{
  "best_metric": 3.2069807052612305,
  "best_model_checkpoint": "output/kanye-west/checkpoint-1098",
  "epoch": 2.0,
  "global_step": 1098,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00013717009945820184,
      "loss": 4.0869,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001370804238981834,
      "loss": 3.916,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013693105149335086,
      "loss": 3.8652,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00013672211245699381,
      "loss": 3.7385,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001364537889287738,
      "loss": 3.9589,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001361263148159465,
      "loss": 3.7062,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001357399755894565,
      "loss": 3.7812,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013529510803508195,
      "loss": 3.7942,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013479209995984626,
      "loss": 3.5225,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001342313898539529,
      "loss": 3.5656,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013361346650853767,
      "loss": 3.6263,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001329388685895719,
      "loss": 3.4553,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001322081841682881,
      "loss": 3.5207,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00013142205020853694,
      "loss": 3.6126,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001305811520115232,
      "loss": 3.7414,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001296862226184039,
      "loss": 3.7092,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001287380421712702,
      "loss": 3.6186,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001277374372330694,
      "loss": 3.5288,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00012668528006706028,
      "loss": 3.6937,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001255824878764301,
      "loss": 3.4367,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012443002200473538,
      "loss": 3.6998,
      "step": 105
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001232288870978644,
      "loss": 3.6457,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012198013022825123,
      "loss": 3.7173,
      "step": 115
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00012068483998210507,
      "loss": 3.6357,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011934414551045056,
      "loss": 3.5173,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011795921554480633,
      "loss": 3.5689,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00011653125737835967,
      "loss": 3.7171,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011506151581352585,
      "loss": 3.5809,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00011355127207680896,
      "loss": 3.6263,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001120018427019109,
      "loss": 3.2874,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00011041457838206164,
      "loss": 3.5598,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010879086279257143,
      "loss": 3.4501,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010713211138463122,
      "loss": 3.5461,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010543977015141323,
      "loss": 3.7201,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00010371531436754662,
      "loss": 3.5397,
      "step": 175
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001019602473030677,
      "loss": 3.4675,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00010017609891296537,
      "loss": 3.5239,
      "step": 185
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.836442450346448e-05,
      "loss": 3.7958,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.652680337620956e-05,
      "loss": 3.4768,
      "step": 195
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.466483745153069e-05,
      "loss": 3.743,
      "step": 200
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.278014987199233e-05,
      "loss": 3.4125,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.08743835874413e-05,
      "loss": 3.4941,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.894919992278866e-05,
      "loss": 3.501,
      "step": 215
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.700627712977306e-05,
      "loss": 3.5539,
      "step": 220
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.50473089239683e-05,
      "loss": 3.6408,
      "step": 225
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.307400300831083e-05,
      "loss": 3.4931,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.108807958443359e-05,
      "loss": 3.5534,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.909126985310467e-05,
      "loss": 3.4332,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.708531450507727e-05,
      "loss": 3.3946,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.507196220366703e-05,
      "loss": 3.5149,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.305296806037965e-05,
      "loss": 3.5828,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.10300921049169e-05,
      "loss": 3.5274,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.900509775089564e-05,
      "loss": 3.5936,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.697975025861685e-05,
      "loss": 3.75,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.495581519622486e-05,
      "loss": 3.5977,
      "step": 275
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.293505690059801e-05,
      "loss": 3.5072,
      "step": 280
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.0919236939313083e-05,
      "loss": 3.402,
      "step": 285
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.8910112575023444e-05,
      "loss": 3.4915,
      "step": 290
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.690943523359007e-05,
      "loss": 3.428,
      "step": 295
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.4918948977300765e-05,
      "loss": 3.4624,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.294038898450848e-05,
      "loss": 3.5907,
      "step": 305
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.097548003701393e-05,
