{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014177358758063374,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014177358758063374,
      "grad_norm": 0.7821202278137207,
      "learning_rate": 1e-05,
      "loss": 1.4707,
      "step": 1
    },
    {
      "epoch": 0.00014177358758063374,
      "eval_loss": 1.5667353868484497,
      "eval_runtime": 456.9302,
      "eval_samples_per_second": 51.995,
      "eval_steps_per_second": 1.626,
      "step": 1
    },
    {
      "epoch": 0.0002835471751612675,
      "grad_norm": 0.8929142951965332,
      "learning_rate": 2e-05,
      "loss": 1.7748,
      "step": 2
    },
    {
      "epoch": 0.0004253207627419012,
      "grad_norm": 0.7734425663948059,
      "learning_rate": 3e-05,
      "loss": 1.526,
      "step": 3
    },
    {
      "epoch": 0.000567094350322535,
      "grad_norm": 0.7167040109634399,
      "learning_rate": 4e-05,
      "loss": 1.5134,
      "step": 4
    },
    {
      "epoch": 0.0007088679379031686,
      "grad_norm": 0.8051550984382629,
      "learning_rate": 5e-05,
      "loss": 1.3936,
      "step": 5
    },
    {
      "epoch": 0.0008506415254838024,
      "grad_norm": 0.6823679804801941,
      "learning_rate": 6e-05,
      "loss": 1.2961,
      "step": 6
    },
    {
      "epoch": 0.000992415113064436,
      "grad_norm": 0.7503851652145386,
      "learning_rate": 7e-05,
      "loss": 1.1308,
      "step": 7
    },
    {
      "epoch": 0.00113418870064507,
      "grad_norm": 1.1133750677108765,
      "learning_rate": 8e-05,
      "loss": 1.3698,
      "step": 8
    },
    {
      "epoch": 0.0012759622882257036,
      "grad_norm": 1.0564303398132324,
      "learning_rate": 9e-05,
      "loss": 1.1425,
      "step": 9
    },
    {
      "epoch": 0.0012759622882257036,
      "eval_loss": 1.0525261163711548,
      "eval_runtime": 456.9691,
      "eval_samples_per_second": 51.99,
      "eval_steps_per_second": 1.626,
      "step": 9
    },
    {
      "epoch": 0.0014177358758063372,
      "grad_norm": 1.1789106130599976,
      "learning_rate": 0.0001,
      "loss": 1.071,
      "step": 10
    },
    {
      "epoch": 0.001559509463386971,
      "grad_norm": 0.961137592792511,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9062,
      "step": 11
    },
    {
      "epoch": 0.0017012830509676048,
      "grad_norm": 0.7924002408981323,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7036,
      "step": 12
    },
    {
      "epoch": 0.0018430566385482384,
      "grad_norm": 0.6493241190910339,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.6991,
      "step": 13
    },
    {
      "epoch": 0.001984830226128872,
      "grad_norm": 0.9647655487060547,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.76,
      "step": 14
    },
    {
      "epoch": 0.002126603813709506,
      "grad_norm": 0.8076211810112,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6084,
      "step": 15
    },
    {
      "epoch": 0.00226837740129014,
      "grad_norm": 0.8954758048057556,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.646,
      "step": 16
    },
    {
      "epoch": 0.0024101509888707733,
      "grad_norm": 0.6733810305595398,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.5585,
      "step": 17
    },
    {
      "epoch": 0.002551924576451407,
      "grad_norm": 0.7041885256767273,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7161,
      "step": 18
    },
    {
      "epoch": 0.002551924576451407,
      "eval_loss": 0.5472325682640076,
      "eval_runtime": 457.3459,
      "eval_samples_per_second": 51.948,
      "eval_steps_per_second": 1.625,
      "step": 18
    },
    {
      "epoch": 0.002693698164032041,
      "grad_norm": 0.5179082155227661,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5352,
      "step": 19
    },
    {
      "epoch": 0.0028354717516126744,
      "grad_norm": 0.46674951910972595,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4876,
      "step": 20
    },
    {
      "epoch": 0.0029772453391933083,
      "grad_norm": 0.564038872718811,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.4892,
      "step": 21
    },
    {
      "epoch": 0.003119018926773942,
      "grad_norm": 0.5244971513748169,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5351,
      "step": 22
    },
    {
      "epoch": 0.0032607925143545756,
      "grad_norm": 0.4647510051727295,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5202,
      "step": 23
    },
    {
      "epoch": 0.0034025661019352095,
      "grad_norm": 0.8257660269737244,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5329,
      "step": 24
    },
    {
      "epoch": 0.0035443396895158434,
      "grad_norm": 0.4334472417831421,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.502,
      "step": 25
    },
