{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18066847335140018,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018066847335140017,
      "grad_norm": 2.8394027200091747,
      "learning_rate": 0.0,
      "loss": 0.8251,
      "step": 1
    },
    {
      "epoch": 0.0036133694670280035,
      "grad_norm": 2.8846288476633135,
      "learning_rate": 1.0714285714285714e-06,
      "loss": 0.8284,
      "step": 2
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 2.9025021758600973,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 0.8427,
      "step": 3
    },
    {
      "epoch": 0.007226738934056007,
      "grad_norm": 2.8006966406467435,
      "learning_rate": 3.2142857142857143e-06,
      "loss": 0.8377,
      "step": 4
    },
    {
      "epoch": 0.009033423667570008,
      "grad_norm": 2.5933707261583208,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.8227,
      "step": 5
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 2.0871248987589857,
      "learning_rate": 5.357142857142857e-06,
      "loss": 0.8095,
      "step": 6
    },
    {
      "epoch": 0.012646793134598013,
      "grad_norm": 1.5051624332871105,
      "learning_rate": 6.428571428571429e-06,
      "loss": 0.7739,
      "step": 7
    },
    {
      "epoch": 0.014453477868112014,
      "grad_norm": 1.390065658542279,
      "learning_rate": 7.5e-06,
      "loss": 0.7734,
      "step": 8
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 1.3346375437162221,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.7655,
      "step": 9
    },
    {
      "epoch": 0.018066847335140017,
      "grad_norm": 2.368502454719072,
      "learning_rate": 9.642857142857144e-06,
      "loss": 0.7502,
      "step": 10
    },
    {
      "epoch": 0.01987353206865402,
      "grad_norm": 2.355019739749437,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 0.7355,
      "step": 11
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 2.235397645486187,
      "learning_rate": 1.1785714285714286e-05,
      "loss": 0.7489,
      "step": 12
    },
    {
      "epoch": 0.023486901535682024,
      "grad_norm": 1.8443725862230025,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.7253,
      "step": 13
    },
    {
      "epoch": 0.025293586269196026,
      "grad_norm": 3.9119844600464275,
      "learning_rate": 1.3928571428571429e-05,
      "loss": 0.7285,
      "step": 14
    },
    {
      "epoch": 0.02710027100271003,
      "grad_norm": 1.6411422206825859,
      "learning_rate": 1.5e-05,
      "loss": 0.7284,
      "step": 15
    },
    {
      "epoch": 0.028906955736224028,
      "grad_norm": 1.3411860085380753,
      "learning_rate": 1.6071428571428572e-05,
      "loss": 0.7105,
      "step": 16
    },
    {
      "epoch": 0.03071364046973803,
      "grad_norm": 1.157320872714633,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.7068,
      "step": 17
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.7462236915744604,
      "learning_rate": 1.8214285714285712e-05,
      "loss": 0.6926,
      "step": 18
    },
    {
      "epoch": 0.03432700993676603,
      "grad_norm": 0.8473541980236234,
      "learning_rate": 1.928571428571429e-05,
      "loss": 0.6858,
      "step": 19
    },
    {
      "epoch": 0.036133694670280034,
      "grad_norm": 0.7215438560743268,
      "learning_rate": 2.0357142857142858e-05,
      "loss": 0.6605,
      "step": 20
    },
    {
      "epoch": 0.037940379403794036,
      "grad_norm": 0.6345550993430565,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.6668,
      "step": 21
    },
    {
      "epoch": 0.03974706413730804,
      "grad_norm": 0.6182590458724911,
      "learning_rate": 2.25e-05,
      "loss": 0.6559,
      "step": 22
    },
    {
      "epoch": 0.04155374887082204,
      "grad_norm": 0.623617204927979,
      "learning_rate": 2.357142857142857e-05,
      "loss": 0.6561,
      "step": 23
    },
    {
      "epoch": 0.04336043360433604,
      "grad_norm": 0.5049024834505677,
      "learning_rate": 2.464285714285714e-05,
      "loss": 0.6613,
      "step": 24
    },
    {
      "epoch": 0.045167118337850046,
      "grad_norm": 0.5485283866894338,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 0.6429,
      "step": 25
    },
    {
      "epoch": 0.04697380307136405,
