{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9987569919204475,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.444444444444444e-06,
      "loss": 2.687,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.888888888888888e-06,
      "loss": 2.7029,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.6189,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 2.5673,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9999417253661235e-05,
      "loss": 2.6342,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9994755690455154e-05,
      "loss": 2.7195,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.998543473718677e-05,
      "loss": 2.6762,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9971458739130598e-05,
      "loss": 2.8015,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.995283421166614e-05,
      "loss": 2.4821,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9929569837240567e-05,
      "loss": 2.3197,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.990167646132107e-05,
      "loss": 2.4756,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9869167087338908e-05,
      "loss": 2.5277,
      "step": 24
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.983205687062742e-05,
      "loss": 2.7706,
      "step": 26
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9790363111356838e-05,
      "loss": 2.6553,
      "step": 28
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9744105246469264e-05,
      "loss": 2.6354,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9693304840617456e-05,
      "loss": 2.4762,
      "step": 32
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.963798557611178e-05,
      "loss": 2.6096,
      "step": 34
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.957817324187987e-05,
      "loss": 2.4001,
      "step": 36
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9513895721444286e-05,
      "loss": 2.4426,
      "step": 38
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.9445182979923657e-05,
      "loss": 2.5961,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.937206705006344e-05,
      "loss": 2.5445,
      "step": 42
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9294582017302797e-05,
      "loss": 2.4417,
      "step": 44
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.921276400388451e-05,
      "loss": 2.4769,
      "step": 46
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.9126651152015404e-05,
      "loss": 2.532,
      "step": 48
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9036283606085057e-05,
      "loss": 2.698,
      "step": 50
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.8941703493951163e-05,
      "loss": 2.5106,
      "step": 52
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.8842954907300236e-05,
      "loss": 2.4174,
      "step": 54
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.874008388109276e-05,
      "loss": 2.4691,
      "step": 56
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.863313837210247e-05,
      "loss": 2.3981,
      "step": 58
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.8522168236559693e-05,
      "loss": 2.5144,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.840722520690921e-05,
      "loss": 2.3611,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.8288362867693414e-05,
      "loss": 2.4442,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.816563663057211e-05,
      "loss": 2.4351,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.8039103708490503e-05,
      "loss": 2.3272,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.790882308900746e-05,
      "loss": 2.3544,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.7774855506796497e-05,
      "loss": 2.3661,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7637263415332272e-05,
      "loss": 2.4607,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.749611095777581e-05,
      "loss": 2.4305,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.7351463937072008e-05,
      "loss": 2.5995,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.7203389785273402e-05,
      "loss": 2.3701,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.705195753210446e-05,
      "loss": 2.3289,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.6897237772781046e-05,
      "loss": 2.4084,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.673930263510011e-05,
      "loss": 2.3949,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.6578225745814907e-05,
      "loss": 2.4651,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.6414082196311402e-05,
      "loss": 2.4417,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6246948507601915e-05,
      "loss": 2.3136,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.607690259465229e-05,
      "loss": 2.2265,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5904023730059227e-05,
      "loss": 2.4076,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.57283925070947e-05,
      "loss": 2.3468,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.55500908021347e-05,
      "loss": 2.2458,
      "step": 100
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.536920173648984e-05,
      "loss": 2.2984,
      "step": 102
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.5185809637655548e-05,
      "loss": 2.3769,
      "step": 104
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.284,
      "step": 106
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.4811859444908053e-05,
      "loss": 2.4381,
      "step": 108
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.4621475680399771e-05,
      "loss": 2.409,
      "step": 110
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.4428937460242417e-05,
      "loss": 2.3612,
      "step": 112
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.4234334542574906e-05,
      "loss": 2.3199,
      "step": 114
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.4037757648064019e-05,
      "loss": 2.2612,
      "step": 116
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.3839298417611964e-05,
      "loss": 2.2587,
      "step": 118
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3639049369634878e-05,
      "loss": 2.2673,
      "step": 120
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.3437103856932266e-05,
      "loss": 2.2712,
      "step": 122
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.3233556023167487e-05,
      "loss": 2.2305,
      "step": 124
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.3028500758979507e-05,
      "loss": 2.4667,
      "step": 126
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.2822033657746478e-05,
      "loss": 2.4123,
      "step": 128
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.2614250971021658e-05,
      "loss": 2.2408,
      "step": 130
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.2405249563662539e-05,
      "loss": 2.3962,
      "step": 132
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.2195126868674052e-05,
      "loss": 2.3659,
      "step": 134
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.1983980841786899e-05,
      "loss": 2.4564,
      "step": 136
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.177190991579223e-05,
      "loss": 2.2792,
      "step": 138
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.1559012954653865e-05,
      "loss": 2.2928,
      "step": 140
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.1345389207419588e-05,
      "loss": 2.4787,
      "step": 142
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.1131138261952845e-05,
      "loss": 2.1273,
      "step": 144
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.0916359998506549e-05,
      "loss": 2.1601,
      "step": 146
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.070115454316054e-05,
      "loss": 2.2203,
      "step": 148
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.0485622221144485e-05,
      "loss": 2.3428,
      "step": 150
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.0269863510067872e-05,
      "loss": 2.2332,
      "step": 152
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.0053978993079046e-05,
      "loss": 2.4753,
      "step": 154
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.838069311974986e-06,
      "loss": 2.3579,
      "step": 156
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.622235120283769e-06,
      "loss": 2.2148,
      "step": 158
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.406577036341548e-06,
      "loss": 2.3775,
      "step": 160
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.19119559638596e-06,
      "loss": 2.321,
      "step": 162
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.976191207687775e-06,
      "loss": 2.2917,
      "step": 164
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.7616641017427e-06,
      "loss": 2.191,
      "step": 166
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.5477142875451e-06,
      "loss": 2.3916,
      "step": 168
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.334441504965456e-06,
      "loss": 2.0293,
      "step": 170
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.1219451782533e-06,
      "loss": 2.2324,
      "step": 172
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.91032436968725e-06,
      "loss": 2.3022,
      "step": 174
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.699677733393827e-06,
      "loss": 2.4032,
      "step": 176
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.490103469356513e-06,
      "loss": 2.3939,
      "step": 178
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.2816992776365714e-06,
      "loss": 2.318,
      "step": 180
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.0745623128268605e-06,
      "loss": 2.4244,
      "step": 182
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.868789138759977e-06,
      "loss": 2.4398,
      "step": 184
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.664475683491797e-06,
      "loss": 2.2545,
      "step": 186
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.461717194581394e-06,
      "loss": 2.3647,
      "step": 188
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.260608194688207e-06,
      "loss": 2.3776,
      "step": 190
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.061242437507131e-06,
      "loss": 2.2619,
      "step": 192
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.863712864062089e-06,
      "loss": 2.1638,
      "step": 194
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.6681115593784705e-06,
      "loss": 2.2278,
      "step": 196
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.4745297095546125e-06,
      "loss": 2.2256,
      "step": 198
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.2830575592523415e-06,
      "loss": 2.1212,
      "step": 200
    }
  ],
  "logging_steps": 2,
  "max_steps": 300,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.734000020127744e+16,
  "trial_name": null,
  "trial_params": null
}