{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.943019943019944,
  "eval_steps": 1000,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005698005698005698,
      "grad_norm": 5.125274658203125,
      "learning_rate": 0.0,
      "loss": 1.4488,
      "step": 1
    },
    {
      "epoch": 0.2849002849002849,
      "grad_norm": 1.6660258769989014,
      "learning_rate": 0.0001977977977977978,
      "loss": 0.7332,
      "step": 50
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 1.358102560043335,
      "learning_rate": 0.0001952952952952953,
      "loss": 0.6182,
      "step": 100
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 1.7879210710525513,
      "learning_rate": 0.00019279279279279282,
      "loss": 0.5843,
      "step": 150
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 2.010268449783325,
      "learning_rate": 0.0001902902902902903,
      "loss": 0.4683,
      "step": 200
    },
    {
      "epoch": 1.4245014245014245,
      "grad_norm": 2.0085535049438477,
      "learning_rate": 0.0001877877877877878,
      "loss": 0.3547,
      "step": 250
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 2.418802261352539,
      "learning_rate": 0.00018528528528528532,
      "loss": 0.3364,
      "step": 300
    },
    {
      "epoch": 1.9943019943019942,
      "grad_norm": 2.5009264945983887,
      "learning_rate": 0.0001827827827827828,
      "loss": 0.366,
      "step": 350
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 2.0691003799438477,
      "learning_rate": 0.00018028028028028027,
      "loss": 0.1792,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 2.531602621078491,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.1762,
      "step": 450
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 2.9127748012542725,
      "learning_rate": 0.00017527527527527528,
      "loss": 0.1918,
      "step": 500
    },
    {
      "epoch": 3.133903133903134,
      "grad_norm": 2.571071147918701,
      "learning_rate": 0.00017277277277277277,
      "loss": 0.1541,
      "step": 550
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 1.5915725231170654,
      "learning_rate": 0.00017027027027027028,
      "loss": 0.1156,
      "step": 600
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 1.2947059869766235,
      "learning_rate": 0.00016776776776776777,
      "loss": 0.1157,
      "step": 650
    },
    {
      "epoch": 3.9886039886039883,
      "grad_norm": 1.7114081382751465,
      "learning_rate": 0.00016526526526526526,
      "loss": 0.1309,
      "step": 700
    },
    {
      "epoch": 4.273504273504273,
      "grad_norm": 2.1177897453308105,
      "learning_rate": 0.00016276276276276275,
      "loss": 0.099,
      "step": 750
    },
    {
      "epoch": 4.5584045584045585,
      "grad_norm": 2.950777292251587,
      "learning_rate": 0.00016026026026026027,
      "loss": 0.1007,
      "step": 800
    },
    {
      "epoch": 4.843304843304844,
      "grad_norm": 2.4155728816986084,
      "learning_rate": 0.00015775775775775776,
      "loss": 0.102,
      "step": 850
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 1.3441689014434814,
      "learning_rate": 0.00015525525525525525,
      "loss": 0.0948,
      "step": 900
    },
    {
      "epoch": 5.413105413105413,
      "grad_norm": 1.041314721107483,
      "learning_rate": 0.00015275275275275277,
      "loss": 0.0851,
      "step": 950
    },
    {
      "epoch": 5.698005698005698,
      "grad_norm": 1.53568696975708,
      "learning_rate": 0.00015025025025025026,
      "loss": 0.0876,
      "step": 1000
    },
    {
      "epoch": 5.982905982905983,
      "grad_norm": 1.0592001676559448,
      "learning_rate": 0.00014774774774774775,
      "loss": 0.0909,
      "step": 1050
    },
    {
      "epoch": 6.267806267806268,
      "grad_norm": 1.4785758256912231,
      "learning_rate": 0.00014524524524524526,
      "loss": 0.0838,
      "step": 1100
    },
    {
      "epoch": 6.552706552706553,
      "grad_norm": 0.6601145267486572,
      "learning_rate": 0.00014274274274274275,
      "loss": 0.0827,
      "step": 1150
    },
    {
      "epoch": 6.837606837606837,
