{
  "best_metric": 0.12982094287872314,
  "best_model_checkpoint": "./results/checkpoint-881",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 881,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.9716231555051076e-05,
      "loss": 7.8572,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.943246311010216e-05,
      "loss": 3.0916,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.914869466515324e-05,
      "loss": 1.8922,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.886492622020432e-05,
      "loss": 1.3329,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.858115777525539e-05,
      "loss": 0.981,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.829738933030647e-05,
      "loss": 0.7023,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8013620885357555e-05,
      "loss": 0.5746,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.772985244040863e-05,
      "loss": 0.4267,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.74460839954597e-05,
      "loss": 0.4005,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.7162315550510784e-05,
      "loss": 0.3931,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.6878547105561864e-05,
      "loss": 0.3501,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.6594778660612945e-05,
      "loss": 0.3233,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.631101021566402e-05,
      "loss": 0.3265,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.602724177071509e-05,
      "loss": 0.3082,
      "step": 70
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.574347332576618e-05,
      "loss": 0.2988,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.5459704880817255e-05,
      "loss": 0.2786,
      "step": 80
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.5175936435868336e-05,
      "loss": 0.2757,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.489216799091941e-05,
      "loss": 0.2801,
      "step": 90
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.460839954597049e-05,
      "loss": 0.2606,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.432463110102157e-05,
      "loss": 0.2792,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.4040862656072645e-05,
      "loss": 0.2439,
      "step": 105
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.375709421112372e-05,
      "loss": 0.272,
      "step": 110
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.347332576617481e-05,
      "loss": 0.2479,
      "step": 115
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.318955732122588e-05,
      "loss": 0.2476,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.290578887627696e-05,
      "loss": 0.2336,
      "step": 125
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.2622020431328036e-05,
      "loss": 0.2419,
      "step": 130
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.233825198637912e-05,
      "loss": 0.2395,
      "step": 135
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.20544835414302e-05,
      "loss": 0.2335,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.177071509648127e-05,
      "loss": 0.2412,
      "step": 145
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.1486946651532346e-05,
      "loss": 0.2253,
      "step": 150
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.120317820658343e-05,
      "loss": 0.2131,
      "step": 155
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.091940976163451e-05,
      "loss": 0.2243,
      "step": 160
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.063564131668559e-05,
      "loss": 0.2353,
      "step": 165
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.035187287173666e-05,
      "loss": 0.192,
      "step": 170
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.006810442678774e-05,
      "loss": 0.2204,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.9784335981838824e-05,
      "loss": 0.2041,
      "step": 180
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.95005675368899e-05,
      "loss": 0.2267,
      "step": 185
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.921679909194098e-05,
      "loss": 0.2103,
      "step": 190
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.893303064699206e-05,
      "loss": 0.2004,
      "step": 195
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.8649262202043134e-05,
      "loss": 0.2099,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.8365493757094214e-05,
      "loss": 0.2022,
      "step": 205
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.808172531214529e-05,
      "loss": 0.2,
      "step": 210
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.779795686719637e-05,
      "loss": 0.2324,
      "step": 215
    },
    {
      "epoch": 0.25,
      "learning_rate": 3.751418842224745e-05,
      "loss": 0.2039,
      "step": 220
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.7230419977298524e-05,
      "loss": 0.2233,
      "step": 225
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.6946651532349605e-05,
      "loss": 0.1974,
      "step": 230
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.6662883087400686e-05,
      "loss": 0.2119,
      "step": 235
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.637911464245176e-05,
      "loss": 0.1909,
      "step": 240
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.609534619750284e-05,
      "loss": 0.1823,
      "step": 245
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.5811577752553915e-05,
      "loss": 0.1917,
      "step": 250
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.5527809307604996e-05,
      "loss": 0.1837,
      "step": 255
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.5244040862656076e-05,
      "loss": 0.1968,
      "step": 260
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.496027241770715e-05,
      "loss": 0.182,
      "step": 265
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.467650397275823e-05,
      "loss": 0.185,
      "step": 270
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.439273552780931e-05,
      "loss": 0.1836,
      "step": 275
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.4108967082860386e-05,
      "loss": 0.1922,
      "step": 280
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.382519863791147e-05,
      "loss": 0.1887,
      "step": 285
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.354143019296254e-05,
      "loss": 0.174,
      "step": 290
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.325766174801362e-05,
      "loss": 0.1812,
      "step": 295
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.29738933030647e-05,
      "loss": 0.1687,
      "step": 300
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.269012485811578e-05,
      "loss": 0.1959,
      "step": 305
