{
  "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": 2.667692336452461,
      "learning_rate": 5e-06,
      "loss": 0.7534,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8063888051525331,
      "learning_rate": 5e-06,
      "loss": 0.699,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9060943666753217,
      "learning_rate": 5e-06,
      "loss": 0.6792,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.863100204101913,
      "learning_rate": 5e-06,
      "loss": 0.6793,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8020158873807923,
      "learning_rate": 5e-06,
      "loss": 0.6755,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.684096154720575,
      "learning_rate": 5e-06,
      "loss": 0.6553,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.45007895438831524,
      "learning_rate": 5e-06,
      "loss": 0.6522,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.3793094921700233,
      "learning_rate": 5e-06,
      "loss": 0.6551,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3149452056766187,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.3009594867680131,
      "learning_rate": 5e-06,
      "loss": 0.6412,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.34212181307790984,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.3071741827743272,
      "learning_rate": 5e-06,
      "loss": 0.6407,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2921267402694689,
      "learning_rate": 5e-06,
      "loss": 0.6417,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.3086951712828636,
      "learning_rate": 5e-06,
      "loss": 0.6438,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.31203378476932964,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.31089407638977484,
      "learning_rate": 5e-06,
      "loss": 0.6415,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35439340860374086,
      "learning_rate": 5e-06,
      "loss": 0.6333,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3029281442256716,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3035263406218673,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.30613699941499445,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3097244580495573,
      "learning_rate": 5e-06,
      "loss": 0.6358,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.30052514890974735,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3247757790920796,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.3002320555356954,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.33788540070089457,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.29983726730351934,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3083145101540858,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.31499238828203335,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.32514749431753714,
      "learning_rate": 5e-06,
      "loss": 0.6307,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.28853752402247734,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2977250374761748,
      "learning_rate": 5e-06,
      "loss": 0.6286,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.33869550896521733,
      "learning_rate": 5e-06,
      "loss": 0.6292,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.30377512470657203,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3285936613654986,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3338489009754525,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.31401301210309734,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.32729904251625536,
      "learning_rate": 5e-06,
      "loss": 0.6242,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3137460681429382,
      "learning_rate": 5e-06,
      "loss": 0.6365,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.32750286290464264,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.2982635849558681,
      "learning_rate": 5e-06,
      "loss": 0.6383,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.2855401575649863,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.3006500631775212,
      "learning_rate": 5e-06,
      "loss": 0.6215,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.34295212142334275,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251533031463623,
      "eval_runtime": 443.2695,
      "eval_samples_per_second": 26.672,
      "eval_steps_per_second": 0.417,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.35024631622777125,
      "learning_rate": 5e-06,
      "loss": 0.6472,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.33002240579640935,
      "learning_rate": 5e-06,
      "loss": 0.6017,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.31651186830890377,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.2916006238361447,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.3048367563892593,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3276162015278515,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.29051409762342256,
      "learning_rate": 5e-06,
      "loss": 0.5987,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.309815710665164,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.2943518362832322,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.3206888044455193,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.28810098486400076,
      "learning_rate": 5e-06,
      "loss": 0.6056,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.33684168520106755,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.2930925524871367,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.2997084038260789,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2724633931757638,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.29594928695290523,
      "learning_rate": 5e-06,
      "loss": 0.5959,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.3509170428001788,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.31871308148877675,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.29158762025250556,
      "learning_rate": 5e-06,
      "loss": 0.6041,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.31932103979021054,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.30549722640769267,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.2951879017910213,
      "learning_rate": 5e-06,
      "loss": 0.5949,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.2890301521070669,
      "learning_rate": 5e-06,
      "loss": 0.5946,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.3152131309167344,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.27457370025182487,
      "learning_rate": 5e-06,
      "loss": 0.5908,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.32514865685817596,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.2869347820786928,
      "learning_rate": 5e-06,
      "loss": 0.6103,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.3130330176159502,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.29489095764802076,
      "learning_rate": 5e-06,
      "loss": 0.602,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.3334123404509505,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.3211675496150495,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2952767746051378,
      "learning_rate": 5e-06,
      "loss": 0.5935,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.3122013602871499,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.29493014283340135,
      "learning_rate": 5e-06,
      "loss": 0.5939,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.30726201417055676,
      "learning_rate": 5e-06,
      "loss": 0.601,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.29691381334334693,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.31312793491026397,
      "learning_rate": 5e-06,
      "loss": 0.5854,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.30709319545073666,
      "learning_rate": 5e-06,
      "loss": 0.5932,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.3023157832075651,
      "learning_rate": 5e-06,
      "loss": 0.591,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.32438843189452765,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.3133407951548133,
      "learning_rate": 5e-06,
      "loss": 0.5992,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.2991755831382789,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.3113336058021223,
      "learning_rate": 5e-06,
      "loss": 0.5987,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3520179966585449,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6187062859535217,
      "eval_runtime": 442.9315,
      "eval_samples_per_second": 26.693,
      "eval_steps_per_second": 0.418,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.3402585851685105,
      "learning_rate": 5e-06,
      "loss": 0.6155,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.34358400255798927,
      "learning_rate": 5e-06,
      "loss": 0.5547,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.30065738065627035,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.350961553117733,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.33412845962784443,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.28301100428565806,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.29246926901624365,
      "learning_rate": 5e-06,
      "loss": 0.5637,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.3085716692725879,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.31238615273409037,
      "learning_rate": 5e-06,
      "loss": 0.5697,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.2889893652608361,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28744425674496726,
      "learning_rate": 5e-06,
      "loss": 0.5588,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.31862553873260213,
      "learning_rate": 5e-06,
      "loss": 0.5678,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.30176325862165776,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.3415868984406676,
      "learning_rate": 5e-06,
      "loss": 0.5656,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.3053031592130626,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.34927703789690623,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.2971790308579545,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.30598279561257147,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.3038193133765918,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.30594054629347417,
      "learning_rate": 5e-06,
      "loss": 0.5785,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.3047017356999142,
      "learning_rate": 5e-06,
      "loss": 0.5738,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.30228571032388474,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.30561689682501575,
      "learning_rate": 5e-06,
      "loss": 0.5778,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.3218399680160419,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.29888426709529753,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.30030693301168837,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.31110920572933626,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.30377446561184135,
      "learning_rate": 5e-06,
      "loss": 0.5688,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.30883960403656696,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.295333664191936,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.29666095565935197,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.2896839269345245,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.28697330475888133,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.2937887632208763,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.287081423243111,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.29865384294519426,
      "learning_rate": 5e-06,
      "loss": 0.5639,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.31153098262281526,
      "learning_rate": 5e-06,
      "loss": 0.5787,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.3019801645510001,
      "learning_rate": 5e-06,
      "loss": 0.5754,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.29801055775475277,
      "learning_rate": 5e-06,
      "loss": 0.5725,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.3022646107633967,
      "learning_rate": 5e-06,
      "loss": 0.5735,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.288708077282271,
      "learning_rate": 5e-06,
      "loss": 0.5637,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.3003385354677671,
      "learning_rate": 5e-06,
      "loss": 0.5639,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.35679915826472547,
      "learning_rate": 5e-06,
      "loss": 0.5651,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.3072621489316874,
      "learning_rate": 5e-06,
      "loss": 0.5749,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.618656575679779,
      "eval_runtime": 442.1394,
      "eval_samples_per_second": 26.74,
      "eval_steps_per_second": 0.418,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6039760675241596,
      "train_runtime": 70715.1755,
      "train_samples_per_second": 9.529,
      "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
}