{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.994871794871795,
  "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": 1.1033914624737764,
      "learning_rate": 5e-06,
      "loss": 0.7542,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8109410851769083,
      "learning_rate": 5e-06,
      "loss": 0.6985,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9099103982412959,
      "learning_rate": 5e-06,
      "loss": 0.6794,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8632459550210195,
      "learning_rate": 5e-06,
      "loss": 0.6793,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8040080224312661,
      "learning_rate": 5e-06,
      "loss": 0.6753,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.6847089213391986,
      "learning_rate": 5e-06,
      "loss": 0.6552,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.45196884230741763,
      "learning_rate": 5e-06,
      "loss": 0.6526,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.3817215592919749,
      "learning_rate": 5e-06,
      "loss": 0.6556,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.3174029370460777,
      "learning_rate": 5e-06,
      "loss": 0.6397,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.2992638702114845,
      "learning_rate": 5e-06,
      "loss": 0.6413,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.34013151274064657,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.30697913906117164,
      "learning_rate": 5e-06,
      "loss": 0.641,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2909370326302584,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.30412386444661677,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.3110154017381052,
      "learning_rate": 5e-06,
      "loss": 0.6369,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.31300399265594936,
      "learning_rate": 5e-06,
      "loss": 0.6422,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.35115445201645934,
      "learning_rate": 5e-06,
      "loss": 0.6333,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3041234924931737,
      "learning_rate": 5e-06,
      "loss": 0.6394,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.3021535754436785,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.30656102957502734,
      "learning_rate": 5e-06,
      "loss": 0.6397,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3093236757195106,
      "learning_rate": 5e-06,
      "loss": 0.6356,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.30107361439307173,
      "learning_rate": 5e-06,
      "loss": 0.6397,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.32244066748703176,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.29846949002474976,
      "learning_rate": 5e-06,
      "loss": 0.6311,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3416572206471786,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3017135263081706,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.31052333804446103,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.31828200693862163,
      "learning_rate": 5e-06,
      "loss": 0.6427,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3248859723692002,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.28841906467504097,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.29508219339863506,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.34059354046579493,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3029847609341353,
      "learning_rate": 5e-06,
      "loss": 0.626,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.324884962509171,
      "learning_rate": 5e-06,
      "loss": 0.6319,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3352508237129559,
      "learning_rate": 5e-06,
      "loss": 0.6392,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.31913479062577094,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.32757703330826826,
      "learning_rate": 5e-06,
      "loss": 0.6245,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.3151162100561751,
      "learning_rate": 5e-06,
      "loss": 0.6366,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3324106910935759,
      "learning_rate": 5e-06,
      "loss": 0.6353,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.29744890905748256,
      "learning_rate": 5e-06,
      "loss": 0.6387,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.28840382234732076,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.3038895701446677,
      "learning_rate": 5e-06,
      "loss": 0.6216,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3493874620191421,
      "learning_rate": 5e-06,
      "loss": 0.6343,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251364946365356,
      "eval_runtime": 223.3052,
      "eval_samples_per_second": 52.945,
      "eval_steps_per_second": 0.416,
      "step": 438
    },
    {
      "epoch": 1.002849002849003,
      "grad_norm": 0.34535972946942295,
      "learning_rate": 5e-06,
      "loss": 0.6298,
      "step": 440
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.30479869272169213,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 450
    },
    {
      "epoch": 1.0484330484330484,
      "grad_norm": 0.3121837337568202,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 460
    },
    {
      "epoch": 1.0712250712250713,
      "grad_norm": 0.29987266391596784,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 470
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.31746780575952666,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 480
    },
    {
      "epoch": 1.1168091168091168,
      "grad_norm": 0.31887714949895496,
      "learning_rate": 5e-06,
      "loss": 0.6084,
      "step": 490
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 0.29532452458842373,
      "learning_rate": 5e-06,
      "loss": 0.5987,
      "step": 500
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.3227831362354891,
      "learning_rate": 5e-06,
      "loss": 0.5967,
      "step": 510
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.29762592061155374,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 520