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.240635641316686e-05,
      "loss": 0.1923,
      "step": 310
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.212258796821794e-05,
      "loss": 0.18,
      "step": 315
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.183881952326901e-05,
      "loss": 0.168,
      "step": 320
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.155505107832009e-05,
      "loss": 0.1802,
      "step": 325
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.127128263337117e-05,
      "loss": 0.183,
      "step": 330
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.098751418842225e-05,
      "loss": 0.1921,
      "step": 335
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.070374574347333e-05,
      "loss": 0.1784,
      "step": 340
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.0419977298524406e-05,
      "loss": 0.1674,
      "step": 345
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.013620885357548e-05,
      "loss": 0.1747,
      "step": 350
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.9852440408626565e-05,
      "loss": 0.1785,
      "step": 355
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.9568671963677642e-05,
      "loss": 0.1893,
      "step": 360
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.928490351872872e-05,
      "loss": 0.177,
      "step": 365
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.9001135073779793e-05,
      "loss": 0.1889,
      "step": 370
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.8717366628830878e-05,
      "loss": 0.2004,
      "step": 375
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.8433598183881955e-05,
      "loss": 0.1796,
      "step": 380
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.8149829738933033e-05,
      "loss": 0.1771,
      "step": 385
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.7866061293984107e-05,
      "loss": 0.1895,
      "step": 390
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.758229284903519e-05,
      "loss": 0.187,
      "step": 395
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.7298524404086268e-05,
      "loss": 0.1786,
      "step": 400
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7014755959137346e-05,
      "loss": 0.1728,
      "step": 405
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.673098751418842e-05,
      "loss": 0.1815,
      "step": 410
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.6447219069239504e-05,
      "loss": 0.1797,
      "step": 415
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.616345062429058e-05,
      "loss": 0.1735,
      "step": 420
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.587968217934166e-05,
      "loss": 0.1708,
      "step": 425
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5595913734392736e-05,
      "loss": 0.1642,
      "step": 430
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.5312145289443817e-05,
      "loss": 0.1642,
      "step": 435
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.5028376844494894e-05,
      "loss": 0.1825,
      "step": 440
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.4744608399545972e-05,
      "loss": 0.1802,
      "step": 445
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.446083995459705e-05,
      "loss": 0.1739,
      "step": 450
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.4177071509648127e-05,
      "loss": 0.1513,
      "step": 455
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.3893303064699208e-05,
      "loss": 0.1767,
      "step": 460
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.3609534619750285e-05,
      "loss": 0.1631,
      "step": 465
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.3325766174801362e-05,
      "loss": 0.1935,
      "step": 470
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.304199772985244e-05,
      "loss": 0.1956,
      "step": 475
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.275822928490352e-05,
      "loss": 0.1657,
      "step": 480
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.2474460839954598e-05,
      "loss": 0.143,
      "step": 485
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.2190692395005676e-05,
      "loss": 0.1641,
      "step": 490
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.1906923950056753e-05,
      "loss": 0.1633,
      "step": 495
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.1623155505107834e-05,
      "loss": 0.1852,
      "step": 500
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.133938706015891e-05,
      "loss": 0.1725,
      "step": 505
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.1055618615209992e-05,
      "loss": 0.1621,
      "step": 510
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.0771850170261066e-05,
      "loss": 0.1827,
      "step": 515
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.0488081725312147e-05,
      "loss": 0.1664,
      "step": 520
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.0204313280363224e-05,
      "loss": 0.1532,
      "step": 525
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.9920544835414305e-05,
      "loss": 0.1447,
      "step": 530
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.963677639046538e-05,
      "loss": 0.1669,
      "step": 535
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.935300794551646e-05,
      "loss": 0.1469,
      "step": 540
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.9069239500567538e-05,
      "loss": 0.1685,
      "step": 545
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.878547105561862e-05,
      "loss": 0.1745,
      "step": 550
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8501702610669692e-05,
      "loss": 0.1508,
      "step": 555
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.8217934165720773e-05,
      "loss": 0.1753,
      "step": 560
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.793416572077185e-05,
      "loss": 0.1572,
      "step": 565
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.765039727582293e-05,
      "loss": 0.1433,
      "step": 570
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.7366628830874006e-05,
      "loss": 0.1774,
      "step": 575
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.7082860385925086e-05,
      "loss": 0.1551,
      "step": 580
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.6799091940976164e-05,
      "loss": 0.1603,
      "step": 585
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6515323496027245e-05,
      "loss": 0.1623,
      "step": 590
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.6231555051078322e-05,
      "loss": 0.1705,
      "step": 595
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.59477866061294e-05,
      "loss": 0.1731,
      "step": 600
