{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.324324324324325,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.036036036036036036,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.2548,
      "step": 1
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.7083,
      "step": 2
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.9566,
      "step": 3
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.2875,
      "step": 4
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.0179,
      "step": 5
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.1465,
      "step": 6
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.0991,
      "step": 7
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.0996,
      "step": 8
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 3.127271890640259,
      "learning_rate": 2e-05,
      "loss": 2.0748,
      "step": 9
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.1929919719696045,
      "learning_rate": 4e-05,
      "loss": 1.7543,
      "step": 10
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 3.9285449981689453,
      "learning_rate": 6e-05,
      "loss": 2.1182,
      "step": 11
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 3.9492204189300537,
      "learning_rate": 8e-05,
      "loss": 2.1398,
      "step": 12
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 4.697811603546143,
      "learning_rate": 0.0001,
      "loss": 1.944,
      "step": 13
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 2.257394313812256,
      "learning_rate": 0.00012,
      "loss": 1.6118,
      "step": 14
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.470400333404541,
      "learning_rate": 0.00014,
      "loss": 1.6489,
      "step": 15
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.9114196300506592,
      "learning_rate": 0.00016,
      "loss": 1.3067,
      "step": 16
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 1.9045084714889526,
      "learning_rate": 0.00018,
      "loss": 1.4384,
      "step": 17
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.669812560081482,
      "learning_rate": 0.0002,
      "loss": 1.3614,
      "step": 18
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 0.982727587223053,
      "learning_rate": 0.00019818181818181821,
      "loss": 1.29,
      "step": 19
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.5169259309768677,
      "learning_rate": 0.00019636363636363636,
      "loss": 1.2386,
      "step": 20
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.3028675317764282,
      "learning_rate": 0.00019454545454545457,
      "loss": 1.1707,
      "step": 21
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.35564807057380676,
      "learning_rate": 0.00019272727272727274,
      "loss": 0.9072,
      "step": 22
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 0.30732882022857666,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.9289,
      "step": 23
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.31778138875961304,
      "learning_rate": 0.0001890909090909091,
      "loss": 0.9955,
      "step": 24
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.3151562809944153,
      "learning_rate": 0.00018727272727272728,
      "loss": 0.8705,
      "step": 25
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.3682255744934082,
      "learning_rate": 0.00018545454545454545,
      "loss": 1.197,
      "step": 26
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.25122687220573425,
      "learning_rate": 0.00018363636363636366,
      "loss": 1.0997,
      "step": 27
    },
    {
      "epoch": 1.009009009009009,
      "grad_norm": 0.23811328411102295,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0265,
      "step": 28
    },
    {
      "epoch": 1.045045045045045,
      "grad_norm": 0.23290874063968658,
      "learning_rate": 0.00018,
      "loss": 0.7358,
      "step": 29
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.21789032220840454,
      "learning_rate": 0.0001781818181818182,
      "loss": 0.7165,
      "step": 30
    },
    {
      "epoch": 1.117117117117117,
      "grad_norm": 0.3115369975566864,
      "learning_rate": 0.00017636363636363637,
      "loss": 0.7812,
      "step": 31
    },
    {
      "epoch": 1.1531531531531531,
      "grad_norm": 0.21534988284111023,
      "learning_rate": 0.00017454545454545454,
      "loss": 0.706,
      "step": 32
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 0.21201848983764648,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.6389,
      "step": 33
    },
    {
      "epoch": 1.2252252252252251,
      "grad_norm": 0.16613227128982544,
      "learning_rate": 0.0001709090909090909,
      "loss": 0.7041,
      "step": 34
    },
    {
      "epoch": 1.2612612612612613,