      "grad_norm": 0.5146774550210349,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 0.6572,
      "step": 26
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.4849533483489942,
      "learning_rate": 2.7857142857142858e-05,
      "loss": 0.6352,
      "step": 27
    },
    {
      "epoch": 0.05058717253839205,
      "grad_norm": 0.4679753904023602,
      "learning_rate": 2.892857142857143e-05,
      "loss": 0.6372,
      "step": 28
    },
    {
      "epoch": 0.052393857271906055,
      "grad_norm": 0.49823982670847244,
      "learning_rate": 3e-05,
      "loss": 0.649,
      "step": 29
    },
    {
      "epoch": 0.05420054200542006,
      "grad_norm": 0.3998487451158294,
      "learning_rate": 2.9999731440137413e-05,
      "loss": 0.6492,
      "step": 30
    },
    {
      "epoch": 0.05600722673893405,
      "grad_norm": 0.4037683931810622,
      "learning_rate": 2.9998925770166232e-05,
      "loss": 0.6384,
      "step": 31
    },
    {
      "epoch": 0.057813911472448055,
      "grad_norm": 0.3869283159888842,
      "learning_rate": 2.9997583018935875e-05,
      "loss": 0.6266,
      "step": 32
    },
    {
      "epoch": 0.05962059620596206,
      "grad_norm": 0.4105676527710418,
      "learning_rate": 2.9995703234527553e-05,
      "loss": 0.6365,
      "step": 33
    },
    {
      "epoch": 0.06142728093947606,
      "grad_norm": 0.3428905600355113,
      "learning_rate": 2.999328648425255e-05,
      "loss": 0.6236,
      "step": 34
    },
    {
      "epoch": 0.06323396567299007,
      "grad_norm": 0.3666139696974658,
      "learning_rate": 2.999033285464982e-05,
      "loss": 0.6293,
      "step": 35
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.369662441500822,
      "learning_rate": 2.9986842451482876e-05,
      "loss": 0.6251,
      "step": 36
    },
    {
      "epoch": 0.06684733514001806,
      "grad_norm": 0.3677980333288224,
      "learning_rate": 2.9982815399736008e-05,
      "loss": 0.6297,
      "step": 37
    },
    {
      "epoch": 0.06865401987353206,
      "grad_norm": 0.3223035029779702,
      "learning_rate": 2.9978251843609816e-05,
      "loss": 0.6219,
      "step": 38
    },
    {
      "epoch": 0.07046070460704607,
      "grad_norm": 0.37293367784153375,
      "learning_rate": 2.9973151946516027e-05,
      "loss": 0.6242,
      "step": 39
    },
    {
      "epoch": 0.07226738934056007,
      "grad_norm": 0.322511907065973,
      "learning_rate": 2.996751589107167e-05,
      "loss": 0.6122,
      "step": 40
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.34111037181843756,
      "learning_rate": 2.9961343879092512e-05,
      "loss": 0.6186,
      "step": 41
    },
    {
      "epoch": 0.07588075880758807,
      "grad_norm": 0.30130338237811194,
      "learning_rate": 2.9954636131585845e-05,
      "loss": 0.6113,
      "step": 42
    },
    {
      "epoch": 0.07768744354110207,
      "grad_norm": 0.32753158641617225,
      "learning_rate": 2.9947392888742566e-05,
      "loss": 0.6112,
      "step": 43
    },
    {
      "epoch": 0.07949412827461608,
      "grad_norm": 0.3060506987492754,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.6056,
      "step": 44
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 0.5813127875924191,
      "learning_rate": 2.993130097367553e-05,
      "loss": 0.6131,
      "step": 45
    },
    {
      "epoch": 0.08310749774164408,
      "grad_norm": 0.30546110146813144,
      "learning_rate": 2.9922452877670775e-05,
      "loss": 0.6144,
      "step": 46
    },
    {
      "epoch": 0.08491418247515808,
      "grad_norm": 0.3009821627626054,
      "learning_rate": 2.991307043874677e-05,
      "loss": 0.617,
      "step": 47
    },
    {
      "epoch": 0.08672086720867209,
      "grad_norm": 0.2835661481876977,
      "learning_rate": 2.9903153992869734e-05,
      "loss": 0.6031,
      "step": 48
    },
    {
      "epoch": 0.08852755194218609,
      "grad_norm": 0.31548723118407335,
      "learning_rate": 2.989270389512756e-05,
      "loss": 0.6107,
      "step": 49
    },
    {
      "epoch": 0.09033423667570009,
      "grad_norm": 0.2864309330552123,
      "learning_rate": 2.988172051971717e-05,
      "loss": 0.6097,
      "step": 50
    },
    {
      "epoch": 0.0921409214092141,
      "grad_norm": 0.29953498642613263,
      "learning_rate": 2.9870204259931062e-05,
