{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 907,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 7.142857142857143e-07,
      "loss": 1.0707,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 1.0883,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 1.0538,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 1.0773,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 1.057,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.785714285714286e-05,
      "loss": 1.046,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9999744523980044e-05,
      "loss": 1.0391,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9996870568665825e-05,
      "loss": 1.0144,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9990804233834707e-05,
      "loss": 1.0181,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9981547456697224e-05,
      "loss": 1.0307,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.996910319329303e-05,
      "loss": 1.0375,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.995347541754689e-05,
      "loss": 1.0107,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.993466911999968e-05,
      "loss": 1.0326,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9912690306214705e-05,
      "loss": 1.03,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.988754599485991e-05,
      "loss": 1.0201,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9859244215466525e-05,
      "loss": 1.0059,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.982779400586497e-05,
      "loss": 1.0111,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9793205409298696e-05,
      "loss": 0.988,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.975548947121702e-05,
      "loss": 1.0176,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9714658235747888e-05,
      "loss": 1.0027,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9670724741851737e-05,
      "loss": 1.0196,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9623703019157637e-05,
      "loss": 1.0006,
      "step": 105
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9573608083483124e-05,
      "loss": 0.9745,
      "step": 110
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9520455932039074e-05,
      "loss": 1.0004,
      "step": 115
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9464263538321176e-05,
      "loss": 1.0367,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9405048846689668e-05,
      "loss": 0.9981,
      "step": 125
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9342830766639013e-05,
      "loss": 0.9896,
      "step": 130
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.927762916675938e-05,
      "loss": 1.0117,
      "step": 135
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9209464868391863e-05,
      "loss": 1.0193,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9138359638979423e-05,
      "loss": 0.9941,
      "step": 145
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9064336185115718e-05,
      "loss": 1.01,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8987418145294045e-05,
      "loss": 0.9847,
      "step": 155
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8907630082358657e-05,
      "loss": 1.0326,
      "step": 160
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8824997475660925e-05,
      "loss": 1.0172,
      "step": 165
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8739546712922805e-05,
      "loss": 0.996,
      "step": 170
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.865130508181026e-05,
      "loss": 1.0048,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8560300761219246e-05,
      "loss": 0.9907,
      "step": 180
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8466562812277146e-05,
      "loss": 1.0163,
      "step": 185
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8370121169062436e-05,
      "loss": 1.0111,
      "step": 190
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8271006629045618e-05,
      "loss": 1.0038,
      "step": 195
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8169250843254397e-05,
      "loss": 1.0324,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8064886306166326e-05,
      "loss": 1.0097,
      "step": 205
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.795794634533208e-05,
      "loss": 0.9967,
      "step": 210
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7848465110732713e-05,
      "loss": 1.0042,
      "step": 215
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7736477563874274e-05,
      "loss": 1.0252,
      "step": 220
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7622019466623265e-05,
      "loss": 1.0163,
      "step": 225
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7505127369786524e-05,
      "loss": 0.9979,
      "step": 230
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.7385838601439193e-05,
      "loss": 1.0124,
      "step": 235
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.72641912550044e-05,
      "loss": 0.9971,
      "step": 240
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7140224177088638e-05,
      "loss": 0.9959,
      "step": 245
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.7013976955076534e-05,
      "loss": 0.9944,
      "step": 250
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6885489904489113e-05,
      "loss": 1.0211,
      "step": 255
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6754804056109528e-05,
      "loss": 0.9932,
      "step": 260
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6621961142880368e-05,
      "loss": 1.0241,
      "step": 265
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.6487003586576755e-05,
      "loss": 0.9861,
      "step": 270
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.6349974484259452e-05,
      "loss": 1.0314,
      "step": 275
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.6210917594512355e-05,
      "loss": 1.0052,
      "step": 280
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.6069877323468713e-05,
      "loss": 1.0184,
      "step": 285
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.5926898710630562e-05,
      "loss": 0.9924,
      "step": 290
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5782027414485906e-05,
      "loss": 0.9744,
      "step": 295
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5635309697928244e-05,
      "loss": 0.9718,
      "step": 300
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.5486792413483057e-05,
      "loss": 0.9897,
      "step": 305
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.5336522988346047e-05,
      "loss": 1.0158,
      "step": 310
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.5184549409237806e-05,
      "loss": 1.0233,
      "step": 315
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.503092020707985e-05,
      "loss": 1.0142,
      "step": 320
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4875684441496883e-05,
      "loss": 1.0037,
