{
  "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": 1.1634962558746338,
      "learning_rate": 1.4634146341463416e-06,
      "loss": 1.3381,
      "step": 5
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 0.9751255512237549,
      "learning_rate": 3.2926829268292685e-06,
      "loss": 1.3201,
      "step": 10
    },
    {
      "epoch": 0.045941807044410414,
      "grad_norm": 0.6420730948448181,
      "learning_rate": 5.121951219512195e-06,
      "loss": 1.3144,
      "step": 15
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 0.5940472483634949,
      "learning_rate": 6.951219512195123e-06,
      "loss": 1.2986,
      "step": 20
    },
    {
      "epoch": 0.07656967840735068,
      "grad_norm": 0.6182255148887634,
      "learning_rate": 8.780487804878048e-06,
      "loss": 1.3159,
      "step": 25
    },
    {
      "epoch": 0.09188361408882083,
      "grad_norm": 0.5141950845718384,
      "learning_rate": 1.0609756097560975e-05,
      "loss": 1.268,
      "step": 30
    },
    {
      "epoch": 0.10719754977029096,
      "grad_norm": 0.528359055519104,
      "learning_rate": 1.2439024390243903e-05,
      "loss": 1.207,
      "step": 35
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 0.48875945806503296,
      "learning_rate": 1.4268292682926829e-05,
      "loss": 1.2673,
      "step": 40
    },
    {
      "epoch": 0.13782542113323124,
      "grad_norm": 0.5121011137962341,
      "learning_rate": 1.6097560975609757e-05,
      "loss": 1.201,
      "step": 45
    },
    {
      "epoch": 0.15313935681470137,
      "grad_norm": 0.4511997699737549,
      "learning_rate": 1.7926829268292684e-05,
      "loss": 1.2696,
      "step": 50
    },
    {
      "epoch": 0.16845329249617153,
      "grad_norm": 0.42570406198501587,
      "learning_rate": 1.975609756097561e-05,
      "loss": 1.1761,
      "step": 55
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 0.4839572012424469,
      "learning_rate": 2.1585365853658537e-05,
      "loss": 1.1657,
      "step": 60
    },
    {
      "epoch": 0.1990811638591118,
      "grad_norm": 0.4797247648239136,
      "learning_rate": 2.3414634146341466e-05,
      "loss": 1.2398,
      "step": 65
    },
    {
      "epoch": 0.21439509954058192,
      "grad_norm": 0.45414257049560547,
      "learning_rate": 2.524390243902439e-05,
      "loss": 1.2156,
      "step": 70
    },
    {
      "epoch": 0.22970903522205208,
      "grad_norm": 0.41919460892677307,
      "learning_rate": 2.707317073170732e-05,
      "loss": 1.1861,
      "step": 75
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 0.4727442264556885,
      "learning_rate": 2.8902439024390242e-05,
      "loss": 1.1336,
      "step": 80
    },
    {
      "epoch": 0.26033690658499237,
      "grad_norm": 0.5595141649246216,
      "learning_rate": 2.9999877234172298e-05,
      "loss": 1.161,
      "step": 85
    },
    {
      "epoch": 0.27565084226646247,
      "grad_norm": 0.48706549406051636,
      "learning_rate": 2.999849614168868e-05,
      "loss": 1.163,
      "step": 90
    },
    {
      "epoch": 0.29096477794793263,
      "grad_norm": 0.5425196886062622,
      "learning_rate": 2.999558064119925e-05,
      "loss": 1.1033,
      "step": 95
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 0.5159770250320435,
      "learning_rate": 2.999113103097174e-05,
      "loss": 1.0591,
      "step": 100
    },
    {
      "epoch": 0.3215926493108729,
      "grad_norm": 0.6011470556259155,
      "learning_rate": 2.9985147766219615e-05,
      "loss": 1.1068,
      "step": 105
    },
    {
      "epoch": 0.33690658499234305,
      "grad_norm": 0.6025936007499695,
      "learning_rate": 2.9977631459055537e-05,
      "loss": 1.1102,
      "step": 110
    },
    {
      "epoch": 0.35222052067381315,
