{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005614783725549371,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.614783725549371e-06,
      "grad_norm": 1.063336968421936,
      "learning_rate": 0.0002,
      "loss": 1.0718,
      "step": 1
    },
    {
      "epoch": 5.614783725549371e-06,
      "eval_loss": 1.0175169706344604,
      "eval_runtime": 13561.1744,
      "eval_samples_per_second": 2.765,
      "eval_steps_per_second": 2.765,
      "step": 1
    },
    {
      "epoch": 1.1229567451098743e-05,
      "grad_norm": 0.9254959225654602,
      "learning_rate": 0.0004,
      "loss": 1.26,
      "step": 2
    },
    {
      "epoch": 1.6844351176648115e-05,
      "grad_norm": 0.4091038107872009,
      "learning_rate": 0.0006,
      "loss": 0.7047,
      "step": 3
    },
    {
      "epoch": 2.2459134902197485e-05,
      "grad_norm": 0.8800899982452393,
      "learning_rate": 0.0008,
      "loss": 0.9239,
      "step": 4
    },
    {
      "epoch": 2.8073918627746856e-05,
      "grad_norm": 1.2747443914413452,
      "learning_rate": 0.001,
      "loss": 0.7746,
      "step": 5
    },
    {
      "epoch": 3.368870235329623e-05,
      "grad_norm": 1.434735894203186,
      "learning_rate": 0.0012,
      "loss": 1.1616,
      "step": 6
    },
    {
      "epoch": 3.9303486078845604e-05,
      "grad_norm": 1.1246367692947388,
      "learning_rate": 0.0014,
      "loss": 0.7168,
      "step": 7
    },
    {
      "epoch": 4.491826980439497e-05,
      "grad_norm": 0.9489652514457703,
      "learning_rate": 0.0016,
      "loss": 0.9415,
      "step": 8
    },
    {
      "epoch": 5.0533053529944345e-05,
      "grad_norm": 0.6757056713104248,
      "learning_rate": 0.0018000000000000002,
      "loss": 0.6533,
      "step": 9
    },
    {
      "epoch": 5.614783725549371e-05,
      "grad_norm": 1.3025261163711548,
      "learning_rate": 0.002,
      "loss": 0.6712,
      "step": 10
    },
    {
      "epoch": 6.176262098104309e-05,
      "grad_norm": 1.0577226877212524,
      "learning_rate": 0.0019993908270190958,
      "loss": 0.7631,
      "step": 11
    },
    {
      "epoch": 6.737740470659246e-05,
      "grad_norm": 1.5588256120681763,
      "learning_rate": 0.0019975640502598244,
      "loss": 1.1228,
      "step": 12
    },
    {
      "epoch": 7.299218843214183e-05,
      "grad_norm": 1.1976680755615234,
      "learning_rate": 0.0019945218953682734,
      "loss": 0.6171,
      "step": 13
    },
    {
      "epoch": 7.860697215769121e-05,
      "grad_norm": 1.1977174282073975,
      "learning_rate": 0.0019902680687415705,
      "loss": 0.7131,
      "step": 14
    },
    {
      "epoch": 8.422175588324057e-05,
      "grad_norm": 1.8031384944915771,
      "learning_rate": 0.001984807753012208,
      "loss": 1.1394,
      "step": 15
    },
    {
      "epoch": 8.983653960878994e-05,
      "grad_norm": 2.389751434326172,
      "learning_rate": 0.0019781476007338056,
      "loss": 0.822,
      "step": 16
    },
    {
      "epoch": 9.545132333433932e-05,
      "grad_norm": 2.088827610015869,
      "learning_rate": 0.0019702957262759963,
      "loss": 1.0301,
      "step": 17
    },
    {
      "epoch": 0.00010106610705988869,
      "grad_norm": 1.35056734085083,
      "learning_rate": 0.001961261695938319,
      "loss": 0.6762,
      "step": 18
    },
    {
      "epoch": 0.00010668089078543806,
      "grad_norm": 1.7480477094650269,
      "learning_rate": 0.0019510565162951536,
      "loss": 0.9004,
      "step": 19
    },
    {
      "epoch": 0.00011229567451098742,
      "grad_norm": 1.480393409729004,
      "learning_rate": 0.0019396926207859084,
      "loss": 0.9562,
      "step": 20
    },
    {
      "epoch": 0.0001179104582365368,