      "step": 325
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4718891685150151e-05,
      "loss": 0.9973,
      "step": 330
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.456059200790706e-05,
      "loss": 1.0046,
      "step": 335
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.4400835960851938e-05,
      "loss": 1.0032,
      "step": 340
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.4239674560143168e-05,
      "loss": 0.9965,
      "step": 345
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.407715927072181e-05,
      "loss": 1.0034,
      "step": 350
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3913341989876876e-05,
      "loss": 1.0264,
      "step": 355
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3748275030672569e-05,
      "loss": 1.0017,
      "step": 360
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3582011105242734e-05,
      "loss": 0.9878,
      "step": 365
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.341460330795789e-05,
      "loss": 1.0051,
      "step": 370
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.3246105098470166e-05,
      "loss": 1.0036,
      "step": 375
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.3076570284641625e-05,
      "loss": 0.9857,
      "step": 380
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.2906053005361366e-05,
      "loss": 1.0268,
      "step": 385
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.273460771325693e-05,
      "loss": 1.0209,
      "step": 390
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.2562289157305514e-05,
      "loss": 0.9882,
      "step": 395
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.238915236535054e-05,
      "loss": 0.9885,
      "step": 400
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2215252626529197e-05,
      "loss": 1.0106,
      "step": 405
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2040645473616496e-05,
      "loss": 0.9831,
      "step": 410
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1865386665291591e-05,
      "loss": 1.0113,
      "step": 415
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1689532168331877e-05,
      "loss": 1.001,
      "step": 420
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.151313813974071e-05,
      "loss": 1.0121,
      "step": 425
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.1336260908814335e-05,
      "loss": 1.0086,
      "step": 430
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.1158956959153808e-05,
      "loss": 1.0244,
      "step": 435
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0981282910627646e-05,
      "loss": 0.992,
      "step": 440
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0803295501290954e-05,
      "loss": 1.0017,
      "step": 445
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.062505156926681e-05,
      "loss": 0.9844,
      "step": 450
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0446608034595718e-05,
      "loss": 0.9988,
      "step": 455
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.0268021881058858e-05,
      "loss": 1.01,
      "step": 460
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.0089350137981022e-05,
      "loss": 1.0094,
      "step": 465
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.910649862018981e-06,
      "loss": 1.0195,
      "step": 470
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.731978118941143e-06,
      "loss": 0.9931,
      "step": 475
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.553391965404287e-06,
      "loss": 0.9998,
      "step": 480
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.374948430733191e-06,
      "loss": 1.0168,
      "step": 485
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.196704498709049e-06,
      "loss": 1.0121,
      "step": 490
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.018717089372356e-06,
      "loss": 1.0011,
      "step": 495
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.841043040846192e-06,
      "loss": 1.0001,
      "step": 500
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.663739091185668e-06,
      "loss": 0.9908,
      "step": 505
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.486861860259294e-06,
      "loss": 0.9903,
      "step": 510
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.310467831668128e-06,
      "loss": 1.0138,
      "step": 515
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.134613334708412e-06,
      "loss": 1.0015,
      "step": 520
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.959354526383502e-06,
      "loss": 0.9801,
      "step": 525
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.784747373470806e-06,
      "loss": 0.9955,
      "step": 530
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.610847634649459e-06,
      "loss": 0.9947,
      "step": 535
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.43771084269449e-06,
      "loss": 1.0037,
      "step": 540
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.2653922867430725e-06,
      "loss": 0.9997,
      "step": 545
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.093946994638638e-06,
      "loss": 0.9735,
      "step": 550
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.923429715358377e-06,
      "loss": 0.9877,
      "step": 555
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.753894901529834e-06,
      "loss": 0.9884,
      "step": 560
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.585396692042113e-06,
      "loss": 1.0122,
      "step": 565
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.417988894757267e-06,
      "loss": 1.0112,
      "step": 570
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.251724969327435e-06,
      "loss": 1.0007,
      "step": 575
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.086658010123125e-06,
      "loss": 1.0037,
      "step": 580
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.9228407292781945e-06,
      "loss": 0.9924,
      "step": 585
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.760325439856833e-06,
      "loss": 0.9994,
      "step": 590
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.599164039148066e-06,
      "loss": 0.9928,
      "step": 595
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.4394079920929425e-06,
      "loss": 1.023,
      "step": 600
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.281108314849851e-06,
      "loss": 0.9677,
      "step": 605
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.124315558503122e-06,
      "loss": 0.9957,
      "step": 610
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.96907979292015e-06,
      "loss": 1.013,
      "step": 615
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.815450590762203e-06,
      "loss": 1.0111,
      "step": 620
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.663477011653955e-06,
      "loss": 1.0065,
      "step": 625
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.513207586516943e-06,
