{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9984810126582278,
  "eval_steps": 500,
  "global_step": 2961,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010126582278481013,
      "grad_norm": 2.9319232619463147,
      "learning_rate": 5e-06,
      "loss": 0.754,
      "step": 10
    },
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 2.3527842138237443,
      "learning_rate": 5e-06,
      "loss": 0.6565,
      "step": 20
    },
    {
      "epoch": 0.030379746835443037,
      "grad_norm": 2.218097297827581,
      "learning_rate": 5e-06,
      "loss": 0.6343,
      "step": 30
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 1.728885416020883,
      "learning_rate": 5e-06,
      "loss": 0.6266,
      "step": 40
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 1.7600150721761239,
      "learning_rate": 5e-06,
      "loss": 0.6225,
      "step": 50
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.036486573113631,
      "learning_rate": 5e-06,
      "loss": 0.6185,
      "step": 60
    },
    {
      "epoch": 0.07088607594936709,
      "grad_norm": 1.8472990337897077,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 70
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 2.0268825324116926,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 80
    },
    {
      "epoch": 0.09113924050632911,
      "grad_norm": 1.7502041363801772,
      "learning_rate": 5e-06,
      "loss": 0.6063,
      "step": 90
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 1.7706135514845762,
      "learning_rate": 5e-06,
      "loss": 0.5954,
      "step": 100
    },
    {
      "epoch": 0.11139240506329114,
      "grad_norm": 1.6647485123629138,
      "learning_rate": 5e-06,
      "loss": 0.5933,
      "step": 110
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 2.299944971561371,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 120
    },
    {
      "epoch": 0.13164556962025317,
      "grad_norm": 1.4323042297049071,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 130
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.5735470897186044,
      "learning_rate": 5e-06,
      "loss": 0.5859,
      "step": 140
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 1.4396445107803788,
      "learning_rate": 5e-06,
      "loss": 0.5833,
      "step": 150
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.6048875360767698,
      "learning_rate": 5e-06,
      "loss": 0.5926,
      "step": 160
    },
    {
      "epoch": 0.17215189873417722,
      "grad_norm": 1.7629611019629856,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 170
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.692513854306383,
      "learning_rate": 5e-06,
      "loss": 0.5875,
      "step": 180
    },
    {
      "epoch": 0.19240506329113924,
      "grad_norm": 2.4645583630800614,
      "learning_rate": 5e-06,
      "loss": 0.5908,
      "step": 190
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 1.6304964629686653,
      "learning_rate": 5e-06,
      "loss": 0.5887,
      "step": 200
    },
    {
      "epoch": 0.21265822784810126,
      "grad_norm": 2.117270092101592,
      "learning_rate": 5e-06,
      "loss": 0.5872,
      "step": 210
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.5677168838868496,
      "learning_rate": 5e-06,
      "loss": 0.575,
      "step": 220
    },
    {
      "epoch": 0.23291139240506328,
      "grad_norm": 1.6515647911636342,
      "learning_rate": 5e-06,
      "loss": 0.5747,
      "step": 230
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.4834458457301771,
      "learning_rate": 5e-06,
      "loss": 0.5834,
      "step": 240
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 2.090691823913493,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 250
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 1.4520944372541345,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 260
    },
    {
      "epoch": 0.27341772151898736,
      "grad_norm": 1.7905780272726646,
      "learning_rate": 5e-06,
      "loss": 0.5637,
      "step": 270
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.6753642665165924,
      "learning_rate": 5e-06,
      "loss": 0.5745,
      "step": 280
    },
    {
      "epoch": 0.2936708860759494,
      "grad_norm": 1.8117100564747939,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 290
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.5160896257954382,
      "learning_rate": 5e-06,
      "loss": 0.5821,
      "step": 300
    },
    {
      "epoch": 0.3139240506329114,
      "grad_norm": 1.5338602444115943,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 310
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.5768816348730115,
      "learning_rate": 5e-06,
      "loss": 0.5831,
      "step": 320
    },
    {
      "epoch": 0.3341772151898734,
      "grad_norm": 1.5251244093370149,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 330
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.5422210280401378,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 340
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 1.4422891794630028,
      "learning_rate": 5e-06,
      "loss": 0.5794,
      "step": 350
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.778098375508798,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 360
    },
    {
      "epoch": 0.37468354430379747,
      "grad_norm": 1.4276847831429058,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 370
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.8350692685441172,
      "learning_rate": 5e-06,
      "loss": 0.5742,
