{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002106460514397658,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1064605143976575e-05,
      "grad_norm": 0.0323529914021492,
      "learning_rate": 1e-05,
      "loss": 10.3808,
      "step": 1
    },
    {
      "epoch": 2.1064605143976575e-05,
      "eval_loss": 10.377638816833496,
      "eval_runtime": 325.5686,
      "eval_samples_per_second": 122.794,
      "eval_steps_per_second": 15.352,
      "step": 1
    },
    {
      "epoch": 4.212921028795315e-05,
      "grad_norm": 0.033095818012952805,
      "learning_rate": 2e-05,
      "loss": 10.3753,
      "step": 2
    },
    {
      "epoch": 6.319381543192973e-05,
      "grad_norm": 0.03802718222141266,
      "learning_rate": 3e-05,
      "loss": 10.3781,
      "step": 3
    },
    {
      "epoch": 8.42584205759063e-05,
      "grad_norm": 0.03922766447067261,
      "learning_rate": 4e-05,
      "loss": 10.3802,
      "step": 4
    },
    {
      "epoch": 0.00010532302571988288,
      "grad_norm": 0.029788147658109665,
      "learning_rate": 5e-05,
      "loss": 10.3783,
      "step": 5
    },
    {
      "epoch": 0.00012638763086385946,
      "grad_norm": 0.03316537290811539,
      "learning_rate": 6e-05,
      "loss": 10.3773,
      "step": 6
    },
    {
      "epoch": 0.00014745223600783603,
      "grad_norm": 0.04057418555021286,
      "learning_rate": 7e-05,
      "loss": 10.3763,
      "step": 7
    },
    {
      "epoch": 0.0001685168411518126,
      "grad_norm": 0.03403380885720253,
      "learning_rate": 8e-05,
      "loss": 10.3768,
      "step": 8
    },
    {
      "epoch": 0.0001895814462957892,
      "grad_norm": 0.0315258726477623,
      "learning_rate": 9e-05,
      "loss": 10.3756,
      "step": 9
    },
    {
      "epoch": 0.0001895814462957892,
      "eval_loss": 10.37730598449707,
      "eval_runtime": 326.3329,
      "eval_samples_per_second": 122.507,
      "eval_steps_per_second": 15.316,
      "step": 9
    },
    {
      "epoch": 0.00021064605143976577,
      "grad_norm": 0.04213544726371765,
      "learning_rate": 0.0001,
      "loss": 10.3773,
      "step": 10
    },
    {
      "epoch": 0.00023171065658374233,
      "grad_norm": 0.03319665044546127,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.377,
      "step": 11
    },
    {
      "epoch": 0.00025277526172771893,
      "grad_norm": 0.03507379814982414,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3762,
      "step": 12
    },
    {
      "epoch": 0.00027383986687169547,
      "grad_norm": 0.038384709507226944,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.379,
      "step": 13
    },
    {
      "epoch": 0.00029490447201567207,
      "grad_norm": 0.03694895654916763,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3775,
      "step": 14
    },
    {
      "epoch": 0.00031596907715964866,
      "grad_norm": 0.03095310926437378,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3755,
      "step": 15
    },
    {
      "epoch": 0.0003370336823036252,
      "grad_norm": 0.039225611835718155,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3762,
      "step": 16
    },
    {
      "epoch": 0.0003580982874476018,
      "grad_norm": 0.036280952394008636,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3766,
      "step": 17
    },
    {
      "epoch": 0.0003791628925915784,
      "grad_norm": 0.03579021990299225,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3789,
      "step": 18
    },
    {
      "epoch": 0.0003791628925915784,
      "eval_loss": 10.376466751098633,
      "eval_runtime": 326.5405,
      "eval_samples_per_second": 122.429,
      "eval_steps_per_second": 15.306,
      "step": 18
    },
    {
      "epoch": 0.00040022749773555494,
      "grad_norm": 0.0345304012298584,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3765,
      "step": 19
    },
    {
      "epoch": 0.00042129210287953153,
      "grad_norm": 0.04037633165717125,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3748,
      "step": 20
    },
    {
      "epoch": 0.00044235670802350807,
      "grad_norm": 0.03361587971448898,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.376,
      "step": 21
    },
    {
      "epoch": 0.00046342131316748467,
      "grad_norm": 0.03614883869886398,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3734,
      "step": 22
    },
    {
      "epoch": 0.00048448591831146126,
      "grad_norm": 0.04295242205262184,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3764,
      "step": 23
    },
    {
      "epoch": 0.0005055505234554379,
      "grad_norm": 0.04079096391797066,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3732,
      "step": 24
    },
    {
      "epoch": 0.0005266151285994145,
      "grad_norm": 0.03456183150410652,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3755,
