{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02109120628517947,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042182412570358947,
      "grad_norm": 0.8065983057022095,
      "learning_rate": 2.52808988764045e-07,
      "loss": 35.651678466796874,
      "step": 10
    },
    {
      "epoch": 0.0008436482514071789,
      "grad_norm": 0.9798905849456787,
      "learning_rate": 5.337078651685394e-07,
      "loss": 35.52773742675781,
      "step": 20
    },
    {
      "epoch": 0.0012654723771107683,
      "grad_norm": 0.9430276155471802,
      "learning_rate": 8.146067415730338e-07,
      "loss": 35.94612426757813,
      "step": 30
    },
    {
      "epoch": 0.0016872965028143579,
      "grad_norm": 0.8668350577354431,
      "learning_rate": 1.0955056179775282e-06,
      "loss": 35.54988098144531,
      "step": 40
    },
    {
      "epoch": 0.0021091206285179472,
      "grad_norm": 0.8153179883956909,
      "learning_rate": 1.3764044943820225e-06,
      "loss": 35.851254272460935,
      "step": 50
    },
    {
      "epoch": 0.0025309447542215366,
      "grad_norm": 0.9380270838737488,
      "learning_rate": 1.6573033707865168e-06,
      "loss": 35.082681274414064,
      "step": 60
    },
    {
      "epoch": 0.0029527688799251264,
      "grad_norm": 0.8418566584587097,
      "learning_rate": 1.9382022471910116e-06,
      "loss": 35.33572998046875,
      "step": 70
    },
    {
      "epoch": 0.0033745930056287158,
      "grad_norm": 0.8267859816551208,
      "learning_rate": 2.2191011235955057e-06,
      "loss": 34.830789184570314,
      "step": 80
    },
    {
      "epoch": 0.003796417131332305,
      "grad_norm": 0.8174882531166077,
      "learning_rate": 2.5e-06,
      "loss": 33.9393798828125,
      "step": 90
    },
    {
      "epoch": 0.0042182412570358945,
      "grad_norm": 0.8325590491294861,
      "learning_rate": 2.7808988764044947e-06,
      "loss": 33.55337829589844,
      "step": 100
    },
    {
      "epoch": 0.004640065382739484,
      "grad_norm": 0.7891654372215271,
      "learning_rate": 3.0617977528089893e-06,
      "loss": 33.115335083007814,
      "step": 110
    },
    {
      "epoch": 0.005061889508443073,
      "grad_norm": 1.0313451290130615,
      "learning_rate": 3.3426966292134834e-06,
      "loss": 32.383547973632815,
      "step": 120
    },
    {
      "epoch": 0.005483713634146663,
      "grad_norm": 0.5737534165382385,
      "learning_rate": 3.623595505617978e-06,
      "loss": 31.1286865234375,
      "step": 130
    },
    {
      "epoch": 0.005905537759850253,
      "grad_norm": 0.7010501027107239,
      "learning_rate": 3.9044943820224724e-06,
      "loss": 29.55970458984375,
      "step": 140
    },
    {
      "epoch": 0.006327361885553842,
      "grad_norm": 0.5494692325592041,
      "learning_rate": 4.185393258426967e-06,
      "loss": 29.449929809570314,
      "step": 150
    },
    {
      "epoch": 0.0067491860112574315,
      "grad_norm": 0.41349244117736816,
      "learning_rate": 4.466292134831461e-06,
      "loss": 28.477688598632813,
      "step": 160
    },
    {
      "epoch": 0.007171010136961021,
      "grad_norm": 0.30324503779411316,
      "learning_rate": 4.747191011235955e-06,
      "loss": 27.354144287109374,
      "step": 170
    },
    {
      "epoch": 0.00759283426266461,
      "grad_norm": 0.327568918466568,
      "learning_rate": 5.02808988764045e-06,
      "loss": 26.92130126953125,
      "step": 180
    },
    {
      "epoch": 0.0080146583883682,
      "grad_norm": 0.29565760493278503,
      "learning_rate": 5.308988764044944e-06,
      "loss": 26.194525146484374,
      "step": 190
    },
    {
      "epoch": 0.008436482514071789,
      "grad_norm": 0.2572338283061981,
      "learning_rate": 5.589887640449439e-06,
      "loss": 25.769549560546874,
      "step": 200
    },
    {
      "epoch": 0.008858306639775378,
      "grad_norm": 0.2657480239868164,
      "learning_rate": 5.870786516853933e-06,
      "loss": 25.394000244140624,
      "step": 210
    },
    {
      "epoch": 0.009280130765478968,
      "grad_norm": 0.20723949372768402,
      "learning_rate": 6.151685393258428e-06,
      "loss": 24.25175323486328,
      "step": 220
    },
    {
      "epoch": 0.009701954891182557,
      "grad_norm": 0.19784937798976898,
      "learning_rate": 6.4325842696629215e-06,
      "loss": 23.95145263671875,
      "step": 230
    },
    {
      "epoch": 0.010123779016886146,
      "grad_norm": 0.1812913715839386,
      "learning_rate": 6.713483146067417e-06,
      "loss": 23.77376708984375,
      "step": 240
    },
    {
      "epoch": 0.010545603142589736,
      "grad_norm": 0.19627007842063904,
      "learning_rate": 6.9943820224719105e-06,
      "loss": 23.246966552734374,
      "step": 250
    },
    {
