{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005183361409874304,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.183361409874304e-05,
      "grad_norm": 2.3113319873809814,
      "learning_rate": 1e-05,
      "loss": 3.5351,
      "step": 1
    },
    {
      "epoch": 5.183361409874304e-05,
      "eval_loss": 3.5113468170166016,
      "eval_runtime": 1769.9186,
      "eval_samples_per_second": 9.18,
      "eval_steps_per_second": 1.148,
      "step": 1
    },
    {
      "epoch": 0.00010366722819748608,
      "grad_norm": 2.229635238647461,
      "learning_rate": 2e-05,
      "loss": 3.4005,
      "step": 2
    },
    {
      "epoch": 0.00015550084229622911,
      "grad_norm": 2.0467476844787598,
      "learning_rate": 3e-05,
      "loss": 3.5197,
      "step": 3
    },
    {
      "epoch": 0.00020733445639497215,
      "grad_norm": 2.512348175048828,
      "learning_rate": 4e-05,
      "loss": 3.621,
      "step": 4
    },
    {
      "epoch": 0.0002591680704937152,
      "grad_norm": 2.532371997833252,
      "learning_rate": 5e-05,
      "loss": 3.5631,
      "step": 5
    },
    {
      "epoch": 0.00031100168459245823,
      "grad_norm": 2.249849319458008,
      "learning_rate": 6e-05,
      "loss": 3.404,
      "step": 6
    },
    {
      "epoch": 0.00036283529869120127,
      "grad_norm": 2.5401272773742676,
      "learning_rate": 7e-05,
      "loss": 3.4107,
      "step": 7
    },
    {
      "epoch": 0.0004146689127899443,
      "grad_norm": 2.23197603225708,
      "learning_rate": 8e-05,
      "loss": 3.0562,
      "step": 8
    },
    {
      "epoch": 0.0004665025268886873,
      "grad_norm": 2.439784526824951,
      "learning_rate": 9e-05,
      "loss": 3.0909,
      "step": 9
    },
    {
      "epoch": 0.0004665025268886873,
      "eval_loss": 2.900395393371582,
      "eval_runtime": 1774.4876,
      "eval_samples_per_second": 9.156,
      "eval_steps_per_second": 1.145,
      "step": 9
    },
    {
      "epoch": 0.0005183361409874304,
      "grad_norm": 2.121995687484741,
      "learning_rate": 0.0001,
      "loss": 2.7377,
      "step": 10
    },
    {
      "epoch": 0.0005701697550861734,
      "grad_norm": 2.543422222137451,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.8312,
      "step": 11
    },
    {
      "epoch": 0.0006220033691849165,
      "grad_norm": 3.130173444747925,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8057,
      "step": 12
    },
    {
      "epoch": 0.0006738369832836595,
      "grad_norm": 2.596888542175293,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6877,
      "step": 13
    },
    {
      "epoch": 0.0007256705973824025,
      "grad_norm": 2.7695186138153076,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.8845,
      "step": 14
    },
    {
      "epoch": 0.0007775042114811456,
      "grad_norm": 2.208770751953125,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4707,
      "step": 15
    },
    {
      "epoch": 0.0008293378255798886,
      "grad_norm": 2.075831174850464,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.6753,
      "step": 16
    },
    {
      "epoch": 0.0008811714396786315,
      "grad_norm": 3.6710920333862305,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.5295,
      "step": 17
    },
    {
      "epoch": 0.0009330050537773746,
      "grad_norm": 1.9427752494812012,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.5586,
      "step": 18
    },
    {
      "epoch": 0.0009330050537773746,
      "eval_loss": 2.5122954845428467,
      "eval_runtime": 1772.457,
      "eval_samples_per_second": 9.166,
      "eval_steps_per_second": 1.146,
      "step": 18
    },
    {
      "epoch": 0.0009848386678761177,
      "grad_norm": 2.3610899448394775,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5588,
      "step": 19
    },
    {
      "epoch": 0.0010366722819748608,
      "grad_norm": 1.9613486528396606,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5903,
      "step": 20
    },
    {
      "epoch": 0.0010885058960736038,
      "grad_norm": 1.8334481716156006,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4418,
      "step": 21
    },
    {
      "epoch": 0.0011403395101723468,
      "grad_norm": 1.7611281871795654,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.5619,
      "step": 22
    },
    {
      "epoch": 0.0011921731242710899,
      "grad_norm": 2.285313606262207,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.4165,
      "step": 23
    },
    {
      "epoch": 0.001244006738369833,
      "grad_norm": 1.6585972309112549,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.4672,
      "step": 24
    },
    {
      "epoch": 0.001295840352468576,
      "grad_norm": 1.6722080707550049,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3507,
