{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19461563412260785,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025948751216347712,
      "grad_norm": 114.6451644897461,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 86.6227,
      "step": 1
    },
    {
      "epoch": 0.0025948751216347712,
      "eval_loss": 11.188401222229004,
      "eval_runtime": 240.2405,
      "eval_samples_per_second": 1.353,
      "eval_steps_per_second": 0.678,
      "step": 1
    },
    {
      "epoch": 0.0051897502432695424,
      "grad_norm": 110.34148406982422,
      "learning_rate": 6.666666666666667e-05,
      "loss": 86.6639,
      "step": 2
    },
    {
      "epoch": 0.007784625364904314,
      "grad_norm": 140.974365234375,
      "learning_rate": 0.0001,
      "loss": 86.2836,
      "step": 3
    },
    {
      "epoch": 0.010379500486539085,
      "grad_norm": 107.53729248046875,
      "learning_rate": 9.99524110790929e-05,
      "loss": 76.8209,
      "step": 4
    },
    {
      "epoch": 0.012974375608173857,
      "grad_norm": 58.06427001953125,
      "learning_rate": 9.980973490458728e-05,
      "loss": 70.0069,
      "step": 5
    },
    {
      "epoch": 0.015569250729808628,
      "grad_norm": 63.29356384277344,
      "learning_rate": 9.957224306869053e-05,
      "loss": 53.7268,
      "step": 6
    },
    {
      "epoch": 0.018164125851443398,
      "grad_norm": 64.70842742919922,
      "learning_rate": 9.924038765061042e-05,
      "loss": 43.4032,
      "step": 7
    },
    {
      "epoch": 0.02075900097307817,
      "grad_norm": 66.98622131347656,
      "learning_rate": 9.881480035599667e-05,
      "loss": 30.8297,
      "step": 8
    },
    {
      "epoch": 0.02335387609471294,
      "grad_norm": 75.47815704345703,
      "learning_rate": 9.829629131445342e-05,
      "loss": 19.1012,
      "step": 9
    },
    {
      "epoch": 0.025948751216347713,
      "grad_norm": 59.91986083984375,
      "learning_rate": 9.768584753741134e-05,
      "loss": 7.854,
      "step": 10
    },
    {
      "epoch": 0.028543626337982485,
      "grad_norm": 61.32648468017578,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.9719,
      "step": 11
    },
    {
      "epoch": 0.031138501459617256,
      "grad_norm": 50.40642547607422,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.8169,
      "step": 12
    },
    {
      "epoch": 0.03373337658125203,
      "grad_norm": 39.5262336730957,
      "learning_rate": 9.53153893518325e-05,
      "loss": 3.6317,
      "step": 13
    },
    {
      "epoch": 0.036328251702886796,
      "grad_norm": 34.03517150878906,
      "learning_rate": 9.435054165891109e-05,
      "loss": 2.619,
      "step": 14
    },
    {
      "epoch": 0.03892312682452157,
      "grad_norm": 40.00255584716797,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9728,
      "step": 15
    },
    {
      "epoch": 0.04151800194615634,
      "grad_norm": 62.94084167480469,
      "learning_rate": 9.21695722906443e-05,
      "loss": 2.668,
      "step": 16
    },
    {
      "epoch": 0.044112877067791115,
      "grad_norm": 64.5201416015625,
      "learning_rate": 9.09576022144496e-05,
      "loss": 3.8366,
      "step": 17
    },
    {
      "epoch": 0.04670775218942588,
      "grad_norm": 39.453330993652344,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.834,
      "step": 18
    },
    {
      "epoch": 0.04930262731106066,
      "grad_norm": 74.45320892333984,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.1071,
      "step": 19
    },
    {
      "epoch": 0.051897502432695426,
      "grad_norm": 119.65555572509766,
      "learning_rate": 8.68638668405062e-05,
      "loss": 5.0249,
      "step": 20
    },
    {
      "epoch": 0.054492377554330194,
      "grad_norm": 57.47029113769531,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.8011,
      "step": 21
    },
    {
      "epoch": 0.05708725267596497,
      "grad_norm": 23.485986709594727,
      "learning_rate": 8.377951038078302e-05,
      "loss": 1.008,
      "step": 22
    },
    {
      "epoch": 0.05968212779759974,
      "grad_norm": 15.74601936340332,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6645,
      "step": 23
    },
    {
      "epoch": 0.06227700291923451,
      "grad_norm": 35.179073333740234,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.0041,
      "step": 24
    },
    {
      "epoch": 0.06487187804086929,
      "grad_norm": 35.2408332824707,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.1321,
