{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012773023374632776,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012773023374632777,
      "grad_norm": 0.7554705142974854,
      "learning_rate": 1e-05,
      "loss": 1.0085,
      "step": 1
    },
    {
      "epoch": 0.00012773023374632777,
      "eval_loss": 1.0360164642333984,
      "eval_runtime": 695.6018,
      "eval_samples_per_second": 9.478,
      "eval_steps_per_second": 1.186,
      "step": 1
    },
    {
      "epoch": 0.00025546046749265553,
      "grad_norm": 0.7813836336135864,
      "learning_rate": 2e-05,
      "loss": 1.021,
      "step": 2
    },
    {
      "epoch": 0.00038319070123898327,
      "grad_norm": 0.8181647658348083,
      "learning_rate": 3e-05,
      "loss": 1.0881,
      "step": 3
    },
    {
      "epoch": 0.0005109209349853111,
      "grad_norm": 0.6512744426727295,
      "learning_rate": 4e-05,
      "loss": 0.9681,
      "step": 4
    },
    {
      "epoch": 0.0006386511687316387,
      "grad_norm": 0.9087441563606262,
      "learning_rate": 5e-05,
      "loss": 1.1306,
      "step": 5
    },
    {
      "epoch": 0.0007663814024779665,
      "grad_norm": 0.679741621017456,
      "learning_rate": 6e-05,
      "loss": 0.9775,
      "step": 6
    },
    {
      "epoch": 0.0008941116362242943,
      "grad_norm": 0.702995240688324,
      "learning_rate": 7e-05,
      "loss": 0.9004,
      "step": 7
    },
    {
      "epoch": 0.0010218418699706221,
      "grad_norm": 0.6602010130882263,
      "learning_rate": 8e-05,
      "loss": 0.8342,
      "step": 8
    },
    {
      "epoch": 0.0011495721037169497,
      "grad_norm": 0.580272376537323,
      "learning_rate": 9e-05,
      "loss": 0.8136,
      "step": 9
    },
    {
      "epoch": 0.0011495721037169497,
      "eval_loss": 0.7176733613014221,
      "eval_runtime": 695.546,
      "eval_samples_per_second": 9.479,
      "eval_steps_per_second": 1.186,
      "step": 9
    },
    {
      "epoch": 0.0012773023374632775,
      "grad_norm": 0.6186894774436951,
      "learning_rate": 0.0001,
      "loss": 0.7633,
      "step": 10
    },
    {
      "epoch": 0.0014050325712096053,
      "grad_norm": 0.6979142427444458,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.6633,
      "step": 11
    },
    {
      "epoch": 0.001532762804955933,
      "grad_norm": 0.5527171492576599,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6386,
      "step": 12
    },
    {
      "epoch": 0.0016604930387022609,
      "grad_norm": 0.5357381701469421,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.5681,
      "step": 13
    },
    {
      "epoch": 0.0017882232724485887,
      "grad_norm": 0.5910691022872925,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.4372,
      "step": 14
    },
    {
      "epoch": 0.0019159535061949162,
      "grad_norm": 0.5314550399780273,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4318,
      "step": 15
    },
    {
      "epoch": 0.0020436837399412443,
      "grad_norm": 0.49278292059898376,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4241,
      "step": 16
    },
    {
      "epoch": 0.002171413973687572,
      "grad_norm": 0.5225505232810974,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.4098,
      "step": 17
    },
    {
      "epoch": 0.0022991442074338994,
      "grad_norm": 0.48126670718193054,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4857,
      "step": 18
    },
    {
      "epoch": 0.0022991442074338994,
      "eval_loss": 0.3560289442539215,
      "eval_runtime": 695.9474,
      "eval_samples_per_second": 9.473,
      "eval_steps_per_second": 1.185,
      "step": 18
    },
    {
      "epoch": 0.002426874441180227,
      "grad_norm": 0.41035354137420654,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3517,
      "step": 19
    },
    {
      "epoch": 0.002554604674926555,
      "grad_norm": 0.4637379050254822,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3347,
      "step": 20
    },
    {
      "epoch": 0.002682334908672883,
      "grad_norm": 0.4258130192756653,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3689,
      "step": 21
    },
    {
      "epoch": 0.0028100651424192106,
      "grad_norm": 0.3865697383880615,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.3041,
      "step": 22
    },
    {
      "epoch": 0.0029377953761655384,
      "grad_norm": 0.42880889773368835,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.3822,
      "step": 23
    },
    {
      "epoch": 0.003065525609911866,
      "grad_norm": 0.4190964996814728,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3054,
      "step": 24
    },
    {
      "epoch": 0.003193255843658194,
      "grad_norm": 0.3284166157245636,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.3263,
      "step": 25
