007313,
      "learning_rate": 5e-06,
      "loss": 0.6661,
      "step": 1280
    },
    {
      "epoch": 1.5439856373429084,
      "grad_norm": 0.5853041784577795,
      "learning_rate": 5e-06,
      "loss": 0.6681,
      "step": 1290
    },
    {
      "epoch": 1.5559545182525434,
      "grad_norm": 0.7356480278739408,
      "learning_rate": 5e-06,
      "loss": 0.6678,
      "step": 1300
    },
    {
      "epoch": 1.5679233991621784,
      "grad_norm": 0.6949205522779035,
      "learning_rate": 5e-06,
      "loss": 0.6669,
      "step": 1310
    },
    {
      "epoch": 1.5798922800718134,
      "grad_norm": 0.6507079001414935,
      "learning_rate": 5e-06,
      "loss": 0.67,
      "step": 1320
    },
    {
      "epoch": 1.5918611609814484,
      "grad_norm": 0.6100230292150697,
      "learning_rate": 5e-06,
      "loss": 0.6653,
      "step": 1330
    },
    {
      "epoch": 1.6038300418910831,
      "grad_norm": 0.594443951679209,
      "learning_rate": 5e-06,
      "loss": 0.664,
      "step": 1340
    },
    {
      "epoch": 1.6157989228007181,
      "grad_norm": 0.6096985220862555,
      "learning_rate": 5e-06,
      "loss": 0.6647,
      "step": 1350
    },
    {
      "epoch": 1.6277678037103531,
      "grad_norm": 0.5760594804542581,
      "learning_rate": 5e-06,
      "loss": 0.6669,
      "step": 1360
    },
    {
      "epoch": 1.639736684619988,
      "grad_norm": 0.691475316154413,
      "learning_rate": 5e-06,
      "loss": 0.6659,
      "step": 1370
    },
    {
      "epoch": 1.6517055655296229,
      "grad_norm": 0.6527081133567483,
      "learning_rate": 5e-06,
      "loss": 0.6682,
      "step": 1380
    },
    {
      "epoch": 1.6636744464392579,
      "grad_norm": 0.620764034153086,
      "learning_rate": 5e-06,
      "loss": 0.6658,
      "step": 1390
    },
    {
      "epoch": 1.6756433273488929,
      "grad_norm": 0.5624863643686968,
      "learning_rate": 5e-06,
      "loss": 0.6629,
      "step": 1400
    },
    {
      "epoch": 1.6876122082585279,
      "grad_norm": 0.5866917073665039,
      "learning_rate": 5e-06,
      "loss": 0.662,
      "step": 1410
    },
    {
      "epoch": 1.6995810891681629,
      "grad_norm": 0.5725120938110386,
      "learning_rate": 5e-06,
      "loss": 0.6679,
      "step": 1420
    },
    {
      "epoch": 1.7115499700777979,
      "grad_norm": 0.6259302322367788,
      "learning_rate": 5e-06,
      "loss": 0.6681,
      "step": 1430
    },
    {
      "epoch": 1.7235188509874326,
      "grad_norm": 0.6855515829037336,
      "learning_rate": 5e-06,
      "loss": 0.6642,
      "step": 1440
    },
    {
      "epoch": 1.7354877318970676,
      "grad_norm": 0.586477759363614,
      "learning_rate": 5e-06,
      "loss": 0.6645,
      "step": 1450
    },
    {
      "epoch": 1.7474566128067026,
      "grad_norm": 0.7473190145452194,
      "learning_rate": 5e-06,
      "loss": 0.6657,
      "step": 1460
    },
    {
      "epoch": 1.7594254937163374,
      "grad_norm": 0.6856637572630547,
      "learning_rate": 5e-06,
      "loss": 0.6666,
      "step": 1470
    },
    {
      "epoch": 1.7713943746259724,
      "grad_norm": 0.6356257155539595,
      "learning_rate": 5e-06,
      "loss": 0.6632,
      "step": 1480
    },
    {
      "epoch": 1.7833632555356074,
      "grad_norm": 0.5780948416794784,
      "learning_rate": 5e-06,
