{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8173160173160173,
  "eval_steps": 59,
  "global_step": 236,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003463203463203463,
      "grad_norm": 0.26726240342863167,
      "learning_rate": 5e-06,
      "loss": 1.8182,
      "step": 1
    },
    {
      "epoch": 0.003463203463203463,
      "eval_loss": 2.1284499168395996,
      "eval_runtime": 293.5739,
      "eval_samples_per_second": 0.341,
      "eval_steps_per_second": 0.17,
      "step": 1
    },
    {
      "epoch": 0.006926406926406926,
      "grad_norm": 0.20034662456059837,
      "learning_rate": 1e-05,
      "loss": 1.9101,
      "step": 2
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 0.23729183422165226,
      "learning_rate": 1.5e-05,
      "loss": 1.9238,
      "step": 3
    },
    {
      "epoch": 0.013852813852813853,
      "grad_norm": 0.1802988503389903,
      "learning_rate": 2e-05,
      "loss": 1.8901,
      "step": 4
    },
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 0.18865054609738205,
      "learning_rate": 2.5e-05,
      "loss": 1.9419,
      "step": 5
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 0.2153919517946603,
      "learning_rate": 3e-05,
      "loss": 1.9561,
      "step": 6
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 0.23646989547590208,
      "learning_rate": 3.5e-05,
      "loss": 1.9231,
      "step": 7
    },
    {
      "epoch": 0.027705627705627706,
      "grad_norm": 0.1695483068973071,
      "learning_rate": 4e-05,
      "loss": 1.7199,
      "step": 8
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 0.17169305240230742,
      "learning_rate": 4.5e-05,
      "loss": 1.9328,
      "step": 9
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 0.1769763038127782,
      "learning_rate": 5e-05,
      "loss": 1.794,
      "step": 10
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.2739291337489883,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.8976,
      "step": 11
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 0.1687629241124428,
      "learning_rate": 6e-05,
      "loss": 1.8382,
      "step": 12
    },
    {
      "epoch": 0.045021645021645025,
      "grad_norm": 0.170449291833281,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.8339,
      "step": 13
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.13830013122227536,
      "learning_rate": 7e-05,
      "loss": 1.7958,
      "step": 14
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.3120525656602162,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8834,
      "step": 15
    },
    {
      "epoch": 0.05541125541125541,
      "grad_norm": 0.1740554404965808,
      "learning_rate": 8e-05,
      "loss": 1.643,
      "step": 16
    },
    {
      "epoch": 0.05887445887445888,
      "grad_norm": 0.13272024244803257,
      "learning_rate": 8.5e-05,
      "loss": 1.7635,
      "step": 17
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 0.13865354195619714,
      "learning_rate": 9e-05,
      "loss": 1.8596,
      "step": 18
    },
    {
      "epoch": 0.0658008658008658,
      "grad_norm": 0.17558880062270332,
      "learning_rate": 9.5e-05,
      "loss": 2.0007,
      "step": 19
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 0.18945613013501378,
      "learning_rate": 0.0001,
      "loss": 1.8773,
      "step": 20
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.11111588495801177,
      "learning_rate": 9.999697629917739e-05,
      "loss": 1.8568,
      "step": 21
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.2167792483298019,
      "learning_rate": 9.998790560305473e-05,
      "loss": 1.7966,
      "step": 22
    },
    {
      "epoch": 0.07965367965367966,
      "grad_norm": 0.17058063410322674,
      "learning_rate": 9.997278913061298e-05,
      "loss": 1.8296,
      "step": 23
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 0.22535134477990126,
      "learning_rate": 9.995162891330504e-05,
      "loss": 1.8398,
      "step": 24
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 0.13284807817034902,
      "learning_rate": 9.992442779478275e-05,
      "loss": 1.7536,
      "step": 25
    },
    {
      "epoch": 0.09004329004329005,
      "grad_norm": 0.1525380710864997,
      "learning_rate": 9.989118943051471e-05,
      "loss": 1.8267,
      "step": 26
    },
    {
      "epoch": 0.09350649350649351,
      "grad_norm": 0.38389909659403076,
      "learning_rate": 9.985191828729519e-05,
      "loss": 1.7526,
      "step": 27
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.1311981474834846,
      "learning_rate": 9.98066196426436e-05,
      "loss": 1.8789,
      "step": 28
    },
    {
      "epoch": 0.10043290043290043,
      "grad_norm": 0.14321635310477376,
      "learning_rate": 9.97552995840955e-05,
      "loss": 1.8666,
      "step": 29
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.131774192226824,
      "learning_rate": 9.969796500838434e-05,
      "loss": 1.8831,
      "step": 30
    },
    {
      "epoch": 0.10735930735930736,
      "grad_norm": 0.13710505067770457,
