{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010790396547073105,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002158079309414621,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 894.8315,
      "step": 1
    },
    {
      "epoch": 0.002158079309414621,
      "eval_loss": NaN,
      "eval_runtime": 30.7107,
      "eval_samples_per_second": 25.431,
      "eval_steps_per_second": 12.732,
      "step": 1
    },
    {
      "epoch": 0.004316158618829242,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004316158618829242,
      "eval_loss": NaN,
      "eval_runtime": 3.2412,
      "eval_samples_per_second": 240.961,
      "eval_steps_per_second": 120.635,
      "step": 2
    },
    {
      "epoch": 0.006474237928243863,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.008632317237658484,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.008632317237658484,
      "eval_loss": NaN,
      "eval_runtime": 3.2769,
      "eval_samples_per_second": 238.333,
      "eval_steps_per_second": 119.319,
      "step": 4
    },
    {
      "epoch": 0.010790396547073105,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "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": 2462220288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}