{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.875,
  "eval_steps": 25,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31,
      "learning_rate": 2.3797595190380762e-05,
      "loss": 1.5268,
      "step": 25
    },
    {
      "epoch": 0.31,
      "eval_loss": 1.3393522500991821,
      "eval_runtime": 27.8357,
      "eval_samples_per_second": 5.748,
      "eval_steps_per_second": 0.719,
      "step": 25
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.2545090180360722e-05,
      "loss": 1.2384,
      "step": 50
    },
    {
      "epoch": 0.62,
      "eval_loss": 1.1721185445785522,
      "eval_runtime": 27.5856,
      "eval_samples_per_second": 5.8,
      "eval_steps_per_second": 0.725,
      "step": 50
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1292585170340683e-05,
      "loss": 1.1679,
      "step": 75
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.1183788776397705,
      "eval_runtime": 27.588,
      "eval_samples_per_second": 5.8,
      "eval_steps_per_second": 0.725,
      "step": 75
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.0040080160320643e-05,
      "loss": 1.0609,
      "step": 100
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.0915592908859253,
      "eval_runtime": 27.5872,
      "eval_samples_per_second": 5.8,
      "eval_steps_per_second": 0.725,
      "step": 100
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.87875751503006e-05,
      "loss": 1.0326,
      "step": 125
    },
    {
      "epoch": 1.56,
      "eval_loss": 1.0739314556121826,
      "eval_runtime": 27.6388,
      "eval_samples_per_second": 5.789,
      "eval_steps_per_second": 0.724,
      "step": 125
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.7535070140280564e-05,
      "loss": 1.0312,
      "step": 150
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.0567680597305298,
      "eval_runtime": 27.6528,
      "eval_samples_per_second": 5.786,
      "eval_steps_per_second": 0.723,
      "step": 150
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_train_epochs": 7,
  "save_steps": 25,
  "total_flos": 2.626920204415795e+16,
  "trial_name": null,
  "trial_params": null
}