      "step": 25
    },
    {
      "epoch": 0.001347673966567319,
      "grad_norm": 2.0271666049957275,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.3528,
      "step": 26
    },
    {
      "epoch": 0.001399507580666062,
      "grad_norm": 1.7645819187164307,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.4185,
      "step": 27
    },
    {
      "epoch": 0.001399507580666062,
      "eval_loss": 2.4034855365753174,
      "eval_runtime": 1773.3095,
      "eval_samples_per_second": 9.162,
      "eval_steps_per_second": 1.145,
      "step": 27
    },
    {
      "epoch": 0.001451341194764805,
      "grad_norm": 1.8423093557357788,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4298,
      "step": 28
    },
    {
      "epoch": 0.001503174808863548,
      "grad_norm": 2.868162155151367,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.3648,
      "step": 29
    },
    {
      "epoch": 0.0015550084229622911,
      "grad_norm": 2.26560378074646,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.3836,
      "step": 30
    },
    {
      "epoch": 0.0016068420370610342,
      "grad_norm": 1.755423665046692,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.3411,
      "step": 31
    },
    {
      "epoch": 0.0016586756511597772,
      "grad_norm": 1.673230528831482,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.5404,
      "step": 32
    },
    {
      "epoch": 0.0017105092652585203,
      "grad_norm": 1.7275108098983765,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.492,
      "step": 33
    },
    {
      "epoch": 0.001762342879357263,
      "grad_norm": 1.8824987411499023,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.5956,
      "step": 34
    },
    {
      "epoch": 0.0018141764934560061,
      "grad_norm": 1.8801908493041992,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.427,
      "step": 35
    },
    {
      "epoch": 0.0018660101075547492,
      "grad_norm": 2.096254587173462,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.4255,
      "step": 36
    },
    {
      "epoch": 0.0018660101075547492,
      "eval_loss": 2.351825475692749,
      "eval_runtime": 1774.3205,
      "eval_samples_per_second": 9.157,
      "eval_steps_per_second": 1.145,
      "step": 36
    },
    {
      "epoch": 0.0019178437216534922,
      "grad_norm": 2.0004048347473145,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0979,
      "step": 37
    },
    {
      "epoch": 0.0019696773357522354,
      "grad_norm": 2.086202621459961,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2972,
      "step": 38
    },
    {
      "epoch": 0.0020215109498509785,
      "grad_norm": 1.5125240087509155,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.3179,
      "step": 39
    },
    {
      "epoch": 0.0020733445639497215,
      "grad_norm": 1.5626386404037476,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2221,
      "step": 40
    },
    {
      "epoch": 0.0021251781780484646,
      "grad_norm": 1.8468570709228516,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.436,
      "step": 41
    },
    {
      "epoch": 0.0021770117921472076,
      "grad_norm": 1.7203456163406372,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.3326,
      "step": 42
    },
    {
      "epoch": 0.0022288454062459506,
      "grad_norm": 1.7609412670135498,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.4079,
      "step": 43
    },
    {
      "epoch": 0.0022806790203446937,
      "grad_norm": 1.9543553590774536,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.3076,
      "step": 44
    },
    {
      "epoch": 0.0023325126344434367,
      "grad_norm": 1.9948867559432983,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.3295,
      "step": 45
    },
    {
      "epoch": 0.0023325126344434367,
      "eval_loss": 2.3102049827575684,
      "eval_runtime": 1772.0158,
      "eval_samples_per_second": 9.169,
      "eval_steps_per_second": 1.146,
      "step": 45
    },
    {
      "epoch": 0.0023843462485421798,
      "grad_norm": 1.8627070188522339,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2056,
      "step": 46
    },
    {
      "epoch": 0.002436179862640923,
      "grad_norm": 1.692333459854126,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.2567,
      "step": 47
    },
    {
      "epoch": 0.002488013476739666,
      "grad_norm": 1.8308770656585693,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.3291,
      "step": 48
    },
    {
      "epoch": 0.002539847090838409,
      "grad_norm": 1.635390281677246,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.4812,
      "step": 49
    },
    {
      "epoch": 0.002591680704937152,
      "grad_norm": 1.5308008193969727,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.2056,
      "step": 50
