{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.110671936758893,
  "eval_steps": 10,
  "global_step": 1201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999576610920983,
      "loss": 3.0929,
      "step": 10
    },
    {
      "epoch": 0.02,
      "eval_loss": 2.167867660522461,
      "eval_runtime": 21.3399,
      "eval_samples_per_second": 23.383,
      "eval_steps_per_second": 5.858,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019998306479535586,
      "loss": 1.8074,
      "step": 20
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.4092761278152466,
      "eval_runtime": 21.3617,
      "eval_samples_per_second": 23.36,
      "eval_steps_per_second": 5.852,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019996189713395766,
      "loss": 1.2188,
      "step": 30
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.1258704662322998,
      "eval_runtime": 21.3588,
      "eval_samples_per_second": 23.363,
      "eval_steps_per_second": 5.852,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019993226491744662,
      "loss": 1.0841,
      "step": 40
    },
    {
      "epoch": 0.07,
      "eval_loss": 0.9605854153633118,
      "eval_runtime": 21.3693,
      "eval_samples_per_second": 23.351,
      "eval_steps_per_second": 5.85,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019989417065501396,
      "loss": 0.9594,
      "step": 50
    },
    {
      "epoch": 0.09,
      "eval_loss": 0.8681771159172058,
      "eval_runtime": 21.3662,
      "eval_samples_per_second": 23.355,
      "eval_steps_per_second": 5.85,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019984761757239875,
      "loss": 0.8765,
      "step": 60
    },
    {
      "epoch": 0.11,
      "eval_loss": 0.816562294960022,
      "eval_runtime": 21.3405,
      "eval_samples_per_second": 23.383,
      "eval_steps_per_second": 5.857,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019979260961161427,
      "loss": 0.852,
      "step": 70
    },
    {
      "epoch": 0.12,
      "eval_loss": 0.7803006768226624,
      "eval_runtime": 21.3622,
      "eval_samples_per_second": 23.359,
      "eval_steps_per_second": 5.851,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019972915143061455,
      "loss": 0.8404,
      "step": 80
    },
    {
      "epoch": 0.14,
      "eval_loss": 0.760216236114502,
      "eval_runtime": 21.379,
      "eval_samples_per_second": 23.341,
      "eval_steps_per_second": 5.847,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001996572484028997,
      "loss": 0.8183,
      "step": 90
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.7222956418991089,
      "eval_runtime": 21.3895,
      "eval_samples_per_second": 23.329,
      "eval_steps_per_second": 5.844,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019957690661706108,
      "loss": 0.7816,
      "step": 100
    },
    {
      "epoch": 0.18,
      "eval_loss": 0.7133845686912537,
      "eval_runtime": 21.3742,
      "eval_samples_per_second": 23.346,
      "eval_steps_per_second": 5.848,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019948813287626563,
      "loss": 0.7792,
      "step": 110
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.7233743667602539,
      "eval_runtime": 21.3703,
      "eval_samples_per_second": 23.35,
      "eval_steps_per_second": 5.849,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001993909346976798,
      "loss": 0.7648,
      "step": 120
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.6882979273796082,
      "eval_runtime": 21.3682,
      "eval_samples_per_second": 23.352,
      "eval_steps_per_second": 5.85,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001992853203118331,
      "loss": 0.8132,
      "step": 130
    },
    {
      "epoch": 0.23,
      "eval_loss": 0.7019714117050171,
      "eval_runtime": 21.374,
      "eval_samples_per_second": 23.346,
      "eval_steps_per_second": 5.848,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000199171298661921,
      "loss": 0.7599,
      "step": 140
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.668350338935852,
      "eval_runtime": 21.323,
      "eval_samples_per_second": 23.402,
      "eval_steps_per_second": 5.862,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001990488794030478,
      "loss": 0.7518,
      "step": 150
    },
    {
      "epoch": 0.26,
      "eval_loss": 0.6716361045837402,
      "eval_runtime": 21.3312,
      "eval_samples_per_second": 23.393,
      "eval_steps_per_second": 5.86,
      "step": 150
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019891807290140892,
      "loss": 0.7452,
      "step": 160
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.6634441018104553,
      "eval_runtime": 21.3388,
