{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.858585858585858,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.85,
      "learning_rate": 0.0001,
      "loss": 3.5767,
      "step": 300
    },
    {
      "epoch": 8.08,
      "eval_loss": 4.96760368347168,
      "eval_runtime": 17.5269,
      "eval_samples_per_second": 202.717,
      "eval_steps_per_second": 12.723,
      "step": 500
    },
    {
      "epoch": 9.7,
      "learning_rate": 9.08098456178111e-05,
      "loss": 1.8485,
      "step": 600
    },
    {
      "epoch": 14.55,
      "learning_rate": 6.661773997398298e-05,
      "loss": 0.7719,
      "step": 900
    },
    {
      "epoch": 16.16,
      "eval_loss": 6.302948951721191,
      "eval_runtime": 17.531,
      "eval_samples_per_second": 202.67,
      "eval_steps_per_second": 12.72,
      "step": 1000
    },
    {
      "epoch": 19.39,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.3681,
      "step": 1200
    },
    {
      "epoch": 24.24,
      "learning_rate": 1.1045971273716477e-05,
      "loss": 0.2404,
      "step": 1500
    },
    {
      "epoch": 24.24,
      "eval_loss": 6.584695816040039,
      "eval_runtime": 17.4639,
      "eval_samples_per_second": 203.448,
      "eval_steps_per_second": 12.769,
      "step": 1500
    }
  ],
  "logging_steps": 300,
  "max_steps": 1830,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 800,
  "total_flos": 1.18685046571008e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}