      "loss": 3.3823,
      "step": 310
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.902593501651139e-05,
      "loss": 3.392,
      "step": 315
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.709345341140823e-05,
      "loss": 3.5123,
      "step": 320
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.517971983531982e-05,
      "loss": 3.3342,
      "step": 325
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.3286402558531396e-05,
      "loss": 3.3545,
      "step": 330
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.141515205370683e-05,
      "loss": 3.4315,
      "step": 335
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.956759955711245e-05,
      "loss": 3.3875,
      "step": 340
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.7745355646609715e-05,
      "loss": 3.5645,
      "step": 345
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.5950008837656755e-05,
      "loss": 3.6196,
      "step": 350
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.418312419854227e-05,
      "loss": 3.3208,
      "step": 355
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.244624198605935e-05,
      "loss": 3.4232,
      "step": 360
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0740876302808455e-05,
      "loss": 3.3791,
      "step": 365
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.9068513777299503e-05,
      "loss": 3.4745,
      "step": 370
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.7430612268004742e-05,
      "loss": 3.3075,
      "step": 375
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.5828599592490882e-05,
      "loss": 3.4197,
      "step": 380
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.4263872282739445e-05,
      "loss": 3.4358,
      "step": 385
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.2737794367739613e-05,
      "loss": 3.6132,
      "step": 390
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.1251696184415103e-05,
      "loss": 3.4919,
      "step": 395
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.980687321792179e-05,
      "loss": 3.6213,
      "step": 400
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.8404584972326772e-05,
      "loss": 3.3808,
      "step": 405
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.704605387265335e-05,
      "loss": 3.4937,
      "step": 410
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.573246419924937e-05,
      "loss": 3.5387,
      "step": 415
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4464961055407408e-05,
      "loss": 3.5004,
      "step": 420
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3244649369137107e-05,
      "loss": 3.2293,
      "step": 425
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2072592929959826e-05,
      "loss": 3.4326,
      "step": 430
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.0949813461565069e-05,
      "loss": 3.3648,
      "step": 435
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.87728973113722e-06,
      "loss": 3.5226,
      "step": 440
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.855956696129068e-06,
      "loss": 3.464,
      "step": 445
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.88670468922587e-06,
      "loss": 3.3838,
      "step": 450
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.97037864221025e-06,
      "loss": 3.6019,
      "step": 455
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.107777349404974e-06,
      "loss": 3.3959,
      "step": 460
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.299652771335096e-06,
      "loss": 3.2737,
      "step": 465
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.546709379217107e-06,
      "loss": 3.5271,
      "step": 470
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.849603540845984e-06,
      "loss": 3.1793,
      "step": 475
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.2089429484158363e-06,
      "loss": 3.5368,
      "step": 480
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.625286088772771e-06,
      "loss": 3.4441,
      "step": 485
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.0991417565619363e-06,
      "loss": 3.3483,
      "step": 490
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6309686106928596e-06,
      "loss": 3.5513,
      "step": 495
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.221174774510045e-06,
      "loss": 3.3951,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.701174800172293e-07,
      "loss": 3.5312,
      "step": 505
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.78102756465344e-07,
      "loss": 3.4318,
      "step": 510
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.45385163575888e-07,
      "loss": 3.4111,
      "step": 515
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7216756963205766e-07,
      "loss": 3.2725,
      "step": 520
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.860097463115006e-08,
      "loss": 3.6447,
      "step": 525
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.784378652498966e-09,
      "loss": 3.4154,
      "step": 530
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.426886558532715,
      "eval_runtime": 40.4727,
      "eval_samples_per_second": 22.04,
      "eval_steps_per_second": 2.767,
      "step": 532
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.200254683906266e-07,
      "loss": 3.4087,
      "step": 535
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.09574339006257e-08,
      "loss": 3.3394,
      "step": 540
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.797008773112274e-08,
      "loss": 3.413,
      "step": 545
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.219294786453247,
      "eval_runtime": 34.625,
      "eval_samples_per_second": 21.863,
      "eval_steps_per_second": 2.744,
      "step": 549
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.123176456552244e-09,
      "loss": 3.4155,
      "step": 550
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.0430490758340044e-08,
      "loss": 3.3359,
      "step": 555
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.3585985413598608e-07,
      "loss": 3.4372,
      "step": 560
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.8733314924638363e-07,
      "loss": 3.5177,
