{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008861244834490692,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.816342180377454e-05,
      "grad_norm": 10.726434707641602,
      "learning_rate": 1e-05,
      "loss": 6.7949,
      "step": 1
    },
    {
      "epoch": 6.816342180377454e-05,
      "eval_loss": 7.433081150054932,
      "eval_runtime": 3610.8008,
      "eval_samples_per_second": 6.843,
      "eval_steps_per_second": 3.422,
      "step": 1
    },
    {
      "epoch": 0.0001363268436075491,
      "grad_norm": 13.176578521728516,
      "learning_rate": 2e-05,
      "loss": 7.2107,
      "step": 2
    },
    {
      "epoch": 0.00020449026541132366,
      "grad_norm": 12.275219917297363,
      "learning_rate": 3e-05,
      "loss": 7.3524,
      "step": 3
    },
    {
      "epoch": 0.0002726536872150982,
      "grad_norm": 13.537530899047852,
      "learning_rate": 4e-05,
      "loss": 7.3109,
      "step": 4
    },
    {
      "epoch": 0.00034081710901887275,
      "grad_norm": 16.737390518188477,
      "learning_rate": 5e-05,
      "loss": 7.1299,
      "step": 5
    },
    {
      "epoch": 0.0004089805308226473,
      "grad_norm": 16.55790138244629,
      "learning_rate": 6e-05,
      "loss": 5.7001,
      "step": 6
    },
    {
      "epoch": 0.00047714395262642183,
      "grad_norm": 12.568345069885254,
      "learning_rate": 7e-05,
      "loss": 4.4402,
      "step": 7
    },
    {
      "epoch": 0.0005453073744301963,
      "grad_norm": 14.332297325134277,
      "learning_rate": 8e-05,
      "loss": 1.9874,
      "step": 8
    },
    {
      "epoch": 0.000613470796233971,
      "grad_norm": 13.18618392944336,
      "learning_rate": 9e-05,
      "loss": 2.3065,
      "step": 9
    },
    {
      "epoch": 0.0006816342180377455,
      "grad_norm": 8.724907875061035,
      "learning_rate": 0.0001,
      "loss": 2.3028,
      "step": 10
    },
    {
      "epoch": 0.00074979763984152,
      "grad_norm": 17.249616622924805,
      "learning_rate": 9.98458666866564e-05,
      "loss": 1.5665,
      "step": 11
    },
    {
      "epoch": 0.0008179610616452946,
      "grad_norm": 12.082292556762695,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.1444,
      "step": 12
    },
    {
      "epoch": 0.0008861244834490692,
      "grad_norm": 6.85310697555542,
      "learning_rate": 9.861849601988383e-05,
      "loss": 1.3781,
      "step": 13
    },
    {
      "epoch": 0.0008861244834490692,
      "eval_loss": 1.087676763534546,
      "eval_runtime": 3614.8284,
      "eval_samples_per_second": 6.835,
      "eval_steps_per_second": 3.418,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.71562774902866e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}