{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.942760942760943,
  "eval_steps": 400,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 0.01257950346916914,
      "learning_rate": 0.000990909090909091,
      "loss": 2.8653,
      "step": 2
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 0.02894681692123413,
      "learning_rate": 0.0009727272727272728,
      "loss": 2.8469,
      "step": 4
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.0666627511382103,
      "learning_rate": 0.0009545454545454546,
      "loss": 2.7697,
      "step": 6
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.1011333167552948,
      "learning_rate": 0.0009363636363636364,
      "loss": 2.8416,
      "step": 8
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 0.1431330442428589,
      "learning_rate": 0.0009181818181818182,
      "loss": 2.8207,
      "step": 10
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.17145054042339325,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.791,
      "step": 12
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 0.18456311523914337,
      "learning_rate": 0.0008818181818181819,
      "loss": 2.7702,
      "step": 14
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.17877964675426483,
      "learning_rate": 0.0008636363636363636,
      "loss": 2.7494,
      "step": 16
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.16067726910114288,
      "learning_rate": 0.0008454545454545455,
      "loss": 2.7386,
      "step": 18
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.18989939987659454,
      "learning_rate": 0.0008272727272727273,
      "loss": 2.7428,
      "step": 20
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1703718900680542,
      "learning_rate": 0.0008090909090909092,
      "loss": 2.7249,
      "step": 22
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.15262621641159058,
      "learning_rate": 0.0007909090909090909,
      "loss": 2.7456,
      "step": 24
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 0.15567754209041595,
      "learning_rate": 0.0007727272727272727,
      "loss": 2.7306,
      "step": 26
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 0.12221667915582657,
      "learning_rate": 0.0007545454545454546,
      "loss": 2.7012,
      "step": 28
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.11120902001857758,
      "learning_rate": 0.0007363636363636363,
      "loss": 2.7122,
      "step": 30
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 0.10489355772733688,
      "learning_rate": 0.0007181818181818181,
      "loss": 2.7142,
      "step": 32
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 0.10036630928516388,
      "learning_rate": 0.0007,
      "loss": 2.7211,
      "step": 34
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.0986902043223381,
      "learning_rate": 0.0006818181818181818,
      "loss": 2.6404,
      "step": 36
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2551414966583252,
      "learning_rate": 0.0006636363636363638,
      "loss": 2.6932,
      "step": 38
    },
    {
      "epoch": 1.0538720538720538,
      "grad_norm": 0.12025883048772812,
      "learning_rate": 0.0006454545454545455,
      "loss": 2.698,
      "step": 40
    },
    {
      "epoch": 1.1077441077441077,
      "grad_norm": 0.1064164862036705,
      "learning_rate": 0.0006272727272727273,
      "loss": 2.66,
      "step": 42
    },
    {
      "epoch": 1.1616161616161615,
      "grad_norm": 0.12751424312591553,
      "learning_rate": 0.0006090909090909092,
      "loss": 2.6307,
      "step": 44
    },
    {
      "epoch": 1.2154882154882154,
      "grad_norm": 0.12690748274326324,
      "learning_rate": 0.0005909090909090909,
      "loss": 2.6843,
      "step": 46
    },
    {
      "epoch": 1.2693602693602695,
      "grad_norm": 0.12534023821353912,
      "learning_rate": 0.0005727272727272727,
      "loss": 2.6592,
      "step": 48
    },
    {
      "epoch": 1.3232323232323233,
      "grad_norm": 0.10958981513977051,
      "learning_rate": 0.0005545454545454546,
      "loss": 2.6535,
      "step": 50
    },
    {
      "epoch": 1.3771043771043772,
      "grad_norm": 0.12295985221862793,
      "learning_rate": 0.0005363636363636364,
      "loss": 2.6185,
      "step": 52
    },
    {
      "epoch": 1.430976430976431,
      "grad_norm": 0.12431646883487701,
      "learning_rate": 0.0005181818181818182,
      "loss": 2.6336,
      "step": 54
    },
    {
      "epoch": 1.4848484848484849,
      "grad_norm": 0.10543714463710785,
      "learning_rate": 0.0005,
      "loss": 2.6503,
      "step": 56
    },
    {
      "epoch": 1.5387205387205387,
      "grad_norm": 0.11133274435997009,
      "learning_rate": 0.00048181818181818184,
      "loss": 2.6365,
      "step": 58
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 0.11586187779903412,
      "learning_rate": 0.00046363636363636366,
      "loss": 2.6366,
      "step": 60
    },
    {
      "epoch": 1.6464646464646466,
      "grad_norm": 0.11602918803691864,