      "step": 565
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.947263818497525e-07,
      "loss": 3.3014,
      "step": 570
    },
    {
      "epoch": 1.05,
      "learning_rate": 7.578697823098032e-07,
      "loss": 3.4521,
      "step": 575
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.0765479445652215e-06,
      "loss": 3.263,
      "step": 580
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.4505000024584544e-06,
      "loss": 3.3575,
      "step": 585
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.8794198432776367e-06,
      "loss": 3.5385,
      "step": 590
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.362956358336902e-06,
      "loss": 3.2621,
      "step": 595
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.900713730389673e-06,
      "loss": 3.3471,
      "step": 600
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.4922517576400357e-06,
      "loss": 3.3317,
      "step": 605
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.137086214086682e-06,
      "loss": 3.3101,
      "step": 610
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.834689245904529e-06,
      "loss": 3.5044,
      "step": 615
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.584489803539656e-06,
      "loss": 3.2145,
      "step": 620
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.385874109163592e-06,
      "loss": 3.088,
      "step": 625
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.238186159104615e-06,
      "loss": 3.2756,
      "step": 630
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.140728260844604e-06,
      "loss": 3.3539,
      "step": 635
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.09276160414173e-06,
      "loss": 3.3302,
      "step": 640
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.0093506865811846e-05,
      "loss": 3.3183,
      "step": 645
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.1142144847673131e-05,
      "loss": 3.3733,
      "step": 650
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.2237817147132003e-05,
      "loss": 3.3992,
      "step": 655
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3379626859861349e-05,
      "loss": 3.4621,
      "step": 660
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.4566639313995615e-05,
      "loss": 3.4193,
      "step": 665
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.5797882835242138e-05,
      "loss": 3.4483,
      "step": 670
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7072349542282338e-05,
      "loss": 3.1321,
      "step": 675
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.8388996171811105e-05,
      "loss": 3.5093,
      "step": 680
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.9746744932540055e-05,
      "loss": 3.3516,
      "step": 685
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.1144484387464373e-05,
      "loss": 3.3896,
      "step": 690
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.258107036367215e-05,
      "loss": 3.4337,
      "step": 695
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.4055326888950756e-05,
      "loss": 3.3167,
      "step": 700
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.5566047154423428e-05,
      "loss": 3.3134,
      "step": 705
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.711199450242914e-05,
      "loss": 3.2474,
      "step": 710
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.8691903438835377e-05,
      "loss": 3.234,
      "step": 715
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.030448066895703e-05,
      "loss": 3.3668,
      "step": 720
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.194840615623184e-05,
      "loss": 3.4867,
      "step": 725
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.36223342027866e-05,
      "loss": 3.3089,
      "step": 730
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.53248945510095e-05,
      "loss": 3.273,
      "step": 735
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.7054693505226934e-05,
      "loss": 3.3763,
      "step": 740
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.8810315072565846e-05,
      "loss": 3.4708,
      "step": 745
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.0590322122068896e-05,
      "loss": 3.3732,
      "step": 750
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.239325756111289e-05,
      "loss": 3.3236,
      "step": 755
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.421764552816718e-05,
      "loss": 3.3189,
      "step": 760
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.6061992600916735e-05,
      "loss": 3.3587,
      "step": 765
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.792478901875958e-05,
      "loss": 3.3553,
      "step": 770
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.980450991867903e-05,
      "loss": 3.3437,
      "step": 775
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.1699616583478625e-05,
      "loss": 3.113,
      "step": 780
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.360855770135732e-05,
      "loss": 3.5307,
      "step": 785
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.5529770635795374e-05,
      "loss": 3.277,
      "step": 790
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.746168270470958e-05,
      "loss": 3.4986,
      "step": 795
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.940271246783254e-05,
      "loss": 3.0947,
      "step": 800
    },
    {
      "epoch": 1.47,
      "learning_rate": 6.13512710212607e-05,
      "loss": 3.453,
      "step": 805
    },
    {
      "epoch": 1.48,
      "learning_rate": 6.330576329811206e-05,
      "loss": 3.2989,
      "step": 810
    },
    {
      "epoch": 1.48,
      "learning_rate": 6.526458937422915e-05,
      "loss": 3.2466,
      "step": 815
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.722614577785811e-05,
      "loss": 3.3078,
      "step": 820
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.918882680223113e-05,
      "loss": 3.3115,
      "step": 825
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.115102581997948e-05,
      "loss": 3.401,
      "step": 830
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.311113659829913e-05,
      "loss": 3.388,
      "step": 835
