gyung's picture
Upload Gemma 4 E2B 2epoch DDP model artifacts
61b3229 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 367,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0027247956403269754,
"grad_norm": 3152.0,
"learning_rate": 0.0,
"loss": 48.40627670288086,
"step": 1
},
{
"epoch": 0.005449591280653951,
"grad_norm": 2672.0,
"learning_rate": 8.695652173913044e-07,
"loss": 47.4522819519043,
"step": 2
},
{
"epoch": 0.008174386920980926,
"grad_norm": 2656.0,
"learning_rate": 1.7391304347826088e-06,
"loss": 47.537269592285156,
"step": 3
},
{
"epoch": 0.010899182561307902,
"grad_norm": 2896.0,
"learning_rate": 2.6086956521739132e-06,
"loss": 47.03502655029297,
"step": 4
},
{
"epoch": 0.013623978201634877,
"grad_norm": 2112.0,
"learning_rate": 3.4782608695652175e-06,
"loss": 44.74693298339844,
"step": 5
},
{
"epoch": 0.01634877384196185,
"grad_norm": 1832.0,
"learning_rate": 4.347826086956522e-06,
"loss": 43.523712158203125,
"step": 6
},
{
"epoch": 0.01907356948228883,
"grad_norm": 4960.0,
"learning_rate": 5.2173913043478265e-06,
"loss": 39.67890930175781,
"step": 7
},
{
"epoch": 0.021798365122615803,
"grad_norm": 1004.0,
"learning_rate": 6.086956521739132e-06,
"loss": 38.25300216674805,
"step": 8
},
{
"epoch": 0.02452316076294278,
"grad_norm": 976.0,
"learning_rate": 6.956521739130435e-06,
"loss": 36.702880859375,
"step": 9
},
{
"epoch": 0.027247956403269755,
"grad_norm": 692.0,
"learning_rate": 7.82608695652174e-06,
"loss": 36.129356384277344,
"step": 10
},
{
"epoch": 0.02997275204359673,
"grad_norm": 484.0,
"learning_rate": 8.695652173913044e-06,
"loss": 33.03797149658203,
"step": 11
},
{
"epoch": 0.0326975476839237,
"grad_norm": 374.0,
"learning_rate": 9.565217391304349e-06,
"loss": 30.922203063964844,
"step": 12
},
{
"epoch": 0.035422343324250684,
"grad_norm": 364.0,
"learning_rate": 1.0434782608695653e-05,
"loss": 30.420955657958984,
"step": 13
},
{
"epoch": 0.03814713896457766,
"grad_norm": 272.0,
"learning_rate": 1.1304347826086957e-05,
"loss": 29.078968048095703,
"step": 14
},
{
"epoch": 0.04087193460490463,
"grad_norm": 268.0,
"learning_rate": 1.2173913043478263e-05,
"loss": 28.454662322998047,
"step": 15
},
{
"epoch": 0.043596730245231606,
"grad_norm": 284.0,
"learning_rate": 1.3043478260869566e-05,
"loss": 26.663990020751953,
"step": 16
},
{
"epoch": 0.04632152588555858,
"grad_norm": 180.0,
"learning_rate": 1.391304347826087e-05,
"loss": 26.216550827026367,
"step": 17
},
{
"epoch": 0.04904632152588556,
"grad_norm": 760.0,
"learning_rate": 1.4782608695652174e-05,
"loss": 25.440536499023438,
"step": 18
},
{
"epoch": 0.051771117166212535,
"grad_norm": 250.0,
"learning_rate": 1.565217391304348e-05,
"loss": 25.319339752197266,
"step": 19
},
{
"epoch": 0.05449591280653951,
"grad_norm": 160.0,
"learning_rate": 1.6521739130434785e-05,
"loss": 24.522743225097656,
"step": 20
},
{
"epoch": 0.05722070844686648,
"grad_norm": 99.0,
"learning_rate": 1.739130434782609e-05,
"loss": 23.68889045715332,
"step": 21
},
{
"epoch": 0.05994550408719346,
"grad_norm": 137.0,
"learning_rate": 1.8260869565217393e-05,
"loss": 22.45394515991211,
"step": 22
},
{
"epoch": 0.06267029972752043,
"grad_norm": 96.0,
"learning_rate": 1.9130434782608697e-05,
"loss": 21.58340835571289,
"step": 23
},
{
"epoch": 0.0653950953678474,
"grad_norm": 79.5,
"learning_rate": 2e-05,
"loss": 21.60813331604004,
"step": 24
},
{
"epoch": 0.0681198910081744,
"grad_norm": 68.0,
"learning_rate": 1.9999902382014363e-05,
"loss": 19.326705932617188,
"step": 25
},
{
"epoch": 0.07084468664850137,
"grad_norm": 195.0,
"learning_rate": 1.9999609529963303e-05,
"loss": 20.620744705200195,
"step": 26
},
{
"epoch": 0.07356948228882834,
"grad_norm": 204.0,
"learning_rate": 1.9999121449564347e-05,
"loss": 19.753509521484375,
"step": 27
},
{
"epoch": 0.07629427792915532,
"grad_norm": 71.5,
"learning_rate": 1.9998438150346578e-05,
"loss": 20.347627639770508,
"step": 28
},
{
"epoch": 0.07901907356948229,
"grad_norm": 215.0,
"learning_rate": 1.999755964565046e-05,
"loss": 19.19959831237793,
"step": 29
},
{
"epoch": 0.08174386920980926,
"grad_norm": 314.0,
"learning_rate": 1.9996485952627554e-05,
"loss": 18.856372833251953,
"step": 30
},
{
"epoch": 0.08446866485013624,
"grad_norm": 199.0,
"learning_rate": 1.999521709224022e-05,
"loss": 19.498279571533203,
"step": 31
},
{
"epoch": 0.08719346049046321,
"grad_norm": 69.5,
"learning_rate": 1.9993753089261175e-05,
"loss": 17.953914642333984,
"step": 32
},
{
"epoch": 0.08991825613079019,
"grad_norm": 180.0,
"learning_rate": 1.999209397227302e-05,
"loss": 17.53020477294922,
"step": 33
},
{
"epoch": 0.09264305177111716,
"grad_norm": 346.0,
"learning_rate": 1.999023977366769e-05,
"loss": 17.79115867614746,
"step": 34
},
{
"epoch": 0.09536784741144415,
"grad_norm": 237.0,
"learning_rate": 1.998819052964581e-05,
"loss": 18.816436767578125,
"step": 35
},
{
"epoch": 0.09809264305177112,
"grad_norm": 196.0,
"learning_rate": 1.9985946280215996e-05,
"loss": 17.000261306762695,
"step": 36
},
{
"epoch": 0.1008174386920981,
"grad_norm": 169.0,
"learning_rate": 1.998350706919407e-05,
"loss": 17.606061935424805,
"step": 37
},
{
"epoch": 0.10354223433242507,
"grad_norm": 55.0,
"learning_rate": 1.9980872944202203e-05,
"loss": 16.317874908447266,
"step": 38
},
{
"epoch": 0.10626702997275204,
"grad_norm": 122.0,
"learning_rate": 1.997804395666799e-05,
"loss": 16.31488800048828,
"step": 39
},
{
"epoch": 0.10899182561307902,
"grad_norm": 314.0,
"learning_rate": 1.9975020161823445e-05,
"loss": 16.29736328125,
"step": 40
},
{
"epoch": 0.11171662125340599,
"grad_norm": 64.5,
"learning_rate": 1.9971801618703924e-05,
"loss": 17.167266845703125,
"step": 41
},
{
"epoch": 0.11444141689373297,
"grad_norm": 52.0,
"learning_rate": 1.996838839014696e-05,
"loss": 15.893667221069336,
"step": 42
},
{
"epoch": 0.11716621253405994,
"grad_norm": 52.25,
"learning_rate": 1.9964780542791057e-05,
"loss": 15.158836364746094,
"step": 43
},
{
"epoch": 0.11989100817438691,
"grad_norm": 101.5,
"learning_rate": 1.9960978147074367e-05,
"loss": 15.873449325561523,
"step": 44
},
{
"epoch": 0.1226158038147139,
"grad_norm": 85.0,
"learning_rate": 1.9956981277233342e-05,
"loss": 15.50723648071289,
