{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.298502382573179,
  "eval_steps": 25,
  "global_step": 385,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 0.7751,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.25e-06,
      "loss": 0.804,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.5e-06,
      "loss": 0.7948,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.496524064171123e-06,
      "loss": 0.7803,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.493048128342246e-06,
      "loss": 0.8638,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.4895721925133685e-06,
      "loss": 0.7873,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.486096256684491e-06,
      "loss": 0.7784,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.482620320855615e-06,
      "loss": 0.8244,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.479144385026738e-06,
      "loss": 0.7983,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.47566844919786e-06,
      "loss": 0.807,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.4721925133689835e-06,
      "loss": 0.8075,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.468716577540107e-06,
      "loss": 0.7881,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.46524064171123e-06,
      "loss": 0.7896,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.461764705882352e-06,
      "loss": 0.7941,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.458288770053475e-06,
      "loss": 0.7891,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.454812834224599e-06,
      "loss": 0.7909,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.451336898395722e-06,
      "loss": 0.7958,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.447860962566844e-06,
      "loss": 0.8015,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.4443850267379675e-06,
      "loss": 0.7899,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.440909090909091e-06,
      "loss": 0.7932,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.437433155080214e-06,
      "loss": 0.7848,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.433957219251336e-06,
      "loss": 0.7812,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.430481283422459e-06,
      "loss": 0.7773,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.4270053475935825e-06,
      "loss": 0.8001,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.423529411764706e-06,
      "loss": 0.7818,
      "step": 25
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.5808905363082886,
      "eval_runtime": 25.1343,
      "eval_samples_per_second": 293.543,
      "eval_steps_per_second": 24.469,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.420053475935828e-06,
      "loss": 0.7864,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.416577540106951e-06,
      "loss": 0.7893,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.413101604278074e-06,
      "loss": 0.7728,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.409625668449198e-06,
      "loss": 0.7654,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 6.40614973262032e-06,
      "loss": 0.7705,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 6.402673796791443e-06,
      "loss": 0.7758,
      "step": 31
    },
    {
      "epoch": 0.1,
      "learning_rate": 6.3991978609625665e-06,
      "loss": 0.7911,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.39572192513369e-06,
      "loss": 0.7816,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.392245989304813e-06,
      "loss": 0.786,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.388770053475935e-06,
      "loss": 0.7741,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.385294117647058e-06,
      "loss": 0.7676,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.3818181818181815e-06,
      "loss": 0.7671,
      "step": 37
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.378342245989305e-06,
      "loss": 0.7742,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.374866310160427e-06,
      "loss": 0.7653,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 6.37139037433155e-06,
      "loss": 0.7726,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 6.367914438502674e-06,
      "loss": 0.746,
      "step": 41
    },
    {
      "epoch": 0.13,
      "learning_rate": 6.364438502673797e-06,
      "loss": 0.7754,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 6.360962566844919e-06,
      "loss": 0.7712,
      "step": 43
    },
    {
      "epoch": 0.14,
      "learning_rate": 6.357486631016042e-06,
      "loss": 0.763,
      "step": 44
    },
    {
      "epoch": 0.14,
      "learning_rate": 6.3540106951871655e-06,
      "loss": 0.757,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 6.350534759358289e-06,
      "loss": 0.7773,
      "step": 46
    },
    {
      "epoch": 0.15,
      "learning_rate": 6.347058823529411e-06,
      "loss": 0.7678,
      "step": 47
    },
    {
      "epoch": 0.15,
      "learning_rate": 6.343582887700534e-06,
      "loss": 0.7607,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 6.340106951871657e-06,
      "loss": 0.7698,
      "step": 49
    },
    {
      "epoch": 0.16,
      "learning_rate": 6.3366310160427806e-06,
      "loss": 0.7689,
      "step": 50
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.5711967945098877,
      "eval_runtime": 25.1163,
      "eval_samples_per_second": 293.753,
      "eval_steps_per_second": 24.486,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 6.333155080213903e-06,
      "loss": 0.7586,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.329679144385026e-06,
      "loss": 0.7747,
      "step": 52
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.3262032085561494e-06,
      "loss": 0.781,
      "step": 53
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.322727272727273e-06,
