{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 22.44488977955912,
  "eval_steps": 100,
  "global_step": 2800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "eval_loss": 1.9484879970550537,
      "eval_runtime": 80.1777,
      "eval_samples_per_second": 2.769,
      "eval_steps_per_second": 0.349,
      "step": 100
    },
    {
      "epoch": 1.6,
      "eval_loss": 1.9194128513336182,
      "eval_runtime": 75.485,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 200
    },
    {
      "epoch": 2.4,
      "eval_loss": 1.9068584442138672,
      "eval_runtime": 75.624,
      "eval_samples_per_second": 2.936,
      "eval_steps_per_second": 0.37,
      "step": 300
    },
    {
      "epoch": 3.21,
      "eval_loss": 1.8953101634979248,
      "eval_runtime": 75.4707,
      "eval_samples_per_second": 2.942,
      "eval_steps_per_second": 0.371,
      "step": 400
    },
    {
      "epoch": 4.01,
      "learning_rate": 2.08611481975968e-05,
      "loss": 1.9094,
      "step": 500
    },
    {
      "epoch": 4.01,
      "eval_loss": 1.8837881088256836,
      "eval_runtime": 75.6492,
      "eval_samples_per_second": 2.935,
      "eval_steps_per_second": 0.37,
      "step": 500
    },
    {
      "epoch": 4.81,
      "eval_loss": 1.8737961053848267,
      "eval_runtime": 75.486,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 600
    },
    {
      "epoch": 5.61,
      "eval_loss": 1.8641096353530884,
      "eval_runtime": 75.4927,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 700
    },
    {
      "epoch": 6.41,
      "eval_loss": 1.8550605773925781,
      "eval_runtime": 75.4778,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 800
    },
    {
      "epoch": 7.21,
      "eval_loss": 1.8458194732666016,
      "eval_runtime": 75.4994,
      "eval_samples_per_second": 2.94,
      "eval_steps_per_second": 0.371,
      "step": 900
    },
    {
      "epoch": 8.02,
      "learning_rate": 1.6688918558077437e-05,
      "loss": 1.8138,
      "step": 1000
    },
    {
      "epoch": 8.02,
      "eval_loss": 1.837294340133667,
      "eval_runtime": 75.3775,
      "eval_samples_per_second": 2.945,
      "eval_steps_per_second": 0.371,
      "step": 1000
    },
    {
      "epoch": 8.82,
      "eval_loss": 1.8297418355941772,
      "eval_runtime": 75.4862,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 1100
    },
    {
      "epoch": 9.62,
      "eval_loss": 1.8239439725875854,
      "eval_runtime": 75.4899,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.371,
      "step": 1200
    },
    {
      "epoch": 10.42,
      "eval_loss": 1.8179348707199097,
      "eval_runtime": 75.4662,
      "eval_samples_per_second": 2.942,
      "eval_steps_per_second": 0.371,
      "step": 1300
    },
    {
      "epoch": 11.22,
      "eval_loss": 1.8130933046340942,
      "eval_runtime": 75.5064,
      "eval_samples_per_second": 2.94,
      "eval_steps_per_second": 0.371,
      "step": 1400
    },
    {
      "epoch": 12.02,
      "learning_rate": 1.2516688918558078e-05,
      "loss": 1.7439,
      "step": 1500
    },
    {
      "epoch": 12.02,
      "eval_loss": 1.8075053691864014,
      "eval_runtime": 75.671,
      "eval_samples_per_second": 2.934,
      "eval_steps_per_second": 0.37,
      "step": 1500
    },
    {
      "epoch": 12.83,
      "eval_loss": 1.8044650554656982,
      "eval_runtime": 75.6414,
      "eval_samples_per_second": 2.935,
      "eval_steps_per_second": 0.37,
      "step": 1600
    },
    {
      "epoch": 13.63,
      "eval_loss": 1.8003138303756714,
      "eval_runtime": 75.6422,
      "eval_samples_per_second": 2.935,
      "eval_steps_per_second": 0.37,
      "step": 1700
    },
    {
      "epoch": 14.43,
      "eval_loss": 1.7982312440872192,
      "eval_runtime": 75.6665,
      "eval_samples_per_second": 2.934,
      "eval_steps_per_second": 0.37,
      "step": 1800
    },
    {
      "epoch": 15.23,
      "eval_loss": 1.7970277070999146,
      "eval_runtime": 75.6383,
      "eval_samples_per_second": 2.935,
      "eval_steps_per_second": 0.37,
      "step": 1900
    },
    {
      "epoch": 16.03,
      "learning_rate": 8.344459279038718e-06,
      "loss": 1.7005,
      "step": 2000
    },
    {
      "epoch": 16.03,
      "eval_loss": 1.7927231788635254,
      "eval_runtime": 78.7098,
      "eval_samples_per_second": 2.82,
      "eval_steps_per_second": 0.356,
      "step": 2000
    },
    {
      "epoch": 16.83,
      "eval_loss": 1.790854573249817,
      "eval_runtime": 77.0191,
      "eval_samples_per_second": 2.882,
      "eval_steps_per_second": 0.364,
      "step": 2100
    },
    {
      "epoch": 17.64,
      "eval_loss": 1.7891895771026611,
      "eval_runtime": 76.0084,
      "eval_samples_per_second": 2.921,
      "eval_steps_per_second": 0.368,
      "step": 2200
    },
    {
      "epoch": 18.44,
      "eval_loss": 1.7889128923416138,
      "eval_runtime": 75.6093,
      "eval_samples_per_second": 2.936,
      "eval_steps_per_second": 0.37,
      "step": 2300
    },
    {
      "epoch": 19.24,
      "eval_loss": 1.788590431213379,
      "eval_runtime": 75.7303,
      "eval_samples_per_second": 2.931,
      "eval_steps_per_second": 0.37,
      "step": 2400
    },
    {
      "epoch": 20.04,
      "learning_rate": 4.172229639519359e-06,
      "loss": 1.6705,
      "step": 2500
    },
    {
      "epoch": 20.04,
      "eval_loss": 1.7878992557525635,
      "eval_runtime": 75.5956,
      "eval_samples_per_second": 2.937,
      "eval_steps_per_second": 0.37,
      "step": 2500
    },
    {
      "epoch": 20.84,
      "eval_loss": 1.7869019508361816,
      "eval_runtime": 75.569,
      "eval_samples_per_second": 2.938,
      "eval_steps_per_second": 0.371,
      "step": 2600
    },
    {
      "epoch": 21.64,
      "eval_loss": 1.7858072519302368,
      "eval_runtime": 75.7601,
      "eval_samples_per_second": 2.93,
      "eval_steps_per_second": 0.37,
      "step": 2700
    },
    {
      "epoch": 22.44,
      "eval_loss": 1.7860134840011597,
      "eval_runtime": 75.7457,
      "eval_samples_per_second": 2.931,
      "eval_steps_per_second": 0.37,
      "step": 2800
    }
  ],
  "logging_steps": 500,
  "max_steps": 3000,
  "num_train_epochs": 25,
  "save_steps": 100,
  "total_flos": 3.543009935795159e+18,
  "trial_name": null,
  "trial_params": null
}