"step": 45
},
{
"epoch": 0.12534059945504086,
"grad_norm": 83.0,
"learning_rate": 1.9952790011301248e-05,
"loss": 16.80683135986328,
"step": 46
},
{
"epoch": 0.12806539509536785,
"grad_norm": 111.0,
"learning_rate": 1.994840443110668e-05,
"loss": 16.459972381591797,
"step": 47
},
{
"epoch": 0.1307901907356948,
"grad_norm": 150.0,
"learning_rate": 1.9943824622271934e-05,
"loss": 13.282132148742676,
"step": 48
},
{
"epoch": 0.1335149863760218,
"grad_norm": 128.0,
"learning_rate": 1.9939050674211358e-05,
"loss": 14.049150466918945,
"step": 49
},
{
"epoch": 0.1362397820163488,
"grad_norm": 87.5,
"learning_rate": 1.9934082680129588e-05,
"loss": 14.285058975219727,
"step": 50
},
{
"epoch": 0.13896457765667575,
"grad_norm": 70.5,
"learning_rate": 1.9928920737019735e-05,
"loss": 12.706293106079102,
"step": 51
},
{
"epoch": 0.14168937329700274,
"grad_norm": 75.5,
"learning_rate": 1.9923564945661506e-05,
"loss": 13.83144474029541,
"step": 52
},
{
"epoch": 0.1444141689373297,
"grad_norm": 88.5,
"learning_rate": 1.99180154106192e-05,
"loss": 12.213239669799805,
"step": 53
},
{
"epoch": 0.14713896457765668,
"grad_norm": 97.0,
"learning_rate": 1.9912272240239715e-05,
"loss": 12.70011043548584,
"step": 54
},
{
"epoch": 0.14986376021798364,
"grad_norm": 93.0,
"learning_rate": 1.9906335546650394e-05,
"loss": 11.974971771240234,
"step": 55
},
{
"epoch": 0.15258855585831063,
"grad_norm": 66.0,
"learning_rate": 1.9900205445756845e-05,
"loss": 13.716851234436035,
"step": 56
},
{
"epoch": 0.1553133514986376,
"grad_norm": 57.75,
"learning_rate": 1.9893882057240698e-05,
"loss": 13.276803016662598,
"step": 57
},
{
"epoch": 0.15803814713896458,
"grad_norm": 63.5,
"learning_rate": 1.988736550455723e-05,
"loss": 12.804815292358398,
"step": 58
},
{
"epoch": 0.16076294277929154,
"grad_norm": 57.25,
"learning_rate": 1.9880655914933003e-05,
"loss": 12.110427856445312,
"step": 59
},
{
"epoch": 0.16348773841961853,
"grad_norm": 57.5,
"learning_rate": 1.9873753419363336e-05,
"loss": 12.278120040893555,
"step": 60
},
{
"epoch": 0.16621253405994552,
"grad_norm": 57.5,
"learning_rate": 1.986665815260977e-05,
"loss": 12.700621604919434,
"step": 61
},
{
"epoch": 0.16893732970027248,
"grad_norm": 122.5,
"learning_rate": 1.9859370253197436e-05,
"loss": 12.573596954345703,
"step": 62
},
{
"epoch": 0.17166212534059946,
"grad_norm": 61.75,
"learning_rate": 1.9851889863412347e-05,
"loss": 11.165464401245117,
"step": 63
},
{
"epoch": 0.17438692098092642,
"grad_norm": 67.5,
"learning_rate": 1.9844217129298616e-05,
"loss": 12.087121963500977,
"step": 64
},
{
"epoch": 0.1771117166212534,
"grad_norm": 106.5,
"learning_rate": 1.983635220065562e-05,
"loss": 14.107297897338867,
"step": 65
},
{
"epoch": 0.17983651226158037,
"grad_norm": 77.0,
"learning_rate": 1.9828295231035054e-05,
"loss": 12.48006820678711,
"step": 66
},
{
"epoch": 0.18256130790190736,
"grad_norm": 122.5,
"learning_rate": 1.9820046377737944e-05,
"loss": 12.802762985229492,
"step": 67
},
{
"epoch": 0.18528610354223432,
"grad_norm": 77.0,
"learning_rate": 1.9811605801811578e-05,
"loss": 10.705779075622559,
"step": 68
},
{
"epoch": 0.1880108991825613,
"grad_norm": 52.25,
"learning_rate": 1.9802973668046364e-05,
"loss": 12.537907600402832,
"step": 69
},
{
"epoch": 0.1907356948228883,
"grad_norm": 47.0,
"learning_rate": 1.97941501449726e-05,
"loss": 11.78143310546875,
"step": 70
},
{
"epoch": 0.19346049046321526,
"grad_norm": 41.5,
"learning_rate": 1.9785135404857202e-05,
"loss": 12.222698211669922,
"step": 71
},
{
"epoch": 0.19618528610354224,
"grad_norm": 41.5,
"learning_rate": 1.9775929623700318e-05,
"loss": 12.033823013305664,
"step": 72
},
{
"epoch": 0.1989100817438692,
"grad_norm": 38.5,
"learning_rate": 1.9766532981231913e-05,
"loss": 12.244077682495117,
"step": 73
},
{
"epoch": 0.2016348773841962,
"grad_norm": 49.75,
"learning_rate": 1.975694566090825e-05,
"loss": 11.97701644897461,
"step": 74
},
{
"epoch": 0.20435967302452315,
"grad_norm": 55.5,
"learning_rate": 1.9747167849908305e-05,
"loss": 10.784921646118164,
"step": 75
},
{
"epoch": 0.20708446866485014,
"grad_norm": 61.0,
"learning_rate": 1.9737199739130123e-05,
"loss": 11.930859565734863,
"step": 76
},
{
"epoch": 0.2098092643051771,
"grad_norm": 45.0,
"learning_rate": 1.9727041523187083e-05,
"loss": 13.60090446472168,
"step": 77
},
{
"epoch": 0.2125340599455041,
"grad_norm": 40.5,
"learning_rate": 1.97166934004041e-05,
"loss": 12.982333183288574,
"step": 78
},
{
"epoch": 0.21525885558583105,
"grad_norm": 59.75,
"learning_rate": 1.970615557281376e-05,
"loss": 9.924541473388672,
"step": 79
},
{
"epoch": 0.21798365122615804,
"grad_norm": 57.25,
"learning_rate": 1.969542824615235e-05,
"loss": 11.274691581726074,
"step": 80
},
{
"epoch": 0.22070844686648503,
"grad_norm": 50.75,
"learning_rate": 1.968451162985589e-05,
"loss": 9.735274314880371,
"step": 81
},
{
"epoch": 0.22343324250681199,
"grad_norm": 78.5,
"learning_rate": 1.9673405937055986e-05,
"loss": 10.165392875671387,
"step": 82
},
{
"epoch": 0.22615803814713897,
"grad_norm": 74.5,
"learning_rate": 1.9662111384575716e-05,
"loss": 9.077415466308594,
"step": 83
},
{
"epoch": 0.22888283378746593,
"grad_norm": 54.75,
"learning_rate": 1.9650628192925372e-05,
"loss": 10.11076831817627,
"step": 84
},
{
"epoch": 0.23160762942779292,
"grad_norm": 74.0,
"learning_rate": 1.963895658629816e-05,
"loss": 11.903621673583984,
"step": 85
},
{
"epoch": 0.23433242506811988,
"grad_norm": 47.25,
"learning_rate": 1.9627096792565825e-05,
"loss": 9.115705490112305,
"step": 86
},
{
"epoch": 0.23705722070844687,
"grad_norm": 78.5,
"learning_rate": 1.9615049043274207e-05,
"loss": 11.530861854553223,
"step": 87
},
{
"epoch": 0.23978201634877383,
"grad_norm": 54.75,
"learning_rate": 1.9602813573638705e-05,
"loss": 10.342988014221191,
"step": 88
},
{
"epoch": 0.24250681198910082,
"grad_norm": 46.5,
"learning_rate": 1.9590390622539696e-05,
"loss": 10.499998092651367,
"step": 89
},
{
"epoch": 0.2452316076294278,
"grad_norm": 61.75,
"learning_rate": 1.957778043251788e-05,
"loss": 10.014358520507812,
"step": 90
},
{
"epoch": 0.24795640326975477,
"grad_norm": 84.0,
"learning_rate": 1.9564983249769518e-05,
"loss": 12.045997619628906,
"step": 91
},