    },
    {
      "epoch": 0.0033209860774045218,
      "grad_norm": 0.45865219831466675,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2244,
      "step": 26
    },
    {
      "epoch": 0.0034487163111508496,
      "grad_norm": 0.36550524830818176,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2901,
      "step": 27
    },
    {
      "epoch": 0.0034487163111508496,
      "eval_loss": 0.29397207498550415,
      "eval_runtime": 695.7063,
      "eval_samples_per_second": 9.477,
      "eval_steps_per_second": 1.186,
      "step": 27
    },
    {
      "epoch": 0.0035764465448971773,
      "grad_norm": 0.27659180760383606,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2554,
      "step": 28
    },
    {
      "epoch": 0.0037041767786435047,
      "grad_norm": 0.3061108887195587,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2813,
      "step": 29
    },
    {
      "epoch": 0.0038319070123898325,
      "grad_norm": 0.3267904222011566,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3132,
      "step": 30
    },
    {
      "epoch": 0.00395963724613616,
      "grad_norm": 0.271975576877594,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2374,
      "step": 31
    },
    {
      "epoch": 0.0040873674798824885,
      "grad_norm": 0.34335026144981384,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.5601,
      "step": 32
    },
    {
      "epoch": 0.004215097713628816,
      "grad_norm": 0.24212585389614105,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2673,
      "step": 33
    },
    {
      "epoch": 0.004342827947375144,
      "grad_norm": 0.2609688639640808,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2633,
      "step": 34
    },
    {
      "epoch": 0.0044705581811214715,
      "grad_norm": 0.21580959856510162,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.227,
      "step": 35
    },
    {
      "epoch": 0.004598288414867799,
      "grad_norm": 0.2412666380405426,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3108,
      "step": 36
    },
    {
      "epoch": 0.004598288414867799,
      "eval_loss": 0.27287757396698,
      "eval_runtime": 695.8428,
      "eval_samples_per_second": 9.475,
      "eval_steps_per_second": 1.186,
      "step": 36
    },
    {
      "epoch": 0.004726018648614127,
      "grad_norm": 0.2555369436740875,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2928,
      "step": 37
    },
    {
      "epoch": 0.004853748882360454,
      "grad_norm": 0.27513596415519714,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3757,
      "step": 38
    },
    {
      "epoch": 0.004981479116106783,
      "grad_norm": 0.22413450479507446,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2719,
      "step": 39
    },
    {
      "epoch": 0.00510920934985311,
      "grad_norm": 0.25909605622291565,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4132,
      "step": 40
    },
    {
      "epoch": 0.005236939583599438,
      "grad_norm": 0.25502490997314453,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.3649,
      "step": 41
    },
    {
      "epoch": 0.005364669817345766,
      "grad_norm": 0.253478467464447,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3994,
      "step": 42
    },
    {
      "epoch": 0.005492400051092094,
      "grad_norm": 0.2285216599702835,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2663,
      "step": 43
    },
    {
      "epoch": 0.005620130284838421,
      "grad_norm": 0.21321819722652435,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.4001,
      "step": 44
    },
    {
      "epoch": 0.005747860518584749,
      "grad_norm": 0.20976176857948303,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2715,
      "step": 45
    },
    {
      "epoch": 0.005747860518584749,
      "eval_loss": 0.2592501938343048,
      "eval_runtime": 695.5415,
      "eval_samples_per_second": 9.479,
      "eval_steps_per_second": 1.186,
      "step": 45
    },
    {
      "epoch": 0.005875590752331077,
      "grad_norm": 0.2345636636018753,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4093,
      "step": 46
    },
    {
      "epoch": 0.006003320986077404,
      "grad_norm": 0.22650215029716492,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2707,
      "step": 47
    },
    {
      "epoch": 0.006131051219823732,
      "grad_norm": 0.20617692172527313,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2525,
      "step": 48
    },
    {
      "epoch": 0.00625878145357006,
      "grad_norm": 0.20388655364513397,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2349,
      "step": 49
    },
    {
      "epoch": 0.006386511687316388,
      "grad_norm": 0.2104441225528717,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2044,
      "step": 50
    },
    {
