{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007457677679170706,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014915355358341412,
      "grad_norm": 19.76797103881836,
      "learning_rate": 1e-05,
      "loss": 80.9886,
      "step": 1
    },
    {
      "epoch": 0.00014915355358341412,
      "eval_loss": 5.019608974456787,
      "eval_runtime": 275.7886,
      "eval_samples_per_second": 40.944,
      "eval_steps_per_second": 20.472,
      "step": 1
    },
    {
      "epoch": 0.00029830710716682824,
      "grad_norm": 18.787935256958008,
      "learning_rate": 2e-05,
      "loss": 77.98,
      "step": 2
    },
    {
      "epoch": 0.00029830710716682824,
      "eval_loss": 4.934010982513428,
      "eval_runtime": 284.0111,
      "eval_samples_per_second": 39.759,
      "eval_steps_per_second": 19.88,
      "step": 2
    },
    {
      "epoch": 0.0004474606607502424,
      "grad_norm": 18.34357261657715,
      "learning_rate": 3e-05,
      "loss": 78.6641,
      "step": 3
    },
    {
      "epoch": 0.0005966142143336565,
      "grad_norm": 21.512243270874023,
      "learning_rate": 4e-05,
      "loss": 80.9957,
      "step": 4
    },
    {
      "epoch": 0.0005966142143336565,
      "eval_loss": 4.881850719451904,
      "eval_runtime": 412.7708,
      "eval_samples_per_second": 27.357,
      "eval_steps_per_second": 13.678,
      "step": 4
    },
    {
      "epoch": 0.0007457677679170706,
      "grad_norm": 22.670307159423828,
      "learning_rate": 5e-05,
      "loss": 77.9762,
      "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
}