      "grad_norm": 0.6048042178153992,
      "learning_rate": 2.996858287842873e-05,
      "loss": 1.0633,
      "step": 115
    },
    {
      "epoch": 0.3675344563552833,
      "grad_norm": 0.5745708346366882,
      "learning_rate": 2.995800295004629e-05,
      "loss": 1.0355,
      "step": 120
    },
    {
      "epoch": 0.38284839203675347,
      "grad_norm": 0.6400654315948486,
      "learning_rate": 2.9945892756278543e-05,
      "loss": 0.9959,
      "step": 125
    },
    {
      "epoch": 0.3981623277182236,
      "grad_norm": 0.6600092053413391,
      "learning_rate": 2.993225353604824e-05,
      "loss": 0.923,
      "step": 130
    },
    {
      "epoch": 0.41347626339969373,
      "grad_norm": 0.6698320508003235,
      "learning_rate": 2.9917086684703844e-05,
      "loss": 0.9218,
      "step": 135
    },
    {
      "epoch": 0.42879019908116384,
      "grad_norm": 0.6736750602722168,
      "learning_rate": 2.9900393753876816e-05,
      "loss": 1.0266,
      "step": 140
    },
    {
      "epoch": 0.444104134762634,
      "grad_norm": 0.7200514674186707,
      "learning_rate": 2.9882176451322798e-05,
      "loss": 0.9735,
      "step": 145
    },
    {
      "epoch": 0.45941807044410415,
      "grad_norm": 0.7945486903190613,
      "learning_rate": 2.9862436640746973e-05,
      "loss": 0.9593,
      "step": 150
    },
    {
      "epoch": 0.47473200612557426,
      "grad_norm": 0.7599704265594482,
      "learning_rate": 2.9841176341613364e-05,
      "loss": 0.9086,
      "step": 155
    },
    {
      "epoch": 0.4900459418070444,
      "grad_norm": 0.7764740586280823,
      "learning_rate": 2.981839772893825e-05,
      "loss": 0.9635,
      "step": 160
    },
    {
      "epoch": 0.5053598774885145,
      "grad_norm": 0.7852749824523926,
      "learning_rate": 2.9794103133067637e-05,
      "loss": 0.9173,
      "step": 165
    },
    {
      "epoch": 0.5206738131699847,
      "grad_norm": 0.7193847894668579,
      "learning_rate": 2.9768295039438868e-05,
      "loss": 0.8323,
      "step": 170
    },
    {
      "epoch": 0.5359877488514548,
      "grad_norm": 0.7468358874320984,
      "learning_rate": 2.974097608832635e-05,
      "loss": 0.9018,
      "step": 175
    },
    {
      "epoch": 0.5513016845329249,
      "grad_norm": 0.7651287913322449,
      "learning_rate": 2.9712149074571433e-05,
      "loss": 0.8993,
      "step": 180
    },
    {
      "epoch": 0.5666156202143952,
      "grad_norm": 0.8457761406898499,
      "learning_rate": 2.968181694729651e-05,
      "loss": 0.8642,
      "step": 185
    },
    {
      "epoch": 0.5819295558958653,
      "grad_norm": 0.981182336807251,
      "learning_rate": 2.964998280960328e-05,
      "loss": 0.8593,
      "step": 190
    },
    {
      "epoch": 0.5972434915773354,
      "grad_norm": 0.9098852872848511,
      "learning_rate": 2.961664991825531e-05,
      "loss": 0.8578,
      "step": 195
    },
    {
      "epoch": 0.6125574272588055,
      "grad_norm": 1.0851359367370605,
      "learning_rate": 2.9581821683344832e-05,
      "loss": 0.8896,
      "step": 200
    },
    {
      "epoch": 0.6278713629402757,
      "grad_norm": 0.8962501883506775,
      "learning_rate": 2.954550166794391e-05,
      "loss": 0.7954,
      "step": 205
    },
    {
      "epoch": 0.6431852986217458,
      "grad_norm": 1.154096007347107,
      "learning_rate": 2.9507693587739895e-05,
      "loss": 0.8227,
      "step": 210
    },
    {
      "epoch": 0.6584992343032159,
      "grad_norm": 0.8688374757766724,
      "learning_rate": 2.9468401310655303e-05,
      "loss": 0.8133,
      "step": 215
    },
    {
      "epoch": 0.6738131699846861,
      "grad_norm": 0.8076976537704468,
      "learning_rate": 2.942762885645211e-05,
      "loss": 0.8698,