      "epoch": 0.010967427268293325,
      "grad_norm": 0.22846540808677673,
      "learning_rate": 7.275280898876404e-06,
      "loss": 23.158154296875,
      "step": 260
    },
    {
      "epoch": 0.011389251393996916,
      "grad_norm": 0.1520307958126068,
      "learning_rate": 7.5561797752809e-06,
      "loss": 22.498358154296874,
      "step": 270
    },
    {
      "epoch": 0.011811075519700506,
      "grad_norm": 0.14488539099693298,
      "learning_rate": 7.837078651685394e-06,
      "loss": 22.60594482421875,
      "step": 280
    },
    {
      "epoch": 0.012232899645404095,
      "grad_norm": 0.14345483481884003,
      "learning_rate": 8.117977528089889e-06,
      "loss": 22.301371765136718,
      "step": 290
    },
    {
      "epoch": 0.012654723771107684,
      "grad_norm": 0.6615362763404846,
      "learning_rate": 8.398876404494383e-06,
      "loss": 21.755278015136717,
      "step": 300
    },
    {
      "epoch": 0.013076547896811274,
      "grad_norm": 0.1423025280237198,
      "learning_rate": 8.679775280898876e-06,
      "loss": 21.386692810058594,
      "step": 310
    },
    {
      "epoch": 0.013498372022514863,
      "grad_norm": 0.14323103427886963,
      "learning_rate": 8.960674157303372e-06,
      "loss": 21.5313232421875,
      "step": 320
    },
    {
      "epoch": 0.013920196148218452,
      "grad_norm": 0.13975073397159576,
      "learning_rate": 9.241573033707865e-06,
      "loss": 21.04039306640625,
      "step": 330
    },
    {
      "epoch": 0.014342020273922042,
      "grad_norm": 0.18143784999847412,
      "learning_rate": 9.522471910112361e-06,
      "loss": 21.435638427734375,
      "step": 340
    },
    {
      "epoch": 0.014763844399625631,
      "grad_norm": 0.16371376812458038,
      "learning_rate": 9.803370786516854e-06,
      "loss": 21.240106201171876,
      "step": 350
    },
    {
      "epoch": 0.01518566852532922,
      "grad_norm": 0.19794277846813202,
      "learning_rate": 1.0084269662921349e-05,
      "loss": 21.265296936035156,
      "step": 360
    },
    {
      "epoch": 0.01560749265103281,
      "grad_norm": 0.15830059349536896,
      "learning_rate": 1.0365168539325843e-05,
      "loss": 20.513796997070312,
      "step": 370
    },
    {
      "epoch": 0.0160293167767364,
      "grad_norm": 0.15261049568653107,
      "learning_rate": 1.064606741573034e-05,
      "loss": 20.430271911621094,
      "step": 380
    },
    {
      "epoch": 0.01645114090243999,
      "grad_norm": 0.17001120746135712,
      "learning_rate": 1.0926966292134832e-05,
      "loss": 20.2728759765625,
      "step": 390
    },
    {
      "epoch": 0.016872965028143578,
      "grad_norm": 0.1754172444343567,
      "learning_rate": 1.1207865168539327e-05,
      "loss": 20.585818481445312,
      "step": 400
    },
    {
      "epoch": 0.01729478915384717,
      "grad_norm": 0.1494324952363968,
      "learning_rate": 1.1488764044943821e-05,
      "loss": 20.26520690917969,
      "step": 410
    },
    {
      "epoch": 0.017716613279550757,
      "grad_norm": 0.2788557708263397,
      "learning_rate": 1.1769662921348314e-05,
      "loss": 20.216525268554687,
      "step": 420
    },
    {
      "epoch": 0.018138437405254348,
      "grad_norm": 0.22943347692489624,
      "learning_rate": 1.2050561797752809e-05,
      "loss": 19.879740905761718,
      "step": 430
    },
    {
      "epoch": 0.018560261530957935,
      "grad_norm": 0.19310815632343292,
      "learning_rate": 1.2331460674157305e-05,
      "loss": 20.340792846679687,
      "step": 440
    },
    {
      "epoch": 0.018982085656661526,
      "grad_norm": 0.17677143216133118,
      "learning_rate": 1.26123595505618e-05,
      "loss": 20.295317077636717,
      "step": 450
    },
    {
      "epoch": 0.019403909782365114,
      "grad_norm": 0.1568199247121811,
      "learning_rate": 1.2893258426966292e-05,
      "loss": 20.30619659423828,
      "step": 460
    },
    {
      "epoch": 0.019825733908068705,
      "grad_norm": 0.14602652192115784,
      "learning_rate": 1.3174157303370787e-05,
      "loss": 19.96039581298828,
      "step": 470
    },
    {
      "epoch": 0.020247558033772293,
      "grad_norm": 0.19724591076374054,
      "learning_rate": 1.3455056179775281e-05,
      "loss": 19.820477294921876,
      "step": 480
    },
    {
      "epoch": 0.020669382159475884,
      "grad_norm": 0.14715564250946045,
      "learning_rate": 1.3735955056179778e-05,
      "loss": 19.374057006835937,
      "step": 490
    },
    {
      "epoch": 0.02109120628517947,
      "grad_norm": 0.16100069880485535,
      "learning_rate": 1.401685393258427e-05,
      "loss": 19.71839599609375,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 23707,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}