Qwen2.5-7B-Instruct-agenttuning / trainer_state.json
lemonhat's picture
Add files using upload-large-folder tool
cf5a337 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 100,
"global_step": 466,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002145922746781116,
"grad_norm": 76.18501490873153,
"learning_rate": 4.999943188496862e-06,
"loss": 1.6093,
"step": 1
},
{
"epoch": 0.004291845493562232,
"grad_norm": 14.009670404971743,
"learning_rate": 4.999772756569482e-06,
"loss": 0.4008,
"step": 2
},
{
"epoch": 0.006437768240343348,
"grad_norm": 6.1214346980998515,
"learning_rate": 4.999488711963857e-06,
"loss": 0.3077,
"step": 3
},
{
"epoch": 0.008583690987124463,
"grad_norm": 14.429243581164625,
"learning_rate": 4.999091067589587e-06,
"loss": 0.4675,
"step": 4
},
{
"epoch": 0.01072961373390558,
"grad_norm": 7.580155180829176,
"learning_rate": 4.998579841519292e-06,
"loss": 0.4538,
"step": 5
},
{
"epoch": 0.012875536480686695,
"grad_norm": 7.832206035781183,
"learning_rate": 4.99795505698779e-06,
"loss": 0.2233,
"step": 6
},
{
"epoch": 0.015021459227467811,
"grad_norm": 6.259035686547294,
"learning_rate": 4.997216742391038e-06,
"loss": 0.2383,
"step": 7
},
{
"epoch": 0.017167381974248927,
"grad_norm": 6.2512799288622,
"learning_rate": 4.996364931284847e-06,
"loss": 0.2912,
"step": 8
},
{
"epoch": 0.019313304721030045,
"grad_norm": 7.589384412275137,
"learning_rate": 4.995399662383352e-06,
"loss": 0.2463,
"step": 9
},
{
"epoch": 0.02145922746781116,
"grad_norm": 10.710971905656887,
"learning_rate": 4.994320979557256e-06,
"loss": 0.3021,
"step": 10
},
{
"epoch": 0.023605150214592276,
"grad_norm": 9.561570863346544,
"learning_rate": 4.99312893183183e-06,
"loss": 0.3147,
"step": 11
},
{
"epoch": 0.02575107296137339,
"grad_norm": 38.042377389708484,
"learning_rate": 4.991823573384695e-06,
"loss": 0.8302,
"step": 12
},
{
"epoch": 0.027896995708154508,
"grad_norm": 8.86173699044075,
"learning_rate": 4.990404963543352e-06,
"loss": 0.4076,
"step": 13
},
{
"epoch": 0.030042918454935622,
"grad_norm": 21.537285072501607,
"learning_rate": 4.988873166782485e-06,
"loss": 0.7611,
"step": 14
},
{
"epoch": 0.032188841201716736,
"grad_norm": 6.047109119735588,
"learning_rate": 4.987228252721037e-06,
"loss": 0.3053,
"step": 15
},
{
"epoch": 0.034334763948497854,
"grad_norm": 14.447362163381339,
"learning_rate": 4.985470296119038e-06,
"loss": 0.5285,
"step": 16
},
{
"epoch": 0.03648068669527897,
"grad_norm": 7.74290518703786,
"learning_rate": 4.983599376874216e-06,
"loss": 0.2236,
"step": 17
},
{
"epoch": 0.03862660944206009,
"grad_norm": 5.727455325582489,
"learning_rate": 4.981615580018358e-06,
"loss": 0.204,
"step": 18
},
{
"epoch": 0.0407725321888412,
"grad_norm": 16.691846221989785,
"learning_rate": 4.979518995713448e-06,
"loss": 0.4196,
"step": 19
},
{
"epoch": 0.04291845493562232,
"grad_norm": 16.720958919193354,
"learning_rate": 4.977309719247571e-06,
"loss": 0.7494,
"step": 20
},
{
"epoch": 0.045064377682403435,
"grad_norm": 6.612052621566363,
"learning_rate": 4.974987851030581e-06,
"loss": 0.3287,
"step": 21
},
{
"epoch": 0.04721030042918455,
"grad_norm": 7.3652166724204315,
"learning_rate": 4.972553496589537e-06,
"loss": 0.3473,
"step": 22
},
{
"epoch": 0.04935622317596566,
"grad_norm": 5.025111473292376,
"learning_rate": 4.970006766563906e-06,
"loss": 0.3725,
"step": 23
},
{
"epoch": 0.05150214592274678,
"grad_norm": 11.718331155399566,
"learning_rate": 4.967347776700538e-06,
"loss": 0.6273,
"step": 24
},
{
"epoch": 0.0536480686695279,
"grad_norm": 4.873321533780134,
"learning_rate": 4.964576647848401e-06,
"loss": 0.5175,
"step": 25
},
{
"epoch": 0.055793991416309016,
"grad_norm": 4.204769507730203,
"learning_rate": 4.9616935059530915e-06,
"loss": 0.1414,
"step": 26
},
{
"epoch": 0.05793991416309013,
"grad_norm": 7.206330363974099,
"learning_rate": 4.958698482051109e-06,
"loss": 0.2285,
"step": 27
},
{
"epoch": 0.060085836909871244,
"grad_norm": 4.7858940585296095,
"learning_rate": 4.955591712263901e-06,
"loss": 0.2037,
"step": 28
},
{
"epoch": 0.06223175965665236,
"grad_norm": 12.477235363576892,
"learning_rate": 4.952373337791678e-06,
"loss": 0.5673,
"step": 29
},
{
"epoch": 0.06437768240343347,
"grad_norm": 3.797571893331321,
"learning_rate": 4.9490435049069925e-06,
"loss": 0.2233,
"step": 30
},
{
"epoch": 0.06652360515021459,
"grad_norm": 3.3156309080116158,
"learning_rate": 4.9456023649480935e-06,
"loss": 0.1981,
"step": 31
},
{
"epoch": 0.06866952789699571,
"grad_norm": 4.531878367746364,
"learning_rate": 4.942050074312048e-06,
"loss": 0.1946,
"step": 32
},
{
"epoch": 0.07081545064377683,
"grad_norm": 5.78159856239121,
"learning_rate": 4.9383867944476325e-06,
"loss": 0.2749,
"step": 33
},
{
"epoch": 0.07296137339055794,
"grad_norm": 3.7408734670014794,
"learning_rate": 4.934612691847995e-06,
"loss": 0.3626,
"step": 34
},
{
"epoch": 0.07510729613733906,
"grad_norm": 15.815816851091464,
"learning_rate": 4.930727938043091e-06,
"loss": 0.4734,
"step": 35
},
{
"epoch": 0.07725321888412018,
"grad_norm": 5.5369981240766935,
"learning_rate": 4.926732709591879e-06,
"loss": 0.2659,
"step": 36
},
{
"epoch": 0.07939914163090128,
"grad_norm": 12.910997188700815,
"learning_rate": 4.9226271880743086e-06,
"loss": 0.4348,
"step": 37
},
{
"epoch": 0.0815450643776824,
"grad_norm": 8.020574277619785,
"learning_rate": 4.918411560083058e-06,
"loss": 0.3308,
"step": 38
},
{
"epoch": 0.08369098712446352,
"grad_norm": 6.453487445532046,
"learning_rate": 4.914086017215059e-06,
"loss": 0.4054,
"step": 39
},
{
"epoch": 0.08583690987124463,
"grad_norm": 6.115766672764467,
"learning_rate": 4.909650756062782e-06,
"loss": 0.332,
"step": 40
},
{
"epoch": 0.08798283261802575,
"grad_norm": 6.319229087749166,
"learning_rate": 4.9051059782053125e-06,
"loss": 0.2929,
"step": 41
},
{
"epoch": 0.09012875536480687,
"grad_norm": 14.438350682047952,
"learning_rate": 4.900451890199179e-06,
"loss": 0.7799,
"step": 42
},
{
"epoch": 0.09227467811158799,
"grad_norm": 6.79883162868288,
"learning_rate": 4.895688703568968e-06,
"loss": 0.3752,
"step": 43
},
{
"epoch": 0.0944206008583691,
"grad_norm": 5.690387611301978,
"learning_rate": 4.890816634797716e-06,
"loss": 0.2059,
"step": 44
},
{
"epoch": 0.09656652360515021,
"grad_norm": 4.431043352022045,
"learning_rate": 4.885835905317061e-06,
"loss": 0.2755,
"step": 45
},
{
"epoch": 0.09871244635193133,
"grad_norm": 6.846760154412704,
"learning_rate": 4.880746741497187e-06,
"loss": 0.319,
"step": 46
},
{
"epoch": 0.10085836909871244,
"grad_norm": 5.075521155502137,
"learning_rate": 4.87554937463653e-06,
"loss": 0.2944,
"step": 47
},
{
"epoch": 0.10300429184549356,
"grad_norm": 5.000407636367204,
"learning_rate": 4.87024404095127e-06,
"loss": 0.244,
"step": 48
},
{
"epoch": 0.10515021459227468,
"grad_norm": 5.5213729215970515,
"learning_rate": 4.8648309815645915e-06,
"loss": 0.3535,
"step": 49
},
{
"epoch": 0.1072961373390558,
"grad_norm": 5.162325783820257,
"learning_rate": 4.8593104424957275e-06,
"loss": 0.3763,
"step": 50
},
{
"epoch": 0.10944206008583691,
"grad_norm": 5.241667905913422,
"learning_rate": 4.853682674648775e-06,
"loss": 0.256,
"step": 51
},
{
"epoch": 0.11158798283261803,
"grad_norm": 5.009026381629991,
"learning_rate": 4.847947933801296e-06,
"loss": 0.3455,
"step": 52
},
{
"epoch": 0.11373390557939914,
"grad_norm": 12.563430161222314,
"learning_rate": 4.842106480592687e-06,
"loss": 0.6362,
"step": 53
},
{
"epoch": 0.11587982832618025,
"grad_norm": 6.315768827715915,
"learning_rate": 4.836158580512339e-06,
"loss": 0.2889,
"step": 54
},
{
"epoch": 0.11802575107296137,
"grad_norm": 5.218075678965081,
"learning_rate": 4.8301045038875665e-06,
"loss": 0.1951,
"step": 55
},
{
"epoch": 0.12017167381974249,
"grad_norm": 7.3960507355002605,
"learning_rate": 4.823944525871324e-06,
"loss": 0.3214,
"step": 56
},
{
"epoch": 0.1223175965665236,
"grad_norm": 7.4185340069371986,
"learning_rate": 4.817678926429702e-06,
"loss": 0.3852,
"step": 57
},
{
"epoch": 0.12446351931330472,
"grad_norm": 4.9490761074888825,
"learning_rate": 4.8113079903291955e-06,
