{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07732755954222084,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.1645,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9507,
      "step": 50
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.502,
      "step": 75
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.7333,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.2266,
      "step": 125
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.604,
      "step": 150
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2927,
      "step": 175
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4849,
      "step": 200
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2372,
      "step": 225
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4155,
      "step": 250
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1745,
      "step": 275
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3327,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1347,
      "step": 325
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2828,
      "step": 350
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3051,
      "step": 375
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4646,
      "step": 400
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.2109,
      "step": 425
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3195,
      "step": 450
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3475,
      "step": 475
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4109,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0661,
      "step": 525
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.2554,
      "step": 550
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.1572,
      "step": 575
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3693,
      "step": 600
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.9443,
      "step": 625
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3281,
      "step": 650
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.189,
      "step": 675
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3747,
      "step": 700
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.0517,
      "step": 725
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3771,
      "step": 750
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9529,
      "step": 775
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3633,
      "step": 800
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.1759,
      "step": 825
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2803,
      "step": 850
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.1455,
      "step": 875
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2917,
      "step": 900
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.9807,
      "step": 925
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.2193,
      "step": 950
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0852,
      "step": 975
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.2919,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.1368,
      "step": 1025
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.2861,
      "step": 1050
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.162,
      "step": 1075
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.3554,
      "step": 1100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0723,
      "step": 1125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.1713,
      "step": 1150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.258,
      "step": 1175
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3437,
      "step": 1200
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1127,
      "step": 1225
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.295,
      "step": 1250
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.0447,
      "step": 1275
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1771,
      "step": 1300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1057,
      "step": 1325
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2026,
      "step": 1350
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1061,
      "step": 1375
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3012,
      "step": 1400
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1393,
      "step": 1425
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3238,
      "step": 1450
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1414,
      "step": 1475
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3037,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1731,
      "step": 1525
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1238,
      "step": 1550
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9542,
      "step": 1575
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1471,
      "step": 1600
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9938,
      "step": 1625
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.2156,
      "step": 1650
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.03,
      "step": 1675
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2215,
      "step": 1700
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.0335,
      "step": 1725
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.3059,
      "step": 1750
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9583,
      "step": 1775
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.1925,
      "step": 1800
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.0331,
      "step": 1825
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2639,
      "step": 1850
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9898,
      "step": 1875
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2714,
      "step": 1900
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.049,
      "step": 1925
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.2586,
      "step": 1950
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.0331,
      "step": 1975
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.2745,
      "step": 2000
    }
  ],
  "logging_steps": 25,
  "max_steps": 25864,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "total_flos": 1.6927075537256448e+16,
  "trial_name": null,
  "trial_params": null
}