| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500.0, | |
| "global_step": 3750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005333333333333334, | |
| "grad_norm": 161.0, | |
| "learning_rate": 1.7699115044247788e-07, | |
| "loss": 3.0240771770477295, | |
| "step": 1, | |
| "token_acc": 0.6939782823297137 | |
| }, | |
| { | |
| "epoch": 0.005333333333333333, | |
| "grad_norm": 87.0, | |
| "learning_rate": 1.769911504424779e-06, | |
| "loss": 3.004603491889106, | |
| "step": 10, | |
| "token_acc": 0.7050248481501933 | |
| }, | |
| { | |
| "epoch": 0.010666666666666666, | |
| "grad_norm": 68.0, | |
| "learning_rate": 3.539823008849558e-06, | |
| "loss": 2.3852081298828125, | |
| "step": 20, | |
| "token_acc": 0.7311625136503525 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 18.875, | |
| "learning_rate": 5.309734513274337e-06, | |
| "loss": 1.2473203659057617, | |
| "step": 30, | |
| "token_acc": 0.7757027912983013 | |
| }, | |
| { | |
| "epoch": 0.021333333333333333, | |
| "grad_norm": 9.875, | |
| "learning_rate": 7.079646017699116e-06, | |
| "loss": 0.6646689414978028, | |
| "step": 40, | |
| "token_acc": 0.8279005251164173 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 11.0625, | |
| "learning_rate": 8.849557522123895e-06, | |
| "loss": 0.5340797901153564, | |
| "step": 50, | |
| "token_acc": 0.8438339802926247 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 9.8125, | |
| "learning_rate": 1.0619469026548675e-05, | |
| "loss": 0.4082949638366699, | |
| "step": 60, | |
| "token_acc": 0.8741820345032718 | |
| }, | |
| { | |
| "epoch": 0.037333333333333336, | |
| "grad_norm": 7.875, | |
| "learning_rate": 1.2389380530973452e-05, | |
| "loss": 0.3634414911270142, | |
| "step": 70, | |
| "token_acc": 0.8817332538262771 | |
| }, | |
| { | |
| "epoch": 0.042666666666666665, | |
| "grad_norm": 11.0, | |
| "learning_rate": 1.4159292035398232e-05, | |
| "loss": 0.3220649480819702, | |
| "step": 80, | |
| "token_acc": 0.892123629112662 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 13.0625, | |
| "learning_rate": 1.592920353982301e-05, | |
| "loss": 0.2919419288635254, | |
| "step": 90, | |
| "token_acc": 0.9004367679174111 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 7.96875, | |
| "learning_rate": 1.769911504424779e-05, | |
| "loss": 0.26521849632263184, | |
| "step": 100, | |
| "token_acc": 0.9107744107744108 | |
| }, | |
| { | |
| "epoch": 0.058666666666666666, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 1.946902654867257e-05, | |
| "loss": 0.2592456340789795, | |
| "step": 110, | |
| "token_acc": 0.9109942448898591 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 1.9999817199278942e-05, | |
| "loss": 0.2438103199005127, | |
| "step": 120, | |
| "token_acc": 0.9153969526864475 | |
| }, | |
| { | |
| "epoch": 0.06933333333333333, | |
| "grad_norm": 8.125, | |
| "learning_rate": 1.9998921864897123e-05, | |
| "loss": 0.23656888008117677, | |
| "step": 130, | |
| "token_acc": 0.9230464494404278 | |
| }, | |
| { | |
| "epoch": 0.07466666666666667, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 1.9997280487931355e-05, | |
| "loss": 0.2291872978210449, | |
| "step": 140, | |
| "token_acc": 0.9177441814203302 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 10.6875, | |
| "learning_rate": 1.9994893190848556e-05, | |
| "loss": 0.2181375503540039, | |
| "step": 150, | |
| "token_acc": 0.922854002198461 | |
| }, | |
| { | |
| "epoch": 0.08533333333333333, | |
| "grad_norm": 9.5, | |
| "learning_rate": 1.999176015177046e-05, | |
| "loss": 0.22175416946411133, | |
| "step": 160, | |
| "token_acc": 0.9226727471002281 | |
| }, | |
| { | |
| "epoch": 0.09066666666666667, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 1.998788160446032e-05, | |
| "loss": 0.2052232265472412, | |
| "step": 170, | |
| "token_acc": 0.9251984126984127 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 7.375, | |
| "learning_rate": 1.9983257838305487e-05, | |
| "loss": 0.18906147480010987, | |
| "step": 180, | |
| "token_acc": 0.931604473918638 | |
| }, | |
| { | |
| "epoch": 0.10133333333333333, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.9977889198295794e-05, | |
| "loss": 0.18642866611480713, | |
| "step": 190, | |
| "token_acc": 0.9307892628205128 | |
| }, | |
| { | |
| "epoch": 0.10666666666666667, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 1.9971776084997844e-05, | |
| "loss": 0.19384456872940065, | |
| "step": 200, | |
| "token_acc": 0.9313900456077732 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.9964918954525086e-05, | |
| "loss": 0.1800537109375, | |
| "step": 210, | |
| "token_acc": 0.9341019779345989 | |
| }, | |
| { | |
| "epoch": 0.11733333333333333, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 1.995731831850382e-05, | |
| "loss": 0.17389063835144042, | |
| "step": 220, | |
| "token_acc": 0.9366336633663367 | |
| }, | |
| { | |
| "epoch": 0.12266666666666666, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 1.9948974744035002e-05, | |
| "loss": 0.18609018325805665, | |
| "step": 230, | |
| "token_acc": 0.931784032855855 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 7.53125, | |
| "learning_rate": 1.9939888853651933e-05, | |
| "loss": 0.17286394834518432, | |
| "step": 240, | |
| "token_acc": 0.9370755093887335 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 1.9930061325273812e-05, | |
| "loss": 0.17738854885101318, | |
| "step": 250, | |
| "token_acc": 0.9339761881334252 | |
| }, | |
| { | |
| "epoch": 0.13866666666666666, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.9919492892155164e-05, | |
| "loss": 0.16766983270645142, | |
| "step": 260, | |
| "token_acc": 0.9368178632221889 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 7.78125, | |
| "learning_rate": 1.990818434283112e-05, | |
| "loss": 0.1735897421836853, | |
| "step": 270, | |
| "token_acc": 0.9367403865311815 | |
| }, | |
| { | |
| "epoch": 0.14933333333333335, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.989613652105858e-05, | |
| "loss": 0.16657640933990478, | |
| "step": 280, | |
| "token_acc": 0.935840489586418 | |
| }, | |
| { | |
| "epoch": 0.15466666666666667, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 1.9883350325753276e-05, | |
| "loss": 0.16750943660736084, | |
| "step": 290, | |
| "token_acc": 0.9378531073446328 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.875, | |
| "learning_rate": 1.9869826710922676e-05, | |
| "loss": 0.15869977474212646, | |
| "step": 300, | |
| "token_acc": 0.9420132371826534 | |
| }, | |
| { | |
| "epoch": 0.16533333333333333, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 1.9855566685594817e-05, | |
| "loss": 0.16268906593322754, | |
| "step": 310, | |
| "token_acc": 0.9363013017986684 | |
| }, | |
| { | |
| "epoch": 0.17066666666666666, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.984057131374303e-05, | |
| "loss": 0.1463162899017334, | |
| "step": 320, | |
| "token_acc": 0.9472634832020735 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 6.375, | |
| "learning_rate": 1.982484171420654e-05, | |
| "loss": 0.16353240013122558, | |
| "step": 330, | |
| "token_acc": 0.9401197604790419 | |
| }, | |
| { | |
| "epoch": 0.18133333333333335, | |
| "grad_norm": 7.40625, | |
| "learning_rate": 1.980837906060698e-05, | |
| "loss": 0.16135379076004028, | |
| "step": 340, | |
| "token_acc": 0.9402807988926241 | |
| }, | |
| { | |
| "epoch": 0.18666666666666668, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.979118458126085e-05, | |
| "loss": 0.15137779712677002, | |
| "step": 350, | |
| "token_acc": 0.9432553509208561 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.9773259559087838e-05, | |
| "loss": 0.15068085193634034, | |
| "step": 360, | |
| "token_acc": 0.93996003996004 | |
| }, | |
| { | |
| "epoch": 0.19733333333333333, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 1.975460533151513e-05, | |
| "loss": 0.15066895484924317, | |
| "step": 370, | |
| "token_acc": 0.9436843148919294 | |
| }, | |
| { | |
| "epoch": 0.20266666666666666, | |
| "grad_norm": 6.15625, | |
| "learning_rate": 1.9735223290377595e-05, | |
| "loss": 0.14623867273330687, | |
| "step": 380, | |
| "token_acc": 0.9447365810100208 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.971511488181395e-05, | |
| "loss": 0.15090563297271728, | |
| "step": 390, | |
| "token_acc": 0.941380678436818 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 1.9694281606158864e-05, | |
| "loss": 0.151963472366333, | |
| "step": 400, | |
| "token_acc": 0.9443946188340807 | |
| }, | |
| { | |
| "epoch": 0.21866666666666668, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.9672725017831003e-05, | |
| "loss": 0.14691494703292846, | |
| "step": 410, | |
| "token_acc": 0.9460314322427598 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.9650446725217056e-05, | |
| "loss": 0.15266220569610595, | |
| "step": 420, | |
| "token_acc": 0.9427021696252466 | |
| }, | |
| { | |
| "epoch": 0.22933333333333333, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 1.9627448390551736e-05, | |
| "loss": 0.1481661319732666, | |
| "step": 430, | |
| "token_acc": 0.9421021377672208 | |
| }, | |
| { | |
| "epoch": 0.23466666666666666, | |
| "grad_norm": 6.34375, | |
| "learning_rate": 1.9603731729793746e-05, | |
| "loss": 0.13831231594085694, | |
| "step": 440, | |
| "token_acc": 0.9506001388751116 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.9579298512497758e-05, | |
| "loss": 0.14514718055725098, | |
| "step": 450, | |
| "token_acc": 0.9452938840349484 | |
| }, | |
| { | |
| "epoch": 0.24533333333333332, | |
| "grad_norm": 6.375, | |
| "learning_rate": 1.9554150561682374e-05, | |
