{
  "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": 1.0676255426887773,
      "learning_rate": 5e-06,
      "loss": 0.7539,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8020375630102242,
      "learning_rate": 5e-06,
      "loss": 0.6994,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9081397985281835,
      "learning_rate": 5e-06,
      "loss": 0.6795,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8629439851200038,
      "learning_rate": 5e-06,
      "loss": 0.6797,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8090632737201253,
      "learning_rate": 5e-06,
      "loss": 0.6761,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.7076703018196557,
      "learning_rate": 5e-06,
      "loss": 0.6559,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.481474349102952,
      "learning_rate": 5e-06,
      "loss": 0.6528,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.40234059153739476,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3229796123691384,
      "learning_rate": 5e-06,
      "loss": 0.64,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.3020829006985226,
      "learning_rate": 5e-06,
      "loss": 0.6412,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.3368731489594517,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.30803813859251755,
      "learning_rate": 5e-06,
      "loss": 0.6407,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2930770885235812,
      "learning_rate": 5e-06,
      "loss": 0.6417,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.30890527478392654,
      "learning_rate": 5e-06,
      "loss": 0.6438,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3134464611772735,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.3119680733639685,
      "learning_rate": 5e-06,
      "loss": 0.6415,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35232043785760986,
      "learning_rate": 5e-06,
      "loss": 0.6333,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3019822264964147,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3048379828346624,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3084969367482762,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.31079794963488605,
      "learning_rate": 5e-06,
      "loss": 0.6358,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.30264668473005746,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.32525624558303584,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.2964973107205488,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.33755901642762914,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3041302099668124,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.30958802218562187,
      "learning_rate": 5e-06,
      "loss": 0.6312,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.32606132254148357,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3232190180759512,
      "learning_rate": 5e-06,
      "loss": 0.6307,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.29078775385137123,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2954638192885692,
      "learning_rate": 5e-06,
      "loss": 0.6286,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.34030603199468923,
      "learning_rate": 5e-06,
      "loss": 0.6292,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.30519185677280275,
      "learning_rate": 5e-06,
      "loss": 0.6258,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.3221910804630611,
      "learning_rate": 5e-06,
      "loss": 0.6316,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3329448099865066,
      "learning_rate": 5e-06,
      "loss": 0.6387,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.3139350203048552,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.3294650596325528,
      "learning_rate": 5e-06,
      "loss": 0.6242,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.31187269802126066,
      "learning_rate": 5e-06,
      "loss": 0.6365,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3282528612800075,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.2935934984979255,
      "learning_rate": 5e-06,
      "loss": 0.6383,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.2873907170114121,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.30543990735115556,
      "learning_rate": 5e-06,
      "loss": 0.6214,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.33591746917431226,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251206398010254,
      "eval_runtime": 439.9568,
      "eval_samples_per_second": 26.873,
      "eval_steps_per_second": 0.42,
      "step": 438
    },