      "eval_samples_per_second": 23.385,
      "eval_steps_per_second": 5.858,
      "step": 160
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019877889023341323,
      "loss": 0.7215,
      "step": 170
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.6609596610069275,
      "eval_runtime": 21.3355,
      "eval_samples_per_second": 23.388,
      "eval_steps_per_second": 5.859,
      "step": 170
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019863134318474503,
      "loss": 0.7088,
      "step": 180
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.659795880317688,
      "eval_runtime": 21.3459,
      "eval_samples_per_second": 23.377,
      "eval_steps_per_second": 5.856,
      "step": 180
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001984754442493662,
      "loss": 0.7237,
      "step": 190
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.6469973921775818,
      "eval_runtime": 21.3405,
      "eval_samples_per_second": 23.383,
      "eval_steps_per_second": 5.857,
      "step": 190
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000198311206628458,
      "loss": 0.7353,
      "step": 200
    },
    {
      "epoch": 0.35,
      "eval_loss": 0.6315197348594666,
      "eval_runtime": 21.3347,
      "eval_samples_per_second": 23.389,
      "eval_steps_per_second": 5.859,
      "step": 200
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019813864422930347,
      "loss": 0.7111,
      "step": 210
    },
    {
      "epoch": 0.37,
      "eval_loss": 0.6466153860092163,
      "eval_runtime": 21.3369,
      "eval_samples_per_second": 23.387,
      "eval_steps_per_second": 5.858,
      "step": 210
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019795777166410966,
      "loss": 0.7136,
      "step": 220
    },
    {
      "epoch": 0.39,
      "eval_loss": 0.632926344871521,
      "eval_runtime": 21.3244,
      "eval_samples_per_second": 23.4,
      "eval_steps_per_second": 5.862,
      "step": 220
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019776860424877032,
      "loss": 0.7044,
      "step": 230
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.6356912851333618,
      "eval_runtime": 21.3235,
      "eval_samples_per_second": 23.401,
      "eval_steps_per_second": 5.862,
      "step": 230
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000197571158001569,
      "loss": 0.7369,
      "step": 240
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.6214553713798523,
      "eval_runtime": 21.3355,
      "eval_samples_per_second": 23.388,
      "eval_steps_per_second": 5.859,
      "step": 240
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019736544964182268,
      "loss": 0.6995,
      "step": 250
    },
    {
      "epoch": 0.44,
      "eval_loss": 0.6103290915489197,
      "eval_runtime": 21.3392,
      "eval_samples_per_second": 23.384,
      "eval_steps_per_second": 5.858,
      "step": 250
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019715149658846591,
      "loss": 0.7027,
      "step": 260
    },
    {
      "epoch": 0.46,
      "eval_loss": 0.5964030027389526,
      "eval_runtime": 21.3644,
      "eval_samples_per_second": 23.357,
      "eval_steps_per_second": 5.851,
      "step": 260
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000196929316958576,
      "loss": 0.6872,
      "step": 270
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.60444176197052,
      "eval_runtime": 21.3353,
      "eval_samples_per_second": 23.389,
      "eval_steps_per_second": 5.859,
      "step": 270
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019669892956583867,
      "loss": 0.7182,
      "step": 280
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.6127080917358398,
      "eval_runtime": 21.3451,
      "eval_samples_per_second": 23.378,
      "eval_steps_per_second": 5.856,
      "step": 280
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019646035391895512,
      "loss": 0.6897,
      "step": 290
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.6016324758529663,
      "eval_runtime": 21.324,
      "eval_samples_per_second": 23.401,
      "eval_steps_per_second": 5.862,
      "step": 290
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019621361021999008,
      "loss": 0.6824,
      "step": 300
    },
    {
      "epoch": 0.53,
      "eval_loss": 0.5880205631256104,
      "eval_runtime": 21.3379,
      "eval_samples_per_second": 23.386,
      "eval_steps_per_second": 5.858,
      "step": 300
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000195958719362661,
      "loss": 0.673,
      "step": 310
    },
    {
      "epoch": 0.54,
      "eval_loss": 0.5902190804481506,
      "eval_runtime": 21.3191,
      "eval_samples_per_second": 23.406,