"loss": 0.4695,
"step": 58
},
{
"epoch": 0.12660944206008584,
"grad_norm": 5.408957891954199,
"learning_rate": 4.804832007123771e-06,
"loss": 0.3385,
"step": 59
},
{
"epoch": 0.12875536480686695,
"grad_norm": 12.766577641000062,
"learning_rate": 4.7982512711416995e-06,
"loss": 0.4539,
"step": 60
},
{
"epoch": 0.13090128755364808,
"grad_norm": 6.338330185457858,
"learning_rate": 4.791566081472185e-06,
"loss": 0.4034,
"step": 61
},
{
"epoch": 0.13304721030042918,
"grad_norm": 6.151730476584575,
"learning_rate": 4.784776741951766e-06,
"loss": 0.3683,
"step": 62
},
{
"epoch": 0.1351931330472103,
"grad_norm": 4.345928683775522,
"learning_rate": 4.777883561150508e-06,
"loss": 0.2088,
"step": 63
},
{
"epoch": 0.13733905579399142,
"grad_norm": 6.444874963490508,
"learning_rate": 4.770886852357983e-06,
"loss": 0.2917,
"step": 64
},
{
"epoch": 0.13948497854077252,
"grad_norm": 5.531328541781978,
"learning_rate": 4.763786933569025e-06,
"loss": 0.279,
"step": 65
},
{
"epoch": 0.14163090128755365,
"grad_norm": 4.080884948693169,
"learning_rate": 4.75658412746928e-06,
"loss": 0.195,
"step": 66
},
{
"epoch": 0.14377682403433475,
"grad_norm": 10.700949555936232,
"learning_rate": 4.7492787614205425e-06,
"loss": 0.4479,
"step": 67
},
{
"epoch": 0.1459227467811159,
"grad_norm": 5.481209106182085,
"learning_rate": 4.7418711674458735e-06,
"loss": 0.2758,
"step": 68
},
{
"epoch": 0.148068669527897,
"grad_norm": 6.189118615859581,
"learning_rate": 4.734361682214511e-06,
"loss": 0.2218,
"step": 69
},
{
"epoch": 0.15021459227467812,
"grad_norm": 6.34535278449602,
"learning_rate": 4.726750647026569e-06,
"loss": 0.4419,
"step": 70
},
{
"epoch": 0.15236051502145923,
"grad_norm": 5.239918053202764,
"learning_rate": 4.719038407797529e-06,
"loss": 0.2557,
"step": 71
},
{
"epoch": 0.15450643776824036,
"grad_norm": 6.26390385146301,
"learning_rate": 4.711225315042513e-06,
"loss": 0.5612,
"step": 72
},
{
"epoch": 0.15665236051502146,
"grad_norm": 6.195157191377425,
"learning_rate": 4.703311723860356e-06,
"loss": 0.3057,
"step": 73
},
{
"epoch": 0.15879828326180256,
"grad_norm": 16.357650722017635,
"learning_rate": 4.695297993917465e-06,
"loss": 0.8227,
"step": 74
},
{
"epoch": 0.1609442060085837,
"grad_norm": 5.339299574193258,
"learning_rate": 4.687184489431476e-06,
"loss": 0.2878,
"step": 75
},
{
"epoch": 0.1630901287553648,
"grad_norm": 14.30043548697042,
"learning_rate": 4.678971579154698e-06,
"loss": 0.8272,
"step": 76
},
{
"epoch": 0.16523605150214593,
"grad_norm": 6.315372884620644,
"learning_rate": 4.670659636357352e-06,
"loss": 0.2812,
"step": 77
},
{
"epoch": 0.16738197424892703,
"grad_norm": 4.0158091796680075,
"learning_rate": 4.66224903881061e-06,
"loss": 0.3212,
"step": 78
},
{
"epoch": 0.16952789699570817,
"grad_norm": 4.741126690857027,
"learning_rate": 4.653740168769424e-06,
"loss": 0.2627,
"step": 79
},
{
"epoch": 0.17167381974248927,
"grad_norm": 4.654686079147113,
"learning_rate": 4.64513341295515e-06,
"loss": 0.1007,
"step": 80
},
{
"epoch": 0.17381974248927037,
"grad_norm": 2.858109471127793,
"learning_rate": 4.6364291625379785e-06,
"loss": 0.1819,
"step": 81
},
{
"epoch": 0.1759656652360515,
"grad_norm": 13.540162342975938,
"learning_rate": 4.627627813119147e-06,
"loss": 0.5442,
"step": 82
},
{
"epoch": 0.1781115879828326,
"grad_norm": 14.029611827699513,
"learning_rate": 4.618729764712969e-06,
"loss": 0.9108,
"step": 83
},
{
"epoch": 0.18025751072961374,
"grad_norm": 4.457304810520309,
"learning_rate": 4.609735421728647e-06,
"loss": 0.2638,
"step": 84
},
{
"epoch": 0.18240343347639484,
"grad_norm": 5.935629670933359,
"learning_rate": 4.600645192951898e-06,
"loss": 0.2403,
"step": 85
},
{
"epoch": 0.18454935622317598,
"grad_norm": 5.136446320474782,
"learning_rate": 4.591459491526371e-06,
"loss": 0.246,
"step": 86
},
{
"epoch": 0.18669527896995708,
"grad_norm": 5.684377700354834,
"learning_rate": 4.582178734934869e-06,
"loss": 0.2751,
"step": 87
},
{
"epoch": 0.1888412017167382,
"grad_norm": 15.146436017458708,
"learning_rate": 4.572803344980378e-06,
"loss": 0.8044,
"step": 88
},
{
"epoch": 0.19098712446351931,
"grad_norm": 4.636355059101864,
"learning_rate": 4.563333747766896e-06,
"loss": 0.2279,
"step": 89
},
{
"epoch": 0.19313304721030042,
"grad_norm": 4.963353306284944,
"learning_rate": 4.553770373680062e-06,
"loss": 0.1785,
"step": 90
},
{
"epoch": 0.19527896995708155,
"grad_norm": 3.887562311073866,
"learning_rate": 4.544113657367604e-06,
"loss": 0.1408,
"step": 91
},
{
"epoch": 0.19742489270386265,
"grad_norm": 4.996113376607759,
"learning_rate": 4.5343640377195766e-06,
"loss": 0.2715,
"step": 92
},
{
"epoch": 0.19957081545064378,
"grad_norm": 5.484264961569098,
"learning_rate": 4.524521957848416e-06,
"loss": 0.3287,
"step": 93
},
{
"epoch": 0.2017167381974249,
"grad_norm": 5.08682917163341,
"learning_rate": 4.514587865068806e-06,
"loss": 0.366,
"step": 94
},
{
"epoch": 0.20386266094420602,
"grad_norm": 6.8043618981585725,
"learning_rate": 4.504562210877338e-06,
"loss": 0.3089,
"step": 95
},
{
"epoch": 0.20600858369098712,
"grad_norm": 14.009371009062516,
"learning_rate": 4.494445450932003e-06,
"loss": 0.5487,
"step": 96
},
{
"epoch": 0.20815450643776823,
"grad_norm": 13.77182300710328,
"learning_rate": 4.484238045031471e-06,
"loss": 0.6681,
"step": 97
},
{
"epoch": 0.21030042918454936,
"grad_norm": 5.373599093252736,
"learning_rate": 4.473940457094199e-06,
"loss": 0.2824,
"step": 98
},
{
"epoch": 0.21244635193133046,
"grad_norm": 7.7339638883523145,
"learning_rate": 4.463553155137348e-06,
"loss": 0.3773,
"step": 99
},
{
"epoch": 0.2145922746781116,
"grad_norm": 4.358486041621687,
"learning_rate": 4.453076611255507e-06,
"loss": 0.1968,
"step": 100
},
{
"epoch": 0.2145922746781116,
"eval_loss": 1.61643385887146,
"eval_runtime": 0.5589,
"eval_samples_per_second": 3.578,
"eval_steps_per_second": 1.789,
"step": 100
},
{
"epoch": 0.2167381974248927,
"grad_norm": 10.51123783356939,
"learning_rate": 4.442511301599241e-06,
"loss": 0.6631,
"step": 101
},
{
"epoch": 0.21888412017167383,
"grad_norm": 6.204285891841481,
"learning_rate": 4.431857706353449e-06,
"loss": 0.1981,
"step": 102
},
{
"epoch": 0.22103004291845493,
"grad_norm": 3.509886696140534,
"learning_rate": 4.4211163097155375e-06,
"loss": 0.2514,
"step": 103
},
{
"epoch": 0.22317596566523606,
"grad_norm": 5.794240091360383,
"learning_rate": 4.4102875998734176e-06,
"loss": 0.4743,
"step": 104
},
{
"epoch": 0.22532188841201717,
"grad_norm": 7.1780216249839475,
"learning_rate": 4.399372068983317e-06,
"loss": 0.3754,
"step": 105
},
{
"epoch": 0.22746781115879827,
"grad_norm": 3.4853873904835835,
"learning_rate": 4.388370213147409e-06,
"loss": 0.1217,
"step": 106
},
{
"epoch": 0.2296137339055794,
"grad_norm": 5.282583393202969,
"learning_rate": 4.377282532391267e-06,
"loss": 0.2422,
"step": 107
},
{
"epoch": 0.2317596566523605,
"grad_norm": 5.917106273735147,
"learning_rate": 4.36610953064114e-06,
"loss": 0.3188,
"step": 108
},
{
"epoch": 0.23390557939914164,
"grad_norm": 5.49762193840351,
"learning_rate": 4.354851715701046e-06,
"loss": 0.2603,
"step": 109
},
{
"epoch": 0.23605150214592274,
"grad_norm": 5.113114203550232,
"learning_rate": 4.343509599229697e-06,
"loss": 0.2025,
"step": 110
},
{
"epoch": 0.23819742489270387,
"grad_norm": 3.9665916022215733,
"learning_rate": 4.332083696717242e-06,
"loss": 0.2608,
"step": 111
},
{
"epoch": 0.24034334763948498,
"grad_norm": 5.001407701927511,
"learning_rate": 4.3205745274618365e-06,
"loss": 0.3543,
"step": 112
},
{
"epoch": 0.24248927038626608,
"grad_norm": 4.783668888273014,
"learning_rate": 4.308982614546045e-06,
"loss": 0.1367,
"step": 113
},
{
"epoch": 0.2446351931330472,
"grad_norm": 13.339939405425257,
"learning_rate": 4.297308484813067e-06,
"loss": 0.4563,
"step": 114
},
{
"epoch": 0.24678111587982832,
"grad_norm": 6.774593211018968,
"learning_rate": 4.2855526688427875e-06,
"loss": 0.2344,
"step": 115
},
{
"epoch": 0.24892703862660945,
"grad_norm": 6.032144655648605,
"learning_rate": 4.273715700927666e-06,
"loss": 0.3559,
"step": 116
