{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0051684928674798425,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.168492867479843e-05,
      "grad_norm": 4.011151313781738,
      "learning_rate": 1e-05,
      "loss": 1.4946,
      "step": 1
    },
    {
      "epoch": 5.168492867479843e-05,
      "eval_loss": 1.436689019203186,
      "eval_runtime": 1991.112,
      "eval_samples_per_second": 8.183,
      "eval_steps_per_second": 1.023,
      "step": 1
    },
    {
      "epoch": 0.00010336985734959685,
      "grad_norm": 3.6007654666900635,
      "learning_rate": 2e-05,
      "loss": 1.3124,
      "step": 2
    },
    {
      "epoch": 0.0001550547860243953,
      "grad_norm": 3.825056791305542,
      "learning_rate": 3e-05,
      "loss": 1.4912,
      "step": 3
    },
    {
      "epoch": 0.0002067397146991937,
      "grad_norm": 3.09142804145813,
      "learning_rate": 4e-05,
      "loss": 1.3989,
      "step": 4
    },
    {
      "epoch": 0.00025842464337399215,
      "grad_norm": 3.03934645652771,
      "learning_rate": 5e-05,
      "loss": 1.2052,
      "step": 5
    },
    {
      "epoch": 0.0003101095720487906,
      "grad_norm": 2.6759002208709717,
      "learning_rate": 6e-05,
      "loss": 0.9872,
      "step": 6
    },
    {
      "epoch": 0.000361794500723589,
      "grad_norm": 3.3814027309417725,
      "learning_rate": 7e-05,
      "loss": 1.0471,
      "step": 7
    },
    {
      "epoch": 0.0004134794293983874,
      "grad_norm": 3.302344799041748,
      "learning_rate": 8e-05,
      "loss": 1.0987,
      "step": 8
    },
    {
      "epoch": 0.00046516435807318586,
      "grad_norm": 2.9471261501312256,
      "learning_rate": 9e-05,
      "loss": 1.0167,
      "step": 9
    },
    {
      "epoch": 0.00046516435807318586,
      "eval_loss": 0.7832714319229126,
      "eval_runtime": 2002.3676,
      "eval_samples_per_second": 8.137,
      "eval_steps_per_second": 1.017,
      "step": 9
    },
    {
      "epoch": 0.0005168492867479843,
      "grad_norm": 1.9527397155761719,
      "learning_rate": 0.0001,
      "loss": 0.6083,
      "step": 10
    },
    {
      "epoch": 0.0005685342154227827,
      "grad_norm": 2.313215494155884,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.7766,
      "step": 11
    },
    {
      "epoch": 0.0006202191440975812,
      "grad_norm": 1.7922486066818237,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4838,
      "step": 12
    },
    {
      "epoch": 0.0006719040727723796,
      "grad_norm": 1.5234678983688354,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.375,
      "step": 13
    },
    {
      "epoch": 0.000723589001447178,
      "grad_norm": 1.666954755783081,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.4431,
      "step": 14
    },
    {
      "epoch": 0.0007752739301219764,
      "grad_norm": 1.3458898067474365,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.306,
      "step": 15
    },
    {
      "epoch": 0.0008269588587967748,
      "grad_norm": 1.6406625509262085,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2737,
      "step": 16
    },
    {
      "epoch": 0.0008786437874715733,
      "grad_norm": 2.2472527027130127,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2622,
      "step": 17
    },
    {
      "epoch": 0.0009303287161463717,
      "grad_norm": 1.3017550706863403,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2318,
      "step": 18
    },
    {
      "epoch": 0.0009303287161463717,
      "eval_loss": 0.2425360381603241,
      "eval_runtime": 2001.2577,
      "eval_samples_per_second": 8.141,
      "eval_steps_per_second": 1.018,
      "step": 18
    },
    {
      "epoch": 0.00098201364482117,
      "grad_norm": 1.214409351348877,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1977,
      "step": 19
    },
    {
      "epoch": 0.0010336985734959686,
      "grad_norm": 1.215752124786377,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2023,
      "step": 20
    },
    {
      "epoch": 0.001085383502170767,
      "grad_norm": 1.1496645212173462,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.184,
      "step": 21
    },
    {
      "epoch": 0.0011370684308455654,
      "grad_norm": 1.1634231805801392,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1664,
      "step": 22
    },
    {
      "epoch": 0.0011887533595203639,
      "grad_norm": 1.7621711492538452,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2199,
      "step": 23
    },
    {
      "epoch": 0.0012404382881951624,
      "grad_norm": 0.9533162713050842,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1305,
      "step": 24
    },
    {
      "epoch": 0.0012921232168699606,
      "grad_norm": 0.6479572653770447,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1185,
