{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 10000,
  "global_step": 60130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04157658406785299,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.08315316813570597,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.12472975220355896,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.16630633627141195,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 0.20788292033926492,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 0.24945950440711792,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 0.2910360884749709,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 0.3326126725428239,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 0.37418925661067687,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 4500
    },
    {
      "epoch": 0.41576584067852984,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 0.4573424247463828,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 0.49891900881423584,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 0.5404955928820888,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6500
    },
    {
      "epoch": 0.5820721769499418,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 0.6236487610177948,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7500
    },
    {
      "epoch": 0.6652253450856478,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 0.7068019291535007,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 8500
    },
    {
      "epoch": 0.7483785132213537,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 0.7899550972892068,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 9500
    },
    {
      "epoch": 0.8315316813570597,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 0.8315316813570597,
      "eval_loss": NaN,
      "eval_runtime": 2641.4469,
      "eval_samples_per_second": 145.687,
      "eval_steps_per_second": 4.553,
      "step": 10000
    },
    {
      "epoch": 0.8731082654249127,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 10500
    },
    {
      "epoch": 0.9146848494927656,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 11000
    },
    {
      "epoch": 0.9562614335606187,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 11500
    },
    {
      "epoch": 0.9978380176284717,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12000
    },
    {
      "epoch": 1.0394146016963246,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12500
    },
    {
      "epoch": 1.0809911857641776,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 13000
    },
    {
      "epoch": 1.1225677698320307,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 13500
    },
    {
      "epoch": 1.1641443538998835,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 14000
    },
    {
      "epoch": 1.2057209379677365,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 14500
    },
    {
      "epoch": 1.2472975220355895,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 15000
    },
    {
      "epoch": 1.2888741061034426,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 15500
    },
    {
      "epoch": 1.3304506901712956,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16000
    },
    {
      "epoch": 1.3720272742391484,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16500
    },
    {
      "epoch": 1.4136038583070014,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 17000
    },
    {
      "epoch": 1.4551804423748544,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 17500
    },
    {
      "epoch": 1.4967570264427075,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18000
    },
    {
      "epoch": 1.5383336105105605,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18500
    },
    {
      "epoch": 1.5799101945784133,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 19000
    },
    {
      "epoch": 1.6214867786462666,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 19500
    },
    {
      "epoch": 1.6630633627141194,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20000
    },
    {
      "epoch": 1.6630633627141194,
      "eval_loss": NaN,
      "eval_runtime": 2644.954,
      "eval_samples_per_second": 145.494,
      "eval_steps_per_second": 4.547,
      "step": 20000
    },
    {
      "epoch": 1.7046399467819724,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20500
    },
    {
      "epoch": 1.7462165308498254,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 21000
    },
    {
      "epoch": 1.7877931149176782,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 21500
    },
    {
      "epoch": 1.8293696989855315,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 22000
    },
    {
      "epoch": 1.8709462830533843,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 22500
    },
    {
      "epoch": 1.9125228671212373,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 23000
    },
    {
      "epoch": 1.9540994511890903,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 23500
    },
    {
      "epoch": 1.9956760352569431,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24000
    },
    {
      "epoch": 2.0372526193247964,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24500
    },
    {
      "epoch": 2.078829203392649,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25000
    },
    {
      "epoch": 2.1204057874605025,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25500
    },
    {
      "epoch": 2.1619823715283553,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 26000
    },
    {
      "epoch": 2.203558955596208,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 26500
    },
    {
      "epoch": 2.2451355396640613,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 27000
    },
    {
      "epoch": 2.286712123731914,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 27500
    },
    {
      "epoch": 2.328288707799767,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 28000
    },
    {
      "epoch": 2.36986529186762,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 28500
    },
    {
      "epoch": 2.411441875935473,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 29000
    },
    {
      "epoch": 2.4530184600033262,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 29500
    },
    {
      "epoch": 2.494595044071179,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30000
    },
    {
      "epoch": 2.494595044071179,
      "eval_loss": NaN,
      "eval_runtime": 2679.1955,
      "eval_samples_per_second": 143.635,
      "eval_steps_per_second": 4.489,
      "step": 30000
    },
    {
      "epoch": 2.536171628139032,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30500
    },
    {
      "epoch": 2.577748212206885,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 31000
    },
    {
      "epoch": 2.619324796274738,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 31500
