{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012903225806451613,
      "grad_norm": 26.093698501586914,
      "learning_rate": 2.422680412371134e-05,
      "loss": 21.547802734375,
      "step": 50
    },
    {
      "epoch": 0.025806451612903226,
      "grad_norm": 8.91745376586914,
      "learning_rate": 5e-05,
      "loss": 7.79892578125,
      "step": 100
    },
    {
      "epoch": 0.03870967741935484,
      "grad_norm": 15.630369186401367,
      "learning_rate": 7.577319587628867e-05,
      "loss": 3.3275311279296873,
      "step": 150
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 5.726988315582275,
      "learning_rate": 0.00010154639175257732,
      "loss": 2.767955322265625,
      "step": 200
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 4.718327045440674,
      "learning_rate": 0.00012731958762886598,
      "loss": 2.490103912353516,
      "step": 250
    },
    {
      "epoch": 0.07741935483870968,
      "grad_norm": 5.474207878112793,
      "learning_rate": 0.00015309278350515463,
      "loss": 2.3953448486328126,
      "step": 300
    },
    {
      "epoch": 0.09032258064516129,
      "grad_norm": 4.799027442932129,
      "learning_rate": 0.00017886597938144332,
      "loss": 2.3500601196289064,
      "step": 350
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 3.088228225708008,
      "learning_rate": 0.00019999671263070532,
      "loss": 2.08624755859375,
      "step": 400
    },
    {
      "epoch": 0.11612903225806452,
      "grad_norm": 4.027886390686035,
      "learning_rate": 0.00019985875677783286,
      "loss": 2.299346618652344,
      "step": 450
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 2.617861747741699,
      "learning_rate": 0.0001995181966653377,
      "loss": 2.076806945800781,
      "step": 500
    },
    {
      "epoch": 0.14193548387096774,
      "grad_norm": 2.939183235168457,
      "learning_rate": 0.00019897572325845597,
      "loss": 1.9734559631347657,
      "step": 550
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 3.2188785076141357,
      "learning_rate": 0.0001982324371859808,
      "loss": 2.0425050354003904,
      "step": 600
    },
    {
      "epoch": 0.16774193548387098,
      "grad_norm": 2.385723829269409,
      "learning_rate": 0.0001972898465071878,
      "loss": 1.7387680053710937,
      "step": 650
    },
    {
      "epoch": 0.18064516129032257,
      "grad_norm": 2.0678470134735107,
      "learning_rate": 0.00019614986365212075,
      "loss": 1.9845478820800782,
      "step": 700
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 2.6310617923736572,
      "learning_rate": 0.00019481480154144674,
      "loss": 1.9621870422363281,
      "step": 750
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 2.003772497177124,
      "learning_rate": 0.00019328736889375194,
      "loss": 1.679602813720703,
      "step": 800
    },
    {
      "epoch": 0.21935483870967742,
      "grad_norm": 1.7277588844299316,
      "learning_rate": 0.0001915706647298003,
      "loss": 1.7411506652832032,
      "step": 850
    },
    {
      "epoch": 0.23225806451612904,
      "grad_norm": 1.8283025026321411,
      "learning_rate": 0.00018966817208490436,
      "loss": 1.7389830017089845,
      "step": 900
    },
    {
      "epoch": 0.24516129032258063,
      "grad_norm": 1.9952781200408936,
      "learning_rate": 0.00018758375094216623,
      "loss": 1.8508444213867188,
      "step": 950
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 1.729681134223938,
      "learning_rate": 0.00018532163040092573,
      "loss": 1.8801399230957032,
      "step": 1000
    },
    {
      "epoch": 0.2709677419354839,
      "grad_norm": 1.6578916311264038,
      "learning_rate": 0.00018288640009630572,
      "loss": 1.7960881042480468,
      "step": 1050
    },
    {
      "epoch": 0.2838709677419355,
      "grad_norm": 2.551797389984131,
      "learning_rate": 0.00018028300088726343,
      "loss": 2.0008944702148437,
      "step": 1100
    },
    {
      "epoch": 0.2967741935483871,
      "grad_norm": 1.433000087738037,
      "learning_rate": 0.0001775167148320406,
      "loss": 1.9145297241210937,
      "step": 1150
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 1.8882386684417725,
      "learning_rate": 0.0001745931544713518,
      "loss": 1.7149647521972655,
      "step": 1200
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 1.8606927394866943,
      "learning_rate": 0.00017151825144105407,
      "loss": 1.8581932067871094,
      "step": 1250
    },
    {
      "epoch": 0.33548387096774196,
      "grad_norm": 1.9521467685699463,
      "learning_rate": 0.0001682982444374016,
      "loss": 1.885094451904297,
