{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3429796355841372,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019931271477663232,
      "loss": 2.5587,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001986254295532646,
      "loss": 2.3914,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019793814432989693,
      "loss": 2.4218,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019725085910652924,
      "loss": 2.3414,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001965635738831615,
      "loss": 2.2469,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019587628865979381,
      "loss": 2.3241,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019518900343642613,
      "loss": 2.3266,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019450171821305842,
      "loss": 2.1856,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019381443298969073,
      "loss": 2.3247,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019312714776632305,
      "loss": 2.3245,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019243986254295533,
      "loss": 2.2591,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019175257731958765,
      "loss": 2.1767,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019106529209621996,
      "loss": 2.3478,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019037800687285222,
      "loss": 2.3339,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018969072164948454,
      "loss": 2.234,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018900343642611685,
      "loss": 2.2651,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018831615120274914,
      "loss": 2.1831,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018762886597938145,
      "loss": 2.216,
      "step": 18
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018694158075601377,
      "loss": 2.1359,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018625429553264605,
      "loss": 2.1215,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018556701030927837,
      "loss": 2.2179,
      "step": 21
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018487972508591068,
      "loss": 2.2598,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018419243986254294,
      "loss": 2.1813,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018350515463917526,
      "loss": 2.2006,
      "step": 24
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018281786941580757,
      "loss": 2.1564,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018213058419243986,
      "loss": 2.2537,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018144329896907217,
      "loss": 2.1975,
      "step": 27
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001807560137457045,
      "loss": 2.2566,
      "step": 28
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018006872852233677,
      "loss": 2.1464,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001793814432989691,
      "loss": 2.1421,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001786941580756014,
      "loss": 2.1276,
      "step": 31
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017800687285223366,
      "loss": 2.0649,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00017731958762886598,
      "loss": 2.1835,
      "step": 33
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001766323024054983,
      "loss": 2.1711,
      "step": 34
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017594501718213058,
      "loss": 2.2591,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001752577319587629,
      "loss": 2.1471,
      "step": 36
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001745704467353952,
      "loss": 2.0861,
      "step": 37
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001738831615120275,
      "loss": 2.0702,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001731958762886598,
      "loss": 2.1096,
      "step": 39
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017250859106529212,
      "loss": 2.1062,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017182130584192438,
      "loss": 2.2545,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001711340206185567,
      "loss": 2.1572,
      "step": 42
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000170446735395189,
      "loss": 2.0749,
      "step": 43
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001697594501718213,
      "loss": 2.1922,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00016907216494845361,
      "loss": 2.1915,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016838487972508593,
      "loss": 2.1594,
      "step": 46
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016769759450171822,
      "loss": 2.176,
      "step": 47
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00016701030927835053,
      "loss": 2.1223,
      "step": 48
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016632302405498285,
      "loss": 2.1263,
      "step": 49
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016563573883161513,
      "loss": 2.0481,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016494845360824742,
      "loss": 2.1043,
      "step": 51
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016426116838487973,
      "loss": 2.1678,
      "step": 52
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016357388316151202,
      "loss": 2.1602,
      "step": 53
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016288659793814434,
      "loss": 2.1448,
      "step": 54
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016219931271477665,
      "loss": 2.1536,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016151202749140894,
      "loss": 2.0339,
      "step": 56
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016082474226804125,
      "loss": 2.023,
      "step": 57
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016013745704467357,
      "loss": 2.1407,
      "step": 58
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00015945017182130585,
      "loss": 2.1134,
      "step": 59
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015876288659793814,
      "loss": 2.1652,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015807560137457046,
      "loss": 2.0051,
      "step": 61
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00015738831615120274,
      "loss": 2.0604,
      "step": 62
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015670103092783506,
      "loss": 2.1708,
      "step": 63
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015601374570446737,
      "loss": 2.1106,
      "step": 64
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015532646048109966,
      "loss": 2.1445,
      "step": 65
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015463917525773197,
      "loss": 2.0879,
      "step": 66
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001539518900343643,
      "loss": 2.1498,
      "step": 67
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015326460481099657,
      "loss": 2.0719,
      "step": 68
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015257731958762886,
      "loss": 2.2167,
      "step": 69
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015189003436426118,
      "loss": 2.0811,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015120274914089346,
      "loss": 2.1058,
      "step": 71
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015051546391752578,
      "loss": 2.0392,
      "step": 72
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001498281786941581,
      "loss": 2.0957,
      "step": 73
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00014914089347079038,
      "loss": 1.9994,
      "step": 74
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001484536082474227,
      "loss": 2.0464,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000147766323024055,
      "loss": 2.0417,
      "step": 76
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001470790378006873,
      "loss": 2.105,
      "step": 77
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014639175257731958,
      "loss": 2.1147,
      "step": 78
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001457044673539519,
      "loss": 1.9964,
      "step": 79
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014501718213058418,
      "loss": 1.9723,
      "step": 80
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001443298969072165,
      "loss": 2.0621,
      "step": 81
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014364261168384881,
      "loss": 2.2703,
      "step": 82
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001429553264604811,
      "loss": 2.0815,
      "step": 83
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014226804123711342,
      "loss": 2.0774,
      "step": 84
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014158075601374573,
      "loss": 2.066,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014089347079037802,
      "loss": 2.03,
      "step": 86
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001402061855670103,
      "loss": 2.1433,
      "step": 87
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00013951890034364262,
      "loss": 2.0811,
      "step": 88
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001388316151202749,
      "loss": 1.9791,
      "step": 89
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013814432989690722,
      "loss": 2.0876,
      "step": 90
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013745704467353953,
      "loss": 2.0314,
      "step": 91
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013676975945017182,
      "loss": 1.9485,
      "step": 92
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013608247422680414,
      "loss": 2.078,
      "step": 93
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013539518900343645,
      "loss": 2.1251,
      "step": 94
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013470790378006874,
      "loss": 1.9736,
      "step": 95
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013402061855670103,
      "loss": 2.0189,
      "step": 96
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.0061,
      "step": 97
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013264604810996563,
      "loss": 1.9595,
      "step": 98
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013195876288659794,
      "loss": 1.9702,
      "step": 99
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013127147766323026,
      "loss": 2.0322,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 291,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 6.083398113601536e+16,
  "trial_name": null,
  "trial_params": null
}