{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996011396011396,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 2.864508008766109,
      "learning_rate": 2e-06,
      "loss": 0.779,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.9078935811597736,
      "learning_rate": 2e-06,
      "loss": 0.7215,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9591168040971848,
      "learning_rate": 2e-06,
      "loss": 0.6975,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8767413401192973,
      "learning_rate": 2e-06,
      "loss": 0.6978,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8545665855899989,
      "learning_rate": 2e-06,
      "loss": 0.6958,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.8280986731912829,
      "learning_rate": 2e-06,
      "loss": 0.677,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.7119760771817697,
      "learning_rate": 2e-06,
      "loss": 0.6753,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.8493364147676038,
      "learning_rate": 2e-06,
      "loss": 0.6786,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.794423341017749,
      "learning_rate": 2e-06,
      "loss": 0.6624,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.8659153934871785,
      "learning_rate": 2e-06,
      "loss": 0.6618,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.7487650632319812,
      "learning_rate": 2e-06,
      "loss": 0.651,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.7717117299400736,
      "learning_rate": 2e-06,
      "loss": 0.6575,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.7004524658993033,
      "learning_rate": 2e-06,
      "loss": 0.6566,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.6752858564876342,
      "learning_rate": 2e-06,
      "loss": 0.6573,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.5562623802865255,
      "learning_rate": 2e-06,
      "loss": 0.6485,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.4789275636440992,
      "learning_rate": 2e-06,
      "loss": 0.6527,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.4387647670962861,
      "learning_rate": 2e-06,
      "loss": 0.644,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3651502046396496,
      "learning_rate": 2e-06,
      "loss": 0.6491,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3587478512482826,
      "learning_rate": 2e-06,
      "loss": 0.6412,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.35057238218897174,
      "learning_rate": 2e-06,
      "loss": 0.6492,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.316969119781051,
      "learning_rate": 2e-06,
      "loss": 0.6454,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.33352881670277756,
      "learning_rate": 2e-06,
      "loss": 0.649,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.33234583103322946,
      "learning_rate": 2e-06,
      "loss": 0.6443,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.29765701008940304,
      "learning_rate": 2e-06,
      "loss": 0.6402,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3093961084707375,
      "learning_rate": 2e-06,
      "loss": 0.6451,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3170813416727422,
      "learning_rate": 2e-06,
      "loss": 0.6433,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.2882757041299046,
      "learning_rate": 2e-06,
      "loss": 0.6404,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3081992136303576,
      "learning_rate": 2e-06,
      "loss": 0.6512,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3016510334414117,
      "learning_rate": 2e-06,
      "loss": 0.6398,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.29654738723801505,
      "learning_rate": 2e-06,
      "loss": 0.6379,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2863099976470917,
      "learning_rate": 2e-06,
      "loss": 0.6376,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3049298985658395,
      "learning_rate": 2e-06,
      "loss": 0.6381,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.29920289611631834,
      "learning_rate": 2e-06,
      "loss": 0.6349,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.28462260835565456,
      "learning_rate": 2e-06,
      "loss": 0.6407,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.31005901743663883,
      "learning_rate": 2e-06,
      "loss": 0.6479,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.29494933869606077,
      "learning_rate": 2e-06,
      "loss": 0.6396,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.33568791338440107,
      "learning_rate": 2e-06,
      "loss": 0.6334,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3040287915954937,
      "learning_rate": 2e-06,
      "loss": 0.6456,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.28864498526565957,
      "learning_rate": 2e-06,
      "loss": 0.6442,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.293111101754528,
      "learning_rate": 2e-06,
      "loss": 0.6475,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.27087911354534383,
      "learning_rate": 2e-06,
      "loss": 0.6437,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.28437527266058993,
      "learning_rate": 2e-06,
      "loss": 0.6305,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3040557123080402,
      "learning_rate": 2e-06,
      "loss": 0.6437,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.634207010269165,
      "eval_runtime": 440.7496,
      "eval_samples_per_second": 26.825,
      "eval_steps_per_second": 0.42,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.30691349645034643,
      "learning_rate": 2e-06,
      "loss": 0.6589,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.29205865755410254,