      "learning_rate": 9.963462362051473e-05,
      "loss": 1.6771,
      "step": 31
    },
    {
      "epoch": 0.11082251082251082,
      "grad_norm": 0.14077801488589667,
      "learning_rate": 9.956528393272697e-05,
      "loss": 1.8743,
      "step": 32
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.1606260003339504,
      "learning_rate": 9.94899552633531e-05,
      "loss": 1.7463,
      "step": 33
    },
    {
      "epoch": 0.11774891774891776,
      "grad_norm": 0.20844538767698467,
      "learning_rate": 9.940864773556466e-05,
      "loss": 1.8095,
      "step": 34
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.13051717096877563,
      "learning_rate": 9.932137227601224e-05,
      "loss": 1.743,
      "step": 35
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 0.1273670930785435,
      "learning_rate": 9.922814061335716e-05,
      "loss": 1.8164,
      "step": 36
    },
    {
      "epoch": 0.12813852813852813,
      "grad_norm": 0.14632843388917796,
      "learning_rate": 9.912896527669518e-05,
      "loss": 1.6922,
      "step": 37
    },
    {
      "epoch": 0.1316017316017316,
      "grad_norm": 0.1877238002560958,
      "learning_rate": 9.902385959387282e-05,
      "loss": 1.8563,
      "step": 38
    },
    {
      "epoch": 0.13506493506493505,
      "grad_norm": 0.12224962058562377,
      "learning_rate": 9.891283768969633e-05,
      "loss": 1.7657,
      "step": 39
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 0.1552638716363645,
      "learning_rate": 9.879591448403333e-05,
      "loss": 1.9331,
      "step": 40
    },
    {
      "epoch": 0.141991341991342,
      "grad_norm": 0.3572833915022296,
      "learning_rate": 9.867310568980802e-05,
      "loss": 1.6578,
      "step": 41
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.9532440952793683,
      "learning_rate": 9.854442781088935e-05,
      "loss": 1.8014,
      "step": 42
    },
    {
      "epoch": 0.14891774891774892,
      "grad_norm": 0.23015183389227475,
      "learning_rate": 9.840989813987326e-05,
      "loss": 1.6852,
      "step": 43
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.13909635416408656,
      "learning_rate": 9.826953475575873e-05,
      "loss": 1.7686,
      "step": 44
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 0.14004251970994497,
      "learning_rate": 9.812335652151818e-05,
      "loss": 1.8545,
      "step": 45
    },
    {
      "epoch": 0.15930735930735931,
      "grad_norm": 0.12804047264438845,
      "learning_rate": 9.797138308156262e-05,
      "loss": 1.8549,
      "step": 46
    },
    {
      "epoch": 0.16277056277056276,
      "grad_norm": 0.15888098268224185,
      "learning_rate": 9.781363485910162e-05,
      "loss": 1.8095,
      "step": 47
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 0.1753776918443242,
      "learning_rate": 9.765013305339872e-05,
      "loss": 1.7596,
      "step": 48
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": 0.1542382423932175,
      "learning_rate": 9.748089963692256e-05,
      "loss": 1.9146,
      "step": 49
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 0.13847988655949817,
      "learning_rate": 9.730595735239407e-05,
      "loss": 1.7984,
      "step": 50
    },
    {
      "epoch": 0.17662337662337663,
      "grad_norm": 0.4071014591163337,
      "learning_rate": 9.712532970973013e-05,
      "loss": 1.7578,
      "step": 51
    },
    {
      "epoch": 0.1800865800865801,
      "grad_norm": 0.17428941847352164,
      "learning_rate": 9.693904098288415e-05,
      "loss": 1.8245,
      "step": 52
    },
    {
      "epoch": 0.18354978354978355,
      "grad_norm": 0.12001384773806148,
      "learning_rate": 9.674711620658393e-05,
      "loss": 1.8891,
      "step": 53
    },
    {
      "epoch": 0.18701298701298702,
      "grad_norm": 0.14927831515795748,
      "learning_rate": 9.654958117296748e-05,
      "loss": 1.7755,
      "step": 54
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.1328911465672095,
      "learning_rate": 9.634646242811673e-05,
      "loss": 1.8446,
      "step": 55
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.22985304080720362,
      "learning_rate": 9.613778726849014e-05,
      "loss": 1.8517,
      "step": 56
    },
    {
      "epoch": 0.1974025974025974,
      "grad_norm": 0.20379099943758505,
      "learning_rate": 9.592358373725448e-05,
      "loss": 1.6363,
      "step": 57
    },
    {
      "epoch": 0.20086580086580086,
      "grad_norm": 0.13109221546818925,
      "learning_rate": 9.570388062051613e-05,
      "loss": 1.7453,
      "step": 58
    },
    {
      "epoch": 0.20432900432900433,
      "grad_norm": 0.2032056177408556,
      "learning_rate": 9.547870744345262e-05,
      "loss": 1.8279,
      "step": 59
    },
    {
      "epoch": 0.20432900432900433,
      "eval_loss": 1.999111294746399,
      "eval_runtime": 293.5683,
      "eval_samples_per_second": 0.341,
      "eval_steps_per_second": 0.17,
      "step": 59
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.17529821502651677,
      "learning_rate": 9.524809446634491e-05,