},
{
"epoch": 0.2510729613733906,
"grad_norm": 11.663752172897125,
"learning_rate": 4.261798119048456e-06,
"loss": 0.5593,
"step": 117
},
{
"epoch": 0.2532188841201717,
"grad_norm": 11.248638669710262,
"learning_rate": 4.249800464849751e-06,
"loss": 0.4252,
"step": 118
},
{
"epoch": 0.2553648068669528,
"grad_norm": 5.542239291058805,
"learning_rate": 4.2377232836153635e-06,
"loss": 0.2671,
"step": 119
},
{
"epoch": 0.2575107296137339,
"grad_norm": 5.6163735157751935,
"learning_rate": 4.22556712424355e-06,
"loss": 0.2948,
"step": 120
},
{
"epoch": 0.259656652360515,
"grad_norm": 7.094248362569725,
"learning_rate": 4.21333253922206e-06,
"loss": 0.3536,
"step": 121
},
{
"epoch": 0.26180257510729615,
"grad_norm": 6.177984494937913,
"learning_rate": 4.201020084603027e-06,
"loss": 0.3318,
"step": 122
},
{
"epoch": 0.26394849785407726,
"grad_norm": 5.442893696217635,
"learning_rate": 4.1886303199776924e-06,
"loss": 0.3083,
"step": 123
},
{
"epoch": 0.26609442060085836,
"grad_norm": 5.3971104766895355,
"learning_rate": 4.176163808450978e-06,
"loss": 0.2955,
"step": 124
},
{
"epoch": 0.26824034334763946,
"grad_norm": 4.524019146701118,
"learning_rate": 4.163621116615892e-06,
"loss": 0.3251,
"step": 125
},
{
"epoch": 0.2703862660944206,
"grad_norm": 5.615564703579776,
"learning_rate": 4.151002814527774e-06,
"loss": 0.3306,
"step": 126
},
{
"epoch": 0.27253218884120173,
"grad_norm": 5.126082022354096,
"learning_rate": 4.138309475678393e-06,
"loss": 0.2977,
"step": 127
},
{
"epoch": 0.27467811158798283,
"grad_norm": 11.215215705069811,
"learning_rate": 4.125541676969876e-06,
"loss": 0.4561,
"step": 128
},
{
"epoch": 0.27682403433476394,
"grad_norm": 6.185141044554984,
"learning_rate": 4.112699998688492e-06,
"loss": 0.3652,
"step": 129
},
{
"epoch": 0.27896995708154504,
"grad_norm": 14.23422453207559,
"learning_rate": 4.099785024478276e-06,
"loss": 0.5595,
"step": 130
},
{
"epoch": 0.2811158798283262,
"grad_norm": 4.138921969139266,
"learning_rate": 4.086797341314509e-06,
"loss": 0.2577,
"step": 131
},
{
"epoch": 0.2832618025751073,
"grad_norm": 4.766155830963139,
"learning_rate": 4.073737539477033e-06,
"loss": 0.266,
"step": 132
},
{
"epoch": 0.2854077253218884,
"grad_norm": 16.59914611751421,
"learning_rate": 4.060606212523425e-06,
"loss": 0.7351,
"step": 133
},
{
"epoch": 0.2875536480686695,
"grad_norm": 12.70203249759127,
"learning_rate": 4.047403957262024e-06,
"loss": 0.7393,
"step": 134
},
{
"epoch": 0.28969957081545067,
"grad_norm": 5.854857495039337,
"learning_rate": 4.034131373724802e-06,
"loss": 0.3114,
"step": 135
},
{
"epoch": 0.2918454935622318,
"grad_norm": 7.054371064646026,
"learning_rate": 4.020789065140097e-06,
"loss": 0.3954,
"step": 136
},
{
"epoch": 0.2939914163090129,
"grad_norm": 5.777740234720859,
"learning_rate": 4.0073776379051945e-06,
"loss": 0.3613,
"step": 137
},
{
"epoch": 0.296137339055794,
"grad_norm": 6.807856815251271,
"learning_rate": 3.993897701558764e-06,
"loss": 0.2781,
"step": 138
},
{
"epoch": 0.2982832618025751,
"grad_norm": 4.274362381043211,
"learning_rate": 3.980349868753166e-06,
"loss": 0.2904,
"step": 139
},
{
"epoch": 0.30042918454935624,
"grad_norm": 4.166342301745076,
"learning_rate": 3.9667347552265945e-06,
"loss": 0.2234,
"step": 140
},
{
"epoch": 0.30257510729613735,
"grad_norm": 4.702643904412771,
"learning_rate": 3.953052979775103e-06,
"loss": 0.2765,
"step": 141
},
{
"epoch": 0.30472103004291845,
"grad_norm": 15.066466935467592,
"learning_rate": 3.939305164224474e-06,
"loss": 0.7204,
"step": 142
},
{
"epoch": 0.30686695278969955,
"grad_norm": 4.817588986196399,
"learning_rate": 3.925491933401961e-06,
"loss": 0.2919,
"step": 143
},
{
"epoch": 0.3090128755364807,
"grad_norm": 4.841054379645271,
"learning_rate": 3.911613915107888e-06,
"loss": 0.2624,
"step": 144
},
{
"epoch": 0.3111587982832618,
"grad_norm": 5.54460036441131,
"learning_rate": 3.89767174008712e-06,
"loss": 0.3137,
"step": 145
},
{
"epoch": 0.3133047210300429,
"grad_norm": 4.6296008910638164,
"learning_rate": 3.883666042000392e-06,
"loss": 0.2172,
"step": 146
},
{
"epoch": 0.315450643776824,
"grad_norm": 5.738911770360598,
"learning_rate": 3.869597457395514e-06,
"loss": 0.2998,
"step": 147
},
{
"epoch": 0.31759656652360513,
"grad_norm": 4.284288974195585,
"learning_rate": 3.855466625678435e-06,
"loss": 0.2037,
"step": 148
},
{
"epoch": 0.3197424892703863,
"grad_norm": 15.839881512200966,
"learning_rate": 3.841274189084189e-06,
"loss": 0.7527,
"step": 149
},
{
"epoch": 0.3218884120171674,
"grad_norm": 6.689386040699,
"learning_rate": 3.8270207926477e-06,
"loss": 0.3388,
"step": 150
},
{
"epoch": 0.3240343347639485,
"grad_norm": 5.131159476750089,
"learning_rate": 3.8127070841744695e-06,
"loss": 0.21,
"step": 151
},
{
"epoch": 0.3261802575107296,
"grad_norm": 12.20701029064903,
"learning_rate": 3.798333714211132e-06,
"loss": 0.5333,
"step": 152
},
{
"epoch": 0.3283261802575107,
"grad_norm": 2.8374089434590966,
"learning_rate": 3.7839013360158904e-06,
"loss": 0.2125,
"step": 153
},
{
"epoch": 0.33047210300429186,
"grad_norm": 13.285466340975823,
"learning_rate": 3.769410605528824e-06,
"loss": 0.5934,
"step": 154
},
{
"epoch": 0.33261802575107297,
"grad_norm": 5.3446998985506875,
"learning_rate": 3.7548621813420765e-06,
"loss": 0.3581,
"step": 155
},
{
"epoch": 0.33476394849785407,
"grad_norm": 7.274618884484683,
"learning_rate": 3.7402567246699257e-06,
"loss": 0.3321,
"step": 156
},
{
"epoch": 0.3369098712446352,
"grad_norm": 6.497928899578661,
"learning_rate": 3.72559489931873e-06,
"loss": 0.4336,
"step": 157
},
{
"epoch": 0.33905579399141633,
"grad_norm": 5.931060877134416,
"learning_rate": 3.710877371656757e-06,
"loss": 0.2499,
"step": 158
},
{
"epoch": 0.34120171673819744,
"grad_norm": 11.662557566869323,
"learning_rate": 3.696104810583904e-06,
"loss": 0.521,
"step": 159
},
{
"epoch": 0.34334763948497854,
"grad_norm": 10.738868357386822,
"learning_rate": 3.68127788750129e-06,
"loss": 0.3935,
"step": 160
},
{
"epoch": 0.34549356223175964,
"grad_norm": 10.27557863180008,
"learning_rate": 3.6663972762807453e-06,
"loss": 0.3763,
"step": 161
},
{
"epoch": 0.34763948497854075,
"grad_norm": 3.4237960233644866,
"learning_rate": 3.6514636532341825e-06,
"loss": 0.2778,
"step": 162
},
{
"epoch": 0.3497854077253219,
"grad_norm": 3.6998517744689763,
"learning_rate": 3.6364776970828586e-06,
"loss": 0.1564,
"step": 163
},
{
"epoch": 0.351931330472103,
"grad_norm": 4.614921333239657,
"learning_rate": 3.621440088926531e-06,
"loss": 0.272,
"step": 164
},
{
"epoch": 0.3540772532188841,
"grad_norm": 6.050087330401235,
"learning_rate": 3.6063515122124975e-06,
"loss": 0.3652,
"step": 165
},
{
"epoch": 0.3562231759656652,
"grad_norm": 4.387527359728692,
"learning_rate": 3.5912126527045368e-06,
"loss": 0.2172,
"step": 166
},
{
"epoch": 0.3583690987124464,
"grad_norm": 15.020253643431802,
"learning_rate": 3.5760241984517397e-06,
"loss": 0.8165,
"step": 167
},
{
"epoch": 0.3605150214592275,
"grad_norm": 4.553283039366036,
"learning_rate": 3.560786839757242e-06,
"loss": 0.3647,
"step": 168
},
{
"epoch": 0.3626609442060086,
"grad_norm": 7.402637796397458,
"learning_rate": 3.5455012691468417e-06,
"loss": 0.3558,
"step": 169
},
{
"epoch": 0.3648068669527897,
"grad_norm": 9.457334627147352,
"learning_rate": 3.5301681813375343e-06,
"loss": 0.3833,
"step": 170
},
{
"epoch": 0.3669527896995708,
"grad_norm": 4.692028452001265,
"learning_rate": 3.5147882732059323e-06,
"loss": 0.2337,
"step": 171
},
{
"epoch": 0.36909871244635195,
"grad_norm": 8.372452946921305,
"learning_rate": 3.4993622437565955e-06,
"loss": 0.2836,
"step": 172
},
{
"epoch": 0.37124463519313305,
"grad_norm": 3.3319166006121783,
"learning_rate": 3.4838907940902607e-06,
"loss": 0.1544,
"step": 173
},
{
"epoch": 0.37339055793991416,
"grad_norm": 13.281904749983129,
"learning_rate": 3.4683746273719754e-06,
"loss": 0.4684,
"step": 174
},
{
"epoch": 0.37553648068669526,
"grad_norm": 4.672588539349313,
"learning_rate": 3.4528144487991448e-06,
"loss": 0.2533,
"step": 175
},
{
"epoch": 0.3776824034334764,
