{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011922503725782414,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002384500745156483,
      "grad_norm": 12.508318901062012,
      "learning_rate": 1e-05,
      "loss": 11.1816,
      "step": 1
    },
    {
      "epoch": 0.002384500745156483,
      "eval_loss": 11.54417896270752,
      "eval_runtime": 135.6428,
      "eval_samples_per_second": 5.212,
      "eval_steps_per_second": 2.61,
      "step": 1
    },
    {
      "epoch": 0.004769001490312966,
      "grad_norm": 12.505332946777344,
      "learning_rate": 2e-05,
      "loss": 11.8075,
      "step": 2
    },
    {
      "epoch": 0.004769001490312966,
      "eval_loss": 11.412431716918945,
      "eval_runtime": 7.2668,
      "eval_samples_per_second": 97.292,
      "eval_steps_per_second": 48.715,
      "step": 2
    },
    {
      "epoch": 0.007153502235469449,
      "grad_norm": 11.806145668029785,
      "learning_rate": 3e-05,
      "loss": 11.5533,
      "step": 3
    },
    {
      "epoch": 0.009538002980625931,
      "grad_norm": 11.895707130432129,
      "learning_rate": 4e-05,
      "loss": 11.2312,
      "step": 4
    },
    {
      "epoch": 0.009538002980625931,
      "eval_loss": 11.10891342163086,
      "eval_runtime": 7.268,
      "eval_samples_per_second": 97.276,
      "eval_steps_per_second": 48.707,
      "step": 4
    },
    {
      "epoch": 0.011922503725782414,
      "grad_norm": 13.141823768615723,
      "learning_rate": 5e-05,
      "loss": 10.8886,
      "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": 991192531599360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}