      "grad_norm": 1.1280301809310913,
      "learning_rate": 0.00014024024024024024,
      "loss": 0.0762,
      "step": 1200
    },
    {
      "epoch": 7.122507122507122,
      "grad_norm": 1.467143177986145,
      "learning_rate": 0.00013773773773773776,
      "loss": 0.0799,
      "step": 1250
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 1.773697018623352,
      "learning_rate": 0.00013523523523523525,
      "loss": 0.0765,
      "step": 1300
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 3.1821281909942627,
      "learning_rate": 0.00013273273273273274,
      "loss": 0.0787,
      "step": 1350
    },
    {
      "epoch": 7.977207977207978,
      "grad_norm": 0.9911046028137207,
      "learning_rate": 0.00013023023023023023,
      "loss": 0.0731,
      "step": 1400
    },
    {
      "epoch": 8.262108262108262,
      "grad_norm": 2.560380458831787,
      "learning_rate": 0.00012772772772772775,
      "loss": 0.069,
      "step": 1450
    },
    {
      "epoch": 8.547008547008547,
      "grad_norm": 1.88752281665802,
      "learning_rate": 0.00012522522522522524,
      "loss": 0.0708,
      "step": 1500
    },
    {
      "epoch": 8.831908831908832,
      "grad_norm": 1.3793889284133911,
      "learning_rate": 0.00012272272272272273,
      "loss": 0.0748,
      "step": 1550
    },
    {
      "epoch": 9.116809116809117,
      "grad_norm": 0.7198516130447388,
      "learning_rate": 0.00012022022022022023,
      "loss": 0.0695,
      "step": 1600
    },
    {
      "epoch": 9.401709401709402,
      "grad_norm": 0.4231278896331787,
      "learning_rate": 0.00011771771771771771,
      "loss": 0.0671,
      "step": 1650
    },
    {
      "epoch": 9.686609686609687,
      "grad_norm": 2.0300514698028564,
      "learning_rate": 0.00011521521521521521,
      "loss": 0.0659,
      "step": 1700
    },
    {
      "epoch": 9.971509971509972,
      "grad_norm": 1.0142486095428467,
      "learning_rate": 0.00011271271271271271,
      "loss": 0.0714,
      "step": 1750
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 0.3013649582862854,
      "learning_rate": 0.0001102102102102102,
      "loss": 0.0625,
      "step": 1800
    },
    {
      "epoch": 10.54131054131054,
      "grad_norm": 0.974827766418457,
      "learning_rate": 0.00010770770770770771,
      "loss": 0.0651,
      "step": 1850
    },
    {
      "epoch": 10.826210826210826,
      "grad_norm": 1.0164273977279663,
      "learning_rate": 0.0001052052052052052,
      "loss": 0.066,
      "step": 1900
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.12340305745601654,
      "learning_rate": 0.0001027027027027027,
      "loss": 0.0658,
      "step": 1950
    },
    {
      "epoch": 11.396011396011396,
      "grad_norm": 1.1315168142318726,
      "learning_rate": 0.0001002002002002002,
      "loss": 0.0611,
      "step": 2000
    },
    {
      "epoch": 11.68091168091168,
      "grad_norm": 0.2988643944263458,
      "learning_rate": 9.76976976976977e-05,
      "loss": 0.0607,
      "step": 2050
    },
    {
      "epoch": 11.965811965811966,
      "grad_norm": 0.8949713110923767,
      "learning_rate": 9.51951951951952e-05,
      "loss": 0.0632,
      "step": 2100
    },
    {
      "epoch": 12.250712250712251,
      "grad_norm": 0.11667460948228836,
      "learning_rate": 9.26926926926927e-05,
      "loss": 0.0605,
      "step": 2150
    },
    {
      "epoch": 12.535612535612536,
      "grad_norm": 0.1387569159269333,
      "learning_rate": 9.019019019019019e-05,
      "loss": 0.0605,
      "step": 2200
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 0.4826744794845581,
      "learning_rate": 8.76876876876877e-05,
      "loss": 0.0619,
      "step": 2250
    },
    {
      "epoch": 13.105413105413106,
      "grad_norm": 0.09396378695964813,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.0588,
      "step": 2300
    },
    {
      "epoch": 13.39031339031339,
      "grad_norm": 0.6452879905700684,
      "learning_rate": 8.268268268268269e-05,
      "loss": 0.0584,
      "step": 2350
    },
    {
      "epoch": 13.675213675213675,
      "grad_norm": 0.5694031119346619,