      "grad_norm": 1.6566611528396606,
      "learning_rate": 0.0019271838545667874,
      "loss": 0.8456,
      "step": 21
    },
    {
      "epoch": 0.00012352524196208617,
      "grad_norm": 1.7289091348648071,
      "learning_rate": 0.001913545457642601,
      "loss": 1.0861,
      "step": 22
    },
    {
      "epoch": 0.00012914002568763553,
      "grad_norm": 2.511488914489746,
      "learning_rate": 0.001898794046299167,
      "loss": 0.9673,
      "step": 23
    },
    {
      "epoch": 0.00013475480941318492,
      "grad_norm": 2.9465174674987793,
      "learning_rate": 0.001882947592858927,
      "loss": 1.0684,
      "step": 24
    },
    {
      "epoch": 0.00014036959313873428,
      "grad_norm": 2.350576400756836,
      "learning_rate": 0.001866025403784439,
      "loss": 1.1737,
      "step": 25
    },
    {
      "epoch": 0.00014036959313873428,
      "eval_loss": 1.0244402885437012,
      "eval_runtime": 13567.5847,
      "eval_samples_per_second": 2.764,
      "eval_steps_per_second": 2.764,
      "step": 25
    },
    {
      "epoch": 0.00014598437686428367,
      "grad_norm": 2.190694570541382,
      "learning_rate": 0.0018480480961564258,
      "loss": 0.9693,
      "step": 26
    },
    {
      "epoch": 0.00015159916058983303,
      "grad_norm": 3.3499956130981445,
      "learning_rate": 0.0018290375725550417,
      "loss": 1.3869,
      "step": 27
    },
    {
      "epoch": 0.00015721394431538241,
      "grad_norm": 2.3959763050079346,
      "learning_rate": 0.0018090169943749475,
      "loss": 0.9052,
      "step": 28
    },
    {
      "epoch": 0.00016282872804093177,
      "grad_norm": 1.8362096548080444,
      "learning_rate": 0.0017880107536067218,
      "loss": 1.1557,
      "step": 29
    },
    {
      "epoch": 0.00016844351176648113,
      "grad_norm": 2.4866271018981934,
      "learning_rate": 0.001766044443118978,
      "loss": 1.2626,
      "step": 30
    },
    {
      "epoch": 0.00017405829549203052,
      "grad_norm": 3.59562349319458,
      "learning_rate": 0.0017431448254773942,
      "loss": 1.3407,
      "step": 31
    },
    {
      "epoch": 0.00017967307921757988,
      "grad_norm": 2.424304723739624,
      "learning_rate": 0.001719339800338651,
      "loss": 0.9181,
      "step": 32
    },
    {
      "epoch": 0.00018528786294312927,
      "grad_norm": 3.3184380531311035,
      "learning_rate": 0.0016946583704589974,
      "loss": 0.9443,
      "step": 33
    },
    {
      "epoch": 0.00019090264666867863,
      "grad_norm": 3.005448579788208,
      "learning_rate": 0.0016691306063588583,
      "loss": 1.0322,
      "step": 34
    },
    {
      "epoch": 0.000196517430394228,
      "grad_norm": 1.865719199180603,
      "learning_rate": 0.0016427876096865393,
      "loss": 0.8881,
      "step": 35
    },
    {
      "epoch": 0.00020213221411977738,
      "grad_norm": 1.9284836053848267,
      "learning_rate": 0.0016156614753256582,
      "loss": 1.0125,
      "step": 36
    },
    {
      "epoch": 0.00020774699784532674,
      "grad_norm": 3.410578489303589,
      "learning_rate": 0.0015877852522924731,
      "loss": 1.1619,
      "step": 37
    },
    {
      "epoch": 0.00021336178157087613,
      "grad_norm": 2.3564658164978027,
      "learning_rate": 0.0015591929034707468,
      "loss": 1.3581,
      "step": 38
    },
    {
      "epoch": 0.00021897656529642549,
      "grad_norm": 1.6943787336349487,
      "learning_rate": 0.001529919264233205,
      "loss": 0.7817,
      "step": 39
    },
    {
      "epoch": 0.00022459134902197485,
      "grad_norm": 2.2240307331085205,
      "learning_rate": 0.0015,
      "loss": 0.8353,
      "step": 40
    },
    {
      "epoch": 0.00023020613274752423,
      "grad_norm": 3.0564215183258057,
