{
  "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": 1.4386693012758085,
      "learning_rate": 5e-06,
      "loss": 0.7579,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8867158367707256,
      "learning_rate": 5e-06,
      "loss": 0.7029,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9488403053522199,
      "learning_rate": 5e-06,
      "loss": 0.6832,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.884176264535841,
      "learning_rate": 5e-06,
      "loss": 0.6835,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8397561690644878,
      "learning_rate": 5e-06,
      "loss": 0.6797,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.7606997383385686,
      "learning_rate": 5e-06,
      "loss": 0.6592,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.5641772966117866,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.4455570943818377,
      "learning_rate": 5e-06,
      "loss": 0.6573,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.35344748753637006,
      "learning_rate": 5e-06,
      "loss": 0.641,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.3194926627231166,
      "learning_rate": 5e-06,
      "loss": 0.6419,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.327073140109101,
      "learning_rate": 5e-06,
      "loss": 0.6329,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.2902488319100315,
      "learning_rate": 5e-06,
      "loss": 0.641,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3250030845224132,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.301467717572835,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3335273058944758,
      "learning_rate": 5e-06,
      "loss": 0.6365,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.3296991550356145,
      "learning_rate": 5e-06,
      "loss": 0.6417,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.3103731635734424,
      "learning_rate": 5e-06,
      "loss": 0.6334,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.29665465750244296,
      "learning_rate": 5e-06,
      "loss": 0.639,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3060805101577135,
      "learning_rate": 5e-06,
      "loss": 0.6316,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.2969598209435155,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.30839851830912446,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.3053987642580341,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.3348094885478149,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.2950949465171189,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3225072083038658,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.33126618150169374,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3123676307295024,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.31608075186025725,
      "learning_rate": 5e-06,
      "loss": 0.6422,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.295304591634291,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2889796046509888,
      "learning_rate": 5e-06,
      "loss": 0.6289,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2828279092197474,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.3123856218189676,
      "learning_rate": 5e-06,
      "loss": 0.6293,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3053322180872748,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.2926207509847771,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.29988955618078283,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3048877888264376,
      "learning_rate": 5e-06,
      "loss": 0.6306,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.34334690821050184,
      "learning_rate": 5e-06,
      "loss": 0.6243,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3134188238075275,
      "learning_rate": 5e-06,
      "loss": 0.6365,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.30566485805979765,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.31666519162979606,
      "learning_rate": 5e-06,
      "loss": 0.6384,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.2794015692940556,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.3050489727811934,
      "learning_rate": 5e-06,
      "loss": 0.6215,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.34520329516921633,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251624226570129,
      "eval_runtime": 445.1376,
      "eval_samples_per_second": 26.56,
      "eval_steps_per_second": 0.416,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.3500234102689406,
      "learning_rate": 5e-06,
      "loss": 0.6473,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.3135823115202442,
      "learning_rate": 5e-06,
      "loss": 0.602,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.32895439127731363,
      "learning_rate": 5e-06,
      "loss": 0.5954,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.2980741864148205,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.3005539750743244,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3193329083839523,
      "learning_rate": 5e-06,
      "loss": 0.6084,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.2971789146327925,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3014133236150067,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.31061311315632684,
      "learning_rate": 5e-06,
      "loss": 0.6018,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.3030494386702636,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.32399832658742117,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.28839198489010404,
      "learning_rate": 5e-06,
      "loss": 0.6017,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.2964653938206201,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.28722558037585133,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2923968412756558,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.28753838300402135,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.3334994604865794,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.2991486931963729,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.3073110980633579,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.3100450193104537,
      "learning_rate": 5e-06,
      "loss": 0.6018,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.3055297206364041,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.3029784972136167,
      "learning_rate": 5e-06,
      "loss": 0.5946,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.2834424411606447,
      "learning_rate": 5e-06,
      "loss": 0.5942,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.3194897462541008,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.29190992841354146,
      "learning_rate": 5e-06,
      "loss": 0.5904,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.31705729350194956,
      "learning_rate": 5e-06,
      "loss": 0.5944,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.29252625572912966,
      "learning_rate": 5e-06,
      "loss": 0.61,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.31234731377862573,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.3160189008473381,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.29544177148306744,
      "learning_rate": 5e-06,
      "loss": 0.5947,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.30708751751912383,
      "learning_rate": 5e-06,
      "loss": 0.5957,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.3048638695052697,
      "learning_rate": 5e-06,
      "loss": 0.5932,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.3146316081703229,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.32002761544313474,
      "learning_rate": 5e-06,
      "loss": 0.5935,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.30010567894497364,
      "learning_rate": 5e-06,
      "loss": 0.6007,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.28285672159123876,
      "learning_rate": 5e-06,
      "loss": 0.5982,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.28611836059295176,
      "learning_rate": 5e-06,
      "loss": 0.5851,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.30797592386487205,
      "learning_rate": 5e-06,
      "loss": 0.5929,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.3063321918111546,
      "learning_rate": 5e-06,
      "loss": 0.5906,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.30525107848276234,
      "learning_rate": 5e-06,
      "loss": 0.5945,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.29791867679830153,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.29637691821376655,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.30625195405550415,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.33176229383034617,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.618757426738739,
      "eval_runtime": 445.8741,
      "eval_samples_per_second": 26.516,
      "eval_steps_per_second": 0.415,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.2936199686212669,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.32905123086930277,
      "learning_rate": 5e-06,
      "loss": 0.5547,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.31597772907288135,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.3150594692282521,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.3072197547874636,
      "learning_rate": 5e-06,
      "loss": 0.5706,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.30005346574771413,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.3017795274737325,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.30206580494490604,
      "learning_rate": 5e-06,
      "loss": 0.5641,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.2980530215049522,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.31524358050102935,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.3128509983082201,
      "learning_rate": 5e-06,
      "loss": 0.5583,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.3140793309951936,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.28520834084454944,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.29867824686812755,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.3145208805177942,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.2902492701764916,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.2956594814241214,
      "learning_rate": 5e-06,
      "loss": 0.5674,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.31738434358751366,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.28908242561794056,
      "learning_rate": 5e-06,
      "loss": 0.5752,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.2903170979095093,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.2852792499162689,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2753361670224193,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.29187729007400126,
      "learning_rate": 5e-06,
      "loss": 0.5773,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.2948065365452112,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.29233811433610235,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.29251338108992897,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.28887301028922413,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.3130706205394312,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.3098221144899901,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.28798485314235794,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.28437339107985654,
      "learning_rate": 5e-06,
      "loss": 0.5675,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.3036502139166253,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.301383160626782,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.3163849017521735,
      "learning_rate": 5e-06,
      "loss": 0.5752,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.31117137034097503,
      "learning_rate": 5e-06,
      "loss": 0.5651,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2930242603622392,
      "learning_rate": 5e-06,
      "loss": 0.5636,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.3144851013348898,
      "learning_rate": 5e-06,
      "loss": 0.5784,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.2971023651878554,
      "learning_rate": 5e-06,
      "loss": 0.575,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.31461051709792115,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.31229107305530807,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.30391491233086704,
      "learning_rate": 5e-06,
      "loss": 0.5633,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.3087650960617782,
      "learning_rate": 5e-06,
      "loss": 0.5635,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.2942869811591753,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.31862561633033365,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6188442707061768,
      "eval_runtime": 444.3583,
      "eval_samples_per_second": 26.607,
      "eval_steps_per_second": 0.416,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.6039808779909549,
      "train_runtime": 71394.4326,
      "train_samples_per_second": 9.439,
      "train_steps_per_second": 0.018
    }
  ],
  "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
}