{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008103125780769932,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": NaN,
      "eval_runtime": 685.9571,
      "eval_samples_per_second": 22.726,
      "eval_steps_per_second": 11.364,
      "step": 1
    },
    {
      "epoch": 8.103125780769932e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00013505209634616554,
      "eval_loss": NaN,
      "eval_runtime": 684.5474,
      "eval_samples_per_second": 22.773,
      "eval_steps_per_second": 11.387,
      "step": 5
    },
    {
      "epoch": 0.00016206251561539864,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00024309377342309797,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002701041926923311,
      "eval_loss": NaN,
      "eval_runtime": 684.6681,
      "eval_samples_per_second": 22.769,
      "eval_steps_per_second": 11.385,
      "step": 10
    },
    {
      "epoch": 0.0003241250312307973,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0004051562890384966,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004051562890384966,
      "eval_loss": NaN,
      "eval_runtime": 684.9373,
      "eval_samples_per_second": 22.76,
      "eval_steps_per_second": 11.381,
      "step": 15
    },
    {
      "epoch": 0.00048618754684619594,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005402083853846621,
      "eval_loss": NaN,
      "eval_runtime": 684.8772,
      "eval_samples_per_second": 22.762,
      "eval_steps_per_second": 11.382,
      "step": 20
    },
    {
      "epoch": 0.0005672188046538952,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0006482500624615946,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0006752604817308277,
      "eval_loss": NaN,
      "eval_runtime": 684.9186,
      "eval_samples_per_second": 22.76,
      "eval_steps_per_second": 11.381,
      "step": 25
    },
    {
      "epoch": 0.0007292813202692939,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0008103125780769932,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0008103125780769932,
      "eval_loss": NaN,
      "eval_runtime": 685.4354,
      "eval_samples_per_second": 22.743,
      "eval_steps_per_second": 11.372,
      "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": 3341408639385600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}