      "step": 380
    },
    {
      "epoch": 0.3949367088607595,
      "grad_norm": 1.6654466906631886,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 390
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.5625914451532021,
      "learning_rate": 5e-06,
      "loss": 0.5688,
      "step": 400
    },
    {
      "epoch": 0.4151898734177215,
      "grad_norm": 1.5962831101550994,
      "learning_rate": 5e-06,
      "loss": 0.5567,
      "step": 410
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.4805817323596187,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 420
    },
    {
      "epoch": 0.43544303797468353,
      "grad_norm": 1.4164796466458769,
      "learning_rate": 5e-06,
      "loss": 0.5712,
      "step": 430
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.5450127362729664,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 440
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 1.6570421627781717,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 450
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.623306340780734,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 460
    },
    {
      "epoch": 0.4759493670886076,
      "grad_norm": 1.747763610168544,
      "learning_rate": 5e-06,
      "loss": 0.5609,
      "step": 470
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.295527401866004,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 480
    },
    {
      "epoch": 0.4962025316455696,
      "grad_norm": 1.3529876566902441,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 490
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.4541590535564763,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 500
    },
    {
      "epoch": 0.5164556962025316,
      "grad_norm": 1.5391153152763637,
      "learning_rate": 5e-06,
      "loss": 0.5598,
      "step": 510
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.3816263219270335,
      "learning_rate": 5e-06,
      "loss": 0.552,
      "step": 520
    },
    {
      "epoch": 0.5367088607594936,
      "grad_norm": 1.407148137331511,
      "learning_rate": 5e-06,
      "loss": 0.561,
      "step": 530
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.4939662242734717,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 540
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 1.4769024813528058,
      "learning_rate": 5e-06,
      "loss": 0.5628,
      "step": 550
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.5234796484078978,
      "learning_rate": 5e-06,
      "loss": 0.5571,
      "step": 560
    },
    {
      "epoch": 0.5772151898734177,
      "grad_norm": 1.38748512162588,
      "learning_rate": 5e-06,
      "loss": 0.5588,
      "step": 570
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.6616670500045834,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 580
    },
    {
      "epoch": 0.5974683544303797,
      "grad_norm": 1.3613770956091802,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 590
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.9645875965732293,
      "learning_rate": 5e-06,
      "loss": 0.5614,
      "step": 600
    },
    {
      "epoch": 0.6177215189873417,
      "grad_norm": 1.3122962556953037,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 610
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.5024516266743335,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 620
    },
    {
      "epoch": 0.6379746835443038,
      "grad_norm": 1.3599801460050238,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 630
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.3697118174446543,
      "learning_rate": 5e-06,
      "loss": 0.5567,
      "step": 640
    },
    {
      "epoch": 0.6582278481012658,
      "grad_norm": 1.447467777446668,
      "learning_rate": 5e-06,
      "loss": 0.5614,
      "step": 650
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.4332946464750023,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 660
    },
    {
      "epoch": 0.6784810126582278,
      "grad_norm": 1.4245518863907969,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 670
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.392960913673911,
      "learning_rate": 5e-06,
      "loss": 0.5631,
      "step": 680
    },
    {
      "epoch": 0.6987341772151898,
      "grad_norm": 1.3851040024314174,
      "learning_rate": 5e-06,
      "loss": 0.5547,
      "step": 690
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.5665731498555628,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 700
    },
    {
      "epoch": 0.7189873417721518,
      "grad_norm": 1.3541133459928674,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 710
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.3050422174455243,
      "learning_rate": 5e-06,
      "loss": 0.5649,
      "step": 720
    },
    {
      "epoch": 0.739240506329114,
      "grad_norm": 1.4474203168962876,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 730
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.2849691486389958,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 740
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 1.4374182399089128,
      "learning_rate": 5e-06,
      "loss": 0.5485,
      "step": 750
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.2784166011759992,
      "learning_rate": 5e-06,
      "loss": 0.5619,
      "step": 760
    },
    {
      "epoch": 0.779746835443038,
      "grad_norm": 1.338741085455322,
      "learning_rate": 5e-06,
      "loss": 0.5625,
      "step": 770
