{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.064516129032258,
  "eval_steps": 25,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12903225806451613,
      "grad_norm": NaN,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.12903225806451613,
      "eval_loss": NaN,
      "eval_runtime": 0.7266,
      "eval_samples_per_second": 144.511,
      "eval_steps_per_second": 19.268,
      "step": 1
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": NaN,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": NaN,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": NaN,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": NaN,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": NaN,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": NaN,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": NaN,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8899258409222144e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}