    {
      "epoch": 1.0034188034188034,
      "grad_norm": 0.3539973565820665,
      "learning_rate": 5e-06,
      "loss": 0.6472,
      "step": 440
    },
    {
      "epoch": 1.0262108262108263,
      "grad_norm": 0.330124186903256,
      "learning_rate": 5e-06,
      "loss": 0.6019,
      "step": 450
    },
    {
      "epoch": 1.049002849002849,
      "grad_norm": 0.296594727480026,
      "learning_rate": 5e-06,
      "loss": 0.5956,
      "step": 460
    },
    {
      "epoch": 1.0717948717948718,
      "grad_norm": 0.2960312661109275,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 470
    },
    {
      "epoch": 1.0945868945868946,
      "grad_norm": 0.30713149715413646,
      "learning_rate": 5e-06,
      "loss": 0.6039,
      "step": 480
    },
    {
      "epoch": 1.1173789173789175,
      "grad_norm": 0.3192402710541115,
      "learning_rate": 5e-06,
      "loss": 0.609,
      "step": 490
    },
    {
      "epoch": 1.1401709401709401,
      "grad_norm": 0.2940649120603813,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 500
    },
    {
      "epoch": 1.162962962962963,
      "grad_norm": 0.3164230704160555,
      "learning_rate": 5e-06,
      "loss": 0.5967,
      "step": 510
    },
    {
      "epoch": 1.1857549857549858,
      "grad_norm": 0.2951082842032421,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 520
    },
    {
      "epoch": 1.2085470085470085,
      "grad_norm": 0.32566458232787066,
      "learning_rate": 5e-06,
      "loss": 0.5954,
      "step": 530
    },
    {
      "epoch": 1.2313390313390313,
      "grad_norm": 0.28694399224163053,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 540
    },
    {
      "epoch": 1.2541310541310542,
      "grad_norm": 0.3328372357166377,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 550
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.2857747024845843,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 560
    },
    {
      "epoch": 1.2997150997150997,
      "grad_norm": 0.30771180203329035,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 570
    },
    {
      "epoch": 1.3225071225071225,
      "grad_norm": 0.2726439554899611,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 580
    },
    {
      "epoch": 1.3452991452991454,
      "grad_norm": 0.302607126217788,
      "learning_rate": 5e-06,
      "loss": 0.596,
      "step": 590
    },
    {
      "epoch": 1.368091168091168,
      "grad_norm": 0.35301242889924783,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 600
    },
    {
      "epoch": 1.390883190883191,
      "grad_norm": 0.31749034273101956,
      "learning_rate": 5e-06,
      "loss": 0.6017,
      "step": 610
    },
    {
      "epoch": 1.4136752136752135,
      "grad_norm": 0.29090900005500925,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 620
    },
    {
      "epoch": 1.4364672364672364,
      "grad_norm": 0.3230981583755367,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 630
    },
    {
      "epoch": 1.4592592592592593,
      "grad_norm": 0.30452581653159944,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 640
    },
    {
      "epoch": 1.4820512820512821,
      "grad_norm": 0.28276291074002474,
      "learning_rate": 5e-06,
      "loss": 0.595,
      "step": 650
    },
    {
      "epoch": 1.504843304843305,
      "grad_norm": 0.28899487629744874,
      "learning_rate": 5e-06,
      "loss": 0.5947,
      "step": 660
    },
    {
      "epoch": 1.5276353276353276,
      "grad_norm": 0.31006197973706984,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 670
    },
    {
      "epoch": 1.5504273504273505,
      "grad_norm": 0.2773422119207017,
      "learning_rate": 5e-06,
      "loss": 0.5909,
      "step": 680
    },
    {
      "epoch": 1.573219373219373,
      "grad_norm": 0.3260233279442085,
      "learning_rate": 5e-06,
      "loss": 0.5949,
      "step": 690
    },
    {
      "epoch": 1.596011396011396,
      "grad_norm": 0.286226745789164,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 700
    },
    {
      "epoch": 1.6188034188034188,
      "grad_norm": 0.3153986303191968,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 710
    },
    {
      "epoch": 1.6415954415954417,
      "grad_norm": 0.2938729513555088,
      "learning_rate": 5e-06,
      "loss": 0.6021,
      "step": 720
    },
    {
      "epoch": 1.6643874643874645,
      "grad_norm": 0.3270476213610868,
      "learning_rate": 5e-06,
      "loss": 0.5951,
      "step": 730
    },
    {
      "epoch": 1.6871794871794872,
      "grad_norm": 0.31797472091155854,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 740
