{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.6153,
      "step": 25
    },
    {
      "epoch": 0.25,
      "eval_runtime": 216.6929,
      "eval_samples_per_second": 1.846,
      "eval_steps_per_second": 0.157,
      "step": 25
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 0.6312,
      "step": 50
    },
    {
      "epoch": 0.5,
      "eval_runtime": 217.0379,
      "eval_samples_per_second": 1.843,
      "eval_steps_per_second": 0.157,
      "step": 50
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 0.6063,
      "step": 75
    },
    {
      "epoch": 0.75,
      "eval_runtime": 216.6607,
      "eval_samples_per_second": 1.846,
      "eval_steps_per_second": 0.157,
      "step": 75
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 0.5707,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_runtime": 216.7207,
      "eval_samples_per_second": 1.846,
      "eval_steps_per_second": 0.157,
      "step": 100
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 0.4976,
      "step": 125
    },
    {
      "epoch": 1.25,
      "eval_runtime": 216.1906,
      "eval_samples_per_second": 1.85,
      "eval_steps_per_second": 0.157,
      "step": 125
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 0.5296,
      "step": 150
    },
    {
      "epoch": 1.5,
      "eval_runtime": 216.4796,
      "eval_samples_per_second": 1.848,
      "eval_steps_per_second": 0.157,
      "step": 150
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001,
      "loss": 0.5748,
      "step": 175
    },
    {
      "epoch": 1.75,
      "eval_runtime": 216.7074,
      "eval_samples_per_second": 1.846,
      "eval_steps_per_second": 0.157,
      "step": 175
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 0.5471,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_runtime": 216.7005,
      "eval_samples_per_second": 1.846,
      "eval_steps_per_second": 0.157,
      "step": 200
    }
  ],
  "logging_steps": 25,
  "max_steps": 200,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 3.32202164355072e+16,
  "trial_name": null,
  "trial_params": null
}