      "step": 25
    },
    {
      "epoch": 0.0005476797337433909,
      "grad_norm": 0.05067078769207001,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3736,
      "step": 26
    },
    {
      "epoch": 0.0005687443388873675,
      "grad_norm": 0.03656363859772682,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.375,
      "step": 27
    },
    {
      "epoch": 0.0005687443388873675,
      "eval_loss": 10.375572204589844,
      "eval_runtime": 325.6996,
      "eval_samples_per_second": 122.745,
      "eval_steps_per_second": 15.345,
      "step": 27
    },
    {
      "epoch": 0.0005898089440313441,
      "grad_norm": 0.03712327778339386,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3759,
      "step": 28
    },
    {
      "epoch": 0.0006108735491753207,
      "grad_norm": 0.04191397503018379,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3776,
      "step": 29
    },
    {
      "epoch": 0.0006319381543192973,
      "grad_norm": 0.040405046194791794,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3771,
      "step": 30
    },
    {
      "epoch": 0.0006530027594632738,
      "grad_norm": 0.04103453829884529,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3751,
      "step": 31
    },
    {
      "epoch": 0.0006740673646072504,
      "grad_norm": 0.043744977563619614,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3738,
      "step": 32
    },
    {
      "epoch": 0.000695131969751227,
      "grad_norm": 0.041353847831487656,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3742,
      "step": 33
    },
    {
      "epoch": 0.0007161965748952036,
      "grad_norm": 0.041590310633182526,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3747,
      "step": 34
    },
    {
      "epoch": 0.0007372611800391802,
      "grad_norm": 0.042141202837228775,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3763,
      "step": 35
    },
    {
      "epoch": 0.0007583257851831568,
      "grad_norm": 0.051582399755716324,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3748,
      "step": 36
    },
    {
      "epoch": 0.0007583257851831568,
      "eval_loss": 10.374592781066895,
      "eval_runtime": 326.5386,
      "eval_samples_per_second": 122.43,
      "eval_steps_per_second": 15.306,
      "step": 36
    },
    {
      "epoch": 0.0007793903903271333,
      "grad_norm": 0.03906949236989021,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3753,
      "step": 37
    },
    {
      "epoch": 0.0008004549954711099,
      "grad_norm": 0.04390184208750725,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.373,
      "step": 38
    },
    {
      "epoch": 0.0008215196006150865,
      "grad_norm": 0.04439748823642731,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3749,
      "step": 39
    },
    {
      "epoch": 0.0008425842057590631,
      "grad_norm": 0.05099000036716461,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.375,
      "step": 40
    },
    {
      "epoch": 0.0008636488109030397,
      "grad_norm": 0.04918903857469559,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3728,
      "step": 41
    },
    {
      "epoch": 0.0008847134160470161,
      "grad_norm": 0.05172858387231827,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.374,
      "step": 42
    },
    {
      "epoch": 0.0009057780211909927,
      "grad_norm": 0.05202887952327728,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3728,
      "step": 43
    },
    {
      "epoch": 0.0009268426263349693,
      "grad_norm": 0.06054721027612686,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3731,
      "step": 44
    },
    {
      "epoch": 0.0009479072314789459,
      "grad_norm": 0.05004347860813141,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3759,
      "step": 45
    },
    {
      "epoch": 0.0009479072314789459,
      "eval_loss": 10.37352180480957,
      "eval_runtime": 326.6722,
      "eval_samples_per_second": 122.38,
      "eval_steps_per_second": 15.3,
      "step": 45
    },
    {
      "epoch": 0.0009689718366229225,
      "grad_norm": 0.04989779740571976,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3752,
      "step": 46
    },
    {
      "epoch": 0.000990036441766899,
      "grad_norm": 0.05517362803220749,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3756,
      "step": 47
    },
    {
      "epoch": 0.0010111010469108757,
      "grad_norm": 0.05383509770035744,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3726,
      "step": 48
    },
    {
      "epoch": 0.0010321656520548522,
      "grad_norm": 0.06373439729213715,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3715,
      "step": 49
    },
    {
      "epoch": 0.001053230257198829,
      "grad_norm": 0.055983684957027435,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3733,
      "step": 50
    },