      "eval_steps_per_second": 5.863,
      "step": 310
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019569570293056894,
      "loss": 0.6956,
      "step": 320
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.5811321139335632,
      "eval_runtime": 21.3365,
      "eval_samples_per_second": 23.387,
      "eval_steps_per_second": 5.859,
      "step": 320
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019542458319537093,
      "loss": 0.6889,
      "step": 330
    },
    {
      "epoch": 0.58,
      "eval_loss": 0.5849844813346863,
      "eval_runtime": 21.3231,
      "eval_samples_per_second": 23.402,
      "eval_steps_per_second": 5.862,
      "step": 330
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019514538311489395,
      "loss": 0.6773,
      "step": 340
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.5933501720428467,
      "eval_runtime": 21.3446,
      "eval_samples_per_second": 23.378,
      "eval_steps_per_second": 5.856,
      "step": 340
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019485812633119096,
      "loss": 0.6782,
      "step": 350
    },
    {
      "epoch": 0.61,
      "eval_loss": 0.594153642654419,
      "eval_runtime": 21.3347,
      "eval_samples_per_second": 23.389,
      "eval_steps_per_second": 5.859,
      "step": 350
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019456283716853904,
      "loss": 0.719,
      "step": 360
    },
    {
      "epoch": 0.63,
      "eval_loss": 0.5848734974861145,
      "eval_runtime": 21.3162,
      "eval_samples_per_second": 23.409,
      "eval_steps_per_second": 5.864,
      "step": 360
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019425954063137947,
      "loss": 0.6809,
      "step": 370
    },
    {
      "epoch": 0.65,
      "eval_loss": 0.579924464225769,
      "eval_runtime": 21.3339,
      "eval_samples_per_second": 23.39,
      "eval_steps_per_second": 5.859,
      "step": 370
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019394826240220057,
      "loss": 0.6412,
      "step": 380
    },
    {
      "epoch": 0.67,
      "eval_loss": 0.5709846019744873,
      "eval_runtime": 21.3459,
      "eval_samples_per_second": 23.377,
      "eval_steps_per_second": 5.856,
      "step": 380
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019362902883936288,
      "loss": 0.6411,
      "step": 390
    },
    {
      "epoch": 0.69,
      "eval_loss": 0.562785267829895,
      "eval_runtime": 21.3375,
      "eval_samples_per_second": 23.386,
      "eval_steps_per_second": 5.858,
      "step": 390
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019330186697486722,
      "loss": 0.6519,
      "step": 400
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.5611785650253296,
      "eval_runtime": 21.3506,
      "eval_samples_per_second": 23.372,
      "eval_steps_per_second": 5.855,
      "step": 400
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019296680451206575,
      "loss": 0.6446,
      "step": 410
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.5562126636505127,
      "eval_runtime": 21.3482,
      "eval_samples_per_second": 23.374,
      "eval_steps_per_second": 5.855,
      "step": 410
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019262386982331594,
      "loss": 0.6574,
      "step": 420
    },
    {
      "epoch": 0.74,
      "eval_loss": 0.5644647479057312,
      "eval_runtime": 21.3719,
      "eval_samples_per_second": 23.348,
      "eval_steps_per_second": 5.849,
      "step": 420
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019227309194757818,
      "loss": 0.6633,
      "step": 430
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.5663937926292419,
      "eval_runtime": 21.3728,
      "eval_samples_per_second": 23.347,
      "eval_steps_per_second": 5.849,
      "step": 430
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019191450058795683,
      "loss": 0.6673,
      "step": 440
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.5483366847038269,
      "eval_runtime": 21.352,
      "eval_samples_per_second": 23.37,
      "eval_steps_per_second": 5.854,
      "step": 440
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019154812610918501,
      "loss": 0.6466,
      "step": 450
    },
    {
      "epoch": 0.79,
      "eval_loss": 0.554151713848114,
      "eval_runtime": 21.4045,
      "eval_samples_per_second": 23.313,
      "eval_steps_per_second": 5.84,
      "step": 450
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019117399953505335,
      "loss": 0.653,
      "step": 460
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.5411431789398193,
      "eval_runtime": 21.3349,
      "eval_samples_per_second": 23.389,