      "loss": 0.6651,
      "step": 1490
    },
    {
      "epoch": 1.7953321364452424,
      "grad_norm": 0.6040049759436176,
      "learning_rate": 5e-06,
      "loss": 0.6687,
      "step": 1500
    },
    {
      "epoch": 1.8073010173548774,
      "grad_norm": 0.6116754536140059,
      "learning_rate": 5e-06,
      "loss": 0.6611,
      "step": 1510
    },
    {
      "epoch": 1.8192698982645124,
      "grad_norm": 0.6285933290005205,
      "learning_rate": 5e-06,
      "loss": 0.6685,
      "step": 1520
    },
    {
      "epoch": 1.8312387791741473,
      "grad_norm": 0.6069230952248156,
      "learning_rate": 5e-06,
      "loss": 0.6633,
      "step": 1530
    },
    {
      "epoch": 1.8432076600837821,
      "grad_norm": 0.5757493835177011,
      "learning_rate": 5e-06,
      "loss": 0.6595,
      "step": 1540
    },
    {
      "epoch": 1.8551765409934171,
      "grad_norm": 0.6335783323377564,
      "learning_rate": 5e-06,
      "loss": 0.6667,
      "step": 1550
    },
    {
      "epoch": 1.867145421903052,
      "grad_norm": 0.5676650286620293,
      "learning_rate": 5e-06,
      "loss": 0.662,
      "step": 1560
    },
    {
      "epoch": 1.8791143028126869,
      "grad_norm": 0.6035969519376175,
      "learning_rate": 5e-06,
      "loss": 0.6628,
      "step": 1570
    },
    {
      "epoch": 1.8910831837223219,
      "grad_norm": 0.5896338538296376,
      "learning_rate": 5e-06,
      "loss": 0.664,
      "step": 1580
    },
    {
      "epoch": 1.9030520646319569,
      "grad_norm": 0.6039070875737724,
      "learning_rate": 5e-06,
      "loss": 0.6658,
      "step": 1590
    },
    {
      "epoch": 1.9150209455415919,
      "grad_norm": 0.6567541390615723,
      "learning_rate": 5e-06,
      "loss": 0.6622,
      "step": 1600
    },
    {
      "epoch": 1.9269898264512269,
      "grad_norm": 0.6276807530688414,
      "learning_rate": 5e-06,
      "loss": 0.6604,
      "step": 1610
    },
    {
      "epoch": 1.9389587073608618,
      "grad_norm": 0.8336847726568148,
      "learning_rate": 5e-06,
      "loss": 0.6663,
      "step": 1620
    },
    {
      "epoch": 1.9509275882704968,
      "grad_norm": 0.7013759476620051,
      "learning_rate": 5e-06,
      "loss": 0.6664,
      "step": 1630
    },
    {
      "epoch": 1.9628964691801316,
      "grad_norm": 0.611731666630219,
      "learning_rate": 5e-06,
      "loss": 0.6663,
      "step": 1640
    },
    {
      "epoch": 1.9748653500897666,
      "grad_norm": 0.7128314798758998,
      "learning_rate": 5e-06,
      "loss": 0.6692,
      "step": 1650
    },
    {
      "epoch": 1.9868342309994016,
      "grad_norm": 0.6475123732829592,
      "learning_rate": 5e-06,
      "loss": 0.6627,
      "step": 1660
    },
    {
      "epoch": 1.9988031119090364,
      "grad_norm": 0.6022136617663713,
      "learning_rate": 5e-06,
      "loss": 0.6629,
      "step": 1670
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7005711197853088,
      "eval_runtime": 146.1272,
      "eval_samples_per_second": 154.071,
      "eval_steps_per_second": 0.602,
      "step": 1671
    },
    {
      "epoch": 2.0107719928186714,
      "grad_norm": 0.7068198157977486,
      "learning_rate": 5e-06,
      "loss": 0.6508,
      "step": 1680
    },
    {
      "epoch": 2.0227408737283064,
      "grad_norm": 0.7453932940551323,
      "learning_rate": 5e-06,