    },
    {
      "epoch": 2.660901380342591,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 32000
    },
    {
      "epoch": 2.702477964410444,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 32500
    },
    {
      "epoch": 2.7440545484782968,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 33000
    },
    {
      "epoch": 2.78563113254615,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 33500
    },
    {
      "epoch": 2.827207716614003,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 34000
    },
    {
      "epoch": 2.868784300681856,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 34500
    },
    {
      "epoch": 2.910360884749709,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 35000
    },
    {
      "epoch": 2.9519374688175617,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 35500
    },
    {
      "epoch": 2.993514052885415,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 36000
    },
    {
      "epoch": 3.0350906369532678,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 36500
    },
    {
      "epoch": 3.076667221021121,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 37000
    },
    {
      "epoch": 3.118243805088974,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 37500
    },
    {
      "epoch": 3.159820389156827,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 38000
    },
    {
      "epoch": 3.20139697322468,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 38500
    },
    {
      "epoch": 3.2429735572925327,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 39000
    },
    {
      "epoch": 3.284550141360386,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 39500
    },
    {
      "epoch": 3.3261267254282387,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 40000
    },
    {
      "epoch": 3.3261267254282387,
      "eval_loss": NaN,
      "eval_runtime": 2656.6227,
      "eval_samples_per_second": 144.855,
      "eval_steps_per_second": 4.527,
      "step": 40000
    },
    {
      "epoch": 3.367703309496092,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 40500
    },
    {
      "epoch": 3.409279893563945,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 41000
    },
    {
      "epoch": 3.4508564776317976,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 41500
    },
    {
      "epoch": 3.492433061699651,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 42000
    },
    {
      "epoch": 3.5340096457675036,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 42500
    },
    {
      "epoch": 3.5755862298353565,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 43000
    },
    {
      "epoch": 3.6171628139032097,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 43500
    },
    {
      "epoch": 3.658739397971063,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 44000
    },
    {
      "epoch": 3.7003159820389158,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 44500
    },
    {
      "epoch": 3.7418925661067686,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 45000
    },
    {
      "epoch": 3.7834691501746214,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 45500
    },
    {
      "epoch": 3.8250457342424746,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 46000
    },
    {
      "epoch": 3.866622318310328,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 46500
    },
    {
      "epoch": 3.9081989023781807,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 47000
    },
    {
      "epoch": 3.9497754864460335,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 47500
    },
    {
      "epoch": 3.9913520705138867,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 48000
    },
    {
      "epoch": 4.03292865458174,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 48500
    },
    {
      "epoch": 4.074505238649593,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 49000
    },
    {
      "epoch": 4.116081822717446,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 49500
    },
    {
      "epoch": 4.157658406785298,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50000
    },
    {
      "epoch": 4.157658406785298,
      "eval_loss": NaN,
      "eval_runtime": 2666.9169,
      "eval_samples_per_second": 144.296,
      "eval_steps_per_second": 4.509,
      "step": 50000
    },
    {
      "epoch": 4.199234990853151,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50500
    },
    {
      "epoch": 4.240811574921005,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 51000
    },
    {
      "epoch": 4.282388158988858,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 51500
    },
    {
      "epoch": 4.3239647430567105,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 52000
    },
    {
      "epoch": 4.365541327124563,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 52500
    },
    {
      "epoch": 4.407117911192416,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 53000
    },
    {
      "epoch": 4.44869449526027,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 53500
    },
    {
      "epoch": 4.490271079328123,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 54000
    },
    {
      "epoch": 4.5318476633959754,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 54500
    },
    {
      "epoch": 4.573424247463828,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 55000
    },
    {
      "epoch": 4.615000831531681,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 55500
    },
    {
      "epoch": 4.656577415599534,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 56000
    },
    {
      "epoch": 4.698153999667388,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 56500
    },
    {
      "epoch": 4.73973058373524,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 57000
    },
    {
      "epoch": 4.781307167803093,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 57500
    },
    {
      "epoch": 4.822883751870946,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 58000
    },
    {
      "epoch": 4.8644603359388,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 58500
    },
    {
      "epoch": 4.9060369200066525,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 59000
    },
    {
      "epoch": 4.947613504074505,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 59500
    },
    {
      "epoch": 4.989190088142358,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 60000
    },
    {
      "epoch": 4.989190088142358,
      "eval_loss": NaN,
      "eval_runtime": 2669.6986,
      "eval_samples_per_second": 144.145,
      "eval_steps_per_second": 4.505,
      "step": 60000
    }
  ],
  "logging_steps": 500,
  "max_steps": 60130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.7410158852963e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}