"grad_norm": 9.892923641996738,
"learning_rate": 3.437210965569475e-06,
"loss": 0.2724,
"step": 176
},
{
"epoch": 0.3798283261802575,
"grad_norm": 11.942875136773626,
"learning_rate": 3.421564886848835e-06,
"loss": 0.5145,
"step": 177
},
{
"epoch": 0.38197424892703863,
"grad_norm": 5.004292816588128,
"learning_rate": 3.4058769237390254e-06,
"loss": 0.2421,
"step": 178
},
{
"epoch": 0.38412017167381973,
"grad_norm": 6.348610825705306,
"learning_rate": 3.3901477892454583e-06,
"loss": 0.5266,
"step": 179
},
{
"epoch": 0.38626609442060084,
"grad_norm": 11.476145919220956,
"learning_rate": 3.3743781982447533e-06,
"loss": 0.5593,
"step": 180
},
{
"epoch": 0.388412017167382,
"grad_norm": 4.384950541640652,
"learning_rate": 3.3585688674522438e-06,
"loss": 0.1745,
"step": 181
},
{
"epoch": 0.3905579399141631,
"grad_norm": 12.738421839026058,
"learning_rate": 3.3427205153894088e-06,
"loss": 0.8569,
"step": 182
},
{
"epoch": 0.3927038626609442,
"grad_norm": 4.770469502184926,
"learning_rate": 3.3268338623512094e-06,
"loss": 0.3608,
"step": 183
},
{
"epoch": 0.3948497854077253,
"grad_norm": 5.608829333428552,
"learning_rate": 3.3109096303733564e-06,
"loss": 0.2229,
"step": 184
},
{
"epoch": 0.3969957081545064,
"grad_norm": 14.271945687755156,
"learning_rate": 3.2949485431994945e-06,
"loss": 0.7949,
"step": 185
},
{
"epoch": 0.39914163090128757,
"grad_norm": 17.320126868800134,
"learning_rate": 3.2789513262483053e-06,
"loss": 0.7768,
"step": 186
},
{
"epoch": 0.4012875536480687,
"grad_norm": 6.304445282235124,
"learning_rate": 3.2629187065805445e-06,
"loss": 0.3341,
"step": 187
},
{
"epoch": 0.4034334763948498,
"grad_norm": 4.772846096021666,
"learning_rate": 3.2468514128659884e-06,
"loss": 0.2169,
"step": 188
},
{
"epoch": 0.4055793991416309,
"grad_norm": 12.095944359895759,
"learning_rate": 3.230750175350324e-06,
"loss": 0.5972,
"step": 189
},
{
"epoch": 0.40772532188841204,
"grad_norm": 17.046644577375776,
"learning_rate": 3.2146157258219534e-06,
"loss": 0.8746,
"step": 190
},
{
"epoch": 0.40987124463519314,
"grad_norm": 5.155144213224812,
"learning_rate": 3.1984487975787433e-06,
"loss": 0.403,
"step": 191
},
{
"epoch": 0.41201716738197425,
"grad_norm": 3.2493116945473273,
"learning_rate": 3.1822501253946875e-06,
"loss": 0.2046,
"step": 192
},
{
"epoch": 0.41416309012875535,
"grad_norm": 4.232233097969361,
"learning_rate": 3.1660204454865203e-06,
"loss": 0.3811,
"step": 193
},
{
"epoch": 0.41630901287553645,
"grad_norm": 4.72756957325817,
"learning_rate": 3.1497604954802485e-06,
"loss": 0.3,
"step": 194
},
{
"epoch": 0.4184549356223176,
"grad_norm": 12.946178614407032,
"learning_rate": 3.1334710143776346e-06,
"loss": 0.5872,
"step": 195
},
{
"epoch": 0.4206008583690987,
"grad_norm": 4.61301032231011,
"learning_rate": 3.1171527425226027e-06,
"loss": 0.2081,
"step": 196
},
{
"epoch": 0.4227467811158798,
"grad_norm": 12.907938814433235,
"learning_rate": 3.100806421567596e-06,
"loss": 0.6287,
"step": 197
},
{
"epoch": 0.4248927038626609,
"grad_norm": 5.546582248819232,
"learning_rate": 3.084432794439865e-06,
"loss": 0.3105,
"step": 198
},
{
"epoch": 0.4270386266094421,
"grad_norm": 7.245512728978741,
"learning_rate": 3.0680326053077047e-06,
"loss": 0.3016,
"step": 199
},
{
"epoch": 0.4291845493562232,
"grad_norm": 10.84493687480769,
"learning_rate": 3.0516065995466336e-06,
"loss": 0.3219,
"step": 200
},
{
"epoch": 0.4291845493562232,
"eval_loss": 1.4745992422103882,
"eval_runtime": 0.5572,
"eval_samples_per_second": 3.59,
"eval_steps_per_second": 1.795,
"step": 200
},
{
"epoch": 0.4313304721030043,
"grad_norm": 4.10172843012159,
"learning_rate": 3.0351555237055135e-06,
"loss": 0.1799,
"step": 201
},
{
"epoch": 0.4334763948497854,
"grad_norm": 5.306456302714684,
"learning_rate": 3.0186801254726213e-06,
"loss": 0.2365,
"step": 202
},
{
"epoch": 0.4356223175965665,
"grad_norm": 5.299147474065381,
"learning_rate": 3.0021811536416676e-06,
"loss": 0.2406,
"step": 203
},
{
"epoch": 0.43776824034334766,
"grad_norm": 4.14896225307621,
"learning_rate": 2.985659358077765e-06,
"loss": 0.1931,
"step": 204
},
{
"epoch": 0.43991416309012876,
"grad_norm": 13.03761590039539,
"learning_rate": 2.9691154896833454e-06,
"loss": 0.325,
"step": 205
},
{
"epoch": 0.44206008583690987,
"grad_norm": 10.573666701230737,
"learning_rate": 2.9525503003640336e-06,
"loss": 0.324,
"step": 206
},
{
"epoch": 0.44420600858369097,
"grad_norm": 11.926884819820218,
"learning_rate": 2.935964542994475e-06,
"loss": 0.5481,
"step": 207
},
{
"epoch": 0.44635193133047213,
"grad_norm": 10.151629428230573,
"learning_rate": 2.9193589713841132e-06,
"loss": 0.5082,
"step": 208
},
{
"epoch": 0.44849785407725323,
"grad_norm": 12.486051719027907,
"learning_rate": 2.902734340242937e-06,
"loss": 0.3599,
"step": 209
},
{
"epoch": 0.45064377682403434,
"grad_norm": 15.529513845799773,
"learning_rate": 2.8860914051471722e-06,
"loss": 0.7298,
"step": 210
},
{
"epoch": 0.45278969957081544,
"grad_norm": 5.461786086907061,
"learning_rate": 2.869430922504947e-06,
"loss": 0.2674,
"step": 211
},
{
"epoch": 0.45493562231759654,
"grad_norm": 5.376224720954328,
"learning_rate": 2.852753649521911e-06,
"loss": 0.3557,
"step": 212
},
{
"epoch": 0.4570815450643777,
"grad_norm": 17.151457129512085,
"learning_rate": 2.836060344166821e-06,
"loss": 0.6405,
"step": 213
},
{
"epoch": 0.4592274678111588,
"grad_norm": 4.757476534660833,
"learning_rate": 2.8193517651370934e-06,
"loss": 0.3124,
"step": 214
},
{
"epoch": 0.4613733905579399,
"grad_norm": 5.64585393975328,
"learning_rate": 2.80262867182432e-06,
"loss": 0.2888,
"step": 215
},
{
"epoch": 0.463519313304721,
"grad_norm": 13.765994790690012,
"learning_rate": 2.785891824279755e-06,
"loss": 0.5319,
"step": 216
},
{
"epoch": 0.4656652360515021,
"grad_norm": 3.4645720688637702,
"learning_rate": 2.7691419831797724e-06,
"loss": 0.1354,
"step": 217
},
{
"epoch": 0.4678111587982833,
"grad_norm": 4.728651796593724,
"learning_rate": 2.7523799097912905e-06,
"loss": 0.2457,
"step": 218
},
{
"epoch": 0.4699570815450644,
"grad_norm": 5.579222939328203,
"learning_rate": 2.73560636593718e-06,
"loss": 0.3542,
"step": 219
},
{
"epoch": 0.4721030042918455,
"grad_norm": 5.988497269511321,
"learning_rate": 2.7188221139616303e-06,
"loss": 0.4184,
"step": 220
},
{
"epoch": 0.4742489270386266,
"grad_norm": 6.257959157029455,
"learning_rate": 2.70202791669551e-06,
"loss": 0.2553,
"step": 221
},
{
"epoch": 0.47639484978540775,
"grad_norm": 12.558388707787643,
"learning_rate": 2.68522453742169e-06,
"loss": 0.541,
"step": 222
},
{
"epoch": 0.47854077253218885,
"grad_norm": 5.81966073574648,
"learning_rate": 2.66841273984036e-06,
"loss": 0.3147,
"step": 223
},
{
"epoch": 0.48068669527896996,
"grad_norm": 12.408285990600806,
"learning_rate": 2.6515932880343103e-06,
"loss": 0.4052,
"step": 224
},
{
"epoch": 0.48283261802575106,
"grad_norm": 6.652286326696977,
"learning_rate": 2.634766946434214e-06,
"loss": 0.2372,
"step": 225
},
{
"epoch": 0.48497854077253216,
"grad_norm": 11.13575728119692,
"learning_rate": 2.6179344797838775e-06,
"loss": 0.3067,
"step": 226
},
{
"epoch": 0.4871244635193133,
"grad_norm": 11.134631212750397,
"learning_rate": 2.6010966531054852e-06,
"loss": 0.8026,
"step": 227
},
{
"epoch": 0.4892703862660944,
"grad_norm": 3.8667307700150446,
"learning_rate": 2.5842542316648333e-06,
"loss": 0.2596,
"step": 228
},
{
"epoch": 0.49141630901287553,
"grad_norm": 6.443730023062394,
"learning_rate": 2.5674079809365443e-06,
"loss": 0.288,
"step": 229
},
{
"epoch": 0.49356223175965663,
"grad_norm": 2.9440291648892987,
"learning_rate": 2.550558666569279e-06,
"loss": 0.1493,
"step": 230
},
{
"epoch": 0.4957081545064378,
"grad_norm": 4.462532793208141,
"learning_rate": 2.533707054350938e-06,
"loss": 0.1839,
"step": 231
},
{
"epoch": 0.4978540772532189,
"grad_norm": 4.9063569155392015,
"learning_rate": 2.5168539101738576e-06,
"loss": 0.2802,
"step": 232
},
{
"epoch": 0.5,
"grad_norm": 10.022637557306455,
"learning_rate": 2.5e-06,
"loss": 0.3349,
"step": 233
},
{
"epoch": 0.5021459227467812,
"grad_norm": 4.3433358033272,