      "loss": 0.6156,
      "step": 1690
    },
    {
      "epoch": 2.0347097546379413,
      "grad_norm": 0.8134275271355035,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 1700
    },
    {
      "epoch": 2.0466786355475763,
      "grad_norm": 0.7119278959971719,
      "learning_rate": 5e-06,
      "loss": 0.6121,
      "step": 1710
    },
    {
      "epoch": 2.0586475164572113,
      "grad_norm": 0.581844000106152,
      "learning_rate": 5e-06,
      "loss": 0.614,
      "step": 1720
    },
    {
      "epoch": 2.0706163973668463,
      "grad_norm": 0.6161063490938795,
      "learning_rate": 5e-06,
      "loss": 0.6179,
      "step": 1730
    },
    {
      "epoch": 2.0825852782764813,
      "grad_norm": 0.6987854084656979,
      "learning_rate": 5e-06,
      "loss": 0.6166,
      "step": 1740
    },
    {
      "epoch": 2.0945541591861163,
      "grad_norm": 0.6139695159601696,
      "learning_rate": 5e-06,
      "loss": 0.6181,
      "step": 1750
    },
    {
      "epoch": 2.106523040095751,
      "grad_norm": 0.6608056746575605,
      "learning_rate": 5e-06,
      "loss": 0.6169,
      "step": 1760
    },
    {
      "epoch": 2.118491921005386,
      "grad_norm": 0.8330792159736297,
      "learning_rate": 5e-06,
      "loss": 0.621,
      "step": 1770
    },
    {
      "epoch": 2.130460801915021,
      "grad_norm": 0.6496515220438018,
      "learning_rate": 5e-06,
      "loss": 0.6168,
      "step": 1780
    },
    {
      "epoch": 2.142429682824656,
      "grad_norm": 0.5764478857585879,
      "learning_rate": 5e-06,
      "loss": 0.6172,
      "step": 1790
    },
    {
      "epoch": 2.154398563734291,
      "grad_norm": 0.5983155038303072,
      "learning_rate": 5e-06,
      "loss": 0.6165,
      "step": 1800
    },
    {
      "epoch": 2.166367444643926,
      "grad_norm": 0.6670875041460964,
      "learning_rate": 5e-06,
      "loss": 0.6154,
      "step": 1810
    },
    {
      "epoch": 2.178336325553561,
      "grad_norm": 0.5905406904657257,
      "learning_rate": 5e-06,
      "loss": 0.6136,
      "step": 1820
    },
    {
      "epoch": 2.190305206463196,
      "grad_norm": 0.7480577496080604,
      "learning_rate": 5e-06,
      "loss": 0.6174,
      "step": 1830
    },
    {
      "epoch": 2.202274087372831,
      "grad_norm": 0.6481682954787796,
      "learning_rate": 5e-06,
      "loss": 0.6193,
      "step": 1840
    },
    {
      "epoch": 2.2142429682824654,
      "grad_norm": 0.697692521344505,
      "learning_rate": 5e-06,
      "loss": 0.6151,
      "step": 1850
    },
    {
      "epoch": 2.2262118491921004,
      "grad_norm": 0.6518002225384566,
      "learning_rate": 5e-06,
      "loss": 0.62,
      "step": 1860
    },
    {
      "epoch": 2.2381807301017353,
      "grad_norm": 0.7977413337144527,
      "learning_rate": 5e-06,
      "loss": 0.6174,
      "step": 1870
    },
    {
      "epoch": 2.2501496110113703,
      "grad_norm": 0.6920554891456565,
      "learning_rate": 5e-06,
      "loss": 0.6206,
      "step": 1880
    },
    {
      "epoch": 2.2621184919210053,
      "grad_norm": 1.0045237891952645,
      "learning_rate": 5e-06,
      "loss": 0.6174,
      "step": 1890
    },
    {
      "epoch": 2.2740873728306403,
      "grad_norm": 0.7405972846803555,
      "learning_rate": 5e-06,
      "loss": 0.6218,
      "step": 1900
    },
    {
