{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004910747170181944,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.910747170181943e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.910747170181943e-05,
      "eval_loss": NaN,
      "eval_runtime": 1849.5145,
      "eval_samples_per_second": 4.636,
      "eval_steps_per_second": 2.318,
      "step": 1
    },
    {
      "epoch": 9.821494340363886e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 9.821494340363886e-05,
      "eval_loss": NaN,
      "eval_runtime": 1849.3843,
      "eval_samples_per_second": 4.637,
      "eval_steps_per_second": 2.319,
      "step": 2
    },
    {
      "epoch": 0.0001473224151054583,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001473224151054583,
      "eval_loss": NaN,
      "eval_runtime": 1849.3857,
      "eval_samples_per_second": 4.637,
      "eval_steps_per_second": 2.319,
      "step": 3
    },
    {
      "epoch": 0.00019642988680727773,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00019642988680727773,
      "eval_loss": NaN,
      "eval_runtime": 1849.4401,
      "eval_samples_per_second": 4.637,
      "eval_steps_per_second": 2.319,
      "step": 4
    },
    {
      "epoch": 0.0002455373585090972,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0002455373585090972,
      "eval_loss": NaN,
      "eval_runtime": 1849.3494,
      "eval_samples_per_second": 4.637,
      "eval_steps_per_second": 2.319,
      "step": 5
    },
    {
      "epoch": 0.0002946448302109166,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002946448302109166,
      "eval_loss": NaN,
      "eval_runtime": 1849.2839,
      "eval_samples_per_second": 4.637,
      "eval_steps_per_second": 2.319,
      "step": 6
    },
    {
      "epoch": 0.00034375230191273603,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00034375230191273603,
      "eval_loss": NaN,
      "eval_runtime": 1850.6351,
      "eval_samples_per_second": 4.634,
      "eval_steps_per_second": 2.317,
      "step": 7
    },
    {
      "epoch": 0.00039285977361455546,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00039285977361455546,
      "eval_loss": NaN,
      "eval_runtime": 1850.0971,
      "eval_samples_per_second": 4.635,
      "eval_steps_per_second": 2.318,
      "step": 8
    },
    {
      "epoch": 0.0004419672453163749,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0004419672453163749,
      "eval_loss": NaN,
      "eval_runtime": 1850.505,
      "eval_samples_per_second": 4.634,
      "eval_steps_per_second": 2.317,
      "step": 9
    },
    {
      "epoch": 0.0004910747170181944,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0004910747170181944,
      "eval_loss": NaN,
      "eval_runtime": 1850.448,
      "eval_samples_per_second": 4.634,
      "eval_steps_per_second": 2.317,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6514932543651840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}