"learning_rate": 2.4831460898261428e-06,
"loss": 0.2626,
"step": 234
},
{
"epoch": 0.5042918454935622,
"grad_norm": 9.069133083700263,
"learning_rate": 2.4662929456490633e-06,
"loss": 0.2204,
"step": 235
},
{
"epoch": 0.5064377682403434,
"grad_norm": 4.611418200226192,
"learning_rate": 2.449441333430722e-06,
"loss": 0.1723,
"step": 236
},
{
"epoch": 0.5085836909871244,
"grad_norm": 4.915343701063927,
"learning_rate": 2.432592019063456e-06,
"loss": 0.28,
"step": 237
},
{
"epoch": 0.5107296137339056,
"grad_norm": 4.878529367689273,
"learning_rate": 2.415745768335167e-06,
"loss": 0.3336,
"step": 238
},
{
"epoch": 0.5128755364806867,
"grad_norm": 5.589922591964495,
"learning_rate": 2.398903346894515e-06,
"loss": 0.2363,
"step": 239
},
{
"epoch": 0.5150214592274678,
"grad_norm": 4.07202657981208,
"learning_rate": 2.3820655202161237e-06,
"loss": 0.2744,
"step": 240
},
{
"epoch": 0.5171673819742489,
"grad_norm": 3.9798028023766703,
"learning_rate": 2.365233053565787e-06,
"loss": 0.2538,
"step": 241
},
{
"epoch": 0.51931330472103,
"grad_norm": 4.2713689569349,
"learning_rate": 2.3484067119656905e-06,
"loss": 0.2072,
"step": 242
},
{
"epoch": 0.5214592274678111,
"grad_norm": 4.132159038986101,
"learning_rate": 2.331587260159641e-06,
"loss": 0.2537,
"step": 243
},
{
"epoch": 0.5236051502145923,
"grad_norm": 4.7509182744825695,
"learning_rate": 2.31477546257831e-06,
"loss": 0.2475,
"step": 244
},
{
"epoch": 0.5257510729613734,
"grad_norm": 12.573882879618065,
"learning_rate": 2.297972083304491e-06,
"loss": 0.5451,
"step": 245
},
{
"epoch": 0.5278969957081545,
"grad_norm": 4.265194868971971,
"learning_rate": 2.28117788603837e-06,
"loss": 0.2038,
"step": 246
},
{
"epoch": 0.5300429184549357,
"grad_norm": 5.327237193336404,
"learning_rate": 2.2643936340628205e-06,
"loss": 0.2953,
"step": 247
},
{
"epoch": 0.5321888412017167,
"grad_norm": 3.830903874010895,
"learning_rate": 2.24762009020871e-06,
"loss": 0.2118,
"step": 248
},
{
"epoch": 0.5343347639484979,
"grad_norm": 3.692771359304331,
"learning_rate": 2.2308580168202284e-06,
"loss": 0.2862,
"step": 249
},
{
"epoch": 0.5364806866952789,
"grad_norm": 4.46004020199315,
"learning_rate": 2.214108175720246e-06,
"loss": 0.1485,
"step": 250
},
{
"epoch": 0.5386266094420601,
"grad_norm": 4.194077533120119,
"learning_rate": 2.197371328175681e-06,
"loss": 0.18,
"step": 251
},
{
"epoch": 0.5407725321888412,
"grad_norm": 4.670466175503201,
"learning_rate": 2.1806482348629065e-06,
"loss": 0.2563,
"step": 252
},
{
"epoch": 0.5429184549356223,
"grad_norm": 11.620363098035735,
"learning_rate": 2.1639396558331794e-06,
"loss": 0.4257,
"step": 253
},
{
"epoch": 0.5450643776824035,
"grad_norm": 5.143937972622028,
"learning_rate": 2.1472463504780893e-06,
"loss": 0.2771,
"step": 254
},
{
"epoch": 0.5472103004291845,
"grad_norm": 4.790083924982343,
"learning_rate": 2.1305690774950543e-06,
"loss": 0.3618,
"step": 255
},
{
"epoch": 0.5493562231759657,
"grad_norm": 4.122103689477043,
"learning_rate": 2.1139085948528286e-06,
"loss": 0.1102,
"step": 256
},
{
"epoch": 0.5515021459227468,
"grad_norm": 4.807538148349604,
"learning_rate": 2.097265659757064e-06,
"loss": 0.2713,
"step": 257
},
{
"epoch": 0.5536480686695279,
"grad_norm": 3.2834156049564003,
"learning_rate": 2.080641028615888e-06,
"loss": 0.1608,
"step": 258
},
{
"epoch": 0.555793991416309,
"grad_norm": 4.843114090474319,
"learning_rate": 2.064035457005526e-06,
"loss": 0.2053,
"step": 259
},
{
"epoch": 0.5579399141630901,
"grad_norm": 4.187255961249243,
"learning_rate": 2.0474496996359676e-06,
"loss": 0.3847,
"step": 260
},
{
"epoch": 0.5600858369098712,
"grad_norm": 4.835958039304007,
"learning_rate": 2.0308845103166555e-06,
"loss": 0.2324,
"step": 261
},
{
"epoch": 0.5622317596566524,
"grad_norm": 4.612281021599447,
"learning_rate": 2.0143406419222354e-06,
"loss": 0.1589,
"step": 262
},
{
"epoch": 0.5643776824034334,
"grad_norm": 4.679769267914521,
"learning_rate": 1.997818846358333e-06,
"loss": 0.2734,
"step": 263
},
{
"epoch": 0.5665236051502146,
"grad_norm": 15.988595800455592,
"learning_rate": 1.98131987452738e-06,
"loss": 0.5932,
"step": 264
},
{
"epoch": 0.5686695278969958,
"grad_norm": 6.13615019112239,
"learning_rate": 1.964844476294487e-06,
"loss": 0.3048,
"step": 265
},
{
"epoch": 0.5708154506437768,
"grad_norm": 5.642706295976752,
"learning_rate": 1.948393400453367e-06,
"loss": 0.2217,
"step": 266
},
{
"epoch": 0.572961373390558,
"grad_norm": 4.00696562989142,
"learning_rate": 1.9319673946922953e-06,
"loss": 0.142,
"step": 267
},
{
"epoch": 0.575107296137339,
"grad_norm": 4.431532041750428,
"learning_rate": 1.9155672055601364e-06,
"loss": 0.2385,
"step": 268
},
{
"epoch": 0.5772532188841202,
"grad_norm": 4.7544298296222305,
"learning_rate": 1.8991935784324048e-06,
"loss": 0.2229,
"step": 269
},
{
"epoch": 0.5793991416309013,
"grad_norm": 14.806103600453497,
"learning_rate": 1.882847257477398e-06,
"loss": 0.6235,
"step": 270
},
{
"epoch": 0.5815450643776824,
"grad_norm": 3.608004765245334,
"learning_rate": 1.8665289856223662e-06,
"loss": 0.1837,
"step": 271
},
{
"epoch": 0.5836909871244635,
"grad_norm": 4.269748144395558,
"learning_rate": 1.8502395045197522e-06,
"loss": 0.1686,
"step": 272
},
{
"epoch": 0.5858369098712446,
"grad_norm": 3.4279537261830897,
"learning_rate": 1.8339795545134814e-06,
"loss": 0.176,
"step": 273
},
{
"epoch": 0.5879828326180258,
"grad_norm": 3.693149204798503,
"learning_rate": 1.8177498746053129e-06,
"loss": 0.2255,
"step": 274
},
{
"epoch": 0.5901287553648069,
"grad_norm": 7.0891066905956714,
"learning_rate": 1.8015512024212573e-06,
"loss": 0.3132,
"step": 275
},
{
"epoch": 0.592274678111588,
"grad_norm": 4.371558241354916,
"learning_rate": 1.7853842741780474e-06,
"loss": 0.2161,
"step": 276
},
{
"epoch": 0.5944206008583691,
"grad_norm": 3.7439703795742423,
"learning_rate": 1.769249824649677e-06,
"loss": 0.1681,
"step": 277
},
{
"epoch": 0.5965665236051502,
"grad_norm": 4.954905160767698,
"learning_rate": 1.7531485871340122e-06,
"loss": 0.2169,
"step": 278
},
{
"epoch": 0.5987124463519313,
"grad_norm": 4.509338306319588,
"learning_rate": 1.7370812934194565e-06,
"loss": 0.3037,
"step": 279
},
{
"epoch": 0.6008583690987125,
"grad_norm": 3.5630209392348315,
"learning_rate": 1.7210486737516947e-06,
"loss": 0.1491,
"step": 280
},
{
"epoch": 0.6030042918454935,
"grad_norm": 4.721486742009494,
"learning_rate": 1.7050514568005072e-06,
"loss": 0.2978,
"step": 281
},
{
"epoch": 0.6051502145922747,
"grad_norm": 4.438705208811552,
"learning_rate": 1.6890903696266447e-06,
"loss": 0.2172,
"step": 282
},
{
"epoch": 0.6072961373390557,
"grad_norm": 10.633440687114604,
"learning_rate": 1.6731661376487923e-06,
"loss": 0.2509,
"step": 283
},
{
"epoch": 0.6094420600858369,
"grad_norm": 9.519241352604435,
"learning_rate": 1.6572794846105919e-06,
"loss": 0.3126,
"step": 284
},
{
"epoch": 0.6115879828326181,
"grad_norm": 6.236116887316222,
"learning_rate": 1.6414311325477567e-06,
"loss": 0.3433,
"step": 285
},
{
"epoch": 0.6137339055793991,
"grad_norm": 6.652929433249715,
"learning_rate": 1.6256218017552484e-06,
"loss": 0.3924,
"step": 286
},
{
"epoch": 0.6158798283261803,
"grad_norm": 4.230578383590287,
"learning_rate": 1.6098522107545426e-06,
"loss": 0.1969,
"step": 287
},
{
"epoch": 0.6180257510729614,
"grad_norm": 4.584849008876823,
"learning_rate": 1.594123076260975e-06,
"loss": 0.1952,
"step": 288
},
{
"epoch": 0.6201716738197425,
"grad_norm": 10.774923368712571,
"learning_rate": 1.578435113151166e-06,
"loss": 0.3867,
"step": 289
},
{
"epoch": 0.6223175965665236,
"grad_norm": 3.7956827550236603,
"learning_rate": 1.5627890344305256e-06,
"loss": 0.1921,
"step": 290
},
{
"epoch": 0.6244635193133047,
"grad_norm": 2.7587416399153897,
"learning_rate": 1.547185551200856e-06,
"loss": 0.1014,
"step": 291
},
{
"epoch": 0.6266094420600858,
"grad_norm": 5.27854274924106,
"learning_rate": 1.531625372628025e-06,
"loss": 0.2008,
"step": 292
},
{
"epoch": 0.628755364806867,
"grad_norm": 8.635037982539608,
"learning_rate": 1.5161092059097399e-06,