    },
    {
      "epoch": 0.002643514319035895,
      "grad_norm": 2.0369045734405518,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.3343,
      "step": 51
    },
    {
      "epoch": 0.002695347933134638,
      "grad_norm": 2.05702805519104,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.3432,
      "step": 52
    },
    {
      "epoch": 0.002747181547233381,
      "grad_norm": 2.1582486629486084,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.2655,
      "step": 53
    },
    {
      "epoch": 0.002799015161332124,
      "grad_norm": 1.8354802131652832,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.3433,
      "step": 54
    },
    {
      "epoch": 0.002799015161332124,
      "eval_loss": 2.2847542762756348,
      "eval_runtime": 1770.0011,
      "eval_samples_per_second": 9.179,
      "eval_steps_per_second": 1.147,
      "step": 54
    },
    {
      "epoch": 0.002850848775430867,
      "grad_norm": 1.9610837697982788,
      "learning_rate": 5e-05,
      "loss": 2.1992,
      "step": 55
    },
    {
      "epoch": 0.00290268238952961,
      "grad_norm": 1.579572081565857,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.1116,
      "step": 56
    },
    {
      "epoch": 0.002954516003628353,
      "grad_norm": 1.77374267578125,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.2648,
      "step": 57
    },
    {
      "epoch": 0.003006349617727096,
      "grad_norm": 1.728236198425293,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.0728,
      "step": 58
    },
    {
      "epoch": 0.0030581832318258392,
      "grad_norm": 1.6870540380477905,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.4743,
      "step": 59
    },
    {
      "epoch": 0.0031100168459245823,
      "grad_norm": 1.6203986406326294,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.2212,
      "step": 60
    },
    {
      "epoch": 0.0031618504600233253,
      "grad_norm": 1.8643229007720947,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.1234,
      "step": 61
    },
    {
      "epoch": 0.0032136840741220684,
      "grad_norm": 1.7956637144088745,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.3623,
      "step": 62
    },
    {
      "epoch": 0.0032655176882208114,
      "grad_norm": 1.8225525617599487,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.4043,
      "step": 63
    },
    {
      "epoch": 0.0032655176882208114,
      "eval_loss": 2.261367082595825,
      "eval_runtime": 1771.9017,
      "eval_samples_per_second": 9.169,
      "eval_steps_per_second": 1.146,
      "step": 63
    },
    {
      "epoch": 0.0033173513023195544,
      "grad_norm": 1.7963026762008667,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.2372,
      "step": 64
    },
    {
      "epoch": 0.0033691849164182975,
      "grad_norm": 2.1030032634735107,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.3892,
      "step": 65
    },
    {
      "epoch": 0.0034210185305170405,
      "grad_norm": 1.8022874593734741,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.3182,
      "step": 66
    },
    {
      "epoch": 0.003472852144615783,
      "grad_norm": 1.59199059009552,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.0964,
      "step": 67
    },
    {
      "epoch": 0.003524685758714526,
      "grad_norm": 1.6810811758041382,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.2439,
      "step": 68
    },
    {
      "epoch": 0.003576519372813269,
      "grad_norm": 1.7184687852859497,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.2171,
      "step": 69
    },
    {
      "epoch": 0.0036283529869120122,
      "grad_norm": 1.6229767799377441,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1948,
      "step": 70
    },
    {
      "epoch": 0.0036801866010107553,
      "grad_norm": 2.0005605220794678,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.3955,
      "step": 71
    },
    {
      "epoch": 0.0037320202151094983,
      "grad_norm": 1.8693921566009521,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2246,
      "step": 72
    },
    {
      "epoch": 0.0037320202151094983,
      "eval_loss": 2.2489724159240723,
      "eval_runtime": 1772.581,
      "eval_samples_per_second": 9.166,
      "eval_steps_per_second": 1.146,
      "step": 72
    },
    {
      "epoch": 0.0037838538292082413,
      "grad_norm": 1.7349319458007812,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.331,
      "step": 73
    },
    {
      "epoch": 0.0038356874433069844,
      "grad_norm": 1.7528749704360962,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.3136,
      "step": 74
    },
    {
      "epoch": 0.0038875210574057274,
      "grad_norm": 2.004699468612671,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.3924,
      "step": 75
    },
