{
  "best_metric": 1.5345921516418457,
  "best_model_checkpoint": "saves/ChineseLLaMA2-7B-Chat/lora/2023-09-07-12-02-29/checkpoint-300",
  "epoch": 0.3251151449471688,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0009999919374161553,
      "loss": 2.0025,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009999677499246417,
      "loss": 1.7737,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0009999274383055143,
      "loss": 1.7391,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0009998710038588363,
      "loss": 1.7959,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009997984484046375,
      "loss": 1.713,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0009997097742828556,
      "loss": 1.6441,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009996049843532607,
      "loss": 1.704,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009994840819953633,
      "loss": 1.6532,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009993470711083048,
      "loss": 1.6791,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009991939561107325,
      "loss": 1.6465,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000999024741940656,
      "loss": 1.6511,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009988394340552898,
      "loss": 1.6727,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009986380384308746,
      "loss": 1.6653,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009984205615624873,
      "loss": 1.6339,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009981870104638294,
      "loss": 1.5562,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009979373926670028,
      "loss": 1.6291,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009976717162222645,
      "loss": 1.625,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009973899896977695,
      "loss": 1.6008,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000997092222179292,
      "loss": 1.6821,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009967784232699352,
      "loss": 1.582,
      "step": 100
    },
    {
      "epoch": 0.11,
      "eval_loss": 1.6186352968215942,
      "eval_runtime": 10.6735,
      "eval_samples_per_second": 14.054,
      "eval_steps_per_second": 1.78,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009964486030898186,
      "loss": 1.5769,
      "step": 105
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009961027722757538,
      "loss": 1.5868,
      "step": 110
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009957409419809006,
      "loss": 1.5601,
      "step": 115
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000995363123874407,
      "loss": 1.6061,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009949693301410341,
      "loss": 1.6073,
      "step": 125
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009945595734807615,
      "loss": 1.4998,
      "step": 130
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009941338671083794,
      "loss": 1.5295,
      "step": 135
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009936922247530606,
      "loss": 1.5418,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009932346606579192,
      "loss": 1.554,
      "step": 145
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009927611895795513,
      "loss": 1.5509,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009922718267875571,
      "loss": 1.6123,
      "step": 155
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009917665880640515,
      "loss": 1.6267,
      "step": 160
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009912454897031524,
      "loss": 1.6116,
      "step": 165
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009907085485104568,
      "loss": 1.5618,
      "step": 170
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0009901557818024981,
      "loss": 1.6085,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009895872074061885,
      "loss": 1.5829,
      "step": 180
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009890028436582426,
      "loss": 1.5407,
      "step": 185
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009884027094045871,
      "loss": 1.5568,
      "step": 190
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009877868239997532,
      "loss": 1.5831,
      "step": 195
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009871552073062516,
      "loss": 1.5231,
      "step": 200
    },
    {
      "epoch": 0.22,
      "eval_loss": 1.5717933177947998,
      "eval_runtime": 10.6708,
      "eval_samples_per_second": 14.057,
      "eval_steps_per_second": 1.781,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009865078796939327,
      "loss": 1.5467,
      "step": 205
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000985844862039329,
      "loss": 1.6403,
      "step": 210
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009851661757249823,
      "loss": 1.5352,
      "step": 215
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0009844718426387537,
      "loss": 1.5616,
      "step": 220
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000983761885173118,
      "loss": 1.5274,
      "step": 225
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000983036326224442,
      "loss": 1.6153,
      "step": 230
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0009822951891922448,
      "loss": 1.5062,
      "step": 235
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0009815384979784444,
      "loss": 1.6038,
      "step": 240
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000980766276986586,
      "loss": 1.5097,
      "step": 245
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009799785511210557,
      "loss": 1.535,
      "step": 250
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000979175345786277,
      "loss": 1.52,
      "step": 255
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0009783566868858912,
      "loss": 1.5678,
      "step": 260
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009775226008219224,
      "loss": 1.5536,
      "step": 265
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009766731144939258,
      "loss": 1.4826,
      "step": 270
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009758082552981204,
      "loss": 1.5537,
      "step": 275
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009749280511265056,
      "loss": 1.5277,
      "step": 280
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009740325303659609,
      "loss": 1.5445,
      "step": 285
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000973121721897331,
      "loss": 1.4944,
      "step": 290
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0009721956550944948,
      "loss": 1.5088,
      "step": 295
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0009712543598234172,
      "loss": 1.585,
      "step": 300
    },
    {
      "epoch": 0.33,
      "eval_loss": 1.5345921516418457,
      "eval_runtime": 10.6704,
      "eval_samples_per_second": 14.058,
      "eval_steps_per_second": 1.781,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 2766,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 9.88981248393216e+16,
  "trial_name": null,
  "trial_params": null
}