{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0001555625,
  "eval_steps": 500,
  "global_step": 21000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.995e-05,
      "loss": 3.1324,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.99e-05,
      "loss": 2.7883,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 2.576,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 2.5156,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.975e-05,
      "loss": 2.4018,
      "step": 2500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.97e-05,
      "loss": 2.3792,
      "step": 3000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.965e-05,
      "loss": 2.3919,
      "step": 3500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.96e-05,
      "loss": 2.2942,
      "step": 4000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9550000000000005e-05,
      "loss": 2.2954,
      "step": 4500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 2.2145,
      "step": 5000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.945e-05,
      "loss": 2.1963,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.94e-05,
      "loss": 2.218,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.935e-05,
      "loss": 2.1342,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.93e-05,
      "loss": 2.1712,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9250000000000004e-05,
      "loss": 2.1653,
      "step": 7500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.92e-05,
      "loss": 2.1579,
      "step": 8000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.915e-05,
      "loss": 2.1273,
      "step": 8500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.91e-05,
      "loss": 2.1075,
      "step": 9000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.905e-05,
      "loss": 2.0985,
      "step": 9500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9e-05,
      "loss": 2.0555,
      "step": 10000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8950000000000004e-05,
      "loss": 2.0641,
      "step": 10500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.89e-05,
      "loss": 2.062,
      "step": 11000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.885e-05,
      "loss": 2.0178,
      "step": 11500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.88e-05,
      "loss": 2.0227,
      "step": 12000
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.875e-05,
      "loss": 2.0456,
      "step": 12500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.87e-05,
      "loss": 1.9856,
      "step": 13000
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.8650000000000003e-05,
      "loss": 2.0806,
      "step": 13500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.86e-05,
      "loss": 1.9999,
      "step": 14000
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.855e-05,
      "loss": 1.9597,
      "step": 14500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.85e-05,
      "loss": 1.9367,
      "step": 15000
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.845e-05,
      "loss": 1.9949,
      "step": 15500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 1.9795,
      "step": 16000
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.835e-05,
      "loss": 1.9473,
      "step": 16500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.83e-05,
      "loss": 1.949,
      "step": 17000
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.825e-05,
      "loss": 1.9626,
      "step": 17500
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.82e-05,
      "loss": 1.9295,
      "step": 18000
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.815e-05,
      "loss": 1.9425,
      "step": 18500
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8100000000000004e-05,
      "loss": 1.8936,
      "step": 19000
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.805e-05,
      "loss": 1.9084,
      "step": 19500
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8e-05,
      "loss": 1.907,
      "step": 20000
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.795e-05,
      "loss": 1.8878,
      "step": 20500
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.79e-05,
      "loss": 1.9235,
      "step": 21000
    }
  ],
  "logging_steps": 500,
  "max_steps": 500000,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 9.977612193497088e+18,
  "trial_name": null,
  "trial_params": null
}