{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16339869281045752,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032679738562091504,
      "eval_loss": NaN,
      "eval_runtime": 6.0824,
      "eval_samples_per_second": 21.209,
      "eval_steps_per_second": 10.687,
      "step": 1
    },
    {
      "epoch": 0.016339869281045753,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.032679738562091505,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.032679738562091505,
      "eval_loss": NaN,
      "eval_runtime": 4.9856,
      "eval_samples_per_second": 25.874,
      "eval_steps_per_second": 13.038,
      "step": 10
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.06535947712418301,
      "eval_loss": NaN,
      "eval_runtime": 5.0444,
      "eval_samples_per_second": 25.573,
      "eval_steps_per_second": 12.886,
      "step": 20
    },
    {
      "epoch": 0.08169934640522876,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.09803921568627451,
      "eval_loss": NaN,
      "eval_runtime": 4.9802,
      "eval_samples_per_second": 25.903,
      "eval_steps_per_second": 13.052,
      "step": 30
    },
    {
      "epoch": 0.11437908496732026,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.13071895424836602,
      "eval_loss": NaN,
      "eval_runtime": 5.1061,
      "eval_samples_per_second": 25.264,
      "eval_steps_per_second": 12.73,
      "step": 40
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.16339869281045752,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.16339869281045752,
      "eval_loss": NaN,
      "eval_runtime": 5.0254,
      "eval_samples_per_second": 25.67,
      "eval_steps_per_second": 12.934,
      "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": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}