{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9993820294154,
  "eval_steps": 500,
  "global_step": 20225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 0.0572,
      "step": 500
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9921402862953804e-05,
      "loss": 0.0701,
      "step": 1000
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.968484642500649e-05,
      "loss": 0.0733,
      "step": 1500
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.92918287952728e-05,
      "loss": 0.0821,
      "step": 2000
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.8744841056973686e-05,
      "loss": 0.0868,
      "step": 2500
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.8047350209739364e-05,
      "loss": 0.0855,
      "step": 3000
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.720377719455276e-05,
      "loss": 0.0851,
      "step": 3500
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.6219468872279157e-05,
      "loss": 0.085,
      "step": 4000
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.510303139450832e-05,
      "loss": 0.0704,
      "step": 4500
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.385706880295634e-05,
      "loss": 0.0715,
      "step": 5000
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.249158351283414e-05,
      "loss": 0.0704,
      "step": 5500
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.101523044757859e-05,
      "loss": 0.075,
      "step": 6000
    },
    {
      "epoch": 1.61,
      "learning_rate": 3.94406177364273e-05,
      "loss": 0.0718,
      "step": 6500
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.7771418094841905e-05,
      "loss": 0.0701,
      "step": 7000
    },
    {
      "epoch": 1.85,
      "learning_rate": 3.602126873772994e-05,
      "loss": 0.0686,
      "step": 7500
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.420126272394637e-05,
      "loss": 0.0666,
      "step": 8000
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.2326742887008035e-05,
      "loss": 0.0596,
      "step": 8500
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.0402081462665028e-05,
      "loss": 0.0535,
      "step": 9000
    },
    {
      "epoch": 2.35,
      "learning_rate": 2.844317975627921e-05,
      "loss": 0.053,
      "step": 9500
    },
    {
      "epoch": 2.47,
      "learning_rate": 2.6462453972120053e-05,
      "loss": 0.0531,
      "step": 10000
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.447643950291608e-05,
      "loss": 0.0509,
      "step": 10500
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.24937302895087e-05,
      "loss": 0.0528,
      "step": 11000
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.0522925817157924e-05,
      "loss": 0.0509,
      "step": 11500
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.858049860712845e-05,
      "loss": 0.0534,
      "step": 12000
    },
    {
      "epoch": 3.09,
      "learning_rate": 1.6678760442568807e-05,
      "loss": 0.0397,
      "step": 12500
    },
    {
      "epoch": 3.21,
      "learning_rate": 1.4829765205223683e-05,
      "loss": 0.0384,
      "step": 13000
    },
    {
      "epoch": 3.34,
      "learning_rate": 1.3045232473714773e-05,
      "loss": 0.0378,
      "step": 13500
    },
    {
      "epoch": 3.46,
      "learning_rate": 1.1339807851507919e-05,
      "loss": 0.0395,
      "step": 14000
    },
    {
      "epoch": 3.58,
      "learning_rate": 9.717469167141063e-06,
      "loss": 0.0417,
      "step": 14500
    },
    {
      "epoch": 3.71,
      "learning_rate": 8.191996509260754e-06,
      "loss": 0.0412,
      "step": 15000
    },
    {
      "epoch": 3.83,
      "learning_rate": 6.773058857206802e-06,
      "loss": 0.0405,
      "step": 15500
    },
    {
      "epoch": 3.96,
      "learning_rate": 5.469649934184448e-06,
      "loss": 0.0404,
      "step": 16000
    },
    {
      "epoch": 4.08,
      "learning_rate": 4.292261791598673e-06,
      "loss": 0.0324,
      "step": 16500
    },
    {
      "epoch": 4.2,
      "learning_rate": 3.243640635932488e-06,
      "loss": 0.0339,
      "step": 17000
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.3329188966299516e-06,
      "loss": 0.0355,
      "step": 17500
    },
    {
      "epoch": 4.45,
      "learning_rate": 1.565869046659435e-06,
      "loss": 0.0357,
      "step": 18000
    },
    {
      "epoch": 4.57,
      "learning_rate": 9.484389467240757e-07,
      "loss": 0.0335,
      "step": 18500
    },
    {
      "epoch": 4.7,
      "learning_rate": 4.820687255986694e-07,
      "loss": 0.0346,
      "step": 19000
    },
    {
      "epoch": 4.82,
      "learning_rate": 1.711017296455786e-07,
      "loss": 0.0391,
      "step": 19500
    },
    {
      "epoch": 4.94,
      "learning_rate": 1.750897646625449e-08,
      "loss": 0.0438,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20225,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.7146262160275866e+17,
  "trial_name": null,
  "trial_params": null
}