{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029304029304029304,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029304029304029304,
      "grad_norm": 0.5861062407493591,
      "learning_rate": 2e-05,
      "loss": 6.6062,
      "step": 1
    },
    {
      "epoch": 0.0029304029304029304,
      "eval_loss": NaN,
      "eval_runtime": 6.3875,
      "eval_samples_per_second": 22.544,
      "eval_steps_per_second": 11.272,
      "step": 1
    },
    {
      "epoch": 0.005860805860805861,
      "grad_norm": 0.5407289862632751,
      "learning_rate": 4e-05,
      "loss": 7.0425,
      "step": 2
    },
    {
      "epoch": 0.008791208791208791,
      "grad_norm": 0.5113309025764465,
      "learning_rate": 6e-05,
      "loss": 7.0016,
      "step": 3
    },
    {
      "epoch": 0.008791208791208791,
      "eval_loss": NaN,
      "eval_runtime": 5.2033,
      "eval_samples_per_second": 27.675,
      "eval_steps_per_second": 13.837,
      "step": 3
    },
    {
      "epoch": 0.011721611721611722,
      "grad_norm": 0.679397463798523,
      "learning_rate": 8e-05,
      "loss": 7.1162,
      "step": 4
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 9.1051,
      "step": 5
    },
    {
      "epoch": 0.017582417582417582,
      "grad_norm": 0.5326178073883057,
      "learning_rate": 0.00012,
      "loss": 6.3593,
      "step": 6
    },
    {
      "epoch": 0.017582417582417582,
      "eval_loss": NaN,
      "eval_runtime": 5.2712,
      "eval_samples_per_second": 27.318,
      "eval_steps_per_second": 13.659,
      "step": 6
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 0.5934760570526123,
      "learning_rate": 0.00014,
      "loss": 5.707,
      "step": 7
    },
    {
      "epoch": 0.023443223443223443,
      "grad_norm": 0.6270977258682251,
      "learning_rate": 0.00016,
      "loss": 7.0855,
      "step": 8
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.5605975389480591,
      "learning_rate": 0.00018,
      "loss": 6.4283,
      "step": 9
    },
    {
      "epoch": 0.026373626373626374,
      "eval_loss": NaN,
      "eval_runtime": 5.2384,
      "eval_samples_per_second": 27.49,
      "eval_steps_per_second": 13.745,
      "step": 9
    },
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 0.7717577815055847,
      "learning_rate": 0.0002,
      "loss": 6.2534,
      "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": 1837066396631040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}