{
"epoch": 0.2506811989100817,
"grad_norm": 110.0,
"learning_rate": 1.9551999324141656e-05,
"loss": 10.226362228393555,
"step": 92
},
{
"epoch": 0.25340599455040874,
"grad_norm": 88.5,
"learning_rate": 1.953882890912723e-05,
"loss": 10.071401596069336,
"step": 93
},
{
"epoch": 0.2561307901907357,
"grad_norm": 92.0,
"learning_rate": 1.9525472261860112e-05,
"loss": 11.945771217346191,
"step": 94
},
{
"epoch": 0.25885558583106266,
"grad_norm": 59.25,
"learning_rate": 1.9511929643110095e-05,
"loss": 10.799688339233398,
"step": 95
},
{
"epoch": 0.2615803814713896,
"grad_norm": 85.0,
"learning_rate": 1.949820131727783e-05,
"loss": 12.050772666931152,
"step": 96
},
{
"epoch": 0.26430517711171664,
"grad_norm": 75.5,
"learning_rate": 1.9484287552389603e-05,
"loss": 10.570755004882812,
"step": 97
},
{
"epoch": 0.2670299727520436,
"grad_norm": 101.0,
"learning_rate": 1.9470188620092162e-05,
"loss": 10.214563369750977,
"step": 98
},
{
"epoch": 0.26975476839237056,
"grad_norm": 59.25,
"learning_rate": 1.945590479564738e-05,
"loss": 10.041733741760254,
"step": 99
},
{
"epoch": 0.2724795640326976,
"grad_norm": 80.0,
"learning_rate": 1.9441436357926892e-05,
"loss": 12.891487121582031,
"step": 100
},
{
"epoch": 0.27520435967302453,
"grad_norm": 67.5,
"learning_rate": 1.9426783589406645e-05,
"loss": 10.844165802001953,
"step": 101
},
{
"epoch": 0.2779291553133515,
"grad_norm": 48.75,
"learning_rate": 1.9411946776161388e-05,
"loss": 11.822603225708008,
"step": 102
},
{
"epoch": 0.28065395095367845,
"grad_norm": 68.5,
"learning_rate": 1.9396926207859085e-05,
"loss": 10.97657585144043,
"step": 103
},
{
"epoch": 0.28337874659400547,
"grad_norm": 134.0,
"learning_rate": 1.9381722177755266e-05,
"loss": 10.612011909484863,
"step": 104
},
{
"epoch": 0.28610354223433243,
"grad_norm": 154.0,
"learning_rate": 1.936633498268728e-05,
"loss": 9.453835487365723,
"step": 105
},
{
"epoch": 0.2888283378746594,
"grad_norm": 127.0,
"learning_rate": 1.9350764923068533e-05,
"loss": 9.9420166015625,
"step": 106
},
{
"epoch": 0.29155313351498635,
"grad_norm": 65.5,
"learning_rate": 1.933501230288259e-05,
"loss": 9.418241500854492,
"step": 107
},
{
"epoch": 0.29427792915531337,
"grad_norm": 62.75,
"learning_rate": 1.931907742967727e-05,
"loss": 8.981918334960938,
"step": 108
},
{
"epoch": 0.2970027247956403,
"grad_norm": 82.5,
"learning_rate": 1.9302960614558604e-05,
"loss": 10.584541320800781,
"step": 109
},
{
"epoch": 0.2997275204359673,
"grad_norm": 117.5,
"learning_rate": 1.928666217218481e-05,
"loss": 9.602861404418945,
"step": 110
},
{
"epoch": 0.3024523160762943,
"grad_norm": 148.0,
"learning_rate": 1.9270182420760104e-05,
"loss": 11.30278205871582,
"step": 111
},
{
"epoch": 0.30517711171662126,
"grad_norm": 62.5,
"learning_rate": 1.9253521682028515e-05,
"loss": 9.8443021774292,
"step": 112
},
{
"epoch": 0.3079019073569482,
"grad_norm": 84.0,
"learning_rate": 1.9236680281267594e-05,
"loss": 7.5392961502075195,
"step": 113
},
{
"epoch": 0.3106267029972752,
"grad_norm": 56.75,
"learning_rate": 1.921965854728207e-05,
"loss": 10.067930221557617,
"step": 114
},
{
"epoch": 0.3133514986376022,
"grad_norm": 44.75,
"learning_rate": 1.920245681239741e-05,
"loss": 8.589845657348633,
"step": 115
},
{
"epoch": 0.31607629427792916,
"grad_norm": 122.0,
"learning_rate": 1.918507541245336e-05,
"loss": 11.69874382019043,
"step": 116
},
{
"epoch": 0.3188010899182561,
"grad_norm": 89.0,
"learning_rate": 1.916751468679737e-05,
"loss": 9.99834156036377,
"step": 117
},
{
"epoch": 0.3215258855585831,
"grad_norm": 84.0,
"learning_rate": 1.9149774978277975e-05,
"loss": 9.743596076965332,
"step": 118
},
{
"epoch": 0.3242506811989101,
"grad_norm": 86.0,
"learning_rate": 1.9131856633238096e-05,
"loss": 9.140531539916992,
"step": 119
},
{
"epoch": 0.32697547683923706,
"grad_norm": 65.0,
"learning_rate": 1.911376000150828e-05,
"loss": 8.819114685058594,
"step": 120
},
{
"epoch": 0.329700272479564,
"grad_norm": 73.0,
"learning_rate": 1.9095485436399878e-05,
"loss": 9.055301666259766,
"step": 121
},
{
"epoch": 0.33242506811989103,
"grad_norm": 69.0,
"learning_rate": 1.9077033294698135e-05,
"loss": 9.458704948425293,
"step": 122
},
{
"epoch": 0.335149863760218,
"grad_norm": 64.0,
"learning_rate": 1.9058403936655235e-05,
"loss": 9.699943542480469,
"step": 123
},
{
"epoch": 0.33787465940054495,
"grad_norm": 59.5,
"learning_rate": 1.9039597725983254e-05,
"loss": 8.256848335266113,
"step": 124
},
{
"epoch": 0.3405994550408719,
"grad_norm": 59.25,
"learning_rate": 1.9020615029847073e-05,
"loss": 9.696537017822266,
"step": 125
},
{
"epoch": 0.34332425068119893,
"grad_norm": 53.75,
"learning_rate": 1.9001456218857207e-05,
"loss": 9.273826599121094,
"step": 126
},
{
"epoch": 0.3460490463215259,
"grad_norm": 57.5,
"learning_rate": 1.8982121667062566e-05,
"loss": 8.918879508972168,
"step": 127
},
{
"epoch": 0.34877384196185285,
"grad_norm": 130.0,
"learning_rate": 1.8962611751943142e-05,
"loss": 9.746708869934082,
"step": 128
},
{
"epoch": 0.35149863760217986,
"grad_norm": 73.0,
"learning_rate": 1.894292685440266e-05,
"loss": 9.20458984375,
"step": 129
},
{
"epoch": 0.3542234332425068,
"grad_norm": 57.25,
"learning_rate": 1.8923067358761135e-05,
"loss": 9.030914306640625,
"step": 130
},
{
"epoch": 0.3569482288828338,
"grad_norm": 48.25,
"learning_rate": 1.8903033652747352e-05,
"loss": 10.621173858642578,
"step": 131
},
{
"epoch": 0.35967302452316074,
"grad_norm": 55.5,
"learning_rate": 1.888282612749132e-05,
"loss": 10.09680461883545,
"step": 132
},
{
"epoch": 0.36239782016348776,
"grad_norm": 39.75,
"learning_rate": 1.8862445177516622e-05,
"loss": 9.972148895263672,
"step": 133
},
{
"epoch": 0.3651226158038147,
"grad_norm": 44.5,
"learning_rate": 1.8841891200732706e-05,
"loss": 9.76202392578125,
"step": 134
},
{
"epoch": 0.3678474114441417,
"grad_norm": 60.75,
"learning_rate": 1.8821164598427148e-05,
"loss": 8.579317092895508,
"step": 135
},
{
"epoch": 0.37057220708446864,
"grad_norm": 46.0,
"learning_rate": 1.8800265775257772e-05,
"loss": 9.23803424835205,
"step": 136
},
{
"epoch": 0.37329700272479566,
"grad_norm": 41.25,
"learning_rate": 1.877919513924478e-05,
"loss": 9.676480293273926,
"step": 137
},
{