    {
      "epoch": 0.003939354671504471,
      "grad_norm": 1.9035282135009766,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.1904,
      "step": 76
    },
    {
      "epoch": 0.0039911882856032135,
      "grad_norm": 1.868543028831482,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.3523,
      "step": 77
    },
    {
      "epoch": 0.004043021899701957,
      "grad_norm": 1.9037656784057617,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.3251,
      "step": 78
    },
    {
      "epoch": 0.0040948555138007,
      "grad_norm": 1.8855937719345093,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.974,
      "step": 79
    },
    {
      "epoch": 0.004146689127899443,
      "grad_norm": 1.6533581018447876,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.1961,
      "step": 80
    },
    {
      "epoch": 0.004198522741998186,
      "grad_norm": 1.6351205110549927,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.2121,
      "step": 81
    },
    {
      "epoch": 0.004198522741998186,
      "eval_loss": 2.2391388416290283,
      "eval_runtime": 1773.2182,
      "eval_samples_per_second": 9.162,
      "eval_steps_per_second": 1.145,
      "step": 81
    },
    {
      "epoch": 0.004250356356096929,
      "grad_norm": 1.744607925415039,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1732,
      "step": 82
    },
    {
      "epoch": 0.004302189970195672,
      "grad_norm": 1.846276044845581,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.0788,
      "step": 83
    },
    {
      "epoch": 0.004354023584294415,
      "grad_norm": 1.7794817686080933,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.2174,
      "step": 84
    },
    {
      "epoch": 0.004405857198393158,
      "grad_norm": 1.8473767042160034,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1947,
      "step": 85
    },
    {
      "epoch": 0.004457690812491901,
      "grad_norm": 1.684167742729187,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.1724,
      "step": 86
    },
    {
      "epoch": 0.004509524426590644,
      "grad_norm": 1.7272619009017944,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.2323,
      "step": 87
    },
    {
      "epoch": 0.004561358040689387,
      "grad_norm": 1.6552352905273438,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1764,
      "step": 88
    },
    {
      "epoch": 0.00461319165478813,
      "grad_norm": 1.6339068412780762,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.4096,
      "step": 89
    },
    {
      "epoch": 0.004665025268886873,
      "grad_norm": 1.717753291130066,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.1329,
      "step": 90
    },
    {
      "epoch": 0.004665025268886873,
      "eval_loss": 2.235034465789795,
      "eval_runtime": 1771.9502,
      "eval_samples_per_second": 9.169,
      "eval_steps_per_second": 1.146,
      "step": 90
    },
    {
      "epoch": 0.004716858882985616,
      "grad_norm": 1.6244786977767944,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.1637,
      "step": 91
    },
    {
      "epoch": 0.0047686924970843595,
      "grad_norm": 1.8540843725204468,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1113,
      "step": 92
    },
    {
      "epoch": 0.004820526111183102,
      "grad_norm": 1.5808759927749634,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.3416,
      "step": 93
    },
    {
      "epoch": 0.004872359725281846,
      "grad_norm": 2.3207199573516846,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2717,
      "step": 94
    },
    {
      "epoch": 0.004924193339380588,
      "grad_norm": 1.8996020555496216,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.1846,
      "step": 95
    },
    {
      "epoch": 0.004976026953479332,
      "grad_norm": 1.9061933755874634,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.3429,
      "step": 96
    },
    {
      "epoch": 0.005027860567578074,
      "grad_norm": 1.855987310409546,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.276,
      "step": 97
    },
    {
      "epoch": 0.005079694181676818,
      "grad_norm": 2.0523297786712646,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0707,
      "step": 98
    },
    {
      "epoch": 0.00513152779577556,
      "grad_norm": 1.991876482963562,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.0749,
      "step": 99
    },
    {
      "epoch": 0.00513152779577556,
      "eval_loss": 2.2339484691619873,
      "eval_runtime": 1772.5813,
      "eval_samples_per_second": 9.166,
      "eval_steps_per_second": 1.146,
      "step": 99
    },
    {
      "epoch": 0.005183361409874304,
      "grad_norm": 1.7509509325027466,
      "learning_rate": 0.0,
      "loss": 2.2408,
      "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
}