"loss": 0.5101,
"step": 293
},
{
"epoch": 0.630901287553648,
"grad_norm": 3.3848075411641076,
"learning_rate": 1.500637756243405e-06,
"loss": 0.1936,
"step": 294
},
{
"epoch": 0.6330472103004292,
"grad_norm": 10.323449388666509,
"learning_rate": 1.485211726794068e-06,
"loss": 0.3156,
"step": 295
},
{
"epoch": 0.6351931330472103,
"grad_norm": 3.3898443020378823,
"learning_rate": 1.469831818662467e-06,
"loss": 0.4251,
"step": 296
},
{
"epoch": 0.6373390557939914,
"grad_norm": 5.429823091284252,
"learning_rate": 1.4544987308531594e-06,
"loss": 0.2863,
"step": 297
},
{
"epoch": 0.6394849785407726,
"grad_norm": 6.489533944140564,
"learning_rate": 1.439213160242759e-06,
"loss": 0.2321,
"step": 298
},
{
"epoch": 0.6416309012875536,
"grad_norm": 5.491165521890711,
"learning_rate": 1.4239758015482607e-06,
"loss": 0.5229,
"step": 299
},
{
"epoch": 0.6437768240343348,
"grad_norm": 10.960007456788807,
"learning_rate": 1.4087873472954638e-06,
"loss": 0.3474,
"step": 300
},
{
"epoch": 0.6437768240343348,
"eval_loss": 1.4280835390090942,
"eval_runtime": 0.5582,
"eval_samples_per_second": 3.583,
"eval_steps_per_second": 1.792,
"step": 300
},
{
"epoch": 0.6459227467811158,
"grad_norm": 4.097125958239756,
"learning_rate": 1.393648487787504e-06,
"loss": 0.175,
"step": 301
},
{
"epoch": 0.648068669527897,
"grad_norm": 9.06788832499044,
"learning_rate": 1.37855991107347e-06,
"loss": 0.3413,
"step": 302
},
{
"epoch": 0.6502145922746781,
"grad_norm": 4.058418163873224,
"learning_rate": 1.3635223029171418e-06,
"loss": 0.1829,
"step": 303
},
{
"epoch": 0.6523605150214592,
"grad_norm": 148.2865695887899,
"learning_rate": 1.3485363467658186e-06,
"loss": 6.7839,
"step": 304
},
{
"epoch": 0.6545064377682404,
"grad_norm": 5.592326984498724,
"learning_rate": 1.3336027237192551e-06,
"loss": 0.2715,
"step": 305
},
{
"epoch": 0.6566523605150214,
"grad_norm": 11.675146672194217,
"learning_rate": 1.3187221124987107e-06,
"loss": 0.3927,
"step": 306
},
{
"epoch": 0.6587982832618026,
"grad_norm": 6.303487956163143,
"learning_rate": 1.3038951894160962e-06,
"loss": 0.3058,
"step": 307
},
{
"epoch": 0.6609442060085837,
"grad_norm": 3.5714075946161583,
"learning_rate": 1.289122628343244e-06,
"loss": 0.1626,
"step": 308
},
{
"epoch": 0.6630901287553648,
"grad_norm": 2.8795739712912747,
"learning_rate": 1.2744051006812712e-06,
"loss": 0.1164,
"step": 309
},
{
"epoch": 0.6652360515021459,
"grad_norm": 3.784768504884893,
"learning_rate": 1.2597432753300753e-06,
"loss": 0.2305,
"step": 310
},
{
"epoch": 0.6673819742489271,
"grad_norm": 5.42666962884753,
"learning_rate": 1.245137818657924e-06,
"loss": 0.2721,
"step": 311
},
{
"epoch": 0.6695278969957081,
"grad_norm": 5.933064715860253,
"learning_rate": 1.2305893944711773e-06,
"loss": 0.2627,
"step": 312
},
{
"epoch": 0.6716738197424893,
"grad_norm": 4.451323659006045,
"learning_rate": 1.21609866398411e-06,
"loss": 0.2969,
"step": 313
},
{
"epoch": 0.6738197424892703,
"grad_norm": 4.851157313459204,
"learning_rate": 1.201666285788869e-06,
"loss": 0.2446,
"step": 314
},
{
"epoch": 0.6759656652360515,
"grad_norm": 4.25532850589281,
"learning_rate": 1.187292915825531e-06,
"loss": 0.2488,
"step": 315
},
{
"epoch": 0.6781115879828327,
"grad_norm": 4.400762031022185,
"learning_rate": 1.1729792073523e-06,
"loss": 0.2463,
"step": 316
},
{
"epoch": 0.6802575107296137,
"grad_norm": 4.1661170844892785,
"learning_rate": 1.1587258109158114e-06,
"loss": 0.2479,
"step": 317
},
{
"epoch": 0.6824034334763949,
"grad_norm": 4.315876128019499,
"learning_rate": 1.1445333743215648e-06,
"loss": 0.3109,
"step": 318
},
{
"epoch": 0.6845493562231759,
"grad_norm": 4.507385647592385,
"learning_rate": 1.1304025426044869e-06,
"loss": 0.2711,
"step": 319
},
{
"epoch": 0.6866952789699571,
"grad_norm": 4.922745847528059,
"learning_rate": 1.116333957999608e-06,
"loss": 0.2441,
"step": 320
},
{
"epoch": 0.6888412017167382,
"grad_norm": 4.076334007452991,
"learning_rate": 1.1023282599128797e-06,
"loss": 0.2134,
"step": 321
},
{
"epoch": 0.6909871244635193,
"grad_norm": 4.671754190487534,
"learning_rate": 1.0883860848921122e-06,
"loss": 0.2048,
"step": 322
},
{
"epoch": 0.6931330472103004,
"grad_norm": 9.92777165374971,
"learning_rate": 1.07450806659804e-06,
"loss": 0.4585,
"step": 323
},
{
"epoch": 0.6952789699570815,
"grad_norm": 5.249124657109493,
"learning_rate": 1.060694835775527e-06,
"loss": 0.2441,
"step": 324
},
{
"epoch": 0.6974248927038627,
"grad_norm": 3.576374367164296,
"learning_rate": 1.0469470202248976e-06,
"loss": 0.2092,
"step": 325
},
{
"epoch": 0.6995708154506438,
"grad_norm": 4.1766033624138315,
"learning_rate": 1.0332652447734057e-06,
"loss": 0.2437,
"step": 326
},
{
"epoch": 0.7017167381974249,
"grad_norm": 4.5911217940771865,
"learning_rate": 1.019650131246835e-06,
"loss": 0.3378,
"step": 327
},
{
"epoch": 0.703862660944206,
"grad_norm": 5.049668031588922,
"learning_rate": 1.006102298441236e-06,
"loss": 0.276,
"step": 328
},
{
"epoch": 0.7060085836909872,
"grad_norm": 3.2474445516283366,
"learning_rate": 9.926223620948061e-07,
"loss": 0.1107,
"step": 329
},
{
"epoch": 0.7081545064377682,
"grad_norm": 12.87037417509136,
"learning_rate": 9.792109348599036e-07,
"loss": 0.3857,
"step": 330
},
{
"epoch": 0.7103004291845494,
"grad_norm": 5.089010214872758,
"learning_rate": 9.65868626275198e-07,
"loss": 0.3078,
"step": 331
},
{
"epoch": 0.7124463519313304,
"grad_norm": 12.594828602227423,
"learning_rate": 9.525960427379772e-07,
"loss": 0.3576,
"step": 332
},
{
"epoch": 0.7145922746781116,
"grad_norm": 13.530682640951623,
"learning_rate": 9.393937874765754e-07,
"loss": 0.5429,
"step": 333
},
{
"epoch": 0.7167381974248928,
"grad_norm": 3.963378157061749,
"learning_rate": 9.262624605229673e-07,
"loss": 0.2409,
"step": 334
},
{
"epoch": 0.7188841201716738,
"grad_norm": 3.7920088399022287,
"learning_rate": 9.132026586854909e-07,
"loss": 0.249,
"step": 335
},
{
"epoch": 0.721030042918455,
"grad_norm": 13.220884914625854,
"learning_rate": 9.002149755217246e-07,
"loss": 0.654,
"step": 336
},
{
"epoch": 0.723175965665236,
"grad_norm": 3.585564797999746,
"learning_rate": 8.873000013115099e-07,
"loss": 0.1466,
"step": 337
},
{
"epoch": 0.7253218884120172,
"grad_norm": 4.837559263261418,
"learning_rate": 8.744583230301248e-07,
"loss": 0.2767,
"step": 338
},
{
"epoch": 0.7274678111587983,
"grad_norm": 5.252715623197888,
"learning_rate": 8.61690524321607e-07,
"loss": 0.4616,
"step": 339
},
{
"epoch": 0.7296137339055794,
"grad_norm": 4.394456008160045,
"learning_rate": 8.48997185472226e-07,
"loss": 0.3365,
"step": 340
},
{
"epoch": 0.7317596566523605,
"grad_norm": 4.731413577745255,
"learning_rate": 8.363788833841083e-07,
"loss": 0.2681,
"step": 341
},
{
"epoch": 0.7339055793991416,
"grad_norm": 4.23884351278645,
"learning_rate": 8.238361915490226e-07,
"loss": 0.2179,
"step": 342
},
{
"epoch": 0.7360515021459227,
"grad_norm": 4.991832411605434,
"learning_rate": 8.113696800223084e-07,
"loss": 0.3074,
"step": 343
},
{
"epoch": 0.7381974248927039,
"grad_norm": 11.78247542725481,
"learning_rate": 7.989799153969735e-07,
"loss": 0.7113,
"step": 344
},
{
"epoch": 0.740343347639485,
"grad_norm": 2.677869163204128,
"learning_rate": 7.866674607779401e-07,
"loss": 0.1147,
"step": 345
},
{
"epoch": 0.7424892703862661,
"grad_norm": 15.72663219186909,
"learning_rate": 7.744328757564501e-07,
"loss": 0.8535,
"step": 346
},
{
"epoch": 0.7446351931330472,
"grad_norm": 5.679767488995843,
"learning_rate": 7.622767163846376e-07,
"loss": 0.2275,
"step": 347
},
{
"epoch": 0.7467811158798283,
"grad_norm": 4.066844515227611,
"learning_rate": 7.501995351502497e-07,
"loss": 0.3943,
"step": 348
},
{
"epoch": 0.7489270386266095,
"grad_norm": 5.645157777694975,
"learning_rate": 7.38201880951544e-07,
"loss": 0.4427,
"step": 349
},
{
"epoch": 0.7510729613733905,
"grad_norm": 4.956779129225836,
"learning_rate": 7.26284299072334e-07,
"loss": 0.202,
"step": 350
},
{
"epoch": 0.7532188841201717,
"grad_norm": 2.5935658433153566,
"learning_rate": 7.144473311572136e-07,
"loss": 0.1596,
"step": 351
},
{