      "epoch": 0.006514241921062715,
      "grad_norm": 0.20816461741924286,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2681,
      "step": 51
    },
    {
      "epoch": 0.0066419721548090435,
      "grad_norm": 0.21216654777526855,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2288,
      "step": 52
    },
    {
      "epoch": 0.006769702388555371,
      "grad_norm": 0.20397478342056274,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2458,
      "step": 53
    },
    {
      "epoch": 0.006897432622301699,
      "grad_norm": 0.19964686036109924,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.22,
      "step": 54
    },
    {
      "epoch": 0.006897432622301699,
      "eval_loss": 0.24918808043003082,
      "eval_runtime": 695.539,
      "eval_samples_per_second": 9.479,
      "eval_steps_per_second": 1.186,
      "step": 54
    },
    {
      "epoch": 0.0070251628560480265,
      "grad_norm": 0.2123086005449295,
      "learning_rate": 5e-05,
      "loss": 0.2356,
      "step": 55
    },
    {
      "epoch": 0.007152893089794355,
      "grad_norm": 0.22328320145606995,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2362,
      "step": 56
    },
    {
      "epoch": 0.007280623323540682,
      "grad_norm": 0.21200844645500183,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2329,
      "step": 57
    },
    {
      "epoch": 0.007408353557287009,
      "grad_norm": 0.2361147105693817,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2535,
      "step": 58
    },
    {
      "epoch": 0.007536083791033338,
      "grad_norm": 0.21640770137310028,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.235,
      "step": 59
    },
    {
      "epoch": 0.007663814024779665,
      "grad_norm": 0.2323594093322754,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2371,
      "step": 60
    },
    {
      "epoch": 0.007791544258525993,
      "grad_norm": 0.23051013052463531,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2927,
      "step": 61
    },
    {
      "epoch": 0.00791927449227232,
      "grad_norm": 0.2025759071111679,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2281,
      "step": 62
    },
    {
      "epoch": 0.008047004726018648,
      "grad_norm": 0.23811249434947968,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2551,
      "step": 63
    },
    {
      "epoch": 0.008047004726018648,
      "eval_loss": 0.24247978627681732,
      "eval_runtime": 695.4815,
      "eval_samples_per_second": 9.48,
      "eval_steps_per_second": 1.186,
      "step": 63
    },
    {
      "epoch": 0.008174734959764977,
      "grad_norm": 0.21948158740997314,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2454,
      "step": 64
    },
    {
      "epoch": 0.008302465193511304,
      "grad_norm": 0.21607862412929535,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2375,
      "step": 65
    },
    {
      "epoch": 0.008430195427257632,
      "grad_norm": 0.25880932807922363,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2655,
      "step": 66
    },
    {
      "epoch": 0.008557925661003959,
      "grad_norm": 0.2489837110042572,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2114,
      "step": 67
    },
    {
      "epoch": 0.008685655894750288,
      "grad_norm": 0.20333106815814972,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2037,
      "step": 68
    },
    {
      "epoch": 0.008813386128496616,
      "grad_norm": 0.2214207649230957,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.221,
      "step": 69
    },
    {
      "epoch": 0.008941116362242943,
      "grad_norm": 0.22859688103199005,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2135,
      "step": 70
    },
    {
      "epoch": 0.00906884659598927,
      "grad_norm": 0.23980282247066498,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2265,
      "step": 71
    },
    {
      "epoch": 0.009196576829735598,
      "grad_norm": 0.22004252672195435,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2166,
      "step": 72
    },
    {
      "epoch": 0.009196576829735598,
      "eval_loss": 0.23859815299510956,
      "eval_runtime": 695.5958,
      "eval_samples_per_second": 9.478,
      "eval_steps_per_second": 1.186,
      "step": 72
    },
    {
      "epoch": 0.009324307063481927,
      "grad_norm": 0.21411015093326569,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1823,
      "step": 73
    },
    {
      "epoch": 0.009452037297228254,
      "grad_norm": 0.2567249834537506,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2444,
      "step": 74
    },
    {
      "epoch": 0.009579767530974581,
      "grad_norm": 0.22692155838012695,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2381,
      "step": 75
    },
    {
      "epoch": 0.009707497764720909,