"epoch": 0.3760217983651226,
"grad_norm": 52.0,
"learning_rate": 1.8757953101762786e-05,
"loss": 10.324712753295898,
"step": 138
},
{
"epoch": 0.3787465940054496,
"grad_norm": 42.75,
"learning_rate": 1.8736540077532773e-05,
"loss": 9.265958786010742,
"step": 139
},
{
"epoch": 0.3814713896457766,
"grad_norm": 60.75,
"learning_rate": 1.8714956484613996e-05,
"loss": 8.837886810302734,
"step": 140
},
{
"epoch": 0.38419618528610355,
"grad_norm": 56.75,
"learning_rate": 1.869320274439583e-05,
"loss": 10.104880332946777,
"step": 141
},
{
"epoch": 0.3869209809264305,
"grad_norm": 54.75,
"learning_rate": 1.8671279281589528e-05,
"loss": 8.19149398803711,
"step": 142
},
{
"epoch": 0.3896457765667575,
"grad_norm": 149.0,
"learning_rate": 1.8649186524219956e-05,
"loss": 8.385530471801758,
"step": 143
},
{
"epoch": 0.3923705722070845,
"grad_norm": 61.75,
"learning_rate": 1.86269249036172e-05,
"loss": 8.006965637207031,
"step": 144
},
{
"epoch": 0.39509536784741145,
"grad_norm": 142.0,
"learning_rate": 1.8604494854408176e-05,
"loss": 7.986896514892578,
"step": 145
},
{
"epoch": 0.3978201634877384,
"grad_norm": 62.75,
"learning_rate": 1.858189681450813e-05,
"loss": 8.249701499938965,
"step": 146
},
{
"epoch": 0.40054495912806537,
"grad_norm": 117.0,
"learning_rate": 1.8559131225112085e-05,
"loss": 10.889843940734863,
"step": 147
},
{
"epoch": 0.4032697547683924,
"grad_norm": 73.5,
"learning_rate": 1.853619853068624e-05,
"loss": 9.433284759521484,
"step": 148
},
{
"epoch": 0.40599455040871935,
"grad_norm": 55.75,
"learning_rate": 1.851309917895928e-05,
"loss": 9.875059127807617,
"step": 149
},
{
"epoch": 0.4087193460490463,
"grad_norm": 47.75,
"learning_rate": 1.8489833620913644e-05,
"loss": 9.996278762817383,
"step": 150
},
{
"epoch": 0.4114441416893733,
"grad_norm": 97.5,
"learning_rate": 1.846640231077671e-05,
"loss": 8.902766227722168,
"step": 151
},
{
"epoch": 0.4141689373297003,
"grad_norm": 59.5,
"learning_rate": 1.8442805706011936e-05,
"loss": 9.887271881103516,
"step": 152
},
{
"epoch": 0.41689373297002724,
"grad_norm": 110.0,
"learning_rate": 1.841904426730994e-05,
"loss": 7.887417793273926,
"step": 153
},
{
"epoch": 0.4196185286103542,
"grad_norm": 74.0,
"learning_rate": 1.839511845857946e-05,
"loss": 8.48383903503418,
"step": 154
},
{
"epoch": 0.4223433242506812,
"grad_norm": 72.5,
"learning_rate": 1.837102874693836e-05,
"loss": 7.879996299743652,
"step": 155
},
{
"epoch": 0.4250681198910082,
"grad_norm": 249.0,
"learning_rate": 1.8346775602704464e-05,
"loss": 8.765167236328125,
"step": 156
},
{
"epoch": 0.42779291553133514,
"grad_norm": 93.5,
"learning_rate": 1.832235949938638e-05,
"loss": 7.563960075378418,
"step": 157
},
{
"epoch": 0.4305177111716621,
"grad_norm": 247.0,
"learning_rate": 1.8297780913674286e-05,
"loss": 10.175262451171875,
"step": 158
},
{
"epoch": 0.4332425068119891,
"grad_norm": 101.0,
"learning_rate": 1.8273040325430575e-05,
"loss": 9.55147647857666,
"step": 159
},
{
"epoch": 0.4359673024523161,
"grad_norm": 113.5,
"learning_rate": 1.824813821768053e-05,
"loss": 10.279187202453613,
"step": 160
},
{
"epoch": 0.43869209809264303,
"grad_norm": 57.75,
"learning_rate": 1.822307507660287e-05,
"loss": 7.288547515869141,
"step": 161
},
{
"epoch": 0.44141689373297005,
"grad_norm": 62.75,
"learning_rate": 1.8197851391520265e-05,
"loss": 8.8092679977417,
"step": 162
},
{
"epoch": 0.444141689373297,
"grad_norm": 62.25,
"learning_rate": 1.817246765488978e-05,
"loss": 9.367995262145996,
"step": 163
},
{
"epoch": 0.44686648501362397,
"grad_norm": 87.5,
"learning_rate": 1.814692436229326e-05,
"loss": 9.748262405395508,
"step": 164
},
{
"epoch": 0.44959128065395093,
"grad_norm": 228.0,
"learning_rate": 1.8121222012427666e-05,
"loss": 8.287470817565918,
"step": 165
},
{
"epoch": 0.45231607629427795,
"grad_norm": 115.0,
"learning_rate": 1.809536110709531e-05,
"loss": 6.930819988250732,
"step": 166
},
{
"epoch": 0.4550408719346049,
"grad_norm": 74.5,
"learning_rate": 1.8069342151194105e-05,
"loss": 8.564351081848145,
"step": 167
},
{
"epoch": 0.45776566757493187,
"grad_norm": 73.5,
"learning_rate": 1.804316565270765e-05,
"loss": 8.866043090820312,
"step": 168
},
{
"epoch": 0.4604904632152589,
"grad_norm": 59.0,
"learning_rate": 1.801683212269536e-05,
"loss": 8.809003829956055,
"step": 169
},
{
"epoch": 0.46321525885558584,
"grad_norm": 62.25,
"learning_rate": 1.799034207528247e-05,
"loss": 8.33181381225586,
"step": 170
},
{
"epoch": 0.4659400544959128,
"grad_norm": 47.5,
"learning_rate": 1.796369602764999e-05,
"loss": 8.698205947875977,
"step": 171
},
{
"epoch": 0.46866485013623976,
"grad_norm": 53.5,
"learning_rate": 1.7936894500024614e-05,
"loss": 6.74378776550293,
"step": 172
},
{
"epoch": 0.4713896457765668,
"grad_norm": 388.0,
"learning_rate": 1.790993801566858e-05,
"loss": 9.079641342163086,
"step": 173
},
{
"epoch": 0.47411444141689374,
"grad_norm": 77.0,
"learning_rate": 1.788282710086942e-05,
"loss": 9.122142791748047,
"step": 174
},
{
"epoch": 0.4768392370572207,
"grad_norm": 588.0,
"learning_rate": 1.785556228492972e-05,
"loss": 7.489294528961182,
"step": 175
},
{
"epoch": 0.47956403269754766,
"grad_norm": 52.25,
"learning_rate": 1.7828144100156754e-05,
"loss": 9.699580192565918,
"step": 176
},
{
"epoch": 0.4822888283378747,
"grad_norm": 68.0,
"learning_rate": 1.7800573081852124e-05,
"loss": 8.443748474121094,
"step": 177
},
{
"epoch": 0.48501362397820164,
"grad_norm": 59.25,
"learning_rate": 1.7772849768301273e-05,
"loss": 8.995189666748047,
"step": 178
},
{
"epoch": 0.4877384196185286,
"grad_norm": 70.5,
"learning_rate": 1.7744974700763018e-05,
"loss": 9.576644897460938,
"step": 179
},
{
"epoch": 0.4904632152588556,
"grad_norm": 57.25,
"learning_rate": 1.771694842345894e-05,
"loss": 9.02816390991211,
"step": 180
},
{
"epoch": 0.49318801089918257,
"grad_norm": 70.5,
"learning_rate": 1.7688771483562788e-05,
"loss": 7.724009990692139,
"step": 181
},
{
"epoch": 0.49591280653950953,
"grad_norm": 47.75,
"learning_rate": 1.766044443118978e-05,
"loss": 8.413365364074707,
"step": 182
},
{
"epoch": 0.4986376021798365,
"grad_norm": 55.5,
"learning_rate": 1.7631967819385883e-05,
"loss": 7.405316352844238,
"step": 183
},
{
"epoch": 0.5013623978201635,
