{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025948751216347713,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0051897502432695424,
      "grad_norm": 125.67073822021484,
      "learning_rate": 1e-05,
      "loss": 174.2459,
      "step": 1
    },
    {
      "epoch": 0.0051897502432695424,
      "eval_loss": NaN,
      "eval_runtime": 124.1633,
      "eval_samples_per_second": 2.618,
      "eval_steps_per_second": 1.313,
      "step": 1
    },
    {
      "epoch": 0.010379500486539085,
      "grad_norm": 112.84034729003906,
      "learning_rate": 2e-05,
      "loss": 174.9422,
      "step": 2
    },
    {
      "epoch": 0.010379500486539085,
      "eval_loss": NaN,
      "eval_runtime": 24.315,
      "eval_samples_per_second": 13.366,
      "eval_steps_per_second": 6.704,
      "step": 2
    },
    {
      "epoch": 0.015569250729808628,
      "grad_norm": 115.78556060791016,
      "learning_rate": 3e-05,
      "loss": 171.2719,
      "step": 3
    },
    {
      "epoch": 0.02075900097307817,
      "grad_norm": 119.48433685302734,
      "learning_rate": 4e-05,
      "loss": 170.3447,
      "step": 4
    },
    {
      "epoch": 0.02075900097307817,
      "eval_loss": NaN,
      "eval_runtime": 25.153,
      "eval_samples_per_second": 12.921,
      "eval_steps_per_second": 6.48,
      "step": 4
    },
    {
      "epoch": 0.025948751216347713,
      "grad_norm": 119.24961853027344,
      "learning_rate": 5e-05,
      "loss": 167.2139,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3257498484080640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}