{
  "best_metric": 1.7561986446380615,
  "best_model_checkpoint": "outputs/checkpoint-92",
  "epoch": 1.9865047233468287,
  "eval_steps": 500,
  "global_step": 92,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4318488529014845,
      "grad_norm": 0.9230825901031494,
      "learning_rate": 6e-06,
      "loss": 2.3403,
      "step": 20
    },
    {
      "epoch": 0.863697705802969,
      "grad_norm": 0.656217098236084,
      "learning_rate": 1.2e-05,
      "loss": 2.2959,
      "step": 40
    },
    {
      "epoch": 0.9932523616734144,
      "eval_loss": 2.0449142456054688,
      "eval_runtime": 11.6816,
      "eval_samples_per_second": 31.845,
      "eval_steps_per_second": 4.023,
      "step": 46
    },
    {
      "epoch": 1.2955465587044535,
      "grad_norm": 0.5638908743858337,
      "learning_rate": 1.8e-05,
      "loss": 2.1979,
      "step": 60
    },
    {
      "epoch": 1.7273954116059378,
      "grad_norm": 0.51393723487854,
      "learning_rate": 2.4e-05,
      "loss": 2.0118,
      "step": 80
    },
    {
      "epoch": 1.9865047233468287,
      "eval_loss": 1.7561986446380615,
      "eval_runtime": 11.7086,
      "eval_samples_per_second": 31.772,
      "eval_steps_per_second": 4.014,
      "step": 92
    }
  ],
  "logging_steps": 20,
  "max_steps": 1380,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 8178939446575104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}