{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008141112618724558,
  "eval_steps": 5,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020874647740319382,
      "eval_loss": NaN,
      "eval_runtime": 390.5679,
      "eval_samples_per_second": 5.167,
      "eval_steps_per_second": 2.583,
      "step": 1
    },
    {
      "epoch": 0.0006262394322095815,
      "grad_norm": NaN,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001043732387015969,
      "eval_loss": NaN,
      "eval_runtime": 390.6489,
      "eval_samples_per_second": 5.166,
      "eval_steps_per_second": 2.583,
      "step": 5
    },
    {
      "epoch": 0.001252478864419163,
      "grad_norm": NaN,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0018787182966287445,
      "grad_norm": NaN,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.002087464774031938,
      "eval_loss": NaN,
      "eval_runtime": 390.6793,
      "eval_samples_per_second": 5.165,
      "eval_steps_per_second": 2.583,
      "step": 10
    },
    {
      "epoch": 0.002504957728838326,
      "grad_norm": NaN,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0031311971610479073,
      "grad_norm": NaN,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0031311971610479073,
      "eval_loss": NaN,
      "eval_runtime": 390.7783,
      "eval_samples_per_second": 5.164,
      "eval_steps_per_second": 2.582,
      "step": 15
    },
    {
      "epoch": 0.003757436593257489,
      "grad_norm": NaN,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.004174929548063876,
      "eval_loss": NaN,
      "eval_runtime": 389.3155,
      "eval_samples_per_second": 5.183,
      "eval_steps_per_second": 2.592,
      "step": 20
    },
    {
      "epoch": 0.00438367602546707,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.005009915457676652,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0052186619350798455,
      "eval_loss": NaN,
      "eval_runtime": 390.9225,
      "eval_samples_per_second": 5.162,
      "eval_steps_per_second": 2.581,
      "step": 25
    },
    {
      "epoch": 0.005636154889886233,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0062623943220958146,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0062623943220958146,
      "eval_loss": NaN,
      "eval_runtime": 390.8344,
      "eval_samples_per_second": 5.163,
      "eval_steps_per_second": 2.582,
      "step": 30
    },
    {
      "epoch": 0.006888633754305396,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.007306126709111784,
      "eval_loss": NaN,
      "eval_runtime": 390.774,
      "eval_samples_per_second": 5.164,
      "eval_steps_per_second": 2.582,
      "step": 35
    },
    {
      "epoch": 0.007514873186514978,
      "grad_norm": NaN,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.008141112618724558,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 39
    }
  ],
  "logging_steps": 3,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 21,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0752844017696768e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}