{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01126800239445051,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005634001197225254,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 172.3552,
      "step": 1
    },
    {
      "epoch": 0.0005634001197225254,
      "eval_loss": NaN,
      "eval_runtime": 123.8303,
      "eval_samples_per_second": 24.146,
      "eval_steps_per_second": 12.073,
      "step": 1
    },
    {
      "epoch": 0.0011268002394450509,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0016902003591675763,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0022536004788901018,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0028170005986126274,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0028170005986126274,
      "eval_loss": NaN,
      "eval_runtime": 39.6353,
      "eval_samples_per_second": 75.438,
      "eval_steps_per_second": 37.719,
      "step": 5
    },
    {
      "epoch": 0.0033804007183351526,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003943800838057678,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0045072009577802035,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.005070601077502729,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.005634001197225255,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005634001197225255,
      "eval_loss": NaN,
      "eval_runtime": 39.6059,
      "eval_samples_per_second": 75.494,
      "eval_steps_per_second": 37.747,
      "step": 10
    },
    {
      "epoch": 0.00619740131694778,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.006760801436670305,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.007324201556392831,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007887601676115356,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.008451001795837881,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.008451001795837881,
      "eval_loss": NaN,
      "eval_runtime": 39.6134,
      "eval_samples_per_second": 75.479,
      "eval_steps_per_second": 37.74,
      "step": 15
    },
    {
      "epoch": 0.009014401915560407,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.009577802035282933,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.010141202155005458,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.010704602274727984,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.01126800239445051,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01126800239445051,
      "eval_loss": NaN,
      "eval_runtime": 39.6009,
      "eval_samples_per_second": 75.503,
      "eval_steps_per_second": 37.752,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1183715843112960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}