{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 1329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 1.0747386077855485,
      "learning_rate": 5e-06,
      "loss": 0.7442,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.9250006754740806,
      "learning_rate": 5e-06,
      "loss": 0.6805,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.6391300982137391,
      "learning_rate": 5e-06,
      "loss": 0.6629,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.6970407489760442,
      "learning_rate": 5e-06,
      "loss": 0.6404,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.8264400986148096,
      "learning_rate": 5e-06,
      "loss": 0.6338,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.6337702782177299,
      "learning_rate": 5e-06,
      "loss": 0.6332,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.7026400154879202,
      "learning_rate": 5e-06,
      "loss": 0.629,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.6110008950691942,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.7377741477995501,
      "learning_rate": 5e-06,
      "loss": 0.6282,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.6062643431016188,
      "learning_rate": 5e-06,
      "loss": 0.6273,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.5908093304486361,
      "learning_rate": 5e-06,
      "loss": 0.6181,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.6356319486792598,
      "learning_rate": 5e-06,
      "loss": 0.6173,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.8794413412831209,
      "learning_rate": 5e-06,
      "loss": 0.6186,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.6380252583082179,
      "learning_rate": 5e-06,
      "loss": 0.6135,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.6102043201784026,
      "learning_rate": 5e-06,
      "loss": 0.6143,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.5825321430591771,
      "learning_rate": 5e-06,
      "loss": 0.616,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.630325190703719,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.6224319956534152,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.7290355460412141,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.6096673130477651,
      "learning_rate": 5e-06,
      "loss": 0.6099,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.5868357514937059,
      "learning_rate": 5e-06,
      "loss": 0.6063,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.689902399409136,
      "learning_rate": 5e-06,
      "loss": 0.5981,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.616782891542955,
      "learning_rate": 5e-06,
      "loss": 0.607,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.6202512339508975,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.5774115973733374,
      "learning_rate": 5e-06,
      "loss": 0.6,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.7043874076787283,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.58995535424681,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.6645617563424304,
      "learning_rate": 5e-06,
      "loss": 0.6047,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.8024829007382146,
      "learning_rate": 5e-06,
      "loss": 0.5982,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.7872885938780655,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.5860360834354194,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.602505842863584,
      "learning_rate": 5e-06,
      "loss": 0.6006,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.5612615132295476,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5753640699331777,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.6786534296702089,
      "learning_rate": 5e-06,
      "loss": 0.5972,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.5824028322456011,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.5857564927531737,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.5559490568068783,
      "learning_rate": 5e-06,
      "loss": 0.5999,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.5936969621377869,
      "learning_rate": 5e-06,
      "loss": 0.5939,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.5536301670254788,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.6129582402142512,
      "learning_rate": 5e-06,
      "loss": 0.5942,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.5988575144700949,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.5953708423724527,
      "learning_rate": 5e-06,
      "loss": 0.5888,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.7086142865197167,
      "learning_rate": 5e-06,
      "loss": 0.5936,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.591454029083252,
      "eval_runtime": 700.44,
      "eval_samples_per_second": 17.048,
      "eval_steps_per_second": 0.534,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.7282548310224137,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.6094487614641326,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.5836024832309795,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.5896353538118286,
      "learning_rate": 5e-06,
      "loss": 0.5309,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.6018469874864032,
      "learning_rate": 5e-06,
      "loss": 0.541,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.5868762451394651,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.6164687056963604,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.5878215518953811,
      "learning_rate": 5e-06,
      "loss": 0.5335,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.6737371667740706,
      "learning_rate": 5e-06,
      "loss": 0.5397,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.5834960629813468,
      "learning_rate": 5e-06,
      "loss": 0.5371,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.6503378874314304,
      "learning_rate": 5e-06,
      "loss": 0.5419,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.6263040414380777,
      "learning_rate": 5e-06,
      "loss": 0.5437,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.579825474440825,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.5424695027511006,
      "learning_rate": 5e-06,
      "loss": 0.541,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.5563535085690828,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.6502789053974841,
      "learning_rate": 5e-06,
      "loss": 0.5462,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.5347225100617908,
      "learning_rate": 5e-06,
      "loss": 0.5389,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.5969533006122975,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.54570908566952,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.6591039571760914,
      "learning_rate": 5e-06,
      "loss": 0.5408,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.6064976081971594,
      "learning_rate": 5e-06,
      "loss": 0.5417,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.6219511585396352,
      "learning_rate": 5e-06,
      "loss": 0.5455,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.5582000350304234,
      "learning_rate": 5e-06,
      "loss": 0.5401,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5534447464296384,
      "learning_rate": 5e-06,
      "loss": 0.5343,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.5865748914613451,
      "learning_rate": 5e-06,
      "loss": 0.5364,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.5695396323525544,
      "learning_rate": 5e-06,
      "loss": 0.5406,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.5539790538877291,
      "learning_rate": 5e-06,
      "loss": 0.5434,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.6128481963660832,
