{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023487686580310274,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6975373160620544e-05,
      "eval_loss": NaN,
      "eval_runtime": 322.5942,
      "eval_samples_per_second": 27.787,
      "eval_steps_per_second": 13.894,
      "step": 1
    },
    {
      "epoch": 0.00023487686580310273,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00046975373160620547,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00046975373160620547,
      "eval_loss": NaN,
      "eval_runtime": 323.35,
      "eval_samples_per_second": 27.722,
      "eval_steps_per_second": 13.861,
      "step": 10
    },
    {
      "epoch": 0.0007046305974093081,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0009395074632124109,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0009395074632124109,
      "eval_loss": NaN,
      "eval_runtime": 320.6579,
      "eval_samples_per_second": 27.955,
      "eval_steps_per_second": 13.978,
      "step": 20
    },
    {
      "epoch": 0.0011743843290155137,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0014092611948186163,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0014092611948186163,
      "eval_loss": NaN,
      "eval_runtime": 322.0001,
      "eval_samples_per_second": 27.838,
      "eval_steps_per_second": 13.919,
      "step": 30
    },
    {
      "epoch": 0.001644138060621719,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0018790149264248219,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0018790149264248219,
      "eval_loss": NaN,
      "eval_runtime": 322.0911,
      "eval_samples_per_second": 27.831,
      "eval_steps_per_second": 13.915,
      "step": 40
    },
    {
      "epoch": 0.0021138917922279244,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0023487686580310274,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0023487686580310274,
      "eval_loss": NaN,
      "eval_runtime": 321.0016,
      "eval_samples_per_second": 27.925,
      "eval_steps_per_second": 13.963,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 652204549865472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}