    {
      "epoch": 0.003686113277096477,
      "grad_norm": 0.3279978334903717,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4293,
      "step": 26
    },
    {
      "epoch": 0.0038278868646771107,
      "grad_norm": 0.37488213181495667,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.4155,
      "step": 27
    },
    {
      "epoch": 0.0038278868646771107,
      "eval_loss": 0.471792608499527,
      "eval_runtime": 459.3134,
      "eval_samples_per_second": 51.725,
      "eval_steps_per_second": 1.618,
      "step": 27
    },
    {
      "epoch": 0.003969660452257744,
      "grad_norm": 0.4220845401287079,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.472,
      "step": 28
    },
    {
      "epoch": 0.004111434039838378,
      "grad_norm": 0.3637070953845978,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.3771,
      "step": 29
    },
    {
      "epoch": 0.004253207627419012,
      "grad_norm": 0.41591402888298035,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.49,
      "step": 30
    },
    {
      "epoch": 0.004394981214999646,
      "grad_norm": 0.4210003912448883,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4383,
      "step": 31
    },
    {
      "epoch": 0.00453675480258028,
      "grad_norm": 0.30932655930519104,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3811,
      "step": 32
    },
    {
      "epoch": 0.004678528390160913,
      "grad_norm": 0.4257589876651764,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4686,
      "step": 33
    },
    {
      "epoch": 0.0048203019777415465,
      "grad_norm": 0.3219594359397888,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4014,
      "step": 34
    },
    {
      "epoch": 0.00496207556532218,
      "grad_norm": 0.3486030399799347,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3564,
      "step": 35
    },
    {
      "epoch": 0.005103849152902814,
      "grad_norm": 0.30892881751060486,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3661,
      "step": 36
    },
    {
      "epoch": 0.005103849152902814,
      "eval_loss": 0.42871150374412537,
      "eval_runtime": 458.5899,
      "eval_samples_per_second": 51.807,
      "eval_steps_per_second": 1.62,
      "step": 36
    },
    {
      "epoch": 0.005245622740483448,
      "grad_norm": 0.3870173692703247,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.408,
      "step": 37
    },
    {
      "epoch": 0.005387396328064082,
      "grad_norm": 0.35822123289108276,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.4263,
      "step": 38
    },
    {
      "epoch": 0.005529169915644715,
      "grad_norm": 0.4277469217777252,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.4198,
      "step": 39
    },
    {
      "epoch": 0.005670943503225349,
      "grad_norm": 0.3776010572910309,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4181,
      "step": 40
    },
    {
      "epoch": 0.005812717090805983,
      "grad_norm": 0.43272149562835693,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.4377,
      "step": 41
    },
    {
      "epoch": 0.005954490678386617,
      "grad_norm": 0.36881357431411743,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3785,
      "step": 42
    },
    {
      "epoch": 0.0060962642659672505,
      "grad_norm": 0.34524157643318176,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3777,
      "step": 43
    },
    {
      "epoch": 0.006238037853547884,
      "grad_norm": 0.41083481907844543,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3577,
      "step": 44
    },
    {
      "epoch": 0.006379811441128517,
      "grad_norm": 0.4385363757610321,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4127,
      "step": 45
    },
    {
      "epoch": 0.006379811441128517,
      "eval_loss": 0.4042835533618927,
      "eval_runtime": 457.5257,
      "eval_samples_per_second": 51.927,
      "eval_steps_per_second": 1.624,
      "step": 45
    },
    {
      "epoch": 0.006521585028709151,
      "grad_norm": 0.4030939042568207,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3953,
      "step": 46
    },
    {
      "epoch": 0.006663358616289785,
      "grad_norm": 0.45316946506500244,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3974,
      "step": 47
    },
    {
      "epoch": 0.006805132203870419,
      "grad_norm": 0.44012251496315,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4249,
      "step": 48
    },
    {
      "epoch": 0.006946905791451053,
      "grad_norm": 0.3398742079734802,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.3646,
      "step": 49
    },
    {
      "epoch": 0.007088679379031687,
      "grad_norm": 0.4940671920776367,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3865,
      "step": 50
    },
    {
      "epoch": 0.00723045296661232,
