{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 89.82371603949359,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.6564,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 75.2735878207548,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.6478,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 33.58735952139897,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.2785,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 14.171883076827761,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.1944,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 14.61980793964136,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0565,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 11.030361913924636,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.9451,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 11.483038196037421,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.8853,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 10.282307478721446,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.8899,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 9.403395764096778,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.8369,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.39082411153001,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.8321,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 8.467837375829392,
      "learning_rate": 4.4e-06,
      "loss": 1.7815,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 7.619179269881611,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.7541,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 8.495247169424331,
      "learning_rate": 5.2e-06,
      "loss": 1.8144,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 7.812369921180664,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.7004,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.024623815868656,
      "learning_rate": 6e-06,
      "loss": 1.7253,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 7.360902183318722,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.7047,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 8.562290112967787,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.6259,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 7.497861834873093,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.6508,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 7.977323163225298,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.6438,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.076428643203684,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6396,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 7.976089395817468,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.6967,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 7.0639566402763245,
      "learning_rate": 8.8e-06,
      "loss": 1.5554,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 7.731398632191519,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.5971,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.937712860421918,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.5833,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.563914418145805,
      "learning_rate": 1e-05,
      "loss": 1.555,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 7.803252722361364,
      "learning_rate": 9.9e-06,
      "loss": 1.3656,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 7.929626065845273,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.4725,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 7.161720074072072,
      "learning_rate": 9.7e-06,
      "loss": 1.4018,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 8.135421849383178,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.378,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 7.591888228234121,
      "learning_rate": 9.5e-06,
      "loss": 1.4169,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 7.506276067252539,
      "learning_rate": 9.4e-06,
      "loss": 1.3111,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 8.30322573720057,
      "learning_rate": 9.3e-06,
      "loss": 1.3481,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 8.49867887645396,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.3461,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 8.401741468634247,
      "learning_rate": 9.100000000000001e-06,
      "loss": 1.3903,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 8.65770914891247,
      "learning_rate": 9e-06,
      "loss": 1.2654,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 8.500088292254128,
      "learning_rate": 8.900000000000001e-06,
      "loss": 1.3821,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 7.421515621477695,
      "learning_rate": 8.8e-06,
      "loss": 1.3662,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 8.190508815008455,
      "learning_rate": 8.700000000000001e-06,
      "loss": 1.3802,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 7.428504273817973,
      "learning_rate": 8.6e-06,
      "loss": 1.3208,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 8.293872163578715,
      "learning_rate": 8.5e-06,
      "loss": 1.3723,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 7.668913906629593,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.3877,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 7.2640670839071175,
      "learning_rate": 8.3e-06,
      "loss": 1.3366,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 8.45905985289491,
      "learning_rate": 8.2e-06,
      "loss": 1.3809,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 8.420327743224147,
      "learning_rate": 8.1e-06,
      "loss": 1.3381,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 7.091088067273984,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3458,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 8.157993701322475,
