{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 18750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 2.92016e-05,
      "loss": 0.0366,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.84016e-05,
      "loss": 0.0066,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.76016e-05,
      "loss": 0.0056,
      "step": 1500
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.68016e-05,
      "loss": 0.0049,
      "step": 2000
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.6001600000000002e-05,
      "loss": 0.0045,
      "step": 2500
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.52016e-05,
      "loss": 0.0041,
      "step": 3000
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.44016e-05,
      "loss": 0.0039,
      "step": 3500
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.36016e-05,
      "loss": 0.0038,
      "step": 4000
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.2801600000000002e-05,
      "loss": 0.0035,
      "step": 4500
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.20016e-05,
      "loss": 0.0035,
      "step": 5000
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.12016e-05,
      "loss": 0.0033,
      "step": 5500
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.0401599999999998e-05,
      "loss": 0.0032,
      "step": 6000
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.9601600000000002e-05,
      "loss": 0.0031,
      "step": 6500
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.8801600000000003e-05,
      "loss": 0.003,
      "step": 7000
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.80016e-05,
      "loss": 0.0029,
      "step": 7500
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.72016e-05,
      "loss": 0.0029,
      "step": 8000
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.64016e-05,
      "loss": 0.0028,
      "step": 8500
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.56016e-05,
      "loss": 0.0029,
      "step": 9000
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.4801599999999999e-05,
      "loss": 0.0028,
      "step": 9500
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.4001600000000002e-05,
      "loss": 0.0028,
      "step": 10000
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.32032e-05,
      "loss": 0.0028,
      "step": 10500
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.24032e-05,
      "loss": 0.0027,
      "step": 11000
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.1603200000000001e-05,
      "loss": 0.0027,
      "step": 11500
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.08032e-05,
      "loss": 0.0026,
      "step": 12000
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.00048e-05,
      "loss": 0.0026,
      "step": 12500
    },
    {
      "epoch": 2.08,
      "learning_rate": 9.2048e-06,
      "loss": 0.0026,
      "step": 13000
    },
    {
      "epoch": 2.16,
      "learning_rate": 8.404800000000001e-06,
      "loss": 0.0026,
      "step": 13500
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.6048000000000004e-06,
      "loss": 0.0026,
      "step": 14000
    },
    {
      "epoch": 2.32,
      "learning_rate": 6.8048000000000005e-06,
      "loss": 0.0025,
      "step": 14500
    },
    {
      "epoch": 2.4,
      "learning_rate": 6.0064e-06,
      "loss": 0.0025,
      "step": 15000
    },
    {
      "epoch": 2.48,
      "learning_rate": 5.2064e-06,
      "loss": 0.0025,
      "step": 15500
    },
    {
      "epoch": 2.56,
      "learning_rate": 4.406400000000001e-06,
      "loss": 0.0026,
      "step": 16000
    },
    {
      "epoch": 2.64,
      "learning_rate": 3.6064000000000003e-06,
      "loss": 0.0025,
      "step": 16500
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.808e-06,
      "loss": 0.0025,
      "step": 17000
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.008e-06,
      "loss": 0.0025,
      "step": 17500
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.208e-06,
      "loss": 0.0025,
      "step": 18000
    },
    {
      "epoch": 2.96,
      "learning_rate": 4.08e-07,
      "loss": 0.0025,
      "step": 18500
    },
    {
      "epoch": 3.0,
      "step": 18750,
      "total_flos": 0,
      "train_runtime": 2339.1211,
      "train_samples_per_second": 8.016
    }
  ],
  "max_steps": 18750,
  "num_train_epochs": 3,
  "total_flos": 0,
  "trial_name": null,
  "trial_params": null
}