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.3830345955439087,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 780
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.2560229071250701,
      "learning_rate": 5e-06,
      "loss": 0.557,
      "step": 790
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.3094948207554686,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 800
    },
    {
      "epoch": 0.8202531645569621,
      "grad_norm": 1.2980406537156193,
      "learning_rate": 5e-06,
      "loss": 0.5435,
      "step": 810
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.3336678028790407,
      "learning_rate": 5e-06,
      "loss": 0.5644,
      "step": 820
    },
    {
      "epoch": 0.8405063291139241,
      "grad_norm": 1.4362113888678505,
      "learning_rate": 5e-06,
      "loss": 0.5615,
      "step": 830
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.5496595209680522,
      "learning_rate": 5e-06,
      "loss": 0.5619,
      "step": 840
    },
    {
      "epoch": 0.8607594936708861,
      "grad_norm": 1.4648845925364151,
      "learning_rate": 5e-06,
      "loss": 0.5556,
      "step": 850
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.3830147030582034,
      "learning_rate": 5e-06,
      "loss": 0.5534,
      "step": 860
    },
    {
      "epoch": 0.8810126582278481,
      "grad_norm": 1.3802375047462647,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 870
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.665356350061181,
      "learning_rate": 5e-06,
      "loss": 0.5542,
      "step": 880
    },
    {
      "epoch": 0.9012658227848102,
      "grad_norm": 1.5275969827966436,
      "learning_rate": 5e-06,
      "loss": 0.5492,
      "step": 890
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.5257937868842386,
      "learning_rate": 5e-06,
      "loss": 0.5509,
      "step": 900
    },
    {
      "epoch": 0.9215189873417722,
      "grad_norm": 1.3059469433496236,
      "learning_rate": 5e-06,
      "loss": 0.5563,
      "step": 910
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.3687394115237168,
      "learning_rate": 5e-06,
      "loss": 0.5527,
      "step": 920
    },
    {
      "epoch": 0.9417721518987342,
      "grad_norm": 1.3468586235595001,
      "learning_rate": 5e-06,
      "loss": 0.5594,
      "step": 930
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.4377274430310882,
      "learning_rate": 5e-06,
      "loss": 0.5512,
      "step": 940
    },
    {
      "epoch": 0.9620253164556962,
      "grad_norm": 1.2680685522134791,
      "learning_rate": 5e-06,
      "loss": 0.5486,
      "step": 950
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.2807954706357672,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 960
    },
    {
      "epoch": 0.9822784810126582,
      "grad_norm": 1.3423829666439555,
      "learning_rate": 5e-06,
      "loss": 0.5485,
      "step": 970
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.4283880670670543,
      "learning_rate": 5e-06,
      "loss": 0.5515,
      "step": 980
    },
    {
      "epoch": 0.999493670886076,
      "eval_loss": 0.13834980130195618,
      "eval_runtime": 507.9163,
      "eval_samples_per_second": 26.193,
      "eval_steps_per_second": 0.41,
      "step": 987
    },
    {
      "epoch": 1.0025316455696203,
      "grad_norm": 1.6161728864680243,
      "learning_rate": 5e-06,
      "loss": 0.5308,
      "step": 990
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.5737881952906483,
      "learning_rate": 5e-06,
      "loss": 0.4633,
      "step": 1000
    },
    {
      "epoch": 1.0227848101265822,
      "grad_norm": 1.5616941170427905,
      "learning_rate": 5e-06,
      "loss": 0.4634,
      "step": 1010
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.5346519713859017,
      "learning_rate": 5e-06,
      "loss": 0.4435,
      "step": 1020
    },
    {
      "epoch": 1.0430379746835443,
      "grad_norm": 1.3492138788127321,
      "learning_rate": 5e-06,
      "loss": 0.4503,
      "step": 1030
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.4763337790140822,
      "learning_rate": 5e-06,
      "loss": 0.4506,
      "step": 1040
    },
    {
      "epoch": 1.0632911392405062,
      "grad_norm": 1.4225225244349122,
      "learning_rate": 5e-06,
      "loss": 0.4591,
      "step": 1050
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.377686472346139,
      "learning_rate": 5e-06,
      "loss": 0.4498,
      "step": 1060
    },
    {
      "epoch": 1.0835443037974684,
      "grad_norm": 1.524899956605274,
      "learning_rate": 5e-06,
      "loss": 0.4521,
      "step": 1070
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.4555671547809872,
      "learning_rate": 5e-06,
      "loss": 0.4537,
      "step": 1080
    },
    {
      "epoch": 1.1037974683544305,
      "grad_norm": 1.352652609202294,
      "learning_rate": 5e-06,
      "loss": 0.4591,
      "step": 1090
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.389780851883711,
      "learning_rate": 5e-06,
      "loss": 0.451,
      "step": 1100
    },
    {
      "epoch": 1.1240506329113924,
      "grad_norm": 1.5493151434769157,
      "learning_rate": 5e-06,
      "loss": 0.4545,
      "step": 1110
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.4921163467682323,
      "learning_rate": 5e-06,
      "loss": 0.4511,
      "step": 1120
    },
    {
      "epoch": 1.1443037974683543,
      "grad_norm": 1.3424106662166821,
      "learning_rate": 5e-06,
      "loss": 0.4597,
      "step": 1130
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.4205445966678738,
      "learning_rate": 5e-06,