      "eval_steps_per_second": 5.859,
      "step": 460
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019079215254578293,
      "loss": 0.6384,
      "step": 470
    },
    {
      "epoch": 0.83,
      "eval_loss": 0.5362362265586853,
      "eval_runtime": 21.3477,
      "eval_samples_per_second": 23.375,
      "eval_steps_per_second": 5.855,
      "step": 470
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019040261747534283,
      "loss": 0.6287,
      "step": 480
    },
    {
      "epoch": 0.84,
      "eval_loss": 0.5452967286109924,
      "eval_runtime": 21.3462,
      "eval_samples_per_second": 23.377,
      "eval_steps_per_second": 5.856,
      "step": 480
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00019000542730871197,
      "loss": 0.661,
      "step": 490
    },
    {
      "epoch": 0.86,
      "eval_loss": 0.5644904971122742,
      "eval_runtime": 21.3569,
      "eval_samples_per_second": 23.365,
      "eval_steps_per_second": 5.853,
      "step": 490
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001896006156790861,
      "loss": 0.608,
      "step": 500
    },
    {
      "epoch": 0.88,
      "eval_loss": 0.5245234370231628,
      "eval_runtime": 21.3459,
      "eval_samples_per_second": 23.377,
      "eval_steps_per_second": 5.856,
      "step": 500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018918821686502989,
      "loss": 0.6584,
      "step": 510
    },
    {
      "epoch": 0.9,
      "eval_loss": 0.5376425385475159,
      "eval_runtime": 21.3569,
      "eval_samples_per_second": 23.365,
      "eval_steps_per_second": 5.853,
      "step": 510
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001887682657875741,
      "loss": 0.6416,
      "step": 520
    },
    {
      "epoch": 0.91,
      "eval_loss": 0.5471484661102295,
      "eval_runtime": 21.3644,
      "eval_samples_per_second": 23.357,
      "eval_steps_per_second": 5.851,
      "step": 520
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018834079800725872,
      "loss": 0.6527,
      "step": 530
    },
    {
      "epoch": 0.93,
      "eval_loss": 0.5425943732261658,
      "eval_runtime": 21.3669,
      "eval_samples_per_second": 23.354,
      "eval_steps_per_second": 5.85,
      "step": 530
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018790584972112174,
      "loss": 0.6164,
      "step": 540
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.5284227728843689,
      "eval_runtime": 21.3751,
      "eval_samples_per_second": 23.345,
      "eval_steps_per_second": 5.848,
      "step": 540
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018746345775963395,
      "loss": 0.611,
      "step": 550
    },
    {
      "epoch": 0.97,
      "eval_loss": 0.5312528014183044,
      "eval_runtime": 21.3628,
      "eval_samples_per_second": 23.358,
      "eval_steps_per_second": 5.851,
      "step": 550
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018701365958358047,
      "loss": 0.614,
      "step": 560
    },
    {
      "epoch": 0.98,
      "eval_loss": 0.5262718796730042,
      "eval_runtime": 21.3578,
      "eval_samples_per_second": 23.364,
      "eval_steps_per_second": 5.853,
      "step": 560
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018655649328088835,
      "loss": 0.6382,
      "step": 570
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5316660404205322,
      "eval_runtime": 21.3512,
      "eval_samples_per_second": 23.371,
      "eval_steps_per_second": 5.854,
      "step": 570
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018609199756340156,
      "loss": 0.5804,
      "step": 580
    },
    {
      "epoch": 1.02,
      "eval_loss": 0.5207402110099792,
      "eval_runtime": 21.3663,
      "eval_samples_per_second": 23.355,
      "eval_steps_per_second": 5.85,
      "step": 580
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001856202117636029,
      "loss": 0.6291,
      "step": 590
    },
    {
      "epoch": 1.04,
      "eval_loss": 0.5237697958946228,
      "eval_runtime": 21.3922,
      "eval_samples_per_second": 23.326,
      "eval_steps_per_second": 5.843,
      "step": 590
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018514117583128347,
      "loss": 0.5911,
      "step": 600
    },
    {
      "epoch": 1.05,
      "eval_loss": 0.517393171787262,
      "eval_runtime": 21.3498,
      "eval_samples_per_second": 23.373,
      "eval_steps_per_second": 5.855,
      "step": 600
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018465493033015967,
      "loss": 0.6111,
      "step": 610
    },
    {
      "epoch": 1.07,
      "eval_loss": 0.5281241536140442,
      "eval_runtime": 21.3522,
      "eval_samples_per_second": 23.37,
      "eval_steps_per_second": 5.854,