      "epoch": 2.2860562537402753,
      "grad_norm": 0.7565616201062902,
      "learning_rate": 5e-06,
      "loss": 0.6212,
      "step": 1910
    },
    {
      "epoch": 2.2980251346499103,
      "grad_norm": 0.6602100152398376,
      "learning_rate": 5e-06,
      "loss": 0.6165,
      "step": 1920
    },
    {
      "epoch": 2.3099940155595453,
      "grad_norm": 0.6690244571651464,
      "learning_rate": 5e-06,
      "loss": 0.6213,
      "step": 1930
    },
    {
      "epoch": 2.3219628964691803,
      "grad_norm": 0.7205634813241224,
      "learning_rate": 5e-06,
      "loss": 0.6199,
      "step": 1940
    },
    {
      "epoch": 2.3339317773788153,
      "grad_norm": 0.6533808767235285,
      "learning_rate": 5e-06,
      "loss": 0.6197,
      "step": 1950
    },
    {
      "epoch": 2.34590065828845,
      "grad_norm": 0.6671459242816263,
      "learning_rate": 5e-06,
      "loss": 0.6248,
      "step": 1960
    },
    {
      "epoch": 2.357869539198085,
      "grad_norm": 0.5765039507445094,
      "learning_rate": 5e-06,
      "loss": 0.6198,
      "step": 1970
    },
    {
      "epoch": 2.36983842010772,
      "grad_norm": 0.6003833286471706,
      "learning_rate": 5e-06,
      "loss": 0.6211,
      "step": 1980
    },
    {
      "epoch": 2.381807301017355,
      "grad_norm": 0.6310887330444114,
      "learning_rate": 5e-06,
      "loss": 0.6181,
      "step": 1990
    },
    {
      "epoch": 2.39377618192699,
      "grad_norm": 0.6533436296134522,
      "learning_rate": 5e-06,
      "loss": 0.6223,
      "step": 2000
    },
    {
      "epoch": 2.405745062836625,
      "grad_norm": 0.7613938683728527,
      "learning_rate": 5e-06,
      "loss": 0.6209,
      "step": 2010
    },
    {
      "epoch": 2.41771394374626,
      "grad_norm": 0.7227768963538012,
      "learning_rate": 5e-06,
      "loss": 0.6203,
      "step": 2020
    },
    {
      "epoch": 2.429682824655895,
      "grad_norm": 0.8304498753841795,
      "learning_rate": 5e-06,
      "loss": 0.6154,
      "step": 2030
    },
    {
      "epoch": 2.44165170556553,
      "grad_norm": 0.7574321335984159,
      "learning_rate": 5e-06,
      "loss": 0.6221,
      "step": 2040
    },
    {
      "epoch": 2.4536205864751643,
      "grad_norm": 0.6154411257768034,
      "learning_rate": 5e-06,
      "loss": 0.6213,
      "step": 2050
    },
    {
      "epoch": 2.4655894673847993,
      "grad_norm": 0.6619336134055549,
      "learning_rate": 5e-06,
      "loss": 0.6229,
      "step": 2060
    },
    {
      "epoch": 2.4775583482944343,
      "grad_norm": 0.5882549911232717,
      "learning_rate": 5e-06,
      "loss": 0.62,
      "step": 2070
    },
    {
      "epoch": 2.4895272292040693,
      "grad_norm": 0.6446559545029906,
      "learning_rate": 5e-06,
      "loss": 0.6256,
      "step": 2080
    },
    {
      "epoch": 2.5014961101137043,
      "grad_norm": 0.6769098922036072,
      "learning_rate": 5e-06,
      "loss": 0.6233,
      "step": 2090
    },
    {
      "epoch": 2.5134649910233393,
      "grad_norm": 0.7292441062228914,
      "learning_rate": 5e-06,
      "loss": 0.6193,
      "step": 2100
    },
    {
      "epoch": 2.5254338719329743,
      "grad_norm": 0.8318160977446282,
      "learning_rate": 5e-06,
      "loss": 0.6187,
      "step": 2110
    },
    {
      "epoch": 2.5374027528426093,
      "grad_norm": 0.6089671262894073,