      "grad_norm": 0.2354595959186554,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.243,
      "step": 76
    },
    {
      "epoch": 0.009835227998467238,
      "grad_norm": 0.23027749359607697,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2329,
      "step": 77
    },
    {
      "epoch": 0.009962958232213565,
      "grad_norm": 0.2699197232723236,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.4067,
      "step": 78
    },
    {
      "epoch": 0.010090688465959893,
      "grad_norm": 0.21186845004558563,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2092,
      "step": 79
    },
    {
      "epoch": 0.01021841869970622,
      "grad_norm": 0.2345714122056961,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2354,
      "step": 80
    },
    {
      "epoch": 0.010346148933452547,
      "grad_norm": 0.23713068664073944,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2358,
      "step": 81
    },
    {
      "epoch": 0.010346148933452547,
      "eval_loss": 0.2366475909948349,
      "eval_runtime": 696.6434,
      "eval_samples_per_second": 9.464,
      "eval_steps_per_second": 1.184,
      "step": 81
    },
    {
      "epoch": 0.010473879167198876,
      "grad_norm": 0.240807443857193,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2159,
      "step": 82
    },
    {
      "epoch": 0.010601609400945204,
      "grad_norm": 0.2546962797641754,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2251,
      "step": 83
    },
    {
      "epoch": 0.010729339634691531,
      "grad_norm": 0.22596092522144318,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1835,
      "step": 84
    },
    {
      "epoch": 0.010857069868437859,
      "grad_norm": 0.2240147888660431,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2367,
      "step": 85
    },
    {
      "epoch": 0.010984800102184188,
      "grad_norm": 0.21561257541179657,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2065,
      "step": 86
    },
    {
      "epoch": 0.011112530335930515,
      "grad_norm": 0.2575628459453583,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2126,
      "step": 87
    },
    {
      "epoch": 0.011240260569676842,
      "grad_norm": 0.22616754472255707,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2175,
      "step": 88
    },
    {
      "epoch": 0.01136799080342317,
      "grad_norm": 0.2656971514225006,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.261,
      "step": 89
    },
    {
      "epoch": 0.011495721037169499,
      "grad_norm": 0.22394046187400818,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.223,
      "step": 90
    },
    {
      "epoch": 0.011495721037169499,
      "eval_loss": 0.23559892177581787,
      "eval_runtime": 696.0505,
      "eval_samples_per_second": 9.472,
      "eval_steps_per_second": 1.185,
      "step": 90
    },
    {
      "epoch": 0.011623451270915826,
      "grad_norm": 0.2391272783279419,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2882,
      "step": 91
    },
    {
      "epoch": 0.011751181504662154,
      "grad_norm": 0.2529905140399933,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2448,
      "step": 92
    },
    {
      "epoch": 0.011878911738408481,
      "grad_norm": 0.22004134953022003,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.215,
      "step": 93
    },
    {
      "epoch": 0.012006641972154808,
      "grad_norm": 0.22307589650154114,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2087,
      "step": 94
    },
    {
      "epoch": 0.012134372205901137,
      "grad_norm": 0.2611097991466522,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.254,
      "step": 95
    },
    {
      "epoch": 0.012262102439647465,
      "grad_norm": 0.22441336512565613,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2229,
      "step": 96
    },
    {
      "epoch": 0.012389832673393792,
      "grad_norm": 0.23511357605457306,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.186,
      "step": 97
    },
    {
      "epoch": 0.01251756290714012,
      "grad_norm": 0.2311200350522995,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1808,
      "step": 98
    },
    {
      "epoch": 0.012645293140886448,
      "grad_norm": 0.2409658282995224,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2209,
      "step": 99
    },
    {
      "epoch": 0.012645293140886448,
      "eval_loss": 0.2354019284248352,
      "eval_runtime": 696.1494,
      "eval_samples_per_second": 9.471,
      "eval_steps_per_second": 1.185,
      "step": 99
    },
    {
      "epoch": 0.012773023374632776,
      "grad_norm": 0.24480025470256805,
      "learning_rate": 0.0,
      "loss": 0.2418,
      "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": 3.342082388262912e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}