{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 199.0662251655629,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.07,
      "learning_rate": 9.933774834437087e-07,
      "loss": 2.1111,
      "step": 30
    },
    {
      "epoch": 5.07,
      "learning_rate": 1.9867549668874175e-06,
      "loss": 2.0911,
      "step": 60
    },
    {
      "epoch": 8.07,
      "learning_rate": 2.9801324503311258e-06,
      "loss": 2.0488,
      "step": 90
    },
    {
      "epoch": 11.07,
      "learning_rate": 3.973509933774835e-06,
      "loss": 1.9825,
      "step": 120
    },
    {
      "epoch": 14.07,
      "learning_rate": 4.966887417218543e-06,
      "loss": 1.8997,
      "step": 150
    },
    {
      "epoch": 17.07,
      "learning_rate": 5.9602649006622515e-06,
      "loss": 1.811,
      "step": 180
    },
    {
      "epoch": 20.07,
      "learning_rate": 6.95364238410596e-06,
      "loss": 1.7265,
      "step": 210
    },
    {
      "epoch": 23.07,
      "learning_rate": 7.94701986754967e-06,
      "loss": 1.6527,
      "step": 240
    },
    {
      "epoch": 26.07,
      "learning_rate": 8.940397350993377e-06,
      "loss": 1.5955,
      "step": 270
    },
    {
      "epoch": 29.07,
      "learning_rate": 9.933774834437086e-06,
      "loss": 1.5492,
      "step": 300
    },
    {
      "epoch": 32.07,
      "learning_rate": 1.0927152317880796e-05,
      "loss": 1.508,
      "step": 330
    },
    {
      "epoch": 35.07,
      "learning_rate": 1.1920529801324503e-05,
      "loss": 1.4678,
      "step": 360
    },
    {
      "epoch": 38.07,
      "learning_rate": 1.2913907284768212e-05,
      "loss": 1.4278,
      "step": 390
    },
    {
      "epoch": 41.07,
      "learning_rate": 1.390728476821192e-05,
      "loss": 1.3864,
      "step": 420
    },
    {
      "epoch": 44.07,
      "learning_rate": 1.490066225165563e-05,
      "loss": 1.3418,
      "step": 450
    },
    {
      "epoch": 47.07,
      "learning_rate": 1.589403973509934e-05,
      "loss": 1.2955,
      "step": 480
    },
    {
      "epoch": 50.07,
      "learning_rate": 1.688741721854305e-05,
      "loss": 1.2506,
      "step": 510
    },
    {
      "epoch": 53.07,
      "learning_rate": 1.7880794701986755e-05,
      "loss": 1.2051,
      "step": 540
    },
    {
      "epoch": 56.07,
      "learning_rate": 1.8874172185430464e-05,
      "loss": 1.1617,
      "step": 570
    },
    {
      "epoch": 59.07,
      "learning_rate": 1.9867549668874173e-05,
      "loss": 1.1198,
      "step": 600
    },
    {
      "epoch": 62.07,
      "learning_rate": 2.0860927152317882e-05,
      "loss": 1.0815,
      "step": 630
    },
    {
      "epoch": 65.07,
      "learning_rate": 2.185430463576159e-05,
      "loss": 1.0462,
      "step": 660
    },
    {
      "epoch": 68.07,
      "learning_rate": 2.28476821192053e-05,
      "loss": 1.0112,
      "step": 690
    },
    {
      "epoch": 71.07,
      "learning_rate": 2.3841059602649006e-05,
      "loss": 0.9762,
      "step": 720
    },
    {
      "epoch": 74.07,
      "learning_rate": 2.4834437086092715e-05,
      "loss": 0.941,
      "step": 750
    },
    {
      "epoch": 77.07,
      "learning_rate": 2.5827814569536424e-05,
      "loss": 0.9048,
      "step": 780
    },
    {
      "epoch": 80.07,
      "learning_rate": 2.6821192052980134e-05,
      "loss": 0.8728,
      "step": 810
    },
    {
      "epoch": 83.07,
      "learning_rate": 2.781456953642384e-05,
      "loss": 0.839,
      "step": 840
    },
    {
      "epoch": 86.07,
      "learning_rate": 2.880794701986755e-05,
      "loss": 0.8041,
      "step": 870
    },
    {
      "epoch": 89.07,
      "learning_rate": 2.980132450331126e-05,
      "loss": 0.7714,
      "step": 900
    },
    {
      "epoch": 92.07,
      "learning_rate": 3.079470198675497e-05,
      "loss": 0.7396,
      "step": 930
    },
    {
      "epoch": 95.07,
      "learning_rate": 3.178807947019868e-05,
      "loss": 0.7062,
      "step": 960
    },
    {
      "epoch": 98.07,
      "learning_rate": 3.278145695364239e-05,
      "loss": 0.6731,
      "step": 990
    },
    {
      "epoch": 101.07,
      "learning_rate": 3.37748344370861e-05,
