{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3241491085899514,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032414910858995136,
      "grad_norm": 1.3159303665161133,
      "learning_rate": 1e-05,
      "loss": 2.2466,
      "step": 1
    },
    {
      "epoch": 0.0032414910858995136,
      "eval_loss": 2.300732135772705,
      "eval_runtime": 31.3013,
      "eval_samples_per_second": 8.306,
      "eval_steps_per_second": 1.054,
      "step": 1
    },
    {
      "epoch": 0.006482982171799027,
      "grad_norm": 1.4277948141098022,
      "learning_rate": 2e-05,
      "loss": 2.1197,
      "step": 2
    },
    {
      "epoch": 0.009724473257698542,
      "grad_norm": 1.28606379032135,
      "learning_rate": 3e-05,
      "loss": 2.3738,
      "step": 3
    },
    {
      "epoch": 0.012965964343598054,
      "grad_norm": 1.296878457069397,
      "learning_rate": 4e-05,
      "loss": 2.1738,
      "step": 4
    },
    {
      "epoch": 0.01620745542949757,
      "grad_norm": 1.3691641092300415,
      "learning_rate": 5e-05,
      "loss": 2.4135,
      "step": 5
    },
    {
      "epoch": 0.019448946515397084,
      "grad_norm": 1.4580014944076538,
      "learning_rate": 6e-05,
      "loss": 1.9441,
      "step": 6
    },
    {
      "epoch": 0.022690437601296597,
      "grad_norm": 1.5247328281402588,
      "learning_rate": 7e-05,
      "loss": 2.3308,
      "step": 7
    },
    {
      "epoch": 0.02593192868719611,
      "grad_norm": 1.5503054857254028,
      "learning_rate": 8e-05,
      "loss": 2.0659,
      "step": 8
    },
    {
      "epoch": 0.029173419773095625,
      "grad_norm": 1.7505052089691162,
      "learning_rate": 9e-05,
      "loss": 2.1878,
      "step": 9
    },
    {
      "epoch": 0.029173419773095625,
      "eval_loss": 2.0789592266082764,
      "eval_runtime": 30.5568,
      "eval_samples_per_second": 8.509,
      "eval_steps_per_second": 1.08,
      "step": 9
    },
    {
      "epoch": 0.03241491085899514,
      "grad_norm": 1.533875823020935,
      "learning_rate": 0.0001,
      "loss": 2.2469,
      "step": 10
    },
    {
      "epoch": 0.03565640194489465,
      "grad_norm": 0.9546141028404236,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8343,
      "step": 11
    },
    {
      "epoch": 0.03889789303079417,
      "grad_norm": 1.3002139329910278,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5963,
      "step": 12
    },
    {
      "epoch": 0.04213938411669368,
      "grad_norm": 1.71047043800354,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.0106,
      "step": 13
    },
    {
      "epoch": 0.04538087520259319,
      "grad_norm": 1.4317657947540283,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.2752,
      "step": 14
    },
    {
      "epoch": 0.04862236628849271,
      "grad_norm": 1.0865490436553955,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.0168,
      "step": 15
    },
    {
      "epoch": 0.05186385737439222,
      "grad_norm": 0.99887615442276,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0054,
      "step": 16
    },
    {
      "epoch": 0.055105348460291734,
      "grad_norm": 0.8520192503929138,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.3288,
      "step": 17
    },
    {
      "epoch": 0.05834683954619125,
      "grad_norm": 0.9660809636116028,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0576,
      "step": 18
    },
    {
      "epoch": 0.05834683954619125,
      "eval_loss": 1.9661881923675537,
      "eval_runtime": 30.6092,
      "eval_samples_per_second": 8.494,
      "eval_steps_per_second": 1.078,
      "step": 18
    },
    {
      "epoch": 0.06158833063209076,
      "grad_norm": 1.572944164276123,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0662,
      "step": 19
    },
    {
      "epoch": 0.06482982171799027,
      "grad_norm": 1.2723232507705688,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2183,
      "step": 20
    },
    {
      "epoch": 0.06807131280388978,
      "grad_norm": 1.1963719129562378,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.957,
      "step": 21
    },
    {
      "epoch": 0.0713128038897893,
      "grad_norm": 0.9221727848052979,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.0593,
      "step": 22
    },
    {
      "epoch": 0.07455429497568881,
      "grad_norm": 1.0266880989074707,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.9636,
      "step": 23
    },
    {
      "epoch": 0.07779578606158834,
      "grad_norm": 0.9122965931892395,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7305,
      "step": 24
    },
    {
      "epoch": 0.08103727714748785,
      "grad_norm": 0.7953706383705139,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9669,
      "step": 25