    {
      "epoch": 0.0010742948623428054,
      "grad_norm": 0.05248018354177475,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.375,
      "step": 51
    },
    {
      "epoch": 0.0010953594674867819,
      "grad_norm": 0.05726935714483261,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3719,
      "step": 52
    },
    {
      "epoch": 0.0011164240726307586,
      "grad_norm": 0.06659786403179169,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3712,
      "step": 53
    },
    {
      "epoch": 0.001137488677774735,
      "grad_norm": 0.07157450169324875,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3746,
      "step": 54
    },
    {
      "epoch": 0.001137488677774735,
      "eval_loss": 10.372406005859375,
      "eval_runtime": 325.9982,
      "eval_samples_per_second": 122.633,
      "eval_steps_per_second": 15.331,
      "step": 54
    },
    {
      "epoch": 0.0011585532829187118,
      "grad_norm": 0.07614810019731522,
      "learning_rate": 5e-05,
      "loss": 10.3737,
      "step": 55
    },
    {
      "epoch": 0.0011796178880626883,
      "grad_norm": 0.0629672184586525,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3721,
      "step": 56
    },
    {
      "epoch": 0.0012006824932066648,
      "grad_norm": 0.06121913716197014,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3733,
      "step": 57
    },
    {
      "epoch": 0.0012217470983506415,
      "grad_norm": 0.07098937779664993,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3714,
      "step": 58
    },
    {
      "epoch": 0.001242811703494618,
      "grad_norm": 0.07375166565179825,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.373,
      "step": 59
    },
    {
      "epoch": 0.0012638763086385946,
      "grad_norm": 0.07011041790246964,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3747,
      "step": 60
    },
    {
      "epoch": 0.0012849409137825711,
      "grad_norm": 0.07801834493875504,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3708,
      "step": 61
    },
    {
      "epoch": 0.0013060055189265476,
      "grad_norm": 0.06852724403142929,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3679,
      "step": 62
    },
    {
      "epoch": 0.0013270701240705243,
      "grad_norm": 0.08574629575014114,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.371,
      "step": 63
    },
    {
      "epoch": 0.0013270701240705243,
      "eval_loss": 10.371370315551758,
      "eval_runtime": 326.3428,
      "eval_samples_per_second": 122.503,
      "eval_steps_per_second": 15.315,
      "step": 63
    },
    {
      "epoch": 0.0013481347292145008,
      "grad_norm": 0.07531008124351501,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3716,
      "step": 64
    },
    {
      "epoch": 0.0013691993343584775,
      "grad_norm": 0.07393725961446762,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3698,
      "step": 65
    },
    {
      "epoch": 0.001390263939502454,
      "grad_norm": 0.06109638884663582,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3713,
      "step": 66
    },
    {
      "epoch": 0.0014113285446464307,
      "grad_norm": 0.06804902851581573,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3729,
      "step": 67
    },
    {
      "epoch": 0.0014323931497904072,
      "grad_norm": 0.06823346018791199,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3726,
      "step": 68
    },
    {
      "epoch": 0.0014534577549343837,
      "grad_norm": 0.08150950819253922,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3709,
      "step": 69
    },
    {
      "epoch": 0.0014745223600783604,
      "grad_norm": 0.0740344300866127,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3701,
      "step": 70
    },
    {
      "epoch": 0.0014955869652223369,
      "grad_norm": 0.07693792879581451,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3696,
      "step": 71
    },
    {
      "epoch": 0.0015166515703663136,
      "grad_norm": 0.07825221121311188,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.371,
      "step": 72
    },
    {
      "epoch": 0.0015166515703663136,
      "eval_loss": 10.370597839355469,
      "eval_runtime": 326.4253,
      "eval_samples_per_second": 122.472,
      "eval_steps_per_second": 15.311,
      "step": 72
    },
    {
      "epoch": 0.00153771617551029,
      "grad_norm": 0.07389895617961884,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3719,
      "step": 73
    },
    {
      "epoch": 0.0015587807806542666,
      "grad_norm": 0.07960311323404312,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3719,
      "step": 74
    },
    {
      "epoch": 0.0015798453857982433,
      "grad_norm": 0.07482942938804626,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3725,
      "step": 75
    },
    {
      "epoch": 0.0016009099909422197,