      "loss": 0.7746,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.319251336898395e-06,
      "loss": 0.7636,
      "step": 55
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.315775401069518e-06,
      "loss": 0.7521,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.312299465240641e-06,
      "loss": 0.7662,
      "step": 57
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.3088235294117645e-06,
      "loss": 0.7807,
      "step": 58
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.305347593582887e-06,
      "loss": 0.7643,
      "step": 59
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.30187165775401e-06,
      "loss": 0.7671,
      "step": 60
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.298395721925133e-06,
      "loss": 0.7599,
      "step": 61
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.294919786096257e-06,
      "loss": 0.7467,
      "step": 62
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.2914438502673796e-06,
      "loss": 0.761,
      "step": 63
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.287967914438502e-06,
      "loss": 0.7679,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 6.284491978609625e-06,
      "loss": 0.7841,
      "step": 65
    },
    {
      "epoch": 0.21,
      "learning_rate": 6.2810160427807484e-06,
      "loss": 0.7792,
      "step": 66
    },
    {
      "epoch": 0.21,
      "learning_rate": 6.277540106951872e-06,
      "loss": 0.768,
      "step": 67
    },
    {
      "epoch": 0.22,
      "learning_rate": 6.274064171122994e-06,
      "loss": 0.7568,
      "step": 68
    },
    {
      "epoch": 0.22,
      "learning_rate": 6.270588235294117e-06,
      "loss": 0.7832,
      "step": 69
    },
    {
      "epoch": 0.22,
      "learning_rate": 6.26711229946524e-06,
      "loss": 0.7548,
      "step": 70
    },
    {
      "epoch": 0.23,
      "learning_rate": 6.2636363636363635e-06,
      "loss": 0.7444,
      "step": 71
    },
    {
      "epoch": 0.23,
      "learning_rate": 6.260160427807486e-06,
      "loss": 0.7656,
      "step": 72
    },
    {
      "epoch": 0.23,
      "learning_rate": 6.256684491978609e-06,
      "loss": 0.761,
      "step": 73
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.253208556149732e-06,
      "loss": 0.7576,
      "step": 74
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.249732620320856e-06,
      "loss": 0.7838,
      "step": 75
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.5673521757125854,
      "eval_runtime": 25.1312,
      "eval_samples_per_second": 293.58,
      "eval_steps_per_second": 24.472,
      "step": 75
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.246256684491978e-06,
      "loss": 0.7697,
      "step": 76
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.242780748663101e-06,
      "loss": 0.7691,
      "step": 77
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.239304812834224e-06,
      "loss": 0.7579,
      "step": 78
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.2358288770053474e-06,
      "loss": 0.7659,
      "step": 79
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.23235294117647e-06,
      "loss": 0.7552,
      "step": 80
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.228877005347593e-06,
      "loss": 0.7593,
      "step": 81
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.225401069518716e-06,
      "loss": 0.7558,
      "step": 82
    },
    {
      "epoch": 0.27,
      "learning_rate": 6.22192513368984e-06,
      "loss": 0.7784,
      "step": 83
    },
    {
      "epoch": 0.27,
      "learning_rate": 6.218449197860962e-06,
      "loss": 0.7616,
      "step": 84
    },
    {
      "epoch": 0.27,
      "learning_rate": 6.214973262032085e-06,
      "loss": 0.772,
      "step": 85
    },
    {
      "epoch": 0.28,
      "learning_rate": 6.211497326203208e-06,
      "loss": 0.7557,
      "step": 86
    },
    {
      "epoch": 0.28,
      "learning_rate": 6.208021390374331e-06,
      "loss": 0.7517,
      "step": 87
    },
    {
      "epoch": 0.28,
      "learning_rate": 6.204545454545454e-06,
      "loss": 0.7659,
      "step": 88
    },
    {
      "epoch": 0.28,
      "learning_rate": 6.201069518716577e-06,
      "loss": 0.742,
      "step": 89
    },
    {
      "epoch": 0.29,
      "learning_rate": 6.1975935828877e-06,
      "loss": 0.7676,
      "step": 90
    },
    {
      "epoch": 0.29,
      "learning_rate": 6.194117647058823e-06,
      "loss": 0.7506,
      "step": 91
    },
    {
      "epoch": 0.29,
      "learning_rate": 6.1906417112299464e-06,
      "loss": 0.7528,
      "step": 92
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.187165775401069e-06,
      "loss": 0.7771,
      "step": 93
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.183689839572192e-06,
      "loss": 0.7763,
      "step": 94
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.180213903743315e-06,
      "loss": 0.7616,
      "step": 95
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.176737967914439e-06,
      "loss": 0.7564,
      "step": 96
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.173262032085561e-06,
      "loss": 0.752,
      "step": 97
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.169786096256684e-06,
      "loss": 0.7651,
      "step": 98
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.166310160427807e-06,
      "loss": 0.7418,
      "step": 99
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.16283422459893e-06,
      "loss": 0.7633,
      "step": 100
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.5642256140708923,
      "eval_runtime": 25.1588,
      "eval_samples_per_second": 293.258,
      "eval_steps_per_second": 24.445,
      "step": 100
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.159358288770053e-06,
      "loss": 0.7693,
      "step": 101
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.155882352941176e-06,