      "step": 610
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001841615164344385,
      "loss": 0.5578,
      "step": 620
    },
    {
      "epoch": 1.09,
      "eval_loss": 0.5255175232887268,
      "eval_runtime": 21.3637,
      "eval_samples_per_second": 23.357,
      "eval_steps_per_second": 5.851,
      "step": 620
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018366097592533093,
      "loss": 0.6055,
      "step": 630
    },
    {
      "epoch": 1.11,
      "eval_loss": 0.5177362561225891,
      "eval_runtime": 21.3827,
      "eval_samples_per_second": 23.337,
      "eval_steps_per_second": 5.846,
      "step": 630
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018315335118751396,
      "loss": 0.6015,
      "step": 640
    },
    {
      "epoch": 1.12,
      "eval_loss": 0.5130926370620728,
      "eval_runtime": 21.4348,
      "eval_samples_per_second": 23.28,
      "eval_steps_per_second": 5.832,
      "step": 640
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001826386852055417,
      "loss": 0.6072,
      "step": 650
    },
    {
      "epoch": 1.14,
      "eval_loss": 0.5168054103851318,
      "eval_runtime": 21.3583,
      "eval_samples_per_second": 23.363,
      "eval_steps_per_second": 5.853,
      "step": 650
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001821170215602053,
      "loss": 0.5956,
      "step": 660
    },
    {
      "epoch": 1.16,
      "eval_loss": 0.5168840289115906,
      "eval_runtime": 21.3753,
      "eval_samples_per_second": 23.345,
      "eval_steps_per_second": 5.848,
      "step": 660
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001815884044248429,
      "loss": 0.6099,
      "step": 670
    },
    {
      "epoch": 1.18,
      "eval_loss": 0.5169732570648193,
      "eval_runtime": 21.3472,
      "eval_samples_per_second": 23.375,
      "eval_steps_per_second": 5.856,
      "step": 670
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001810528785615989,
      "loss": 0.6038,
      "step": 680
    },
    {
      "epoch": 1.19,
      "eval_loss": 0.5055590867996216,
      "eval_runtime": 21.3489,
      "eval_samples_per_second": 23.374,
      "eval_steps_per_second": 5.855,
      "step": 680
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00018051048931763366,
      "loss": 0.583,
      "step": 690
    },
    {
      "epoch": 1.21,
      "eval_loss": 0.5121394395828247,
      "eval_runtime": 21.3436,
      "eval_samples_per_second": 23.379,
      "eval_steps_per_second": 5.857,
      "step": 690
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001799612826212837,
      "loss": 0.5885,
      "step": 700
    },
    {
      "epoch": 1.23,
      "eval_loss": 0.523388683795929,
      "eval_runtime": 21.3616,
      "eval_samples_per_second": 23.36,
      "eval_steps_per_second": 5.852,
      "step": 700
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017940530497817254,
      "loss": 0.5784,
      "step": 710
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.5028228163719177,
      "eval_runtime": 21.3469,
      "eval_samples_per_second": 23.376,
      "eval_steps_per_second": 5.856,
      "step": 710
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017884260346727254,
      "loss": 0.5744,
      "step": 720
    },
    {
      "epoch": 1.26,
      "eval_loss": 0.5100187063217163,
      "eval_runtime": 21.3603,
      "eval_samples_per_second": 23.361,
      "eval_steps_per_second": 5.852,
      "step": 720
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017827322573691872,
      "loss": 0.6014,
      "step": 730
    },
    {
      "epoch": 1.28,
      "eval_loss": 0.5038166046142578,
      "eval_runtime": 21.3431,
      "eval_samples_per_second": 23.38,
      "eval_steps_per_second": 5.857,
      "step": 730
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001776972200007735,
      "loss": 0.6185,
      "step": 740
    },
    {
      "epoch": 1.3,
      "eval_loss": 0.5146144032478333,
      "eval_runtime": 21.3367,
      "eval_samples_per_second": 23.387,
      "eval_steps_per_second": 5.858,
      "step": 740
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017711463503374466,
      "loss": 0.6184,
      "step": 750
    },
    {
      "epoch": 1.32,
      "eval_loss": 0.5316588282585144,
      "eval_runtime": 21.3617,
      "eval_samples_per_second": 23.36,
      "eval_steps_per_second": 5.852,
      "step": 750
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001765255201678546,
      "loss": 0.6141,
      "step": 760
    },
    {
      "epoch": 1.34,
      "eval_loss": 0.5080065727233887,
      "eval_runtime": 21.3913,
      "eval_samples_per_second": 23.327,
      "eval_steps_per_second": 5.844,
      "step": 760