| "loss": 0.14355964660644532, | |
| "step": 460, | |
| "token_acc": 0.946384409931744 | |
| }, | |
| { | |
| "epoch": 0.25066666666666665, | |
| "grad_norm": 6.84375, | |
| "learning_rate": 1.9528289753694108e-05, | |
| "loss": 0.14325175285339356, | |
| "step": 470, | |
| "token_acc": 0.9461576598909271 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.9501718018067395e-05, | |
| "loss": 0.1453178644180298, | |
| "step": 480, | |
| "token_acc": 0.9461149151533195 | |
| }, | |
| { | |
| "epoch": 0.2613333333333333, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.9474437337380608e-05, | |
| "loss": 0.14968839883804322, | |
| "step": 490, | |
| "token_acc": 0.9441117764471058 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.944644974710816e-05, | |
| "loss": 0.1389085054397583, | |
| "step": 500, | |
| "token_acc": 0.9453148388384393 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.9417757335468596e-05, | |
| "loss": 0.14659820795059203, | |
| "step": 510, | |
| "token_acc": 0.9444941808415398 | |
| }, | |
| { | |
| "epoch": 0.2773333333333333, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.9388362243268823e-05, | |
| "loss": 0.13635566234588622, | |
| "step": 520, | |
| "token_acc": 0.9480803660234732 | |
| }, | |
| { | |
| "epoch": 0.2826666666666667, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 1.935826666374435e-05, | |
| "loss": 0.12984724044799806, | |
| "step": 530, | |
| "token_acc": 0.9493569933207058 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.9327472842395666e-05, | |
| "loss": 0.13808577060699462, | |
| "step": 540, | |
| "token_acc": 0.9476841380666732 | |
| }, | |
| { | |
| "epoch": 0.29333333333333333, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.9295983076820687e-05, | |
| "loss": 0.13398956060409545, | |
| "step": 550, | |
| "token_acc": 0.9459513362584763 | |
| }, | |
| { | |
| "epoch": 0.2986666666666667, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 1.9263799716543335e-05, | |
| "loss": 0.13375203609466552, | |
| "step": 560, | |
| "token_acc": 0.9468718967229395 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.9230925162838223e-05, | |
| "loss": 0.13835164308547973, | |
| "step": 570, | |
| "token_acc": 0.9464178806625424 | |
| }, | |
| { | |
| "epoch": 0.30933333333333335, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.9197361868551498e-05, | |
| "loss": 0.12979514598846437, | |
| "step": 580, | |
| "token_acc": 0.951837140019861 | |
| }, | |
| { | |
| "epoch": 0.31466666666666665, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.916311233791783e-05, | |
| "loss": 0.13770484924316406, | |
| "step": 590, | |
| "token_acc": 0.9471496437054632 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.912817912637357e-05, | |
| "loss": 0.1396735668182373, | |
| "step": 600, | |
| "token_acc": 0.9465330820355123 | |
| }, | |
| { | |
| "epoch": 0.3253333333333333, | |
| "grad_norm": 7.15625, | |
| "learning_rate": 1.909256484036606e-05, | |
| "loss": 0.13082077503204345, | |
| "step": 610, | |
| "token_acc": 0.951573133445113 | |
| }, | |
| { | |
| "epoch": 0.33066666666666666, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.9056272137159187e-05, | |
| "loss": 0.12859055995941163, | |
| "step": 620, | |
| "token_acc": 0.9530718431058636 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.901930372463511e-05, | |
| "loss": 0.13520824909210205, | |
| "step": 630, | |
| "token_acc": 0.9505831191935165 | |
| }, | |
| { | |
| "epoch": 0.3413333333333333, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.8981662361092206e-05, | |
| "loss": 0.1334831714630127, | |
| "step": 640, | |
| "token_acc": 0.9487128712871287 | |
| }, | |
| { | |
| "epoch": 0.3466666666666667, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 1.8943350855039288e-05, | |
| "loss": 0.1388801097869873, | |
| "step": 650, | |
| "token_acc": 0.9456208370613381 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.8904372064986033e-05, | |
| "loss": 0.13052648305892944, | |
| "step": 660, | |
| "token_acc": 0.9508406253072461 | |
| }, | |
| { | |
| "epoch": 0.35733333333333334, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.886472889922972e-05, | |
| "loss": 0.14282100200653075, | |
| "step": 670, | |
| "token_acc": 0.9462568170550322 | |
| }, | |
| { | |
| "epoch": 0.3626666666666667, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.8824424315638233e-05, | |
| "loss": 0.12628421783447266, | |
| "step": 680, | |
| "token_acc": 0.9525287931897847 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.8783461321429356e-05, | |
| "loss": 0.12385869026184082, | |
| "step": 690, | |
| "token_acc": 0.9543329021987862 | |
| }, | |
| { | |
| "epoch": 0.37333333333333335, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.874184297294641e-05, | |
| "loss": 0.13400530815124512, | |
| "step": 700, | |
| "token_acc": 0.9489755321265169 | |
| }, | |
| { | |
| "epoch": 0.37866666666666665, | |
| "grad_norm": 6.5625, | |
| "learning_rate": 1.8699572375430206e-05, | |
| "loss": 0.12999823093414306, | |
| "step": 710, | |
| "token_acc": 0.9485221186272565 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.8656652682787356e-05, | |
| "loss": 0.13085007667541504, | |
| "step": 720, | |
| "token_acc": 0.9504074736632876 | |
| }, | |
| { | |
| "epoch": 0.3893333333333333, | |
| "grad_norm": 5.125, | |
| "learning_rate": 1.861308709735496e-05, | |
| "loss": 0.12334835529327393, | |
| "step": 730, | |
| "token_acc": 0.9541530217326585 | |
| }, | |
| { | |
| "epoch": 0.39466666666666667, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.856887886966166e-05, | |
| "loss": 0.1365646243095398, | |
| "step": 740, | |
| "token_acc": 0.9485771342985522 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 1.8524031298185114e-05, | |
| "loss": 0.12420816421508789, | |
| "step": 750, | |
| "token_acc": 0.9519659304743984 | |
| }, | |
| { | |
| "epoch": 0.4053333333333333, | |
| "grad_norm": 6.25, | |
| "learning_rate": 1.8478547729105898e-05, | |
| "loss": 0.13191494941711426, | |
| "step": 760, | |
| "token_acc": 0.9475917883932097 | |
| }, | |
| { | |
| "epoch": 0.4106666666666667, | |
| "grad_norm": 5.5, | |
| "learning_rate": 1.8432431556057832e-05, | |
| "loss": 0.12565431594848633, | |
| "step": 770, | |
| "token_acc": 0.9515683566778458 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.838568621987478e-05, | |
| "loss": 0.12868111133575438, | |
| "step": 780, | |
| "token_acc": 0.9523903790953182 | |
| }, | |
| { | |
| "epoch": 0.42133333333333334, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.8338315208333904e-05, | |
| "loss": 0.1298436164855957, | |
| "step": 790, | |
| "token_acc": 0.9512583308465135 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.8290322055895454e-05, | |
| "loss": 0.12684075832366942, | |
| "step": 800, | |
| "token_acc": 0.9475461951122591 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.8241710343439042e-05, | |
| "loss": 0.12810778617858887, | |
| "step": 810, | |
| "token_acc": 0.9511163568407593 | |
| }, | |
| { | |
| "epoch": 0.43733333333333335, | |
| "grad_norm": 6.15625, | |
| "learning_rate": 1.8192483697996473e-05, | |
| "loss": 0.12917327880859375, | |
| "step": 820, | |
| "token_acc": 0.9512437810945273 | |
| }, | |
| { | |
| "epoch": 0.44266666666666665, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.814264579248111e-05, | |
| "loss": 0.12338850498199463, | |
| "step": 830, | |
| "token_acc": 0.9531187922129519 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 1.809220034541384e-05, | |
| "loss": 0.12673957347869874, | |
| "step": 840, | |
| "token_acc": 0.9499057633171313 | |
| }, | |
| { | |
| "epoch": 0.4533333333333333, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.8041151120645622e-05, | |
| "loss": 0.11919513940811158, | |
| "step": 850, | |
| "token_acc": 0.9537009438648782 | |
| }, | |
| { | |
| "epoch": 0.45866666666666667, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.7989501927076663e-05, | |
| "loss": 0.1332385301589966, | |
| "step": 860, | |
| "token_acc": 0.9504950495049505 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.793725661837223e-05, | |
| "loss": 0.13603968620300294, | |
| "step": 870, | |
| "token_acc": 0.9469282087025789 | |
| }, | |
| { | |
| "epoch": 0.4693333333333333, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 1.7884419092675104e-05, | |
| "loss": 0.12130333185195923, | |
| "step": 880, | |
| "token_acc": 0.954468802698145 | |
| }, | |
| { | |
| "epoch": 0.4746666666666667, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.7830993292314736e-05, | |
| "loss": 0.125826632976532, | |
| "step": 890, | |
| "token_acc": 0.951788026695886 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.7776983203513113e-05, | |
| "loss": 0.13028650283813475, | |
| "step": 900, | |
| "token_acc": 0.9483915531872903 | |
| }, | |
| { | |
| "epoch": 0.48533333333333334, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.7722392856087326e-05, | |
| "loss": 0.12998759746551514, | |
| "step": 910, | |
| "token_acc": 0.9507042253521126 | |
| }, | |
| { | |
| "epoch": 0.49066666666666664, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.7667226323148894e-05, | |
| "loss": 0.12416449785232545, | |
| "step": 920, | |
| "token_acc": 0.952191235059761 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "grad_norm": 6.25, | |
| "learning_rate": 1.7611487720799868e-05, | |
| "loss": 0.1253748655319214, | |
| "step": 930, | |
| "token_acc": 0.9519059845941141 | |
| }, | |
| { | |
| "epoch": 0.5013333333333333, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.7555181207825712e-05, | |
| "loss": 0.11640918254852295, | |
| "step": 940, | |
| "token_acc": 0.9551645292772641 | |