      "loss": 0.4587,
      "step": 1140
    },
    {
      "epoch": 1.1645569620253164,
      "grad_norm": 1.3812137606947525,
      "learning_rate": 5e-06,
      "loss": 0.457,
      "step": 1150
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.504094206656827,
      "learning_rate": 5e-06,
      "loss": 0.4582,
      "step": 1160
    },
    {
      "epoch": 1.1848101265822786,
      "grad_norm": 1.4384269712621547,
      "learning_rate": 5e-06,
      "loss": 0.4478,
      "step": 1170
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.4604436825013358,
      "learning_rate": 5e-06,
      "loss": 0.4561,
      "step": 1180
    },
    {
      "epoch": 1.2050632911392405,
      "grad_norm": 1.484357252258588,
      "learning_rate": 5e-06,
      "loss": 0.463,
      "step": 1190
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.3507024353159274,
      "learning_rate": 5e-06,
      "loss": 0.4557,
      "step": 1200
    },
    {
      "epoch": 1.2253164556962026,
      "grad_norm": 1.5356768758566504,
      "learning_rate": 5e-06,
      "loss": 0.4616,
      "step": 1210
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.507777364560312,
      "learning_rate": 5e-06,
      "loss": 0.4492,
      "step": 1220
    },
    {
      "epoch": 1.2455696202531645,
      "grad_norm": 1.402742621286163,
      "learning_rate": 5e-06,
      "loss": 0.4623,
      "step": 1230
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.4914361590080172,
      "learning_rate": 5e-06,
      "loss": 0.4576,
      "step": 1240
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 1.4449809880641054,
      "learning_rate": 5e-06,
      "loss": 0.4581,
      "step": 1250
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.401311614162818,
      "learning_rate": 5e-06,
      "loss": 0.4613,
      "step": 1260
    },
    {
      "epoch": 1.2860759493670886,
      "grad_norm": 1.4035116916924748,
      "learning_rate": 5e-06,
      "loss": 0.4546,
      "step": 1270
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.5360414127344846,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 1280
    },
    {
      "epoch": 1.3063291139240507,
      "grad_norm": 1.4721064580495236,
      "learning_rate": 5e-06,
      "loss": 0.4605,
      "step": 1290
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 1.5018662441760837,
      "learning_rate": 5e-06,
      "loss": 0.4656,
      "step": 1300
    },
    {
      "epoch": 1.3265822784810126,
      "grad_norm": 1.4057750381381058,
      "learning_rate": 5e-06,
      "loss": 0.4546,
      "step": 1310
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.472547127671551,
      "learning_rate": 5e-06,
      "loss": 0.4509,
      "step": 1320
    },
    {
      "epoch": 1.3468354430379748,
      "grad_norm": 1.378222631334251,
      "learning_rate": 5e-06,
      "loss": 0.4592,
      "step": 1330
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.477645235480499,
      "learning_rate": 5e-06,
      "loss": 0.4731,
      "step": 1340
    },
    {
      "epoch": 1.3670886075949367,
      "grad_norm": 1.4190131074856087,
      "learning_rate": 5e-06,
      "loss": 0.4614,
      "step": 1350
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.598773468818255,
      "learning_rate": 5e-06,
      "loss": 0.4642,
      "step": 1360
    },
    {
      "epoch": 1.3873417721518988,
      "grad_norm": 1.401701470107724,
      "learning_rate": 5e-06,
      "loss": 0.4599,
      "step": 1370
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.5834771319486265,
      "learning_rate": 5e-06,
      "loss": 0.4635,
      "step": 1380
    },
    {
      "epoch": 1.4075949367088607,
      "grad_norm": 1.398082340799174,
      "learning_rate": 5e-06,
      "loss": 0.4581,
      "step": 1390
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.4006340071029044,
      "learning_rate": 5e-06,
      "loss": 0.4602,
      "step": 1400
    },
    {
      "epoch": 1.4278481012658228,
      "grad_norm": 1.3336328229398797,
      "learning_rate": 5e-06,
      "loss": 0.4602,
      "step": 1410
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.3492817883075563,
      "learning_rate": 5e-06,
      "loss": 0.4687,
      "step": 1420
    },
    {
      "epoch": 1.4481012658227848,
      "grad_norm": 1.342687219512621,
      "learning_rate": 5e-06,
      "loss": 0.4651,
      "step": 1430
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.4950318280118493,
      "learning_rate": 5e-06,
      "loss": 0.4643,
      "step": 1440
    },
    {
      "epoch": 1.4683544303797469,
      "grad_norm": 1.5341419482481558,
      "learning_rate": 5e-06,
      "loss": 0.467,
      "step": 1450
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.3873503711966886,
      "learning_rate": 5e-06,
      "loss": 0.4692,
      "step": 1460
    },
    {
      "epoch": 1.4886075949367088,
      "grad_norm": 1.3838670814377412,
      "learning_rate": 5e-06,
      "loss": 0.4606,
      "step": 1470
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.435159074036311,
      "learning_rate": 5e-06,
      "loss": 0.4607,
      "step": 1480
    },
    {
      "epoch": 1.508860759493671,
      "grad_norm": 1.416449038632833,
      "learning_rate": 5e-06,
      "loss": 0.4603,
      "step": 1490
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.349053423409347,
      "learning_rate": 5e-06,
      "loss": 0.4671,
      "step": 1500
    },
    {
      "epoch": 1.529113924050633,
      "grad_norm": 1.5418750945784405,
      "learning_rate": 5e-06,
      "loss": 0.4642,
      "step": 1510
