{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0192,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 1.9328099489212036,
      "learning_rate": 0.00019289767198167916,
      "loss": 3.0748,
      "step": 10
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.098536729812622,
      "learning_rate": 0.00016051742151937655,
      "loss": 0.8299,
      "step": 20
    },
    {
      "epoch": 0.0096,
      "grad_norm": 1.0885381698608398,
      "learning_rate": 0.00011081190184239419,
      "loss": 0.5157,
      "step": 30
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.6997808814048767,
      "learning_rate": 5.801108984397354e-05,
      "loss": 0.3862,
      "step": 40
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.5410671234130859,
      "learning_rate": 1.7231100184310956e-05,
      "loss": 0.3463,
      "step": 50
    },
    {
      "epoch": 0.0192,
      "grad_norm": 0.5440347790718079,
      "learning_rate": 1.4665861488761813e-07,
      "loss": 0.3462,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6940287542200832e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}