      "step": 25
    },
    {
      "epoch": 0.0013438081455447591,
      "grad_norm": 0.9580687284469604,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1054,
      "step": 26
    },
    {
      "epoch": 0.0013954930742195576,
      "grad_norm": 1.408044695854187,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1348,
      "step": 27
    },
    {
      "epoch": 0.0013954930742195576,
      "eval_loss": 0.121719591319561,
      "eval_runtime": 2000.6672,
      "eval_samples_per_second": 8.144,
      "eval_steps_per_second": 1.018,
      "step": 27
    },
    {
      "epoch": 0.001447178002894356,
      "grad_norm": 0.9024913907051086,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1044,
      "step": 28
    },
    {
      "epoch": 0.0014988629315691544,
      "grad_norm": 0.8593191504478455,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1124,
      "step": 29
    },
    {
      "epoch": 0.0015505478602439529,
      "grad_norm": 0.6453657746315002,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0967,
      "step": 30
    },
    {
      "epoch": 0.0016022327889187514,
      "grad_norm": 1.0000425577163696,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1054,
      "step": 31
    },
    {
      "epoch": 0.0016539177175935497,
      "grad_norm": 0.9135391116142273,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1079,
      "step": 32
    },
    {
      "epoch": 0.0017056026462683482,
      "grad_norm": 0.6197313666343689,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0927,
      "step": 33
    },
    {
      "epoch": 0.0017572875749431466,
      "grad_norm": 0.6528716683387756,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0811,
      "step": 34
    },
    {
      "epoch": 0.001808972503617945,
      "grad_norm": 0.8095766305923462,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0757,
      "step": 35
    },
    {
      "epoch": 0.0018606574322927434,
      "grad_norm": 1.3153815269470215,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1376,
      "step": 36
    },
    {
      "epoch": 0.0018606574322927434,
      "eval_loss": 0.09214772284030914,
      "eval_runtime": 2000.5366,
      "eval_samples_per_second": 8.144,
      "eval_steps_per_second": 1.018,
      "step": 36
    },
    {
      "epoch": 0.001912342360967542,
      "grad_norm": 0.6268633008003235,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0819,
      "step": 37
    },
    {
      "epoch": 0.00196402728964234,
      "grad_norm": 0.5090088844299316,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0717,
      "step": 38
    },
    {
      "epoch": 0.002015712218317139,
      "grad_norm": 0.9383134841918945,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1401,
      "step": 39
    },
    {
      "epoch": 0.002067397146991937,
      "grad_norm": 0.8806520700454712,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1129,
      "step": 40
    },
    {
      "epoch": 0.0021190820756667355,
      "grad_norm": 0.5183126330375671,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0686,
      "step": 41
    },
    {
      "epoch": 0.002170767004341534,
      "grad_norm": 0.6590868830680847,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1052,
      "step": 42
    },
    {
      "epoch": 0.0022224519330163325,
      "grad_norm": 0.5947044491767883,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0758,
      "step": 43
    },
    {
      "epoch": 0.0022741368616911307,
      "grad_norm": 0.739967942237854,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0799,
      "step": 44
    },
    {
      "epoch": 0.0023258217903659294,
      "grad_norm": 0.8281837701797485,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0646,
      "step": 45
    },
    {
      "epoch": 0.0023258217903659294,
      "eval_loss": 0.07997908443212509,
      "eval_runtime": 2000.9661,
      "eval_samples_per_second": 8.143,
      "eval_steps_per_second": 1.018,
      "step": 45
    },
    {
      "epoch": 0.0023775067190407277,
      "grad_norm": 0.5553789138793945,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.062,
      "step": 46
    },
    {
      "epoch": 0.002429191647715526,
      "grad_norm": 0.5033071041107178,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0631,
      "step": 47
    },
    {
      "epoch": 0.0024808765763903247,
      "grad_norm": 0.7486463785171509,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0951,
      "step": 48
    },
    {
      "epoch": 0.002532561505065123,
      "grad_norm": 0.48908039927482605,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0559,
      "step": 49
    },
    {
      "epoch": 0.0025842464337399213,
      "grad_norm": 0.45823943614959717,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0498,
