{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 2025,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 4.876543209876544e-05,
      "loss": 6.5495,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7530864197530866e-05,
      "loss": 5.3676,
      "step": 100
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.62962962962963e-05,
      "loss": 4.7027,
      "step": 150
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.506172839506173e-05,
      "loss": 4.2735,
      "step": 200
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.3827160493827164e-05,
      "loss": 4.0016,
      "step": 250
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.259259259259259e-05,
      "loss": 3.7738,
      "step": 300
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.135802469135803e-05,
      "loss": 3.6269,
      "step": 350
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.012345679012346e-05,
      "loss": 3.5536,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.888888888888889e-05,
      "loss": 3.4593,
      "step": 450
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7654320987654326e-05,
      "loss": 3.4005,
      "step": 500
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.6419753086419754e-05,
      "loss": 3.3179,
      "step": 550
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.518518518518519e-05,
      "loss": 3.1816,
      "step": 600
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.395061728395062e-05,
      "loss": 3.1718,
      "step": 650
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.271604938271605e-05,
      "loss": 3.1147,
      "step": 700
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.148148148148148e-05,
      "loss": 3.0359,
      "step": 750
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.0246913580246916e-05,
      "loss": 3.0169,
      "step": 800
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.9012345679012347e-05,
      "loss": 2.9607,
      "step": 850
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.9408,
      "step": 900
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.654320987654321e-05,
      "loss": 2.8506,
      "step": 950
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5308641975308646e-05,
      "loss": 2.7977,
      "step": 1000
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 2.821,
      "step": 1050
    },
    {
      "epoch": 1.63,
      "learning_rate": 2.2839506172839506e-05,
      "loss": 2.6649,
      "step": 1100
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.1604938271604937e-05,
      "loss": 2.6711,
      "step": 1150
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.037037037037037e-05,
      "loss": 2.6221,
      "step": 1200
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.91358024691358e-05,
      "loss": 2.5494,
      "step": 1250
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.7901234567901236e-05,
      "loss": 2.5921,
      "step": 1300
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.5591,
      "step": 1350
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.54320987654321e-05,
      "loss": 2.5024,
      "step": 1400
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.419753086419753e-05,
      "loss": 2.5085,
      "step": 1450
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 2.4649,
      "step": 1500
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.1728395061728396e-05,
      "loss": 2.5289,
      "step": 1550
    },
    {
      "epoch": 2.37,
      "learning_rate": 1.0493827160493827e-05,
      "loss": 2.438,
      "step": 1600
    },
    {
      "epoch": 2.44,
      "learning_rate": 9.259259259259259e-06,
      "loss": 2.4624,
      "step": 1650
    },
    {
      "epoch": 2.52,
      "learning_rate": 8.02469135802469e-06,
      "loss": 2.421,
      "step": 1700
    },
    {
      "epoch": 2.59,
      "learning_rate": 6.790123456790123e-06,
      "loss": 2.4613,
      "step": 1750
    },
    {
      "epoch": 2.67,
      "learning_rate": 5.555555555555556e-06,
      "loss": 2.443,
      "step": 1800
    },
    {
      "epoch": 2.74,
      "learning_rate": 4.3209876543209875e-06,
      "loss": 2.3844,
      "step": 1850
    },
    {
      "epoch": 2.81,
      "learning_rate": 3.0864197530864196e-06,
      "loss": 2.381,
      "step": 1900
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 2.4274,
      "step": 1950
    },
    {
      "epoch": 2.96,
      "learning_rate": 6.17283950617284e-07,
      "loss": 2.4303,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "step": 2025,
      "train_runtime": 5654.6733,
      "train_samples_per_second": 0.358
    }
  ],
  "max_steps": 2025,
  "num_train_epochs": 3,
  "total_flos": 3652633623527424,
  "trial_name": null,
  "trial_params": null
}