    },
    {
      "epoch": 1.7099715099715098,
      "grad_norm": 0.2979503073351899,
      "learning_rate": 5e-06,
      "loss": 0.5936,
      "step": 750
    },
    {
      "epoch": 1.7327635327635327,
      "grad_norm": 0.3108049075257714,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 760
    },
    {
      "epoch": 1.7555555555555555,
      "grad_norm": 0.2968950407300482,
      "learning_rate": 5e-06,
      "loss": 0.594,
      "step": 770
    },
    {
      "epoch": 1.7783475783475784,
      "grad_norm": 0.30859935094129987,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 780
    },
    {
      "epoch": 1.8011396011396013,
      "grad_norm": 0.298714381421679,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 790
    },
    {
      "epoch": 1.823931623931624,
      "grad_norm": 0.3118433749080113,
      "learning_rate": 5e-06,
      "loss": 0.5855,
      "step": 800
    },
    {
      "epoch": 1.8467236467236468,
      "grad_norm": 0.30813804743949663,
      "learning_rate": 5e-06,
      "loss": 0.5933,
      "step": 810
    },
    {
      "epoch": 1.8695156695156694,
      "grad_norm": 0.30314029744468807,
      "learning_rate": 5e-06,
      "loss": 0.5911,
      "step": 820
    },
    {
      "epoch": 1.8923076923076922,
      "grad_norm": 0.31527652107320625,
      "learning_rate": 5e-06,
      "loss": 0.5949,
      "step": 830
    },
    {
      "epoch": 1.915099715099715,
      "grad_norm": 0.3081685579770928,
      "learning_rate": 5e-06,
      "loss": 0.5994,
      "step": 840
    },
    {
      "epoch": 1.937891737891738,
      "grad_norm": 0.2995476381118034,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 850
    },
    {
      "epoch": 1.9606837606837608,
      "grad_norm": 0.31295233104229314,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 860
    },
    {
      "epoch": 1.9834757834757835,
      "grad_norm": 0.3510224266753675,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 870
    },
    {
      "epoch": 1.9994301994301993,
      "eval_loss": 0.6187628507614136,
      "eval_runtime": 441.2477,
      "eval_samples_per_second": 26.794,
      "eval_steps_per_second": 0.419,
      "step": 877
    },
    {
      "epoch": 2.006837606837607,
      "grad_norm": 0.33060625279185024,
      "learning_rate": 5e-06,
      "loss": 0.6158,
      "step": 880
    },
    {
      "epoch": 2.0296296296296297,
      "grad_norm": 0.3447465673092643,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 890
    },
    {
      "epoch": 2.0524216524216525,
      "grad_norm": 0.3133891981560779,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 900
    },
    {
      "epoch": 2.0752136752136754,
      "grad_norm": 0.3566939142346203,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 910
    },
    {
      "epoch": 2.098005698005698,
      "grad_norm": 0.310548330800546,
      "learning_rate": 5e-06,
      "loss": 0.5717,
      "step": 920
    },
    {
      "epoch": 2.1207977207977207,
      "grad_norm": 0.2833781425363,
      "learning_rate": 5e-06,
      "loss": 0.5697,
      "step": 930
    },
    {
      "epoch": 2.1435897435897435,
      "grad_norm": 0.30929189545644564,
      "learning_rate": 5e-06,
      "loss": 0.5644,
      "step": 940
    },
    {
      "epoch": 2.1663817663817664,
      "grad_norm": 0.3084436450920294,
      "learning_rate": 5e-06,
      "loss": 0.5653,
      "step": 950
    },
    {
      "epoch": 2.1891737891737892,
      "grad_norm": 0.311190729300869,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 960
    },
    {
      "epoch": 2.211965811965812,
      "grad_norm": 0.2864766414758856,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 970
    },
    {
      "epoch": 2.234757834757835,
      "grad_norm": 0.28816757429184325,
      "learning_rate": 5e-06,
      "loss": 0.5594,
      "step": 980
    },
    {
      "epoch": 2.2575498575498574,
      "grad_norm": 0.31782536112064647,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 990
    },
    {
      "epoch": 2.2803418803418802,
      "grad_norm": 0.3101952072571342,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1000
    },
    {
      "epoch": 2.303133903133903,
      "grad_norm": 0.30738435771995715,
      "learning_rate": 5e-06,
      "loss": 0.5662,
      "step": 1010
    },
    {
      "epoch": 2.325925925925926,
      "grad_norm": 0.310152399502094,
      "learning_rate": 5e-06,
      "loss": 0.5693,
      "step": 1020
    },
    {
      "epoch": 2.348717948717949,
      "grad_norm": 0.34153029167785237,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 1030
    },
    {
