{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017185821697099892,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 75.14957427978516,
      "learning_rate": 1e-05,
      "loss": 140.2881,
      "step": 1
    },
    {
      "epoch": 0.0034371643394199786,
      "eval_loss": 9.045337677001953,
      "eval_runtime": 43.9082,
      "eval_samples_per_second": 11.16,
      "eval_steps_per_second": 5.58,
      "step": 1
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 73.66410827636719,
      "learning_rate": 2e-05,
      "loss": 145.9325,
      "step": 2
    },
    {
      "epoch": 0.006874328678839957,
      "eval_loss": 8.90595531463623,
      "eval_runtime": 23.0643,
      "eval_samples_per_second": 21.245,
      "eval_steps_per_second": 10.622,
      "step": 2
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 89.51107788085938,
      "learning_rate": 3e-05,
      "loss": 143.0815,
      "step": 3
    },
    {
      "epoch": 0.013748657357679914,
      "grad_norm": 89.08412170410156,
      "learning_rate": 4e-05,
      "loss": 151.7754,
      "step": 4
    },
    {
      "epoch": 0.013748657357679914,
      "eval_loss": 8.762223243713379,
      "eval_runtime": 23.1431,
      "eval_samples_per_second": 21.173,
      "eval_steps_per_second": 10.586,
      "step": 4
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 78.39874267578125,
      "learning_rate": 5e-05,
      "loss": 134.3888,
      "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": 5700565975695360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}