{
  "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": 1.0060717937312023,
      "learning_rate": 5e-06,
      "loss": 0.7524,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.7891563140905129,
      "learning_rate": 5e-06,
      "loss": 0.6969,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9139530591526533,
      "learning_rate": 5e-06,
      "loss": 0.6771,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8498162025655388,
      "learning_rate": 5e-06,
      "loss": 0.6775,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.7817634582289844,
      "learning_rate": 5e-06,
      "loss": 0.6738,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.6293849390879412,
      "learning_rate": 5e-06,
      "loss": 0.6538,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.41921457987793875,
      "learning_rate": 5e-06,
      "loss": 0.6513,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.36300206030899534,
      "learning_rate": 5e-06,
      "loss": 0.6548,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.309957963162278,
      "learning_rate": 5e-06,
      "loss": 0.6398,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.32328999508305195,
      "learning_rate": 5e-06,
      "loss": 0.6411,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.330574745397823,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.29931157739012315,
      "learning_rate": 5e-06,
      "loss": 0.6407,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.34029859245399474,
      "learning_rate": 5e-06,
      "loss": 0.6417,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.30127106255202635,
      "learning_rate": 5e-06,
      "loss": 0.6438,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3151006777409588,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.33032068654862884,
      "learning_rate": 5e-06,
      "loss": 0.6416,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.34687627705792795,
      "learning_rate": 5e-06,
      "loss": 0.6333,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.30299829941401296,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.32126277950058085,
      "learning_rate": 5e-06,
      "loss": 0.6315,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.32181196392081757,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.29027414461556106,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.3004935364337486,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3182054190088126,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.29257308790197833,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3281874063385835,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.30750195742038006,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3054834309240547,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.31232338920961195,
      "learning_rate": 5e-06,
      "loss": 0.6421,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.33312268715489884,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.28430439482527575,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.30649270069730716,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3040140255060057,
      "learning_rate": 5e-06,
      "loss": 0.6293,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3545999092593587,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.30986750638847393,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3216062543695188,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.317954119212454,
      "learning_rate": 5e-06,
      "loss": 0.6306,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.3552789384520918,
      "learning_rate": 5e-06,
      "loss": 0.6243,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.2927240780631906,
      "learning_rate": 5e-06,
      "loss": 0.6366,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3362026135681421,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.3171566741033119,
      "learning_rate": 5e-06,
      "loss": 0.6384,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.3178698000797058,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.3103202303938852,
      "learning_rate": 5e-06,
      "loss": 0.6215,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3815191468278998,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251751184463501,
      "eval_runtime": 443.8724,
      "eval_samples_per_second": 26.636,
      "eval_steps_per_second": 0.417,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.33172834615136476,
      "learning_rate": 5e-06,
      "loss": 0.6473,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.34424149066722537,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.3028655590581102,
      "learning_rate": 5e-06,
      "loss": 0.5957,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.2884231268619158,
      "learning_rate": 5e-06,
      "loss": 0.5967,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.30659760009174,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.32926249950938313,
      "learning_rate": 5e-06,
      "loss": 0.6093,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.3158323453023191,
      "learning_rate": 5e-06,
      "loss": 0.5991,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3031613959301613,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.288147157900111,
      "learning_rate": 5e-06,
      "loss": 0.6027,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.30665751637918065,
      "learning_rate": 5e-06,
      "loss": 0.5957,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.3188310134389718,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.3056881609648514,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.27741435521459135,
      "learning_rate": 5e-06,
      "loss": 0.6041,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.30256280677733355,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2849315058896214,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.28805599862814474,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.30205024558551485,
      "learning_rate": 5e-06,
      "loss": 0.6018,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.3082719282952612,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.3149801306843495,
      "learning_rate": 5e-06,
      "loss": 0.6045,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.3588632396980364,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.32450978554155874,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.3072016967628761,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.3234819157170789,
      "learning_rate": 5e-06,
      "loss": 0.595,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.33073183709411097,
      "learning_rate": 5e-06,
      "loss": 0.6026,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2827694243710057,
      "learning_rate": 5e-06,
      "loss": 0.5911,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.313252659198283,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.3006117467907023,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.30612410275194285,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.3024691477363925,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.2977897390172667,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.36185544494498323,
      "learning_rate": 5e-06,
      "loss": 0.5965,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2841927419626393,
      "learning_rate": 5e-06,
      "loss": 0.5938,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.3419351965360681,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.30800250495317405,
      "learning_rate": 5e-06,
      "loss": 0.5941,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.29984584493486444,
      "learning_rate": 5e-06,
      "loss": 0.6013,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.30044148053925274,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.3025363179456475,
      "learning_rate": 5e-06,
      "loss": 0.5856,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.3145503828700074,
      "learning_rate": 5e-06,
      "loss": 0.5935,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.35065394981808123,
      "learning_rate": 5e-06,
      "loss": 0.5912,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.2974502518481575,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.32731845865746034,
      "learning_rate": 5e-06,
      "loss": 0.5996,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.31162936799394053,
      "learning_rate": 5e-06,
      "loss": 0.5976,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.32719072803884974,
      "learning_rate": 5e-06,
      "loss": 0.5989,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3101089792190507,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6190649271011353,
      "eval_runtime": 441.9179,
      "eval_samples_per_second": 26.754,
      "eval_steps_per_second": 0.419,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.31583692108300393,
      "learning_rate": 5e-06,
      "loss": 0.6158,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.3549258835016534,
      "learning_rate": 5e-06,
      "loss": 0.5549,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.33724473694318774,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.3141133261122478,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.29764089324641324,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.28790057942161257,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.29743546832324724,
      "learning_rate": 5e-06,
      "loss": 0.5642,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.2954585305184846,
      "learning_rate": 5e-06,
      "loss": 0.5651,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.3050175730295642,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.32132099983730744,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.2837390182666578,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.29469997963523875,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.3120611664539125,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.3537751093167747,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.2852167762719538,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.32111957707443545,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.3012654149735683,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.308454191252784,
      "learning_rate": 5e-06,
      "loss": 0.5677,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.31064428522383297,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.3058217002467149,
      "learning_rate": 5e-06,
      "loss": 0.5789,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.32737211111120573,
      "learning_rate": 5e-06,
      "loss": 0.5742,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.28097098781753427,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.3370867700826581,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.3481252533458522,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.28443121713707625,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.28884871195764056,
      "learning_rate": 5e-06,
      "loss": 0.5693,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.3009832609905576,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.3048094427833053,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.3295891153062313,
      "learning_rate": 5e-06,
      "loss": 0.5703,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.2965154504918107,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.3026395616545691,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.3390836756743429,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.31852178230857053,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.28505692332238153,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.296853334138319,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2995278356454653,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.31122420075903284,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.28755094750291593,
      "learning_rate": 5e-06,
      "loss": 0.5757,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.31965652378893494,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.32825908653753605,
      "learning_rate": 5e-06,
      "loss": 0.5739,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.3071446259514345,
      "learning_rate": 5e-06,
      "loss": 0.5641,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.3148839567474544,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.2929400491067566,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.31295742772627644,
      "learning_rate": 5e-06,
      "loss": 0.5752,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6186820268630981,
      "eval_runtime": 441.0146,
      "eval_samples_per_second": 26.809,
      "eval_steps_per_second": 0.419,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6041361260450413,
      "train_runtime": 70558.5882,
      "train_samples_per_second": 9.55,
      "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
}