      "learning_rate": 0.0014694715627858908,
      "loss": 1.0998,
      "step": 41
    },
    {
      "epoch": 0.0002358209164730736,
      "grad_norm": 3.891338348388672,
      "learning_rate": 0.0014383711467890773,
      "loss": 1.4342,
      "step": 42
    },
    {
      "epoch": 0.00024143570019862298,
      "grad_norm": 1.7128349542617798,
      "learning_rate": 0.0014067366430758003,
      "loss": 0.9709,
      "step": 43
    },
    {
      "epoch": 0.00024705048392417234,
      "grad_norm": 4.62891960144043,
      "learning_rate": 0.0013746065934159121,
      "loss": 1.0202,
      "step": 44
    },
    {
      "epoch": 0.00025266526764972173,
      "grad_norm": 4.355927467346191,
      "learning_rate": 0.0013420201433256688,
      "loss": 1.0459,
      "step": 45
    },
    {
      "epoch": 0.00025828005137527106,
      "grad_norm": 2.2983617782592773,
      "learning_rate": 0.0013090169943749475,
      "loss": 1.1911,
      "step": 46
    },
    {
      "epoch": 0.00026389483510082045,
      "grad_norm": 2.7273306846618652,
      "learning_rate": 0.0012756373558169992,
      "loss": 0.6804,
      "step": 47
    },
    {
      "epoch": 0.00026950961882636984,
      "grad_norm": 3.133652687072754,
      "learning_rate": 0.0012419218955996676,
      "loss": 0.9479,
      "step": 48
    },
    {
      "epoch": 0.0002751244025519192,
      "grad_norm": 1.5990813970565796,
      "learning_rate": 0.0012079116908177592,
      "loss": 1.1125,
      "step": 49
    },
    {
      "epoch": 0.00028073918627746856,
      "grad_norm": 3.576906204223633,
      "learning_rate": 0.0011736481776669307,
      "loss": 1.1765,
      "step": 50
    },
    {
      "epoch": 0.00028073918627746856,
      "eval_loss": 1.0542502403259277,
      "eval_runtime": 13596.4994,
      "eval_samples_per_second": 2.758,
      "eval_steps_per_second": 2.758,
      "step": 50
    },
    {
      "epoch": 0.00028635397000301795,
      "grad_norm": 3.177819013595581,
      "learning_rate": 0.0011391731009600654,
      "loss": 1.0826,
      "step": 51
    },
    {
      "epoch": 0.00029196875372856733,
      "grad_norm": 1.8690358400344849,
      "learning_rate": 0.0011045284632676536,
      "loss": 1.1652,
      "step": 52
    },
    {
      "epoch": 0.00029758353745411667,
      "grad_norm": 2.333109140396118,
      "learning_rate": 0.0010697564737441251,
      "loss": 0.9394,
      "step": 53
    },
    {
      "epoch": 0.00030319832117966605,
      "grad_norm": 2.443849802017212,
      "learning_rate": 0.0010348994967025011,
      "loss": 1.1265,
      "step": 54
    },
    {
      "epoch": 0.00030881310490521544,
      "grad_norm": 2.8769495487213135,
      "learning_rate": 0.001,
      "loss": 1.2229,
      "step": 55
    },
    {
      "epoch": 0.00031442788863076483,
      "grad_norm": 2.619149684906006,
      "learning_rate": 0.0009651005032974994,
      "loss": 0.9862,
      "step": 56
    },
    {
      "epoch": 0.00032004267235631416,
      "grad_norm": 2.4989588260650635,
      "learning_rate": 0.0009302435262558747,
      "loss": 1.2905,
      "step": 57
    },
    {
      "epoch": 0.00032565745608186355,
      "grad_norm": 2.512277841567993,
      "learning_rate": 0.0008954715367323467,
      "loss": 1.154,
      "step": 58
    },
    {
      "epoch": 0.00033127223980741294,
      "grad_norm": 2.4800610542297363,
      "learning_rate": 0.0008608268990399348,
      "loss": 1.5995,
      "step": 59
    },
    {
      "epoch": 0.00033688702353296227,
      "grad_norm": 2.3938980102539062,
      "learning_rate": 0.0008263518223330697,
      "loss": 1.319,
      "step": 60
    },
    {
      "epoch": 0.00034250180725851166,
      "grad_norm": 2.4228010177612305,