    },
    {
      "epoch": 0.08427876823338736,
      "grad_norm": 0.9726611971855164,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8932,
      "step": 26
    },
    {
      "epoch": 0.08752025931928688,
      "grad_norm": 0.8515148758888245,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.175,
      "step": 27
    },
    {
      "epoch": 0.08752025931928688,
      "eval_loss": 1.910936713218689,
      "eval_runtime": 30.5558,
      "eval_samples_per_second": 8.509,
      "eval_steps_per_second": 1.08,
      "step": 27
    },
    {
      "epoch": 0.09076175040518639,
      "grad_norm": 1.1065913438796997,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0627,
      "step": 28
    },
    {
      "epoch": 0.0940032414910859,
      "grad_norm": 0.7604870796203613,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.7624,
      "step": 29
    },
    {
      "epoch": 0.09724473257698542,
      "grad_norm": 0.7163789868354797,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.9211,
      "step": 30
    },
    {
      "epoch": 0.10048622366288493,
      "grad_norm": 0.7813649773597717,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.7941,
      "step": 31
    },
    {
      "epoch": 0.10372771474878444,
      "grad_norm": 0.7049025893211365,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.8533,
      "step": 32
    },
    {
      "epoch": 0.10696920583468396,
      "grad_norm": 0.8610150218009949,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8968,
      "step": 33
    },
    {
      "epoch": 0.11021069692058347,
      "grad_norm": 0.8108399510383606,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8813,
      "step": 34
    },
    {
      "epoch": 0.11345218800648298,
      "grad_norm": 0.7536383271217346,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.0364,
      "step": 35
    },
    {
      "epoch": 0.1166936790923825,
      "grad_norm": 0.7456100583076477,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.9087,
      "step": 36
    },
    {
      "epoch": 0.1166936790923825,
      "eval_loss": 1.8882397413253784,
      "eval_runtime": 30.5606,
      "eval_samples_per_second": 8.508,
      "eval_steps_per_second": 1.08,
      "step": 36
    },
    {
      "epoch": 0.11993517017828201,
      "grad_norm": 0.776051938533783,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8879,
      "step": 37
    },
    {
      "epoch": 0.12317666126418152,
      "grad_norm": 0.8994588851928711,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.8925,
      "step": 38
    },
    {
      "epoch": 0.12641815235008103,
      "grad_norm": 1.0777877569198608,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.8501,
      "step": 39
    },
    {
      "epoch": 0.12965964343598055,
      "grad_norm": 0.8337717056274414,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7385,
      "step": 40
    },
    {
      "epoch": 0.13290113452188007,
      "grad_norm": 0.9384728670120239,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.0473,
      "step": 41
    },
    {
      "epoch": 0.13614262560777957,
      "grad_norm": 0.7161359786987305,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.629,
      "step": 42
    },
    {
      "epoch": 0.1393841166936791,
      "grad_norm": 0.6769235134124756,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.6738,
      "step": 43
    },
    {
      "epoch": 0.1426256077795786,
      "grad_norm": 0.9046027064323425,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7918,
      "step": 44
    },
    {
      "epoch": 0.1458670988654781,
      "grad_norm": 0.7475665807723999,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9391,
      "step": 45
    },
    {
      "epoch": 0.1458670988654781,
      "eval_loss": 1.8725632429122925,
      "eval_runtime": 30.5662,
      "eval_samples_per_second": 8.506,
      "eval_steps_per_second": 1.08,
      "step": 45
    },
    {
      "epoch": 0.14910858995137763,
      "grad_norm": 0.7976102828979492,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7137,
      "step": 46
    },
    {
      "epoch": 0.15235008103727715,
      "grad_norm": 1.059738039970398,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7397,
      "step": 47
    },
    {
      "epoch": 0.15559157212317667,
      "grad_norm": 0.7454342842102051,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6178,
      "step": 48
    },
    {
      "epoch": 0.15883306320907617,
      "grad_norm": 0.8142852783203125,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8938,
      "step": 49
    },
    {
      "epoch": 0.1620745542949757,
      "grad_norm": 0.6792764663696289,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7705,
      "step": 50
    },
    {