    },
    {
      "epoch": 1.207977207977208,
      "grad_norm": 0.29744921428488813,
      "learning_rate": 5e-06,
      "loss": 0.5972,
      "step": 530
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.2920128555886255,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 540
    },
    {
      "epoch": 1.2535612535612537,
      "grad_norm": 0.3422984487396355,
      "learning_rate": 5e-06,
      "loss": 0.604,
      "step": 550
    },
    {
      "epoch": 1.2763532763532763,
      "grad_norm": 0.31836433327660996,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 560
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.2958082568198381,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 570
    },
    {
      "epoch": 1.3219373219373218,
      "grad_norm": 0.28078849345776447,
      "learning_rate": 5e-06,
      "loss": 0.5984,
      "step": 580
    },
    {
      "epoch": 1.3447293447293447,
      "grad_norm": 0.27722520490196495,
      "learning_rate": 5e-06,
      "loss": 0.5946,
      "step": 590
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.33937248699113803,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 600
    },
    {
      "epoch": 1.3903133903133904,
      "grad_norm": 0.3406201022178343,
      "learning_rate": 5e-06,
      "loss": 0.6,
      "step": 610
    },
    {
      "epoch": 1.413105413105413,
      "grad_norm": 0.2979885935949769,
      "learning_rate": 5e-06,
      "loss": 0.6048,
      "step": 620
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.3119095131251995,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 630
    },
    {
      "epoch": 1.4586894586894588,
      "grad_norm": 0.32324357639033324,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 640
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.29894937890501483,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 650
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.30003636200257305,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 660
    },
    {
      "epoch": 1.5270655270655271,
      "grad_norm": 0.3244389807270533,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 670
    },
    {
      "epoch": 1.54985754985755,
      "grad_norm": 0.29300046505226857,
      "learning_rate": 5e-06,
      "loss": 0.5924,
      "step": 680
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.3156738383272548,
      "learning_rate": 5e-06,
      "loss": 0.5932,
      "step": 690
    },
    {
      "epoch": 1.5954415954415955,
      "grad_norm": 0.28713248191141744,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 700
    },
    {
      "epoch": 1.618233618233618,
      "grad_norm": 0.30382731484622355,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 710
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.28385550641960644,
      "learning_rate": 5e-06,
      "loss": 0.6005,
      "step": 720
    },
    {
      "epoch": 1.6638176638176638,
      "grad_norm": 0.3505820455231031,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 730
    },
    {
      "epoch": 1.6866096866096867,
      "grad_norm": 0.34170389369319654,
      "learning_rate": 5e-06,
      "loss": 0.594,
      "step": 740
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.31165507992721014,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 750
    },
    {
      "epoch": 1.7321937321937322,
      "grad_norm": 0.29832556034740665,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 760
    },
    {
      "epoch": 1.7549857549857548,
      "grad_norm": 0.2978471037988754,
      "learning_rate": 5e-06,
      "loss": 0.593,
      "step": 770
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.31393055297749334,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 780
    },
    {
      "epoch": 1.8005698005698005,
      "grad_norm": 0.32909754586610496,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 790
    },
    {
      "epoch": 1.8233618233618234,
      "grad_norm": 0.322397270555009,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 800
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.3197492700237961,
      "learning_rate": 5e-06,
      "loss": 0.5904,
      "step": 810
    },
    {
      "epoch": 1.868945868945869,
      "grad_norm": 0.3170108310118261,
      "learning_rate": 5e-06,
      "loss": 0.5917,
      "step": 820
    },
    {
      "epoch": 1.8917378917378918,
      "grad_norm": 0.3123933799909585,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 830
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.3113696917480836,
      "learning_rate": 5e-06,
      "loss": 0.5989,
      "step": 840
    },
    {
      "epoch": 1.9373219373219372,
      "grad_norm": 0.295210894230663,
      "learning_rate": 5e-06,
      "loss": 0.5991,
      "step": 850
    },
    {
      "epoch": 1.96011396011396,
      "grad_norm": 0.30943331052296386,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 860
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.34554439142729454,
      "learning_rate": 5e-06,
      "loss": 0.5965,
      "step": 870
    },
    {
      "epoch": 1.998860398860399,
      "eval_loss": 0.6186895370483398,
      "eval_runtime": 224.1246,
      "eval_samples_per_second": 52.752,
      "eval_steps_per_second": 0.415,
      "step": 877
    },
    {
      "epoch": 2.005698005698006,
      "grad_norm": 0.31272607383473366,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 880
    },
    {
      "epoch": 2.0284900284900287,
      "grad_norm": 0.3135753595574758,
      "learning_rate": 5e-06,
      "loss": 0.5544,
      "step": 890
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.3094857106253417,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 900
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.3743742081337389,
      "learning_rate": 5e-06,
      "loss": 0.5678,
      "step": 910
    },
    {
      "epoch": 2.096866096866097,
      "grad_norm": 0.34841540648401936,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 920
    },
    {
      "epoch": 2.1196581196581197,
      "grad_norm": 0.3074293501432147,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 930