| }, | |
| { | |
| "epoch": 0.5066666666666667, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.749831098538501e-05, | |
| "loss": 0.11529660224914551, | |
| "step": 950, | |
| "token_acc": 0.9572463049300665 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.744088129669601e-05, | |
| "loss": 0.1184117078781128, | |
| "step": 960, | |
| "token_acc": 0.9557610100407595 | |
| }, | |
| { | |
| "epoch": 0.5173333333333333, | |
| "grad_norm": 5.875, | |
| "learning_rate": 1.7382896426720025e-05, | |
| "loss": 0.11719763278961182, | |
| "step": 970, | |
| "token_acc": 0.9543790202869866 | |
| }, | |
| { | |
| "epoch": 0.5226666666666666, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.732436070184172e-05, | |
| "loss": 0.12645375728607178, | |
| "step": 980, | |
| "token_acc": 0.9505854336177814 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.726527848954631e-05, | |
| "loss": 0.12238850593566894, | |
| "step": 990, | |
| "token_acc": 0.951927842204381 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.72056541980937e-05, | |
| "loss": 0.12163641452789306, | |
| "step": 1000, | |
| "token_acc": 0.9520103761348897 | |
| }, | |
| { | |
| "epoch": 0.5386666666666666, | |
| "grad_norm": 5.125, | |
| "learning_rate": 1.7145492276189565e-05, | |
| "loss": 0.11958187818527222, | |
| "step": 1010, | |
| "token_acc": 0.9516354208216993 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.7084797212653427e-05, | |
| "loss": 0.12016124725341797, | |
| "step": 1020, | |
| "token_acc": 0.9542204568023833 | |
| }, | |
| { | |
| "epoch": 0.5493333333333333, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.7023573536083734e-05, | |
| "loss": 0.11870989799499512, | |
| "step": 1030, | |
| "token_acc": 0.953724716329551 | |
| }, | |
| { | |
| "epoch": 0.5546666666666666, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.6961825814519976e-05, | |
| "loss": 0.11139537096023559, | |
| "step": 1040, | |
| "token_acc": 0.9583539420318528 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.6899558655101832e-05, | |
| "loss": 0.11470913887023926, | |
| "step": 1050, | |
| "token_acc": 0.9555929186035012 | |
| }, | |
| { | |
| "epoch": 0.5653333333333334, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.683677670372544e-05, | |
| "loss": 0.11613589525222778, | |
| "step": 1060, | |
| "token_acc": 0.954287985690152 | |
| }, | |
| { | |
| "epoch": 0.5706666666666667, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.6773484644696764e-05, | |
| "loss": 0.120987868309021, | |
| "step": 1070, | |
| "token_acc": 0.9521691866785256 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.6709687200382057e-05, | |
| "loss": 0.1105571985244751, | |
| "step": 1080, | |
| "token_acc": 0.9579882247280711 | |
| }, | |
| { | |
| "epoch": 0.5813333333333334, | |
| "grad_norm": 5.5, | |
| "learning_rate": 1.6645389130855547e-05, | |
| "loss": 0.11375106573104858, | |
| "step": 1090, | |
| "token_acc": 0.9569710821822518 | |
| }, | |
| { | |
| "epoch": 0.5866666666666667, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.658059523354425e-05, | |
| "loss": 0.11751453876495362, | |
| "step": 1100, | |
| "token_acc": 0.9549486693910096 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.6515310342870038e-05, | |
| "loss": 0.11175121068954467, | |
| "step": 1110, | |
| "token_acc": 0.9574026487448112 | |
| }, | |
| { | |
| "epoch": 0.5973333333333334, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.6449539329888934e-05, | |
| "loss": 0.11051352024078369, | |
| "step": 1120, | |
| "token_acc": 0.9592908082408875 | |
| }, | |
| { | |
| "epoch": 0.6026666666666667, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.638328710192766e-05, | |
| "loss": 0.11559228897094727, | |
| "step": 1130, | |
| "token_acc": 0.9572303437376531 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.63165586022175e-05, | |
| "loss": 0.12151663303375244, | |
| "step": 1140, | |
| "token_acc": 0.9510008963250672 | |
| }, | |
| { | |
| "epoch": 0.6133333333333333, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.6249358809525457e-05, | |
| "loss": 0.10959932804107667, | |
| "step": 1150, | |
| "token_acc": 0.9576421800947867 | |
| }, | |
| { | |
| "epoch": 0.6186666666666667, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.6181692737782806e-05, | |
| "loss": 0.11154863834381104, | |
| "step": 1160, | |
| "token_acc": 0.9568188570862632 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.6113565435710975e-05, | |
| "loss": 0.11755884885787964, | |
| "step": 1170, | |
| "token_acc": 0.9563193343898574 | |
| }, | |
| { | |
| "epoch": 0.6293333333333333, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.6044981986444827e-05, | |
| "loss": 0.11262714862823486, | |
| "step": 1180, | |
| "token_acc": 0.9568939771030364 | |
| }, | |
| { | |
| "epoch": 0.6346666666666667, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.597594750715344e-05, | |
| "loss": 0.10623650550842285, | |
| "step": 1190, | |
| "token_acc": 0.9600519324877659 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 1.590646714865828e-05, | |
| "loss": 0.11796576976776123, | |
| "step": 1200, | |
| "token_acc": 0.954192391953794 | |
| }, | |
| { | |
| "epoch": 0.6453333333333333, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.5836546095048873e-05, | |
| "loss": 0.10432027578353882, | |
| "step": 1210, | |
| "token_acc": 0.9588485507963201 | |
| }, | |
| { | |
| "epoch": 0.6506666666666666, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.5766189563296027e-05, | |
| "loss": 0.11256073713302613, | |
| "step": 1220, | |
| "token_acc": 0.9537848605577689 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.5695402802862586e-05, | |
| "loss": 0.1090101957321167, | |
| "step": 1230, | |
| "token_acc": 0.9566379566379566 | |
| }, | |
| { | |
| "epoch": 0.6613333333333333, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.5624191095311736e-05, | |
| "loss": 0.1086958885192871, | |
| "step": 1240, | |
| "token_acc": 0.9592020850040096 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.5552559753912952e-05, | |
| "loss": 0.11115623712539673, | |
| "step": 1250, | |
| "token_acc": 0.9561159650516283 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.5480514123245557e-05, | |
| "loss": 0.1095876932144165, | |
| "step": 1260, | |
| "token_acc": 0.9578319244157135 | |
| }, | |
| { | |
| "epoch": 0.6773333333333333, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 1.540805957879994e-05, | |
| "loss": 0.11510846614837647, | |
| "step": 1270, | |
| "token_acc": 0.9544681276893826 | |
| }, | |
| { | |
| "epoch": 0.6826666666666666, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.5335201526576505e-05, | |
| "loss": 0.10857385396957397, | |
| "step": 1280, | |
| "token_acc": 0.9567288606589917 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.5261945402682292e-05, | |
| "loss": 0.1099466323852539, | |
| "step": 1290, | |
| "token_acc": 0.9570320270539089 | |
| }, | |
| { | |
| "epoch": 0.6933333333333334, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.5188296672925378e-05, | |
| "loss": 0.10625450611114502, | |
| "step": 1300, | |
| "token_acc": 0.9592585249801745 | |
| }, | |
| { | |
| "epoch": 0.6986666666666667, | |
| "grad_norm": 6.71875, | |
| "learning_rate": 1.511426083240708e-05, | |
| "loss": 0.10511682033538819, | |
| "step": 1310, | |
| "token_acc": 0.9581711091145053 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.503984340511193e-05, | |
| "loss": 0.10603854656219483, | |
| "step": 1320, | |
| "token_acc": 0.959593949044586 | |
| }, | |
| { | |
| "epoch": 0.7093333333333334, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.496504994349554e-05, | |
| "loss": 0.10640466213226318, | |
| "step": 1330, | |
| "token_acc": 0.9608292634306788 | |
| }, | |
| { | |
| "epoch": 0.7146666666666667, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.4889886028070295e-05, | |
| "loss": 0.10628764629364014, | |
| "step": 1340, | |
| "token_acc": 0.9591533972900801 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.4814357266989e-05, | |
| "loss": 0.09471931457519531, | |
| "step": 1350, | |
| "token_acc": 0.96225475550244 | |
| }, | |
| { | |
| "epoch": 0.7253333333333334, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.4738469295626435e-05, | |
| "loss": 0.11037859916687012, | |
| "step": 1360, | |
| "token_acc": 0.9583333333333334 | |
| }, | |
| { | |
| "epoch": 0.7306666666666667, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.4662227776158877e-05, | |
| "loss": 0.10702688694000244, | |
| "step": 1370, | |
| "token_acc": 0.9577590480912246 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 6.125, | |
| "learning_rate": 1.4585638397141657e-05, | |
| "loss": 0.10900003910064697, | |
| "step": 1380, | |
| "token_acc": 0.9568480300187617 | |
| }, | |
| { | |
| "epoch": 0.7413333333333333, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.4508706873084691e-05, | |
| "loss": 0.09608756303787232, | |
| "step": 1390, | |
| "token_acc": 0.9632034632034632 | |
| }, | |
| { | |
| "epoch": 0.7466666666666667, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.4431438944026135e-05, | |
| "loss": 0.10125172138214111, | |
| "step": 1400, | |
| "token_acc": 0.9609785084678617 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.4353840375104093e-05, | |
| "loss": 0.09823362827301026, | |
| "step": 1410, | |
| "token_acc": 0.9601625210583689 | |
| }, | |
| { | |
| "epoch": 0.7573333333333333, | |
| "grad_norm": 6.875, | |
| "learning_rate": 1.4275916956126475e-05, | |
| "loss": 0.10848079919815064, | |
| "step": 1420, | |
| "token_acc": 0.9589259075087021 | |
| }, | |
| { | |