      "grad_norm": 0.08592105656862259,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.37,
      "step": 76
    },
    {
      "epoch": 0.0016219745960861964,
      "grad_norm": 0.08493143320083618,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3702,
      "step": 77
    },
    {
      "epoch": 0.001643039201230173,
      "grad_norm": 0.08430784940719604,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3686,
      "step": 78
    },
    {
      "epoch": 0.0016641038063741494,
      "grad_norm": 0.07680730521678925,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3688,
      "step": 79
    },
    {
      "epoch": 0.0016851684115181261,
      "grad_norm": 0.08067227154970169,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3713,
      "step": 80
    },
    {
      "epoch": 0.0017062330166621026,
      "grad_norm": 0.08333154767751694,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3701,
      "step": 81
    },
    {
      "epoch": 0.0017062330166621026,
      "eval_loss": 10.370133399963379,
      "eval_runtime": 326.1701,
      "eval_samples_per_second": 122.568,
      "eval_steps_per_second": 15.323,
      "step": 81
    },
    {
      "epoch": 0.0017272976218060793,
      "grad_norm": 0.0690532922744751,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3728,
      "step": 82
    },
    {
      "epoch": 0.0017483622269500558,
      "grad_norm": 0.0802256315946579,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3694,
      "step": 83
    },
    {
      "epoch": 0.0017694268320940323,
      "grad_norm": 0.08990988880395889,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3699,
      "step": 84
    },
    {
      "epoch": 0.001790491437238009,
      "grad_norm": 0.0876426100730896,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3691,
      "step": 85
    },
    {
      "epoch": 0.0018115560423819855,
      "grad_norm": 0.0830601155757904,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3695,
      "step": 86
    },
    {
      "epoch": 0.0018326206475259622,
      "grad_norm": 0.08276013284921646,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3715,
      "step": 87
    },
    {
      "epoch": 0.0018536852526699387,
      "grad_norm": 0.08257749676704407,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.368,
      "step": 88
    },
    {
      "epoch": 0.0018747498578139154,
      "grad_norm": 0.08675715327262878,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3693,
      "step": 89
    },
    {
      "epoch": 0.0018958144629578919,
      "grad_norm": 0.07969921082258224,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3689,
      "step": 90
    },
    {
      "epoch": 0.0018958144629578919,
      "eval_loss": 10.369930267333984,
      "eval_runtime": 326.3104,
      "eval_samples_per_second": 122.515,
      "eval_steps_per_second": 15.317,
      "step": 90
    },
    {
      "epoch": 0.0019168790681018684,
      "grad_norm": 0.08067625761032104,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3702,
      "step": 91
    },
    {
      "epoch": 0.001937943673245845,
      "grad_norm": 0.07955577224493027,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3701,
      "step": 92
    },
    {
      "epoch": 0.0019590082783898215,
      "grad_norm": 0.08348768204450607,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3745,
      "step": 93
    },
    {
      "epoch": 0.001980072883533798,
      "grad_norm": 0.08660487085580826,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3674,
      "step": 94
    },
    {
      "epoch": 0.002001137488677775,
      "grad_norm": 0.0937645360827446,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3699,
      "step": 95
    },
    {
      "epoch": 0.0020222020938217514,
      "grad_norm": 0.0810457393527031,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3703,
      "step": 96
    },
    {
      "epoch": 0.002043266698965728,
      "grad_norm": 0.09225189685821533,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3692,
      "step": 97
    },
    {
      "epoch": 0.0020643313041097044,
      "grad_norm": 0.07411503046751022,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3711,
      "step": 98
    },
    {
      "epoch": 0.002085395909253681,
      "grad_norm": 0.07585640251636505,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.369,
      "step": 99
    },
    {
      "epoch": 0.002085395909253681,
      "eval_loss": 10.369887351989746,
      "eval_runtime": 326.4843,
      "eval_samples_per_second": 122.45,
      "eval_steps_per_second": 15.309,
      "step": 99
    },
    {
      "epoch": 0.002106460514397658,
      "grad_norm": 0.08066422492265701,
      "learning_rate": 0.0,
      "loss": 10.3689,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 5596361785344.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}