      "loss": 0.5998,
      "step": 51
    },
    {
      "epoch": 0.0939476061427281,
      "grad_norm": 0.2782739210196595,
      "learning_rate": 2.9858155528143256e-05,
      "loss": 0.6169,
      "step": 52
    },
    {
      "epoch": 0.0957542908762421,
      "grad_norm": 0.3431216549638938,
      "learning_rate": 2.9845574755794522e-05,
      "loss": 0.6024,
      "step": 53
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.26425217740885376,
      "learning_rate": 2.9832462393376926e-05,
      "loss": 0.5921,
      "step": 54
    },
    {
      "epoch": 0.0993676603432701,
      "grad_norm": 0.3422702392148149,
      "learning_rate": 2.9818818910417706e-05,
      "loss": 0.6079,
      "step": 55
    },
    {
      "epoch": 0.1011743450767841,
      "grad_norm": 0.3197424015440345,
      "learning_rate": 2.9804644795462437e-05,
      "loss": 0.612,
      "step": 56
    },
    {
      "epoch": 0.10298102981029811,
      "grad_norm": 0.3035603795716621,
      "learning_rate": 2.9789940556057574e-05,
      "loss": 0.5975,
      "step": 57
    },
    {
      "epoch": 0.10478771454381211,
      "grad_norm": 0.3410992160925094,
      "learning_rate": 2.9774706718732255e-05,
      "loss": 0.6058,
      "step": 58
    },
    {
      "epoch": 0.10659439927732611,
      "grad_norm": 0.27322743279862205,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.592,
      "step": 59
    },
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 0.3639122458989281,
      "learning_rate": 2.9742652451236414e-05,
      "loss": 0.5932,
      "step": 60
    },
    {
      "epoch": 0.1102077687443541,
      "grad_norm": 0.3014533566173352,
      "learning_rate": 2.972583316886451e-05,
      "loss": 0.597,
      "step": 61
    },
    {
      "epoch": 0.1120144534778681,
      "grad_norm": 0.34457895149113055,
      "learning_rate": 2.9708486584128303e-05,
      "loss": 0.6017,
      "step": 62
    },
    {
      "epoch": 0.11382113821138211,
      "grad_norm": 0.30295456441359353,
      "learning_rate": 2.9690613318173966e-05,
      "loss": 0.6015,
      "step": 63
    },
    {
      "epoch": 0.11562782294489611,
      "grad_norm": 0.2899317610304254,
      "learning_rate": 2.9672214011007087e-05,
      "loss": 0.5999,
      "step": 64
    },
    {
      "epoch": 0.11743450767841011,
      "grad_norm": 0.29733861402573497,
      "learning_rate": 2.9653289321469715e-05,
      "loss": 0.5939,
      "step": 65
    },
    {
      "epoch": 0.11924119241192412,
      "grad_norm": 0.27257724173917824,
      "learning_rate": 2.9633839927216793e-05,
      "loss": 0.5969,
      "step": 66
    },
    {
      "epoch": 0.12104787714543812,
      "grad_norm": 0.2898338043822156,
      "learning_rate": 2.9613866524691867e-05,
      "loss": 0.5873,
      "step": 67
    },
    {
      "epoch": 0.12285456187895212,
      "grad_norm": 0.2884348823630205,
      "learning_rate": 2.9593369829102173e-05,
      "loss": 0.6026,
      "step": 68
    },
    {
      "epoch": 0.12466124661246612,
      "grad_norm": 0.28168278457326457,
      "learning_rate": 2.957235057439301e-05,
      "loss": 0.6042,
      "step": 69
    },
    {
      "epoch": 0.12646793134598014,
      "grad_norm": 0.2869178339893195,
      "learning_rate": 2.955080951322147e-05,
      "loss": 0.6085,
      "step": 70
    },
    {
      "epoch": 0.12827461607949414,
      "grad_norm": 0.3037977880321082,
      "learning_rate": 2.9528747416929467e-05,
      "loss": 0.5817,
      "step": 71
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.28914281369381906,
      "learning_rate": 2.9506165075516148e-05,
      "loss": 0.5985,
      "step": 72
    },
    {
      "epoch": 0.13188798554652212,
      "grad_norm": 0.3680574307953626,
      "learning_rate": 2.9483063297609577e-05,
      "loss": 0.5975,
      "step": 73
    },
    {
      "epoch": 0.13369467028003612,
      "grad_norm": 0.3174888148098996,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.5891,
      "step": 74
    },
    {
      "epoch": 0.13550135501355012,
      "grad_norm": 0.31913893930146975,
      "learning_rate": 2.94353047597992e-05,
      "loss": 0.5888,
      "step": 75
    },
    {
      "epoch": 0.13730803974706413,
      "grad_norm": 0.28949770075545406,
      "learning_rate": 2.941064971003224e-05,
      "loss": 0.5841,