      "loss": 1.6943,
      "step": 60
    },
    {
      "epoch": 0.21125541125541125,
      "grad_norm": 0.12745995684364722,
      "learning_rate": 9.501207268051065e-05,
      "loss": 1.7711,
      "step": 61
    },
    {
      "epoch": 0.21471861471861473,
      "grad_norm": 0.13389107026895525,
      "learning_rate": 9.47706738041396e-05,
      "loss": 1.7418,
      "step": 62
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.121236748921413,
      "learning_rate": 9.452393027803087e-05,
      "loss": 1.7933,
      "step": 63
    },
    {
      "epoch": 0.22164502164502164,
      "grad_norm": 0.2677114062718937,
      "learning_rate": 9.427187526123349e-05,
      "loss": 1.6282,
      "step": 64
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 0.1315935010259272,
      "learning_rate": 9.401454262659021e-05,
      "loss": 1.8114,
      "step": 65
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.3087874359247871,
      "learning_rate": 9.375196695618541e-05,
      "loss": 1.8901,
      "step": 66
    },
    {
      "epoch": 0.23203463203463204,
      "grad_norm": 0.16625917755333441,
      "learning_rate": 9.34841835366978e-05,
      "loss": 1.7242,
      "step": 67
    },
    {
      "epoch": 0.2354978354978355,
      "grad_norm": 0.18601871730414293,
      "learning_rate": 9.321122835465832e-05,
      "loss": 1.8886,
      "step": 68
    },
    {
      "epoch": 0.23896103896103896,
      "grad_norm": 0.15023934879358058,
      "learning_rate": 9.293313809161398e-05,
      "loss": 1.9009,
      "step": 69
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.1898870406241783,
      "learning_rate": 9.264995011919842e-05,
      "loss": 1.8542,
      "step": 70
    },
    {
      "epoch": 0.24588744588744588,
      "grad_norm": 0.11719048639879068,
      "learning_rate": 9.236170249410971e-05,
      "loss": 1.7862,
      "step": 71
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 0.17652226951092279,
      "learning_rate": 9.206843395299582e-05,
      "loss": 1.8578,
      "step": 72
    },
    {
      "epoch": 0.2528138528138528,
      "grad_norm": 0.1587295825611423,
      "learning_rate": 9.177018390724922e-05,
      "loss": 1.7351,
      "step": 73
    },
    {
      "epoch": 0.25627705627705627,
      "grad_norm": 0.15111228997710152,
      "learning_rate": 9.146699243771024e-05,
      "loss": 1.7845,
      "step": 74
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.1476778598569357,
      "learning_rate": 9.115890028928096e-05,
      "loss": 1.7964,
      "step": 75
    },
    {
      "epoch": 0.2632034632034632,
      "grad_norm": 0.13451846228173517,
      "learning_rate": 9.084594886544947e-05,
      "loss": 1.7537,
      "step": 76
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.20501729418270834,
      "learning_rate": 9.05281802227259e-05,
      "loss": 1.7966,
      "step": 77
    },
    {
      "epoch": 0.2701298701298701,
      "grad_norm": 0.1343051700663291,
      "learning_rate": 9.020563706499054e-05,
      "loss": 1.7432,
      "step": 78
    },
    {
      "epoch": 0.2735930735930736,
      "grad_norm": 0.2576160107399793,
      "learning_rate": 8.987836273775502e-05,
      "loss": 1.7844,
      "step": 79
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 0.1611750355342202,
      "learning_rate": 8.954640122233717e-05,
      "loss": 1.7335,
      "step": 80
    },
    {
      "epoch": 0.2805194805194805,
      "grad_norm": 0.1535687636039628,
      "learning_rate": 8.92097971299507e-05,
      "loss": 1.8359,
      "step": 81
    },
    {
      "epoch": 0.283982683982684,
      "grad_norm": 0.14335525291232706,
      "learning_rate": 8.886859569570986e-05,
      "loss": 1.5791,
      "step": 82
    },
    {
      "epoch": 0.28744588744588745,
      "grad_norm": 0.12069704359106079,
      "learning_rate": 8.852284277255054e-05,
      "loss": 1.8349,
      "step": 83
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.14265174894073543,
      "learning_rate": 8.817258482506821e-05,
      "loss": 1.6968,
      "step": 84
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 0.15759187672377553,
      "learning_rate": 8.781786892327372e-05,
      "loss": 1.8609,
      "step": 85
    },
    {
      "epoch": 0.29783549783549784,
      "grad_norm": 0.15630758183987872,
      "learning_rate": 8.745874273626769e-05,
      "loss": 1.6969,
      "step": 86
    },
    {
      "epoch": 0.3012987012987013,
      "grad_norm": 0.23155350493633237,
      "learning_rate": 8.70952545258344e-05,
      "loss": 1.7134,
      "step": 87
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.12867694140850763,
      "learning_rate": 8.672745313995617e-05,
      "loss": 1.7176,
      "step": 88
    },
    {
      "epoch": 0.30822510822510824,
      "grad_norm": 0.14660527797094974,
      "learning_rate": 8.635538800624865e-05,
      "loss": 1.7618,
      "step": 89
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.31739145146977316,
      "learning_rate": 8.597910912531857e-05,
      "loss": 1.7678,
      "step": 90