      "learning_rate": 2e-06,
      "loss": 0.6262,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.30392093777188467,
      "learning_rate": 2e-06,
      "loss": 0.6198,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.2828326519597703,
      "learning_rate": 2e-06,
      "loss": 0.6208,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.28162501980854593,
      "learning_rate": 2e-06,
      "loss": 0.6281,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.2939036352432325,
      "learning_rate": 2e-06,
      "loss": 0.6331,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.2763230121687841,
      "learning_rate": 2e-06,
      "loss": 0.6226,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.2854865008524285,
      "learning_rate": 2e-06,
      "loss": 0.6201,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.2855187866369504,
      "learning_rate": 2e-06,
      "loss": 0.6257,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.28579952821101995,
      "learning_rate": 2e-06,
      "loss": 0.6183,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.31286133152047063,
      "learning_rate": 2e-06,
      "loss": 0.6287,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.27149328112131427,
      "learning_rate": 2e-06,
      "loss": 0.6252,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.28442376744542436,
      "learning_rate": 2e-06,
      "loss": 0.6264,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.27944308671830026,
      "learning_rate": 2e-06,
      "loss": 0.6201,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2745193653156677,
      "learning_rate": 2e-06,
      "loss": 0.6187,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.28421785591908916,
      "learning_rate": 2e-06,
      "loss": 0.6183,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.31615427394285256,
      "learning_rate": 2e-06,
      "loss": 0.6239,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.2895588155201198,
      "learning_rate": 2e-06,
      "loss": 0.6239,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.2748857458986795,
      "learning_rate": 2e-06,
      "loss": 0.6263,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.29452945089403426,
      "learning_rate": 2e-06,
      "loss": 0.6242,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.29177001933506297,
      "learning_rate": 2e-06,
      "loss": 0.6191,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.3201830623263587,
      "learning_rate": 2e-06,
      "loss": 0.6167,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.27587844668467365,
      "learning_rate": 2e-06,
      "loss": 0.6164,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.29954875579985213,
      "learning_rate": 2e-06,
      "loss": 0.6242,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2731664505058775,
      "learning_rate": 2e-06,
      "loss": 0.6123,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.31129992079722374,
      "learning_rate": 2e-06,
      "loss": 0.6164,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.2772886517333268,
      "learning_rate": 2e-06,
      "loss": 0.632,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.2876973271112532,
      "learning_rate": 2e-06,
      "loss": 0.6188,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.30143918664865993,
      "learning_rate": 2e-06,
      "loss": 0.6235,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.2873047034444853,
      "learning_rate": 2e-06,
      "loss": 0.6163,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.28340344600988737,
      "learning_rate": 2e-06,
      "loss": 0.6173,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2790689335967899,
      "learning_rate": 2e-06,
      "loss": 0.6145,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.28801564449039246,
      "learning_rate": 2e-06,
      "loss": 0.6188,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.28497713222065674,
      "learning_rate": 2e-06,
      "loss": 0.615,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.2853302771792979,
      "learning_rate": 2e-06,
      "loss": 0.6222,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.2825413400545415,
      "learning_rate": 2e-06,
      "loss": 0.6194,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.2864348042850986,
      "learning_rate": 2e-06,
      "loss": 0.6059,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.29963979013514164,
      "learning_rate": 2e-06,
      "loss": 0.6139,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.27740105545017113,
      "learning_rate": 2e-06,
      "loss": 0.6116,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.27815438089274597,
      "learning_rate": 2e-06,
      "loss": 0.6156,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.2873161616115944,
      "learning_rate": 2e-06,
      "loss": 0.6201,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.2923191233832773,
      "learning_rate": 2e-06,
      "loss": 0.618,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.28243883384079016,
      "learning_rate": 2e-06,
      "loss": 0.6193,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3024016197121533,
      "learning_rate": 2e-06,
      "loss": 0.6168,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6261253356933594,
      "eval_runtime": 441.2387,
      "eval_samples_per_second": 26.795,
      "eval_steps_per_second": 0.419,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.2780767198866166,
      "learning_rate": 2e-06,
      "loss": 0.6416,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.28632050007528936,
      "learning_rate": 2e-06,