      "grad_norm": 0.26245370507240295,
      "learning_rate": 0.0001690909090909091,
      "loss": 0.6188,
      "step": 35
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.17487148940563202,
      "learning_rate": 0.00016727272727272728,
      "loss": 0.7382,
      "step": 36
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.22627073526382446,
      "learning_rate": 0.00016545454545454545,
      "loss": 0.9381,
      "step": 37
    },
    {
      "epoch": 1.3693693693693694,
      "grad_norm": 0.19883334636688232,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0042,
      "step": 38
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.18648912012577057,
      "learning_rate": 0.00016181818181818184,
      "loss": 0.7297,
      "step": 39
    },
    {
      "epoch": 1.4414414414414414,
      "grad_norm": 0.2486204355955124,
      "learning_rate": 0.00016,
      "loss": 1.0105,
      "step": 40
    },
    {
      "epoch": 1.4774774774774775,
      "grad_norm": 0.19586724042892456,
      "learning_rate": 0.0001581818181818182,
      "loss": 0.8904,
      "step": 41
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.1361636519432068,
      "learning_rate": 0.00015636363636363637,
      "loss": 0.7655,
      "step": 42
    },
    {
      "epoch": 1.5495495495495497,
      "grad_norm": 0.1422913819551468,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.884,
      "step": 43
    },
    {
      "epoch": 1.5855855855855856,
      "grad_norm": 0.12737137079238892,
      "learning_rate": 0.00015272727272727275,
      "loss": 0.4881,
      "step": 44
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.14031246304512024,
      "learning_rate": 0.0001509090909090909,
      "loss": 0.4856,
      "step": 45
    },
    {
      "epoch": 1.6576576576576576,
      "grad_norm": 0.152836412191391,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.5526,
      "step": 46
    },
    {
      "epoch": 1.6936936936936937,
      "grad_norm": 0.16750769317150116,
      "learning_rate": 0.00014727272727272728,
      "loss": 0.6862,
      "step": 47
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.15049736201763153,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6051,
      "step": 48
    },
    {
      "epoch": 1.7657657657657657,
      "grad_norm": 0.1748289316892624,
      "learning_rate": 0.00014363636363636363,
      "loss": 0.6521,
      "step": 49
    },
    {
      "epoch": 1.8018018018018018,
      "grad_norm": 0.12289358675479889,
      "learning_rate": 0.00014181818181818184,
      "loss": 0.5631,
      "step": 50
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.14275340735912323,
      "learning_rate": 0.00014,
      "loss": 0.3934,
      "step": 51
    },
    {
      "epoch": 1.8738738738738738,
      "grad_norm": 0.14242391288280487,
      "learning_rate": 0.0001381818181818182,
      "loss": 0.4372,
      "step": 52
    },
    {
      "epoch": 1.90990990990991,
      "grad_norm": 0.1477702260017395,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.7059,
      "step": 53
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.14974962174892426,
      "learning_rate": 0.00013454545454545455,
      "loss": 0.7635,
      "step": 54
    },
    {
      "epoch": 1.981981981981982,
      "grad_norm": 0.14689475297927856,
      "learning_rate": 0.00013272727272727275,
      "loss": 0.7075,
      "step": 55
    },
    {
      "epoch": 2.018018018018018,
      "grad_norm": 0.1843816339969635,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.6481,
      "step": 56
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 0.14116476476192474,
      "learning_rate": 0.0001290909090909091,
      "loss": 0.3951,
      "step": 57
    },
    {
      "epoch": 2.09009009009009,
      "grad_norm": 0.15613681077957153,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.4265,
      "step": 58
    },
    {
      "epoch": 2.126126126126126,
      "grad_norm": 0.1918690949678421,
      "learning_rate": 0.00012545454545454546,
      "loss": 0.9761,
      "step": 59
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.14524200558662415,
      "learning_rate": 0.00012363636363636364,
      "loss": 0.4906,
      "step": 60
    },
    {
      "epoch": 2.1981981981981984,
      "grad_norm": 0.16868562996387482,
      "learning_rate": 0.00012181818181818183,
      "loss": 0.5676,
      "step": 61
    },
    {
      "epoch": 2.234234234234234,
      "grad_norm": 0.14121738076210022,
      "learning_rate": 0.00012,
      "loss": 0.5162,
      "step": 62
    },
    {
      "epoch": 2.27027027027027,
      "grad_norm": 0.180411696434021,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.7837,
      "step": 63
    },
    {
      "epoch": 2.3063063063063063,
      "grad_norm": 0.23065026104450226,
