{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 327,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015313935681470138,
      "grad_norm": 1.1070387363433838,
      "learning_rate": 1.4634146341463416e-06,
      "loss": 1.2917,
      "step": 5
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 1.122970700263977,
      "learning_rate": 3.2926829268292685e-06,
      "loss": 1.2965,
      "step": 10
    },
    {
      "epoch": 0.045941807044410414,
      "grad_norm": 0.8600009083747864,
      "learning_rate": 5.121951219512195e-06,
      "loss": 1.3084,
      "step": 15
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 0.6501789093017578,
      "learning_rate": 6.951219512195123e-06,
      "loss": 1.3178,
      "step": 20
    },
    {
      "epoch": 0.07656967840735068,
      "grad_norm": 0.6199907660484314,
      "learning_rate": 8.780487804878048e-06,
      "loss": 1.258,
      "step": 25
    },
    {
      "epoch": 0.09188361408882083,
      "grad_norm": 0.525578498840332,
      "learning_rate": 1.0609756097560975e-05,
      "loss": 1.2632,
      "step": 30
    },
    {
      "epoch": 0.10719754977029096,
      "grad_norm": 0.5301306843757629,
      "learning_rate": 1.2439024390243903e-05,
      "loss": 1.1863,
      "step": 35
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 0.45140478014945984,
      "learning_rate": 1.4268292682926829e-05,
      "loss": 1.1721,
      "step": 40
    },
    {
      "epoch": 0.13782542113323124,
      "grad_norm": 0.5104884505271912,
      "learning_rate": 1.6097560975609757e-05,
      "loss": 1.2507,
      "step": 45
    },
    {
      "epoch": 0.15313935681470137,
      "grad_norm": 0.4204311668872833,
      "learning_rate": 1.7926829268292684e-05,
      "loss": 1.1973,
      "step": 50
    },
    {
      "epoch": 0.16845329249617153,
      "grad_norm": 0.43958738446235657,
      "learning_rate": 1.975609756097561e-05,
      "loss": 1.1404,
      "step": 55
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 0.45204630494117737,
      "learning_rate": 2.1585365853658537e-05,
      "loss": 1.1811,
      "step": 60
    },
    {
      "epoch": 0.1990811638591118,
      "grad_norm": 0.4730817973613739,
      "learning_rate": 2.3414634146341466e-05,
      "loss": 1.1368,
      "step": 65
    },
    {
      "epoch": 0.21439509954058192,
      "grad_norm": 0.5665387511253357,
      "learning_rate": 2.524390243902439e-05,
      "loss": 1.1341,
      "step": 70
    },
    {
      "epoch": 0.22970903522205208,
      "grad_norm": 0.49841874837875366,
      "learning_rate": 2.707317073170732e-05,
      "loss": 1.1277,
      "step": 75
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 0.4274734556674957,
      "learning_rate": 2.8902439024390242e-05,
      "loss": 1.0674,
      "step": 80
    },
    {
      "epoch": 0.26033690658499237,
      "grad_norm": 0.6278162598609924,
      "learning_rate": 2.9999877234172298e-05,
      "loss": 1.0953,
      "step": 85
    },
    {
      "epoch": 0.27565084226646247,
      "grad_norm": 0.5454415082931519,
      "learning_rate": 2.999849614168868e-05,
      "loss": 1.0974,
      "step": 90
    },
    {
      "epoch": 0.29096477794793263,
      "grad_norm": 0.5087949633598328,
      "learning_rate": 2.999558064119925e-05,
      "loss": 1.1079,
      "step": 95
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 0.5586227774620056,
      "learning_rate": 2.999113103097174e-05,
      "loss": 1.0655,
      "step": 100
    },
    {
      "epoch": 0.3215926493108729,
      "grad_norm": 0.5441133975982666,
      "learning_rate": 2.9985147766219615e-05,
      "loss": 1.0631,
      "step": 105
    },
    {
      "epoch": 0.33690658499234305,
      "grad_norm": 0.6769384741783142,
      "learning_rate": 2.9977631459055537e-05,
      "loss": 1.0438,
      "step": 110
