{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00035904386618435105,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.590438661843511e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.590438661843511e-05,
      "eval_loss": NaN,
      "eval_runtime": 249.6331,
      "eval_samples_per_second": 46.977,
      "eval_steps_per_second": 23.49,
      "step": 1
    },
    {
      "epoch": 7.180877323687022e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00010771315985530532,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00010771315985530532,
      "eval_loss": NaN,
      "eval_runtime": 248.7971,
      "eval_samples_per_second": 47.135,
      "eval_steps_per_second": 23.569,
      "step": 3
    },
    {
      "epoch": 0.00014361754647374044,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00017952193309217552,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00021542631971061064,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00021542631971061064,
      "eval_loss": NaN,
      "eval_runtime": 248.0834,
      "eval_samples_per_second": 47.27,
      "eval_steps_per_second": 23.637,
      "step": 6
    },
    {
      "epoch": 0.00025133070632904573,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00028723509294748087,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00032313947956591596,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00032313947956591596,
      "eval_loss": NaN,
      "eval_runtime": 248.5992,
      "eval_samples_per_second": 47.172,
      "eval_steps_per_second": 23.588,
      "step": 9
    },
    {
      "epoch": 0.00035904386618435105,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 144687016181760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}