{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09528346831824679,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 1.3314216136932373,
      "learning_rate": 1e-05,
      "loss": 2.8561,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "eval_loss": 3.010896921157837,
      "eval_runtime": 194.9161,
      "eval_samples_per_second": 4.535,
      "eval_steps_per_second": 0.569,
      "step": 1
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 1.108765721321106,
      "learning_rate": 2e-05,
      "loss": 2.8611,
      "step": 2
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.0992165803909302,
      "learning_rate": 3e-05,
      "loss": 2.958,
      "step": 3
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.9974603652954102,
      "learning_rate": 4e-05,
      "loss": 2.8721,
      "step": 4
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 1.0912249088287354,
      "learning_rate": 5e-05,
      "loss": 2.8375,
      "step": 5
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 1.070563793182373,
      "learning_rate": 6e-05,
      "loss": 2.7195,
      "step": 6
    },
    {
      "epoch": 0.006669842782277275,
      "grad_norm": 1.2317885160446167,
      "learning_rate": 7e-05,
      "loss": 2.816,
      "step": 7
    },
    {
      "epoch": 0.007622677465459742,
      "grad_norm": 1.3422398567199707,
      "learning_rate": 8e-05,
      "loss": 2.6737,
      "step": 8
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 1.3986526727676392,
      "learning_rate": 9e-05,
      "loss": 2.7706,
      "step": 9
    },
    {
      "epoch": 0.00857551214864221,
      "eval_loss": 2.8102166652679443,
      "eval_runtime": 195.3531,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 9
    },
    {
      "epoch": 0.009528346831824679,
      "grad_norm": 1.2939263582229614,
      "learning_rate": 0.0001,
      "loss": 2.8952,
      "step": 10
    },
    {
      "epoch": 0.010481181515007145,
      "grad_norm": 1.1111377477645874,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.7657,
      "step": 11
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 1.2477428913116455,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4967,
      "step": 12
    },
    {
      "epoch": 0.012386850881372083,
      "grad_norm": 1.0746080875396729,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.359,
      "step": 13
    },
    {
      "epoch": 0.01333968556455455,
      "grad_norm": 1.6572176218032837,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.608,
      "step": 14
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 1.4233778715133667,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4839,
      "step": 15
    },
    {
      "epoch": 0.015245354930919485,
      "grad_norm": 1.346785306930542,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.4763,
      "step": 16
    },
    {
      "epoch": 0.016198189614101955,
      "grad_norm": 1.2152442932128906,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.428,
      "step": 17
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 1.0687611103057861,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4665,
      "step": 18
    },
    {
      "epoch": 0.01715102429728442,
      "eval_loss": 2.5243494510650635,
      "eval_runtime": 195.3053,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 18
    },
    {
      "epoch": 0.01810385898046689,
      "grad_norm": 1.1508054733276367,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3153,
      "step": 19
    },
    {
      "epoch": 0.019056693663649357,
      "grad_norm": 1.267975091934204,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4924,
      "step": 20
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 1.2117677927017212,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4421,
      "step": 21
    },
    {
      "epoch": 0.02096236303001429,
      "grad_norm": 1.7183105945587158,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.6475,
      "step": 22
    },
    {
      "epoch": 0.02191519771319676,
      "grad_norm": 1.2931954860687256,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.0165,
      "step": 23
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 1.4074746370315552,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.8582,
      "step": 24
    },
    {
      "epoch": 0.023820867079561697,
      "grad_norm": 1.149705410003662,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2325,
      "step": 25
    },
    {
      "epoch": 0.024773701762744165,
      "grad_norm": 1.1608455181121826,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.4246,
      "step": 26
    },
    {