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017592992528806352,
      "loss": 0.6146,
      "step": 770
    },
    {
      "epoch": 1.35,
      "eval_loss": 0.5165488719940186,
      "eval_runtime": 21.3517,
      "eval_samples_per_second": 23.371,
      "eval_steps_per_second": 5.854,
      "step": 770
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001753279008280449,
      "loss": 0.5721,
      "step": 780
    },
    {
      "epoch": 1.37,
      "eval_loss": 0.5040128231048584,
      "eval_runtime": 21.3467,
      "eval_samples_per_second": 23.376,
      "eval_steps_per_second": 5.856,
      "step": 780
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00017471949776591504,
      "loss": 0.5931,
      "step": 790
    },
    {
      "epoch": 1.39,
      "eval_loss": 0.49337631464004517,
      "eval_runtime": 21.3473,
      "eval_samples_per_second": 23.375,
      "eval_steps_per_second": 5.856,
      "step": 790
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00017410476761991643,
      "loss": 0.5944,
      "step": 800
    },
    {
      "epoch": 1.41,
      "eval_loss": 0.487575501203537,
      "eval_runtime": 21.3451,
      "eval_samples_per_second": 23.378,
      "eval_steps_per_second": 5.856,
      "step": 800
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00017348376244405512,
      "loss": 0.6002,
      "step": 810
    },
    {
      "epoch": 1.42,
      "eval_loss": 0.4929651618003845,
      "eval_runtime": 21.3604,
      "eval_samples_per_second": 23.361,
      "eval_steps_per_second": 5.852,
      "step": 810
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.000172856534823693,
      "loss": 0.5557,
      "step": 820
    },
    {
      "epoch": 1.44,
      "eval_loss": 0.4913093149662018,
      "eval_runtime": 21.3626,
      "eval_samples_per_second": 23.359,
      "eval_steps_per_second": 5.851,
      "step": 820
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00017222313787109496,
      "loss": 0.58,
      "step": 830
    },
    {
      "epoch": 1.46,
      "eval_loss": 0.4909800887107849,
      "eval_runtime": 21.4163,
      "eval_samples_per_second": 23.3,
      "eval_steps_per_second": 5.837,
      "step": 830
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00017158362522093153,
      "loss": 0.5459,
      "step": 840
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.4883653223514557,
      "eval_runtime": 21.3483,
      "eval_samples_per_second": 23.374,
      "eval_steps_per_second": 5.855,
      "step": 840
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00017093805102573706,
      "loss": 0.5871,
      "step": 850
    },
    {
      "epoch": 1.49,
      "eval_loss": 0.48601067066192627,
      "eval_runtime": 21.3674,
      "eval_samples_per_second": 23.353,
      "eval_steps_per_second": 5.85,
      "step": 850
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00017028646995132435,
      "loss": 0.5554,
      "step": 860
    },
    {
      "epoch": 1.51,
      "eval_loss": 0.4856807291507721,
      "eval_runtime": 21.366,
      "eval_samples_per_second": 23.355,
      "eval_steps_per_second": 5.85,
      "step": 860
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001696289371721556,
      "loss": 0.5819,
      "step": 870
    },
    {
      "epoch": 1.53,
      "eval_loss": 0.4648899435997009,
      "eval_runtime": 21.3516,
      "eval_samples_per_second": 23.371,
      "eval_steps_per_second": 5.854,
      "step": 870
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016896550836667035,
      "loss": 0.5649,
      "step": 880
    },
    {
      "epoch": 1.55,
      "eval_loss": 0.47903972864151,
      "eval_runtime": 21.3528,
      "eval_samples_per_second": 23.369,
      "eval_steps_per_second": 5.854,
      "step": 880
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016829623971257088,
      "loss": 0.5779,
      "step": 890
    },
    {
      "epoch": 1.56,
      "eval_loss": 0.4807458519935608,
      "eval_runtime": 21.377,
      "eval_samples_per_second": 23.343,
      "eval_steps_per_second": 5.847,
      "step": 890
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016762118788206487,
      "loss": 0.5756,
      "step": 900
    },
    {
      "epoch": 1.58,
      "eval_loss": 0.483437180519104,
      "eval_runtime": 21.3913,
      "eval_samples_per_second": 23.327,
      "eval_steps_per_second": 5.843,
      "step": 900
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.000166940410037067,
      "loss": 0.5563,
      "step": 910
    },
    {
      "epoch": 1.6,
      "eval_loss": 0.49455228447914124,
      "eval_runtime": 21.365,
      "eval_samples_per_second": 23.356,
      "eval_steps_per_second": 5.851,
      "step": 910
