{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002656512884087488,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.855042946958293e-05,
      "eval_loss": NaN,
      "eval_runtime": 101.0913,
      "eval_samples_per_second": 11.762,
      "eval_steps_per_second": 5.886,
      "step": 1
    },
    {
      "epoch": 0.0002656512884087488,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005313025768174976,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0007084034357566634,
      "eval_loss": NaN,
      "eval_runtime": 100.2405,
      "eval_samples_per_second": 11.861,
      "eval_steps_per_second": 5.936,
      "step": 8
    },
    {
      "epoch": 0.0007969538652262463,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0010626051536349952,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.001328256442043744,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0014168068715133268,
      "eval_loss": NaN,
      "eval_runtime": 100.3392,
      "eval_samples_per_second": 11.85,
      "eval_steps_per_second": 5.93,
      "step": 16
    },
    {
      "epoch": 0.0015939077304524926,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0018595590188612416,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0021252103072699905,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0021252103072699905,
      "eval_loss": NaN,
      "eval_runtime": 100.3687,
      "eval_samples_per_second": 11.846,
      "eval_steps_per_second": 5.928,
      "step": 24
    },
    {
      "epoch": 0.002390861595678739,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.002656512884087488,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 2782077313351680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}