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": 0.12878964888578534,
      "learning_rate": 8.559866706404422e-05,
      "loss": 1.6939,
      "step": 91
    },
    {
      "epoch": 0.31861471861471863,
      "grad_norm": 0.1294085657296158,
      "learning_rate": 8.521411294877998e-05,
      "loss": 1.9087,
      "step": 92
    },
    {
      "epoch": 0.3220779220779221,
      "grad_norm": 0.13843213421574815,
      "learning_rate": 8.482549845848562e-05,
      "loss": 1.889,
      "step": 93
    },
    {
      "epoch": 0.3255411255411255,
      "grad_norm": 0.11234571905653916,
      "learning_rate": 8.443287581778132e-05,
      "loss": 1.761,
      "step": 94
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 0.28802636544720606,
      "learning_rate": 8.403629778992935e-05,
      "loss": 1.7695,
      "step": 95
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 0.17442102072693685,
      "learning_rate": 8.363581766974347e-05,
      "loss": 1.868,
      "step": 96
    },
    {
      "epoch": 0.3359307359307359,
      "grad_norm": 0.18092190501025998,
      "learning_rate": 8.323148927642676e-05,
      "loss": 1.8138,
      "step": 97
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.14180736758315962,
      "learning_rate": 8.282336694633897e-05,
      "loss": 1.7451,
      "step": 98
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.1260334956751797,
      "learning_rate": 8.241150552569461e-05,
      "loss": 1.8159,
      "step": 99
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 0.28483954218537194,
      "learning_rate": 8.199596036319213e-05,
      "loss": 1.8712,
      "step": 100
    },
    {
      "epoch": 0.3497835497835498,
      "grad_norm": 0.3058596658282089,
      "learning_rate": 8.157678730257599e-05,
      "loss": 1.716,
      "step": 101
    },
    {
      "epoch": 0.35324675324675325,
      "grad_norm": 0.14780337095271387,
      "learning_rate": 8.115404267513189e-05,
      "loss": 1.5771,
      "step": 102
    },
    {
      "epoch": 0.3567099567099567,
      "grad_norm": 0.12983691765086658,
      "learning_rate": 8.072778329211661e-05,
      "loss": 1.7949,
      "step": 103
    },
    {
      "epoch": 0.3601731601731602,
      "grad_norm": 0.16953000547808353,
      "learning_rate": 8.029806643712335e-05,
      "loss": 1.7907,
      "step": 104
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.14609853698140796,
      "learning_rate": 7.986494985838359e-05,
      "loss": 1.8516,
      "step": 105
    },
    {
      "epoch": 0.3670995670995671,
      "grad_norm": 0.22124945234658114,
      "learning_rate": 7.942849176100647e-05,
      "loss": 1.694,
      "step": 106
    },
    {
      "epoch": 0.37056277056277054,
      "grad_norm": 0.15542150684527328,
      "learning_rate": 7.898875079915673e-05,
      "loss": 1.6885,
      "step": 107
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 0.22905935117923695,
      "learning_rate": 7.854578606817258e-05,
      "loss": 1.7547,
      "step": 108
    },
    {
      "epoch": 0.3774891774891775,
      "grad_norm": 0.1499752392806047,
      "learning_rate": 7.809965709662383e-05,
      "loss": 1.7788,
      "step": 109
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.15569825335048748,
      "learning_rate": 7.765042383831217e-05,
      "loss": 1.6898,
      "step": 110
    },
    {
      "epoch": 0.38441558441558443,
      "grad_norm": 0.23871935106992861,
      "learning_rate": 7.719814666421421e-05,
      "loss": 1.76,
      "step": 111
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.1525667688507407,
      "learning_rate": 7.674288635436826e-05,
      "loss": 1.7709,
      "step": 112
    },
    {
      "epoch": 0.3913419913419913,
      "grad_norm": 0.16436932375822805,
      "learning_rate": 7.628470408970652e-05,
      "loss": 1.8098,
      "step": 113
    },
    {
      "epoch": 0.3948051948051948,
      "grad_norm": 0.14429830327760923,
      "learning_rate": 7.582366144383298e-05,
      "loss": 1.7326,
      "step": 114
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 0.18442389673710763,
      "learning_rate": 7.535982037474891e-05,
      "loss": 1.878,
      "step": 115
    },
    {
      "epoch": 0.4017316017316017,
      "grad_norm": 0.1606647287097204,
      "learning_rate": 7.489324321652635e-05,
      "loss": 1.8083,
      "step": 116
    },
    {
      "epoch": 0.4051948051948052,
      "grad_norm": 0.21550638422267673,
      "learning_rate": 7.442399267093145e-05,
      "loss": 1.7426,
      "step": 117
    },
    {
      "epoch": 0.40865800865800866,
      "grad_norm": 0.1398337195854571,
      "learning_rate": 7.395213179899797e-05,
      "loss": 1.8002,
      "step": 118
    },
    {
      "epoch": 0.40865800865800866,
      "eval_loss": 1.9487916231155396,
      "eval_runtime": 293.7231,
      "eval_samples_per_second": 0.34,
      "eval_steps_per_second": 0.17,
      "step": 118
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": 0.25611170557780655,
      "learning_rate": 7.34777240125529e-05,
      "loss": 1.6664,
      "step": 119
