{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6923076923076923,
  "eval_steps": 500,
  "global_step": 105,
  "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": 0.8124693632125854,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3178,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4746452569961548,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3747,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0956214666366577,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2291,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5584886074066162,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2929,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8778825402259827,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0355,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5020594596862793,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1668,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4985601305961609,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1048,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4597553312778473,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0144,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.44980549812316895,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.128,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.33276212215423584,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9434,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.46772485971450806,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2302,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3876091241836548,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0448,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3786633610725403,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0449,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4180683195590973,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1112,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4051693081855774,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0586,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30783703923225403,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.9412,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3420283794403076,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9213,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.47376200556755066,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9635,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3626822233200073,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7696,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.46646377444267273,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.098,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.38763922452926636,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1587,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3439793288707733,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1153,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.30000773072242737,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9554,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3823530972003937,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8394,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.34664639830589294,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9849,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3785923719406128,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9833,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2902650535106659,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8436,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3445191979408264,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.1307,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3029124438762665,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9933,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.35134652256965637,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0888,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3323468863964081,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9426,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.30780231952667236,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0471,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.33622869849205017,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0502,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27680298686027527,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9102,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30690091848373413,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8996,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.25448524951934814,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.1005,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.34958240389823914,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0281,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4468621015548706,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0252,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31876784563064575,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8992,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34545132517814636,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.068,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.32640132308006287,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.1285,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3564831018447876,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.2185,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.32339203357696533,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0446,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.35078808665275574,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.1539,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2938004732131958,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9885,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3535275459289551,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.2243,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.27938902378082275,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8127,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3669883906841278,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1137,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.29758307337760925,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8903,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.33421579003334045,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9599,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2770750820636749,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8669,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.30138126015663147,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9341,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.40909135341644287,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9882,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3172509968280792,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.947,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3970111012458801,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0486,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.31454795598983765,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0186,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3479641079902649,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9327,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3524766266345978,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9507,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2844376266002655,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7746,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3422749638557434,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.0457,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4011959135532379,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.007,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4012478291988373,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0548,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3155313730239868,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0115,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.42125996947288513,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.0328,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24873152375221252,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8636,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3159611225128174,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.33214104175567627,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9654,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.347202867269516,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9652,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2956635653972626,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8443,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.32437971234321594,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7974,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.34554967284202576,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8792,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.36469560861587524,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.866,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.344759076833725,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8353,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.34023046493530273,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.02,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.333598256111145,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0249,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3101555109024048,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9582,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.33129116892814636,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.1624,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.30904698371887207,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9186,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3824373483657837,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0527,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.32758963108062744,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1586,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.39826932549476624,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.2648,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3101160526275635,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.0503,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5018938183784485,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8718,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.314115434885025,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9757,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3091287314891815,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9042,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3007432520389557,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9866,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.33295589685440063,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8291,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3381161689758301,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.0308,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3053942024707794,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7676,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.32999739050865173,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7638,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.4934881627559662,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9291,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.36715981364250183,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9131,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3625679314136505,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0562,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.36306384205818176,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9225,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2506583333015442,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.7906,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.34501585364341736,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.866,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3541669547557831,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.936,
      "step": 105
    }
  ],
  "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": 1.6937831600160768e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}