      "loss": 0.7559,
      "step": 102
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.152406417112299e-06,
      "loss": 0.746,
      "step": 103
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.148930481283423e-06,
      "loss": 0.7616,
      "step": 104
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.145454545454545e-06,
      "loss": 0.7741,
      "step": 105
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.141978609625668e-06,
      "loss": 0.7539,
      "step": 106
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.138502673796791e-06,
      "loss": 0.7694,
      "step": 107
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.135026737967914e-06,
      "loss": 0.7661,
      "step": 108
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.131550802139037e-06,
      "loss": 0.7482,
      "step": 109
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.12807486631016e-06,
      "loss": 0.7553,
      "step": 110
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.124598930481283e-06,
      "loss": 0.7521,
      "step": 111
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.121122994652406e-06,
      "loss": 0.7453,
      "step": 112
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.1176470588235285e-06,
      "loss": 0.7494,
      "step": 113
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.114171122994652e-06,
      "loss": 0.7745,
      "step": 114
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.110695187165775e-06,
      "loss": 0.7595,
      "step": 115
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.107219251336898e-06,
      "loss": 0.7455,
      "step": 116
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.103743315508021e-06,
      "loss": 0.7686,
      "step": 117
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.100267379679144e-06,
      "loss": 0.7605,
      "step": 118
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.096791443850267e-06,
      "loss": 0.7482,
      "step": 119
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.09331550802139e-06,
      "loss": 0.7454,
      "step": 120
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.089839572192513e-06,
      "loss": 0.7559,
      "step": 121
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.086363636363636e-06,
      "loss": 0.7557,
      "step": 122
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.082887700534759e-06,
      "loss": 0.7429,
      "step": 123
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.079411764705882e-06,
      "loss": 0.7684,
      "step": 124
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.075935828877006e-06,
      "loss": 0.7319,
      "step": 125
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.562572717666626,
      "eval_runtime": 25.1626,
      "eval_samples_per_second": 293.213,
      "eval_steps_per_second": 24.441,
      "step": 125
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.0724598930481275e-06,
      "loss": 0.7494,
      "step": 126
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.068983957219251e-06,
      "loss": 0.7598,
      "step": 127
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.065508021390374e-06,
      "loss": 0.7452,
      "step": 128
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.062032085561497e-06,
      "loss": 0.753,
      "step": 129
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.05855614973262e-06,
      "loss": 0.7338,
      "step": 130
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.055080213903743e-06,
      "loss": 0.7526,
      "step": 131
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.051604278074866e-06,
      "loss": 0.759,
      "step": 132
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.04812834224599e-06,
      "loss": 0.7564,
      "step": 133
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.0446524064171115e-06,
      "loss": 0.7585,
      "step": 134
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.041176470588235e-06,
      "loss": 0.7552,
      "step": 135
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.037700534759358e-06,
      "loss": 0.7541,
      "step": 136
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.034224598930481e-06,
      "loss": 0.7603,
      "step": 137
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.030748663101604e-06,
      "loss": 0.7525,
      "step": 138
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.0272727272727265e-06,
      "loss": 0.7523,
      "step": 139
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.02379679144385e-06,
      "loss": 0.7543,
      "step": 140
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.020320855614973e-06,
      "loss": 0.7475,
      "step": 141
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.016844919786095e-06,
      "loss": 0.7599,
      "step": 142
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.013368983957219e-06,
      "loss": 0.7623,
      "step": 143
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.009893048128342e-06,
      "loss": 0.7472,
      "step": 144
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.006417112299465e-06,
      "loss": 0.747,
      "step": 145
    },
    {
      "epoch": 0.47,
      "learning_rate": 6.002941176470588e-06,
      "loss": 0.7488,
      "step": 146
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.9994652406417105e-06,
      "loss": 0.7422,
      "step": 147
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.995989304812834e-06,
      "loss": 0.7787,
      "step": 148
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.992513368983957e-06,
      "loss": 0.7496,
      "step": 149
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.98903743315508e-06,
      "loss": 0.749,
      "step": 150
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.5596185326576233,
      "eval_runtime": 25.1232,
