{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009845103701758991,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.281701233919664e-05,
      "eval_loss": NaN,
      "eval_runtime": 478.7995,
      "eval_samples_per_second": 26.798,
      "eval_steps_per_second": 13.4,
      "step": 1
    },
    {
      "epoch": 9.845103701758992e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001640850616959832,
      "eval_loss": NaN,
      "eval_runtime": 493.4902,
      "eval_samples_per_second": 26.001,
      "eval_steps_per_second": 13.001,
      "step": 5
    },
    {
      "epoch": 0.00019690207403517984,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002953531110527698,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003281701233919664,
      "eval_loss": NaN,
      "eval_runtime": 505.9582,
      "eval_samples_per_second": 25.36,
      "eval_steps_per_second": 12.681,
      "step": 10
    },
    {
      "epoch": 0.00039380414807035967,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0004922551850879496,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004922551850879496,
      "eval_loss": NaN,
      "eval_runtime": 555.0315,
      "eval_samples_per_second": 23.118,
      "eval_steps_per_second": 11.56,
      "step": 15
    },
    {
      "epoch": 0.0005907062221055396,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0006563402467839327,
      "eval_loss": NaN,
      "eval_runtime": 553.7825,
      "eval_samples_per_second": 23.17,
      "eval_steps_per_second": 11.586,
      "step": 20
    },
    {
      "epoch": 0.0006891572591231294,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0007876082961407193,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.000820425308479916,
      "eval_loss": NaN,
      "eval_runtime": 499.4001,
      "eval_samples_per_second": 25.693,
      "eval_steps_per_second": 12.847,
      "step": 25
    },
    {
      "epoch": 0.0008860593331583092,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0009845103701758991,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0009845103701758991,
      "eval_loss": NaN,
      "eval_runtime": 496.3978,
      "eval_samples_per_second": 25.848,
      "eval_steps_per_second": 12.925,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 163805826908160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}