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.5350888472278188,
      "learning_rate": 5e-06,
      "loss": 0.4654,
      "step": 1520
    },
    {
      "epoch": 1.549367088607595,
      "grad_norm": 1.5918459039624637,
      "learning_rate": 5e-06,
      "loss": 0.4623,
      "step": 1530
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.4044783253886717,
      "learning_rate": 5e-06,
      "loss": 0.4644,
      "step": 1540
    },
    {
      "epoch": 1.5696202531645569,
      "grad_norm": 1.4733622287724428,
      "learning_rate": 5e-06,
      "loss": 0.4699,
      "step": 1550
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.4190534275279456,
      "learning_rate": 5e-06,
      "loss": 0.4585,
      "step": 1560
    },
    {
      "epoch": 1.589873417721519,
      "grad_norm": 1.588541120324257,
      "learning_rate": 5e-06,
      "loss": 0.4674,
      "step": 1570
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4489487698353771,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 1580
    },
    {
      "epoch": 1.6101265822784812,
      "grad_norm": 1.3499923545579962,
      "learning_rate": 5e-06,
      "loss": 0.4582,
      "step": 1590
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.3640430679010667,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 1600
    },
    {
      "epoch": 1.630379746835443,
      "grad_norm": 1.3690059243296218,
      "learning_rate": 5e-06,
      "loss": 0.4612,
      "step": 1610
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.2447374210211029,
      "learning_rate": 5e-06,
      "loss": 0.4506,
      "step": 1620
    },
    {
      "epoch": 1.650632911392405,
      "grad_norm": 1.351219366349358,
      "learning_rate": 5e-06,
      "loss": 0.4611,
      "step": 1630
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.335122455907824,
      "learning_rate": 5e-06,
      "loss": 0.4699,
      "step": 1640
    },
    {
      "epoch": 1.6708860759493671,
      "grad_norm": 1.5625860035007904,
      "learning_rate": 5e-06,
      "loss": 0.4612,
      "step": 1650
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.6296205380869357,
      "learning_rate": 5e-06,
      "loss": 0.4623,
      "step": 1660
    },
    {
      "epoch": 1.6911392405063292,
      "grad_norm": 1.4330065379895607,
      "learning_rate": 5e-06,
      "loss": 0.4625,
      "step": 1670
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.3278761181861125,
      "learning_rate": 5e-06,
      "loss": 0.4627,
      "step": 1680
    },
    {
      "epoch": 1.7113924050632912,
      "grad_norm": 1.4304366765861536,
      "learning_rate": 5e-06,
      "loss": 0.4646,
      "step": 1690
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.3460103891901807,
      "learning_rate": 5e-06,
      "loss": 0.4648,
      "step": 1700
    },
    {
      "epoch": 1.731645569620253,
      "grad_norm": 1.4336438757742112,
      "learning_rate": 5e-06,
      "loss": 0.4708,
      "step": 1710
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.333163056745564,
      "learning_rate": 5e-06,
      "loss": 0.4591,
      "step": 1720
    },
    {
      "epoch": 1.7518987341772152,
      "grad_norm": 1.3819280069426765,
      "learning_rate": 5e-06,
      "loss": 0.4651,
      "step": 1730
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.413028622360716,
      "learning_rate": 5e-06,
      "loss": 0.4714,
      "step": 1740
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 1.3989242299354576,
      "learning_rate": 5e-06,
      "loss": 0.466,
      "step": 1750
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.3712554248183217,
      "learning_rate": 5e-06,
      "loss": 0.4727,
      "step": 1760
    },
    {
      "epoch": 1.7924050632911392,
      "grad_norm": 1.4780769754046013,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 1770
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.4002831190634755,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 1780
    },
    {
      "epoch": 1.8126582278481012,
      "grad_norm": 1.3944675393169206,
      "learning_rate": 5e-06,
      "loss": 0.4644,
      "step": 1790
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.4867966880006709,
      "learning_rate": 5e-06,
      "loss": 0.4675,
      "step": 1800
    },
    {
      "epoch": 1.8329113924050633,
      "grad_norm": 1.404496416486814,
      "learning_rate": 5e-06,
      "loss": 0.4624,
      "step": 1810
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.5305845929183253,
      "learning_rate": 5e-06,
      "loss": 0.4739,
      "step": 1820
    },
    {
      "epoch": 1.8531645569620254,
      "grad_norm": 1.3084464311737185,
      "learning_rate": 5e-06,
      "loss": 0.4655,
      "step": 1830
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.3059438675535409,
      "learning_rate": 5e-06,
      "loss": 0.4678,
      "step": 1840
    },
    {
      "epoch": 1.8734177215189873,
      "grad_norm": 1.3867484618996055,
      "learning_rate": 5e-06,
      "loss": 0.4609,
      "step": 1850
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.3420942943215763,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 1860
    },
    {
      "epoch": 1.8936708860759492,
      "grad_norm": 1.421266278043212,
      "learning_rate": 5e-06,
      "loss": 0.4665,
      "step": 1870
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.36634296470369,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 1880
    },
    {
      "epoch": 1.9139240506329114,
      "grad_norm": 1.2659671091408768,
      "learning_rate": 5e-06,
      "loss": 0.4669,
      "step": 1890