      "eval_samples_per_second": 293.673,
      "eval_steps_per_second": 24.479,
      "step": 150
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.985561497326203e-06,
      "loss": 0.7469,
      "step": 151
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.9820855614973256e-06,
      "loss": 0.7604,
      "step": 152
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.978609625668449e-06,
      "loss": 0.7698,
      "step": 153
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.975133689839573e-06,
      "loss": 0.7613,
      "step": 154
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.9716577540106944e-06,
      "loss": 0.7523,
      "step": 155
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.968181818181818e-06,
      "loss": 0.7525,
      "step": 156
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.964705882352941e-06,
      "loss": 0.7413,
      "step": 157
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.961229946524064e-06,
      "loss": 0.7492,
      "step": 158
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.957754010695187e-06,
      "loss": 0.764,
      "step": 159
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.9542780748663095e-06,
      "loss": 0.7672,
      "step": 160
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.950802139037433e-06,
      "loss": 0.7549,
      "step": 161
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.947326203208556e-06,
      "loss": 0.7398,
      "step": 162
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.943850267379678e-06,
      "loss": 0.7503,
      "step": 163
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.940374331550802e-06,
      "loss": 0.7574,
      "step": 164
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.9368983957219246e-06,
      "loss": 0.7702,
      "step": 165
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.933422459893048e-06,
      "loss": 0.7589,
      "step": 166
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.929946524064171e-06,
      "loss": 0.7727,
      "step": 167
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.9264705882352934e-06,
      "loss": 0.7627,
      "step": 168
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.922994652406417e-06,
      "loss": 0.7565,
      "step": 169
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.91951871657754e-06,
      "loss": 0.7354,
      "step": 170
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.916042780748662e-06,
      "loss": 0.7562,
      "step": 171
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.912566844919786e-06,
      "loss": 0.7406,
      "step": 172
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.9090909090909085e-06,
      "loss": 0.734,
      "step": 173
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.905614973262032e-06,
      "loss": 0.7619,
      "step": 174
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.902139037433155e-06,
      "loss": 0.7427,
      "step": 175
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.5575200319290161,
      "eval_runtime": 25.1443,
      "eval_samples_per_second": 293.426,
      "eval_steps_per_second": 24.459,
      "step": 175
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.898663101604277e-06,
      "loss": 0.7427,
      "step": 176
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.895187165775401e-06,
      "loss": 0.7462,
      "step": 177
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.8917112299465236e-06,
      "loss": 0.763,
      "step": 178
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.888235294117647e-06,
      "loss": 0.7538,
      "step": 179
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.88475935828877e-06,
      "loss": 0.7547,
      "step": 180
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.8812834224598924e-06,
      "loss": 0.7514,
      "step": 181
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.877807486631016e-06,
      "loss": 0.7453,
      "step": 182
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.874331550802139e-06,
      "loss": 0.7679,
      "step": 183
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.870855614973261e-06,
      "loss": 0.7636,
      "step": 184
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.867379679144385e-06,
      "loss": 0.7323,
      "step": 185
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.8639037433155075e-06,
      "loss": 0.7644,
      "step": 186
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.860427807486631e-06,
      "loss": 0.7387,
      "step": 187
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.856951871657754e-06,
      "loss": 0.7621,
      "step": 188
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.853475935828876e-06,
      "loss": 0.7794,
      "step": 189
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.85e-06,
      "loss": 0.7658,
      "step": 190
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.8465240641711226e-06,
      "loss": 0.7565,
      "step": 191
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.843048128342245e-06,
      "loss": 0.7537,
      "step": 192
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.839572192513369e-06,
      "loss": 0.7477,
      "step": 193
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.8360962566844914e-06,
      "loss": 0.724,
      "step": 194
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.832620320855615e-06,
      "loss": 0.7467,
      "step": 195
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.829144385026738e-06,
      "loss": 0.7507,
      "step": 196
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.82566844919786e-06,
      "loss": 0.7564,
      "step": 197
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.822192513368984e-06,
      "loss": 0.7539,
      "step": 198
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.8187165775401065e-06,