"epoch": 0.7553648068669528,
"grad_norm": 4.01470514282122,
"learning_rate": 7.026915151869335e-07,
"loss": 0.1781,
"step": 352
},
{
"epoch": 0.7575107296137339,
"grad_norm": 4.6123159242382075,
"learning_rate": 6.910173854539551e-07,
"loss": 0.25,
"step": 353
},
{
"epoch": 0.759656652360515,
"grad_norm": 3.0887466278904703,
"learning_rate": 6.794254725381641e-07,
"loss": 0.2184,
"step": 354
},
{
"epoch": 0.7618025751072961,
"grad_norm": 4.1284793392534995,
"learning_rate": 6.679163032827593e-07,
"loss": 0.2396,
"step": 355
},
{
"epoch": 0.7639484978540773,
"grad_norm": 4.382346488786086,
"learning_rate": 6.564904007703032e-07,
"loss": 0.2136,
"step": 356
},
{
"epoch": 0.7660944206008584,
"grad_norm": 10.798704798244964,
"learning_rate": 6.45148284298954e-07,
"loss": 0.6572,
"step": 357
},
{
"epoch": 0.7682403433476395,
"grad_norm": 4.878129288407048,
"learning_rate": 6.33890469358861e-07,
"loss": 0.3525,
"step": 358
},
{
"epoch": 0.7703862660944206,
"grad_norm": 5.030026237930303,
"learning_rate": 6.227174676087333e-07,
"loss": 0.2312,
"step": 359
},
{
"epoch": 0.7725321888412017,
"grad_norm": 17.098271284659155,
"learning_rate": 6.11629786852592e-07,
"loss": 0.6886,
"step": 360
},
{
"epoch": 0.7746781115879828,
"grad_norm": 4.264109038299607,
"learning_rate": 6.006279310166835e-07,
"loss": 0.2899,
"step": 361
},
{
"epoch": 0.776824034334764,
"grad_norm": 4.9567417333092605,
"learning_rate": 5.897124001265822e-07,
"loss": 0.2594,
"step": 362
},
{
"epoch": 0.778969957081545,
"grad_norm": 4.793597034829966,
"learning_rate": 5.788836902844633e-07,
"loss": 0.2406,
"step": 363
},
{
"epoch": 0.7811158798283262,
"grad_norm": 5.338193032183525,
"learning_rate": 5.681422936465522e-07,
"loss": 0.3718,
"step": 364
},
{
"epoch": 0.7832618025751072,
"grad_norm": 4.677431437894929,
"learning_rate": 5.574886984007602e-07,
"loss": 0.1582,
"step": 365
},
{
"epoch": 0.7854077253218884,
"grad_norm": 5.490552521240752,
"learning_rate": 5.469233887444941e-07,
"loss": 0.3061,
"step": 366
},
{
"epoch": 0.7875536480686696,
"grad_norm": 3.324520040683454,
"learning_rate": 5.36446844862653e-07,
"loss": 0.416,
"step": 367
},
{
"epoch": 0.7896995708154506,
"grad_norm": 4.170197573866644,
"learning_rate": 5.260595429058021e-07,
"loss": 0.182,
"step": 368
},
{
"epoch": 0.7918454935622318,
"grad_norm": 15.271343898793598,
"learning_rate": 5.1576195496853e-07,
"loss": 0.971,
"step": 369
},
{
"epoch": 0.7939914163090128,
"grad_norm": 5.773601400585028,
"learning_rate": 5.055545490679981e-07,
"loss": 0.373,
"step": 370
},
{
"epoch": 0.796137339055794,
"grad_norm": 5.969373195356161,
"learning_rate": 4.954377891226623e-07,
"loss": 0.1698,
"step": 371
},
{
"epoch": 0.7982832618025751,
"grad_norm": 4.932322793806067,
"learning_rate": 4.854121349311949e-07,
"loss": 0.3279,
"step": 372
},
{
"epoch": 0.8004291845493562,
"grad_norm": 4.577118395812275,
"learning_rate": 4.7547804215158476e-07,
"loss": 0.2336,
"step": 373
},
{
"epoch": 0.8025751072961373,
"grad_norm": 4.347265571148098,
"learning_rate": 4.6563596228042433e-07,
"loss": 0.2708,
"step": 374
},
{
"epoch": 0.8047210300429185,
"grad_norm": 5.494640250591727,
"learning_rate": 4.558863426323962e-07,
"loss": 0.1907,
"step": 375
},
{
"epoch": 0.8068669527896996,
"grad_norm": 3.3572786766867844,
"learning_rate": 4.462296263199381e-07,
"loss": 0.2496,
"step": 376
},
{
"epoch": 0.8090128755364807,
"grad_norm": 5.900778507191783,
"learning_rate": 4.366662522331053e-07,
"loss": 0.348,
"step": 377
},
{
"epoch": 0.8111587982832618,
"grad_norm": 9.530668791644544,
"learning_rate": 4.27196655019623e-07,
"loss": 0.31,
"step": 378
},
{
"epoch": 0.8133047210300429,
"grad_norm": 11.51101766547589,
"learning_rate": 4.1782126506513196e-07,
"loss": 0.4048,
"step": 379
},
{
"epoch": 0.8154506437768241,
"grad_norm": 4.265212244249617,
"learning_rate": 4.0854050847362966e-07,
"loss": 0.3379,
"step": 380
},
{
"epoch": 0.8175965665236051,
"grad_norm": 4.266290446089351,
"learning_rate": 3.9935480704810237e-07,
"loss": 0.2869,
"step": 381
},
{
"epoch": 0.8197424892703863,
"grad_norm": 10.069859696254095,
"learning_rate": 3.9026457827135324e-07,
"loss": 0.3259,
"step": 382
},
{
"epoch": 0.8218884120171673,
"grad_norm": 4.789626593387076,
"learning_rate": 3.812702352870321e-07,
"loss": 0.2795,
"step": 383
},
{
"epoch": 0.8240343347639485,
"grad_norm": 7.071090188512615,
"learning_rate": 3.723721868808533e-07,
"loss": 0.3904,
"step": 384
},
{
"epoch": 0.8261802575107297,
"grad_norm": 6.396013480233416,
"learning_rate": 3.6357083746202173e-07,
"loss": 0.3435,
"step": 385
},
{
"epoch": 0.8283261802575107,
"grad_norm": 6.912201776722396,
"learning_rate": 3.5486658704484977e-07,
"loss": 0.1841,
"step": 386
},
{
"epoch": 0.8304721030042919,
"grad_norm": 3.7884598131328793,
"learning_rate": 3.4625983123057624e-07,
"loss": 0.1977,
"step": 387
},
{
"epoch": 0.8326180257510729,
"grad_norm": 4.539195321014333,
"learning_rate": 3.3775096118939033e-07,
"loss": 0.2573,
"step": 388
},
{
"epoch": 0.8347639484978541,
"grad_norm": 13.401579924542975,
"learning_rate": 3.2934036364264845e-07,
"loss": 0.4396,
"step": 389
},
{
"epoch": 0.8369098712446352,
"grad_norm": 3.4147384980259816,
"learning_rate": 3.2102842084530293e-07,
"loss": 0.1677,
"step": 390
},
{
"epoch": 0.8390557939914163,
"grad_norm": 12.280073964483028,
"learning_rate": 3.128155105685243e-07,
"loss": 0.6472,
"step": 391
},
{
"epoch": 0.8412017167381974,
"grad_norm": 14.537818479540036,
"learning_rate": 3.0470200608253594e-07,
"loss": 0.6278,
"step": 392
},
{
"epoch": 0.8433476394849786,
"grad_norm": 4.602724381634226,
"learning_rate": 2.96688276139645e-07,
"loss": 0.2403,
"step": 393
},
{
"epoch": 0.8454935622317596,
"grad_norm": 5.352137114560932,
"learning_rate": 2.887746849574877e-07,
"loss": 0.3369,
"step": 394
},
{
"epoch": 0.8476394849785408,
"grad_norm": 6.023327004803226,
"learning_rate": 2.809615922024711e-07,
"loss": 0.2251,
"step": 395
},
{
"epoch": 0.8497854077253219,
"grad_norm": 5.227321763313939,
"learning_rate": 2.7324935297343146e-07,
"loss": 0.3855,
"step": 396
},
{
"epoch": 0.851931330472103,
"grad_norm": 3.301210094777184,
"learning_rate": 2.6563831778549015e-07,
"loss": 0.1753,
"step": 397
},
{
"epoch": 0.8540772532188842,
"grad_norm": 3.8623722681440125,
"learning_rate": 2.5812883255412704e-07,
"loss": 0.1972,
"step": 398
},
{
"epoch": 0.8562231759656652,
"grad_norm": 11.977134679582875,
"learning_rate": 2.5072123857945773e-07,
"loss": 0.4452,
"step": 399
},
{
"epoch": 0.8583690987124464,
"grad_norm": 11.01382449808334,
"learning_rate": 2.4341587253072035e-07,
"loss": 0.365,
"step": 400
},
{
"epoch": 0.8583690987124464,
"eval_loss": 1.3694226741790771,
"eval_runtime": 0.5595,
"eval_samples_per_second": 3.575,
"eval_steps_per_second": 1.787,
"step": 400
},
{
"epoch": 0.8605150214592274,
"grad_norm": 5.5777813351540315,
"learning_rate": 2.3621306643097613e-07,
"loss": 0.2782,
"step": 401
},
{
"epoch": 0.8626609442060086,
"grad_norm": 4.6116367037678785,
"learning_rate": 2.2911314764201775e-07,
"loss": 0.3513,
"step": 402
},
{
"epoch": 0.8648068669527897,
"grad_norm": 4.483486905044895,
"learning_rate": 2.221164388494923e-07,
"loss": 0.4313,
"step": 403
},
{
"epoch": 0.8669527896995708,
"grad_norm": 4.272277428586251,
"learning_rate": 2.1522325804823496e-07,
"loss": 0.2204,
"step": 404
},
{
"epoch": 0.869098712446352,
"grad_norm": 3.896674815860478,
"learning_rate": 2.0843391852781558e-07,
"loss": 0.2286,
"step": 405
},
{
"epoch": 0.871244635193133,
"grad_norm": 11.404612671959441,
"learning_rate": 2.0174872885830117e-07,
"loss": 0.5745,
"step": 406
},
{
"epoch": 0.8733905579399142,
"grad_norm": 5.761128589810944,
"learning_rate": 1.9516799287622984e-07,
"loss": 0.2869,
"step": 407
},
{
"epoch": 0.8755364806866953,
"grad_norm": 3.268320125330955,
"learning_rate": 1.8869200967080503e-07,
"loss": 0.1103,
"step": 408
},
{
"epoch": 0.8776824034334764,
"grad_norm": 4.38842912004494,
"learning_rate": 1.8232107357029877e-07,
"loss": 0.2272,
"step": 409
},
{
"epoch": 0.8798283261802575,