      "grad_norm": 0.301004022359848,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2993,
      "step": 51
    },
    {
      "epoch": 0.007372226554192954,
      "grad_norm": 0.4265194833278656,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.3726,
      "step": 52
    },
    {
      "epoch": 0.0075140001417735875,
      "grad_norm": 0.5026067495346069,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.4026,
      "step": 53
    },
    {
      "epoch": 0.007655773729354221,
      "grad_norm": 0.4086029529571533,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4001,
      "step": 54
    },
    {
      "epoch": 0.007655773729354221,
      "eval_loss": 0.38816213607788086,
      "eval_runtime": 457.3187,
      "eval_samples_per_second": 51.951,
      "eval_steps_per_second": 1.625,
      "step": 54
    },
    {
      "epoch": 0.007797547316934855,
      "grad_norm": 0.38459664583206177,
      "learning_rate": 5e-05,
      "loss": 0.3193,
      "step": 55
    },
    {
      "epoch": 0.007939320904515488,
      "grad_norm": 0.42123913764953613,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3873,
      "step": 56
    },
    {
      "epoch": 0.008081094492096123,
      "grad_norm": 0.39172083139419556,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3278,
      "step": 57
    },
    {
      "epoch": 0.008222868079676756,
      "grad_norm": 0.36400213837623596,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3952,
      "step": 58
    },
    {
      "epoch": 0.00836464166725739,
      "grad_norm": 0.4071996510028839,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.3827,
      "step": 59
    },
    {
      "epoch": 0.008506415254838024,
      "grad_norm": 0.4008931815624237,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3668,
      "step": 60
    },
    {
      "epoch": 0.008648188842418657,
      "grad_norm": 0.5234931111335754,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.4028,
      "step": 61
    },
    {
      "epoch": 0.008789962429999292,
      "grad_norm": 0.4863264262676239,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.4016,
      "step": 62
    },
    {
      "epoch": 0.008931736017579925,
      "grad_norm": 0.41659411787986755,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3251,
      "step": 63
    },
    {
      "epoch": 0.008931736017579925,
      "eval_loss": 0.3772662281990051,
      "eval_runtime": 459.794,
      "eval_samples_per_second": 51.671,
      "eval_steps_per_second": 1.616,
      "step": 63
    },
    {
      "epoch": 0.00907350960516056,
      "grad_norm": 0.39211297035217285,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3789,
      "step": 64
    },
    {
      "epoch": 0.009215283192741192,
      "grad_norm": 0.507423996925354,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.3961,
      "step": 65
    },
    {
      "epoch": 0.009357056780321825,
      "grad_norm": 0.4308820366859436,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3715,
      "step": 66
    },
    {
      "epoch": 0.00949883036790246,
      "grad_norm": 0.32074931263923645,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.3241,
      "step": 67
    },
    {
      "epoch": 0.009640603955483093,
      "grad_norm": 0.4536798894405365,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.4396,
      "step": 68
    },
    {
      "epoch": 0.009782377543063728,
      "grad_norm": 0.3578198552131653,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.3105,
      "step": 69
    },
    {
      "epoch": 0.00992415113064436,
      "grad_norm": 0.3614351749420166,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3305,
      "step": 70
    },
    {
      "epoch": 0.010065924718224996,
      "grad_norm": 0.41987571120262146,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.3759,
      "step": 71
    },
    {
      "epoch": 0.010207698305805629,
      "grad_norm": 0.4036664664745331,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3656,
      "step": 72
    },
    {
      "epoch": 0.010207698305805629,
      "eval_loss": 0.3719382882118225,
      "eval_runtime": 461.9714,
      "eval_samples_per_second": 51.427,
      "eval_steps_per_second": 1.608,
      "step": 72
    },
    {
      "epoch": 0.010349471893386262,
      "grad_norm": 0.35854002833366394,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2636,
      "step": 73
    },
    {
      "epoch": 0.010491245480966896,
      "grad_norm": 0.3998740613460541,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.3917,
      "step": 74
    },
    {
      "epoch": 0.01063301906854753,
      "grad_norm": 0.3420690894126892,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.3281,
      "step": 75
    },
    {
      "epoch": 0.010774792656128164,