      "learning_rate": 7.9e-06,
      "loss": 1.3222,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 7.517398704427892,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.3658,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 8.142832872735468,
      "learning_rate": 7.7e-06,
      "loss": 1.3645,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 7.781387568953773,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.3339,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.018401738016298,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.3626,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 7.178146988044731,
      "learning_rate": 7.4e-06,
      "loss": 0.9447,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 7.582541553977795,
      "learning_rate": 7.3e-06,
      "loss": 0.9022,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 9.803729014002805,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.9051,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 9.447767686350764,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.8667,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 8.327471781348626,
      "learning_rate": 7e-06,
      "loss": 0.796,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 9.465641503438128,
      "learning_rate": 6.9e-06,
      "loss": 0.9401,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 8.678391102462472,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.865,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 9.266451696995004,
      "learning_rate": 6.700000000000001e-06,
      "loss": 0.9266,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 10.225758737461298,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.907,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 8.465991958734747,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.9329,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 8.432762841049588,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.91,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 10.012927090762362,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.8835,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 8.405221169802761,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.8803,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 8.567685032288303,
      "learning_rate": 6.1e-06,
      "loss": 0.8581,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 9.655710893112909,
      "learning_rate": 6e-06,
      "loss": 0.8636,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 9.213194754159915,
      "learning_rate": 5.9e-06,
      "loss": 0.8703,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 8.394853800291447,
      "learning_rate": 5.8e-06,
      "loss": 0.8889,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 8.25623902667668,
      "learning_rate": 5.7e-06,
      "loss": 0.9199,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 9.432213529061965,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.9354,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 9.331975998189465,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.8731,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 9.419112744932255,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.9096,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 9.044996816630446,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.8739,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 9.589663642804883,
      "learning_rate": 5.2e-06,
      "loss": 0.9271,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 9.193576698813617,
      "learning_rate": 5.1e-06,
      "loss": 0.8918,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.81010310005968,
      "learning_rate": 5e-06,
      "loss": 0.8967,
      "step": 375
    },
    {
      "epoch": 3.04,
      "grad_norm": 8.019001290351486,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.5329,
      "step": 380
    },
    {
      "epoch": 3.08,
      "grad_norm": 10.84261876285756,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.4985,
      "step": 385
    },
    {
      "epoch": 3.12,
      "grad_norm": 9.387923983319462,
      "learning_rate": 4.7e-06,
      "loss": 0.468,
      "step": 390
    },
    {
      "epoch": 3.16,
      "grad_norm": 8.269965182173046,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.4458,
      "step": 395
    },
    {
      "epoch": 3.2,
      "grad_norm": 9.535893549281663,
      "learning_rate": 4.5e-06,
      "loss": 0.4821,
      "step": 400
    },
    {
      "epoch": 3.24,
      "grad_norm": 9.401974393546057,
      "learning_rate": 4.4e-06,
      "loss": 0.472,
      "step": 405
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 11.09046610543629,
      "learning_rate": 4.3e-06,
      "loss": 0.483,
      "step": 410
    },
    {
      "epoch": 3.32,
      "grad_norm": 8.638663259816369,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.462,
      "step": 415
    },
    {
      "epoch": 3.36,
      "grad_norm": 9.601865633584897,
      "learning_rate": 4.1e-06,
      "loss": 0.4518,
      "step": 420
    },
    {
      "epoch": 3.4,
      "grad_norm": 9.288745640929617,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.465,
      "step": 425
    },
    {
      "epoch": 3.44,
      "grad_norm": 9.868753828103186,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.4716,
      "step": 430
    },
    {
      "epoch": 3.48,
      "grad_norm": 11.773719476313133,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.4535,
      "step": 435
    },
    {
      "epoch": 3.52,
      "grad_norm": 10.591718001217169,
      "learning_rate": 3.7e-06,
      "loss": 0.4815,
      "step": 440
    },
    {
      "epoch": 3.56,
