{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1532816104005033,
  "global_step": 5500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 1.930104144824212e-05,
      "loss": 2.0398,
      "step": 500
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.860208289648424e-05,
      "loss": 1.7138,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.790312434472636e-05,
      "loss": 1.6022,
      "step": 1500
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.720416579296848e-05,
      "loss": 1.5263,
      "step": 2000
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.6505207241210597e-05,
      "loss": 1.4804,
      "step": 2500
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.5806248689452716e-05,
      "loss": 1.434,
      "step": 3000
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5107290137694836e-05,
      "loss": 1.4131,
      "step": 3500
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4408331585936954e-05,
      "loss": 1.3862,
      "step": 4000
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.3709373034179074e-05,
      "loss": 1.3675,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4010822772979736,
      "eval_runtime": 3146.6255,
      "eval_samples_per_second": 11.181,
      "eval_steps_per_second": 1.398,
      "step": 4769
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.3010414482421195e-05,
      "loss": 1.3461,
      "step": 5000
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.2311455930663311e-05,
      "loss": 1.3293,
      "step": 5500
    }
  ],
  "max_steps": 14307,
  "num_train_epochs": 3,
  "total_flos": 1436968817786880.0,
  "trial_name": null,
  "trial_params": null
}