      "learning_rate": 8.018018018018019e-05,
      "loss": 0.0582,
      "step": 2400
    },
    {
      "epoch": 13.96011396011396,
      "grad_norm": 0.34324464201927185,
      "learning_rate": 7.767767767767768e-05,
      "loss": 0.0602,
      "step": 2450
    },
    {
      "epoch": 14.245014245014245,
      "grad_norm": 0.07841510325670242,
      "learning_rate": 7.517517517517519e-05,
      "loss": 0.0593,
      "step": 2500
    },
    {
      "epoch": 14.52991452991453,
      "grad_norm": 0.1685921549797058,
      "learning_rate": 7.267267267267268e-05,
      "loss": 0.0579,
      "step": 2550
    },
    {
      "epoch": 14.814814814814815,
      "grad_norm": 0.32586222887039185,
      "learning_rate": 7.017017017017016e-05,
      "loss": 0.0533,
      "step": 2600
    },
    {
      "epoch": 15.0997150997151,
      "grad_norm": 0.6495370864868164,
      "learning_rate": 6.766766766766767e-05,
      "loss": 0.0575,
      "step": 2650
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 0.10936163365840912,
      "learning_rate": 6.516516516516516e-05,
      "loss": 0.0539,
      "step": 2700
    },
    {
      "epoch": 15.66951566951567,
      "grad_norm": 0.09928351640701294,
      "learning_rate": 6.266266266266266e-05,
      "loss": 0.0573,
      "step": 2750
    },
    {
      "epoch": 15.954415954415955,
      "grad_norm": 0.07429605722427368,
      "learning_rate": 6.016016016016016e-05,
      "loss": 0.0541,
      "step": 2800
    },
    {
      "epoch": 16.23931623931624,
      "grad_norm": 0.0647626668214798,
      "learning_rate": 5.765765765765766e-05,
      "loss": 0.0546,
      "step": 2850
    },
    {
      "epoch": 16.524216524216524,
      "grad_norm": 0.06490299850702286,
      "learning_rate": 5.515515515515516e-05,
      "loss": 0.0537,
      "step": 2900
    },
    {
      "epoch": 16.80911680911681,
      "grad_norm": 0.07492049783468246,
      "learning_rate": 5.2652652652652655e-05,
      "loss": 0.0567,
      "step": 2950
    },
    {
      "epoch": 17.094017094017094,
      "grad_norm": 0.18874266743659973,
      "learning_rate": 5.015015015015015e-05,
      "loss": 0.0534,
      "step": 3000
    },
    {
      "epoch": 17.37891737891738,
      "grad_norm": 0.06696134060621262,
      "learning_rate": 4.764764764764765e-05,
      "loss": 0.0534,
      "step": 3050
    },
    {
      "epoch": 17.663817663817664,
      "grad_norm": 0.07864591479301453,
      "learning_rate": 4.5145145145145146e-05,
      "loss": 0.0543,
      "step": 3100
    },
    {
      "epoch": 17.94871794871795,
      "grad_norm": 0.04788205400109291,
      "learning_rate": 4.264264264264264e-05,
      "loss": 0.055,
      "step": 3150
    },
    {
      "epoch": 18.233618233618234,
      "grad_norm": 0.08312636613845825,
      "learning_rate": 4.014014014014014e-05,
      "loss": 0.0556,
      "step": 3200
    },
    {
      "epoch": 18.51851851851852,
      "grad_norm": 0.050425197929143906,
      "learning_rate": 3.763763763763764e-05,
      "loss": 0.0531,
      "step": 3250
    },
    {
      "epoch": 18.803418803418804,
      "grad_norm": 0.06965469568967819,
      "learning_rate": 3.513513513513514e-05,
      "loss": 0.0533,
      "step": 3300
    },
    {
      "epoch": 19.08831908831909,
      "grad_norm": 0.05819595977663994,
      "learning_rate": 3.263263263263263e-05,
      "loss": 0.0554,
      "step": 3350
    },
    {
      "epoch": 19.373219373219374,
      "grad_norm": 0.06934893876314163,
      "learning_rate": 3.013013013013013e-05,
      "loss": 0.0545,
      "step": 3400
    },
    {
      "epoch": 19.65811965811966,
      "grad_norm": 0.0720212310552597,
      "learning_rate": 2.762762762762763e-05,
      "loss": 0.0524,
      "step": 3450
    },
    {
      "epoch": 19.943019943019944,
      "grad_norm": 0.04772196337580681,
      "learning_rate": 2.5125125125125126e-05,
      "loss": 0.0553,
      "step": 3500
    }
  ],
  "logging_steps": 50,
  "max_steps": 4001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 23,
  "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": 9.530782880523878e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}