{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004052028040034037,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.052028040034037e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.052028040034037e-05,
      "eval_loss": NaN,
      "eval_runtime": 588.2101,
      "eval_samples_per_second": 17.667,
      "eval_steps_per_second": 8.834,
      "step": 1
    },
    {
      "epoch": 8.104056080068074e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00012156084120102111,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00012156084120102111,
      "eval_loss": NaN,
      "eval_runtime": 587.4919,
      "eval_samples_per_second": 17.689,
      "eval_steps_per_second": 8.844,
      "step": 3
    },
    {
      "epoch": 0.00016208112160136148,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 23.762,
      "step": 4
    },
    {
      "epoch": 0.00020260140200170185,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00024312168240204221,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 11.9397,
      "step": 6
    },
    {
      "epoch": 0.00024312168240204221,
      "eval_loss": NaN,
      "eval_runtime": 895.3992,
      "eval_samples_per_second": 11.606,
      "eval_steps_per_second": 5.803,
      "step": 6
    },
    {
      "epoch": 0.0002836419628023826,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00032416224320272295,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 10.0377,
      "step": 8
    },
    {
      "epoch": 0.0003646825236030633,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003646825236030633,
      "eval_loss": NaN,
      "eval_runtime": 1012.6445,
      "eval_samples_per_second": 10.262,
      "eval_steps_per_second": 5.131,
      "step": 9
    },
    {
      "epoch": 0.0004052028040034037,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 10.3023,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3492879141961728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}