{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00595847686435155,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002979238432175775,
      "grad_norm": 0.013859261758625507,
      "learning_rate": 1e-05,
      "loss": 11.9245,
      "step": 1
    },
    {
      "epoch": 0.0002979238432175775,
      "eval_loss": 11.930392265319824,
      "eval_runtime": 15.0362,
      "eval_samples_per_second": 376.027,
      "eval_steps_per_second": 188.013,
      "step": 1
    },
    {
      "epoch": 0.000595847686435155,
      "grad_norm": 0.013614109717309475,
      "learning_rate": 2e-05,
      "loss": 11.9318,
      "step": 2
    },
    {
      "epoch": 0.0008937715296527325,
      "grad_norm": 0.013719133101403713,
      "learning_rate": 3e-05,
      "loss": 11.9329,
      "step": 3
    },
    {
      "epoch": 0.00119169537287031,
      "grad_norm": 0.014367117546498775,
      "learning_rate": 4e-05,
      "loss": 11.9325,
      "step": 4
    },
    {
      "epoch": 0.0014896192160878876,
      "grad_norm": 0.013640515506267548,
      "learning_rate": 5e-05,
      "loss": 11.9285,
      "step": 5
    },
    {
      "epoch": 0.0014896192160878876,
      "eval_loss": 11.930379867553711,
      "eval_runtime": 7.6643,
      "eval_samples_per_second": 737.707,
      "eval_steps_per_second": 368.854,
      "step": 5
    },
    {
      "epoch": 0.001787543059305465,
      "grad_norm": 0.013276793994009495,
      "learning_rate": 6e-05,
      "loss": 11.9311,
      "step": 6
    },
    {
      "epoch": 0.0020854669025230426,
      "grad_norm": 0.014673787169158459,
      "learning_rate": 7e-05,
      "loss": 11.9264,
      "step": 7
    },
    {
      "epoch": 0.00238339074574062,
      "grad_norm": 0.014198667369782925,
      "learning_rate": 8e-05,
      "loss": 11.9318,
      "step": 8
    },
    {
      "epoch": 0.0026813145889581975,
      "grad_norm": 0.013602347113192081,
      "learning_rate": 9e-05,
      "loss": 11.9322,
      "step": 9
    },
    {
      "epoch": 0.002979238432175775,
      "grad_norm": 0.012240378186106682,
      "learning_rate": 0.0001,
      "loss": 11.933,
      "step": 10
    },
    {
      "epoch": 0.002979238432175775,
      "eval_loss": 11.930337905883789,
      "eval_runtime": 7.9261,
      "eval_samples_per_second": 713.34,
      "eval_steps_per_second": 356.67,
      "step": 10
    },
    {
      "epoch": 0.003277162275393353,
      "grad_norm": 0.014199422672390938,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9283,
      "step": 11
    },
    {
      "epoch": 0.00357508611861093,
      "grad_norm": 0.01845669187605381,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9266,
      "step": 12
    },
    {
      "epoch": 0.0038730099618285076,
      "grad_norm": 0.01380027923732996,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.9286,
      "step": 13
    },
    {
      "epoch": 0.004170933805046085,
      "grad_norm": 0.014826415106654167,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9277,
      "step": 14
    },
    {
      "epoch": 0.004468857648263663,
      "grad_norm": 0.012456392869353294,
      "learning_rate": 5e-05,
      "loss": 11.934,
      "step": 15
    },
    {
      "epoch": 0.004468857648263663,
      "eval_loss": 11.930290222167969,
      "eval_runtime": 7.7915,
      "eval_samples_per_second": 725.664,
      "eval_steps_per_second": 362.832,
      "step": 15
    },
    {
      "epoch": 0.00476678149148124,
      "grad_norm": 0.018006734549999237,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.9274,
      "step": 16
    },
    {
      "epoch": 0.005064705334698817,
      "grad_norm": 0.013570823706686497,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9304,
      "step": 17
    },
    {
      "epoch": 0.005362629177916395,
      "grad_norm": 0.012760688550770283,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.9299,
      "step": 18
    },
    {
      "epoch": 0.005660553021133973,
      "grad_norm": 0.014291306026279926,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.9341,
      "step": 19
    },
    {
      "epoch": 0.00595847686435155,
      "grad_norm": 0.01459888182580471,
      "learning_rate": 0.0,
      "loss": 11.9277,
      "step": 20
    },
    {
      "epoch": 0.00595847686435155,
      "eval_loss": 11.930275917053223,
      "eval_runtime": 7.8619,
      "eval_samples_per_second": 719.166,
      "eval_steps_per_second": 359.583,
      "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": 9452912640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}