      "grad_norm": 0.29929959774017334,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.3321,
      "step": 76
    },
    {
      "epoch": 0.010916566243708797,
      "grad_norm": 0.3418530821800232,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.3091,
      "step": 77
    },
    {
      "epoch": 0.01105833983128943,
      "grad_norm": 0.4336473345756531,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3489,
      "step": 78
    },
    {
      "epoch": 0.011200113418870065,
      "grad_norm": 0.3733072280883789,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3986,
      "step": 79
    },
    {
      "epoch": 0.011341887006450698,
      "grad_norm": 0.42507871985435486,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3606,
      "step": 80
    },
    {
      "epoch": 0.011483660594031333,
      "grad_norm": 0.3113017976284027,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.295,
      "step": 81
    },
    {
      "epoch": 0.011483660594031333,
      "eval_loss": 0.36742064356803894,
      "eval_runtime": 457.918,
      "eval_samples_per_second": 51.883,
      "eval_steps_per_second": 1.623,
      "step": 81
    },
    {
      "epoch": 0.011625434181611966,
      "grad_norm": 0.4552273452281952,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3798,
      "step": 82
    },
    {
      "epoch": 0.0117672077691926,
      "grad_norm": 0.4212648272514343,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.4229,
      "step": 83
    },
    {
      "epoch": 0.011908981356773233,
      "grad_norm": 0.41278165578842163,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3868,
      "step": 84
    },
    {
      "epoch": 0.012050754944353866,
      "grad_norm": 0.5053354501724243,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4725,
      "step": 85
    },
    {
      "epoch": 0.012192528531934501,
      "grad_norm": 0.4368284344673157,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.3856,
      "step": 86
    },
    {
      "epoch": 0.012334302119515134,
      "grad_norm": 0.45541080832481384,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4256,
      "step": 87
    },
    {
      "epoch": 0.012476075707095769,
      "grad_norm": 0.4322318732738495,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.4001,
      "step": 88
    },
    {
      "epoch": 0.012617849294676402,
      "grad_norm": 0.3526219129562378,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2954,
      "step": 89
    },
    {
      "epoch": 0.012759622882257035,
      "grad_norm": 0.4916418492794037,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4267,
      "step": 90
    },
    {
      "epoch": 0.012759622882257035,
      "eval_loss": 0.36518150568008423,
      "eval_runtime": 456.8708,
      "eval_samples_per_second": 52.002,
      "eval_steps_per_second": 1.626,
      "step": 90
    },
    {
      "epoch": 0.01290139646983767,
      "grad_norm": 0.4147554039955139,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3658,
      "step": 91
    },
    {
      "epoch": 0.013043170057418303,
      "grad_norm": 0.5261914134025574,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.3629,
      "step": 92
    },
    {
      "epoch": 0.013184943644998937,
      "grad_norm": 0.368895947933197,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3717,
      "step": 93
    },
    {
      "epoch": 0.01332671723257957,
      "grad_norm": 0.42983049154281616,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.403,
      "step": 94
    },
    {
      "epoch": 0.013468490820160205,
      "grad_norm": 0.38002729415893555,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.4239,
      "step": 95
    },
    {
      "epoch": 0.013610264407740838,
      "grad_norm": 0.42320290207862854,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.3181,
      "step": 96
    },
    {
      "epoch": 0.013752037995321471,
      "grad_norm": 0.3484988212585449,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.3458,
      "step": 97
    },
    {
      "epoch": 0.013893811582902106,
      "grad_norm": 0.4318980872631073,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3584,
      "step": 98
    },
    {
      "epoch": 0.014035585170482739,
      "grad_norm": 0.4487537741661072,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.3669,
      "step": 99
    },
    {
      "epoch": 0.014035585170482739,
      "eval_loss": 0.36475813388824463,
      "eval_runtime": 456.8244,
      "eval_samples_per_second": 52.007,
      "eval_steps_per_second": 1.626,
      "step": 99
    },
    {
      "epoch": 0.014177358758063374,
      "grad_norm": 0.3945620357990265,
      "learning_rate": 0.0,
      "loss": 0.3663,
      "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": 3.031116601748357e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}