"grad_norm": 81.5,
"learning_rate": 1.760334220411699e-05,
"loss": 10.031204223632812,
"step": 184
},
{
"epoch": 0.5040871934604905,
"grad_norm": 86.0,
"learning_rate": 1.7574568144258078e-05,
"loss": 8.520164489746094,
"step": 185
},
{
"epoch": 0.5068119891008175,
"grad_norm": 100.5,
"learning_rate": 1.7545646201582304e-05,
"loss": 9.04115104675293,
"step": 186
},
{
"epoch": 0.5095367847411444,
"grad_norm": 71.5,
"learning_rate": 1.751657694075002e-05,
"loss": 7.026916027069092,
"step": 187
},
{
"epoch": 0.5122615803814714,
"grad_norm": 41.5,
"learning_rate": 1.7487360929297765e-05,
"loss": 8.15958023071289,
"step": 188
},
{
"epoch": 0.5149863760217984,
"grad_norm": 51.75,
"learning_rate": 1.7457998737627183e-05,
"loss": 7.412751197814941,
"step": 189
},
{
"epoch": 0.5177111716621253,
"grad_norm": 100.0,
"learning_rate": 1.7428490938993864e-05,
"loss": 8.202327728271484,
"step": 190
},
{
"epoch": 0.5204359673024523,
"grad_norm": 288.0,
"learning_rate": 1.7398838109496187e-05,
"loss": 10.258552551269531,
"step": 191
},
{
"epoch": 0.5231607629427792,
"grad_norm": 131.0,
"learning_rate": 1.7369040828064046e-05,
"loss": 8.944820404052734,
"step": 192
},
{
"epoch": 0.5258855585831063,
"grad_norm": 67.5,
"learning_rate": 1.7339099676447564e-05,
"loss": 8.260212898254395,
"step": 193
},
{
"epoch": 0.5286103542234333,
"grad_norm": 60.0,
"learning_rate": 1.7309015239205717e-05,
"loss": 7.93248176574707,
"step": 194
},
{
"epoch": 0.5313351498637602,
"grad_norm": 98.0,
"learning_rate": 1.7278788103694944e-05,
"loss": 8.025236129760742,
"step": 195
},
{
"epoch": 0.5340599455040872,
"grad_norm": 57.5,
"learning_rate": 1.7248418860057653e-05,
"loss": 8.118586540222168,
"step": 196
},
{
"epoch": 0.5367847411444142,
"grad_norm": 50.75,
"learning_rate": 1.7217908101210725e-05,
"loss": 8.220122337341309,
"step": 197
},
{
"epoch": 0.5395095367847411,
"grad_norm": 60.75,
"learning_rate": 1.7187256422833928e-05,
"loss": 8.953962326049805,
"step": 198
},
{
"epoch": 0.5422343324250681,
"grad_norm": 36.25,
"learning_rate": 1.7156464423358277e-05,
"loss": 8.30789566040039,
"step": 199
},
{
"epoch": 0.5449591280653951,
"grad_norm": 44.0,
"learning_rate": 1.7125532703954366e-05,
"loss": 8.25827407836914,
"step": 200
},
{
"epoch": 0.547683923705722,
"grad_norm": 43.0,
"learning_rate": 1.7094461868520625e-05,
"loss": 9.002181053161621,
"step": 201
},
{
"epoch": 0.5504087193460491,
"grad_norm": 45.25,
"learning_rate": 1.706325252367152e-05,
"loss": 8.918088912963867,
"step": 202
},
{
"epoch": 0.553133514986376,
"grad_norm": 60.25,
"learning_rate": 1.703190527872574e-05,
"loss": 8.397649765014648,
"step": 203
},
{
"epoch": 0.555858310626703,
"grad_norm": 59.5,
"learning_rate": 1.7000420745694256e-05,
"loss": 8.530458450317383,
"step": 204
},
{
"epoch": 0.55858310626703,
"grad_norm": 336.0,
"learning_rate": 1.6968799539268408e-05,
"loss": 11.207830429077148,
"step": 205
},
{
"epoch": 0.5613079019073569,
"grad_norm": 51.75,
"learning_rate": 1.6937042276807893e-05,
"loss": 7.851648807525635,
"step": 206
},
{
"epoch": 0.5640326975476839,
"grad_norm": 46.75,
"learning_rate": 1.6905149578328705e-05,
"loss": 8.705131530761719,
"step": 207
},
{
"epoch": 0.5667574931880109,
"grad_norm": 46.25,
"learning_rate": 1.6873122066491046e-05,
"loss": 8.54839038848877,
"step": 208
},
{
"epoch": 0.5694822888283378,
"grad_norm": 45.5,
"learning_rate": 1.6840960366587153e-05,
"loss": 9.251383781433105,
"step": 209
},
{
"epoch": 0.5722070844686649,
"grad_norm": 48.25,
"learning_rate": 1.6808665106529096e-05,
"loss": 8.868568420410156,
"step": 210
},
{
"epoch": 0.5749318801089919,
"grad_norm": 53.5,
"learning_rate": 1.6776236916836518e-05,
"loss": 7.161401271820068,
"step": 211
},
{
"epoch": 0.5776566757493188,
"grad_norm": 155.0,
"learning_rate": 1.674367643062434e-05,
"loss": 8.508842468261719,
"step": 212
},
{
"epoch": 0.5803814713896458,
"grad_norm": 52.5,
"learning_rate": 1.671098428359037e-05,
"loss": 7.233345985412598,
"step": 213
},
{
"epoch": 0.5831062670299727,
"grad_norm": 56.5,
"learning_rate": 1.6678161114002916e-05,
"loss": 9.324285507202148,
"step": 214
},
{
"epoch": 0.5858310626702997,
"grad_norm": 43.0,
"learning_rate": 1.664520756268832e-05,
"loss": 9.344024658203125,
"step": 215
},
{
"epoch": 0.5885558583106267,
"grad_norm": 59.0,
"learning_rate": 1.661212427301844e-05,
"loss": 9.818446159362793,
"step": 216
},
{
"epoch": 0.5912806539509536,
"grad_norm": 63.75,
"learning_rate": 1.6578911890898095e-05,
"loss": 9.475311279296875,
"step": 217
},
{
"epoch": 0.5940054495912807,
"grad_norm": 54.25,
"learning_rate": 1.6545571064752454e-05,
"loss": 8.2189302444458,
"step": 218
},
{
"epoch": 0.5967302452316077,
"grad_norm": 88.5,
"learning_rate": 1.6512102445514376e-05,
"loss": 6.581336975097656,
"step": 219
},
{
"epoch": 0.5994550408719346,
"grad_norm": 167.0,
"learning_rate": 1.6478506686611698e-05,
"loss": 7.07267951965332,
"step": 220
},
{
"epoch": 0.6021798365122616,
"grad_norm": 123.0,
"learning_rate": 1.644478444395448e-05,
"loss": 8.498826026916504,
"step": 221
},
{
"epoch": 0.6049046321525886,
"grad_norm": 93.0,
"learning_rate": 1.64109363759222e-05,
"loss": 8.827077865600586,
"step": 222
},
{
"epoch": 0.6076294277929155,
"grad_norm": 94.5,
"learning_rate": 1.6376963143350915e-05,
"loss": 7.177187919616699,
"step": 223
},
{
"epoch": 0.6103542234332425,
"grad_norm": 62.0,
"learning_rate": 1.6342865409520318e-05,
"loss": 7.975133419036865,
"step": 224
},
{
"epoch": 0.6130790190735694,
"grad_norm": 70.0,
"learning_rate": 1.630864384014083e-05,
"loss": 8.900384902954102,
"step": 225
},
{
"epoch": 0.6158038147138964,
"grad_norm": 60.25,
"learning_rate": 1.627429910334058e-05,
"loss": 7.536081314086914,
"step": 226
},
{
"epoch": 0.6185286103542235,
"grad_norm": 58.25,
"learning_rate": 1.6239831869652384e-05,
"loss": 7.778719902038574,
"step": 227
},
{
"epoch": 0.6212534059945504,
"grad_norm": 78.5,
"learning_rate": 1.620524281200062e-05,
"loss": 9.885849952697754,
"step": 228
},
{
"epoch": 0.6239782016348774,
"grad_norm": 65.5,
"learning_rate": 1.6170532605688115e-05,
"loss": 8.622196197509766,
"step": 229
},
{
"epoch": 0.6267029972752044,
"grad_norm": 77.5,
