{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9929780131230572,
  "eval_steps": 500,
  "global_step": 26000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 9.99092041233887e-05,
      "loss": 0.6515,
      "step": 500
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.963714624920319e-05,
      "loss": 0.6374,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.918481444677047e-05,
      "loss": 0.6399,
      "step": 1500
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.855385151059141e-05,
      "loss": 0.6424,
      "step": 2000
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.774654899398198e-05,
      "loss": 0.6391,
      "step": 2500
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.676583888652963e-05,
      "loss": 0.6313,
      "step": 3000
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.561528296559068e-05,
      "loss": 0.6355,
      "step": 3500
    },
    {
      "epoch": 0.46,
      "learning_rate": 9.429905986050238e-05,
      "loss": 0.6304,
      "step": 4000
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.282194987649045e-05,
      "loss": 0.6256,
      "step": 4500
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.118931763338888e-05,
      "loss": 0.6269,
      "step": 5000
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.94070925822255e-05,
      "loss": 0.6306,
      "step": 5500
    },
    {
      "epoch": 0.69,
      "learning_rate": 8.748174747043391e-05,
      "loss": 0.6237,
      "step": 6000
    },
    {
      "epoch": 0.75,
      "learning_rate": 8.542027483390225e-05,
      "loss": 0.6325,
      "step": 6500
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.323016160123629e-05,
      "loss": 0.6266,
      "step": 7000
    },
    {
      "epoch": 0.86,
      "learning_rate": 8.091936190246954e-05,
      "loss": 0.6261,
      "step": 7500
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.849626818097493e-05,
      "loss": 0.6282,
      "step": 8000
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.596968071349464e-05,
      "loss": 0.6271,
      "step": 8500
    },
    {
      "epoch": 1.04,
      "learning_rate": 7.334877564898644e-05,
      "loss": 0.6232,
      "step": 9000
    },
    {
      "epoch": 1.09,
      "learning_rate": 7.064307168236421e-05,
      "loss": 0.6224,
      "step": 9500
    },
    {
      "epoch": 1.15,
      "learning_rate": 6.786239548416799e-05,
      "loss": 0.6247,
      "step": 10000
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.501684601171727e-05,
      "loss": 0.6238,
      "step": 10500
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.21167578313637e-05,
      "loss": 0.628,
      "step": 11000
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.917266358505073e-05,
      "loss": 0.6267,
      "step": 11500
    },
    {
      "epoch": 1.38,
      "learning_rate": 5.6195255737495125e-05,
      "loss": 0.6285,
      "step": 12000
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.319534774291885e-05,
      "loss": 0.6285,
      "step": 12500
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.0183834772366734e-05,
      "loss": 0.6246,
      "step": 13000
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.7171654144242266e-05,
      "loss": 0.628,
      "step": 13500
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.416974560177112e-05,
      "loss": 0.6276,
      "step": 14000
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.1189011581658147e-05,
      "loss": 0.6284,
      "step": 14500
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.82402776182354e-05,
      "loss": 0.6242,
      "step": 15000
    },
    {
      "epoch": 1.78,
      "learning_rate": 3.5334253026906946e-05,
      "loss": 0.6222,
      "step": 15500
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.248149200968176e-05,
      "loss": 0.6241,
      "step": 16000
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.969235532405272e-05,
      "loss": 0.6145,
      "step": 16500
    },
    {
      "epoch": 1.96,
      "learning_rate": 2.6976972654434195e-05,
      "loss": 0.6181,
      "step": 17000
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.434520582281914e-05,
      "loss": 0.6257,
      "step": 17500
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.1806612972268065e-05,
      "loss": 0.6167,
      "step": 18000
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.9370413853309972e-05,
      "loss": 0.6208,
      "step": 18500
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.7045456339329084e-05,
      "loss": 0.6162,
      "step": 19000
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4840184292548053e-05,
      "loss": 0.6118,
      "step": 19500
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.2762606897313006e-05,
      "loss": 0.6155,
      "step": 20000
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.0820269572057097e-05,
      "loss": 0.6208,
      "step": 20500
    },
    {
      "epoch": 2.42,
      "learning_rate": 9.020226565585154e-06,
      "loss": 0.6152,
      "step": 21000
    },
    {
      "epoch": 2.47,
      "learning_rate": 7.36901533720562e-06,
      "loss": 0.6135,
      "step": 21500
    },
    {
      "epoch": 2.53,
      "learning_rate": 5.87263281375654e-06,
      "loss": 0.6098,
      "step": 22000
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.536513609756426e-06,
      "loss": 0.6157,
      "step": 22500
    },
    {
      "epoch": 2.65,
      "learning_rate": 3.365510289780621e-06,
      "loss": 0.6156,
      "step": 23000
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.3638757447472237e-06,
      "loss": 0.6143,
      "step": 23500
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.535247746118651e-06,
      "loss": 0.6206,
      "step": 24000
    },
    {
      "epoch": 2.82,
      "learning_rate": 8.826357341157054e-07,
      "loss": 0.6161,
      "step": 24500
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.084098879270637e-07,
      "loss": 0.6193,
      "step": 25000
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.1429251760938231e-07,
      "loss": 0.6147,
      "step": 25500
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.3518089412467572e-09,
      "loss": 0.6172,
      "step": 26000
    }
  ],
  "logging_steps": 500,
  "max_steps": 26061,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.6163640128943923e+18,
  "trial_name": null,
  "trial_params": null
}