      "step": 1300
    },
    {
      "epoch": 0.34838709677419355,
      "grad_norm": 1.683640956878662,
      "learning_rate": 0.00016493966655930345,
      "loss": 1.8922116088867187,
      "step": 1350
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 1.5866836309432983,
      "learning_rate": 0.00016144933205326464,
      "loss": 1.601314239501953,
      "step": 1400
    },
    {
      "epoch": 0.3741935483870968,
      "grad_norm": 1.6596488952636719,
      "learning_rate": 0.00015783432248790515,
      "loss": 1.5874720764160157,
      "step": 1450
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 1.682254672050476,
      "learning_rate": 0.00015410197238610671,
      "loss": 1.7112892150878907,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.7930126190185547,
      "learning_rate": 0.00015025985434393826,
      "loss": 1.7229920959472655,
      "step": 1550
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 1.803107500076294,
      "learning_rate": 0.00014631576366655314,
      "loss": 1.767000732421875,
      "step": 1600
    },
    {
      "epoch": 0.4258064516129032,
      "grad_norm": 1.7437456846237183,
      "learning_rate": 0.00014227770255222975,
      "loss": 1.4893592834472655,
      "step": 1650
    },
    {
      "epoch": 0.43870967741935485,
      "grad_norm": 1.5099666118621826,
      "learning_rate": 0.00013815386385664525,
      "loss": 1.6000193786621093,
      "step": 1700
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 1.3937677145004272,
      "learning_rate": 0.00013395261447032267,
      "loss": 1.6117967224121095,
      "step": 1750
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 1.4220941066741943,
      "learning_rate": 0.00012968247834297728,
      "loss": 1.7979049682617188,
      "step": 1800
    },
    {
      "epoch": 0.4774193548387097,
      "grad_norm": 1.9548654556274414,
      "learning_rate": 0.00012535211918920447,
      "loss": 1.565934295654297,
      "step": 1850
    },
    {
      "epoch": 0.49032258064516127,
      "grad_norm": 1.7108862400054932,
      "learning_rate": 0.00012097032291059718,
      "loss": 1.6084927368164061,
      "step": 1900
    },
    {
      "epoch": 0.5032258064516129,
      "grad_norm": 1.0150501728057861,
      "learning_rate": 0.0001165459797699575,
      "loss": 1.5946754455566405,
      "step": 1950
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 1.469245195388794,
      "learning_rate": 0.00011208806635376871,
      "loss": 1.6331881713867187,
      "step": 2000
    },
    {
      "epoch": 0.5290322580645161,
      "grad_norm": 2.031064510345459,
      "learning_rate": 0.00010760562735952446,
      "loss": 1.5287588500976563,
      "step": 2050
    },
    {
      "epoch": 0.5419354838709678,
      "grad_norm": 1.480450987815857,
      "learning_rate": 0.00010310775724486713,
      "loss": 1.5194261169433594,
      "step": 2100
    },
    {
      "epoch": 0.5548387096774193,
      "grad_norm": 1.740302562713623,
      "learning_rate": 9.860358177576719e-05,
      "loss": 1.515797119140625,
      "step": 2150
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 1.1037625074386597,
      "learning_rate": 9.410223951118099e-05,
      "loss": 1.611996612548828,
      "step": 2200
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 1.4843175411224365,
      "learning_rate": 8.961286326175288e-05,
      "loss": 1.5870240783691407,
      "step": 2250
    },
    {
      "epoch": 0.5935483870967742,
      "grad_norm": 1.6576191186904907,
      "learning_rate": 8.514456156017973e-05,
      "loss": 1.5969232177734376,
      "step": 2300
    },
    {
      "epoch": 0.6064516129032258,
      "grad_norm": 1.569069266319275,
      "learning_rate": 8.070640018083358e-05,
      "loss": 1.6783047485351563,
      "step": 2350
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 1.367903232574463,
      "learning_rate": 7.630738374613674e-05,
      "loss": 1.4527403259277343,
      "step": 2400
    },
    {
      "epoch": 0.632258064516129,
      "grad_norm": 1.4572464227676392,
      "learning_rate": 7.195643745700882e-05,
      "loss": 1.5939321899414063,
      "step": 2450
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 1.1555101871490479,
      "learning_rate": 6.766238898445239e-05,
      "loss": 1.634443817138672,
      "step": 2500
    },
    {
      "epoch": 0.6580645161290323,
      "grad_norm": 1.4471911191940308,
      "learning_rate": 6.343395055901829e-05,
      "loss": 1.5031852722167969,
      "step": 2550
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 1.2475024461746216,
      "learning_rate": 5.927970129448871e-05,
      "loss": 1.509783935546875,
      "step": 2600