"learning_rate": 1.6135701928382952e-05,
"loss": 10.154062271118164,
"step": 230
},
{
"epoch": 0.6294277929155313,
"grad_norm": 78.5,
"learning_rate": 1.6100751460105244e-05,
"loss": 9.700957298278809,
"step": 231
},
{
"epoch": 0.6321525885558583,
"grad_norm": 106.5,
"learning_rate": 1.6065681883213854e-05,
"loss": 6.72788667678833,
"step": 232
},
{
"epoch": 0.6348773841961853,
"grad_norm": 91.0,
"learning_rate": 1.6030493882393076e-05,
"loss": 8.668846130371094,
"step": 233
},
{
"epoch": 0.6376021798365122,
"grad_norm": 106.0,
"learning_rate": 1.599518814463925e-05,
"loss": 8.67601203918457,
"step": 234
},
{
"epoch": 0.6403269754768393,
"grad_norm": 121.0,
"learning_rate": 1.595976535924739e-05,
"loss": 9.827007293701172,
"step": 235
},
{
"epoch": 0.6430517711171662,
"grad_norm": 588.0,
"learning_rate": 1.5924226217797677e-05,
"loss": 9.226984024047852,
"step": 236
},
{
"epoch": 0.6457765667574932,
"grad_norm": 64.0,
"learning_rate": 1.5888571414141997e-05,
"loss": 8.387163162231445,
"step": 237
},
{
"epoch": 0.6485013623978202,
"grad_norm": 118.0,
"learning_rate": 1.585280164439037e-05,
"loss": 8.13496208190918,
"step": 238
},
{
"epoch": 0.6512261580381471,
"grad_norm": 81.5,
"learning_rate": 1.581691760689737e-05,
"loss": 9.463398933410645,
"step": 239
},
{
"epoch": 0.6539509536784741,
"grad_norm": 63.0,
"learning_rate": 1.5780920002248484e-05,
"loss": 8.129623413085938,
"step": 240
},
{
"epoch": 0.6566757493188011,
"grad_norm": 76.5,
"learning_rate": 1.574480953324645e-05,
"loss": 8.715579986572266,
"step": 241
},
{
"epoch": 0.659400544959128,
"grad_norm": 56.5,
"learning_rate": 1.5708586904897518e-05,
"loss": 7.299056053161621,
"step": 242
},
{
"epoch": 0.662125340599455,
"grad_norm": 54.25,
"learning_rate": 1.5672252824397683e-05,
"loss": 7.277167320251465,
"step": 243
},
{
"epoch": 0.6648501362397821,
"grad_norm": 55.0,
"learning_rate": 1.56358080011189e-05,
"loss": 7.999053955078125,
"step": 244
},
{
"epoch": 0.667574931880109,
"grad_norm": 78.5,
"learning_rate": 1.559925314659521e-05,
"loss": 7.08182954788208,
"step": 245
},
{
"epoch": 0.670299727520436,
"grad_norm": 68.0,
"learning_rate": 1.556258897450887e-05,
"loss": 7.931889533996582,
"step": 246
},
{
"epoch": 0.6730245231607629,
"grad_norm": 84.5,
"learning_rate": 1.552581620067641e-05,
"loss": 9.470329284667969,
"step": 247
},
{
"epoch": 0.6757493188010899,
"grad_norm": 228.0,
"learning_rate": 1.5488935543034644e-05,
"loss": 8.88481616973877,
"step": 248
},
{
"epoch": 0.6784741144414169,
"grad_norm": 137.0,
"learning_rate": 1.5451947721626676e-05,
"loss": 7.863848686218262,
"step": 249
},
{
"epoch": 0.6811989100817438,
"grad_norm": 47.75,
"learning_rate": 1.5414853458587834e-05,
"loss": 8.018930435180664,
"step": 250
},
{
"epoch": 0.6839237057220708,
"grad_norm": 53.25,
"learning_rate": 1.5377653478131557e-05,
"loss": 8.23213005065918,
"step": 251
},
{
"epoch": 0.6866485013623979,
"grad_norm": 143.0,
"learning_rate": 1.534034850653528e-05,
"loss": 6.6429572105407715,
"step": 252
},
{
"epoch": 0.6893732970027248,
"grad_norm": 320.0,
"learning_rate": 1.5302939272126243e-05,
"loss": 8.471845626831055,
"step": 253
},
{
"epoch": 0.6920980926430518,
"grad_norm": 56.25,
"learning_rate": 1.5265426505267265e-05,
"loss": 9.73794937133789,
"step": 254
},
{
"epoch": 0.6948228882833788,
"grad_norm": 136.0,
"learning_rate": 1.5227810938342493e-05,
"loss": 7.138307571411133,
"step": 255
},
{
"epoch": 0.6975476839237057,
"grad_norm": 81.5,
"learning_rate": 1.5190093305743103e-05,
"loss": 7.136944770812988,
"step": 256
},
{
"epoch": 0.7002724795640327,
"grad_norm": 65.5,
"learning_rate": 1.5152274343852953e-05,
"loss": 9.011394500732422,
"step": 257
},
{
"epoch": 0.7029972752043597,
"grad_norm": 88.5,
"learning_rate": 1.5114354791034225e-05,
"loss": 8.616395950317383,
"step": 258
},
{
"epoch": 0.7057220708446866,
"grad_norm": 97.0,
"learning_rate": 1.5076335387612987e-05,
"loss": 8.706403732299805,
"step": 259
},
{
"epoch": 0.7084468664850136,
"grad_norm": 53.25,
"learning_rate": 1.5038216875864758e-05,
"loss": 9.25063419342041,
"step": 260
},
{
"epoch": 0.7111716621253406,
"grad_norm": 55.0,
"learning_rate": 1.5000000000000002e-05,
"loss": 7.913337230682373,
"step": 261
},
{
"epoch": 0.7138964577656676,
"grad_norm": 51.5,
"learning_rate": 1.4961685506149608e-05,
"loss": 7.538181304931641,
"step": 262
},
{
"epoch": 0.7166212534059946,
"grad_norm": 50.25,
"learning_rate": 1.492327414235032e-05,
"loss": 9.69723892211914,
"step": 263
},
{
"epoch": 0.7193460490463215,
"grad_norm": 70.0,
"learning_rate": 1.4884766658530126e-05,
"loss": 9.871997833251953,
"step": 264
},
{
"epoch": 0.7220708446866485,
"grad_norm": 47.5,
"learning_rate": 1.4846163806493628e-05,
"loss": 9.25969123840332,
"step": 265
},
{
"epoch": 0.7247956403269755,
"grad_norm": 272.0,
"learning_rate": 1.4807466339907358e-05,
"loss": 8.33348274230957,
"step": 266
},
{
"epoch": 0.7275204359673024,
"grad_norm": 1504.0,
"learning_rate": 1.4768675014285063e-05,
"loss": 9.026241302490234,
"step": 267
},
{
"epoch": 0.7302452316076294,
"grad_norm": 168.0,
"learning_rate": 1.4729790586972957e-05,
"loss": 7.3931403160095215,
"step": 268
},
{
"epoch": 0.7329700272479565,
"grad_norm": 103.5,
"learning_rate": 1.469081381713493e-05,
"loss": 8.33013916015625,
"step": 269
},
{
"epoch": 0.7356948228882834,
"grad_norm": 105.0,
"learning_rate": 1.465174546573774e-05,
"loss": 7.207721710205078,
"step": 270
},
{
"epoch": 0.7384196185286104,
"grad_norm": 73.0,
"learning_rate": 1.4612586295536136e-05,
"loss": 7.389970779418945,
"step": 271
},
{
"epoch": 0.7411444141689373,
"grad_norm": 60.0,
"learning_rate": 1.457333707105798e-05,
"loss": 7.272927761077881,
"step": 272
},
{
"epoch": 0.7438692098092643,
"grad_norm": 73.0,
"learning_rate": 1.4533998558589319e-05,
"loss": 7.018216133117676,
"step": 273
},
{
"epoch": 0.7465940054495913,
"grad_norm": 75.0,
"learning_rate": 1.4494571526159427e-05,
"loss": 8.663573265075684,
"step": 274
},
{
"epoch": 0.7493188010899182,
"grad_norm": 71.5,
"learning_rate": 1.4455056743525793e-05,
"loss": 7.3470258712768555,
"step": 275
},
{
"epoch": 0.7520435967302452,
"grad_norm": 61.5,
"learning_rate": 1.4415454982159121e-05,