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00016625396382435813,
      "loss": 0.5393,
      "step": 920
    },
    {
      "epoch": 1.62,
      "eval_loss": 0.4847542643547058,
      "eval_runtime": 21.3614,
      "eval_samples_per_second": 23.36,
      "eval_steps_per_second": 5.852,
      "step": 920
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016556190737070428,
      "loss": 0.5551,
      "step": 930
    },
    {
      "epoch": 1.63,
      "eval_loss": 0.4845309257507324,
      "eval_runtime": 21.4008,
      "eval_samples_per_second": 23.317,
      "eval_steps_per_second": 5.841,
      "step": 930
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00016486429927793436,
      "loss": 0.5687,
      "step": 940
    },
    {
      "epoch": 1.65,
      "eval_loss": 0.4806869626045227,
      "eval_runtime": 21.374,
      "eval_samples_per_second": 23.346,
      "eval_steps_per_second": 5.848,
      "step": 940
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00016416119861797796,
      "loss": 0.5469,
      "step": 950
    },
    {
      "epoch": 1.67,
      "eval_loss": 0.4748505651950836,
      "eval_runtime": 21.355,
      "eval_samples_per_second": 23.367,
      "eval_steps_per_second": 5.853,
      "step": 950
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001634526649278632,
      "loss": 0.5771,
      "step": 960
    },
    {
      "epoch": 1.69,
      "eval_loss": 0.4859110414981842,
      "eval_runtime": 21.3418,
      "eval_samples_per_second": 23.381,
      "eval_steps_per_second": 5.857,
      "step": 960
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00016273875820467545,
      "loss": 0.5689,
      "step": 970
    },
    {
      "epoch": 1.7,
      "eval_loss": 0.4734295606613159,
      "eval_runtime": 21.3607,
      "eval_samples_per_second": 23.361,
      "eval_steps_per_second": 5.852,
      "step": 970
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001620195389004767,
      "loss": 0.5741,
      "step": 980
    },
    {
      "epoch": 1.72,
      "eval_loss": 0.4881950914859772,
      "eval_runtime": 21.3786,
      "eval_samples_per_second": 23.341,
      "eval_steps_per_second": 5.847,
      "step": 980
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00016129506791718665,
      "loss": 0.5643,
      "step": 990
    },
    {
      "epoch": 1.74,
      "eval_loss": 0.4815501570701599,
      "eval_runtime": 21.3699,
      "eval_samples_per_second": 23.351,
      "eval_steps_per_second": 5.849,
      "step": 990
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00016056540660142586,
      "loss": 0.5603,
      "step": 1000
    },
    {
      "epoch": 1.76,
      "eval_loss": 0.46760401129722595,
      "eval_runtime": 21.354,
      "eval_samples_per_second": 23.368,
      "eval_steps_per_second": 5.854,
      "step": 1000
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001598306167393208,
      "loss": 0.5925,
      "step": 1010
    },
    {
      "epoch": 1.77,
      "eval_loss": 0.46860912442207336,
      "eval_runtime": 21.3958,
      "eval_samples_per_second": 23.322,
      "eval_steps_per_second": 5.842,
      "step": 1010
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015909076055127202,
      "loss": 0.5834,
      "step": 1020
    },
    {
      "epoch": 1.79,
      "eval_loss": 0.47431066632270813,
      "eval_runtime": 21.4034,
      "eval_samples_per_second": 23.314,
      "eval_steps_per_second": 5.84,
      "step": 1020
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00019360595357389735,
      "loss": 0.5902,
      "step": 1030
    },
    {
      "epoch": 1.81,
      "eval_loss": 0.49162757396698,
      "eval_runtime": 38.6636,
      "eval_samples_per_second": 12.906,
      "eval_steps_per_second": 3.233,
      "step": 1030
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00019348256763960145,
      "loss": 0.5777,
      "step": 1040
    },
    {
      "epoch": 1.83,
      "eval_loss": 0.47481468319892883,
      "eval_runtime": 41.2268,
      "eval_samples_per_second": 12.104,
      "eval_steps_per_second": 3.032,
      "step": 1040
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00019335804264972018,
      "loss": 0.5921,
      "step": 1050
    },
    {
      "epoch": 1.84,
      "eval_loss": 0.48432889580726624,
      "eval_runtime": 30.5847,
      "eval_samples_per_second": 16.315,
      "eval_steps_per_second": 4.087,
      "step": 1050
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00019323238012155123,
      "loss": 0.5877,
      "step": 1060
    },
    {
      "epoch": 1.86,
      "eval_loss": 0.47419798374176025,
      "eval_runtime": 37.8731,
      "eval_samples_per_second": 13.176,
      "eval_steps_per_second": 3.3,
      "step": 1060