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.17940479460583333,
      "learning_rate": 7.300083306569465e-05,
      "loss": 1.6816,
      "step": 120
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 0.15017902454932838,
      "learning_rate": 7.252152304622533e-05,
      "loss": 1.8012,
      "step": 121
    },
    {
      "epoch": 0.4225108225108225,
      "grad_norm": 0.14284666939949986,
      "learning_rate": 7.203985836703833e-05,
      "loss": 1.6545,
      "step": 122
    },
    {
      "epoch": 0.42597402597402595,
      "grad_norm": 0.1559473771327877,
      "learning_rate": 7.155590375746192e-05,
      "loss": 1.7871,
      "step": 123
    },
    {
      "epoch": 0.42943722943722945,
      "grad_norm": 0.14475597256584571,
      "learning_rate": 7.106972425456059e-05,
      "loss": 1.865,
      "step": 124
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 0.14244658764044832,
      "learning_rate": 7.058138519439493e-05,
      "loss": 1.8481,
      "step": 125
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.14693435900184554,
      "learning_rate": 7.009095220324128e-05,
      "loss": 1.8633,
      "step": 126
    },
    {
      "epoch": 0.43982683982683984,
      "grad_norm": 0.3739649239005357,
      "learning_rate": 6.959849118877247e-05,
      "loss": 1.6491,
      "step": 127
    },
    {
      "epoch": 0.4432900432900433,
      "grad_norm": 0.15353898219906464,
      "learning_rate": 6.91040683312007e-05,
      "loss": 1.7563,
      "step": 128
    },
    {
      "epoch": 0.44675324675324674,
      "grad_norm": 0.17393666770414995,
      "learning_rate": 6.860775007438383e-05,
      "loss": 1.6639,
      "step": 129
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 0.5088738245902021,
      "learning_rate": 6.81096031168961e-05,
      "loss": 1.6868,
      "step": 130
    },
    {
      "epoch": 0.4536796536796537,
      "grad_norm": 0.14154446443655647,
      "learning_rate": 6.760969440306488e-05,
      "loss": 1.7063,
      "step": 131
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.14714279411071443,
      "learning_rate": 6.710809111397414e-05,
      "loss": 1.6543,
      "step": 132
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": 0.1457931614410346,
      "learning_rate": 6.66048606584362e-05,
      "loss": 1.7306,
      "step": 133
    },
    {
      "epoch": 0.4640692640692641,
      "grad_norm": 0.1820287707917239,
      "learning_rate": 6.610007066393298e-05,
      "loss": 1.7588,
      "step": 134
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.13406985602901073,
      "learning_rate": 6.559378896752764e-05,
      "loss": 1.6295,
      "step": 135
    },
    {
      "epoch": 0.470995670995671,
      "grad_norm": 0.1432972375320372,
      "learning_rate": 6.508608360674825e-05,
      "loss": 1.7229,
      "step": 136
    },
    {
      "epoch": 0.47445887445887447,
      "grad_norm": 0.1428289854884471,
      "learning_rate": 6.457702281044451e-05,
      "loss": 1.7604,
      "step": 137
    },
    {
      "epoch": 0.4779220779220779,
      "grad_norm": 0.19259569118792785,
      "learning_rate": 6.406667498961853e-05,
      "loss": 1.7896,
      "step": 138
    },
    {
      "epoch": 0.48138528138528136,
      "grad_norm": 0.1864354045164866,
      "learning_rate": 6.355510872823144e-05,
      "loss": 1.7054,
      "step": 139
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.16126945970699844,
      "learning_rate": 6.304239277398663e-05,
      "loss": 1.617,
      "step": 140
    },
    {
      "epoch": 0.4883116883116883,
      "grad_norm": 0.16374325192757327,
      "learning_rate": 6.252859602909085e-05,
      "loss": 1.7218,
      "step": 141
    },
    {
      "epoch": 0.49177489177489175,
      "grad_norm": 0.1952160819129351,
      "learning_rate": 6.201378754099481e-05,
      "loss": 1.6761,
      "step": 142
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 0.21245873164185414,
      "learning_rate": 6.149803649311398e-05,
      "loss": 1.7334,
      "step": 143
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 0.26373074560690185,
      "learning_rate": 6.0981412195531394e-05,
      "loss": 1.7975,
      "step": 144
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 0.13130587484364126,
      "learning_rate": 6.046398407568321e-05,
      "loss": 1.6963,
      "step": 145
    },
    {
      "epoch": 0.5056277056277056,
      "grad_norm": 0.2946558079919653,
      "learning_rate": 5.994582166902862e-05,
      "loss": 1.6738,
      "step": 146
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.1504401196101401,
      "learning_rate": 5.9426994609705167e-05,
      "loss": 1.7497,
      "step": 147
    },
    {
      "epoch": 0.5125541125541125,
      "grad_norm": 0.1699306898333981,
      "learning_rate": 5.890757262117092e-05,
      "loss": 1.7837,
      "step": 148
    },
    {
      "epoch": 0.516017316017316,
      "grad_norm": 0.17221685345492665,
      "learning_rate": 5.838762550683449e-05,
      "loss": 1.7598,
      "step": 149
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.14578009779117443,