      "learning_rate": 5e-06,
      "loss": 0.624,
      "step": 2120
    },
    {
      "epoch": 2.5493716337522443,
      "grad_norm": 0.7615201829189324,
      "learning_rate": 5e-06,
      "loss": 0.6171,
      "step": 2130
    },
    {
      "epoch": 2.561340514661879,
      "grad_norm": 0.724596159991658,
      "learning_rate": 5e-06,
      "loss": 0.6217,
      "step": 2140
    },
    {
      "epoch": 2.5733093955715143,
      "grad_norm": 0.612004698756559,
      "learning_rate": 5e-06,
      "loss": 0.6226,
      "step": 2150
    },
    {
      "epoch": 2.585278276481149,
      "grad_norm": 0.596628658148184,
      "learning_rate": 5e-06,
      "loss": 0.6271,
      "step": 2160
    },
    {
      "epoch": 2.597247157390784,
      "grad_norm": 0.6069344442414866,
      "learning_rate": 5e-06,
      "loss": 0.6224,
      "step": 2170
    },
    {
      "epoch": 2.609216038300419,
      "grad_norm": 0.6286980131185356,
      "learning_rate": 5e-06,
      "loss": 0.6212,
      "step": 2180
    },
    {
      "epoch": 2.621184919210054,
      "grad_norm": 0.6326929087930854,
      "learning_rate": 5e-06,
      "loss": 0.6235,
      "step": 2190
    },
    {
      "epoch": 2.633153800119689,
      "grad_norm": 0.7985721977529328,
      "learning_rate": 5e-06,
      "loss": 0.6237,
      "step": 2200
    },
    {
      "epoch": 2.645122681029324,
      "grad_norm": 0.644881510300382,
      "learning_rate": 5e-06,
      "loss": 0.6269,
      "step": 2210
    },
    {
      "epoch": 2.657091561938959,
      "grad_norm": 0.6012955887624781,
      "learning_rate": 5e-06,
      "loss": 0.6213,
      "step": 2220
    },
    {
      "epoch": 2.669060442848594,
      "grad_norm": 0.7267444291377996,
      "learning_rate": 5e-06,
      "loss": 0.6261,
      "step": 2230
    },
    {
      "epoch": 2.6810293237582288,
      "grad_norm": 0.7195410501187053,
      "learning_rate": 5e-06,
      "loss": 0.6238,
      "step": 2240
    },
    {
      "epoch": 2.6929982046678633,
      "grad_norm": 0.6633140798395725,
      "learning_rate": 5e-06,
      "loss": 0.6224,
      "step": 2250
    },
    {
      "epoch": 2.7049670855774988,
      "grad_norm": 0.6423861744102355,
      "learning_rate": 5e-06,
      "loss": 0.6245,
      "step": 2260
    },
    {
      "epoch": 2.7169359664871333,
      "grad_norm": 0.6091203181297667,
      "learning_rate": 5e-06,
      "loss": 0.626,
      "step": 2270
    },
    {
      "epoch": 2.7289048473967683,
      "grad_norm": 0.5794538334059404,
      "learning_rate": 5e-06,
      "loss": 0.6213,
      "step": 2280
    },
    {
      "epoch": 2.7408737283064033,
      "grad_norm": 0.6730274420363707,
      "learning_rate": 5e-06,
      "loss": 0.6257,
      "step": 2290
    },
    {
      "epoch": 2.7528426092160383,
      "grad_norm": 0.7260668423987153,
      "learning_rate": 5e-06,
      "loss": 0.6209,
      "step": 2300
    },
    {
      "epoch": 2.7648114901256733,
      "grad_norm": 0.6505297721856697,
      "learning_rate": 5e-06,
      "loss": 0.627,
      "step": 2310
    },
    {
      "epoch": 2.7767803710353083,
      "grad_norm": 0.6701846540950109,
      "learning_rate": 5e-06,
      "loss": 0.626,
      "step": 2320
    },
    {
      "epoch": 2.7887492519449433,
      "grad_norm": 0.6651727549955714,
      "learning_rate": 5e-06,