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.373264332933901,
      "learning_rate": 5e-06,
      "loss": 0.4701,
      "step": 1900
    },
    {
      "epoch": 1.9341772151898735,
      "grad_norm": 1.3568414058185374,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 1910
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.3940261082697252,
      "learning_rate": 5e-06,
      "loss": 0.4763,
      "step": 1920
    },
    {
      "epoch": 1.9544303797468354,
      "grad_norm": 1.3879188735035681,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 1930
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.363003506285662,
      "learning_rate": 5e-06,
      "loss": 0.4667,
      "step": 1940
    },
    {
      "epoch": 1.9746835443037973,
      "grad_norm": 1.4533412320271968,
      "learning_rate": 5e-06,
      "loss": 0.469,
      "step": 1950
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.4479310447515883,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 1960
    },
    {
      "epoch": 1.9949367088607595,
      "grad_norm": 1.2966648783230335,
      "learning_rate": 5e-06,
      "loss": 0.468,
      "step": 1970
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.1398227959871292,
      "eval_runtime": 506.8788,
      "eval_samples_per_second": 26.247,
      "eval_steps_per_second": 0.41,
      "step": 1975
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 3.06600016953371,
      "learning_rate": 5e-06,
      "loss": 0.4085,
      "step": 1980
    },
    {
      "epoch": 2.0151898734177216,
      "grad_norm": 2.0901467389116335,
      "learning_rate": 5e-06,
      "loss": 0.3545,
      "step": 1990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.7198026240231687,
      "learning_rate": 5e-06,
      "loss": 0.3486,
      "step": 2000
    },
    {
      "epoch": 2.0354430379746837,
      "grad_norm": 1.6596559930998485,
      "learning_rate": 5e-06,
      "loss": 0.3485,
      "step": 2010
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.6010412767976676,
      "learning_rate": 5e-06,
      "loss": 0.3469,
      "step": 2020
    },
    {
      "epoch": 2.0556962025316454,
      "grad_norm": 1.619456570416184,
      "learning_rate": 5e-06,
      "loss": 0.3412,
      "step": 2030
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.5477510460994646,
      "learning_rate": 5e-06,
      "loss": 0.3499,
      "step": 2040
    },
    {
      "epoch": 2.0759493670886076,
      "grad_norm": 1.6995317518377548,
      "learning_rate": 5e-06,
      "loss": 0.3431,
      "step": 2050
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.6672377260042517,
      "learning_rate": 5e-06,
      "loss": 0.3509,
      "step": 2060
    },
    {
      "epoch": 2.0962025316455697,
      "grad_norm": 1.5137523020681678,
      "learning_rate": 5e-06,
      "loss": 0.3485,
      "step": 2070
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.5728338684227074,
      "learning_rate": 5e-06,
      "loss": 0.3414,
      "step": 2080
    },
    {
      "epoch": 2.116455696202532,
      "grad_norm": 1.7215854826795536,
      "learning_rate": 5e-06,
      "loss": 0.356,
      "step": 2090
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.547269577634038,
      "learning_rate": 5e-06,
      "loss": 0.351,
      "step": 2100
    },
    {
      "epoch": 2.1367088607594935,
      "grad_norm": 1.7846477440752144,
      "learning_rate": 5e-06,
      "loss": 0.3475,
      "step": 2110
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.6766174751768645,
      "learning_rate": 5e-06,
      "loss": 0.3507,
      "step": 2120
    },
    {
      "epoch": 2.1569620253164556,
      "grad_norm": 1.6129490070505184,
      "learning_rate": 5e-06,
      "loss": 0.3544,
      "step": 2130
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.6006266055236678,
      "learning_rate": 5e-06,
      "loss": 0.3514,
      "step": 2140
    },
    {
      "epoch": 2.1772151898734178,
      "grad_norm": 1.5978325737155568,
      "learning_rate": 5e-06,
      "loss": 0.3525,
      "step": 2150
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.5951449058616392,
      "learning_rate": 5e-06,
      "loss": 0.3507,
      "step": 2160
    },
    {
      "epoch": 2.19746835443038,
      "grad_norm": 1.5513789073675182,
      "learning_rate": 5e-06,
      "loss": 0.3496,
      "step": 2170
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.5229143655144641,
      "learning_rate": 5e-06,
      "loss": 0.3494,
      "step": 2180
    },
    {
      "epoch": 2.2177215189873416,
      "grad_norm": 1.660242717310412,
      "learning_rate": 5e-06,
      "loss": 0.3553,
      "step": 2190
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.6739776038113652,
      "learning_rate": 5e-06,
      "loss": 0.3607,
      "step": 2200
    },
    {
      "epoch": 2.2379746835443037,
      "grad_norm": 1.7005249152138244,
      "learning_rate": 5e-06,
      "loss": 0.3486,
      "step": 2210
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.6489218772469403,
      "learning_rate": 5e-06,
      "loss": 0.3592,
      "step": 2220
    },
    {
      "epoch": 2.258227848101266,
      "grad_norm": 1.6209760997530658,
      "learning_rate": 5e-06,
      "loss": 0.3584,
      "step": 2230
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.6153685359109242,
      "learning_rate": 5e-06,
      "loss": 0.3554,
      "step": 2240
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 1.6268217139529644,
      "learning_rate": 5e-06,
      "loss": 0.3542,
      "step": 2250
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.7752820541706038,