      "loss": 0.7468,
      "step": 199
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.815240641711229e-06,
      "loss": 0.7353,
      "step": 200
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.5562187433242798,
      "eval_runtime": 25.1284,
      "eval_samples_per_second": 293.613,
      "eval_steps_per_second": 24.474,
      "step": 200
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.811764705882353e-06,
      "loss": 0.7472,
      "step": 201
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.808288770053475e-06,
      "loss": 0.7569,
      "step": 202
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.804812834224599e-06,
      "loss": 0.7443,
      "step": 203
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.8013368983957216e-06,
      "loss": 0.7552,
      "step": 204
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.797860962566844e-06,
      "loss": 0.7517,
      "step": 205
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.794385026737968e-06,
      "loss": 0.7581,
      "step": 206
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.7909090909090904e-06,
      "loss": 0.7616,
      "step": 207
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.787433155080214e-06,
      "loss": 0.7441,
      "step": 208
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.783957219251337e-06,
      "loss": 0.7385,
      "step": 209
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.780481283422459e-06,
      "loss": 0.7742,
      "step": 210
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.777005347593583e-06,
      "loss": 0.7654,
      "step": 211
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.7735294117647055e-06,
      "loss": 0.7504,
      "step": 212
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.770053475935828e-06,
      "loss": 0.7472,
      "step": 213
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.766577540106952e-06,
      "loss": 0.7472,
      "step": 214
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.763101604278074e-06,
      "loss": 0.7574,
      "step": 215
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.759625668449198e-06,
      "loss": 0.737,
      "step": 216
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.756149732620321e-06,
      "loss": 0.7496,
      "step": 217
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.752673796791443e-06,
      "loss": 0.7572,
      "step": 218
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.749197860962567e-06,
      "loss": 0.7557,
      "step": 219
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.7457219251336895e-06,
      "loss": 0.7668,
      "step": 220
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.742245989304812e-06,
      "loss": 0.7614,
      "step": 221
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.738770053475936e-06,
      "loss": 0.761,
      "step": 222
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.735294117647058e-06,
      "loss": 0.7411,
      "step": 223
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.731818181818182e-06,
      "loss": 0.7557,
      "step": 224
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.7283422459893045e-06,
      "loss": 0.7363,
      "step": 225
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.5533275604248047,
      "eval_runtime": 25.128,
      "eval_samples_per_second": 293.617,
      "eval_steps_per_second": 24.475,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.724866310160427e-06,
      "loss": 0.7624,
      "step": 226
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.721390374331551e-06,
      "loss": 0.7605,
      "step": 227
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.717914438502673e-06,
      "loss": 0.7588,
      "step": 228
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.714438502673796e-06,
      "loss": 0.7408,
      "step": 229
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.71096256684492e-06,
      "loss": 0.7361,
      "step": 230
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.707486631016042e-06,
      "loss": 0.7522,
      "step": 231
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.652334851936218e-06,
      "loss": 0.7383,
      "step": 232
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.648633257403189e-06,
      "loss": 0.7295,
      "step": 233
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.644931662870159e-06,
      "loss": 0.7384,
      "step": 234
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.64123006833713e-06,
      "loss": 0.726,
      "step": 235
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.6375284738041e-06,
      "loss": 0.703,
      "step": 236
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.63382687927107e-06,
      "loss": 0.7218,
      "step": 237
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.6301252847380405e-06,
      "loss": 0.7201,
      "step": 238
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.626423690205011e-06,
      "loss": 0.7319,
      "step": 239
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.6227220956719815e-06,
      "loss": 0.7261,
      "step": 240
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.619020501138952e-06,
      "loss": 0.7327,
      "step": 241
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.6153189066059225e-06,
      "loss": 0.6999,
      "step": 242
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.611617312072893e-06,
      "loss": 0.7185,
      "step": 243
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.6079157175398635e-06,
      "loss": 0.7169,
      "step": 244
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.604214123006833e-06,
      "loss": 0.7165,
      "step": 245
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.600512528473804e-06,
      "loss": 0.7273,
      "step": 246