      "learning_rate": 5.786722314067443e-05,
      "loss": 1.7327,
      "step": 150
    },
    {
      "epoch": 0.5229437229437229,
      "grad_norm": 0.12696754203014826,
      "learning_rate": 5.7346435457849077e-05,
      "loss": 1.8431,
      "step": 151
    },
    {
      "epoch": 0.5264069264069264,
      "grad_norm": 0.2762648056037374,
      "learning_rate": 5.68253324452982e-05,
      "loss": 1.8256,
      "step": 152
    },
    {
      "epoch": 0.5298701298701298,
      "grad_norm": 0.16006386814999288,
      "learning_rate": 5.630398413233771e-05,
      "loss": 1.5694,
      "step": 153
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.26526907326241866,
      "learning_rate": 5.5782460581248605e-05,
      "loss": 1.6618,
      "step": 154
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 0.16031072879740277,
      "learning_rate": 5.5260831877861595e-05,
      "loss": 1.7254,
      "step": 155
    },
    {
      "epoch": 0.5402597402597402,
      "grad_norm": 0.33676205223750044,
      "learning_rate": 5.473916812213843e-05,
      "loss": 1.6954,
      "step": 156
    },
    {
      "epoch": 0.5437229437229437,
      "grad_norm": 0.19851104745562503,
      "learning_rate": 5.421753941875139e-05,
      "loss": 1.6451,
      "step": 157
    },
    {
      "epoch": 0.5471861471861472,
      "grad_norm": 0.14860904648265985,
      "learning_rate": 5.369601586766231e-05,
      "loss": 1.6706,
      "step": 158
    },
    {
      "epoch": 0.5506493506493506,
      "grad_norm": 0.1918922225725335,
      "learning_rate": 5.3174667554701807e-05,
      "loss": 1.7438,
      "step": 159
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 0.14075522683093092,
      "learning_rate": 5.265356454215095e-05,
      "loss": 1.7224,
      "step": 160
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": 0.15496076267116046,
      "learning_rate": 5.2132776859325595e-05,
      "loss": 1.782,
      "step": 161
    },
    {
      "epoch": 0.561038961038961,
      "grad_norm": 0.14206902015954567,
      "learning_rate": 5.161237449316553e-05,
      "loss": 1.7243,
      "step": 162
    },
    {
      "epoch": 0.5645021645021645,
      "grad_norm": 0.14890489490820047,
      "learning_rate": 5.109242737882909e-05,
      "loss": 1.7799,
      "step": 163
    },
    {
      "epoch": 0.567965367965368,
      "grad_norm": 0.16028268624898823,
      "learning_rate": 5.057300539029484e-05,
      "loss": 1.4963,
      "step": 164
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.2051022099288977,
      "learning_rate": 5.00541783309714e-05,
      "loss": 1.8039,
      "step": 165
    },
    {
      "epoch": 0.5748917748917749,
      "grad_norm": 0.15327061149973434,
      "learning_rate": 4.953601592431679e-05,
      "loss": 1.7388,
      "step": 166
    },
    {
      "epoch": 0.5783549783549784,
      "grad_norm": 0.16523339444574944,
      "learning_rate": 4.9018587804468616e-05,
      "loss": 1.729,
      "step": 167
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.1727169607709046,
      "learning_rate": 4.8501963506886026e-05,
      "loss": 1.6802,
      "step": 168
    },
    {
      "epoch": 0.5852813852813853,
      "grad_norm": 0.1597167200325283,
      "learning_rate": 4.798621245900522e-05,
      "loss": 1.6909,
      "step": 169
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 0.16533426273811605,
      "learning_rate": 4.747140397090915e-05,
      "loss": 1.7411,
      "step": 170
    },
    {
      "epoch": 0.5922077922077922,
      "grad_norm": 0.15690121637261828,
      "learning_rate": 4.6957607226013386e-05,
      "loss": 1.6433,
      "step": 171
    },
    {
      "epoch": 0.5956709956709957,
      "grad_norm": 0.14430263110279673,
      "learning_rate": 4.6444891271768585e-05,
      "loss": 1.4937,
      "step": 172
    },
    {
      "epoch": 0.5991341991341992,
      "grad_norm": 0.20258648466753146,
      "learning_rate": 4.593332501038149e-05,
      "loss": 1.7678,
      "step": 173
    },
    {
      "epoch": 0.6025974025974026,
      "grad_norm": 0.21379822253391412,
      "learning_rate": 4.542297718955552e-05,
      "loss": 1.7766,
      "step": 174
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.254670201330481,
      "learning_rate": 4.491391639325176e-05,
      "loss": 1.5055,
      "step": 175
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.14982857678293512,
      "learning_rate": 4.440621103247237e-05,
      "loss": 1.811,
      "step": 176
    },
    {
      "epoch": 0.612987012987013,
      "grad_norm": 0.3221501849805362,
      "learning_rate": 4.3899929336067026e-05,
      "loss": 1.7188,
      "step": 177
    },
    {
      "epoch": 0.612987012987013,
      "eval_loss": 1.9185175895690918,
      "eval_runtime": 293.6672,
      "eval_samples_per_second": 0.341,
      "eval_steps_per_second": 0.17,
      "step": 177
    },
    {
      "epoch": 0.6164502164502165,
      "grad_norm": 0.1731935798139185,
      "learning_rate": 4.339513934156381e-05,
      "loss": 1.7036,
      "step": 178
    },
    {
      "epoch": 0.6199134199134199,