      "epoch": 2.3715099715099717,
      "grad_norm": 0.29765146909204804,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 1040
    },
    {
      "epoch": 2.394301994301994,
      "grad_norm": 0.30506762266757326,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 1050
    },
    {
      "epoch": 2.417094017094017,
      "grad_norm": 0.29637636034766673,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 1060
    },
    {
      "epoch": 2.43988603988604,
      "grad_norm": 0.2984918006391642,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 1070
    },
    {
      "epoch": 2.4626780626780627,
      "grad_norm": 0.30268194590641667,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 1080
    },
    {
      "epoch": 2.4854700854700855,
      "grad_norm": 0.2958595594526694,
      "learning_rate": 5e-06,
      "loss": 0.5719,
      "step": 1090
    },
    {
      "epoch": 2.5082621082621084,
      "grad_norm": 0.31328789411658664,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 1100
    },
    {
      "epoch": 2.5310541310541312,
      "grad_norm": 0.3040490252707385,
      "learning_rate": 5e-06,
      "loss": 0.5719,
      "step": 1110
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.30808279073139194,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1120
    },
    {
      "epoch": 2.5766381766381765,
      "grad_norm": 0.31190290568204354,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1130
    },
    {
      "epoch": 2.5994301994301994,
      "grad_norm": 0.30785461816229887,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 1140
    },
    {
      "epoch": 2.6222222222222222,
      "grad_norm": 0.30589194901590094,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 1150
    },
    {
      "epoch": 2.645014245014245,
      "grad_norm": 0.30593139108420453,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 1160
    },
    {
      "epoch": 2.667806267806268,
      "grad_norm": 0.29399109219548114,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 1170
    },
    {
      "epoch": 2.690598290598291,
      "grad_norm": 0.28833283350484235,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1180
    },
    {
      "epoch": 2.7133903133903132,
      "grad_norm": 0.28358730946445676,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1190
    },
    {
      "epoch": 2.736182336182336,
      "grad_norm": 0.28840371071399123,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 1200
    },
    {
      "epoch": 2.758974358974359,
      "grad_norm": 0.28927598215120964,
      "learning_rate": 5e-06,
      "loss": 0.5761,
      "step": 1210
    },
    {
      "epoch": 2.781766381766382,
      "grad_norm": 0.28683752383155636,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 1220
    },
    {
      "epoch": 2.8045584045584047,
      "grad_norm": 0.2988773089548435,
      "learning_rate": 5e-06,
      "loss": 0.5645,
      "step": 1230
    },
    {
      "epoch": 2.827350427350427,
      "grad_norm": 0.30905358446493314,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 1240
    },
    {
      "epoch": 2.8501424501424504,
      "grad_norm": 0.30620875678895276,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 1250
    },
    {
      "epoch": 2.872934472934473,
      "grad_norm": 0.29859424875643514,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 1260
    },
    {
      "epoch": 2.8957264957264957,
      "grad_norm": 0.30362090983740225,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 1270
    },
    {
      "epoch": 2.9185185185185185,
      "grad_norm": 0.28737725892530547,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 1280
    },
    {
      "epoch": 2.9413105413105414,
      "grad_norm": 0.3042755750611846,
      "learning_rate": 5e-06,
      "loss": 0.5644,
      "step": 1290
    },
    {
      "epoch": 2.9641025641025642,
      "grad_norm": 0.35301875218810747,
      "learning_rate": 5e-06,
      "loss": 0.5656,
      "step": 1300
    },
    {
      "epoch": 2.9868945868945866,
      "grad_norm": 0.30508009821216026,
      "learning_rate": 5e-06,
      "loss": 0.5754,
      "step": 1310
    },
    {
      "epoch": 2.996011396011396,
      "eval_loss": 0.6186878681182861,
      "eval_runtime": 441.3496,
      "eval_samples_per_second": 26.788,
      "eval_steps_per_second": 0.419,
      "step": 1314
    },
    {
      "epoch": 2.996011396011396,
      "step": 1314,
      "total_flos": 2755219238682624.0,
      "train_loss": 0.604226290363155,
      "train_runtime": 70285.441,
      "train_samples_per_second": 9.587,
      "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
}