      "learning_rate": 0.00011636363636363636,
      "loss": 0.4959,
      "step": 64
    },
    {
      "epoch": 2.3423423423423424,
      "grad_norm": 0.1973959058523178,
      "learning_rate": 0.00011454545454545456,
      "loss": 0.4391,
      "step": 65
    },
    {
      "epoch": 2.3783783783783785,
      "grad_norm": 0.17862387001514435,
      "learning_rate": 0.00011272727272727272,
      "loss": 0.4177,
      "step": 66
    },
    {
      "epoch": 2.4144144144144146,
      "grad_norm": 0.19349342584609985,
      "learning_rate": 0.00011090909090909092,
      "loss": 0.7445,
      "step": 67
    },
    {
      "epoch": 2.4504504504504503,
      "grad_norm": 0.1336154341697693,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.2191,
      "step": 68
    },
    {
      "epoch": 2.4864864864864864,
      "grad_norm": 0.21199998259544373,
      "learning_rate": 0.00010727272727272728,
      "loss": 0.4845,
      "step": 69
    },
    {
      "epoch": 2.5225225225225225,
      "grad_norm": 0.18532893061637878,
      "learning_rate": 0.00010545454545454545,
      "loss": 0.7252,
      "step": 70
    },
    {
      "epoch": 2.5585585585585586,
      "grad_norm": 0.14763948321342468,
      "learning_rate": 0.00010363636363636364,
      "loss": 0.4816,
      "step": 71
    },
    {
      "epoch": 2.5945945945945947,
      "grad_norm": 0.19213160872459412,
      "learning_rate": 0.00010181818181818181,
      "loss": 0.4775,
      "step": 72
    },
    {
      "epoch": 2.6306306306306304,
      "grad_norm": 0.19077633321285248,
      "learning_rate": 0.0001,
      "loss": 0.451,
      "step": 73
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.15648439526557922,
      "learning_rate": 9.818181818181818e-05,
      "loss": 0.2877,
      "step": 74
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 0.15609943866729736,
      "learning_rate": 9.636363636363637e-05,
      "loss": 0.2944,
      "step": 75
    },
    {
      "epoch": 2.7387387387387387,
      "grad_norm": 0.3236052989959717,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.62,
      "step": 76
    },
    {
      "epoch": 2.774774774774775,
      "grad_norm": 0.222801074385643,
      "learning_rate": 9.272727272727273e-05,
      "loss": 0.6515,
      "step": 77
    },
    {
      "epoch": 2.810810810810811,
      "grad_norm": 0.2324117124080658,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.5766,
      "step": 78
    },
    {
      "epoch": 2.846846846846847,
      "grad_norm": 0.20293325185775757,
      "learning_rate": 8.90909090909091e-05,
      "loss": 0.4531,
      "step": 79
    },
    {
      "epoch": 2.8828828828828827,
      "grad_norm": 0.20165590941905975,
      "learning_rate": 8.727272727272727e-05,
      "loss": 0.5847,
      "step": 80
    },
    {
      "epoch": 2.918918918918919,
      "grad_norm": 0.3000154197216034,
      "learning_rate": 8.545454545454545e-05,
      "loss": 0.4334,
      "step": 81
    },
    {
      "epoch": 2.954954954954955,
      "grad_norm": 0.20399592816829681,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.2509,
      "step": 82
    },
    {
      "epoch": 2.990990990990991,
      "grad_norm": 0.2015918642282486,
      "learning_rate": 8.181818181818183e-05,
      "loss": 0.3644,
      "step": 83
    },
    {
      "epoch": 3.027027027027027,
      "grad_norm": 0.16283659636974335,
      "learning_rate": 8e-05,
      "loss": 0.3619,
      "step": 84
    },
    {
      "epoch": 3.063063063063063,
      "grad_norm": 0.23384951055049896,
      "learning_rate": 7.818181818181818e-05,
      "loss": 0.4679,
      "step": 85
    },
    {
      "epoch": 3.099099099099099,
      "grad_norm": 0.3092138171195984,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.504,
      "step": 86
    },
    {
      "epoch": 3.135135135135135,
      "grad_norm": 0.2725450396537781,
      "learning_rate": 7.454545454545455e-05,
      "loss": 0.3763,
      "step": 87
    },
    {
      "epoch": 3.171171171171171,
      "grad_norm": 0.2366735339164734,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.3513,
      "step": 88
    },
    {
      "epoch": 3.2072072072072073,
      "grad_norm": 0.2573714554309845,
      "learning_rate": 7.090909090909092e-05,
      "loss": 0.3202,
      "step": 89
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 0.39939162135124207,
      "learning_rate": 6.90909090909091e-05,
      "loss": 0.4374,
      "step": 90
    },
    {
      "epoch": 3.279279279279279,
      "grad_norm": 0.3089916408061981,
      "learning_rate": 6.727272727272727e-05,
      "loss": 0.4418,
      "step": 91
    },
    {
      "epoch": 3.315315315315315,
      "grad_norm": 0.26053813099861145,
      "learning_rate": 6.545454545454546e-05,
      "loss": 0.3301,
      "step": 92
    },