      "grad_norm": 0.16249320381581486,
      "learning_rate": 4.289190888602587e-05,
      "loss": 1.71,
      "step": 179
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.1902271793415421,
      "learning_rate": 4.239030559693512e-05,
      "loss": 1.7375,
      "step": 180
    },
    {
      "epoch": 0.6268398268398269,
      "grad_norm": 0.17531303512998433,
      "learning_rate": 4.1890396883103924e-05,
      "loss": 1.6996,
      "step": 181
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 0.17481423497584686,
      "learning_rate": 4.1392249925616186e-05,
      "loss": 1.7668,
      "step": 182
    },
    {
      "epoch": 0.6337662337662338,
      "grad_norm": 0.4334115272063004,
      "learning_rate": 4.089593166879931e-05,
      "loss": 1.7081,
      "step": 183
    },
    {
      "epoch": 0.6372294372294373,
      "grad_norm": 0.20688540823844873,
      "learning_rate": 4.040150881122754e-05,
      "loss": 1.7735,
      "step": 184
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 0.32317827783506425,
      "learning_rate": 3.990904779675874e-05,
      "loss": 1.8158,
      "step": 185
    },
    {
      "epoch": 0.6441558441558441,
      "grad_norm": 0.1691288788691292,
      "learning_rate": 3.941861480560508e-05,
      "loss": 1.7672,
      "step": 186
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 0.1584883120734462,
      "learning_rate": 3.8930275745439416e-05,
      "loss": 1.823,
      "step": 187
    },
    {
      "epoch": 0.651082251082251,
      "grad_norm": 0.17327298666115296,
      "learning_rate": 3.8444096242538095e-05,
      "loss": 1.7887,
      "step": 188
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.23742488505369586,
      "learning_rate": 3.7960141632961675e-05,
      "loss": 1.7245,
      "step": 189
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 0.3334448239855052,
      "learning_rate": 3.7478476953774675e-05,
      "loss": 1.6499,
      "step": 190
    },
    {
      "epoch": 0.6614718614718614,
      "grad_norm": 0.14288989763047222,
      "learning_rate": 3.6999166934305384e-05,
      "loss": 1.639,
      "step": 191
    },
    {
      "epoch": 0.6649350649350649,
      "grad_norm": 0.17597033124467082,
      "learning_rate": 3.652227598744713e-05,
      "loss": 1.7659,
      "step": 192
    },
    {
      "epoch": 0.6683982683982684,
      "grad_norm": 0.1481626125821947,
      "learning_rate": 3.604786820100205e-05,
      "loss": 1.7302,
      "step": 193
    },
    {
      "epoch": 0.6718614718614718,
      "grad_norm": 0.1913067720732489,
      "learning_rate": 3.557600732906857e-05,
      "loss": 1.7382,
      "step": 194
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 0.1549292377420287,
      "learning_rate": 3.510675678347366e-05,
      "loss": 1.8693,
      "step": 195
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 0.27044187175312145,
      "learning_rate": 3.464017962525111e-05,
      "loss": 1.7003,
      "step": 196
    },
    {
      "epoch": 0.6822510822510822,
      "grad_norm": 0.1487612518462415,
      "learning_rate": 3.417633855616702e-05,
      "loss": 1.661,
      "step": 197
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.14770557805481802,
      "learning_rate": 3.37152959102935e-05,
      "loss": 1.6209,
      "step": 198
    },
    {
      "epoch": 0.6891774891774892,
      "grad_norm": 0.19753949166856186,
      "learning_rate": 3.325711364563174e-05,
      "loss": 1.6268,
      "step": 199
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 0.19557699435491527,
      "learning_rate": 3.2801853335785815e-05,
      "loss": 1.6176,
      "step": 200
    },
    {
      "epoch": 0.6961038961038961,
      "grad_norm": 0.3049720125391528,
      "learning_rate": 3.234957616168784e-05,
      "loss": 1.6267,
      "step": 201
    },
    {
      "epoch": 0.6995670995670996,
      "grad_norm": 0.16006140974472785,
      "learning_rate": 3.190034290337619e-05,
      "loss": 1.601,
      "step": 202
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": 0.1830402821474818,
      "learning_rate": 3.1454213931827434e-05,
      "loss": 1.7327,
      "step": 203
    },
    {
      "epoch": 0.7064935064935065,
      "grad_norm": 0.18546433691116893,
      "learning_rate": 3.1011249200843275e-05,
      "loss": 1.6545,
      "step": 204
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 0.2138015586288683,
      "learning_rate": 3.0571508238993564e-05,
      "loss": 1.7183,
      "step": 205
    },
    {
      "epoch": 0.7134199134199134,
      "grad_norm": 0.21468892402946096,
      "learning_rate": 3.0135050141616416e-05,
      "loss": 1.6208,
      "step": 206
    },
    {
      "epoch": 0.7168831168831169,
      "grad_norm": 0.1882751964380619,
      "learning_rate": 2.970193356287666e-05,
      "loss": 1.7382,
      "step": 207
    },
    {
      "epoch": 0.7203463203463204,
      "grad_norm": 0.18629282268698374,
      "learning_rate": 2.9272216707883392e-05,
      "loss": 1.6971,
      "step": 208
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 0.15099779711309158,
      "learning_rate": 2.8845957324868127e-05,