      "step": 25
    },
    {
      "epoch": 0.06487187804086929,
      "eval_loss": 0.19091396033763885,
      "eval_runtime": 240.1741,
      "eval_samples_per_second": 1.353,
      "eval_steps_per_second": 0.679,
      "step": 25
    },
    {
      "epoch": 0.06746675316250406,
      "grad_norm": 22.732812881469727,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.6565,
      "step": 26
    },
    {
      "epoch": 0.07006162828413882,
      "grad_norm": 9.80388355255127,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2933,
      "step": 27
    },
    {
      "epoch": 0.07265650340577359,
      "grad_norm": 14.081550598144531,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.4886,
      "step": 28
    },
    {
      "epoch": 0.07525137852740837,
      "grad_norm": 16.663516998291016,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.7272,
      "step": 29
    },
    {
      "epoch": 0.07784625364904314,
      "grad_norm": 15.300065040588379,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4666,
      "step": 30
    },
    {
      "epoch": 0.08044112877067791,
      "grad_norm": 40.297645568847656,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5482,
      "step": 31
    },
    {
      "epoch": 0.08303600389231268,
      "grad_norm": 11.791970252990723,
      "learning_rate": 6.503528997521366e-05,
      "loss": 1.3021,
      "step": 32
    },
    {
      "epoch": 0.08563087901394745,
      "grad_norm": 34.81112289428711,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5804,
      "step": 33
    },
    {
      "epoch": 0.08822575413558223,
      "grad_norm": 12.368243217468262,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 1.5155,
      "step": 34
    },
    {
      "epoch": 0.090820629257217,
      "grad_norm": 19.11678123474121,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.9189,
      "step": 35
    },
    {
      "epoch": 0.09341550437885177,
      "grad_norm": 40.73845291137695,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.2073,
      "step": 36
    },
    {
      "epoch": 0.09601037950048653,
      "grad_norm": 30.314462661743164,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.1171,
      "step": 37
    },
    {
      "epoch": 0.09860525462212132,
      "grad_norm": 13.374330520629883,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.3863,
      "step": 38
    },
    {
      "epoch": 0.10120012974375608,
      "grad_norm": 21.539278030395508,
      "learning_rate": 5e-05,
      "loss": 1.2575,
      "step": 39
    },
    {
      "epoch": 0.10379500486539085,
      "grad_norm": 8.351127624511719,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.2764,
      "step": 40
    },
    {
      "epoch": 0.10638987998702562,
      "grad_norm": 29.027982711791992,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.042,
      "step": 41
    },
    {
      "epoch": 0.10898475510866039,
      "grad_norm": 10.286849021911621,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.3774,
      "step": 42
    },
    {
      "epoch": 0.11157963023029517,
      "grad_norm": 2.650897264480591,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0587,
      "step": 43
    },
    {
      "epoch": 0.11417450535192994,
      "grad_norm": 14.90556526184082,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.6228,
      "step": 44
    },
    {
      "epoch": 0.11676938047356471,
      "grad_norm": 3.8510780334472656,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.101,
      "step": 45
    },
    {
      "epoch": 0.11936425559519948,
      "grad_norm": 25.16055679321289,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.8737,
      "step": 46
    },
    {
      "epoch": 0.12195913071683426,
      "grad_norm": 33.220306396484375,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.9121,
      "step": 47
    },
    {
      "epoch": 0.12455400583846903,
      "grad_norm": 30.670238494873047,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5032,
      "step": 48
    },
    {
      "epoch": 0.1271488809601038,
      "grad_norm": 24.66783905029297,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.5967,
      "step": 49
    },
    {
      "epoch": 0.12974375608173858,
      "grad_norm": 48.0320930480957,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 3.6341,
      "step": 50
    },
    {
      "epoch": 0.12974375608173858,
      "eval_loss": 0.18054018914699554,
      "eval_runtime": 239.9435,
