{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.2356020942408374,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26,
      "learning_rate": 6.25e-06,
      "loss": 7.3722,
      "step": 500
    },
    {
      "epoch": 0.26,
      "eval_runtime": 4.9957,
      "eval_samples_per_second": 20.017,
      "eval_steps_per_second": 10.009,
      "step": 500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.895833333333334e-06,
      "loss": 1.5052,
      "step": 1000
    },
    {
      "epoch": 0.52,
      "eval_runtime": 5.5484,
      "eval_samples_per_second": 18.023,
      "eval_steps_per_second": 9.012,
      "step": 1000
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.635416666666668e-06,
      "loss": 1.3479,
      "step": 1500
    },
    {
      "epoch": 0.79,
      "eval_runtime": 5.4316,
      "eval_samples_per_second": 18.411,
      "eval_steps_per_second": 9.205,
      "step": 1500
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.375000000000001e-06,
      "loss": 1.3177,
      "step": 2000
    },
    {
      "epoch": 1.05,
      "eval_runtime": 5.4246,
      "eval_samples_per_second": 18.435,
      "eval_steps_per_second": 9.217,
      "step": 2000
    },
    {
      "epoch": 1.31,
      "learning_rate": 9.114583333333334e-06,
      "loss": 1.2962,
      "step": 2500
    },
    {
      "epoch": 1.31,
      "eval_runtime": 5.0933,
      "eval_samples_per_second": 19.634,
      "eval_steps_per_second": 9.817,
      "step": 2500
    },
    {
      "epoch": 1.57,
      "learning_rate": 8.854166666666667e-06,
      "loss": 1.2824,
      "step": 3000
    },
    {
      "epoch": 1.57,
      "eval_runtime": 6.1894,
      "eval_samples_per_second": 16.157,
      "eval_steps_per_second": 8.078,
      "step": 3000
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.59375e-06,
      "loss": 1.2784,
      "step": 3500
    },
    {
      "epoch": 1.83,
      "eval_runtime": 4.7573,
      "eval_samples_per_second": 21.02,
      "eval_steps_per_second": 10.51,
      "step": 3500
    },
    {
      "epoch": 2.09,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.2655,
      "step": 4000
    },
    {
      "epoch": 2.09,
      "eval_runtime": 5.5685,
      "eval_samples_per_second": 17.958,
      "eval_steps_per_second": 8.979,
      "step": 4000
    },
    {
      "epoch": 2.36,
      "learning_rate": 8.072916666666667e-06,
      "loss": 1.2553,
      "step": 4500
    },
    {
      "epoch": 2.36,
      "eval_runtime": 6.732,
      "eval_samples_per_second": 14.854,
      "eval_steps_per_second": 7.427,
      "step": 4500
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.8125e-06,
      "loss": 1.2627,
      "step": 5000
    },
    {
      "epoch": 2.62,
      "eval_runtime": 4.5523,
      "eval_samples_per_second": 21.967,
      "eval_steps_per_second": 10.983,
      "step": 5000
    },
    {
      "epoch": 2.88,
      "learning_rate": 7.552083333333334e-06,
      "loss": 1.2358,
      "step": 5500
    },
    {
      "epoch": 2.88,
      "eval_runtime": 4.906,
      "eval_samples_per_second": 20.383,
      "eval_steps_per_second": 10.192,
      "step": 5500
    },
    {
      "epoch": 3.14,
      "learning_rate": 7.291666666666667e-06,
      "loss": 1.2495,
      "step": 6000
    },
    {
      "epoch": 3.14,
      "eval_runtime": 5.2379,
      "eval_samples_per_second": 19.092,
      "eval_steps_per_second": 9.546,
      "step": 6000
    },
    {
      "epoch": 3.4,
      "learning_rate": 7.031250000000001e-06,
      "loss": 1.234,
      "step": 6500
    },
    {
      "epoch": 3.4,
      "eval_runtime": 5.2459,
      "eval_samples_per_second": 19.062,
      "eval_steps_per_second": 9.531,
      "step": 6500
    },
    {
      "epoch": 3.66,
      "learning_rate": 6.770833333333334e-06,
      "loss": 1.2228,
      "step": 7000
    },
    {
      "epoch": 3.66,
      "eval_runtime": 5.186,
      "eval_samples_per_second": 19.283,
      "eval_steps_per_second": 9.641,
      "step": 7000
    },
    {
      "epoch": 3.93,
      "learning_rate": 6.510416666666667e-06,
      "loss": 1.2403,
      "step": 7500
    },
    {
      "epoch": 3.93,
      "eval_runtime": 5.9443,
      "eval_samples_per_second": 16.823,
      "eval_steps_per_second": 8.411,
      "step": 7500
    },
    {
      "epoch": 4.19,
      "learning_rate": 6.25e-06,
      "loss": 1.2254,
      "step": 8000
    },
    {
      "epoch": 4.19,
      "eval_runtime": 6.1004,
      "eval_samples_per_second": 16.392,
      "eval_steps_per_second": 8.196,
      "step": 8000
    },
    {
      "epoch": 4.45,
      "learning_rate": 5.989583333333334e-06,
      "loss": 1.2203,
      "step": 8500
    },
    {
      "epoch": 4.45,
      "eval_runtime": 4.7155,
      "eval_samples_per_second": 21.207,
      "eval_steps_per_second": 10.603,
      "step": 8500
    },
    {
      "epoch": 4.71,
      "learning_rate": 5.729166666666667e-06,
      "loss": 1.2198,
      "step": 9000
    },
    {
      "epoch": 4.71,
      "eval_runtime": 5.2917,
      "eval_samples_per_second": 18.897,
      "eval_steps_per_second": 9.449,
      "step": 9000
    },
    {
      "epoch": 4.97,
      "learning_rate": 5.468750000000001e-06,
      "loss": 1.2405,
      "step": 9500
    },
    {
      "epoch": 4.97,
      "eval_runtime": 5.6681,
      "eval_samples_per_second": 17.643,
      "eval_steps_per_second": 8.821,
      "step": 9500
    },
    {
      "epoch": 5.24,
      "learning_rate": 5.208333333333334e-06,
      "loss": 1.2209,
      "step": 10000
    },
    {
      "epoch": 5.24,
      "eval_runtime": 4.7064,
      "eval_samples_per_second": 21.247,
      "eval_steps_per_second": 10.624,
      "step": 10000
    }
  ],
  "max_steps": 20000,
  "num_train_epochs": 11,
  "total_flos": 8.36711025084334e+16,
  "trial_name": null,
  "trial_params": null
}