{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008696597456245243,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017393194912490488,
      "grad_norm": 46.735469818115234,
      "learning_rate": 1e-05,
      "loss": 46.8325,
      "step": 1
    },
    {
      "epoch": 0.0017393194912490488,
      "eval_loss": 3.044590711593628,
      "eval_runtime": 68.8579,
      "eval_samples_per_second": 14.072,
      "eval_steps_per_second": 7.043,
      "step": 1
    },
    {
      "epoch": 0.0034786389824980977,
      "grad_norm": 50.22098159790039,
      "learning_rate": 2e-05,
      "loss": 47.4681,
      "step": 2
    },
    {
      "epoch": 0.0034786389824980977,
      "eval_loss": 2.909543752670288,
      "eval_runtime": 48.5567,
      "eval_samples_per_second": 19.956,
      "eval_steps_per_second": 9.988,
      "step": 2
    },
    {
      "epoch": 0.0052179584737471465,
      "grad_norm": 46.65412902832031,
      "learning_rate": 3e-05,
      "loss": 47.9627,
      "step": 3
    },
    {
      "epoch": 0.006957277964996195,
      "grad_norm": 53.88131332397461,
      "learning_rate": 4e-05,
      "loss": 51.0075,
      "step": 4
    },
    {
      "epoch": 0.006957277964996195,
      "eval_loss": 2.7896740436553955,
      "eval_runtime": 48.5469,
      "eval_samples_per_second": 19.96,
      "eval_steps_per_second": 9.99,
      "step": 4
    },
    {
      "epoch": 0.008696597456245243,
      "grad_norm": 61.024837493896484,
      "learning_rate": 5e-05,
      "loss": 51.9992,
      "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": 6514932543651840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}