      "learning_rate": 0.0007920883091822408,
      "loss": 0.8742,
      "step": 61
    },
    {
      "epoch": 0.00034811659098406104,
      "grad_norm": 2.0796005725860596,
      "learning_rate": 0.0007580781044003324,
      "loss": 1.1228,
      "step": 62
    },
    {
      "epoch": 0.0003537313747096104,
      "grad_norm": 2.852293014526367,
      "learning_rate": 0.0007243626441830009,
      "loss": 0.9704,
      "step": 63
    },
    {
      "epoch": 0.00035934615843515977,
      "grad_norm": 2.3396663665771484,
      "learning_rate": 0.0006909830056250527,
      "loss": 0.6046,
      "step": 64
    },
    {
      "epoch": 0.00036496094216070915,
      "grad_norm": 2.455451488494873,
      "learning_rate": 0.0006579798566743314,
      "loss": 1.1228,
      "step": 65
    },
    {
      "epoch": 0.00037057572588625854,
      "grad_norm": 2.2324576377868652,
      "learning_rate": 0.0006253934065840879,
      "loss": 0.8794,
      "step": 66
    },
    {
      "epoch": 0.0003761905096118079,
      "grad_norm": 1.5327250957489014,
      "learning_rate": 0.0005932633569242,
      "loss": 0.9488,
      "step": 67
    },
    {
      "epoch": 0.00038180529333735726,
      "grad_norm": 1.51426362991333,
      "learning_rate": 0.0005616288532109225,
      "loss": 0.5928,
      "step": 68
    },
    {
      "epoch": 0.00038742007706290665,
      "grad_norm": 2.4975624084472656,
      "learning_rate": 0.0005305284372141095,
      "loss": 0.8214,
      "step": 69
    },
    {
      "epoch": 0.000393034860788456,
      "grad_norm": 2.9134929180145264,
      "learning_rate": 0.0005000000000000002,
      "loss": 1.1048,
      "step": 70
    },
    {
      "epoch": 0.00039864964451400537,
      "grad_norm": 2.5357260704040527,
      "learning_rate": 0.0004700807357667952,
      "loss": 1.4895,
      "step": 71
    },
    {
      "epoch": 0.00040426442823955476,
      "grad_norm": 1.9591279029846191,
      "learning_rate": 0.0004408070965292533,
      "loss": 0.8524,
      "step": 72
    },
    {
      "epoch": 0.00040987921196510414,
      "grad_norm": 1.8926405906677246,
      "learning_rate": 0.00041221474770752696,
      "loss": 0.9163,
      "step": 73
    },
    {
      "epoch": 0.0004154939956906535,
      "grad_norm": 1.8855713605880737,
      "learning_rate": 0.0003843385246743417,
      "loss": 1.4346,
      "step": 74
    },
    {
      "epoch": 0.00042110877941620286,
      "grad_norm": 3.0587925910949707,
      "learning_rate": 0.0003572123903134606,
      "loss": 0.9795,
      "step": 75
    },
    {
      "epoch": 0.00042110877941620286,
      "eval_loss": 0.9440500140190125,
      "eval_runtime": 13647.0704,
      "eval_samples_per_second": 2.747,
      "eval_steps_per_second": 2.747,
      "step": 75
    },
    {
      "epoch": 0.00042672356314175225,
      "grad_norm": 1.1029833555221558,
      "learning_rate": 0.0003308693936411421,
      "loss": 0.8496,
      "step": 76
    },
    {
      "epoch": 0.0004323383468673016,
      "grad_norm": 1.740774393081665,
      "learning_rate": 0.00030534162954100265,
      "loss": 0.8706,
      "step": 77
    },
    {
      "epoch": 0.00043795313059285097,
      "grad_norm": 1.9898922443389893,
      "learning_rate": 0.00028066019966134904,
      "loss": 0.8711,
      "step": 78
    },
    {
      "epoch": 0.00044356791431840036,
      "grad_norm": 1.1141417026519775,
      "learning_rate": 0.00025685517452260563,
      "loss": 0.7094,
      "step": 79
    },
    {
      "epoch": 0.0004491826980439497,
      "grad_norm": 1.7842293977737427,
      "learning_rate": 0.0002339555568810221,
      "loss": 1.0987,
      "step": 80
    },
    {
      "epoch": 0.0004547974817694991,
      "grad_norm": 1.4790884256362915,
