{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004730928444707274,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "grad_norm": 1.51093554450199e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": 11.5,
      "eval_runtime": 4.5964,
      "eval_samples_per_second": 193.628,
      "eval_steps_per_second": 96.814,
      "step": 1
    },
    {
      "epoch": 0.0009461856889414548,
      "grad_norm": 3.0726423574378714e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0014192785334121822,
      "grad_norm": 2.4989127268781886e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0014192785334121822,
      "eval_loss": 11.5,
      "eval_runtime": 4.5352,
      "eval_samples_per_second": 196.242,
      "eval_steps_per_second": 98.121,
      "step": 3
    },
    {
      "epoch": 0.0018923713778829095,
      "grad_norm": 1.1158717825310305e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.002365464222353637,
      "grad_norm": 1.5912713934085332e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0028385570668243644,
      "grad_norm": 1.4793805348745082e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0028385570668243644,
      "eval_loss": 11.5,
      "eval_runtime": 4.6893,
      "eval_samples_per_second": 189.793,
      "eval_steps_per_second": 94.897,
      "step": 6
    },
    {
      "epoch": 0.0033116499112950917,
      "grad_norm": 1.9216367945773527e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.003784742755765819,
      "grad_norm": 1.4391673175850883e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.004257835600236547,
      "grad_norm": 2.7846914235851727e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.004257835600236547,
      "eval_loss": 11.5,
      "eval_runtime": 4.5833,
      "eval_samples_per_second": 194.185,
      "eval_steps_per_second": 97.092,
      "step": 9
    },
    {
      "epoch": 0.004730928444707274,
      "grad_norm": 2.749868690443691e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "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": 199228784640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}