{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004220121539500338,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.440243079000676e-05,
      "eval_loss": NaN,
      "eval_runtime": 164.277,
      "eval_samples_per_second": 30.369,
      "eval_steps_per_second": 15.188,
      "step": 1
    },
    {
      "epoch": 0.00042201215395003375,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008440243079000675,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008440243079000675,
      "eval_loss": NaN,
      "eval_runtime": 163.4663,
      "eval_samples_per_second": 30.52,
      "eval_steps_per_second": 15.263,
      "step": 10
    },
    {
      "epoch": 0.0012660364618501012,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.001688048615800135,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.001688048615800135,
      "eval_loss": NaN,
      "eval_runtime": 163.6572,
      "eval_samples_per_second": 30.484,
      "eval_steps_per_second": 15.245,
      "step": 20
    },
    {
      "epoch": 0.002110060769750169,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0025320729237002025,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0025320729237002025,
      "eval_loss": NaN,
      "eval_runtime": 163.3284,
      "eval_samples_per_second": 30.546,
      "eval_steps_per_second": 15.276,
      "step": 30
    },
    {
      "epoch": 0.0029540850776502365,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.00337609723160027,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00337609723160027,
      "eval_loss": NaN,
      "eval_runtime": 164.307,
      "eval_samples_per_second": 30.364,
      "eval_steps_per_second": 15.185,
      "step": 40
    },
    {
      "epoch": 0.003798109385550304,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.004220121539500338,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.004220121539500338,
      "eval_loss": NaN,
      "eval_runtime": 163.0274,
      "eval_samples_per_second": 30.602,
      "eval_steps_per_second": 15.304,
      "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": 445190819020800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}