| "epoch": 0.7626666666666667, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.4197674501138993e-05, | |
| "loss": 0.09750932455062866, | |
| "step": 1430, | |
| "token_acc": 0.9610363924050633 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.411911884799138e-05, | |
| "loss": 0.1041105031967163, | |
| "step": 1440, | |
| "token_acc": 0.9594903951428287 | |
| }, | |
| { | |
| "epoch": 0.7733333333333333, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.4040255857901797e-05, | |
| "loss": 0.10584063529968261, | |
| "step": 1450, | |
| "token_acc": 0.9586686537506209 | |
| }, | |
| { | |
| "epoch": 0.7786666666666666, | |
| "grad_norm": 5.125, | |
| "learning_rate": 1.3961091415019525e-05, | |
| "loss": 0.0976940393447876, | |
| "step": 1460, | |
| "token_acc": 0.9595679318204341 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "grad_norm": 11.8125, | |
| "learning_rate": 1.3881631425985935e-05, | |
| "loss": 0.09462392330169678, | |
| "step": 1470, | |
| "token_acc": 0.962046696472926 | |
| }, | |
| { | |
| "epoch": 0.7893333333333333, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.3801881819493772e-05, | |
| "loss": 0.10079967975616455, | |
| "step": 1480, | |
| "token_acc": 0.9625494071146246 | |
| }, | |
| { | |
| "epoch": 0.7946666666666666, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.3721848545844812e-05, | |
| "loss": 0.10591773986816407, | |
| "step": 1490, | |
| "token_acc": 0.9585358595377442 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.3641537576505882e-05, | |
| "loss": 0.09992707967758178, | |
| "step": 1500, | |
| "token_acc": 0.9617372291790897 | |
| }, | |
| { | |
| "epoch": 0.8053333333333333, | |
| "grad_norm": 6.125, | |
| "learning_rate": 1.3560954903663333e-05, | |
| "loss": 0.10718950033187866, | |
| "step": 1510, | |
| "token_acc": 0.9582632776184353 | |
| }, | |
| { | |
| "epoch": 0.8106666666666666, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.3480106539775935e-05, | |
| "loss": 0.104136061668396, | |
| "step": 1520, | |
| "token_acc": 0.9613248710829037 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 9.5, | |
| "learning_rate": 1.3398998517126275e-05, | |
| "loss": 0.10529080629348755, | |
| "step": 1530, | |
| "token_acc": 0.956207272366987 | |
| }, | |
| { | |
| "epoch": 0.8213333333333334, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.3317636887370695e-05, | |
| "loss": 0.10142601728439331, | |
| "step": 1540, | |
| "token_acc": 0.961668657905217 | |
| }, | |
| { | |
| "epoch": 0.8266666666666667, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.3236027721087724e-05, | |
| "loss": 0.09501729011535645, | |
| "step": 1550, | |
| "token_acc": 0.9636110558759197 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 5.875, | |
| "learning_rate": 1.3154177107325174e-05, | |
| "loss": 0.09613993763923645, | |
| "step": 1560, | |
| "token_acc": 0.9610415228326264 | |
| }, | |
| { | |
| "epoch": 0.8373333333333334, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.307209115314581e-05, | |
| "loss": 0.10287705659866334, | |
| "step": 1570, | |
| "token_acc": 0.9613574932425668 | |
| }, | |
| { | |
| "epoch": 0.8426666666666667, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.2989775983171688e-05, | |
| "loss": 0.09376062750816345, | |
| "step": 1580, | |
| "token_acc": 0.9648067823343849 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.2907237739127174e-05, | |
| "loss": 0.09870033264160157, | |
| "step": 1590, | |
| "token_acc": 0.9628045748383889 | |
| }, | |
| { | |
| "epoch": 0.8533333333333334, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.2824482579380715e-05, | |
| "loss": 0.09684454202651978, | |
| "step": 1600, | |
| "token_acc": 0.9618441971383148 | |
| }, | |
| { | |
| "epoch": 0.8586666666666667, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 1.274151667848533e-05, | |
| "loss": 0.09628376960754395, | |
| "step": 1610, | |
| "token_acc": 0.9608938547486033 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.2658346226717917e-05, | |
| "loss": 0.09724725484848022, | |
| "step": 1620, | |
| "token_acc": 0.9619226584907526 | |
| }, | |
| { | |
| "epoch": 0.8693333333333333, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.25749774296174e-05, | |
| "loss": 0.10113248825073243, | |
| "step": 1630, | |
| "token_acc": 0.9626621768842231 | |
| }, | |
| { | |
| "epoch": 0.8746666666666667, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.2491416507521692e-05, | |
| "loss": 0.10067527294158936, | |
| "step": 1640, | |
| "token_acc": 0.9598209845847837 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.2407669695103602e-05, | |
| "loss": 0.09440578818321228, | |
| "step": 1650, | |
| "token_acc": 0.9627329192546584 | |
| }, | |
| { | |
| "epoch": 0.8853333333333333, | |
| "grad_norm": 7.6875, | |
| "learning_rate": 1.2323743240905634e-05, | |
| "loss": 0.0972176194190979, | |
| "step": 1660, | |
| "token_acc": 0.9632352941176471 | |
| }, | |
| { | |
| "epoch": 0.8906666666666667, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 1.223964340687379e-05, | |
| "loss": 0.09761661887168885, | |
| "step": 1670, | |
| "token_acc": 0.9624119805613409 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 1.2155376467890341e-05, | |
| "loss": 0.10594066381454467, | |
| "step": 1680, | |
| "token_acc": 0.9594741524167243 | |
| }, | |
| { | |
| "epoch": 0.9013333333333333, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 1.207094871130563e-05, | |
| "loss": 0.09854521751403808, | |
| "step": 1690, | |
| "token_acc": 0.9625062158130283 | |
| }, | |
| { | |
| "epoch": 0.9066666666666666, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.1986366436468986e-05, | |
| "loss": 0.08949284553527832, | |
| "step": 1700, | |
| "token_acc": 0.9651726526169981 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 9.5625, | |
| "learning_rate": 1.1901635954258688e-05, | |
| "loss": 0.09419882297515869, | |
| "step": 1710, | |
| "token_acc": 0.9641434262948207 | |
| }, | |
| { | |
| "epoch": 0.9173333333333333, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.1816763586611121e-05, | |
| "loss": 0.09756133556365967, | |
| "step": 1720, | |
| "token_acc": 0.9613712704999012 | |
| }, | |
| { | |
| "epoch": 0.9226666666666666, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.1731755666049058e-05, | |
| "loss": 0.08990415334701538, | |
| "step": 1730, | |
| "token_acc": 0.9664323200316863 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.16466185352092e-05, | |
| "loss": 0.09485629200935364, | |
| "step": 1740, | |
| "token_acc": 0.9621054714554269 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.1561358546368907e-05, | |
| "loss": 0.09861080646514893, | |
| "step": 1750, | |
| "token_acc": 0.9598108747044918 | |
| }, | |
| { | |
| "epoch": 0.9386666666666666, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.1475982060972273e-05, | |
| "loss": 0.09501796960830688, | |
| "step": 1760, | |
| "token_acc": 0.9628495207983401 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "grad_norm": 6.5625, | |
| "learning_rate": 1.1390495449155461e-05, | |
| "loss": 0.09370712041854859, | |
| "step": 1770, | |
| "token_acc": 0.9624413145539906 | |
| }, | |
| { | |
| "epoch": 0.9493333333333334, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.1304905089271419e-05, | |
| "loss": 0.09164633750915527, | |
| "step": 1780, | |
| "token_acc": 0.9649820931157979 | |
| }, | |
| { | |
| "epoch": 0.9546666666666667, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.1219217367413979e-05, | |
| "loss": 0.09200198650360107, | |
| "step": 1790, | |
| "token_acc": 0.9639621702339473 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.1133438676941376e-05, | |
| "loss": 0.0913775086402893, | |
| "step": 1800, | |
| "token_acc": 0.9636019146390108 | |
| }, | |
| { | |
| "epoch": 0.9653333333333334, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.1047575417999222e-05, | |
| "loss": 0.09320381283760071, | |
| "step": 1810, | |
| "token_acc": 0.9631204271307099 | |
| }, | |
| { | |
| "epoch": 0.9706666666666667, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.0961633997042972e-05, | |
| "loss": 0.09073319435119628, | |
| "step": 1820, | |
| "token_acc": 0.9654966689867753 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.0875620826359939e-05, | |
| "loss": 0.09031926393508911, | |
| "step": 1830, | |
| "token_acc": 0.9658706467661692 | |
| }, | |
| { | |
| "epoch": 0.9813333333333333, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.0789542323590839e-05, | |
| "loss": 0.09178189039230347, | |
| "step": 1840, | |
| "token_acc": 0.9646664034741413 | |
| }, | |
| { | |
| "epoch": 0.9866666666666667, | |
| "grad_norm": 9.875, | |
| "learning_rate": 1.0703404911250963e-05, | |
| "loss": 0.0889767050743103, | |
| "step": 1850, | |
| "token_acc": 0.9654834281231615 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 1.0617215016250996e-05, | |
| "loss": 0.09213165044784546, | |
| "step": 1860, | |
| "token_acc": 0.964671737389912 | |
| }, | |
| { | |
| "epoch": 0.9973333333333333, | |
| "grad_norm": 5.5, | |
| "learning_rate": 1.0530979069417463e-05, | |
| "loss": 0.09125626087188721, | |
| "step": 1870, | |
| "token_acc": 0.966362373486803 | |
| }, | |
| { | |
| "epoch": 1.0026666666666666, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 1.044470350501292e-05, | |
| "loss": 0.07592885494232178, | |
| "step": 1880, | |
| "token_acc": 0.9721772561715905 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 3.984375, | |
| "learning_rate": 1.0358394760255891e-05, | |
| "loss": 0.0530848503112793, | |
| "step": 1890, | |
| "token_acc": 0.9835562159484893 | |
| }, | |
| { | |
| "epoch": 1.0133333333333334, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 1.0272059274840555e-05, | |