      "step": 50
    },
    {
      "epoch": 0.00263593136241472,
      "grad_norm": 1.597001314163208,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1898,
      "step": 51
    },
    {
      "epoch": 0.0026876162910895183,
      "grad_norm": 1.0472426414489746,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0887,
      "step": 52
    },
    {
      "epoch": 0.0027393012197643165,
      "grad_norm": 1.2370333671569824,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1294,
      "step": 53
    },
    {
      "epoch": 0.0027909861484391152,
      "grad_norm": 0.623787522315979,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0634,
      "step": 54
    },
    {
      "epoch": 0.0027909861484391152,
      "eval_loss": 0.0726623609662056,
      "eval_runtime": 2001.9362,
      "eval_samples_per_second": 8.139,
      "eval_steps_per_second": 1.018,
      "step": 54
    },
    {
      "epoch": 0.0028426710771139135,
      "grad_norm": 0.5839661359786987,
      "learning_rate": 5e-05,
      "loss": 0.0676,
      "step": 55
    },
    {
      "epoch": 0.002894356005788712,
      "grad_norm": 0.7963717579841614,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0728,
      "step": 56
    },
    {
      "epoch": 0.0029460409344635105,
      "grad_norm": 0.5084842443466187,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0732,
      "step": 57
    },
    {
      "epoch": 0.002997725863138309,
      "grad_norm": 0.5992403030395508,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0716,
      "step": 58
    },
    {
      "epoch": 0.0030494107918131075,
      "grad_norm": 0.4697546064853668,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0616,
      "step": 59
    },
    {
      "epoch": 0.0031010957204879058,
      "grad_norm": 0.6336478590965271,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0646,
      "step": 60
    },
    {
      "epoch": 0.003152780649162704,
      "grad_norm": 0.6779618859291077,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0735,
      "step": 61
    },
    {
      "epoch": 0.0032044655778375028,
      "grad_norm": 0.4873669147491455,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0753,
      "step": 62
    },
    {
      "epoch": 0.003256150506512301,
      "grad_norm": 0.5097606182098389,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0668,
      "step": 63
    },
    {
      "epoch": 0.003256150506512301,
      "eval_loss": 0.06682123243808746,
      "eval_runtime": 2001.2998,
      "eval_samples_per_second": 8.141,
      "eval_steps_per_second": 1.018,
      "step": 63
    },
    {
      "epoch": 0.0033078354351870993,
      "grad_norm": 0.5775445699691772,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.053,
      "step": 64
    },
    {
      "epoch": 0.003359520363861898,
      "grad_norm": 0.6833822727203369,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0524,
      "step": 65
    },
    {
      "epoch": 0.0034112052925366963,
      "grad_norm": 0.43024009466171265,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0691,
      "step": 66
    },
    {
      "epoch": 0.0034628902212114946,
      "grad_norm": 0.43755966424942017,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0623,
      "step": 67
    },
    {
      "epoch": 0.0035145751498862933,
      "grad_norm": 0.5165156126022339,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0588,
      "step": 68
    },
    {
      "epoch": 0.0035662600785610916,
      "grad_norm": 0.43913787603378296,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0672,
      "step": 69
    },
    {
      "epoch": 0.00361794500723589,
      "grad_norm": 0.5426086187362671,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0544,
      "step": 70
    },
    {
      "epoch": 0.0036696299359106886,
      "grad_norm": 0.7457218766212463,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0689,
      "step": 71
    },
    {
      "epoch": 0.003721314864585487,
      "grad_norm": 0.5793647766113281,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0476,
      "step": 72
    },
    {
      "epoch": 0.003721314864585487,
      "eval_loss": 0.06450506299734116,
      "eval_runtime": 2001.6572,
      "eval_samples_per_second": 8.14,
      "eval_steps_per_second": 1.018,
      "step": 72
    },
    {
      "epoch": 0.003772999793260285,
      "grad_norm": 0.3593558967113495,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0443,
      "step": 73
    },
    {
      "epoch": 0.003824684721935084,
      "grad_norm": 0.4152470827102661,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0503,
      "step": 74
    },
    {
      "epoch": 0.003876369650609882,
      "grad_norm": 0.6307422518730164,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0658,
      "step": 75