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00019310558158625285,
      "loss": 0.5453,
      "step": 1070
    },
    {
      "epoch": 1.88,
      "eval_loss": 0.4705266058444977,
      "eval_runtime": 22.4824,
      "eval_samples_per_second": 22.195,
      "eval_steps_per_second": 2.802,
      "step": 1070
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.5445,
      "step": 1080
    },
    {
      "epoch": 1.9,
      "eval_loss": 0.4662667214870453,
      "eval_runtime": 31.6864,
      "eval_samples_per_second": 15.748,
      "eval_steps_per_second": 1.988,
      "step": 1080
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00019284858268809137,
      "loss": 0.5686,
      "step": 1090
    },
    {
      "epoch": 1.92,
      "eval_loss": 0.47445282340049744,
      "eval_runtime": 27.1784,
      "eval_samples_per_second": 18.36,
      "eval_steps_per_second": 2.318,
      "step": 1090
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.5712,
      "step": 1100
    },
    {
      "epoch": 1.93,
      "eval_loss": 0.48884764313697815,
      "eval_runtime": 37.118,
      "eval_samples_per_second": 13.444,
      "eval_steps_per_second": 1.697,
      "step": 1100
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001925870584809995,
      "loss": 0.6032,
      "step": 1110
    },
    {
      "epoch": 1.95,
      "eval_loss": 0.48608502745628357,
      "eval_runtime": 36.4351,
      "eval_samples_per_second": 13.696,
      "eval_steps_per_second": 1.729,
      "step": 1110
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00019245460336123134,
      "loss": 0.5491,
      "step": 1120
    },
    {
      "epoch": 1.97,
      "eval_loss": 0.472098708152771,
      "eval_runtime": 22.4827,
      "eval_samples_per_second": 22.195,
      "eval_steps_per_second": 2.802,
      "step": 1120
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00019232102171129811,
      "loss": 0.5452,
      "step": 1130
    },
    {
      "epoch": 1.99,
      "eval_loss": 0.4644794762134552,
      "eval_runtime": 27.0746,
      "eval_samples_per_second": 18.431,
      "eval_steps_per_second": 2.327,
      "step": 1130
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00019218631515885006,
      "loss": 0.5526,
      "step": 1140
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.48768851161003113,
      "eval_runtime": 32.1887,
      "eval_samples_per_second": 15.502,
      "eval_steps_per_second": 1.957,
      "step": 1140
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00019205048534524406,
      "loss": 0.5443,
      "step": 1150
    },
    {
      "epoch": 2.02,
      "eval_loss": 0.4716103971004486,
      "eval_runtime": 30.3462,
      "eval_samples_per_second": 16.444,
      "eval_steps_per_second": 2.076,
      "step": 1150
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00019191353392552344,
      "loss": 0.5103,
      "step": 1160
    },
    {
      "epoch": 2.04,
      "eval_loss": 0.46319034695625305,
      "eval_runtime": 23.7207,
      "eval_samples_per_second": 21.037,
      "eval_steps_per_second": 2.656,
      "step": 1160
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00019177546256839812,
      "loss": 0.5202,
      "step": 1170
    },
    {
      "epoch": 2.06,
      "eval_loss": 0.4802156984806061,
      "eval_runtime": 24.1547,
      "eval_samples_per_second": 20.658,
      "eval_steps_per_second": 2.608,
      "step": 1170
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00019163627295622397,
      "loss": 0.5436,
      "step": 1180
    },
    {
      "epoch": 2.07,
      "eval_loss": 0.4681110680103302,
      "eval_runtime": 26.9736,
      "eval_samples_per_second": 18.5,
      "eval_steps_per_second": 2.336,
      "step": 1180
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001914959667849825,
      "loss": 0.5454,
      "step": 1190
    },
    {
      "epoch": 2.09,
      "eval_loss": 0.470931738615036,
      "eval_runtime": 36.9982,
      "eval_samples_per_second": 13.487,
      "eval_steps_per_second": 1.703,
      "step": 1190
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.5183,
      "step": 1200
    },
    {
      "epoch": 2.11,
      "eval_loss": 0.47423675656318665,
      "eval_runtime": 33.685,
      "eval_samples_per_second": 14.814,
      "eval_steps_per_second": 1.87,
      "step": 1200
    },
    {
      "epoch": 2.11,
      "step": 1201,
      "total_flos": 3.450559153050747e+17,
      "train_loss": 0.000492346822768822,
      "train_runtime": 4.9952,
      "train_samples_per_second": 3843.723,
      "train_steps_per_second": 240.233
    }
  ],
  "logging_steps": 10,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 3.450559153050747e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}