{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3919,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "grad_norm": 1.9183778762817383,
      "learning_rate": 3.188775510204082e-05,
      "loss": 2.8223,
      "step": 500
    },
    {
      "epoch": 0.26,
      "grad_norm": 2.046781539916992,
      "learning_rate": 4.655502392344498e-05,
      "loss": 1.5043,
      "step": 1000
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.9903734922409058,
      "learning_rate": 3.8580542264752795e-05,
      "loss": 1.4817,
      "step": 1500
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.7653305530548096,
      "learning_rate": 3.060606060606061e-05,
      "loss": 1.4671,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.9060845375061035,
      "learning_rate": 2.2631578947368423e-05,
      "loss": 1.4637,
      "step": 2500
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.784713625907898,
      "learning_rate": 1.4657097288676236e-05,
      "loss": 1.4588,
      "step": 3000
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.737605094909668,
      "learning_rate": 6.6826156299840516e-06,
      "loss": 1.4615,
      "step": 3500
    },
    {
      "epoch": 1.0,
      "step": 3919,
      "total_flos": 102290970089472.0,
      "train_loss": 1.643041113804542,
      "train_runtime": 148.4875,
      "train_samples_per_second": 211.122,
      "train_steps_per_second": 26.393
    }
  ],
  "logging_steps": 500,
  "max_steps": 3919,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 102290970089472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}