{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008601595595983055,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.601595595983055e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.601595595983055e-05,
      "eval_loss": NaN,
      "eval_runtime": 109.768,
      "eval_samples_per_second": 44.603,
      "eval_steps_per_second": 22.302,
      "step": 1
    },
    {
      "epoch": 0.0001720319119196611,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00025804786787949165,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00025804786787949165,
      "eval_loss": NaN,
      "eval_runtime": 109.2861,
      "eval_samples_per_second": 44.8,
      "eval_steps_per_second": 22.4,
      "step": 3
    },
    {
      "epoch": 0.0003440638238393222,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00043007977979915275,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005160957357589833,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005160957357589833,
      "eval_loss": NaN,
      "eval_runtime": 121.1485,
      "eval_samples_per_second": 40.413,
      "eval_steps_per_second": 20.207,
      "step": 6
    },
    {
      "epoch": 0.0006021116917188139,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006881276476786444,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.000774143603638475,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.000774143603638475,
      "eval_loss": NaN,
      "eval_runtime": 117.66,
      "eval_samples_per_second": 41.611,
      "eval_steps_per_second": 20.806,
      "step": 9
    },
    {
      "epoch": 0.0008601595595983055,
      "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": 53401532497920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}