{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.26625840378086935,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005325168075617386,
      "grad_norm": 0.8962735533714294,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.6156774044036866,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.6505459547042847,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.6319706439971924,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.7087418437004089,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.5293724536895752,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.6000648736953735,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.5505657196044922,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.6782986521720886,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.529414176940918,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.7469022870063782,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.5422356128692627,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.48729589581489563,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.4591850280761719,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.7431496381759644,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.5589332580566406,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.7741137742996216,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.464280891418457,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.678589403629303,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.4997251510620117,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.682922899723053,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.47078533172607423,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.6075326800346375,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.4883549213409424,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.6084023118019104,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.46454439163208006,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.4270703196525574,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.5401740550994873,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.476523220539093,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5101356029510498,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.39205488562583923,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.48133230209350586,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.5510543584823608,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.4766493797302246,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.5049210786819458,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.4688286304473877,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.3839053213596344,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.4600823879241943,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.42306873202323914,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.4376970767974854,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.531020998954773,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.5281709671020508,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.5799203515052795,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.43495907783508303,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.8508591651916504,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.44717020988464357,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.27839505672454834,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.5093747138977051,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.34132304787635803,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.43798069953918456,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.5340864062309265,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.45476760864257815,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.3618414103984833,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5258561611175537,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.3316102623939514,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.44420590400695803,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.26986509561538696,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.4392819881439209,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.4154033958911896,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.5123180389404297,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.6473212242126465,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.48792481422424316,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.40945419669151306,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.4634854316711426,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.6368703842163086,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.5561904430389404,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.3966146409511566,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.48015313148498534,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.2615492045879364,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.44255995750427246,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.817905843257904,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.4412506103515625,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.3726387023925781,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.5113882064819336,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.5075891613960266,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.39214348793029785,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.29460638761520386,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.38456382751464846,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.27994513511657715,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.4433499813079834,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.48946434259414673,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.5264839649200439,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.5291221141815186,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.4583121776580811,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.3037419617176056,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.4284197330474854,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.4386015236377716,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.43100814819335936,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.36577337980270386,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.4472473621368408,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.3954521119594574,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.4810364246368408,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.27680379152297974,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.4296328067779541,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.28395938873291016,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.4248642444610596,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.35595008730888367,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.46191959381103515,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.5136922001838684,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.4588924407958984,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1878,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1960495119361905e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}