{
  "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": 1.6525499820709229,
      "learning_rate": 0.0,
      "loss": 2.4309,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.59049391746521,
      "learning_rate": 4e-05,
      "loss": 3.2935,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.4867584705352783,
      "learning_rate": 8e-05,
      "loss": 2.4426,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.8229094743728638,
      "learning_rate": 0.00012,
      "loss": 2.9208,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.2393176555633545,
      "learning_rate": 0.00016,
      "loss": 2.5664,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6051244735717773,
      "learning_rate": 0.0002,
      "loss": 2.4695,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1993753910064697,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6291,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.116241693496704,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3491,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.812495768070221,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3178,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4647173881530762,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3721,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0903385877609253,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2288,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5566668510437012,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2958,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.9000307321548462,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0353,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5002865791320801,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1657,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4956091344356537,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1026,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.46295931935310364,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0131,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.44878455996513367,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1302,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3325801193714142,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9445,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.46596264839172363,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2325,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.38645994663238525,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0453,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3800373375415802,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.045,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4129738211631775,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1104,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.40392687916755676,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0589,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3075926899909973,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.9411,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3475458323955536,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9233,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.49025434255599976,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9665,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3652801215648651,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7703,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.45883381366729736,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0975,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3874357044696808,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1598,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.34444889426231384,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.115,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.29951217770576477,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.954,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3819473087787628,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8394,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.34401172399520874,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9835,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.37742576003074646,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9849,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2915305495262146,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8447,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3420809507369995,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.1309,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.29988887906074524,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9923,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34842392802238464,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0878,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.33255407214164734,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9427,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3048710525035858,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.046,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3348377048969269,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0524,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27776357531547546,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9091,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3071886897087097,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8991,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.25560522079467773,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.1003,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.35056671500205994,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0294,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4527668356895447,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0258,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3258602023124695,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8985,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34211626648902893,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0694,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.33114686608314514,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.1302,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3916858732700348,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.2209,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3141515851020813,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0462,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3583016097545624,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.1564,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3011229634284973,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9886,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.35539111495018005,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.2243,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2820283770561218,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8119,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3814904987812042,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1126,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2957267761230469,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8904,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.33433598279953003,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9598,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.29762426018714905,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8673,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2994730770587921,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9338,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4122157394886017,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9901,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.31992846727371216,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9478,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3978268802165985,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0468,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.31832677125930786,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0186,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.34894299507141113,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9357,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3534030318260193,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9494,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2846975326538086,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7745,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3415786325931549,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.0462,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3965073823928833,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0058,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3992333710193634,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.055,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.31529131531715393,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0131,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.4225400686264038,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.0361,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24861474335193634,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8636,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3111610412597656,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8018,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3332616090774536,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9639,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.34602120518684387,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9634,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.30103614926338196,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8445,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.32351967692375183,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7971,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.34235212206840515,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8789,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.37176913022994995,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8665,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3396773636341095,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8336,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.34001272916793823,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0193,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.331545889377594,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0259,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3043355941772461,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9557,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3296355903148651,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.1619,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3109373450279236,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9192,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.38110268115997314,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0527,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3296146094799042,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1576,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.40074533224105835,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.2656,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.31375083327293396,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.0495,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5065087080001831,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8724,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3122287392616272,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.976,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.32005181908607483,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9045,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.30076995491981506,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9879,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3367771804332733,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8272,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3340472877025604,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.0321,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.303377240896225,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7673,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.32706865668296814,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7637,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.49776825308799744,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9296,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.369322806596756,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9106,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3643234074115753,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.056,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3607897460460663,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9218,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2506844401359558,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.7911,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3446638584136963,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8677,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.35222387313842773,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9361,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.32228022813796997,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0088,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3090541958808899,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.1929,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.28619226813316345,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8911,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.35866305232048035,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0714,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33254724740982056,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0228,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.35273459553718567,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9127,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3310684859752655,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.832,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3684999942779541,
      "learning_rate": 0.00015254988913525498,
      "loss": 1.0707,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3729608952999115,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.1418,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3481763005256653,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9622,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.26267939805984497,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9652,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3408680260181427,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9778,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.30004823207855225,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0143,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.27949169278144836,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.0352,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.48710429668426514,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.1032,
      "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": 1.946915289808896e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}