      "epoch": 0.16531604538087522,
      "grad_norm": 0.6783784031867981,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.5488,
      "step": 51
    },
    {
      "epoch": 0.1685575364667747,
      "grad_norm": 0.809777557849884,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5917,
      "step": 52
    },
    {
      "epoch": 0.17179902755267423,
      "grad_norm": 0.8724034428596497,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8597,
      "step": 53
    },
    {
      "epoch": 0.17504051863857376,
      "grad_norm": 0.8356680274009705,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.6943,
      "step": 54
    },
    {
      "epoch": 0.17504051863857376,
      "eval_loss": 1.8605071306228638,
      "eval_runtime": 30.5356,
      "eval_samples_per_second": 8.515,
      "eval_steps_per_second": 1.081,
      "step": 54
    },
    {
      "epoch": 0.17828200972447325,
      "grad_norm": 0.8904510736465454,
      "learning_rate": 5e-05,
      "loss": 1.8918,
      "step": 55
    },
    {
      "epoch": 0.18152350081037277,
      "grad_norm": 1.043846845626831,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.0157,
      "step": 56
    },
    {
      "epoch": 0.1847649918962723,
      "grad_norm": 0.865654706954956,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.5713,
      "step": 57
    },
    {
      "epoch": 0.1880064829821718,
      "grad_norm": 0.8920210599899292,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.9199,
      "step": 58
    },
    {
      "epoch": 0.1912479740680713,
      "grad_norm": 0.8100156784057617,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6949,
      "step": 59
    },
    {
      "epoch": 0.19448946515397084,
      "grad_norm": 0.7960771918296814,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.7585,
      "step": 60
    },
    {
      "epoch": 0.19773095623987033,
      "grad_norm": 0.93149334192276,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.0148,
      "step": 61
    },
    {
      "epoch": 0.20097244732576985,
      "grad_norm": 0.9921747446060181,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.8604,
      "step": 62
    },
    {
      "epoch": 0.20421393841166938,
      "grad_norm": 1.0371712446212769,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.9035,
      "step": 63
    },
    {
      "epoch": 0.20421393841166938,
      "eval_loss": 1.8514751195907593,
      "eval_runtime": 30.5106,
      "eval_samples_per_second": 8.522,
      "eval_steps_per_second": 1.082,
      "step": 63
    },
    {
      "epoch": 0.20745542949756887,
      "grad_norm": 0.9877856373786926,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7678,
      "step": 64
    },
    {
      "epoch": 0.2106969205834684,
      "grad_norm": 0.9803109765052795,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.768,
      "step": 65
    },
    {
      "epoch": 0.21393841166936792,
      "grad_norm": 2.6569504737854004,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.937,
      "step": 66
    },
    {
      "epoch": 0.2171799027552674,
      "grad_norm": 0.7644363641738892,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.7935,
      "step": 67
    },
    {
      "epoch": 0.22042139384116693,
      "grad_norm": 0.8924177885055542,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9588,
      "step": 68
    },
    {
      "epoch": 0.22366288492706646,
      "grad_norm": 0.8564395904541016,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.758,
      "step": 69
    },
    {
      "epoch": 0.22690437601296595,
      "grad_norm": 0.9097872972488403,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8777,
      "step": 70
    },
    {
      "epoch": 0.23014586709886548,
      "grad_norm": 0.8020492196083069,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.8877,
      "step": 71
    },
    {
      "epoch": 0.233387358184765,
      "grad_norm": 0.9427188634872437,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.7581,
      "step": 72
    },
    {
      "epoch": 0.233387358184765,
      "eval_loss": 1.846287727355957,
      "eval_runtime": 30.5601,
      "eval_samples_per_second": 8.508,
      "eval_steps_per_second": 1.08,
      "step": 72
    },
    {
      "epoch": 0.2366288492706645,
      "grad_norm": 0.8897935152053833,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8315,
      "step": 73
    },
    {
      "epoch": 0.23987034035656402,
      "grad_norm": 0.9120158553123474,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1927,
      "step": 74
    },
    {
      "epoch": 0.24311183144246354,
      "grad_norm": 0.8587985038757324,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8626,
      "step": 75
    },
    {
      "epoch": 0.24635332252836303,
