{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015067426734637502,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0224755782125007e-05,
      "eval_loss": NaN,
      "eval_runtime": 1843.0578,
      "eval_samples_per_second": 4.549,
      "eval_steps_per_second": 2.274,
      "step": 1
    },
    {
      "epoch": 0.00015067426734637502,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00025112377891062503,
      "eval_loss": NaN,
      "eval_runtime": 1842.8599,
      "eval_samples_per_second": 4.549,
      "eval_steps_per_second": 2.275,
      "step": 5
    },
    {
      "epoch": 0.00030134853469275004,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00045202280203912506,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0005022475578212501,
      "eval_loss": NaN,
      "eval_runtime": 1845.4276,
      "eval_samples_per_second": 4.543,
      "eval_steps_per_second": 2.272,
      "step": 10
    },
    {
      "epoch": 0.0006026970693855001,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0007533713367318751,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0007533713367318751,
      "eval_loss": NaN,
      "eval_runtime": 1843.8004,
      "eval_samples_per_second": 4.547,
      "eval_steps_per_second": 2.274,
      "step": 15
    },
    {
      "epoch": 0.0009040456040782501,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0010044951156425001,
      "eval_loss": NaN,
      "eval_runtime": 1843.9752,
      "eval_samples_per_second": 4.547,
      "eval_steps_per_second": 2.273,
      "step": 20
    },
    {
      "epoch": 0.0010547198714246251,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0012053941387710002,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0012556188945531252,
      "eval_loss": NaN,
      "eval_runtime": 1844.8536,
      "eval_samples_per_second": 4.545,
      "eval_steps_per_second": 2.272,
      "step": 25
    },
    {
      "epoch": 0.0013560684061173752,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0015067426734637502,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0015067426734637502,
      "eval_loss": NaN,
      "eval_runtime": 1845.4494,
      "eval_samples_per_second": 4.543,
      "eval_steps_per_second": 2.272,
      "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": 1.4202887328497664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}