      "loss": 0.6284,
      "step": 2330
    },
    {
      "epoch": 2.800718132854578,
      "grad_norm": 0.5926739432014144,
      "learning_rate": 5e-06,
      "loss": 0.6277,
      "step": 2340
    },
    {
      "epoch": 2.8126870137642133,
      "grad_norm": 0.5816608379432976,
      "learning_rate": 5e-06,
      "loss": 0.6214,
      "step": 2350
    },
    {
      "epoch": 2.824655894673848,
      "grad_norm": 0.6395212133787649,
      "learning_rate": 5e-06,
      "loss": 0.6176,
      "step": 2360
    },
    {
      "epoch": 2.836624775583483,
      "grad_norm": 0.6634354922942822,
      "learning_rate": 5e-06,
      "loss": 0.6228,
      "step": 2370
    },
    {
      "epoch": 2.848593656493118,
      "grad_norm": 0.608805000460622,
      "learning_rate": 5e-06,
      "loss": 0.6236,
      "step": 2380
    },
    {
      "epoch": 2.860562537402753,
      "grad_norm": 0.6392304210790648,
      "learning_rate": 5e-06,
      "loss": 0.6247,
      "step": 2390
    },
    {
      "epoch": 2.872531418312388,
      "grad_norm": 0.6074342205287091,
      "learning_rate": 5e-06,
      "loss": 0.6227,
      "step": 2400
    },
    {
      "epoch": 2.884500299222023,
      "grad_norm": 0.5852140611153283,
      "learning_rate": 5e-06,
      "loss": 0.625,
      "step": 2410
    },
    {
      "epoch": 2.8964691801316578,
      "grad_norm": 0.7091297497420493,
      "learning_rate": 5e-06,
      "loss": 0.6195,
      "step": 2420
    },
    {
      "epoch": 2.9084380610412928,
      "grad_norm": 0.5525054193264387,
      "learning_rate": 5e-06,
      "loss": 0.6234,
      "step": 2430
    },
    {
      "epoch": 2.9204069419509278,
      "grad_norm": 0.7138183691173519,
      "learning_rate": 5e-06,
      "loss": 0.6247,
      "step": 2440
    },
    {
      "epoch": 2.9323758228605623,
      "grad_norm": 0.5805881225718816,
      "learning_rate": 5e-06,
      "loss": 0.623,
      "step": 2450
    },
    {
      "epoch": 2.9443447037701977,
      "grad_norm": 0.6015585624593602,
      "learning_rate": 5e-06,
      "loss": 0.6258,
      "step": 2460
    },
    {
      "epoch": 2.9563135846798323,
      "grad_norm": 0.5689711805490192,
      "learning_rate": 5e-06,
      "loss": 0.6196,
      "step": 2470
    },
    {
      "epoch": 2.9682824655894673,
      "grad_norm": 0.5963313497836371,
      "learning_rate": 5e-06,
      "loss": 0.6265,
      "step": 2480
    },
    {
      "epoch": 2.9802513464991023,
      "grad_norm": 0.6519931383722206,
      "learning_rate": 5e-06,
      "loss": 0.6217,
      "step": 2490
    },
    {
      "epoch": 2.9922202274087373,
      "grad_norm": 0.5587383883911408,
      "learning_rate": 5e-06,
      "loss": 0.6193,
      "step": 2500
    },
    {
      "epoch": 2.998204667863555,
      "eval_loss": 0.7030414938926697,
      "eval_runtime": 143.5127,
      "eval_samples_per_second": 156.878,
      "eval_steps_per_second": 0.613,
      "step": 2505
    },
    {
      "epoch": 2.998204667863555,
      "step": 2505,
      "total_flos": 4195130781204480.0,
      "train_loss": 0.6780577095206864,
      "train_runtime": 21666.0023,
      "train_samples_per_second": 59.229,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 10,
  "max_steps": 2505,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4195130781204480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}