{
  "best_global_step": 800,
  "best_metric": 0.5232270359992981,
  "best_model_checkpoint": "./exaone-lora-results-system-custom/checkpoint-800",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 1.4204977750778198,
      "learning_rate": 8e-05,
      "loss": 3.1159,
      "step": 5
    },
    {
      "epoch": 0.025,
      "grad_norm": 1.3447633981704712,
      "learning_rate": 0.00018,
      "loss": 2.9296,
      "step": 10
    },
    {
      "epoch": 0.0375,
      "grad_norm": 1.305059790611267,
      "learning_rate": 0.00019959798994974876,
      "loss": 2.5285,
      "step": 15
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.3643401861190796,
      "learning_rate": 0.0001990954773869347,
      "loss": 2.1402,
      "step": 20
    },
    {
      "epoch": 0.0625,
      "grad_norm": 1.3797638416290283,
      "learning_rate": 0.00019859296482412062,
      "loss": 1.773,
      "step": 25
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.8258603811264038,
      "learning_rate": 0.00019809045226130653,
      "loss": 1.37,
      "step": 30
    },
    {
      "epoch": 0.0875,
      "grad_norm": 1.6069886684417725,
      "learning_rate": 0.00019758793969849249,
      "loss": 1.0568,
      "step": 35
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.1830629110336304,
      "learning_rate": 0.0001970854271356784,
      "loss": 0.76,
      "step": 40
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.8522692322731018,
      "learning_rate": 0.00019658291457286432,
      "loss": 0.6618,
      "step": 45
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.6791490316390991,
      "learning_rate": 0.00019608040201005026,
      "loss": 0.6323,
      "step": 50
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.6827747821807861,
      "learning_rate": 0.0001955778894472362,
      "loss": 0.6331,
      "step": 55
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.6210057139396667,
      "learning_rate": 0.00019507537688442212,
      "loss": 0.551,
      "step": 60
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.6427358388900757,
      "learning_rate": 0.00019457286432160805,
      "loss": 0.5756,
      "step": 65
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.8321182131767273,
      "learning_rate": 0.00019407035175879398,
      "loss": 0.5466,
      "step": 70
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.689738929271698,
      "learning_rate": 0.00019356783919597992,
      "loss": 0.5025,
      "step": 75
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6590372323989868,
      "learning_rate": 0.00019306532663316582,
      "loss": 0.5308,
      "step": 80
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.7442909479141235,
      "learning_rate": 0.00019256281407035178,
      "loss": 0.4907,
      "step": 85
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.6165861487388611,
      "learning_rate": 0.0001920603015075377,
      "loss": 0.519,
      "step": 90
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.4800119996070862,
      "learning_rate": 0.00019155778894472362,
      "loss": 0.4944,
      "step": 95
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5565855503082275,
      "learning_rate": 0.00019105527638190955,
      "loss": 0.4891,
      "step": 100
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.5599360466003418,
      "learning_rate": 0.00019055276381909548,
      "loss": 0.4887,
      "step": 105
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.5745482444763184,
      "learning_rate": 0.00019005025125628142,
      "loss": 0.4915,
      "step": 110
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.5511234998703003,
      "learning_rate": 0.00018954773869346732,
      "loss": 0.5147,
      "step": 115
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.579424262046814,
      "learning_rate": 0.00018904522613065328,
      "loss": 0.4726,
      "step": 120
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.604240357875824,
      "learning_rate": 0.00018854271356783921,
      "loss": 0.5083,
      "step": 125
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.631528913974762,
      "learning_rate": 0.00018804020100502512,
      "loss": 0.4827,
      "step": 130
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.5906082391738892,
      "learning_rate": 0.00018753768844221108,
      "loss": 0.4704,