    },
    {
      "epoch": 0.35222052067381315,
      "grad_norm": 0.523868978023529,
      "learning_rate": 2.996858287842873e-05,
      "loss": 1.0131,
      "step": 115
    },
    {
      "epoch": 0.3675344563552833,
      "grad_norm": 0.5572935342788696,
      "learning_rate": 2.995800295004629e-05,
      "loss": 1.0501,
      "step": 120
    },
    {
      "epoch": 0.38284839203675347,
      "grad_norm": 0.6209707856178284,
      "learning_rate": 2.9945892756278543e-05,
      "loss": 1.0125,
      "step": 125
    },
    {
      "epoch": 0.3981623277182236,
      "grad_norm": 0.6483351588249207,
      "learning_rate": 2.993225353604824e-05,
      "loss": 0.998,
      "step": 130
    },
    {
      "epoch": 0.41347626339969373,
      "grad_norm": 0.6352364420890808,
      "learning_rate": 2.9917086684703844e-05,
      "loss": 1.0163,
      "step": 135
    },
    {
      "epoch": 0.42879019908116384,
      "grad_norm": 0.6867502331733704,
      "learning_rate": 2.9900393753876816e-05,
      "loss": 0.9824,
      "step": 140
    },
    {
      "epoch": 0.444104134762634,
      "grad_norm": 0.6153353452682495,
      "learning_rate": 2.9882176451322798e-05,
      "loss": 0.9395,
      "step": 145
    },
    {
      "epoch": 0.45941807044410415,
      "grad_norm": 0.645903468132019,
      "learning_rate": 2.9862436640746973e-05,
      "loss": 0.914,
      "step": 150
    },
    {
      "epoch": 0.47473200612557426,
      "grad_norm": 0.671872615814209,
      "learning_rate": 2.9841176341613364e-05,
      "loss": 0.9177,
      "step": 155
    },
    {
      "epoch": 0.4900459418070444,
      "grad_norm": 0.6303296089172363,
      "learning_rate": 2.981839772893825e-05,
      "loss": 0.9576,
      "step": 160
    },
    {
      "epoch": 0.5053598774885145,
      "grad_norm": 0.7237289547920227,
      "learning_rate": 2.9794103133067637e-05,
      "loss": 0.9649,
      "step": 165
    },
    {
      "epoch": 0.5206738131699847,
      "grad_norm": 0.6527206301689148,
      "learning_rate": 2.9768295039438868e-05,
      "loss": 0.9158,
      "step": 170
    },
    {
      "epoch": 0.5359877488514548,
      "grad_norm": 0.7285829782485962,
      "learning_rate": 2.974097608832635e-05,
      "loss": 0.9173,
      "step": 175
    },
    {
      "epoch": 0.5513016845329249,
      "grad_norm": 0.8059846758842468,
      "learning_rate": 2.9712149074571433e-05,
      "loss": 0.8667,
      "step": 180
    },
    {
      "epoch": 0.5666156202143952,
      "grad_norm": 0.7382646799087524,
      "learning_rate": 2.968181694729651e-05,
      "loss": 0.877,
      "step": 185
    },
    {
      "epoch": 0.5819295558958653,
      "grad_norm": 0.7463013529777527,
      "learning_rate": 2.964998280960328e-05,
      "loss": 0.9148,
      "step": 190
    },
    {
      "epoch": 0.5972434915773354,
      "grad_norm": 0.7870151400566101,
      "learning_rate": 2.961664991825531e-05,
      "loss": 0.8881,
      "step": 195
    },
    {
      "epoch": 0.6125574272588055,
      "grad_norm": 0.8590981364250183,
      "learning_rate": 2.9581821683344832e-05,
      "loss": 0.8352,
      "step": 200
    },
    {
      "epoch": 0.6278713629402757,
      "grad_norm": 0.7620300650596619,
      "learning_rate": 2.954550166794391e-05,
      "loss": 0.7867,
      "step": 205
    },
    {
      "epoch": 0.6431852986217458,
      "grad_norm": 0.8273492455482483,
      "learning_rate": 2.9507693587739895e-05,
      "loss": 0.8456,
      "step": 210
    },
    {
      "epoch": 0.6584992343032159,
      "grad_norm": 0.7399709224700928,
      "learning_rate": 2.9468401310655303e-05,
      "loss": 0.8156,
      "step": 215
    },
    {
      "epoch": 0.6738131699846861,
      "grad_norm": 0.851788341999054,
      "learning_rate": 2.942762885645211e-05,
      "loss": 0.7952,
      "step": 220