"loss": 6.416076183319092,
"step": 276
},
{
"epoch": 0.7547683923705722,
"grad_norm": 45.25,
"learning_rate": 1.437576701522824e-05,
"loss": 7.636316299438477,
"step": 277
},
{
"epoch": 0.7574931880108992,
"grad_norm": 75.5,
"learning_rate": 1.433599361758503e-05,
"loss": 7.864310264587402,
"step": 278
},
{
"epoch": 0.7602179836512262,
"grad_norm": 86.5,
"learning_rate": 1.429613556574928e-05,
"loss": 6.941385746002197,
"step": 279
},
{
"epoch": 0.7629427792915532,
"grad_norm": 83.5,
"learning_rate": 1.425619363789354e-05,
"loss": 9.594515800476074,
"step": 280
},
{
"epoch": 0.7656675749318801,
"grad_norm": 71.5,
"learning_rate": 1.4216168613827918e-05,
"loss": 7.111987113952637,
"step": 281
},
{
"epoch": 0.7683923705722071,
"grad_norm": 63.5,
"learning_rate": 1.4176061274984858e-05,
"loss": 7.9280242919921875,
"step": 282
},
{
"epoch": 0.771117166212534,
"grad_norm": 112.5,
"learning_rate": 1.4135872404403881e-05,
"loss": 6.869634628295898,
"step": 283
},
{
"epoch": 0.773841961852861,
"grad_norm": 46.0,
"learning_rate": 1.4095602786716312e-05,
"loss": 9.552452087402344,
"step": 284
},
{
"epoch": 0.776566757493188,
"grad_norm": 131.0,
"learning_rate": 1.405525320812994e-05,
"loss": 6.404139041900635,
"step": 285
},
{
"epoch": 0.779291553133515,
"grad_norm": 79.5,
"learning_rate": 1.401482445641368e-05,
"loss": 8.160365104675293,
"step": 286
},
{
"epoch": 0.782016348773842,
"grad_norm": 57.5,
"learning_rate": 1.39743173208822e-05,
"loss": 8.898149490356445,
"step": 287
},
{
"epoch": 0.784741144414169,
"grad_norm": 73.5,
"learning_rate": 1.3933732592380485e-05,
"loss": 8.005890846252441,
"step": 288
},
{
"epoch": 0.7874659400544959,
"grad_norm": 74.5,
"learning_rate": 1.3893071063268431e-05,
"loss": 7.600529193878174,
"step": 289
},
{
"epoch": 0.7901907356948229,
"grad_norm": 143.0,
"learning_rate": 1.3852333527405346e-05,
"loss": 8.386226654052734,
"step": 290
},
{
"epoch": 0.7929155313351499,
"grad_norm": 64.0,
"learning_rate": 1.3811520780134471e-05,
"loss": 8.49716567993164,
"step": 291
},
{
"epoch": 0.7956403269754768,
"grad_norm": 64.5,
"learning_rate": 1.3770633618267444e-05,
"loss": 6.701350212097168,
"step": 292
},
{
"epoch": 0.7983651226158038,
"grad_norm": 106.5,
"learning_rate": 1.3729672840068732e-05,
"loss": 11.180490493774414,
"step": 293
},
{
"epoch": 0.8010899182561307,
"grad_norm": 157.0,
"learning_rate": 1.3688639245240078e-05,
"loss": 7.627303123474121,
"step": 294
},
{
"epoch": 0.8038147138964578,
"grad_norm": 46.0,
"learning_rate": 1.364753363490485e-05,
"loss": 6.636218547821045,
"step": 295
},
{
"epoch": 0.8065395095367848,
"grad_norm": 75.5,
"learning_rate": 1.3606356811592427e-05,
"loss": 9.643957138061523,
"step": 296
},
{
"epoch": 0.8092643051771117,
"grad_norm": 110.5,
"learning_rate": 1.3565109579222511e-05,
"loss": 8.615606307983398,
"step": 297
},
{
"epoch": 0.8119891008174387,
"grad_norm": 76.0,
"learning_rate": 1.3523792743089457e-05,
"loss": 7.899325370788574,
"step": 298
},
{
"epoch": 0.8147138964577657,
"grad_norm": 63.25,
"learning_rate": 1.3482407109846527e-05,
"loss": 8.536578178405762,
"step": 299
},
{
"epoch": 0.8174386920980926,
"grad_norm": 94.5,
"learning_rate": 1.3440953487490145e-05,
"loss": 8.565481185913086,
"step": 300
},
{
"epoch": 0.8201634877384196,
"grad_norm": 55.75,
"learning_rate": 1.3399432685344143e-05,
"loss": 7.926910877227783,
"step": 301
},
{
"epoch": 0.8228882833787466,
"grad_norm": 57.25,
"learning_rate": 1.3357845514043927e-05,
"loss": 8.481698989868164,
"step": 302
},
{
"epoch": 0.8256130790190735,
"grad_norm": 53.5,
"learning_rate": 1.331619278552068e-05,
"loss": 7.775982856750488,
"step": 303
},
{
"epoch": 0.8283378746594006,
"grad_norm": 178.0,
"learning_rate": 1.327447531298549e-05,
"loss": 7.186558723449707,
"step": 304
},
{
"epoch": 0.8310626702997275,
"grad_norm": 42.25,
"learning_rate": 1.3232693910913486e-05,
"loss": 7.542721271514893,
"step": 305
},
{
"epoch": 0.8337874659400545,
"grad_norm": 58.25,
"learning_rate": 1.3190849395027926e-05,
"loss": 8.921777725219727,
"step": 306
},
{
"epoch": 0.8365122615803815,
"grad_norm": 51.0,
"learning_rate": 1.3148942582284286e-05,
"loss": 6.938803195953369,
"step": 307
},
{
"epoch": 0.8392370572207084,
"grad_norm": 69.0,
"learning_rate": 1.3106974290854286e-05,
"loss": 6.134668350219727,
"step": 308
},
{
"epoch": 0.8419618528610354,
"grad_norm": 54.0,
"learning_rate": 1.306494534010995e-05,
"loss": 8.931164741516113,
"step": 309
},
{
"epoch": 0.8446866485013624,
"grad_norm": 87.5,
"learning_rate": 1.3022856550607572e-05,
"loss": 9.727581024169922,
"step": 310
},
{
"epoch": 0.8474114441416893,
"grad_norm": 392.0,
"learning_rate": 1.298070874407173e-05,
"loss": 9.479921340942383,
"step": 311
},
{
"epoch": 0.8501362397820164,
"grad_norm": 78.0,
"learning_rate": 1.2938502743379212e-05,
"loss": 7.574161052703857,
"step": 312
},
{
"epoch": 0.8528610354223434,
"grad_norm": 98.5,
"learning_rate": 1.2896239372542971e-05,
"loss": 6.311966896057129,
"step": 313
},
{
"epoch": 0.8555858310626703,
"grad_norm": 89.5,
"learning_rate": 1.2853919456696038e-05,
"loss": 7.752774238586426,
"step": 314
},
{
"epoch": 0.8583106267029973,
"grad_norm": 128.0,
"learning_rate": 1.2811543822075396e-05,
"loss": 8.187653541564941,
"step": 315
},
{
"epoch": 0.8610354223433242,
"grad_norm": 352.0,
"learning_rate": 1.2769113296005868e-05,
"loss": 8.210296630859375,
"step": 316
},
{
"epoch": 0.8637602179836512,
"grad_norm": 146.0,
"learning_rate": 1.2726628706883947e-05,
"loss": 8.545489311218262,
"step": 317
},
{
"epoch": 0.8664850136239782,
"grad_norm": 52.5,
"learning_rate": 1.2684090884161636e-05,
"loss": 7.061089515686035,
"step": 318
},
{
"epoch": 0.8692098092643051,
"grad_norm": 129.0,
"learning_rate": 1.2641500658330248e-05,
"loss": 6.323040008544922,
"step": 319
},
{
"epoch": 0.8719346049046321,
"grad_norm": 54.75,
"learning_rate": 1.2598858860904193e-05,
"loss": 8.90510368347168,
"step": 320
},
{
"epoch": 0.8746594005449592,
"grad_norm": 57.25,
"learning_rate": 1.2556166324404747e-05,
"loss": 7.848992347717285,
"step": 321
},
{
"epoch": 0.8773841961852861,
"grad_norm": 125.5,
"learning_rate": 1.2513423882343797e-05,
"loss": 9.337868690490723,
"step": 322