      "step": 135
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5601592659950256,
      "learning_rate": 0.00018703517587939698,
      "loss": 0.4645,
      "step": 140
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.5383768081665039,
      "learning_rate": 0.00018653266331658292,
      "loss": 0.4808,
      "step": 145
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.6543328166007996,
      "learning_rate": 0.00018603015075376885,
      "loss": 0.4504,
      "step": 150
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.6863328814506531,
      "learning_rate": 0.00018552763819095478,
      "loss": 0.4411,
      "step": 155
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6257234811782837,
      "learning_rate": 0.00018502512562814071,
      "loss": 0.4852,
      "step": 160
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.5948039293289185,
      "learning_rate": 0.00018452261306532662,
      "loss": 0.4746,
      "step": 165
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.6108356714248657,
      "learning_rate": 0.00018402010050251258,
      "loss": 0.4325,
      "step": 170
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.6409158706665039,
      "learning_rate": 0.0001835175879396985,
      "loss": 0.4792,
      "step": 175
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5427626371383667,
      "learning_rate": 0.00018301507537688442,
      "loss": 0.4591,
      "step": 180
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.5712430477142334,
      "learning_rate": 0.00018251256281407038,
      "loss": 0.4663,
      "step": 185
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.5315428376197815,
      "learning_rate": 0.00018201005025125628,
      "loss": 0.4662,
      "step": 190
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.6806014180183411,
      "learning_rate": 0.00018150753768844221,
      "loss": 0.4589,
      "step": 195
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4812653362751007,
      "learning_rate": 0.00018100502512562815,
      "loss": 0.4747,
      "step": 200
    },
    {
      "epoch": 0.5125,
      "grad_norm": 0.620926558971405,
      "learning_rate": 0.00018050251256281408,
      "loss": 0.4689,
      "step": 205
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.5241305828094482,
      "learning_rate": 0.00018,
      "loss": 0.412,
      "step": 210
    },
    {
      "epoch": 0.5375,
      "grad_norm": 0.5892027020454407,
      "learning_rate": 0.00017949748743718592,
      "loss": 0.4878,
      "step": 215
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5710367560386658,
      "learning_rate": 0.00017899497487437188,
      "loss": 0.4329,
      "step": 220
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.5636909604072571,
      "learning_rate": 0.0001784924623115578,
      "loss": 0.4335,
      "step": 225
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.5712817311286926,
      "learning_rate": 0.00017798994974874371,
      "loss": 0.4728,
      "step": 230
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.5080311298370361,
      "learning_rate": 0.00017748743718592967,
      "loss": 0.4576,
      "step": 235
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5396429896354675,
      "learning_rate": 0.00017698492462311558,
      "loss": 0.4731,
      "step": 240
    },
    {
      "epoch": 0.6125,
      "grad_norm": 0.594582736492157,
      "learning_rate": 0.0001764824120603015,
      "loss": 0.4421,
      "step": 245
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.5550448298454285,
      "learning_rate": 0.00017597989949748744,
      "loss": 0.4473,
      "step": 250
    },
    {
      "epoch": 0.6375,
      "grad_norm": 0.5841835737228394,
      "learning_rate": 0.00017547738693467338,
      "loss": 0.4141,
      "step": 255
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5154719352722168,
      "learning_rate": 0.0001749748743718593,
      "loss": 0.4178,
      "step": 260
    },
    {
      "epoch": 0.6625,
      "grad_norm": 0.6086138486862183,
      "learning_rate": 0.00017447236180904521,
      "loss": 0.4309,
      "step": 265
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.5762608051300049,
      "learning_rate": 0.00017396984924623117,
      "loss": 0.4395,
      "step": 270
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.6579628586769104,