| "loss": 0.05034524202346802, | |
| "step": 1900, | |
| "token_acc": 0.9838533927686973 | |
| }, | |
| { | |
| "epoch": 1.0186666666666666, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.0185703490456281e-05, | |
| "loss": 0.04969725012779236, | |
| "step": 1910, | |
| "token_acc": 0.9833185272924687 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 1.0099333850306979e-05, | |
| "loss": 0.04704121053218842, | |
| "step": 1920, | |
| "token_acc": 0.9846399361659685 | |
| }, | |
| { | |
| "epoch": 1.0293333333333334, | |
| "grad_norm": 3.828125, | |
| "learning_rate": 1.001295679863038e-05, | |
| "loss": 0.048529314994812014, | |
| "step": 1930, | |
| "token_acc": 0.9845605700712589 | |
| }, | |
| { | |
| "epoch": 1.0346666666666666, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 9.926578780217198e-06, | |
| "loss": 0.05159075260162353, | |
| "step": 1940, | |
| "token_acc": 0.9818701349886688 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 9.840206239930286e-06, | |
| "loss": 0.04979468882083893, | |
| "step": 1950, | |
| "token_acc": 0.9831050684794561 | |
| }, | |
| { | |
| "epoch": 1.0453333333333332, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 9.753845622223758e-06, | |
| "loss": 0.045256540179252625, | |
| "step": 1960, | |
| "token_acc": 0.9852270473924252 | |
| }, | |
| { | |
| "epoch": 1.0506666666666666, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 9.66750337066215e-06, | |
| "loss": 0.04541871249675751, | |
| "step": 1970, | |
| "token_acc": 0.9857686911204651 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 9.581185927439665e-06, | |
| "loss": 0.04687809944152832, | |
| "step": 1980, | |
| "token_acc": 0.9838100913786253 | |
| }, | |
| { | |
| "epoch": 1.0613333333333332, | |
| "grad_norm": 4.75, | |
| "learning_rate": 9.4948997328995e-06, | |
| "loss": 0.045229172706604, | |
| "step": 1990, | |
| "token_acc": 0.9848859033883236 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 9.408651225053313e-06, | |
| "loss": 0.05098391771316528, | |
| "step": 2000, | |
| "token_acc": 0.9816413615163243 | |
| }, | |
| { | |
| "epoch": 1.072, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 9.32244683910087e-06, | |
| "loss": 0.0516198992729187, | |
| "step": 2010, | |
| "token_acc": 0.9823757841282486 | |
| }, | |
| { | |
| "epoch": 1.0773333333333333, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 9.236293006949901e-06, | |
| "loss": 0.05135577917098999, | |
| "step": 2020, | |
| "token_acc": 0.9830022729518727 | |
| }, | |
| { | |
| "epoch": 1.0826666666666667, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 9.150196156736205e-06, | |
| "loss": 0.04364476501941681, | |
| "step": 2030, | |
| "token_acc": 0.9849861714737258 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 9.064162712344015e-06, | |
| "loss": 0.048701542615890506, | |
| "step": 2040, | |
| "token_acc": 0.9839112621165185 | |
| }, | |
| { | |
| "epoch": 1.0933333333333333, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 8.978199092926726e-06, | |
| "loss": 0.04445060789585113, | |
| "step": 2050, | |
| "token_acc": 0.9849736292168375 | |
| }, | |
| { | |
| "epoch": 1.0986666666666667, | |
| "grad_norm": 4.375, | |
| "learning_rate": 8.892311712427924e-06, | |
| "loss": 0.04172802269458771, | |
| "step": 2060, | |
| "token_acc": 0.9872592592592593 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 8.806506979102834e-06, | |
| "loss": 0.049462562799453734, | |
| "step": 2070, | |
| "token_acc": 0.9820827558899228 | |
| }, | |
| { | |
| "epoch": 1.1093333333333333, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 8.720791295040175e-06, | |
| "loss": 0.04976886808872223, | |
| "step": 2080, | |
| "token_acc": 0.9825401576374339 | |
| }, | |
| { | |
| "epoch": 1.1146666666666667, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 8.63517105568451e-06, | |
| "loss": 0.046266642212867734, | |
| "step": 2090, | |
| "token_acc": 0.984870958172649 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 8.549652649359053e-06, | |
| "loss": 0.04942557215690613, | |
| "step": 2100, | |
| "token_acc": 0.9834057684709601 | |
| }, | |
| { | |
| "epoch": 1.1253333333333333, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 8.46424245678901e-06, | |
| "loss": 0.04696555435657501, | |
| "step": 2110, | |
| "token_acc": 0.9832569264500698 | |
| }, | |
| { | |
| "epoch": 1.1306666666666667, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 8.37894685062551e-06, | |
| "loss": 0.047610795497894286, | |
| "step": 2120, | |
| "token_acc": 0.9848409294903759 | |
| }, | |
| { | |
| "epoch": 1.1360000000000001, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 8.293772194970137e-06, | |
| "loss": 0.0464180737733841, | |
| "step": 2130, | |
| "token_acc": 0.9837536130768464 | |
| }, | |
| { | |
| "epoch": 1.1413333333333333, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 8.208724844900078e-06, | |
| "loss": 0.0491524338722229, | |
| "step": 2140, | |
| "token_acc": 0.9825240790388243 | |
| }, | |
| { | |
| "epoch": 1.1466666666666667, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 8.123811145993943e-06, | |
| "loss": 0.04688098430633545, | |
| "step": 2150, | |
| "token_acc": 0.9841064865401807 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 8.039037433858334e-06, | |
| "loss": 0.04569154977798462, | |
| "step": 2160, | |
| "token_acc": 0.9852604322278657 | |
| }, | |
| { | |
| "epoch": 1.1573333333333333, | |
| "grad_norm": 5.0, | |
| "learning_rate": 7.95441003365512e-06, | |
| "loss": 0.04637964069843292, | |
| "step": 2170, | |
| "token_acc": 0.9827792156082023 | |
| }, | |
| { | |
| "epoch": 1.1626666666666667, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 7.869935259629486e-06, | |
| "loss": 0.04769515693187713, | |
| "step": 2180, | |
| "token_acc": 0.9834817012858555 | |
| }, | |
| { | |
| "epoch": 1.168, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 7.785619414638836e-06, | |
| "loss": 0.045441615581512454, | |
| "step": 2190, | |
| "token_acc": 0.9853899308983218 | |
| }, | |
| { | |
| "epoch": 1.1733333333333333, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 7.701468789682511e-06, | |
| "loss": 0.04217609167098999, | |
| "step": 2200, | |
| "token_acc": 0.9868120971740209 | |
| }, | |
| { | |
| "epoch": 1.1786666666666668, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 7.6174896634324135e-06, | |
| "loss": 0.04596090614795685, | |
| "step": 2210, | |
| "token_acc": 0.9836653386454183 | |
| }, | |
| { | |
| "epoch": 1.184, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 7.533688301764511e-06, | |
| "loss": 0.0406882107257843, | |
| "step": 2220, | |
| "token_acc": 0.986937880147572 | |
| }, | |
| { | |
| "epoch": 1.1893333333333334, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 7.450070957291366e-06, | |
| "loss": 0.043777698278427125, | |
| "step": 2230, | |
| "token_acc": 0.984913577779998 | |
| }, | |
| { | |
| "epoch": 1.1946666666666665, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 7.3666438688955885e-06, | |
| "loss": 0.0409196674823761, | |
| "step": 2240, | |
| "token_acc": 0.9873268493958149 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 3.703125, | |
| "learning_rate": 7.283413261264341e-06, | |
| "loss": 0.044315993785858154, | |
| "step": 2250, | |
| "token_acc": 0.9849706380013935 | |
| }, | |
| { | |
| "epoch": 1.2053333333333334, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 7.200385344424908e-06, | |
| "loss": 0.04352255165576935, | |
| "step": 2260, | |
| "token_acc": 0.9849781138081973 | |
| }, | |
| { | |
| "epoch": 1.2106666666666666, | |
| "grad_norm": 4.0, | |
| "learning_rate": 7.117566313281346e-06, | |
| "loss": 0.045627248287200925, | |
| "step": 2270, | |
| "token_acc": 0.985937967487783 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 7.03496234715227e-06, | |
| "loss": 0.043829864263534545, | |
| "step": 2280, | |
| "token_acc": 0.9855936413313463 | |
| }, | |
| { | |
| "epoch": 1.2213333333333334, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 6.952579609309793e-06, | |
| "loss": 0.03742110133171082, | |
| "step": 2290, | |
| "token_acc": 0.9889042995839112 | |
| }, | |
| { | |
| "epoch": 1.2266666666666666, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 6.870424246519682e-06, | |
| "loss": 0.04146054983139038, | |
| "step": 2300, | |
| "token_acc": 0.986350503138388 | |
| }, | |
| { | |
| "epoch": 1.232, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 6.788502388582727e-06, | |
| "loss": 0.040186125040054324, | |
| "step": 2310, | |
| "token_acc": 0.9859307359307359 | |
| }, | |
| { | |
| "epoch": 1.2373333333333334, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 6.706820147877388e-06, | |
| "loss": 0.0393997848033905, | |
| "step": 2320, | |
| "token_acc": 0.986780638107544 | |
| }, | |
| { | |
| "epoch": 1.2426666666666666, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 6.625383618903718e-06, | |
| "loss": 0.04266528785228729, | |
| "step": 2330, | |
| "token_acc": 0.9865493027395905 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 4.5, | |
| "learning_rate": 6.5441988778286625e-06, | |
| "loss": 0.03945194482803345, | |
| "step": 2340, | |
| "token_acc": 0.9867132867132867 | |
| }, | |
| { | |
| "epoch": 1.2533333333333334, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 6.463271982032695e-06, | |
| "loss": 0.04942408800125122, | |
| "step": 2350, | |
| "token_acc": 0.983040761678072 | |
| }, | |
| { | |
| "epoch": 1.2586666666666666, | |
| "grad_norm": 4.375, | |
| "learning_rate": 6.382608969657847e-06, | |
| "loss": 0.048211139440536496, | |
| "step": 2360, | |
