{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7912087912087912,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.7760576009750366,
      "learning_rate": 0.0,
      "loss": 2.8624,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.627739667892456,
      "learning_rate": 4e-05,
      "loss": 2.7707,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 2.411036252975464,
      "learning_rate": 8e-05,
      "loss": 3.0115,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.5725748538970947,
      "learning_rate": 0.00012,
      "loss": 2.578,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.3334898948669434,
      "learning_rate": 0.00016,
      "loss": 2.8116,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.7522525787353516,
      "learning_rate": 0.0002,
      "loss": 2.8591,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1036670207977295,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6592,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8711436986923218,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.628,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8910020589828491,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2578,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.2549653053283691,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.2032,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.1423015594482422,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3174,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6086552143096924,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0803,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.38326704502105713,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0704,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5326745510101318,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0406,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5318218469619751,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1875,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4647858440876007,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0578,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4215516448020935,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.8499,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3335304856300354,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9383,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3218725621700287,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7817,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4266487658023834,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9411,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.38664567470550537,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9421,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.38386937975883484,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.89,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.34860938787460327,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.023,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.36557498574256897,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1004,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.35893023014068604,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0868,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.333647757768631,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8831,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3089407980442047,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9126,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3301669657230377,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9857,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2866484522819519,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0487,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3685723543167114,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1583,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.36198097467422485,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.1913,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.36270424723625183,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9796,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.35049617290496826,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0984,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.30711936950683594,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8514,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3361266553401947,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7835,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.31940892338752747,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9101,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.32473820447921753,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.173,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.2708457410335541,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0028,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.35012125968933105,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9161,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.2810596525669098,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9089,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.326106458902359,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8728,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2742505669593811,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9115,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.328368604183197,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9528,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.35647979378700256,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.2276,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4501672685146332,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.2159,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.5152194499969482,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.1993,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.26086127758026123,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7308,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34976181387901306,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0843,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.39914363622665405,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9755,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.33914342522621155,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0366,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3376713693141937,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.958,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3070376515388489,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.947,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2706867754459381,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8023,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3382069170475006,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9184,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2898756265640259,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9894,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3399081528186798,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.9053,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3918396830558777,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0006,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.35674360394477844,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9065,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.31635716557502747,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8588,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.29990875720977783,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.944,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4008603096008301,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9256,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3022041916847229,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.908,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.26360005140304565,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8749,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3298325836658478,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.1187,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3574797511100769,
      "learning_rate": 0.0001738359201773836,
      "loss": 1.0554,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.32374486327171326,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.8371,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.38102686405181885,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.0452,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.30039891600608826,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6833,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3794395327568054,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.943,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3144315779209137,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8897,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3287697434425354,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.7885,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3307992219924927,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8951,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.31876420974731445,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0449,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.32964083552360535,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.0146,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3033060133457184,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9456,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.39799225330352783,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.0701,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3029780387878418,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0342,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3820551633834839,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0372,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2455594688653946,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8209,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.35084041953086853,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.1386,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.4059063196182251,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.0704,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.28880801796913147,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.941,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2802966833114624,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.7446,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3626139760017395,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.2344,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.2894216775894165,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8722,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.33207154273986816,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8346,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3496438264846802,
      "learning_rate": 0.000164079822616408,
      "loss": 0.9866,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.262410968542099,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8781,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.33365076780319214,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9782,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.38833490014076233,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9261,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3653523325920105,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9241,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3591654896736145,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8284,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.35526201128959656,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.1674,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3529767394065857,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9327,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.37259340286254883,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0421,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3770660161972046,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9368,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.38265588879585266,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9695,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.336265504360199,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9045,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2600400745868683,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7187,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3092184364795685,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9763,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.31736651062965393,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.7791,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3679843246936798,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.0813,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.4214973747730255,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8937,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3891105353832245,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.1075,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3421161472797394,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.0693,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3559079170227051,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0473,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3279852867126465,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.0138,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.2687285244464874,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8871,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.29114097356796265,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.8594,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.24637137353420258,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.7653,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.31702902913093567,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.0376,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3365715742111206,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8419,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.24790500104427338,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.7398,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3369625508785248,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.9242,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.30920329689979553,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9772,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.29591354727745056,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.7697,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3208312392234802,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9581,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.5094884037971497,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.8935,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.31081950664520264,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.906,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3331546187400818,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.881,
      "step": 120
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.92316343881728e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}