      "learning_rate": 0.0001734673366834171,
      "loss": 0.4308,
      "step": 275
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5988358855247498,
      "learning_rate": 0.000172964824120603,
      "loss": 0.4157,
      "step": 280
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.5210469365119934,
      "learning_rate": 0.00017246231155778897,
      "loss": 0.4433,
      "step": 285
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.5271325707435608,
      "learning_rate": 0.00017195979899497488,
      "loss": 0.429,
      "step": 290
    },
    {
      "epoch": 0.7375,
      "grad_norm": 0.5668110847473145,
      "learning_rate": 0.0001714572864321608,
      "loss": 0.4789,
      "step": 295
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5577985644340515,
      "learning_rate": 0.00017095477386934674,
      "loss": 0.4278,
      "step": 300
    },
    {
      "epoch": 0.7625,
      "grad_norm": 0.53072190284729,
      "learning_rate": 0.00017045226130653267,
      "loss": 0.4445,
      "step": 305
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.5304411053657532,
      "learning_rate": 0.0001699497487437186,
      "loss": 0.4329,
      "step": 310
    },
    {
      "epoch": 0.7875,
      "grad_norm": 0.5181726813316345,
      "learning_rate": 0.0001694472361809045,
      "loss": 0.429,
      "step": 315
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5597214698791504,
      "learning_rate": 0.00016894472361809047,
      "loss": 0.4225,
      "step": 320
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.5509529709815979,
      "learning_rate": 0.0001684422110552764,
      "loss": 0.4209,
      "step": 325
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.600302517414093,
      "learning_rate": 0.0001679396984924623,
      "loss": 0.4367,
      "step": 330
    },
    {
      "epoch": 0.8375,
      "grad_norm": 0.5333036184310913,
      "learning_rate": 0.00016743718592964827,
      "loss": 0.4362,
      "step": 335
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.5863168835639954,
      "learning_rate": 0.00016693467336683417,
      "loss": 0.4548,
      "step": 340
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.526488184928894,
      "learning_rate": 0.0001664321608040201,
      "loss": 0.4399,
      "step": 345
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.5802232623100281,
      "learning_rate": 0.00016592964824120604,
      "loss": 0.4961,
      "step": 350
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.5905202031135559,
      "learning_rate": 0.00016542713567839197,
      "loss": 0.4453,
      "step": 355
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5512250065803528,
      "learning_rate": 0.0001649246231155779,
      "loss": 0.4135,
      "step": 360
    },
    {
      "epoch": 0.9125,
      "grad_norm": 0.5865863561630249,
      "learning_rate": 0.0001644221105527638,
      "loss": 0.4645,
      "step": 365
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.538692831993103,
      "learning_rate": 0.00016391959798994977,
      "loss": 0.4821,
      "step": 370
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.5884225368499756,
      "learning_rate": 0.0001634170854271357,
      "loss": 0.4484,
      "step": 375
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5514518618583679,
      "learning_rate": 0.0001629145728643216,
      "loss": 0.4529,
      "step": 380
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.577700674533844,
      "learning_rate": 0.00016241206030150756,
      "loss": 0.4651,
      "step": 385
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.5781076550483704,
      "learning_rate": 0.00016190954773869347,
      "loss": 0.4349,
      "step": 390
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.47729212045669556,
      "learning_rate": 0.0001614070351758794,
      "loss": 0.4509,
      "step": 395
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5096570253372192,
      "learning_rate": 0.00016090452261306533,
      "loss": 0.4153,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5257100462913513,
      "eval_runtime": 17.864,
      "eval_samples_per_second": 22.391,
      "eval_steps_per_second": 2.799,
      "step": 400
    },
    {
      "epoch": 1.0125,
      "grad_norm": 0.49858036637306213,
      "learning_rate": 0.00016040201005025127,