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.596810933940774e-06,
      "loss": 0.7267,
      "step": 247
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.593109339407744e-06,
      "loss": 0.6915,
      "step": 248
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.589407744874714e-06,
      "loss": 0.72,
      "step": 249
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.585706150341686e-06,
      "loss": 0.7138,
      "step": 250
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.5525651574134827,
      "eval_runtime": 25.2344,
      "eval_samples_per_second": 292.379,
      "eval_steps_per_second": 24.372,
      "step": 250
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.582004555808656e-06,
      "loss": 0.7168,
      "step": 251
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.578302961275626e-06,
      "loss": 0.7107,
      "step": 252
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.574601366742596e-06,
      "loss": 0.7144,
      "step": 253
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.570899772209567e-06,
      "loss": 0.7108,
      "step": 254
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.567198177676537e-06,
      "loss": 0.7167,
      "step": 255
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.563496583143507e-06,
      "loss": 0.6916,
      "step": 256
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.5597949886104775e-06,
      "loss": 0.712,
      "step": 257
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.556093394077448e-06,
      "loss": 0.7331,
      "step": 258
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.552391799544419e-06,
      "loss": 0.7125,
      "step": 259
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.548690205011389e-06,
      "loss": 0.7151,
      "step": 260
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.5449886104783596e-06,
      "loss": 0.7076,
      "step": 261
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.54128701594533e-06,
      "loss": 0.717,
      "step": 262
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.5375854214123006e-06,
      "loss": 0.7131,
      "step": 263
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.53388382687927e-06,
      "loss": 0.7239,
      "step": 264
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.530182232346241e-06,
      "loss": 0.6994,
      "step": 265
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.526480637813211e-06,
      "loss": 0.7147,
      "step": 266
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.522779043280182e-06,
      "loss": 0.7188,
      "step": 267
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.519077448747152e-06,
      "loss": 0.7113,
      "step": 268
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.515375854214123e-06,
      "loss": 0.7133,
      "step": 269
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.511674259681093e-06,
      "loss": 0.7195,
      "step": 270
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.507972665148064e-06,
      "loss": 0.7118,
      "step": 271
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.5042710706150334e-06,
      "loss": 0.7046,
      "step": 272
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.500569476082004e-06,
      "loss": 0.7037,
      "step": 273
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.4968678815489744e-06,
      "loss": 0.7163,
      "step": 274
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.493166287015945e-06,
      "loss": 0.715,
      "step": 275
    },
    {
      "epoch": 0.94,
      "eval_loss": 0.5483076572418213,
      "eval_runtime": 25.2224,
      "eval_samples_per_second": 292.518,
      "eval_steps_per_second": 24.383,
      "step": 275
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.4894646924829155e-06,
      "loss": 0.7018,
      "step": 276
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.485763097949886e-06,
      "loss": 0.7144,
      "step": 277
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.4820615034168565e-06,
      "loss": 0.7039,
      "step": 278
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.478359908883827e-06,
      "loss": 0.7154,
      "step": 279
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.474658314350797e-06,
      "loss": 0.7067,
      "step": 280
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.470956719817767e-06,
      "loss": 0.7305,
      "step": 281
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.467255125284738e-06,
      "loss": 0.7188,
      "step": 282
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.463553530751708e-06,
      "loss": 0.7127,
      "step": 283
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.459851936218679e-06,
      "loss": 0.7095,
      "step": 284
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.456150341685649e-06,
      "loss": 0.7187,
      "step": 285
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.45244874715262e-06,
      "loss": 0.7034,
      "step": 286
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.44874715261959e-06,
      "loss": 0.7155,
      "step": 287
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.44504555808656e-06,
      "loss": 0.7065,
      "step": 288
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.44134396355353e-06,
      "loss": 0.7038,
      "step": 289
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.437642369020501e-06,
      "loss": 0.724,
      "step": 290
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.433940774487471e-06,
      "loss": 0.7175,
      "step": 291
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.430239179954441e-06,
      "loss": 0.7225,
      "step": 292
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.426537585421412e-06,
      "loss": 0.7096,
      "step": 293
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.422835990888383e-06,