    },
    {
      "epoch": 0.6891271056661562,
      "grad_norm": 0.8381015658378601,
      "learning_rate": 2.9385380396320523e-05,
      "loss": 0.8027,
      "step": 225
    },
    {
      "epoch": 0.7044410413476263,
      "grad_norm": 0.8373646140098572,
      "learning_rate": 2.934166025245223e-05,
      "loss": 0.7943,
      "step": 230
    },
    {
      "epoch": 0.7197549770290965,
      "grad_norm": 0.8320114612579346,
      "learning_rate": 2.9296472897598246e-05,
      "loss": 0.8064,
      "step": 235
    },
    {
      "epoch": 0.7350689127105666,
      "grad_norm": 1.0138018131256104,
      "learning_rate": 2.924982295461131e-05,
      "loss": 0.761,
      "step": 240
    },
    {
      "epoch": 0.7503828483920367,
      "grad_norm": 0.9759603142738342,
      "learning_rate": 2.920171519597297e-05,
      "loss": 0.7114,
      "step": 245
    },
    {
      "epoch": 0.7656967840735069,
      "grad_norm": 0.844030499458313,
      "learning_rate": 2.9152154543305316e-05,
      "loss": 0.7461,
      "step": 250
    },
    {
      "epoch": 0.781010719754977,
      "grad_norm": 0.8687477111816406,
      "learning_rate": 2.9101146066867502e-05,
      "loss": 0.728,
      "step": 255
    },
    {
      "epoch": 0.7963246554364471,
      "grad_norm": 0.9759243726730347,
      "learning_rate": 2.9048694985037e-05,
      "loss": 0.7475,
      "step": 260
    },
    {
      "epoch": 0.8116385911179173,
      "grad_norm": 0.9230566620826721,
      "learning_rate": 2.8994806663775792e-05,
      "loss": 0.8098,
      "step": 265
    },
    {
      "epoch": 0.8269525267993875,
      "grad_norm": 0.8410807251930237,
      "learning_rate": 2.893948661608136e-05,
      "loss": 0.7465,
      "step": 270
    },
    {
      "epoch": 0.8422664624808576,
      "grad_norm": 1.0104124546051025,
      "learning_rate": 2.888274050142271e-05,
      "loss": 0.7799,
      "step": 275
    },
    {
      "epoch": 0.8575803981623277,
      "grad_norm": 0.9490285515785217,
      "learning_rate": 2.8824574125161384e-05,
      "loss": 0.7541,
      "step": 280
    },
    {
      "epoch": 0.8728943338437979,
      "grad_norm": 0.9112844467163086,
      "learning_rate": 2.876499343795754e-05,
      "loss": 0.7424,
      "step": 285
    },
    {
      "epoch": 0.888208269525268,
      "grad_norm": 0.8824840784072876,
      "learning_rate": 2.8704004535161172e-05,
      "loss": 0.7448,
      "step": 290
    },
    {
      "epoch": 0.9035222052067381,
      "grad_norm": 1.3259707689285278,
      "learning_rate": 2.864161365618854e-05,
      "loss": 0.7165,
      "step": 295
    },
    {
      "epoch": 0.9188361408882083,
      "grad_norm": 0.938458263874054,
      "learning_rate": 2.8577827183883853e-05,
      "loss": 0.6724,
      "step": 300
    },
    {
      "epoch": 0.9341500765696784,
      "grad_norm": 0.940185010433197,
      "learning_rate": 2.851265164386627e-05,
      "loss": 0.6722,
      "step": 305
    },
    {
      "epoch": 0.9494640122511485,
      "grad_norm": 1.0995936393737793,
      "learning_rate": 2.84460937038623e-05,
      "loss": 0.6628,
      "step": 310
    },
    {
      "epoch": 0.9647779479326187,
      "grad_norm": 0.9380448460578918,
      "learning_rate": 2.837816017302368e-05,
      "loss": 0.6519,
      "step": 315
    },
    {
      "epoch": 0.9800918836140888,
      "grad_norm": 1.0398368835449219,
      "learning_rate": 2.8308858001230757e-05,
      "loss": 0.6781,
      "step": 320
    },
    {
      "epoch": 0.9954058192955589,
      "grad_norm": 1.1420120000839233,
      "learning_rate": 2.823819427838149e-05,
      "loss": 0.6554,
      "step": 325
    }
  ],
  "logging_steps": 5,
  "max_steps": 1635,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7283530433246e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}