      "loss": 0.427,
      "step": 405
    },
    {
      "epoch": 1.025,
      "grad_norm": 0.5483050346374512,
      "learning_rate": 0.0001598994974874372,
      "loss": 0.4414,
      "step": 410
    },
    {
      "epoch": 1.0375,
      "grad_norm": 0.5298231244087219,
      "learning_rate": 0.0001593969849246231,
      "loss": 0.399,
      "step": 415
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.5137779712677002,
      "learning_rate": 0.00015889447236180906,
      "loss": 0.4153,
      "step": 420
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.5221366882324219,
      "learning_rate": 0.000158391959798995,
      "loss": 0.4176,
      "step": 425
    },
    {
      "epoch": 1.075,
      "grad_norm": 0.6192128658294678,
      "learning_rate": 0.0001578894472361809,
      "loss": 0.4107,
      "step": 430
    },
    {
      "epoch": 1.0875,
      "grad_norm": 0.5545984506607056,
      "learning_rate": 0.00015738693467336686,
      "loss": 0.4102,
      "step": 435
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.5551674365997314,
      "learning_rate": 0.00015688442211055277,
      "loss": 0.4129,
      "step": 440
    },
    {
      "epoch": 1.1125,
      "grad_norm": 0.505490779876709,
      "learning_rate": 0.0001563819095477387,
      "loss": 0.4172,
      "step": 445
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.5239485502243042,
      "learning_rate": 0.00015587939698492463,
      "loss": 0.4188,
      "step": 450
    },
    {
      "epoch": 1.1375,
      "grad_norm": 0.5464276671409607,
      "learning_rate": 0.00015537688442211056,
      "loss": 0.4155,
      "step": 455
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.496952623128891,
      "learning_rate": 0.0001548743718592965,
      "loss": 0.4166,
      "step": 460
    },
    {
      "epoch": 1.1625,
      "grad_norm": 0.5454787015914917,
      "learning_rate": 0.0001543718592964824,
      "loss": 0.4146,
      "step": 465
    },
    {
      "epoch": 1.175,
      "grad_norm": 0.5375080704689026,
      "learning_rate": 0.00015386934673366836,
      "loss": 0.4166,
      "step": 470
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.5614022612571716,
      "learning_rate": 0.00015336683417085427,
      "loss": 0.3995,
      "step": 475
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.530121386051178,
      "learning_rate": 0.0001528643216080402,
      "loss": 0.4187,
      "step": 480
    },
    {
      "epoch": 1.2125,
      "grad_norm": 0.4971998333930969,
      "learning_rate": 0.00015236180904522613,
      "loss": 0.3899,
      "step": 485
    },
    {
      "epoch": 1.225,
      "grad_norm": 0.5462106466293335,
      "learning_rate": 0.00015185929648241206,
      "loss": 0.4359,
      "step": 490
    },
    {
      "epoch": 1.2375,
      "grad_norm": 0.5236663222312927,
      "learning_rate": 0.000151356783919598,
      "loss": 0.4127,
      "step": 495
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.5054829716682434,
      "learning_rate": 0.00015085427135678393,
      "loss": 0.4064,
      "step": 500
    },
    {
      "epoch": 1.2625,
      "grad_norm": 0.5926477909088135,
      "learning_rate": 0.00015035175879396986,
      "loss": 0.4085,
      "step": 505
    },
    {
      "epoch": 1.275,
      "grad_norm": 0.5047740936279297,
      "learning_rate": 0.0001498492462311558,
      "loss": 0.398,
      "step": 510
    },
    {
      "epoch": 1.2875,
      "grad_norm": 0.5045680403709412,
      "learning_rate": 0.0001493467336683417,
      "loss": 0.4198,
      "step": 515
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6037045121192932,
      "learning_rate": 0.00014884422110552766,
      "loss": 0.4625,
      "step": 520
    },
    {
      "epoch": 1.3125,
      "grad_norm": 0.5416387915611267,
      "learning_rate": 0.00014834170854271356,
      "loss": 0.437,
      "step": 525
    },
    {
      "epoch": 1.325,
      "grad_norm": 0.5217929482460022,
      "learning_rate": 0.0001478391959798995,
      "loss": 0.4255,
      "step": 530
    },
    {
      "epoch": 1.3375,
      "grad_norm": 0.6118584275245667,
      "learning_rate": 0.00014733668341708543,
      "loss": 0.4395,
      "step": 535
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.5826886892318726,
      "learning_rate": 0.00014683417085427136,
      "loss": 0.4571,