      "epoch": 0.02572653644592663,
      "grad_norm": 1.520585298538208,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.7656,
      "step": 27
    },
    {
      "epoch": 0.02572653644592663,
      "eval_loss": 2.388444423675537,
      "eval_runtime": 195.2733,
      "eval_samples_per_second": 4.527,
      "eval_steps_per_second": 0.568,
      "step": 27
    },
    {
      "epoch": 0.0266793711291091,
      "grad_norm": 1.0983319282531738,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0036,
      "step": 28
    },
    {
      "epoch": 0.027632205812291567,
      "grad_norm": 1.2645291090011597,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.3768,
      "step": 29
    },
    {
      "epoch": 0.028585040495474036,
      "grad_norm": 1.0958126783370972,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1706,
      "step": 30
    },
    {
      "epoch": 0.029537875178656504,
      "grad_norm": 1.6864413022994995,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.7613,
      "step": 31
    },
    {
      "epoch": 0.03049070986183897,
      "grad_norm": 8.486473083496094,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.4582,
      "step": 32
    },
    {
      "epoch": 0.03144354454502144,
      "grad_norm": 1.4310030937194824,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.5887,
      "step": 33
    },
    {
      "epoch": 0.03239637922820391,
      "grad_norm": 1.9405314922332764,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.3926,
      "step": 34
    },
    {
      "epoch": 0.03334921391138637,
      "grad_norm": 1.6728031635284424,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3928,
      "step": 35
    },
    {
      "epoch": 0.03430204859456884,
      "grad_norm": 2.5665833950042725,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.5681,
      "step": 36
    },
    {
      "epoch": 0.03430204859456884,
      "eval_loss": 2.3183698654174805,
      "eval_runtime": 195.29,
      "eval_samples_per_second": 4.527,
      "eval_steps_per_second": 0.568,
      "step": 36
    },
    {
      "epoch": 0.03525488327775131,
      "grad_norm": 3.006268262863159,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2294,
      "step": 37
    },
    {
      "epoch": 0.03620771796093378,
      "grad_norm": 1.0738325119018555,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.3217,
      "step": 38
    },
    {
      "epoch": 0.037160552644116246,
      "grad_norm": 1.1440376043319702,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.1976,
      "step": 39
    },
    {
      "epoch": 0.038113387327298714,
      "grad_norm": 1.2780272960662842,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2665,
      "step": 40
    },
    {
      "epoch": 0.03906622201048118,
      "grad_norm": 1.0667051076889038,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.2043,
      "step": 41
    },
    {
      "epoch": 0.04001905669366365,
      "grad_norm": 1.230981707572937,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9738,
      "step": 42
    },
    {
      "epoch": 0.04097189137684612,
      "grad_norm": 1.1416908502578735,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.256,
      "step": 43
    },
    {
      "epoch": 0.04192472606002858,
      "grad_norm": 1.4842567443847656,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.2914,
      "step": 44
    },
    {
      "epoch": 0.04287756074321105,
      "grad_norm": 1.039803147315979,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1142,
      "step": 45
    },
    {
      "epoch": 0.04287756074321105,
      "eval_loss": 2.283740520477295,
      "eval_runtime": 195.2949,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 45
    },
    {
      "epoch": 0.04383039542639352,
      "grad_norm": 2.066823720932007,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2865,
      "step": 46
    },
    {
      "epoch": 0.04478323010957599,
      "grad_norm": 1.3638314008712769,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1797,
      "step": 47
    },
    {
      "epoch": 0.045736064792758456,
      "grad_norm": 1.3101152181625366,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.3253,
      "step": 48
    },
    {
      "epoch": 0.046688899475940925,
      "grad_norm": 1.1173464059829712,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1469,
      "step": 49
    },
    {
      "epoch": 0.04764173415912339,
      "grad_norm": 0.9268816113471985,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0037,
      "step": 50
    },
    {
      "epoch": 0.04859456884230586,
      "grad_norm": 0.9991522431373596,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.2485,