      "loss": 0.6376,
      "step": 1020
    },
    {
      "epoch": 104.07,
      "learning_rate": 3.47682119205298e-05,
      "loss": 0.6083,
      "step": 1050
    },
    {
      "epoch": 107.07,
      "learning_rate": 3.576158940397351e-05,
      "loss": 0.5789,
      "step": 1080
    },
    {
      "epoch": 110.07,
      "learning_rate": 3.675496688741722e-05,
      "loss": 0.5487,
      "step": 1110
    },
    {
      "epoch": 113.07,
      "learning_rate": 3.774834437086093e-05,
      "loss": 0.5202,
      "step": 1140
    },
    {
      "epoch": 116.07,
      "learning_rate": 3.8741721854304637e-05,
      "loss": 0.4941,
      "step": 1170
    },
    {
      "epoch": 119.07,
      "learning_rate": 3.9735099337748346e-05,
      "loss": 0.4675,
      "step": 1200
    },
    {
      "epoch": 122.07,
      "learning_rate": 4.0728476821192055e-05,
      "loss": 0.4421,
      "step": 1230
    },
    {
      "epoch": 125.07,
      "learning_rate": 4.1721854304635764e-05,
      "loss": 0.4175,
      "step": 1260
    },
    {
      "epoch": 128.07,
      "learning_rate": 4.271523178807947e-05,
      "loss": 0.3933,
      "step": 1290
    },
    {
      "epoch": 131.07,
      "learning_rate": 4.370860927152318e-05,
      "loss": 0.3664,
      "step": 1320
    },
    {
      "epoch": 134.07,
      "learning_rate": 4.470198675496689e-05,
      "loss": 0.3446,
      "step": 1350
    },
    {
      "epoch": 137.07,
      "learning_rate": 4.56953642384106e-05,
      "loss": 0.32,
      "step": 1380
    },
    {
      "epoch": 140.07,
      "learning_rate": 4.668874172185431e-05,
      "loss": 0.305,
      "step": 1410
    },
    {
      "epoch": 143.07,
      "learning_rate": 4.768211920529801e-05,
      "loss": 0.2827,
      "step": 1440
    },
    {
      "epoch": 146.07,
      "learning_rate": 4.867549668874172e-05,
      "loss": 0.2646,
      "step": 1470
    },
    {
      "epoch": 149.07,
      "learning_rate": 4.966887417218543e-05,
      "loss": 0.2455,
      "step": 1500
    },
    {
      "epoch": 152.07,
      "learning_rate": 5.0662251655629146e-05,
      "loss": 0.2318,
      "step": 1530
    },
    {
      "epoch": 155.07,
      "learning_rate": 5.165562913907285e-05,
      "loss": 0.2141,
      "step": 1560
    },
    {
      "epoch": 158.07,
      "learning_rate": 5.264900662251656e-05,
      "loss": 0.1944,
      "step": 1590
    },
    {
      "epoch": 161.07,
      "learning_rate": 5.364238410596027e-05,
      "loss": 0.1807,
      "step": 1620
    },
    {
      "epoch": 164.07,
      "learning_rate": 5.4635761589403976e-05,
      "loss": 0.1731,
      "step": 1650
    },
    {
      "epoch": 167.07,
      "learning_rate": 5.562913907284768e-05,
      "loss": 0.1582,
      "step": 1680
    },
    {
      "epoch": 170.07,
      "learning_rate": 5.6622516556291394e-05,
      "loss": 0.1514,
      "step": 1710
    },
    {
      "epoch": 173.07,
      "learning_rate": 5.76158940397351e-05,
      "loss": 0.1379,
      "step": 1740
    },
    {
      "epoch": 176.07,
      "learning_rate": 5.860927152317881e-05,
      "loss": 0.1324,
      "step": 1770
    },
    {
      "epoch": 179.07,
      "learning_rate": 5.960264900662252e-05,
      "loss": 0.1194,
      "step": 1800
    },
    {
      "epoch": 182.07,
      "learning_rate": 6.0596026490066224e-05,
      "loss": 0.1099,
      "step": 1830
    },
    {
      "epoch": 185.07,
      "learning_rate": 6.158940397350994e-05,
      "loss": 0.1051,
      "step": 1860
    },
    {
      "epoch": 188.07,
      "learning_rate": 6.258278145695365e-05,
      "loss": 0.0955,
      "step": 1890
    },
    {
      "epoch": 191.07,
      "learning_rate": 6.357615894039736e-05,
      "loss": 0.094,
      "step": 1920
    },
    {
      "epoch": 194.07,
      "learning_rate": 6.456953642384105e-05,
      "loss": 0.0853,
      "step": 1950
    },
    {
      "epoch": 197.07,
      "learning_rate": 6.556291390728478e-05,
      "loss": 0.0786,
      "step": 1980
    }
  ],
  "logging_steps": 30,
  "max_steps": 30200,
  "num_train_epochs": 200,
  "save_steps": 500,
  "total_flos": 3.2310451765248e+16,
  "trial_name": null,
  "trial_params": null
}