      "step": 540
    },
    {
      "epoch": 1.3625,
      "grad_norm": 0.5662903785705566,
      "learning_rate": 0.0001463316582914573,
      "loss": 0.4338,
      "step": 545
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.5721105933189392,
      "learning_rate": 0.00014582914572864323,
      "loss": 0.4413,
      "step": 550
    },
    {
      "epoch": 1.3875,
      "grad_norm": 0.5065754055976868,
      "learning_rate": 0.00014532663316582916,
      "loss": 0.3901,
      "step": 555
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.5614690780639648,
      "learning_rate": 0.0001448241206030151,
      "loss": 0.4349,
      "step": 560
    },
    {
      "epoch": 1.4125,
      "grad_norm": 0.5476651787757874,
      "learning_rate": 0.000144321608040201,
      "loss": 0.4219,
      "step": 565
    },
    {
      "epoch": 1.425,
      "grad_norm": 0.6010956764221191,
      "learning_rate": 0.00014381909547738696,
      "loss": 0.4107,
      "step": 570
    },
    {
      "epoch": 1.4375,
      "grad_norm": 0.5348302721977234,
      "learning_rate": 0.00014331658291457286,
      "loss": 0.406,
      "step": 575
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.5349542498588562,
      "learning_rate": 0.0001428140703517588,
      "loss": 0.4016,
      "step": 580
    },
    {
      "epoch": 1.4625,
      "grad_norm": 0.5250505208969116,
      "learning_rate": 0.00014231155778894473,
      "loss": 0.4373,
      "step": 585
    },
    {
      "epoch": 1.475,
      "grad_norm": 0.5296792984008789,
      "learning_rate": 0.00014180904522613066,
      "loss": 0.4394,
      "step": 590
    },
    {
      "epoch": 1.4875,
      "grad_norm": 0.5652737021446228,
      "learning_rate": 0.0001413065326633166,
      "loss": 0.3933,
      "step": 595
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5297503471374512,
      "learning_rate": 0.00014080402010050252,
      "loss": 0.4161,
      "step": 600
    },
    {
      "epoch": 1.5125,
      "grad_norm": 0.5393604040145874,
      "learning_rate": 0.00014030150753768846,
      "loss": 0.4245,
      "step": 605
    },
    {
      "epoch": 1.525,
      "grad_norm": 0.4794439375400543,
      "learning_rate": 0.0001397989949748744,
      "loss": 0.4124,
      "step": 610
    },
    {
      "epoch": 1.5375,
      "grad_norm": 0.49562177062034607,
      "learning_rate": 0.0001392964824120603,
      "loss": 0.4092,
      "step": 615
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.562262237071991,
      "learning_rate": 0.00013879396984924625,
      "loss": 0.4007,
      "step": 620
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.6310052871704102,
      "learning_rate": 0.00013829145728643216,
      "loss": 0.4124,
      "step": 625
    },
    {
      "epoch": 1.575,
      "grad_norm": 0.5664736032485962,
      "learning_rate": 0.0001377889447236181,
      "loss": 0.3917,
      "step": 630
    },
    {
      "epoch": 1.5875,
      "grad_norm": 0.5304264426231384,
      "learning_rate": 0.00013728643216080402,
      "loss": 0.4028,
      "step": 635
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.48095929622650146,
      "learning_rate": 0.00013678391959798996,
      "loss": 0.4264,
      "step": 640
    },
    {
      "epoch": 1.6125,
      "grad_norm": 0.5145896077156067,
      "learning_rate": 0.0001362814070351759,
      "loss": 0.42,
      "step": 645
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.5223731398582458,
      "learning_rate": 0.0001357788944723618,
      "loss": 0.4678,
      "step": 650
    },
    {
      "epoch": 1.6375,
      "grad_norm": 0.5224917531013489,
      "learning_rate": 0.00013527638190954775,
      "loss": 0.3959,
      "step": 655
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.542758047580719,
      "learning_rate": 0.00013477386934673368,
      "loss": 0.4055,
      "step": 660
    },
    {
      "epoch": 1.6625,
      "grad_norm": 0.5222824215888977,
      "learning_rate": 0.0001342713567839196,
      "loss": 0.4452,
      "step": 665
    },
    {
      "epoch": 1.675,
      "grad_norm": 0.5793522596359253,
      "learning_rate": 0.00013376884422110555,
      "loss": 0.4131,
      "step": 670
    },
    {
      "epoch": 1.6875,
      "grad_norm": 0.5987710952758789,
      "learning_rate": 0.00013326633165829146,
      "loss": 0.4091,
      "step": 675
