{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 28712,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01741432153803288,
      "grad_norm": 9.577305793762207,
      "learning_rate": 1.160092807424594e-05,
      "loss": 3.1831,
      "step": 500
    },
    {
      "epoch": 0.03482864307606576,
      "grad_norm": 12.14001178741455,
      "learning_rate": 1.9900897666068224e-05,
      "loss": 2.7736,
      "step": 1000
    },
    {
      "epoch": 0.052242964614098636,
      "grad_norm": 13.129646301269531,
      "learning_rate": 1.9541831238779175e-05,
      "loss": 2.6251,
      "step": 1500
    },
    {
      "epoch": 0.06965728615213151,
      "grad_norm": 13.319927215576172,
      "learning_rate": 1.9182764811490127e-05,
      "loss": 2.685,
      "step": 2000
    },
    {
      "epoch": 0.0870716076901644,
      "grad_norm": 9.90979290008545,
      "learning_rate": 1.882369838420108e-05,
      "loss": 2.4835,
      "step": 2500
    },
    {
      "epoch": 0.10448592922819727,
      "grad_norm": 7.106535911560059,
      "learning_rate": 1.846463195691203e-05,
      "loss": 2.4759,
      "step": 3000
    },
    {
      "epoch": 0.12190025076623015,
      "grad_norm": 11.579163551330566,
      "learning_rate": 1.8105565529622982e-05,
      "loss": 2.4615,
      "step": 3500
    },
    {
      "epoch": 0.13931457230426303,
      "grad_norm": 8.479988098144531,
      "learning_rate": 1.7746499102333934e-05,
      "loss": 2.5471,
      "step": 4000
    },
    {
      "epoch": 0.1567288938422959,
      "grad_norm": 6.432307720184326,
      "learning_rate": 1.7387432675044886e-05,
      "loss": 2.4572,
      "step": 4500
    },
    {
      "epoch": 0.1741432153803288,
      "grad_norm": 10.89651870727539,
      "learning_rate": 1.7028366247755838e-05,
      "loss": 2.4725,
      "step": 5000
    },
    {
      "epoch": 0.19155753691836166,
      "grad_norm": 8.298269271850586,
      "learning_rate": 1.6669299820466786e-05,
      "loss": 2.4184,
      "step": 5500
    },
    {
      "epoch": 0.20897185845639454,
      "grad_norm": 3.4620511531829834,
      "learning_rate": 1.6310233393177738e-05,
      "loss": 2.3301,
      "step": 6000
    },
    {
      "epoch": 0.22638617999442742,
      "grad_norm": 5.399957180023193,
      "learning_rate": 1.5951166965888693e-05,
      "loss": 2.4545,
      "step": 6500
    },
    {
      "epoch": 0.2438005015324603,
      "grad_norm": 8.993759155273438,
      "learning_rate": 1.559210053859964e-05,
      "loss": 2.3337,
      "step": 7000
    },
    {
      "epoch": 0.26121482307049315,
      "grad_norm": 3.5916497707366943,
      "learning_rate": 1.5233034111310595e-05,
      "loss": 2.4419,
      "step": 7500
    },
    {
      "epoch": 0.27862914460852606,
      "grad_norm": 8.653467178344727,
      "learning_rate": 1.4873967684021545e-05,
      "loss": 2.3755,
      "step": 8000
    },
    {
      "epoch": 0.2960434661465589,
      "grad_norm": 6.519212245941162,
      "learning_rate": 1.4514901256732496e-05,
      "loss": 2.3601,
      "step": 8500
    },
    {
      "epoch": 0.3134577876845918,
      "grad_norm": 8.016100883483887,
      "learning_rate": 1.4155834829443448e-05,
      "loss": 2.2321,
      "step": 9000
    },
    {
      "epoch": 0.33087210922262467,
      "grad_norm": 16.313932418823242,
      "learning_rate": 1.37967684021544e-05,
      "loss": 2.3488,
      "step": 9500
    },
    {
      "epoch": 0.3482864307606576,