      "grad_norm": 8.897682169461483,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.4505,
      "step": 445
    },
    {
      "epoch": 3.6,
      "grad_norm": 9.563808712230394,
      "learning_rate": 3.5e-06,
      "loss": 0.46,
      "step": 450
    },
    {
      "epoch": 3.64,
      "grad_norm": 9.828440492379743,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.4762,
      "step": 455
    },
    {
      "epoch": 3.68,
      "grad_norm": 8.489390772662722,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.4984,
      "step": 460
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 10.014450411847454,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.484,
      "step": 465
    },
    {
      "epoch": 3.76,
      "grad_norm": 9.201375259300189,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.4669,
      "step": 470
    },
    {
      "epoch": 3.8,
      "grad_norm": 9.51157246451395,
      "learning_rate": 3e-06,
      "loss": 0.4643,
      "step": 475
    },
    {
      "epoch": 3.84,
      "grad_norm": 9.62282368600112,
      "learning_rate": 2.9e-06,
      "loss": 0.4911,
      "step": 480
    },
    {
      "epoch": 3.88,
      "grad_norm": 9.444343630230321,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.4856,
      "step": 485
    },
    {
      "epoch": 3.92,
      "grad_norm": 10.047185908955532,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.4907,
      "step": 490
    },
    {
      "epoch": 3.96,
      "grad_norm": 10.121432836197208,
      "learning_rate": 2.6e-06,
      "loss": 0.4956,
      "step": 495
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.897990190318387,
      "learning_rate": 2.5e-06,
      "loss": 0.4784,
      "step": 500
    },
    {
      "epoch": 4.04,
      "grad_norm": 7.43706714195581,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.235,
      "step": 505
    },
    {
      "epoch": 4.08,
      "grad_norm": 10.809663179549249,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.2138,
      "step": 510
    },
    {
      "epoch": 4.12,
      "grad_norm": 10.055114463726696,
      "learning_rate": 2.2e-06,
      "loss": 0.2159,
      "step": 515
    },
    {
      "epoch": 4.16,
      "grad_norm": 10.338716351009188,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.1913,
      "step": 520
    },
    {
      "epoch": 4.2,
      "grad_norm": 8.793111787622328,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.207,
      "step": 525
    },
    {
      "epoch": 4.24,
      "grad_norm": 8.159670512299746,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.1985,
      "step": 530
    },
    {
      "epoch": 4.28,
      "grad_norm": 8.482017636931404,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.1868,
      "step": 535
    },
    {
      "epoch": 4.32,
      "grad_norm": 10.360178503982437,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.1945,
      "step": 540
    },
    {
      "epoch": 4.36,
      "grad_norm": 7.875689134918156,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.2125,
      "step": 545
    },
    {
      "epoch": 4.4,
      "grad_norm": 8.42269826376436,
      "learning_rate": 1.5e-06,
      "loss": 0.1994,
      "step": 550
    },
    {
      "epoch": 4.44,
      "grad_norm": 8.05875558929426,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.1751,
      "step": 555
    },
    {
      "epoch": 4.48,
      "grad_norm": 9.480349080658375,
      "learning_rate": 1.3e-06,
      "loss": 0.2035,
      "step": 560
    },
    {
      "epoch": 4.52,
      "grad_norm": 8.57557041236713,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.1908,
      "step": 565
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 8.597528432511735,
      "learning_rate": 1.1e-06,
      "loss": 0.2119,
      "step": 570
    },
    {
      "epoch": 4.6,
      "grad_norm": 8.009913537969426,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1905,
      "step": 575
    },
    {
      "epoch": 4.64,
      "grad_norm": 8.32445977305177,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.2243,
      "step": 580
    },
    {
      "epoch": 4.68,
      "grad_norm": 8.993283223073181,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.2065,
      "step": 585
    },
    {
      "epoch": 4.72,
      "grad_norm": 6.970573245330436,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.1958,
      "step": 590
    },
    {
      "epoch": 4.76,
      "grad_norm": 7.645253401257893,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.2064,
      "step": 595
    },
    {
      "epoch": 4.8,
      "grad_norm": 9.453343432891174,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.209,
      "step": 600
    },
    {
      "epoch": 4.84,
      "grad_norm": 8.256722521448035,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.2309,
      "step": 605
    },
    {
      "epoch": 4.88,
      "grad_norm": 8.523020194829563,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.212,
      "step": 610
    },
    {
      "epoch": 4.92,
      "grad_norm": 8.809891202943627,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.1959,
      "step": 615
    },
    {
      "epoch": 4.96,
      "grad_norm": 8.54338346414983,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.1868,
      "step": 620
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.459641356527731,
      "learning_rate": 0.0,
      "loss": 0.1983,
      "step": 625
    },
    {
      "epoch": 5.0,
      "step": 625,
      "total_flos": 863416958976.0,
      "train_loss": 0.9574172312736511,
      "train_runtime": 745.662,
      "train_samples_per_second": 26.822,
      "train_steps_per_second": 0.838
    }
  ],
  "logging_steps": 5,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 863416958976.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}