      "loss": 0.7213,
      "step": 294
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.419134396355353e-06,
      "loss": 0.7114,
      "step": 295
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.415432801822323e-06,
      "loss": 0.7198,
      "step": 296
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.4117312072892935e-06,
      "loss": 0.6965,
      "step": 297
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.408029612756264e-06,
      "loss": 0.7015,
      "step": 298
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.404328018223234e-06,
      "loss": 0.7134,
      "step": 299
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.400626423690204e-06,
      "loss": 0.7115,
      "step": 300
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.5488342046737671,
      "eval_runtime": 25.2892,
      "eval_samples_per_second": 291.746,
      "eval_steps_per_second": 24.319,
      "step": 300
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.396924829157175e-06,
      "loss": 0.7134,
      "step": 301
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.393223234624146e-06,
      "loss": 0.722,
      "step": 302
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.389521640091116e-06,
      "loss": 0.7133,
      "step": 303
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.385820045558086e-06,
      "loss": 0.7024,
      "step": 304
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.382118451025057e-06,
      "loss": 0.6885,
      "step": 305
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.378416856492027e-06,
      "loss": 0.7067,
      "step": 306
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.374715261958997e-06,
      "loss": 0.7093,
      "step": 307
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.371013667425967e-06,
      "loss": 0.7083,
      "step": 308
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.367312072892938e-06,
      "loss": 0.7074,
      "step": 309
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.363610478359908e-06,
      "loss": 0.7179,
      "step": 310
    },
    {
      "epoch": 1.05,
      "learning_rate": 5.359908883826879e-06,
      "loss": 0.7128,
      "step": 311
    },
    {
      "epoch": 1.05,
      "learning_rate": 5.3562072892938494e-06,
      "loss": 0.707,
      "step": 312
    },
    {
      "epoch": 1.05,
      "learning_rate": 5.35250569476082e-06,
      "loss": 0.7025,
      "step": 313
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.3488041002277904e-06,
      "loss": 0.6958,
      "step": 314
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.34510250569476e-06,
      "loss": 0.7213,
      "step": 315
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.341400911161731e-06,
      "loss": 0.7045,
      "step": 316
    },
    {
      "epoch": 1.07,
      "learning_rate": 5.337699316628701e-06,
      "loss": 0.6997,
      "step": 317
    },
    {
      "epoch": 1.07,
      "learning_rate": 5.333997722095672e-06,
      "loss": 0.7104,
      "step": 318
    },
    {
      "epoch": 1.07,
      "learning_rate": 5.330296127562642e-06,
      "loss": 0.6975,
      "step": 319
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.326594533029613e-06,
      "loss": 0.7068,
      "step": 320
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.322892938496583e-06,
      "loss": 0.709,
      "step": 321
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.319191343963554e-06,
      "loss": 0.7134,
      "step": 322
    },
    {
      "epoch": 1.09,
      "learning_rate": 5.315489749430523e-06,
      "loss": 0.6999,
      "step": 323
    },
    {
      "epoch": 1.09,
      "learning_rate": 5.311788154897494e-06,
      "loss": 0.7066,
      "step": 324
    },
    {
      "epoch": 1.09,
      "learning_rate": 5.308086560364464e-06,
      "loss": 0.7126,
      "step": 325
    },
    {
      "epoch": 1.09,
      "eval_loss": 0.5455913543701172,
      "eval_runtime": 25.2451,
      "eval_samples_per_second": 292.254,
      "eval_steps_per_second": 24.361,
      "step": 325
    },
    {
      "epoch": 1.1,
      "learning_rate": 5.304384965831435e-06,
      "loss": 0.6963,
      "step": 326
    },
    {
      "epoch": 1.1,
      "learning_rate": 5.300683371298405e-06,
      "loss": 0.7004,
      "step": 327
    },
    {
      "epoch": 1.1,
      "learning_rate": 5.296981776765376e-06,
      "loss": 0.7044,
      "step": 328
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.293280182232346e-06,
      "loss": 0.7024,
      "step": 329
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.289578587699317e-06,
      "loss": 0.6862,
      "step": 330
    },
    {
      "epoch": 1.11,
      "learning_rate": 5.2858769931662865e-06,
      "loss": 0.7015,
      "step": 331
    },
    {
      "epoch": 1.12,
      "learning_rate": 5.282175398633257e-06,
      "loss": 0.7173,
      "step": 332
    },
    {
      "epoch": 1.12,
      "learning_rate": 5.2784738041002275e-06,
      "loss": 0.7094,
      "step": 333
    },
    {
      "epoch": 1.12,
      "learning_rate": 5.274772209567198e-06,
      "loss": 0.7073,
      "step": 334
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.271070615034168e-06,
      "loss": 0.7153,
      "step": 335
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.267369020501139e-06,
      "loss": 0.6949,
      "step": 336
    },
    {
      "epoch": 1.14,
      "learning_rate": 5.2636674259681095e-06,
      "loss": 0.7042,
      "step": 337
    },
    {
      "epoch": 1.14,
      "learning_rate": 5.25996583143508e-06,
      "loss": 0.6999,
      "step": 338
    },
    {
      "epoch": 1.14,
      "learning_rate": 5.25626423690205e-06,
      "loss": 0.7069,
      "step": 339
    },
    {
      "epoch": 1.15,
      "learning_rate": 5.25256264236902e-06,
      "loss": 0.7012,
      "step": 340
    },
    {
      "epoch": 1.15,
