{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 0,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 135.75784301757812,
      "learning_rate": 0.0,
      "loss": 10.6484,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 135.6968536376953,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 10.6641,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 135.83665466308594,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 9.9766,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 57.94816589355469,
      "learning_rate": 8.571428571428571e-06,
      "loss": 3.3945,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 27.795312881469727,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.8257,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 13.902595520019531,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.4709,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 7.484889984130859,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.1921,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.4155075550079346,
      "learning_rate": 2e-05,
      "loss": 0.1349,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 3.3865394592285156,
      "learning_rate": 1.998426815017817e-05,
      "loss": 0.1702,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.4871467053890228,
      "learning_rate": 1.9937122098932428e-05,
      "loss": 0.1534,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.9217754602432251,
      "learning_rate": 1.985871018518236e-05,
      "loss": 0.1285,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.245365023612976,
      "learning_rate": 1.9749279121818235e-05,
      "loss": 0.1144,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 4.214899063110352,
      "learning_rate": 1.9609173219450998e-05,
      "loss": 0.1703,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.2503230571746826,
      "learning_rate": 1.9438833303083677e-05,
      "loss": 0.1322,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.74677973985672,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.1243,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.4760054349899292,
      "learning_rate": 1.900968867902419e-05,
      "loss": 0.1299,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.6457348465919495,
      "learning_rate": 1.8752234219087538e-05,
      "loss": 0.129,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.7069640755653381,
      "learning_rate": 1.8467241992282842e-05,
      "loss": 0.0992,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.7505813837051392,
      "learning_rate": 1.8155608689592604e-05,
      "loss": 0.0886,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.2884610891342163,
      "learning_rate": 1.78183148246803e-05,
      "loss": 0.115,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.54263436794281,
      "learning_rate": 1.7456421648831658e-05,
      "loss": 0.1154,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 1.1725558042526245,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.0932,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.6754504442214966,
      "learning_rate": 1.6663465779520042e-05,
      "loss": 0.0907,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.7802339196205139,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.1005,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.7150468230247498,
      "learning_rate": 1.578671296179806e-05,
      "loss": 0.0739,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.3305799961090088,
      "learning_rate": 1.5320320765153367e-05,
      "loss": 0.0825,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.3834118843078613,
      "learning_rate": 1.4837188871052399e-05,
      "loss": 0.0818,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.0374525785446167,
      "learning_rate": 1.4338837391175582e-05,
      "loss": 0.068,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.7237675786018372,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.0616,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.36288100481033325,
      "learning_rate": 1.3302790619551673e-05,
      "loss": 0.0495,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 1.4335401058197021,
      "learning_rate": 1.2768355114248493e-05,
      "loss": 0.0898,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.8492462635040283,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 0.0441,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.5347748398780823,
      "learning_rate": 1.1675062233047365e-05,
      "loss": 0.049,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.7263269424438477,
      "learning_rate": 1.1119644761033079e-05,
      "loss": 0.0894,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.4866464138031006,
      "learning_rate": 1.0560704472371919e-05,
      "loss": 0.0464,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.6330035328865051,
      "learning_rate": 1e-05,
      "loss": 0.0498,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.7745473384857178,
      "learning_rate": 9.439295527628083e-06,
      "loss": 0.0573,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.5323076844215393,
      "learning_rate": 8.880355238966923e-06,
      "loss": 0.0571,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4111030101776123,
      "learning_rate": 8.324937766952638e-06,
      "loss": 0.0349,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.8452009558677673,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.0701,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.6247994899749756,
      "learning_rate": 7.2316448857515076e-06,
      "loss": 0.0537,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2583736479282379,
      "learning_rate": 6.697209380448333e-06,
      "loss": 0.0371,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.3620803654193878,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.0321,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.5690107941627502,
      "learning_rate": 5.66116260882442e-06,
      "loss": 0.0545,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.3473432958126068,
      "learning_rate": 5.1628111289476025e-06,
      "loss": 0.0253,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.7409687042236328,
      "learning_rate": 4.679679234846636e-06,
      "loss": 0.0504,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.37499386072158813,
      "learning_rate": 4.213287038201943e-06,
      "loss": 0.0336,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.26719093322753906,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.0186,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.3391411602497101,
      "learning_rate": 3.3365342204799613e-06,
      "loss": 0.0282,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.3170095682144165,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.0251,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.2487771213054657,
      "learning_rate": 2.5435783511683444e-06,
      "loss": 0.0274,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.4128139019012451,
      "learning_rate": 2.1816851753197023e-06,
      "loss": 0.0292,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.6280130743980408,
      "learning_rate": 1.8443913104073984e-06,
      "loss": 0.0423,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.48291048407554626,
      "learning_rate": 1.5327580077171589e-06,
      "loss": 0.022,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.508919358253479,
      "learning_rate": 1.2477657809124632e-06,
      "loss": 0.0444,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.3738269805908203,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.0291,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.25037050247192383,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.0239,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.30901408195495605,
      "learning_rate": 5.611666969163243e-07,
      "loss": 0.021,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.6213399767875671,
      "learning_rate": 3.908267805490051e-07,
      "loss": 0.0327,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.2997397780418396,
      "learning_rate": 2.507208781817638e-07,
      "loss": 0.0316,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.3204822540283203,
      "learning_rate": 1.4128981481764115e-07,
      "loss": 0.0299,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.39552855491638184,
      "learning_rate": 6.287790106757396e-08,
      "loss": 0.0235,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5192532539367676,
      "learning_rate": 1.5731849821833955e-08,
      "loss": 0.0399,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0854328659083264e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}