{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7361963190184049,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024539877300613498,
      "eval_loss": NaN,
      "eval_runtime": 1.2003,
      "eval_samples_per_second": 14.996,
      "eval_steps_per_second": 7.498,
      "step": 1
    },
    {
      "epoch": 0.0736196319018405,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.12269938650306748,
      "eval_loss": NaN,
      "eval_runtime": 0.6506,
      "eval_samples_per_second": 27.665,
      "eval_steps_per_second": 13.832,
      "step": 5
    },
    {
      "epoch": 0.147239263803681,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.22085889570552147,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.24539877300613497,
      "eval_loss": NaN,
      "eval_runtime": 0.637,
      "eval_samples_per_second": 28.257,
      "eval_steps_per_second": 14.128,
      "step": 10
    },
    {
      "epoch": 0.294478527607362,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.36809815950920244,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.36809815950920244,
      "eval_loss": NaN,
      "eval_runtime": 0.6759,
      "eval_samples_per_second": 26.631,
      "eval_steps_per_second": 13.315,
      "step": 15
    },
    {
      "epoch": 0.44171779141104295,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.49079754601226994,
      "eval_loss": NaN,
      "eval_runtime": 0.6482,
      "eval_samples_per_second": 27.768,
      "eval_steps_per_second": 13.884,
      "step": 20
    },
    {
      "epoch": 0.5153374233128835,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.588957055214724,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.6134969325153374,
      "eval_loss": NaN,
      "eval_runtime": 0.6285,
      "eval_samples_per_second": 28.641,
      "eval_steps_per_second": 14.32,
      "step": 25
    },
    {
      "epoch": 0.6625766871165644,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.7361963190184049,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.7361963190184049,
      "eval_loss": NaN,
      "eval_runtime": 0.6462,
      "eval_samples_per_second": 27.857,
      "eval_steps_per_second": 13.928,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 671388692643840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}