{
  "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": 41.78816559094165,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.6873,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 39.21754237441028,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.7176,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 22.974790284321642,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.3479,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 12.193951711113014,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.1946,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 8.48073048363401,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0089,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 8.009682967308724,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.8835,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 7.262025173418669,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.828,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 6.699957497225423,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.8063,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 6.875734140452078,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.7573,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.868835010495592,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7719,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 5.7925730718414625,
      "learning_rate": 4.4e-06,
      "loss": 1.7059,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 5.128809225860081,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.6663,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 6.208034423942183,
      "learning_rate": 5.2e-06,
      "loss": 1.7238,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 5.128178248836628,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.6073,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 5.5042579856268175,
      "learning_rate": 6e-06,
      "loss": 1.6385,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 5.2674329619575095,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.6172,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 5.5549430152486545,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.5542,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 5.017683357994054,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.5514,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 5.479487284019013,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.543,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.439391870721549,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.5409,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 5.271016317987487,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.5872,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.792457492455555,
      "learning_rate": 8.8e-06,
      "loss": 1.4757,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 5.075344864087474,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.5087,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 5.714411823037559,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.4804,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.444982165844812,
      "learning_rate": 1e-05,
      "loss": 1.4646,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 5.345841455303372,
      "learning_rate": 9.9e-06,
      "loss": 1.2542,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 5.840702633242517,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.3528,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 5.473939368411626,
      "learning_rate": 9.7e-06,
      "loss": 1.2929,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 6.376898310400968,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.2723,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 5.700427081143242,
      "learning_rate": 9.5e-06,
      "loss": 1.2874,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 5.462582074919751,
      "learning_rate": 9.4e-06,
      "loss": 1.1926,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 6.755874022673723,
      "learning_rate": 9.3e-06,
      "loss": 1.233,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 6.253640966729863,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.2331,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 5.735570732360772,
      "learning_rate": 9.100000000000001e-06,
      "loss": 1.2763,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 6.61744366427225,
      "learning_rate": 9e-06,
      "loss": 1.171,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 6.493064268883384,
      "learning_rate": 8.900000000000001e-06,
      "loss": 1.2608,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 6.053046894810287,
      "learning_rate": 8.8e-06,
      "loss": 1.2761,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 5.898509077004065,
      "learning_rate": 8.700000000000001e-06,
      "loss": 1.2795,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 5.0628507315682825,
      "learning_rate": 8.6e-06,
      "loss": 1.2249,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 6.031568916132478,
      "learning_rate": 8.5e-06,
      "loss": 1.2639,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 5.464553442725951,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.2662,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 5.3543725468001115,
      "learning_rate": 8.3e-06,
      "loss": 1.2381,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 5.526823092037022,
      "learning_rate": 8.2e-06,
      "loss": 1.259,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 5.872863742249989,
      "learning_rate": 8.1e-06,
      "loss": 1.2357,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 5.504339080782453,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.218,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 5.98674025952278,