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.5664018161180477e-05,
      "loss": 0.1682,
      "step": 605
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.5380249716231558e-05,
      "loss": 0.1628,
      "step": 610
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.5096481271282633e-05,
      "loss": 0.172,
      "step": 615
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.4812712826333713e-05,
      "loss": 0.1616,
      "step": 620
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.452894438138479e-05,
      "loss": 0.1504,
      "step": 625
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.424517593643587e-05,
      "loss": 0.1684,
      "step": 630
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3961407491486947e-05,
      "loss": 0.1714,
      "step": 635
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3677639046538027e-05,
      "loss": 0.1684,
      "step": 640
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3393870601589103e-05,
      "loss": 0.1635,
      "step": 645
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3110102156640184e-05,
      "loss": 0.1519,
      "step": 650
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.282633371169126e-05,
      "loss": 0.1634,
      "step": 655
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.254256526674234e-05,
      "loss": 0.1731,
      "step": 660
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2258796821793416e-05,
      "loss": 0.1826,
      "step": 665
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.1975028376844495e-05,
      "loss": 0.1599,
      "step": 670
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.1691259931895573e-05,
      "loss": 0.1749,
      "step": 675
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.1407491486946652e-05,
      "loss": 0.17,
      "step": 680
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.112372304199773e-05,
      "loss": 0.1584,
      "step": 685
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.0839954597048808e-05,
      "loss": 0.169,
      "step": 690
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.0556186152099886e-05,
      "loss": 0.1766,
      "step": 695
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.0272417707150965e-05,
      "loss": 0.1638,
      "step": 700
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.988649262202042e-06,
      "loss": 0.1688,
      "step": 705
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.704880817253122e-06,
      "loss": 0.1636,
      "step": 710
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.4211123723042e-06,
      "loss": 0.162,
      "step": 715
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.137343927355278e-06,
      "loss": 0.1615,
      "step": 720
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.853575482406357e-06,
      "loss": 0.1642,
      "step": 725
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.569807037457435e-06,
      "loss": 0.1699,
      "step": 730
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.286038592508514e-06,
      "loss": 0.1576,
      "step": 735
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.002270147559591e-06,
      "loss": 0.1582,
      "step": 740
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.71850170261067e-06,
      "loss": 0.1569,
      "step": 745
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.434733257661748e-06,
      "loss": 0.1569,
      "step": 750
    },
    {
      "epoch": 0.86,
      "learning_rate": 7.150964812712826e-06,
      "loss": 0.1768,
      "step": 755
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.8671963677639044e-06,
      "loss": 0.1574,
      "step": 760
    },
    {
      "epoch": 0.87,
      "learning_rate": 6.583427922814983e-06,
      "loss": 0.1725,
      "step": 765
    },
    {
      "epoch": 0.87,
      "learning_rate": 6.299659477866062e-06,
      "loss": 0.1539,
      "step": 770
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.01589103291714e-06,
      "loss": 0.1675,
      "step": 775
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.732122587968218e-06,
      "loss": 0.1571,
      "step": 780
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.448354143019297e-06,
      "loss": 0.1484,
      "step": 785
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.164585698070375e-06,
      "loss": 0.1498,
      "step": 790
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.880817253121453e-06,
      "loss": 0.174,
      "step": 795
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5970488081725315e-06,
      "loss": 0.1514,
      "step": 800
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.31328036322361e-06,
      "loss": 0.1531,
      "step": 805
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.029511918274688e-06,
      "loss": 0.1438,
      "step": 810
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.7457434733257664e-06,
      "loss": 0.1741,
      "step": 815
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.4619750283768446e-06,
      "loss": 0.1585,
      "step": 820
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.178206583427923e-06,
      "loss": 0.1661,
      "step": 825
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.894438138479001e-06,
      "loss": 0.1448,
      "step": 830
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.6106696935300795e-06,
      "loss": 0.1601,
      "step": 835
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.3269012485811578e-06,
      "loss": 0.1632,
      "step": 840
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.043132803632236e-06,
      "loss": 0.162,
      "step": 845
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.7593643586833145e-06,
      "loss": 0.1598,
      "step": 850
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4755959137343928e-06,
      "loss": 0.183,
      "step": 855
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.191827468785471e-06,
      "loss": 0.1614,
      "step": 860
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.080590238365494e-07,
      "loss": 0.154,
      "step": 865
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.242905788876277e-07,
      "loss": 0.1445,
      "step": 870
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.4052213393870604e-07,
      "loss": 0.1591,
      "step": 875
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.6753688989784336e-08,
      "loss": 0.1638,
      "step": 880
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.12982094287872314,
      "eval_runtime": 78.2688,
      "eval_samples_per_second": 107.591,
      "eval_steps_per_second": 1.686,
      "step": 881
    }
  ],
  "logging_steps": 5,
  "max_steps": 881,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 4289727740313600.0,
  "trial_name": null,
  "trial_params": null
}