"grad_norm": 4.643796217859636,
"learning_rate": 1.7605547412867574e-07,
"loss": 0.184,
"step": 410
},
{
"epoch": 0.8819742489270386,
"grad_norm": 4.90732488089375,
"learning_rate": 1.6989549611243412e-07,
"loss": 0.3627,
"step": 411
},
{
"epoch": 0.8841201716738197,
"grad_norm": 12.17579771573891,
"learning_rate": 1.638414194876617e-07,
"loss": 0.5054,
"step": 412
},
{
"epoch": 0.8862660944206009,
"grad_norm": 7.752186615318354,
"learning_rate": 1.5789351940731334e-07,
"loss": 0.363,
"step": 413
},
{
"epoch": 0.8884120171673819,
"grad_norm": 4.5450019220648,
"learning_rate": 1.520520661987049e-07,
"loss": 0.3259,
"step": 414
},
{
"epoch": 0.8905579399141631,
"grad_norm": 5.488305915443275,
"learning_rate": 1.463173253512251e-07,
"loss": 0.3395,
"step": 415
},
{
"epoch": 0.8927038626609443,
"grad_norm": 7.094268562494252,
"learning_rate": 1.406895575042727e-07,
"loss": 0.295,
"step": 416
},
{
"epoch": 0.8948497854077253,
"grad_norm": 4.7154597836682965,
"learning_rate": 1.3516901843540876e-07,
"loss": 0.2653,
"step": 417
},
{
"epoch": 0.8969957081545065,
"grad_norm": 11.321571989329978,
"learning_rate": 1.2975595904873073e-07,
"loss": 0.4694,
"step": 418
},
{
"epoch": 0.8991416309012875,
"grad_norm": 4.452790240381536,
"learning_rate": 1.2445062536347057e-07,
"loss": 0.3792,
"step": 419
},
{
"epoch": 0.9012875536480687,
"grad_norm": 4.044178243939312,
"learning_rate": 1.1925325850281416e-07,
"loss": 0.2857,
"step": 420
},
{
"epoch": 0.9034334763948498,
"grad_norm": 5.509954869782006,
"learning_rate": 1.1416409468293977e-07,
"loss": 0.3078,
"step": 421
},
{
"epoch": 0.9055793991416309,
"grad_norm": 4.69558598631356,
"learning_rate": 1.0918336520228474e-07,
"loss": 0.335,
"step": 422
},
{
"epoch": 0.907725321888412,
"grad_norm": 4.4538465310945385,
"learning_rate": 1.0431129643103193e-07,
"loss": 0.2351,
"step": 423
},
{
"epoch": 0.9098712446351931,
"grad_norm": 5.374815587193687,
"learning_rate": 9.954810980082191e-08,
"loss": 0.2546,
"step": 424
},
{
"epoch": 0.9120171673819742,
"grad_norm": 11.52228630231847,
"learning_rate": 9.489402179468754e-08,
"loss": 0.7185,
"step": 425
},
{
"epoch": 0.9141630901287554,
"grad_norm": 3.884298143154326,
"learning_rate": 9.034924393721778e-08,
"loss": 0.2261,
"step": 426
},
{
"epoch": 0.9163090128755365,
"grad_norm": 12.582223724723782,
"learning_rate": 8.5913982784942e-08,
"loss": 0.5048,
"step": 427
},
{
"epoch": 0.9184549356223176,
"grad_norm": 4.909917760044249,
"learning_rate": 8.15884399169417e-08,
"loss": 0.1981,
"step": 428
},
{
"epoch": 0.9206008583690987,
"grad_norm": 4.336475429929087,
"learning_rate": 7.737281192569169e-08,
"loss": 0.2551,
"step": 429
},
{
"epoch": 0.9227467811158798,
"grad_norm": 3.489835127648909,
"learning_rate": 7.326729040812136e-08,
"loss": 0.1921,
"step": 430
},
{
"epoch": 0.924892703862661,
"grad_norm": 4.877570803828318,
"learning_rate": 6.927206195691039e-08,
"loss": 0.2177,
"step": 431
},
{
"epoch": 0.927038626609442,
"grad_norm": 4.717548019415604,
"learning_rate": 6.538730815200483e-08,
"loss": 0.147,
"step": 432
},
{
"epoch": 0.9291845493562232,
"grad_norm": 14.494510709152369,
"learning_rate": 6.1613205552368e-08,
"loss": 0.6247,
"step": 433
},
{
"epoch": 0.9313304721030042,
"grad_norm": 3.5697709692346677,
"learning_rate": 5.79499256879526e-08,
"loss": 0.1588,
"step": 434
},
{
"epoch": 0.9334763948497854,
"grad_norm": 5.135679478772209,
"learning_rate": 5.4397635051907093e-08,
"loss": 0.4196,
"step": 435
},
{
"epoch": 0.9356223175965666,
"grad_norm": 5.329997658405359,
"learning_rate": 5.095649509300804e-08,
"loss": 0.2701,
"step": 436
},
{
"epoch": 0.9377682403433476,
"grad_norm": 3.760523480520758,
"learning_rate": 4.7626662208322405e-08,
"loss": 0.0939,
"step": 437
},
{
"epoch": 0.9399141630901288,
"grad_norm": 5.291669505677406,
"learning_rate": 4.4408287736099344e-08,
"loss": 0.3128,
"step": 438
},
{
"epoch": 0.9420600858369099,
"grad_norm": 11.680854749305373,
"learning_rate": 4.130151794889181e-08,
"loss": 0.3982,
"step": 439
},
{
"epoch": 0.944206008583691,
"grad_norm": 12.506267427980399,
"learning_rate": 3.830649404690939e-08,
"loss": 0.6572,
"step": 440
},
{
"epoch": 0.9463519313304721,
"grad_norm": 4.533062512569462,
"learning_rate": 3.5423352151599534e-08,
"loss": 0.2257,
"step": 441
},
{
"epoch": 0.9484978540772532,
"grad_norm": 3.8785495849634173,
"learning_rate": 3.2652223299462214e-08,
"loss": 0.217,
"step": 442
},
{
"epoch": 0.9506437768240343,
"grad_norm": 6.192440279403632,
"learning_rate": 2.9993233436093895e-08,
"loss": 0.362,
"step": 443
},
{
"epoch": 0.9527896995708155,
"grad_norm": 4.267433754596404,
"learning_rate": 2.7446503410463178e-08,
"loss": 0.2044,
"step": 444
},
{
"epoch": 0.9549356223175965,
"grad_norm": 5.592239506957767,
"learning_rate": 2.5012148969419113e-08,
"loss": 0.3607,
"step": 445
},
{
"epoch": 0.9570815450643777,
"grad_norm": 12.403767416603346,
"learning_rate": 2.2690280752429293e-08,
"loss": 0.5623,
"step": 446
},
{
"epoch": 0.9592274678111588,
"grad_norm": 4.281323531138287,
"learning_rate": 2.0481004286552753e-08,
"loss": 0.2902,
"step": 447
},
{
"epoch": 0.9613733905579399,
"grad_norm": 2.903934981764517,
"learning_rate": 1.8384419981642698e-08,
"loss": 0.1355,
"step": 448
},
{
"epoch": 0.9635193133047211,
"grad_norm": 8.89203528557412,
"learning_rate": 1.6400623125784053e-08,
"loss": 0.3686,
"step": 449
},
{
"epoch": 0.9656652360515021,
"grad_norm": 4.562592593974174,
"learning_rate": 1.452970388096192e-08,
"loss": 0.1926,
"step": 450
},
{
"epoch": 0.9678111587982833,
"grad_norm": 4.534339307707502,
"learning_rate": 1.2771747278963464e-08,
"loss": 0.3514,
"step": 451
},
{
"epoch": 0.9699570815450643,
"grad_norm": 4.556632192151679,
"learning_rate": 1.1126833217514898e-08,
"loss": 0.2418,
"step": 452
},
{
"epoch": 0.9721030042918455,
"grad_norm": 9.909433789309341,
"learning_rate": 9.595036456648277e-09,
"loss": 0.3205,
"step": 453
},
{
"epoch": 0.9742489270386266,
"grad_norm": 3.9689055222382374,
"learning_rate": 8.176426615304767e-09,
"loss": 0.1813,
"step": 454
},
{
"epoch": 0.9763948497854077,
"grad_norm": 5.3691676448201155,
"learning_rate": 6.871068168170237e-09,
"loss": 0.2227,
"step": 455
},
{
"epoch": 0.9785407725321889,
"grad_norm": 3.1063248198160824,
"learning_rate": 5.679020442745098e-09,
"loss": 0.1993,
"step": 456
},
{
"epoch": 0.98068669527897,
"grad_norm": 3.8439436507436415,
"learning_rate": 4.600337616648131e-09,
"loss": 0.2025,
"step": 457
},
{
"epoch": 0.9828326180257511,
"grad_norm": 3.4608789139316882,
"learning_rate": 3.6350687151531782e-09,
"loss": 0.1106,
"step": 458
},
{
"epoch": 0.9849785407725322,
"grad_norm": 4.432907889303436,
"learning_rate": 2.7832576089623086e-09,
"loss": 0.181,
"step": 459
},
{
"epoch": 0.9871244635193133,
"grad_norm": 5.815988851277571,
"learning_rate": 2.044943012210754e-09,
"loss": 0.3236,
"step": 460
},
{
"epoch": 0.9892703862660944,
"grad_norm": 4.622989507343908,
"learning_rate": 1.4201584807083113e-09,
"loss": 0.2848,
"step": 461
},
{
"epoch": 0.9914163090128756,
"grad_norm": 4.812640379426997,
"learning_rate": 9.08932410413621e-10,
"loss": 0.2791,
"step": 462
},
{
"epoch": 0.9935622317596566,
"grad_norm": 11.627724270489814,
"learning_rate": 5.112880361438088e-10,
"loss": 0.7668,
"step": 463
},
{
"epoch": 0.9957081545064378,
"grad_norm": 3.8724681206038953,
"learning_rate": 2.2724343051866438e-10,
"loss": 0.1976,
"step": 464
},
{
"epoch": 0.9978540772532188,
"grad_norm": 6.521739917424491,
"learning_rate": 5.681150313907591e-11,
"loss": 0.2869,
"step": 465
},
{
"epoch": 1.0,
"grad_norm": 3.883799871571989,
"learning_rate": 0.0,
"loss": 0.1588,
"step": 466
},
{
"epoch": 1.0,
"step": 466,
"total_flos": 4281709953024.0,
"train_loss": 0.34951822290220996,
"train_runtime": 959.7413,
"train_samples_per_second": 1.942,
"train_steps_per_second": 0.486
}
],
"logging_steps": 1,
"max_steps": 466,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2000000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4281709953024.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}