      "step": 51
    },
    {
      "epoch": 0.04954740352548833,
      "grad_norm": 1.1253869533538818,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.0507,
      "step": 52
    },
    {
      "epoch": 0.0505002382086708,
      "grad_norm": 0.9809867739677429,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.038,
      "step": 53
    },
    {
      "epoch": 0.05145307289185326,
      "grad_norm": 1.0923676490783691,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.4383,
      "step": 54
    },
    {
      "epoch": 0.05145307289185326,
      "eval_loss": 2.2689011096954346,
      "eval_runtime": 195.1248,
      "eval_samples_per_second": 4.53,
      "eval_steps_per_second": 0.569,
      "step": 54
    },
    {
      "epoch": 0.05240590757503573,
      "grad_norm": 1.0306025743484497,
      "learning_rate": 5e-05,
      "loss": 2.1825,
      "step": 55
    },
    {
      "epoch": 0.0533587422582182,
      "grad_norm": 1.4191091060638428,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.6339,
      "step": 56
    },
    {
      "epoch": 0.054311576941400666,
      "grad_norm": 1.2226223945617676,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.204,
      "step": 57
    },
    {
      "epoch": 0.055264411624583135,
      "grad_norm": 5.3369951248168945,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.0067,
      "step": 58
    },
    {
      "epoch": 0.0562172463077656,
      "grad_norm": 1.2273885011672974,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2786,
      "step": 59
    },
    {
      "epoch": 0.05717008099094807,
      "grad_norm": 1.1748491525650024,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.415,
      "step": 60
    },
    {
      "epoch": 0.05812291567413054,
      "grad_norm": 1.1600786447525024,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.2855,
      "step": 61
    },
    {
      "epoch": 0.05907575035731301,
      "grad_norm": 1.1740864515304565,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.2457,
      "step": 62
    },
    {
      "epoch": 0.06002858504049548,
      "grad_norm": 0.8164812922477722,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.0255,
      "step": 63
    },
    {
      "epoch": 0.06002858504049548,
      "eval_loss": 2.2617905139923096,
      "eval_runtime": 195.3121,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 63
    },
    {
      "epoch": 0.06098141972367794,
      "grad_norm": 1.8397961854934692,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.3015,
      "step": 64
    },
    {
      "epoch": 0.06193425440686041,
      "grad_norm": 1.4221397638320923,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.1798,
      "step": 65
    },
    {
      "epoch": 0.06288708909004288,
      "grad_norm": 5.245110034942627,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.2569,
      "step": 66
    },
    {
      "epoch": 0.06383992377322535,
      "grad_norm": 1.1781222820281982,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.11,
      "step": 67
    },
    {
      "epoch": 0.06479275845640782,
      "grad_norm": 1.3529887199401855,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.2486,
      "step": 68
    },
    {
      "epoch": 0.06574559313959027,
      "grad_norm": 1.1169679164886475,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.1643,
      "step": 69
    },
    {
      "epoch": 0.06669842782277274,
      "grad_norm": 1.144498586654663,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.2978,
      "step": 70
    },
    {
      "epoch": 0.06765126250595521,
      "grad_norm": 1.211686611175537,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.1954,
      "step": 71
    },
    {
      "epoch": 0.06860409718913768,
      "grad_norm": 1.1945290565490723,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2826,
      "step": 72
    },
    {
      "epoch": 0.06860409718913768,
      "eval_loss": 2.2520430088043213,
      "eval_runtime": 195.2934,
      "eval_samples_per_second": 4.527,
      "eval_steps_per_second": 0.568,
      "step": 72
    },
    {
      "epoch": 0.06955693187232015,
      "grad_norm": 0.8045013546943665,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0106,
      "step": 73
    },
    {
      "epoch": 0.07050976655550262,
      "grad_norm": 0.9519303441047668,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1426,
      "step": 74
    },
    {
      "epoch": 0.07146260123868509,
      "grad_norm": 0.9403889775276184,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.1034,
      "step": 75
    },
    {
      "epoch": 0.07241543592186755,
      "grad_norm": 1.2492951154708862,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.2339,