      "loss": 1.021,
      "step": 630
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.36469030207176e-06,
      "loss": 1.0109,
      "step": 635
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.217972585514095e-06,
      "loss": 1.0366,
      "step": 640
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0731012893694435e-06,
      "loss": 1.0129,
      "step": 645
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.930122676531287e-06,
      "loss": 1.0044,
      "step": 650
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7890824054876452e-06,
      "loss": 0.9931,
      "step": 655
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6500255157405504e-06,
      "loss": 0.9962,
      "step": 660
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5129964134232464e-06,
      "loss": 1.006,
      "step": 665
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.378038857119632e-06,
      "loss": 1.0132,
      "step": 670
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2451959438904735e-06,
      "loss": 0.9996,
      "step": 675
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.11451009551089e-06,
      "loss": 0.9911,
      "step": 680
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9860230449234705e-06,
      "loss": 0.9906,
      "step": 685
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.859775822911366e-06,
      "loss": 1.0027,
      "step": 690
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7358087449955996e-06,
      "loss": 0.988,
      "step": 695
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6141613985608093e-06,
      "loss": 1.0035,
      "step": 700
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.494872630213476e-06,
      "loss": 0.9979,
      "step": 705
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3779805333767403e-06,
      "loss": 0.99,
      "step": 710
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.263522436125729e-06,
      "loss": 1.0214,
      "step": 715
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.151534889267287e-06,
      "loss": 1.0037,
      "step": 720
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.042053654667925e-06,
      "loss": 0.9984,
      "step": 725
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9351136938336777e-06,
      "loss": 0.994,
      "step": 730
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.830749156745607e-06,
      "loss": 0.989,
      "step": 735
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7289933709543848e-06,
      "loss": 0.9995,
      "step": 740
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6298788309375646e-06,
      "loss": 0.9884,
      "step": 745
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5334371877228604e-06,
      "loss": 1.0202,
      "step": 750
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4396992387807574e-06,
      "loss": 0.9982,
      "step": 755
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3486949181897435e-06,
      "loss": 1.0206,
      "step": 760
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2604532870771968e-06,
      "loss": 1.0057,
      "step": 765
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1750025243390783e-06,
      "loss": 1.0007,
      "step": 770
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.092369917641345e-06,
      "loss": 1.0193,
      "step": 775
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0125818547059584e-06,
      "loss": 1.0146,
      "step": 780
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.356638148842856e-07,
      "loss": 1.0104,
      "step": 785
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.616403610205814e-07,
      "loss": 0.982,
      "step": 790
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.905351316081377e-07,
      "loss": 1.0158,
      "step": 795
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.223708332406187e-07,
      "loss": 0.9883,
      "step": 800
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.571692333609892e-07,
      "loss": 1.0272,
      "step": 805
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.949511533103336e-07,
      "loss": 1.0191,
      "step": 810
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.357364616788263e-07,
      "loss": 1.0136,
      "step": 815
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.795440679609298e-07,
      "loss": 0.9857,
      "step": 820
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.263919165168762e-07,
      "loss": 1.0191,
      "step": 825
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7629698084236665e-07,
      "loss": 1.0163,
      "step": 830
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.29275258148265e-07,
      "loss": 0.9955,
      "step": 835
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8534176425211166e-07,
      "loss": 1.0113,
      "step": 840
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.44510528782983e-07,
      "loss": 0.9853,
      "step": 845
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0679459070130693e-07,
      "loss": 1.0027,
      "step": 850
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.722059941350329e-07,
      "loss": 1.0057,
      "step": 855
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4075578453347504e-07,
      "loss": 1.007,
      "step": 860
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1245400514009352e-07,
      "loss": 0.9815,
      "step": 865
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.730969378529575e-08,
      "loss": 0.9968,
      "step": 870
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.533088000032273e-08,
      "loss": 0.9971,
      "step": 875
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.652458245311242e-08,
      "loss": 0.9909,
      "step": 880
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.089680670697148e-08,
      "loss": 0.9916,
      "step": 885
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.8452543302776016e-08,
      "loss": 1.0153,
      "step": 890
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.195766165295272e-09,
      "loss": 1.01,
      "step": 895
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.129431334175648e-09,
      "loss": 0.9951,
      "step": 900
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.5547601995912216e-10,
      "loss": 1.0177,
      "step": 905
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0098061561584473,
      "eval_runtime": 480.371,
      "eval_samples_per_second": 13.406,
      "eval_steps_per_second": 0.839,
      "step": 907
    },
    {
      "epoch": 1.0,
      "step": 907,
      "total_flos": 5.321288023160127e+18,
      "train_loss": 1.0062879709056614,
      "train_runtime": 14623.7103,
      "train_samples_per_second": 3.968,
      "train_steps_per_second": 0.062
    }
  ],
  "logging_steps": 5,
  "max_steps": 907,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 5.321288023160127e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}