      "learning_rate": 5e-06,
      "loss": 0.3621,
      "step": 2260
    },
    {
      "epoch": 2.2987341772151897,
      "grad_norm": 1.5709969247849427,
      "learning_rate": 5e-06,
      "loss": 0.3524,
      "step": 2270
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.5534897904208944,
      "learning_rate": 5e-06,
      "loss": 0.3563,
      "step": 2280
    },
    {
      "epoch": 2.318987341772152,
      "grad_norm": 1.6608945730503153,
      "learning_rate": 5e-06,
      "loss": 0.3565,
      "step": 2290
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.5801622846665264,
      "learning_rate": 5e-06,
      "loss": 0.3622,
      "step": 2300
    },
    {
      "epoch": 2.339240506329114,
      "grad_norm": 1.5320500459364543,
      "learning_rate": 5e-06,
      "loss": 0.3589,
      "step": 2310
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 1.581287461651533,
      "learning_rate": 5e-06,
      "loss": 0.3613,
      "step": 2320
    },
    {
      "epoch": 2.359493670886076,
      "grad_norm": 1.6038211850984352,
      "learning_rate": 5e-06,
      "loss": 0.3617,
      "step": 2330
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.625966530104118,
      "learning_rate": 5e-06,
      "loss": 0.3598,
      "step": 2340
    },
    {
      "epoch": 2.379746835443038,
      "grad_norm": 1.7645641137037487,
      "learning_rate": 5e-06,
      "loss": 0.362,
      "step": 2350
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.6940524616595496,
      "learning_rate": 5e-06,
      "loss": 0.361,
      "step": 2360
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.5384052283713547,
      "learning_rate": 5e-06,
      "loss": 0.3639,
      "step": 2370
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.6483060393926068,
      "learning_rate": 5e-06,
      "loss": 0.3586,
      "step": 2380
    },
    {
      "epoch": 2.420253164556962,
      "grad_norm": 1.6074760148392138,
      "learning_rate": 5e-06,
      "loss": 0.3648,
      "step": 2390
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.7080201956192906,
      "learning_rate": 5e-06,
      "loss": 0.3554,
      "step": 2400
    },
    {
      "epoch": 2.440506329113924,
      "grad_norm": 1.625757072296565,
      "learning_rate": 5e-06,
      "loss": 0.3531,
      "step": 2410
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.6544192748138193,
      "learning_rate": 5e-06,
      "loss": 0.3659,
      "step": 2420
    },
    {
      "epoch": 2.460759493670886,
      "grad_norm": 1.6016056620993897,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 2430
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.6466444516635712,
      "learning_rate": 5e-06,
      "loss": 0.3651,
      "step": 2440
    },
    {
      "epoch": 2.481012658227848,
      "grad_norm": 1.6213376274576505,
      "learning_rate": 5e-06,
      "loss": 0.3611,
      "step": 2450
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.61939669911579,
      "learning_rate": 5e-06,
      "loss": 0.3655,
      "step": 2460
    },
    {
      "epoch": 2.50126582278481,
      "grad_norm": 1.7185252999562315,
      "learning_rate": 5e-06,
      "loss": 0.3717,
      "step": 2470
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.5701430968600476,
      "learning_rate": 5e-06,
      "loss": 0.3616,
      "step": 2480
    },
    {
      "epoch": 2.5215189873417723,
      "grad_norm": 1.6525891145092144,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 2490
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.6331648861432553,
      "learning_rate": 5e-06,
      "loss": 0.3608,
      "step": 2500
    },
    {
      "epoch": 2.5417721518987344,
      "grad_norm": 1.5954836812756767,
      "learning_rate": 5e-06,
      "loss": 0.3564,
      "step": 2510
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.6221389574344411,
      "learning_rate": 5e-06,
      "loss": 0.3603,
      "step": 2520
    },
    {
      "epoch": 2.562025316455696,
      "grad_norm": 1.645557544125129,
      "learning_rate": 5e-06,
      "loss": 0.3633,
      "step": 2530
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.7704063332654312,
      "learning_rate": 5e-06,
      "loss": 0.3658,
      "step": 2540
    },
    {
      "epoch": 2.5822784810126582,
      "grad_norm": 1.6779345444764124,
      "learning_rate": 5e-06,
      "loss": 0.3706,
      "step": 2550
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.6024752118154975,
      "learning_rate": 5e-06,
      "loss": 0.3618,
      "step": 2560
    },
    {
      "epoch": 2.6025316455696204,
      "grad_norm": 1.5688766989229237,
      "learning_rate": 5e-06,
      "loss": 0.3719,
      "step": 2570
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.5972321010318007,
      "learning_rate": 5e-06,
      "loss": 0.3695,
      "step": 2580
    },
    {
      "epoch": 2.622784810126582,
      "grad_norm": 1.7926779657765413,
      "learning_rate": 5e-06,
      "loss": 0.3671,
      "step": 2590
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.6497318559260037,
      "learning_rate": 5e-06,
      "loss": 0.3648,
      "step": 2600
    },
    {
      "epoch": 2.643037974683544,
      "grad_norm": 1.825449432151336,
      "learning_rate": 5e-06,
      "loss": 0.3675,
      "step": 2610
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.6048797855449353,
      "learning_rate": 5e-06,
      "loss": 0.3638,
      "step": 2620
    },
    {
      "epoch": 2.6632911392405063,
      "grad_norm": 1.6207591062208428,
      "learning_rate": 5e-06,
      "loss": 0.3683,