      "learning_rate": 7.9e-06,
      "loss": 1.209,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 5.617557990248127,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.2681,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 6.0069967626351,
      "learning_rate": 7.7e-06,
      "loss": 1.2532,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 5.462520707964854,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.2454,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.507642604511613,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.2465,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 4.829636140044014,
      "learning_rate": 7.4e-06,
      "loss": 0.8051,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 5.4153360645753414,
      "learning_rate": 7.3e-06,
      "loss": 0.7526,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 6.73555243497204,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.7706,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 6.964399194935617,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.7134,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 5.691128251983088,
      "learning_rate": 7e-06,
      "loss": 0.6627,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 6.5324310006265,
      "learning_rate": 6.9e-06,
      "loss": 0.7853,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 6.24838267796681,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.7301,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 6.848868280937794,
      "learning_rate": 6.700000000000001e-06,
      "loss": 0.7863,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 6.866708142656634,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.7589,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 6.399583010880786,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.7812,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 6.473150486550314,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.7496,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 7.27079148738982,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.7357,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 6.3863692542883905,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.7405,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 5.738425323665883,
      "learning_rate": 6.1e-06,
      "loss": 0.715,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 7.272206537104772,
      "learning_rate": 6e-06,
      "loss": 0.7275,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 6.335249993334978,
      "learning_rate": 5.9e-06,
      "loss": 0.7293,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 6.178406605090851,
      "learning_rate": 5.8e-06,
      "loss": 0.7418,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 6.4438593559241575,
      "learning_rate": 5.7e-06,
      "loss": 0.7836,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 6.68556487183193,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.7941,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 6.236785962358311,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.734,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 6.817870091612145,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.7666,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 6.402166198855242,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.7343,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 6.603573267937269,
      "learning_rate": 5.2e-06,
      "loss": 0.7747,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 6.391258167495969,
      "learning_rate": 5.1e-06,
      "loss": 0.7422,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.4602886780696736,
      "learning_rate": 5e-06,
      "loss": 0.7269,
      "step": 375
    },
    {
      "epoch": 3.04,
      "grad_norm": 5.1665130569705155,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.3794,
      "step": 380
    },
    {
      "epoch": 3.08,
      "grad_norm": 10.038102142368922,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.3465,
      "step": 385
    },
    {
      "epoch": 3.12,
      "grad_norm": 9.091224220497404,
      "learning_rate": 4.7e-06,
      "loss": 0.3184,
      "step": 390
    },
    {
      "epoch": 3.16,
      "grad_norm": 5.565125811877338,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.3018,
      "step": 395
    },
    {
      "epoch": 3.2,
      "grad_norm": 5.896141152522807,
      "learning_rate": 4.5e-06,
      "loss": 0.3344,
      "step": 400
    },
    {
      "epoch": 3.24,
      "grad_norm": 7.443395279154662,
      "learning_rate": 4.4e-06,
      "loss": 0.3255,
      "step": 405
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 8.734524554137987,
      "learning_rate": 4.3e-06,
      "loss": 0.3354,
      "step": 410
    },
    {
      "epoch": 3.32,
      "grad_norm": 5.90064726923167,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.3103,
      "step": 415
    },
    {
      "epoch": 3.36,
      "grad_norm": 6.893663931007692,
      "learning_rate": 4.1e-06,
      "loss": 0.3142,
      "step": 420
    },
    {
      "epoch": 3.4,
      "grad_norm": 6.1745958995274055,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.3282,
      "step": 425
    },
    {
      "epoch": 3.44,
      "grad_norm": 6.625044961396123,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.3139,
      "step": 430
    },
    {
      "epoch": 3.48,
      "grad_norm": 6.66439206341554,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.2981,
      "step": 435
    },
    {
      "epoch": 3.52,
      "grad_norm": 9.626961732011068,
      "learning_rate": 3.7e-06,
      "loss": 0.3432,
      "step": 440
    },
    {
