{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013427042903598028,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006713521451799014,
      "grad_norm": 0.3204704225063324,
      "learning_rate": 1e-05,
      "loss": 0.2534,
      "step": 1
    },
    {
      "epoch": 0.0006713521451799014,
      "eval_loss": 0.34151291847229004,
      "eval_runtime": 410.3846,
      "eval_samples_per_second": 24.453,
      "eval_steps_per_second": 6.114,
      "step": 1
    },
    {
      "epoch": 0.0013427042903598027,
      "grad_norm": 0.36491429805755615,
      "learning_rate": 2e-05,
      "loss": 0.2745,
      "step": 2
    },
    {
      "epoch": 0.0020140564355397043,
      "grad_norm": 0.3138849139213562,
      "learning_rate": 3e-05,
      "loss": 0.2594,
      "step": 3
    },
    {
      "epoch": 0.0026854085807196055,
      "grad_norm": 0.3455110788345337,
      "learning_rate": 4e-05,
      "loss": 0.2766,
      "step": 4
    },
    {
      "epoch": 0.003356760725899507,
      "grad_norm": 0.3628172278404236,
      "learning_rate": 5e-05,
      "loss": 0.2775,
      "step": 5
    },
    {
      "epoch": 0.003356760725899507,
      "eval_loss": 0.31641557812690735,
      "eval_runtime": 408.4107,
      "eval_samples_per_second": 24.571,
      "eval_steps_per_second": 6.143,
      "step": 5
    },
    {
      "epoch": 0.004028112871079409,
      "grad_norm": 0.3577265739440918,
      "learning_rate": 6e-05,
      "loss": 0.2759,
      "step": 6
    },
    {
      "epoch": 0.00469946501625931,
      "grad_norm": 0.3720860183238983,
      "learning_rate": 7e-05,
      "loss": 0.2451,
      "step": 7
    },
    {
      "epoch": 0.005370817161439211,
      "grad_norm": 0.38583680987358093,
      "learning_rate": 8e-05,
      "loss": 0.202,
      "step": 8
    },
    {
      "epoch": 0.006042169306619113,
      "grad_norm": 0.43849220871925354,
      "learning_rate": 9e-05,
      "loss": 0.1772,
      "step": 9
    },
    {
      "epoch": 0.006713521451799014,
      "grad_norm": 0.4130704402923584,
      "learning_rate": 0.0001,
      "loss": 0.1453,
      "step": 10
    },
    {
      "epoch": 0.006713521451799014,
      "eval_loss": 0.1879773885011673,
      "eval_runtime": 408.4313,
      "eval_samples_per_second": 24.57,
      "eval_steps_per_second": 6.143,
      "step": 10
    },
    {
      "epoch": 0.007384873596978915,
      "grad_norm": 0.4552391469478607,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1409,
      "step": 11
    },
    {
      "epoch": 0.008056225742158817,
      "grad_norm": 0.50043123960495,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1259,
      "step": 12
    },
    {
      "epoch": 0.008727577887338718,
      "grad_norm": 0.44272345304489136,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0926,
      "step": 13
    },
    {
      "epoch": 0.00939893003251862,
      "grad_norm": 0.44065895676612854,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0806,
      "step": 14
    },
    {
      "epoch": 0.01007028217769852,
      "grad_norm": 0.3156546950340271,
      "learning_rate": 5e-05,
      "loss": 0.0583,
      "step": 15
    },
    {
      "epoch": 0.01007028217769852,
      "eval_loss": 0.06674635410308838,
      "eval_runtime": 408.516,
      "eval_samples_per_second": 24.565,
      "eval_steps_per_second": 6.142,
      "step": 15
    },
    {
      "epoch": 0.010741634322878422,
      "grad_norm": 0.23266065120697021,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0488,
      "step": 16
    },
    {
      "epoch": 0.011412986468058323,
      "grad_norm": 0.2226492166519165,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0493,
      "step": 17
    },
    {
      "epoch": 0.012084338613238226,
      "grad_norm": 0.23076535761356354,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0403,
      "step": 18
    },
    {
      "epoch": 0.012755690758418127,
      "grad_norm": 0.21546129882335663,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0362,
      "step": 19
    },
    {
      "epoch": 0.013427042903598028,
      "grad_norm": 0.23565559089183807,
      "learning_rate": 0.0,
      "loss": 0.0457,
      "step": 20
    },
    {
      "epoch": 0.013427042903598028,
      "eval_loss": 0.05111876502633095,
      "eval_runtime": 408.1451,
      "eval_samples_per_second": 24.587,
      "eval_steps_per_second": 6.147,
      "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": 8.360120555667456e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}