      "step": 2630
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.7272301549499494,
      "learning_rate": 5e-06,
      "loss": 0.3685,
      "step": 2640
    },
    {
      "epoch": 2.6835443037974684,
      "grad_norm": 1.6364841258418936,
      "learning_rate": 5e-06,
      "loss": 0.3684,
      "step": 2650
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.6937643730038003,
      "learning_rate": 5e-06,
      "loss": 0.3723,
      "step": 2660
    },
    {
      "epoch": 2.7037974683544306,
      "grad_norm": 1.5774730979594618,
      "learning_rate": 5e-06,
      "loss": 0.3671,
      "step": 2670
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.6768910733845062,
      "learning_rate": 5e-06,
      "loss": 0.3715,
      "step": 2680
    },
    {
      "epoch": 2.7240506329113923,
      "grad_norm": 1.6389744367173145,
      "learning_rate": 5e-06,
      "loss": 0.3674,
      "step": 2690
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.7387883655123013,
      "learning_rate": 5e-06,
      "loss": 0.3701,
      "step": 2700
    },
    {
      "epoch": 2.7443037974683544,
      "grad_norm": 1.622855925296899,
      "learning_rate": 5e-06,
      "loss": 0.3692,
      "step": 2710
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.6049744247340423,
      "learning_rate": 5e-06,
      "loss": 0.3605,
      "step": 2720
    },
    {
      "epoch": 2.7645569620253165,
      "grad_norm": 1.674299981616671,
      "learning_rate": 5e-06,
      "loss": 0.3681,
      "step": 2730
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.6563350827590924,
      "learning_rate": 5e-06,
      "loss": 0.3732,
      "step": 2740
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 1.6562436415268564,
      "learning_rate": 5e-06,
      "loss": 0.3666,
      "step": 2750
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.5565903819361853,
      "learning_rate": 5e-06,
      "loss": 0.3706,
      "step": 2760
    },
    {
      "epoch": 2.8050632911392404,
      "grad_norm": 1.7142515863322454,
      "learning_rate": 5e-06,
      "loss": 0.3679,
      "step": 2770
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.5712425643932983,
      "learning_rate": 5e-06,
      "loss": 0.3761,
      "step": 2780
    },
    {
      "epoch": 2.8253164556962025,
      "grad_norm": 1.597329501161643,
      "learning_rate": 5e-06,
      "loss": 0.3697,
      "step": 2790
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.6642023307988005,
      "learning_rate": 5e-06,
      "loss": 0.3613,
      "step": 2800
    },
    {
      "epoch": 2.8455696202531646,
      "grad_norm": 1.6302362931142675,
      "learning_rate": 5e-06,
      "loss": 0.3773,
      "step": 2810
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.594346958058013,
      "learning_rate": 5e-06,
      "loss": 0.3699,
      "step": 2820
    },
    {
      "epoch": 2.8658227848101268,
      "grad_norm": 1.5803480355180004,
      "learning_rate": 5e-06,
      "loss": 0.3711,
      "step": 2830
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.4800494871531567,
      "learning_rate": 5e-06,
      "loss": 0.3691,
      "step": 2840
    },
    {
      "epoch": 2.8860759493670884,
      "grad_norm": 1.6631915526393122,
      "learning_rate": 5e-06,
      "loss": 0.3747,
      "step": 2850
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.630862108030936,
      "learning_rate": 5e-06,
      "loss": 0.3674,
      "step": 2860
    },
    {
      "epoch": 2.9063291139240506,
      "grad_norm": 1.6893754841333202,
      "learning_rate": 5e-06,
      "loss": 0.373,
      "step": 2870
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.705060151220597,
      "learning_rate": 5e-06,
      "loss": 0.3723,
      "step": 2880
    },
    {
      "epoch": 2.9265822784810127,
      "grad_norm": 1.6188859279801948,
      "learning_rate": 5e-06,
      "loss": 0.3796,
      "step": 2890
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.629353248790061,
      "learning_rate": 5e-06,
      "loss": 0.3828,
      "step": 2900
    },
    {
      "epoch": 2.946835443037975,
      "grad_norm": 1.7509445495897462,
      "learning_rate": 5e-06,
      "loss": 0.3713,
      "step": 2910
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.6650857655447995,
      "learning_rate": 5e-06,
      "loss": 0.369,
      "step": 2920
    },
    {
      "epoch": 2.9670886075949365,
      "grad_norm": 1.8285248313648312,
      "learning_rate": 5e-06,
      "loss": 0.3721,
      "step": 2930
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.6243458834916522,
      "learning_rate": 5e-06,
      "loss": 0.3759,
      "step": 2940
    },
    {
      "epoch": 2.9873417721518987,
      "grad_norm": 1.6911778320262214,
      "learning_rate": 5e-06,
      "loss": 0.3746,
      "step": 2950
    },
    {
      "epoch": 2.9974683544303797,
      "grad_norm": 1.7509767039817499,
      "learning_rate": 5e-06,
      "loss": 0.3711,
      "step": 2960
    },
    {
      "epoch": 2.9984810126582278,
      "eval_loss": 0.15120381116867065,
      "eval_runtime": 508.8119,
      "eval_samples_per_second": 26.147,
      "eval_steps_per_second": 0.409,
      "step": 2961
    },
    {
      "epoch": 2.9984810126582278,
      "step": 2961,
      "total_flos": 2479683262218240.0,
      "train_loss": 0.46617310421968466,
      "train_runtime": 84499.4991,
      "train_samples_per_second": 8.974,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 2961,
  "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": 2479683262218240.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}