| "token_acc": 0.9825009830908376 | |
| }, | |
| { | |
| "epoch": 1.264, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 6.302215859157208e-06, | |
| "loss": 0.04317412078380585, | |
| "step": 2370, | |
| "token_acc": 0.9849975161450572 | |
| }, | |
| { | |
| "epoch": 1.2693333333333334, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 6.22209864884587e-06, | |
| "loss": 0.041670626401901244, | |
| "step": 2380, | |
| "token_acc": 0.9856364536899456 | |
| }, | |
| { | |
| "epoch": 1.2746666666666666, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 6.142263316453376e-06, | |
| "loss": 0.047338935732841494, | |
| "step": 2390, | |
| "token_acc": 0.984057827507674 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 6.062715818677696e-06, | |
| "loss": 0.042187738418579104, | |
| "step": 2400, | |
| "token_acc": 0.9877061469265367 | |
| }, | |
| { | |
| "epoch": 1.2853333333333334, | |
| "grad_norm": 3.0, | |
| "learning_rate": 5.983462090740811e-06, | |
| "loss": 0.040090513229370114, | |
| "step": 2410, | |
| "token_acc": 0.987670279407378 | |
| }, | |
| { | |
| "epoch": 1.2906666666666666, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 5.904508045945854e-06, | |
| "loss": 0.04545362889766693, | |
| "step": 2420, | |
| "token_acc": 0.9842120941316652 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 5.825859575235904e-06, | |
| "loss": 0.04310760498046875, | |
| "step": 2430, | |
| "token_acc": 0.9861673747653394 | |
| }, | |
| { | |
| "epoch": 1.3013333333333335, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 5.747522546754456e-06, | |
| "loss": 0.04736645221710205, | |
| "step": 2440, | |
| "token_acc": 0.9838549920760697 | |
| }, | |
| { | |
| "epoch": 1.3066666666666666, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 5.669502805407592e-06, | |
| "loss": 0.04285838007926941, | |
| "step": 2450, | |
| "token_acc": 0.9850805649492739 | |
| }, | |
| { | |
| "epoch": 1.312, | |
| "grad_norm": 4.625, | |
| "learning_rate": 5.591806172427858e-06, | |
| "loss": 0.04294385612010956, | |
| "step": 2460, | |
| "token_acc": 0.984505246641169 | |
| }, | |
| { | |
| "epoch": 1.3173333333333335, | |
| "grad_norm": 4.25, | |
| "learning_rate": 5.514438444939947e-06, | |
| "loss": 0.04226144552230835, | |
| "step": 2470, | |
| "token_acc": 0.9866124553748512 | |
| }, | |
| { | |
| "epoch": 1.3226666666666667, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 5.437405395528148e-06, | |
| "loss": 0.03766881823539734, | |
| "step": 2480, | |
| "token_acc": 0.9893585280954749 | |
| }, | |
| { | |
| "epoch": 1.328, | |
| "grad_norm": 3.5, | |
| "learning_rate": 5.36071277180567e-06, | |
| "loss": 0.03593007028102875, | |
| "step": 2490, | |
| "token_acc": 0.9881862404447533 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 5.284366295985741e-06, | |
| "loss": 0.04274448156356812, | |
| "step": 2500, | |
| "token_acc": 0.9863830633137859 | |
| }, | |
| { | |
| "epoch": 1.3386666666666667, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 5.208371664454737e-06, | |
| "loss": 0.036032259464263916, | |
| "step": 2510, | |
| "token_acc": 0.9874426948375523 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 5.132734547347088e-06, | |
| "loss": 0.0413934588432312, | |
| "step": 2520, | |
| "token_acc": 0.9857496288965858 | |
| }, | |
| { | |
| "epoch": 1.3493333333333333, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 5.057460588122276e-06, | |
| "loss": 0.0397264838218689, | |
| "step": 2530, | |
| "token_acc": 0.987444389520514 | |
| }, | |
| { | |
| "epoch": 1.3546666666666667, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 4.98255540314372e-06, | |
| "loss": 0.03860927820205688, | |
| "step": 2540, | |
| "token_acc": 0.9876049580167933 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 4.5, | |
| "learning_rate": 4.908024581259744e-06, | |
| "loss": 0.03963862061500549, | |
| "step": 2550, | |
| "token_acc": 0.9869086581374591 | |
| }, | |
| { | |
| "epoch": 1.3653333333333333, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 4.833873683386596e-06, | |
| "loss": 0.036763495206832884, | |
| "step": 2560, | |
| "token_acc": 0.9882026370575989 | |
| }, | |
| { | |
| "epoch": 1.3706666666666667, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 4.760108242093493e-06, | |
| "loss": 0.04345675110816956, | |
| "step": 2570, | |
| "token_acc": 0.983983286908078 | |
| }, | |
| { | |
| "epoch": 1.376, | |
| "grad_norm": 3.75, | |
| "learning_rate": 4.686733761189872e-06, | |
| "loss": 0.0388829231262207, | |
| "step": 2580, | |
| "token_acc": 0.9876321563933772 | |
| }, | |
| { | |
| "epoch": 1.3813333333333333, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 4.613755715314701e-06, | |
| "loss": 0.04166227579116821, | |
| "step": 2590, | |
| "token_acc": 0.9865778484788228 | |
| }, | |
| { | |
| "epoch": 1.3866666666666667, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 4.541179549528032e-06, | |
| "loss": 0.036478173732757566, | |
| "step": 2600, | |
| "token_acc": 0.9887729756582215 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 4.469010678904694e-06, | |
| "loss": 0.03990663886070252, | |
| "step": 2610, | |
| "token_acc": 0.9868264659270999 | |
| }, | |
| { | |
| "epoch": 1.3973333333333333, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 4.397254488130313e-06, | |
| "loss": 0.043915411829948424, | |
| "step": 2620, | |
| "token_acc": 0.9850317208564632 | |
| }, | |
| { | |
| "epoch": 1.4026666666666667, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 4.3259163310995e-06, | |
| "loss": 0.04233855605125427, | |
| "step": 2630, | |
| "token_acc": 0.9862220447284346 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 4.255001530516425e-06, | |
| "loss": 0.04234825372695923, | |
| "step": 2640, | |
| "token_acc": 0.9854527461652647 | |
| }, | |
| { | |
| "epoch": 1.4133333333333333, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 4.184515377497643e-06, | |
| "loss": 0.04514653086662292, | |
| "step": 2650, | |
| "token_acc": 0.9838533927686973 | |
| }, | |
| { | |
| "epoch": 1.4186666666666667, | |
| "grad_norm": 4.125, | |
| "learning_rate": 4.11446313117733e-06, | |
| "loss": 0.0412144660949707, | |
| "step": 2660, | |
| "token_acc": 0.9864325618515563 | |
| }, | |
| { | |
| "epoch": 1.424, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 4.044850018314896e-06, | |
| "loss": 0.0395661473274231, | |
| "step": 2670, | |
| "token_acc": 0.9872051179528188 | |
| }, | |
| { | |
| "epoch": 1.4293333333333333, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 3.975681232904971e-06, | |
| "loss": 0.040367433428764345, | |
| "step": 2680, | |
| "token_acc": 0.9871325348906266 | |
| }, | |
| { | |
| "epoch": 1.4346666666666668, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 3.906961935789914e-06, | |
| "loss": 0.039546287059783934, | |
| "step": 2690, | |
| "token_acc": 0.9881709741550696 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 3.838697254274708e-06, | |
| "loss": 0.043249848484992984, | |
| "step": 2700, | |
| "token_acc": 0.9855836150328097 | |
| }, | |
| { | |
| "epoch": 1.4453333333333334, | |
| "grad_norm": 4.375, | |
| "learning_rate": 3.7708922817444382e-06, | |
| "loss": 0.04401258826255798, | |
| "step": 2710, | |
| "token_acc": 0.9847419003269593 | |
| }, | |
| { | |
| "epoch": 1.4506666666666668, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 3.7035520772842216e-06, | |
| "loss": 0.03827967643737793, | |
| "step": 2720, | |
| "token_acc": 0.9879434037465126 | |
| }, | |
| { | |
| "epoch": 1.456, | |
| "grad_norm": 3.953125, | |
| "learning_rate": 3.636681665301779e-06, | |
| "loss": 0.04192144274711609, | |
| "step": 2730, | |
| "token_acc": 0.9862782141791787 | |
| }, | |
| { | |
| "epoch": 1.4613333333333334, | |
| "grad_norm": 4.25, | |
| "learning_rate": 3.5702860351525216e-06, | |
| "loss": 0.03837197422981262, | |
| "step": 2740, | |
| "token_acc": 0.9874170216982067 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": 3.78125, | |
| "learning_rate": 3.504370140767297e-06, | |
| "loss": 0.037566077709197995, | |
| "step": 2750, | |
| "token_acc": 0.9870942122505708 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "grad_norm": 3.875, | |
| "learning_rate": 3.438938900282768e-06, | |
| "loss": 0.03785140812397003, | |
| "step": 2760, | |
| "token_acc": 0.9867993301152596 | |
| }, | |
| { | |
| "epoch": 1.4773333333333334, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 3.3739971956744444e-06, | |
| "loss": 0.04087229371070862, | |
| "step": 2770, | |
| "token_acc": 0.9853028798411122 | |
| }, | |
| { | |
| "epoch": 1.4826666666666668, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 3.3095498723924514e-06, | |
| "loss": 0.04550619721412659, | |
| "step": 2780, | |
| "token_acc": 0.9848303393213573 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 3.245601738999964e-06, | |
| "loss": 0.04144806861877441, | |
| "step": 2790, | |
| "token_acc": 0.9865586084206365 | |
| }, | |
| { | |
| "epoch": 1.4933333333333334, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 3.182157566814471e-06, | |
| "loss": 0.03926945924758911, | |
| "step": 2800, | |
| "token_acc": 0.9870852374329426 | |
| }, | |
| { | |
| "epoch": 1.4986666666666666, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 3.1192220895517434e-06, | |
| "loss": 0.04469040036201477, | |
| "step": 2810, | |
| "token_acc": 0.9841285685765622 | |
| }, | |
| { | |
| "epoch": 1.504, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 3.056800002972655e-06, | |
| "loss": 0.03768267929553985, | |
| "step": 2820, | |
| "token_acc": 0.9874032929974211 | |
| }, | |
| { | |
| "epoch": 1.5093333333333332, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 2.994895964532818e-06, | |
