{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 15600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 0.00029038461538461537,
      "loss": 0.0701,
      "step": 500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028076923076923076,
      "loss": 0.0536,
      "step": 1000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00027115384615384615,
      "loss": 0.0466,
      "step": 1500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00026153846153846154,
      "loss": 0.0412,
      "step": 2000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002519230769230769,
      "loss": 0.0373,
      "step": 2500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002423076923076923,
      "loss": 0.0324,
      "step": 3000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00023269230769230767,
      "loss": 0.0289,
      "step": 3500
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00022307692307692306,
      "loss": 0.0276,
      "step": 4000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00021346153846153845,
      "loss": 0.0244,
      "step": 4500
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00020384615384615385,
      "loss": 0.0291,
      "step": 5000
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001942307692307692,
      "loss": 0.0221,
      "step": 5500
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001846153846153846,
      "loss": 0.0216,
      "step": 6000
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.000175,
      "loss": 0.0194,
      "step": 6500
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001653846153846154,
      "loss": 0.017,
      "step": 7000
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00015576923076923076,
      "loss": 0.0165,
      "step": 7500
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.015,
      "step": 8000
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00013653846153846152,
      "loss": 0.0156,
      "step": 8500
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001269230769230769,
      "loss": 0.014,
      "step": 9000
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001173076923076923,
      "loss": 0.0134,
      "step": 9500
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00010769230769230768,
      "loss": 0.0113,
      "step": 10000
    },
    {
      "epoch": 3.37,
      "learning_rate": 9.807692307692307e-05,
      "loss": 0.0103,
      "step": 10500
    },
    {
      "epoch": 3.53,
      "learning_rate": 8.846153846153845e-05,
      "loss": 0.0103,
      "step": 11000
    },
    {
      "epoch": 3.69,
      "learning_rate": 7.884615384615384e-05,
      "loss": 0.0098,
      "step": 11500
    },
    {
      "epoch": 3.85,
      "learning_rate": 6.923076923076922e-05,
      "loss": 0.0099,
      "step": 12000
    },
    {
      "epoch": 4.01,
      "learning_rate": 5.961538461538461e-05,
      "loss": 0.0084,
      "step": 12500
    },
    {
      "epoch": 4.17,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0065,
      "step": 13000
    },
    {
      "epoch": 4.33,
      "learning_rate": 4.038461538461538e-05,
      "loss": 0.0066,
      "step": 13500
    },
    {
      "epoch": 4.49,
      "learning_rate": 3.076923076923077e-05,
      "loss": 0.006,
      "step": 14000
    },
    {
      "epoch": 4.65,
      "learning_rate": 2.115384615384615e-05,
      "loss": 0.0065,
      "step": 14500
    },
    {
      "epoch": 4.81,
      "learning_rate": 1.1538461538461538e-05,
      "loss": 0.0056,
      "step": 15000
    },
    {
      "epoch": 4.97,
      "learning_rate": 1.923076923076923e-06,
      "loss": 0.006,
      "step": 15500
    },
    {
      "epoch": 5.0,
      "step": 15600,
      "total_flos": 5.943712364448768e+16,
      "train_loss": 0.020643039299891544,
      "train_runtime": 4743.0348,
      "train_samples_per_second": 105.227,
      "train_steps_per_second": 3.289
    }
  ],
  "logging_steps": 500,
  "max_steps": 15600,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.943712364448768e+16,
  "trial_name": null,
  "trial_params": null
}