      "grad_norm": 1.0571489334106445,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.9725,
      "step": 76
    },
    {
      "epoch": 0.24959481361426256,
      "grad_norm": 0.7617626190185547,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8038,
      "step": 77
    },
    {
      "epoch": 0.25283630470016205,
      "grad_norm": 0.98393315076828,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.0169,
      "step": 78
    },
    {
      "epoch": 0.2560777957860616,
      "grad_norm": 0.9455400109291077,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.7648,
      "step": 79
    },
    {
      "epoch": 0.2593192868719611,
      "grad_norm": 0.99833744764328,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8161,
      "step": 80
    },
    {
      "epoch": 0.2625607779578606,
      "grad_norm": 0.8089686632156372,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.8539,
      "step": 81
    },
    {
      "epoch": 0.2625607779578606,
      "eval_loss": 1.8421069383621216,
      "eval_runtime": 30.558,
      "eval_samples_per_second": 8.508,
      "eval_steps_per_second": 1.08,
      "step": 81
    },
    {
      "epoch": 0.26580226904376014,
      "grad_norm": 1.0099201202392578,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8115,
      "step": 82
    },
    {
      "epoch": 0.26904376012965964,
      "grad_norm": 0.9346497058868408,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.9065,
      "step": 83
    },
    {
      "epoch": 0.27228525121555913,
      "grad_norm": 0.7902043461799622,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6215,
      "step": 84
    },
    {
      "epoch": 0.2755267423014587,
      "grad_norm": 0.9881759881973267,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.929,
      "step": 85
    },
    {
      "epoch": 0.2787682333873582,
      "grad_norm": 0.8457426428794861,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.7417,
      "step": 86
    },
    {
      "epoch": 0.2820097244732577,
      "grad_norm": 0.7483598589897156,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.6865,
      "step": 87
    },
    {
      "epoch": 0.2852512155591572,
      "grad_norm": 0.9153674244880676,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.9731,
      "step": 88
    },
    {
      "epoch": 0.2884927066450567,
      "grad_norm": 0.9437265992164612,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.7751,
      "step": 89
    },
    {
      "epoch": 0.2917341977309562,
      "grad_norm": 1.077127456665039,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.1184,
      "step": 90
    },
    {
      "epoch": 0.2917341977309562,
      "eval_loss": 1.840531826019287,
      "eval_runtime": 30.4979,
      "eval_samples_per_second": 8.525,
      "eval_steps_per_second": 1.082,
      "step": 90
    },
    {
      "epoch": 0.29497568881685576,
      "grad_norm": 1.0355558395385742,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0273,
      "step": 91
    },
    {
      "epoch": 0.29821717990275526,
      "grad_norm": 0.6711990237236023,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4758,
      "step": 92
    },
    {
      "epoch": 0.3014586709886548,
      "grad_norm": 1.0566705465316772,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.2128,
      "step": 93
    },
    {
      "epoch": 0.3047001620745543,
      "grad_norm": 0.7678670883178711,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.8195,
      "step": 94
    },
    {
      "epoch": 0.3079416531604538,
      "grad_norm": 0.8789794445037842,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.801,
      "step": 95
    },
    {
      "epoch": 0.31118314424635335,
      "grad_norm": 0.9785366058349609,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.7027,
      "step": 96
    },
    {
      "epoch": 0.31442463533225284,
      "grad_norm": 0.9214769005775452,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.8092,
      "step": 97
    },
    {
      "epoch": 0.31766612641815234,
      "grad_norm": 0.9695401191711426,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0306,
      "step": 98
    },
    {
      "epoch": 0.3209076175040519,
      "grad_norm": 0.8423238396644592,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.8981,
      "step": 99
    },
    {
      "epoch": 0.3209076175040519,
      "eval_loss": 1.8405555486679077,
      "eval_runtime": 30.5474,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 1.08,
      "step": 99
    },
    {
      "epoch": 0.3241491085899514,
      "grad_norm": 1.0919097661972046,
      "learning_rate": 0.0,
      "loss": 2.0046,
      "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": 8.049616827816346e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}