| "loss": 0.03740772008895874, | |
| "step": 2830, | |
| "token_acc": 0.9866719320762168 | |
| }, | |
| { | |
| "epoch": 1.5146666666666668, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 2.9335145930350852e-06, | |
| "loss": 0.03813513815402984, | |
| "step": 2840, | |
| "token_acc": 0.9872025594881024 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 2.8726604682849192e-06, | |
| "loss": 0.037986403703689574, | |
| "step": 2850, | |
| "token_acc": 0.9885515181682429 | |
| }, | |
| { | |
| "epoch": 1.5253333333333332, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 2.8123381307486875e-06, | |
| "loss": 0.03967353105545044, | |
| "step": 2860, | |
| "token_acc": 0.9861526200438334 | |
| }, | |
| { | |
| "epoch": 1.5306666666666666, | |
| "grad_norm": 3.734375, | |
| "learning_rate": 2.752552081214899e-06, | |
| "loss": 0.03929359912872314, | |
| "step": 2870, | |
| "token_acc": 0.9870245641838352 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 4.125, | |
| "learning_rate": 2.693306780458369e-06, | |
| "loss": 0.037700363993644716, | |
| "step": 2880, | |
| "token_acc": 0.9881058578650015 | |
| }, | |
| { | |
| "epoch": 1.5413333333333332, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 2.6346066489074083e-06, | |
| "loss": 0.041693341732025144, | |
| "step": 2890, | |
| "token_acc": 0.9857881136950905 | |
| }, | |
| { | |
| "epoch": 1.5466666666666666, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.576456066313989e-06, | |
| "loss": 0.035756158828735354, | |
| "step": 2900, | |
| "token_acc": 0.9879518072289156 | |
| }, | |
| { | |
| "epoch": 1.552, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 2.518859371426985e-06, | |
| "loss": 0.04258395731449127, | |
| "step": 2910, | |
| "token_acc": 0.9866852146263911 | |
| }, | |
| { | |
| "epoch": 1.5573333333333332, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 2.4618208616684213e-06, | |
| "loss": 0.03691713809967041, | |
| "step": 2920, | |
| "token_acc": 0.9884158415841584 | |
| }, | |
| { | |
| "epoch": 1.5626666666666666, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 2.405344792812847e-06, | |
| "loss": 0.03898451030254364, | |
| "step": 2930, | |
| "token_acc": 0.9885946642864227 | |
| }, | |
| { | |
| "epoch": 1.568, | |
| "grad_norm": 5.375, | |
| "learning_rate": 2.3494353786698e-06, | |
| "loss": 0.04118772149085999, | |
| "step": 2940, | |
| "token_acc": 0.9864985605082894 | |
| }, | |
| { | |
| "epoch": 1.5733333333333333, | |
| "grad_norm": 3.984375, | |
| "learning_rate": 2.294096790769411e-06, | |
| "loss": 0.03973854184150696, | |
| "step": 2950, | |
| "token_acc": 0.987149070778964 | |
| }, | |
| { | |
| "epoch": 1.5786666666666667, | |
| "grad_norm": 4.125, | |
| "learning_rate": 2.239333158051147e-06, | |
| "loss": 0.04216883778572082, | |
| "step": 2960, | |
| "token_acc": 0.985914095823827 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 2.185148566555738e-06, | |
| "loss": 0.036406677961349485, | |
| "step": 2970, | |
| "token_acc": 0.9885492382754157 | |
| }, | |
| { | |
| "epoch": 1.5893333333333333, | |
| "grad_norm": 4.75, | |
| "learning_rate": 2.131547059120329e-06, | |
| "loss": 0.0353354811668396, | |
| "step": 2980, | |
| "token_acc": 0.9889804427677951 | |
| }, | |
| { | |
| "epoch": 1.5946666666666667, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 2.0785326350768085e-06, | |
| "loss": 0.03935574293136597, | |
| "step": 2990, | |
| "token_acc": 0.9870039682539683 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 2.0261092499534287e-06, | |
| "loss": 0.035825759172439575, | |
| "step": 3000, | |
| "token_acc": 0.9886442184259899 | |
| }, | |
| { | |
| "epoch": 1.6053333333333333, | |
| "grad_norm": 3.765625, | |
| "learning_rate": 1.974280815179659e-06, | |
| "loss": 0.03752996325492859, | |
| "step": 3010, | |
| "token_acc": 0.9868238557558946 | |
| }, | |
| { | |
| "epoch": 1.6106666666666667, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.9230511977943646e-06, | |
| "loss": 0.040970760583877566, | |
| "step": 3020, | |
| "token_acc": 0.9850628153130874 | |
| }, | |
| { | |
| "epoch": 1.616, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 1.8724242201572585e-06, | |
| "loss": 0.043044912815094, | |
| "step": 3030, | |
| "token_acc": 0.9857637172516065 | |
| }, | |
| { | |
| "epoch": 1.6213333333333333, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.822403659663715e-06, | |
| "loss": 0.036146676540374754, | |
| "step": 3040, | |
| "token_acc": 0.9875683739433118 | |
| }, | |
| { | |
| "epoch": 1.6266666666666667, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 1.7729932484629298e-06, | |
| "loss": 0.03931437730789185, | |
| "step": 3050, | |
| "token_acc": 0.9890704903238745 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.724196673179458e-06, | |
| "loss": 0.03747313618659973, | |
| "step": 3060, | |
| "token_acc": 0.9896362730443448 | |
| }, | |
| { | |
| "epoch": 1.6373333333333333, | |
| "grad_norm": 3.421875, | |
| "learning_rate": 1.6760175746381402e-06, | |
| "loss": 0.04139094054698944, | |
| "step": 3070, | |
| "token_acc": 0.9865765138709357 | |
| }, | |
| { | |
| "epoch": 1.6426666666666667, | |
| "grad_norm": 3.5, | |
| "learning_rate": 1.6284595475924547e-06, | |
| "loss": 0.0396723598241806, | |
| "step": 3080, | |
| "token_acc": 0.9874851013110846 | |
| }, | |
| { | |
| "epoch": 1.6480000000000001, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 1.5815261404563066e-06, | |
| "loss": 0.04129367172718048, | |
| "step": 3090, | |
| "token_acc": 0.985513038265561 | |
| }, | |
| { | |
| "epoch": 1.6533333333333333, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.5352208550392745e-06, | |
| "loss": 0.04074010848999023, | |
| "step": 3100, | |
| "token_acc": 0.9864541832669322 | |
| }, | |
| { | |
| "epoch": 1.6586666666666665, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.489547146285325e-06, | |
| "loss": 0.03951275944709778, | |
| "step": 3110, | |
| "token_acc": 0.988421573478476 | |
| }, | |
| { | |
| "epoch": 1.6640000000000001, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 1.4445084220150341e-06, | |
| "loss": 0.037594377994537354, | |
| "step": 3120, | |
| "token_acc": 0.9884542649547129 | |
| }, | |
| { | |
| "epoch": 1.6693333333333333, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 1.4001080426713332e-06, | |
| "loss": 0.04155745506286621, | |
| "step": 3130, | |
| "token_acc": 0.9877453422337352 | |
| }, | |
| { | |
| "epoch": 1.6746666666666665, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 1.3563493210687527e-06, | |
| "loss": 0.043962416052818296, | |
| "step": 3140, | |
| "token_acc": 0.9840078973346496 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 1.3132355221462778e-06, | |
| "loss": 0.03296797275543213, | |
| "step": 3150, | |
| "token_acc": 0.9894537856929658 | |
| }, | |
| { | |
| "epoch": 1.6853333333333333, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.2707698627237152e-06, | |
| "loss": 0.03483983278274536, | |
| "step": 3160, | |
| "token_acc": 0.9894310549190043 | |
| }, | |
| { | |
| "epoch": 1.6906666666666665, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.2289555112617024e-06, | |
| "loss": 0.038097748160362245, | |
| "step": 3170, | |
| "token_acc": 0.9872839260878203 | |
| }, | |
| { | |
| "epoch": 1.696, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 1.1877955876252779e-06, | |
| "loss": 0.04070072174072266, | |
| "step": 3180, | |
| "token_acc": 0.9862648221343874 | |
| }, | |
| { | |
| "epoch": 1.7013333333333334, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.147293162851123e-06, | |
| "loss": 0.042076826095581055, | |
| "step": 3190, | |
| "token_acc": 0.9863341645885286 | |
| }, | |
| { | |
| "epoch": 1.7066666666666666, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 1.1074512589184105e-06, | |
| "loss": 0.036808636784553525, | |
| "step": 3200, | |
| "token_acc": 0.9880155797463298 | |
| }, | |
| { | |
| "epoch": 1.712, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.0682728485233306e-06, | |
| "loss": 0.04157693088054657, | |
| "step": 3210, | |
| "token_acc": 0.9863757527890217 | |
| }, | |
| { | |
| "epoch": 1.7173333333333334, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.0297608548573002e-06, | |
| "loss": 0.03867577910423279, | |
| "step": 3220, | |
| "token_acc": 0.9868682849184242 | |
| }, | |
| { | |
| "epoch": 1.7226666666666666, | |
| "grad_norm": 4.0, | |
| "learning_rate": 9.91918151388841e-07, | |
| "loss": 0.03704025447368622, | |
| "step": 3230, | |
| "token_acc": 0.9880186157045252 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 9.547475616492008e-07, | |
| "loss": 0.04006602168083191, | |
| "step": 3240, | |
| "token_acc": 0.9858022239872914 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": 4.5, | |
| "learning_rate": 9.182518590216616e-07, | |
| "loss": 0.035135465860366824, | |
| "step": 3250, | |
| "token_acc": 0.989517819706499 | |
| }, | |
| { | |
| "epoch": 1.7386666666666666, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 8.824337665346372e-07, | |
| "loss": 0.03798290193080902, | |
| "step": 3260, | |
| "token_acc": 0.9877976190476191 | |
| }, | |
| { | |
| "epoch": 1.744, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 8.472959566584804e-07, | |
| "loss": 0.03600641489028931, | |
| "step": 3270, | |
| "token_acc": 0.9884680385724227 | |
| }, | |
| { | |
| "epoch": 1.7493333333333334, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 8.128410511061002e-07, | |
| "loss": 0.03648544549942016, | |
| "step": 3280, | |
| "token_acc": 0.9888472167390446 | |
| }, | |
| { | |