      "epoch": 3.56,
      "grad_norm": 5.781950416178249,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.3196,
      "step": 445
    },
    {
      "epoch": 3.6,
      "grad_norm": 6.779570337647412,
      "learning_rate": 3.5e-06,
      "loss": 0.3186,
      "step": 450
    },
    {
      "epoch": 3.64,
      "grad_norm": 6.98198989854906,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.3211,
      "step": 455
    },
    {
      "epoch": 3.68,
      "grad_norm": 6.462458342089892,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.3413,
      "step": 460
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 7.091018339254791,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.329,
      "step": 465
    },
    {
      "epoch": 3.76,
      "grad_norm": 6.769774324850197,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.3217,
      "step": 470
    },
    {
      "epoch": 3.8,
      "grad_norm": 6.564865649203158,
      "learning_rate": 3e-06,
      "loss": 0.3071,
      "step": 475
    },
    {
      "epoch": 3.84,
      "grad_norm": 7.322161934451888,
      "learning_rate": 2.9e-06,
      "loss": 0.3335,
      "step": 480
    },
    {
      "epoch": 3.88,
      "grad_norm": 6.791859707490033,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.3176,
      "step": 485
    },
    {
      "epoch": 3.92,
      "grad_norm": 7.265205021493263,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.3364,
      "step": 490
    },
    {
      "epoch": 3.96,
      "grad_norm": 7.172524820435972,
      "learning_rate": 2.6e-06,
      "loss": 0.3391,
      "step": 495
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.549661412065393,
      "learning_rate": 2.5e-06,
      "loss": 0.3152,
      "step": 500
    },
    {
      "epoch": 4.04,
      "grad_norm": 4.151346903217664,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.1282,
      "step": 505
    },
    {
      "epoch": 4.08,
      "grad_norm": 6.731712733657434,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1074,
      "step": 510
    },
    {
      "epoch": 4.12,
      "grad_norm": 7.807784918167321,
      "learning_rate": 2.2e-06,
      "loss": 0.1077,
      "step": 515
    },
    {
      "epoch": 4.16,
      "grad_norm": 6.847097633499647,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0917,
      "step": 520
    },
    {
      "epoch": 4.2,
      "grad_norm": 6.134183949410225,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1021,
      "step": 525
    },
    {
      "epoch": 4.24,
      "grad_norm": 5.319831131391458,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.103,
      "step": 530
    },
    {
      "epoch": 4.28,
      "grad_norm": 7.22929423828226,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0917,
      "step": 535
    },
    {
      "epoch": 4.32,
      "grad_norm": 5.801510107918174,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.1018,
      "step": 540
    },
    {
      "epoch": 4.36,
      "grad_norm": 6.804190001063543,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1059,
      "step": 545
    },
    {
      "epoch": 4.4,
      "grad_norm": 6.079686228135889,
      "learning_rate": 1.5e-06,
      "loss": 0.0981,
      "step": 550
    },
    {
      "epoch": 4.44,
      "grad_norm": 6.728461874646889,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.0868,
      "step": 555
    },
    {
      "epoch": 4.48,
      "grad_norm": 5.1687298425209045,
      "learning_rate": 1.3e-06,
      "loss": 0.0901,
      "step": 560
    },
    {
      "epoch": 4.52,
      "grad_norm": 6.656136927045494,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.1011,
      "step": 565
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 5.873899340424779,
      "learning_rate": 1.1e-06,
      "loss": 0.107,
      "step": 570
    },
    {
      "epoch": 4.6,
      "grad_norm": 4.629909324271422,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0925,
      "step": 575
    },
    {
      "epoch": 4.64,
      "grad_norm": 4.940878561633262,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.1088,
      "step": 580
    },
    {
      "epoch": 4.68,
      "grad_norm": 6.322920106401137,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.1028,
      "step": 585
    },
    {
      "epoch": 4.72,
      "grad_norm": 4.269422068581224,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.0912,
      "step": 590
    },
    {
      "epoch": 4.76,
      "grad_norm": 6.2986335863080205,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.105,
      "step": 595
    },
    {
      "epoch": 4.8,
      "grad_norm": 7.766339855517555,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0993,
      "step": 600
    },
    {
      "epoch": 4.84,
      "grad_norm": 5.08726096349937,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.1075,
      "step": 605
    },
    {
      "epoch": 4.88,
      "grad_norm": 5.420727718681749,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.1013,
      "step": 610
    },
    {
      "epoch": 4.92,
      "grad_norm": 4.448103480540091,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.0949,
      "step": 615
    },
    {
      "epoch": 4.96,
      "grad_norm": 4.985038691135613,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.0923,
      "step": 620
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.897377508928938,
      "learning_rate": 0.0,
      "loss": 0.0959,
      "step": 625
    },
    {
      "epoch": 5.0,
      "step": 625,
      "total_flos": 2237034848256.0,
      "train_loss": 0.8430705074310303,
      "train_runtime": 2010.1374,
      "train_samples_per_second": 9.95,
      "train_steps_per_second": 0.311
    }
  ],
  "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": 2237034848256.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}