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.506755461379409e-05,
      "loss": 3.1893,
      "step": 840
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.701867836592025e-05,
      "loss": 3.1964,
      "step": 845
    },
    {
      "epoch": 1.55,
      "learning_rate": 7.896291068795451e-05,
      "loss": 3.1817,
      "step": 850
    },
    {
      "epoch": 1.56,
      "learning_rate": 8.089866005441645e-05,
      "loss": 3.4222,
      "step": 855
    },
    {
      "epoch": 1.57,
      "learning_rate": 8.28243418838726e-05,
      "loss": 3.3935,
      "step": 860
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.473837983605534e-05,
      "loss": 3.317,
      "step": 865
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.663920710223691e-05,
      "loss": 3.3184,
      "step": 870
    },
    {
      "epoch": 1.59,
      "learning_rate": 8.852526768780001e-05,
      "loss": 3.3909,
      "step": 875
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.039501768595671e-05,
      "loss": 3.3281,
      "step": 880
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.224692654157222e-05,
      "loss": 3.4081,
      "step": 885
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.407947830405896e-05,
      "loss": 3.3443,
      "step": 890
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.589117286831579e-05,
      "loss": 3.2831,
      "step": 895
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.768052720269644e-05,
      "loss": 3.3635,
      "step": 900
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.944607656300112e-05,
      "loss": 3.3023,
      "step": 905
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001011863756914993,
      "loss": 3.3958,
      "step": 910
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00010290000000000001,
      "loss": 3.439,
      "step": 915
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00010458554673600303,
      "loss": 3.3205,
      "step": 920
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00010624163613097559,
      "loss": 3.3548,
      "step": 925
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00010786691252981412,
      "loss": 3.402,
      "step": 930
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00010946004550056765,
      "loss": 3.1367,
      "step": 935
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00011101973092351368,
      "loss": 3.3214,
      "step": 940
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001125446920586948,
      "loss": 3.4555,
      "step": 945
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001140336805910432,
      "loss": 3.1367,
      "step": 950
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011548547765223617,
      "loss": 3.391,
      "step": 955
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00011689889481844766,
      "loss": 3.0626,
      "step": 960
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011827277508317747,
      "loss": 3.4176,
      "step": 965
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00011960599380436336,
      "loss": 3.2121,
      "step": 970
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012089745962499954,
      "loss": 3.231,
      "step": 975
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00012214611536650856,
      "loss": 3.6329,
      "step": 980
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.000123350938894135,
      "loss": 3.1573,
      "step": 985
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00012451094395365327,
      "loss": 3.3721,
      "step": 990
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00012562518097870298,
      "loss": 3.3447,
      "step": 995
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001266927378680932,
      "loss": 3.3603,
      "step": 1000
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00012771274073243748,
      "loss": 3.1145,
      "step": 1005
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00012868435460950916,
      "loss": 3.2607,
      "step": 1010
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00012960678414773185,
      "loss": 3.3824,
      "step": 1015
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00013047927425724446,
      "loss": 3.4136,
      "step": 1020
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.000131301110728009,
      "loss": 3.386,
      "step": 1025
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013207162081445436,
      "loss": 3.2408,
      "step": 1030
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00013279017378617784,
      "loss": 3.2928,
      "step": 1035
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00013345618144425364,
      "loss": 3.16,
      "step": 1040
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00013406909860272533,
      "loss": 3.444,
      "step": 1045
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013462842353488877,
      "loss": 3.5022,
      "step": 1050
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001351336983839996,
      "loss": 3.4006,
      "step": 1055
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00013558450953806924,
      "loss": 3.436,
      "step": 1060
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013598048796844284,
      "loss": 3.3172,
      "step": 1065
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001363213095318818,
      "loss": 3.4138,
      "step": 1070
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013660669523590338,
      "loss": 3.3525,
      "step": 1075
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013683641146716082,
      "loss": 3.5252,
      "step": 1080
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013701027018267633,
      "loss": 3.264,
      "step": 1085
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013712812906377096,
      "loss": 3.262,
      "step": 1090
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013718989163256484,
      "loss": 3.1863,
      "step": 1095
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.2069807052612305,
      "eval_runtime": 34.3846,
      "eval_samples_per_second": 22.016,
      "eval_steps_per_second": 2.763,
      "step": 1098
    }
  ],
  "max_steps": 1098,
  "num_train_epochs": 2,
  "total_flos": 1146157498368000.0,
  "trial_name": null,
  "trial_params": null
}