{
  "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": 2.303626298904419,
      "learning_rate": 0.0,
      "loss": 3.6085,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.439454436302185,
      "learning_rate": 4e-05,
      "loss": 2.4913,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.7588273286819458,
      "learning_rate": 8e-05,
      "loss": 2.6433,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.5198580026626587,
      "learning_rate": 0.00012,
      "loss": 2.3145,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.8622243404388428,
      "learning_rate": 0.00016,
      "loss": 2.4423,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6957828998565674,
      "learning_rate": 0.0002,
      "loss": 2.1699,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.3653955459594727,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5512,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.867249846458435,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4124,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9426868557929993,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4026,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.105395793914795,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.2543,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.788772702217102,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2154,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.53281569480896,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2039,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.40713539719581604,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0836,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5409032702445984,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1098,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.47973766922950745,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.19,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5039457678794861,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1809,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.432468056678772,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1579,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.49248069524765015,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0721,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.506483256816864,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2076,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3699564039707184,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8558,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40447086095809937,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9758,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.42658472061157227,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.062,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3948553204536438,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9631,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.32725754380226135,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0747,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.33828970789909363,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0653,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.27442067861557007,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9254,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27329978346824646,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9075,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.41785359382629395,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0079,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.282429963350296,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.8602,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.37518325448036194,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0907,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2990609407424927,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8994,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.33431681990623474,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9115,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.31373974680900574,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9089,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2787388563156128,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0808,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3206472396850586,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9184,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2402617186307907,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.7528,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.34411153197288513,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9755,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34733089804649353,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0181,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3262622356414795,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0464,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.24500015377998352,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9446,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.2835443913936615,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9856,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27747032046318054,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9622,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.34073948860168457,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9465,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.26712504029273987,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0602,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.37089070677757263,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0997,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.30469098687171936,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9438,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31314560770988464,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8367,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33173537254333496,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0277,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2833123803138733,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7779,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28676313161849976,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0172,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.25923117995262146,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7737,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2750239074230194,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8973,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.30605781078338623,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9545,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2281476855278015,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7999,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3172890245914459,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.893,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.38381415605545044,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0448,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3915952146053314,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0564,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.33569052815437317,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0455,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4101047217845917,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0923,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.42315059900283813,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0163,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2661890387535095,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7853,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3342932462692261,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9406,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3210691809654236,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8858,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2718408703804016,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9452,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.36029088497161865,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8777,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.35389444231987,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0064,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3141503930091858,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.8785,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.27303633093833923,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8559,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3359520137310028,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.096,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.30675244331359863,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0009,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3307923972606659,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0056,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.24969322979450226,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8563,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24619445204734802,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8386,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3848130702972412,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.2539,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35728219151496887,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9608,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.41609638929367065,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1981,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3290999233722687,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0885,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3357957899570465,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9842,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.37297511100769043,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0532,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.333650678396225,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0956,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3169361650943756,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9588,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.28924304246902466,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9038,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2601667046546936,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.7903,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.28349757194519043,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8989,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.37565159797668457,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.1042,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.38468965888023376,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.1407,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.28541499376296997,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8125,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2994617223739624,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9195,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3976408839225769,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.0156,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.30622562766075134,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9982,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28931549191474915,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.928,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.31948480010032654,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.0779,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.33104556798934937,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.0611,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.43478959798812866,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9161,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.32590118050575256,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.1696,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.25838395953178406,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.7856,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3152015507221222,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7904,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.34387698769569397,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.991,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2822190821170807,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9494,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.26281842589378357,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9059,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.42032739520072937,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0635,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2608965337276459,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.6873,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.25404682755470276,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9051,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.34183400869369507,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9823,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.29854243993759155,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9067,
      "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": 1.7135947814633472e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}