{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 5.302074700564879,
      "learning_rate": 6.578947368421053e-07,
      "loss": 0.8677,
      "step": 10
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 2.3539338952660676,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 0.7536,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.3061427287792207,
      "learning_rate": 1.973684210526316e-06,
      "loss": 0.6719,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.7706136132278263,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.6226,
      "step": 40
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 2.31915144001752,
      "learning_rate": 3.289473684210527e-06,
      "loss": 0.5929,
      "step": 50
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 3.6318279241243174,
      "learning_rate": 3.947368421052632e-06,
      "loss": 0.5717,
      "step": 60
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 5.466002436425688,
      "learning_rate": 4.605263157894737e-06,
      "loss": 0.56,
      "step": 70
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.658157430170319,
      "learning_rate": 4.998922515567496e-06,
      "loss": 0.5529,
      "step": 80
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 2.958620225945063,
      "learning_rate": 4.986811479610213e-06,
      "loss": 0.5459,
      "step": 90
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 2.3621141521204074,
      "learning_rate": 4.9613079925074435e-06,
      "loss": 0.5336,
      "step": 100
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 2.132170449736533,
      "learning_rate": 4.922549400498685e-06,
      "loss": 0.5296,
      "step": 110
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.422127656789715,
      "learning_rate": 4.870744433740688e-06,
      "loss": 0.52,
      "step": 120
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 3.209901466327175,
      "learning_rate": 4.806172082214032e-06,
      "loss": 0.5164,
      "step": 130
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.3530816407534223,
      "learning_rate": 4.729180093253106e-06,
      "loss": 0.5092,
      "step": 140
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.0107372006602007,
      "learning_rate": 4.640183098790896e-06,
      "loss": 0.5046,
      "step": 150
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.6986015532338576,
      "learning_rate": 4.53966038240406e-06,
      "loss": 0.4983,
      "step": 160
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.061965156346559525,
      "eval_runtime": 175.8558,
      "eval_samples_per_second": 102.942,
      "eval_steps_per_second": 0.404,
      "step": 168
    },
    {
      "epoch": 1.0119047619047619,
      "grad_norm": 2.0617265758036574,
      "learning_rate": 4.428153298183676e-06,
      "loss": 0.4899,
      "step": 170
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 2.461751865882228,
      "learning_rate": 4.306262355332006e-06,
      "loss": 0.4566,
      "step": 180
    },
    {
      "epoch": 1.130952380952381,
      "grad_norm": 2.540542988750059,
      "learning_rate": 4.17464398418589e-06,
      "loss": 0.4541,
      "step": 190
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.908700820605462,
      "learning_rate": 4.034007001082985e-06,
      "loss": 0.4525,
      "step": 200
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.3119343985161747,
      "learning_rate": 3.8851087911089315e-06,
      "loss": 0.4533,
      "step": 210
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 2.004423567844585,
      "learning_rate": 3.7287512292828364e-06,
      "loss": 0.4491,
      "step": 220
    },
    {
      "epoch": 1.369047619047619,
      "grad_norm": 2.5928234091324764,
      "learning_rate": 3.5657763621470905e-06,
      "loss": 0.4493,
      "step": 230
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.8913706584793621,
      "learning_rate": 3.39706187301784e-06,
      "loss": 0.4476,
      "step": 240
    },
    {
      "epoch": 1.4880952380952381,
      "grad_norm": 2.058386268253094,
      "learning_rate": 3.2235163553175174e-06,
      "loss": 0.4437,
      "step": 250
    },
    {
      "epoch": 1.5476190476190477,
      "grad_norm": 1.9521413891863681,
      "learning_rate": 3.0460744194443658e-06,
      "loss": 0.4423,
      "step": 260
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 1.652934076293377,
      "learning_rate": 2.8656916595304026e-06,
      "loss": 0.44,
      "step": 270