      "learning_rate": 0.00044545454545454543,
      "loss": 2.663,
      "step": 62
    },
    {
      "epoch": 1.7003367003367003,
      "grad_norm": 0.11441349983215332,
      "learning_rate": 0.00042727272727272726,
      "loss": 2.6727,
      "step": 64
    },
    {
      "epoch": 1.7542087542087543,
      "grad_norm": 0.11416248232126236,
      "learning_rate": 0.00040909090909090913,
      "loss": 2.6752,
      "step": 66
    },
    {
      "epoch": 1.808080808080808,
      "grad_norm": 0.11019805073738098,
      "learning_rate": 0.00039090909090909096,
      "loss": 2.6541,
      "step": 68
    },
    {
      "epoch": 1.861952861952862,
      "grad_norm": 0.10957842320203781,
      "learning_rate": 0.00037272727272727273,
      "loss": 2.6745,
      "step": 70
    },
    {
      "epoch": 1.9158249158249159,
      "grad_norm": 0.10212814062833786,
      "learning_rate": 0.00035454545454545455,
      "loss": 2.6264,
      "step": 72
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.10807520151138306,
      "learning_rate": 0.0003363636363636364,
      "loss": 2.6491,
      "step": 74
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.285987913608551,
      "learning_rate": 0.0003181818181818182,
      "loss": 2.6873,
      "step": 76
    },
    {
      "epoch": 2.053872053872054,
      "grad_norm": 0.11446108669042587,
      "learning_rate": 0.0003,
      "loss": 2.639,
      "step": 78
    },
    {
      "epoch": 2.1077441077441077,
      "grad_norm": 0.1077447310090065,
      "learning_rate": 0.0002818181818181818,
      "loss": 2.6196,
      "step": 80
    },
    {
      "epoch": 2.1616161616161618,
      "grad_norm": 0.1157441958785057,
      "learning_rate": 0.0002636363636363636,
      "loss": 2.5955,
      "step": 82
    },
    {
      "epoch": 2.2154882154882154,
      "grad_norm": 0.12017026543617249,
      "learning_rate": 0.00024545454545454545,
      "loss": 2.6339,
      "step": 84
    },
    {
      "epoch": 2.2693602693602695,
      "grad_norm": 0.11678113788366318,
      "learning_rate": 0.00022727272727272727,
      "loss": 2.6475,
      "step": 86
    },
    {
      "epoch": 2.323232323232323,
      "grad_norm": 0.12528547644615173,
      "learning_rate": 0.00020909090909090907,
      "loss": 2.6177,
      "step": 88
    },
    {
      "epoch": 2.377104377104377,
      "grad_norm": 0.1168636754155159,
      "learning_rate": 0.00019090909090909092,
      "loss": 2.6442,
      "step": 90
    },
    {
      "epoch": 2.430976430976431,
      "grad_norm": 0.11126925051212311,
      "learning_rate": 0.00017272727272727272,
      "loss": 2.645,
      "step": 92
    },
    {
      "epoch": 2.484848484848485,
      "grad_norm": 0.1180771067738533,
      "learning_rate": 0.00015454545454545454,
      "loss": 2.5993,
      "step": 94
    },
    {
      "epoch": 2.538720538720539,
      "grad_norm": 0.10938919335603714,
      "learning_rate": 0.00013636363636363637,
      "loss": 2.6169,
      "step": 96
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.11159233003854752,
      "learning_rate": 0.00011818181818181818,
      "loss": 2.6337,
      "step": 98
    },
    {
      "epoch": 2.6464646464646466,
      "grad_norm": 0.11683017015457153,
      "learning_rate": 0.0001,
      "loss": 2.6153,
      "step": 100
    },
    {
      "epoch": 2.7003367003367003,
      "grad_norm": 0.12459760904312134,
      "learning_rate": 8.181818181818182e-05,
      "loss": 2.6644,
      "step": 102
    },
    {
      "epoch": 2.7542087542087543,
      "grad_norm": 0.1154564693570137,
      "learning_rate": 6.363636363636363e-05,
      "loss": 2.5877,
      "step": 104
    },
    {
      "epoch": 2.808080808080808,
      "grad_norm": 0.11724215745925903,
      "learning_rate": 4.545454545454546e-05,
      "loss": 2.6417,
      "step": 106
    },
    {
      "epoch": 2.861952861952862,
      "grad_norm": 0.12444790452718735,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 2.6061,
      "step": 108
    },
    {
      "epoch": 2.915824915824916,
      "grad_norm": 0.12090171128511429,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.5846,
      "step": 110
    },
    {
      "epoch": 2.942760942760943,
      "step": 111,
      "total_flos": 3.0985659629568e+17,
      "train_loss": 2.6788850926064156,
      "train_runtime": 977.7958,
      "train_samples_per_second": 29.175,
      "train_steps_per_second": 0.114
    },
    {
      "epoch": 2.942760942760943,
      "eval_loss": 2.6915676593780518,
      "eval_runtime": 45.4669,
      "eval_samples_per_second": 26.151,
      "eval_steps_per_second": 3.277,
      "step": 111
    },
    {
      "epoch": 2.942760942760943,
      "eval_loss": 2.6915125846862793,
      "eval_runtime": 44.7446,
      "eval_samples_per_second": 26.573,
      "eval_steps_per_second": 3.33,
      "step": 111
    }
  ],
  "logging_steps": 2,
  "max_steps": 111,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.0985659629568e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}