      "learning_rate": 0.00021198924639327811,
      "loss": 0.6301,
      "step": 81
    },
    {
      "epoch": 0.00046041226549504847,
      "grad_norm": 0.9781002998352051,
      "learning_rate": 0.00019098300562505265,
      "loss": 0.893,
      "step": 82
    },
    {
      "epoch": 0.00046602704922059786,
      "grad_norm": 1.3697646856307983,
      "learning_rate": 0.00017096242744495837,
      "loss": 0.6985,
      "step": 83
    },
    {
      "epoch": 0.0004716418329461472,
      "grad_norm": 1.812117576599121,
      "learning_rate": 0.00015195190384357404,
      "loss": 1.1954,
      "step": 84
    },
    {
      "epoch": 0.0004772566166716966,
      "grad_norm": 1.748288631439209,
      "learning_rate": 0.0001339745962155613,
      "loss": 0.9258,
      "step": 85
    },
    {
      "epoch": 0.00048287140039724596,
      "grad_norm": 1.5759660005569458,
      "learning_rate": 0.00011705240714107302,
      "loss": 0.8344,
      "step": 86
    },
    {
      "epoch": 0.0004884861841227954,
      "grad_norm": 1.638961911201477,
      "learning_rate": 0.00010120595370083318,
      "loss": 1.0205,
      "step": 87
    },
    {
      "epoch": 0.0004941009678483447,
      "grad_norm": 1.6769089698791504,
      "learning_rate": 8.645454235739902e-05,
      "loss": 0.9673,
      "step": 88
    },
    {
      "epoch": 0.000499715751573894,
      "grad_norm": 1.4740527868270874,
      "learning_rate": 7.281614543321269e-05,
      "loss": 0.5517,
      "step": 89
    },
    {
      "epoch": 0.0005053305352994435,
      "grad_norm": 1.8537969589233398,
      "learning_rate": 6.0307379214091684e-05,
      "loss": 1.0717,
      "step": 90
    },
    {
      "epoch": 0.0005109453190249928,
      "grad_norm": 1.06834077835083,
      "learning_rate": 4.894348370484647e-05,
      "loss": 0.833,
      "step": 91
    },
    {
      "epoch": 0.0005165601027505421,
      "grad_norm": 2.1590793132781982,
      "learning_rate": 3.873830406168111e-05,
      "loss": 1.2292,
      "step": 92
    },
    {
      "epoch": 0.0005221748864760916,
      "grad_norm": 1.418778419494629,
      "learning_rate": 2.9704273724003528e-05,
      "loss": 0.7584,
      "step": 93
    },
    {
      "epoch": 0.0005277896702016409,
      "grad_norm": 1.332282543182373,
      "learning_rate": 2.1852399266194312e-05,
      "loss": 0.8623,
      "step": 94
    },
    {
      "epoch": 0.0005334044539271903,
      "grad_norm": 1.214484691619873,
      "learning_rate": 1.519224698779198e-05,
      "loss": 0.5786,
      "step": 95
    },
    {
      "epoch": 0.0005390192376527397,
      "grad_norm": 1.5501805543899536,
      "learning_rate": 9.731931258429638e-06,
      "loss": 1.0117,
      "step": 96
    },
    {
      "epoch": 0.000544634021378289,
      "grad_norm": 1.5862345695495605,
      "learning_rate": 5.47810463172671e-06,
      "loss": 0.88,
      "step": 97
    },
    {
      "epoch": 0.0005502488051038384,
      "grad_norm": 1.6535526514053345,
      "learning_rate": 2.4359497401758024e-06,
      "loss": 0.6076,
      "step": 98
    },
    {
      "epoch": 0.0005558635888293878,
      "grad_norm": 0.9868706464767456,
      "learning_rate": 6.091729809042379e-07,
      "loss": 0.6062,
      "step": 99
    },
    {
      "epoch": 0.0005614783725549371,
      "grad_norm": 1.6027213335037231,
      "learning_rate": 0.0,
      "loss": 0.56,
      "step": 100
    },
    {
      "epoch": 0.0005614783725549371,
      "eval_loss": 0.8763332962989807,
      "eval_runtime": 13589.0012,
      "eval_samples_per_second": 2.759,
      "eval_steps_per_second": 2.759,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.70837631753257e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}