      "grad_norm": 28.44437026977539,
      "learning_rate": 1.3437701974865352e-05,
      "loss": 2.3364,
      "step": 10000
    },
    {
      "epoch": 0.3657007522986904,
      "grad_norm": 3.504075527191162,
      "learning_rate": 1.3078635547576302e-05,
      "loss": 2.2997,
      "step": 10500
    },
    {
      "epoch": 0.38311507383672333,
      "grad_norm": 11.785683631896973,
      "learning_rate": 1.2719569120287253e-05,
      "loss": 2.3374,
      "step": 11000
    },
    {
      "epoch": 0.4005293953747562,
      "grad_norm": 9.7432861328125,
      "learning_rate": 1.2360502692998207e-05,
      "loss": 2.266,
      "step": 11500
    },
    {
      "epoch": 0.4179437169127891,
      "grad_norm": 8.663525581359863,
      "learning_rate": 1.2001436265709157e-05,
      "loss": 2.2722,
      "step": 12000
    },
    {
      "epoch": 0.43535803845082194,
      "grad_norm": 8.145735740661621,
      "learning_rate": 1.1642369838420109e-05,
      "loss": 2.3819,
      "step": 12500
    },
    {
      "epoch": 0.45277235998885484,
      "grad_norm": 6.875612258911133,
      "learning_rate": 1.1283303411131059e-05,
      "loss": 2.3541,
      "step": 13000
    },
    {
      "epoch": 0.4701866815268877,
      "grad_norm": 4.973703861236572,
      "learning_rate": 1.0924236983842012e-05,
      "loss": 2.3205,
      "step": 13500
    },
    {
      "epoch": 0.4876010030649206,
      "grad_norm": 8.985243797302246,
      "learning_rate": 1.0565170556552964e-05,
      "loss": 2.3118,
      "step": 14000
    },
    {
      "epoch": 0.5050153246029535,
      "grad_norm": 3.0293591022491455,
      "learning_rate": 1.0206104129263914e-05,
      "loss": 2.2947,
      "step": 14500
    },
    {
      "epoch": 0.5224296461409863,
      "grad_norm": 11.419426918029785,
      "learning_rate": 9.847037701974866e-06,
      "loss": 2.2276,
      "step": 15000
    },
    {
      "epoch": 0.5398439676790192,
      "grad_norm": 9.195966720581055,
      "learning_rate": 9.487971274685817e-06,
      "loss": 2.333,
      "step": 15500
    },
    {
      "epoch": 0.5572582892170521,
      "grad_norm": 7.067108631134033,
      "learning_rate": 9.128904847396769e-06,
      "loss": 2.3562,
      "step": 16000
    },
    {
      "epoch": 0.574672610755085,
      "grad_norm": 5.443989276885986,
      "learning_rate": 8.769838420107721e-06,
      "loss": 2.3378,
      "step": 16500
    },
    {
      "epoch": 0.5920869322931178,
      "grad_norm": 10.031864166259766,
      "learning_rate": 8.410771992818673e-06,
      "loss": 2.3233,
      "step": 17000
    },
    {
      "epoch": 0.6095012538311507,
      "grad_norm": 7.518855094909668,
      "learning_rate": 8.051705565529624e-06,
      "loss": 2.2783,
      "step": 17500
    },
    {
      "epoch": 0.6269155753691836,
      "grad_norm": 8.214040756225586,
      "learning_rate": 7.692639138240574e-06,
      "loss": 2.1764,
      "step": 18000
    },
    {
      "epoch": 0.6443298969072165,
      "grad_norm": 10.006634712219238,
      "learning_rate": 7.333572710951526e-06,
      "loss": 2.3743,
      "step": 18500
    },
    {
      "epoch": 0.6617442184452493,
      "grad_norm": 8.866910934448242,
      "learning_rate": 6.974506283662478e-06,
      "loss": 2.3044,
      "step": 19000
    },
    {
      "epoch": 0.6791585399832822,
      "grad_norm": 5.549246311187744,
      "learning_rate": 6.6154398563734305e-06,
      "loss": 2.2693,
      "step": 19500
    },
    {