      "loss": 1.5243,
      "step": 209
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.1892846305503724,
      "learning_rate": 2.8423212697424017e-05,
      "loss": 1.6373,
      "step": 210
    },
    {
      "epoch": 0.7307359307359307,
      "grad_norm": 0.27675378658153443,
      "learning_rate": 2.8004039636807876e-05,
      "loss": 1.7585,
      "step": 211
    },
    {
      "epoch": 0.7341991341991342,
      "grad_norm": 0.2038541215571779,
      "learning_rate": 2.7588494474305415e-05,
      "loss": 1.6502,
      "step": 212
    },
    {
      "epoch": 0.7376623376623377,
      "grad_norm": 0.16200871543059178,
      "learning_rate": 2.7176633053661028e-05,
      "loss": 1.7047,
      "step": 213
    },
    {
      "epoch": 0.7411255411255411,
      "grad_norm": 0.2549165666589742,
      "learning_rate": 2.6768510723573254e-05,
      "loss": 1.5592,
      "step": 214
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.23118437904882855,
      "learning_rate": 2.636418233025652e-05,
      "loss": 1.7598,
      "step": 215
    },
    {
      "epoch": 0.7480519480519481,
      "grad_norm": 0.1460731671117374,
      "learning_rate": 2.596370221007065e-05,
      "loss": 1.7761,
      "step": 216
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": 0.16573366999606748,
      "learning_rate": 2.5567124182218695e-05,
      "loss": 1.657,
      "step": 217
    },
    {
      "epoch": 0.754978354978355,
      "grad_norm": 0.34384964355975495,
      "learning_rate": 2.5174501541514388e-05,
      "loss": 1.6525,
      "step": 218
    },
    {
      "epoch": 0.7584415584415585,
      "grad_norm": 0.17005667389728593,
      "learning_rate": 2.4785887051220015e-05,
      "loss": 1.5891,
      "step": 219
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.18892149333026265,
      "learning_rate": 2.4401332935955788e-05,
      "loss": 1.8492,
      "step": 220
    },
    {
      "epoch": 0.7653679653679654,
      "grad_norm": 0.17440059994971285,
      "learning_rate": 2.402089087468144e-05,
      "loss": 1.5563,
      "step": 221
    },
    {
      "epoch": 0.7688311688311689,
      "grad_norm": 0.16942774342319117,
      "learning_rate": 2.3644611993751347e-05,
      "loss": 1.6959,
      "step": 222
    },
    {
      "epoch": 0.7722943722943723,
      "grad_norm": 0.2194491735760687,
      "learning_rate": 2.3272546860043838e-05,
      "loss": 1.6236,
      "step": 223
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.2555341946924789,
      "learning_rate": 2.290474547416561e-05,
      "loss": 1.7057,
      "step": 224
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.16820614826667607,
      "learning_rate": 2.2541257263732344e-05,
      "loss": 1.7269,
      "step": 225
    },
    {
      "epoch": 0.7826839826839826,
      "grad_norm": 0.1983255227664725,
      "learning_rate": 2.2182131076726295e-05,
      "loss": 1.7205,
      "step": 226
    },
    {
      "epoch": 0.7861471861471861,
      "grad_norm": 0.2788686651713739,
      "learning_rate": 2.1827415174931804e-05,
      "loss": 1.7635,
      "step": 227
    },
    {
      "epoch": 0.7896103896103897,
      "grad_norm": 0.2062641389634287,
      "learning_rate": 2.1477157227449465e-05,
      "loss": 1.8045,
      "step": 228
    },
    {
      "epoch": 0.793073593073593,
      "grad_norm": 0.33007694187551695,
      "learning_rate": 2.113140430429015e-05,
      "loss": 1.7512,
      "step": 229
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 0.26385180163133926,
      "learning_rate": 2.0790202870049304e-05,
      "loss": 1.7776,
      "step": 230
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.17179213201020885,
      "learning_rate": 2.0453598777662844e-05,
      "loss": 1.7834,
      "step": 231
    },
    {
      "epoch": 0.8034632034632034,
      "grad_norm": 0.18683501191265228,
      "learning_rate": 2.0121637262245014e-05,
      "loss": 1.6556,
      "step": 232
    },
    {
      "epoch": 0.8069264069264069,
      "grad_norm": 0.20557603200486302,
      "learning_rate": 1.9794362935009463e-05,
      "loss": 1.7518,
      "step": 233
    },
    {
      "epoch": 0.8103896103896104,
      "grad_norm": 0.17665938111234616,
      "learning_rate": 1.947181977727411e-05,
      "loss": 1.6748,
      "step": 234
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 0.357745173185865,
      "learning_rate": 1.9154051134550533e-05,
      "loss": 1.6295,
      "step": 235
    },
    {
      "epoch": 0.8173160173160173,
      "grad_norm": 0.20362418089738105,
      "learning_rate": 1.8841099710719053e-05,
      "loss": 1.7306,
      "step": 236
    },
    {
      "epoch": 0.8173160173160173,
      "eval_loss": 1.9117217063903809,
      "eval_runtime": 293.7102,
      "eval_samples_per_second": 0.34,
      "eval_steps_per_second": 0.17,
      "step": 236
    }
  ],
  "logging_steps": 1,
  "max_steps": 291,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 59,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8153071330656256e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}