    },
    {
      "epoch": 0.00392805457928468,
      "grad_norm": 0.5122618079185486,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0615,
      "step": 76
    },
    {
      "epoch": 0.003979739507959479,
      "grad_norm": 0.40899038314819336,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.042,
      "step": 77
    },
    {
      "epoch": 0.004031424436634278,
      "grad_norm": 0.3847385048866272,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0492,
      "step": 78
    },
    {
      "epoch": 0.004083109365309076,
      "grad_norm": 0.8799728155136108,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0751,
      "step": 79
    },
    {
      "epoch": 0.004134794293983874,
      "grad_norm": 0.4237743020057678,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0538,
      "step": 80
    },
    {
      "epoch": 0.004186479222658673,
      "grad_norm": 0.4771229922771454,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0585,
      "step": 81
    },
    {
      "epoch": 0.004186479222658673,
      "eval_loss": 0.0616205632686615,
      "eval_runtime": 2002.2154,
      "eval_samples_per_second": 8.137,
      "eval_steps_per_second": 1.017,
      "step": 81
    },
    {
      "epoch": 0.004238164151333471,
      "grad_norm": 0.420214980840683,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0467,
      "step": 82
    },
    {
      "epoch": 0.004289849080008269,
      "grad_norm": 0.3315078020095825,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0405,
      "step": 83
    },
    {
      "epoch": 0.004341534008683068,
      "grad_norm": 0.4422627389431,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0556,
      "step": 84
    },
    {
      "epoch": 0.004393218937357867,
      "grad_norm": 0.664663553237915,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0848,
      "step": 85
    },
    {
      "epoch": 0.004444903866032665,
      "grad_norm": 0.9881814122200012,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1188,
      "step": 86
    },
    {
      "epoch": 0.004496588794707463,
      "grad_norm": 0.768933892250061,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0472,
      "step": 87
    },
    {
      "epoch": 0.0045482737233822615,
      "grad_norm": 0.545575737953186,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0406,
      "step": 88
    },
    {
      "epoch": 0.00459995865205706,
      "grad_norm": 0.3007638454437256,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0406,
      "step": 89
    },
    {
      "epoch": 0.004651643580731859,
      "grad_norm": 0.4055767059326172,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0426,
      "step": 90
    },
    {
      "epoch": 0.004651643580731859,
      "eval_loss": 0.06025952845811844,
      "eval_runtime": 2002.5397,
      "eval_samples_per_second": 8.136,
      "eval_steps_per_second": 1.017,
      "step": 90
    },
    {
      "epoch": 0.004703328509406657,
      "grad_norm": 0.42823222279548645,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0523,
      "step": 91
    },
    {
      "epoch": 0.0047550134380814554,
      "grad_norm": 0.317855566740036,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0418,
      "step": 92
    },
    {
      "epoch": 0.004806698366756254,
      "grad_norm": 0.5230840444564819,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0538,
      "step": 93
    },
    {
      "epoch": 0.004858383295431052,
      "grad_norm": 1.009881854057312,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0426,
      "step": 94
    },
    {
      "epoch": 0.004910068224105851,
      "grad_norm": 0.34990185499191284,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0524,
      "step": 95
    },
    {
      "epoch": 0.004961753152780649,
      "grad_norm": 0.5936976075172424,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0695,
      "step": 96
    },
    {
      "epoch": 0.005013438081455448,
      "grad_norm": 0.526382565498352,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0483,
      "step": 97
    },
    {
      "epoch": 0.005065123010130246,
      "grad_norm": 0.47215914726257324,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0522,
      "step": 98
    },
    {
      "epoch": 0.005116807938805044,
      "grad_norm": 0.5641908645629883,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0694,
      "step": 99
    },
    {
      "epoch": 0.005116807938805044,
      "eval_loss": 0.06006684526801109,
      "eval_runtime": 2001.6946,
      "eval_samples_per_second": 8.14,
      "eval_steps_per_second": 1.018,
      "step": 99
    },
    {
      "epoch": 0.0051684928674798425,
      "grad_norm": 0.560275137424469,
      "learning_rate": 0.0,
      "loss": 0.054,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}