      "epoch": 0.6965728615213151,
      "grad_norm": 4.0343194007873535,
      "learning_rate": 6.2563734290843814e-06,
      "loss": 2.1788,
      "step": 20000
    },
    {
      "epoch": 0.713987183059348,
      "grad_norm": 6.325515270233154,
      "learning_rate": 5.897307001795332e-06,
      "loss": 2.2589,
      "step": 20500
    },
    {
      "epoch": 0.7314015045973808,
      "grad_norm": 5.234256267547607,
      "learning_rate": 5.538240574506284e-06,
      "loss": 2.1563,
      "step": 21000
    },
    {
      "epoch": 0.7488158261354138,
      "grad_norm": 8.443244934082031,
      "learning_rate": 5.179174147217235e-06,
      "loss": 2.2293,
      "step": 21500
    },
    {
      "epoch": 0.7662301476734467,
      "grad_norm": 3.8823511600494385,
      "learning_rate": 4.820107719928187e-06,
      "loss": 2.2258,
      "step": 22000
    },
    {
      "epoch": 0.7836444692114796,
      "grad_norm": 6.5127034187316895,
      "learning_rate": 4.4610412926391385e-06,
      "loss": 2.1272,
      "step": 22500
    },
    {
      "epoch": 0.8010587907495124,
      "grad_norm": 12.666552543640137,
      "learning_rate": 4.10197486535009e-06,
      "loss": 2.264,
      "step": 23000
    },
    {
      "epoch": 0.8184731122875453,
      "grad_norm": 5.594479084014893,
      "learning_rate": 3.7429084380610415e-06,
      "loss": 2.2525,
      "step": 23500
    },
    {
      "epoch": 0.8358874338255782,
      "grad_norm": 5.7376179695129395,
      "learning_rate": 3.3838420107719933e-06,
      "loss": 2.3071,
      "step": 24000
    },
    {
      "epoch": 0.8533017553636111,
      "grad_norm": 12.593650817871094,
      "learning_rate": 3.0247755834829446e-06,
      "loss": 2.2623,
      "step": 24500
    },
    {
      "epoch": 0.8707160769016439,
      "grad_norm": 10.175933837890625,
      "learning_rate": 2.6657091561938963e-06,
      "loss": 2.2561,
      "step": 25000
    },
    {
      "epoch": 0.8881303984396768,
      "grad_norm": 11.089727401733398,
      "learning_rate": 2.3066427289048477e-06,
      "loss": 2.2185,
      "step": 25500
    },
    {
      "epoch": 0.9055447199777097,
      "grad_norm": 7.090406894683838,
      "learning_rate": 1.947576301615799e-06,
      "loss": 2.204,
      "step": 26000
    },
    {
      "epoch": 0.9229590415157426,
      "grad_norm": 16.22230339050293,
      "learning_rate": 1.5885098743267505e-06,
      "loss": 2.2285,
      "step": 26500
    },
    {
      "epoch": 0.9403733630537754,
      "grad_norm": 4.419189929962158,
      "learning_rate": 1.229443447037702e-06,
      "loss": 2.2739,
      "step": 27000
    },
    {
      "epoch": 0.9577876845918083,
      "grad_norm": 12.452730178833008,
      "learning_rate": 8.703770197486536e-07,
      "loss": 2.1793,
      "step": 27500
    },
    {
      "epoch": 0.9752020061298412,
      "grad_norm": 19.379770278930664,
      "learning_rate": 5.11310592459605e-07,
      "loss": 2.1586,
      "step": 28000
    },
    {
      "epoch": 0.9926163276678741,
      "grad_norm": 19.553585052490234,
      "learning_rate": 1.5224416517055656e-07,
      "loss": 2.1482,
      "step": 28500
    },
    {
      "epoch": 1.0,
      "step": 28712,
      "total_flos": 0.0,
      "train_loss": 2.343143721416024,
      "train_runtime": 98844.7919,
      "train_samples_per_second": 0.581,
      "train_steps_per_second": 0.29
    }
  ],
  "logging_steps": 500,
  "max_steps": 28712,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}