    {
      "epoch": 3.3513513513513513,
      "grad_norm": 0.25036731362342834,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.3525,
      "step": 93
    },
    {
      "epoch": 3.3873873873873874,
      "grad_norm": 0.4556732475757599,
      "learning_rate": 6.181818181818182e-05,
      "loss": 0.3305,
      "step": 94
    },
    {
      "epoch": 3.4234234234234235,
      "grad_norm": 0.26551949977874756,
      "learning_rate": 6e-05,
      "loss": 0.2769,
      "step": 95
    },
    {
      "epoch": 3.4594594594594597,
      "grad_norm": 0.2707691192626953,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.2242,
      "step": 96
    },
    {
      "epoch": 3.4954954954954953,
      "grad_norm": 0.2323060780763626,
      "learning_rate": 5.636363636363636e-05,
      "loss": 0.4295,
      "step": 97
    },
    {
      "epoch": 3.5315315315315314,
      "grad_norm": 0.26477906107902527,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.3623,
      "step": 98
    },
    {
      "epoch": 3.5675675675675675,
      "grad_norm": 0.2650379538536072,
      "learning_rate": 5.272727272727272e-05,
      "loss": 0.2648,
      "step": 99
    },
    {
      "epoch": 3.6036036036036037,
      "grad_norm": 0.33467838168144226,
      "learning_rate": 5.090909090909091e-05,
      "loss": 0.3563,
      "step": 100
    },
    {
      "epoch": 3.6396396396396398,
      "grad_norm": 0.2872948944568634,
      "learning_rate": 4.909090909090909e-05,
      "loss": 0.4959,
      "step": 101
    },
    {
      "epoch": 3.6756756756756754,
      "grad_norm": 0.29369983077049255,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 0.2455,
      "step": 102
    },
    {
      "epoch": 3.7117117117117115,
      "grad_norm": 0.3010379374027252,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.4271,
      "step": 103
    },
    {
      "epoch": 3.7477477477477477,
      "grad_norm": 0.31059783697128296,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.4152,
      "step": 104
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 0.2542209327220917,
      "learning_rate": 4.181818181818182e-05,
      "loss": 0.382,
      "step": 105
    },
    {
      "epoch": 3.81981981981982,
      "grad_norm": 0.2900529205799103,
      "learning_rate": 4e-05,
      "loss": 0.2371,
      "step": 106
    },
    {
      "epoch": 3.855855855855856,
      "grad_norm": 0.25713253021240234,
      "learning_rate": 3.818181818181819e-05,
      "loss": 0.2636,
      "step": 107
    },
    {
      "epoch": 3.891891891891892,
      "grad_norm": 0.2913016378879547,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.4829,
      "step": 108
    },
    {
      "epoch": 3.9279279279279278,
      "grad_norm": 0.25630098581314087,
      "learning_rate": 3.454545454545455e-05,
      "loss": 0.2281,
      "step": 109
    },
    {
      "epoch": 3.963963963963964,
      "grad_norm": 0.29647207260131836,
      "learning_rate": 3.272727272727273e-05,
      "loss": 0.3197,
      "step": 110
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3527073860168457,
      "learning_rate": 3.090909090909091e-05,
      "loss": 0.3282,
      "step": 111
    },
    {
      "epoch": 4.036036036036036,
      "grad_norm": 0.482024610042572,
      "learning_rate": 2.909090909090909e-05,
      "loss": 0.255,
      "step": 112
    },
    {
      "epoch": 4.072072072072072,
      "grad_norm": 0.22163565456867218,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.1771,
      "step": 113
    },
    {
      "epoch": 4.108108108108108,
      "grad_norm": 0.25971901416778564,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.2633,
      "step": 114
    },
    {
      "epoch": 4.1441441441441444,
      "grad_norm": 0.30024221539497375,
      "learning_rate": 2.3636363636363637e-05,
      "loss": 0.2706,
      "step": 115
    },
    {
      "epoch": 4.18018018018018,
      "grad_norm": 0.26607680320739746,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.2513,
      "step": 116
    },
    {
      "epoch": 4.216216216216216,
      "grad_norm": 0.2651140093803406,
      "learning_rate": 2e-05,
      "loss": 0.2306,
      "step": 117
    },
    {
      "epoch": 4.252252252252252,
      "grad_norm": 0.29040372371673584,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.348,
      "step": 118
    },
    {
      "epoch": 4.288288288288288,
      "grad_norm": 0.3690294623374939,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.1826,
      "step": 119
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 0.22308969497680664,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 0.1656,
      "step": 120
    }
  ],
  "logging_steps": 1,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1955401487160934e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}