      "learning_rate": 5.248861047835991e-06,
      "loss": 0.7018,
      "step": 341
    },
    {
      "epoch": 1.15,
      "learning_rate": 5.245159453302961e-06,
      "loss": 0.7054,
      "step": 342
    },
    {
      "epoch": 1.16,
      "learning_rate": 5.241457858769931e-06,
      "loss": 0.7023,
      "step": 343
    },
    {
      "epoch": 1.16,
      "learning_rate": 5.237756264236901e-06,
      "loss": 0.6866,
      "step": 344
    },
    {
      "epoch": 1.16,
      "learning_rate": 5.234054669703872e-06,
      "loss": 0.6978,
      "step": 345
    },
    {
      "epoch": 1.17,
      "learning_rate": 5.230353075170842e-06,
      "loss": 0.7067,
      "step": 346
    },
    {
      "epoch": 1.17,
      "learning_rate": 5.226651480637813e-06,
      "loss": 0.7113,
      "step": 347
    },
    {
      "epoch": 1.17,
      "learning_rate": 5.222949886104783e-06,
      "loss": 0.6967,
      "step": 348
    },
    {
      "epoch": 1.18,
      "learning_rate": 5.219248291571754e-06,
      "loss": 0.7003,
      "step": 349
    },
    {
      "epoch": 1.18,
      "learning_rate": 5.2155466970387236e-06,
      "loss": 0.716,
      "step": 350
    },
    {
      "epoch": 1.18,
      "eval_loss": 0.543171226978302,
      "eval_runtime": 25.2405,
      "eval_samples_per_second": 292.308,
      "eval_steps_per_second": 24.366,
      "step": 350
    },
    {
      "epoch": 1.18,
      "learning_rate": 5.211845102505694e-06,
      "loss": 0.7174,
      "step": 351
    },
    {
      "epoch": 1.19,
      "learning_rate": 5.2081435079726646e-06,
      "loss": 0.7128,
      "step": 352
    },
    {
      "epoch": 1.19,
      "learning_rate": 5.204441913439635e-06,
      "loss": 0.6872,
      "step": 353
    },
    {
      "epoch": 1.19,
      "learning_rate": 5.200740318906606e-06,
      "loss": 0.7058,
      "step": 354
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.197038724373576e-06,
      "loss": 0.7025,
      "step": 355
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.193337129840547e-06,
      "loss": 0.7085,
      "step": 356
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.189635535307517e-06,
      "loss": 0.6916,
      "step": 357
    },
    {
      "epoch": 1.21,
      "learning_rate": 5.185933940774487e-06,
      "loss": 0.7094,
      "step": 358
    },
    {
      "epoch": 1.21,
      "learning_rate": 5.182232346241457e-06,
      "loss": 0.6919,
      "step": 359
    },
    {
      "epoch": 1.21,
      "learning_rate": 5.178530751708428e-06,
      "loss": 0.7143,
      "step": 360
    },
    {
      "epoch": 1.22,
      "learning_rate": 5.174829157175398e-06,
      "loss": 0.7176,
      "step": 361
    },
    {
      "epoch": 1.22,
      "learning_rate": 5.171127562642369e-06,
      "loss": 0.696,
      "step": 362
    },
    {
      "epoch": 1.22,
      "learning_rate": 5.167425968109339e-06,
      "loss": 0.7082,
      "step": 363
    },
    {
      "epoch": 1.23,
      "learning_rate": 5.16372437357631e-06,
      "loss": 0.6996,
      "step": 364
    },
    {
      "epoch": 1.23,
      "learning_rate": 5.16002277904328e-06,
      "loss": 0.7093,
      "step": 365
    },
    {
      "epoch": 1.23,
      "learning_rate": 5.15632118451025e-06,
      "loss": 0.7221,
      "step": 366
    },
    {
      "epoch": 1.24,
      "learning_rate": 5.1526195899772205e-06,
      "loss": 0.6953,
      "step": 367
    },
    {
      "epoch": 1.24,
      "learning_rate": 5.148917995444191e-06,
      "loss": 0.7054,
      "step": 368
    },
    {
      "epoch": 1.24,
      "learning_rate": 5.1452164009111615e-06,
      "loss": 0.6916,
      "step": 369
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.141514806378131e-06,
      "loss": 0.6972,
      "step": 370
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.1378132118451025e-06,
      "loss": 0.7075,
      "step": 371
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.134111617312073e-06,
      "loss": 0.7077,
      "step": 372
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.1304100227790435e-06,
      "loss": 0.7027,
      "step": 373
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.126708428246013e-06,
      "loss": 0.6857,
      "step": 374
    },
    {
      "epoch": 1.26,
      "learning_rate": 5.123006833712984e-06,
      "loss": 0.7108,
      "step": 375
    },
    {
      "epoch": 1.26,
      "eval_loss": 0.5420267581939697,
      "eval_runtime": 25.2293,
      "eval_samples_per_second": 292.438,
      "eval_steps_per_second": 24.376,
      "step": 375
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.119305239179954e-06,
      "loss": 0.6973,
      "step": 376
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.115603644646925e-06,
      "loss": 0.7079,
      "step": 377
    },
    {
      "epoch": 1.27,
      "learning_rate": 5.111902050113894e-06,
      "loss": 0.7195,
      "step": 378
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.108200455580865e-06,
      "loss": 0.6931,
      "step": 379
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.104498861047836e-06,
      "loss": 0.6912,
      "step": 380
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.100797266514807e-06,
      "loss": 0.7038,
      "step": 381
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.097095671981776e-06,
      "loss": 0.7023,
      "step": 382
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.093394077448747e-06,
      "loss": 0.6882,
      "step": 383
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.089692482915717e-06,
      "loss": 0.7167,
      "step": 384
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.085990888382688e-06,
      "loss": 0.6973,
      "step": 385
    }
  ],
  "logging_steps": 1,
  "max_steps": 1758,
  "num_train_epochs": 6,
  "save_steps": 77,
  "total_flos": 1.6147063380492943e+19,
  "trial_name": null,
  "trial_params": null
}