      "step": 76
    },
    {
      "epoch": 0.07336827060505002,
      "grad_norm": 1.2088156938552856,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.2098,
      "step": 77
    },
    {
      "epoch": 0.07432110528823249,
      "grad_norm": 1.1127347946166992,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9861,
      "step": 78
    },
    {
      "epoch": 0.07527393997141496,
      "grad_norm": 1.0793708562850952,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.9812,
      "step": 79
    },
    {
      "epoch": 0.07622677465459743,
      "grad_norm": 1.1515878438949585,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.0356,
      "step": 80
    },
    {
      "epoch": 0.0771796093377799,
      "grad_norm": 1.2502024173736572,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.1648,
      "step": 81
    },
    {
      "epoch": 0.0771796093377799,
      "eval_loss": 2.2468369007110596,
      "eval_runtime": 195.3237,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 81
    },
    {
      "epoch": 0.07813244402096237,
      "grad_norm": 1.0776357650756836,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.2496,
      "step": 82
    },
    {
      "epoch": 0.07908527870414483,
      "grad_norm": 0.9755646586418152,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.0841,
      "step": 83
    },
    {
      "epoch": 0.0800381133873273,
      "grad_norm": 0.9808889031410217,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.3795,
      "step": 84
    },
    {
      "epoch": 0.08099094807050977,
      "grad_norm": 0.9751318693161011,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.3177,
      "step": 85
    },
    {
      "epoch": 0.08194378275369224,
      "grad_norm": 1.2370442152023315,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.4818,
      "step": 86
    },
    {
      "epoch": 0.08289661743687471,
      "grad_norm": 1.041976809501648,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.1223,
      "step": 87
    },
    {
      "epoch": 0.08384945212005716,
      "grad_norm": 1.0111206769943237,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.0988,
      "step": 88
    },
    {
      "epoch": 0.08480228680323963,
      "grad_norm": 1.0791726112365723,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.2097,
      "step": 89
    },
    {
      "epoch": 0.0857551214864221,
      "grad_norm": 0.8062794208526611,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8917,
      "step": 90
    },
    {
      "epoch": 0.0857551214864221,
      "eval_loss": 2.2454254627227783,
      "eval_runtime": 195.2505,
      "eval_samples_per_second": 4.528,
      "eval_steps_per_second": 0.569,
      "step": 90
    },
    {
      "epoch": 0.08670795616960457,
      "grad_norm": 1.086729884147644,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.3498,
      "step": 91
    },
    {
      "epoch": 0.08766079085278704,
      "grad_norm": 3.8277571201324463,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1474,
      "step": 92
    },
    {
      "epoch": 0.0886136255359695,
      "grad_norm": 1.1703578233718872,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.2442,
      "step": 93
    },
    {
      "epoch": 0.08956646021915197,
      "grad_norm": 0.9999949336051941,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2552,
      "step": 94
    },
    {
      "epoch": 0.09051929490233444,
      "grad_norm": 1.0868746042251587,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.914,
      "step": 95
    },
    {
      "epoch": 0.09147212958551691,
      "grad_norm": 1.091508150100708,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.0883,
      "step": 96
    },
    {
      "epoch": 0.09242496426869938,
      "grad_norm": 1.046575903892517,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.4059,
      "step": 97
    },
    {
      "epoch": 0.09337779895188185,
      "grad_norm": 1.3036117553710938,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.2796,
      "step": 98
    },
    {
      "epoch": 0.09433063363506432,
      "grad_norm": 1.0407637357711792,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.309,
      "step": 99
    },
    {
      "epoch": 0.09433063363506432,
      "eval_loss": 2.244947671890259,
      "eval_runtime": 195.3553,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 99
    },
    {
      "epoch": 0.09528346831824679,
      "grad_norm": 1.2726835012435913,
      "learning_rate": 0.0,
      "loss": 2.3422,
      "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": 1.483774567120896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}