    },
    {
      "epoch": 2.1424501424501425,
      "grad_norm": 0.3104625446793507,
      "learning_rate": 5e-06,
      "loss": 0.5649,
      "step": 940
    },
    {
      "epoch": 2.1652421652421654,
      "grad_norm": 0.3123288977589249,
      "learning_rate": 5e-06,
      "loss": 0.5636,
      "step": 950
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": 0.32836933158774917,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 960
    },
    {
      "epoch": 2.2108262108262107,
      "grad_norm": 0.30395496162985497,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 970
    },
    {
      "epoch": 2.2336182336182335,
      "grad_norm": 0.29300746219719775,
      "learning_rate": 5e-06,
      "loss": 0.5614,
      "step": 980
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.29527508312660505,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 990
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 0.3222823880258991,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1000
    },
    {
      "epoch": 2.301994301994302,
      "grad_norm": 0.2917311227225537,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 1010
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": 0.31720685904442264,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1020
    },
    {
      "epoch": 2.347578347578348,
      "grad_norm": 0.2993496445056371,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 1030
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3132874137273585,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 1040
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.315726711758899,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 1050
    },
    {
      "epoch": 2.415954415954416,
      "grad_norm": 0.3081548858355199,
      "learning_rate": 5e-06,
      "loss": 0.5773,
      "step": 1060
    },
    {
      "epoch": 2.438746438746439,
      "grad_norm": 0.34328340430638526,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 1070
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.29714127385974715,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 1080
    },
    {
      "epoch": 2.484330484330484,
      "grad_norm": 0.3104851780704826,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 1090
    },
    {
      "epoch": 2.5071225071225074,
      "grad_norm": 0.3208530041548371,
      "learning_rate": 5e-06,
      "loss": 0.5769,
      "step": 1100
    },
    {
      "epoch": 2.52991452991453,
      "grad_norm": 0.31062902083321725,
      "learning_rate": 5e-06,
      "loss": 0.5715,
      "step": 1110
    },
    {
      "epoch": 2.5527065527065527,
      "grad_norm": 0.2969529598571343,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 1120
    },
    {
      "epoch": 2.5754985754985755,
      "grad_norm": 0.32119534061079474,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 1130
    },
    {
      "epoch": 2.5982905982905984,
      "grad_norm": 0.29615484147828297,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 1140
    },
    {
      "epoch": 2.6210826210826212,
      "grad_norm": 0.3117380264013822,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 1150
    },
    {
      "epoch": 2.6438746438746437,
      "grad_norm": 0.303784243937995,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 1160
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.2816510193986804,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 1170
    },
    {
      "epoch": 2.6894586894586894,
      "grad_norm": 0.2875088612895932,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 1180
    },
    {
      "epoch": 2.7122507122507122,
      "grad_norm": 0.3265587231682108,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 1190
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 0.2925264885291982,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 1200
    },
    {
      "epoch": 2.757834757834758,
      "grad_norm": 0.2864024942446623,
      "learning_rate": 5e-06,
      "loss": 0.5769,
      "step": 1210
    },
    {
      "epoch": 2.780626780626781,
      "grad_norm": 0.2878189141825426,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 1220
    },
    {
      "epoch": 2.8034188034188032,
      "grad_norm": 0.29884382033363066,
      "learning_rate": 5e-06,
      "loss": 0.5652,
      "step": 1230
    },
    {
      "epoch": 2.826210826210826,
      "grad_norm": 0.29771685019095506,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 1240
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 0.288191949538963,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 1250
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.29630604062948845,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1260
    },
    {
      "epoch": 2.8945868945868947,
      "grad_norm": 0.3167527218428604,
      "learning_rate": 5e-06,
      "loss": 0.5761,
      "step": 1270
    },
    {
      "epoch": 2.9173789173789175,
      "grad_norm": 0.2930409848783378,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 1280
    },
    {
      "epoch": 2.9401709401709404,
      "grad_norm": 0.3104086812639866,
      "learning_rate": 5e-06,
      "loss": 0.5648,
      "step": 1290
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.31068196559240563,
      "learning_rate": 5e-06,
      "loss": 0.5653,
      "step": 1300
    },
    {
      "epoch": 2.9857549857549857,
      "grad_norm": 0.31625089007416696,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 1310
    },
    {
      "epoch": 2.994871794871795,
      "eval_loss": 0.6186508536338806,
      "eval_runtime": 223.7691,
      "eval_samples_per_second": 52.836,
      "eval_steps_per_second": 0.416,
      "step": 1314
    },
    {
      "epoch": 2.994871794871795,
      "step": 1314,
      "total_flos": 2754957111459840.0,
      "train_loss": 0.6040742007201847,
      "train_runtime": 35825.9134,
      "train_samples_per_second": 18.809,
      "train_steps_per_second": 0.037
    }
  ],
  "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": 2754957111459840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}