      "loss": 0.5906,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.28591330449055385,
      "learning_rate": 2e-06,
      "loss": 0.6068,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.29332676336619445,
      "learning_rate": 2e-06,
      "loss": 0.6046,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.28668389343499623,
      "learning_rate": 2e-06,
      "loss": 0.6078,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.289239255821366,
      "learning_rate": 2e-06,
      "loss": 0.6052,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.282673762278497,
      "learning_rate": 2e-06,
      "loss": 0.5997,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.28582015763960644,
      "learning_rate": 2e-06,
      "loss": 0.6009,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.2802200672060606,
      "learning_rate": 2e-06,
      "loss": 0.6058,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.29000853156799317,
      "learning_rate": 2e-06,
      "loss": 0.6048,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.3095113688403279,
      "learning_rate": 2e-06,
      "loss": 0.5937,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.296958733510943,
      "learning_rate": 2e-06,
      "loss": 0.6028,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.279130743733046,
      "learning_rate": 2e-06,
      "loss": 0.6029,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.2829565255627152,
      "learning_rate": 2e-06,
      "loss": 0.6002,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.30774789195383456,
      "learning_rate": 2e-06,
      "loss": 0.6034,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.27543037768068174,
      "learning_rate": 2e-06,
      "loss": 0.6049,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.2800183284208171,
      "learning_rate": 2e-06,
      "loss": 0.6021,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.3013281475062929,
      "learning_rate": 2e-06,
      "loss": 0.6015,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.2905972470777562,
      "learning_rate": 2e-06,
      "loss": 0.6102,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.286494804323914,
      "learning_rate": 2e-06,
      "loss": 0.6133,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.276343757422485,
      "learning_rate": 2e-06,
      "loss": 0.6082,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2708146708371793,
      "learning_rate": 2e-06,
      "loss": 0.6053,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.2888450487275576,
      "learning_rate": 2e-06,
      "loss": 0.6124,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.2825228879995427,
      "learning_rate": 2e-06,
      "loss": 0.605,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.2803594149293884,
      "learning_rate": 2e-06,
      "loss": 0.6032,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.2857182498890343,
      "learning_rate": 2e-06,
      "loss": 0.6023,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.28352170043467456,
      "learning_rate": 2e-06,
      "loss": 0.6019,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.3138498081549944,
      "learning_rate": 2e-06,
      "loss": 0.6021,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.2879058037646963,
      "learning_rate": 2e-06,
      "loss": 0.6028,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.2771838146813842,
      "learning_rate": 2e-06,
      "loss": 0.6061,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.2783128898098319,
      "learning_rate": 2e-06,
      "loss": 0.6009,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.2815742815524037,
      "learning_rate": 2e-06,
      "loss": 0.6018,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.2891453557368429,
      "learning_rate": 2e-06,
      "loss": 0.6051,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.29088353404285416,
      "learning_rate": 2e-06,
      "loss": 0.6085,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.28833617475662054,
      "learning_rate": 2e-06,
      "loss": 0.5979,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2853141216724547,
      "learning_rate": 2e-06,
      "loss": 0.5963,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.29954457976745724,
      "learning_rate": 2e-06,
      "loss": 0.6117,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.2791597452969322,
      "learning_rate": 2e-06,
      "loss": 0.6083,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.295287854084783,
      "learning_rate": 2e-06,
      "loss": 0.6052,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.3030851891787806,
      "learning_rate": 2e-06,
      "loss": 0.606,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.29008501545155757,
      "learning_rate": 2e-06,
      "loss": 0.5959,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.28886132459109937,
      "learning_rate": 2e-06,
      "loss": 0.5958,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.2930192014893465,
      "learning_rate": 2e-06,
      "loss": 0.5971,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.2931492064869206,
      "learning_rate": 2e-06,
      "loss": 0.6075,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6223183870315552,
      "eval_runtime": 439.7512,
      "eval_samples_per_second": 26.886,
      "eval_steps_per_second": 0.421,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6269598571495741,
      "train_runtime": 70419.7857,
      "train_samples_per_second": 9.569,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "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": 2755219238682624.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}