      "step": 220
    },
    {
      "epoch": 0.6891271056661562,
      "grad_norm": 0.9876447319984436,
      "learning_rate": 2.9385380396320523e-05,
      "loss": 0.7785,
      "step": 225
    },
    {
      "epoch": 0.7044410413476263,
      "grad_norm": 0.8549358248710632,
      "learning_rate": 2.934166025245223e-05,
      "loss": 0.8522,
      "step": 230
    },
    {
      "epoch": 0.7197549770290965,
      "grad_norm": 1.0136367082595825,
      "learning_rate": 2.9296472897598246e-05,
      "loss": 0.7612,
      "step": 235
    },
    {
      "epoch": 0.7350689127105666,
      "grad_norm": 0.8504995703697205,
      "learning_rate": 2.924982295461131e-05,
      "loss": 0.7773,
      "step": 240
    },
    {
      "epoch": 0.7503828483920367,
      "grad_norm": 0.9323103427886963,
      "learning_rate": 2.920171519597297e-05,
      "loss": 0.7684,
      "step": 245
    },
    {
      "epoch": 0.7656967840735069,
      "grad_norm": 0.9799562096595764,
      "learning_rate": 2.9152154543305316e-05,
      "loss": 0.7306,
      "step": 250
    },
    {
      "epoch": 0.781010719754977,
      "grad_norm": 0.9990427494049072,
      "learning_rate": 2.9101146066867502e-05,
      "loss": 0.7089,
      "step": 255
    },
    {
      "epoch": 0.7963246554364471,
      "grad_norm": 0.94583660364151,
      "learning_rate": 2.9048694985037e-05,
      "loss": 0.7458,
      "step": 260
    },
    {
      "epoch": 0.8116385911179173,
      "grad_norm": 1.0244216918945312,
      "learning_rate": 2.8994806663775792e-05,
      "loss": 0.7193,
      "step": 265
    },
    {
      "epoch": 0.8269525267993875,
      "grad_norm": 0.9860573410987854,
      "learning_rate": 2.893948661608136e-05,
      "loss": 0.7328,
      "step": 270
    },
    {
      "epoch": 0.8422664624808576,
      "grad_norm": 1.1211233139038086,
      "learning_rate": 2.888274050142271e-05,
      "loss": 0.7017,
      "step": 275
    },
    {
      "epoch": 0.8575803981623277,
      "grad_norm": 0.9939438700675964,
      "learning_rate": 2.8824574125161384e-05,
      "loss": 0.7092,
      "step": 280
    },
    {
      "epoch": 0.8728943338437979,
      "grad_norm": 1.0668702125549316,
      "learning_rate": 2.876499343795754e-05,
      "loss": 0.6999,
      "step": 285
    },
    {
      "epoch": 0.888208269525268,
      "grad_norm": 1.0538650751113892,
      "learning_rate": 2.8704004535161172e-05,
      "loss": 0.7,
      "step": 290
    },
    {
      "epoch": 0.9035222052067381,
      "grad_norm": 0.9455710649490356,
      "learning_rate": 2.864161365618854e-05,
      "loss": 0.7119,
      "step": 295
    },
    {
      "epoch": 0.9188361408882083,
      "grad_norm": 1.0059537887573242,
      "learning_rate": 2.8577827183883853e-05,
      "loss": 0.6566,
      "step": 300
    },
    {
      "epoch": 0.9341500765696784,
      "grad_norm": 1.0264160633087158,
      "learning_rate": 2.851265164386627e-05,
      "loss": 0.7123,
      "step": 305
    },
    {
      "epoch": 0.9494640122511485,
      "grad_norm": 0.9730039834976196,
      "learning_rate": 2.84460937038623e-05,
      "loss": 0.6861,
      "step": 310
    },
    {
      "epoch": 0.9647779479326187,
      "grad_norm": 1.0401747226715088,
      "learning_rate": 2.837816017302368e-05,
      "loss": 0.6573,
      "step": 315
    },
    {
      "epoch": 0.9800918836140888,
      "grad_norm": 0.9776532649993896,
      "learning_rate": 2.8308858001230757e-05,
      "loss": 0.6147,
      "step": 320
    },
    {
      "epoch": 0.9954058192955589,
      "grad_norm": 1.103063702583313,
      "learning_rate": 2.823819427838149e-05,
      "loss": 0.6398,
      "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": 4.674677580748554e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}