{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0362154821186057,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036215482118605704,
      "grad_norm": 21.0379638671875,
      "learning_rate": 1e-05,
      "loss": 11.7509,
      "step": 1
    },
    {
      "epoch": 0.0036215482118605704,
      "eval_loss": 12.120037078857422,
      "eval_runtime": 55.513,
      "eval_samples_per_second": 8.376,
      "eval_steps_per_second": 4.197,
      "step": 1
    },
    {
      "epoch": 0.007243096423721141,
      "grad_norm": 17.719921112060547,
      "learning_rate": 2e-05,
      "loss": 11.0539,
      "step": 2
    },
    {
      "epoch": 0.010864644635581712,
      "grad_norm": 18.79608917236328,
      "learning_rate": 3e-05,
      "loss": 10.4219,
      "step": 3
    },
    {
      "epoch": 0.010864644635581712,
      "eval_loss": 11.643424034118652,
      "eval_runtime": 32.854,
      "eval_samples_per_second": 14.154,
      "eval_steps_per_second": 7.092,
      "step": 3
    },
    {
      "epoch": 0.014486192847442281,
      "grad_norm": 23.41111183166504,
      "learning_rate": 4e-05,
      "loss": 12.6428,
      "step": 4
    },
    {
      "epoch": 0.01810774105930285,
      "grad_norm": 21.269493103027344,
      "learning_rate": 5e-05,
      "loss": 12.0864,
      "step": 5
    },
    {
      "epoch": 0.021729289271163424,
      "grad_norm": 20.071081161499023,
      "learning_rate": 6e-05,
      "loss": 9.9225,
      "step": 6
    },
    {
      "epoch": 0.021729289271163424,
      "eval_loss": 9.42410945892334,
      "eval_runtime": 32.8466,
      "eval_samples_per_second": 14.157,
      "eval_steps_per_second": 7.094,
      "step": 6
    },
    {
      "epoch": 0.025350837483023993,
      "grad_norm": 17.764286041259766,
      "learning_rate": 7e-05,
      "loss": 9.3632,
      "step": 7
    },
    {
      "epoch": 0.028972385694884563,
      "grad_norm": 15.867535591125488,
      "learning_rate": 8e-05,
      "loss": 7.6773,
      "step": 8
    },
    {
      "epoch": 0.032593933906745136,
      "grad_norm": 16.599441528320312,
      "learning_rate": 9e-05,
      "loss": 6.5199,
      "step": 9
    },
    {
      "epoch": 0.032593933906745136,
      "eval_loss": NaN,
      "eval_runtime": 32.8587,
      "eval_samples_per_second": 14.151,
      "eval_steps_per_second": 7.091,
      "step": 9
    },
    {
      "epoch": 0.0362154821186057,
      "grad_norm": 16.777368545532227,
      "learning_rate": 0.0001,
      "loss": 6.1656,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.608477264838656e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}