      "learning_rate": 5e-06,
      "loss": 0.5514,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.5370481057399126,
      "learning_rate": 5e-06,
      "loss": 0.5347,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.6400145727787568,
      "learning_rate": 5e-06,
      "loss": 0.5505,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.663525021392975,
      "learning_rate": 5e-06,
      "loss": 0.542,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5740953416231195,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.6485784119905271,
      "learning_rate": 5e-06,
      "loss": 0.5415,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.5840620626669101,
      "learning_rate": 5e-06,
      "loss": 0.5373,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.5610598099881898,
      "learning_rate": 5e-06,
      "loss": 0.5409,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.5471005343720242,
      "learning_rate": 5e-06,
      "loss": 0.5359,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.7337432125212925,
      "learning_rate": 5e-06,
      "loss": 0.5467,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.5560893116945588,
      "learning_rate": 5e-06,
      "loss": 0.5341,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.5953866521929512,
      "learning_rate": 5e-06,
      "loss": 0.5461,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.6364973894343403,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.5426918245161618,
      "learning_rate": 5e-06,
      "loss": 0.5339,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.595991305335456,
      "learning_rate": 5e-06,
      "loss": 0.5389,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.6493484319698485,
      "learning_rate": 5e-06,
      "loss": 0.5454,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.6487493336419082,
      "learning_rate": 5e-06,
      "loss": 0.5437,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5870312452316284,
      "eval_runtime": 698.1454,
      "eval_samples_per_second": 17.104,
      "eval_steps_per_second": 0.536,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 0.9365480171613407,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.743462616086469,
      "learning_rate": 5e-06,
      "loss": 0.4784,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.6281186980302998,
      "learning_rate": 5e-06,
      "loss": 0.4802,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.6021229847596531,
      "learning_rate": 5e-06,
      "loss": 0.4726,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.5913043365668217,
      "learning_rate": 5e-06,
      "loss": 0.4798,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.59391584309919,
      "learning_rate": 5e-06,
      "loss": 0.4839,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.6068126785348577,
      "learning_rate": 5e-06,
      "loss": 0.4856,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.5964488683796753,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.717603893671707,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.6131942285037348,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.5589074592794259,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.6117290382896083,
      "learning_rate": 5e-06,
      "loss": 0.4835,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.5950004577763529,
      "learning_rate": 5e-06,
      "loss": 0.4898,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.7555104513200974,
      "learning_rate": 5e-06,
      "loss": 0.4842,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.6124397990551607,
      "learning_rate": 5e-06,
      "loss": 0.4884,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.6496015046850921,
      "learning_rate": 5e-06,
      "loss": 0.4864,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.6030642086914068,
      "learning_rate": 5e-06,
      "loss": 0.4841,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.60444690253433,
      "learning_rate": 5e-06,
      "loss": 0.4834,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.7179678608372039,
      "learning_rate": 5e-06,
      "loss": 0.4845,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.6875976433747453,
      "learning_rate": 5e-06,
      "loss": 0.4877,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.5749678689948055,
      "learning_rate": 5e-06,
      "loss": 0.4858,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.6033017978227587,
      "learning_rate": 5e-06,
      "loss": 0.489,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.59169430257269,
      "learning_rate": 5e-06,
      "loss": 0.4923,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.636737150629263,
      "learning_rate": 5e-06,
      "loss": 0.4831,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.5910945663109894,
      "learning_rate": 5e-06,
      "loss": 0.4881,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.5678873251322573,
      "learning_rate": 5e-06,
      "loss": 0.4863,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.6959445237535552,
      "learning_rate": 5e-06,
      "loss": 0.4872,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.6298329329899562,
      "learning_rate": 5e-06,
      "loss": 0.4907,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.5880004765583379,
      "learning_rate": 5e-06,
      "loss": 0.4798,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.5960960055798509,
      "learning_rate": 5e-06,
      "loss": 0.4904,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.5605167416365159,
      "learning_rate": 5e-06,
      "loss": 0.4912,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.6525889773079177,
      "learning_rate": 5e-06,
      "loss": 0.4898,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.5879001296566289,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.5909216483045182,
      "learning_rate": 5e-06,
      "loss": 0.4877,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.584873221626307,
      "learning_rate": 5e-06,
      "loss": 0.4943,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.6241217691010849,
      "learning_rate": 5e-06,
      "loss": 0.4927,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.56433922242637,
      "learning_rate": 5e-06,
      "loss": 0.4928,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5817659123841857,
      "learning_rate": 5e-06,
      "loss": 0.4946,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5875932423682607,
      "learning_rate": 5e-06,
      "loss": 0.4915,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.5425720998409109,
      "learning_rate": 5e-06,
      "loss": 0.4896,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.5606018576810341,
      "learning_rate": 5e-06,
      "loss": 0.4933,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.5834474780595325,
      "learning_rate": 5e-06,
      "loss": 0.489,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.6341951400173672,
      "learning_rate": 5e-06,
      "loss": 0.4929,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.587636698954054,
      "learning_rate": 5e-06,
      "loss": 0.4893,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.6003031730651855,
      "eval_runtime": 697.4003,
      "eval_samples_per_second": 17.122,
      "eval_steps_per_second": 0.536,
      "step": 1329
    },
    {
      "epoch": 2.9991537376586743,
      "step": 1329,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.5476742999907093,
      "train_runtime": 122403.0515,
      "train_samples_per_second": 5.56,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 1329,
  "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": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}