    },
    {
      "epoch": 0.6838709677419355,
      "grad_norm": 1.5671921968460083,
      "learning_rate": 5.520806978164216e-05,
      "loss": 1.409991455078125,
      "step": 2650
    },
    {
      "epoch": 0.6967741935483871,
      "grad_norm": 1.1135592460632324,
      "learning_rate": 5.1227316987415655e-05,
      "loss": 1.3631683349609376,
      "step": 2700
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 1.555723786354065,
      "learning_rate": 4.734551949416049e-05,
      "loss": 1.369638671875,
      "step": 2750
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 1.2914938926696777,
      "learning_rate": 4.357055311299736e-05,
      "loss": 1.3853286743164062,
      "step": 2800
    },
    {
      "epoch": 0.7354838709677419,
      "grad_norm": 1.6594687700271606,
      "learning_rate": 3.991007690451778e-05,
      "loss": 1.5454405212402345,
      "step": 2850
    },
    {
      "epoch": 0.7483870967741936,
      "grad_norm": 1.830759048461914,
      "learning_rate": 3.637151763925264e-05,
      "loss": 1.4219670104980469,
      "step": 2900
    },
    {
      "epoch": 0.7612903225806451,
      "grad_norm": 1.1424579620361328,
      "learning_rate": 3.2962054729435746e-05,
      "loss": 1.5119563293457032,
      "step": 2950
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 1.5165542364120483,
      "learning_rate": 2.9688605662634995e-05,
      "loss": 1.5604460144042969,
      "step": 3000
    },
    {
      "epoch": 0.7870967741935484,
      "grad_norm": 1.5374443531036377,
      "learning_rate": 2.6557811966804434e-05,
      "loss": 1.5612307739257814,
      "step": 3050
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.339760661125183,
      "learning_rate": 2.3576025735233e-05,
      "loss": 1.3077503967285156,
      "step": 3100
    },
    {
      "epoch": 0.8129032258064516,
      "grad_norm": 1.3324717283248901,
      "learning_rate": 2.074929673872993e-05,
      "loss": 1.3773248291015625,
      "step": 3150
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 1.319914698600769,
      "learning_rate": 1.8083360151194552e-05,
      "loss": 1.4230650329589845,
      "step": 3200
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 1.2368086576461792,
      "learning_rate": 1.558362491347439e-05,
      "loss": 1.56116943359375,
      "step": 3250
    },
    {
      "epoch": 0.8516129032258064,
      "grad_norm": 0.9475931525230408,
      "learning_rate": 1.3255162759120244e-05,
      "loss": 1.3454847717285157,
      "step": 3300
    },
    {
      "epoch": 0.864516129032258,
      "grad_norm": 1.114356517791748,
      "learning_rate": 1.1102697924303929e-05,
      "loss": 1.4919425964355468,
      "step": 3350
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 1.0553752183914185,
      "learning_rate": 9.130597562776344e-06,
      "loss": 1.3608793640136718,
      "step": 3400
    },
    {
      "epoch": 0.8903225806451613,
      "grad_norm": 1.1978603601455688,
      "learning_rate": 7.342862885312984e-06,
      "loss": 1.4629544067382811,
      "step": 3450
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 1.3607312440872192,
      "learning_rate": 5.743121041624277e-06,
      "loss": 1.4121296691894532,
      "step": 3500
    },
    {
      "epoch": 0.9161290322580645,
      "grad_norm": 1.5344407558441162,
      "learning_rate": 4.3346177612014316e-06,
      "loss": 1.5250901794433593,
      "step": 3550
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 1.4118343591690063,
      "learning_rate": 3.1202107680289193e-06,
      "loss": 1.4813092041015625,
      "step": 3600
    },
    {
      "epoch": 0.9419354838709677,
      "grad_norm": 1.1738020181655884,
      "learning_rate": 2.1023639825246687e-06,
      "loss": 1.5152850341796875,
      "step": 3650
    },
    {
      "epoch": 0.9548387096774194,
      "grad_norm": 2.446970224380493,
      "learning_rate": 1.2831425224714367e-06,
      "loss": 1.462032012939453,
      "step": 3700
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 1.3216476440429688,
      "learning_rate": 6.64208513082254e-07,
      "loss": 1.5554815673828124,
      "step": 3750
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 1.6872673034667969,
      "learning_rate": 2.468177147007533e-07,
      "loss": 1.4851766967773437,
      "step": 3800
    },
    {
      "epoch": 0.9935483870967742,
      "grad_norm": 1.6682299375534058,
      "learning_rate": 3.181697497863789e-08,
      "loss": 1.4984014892578126,
      "step": 3850
    }
  ],
  "logging_steps": 50,
  "max_steps": 3875,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.799738953703045e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}