      "step": 76
    },
    {
      "epoch": 0.13911472448057813,
      "grad_norm": 0.3247755531851961,
      "learning_rate": 2.9385478643984484e-05,
      "loss": 0.5795,
      "step": 77
    },
    {
      "epoch": 0.14092140921409213,
      "grad_norm": 0.3511957059688905,
      "learning_rate": 2.9359792462981007e-05,
      "loss": 0.5905,
      "step": 78
    },
    {
      "epoch": 0.14272809394760613,
      "grad_norm": 0.302521463157134,
      "learning_rate": 2.9333592086792113e-05,
      "loss": 0.5985,
      "step": 79
    },
    {
      "epoch": 0.14453477868112014,
      "grad_norm": 0.3549679822021618,
      "learning_rate": 2.9306878453600382e-05,
      "loss": 0.6074,
      "step": 80
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.3198459509652125,
      "learning_rate": 2.9279652519967105e-05,
      "loss": 0.5922,
      "step": 81
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.3576854570877617,
      "learning_rate": 2.9251915260798024e-05,
      "loss": 0.5846,
      "step": 82
    },
    {
      "epoch": 0.14995483288166214,
      "grad_norm": 0.3452717739532111,
      "learning_rate": 2.9223667669308395e-05,
      "loss": 0.5949,
      "step": 83
    },
    {
      "epoch": 0.15176151761517614,
      "grad_norm": 0.35130798066442276,
      "learning_rate": 2.9194910756987464e-05,
      "loss": 0.5882,
      "step": 84
    },
    {
      "epoch": 0.15356820234869015,
      "grad_norm": 0.2979218241802279,
      "learning_rate": 2.9165645553562215e-05,
      "loss": 0.5911,
      "step": 85
    },
    {
      "epoch": 0.15537488708220415,
      "grad_norm": 0.30352540649162485,
      "learning_rate": 2.9135873106960525e-05,
      "loss": 0.5902,
      "step": 86
    },
    {
      "epoch": 0.15718157181571815,
      "grad_norm": 0.3047300397649292,
      "learning_rate": 2.9105594483273603e-05,
      "loss": 0.5927,
      "step": 87
    },
    {
      "epoch": 0.15898825654923215,
      "grad_norm": 0.3034444492388091,
      "learning_rate": 2.9074810766717865e-05,
      "loss": 0.5969,
      "step": 88
    },
    {
      "epoch": 0.16079494128274616,
      "grad_norm": 0.31726687931722786,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.5938,
      "step": 89
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.2844238571820103,
      "learning_rate": 2.9011732482257835e-05,
      "loss": 0.5856,
      "step": 90
    },
    {
      "epoch": 0.16440831074977416,
      "grad_norm": 0.33861384709236475,
      "learning_rate": 2.89794401730596e-05,
      "loss": 0.5835,
      "step": 91
    },
    {
      "epoch": 0.16621499548328816,
      "grad_norm": 0.31986755243990583,
      "learning_rate": 2.894664728832377e-05,
      "loss": 0.5875,
      "step": 92
    },
    {
      "epoch": 0.16802168021680217,
      "grad_norm": 0.31772953202959486,
      "learning_rate": 2.8913355002297367e-05,
      "loss": 0.5937,
      "step": 93
    },
    {
      "epoch": 0.16982836495031617,
      "grad_norm": 0.3404713775893871,
      "learning_rate": 2.887956450710995e-05,
      "loss": 0.5933,
      "step": 94
    },
    {
      "epoch": 0.17163504968383017,
      "grad_norm": 0.3270438057428047,
      "learning_rate": 2.8845277012730963e-05,
      "loss": 0.5854,
      "step": 95
    },
    {
      "epoch": 0.17344173441734417,
      "grad_norm": 0.2813265419298624,
      "learning_rate": 2.8810493746926364e-05,
      "loss": 0.5849,
      "step": 96
    },
    {
      "epoch": 0.17524841915085818,
      "grad_norm": 0.30908563683812523,
      "learning_rate": 2.87752159552147e-05,
      "loss": 0.5906,
      "step": 97
    },
    {
      "epoch": 0.17705510388437218,
      "grad_norm": 0.28172567784588337,
      "learning_rate": 2.87394449008225e-05,
      "loss": 0.5836,
      "step": 98
    },
    {
      "epoch": 0.17886178861788618,
      "grad_norm": 0.32776100679221937,
      "learning_rate": 2.8703181864639013e-05,
      "loss": 0.5968,
      "step": 99
    },
    {
      "epoch": 0.18066847335140018,
      "grad_norm": 0.2829820594340673,
      "learning_rate": 2.8666428145170385e-05,
      "loss": 0.5698,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 553,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 115440686923776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}