      "eval_samples_per_second": 1.354,
      "eval_steps_per_second": 0.679,
      "step": 50
    },
    {
      "epoch": 0.13233863120337333,
      "grad_norm": 31.205846786499023,
      "learning_rate": 2.500000000000001e-05,
      "loss": 5.3168,
      "step": 51
    },
    {
      "epoch": 0.1349335063250081,
      "grad_norm": 14.114444732666016,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.809,
      "step": 52
    },
    {
      "epoch": 0.13752838144664287,
      "grad_norm": 8.728169441223145,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0702,
      "step": 53
    },
    {
      "epoch": 0.14012325656827765,
      "grad_norm": 33.120567321777344,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.9649,
      "step": 54
    },
    {
      "epoch": 0.14271813168991243,
      "grad_norm": 16.788246154785156,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.8312,
      "step": 55
    },
    {
      "epoch": 0.14531300681154719,
      "grad_norm": 14.110865592956543,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.5348,
      "step": 56
    },
    {
      "epoch": 0.14790788193318197,
      "grad_norm": 21.55290412902832,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8498,
      "step": 57
    },
    {
      "epoch": 0.15050275705481675,
      "grad_norm": 24.52911949157715,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.9744,
      "step": 58
    },
    {
      "epoch": 0.1530976321764515,
      "grad_norm": 22.370573043823242,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7237,
      "step": 59
    },
    {
      "epoch": 0.15569250729808629,
      "grad_norm": 15.488335609436035,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.4487,
      "step": 60
    },
    {
      "epoch": 0.15828738241972104,
      "grad_norm": 13.158798217773438,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.3464,
      "step": 61
    },
    {
      "epoch": 0.16088225754135582,
      "grad_norm": 1.3022491931915283,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0314,
      "step": 62
    },
    {
      "epoch": 0.1634771326629906,
      "grad_norm": 5.222805023193359,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.119,
      "step": 63
    },
    {
      "epoch": 0.16607200778462536,
      "grad_norm": 6.309266090393066,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.1355,
      "step": 64
    },
    {
      "epoch": 0.16866688290626014,
      "grad_norm": 19.3297119140625,
      "learning_rate": 4.684610648167503e-06,
      "loss": 1.0106,
      "step": 65
    },
    {
      "epoch": 0.1712617580278949,
      "grad_norm": 58.562843322753906,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.6547,
      "step": 66
    },
    {
      "epoch": 0.17385663314952968,
      "grad_norm": 88.08123016357422,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.2678,
      "step": 67
    },
    {
      "epoch": 0.17645150827116446,
      "grad_norm": 8.794583320617676,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.2489,
      "step": 68
    },
    {
      "epoch": 0.1790463833927992,
      "grad_norm": 46.94881057739258,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.4205,
      "step": 69
    },
    {
      "epoch": 0.181641258514434,
      "grad_norm": 3.1083903312683105,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0701,
      "step": 70
    },
    {
      "epoch": 0.18423613363606878,
      "grad_norm": 12.472285270690918,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2219,
      "step": 71
    },
    {
      "epoch": 0.18683100875770353,
      "grad_norm": 32.516963958740234,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.5728,
      "step": 72
    },
    {
      "epoch": 0.1894258838793383,
      "grad_norm": 50.7675666809082,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 4.1427,
      "step": 73
    },
    {
      "epoch": 0.19202075900097307,
      "grad_norm": 43.09784698486328,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.7928,
      "step": 74
    },
    {
      "epoch": 0.19461563412260785,
      "grad_norm": 45.91943359375,
      "learning_rate": 0.0,
      "loss": 2.4261,
      "step": 75
    },
    {
      "epoch": 0.19461563412260785,
      "eval_loss": 0.1303597092628479,
      "eval_runtime": 240.3643,
      "eval_samples_per_second": 1.352,
      "eval_steps_per_second": 0.678,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.86091809144832e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}