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.6028478741645813,
      "learning_rate": 0.0001327638190954774,
      "loss": 0.4376,
      "step": 680
    },
    {
      "epoch": 1.7125,
      "grad_norm": 0.5682055950164795,
      "learning_rate": 0.00013226130653266332,
      "loss": 0.4102,
      "step": 685
    },
    {
      "epoch": 1.725,
      "grad_norm": 0.5360214710235596,
      "learning_rate": 0.00013175879396984925,
      "loss": 0.4456,
      "step": 690
    },
    {
      "epoch": 1.7375,
      "grad_norm": 0.5613261461257935,
      "learning_rate": 0.00013125628140703518,
      "loss": 0.4042,
      "step": 695
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.5854392647743225,
      "learning_rate": 0.0001307537688442211,
      "loss": 0.3754,
      "step": 700
    },
    {
      "epoch": 1.7625,
      "grad_norm": 0.5785875916481018,
      "learning_rate": 0.00013025125628140705,
      "loss": 0.4128,
      "step": 705
    },
    {
      "epoch": 1.775,
      "grad_norm": 0.5500577092170715,
      "learning_rate": 0.00012974874371859298,
      "loss": 0.4176,
      "step": 710
    },
    {
      "epoch": 1.7875,
      "grad_norm": 0.5343199372291565,
      "learning_rate": 0.0001292462311557789,
      "loss": 0.4008,
      "step": 715
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.5914020538330078,
      "learning_rate": 0.00012874371859296485,
      "loss": 0.3919,
      "step": 720
    },
    {
      "epoch": 1.8125,
      "grad_norm": 0.5501930117607117,
      "learning_rate": 0.00012824120603015075,
      "loss": 0.3797,
      "step": 725
    },
    {
      "epoch": 1.825,
      "grad_norm": 0.5344274640083313,
      "learning_rate": 0.00012773869346733668,
      "loss": 0.4045,
      "step": 730
    },
    {
      "epoch": 1.8375,
      "grad_norm": 0.5303798913955688,
      "learning_rate": 0.00012723618090452262,
      "loss": 0.4098,
      "step": 735
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.5791289806365967,
      "learning_rate": 0.00012673366834170855,
      "loss": 0.4166,
      "step": 740
    },
    {
      "epoch": 1.8625,
      "grad_norm": 0.5153045058250427,
      "learning_rate": 0.00012623115577889448,
      "loss": 0.4011,
      "step": 745
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.5780820846557617,
      "learning_rate": 0.0001257286432160804,
      "loss": 0.3839,
      "step": 750
    },
    {
      "epoch": 1.8875,
      "grad_norm": 0.5261033177375793,
      "learning_rate": 0.00012522613065326635,
      "loss": 0.402,
      "step": 755
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.5911995768547058,
      "learning_rate": 0.00012472361809045228,
      "loss": 0.4032,
      "step": 760
    },
    {
      "epoch": 1.9125,
      "grad_norm": 0.519932746887207,
      "learning_rate": 0.00012422110552763818,
      "loss": 0.4091,
      "step": 765
    },
    {
      "epoch": 1.925,
      "grad_norm": 0.5260487794876099,
      "learning_rate": 0.00012371859296482414,
      "loss": 0.3896,
      "step": 770
    },
    {
      "epoch": 1.9375,
      "grad_norm": 0.5135574340820312,
      "learning_rate": 0.00012321608040201005,
      "loss": 0.4313,
      "step": 775
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.6207651495933533,
      "learning_rate": 0.00012271356783919598,
      "loss": 0.4357,
      "step": 780
    },
    {
      "epoch": 1.9625,
      "grad_norm": 0.5082093477249146,
      "learning_rate": 0.00012221105527638191,
      "loss": 0.4082,
      "step": 785
    },
    {
      "epoch": 1.975,
      "grad_norm": 0.5137083530426025,
      "learning_rate": 0.00012170854271356785,
      "loss": 0.402,
      "step": 790
    },
    {
      "epoch": 1.9875,
      "grad_norm": 0.5387287139892578,
      "learning_rate": 0.00012120603015075378,
      "loss": 0.3952,
      "step": 795
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5328527092933655,
      "learning_rate": 0.0001207035175879397,
      "loss": 0.394,
      "step": 800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5232270359992981,
      "eval_runtime": 17.3583,
      "eval_samples_per_second": 23.044,
      "eval_steps_per_second": 2.88,
      "step": 800
    }
  ],
  "logging_steps": 5,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.747212965907456e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}