{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 100.0,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001,
      "grad_norm": 43.548129517838454,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.1920576095581055,
      "step": 1,
      "token_acc": 0.34359059658460855
    },
    {
      "epoch": 0.005,
      "grad_norm": 14.427483007671363,
      "learning_rate": 5e-06,
      "loss": 2.9412002563476562,
      "step": 5,
      "token_acc": 0.512452240845581
    },
    {
      "epoch": 0.01,
      "grad_norm": 7.934074490008561,
      "learning_rate": 1e-05,
      "loss": 2.503311347961426,
      "step": 10,
      "token_acc": 0.5123253736192332
    },
    {
      "epoch": 0.015,
      "grad_norm": 2.5682097340060643,
      "learning_rate": 9.999370638369377e-06,
      "loss": 1.8719802856445313,
      "step": 15,
      "token_acc": 0.6410698878343399
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.0601891911453225,
      "learning_rate": 9.997482711915926e-06,
      "loss": 1.7852279663085937,
      "step": 20,
      "token_acc": 0.6242933840865835
    },
    {
      "epoch": 0.025,
      "grad_norm": 2.9591215037175895,
      "learning_rate": 9.994336695915041e-06,
      "loss": 1.6610099792480468,
      "step": 25,
      "token_acc": 0.6568298460323727
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.3839735362461623,
      "learning_rate": 9.989933382359423e-06,
      "loss": 1.6115425109863282,
      "step": 30,
      "token_acc": 0.6632120451693851
    },
    {
      "epoch": 0.035,
      "grad_norm": 2.0296518100505776,
      "learning_rate": 9.984273879759713e-06,
      "loss": 1.7307615280151367,
      "step": 35,
      "token_acc": 0.6267176116002563
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.274063193212189,
      "learning_rate": 9.977359612865424e-06,
      "loss": 1.6226930618286133,
      "step": 40,
      "token_acc": 0.6632471264367816
    },
    {
      "epoch": 0.045,
      "grad_norm": 1.995496122888669,
      "learning_rate": 9.969192322306271e-06,
      "loss": 1.6562419891357423,
      "step": 45,
      "token_acc": 0.6479170419164758
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.030243788478171,
      "learning_rate": 9.959774064153977e-06,
      "loss": 1.5927490234375,
      "step": 50,
      "token_acc": 0.6578526695879487
    },
    {
      "epoch": 0.055,
      "grad_norm": 1.913105067952688,
      "learning_rate": 9.949107209404664e-06,
      "loss": 1.886464500427246,
      "step": 55,
      "token_acc": 0.5819125113628805
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.8949380801330526,
      "learning_rate": 9.937194443381972e-06,
      "loss": 1.6359737396240235,
      "step": 60,
      "token_acc": 0.6552567735622108
    },
    {
      "epoch": 0.065,
      "grad_norm": 1.4853873443995649,
      "learning_rate": 9.924038765061042e-06,
      "loss": 1.3352900505065919,
      "step": 65,
      "token_acc": 0.7206670637284097
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.6844968929576292,
      "learning_rate": 9.909643486313533e-06,
      "loss": 1.4845345497131348,
      "step": 70,
      "token_acc": 0.6865343744776369
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.7982742317399707,
      "learning_rate": 9.894012231073895e-06,
      "loss": 1.5165021896362305,
      "step": 75,
      "token_acc": 0.6689946239260413
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.7083434381167786,
      "learning_rate": 9.877148934427037e-06,
      "loss": 1.501682949066162,
      "step": 80,
      "token_acc": 0.6582693568920952
    },
    {
      "epoch": 0.085,
      "grad_norm": 2.276089893387222,
      "learning_rate": 9.859057841617709e-06,
      "loss": 1.3892568588256835,
      "step": 85,
      "token_acc": 0.7173441424982873
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.2510132262305955,
      "learning_rate": 9.839743506981783e-06,
      "loss": 1.6044925689697265,
      "step": 90,
      "token_acc": 0.6260809087747768
    },
    {
      "epoch": 0.095,
      "grad_norm": 2.3567789267765544,
      "learning_rate": 9.819210792799711e-06,
      "loss": 1.531374168395996,
      "step": 95,
      "token_acc": 0.661787561762045
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.7140659626033266,
      "learning_rate": 9.797464868072489e-06,
      "loss": 1.636698341369629,
      "step": 100,
      "token_acc": 0.6505466960542806
    }
  ],
  "logging_steps": 5,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 93095931019264.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}