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.4254067692233685,
      "learning_rate": 2.68333950719376e-06,
      "loss": 0.4404,
      "step": 280
    },
    {
      "epoch": 1.7261904761904763,
      "grad_norm": 1.9096049494562852,
      "learning_rate": 2.5e-06,
      "loss": 0.4397,
      "step": 290
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.2870553552525479,
      "learning_rate": 2.3166604928062407e-06,
      "loss": 0.4351,
      "step": 300
    },
    {
      "epoch": 1.8452380952380953,
      "grad_norm": 1.2328177499933723,
      "learning_rate": 2.1343083404695987e-06,
      "loss": 0.4341,
      "step": 310
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 1.3465694131057355,
      "learning_rate": 1.9539255805556346e-06,
      "loss": 0.4338,
      "step": 320
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 1.2032285531530662,
      "learning_rate": 1.7764836446824835e-06,
      "loss": 0.4333,
      "step": 330
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.05795557424426079,
      "eval_runtime": 175.972,
      "eval_samples_per_second": 102.874,
      "eval_steps_per_second": 0.403,
      "step": 336
    },
    {
      "epoch": 2.0238095238095237,
      "grad_norm": 1.789131444902922,
      "learning_rate": 1.6029381269821607e-06,
      "loss": 0.414,
      "step": 340
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 1.3420020277085403,
      "learning_rate": 1.4342236378529106e-06,
      "loss": 0.3888,
      "step": 350
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 1.1852540907855833,
      "learning_rate": 1.2712487707171645e-06,
      "loss": 0.3841,
      "step": 360
    },
    {
      "epoch": 2.2023809523809526,
      "grad_norm": 1.6133303890307713,
      "learning_rate": 1.1148912088910687e-06,
      "loss": 0.3837,
      "step": 370
    },
    {
      "epoch": 2.261904761904762,
      "grad_norm": 0.892698173344749,
      "learning_rate": 9.659929989170156e-07,
      "loss": 0.3863,
      "step": 380
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.8511252404619682,
      "learning_rate": 8.253560158141111e-07,
      "loss": 0.3825,
      "step": 390
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.7995163038995144,
      "learning_rate": 6.93737644667995e-07,
      "loss": 0.3817,
      "step": 400
    },
    {
      "epoch": 2.4404761904761907,
      "grad_norm": 0.6938195822302593,
      "learning_rate": 5.718467018163243e-07,
      "loss": 0.3816,
      "step": 410
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.7359496640818899,
      "learning_rate": 4.6033961759594045e-07,
      "loss": 0.3815,
      "step": 420
    },
    {
      "epoch": 2.5595238095238093,
      "grad_norm": 0.7334287317942382,
      "learning_rate": 3.598169012091049e-07,
      "loss": 0.3829,
      "step": 430
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.6722577072763187,
      "learning_rate": 2.708199067468939e-07,
      "loss": 0.3837,
      "step": 440
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.7090527130304488,
      "learning_rate": 1.9382791778596864e-07,
      "loss": 0.3818,
      "step": 450
    },
    {
      "epoch": 2.738095238095238,
      "grad_norm": 0.6664042341300833,
      "learning_rate": 1.2925556625931174e-07,
      "loss": 0.3828,
      "step": 460
    },
    {
      "epoch": 2.7976190476190474,
      "grad_norm": 0.6629290902040299,
      "learning_rate": 7.7450599501315e-08,
      "loss": 0.3819,
      "step": 470
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6540655845446479,
      "learning_rate": 3.869200749255703e-08,
      "loss": 0.3815,
      "step": 480
    },
    {
      "epoch": 2.9166666666666665,
      "grad_norm": 0.6419630459088013,
      "learning_rate": 1.3188520389787462e-08,
      "loss": 0.3791,
      "step": 490
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 0.6685967829333805,
      "learning_rate": 1.0774844325039946e-09,
      "loss": 0.3811,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.057990334928035736,
      "eval_runtime": 175.1942,
      "eval_samples_per_second": 103.331,
      "eval_steps_per_second": 0.405,
      "step": 504
    },
    {
      "epoch": 3.0,
      "step": 504,
      "total_flos": 3376037568184320.0,
      "train_loss": 0.46887724030585515,
      "train_runtime": 29847.5634,
      "train_samples_per_second": 34.571,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3376037568184320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}