},
{
"epoch": 0.8801089918256131,
"grad_norm": 71.5,
"learning_rate": 1.247063236920755e-05,
"loss": 7.9343061447143555,
"step": 323
},
{
"epoch": 0.8828337874659401,
"grad_norm": 51.75,
"learning_rate": 1.242779262044028e-05,
"loss": 7.241304397583008,
"step": 324
},
{
"epoch": 0.885558583106267,
"grad_norm": 62.0,
"learning_rate": 1.2384905472427975e-05,
"loss": 8.429121017456055,
"step": 325
},
{
"epoch": 0.888283378746594,
"grad_norm": 53.5,
"learning_rate": 1.2341971762482043e-05,
"loss": 7.462927341461182,
"step": 326
},
{
"epoch": 0.8910081743869209,
"grad_norm": 83.0,
"learning_rate": 1.2298992328822937e-05,
"loss": 6.1312575340271,
"step": 327
},
{
"epoch": 0.8937329700272479,
"grad_norm": 133.0,
"learning_rate": 1.2255968010563799e-05,
"loss": 7.932398796081543,
"step": 328
},
{
"epoch": 0.896457765667575,
"grad_norm": 115.5,
"learning_rate": 1.2212899647694094e-05,
"loss": 9.538064956665039,
"step": 329
},
{
"epoch": 0.8991825613079019,
"grad_norm": 108.0,
"learning_rate": 1.2169788081063181e-05,
"loss": 8.497495651245117,
"step": 330
},
{
"epoch": 0.9019073569482289,
"grad_norm": 160.0,
"learning_rate": 1.2126634152363924e-05,
"loss": 8.135430335998535,
"step": 331
},
{
"epoch": 0.9046321525885559,
"grad_norm": 47.5,
"learning_rate": 1.2083438704116235e-05,
"loss": 8.22928524017334,
"step": 332
},
{
"epoch": 0.9073569482288828,
"grad_norm": 60.0,
"learning_rate": 1.2040202579650649e-05,
"loss": 8.291242599487305,
"step": 333
},
{
"epoch": 0.9100817438692098,
"grad_norm": 54.0,
"learning_rate": 1.1996926623091839e-05,
"loss": 7.9037251472473145,
"step": 334
},
{
"epoch": 0.9128065395095368,
"grad_norm": 154.0,
"learning_rate": 1.1953611679342144e-05,
"loss": 7.170064449310303,
"step": 335
},
{
"epoch": 0.9155313351498637,
"grad_norm": 206.0,
"learning_rate": 1.1910258594065079e-05,
"loss": 8.21196460723877,
"step": 336
},
{
"epoch": 0.9182561307901907,
"grad_norm": 140.0,
"learning_rate": 1.1866868213668813e-05,
"loss": 8.195924758911133,
"step": 337
},
{
"epoch": 0.9209809264305178,
"grad_norm": 75.5,
"learning_rate": 1.1823441385289656e-05,
"loss": 8.583342552185059,
"step": 338
},
{
"epoch": 0.9237057220708447,
"grad_norm": 69.0,
"learning_rate": 1.1779978956775507e-05,
"loss": 7.357507228851318,
"step": 339
},
{
"epoch": 0.9264305177111717,
"grad_norm": 40.25,
"learning_rate": 1.1736481776669307e-05,
"loss": 9.229513168334961,
"step": 340
},
{
"epoch": 0.9291553133514986,
"grad_norm": 146.0,
"learning_rate": 1.169295069419248e-05,
"loss": 6.533137321472168,
"step": 341
},
{
"epoch": 0.9318801089918256,
"grad_norm": 61.5,
"learning_rate": 1.1649386559228342e-05,
"loss": 7.507099628448486,
"step": 342
},
{
"epoch": 0.9346049046321526,
"grad_norm": 80.0,
"learning_rate": 1.1605790222305516e-05,
"loss": 7.3725810050964355,
"step": 343
},
{
"epoch": 0.9373297002724795,
"grad_norm": 81.0,
"learning_rate": 1.1562162534581318e-05,
"loss": 9.221755981445312,
"step": 344
},
{
"epoch": 0.9400544959128065,
"grad_norm": 334.0,
"learning_rate": 1.1518504347825146e-05,
"loss": 6.867805004119873,
"step": 345
},
{
"epoch": 0.9427792915531336,
"grad_norm": 97.5,
"learning_rate": 1.1474816514401851e-05,
"loss": 8.168418884277344,
"step": 346
},
{
"epoch": 0.9455040871934605,
"grad_norm": 116.5,
"learning_rate": 1.143109988725509e-05,
"loss": 8.540360450744629,
"step": 347
},
{
"epoch": 0.9482288828337875,
"grad_norm": 50.0,
"learning_rate": 1.1387355319890685e-05,
"loss": 5.956089973449707,
"step": 348
},
{
"epoch": 0.9509536784741145,
"grad_norm": 65.5,
"learning_rate": 1.1343583666359938e-05,
"loss": 7.404401779174805,
"step": 349
},
{
"epoch": 0.9536784741144414,
"grad_norm": 79.0,
"learning_rate": 1.1299785781242982e-05,
"loss": 6.322681427001953,
"step": 350
},
{
"epoch": 0.9564032697547684,
"grad_norm": 60.0,
"learning_rate": 1.1255962519632082e-05,
"loss": 7.368110656738281,
"step": 351
},
{
"epoch": 0.9591280653950953,
"grad_norm": 118.5,
"learning_rate": 1.1212114737114941e-05,
"loss": 7.17164945602417,
"step": 352
},
{
"epoch": 0.9618528610354223,
"grad_norm": 52.75,
"learning_rate": 1.1168243289758001e-05,
"loss": 7.229589462280273,
"step": 353
},
{
"epoch": 0.9645776566757494,
"grad_norm": 63.75,
"learning_rate": 1.1124349034089724e-05,
"loss": 7.301548957824707,
"step": 354
},
{
"epoch": 0.9673024523160763,
"grad_norm": 53.5,
"learning_rate": 1.1080432827083874e-05,
"loss": 7.822205543518066,
"step": 355
},
{
"epoch": 0.9700272479564033,
"grad_norm": 165.0,
"learning_rate": 1.1036495526142784e-05,
"loss": 7.196988105773926,
"step": 356
},
{
"epoch": 0.9727520435967303,
"grad_norm": 109.0,
"learning_rate": 1.0992537989080618e-05,
"loss": 7.927482604980469,
"step": 357
},
{
"epoch": 0.9754768392370572,
"grad_norm": 63.25,
"learning_rate": 1.0948561074106618e-05,
"loss": 8.574819564819336,
"step": 358
},
{
"epoch": 0.9782016348773842,
"grad_norm": 219.0,
"learning_rate": 1.0904565639808358e-05,
"loss": 8.466644287109375,
"step": 359
},
{
"epoch": 0.9809264305177112,
"grad_norm": 62.75,
"learning_rate": 1.086055254513497e-05,
"loss": 8.004752159118652,
"step": 360
},
{
"epoch": 0.9836512261580381,
"grad_norm": 672.0,
"learning_rate": 1.0816522649380383e-05,
"loss": 8.849076271057129,
"step": 361
},
{
"epoch": 0.9863760217983651,
"grad_norm": 80.0,
"learning_rate": 1.0772476812166545e-05,
"loss": 7.5196661949157715,
"step": 362
},
{
"epoch": 0.989100817438692,
"grad_norm": 60.5,
"learning_rate": 1.0728415893426636e-05,
"loss": 7.944910049438477,
"step": 363
},
{
"epoch": 0.9918256130790191,
"grad_norm": 676.0,
"learning_rate": 1.0684340753388283e-05,
"loss": 8.418794631958008,
"step": 364
},
{
"epoch": 0.9945504087193461,
"grad_norm": 46.75,
"learning_rate": 1.064025225255676e-05,
"loss": 7.800658226013184,
"step": 365
},
{
"epoch": 0.997275204359673,
"grad_norm": 50.25,
"learning_rate": 1.05961512516982e-05,
"loss": 8.47831916809082,
"step": 366
},
{
"epoch": 1.0,
"grad_norm": 103.0,
"learning_rate": 1.0552038611822774e-05,
"loss": 8.185615539550781,
"step": 367
}
],
"logging_steps": 1,
"max_steps": 734,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.422627732599603e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}