{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 3.742615222930908,
      "learning_rate": 9.333333333333334e-06,
      "loss": 3.166,
      "step": 1
    },
    {
      "epoch": 0.2,
      "eval_loss": 2.9191343784332275,
      "eval_runtime": 0.0741,
      "eval_samples_per_second": 13.503,
      "eval_steps_per_second": 13.503,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.084916353225708,
      "learning_rate": 8.666666666666668e-06,
      "loss": 3.0915,
      "step": 2
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.025700807571411,
      "learning_rate": 7.333333333333333e-06,
      "loss": 3.0184,
      "step": 4
    },
    {
      "epoch": 1.2,
      "grad_norm": 2.60235857963562,
      "learning_rate": 6e-06,
      "loss": 3.0186,
      "step": 6
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.4947702884674072,
      "learning_rate": 4.666666666666667e-06,
      "loss": 2.9807,
      "step": 8
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.2621264457702637,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.0191,
      "step": 10
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.2841224670410156,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.0457,
      "step": 12
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.3721258640289307,
      "learning_rate": 6.666666666666667e-07,
      "loss": 2.8762,
      "step": 14
    }
  ],
  "logging_steps": 2,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 31344851681280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}