| "epoch": 1.7546666666666666, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 7.790716206373283e-07, | |
| "loss": 0.03724295794963837, | |
| "step": 3290, | |
| "token_acc": 0.9882908589983272 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 5.5, | |
| "learning_rate": 7.459901848671347e-07, | |
| "loss": 0.03567275404930115, | |
| "step": 3300, | |
| "token_acc": 0.9892803970223325 | |
| }, | |
| { | |
| "epoch": 1.7653333333333334, | |
| "grad_norm": 3.4375, | |
| "learning_rate": 7.135992120776159e-07, | |
| "loss": 0.03632798194885254, | |
| "step": 3310, | |
| "token_acc": 0.9883651551312649 | |
| }, | |
| { | |
| "epoch": 1.7706666666666666, | |
| "grad_norm": 4.25, | |
| "learning_rate": 6.819011190338309e-07, | |
| "loss": 0.04045731127262116, | |
| "step": 3320, | |
| "token_acc": 0.9866320830007981 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 4.0, | |
| "learning_rate": 6.508982708034962e-07, | |
| "loss": 0.04045606255531311, | |
| "step": 3330, | |
| "token_acc": 0.9870064967516242 | |
| }, | |
| { | |
| "epoch": 1.7813333333333334, | |
| "grad_norm": 4.25, | |
| "learning_rate": 6.205929805805e-07, | |
| "loss": 0.04064445495605469, | |
| "step": 3340, | |
| "token_acc": 0.9874344513703374 | |
| }, | |
| { | |
| "epoch": 1.7866666666666666, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 5.90987509512333e-07, | |
| "loss": 0.039674225449562076, | |
| "step": 3350, | |
| "token_acc": 0.9873617693522907 | |
| }, | |
| { | |
| "epoch": 1.792, | |
| "grad_norm": 3.9375, | |
| "learning_rate": 5.620840665313554e-07, | |
| "loss": 0.03971289396286011, | |
| "step": 3360, | |
| "token_acc": 0.9871845817603815 | |
| }, | |
| { | |
| "epoch": 1.7973333333333334, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 5.338848081900062e-07, | |
| "loss": 0.03789665699005127, | |
| "step": 3370, | |
| "token_acc": 0.9868289762522451 | |
| }, | |
| { | |
| "epoch": 1.8026666666666666, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 5.063918384998801e-07, | |
| "loss": 0.03832893967628479, | |
| "step": 3380, | |
| "token_acc": 0.9873656983684839 | |
| }, | |
| { | |
| "epoch": 1.808, | |
| "grad_norm": 3.625, | |
| "learning_rate": 4.796072087747506e-07, | |
| "loss": 0.03417414128780365, | |
| "step": 3390, | |
| "token_acc": 0.9885656970912738 | |
| }, | |
| { | |
| "epoch": 1.8133333333333335, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 4.5353291747751605e-07, | |
| "loss": 0.03775486946105957, | |
| "step": 3400, | |
| "token_acc": 0.987764846314533 | |
| }, | |
| { | |
| "epoch": 1.8186666666666667, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 4.281709100710907e-07, | |
| "loss": 0.041268390417098996, | |
| "step": 3410, | |
| "token_acc": 0.9870834154999014 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 4.035230788732447e-07, | |
| "loss": 0.039685606956481934, | |
| "step": 3420, | |
| "token_acc": 0.9877361289684502 | |
| }, | |
| { | |
| "epoch": 1.8293333333333335, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 3.7959126291541635e-07, | |
| "loss": 0.03789263963699341, | |
| "step": 3430, | |
| "token_acc": 0.9878606965174129 | |
| }, | |
| { | |
| "epoch": 1.8346666666666667, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 3.5637724780550386e-07, | |
| "loss": 0.03865547776222229, | |
| "step": 3440, | |
| "token_acc": 0.9879853043391917 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 3.338827655946253e-07, | |
| "loss": 0.03745532631874084, | |
| "step": 3450, | |
| "token_acc": 0.9876421156697973 | |
| }, | |
| { | |
| "epoch": 1.8453333333333335, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 3.121094946478942e-07, | |
| "loss": 0.04047192931175232, | |
| "step": 3460, | |
| "token_acc": 0.9872889771598808 | |
| }, | |
| { | |
| "epoch": 1.8506666666666667, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 2.910590595191898e-07, | |
| "loss": 0.040114715695381165, | |
| "step": 3470, | |
| "token_acc": 0.988480635551142 | |
| }, | |
| { | |
| "epoch": 1.8559999999999999, | |
| "grad_norm": 4.125, | |
| "learning_rate": 2.707330308299516e-07, | |
| "loss": 0.04216385185718537, | |
| "step": 3480, | |
| "token_acc": 0.9865373193427044 | |
| }, | |
| { | |
| "epoch": 1.8613333333333333, | |
| "grad_norm": 4.125, | |
| "learning_rate": 2.5113292515198007e-07, | |
| "loss": 0.040276515483856204, | |
| "step": 3490, | |
| "token_acc": 0.984169387553181 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 2.3226020489429235e-07, | |
| "loss": 0.04182217717170715, | |
| "step": 3500, | |
| "token_acc": 0.9864570976670621 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 2.1411627819400317e-07, | |
| "loss": 0.03821204304695129, | |
| "step": 3510, | |
| "token_acc": 0.987941000597967 | |
| }, | |
| { | |
| "epoch": 1.8773333333333333, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.9670249881126202e-07, | |
| "loss": 0.0350002646446228, | |
| "step": 3520, | |
| "token_acc": 0.9889872173058014 | |
| }, | |
| { | |
| "epoch": 1.8826666666666667, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.8002016602824634e-07, | |
| "loss": 0.04192837476730347, | |
| "step": 3530, | |
| "token_acc": 0.9864676616915423 | |
| }, | |
| { | |
| "epoch": 1.888, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.6407052455221562e-07, | |
| "loss": 0.03514524102210999, | |
| "step": 3540, | |
| "token_acc": 0.9886284979729062 | |
| }, | |
| { | |
| "epoch": 1.8933333333333333, | |
| "grad_norm": 3.625, | |
| "learning_rate": 1.4885476442264902e-07, | |
| "loss": 0.04049878716468811, | |
| "step": 3550, | |
| "token_acc": 0.9872188645595957 | |
| }, | |
| { | |
| "epoch": 1.8986666666666667, | |
| "grad_norm": 4.0, | |
| "learning_rate": 1.3437402092244533e-07, | |
| "loss": 0.03796062469482422, | |
| "step": 3560, | |
| "token_acc": 0.9878787878787879 | |
| }, | |
| { | |
| "epoch": 1.904, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 1.2062937449321854e-07, | |
| "loss": 0.03846385180950165, | |
| "step": 3570, | |
| "token_acc": 0.9860460480414631 | |
| }, | |
| { | |
| "epoch": 1.9093333333333333, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.0762185065468889e-07, | |
| "loss": 0.04030992984771729, | |
| "step": 3580, | |
| "token_acc": 0.987700853005356 | |
| }, | |
| { | |
| "epoch": 1.9146666666666667, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 9.535241992816191e-08, | |
| "loss": 0.042255711555480954, | |
| "step": 3590, | |
| "token_acc": 0.9876 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 8.382199776411526e-08, | |
| "loss": 0.03983389139175415, | |
| "step": 3600, | |
| "token_acc": 0.9855956787036111 | |
| }, | |
| { | |
| "epoch": 1.9253333333333333, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 7.303144447389554e-08, | |
| "loss": 0.035570698976516726, | |
| "step": 3610, | |
| "token_acc": 0.9869651741293533 | |
| }, | |
| { | |
| "epoch": 1.9306666666666668, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 6.298156516552966e-08, | |
| "loss": 0.0347730815410614, | |
| "step": 3620, | |
| "token_acc": 0.9881046788263284 | |
| }, | |
| { | |
| "epoch": 1.936, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 5.3673109683656245e-08, | |
| "loss": 0.03999523520469665, | |
| "step": 3630, | |
| "token_acc": 0.9867116223720745 | |
| }, | |
| { | |
| "epoch": 1.9413333333333334, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 4.510677255357143e-08, | |
| "loss": 0.038808077573776245, | |
| "step": 3640, | |
| "token_acc": 0.9859943977591037 | |
| }, | |
| { | |
| "epoch": 1.9466666666666668, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 3.7283192929412624e-08, | |
| "loss": 0.038824063539505, | |
| "step": 3650, | |
| "token_acc": 0.9869138495092693 | |
| }, | |
| { | |
| "epoch": 1.952, | |
| "grad_norm": 5.0, | |
| "learning_rate": 3.020295454647104e-08, | |
| "loss": 0.039383918046951294, | |
| "step": 3660, | |
| "token_acc": 0.9874195146111937 | |
| }, | |
| { | |
| "epoch": 1.9573333333333334, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 2.3866585677635445e-08, | |
| "loss": 0.035313469171524045, | |
| "step": 3670, | |
| "token_acc": 0.9900635930047694 | |
| }, | |
| { | |
| "epoch": 1.9626666666666668, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.827455909397813e-08, | |
| "loss": 0.04173220694065094, | |
| "step": 3680, | |
| "token_acc": 0.9857867011231488 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.3427292029476458e-08, | |
| "loss": 0.04029126763343811, | |
| "step": 3690, | |
| "token_acc": 0.9877477836437892 | |
| }, | |
| { | |
| "epoch": 1.9733333333333334, | |
| "grad_norm": 3.9375, | |
| "learning_rate": 9.325146149888887e-09, | |
| "loss": 0.04099421203136444, | |
| "step": 3700, | |
| "token_acc": 0.9873291429711664 | |
| }, | |
| { | |
| "epoch": 1.9786666666666668, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 5.96842752576543e-09, | |
| "loss": 0.03839865326881409, | |
| "step": 3710, | |
| "token_acc": 0.9865293185419969 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 3.3573866096114903e-09, | |
| "loss": 0.0387137234210968, | |
| "step": 3720, | |
| "token_acc": 0.9878769958604376 | |
| }, | |
| { | |
| "epoch": 1.9893333333333332, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.4922182172016908e-09, | |
| "loss": 0.0345587432384491, | |
| "step": 3730, | |
| "token_acc": 0.9903066271018793 | |
| }, | |
| { | |
| "epoch": 1.9946666666666668, | |
| "grad_norm": 4.25, | |
| "learning_rate": 3.7306151304483675e-10, | |
| "loss": 0.040695366263389585, | |
| "step": 3740, | |
| "token_acc": 0.98731039952414 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 0.0, | |
| "loss": 0.03878684341907501, | |
| "step": 3750, | |
| "token_acc": 0.9870156218299858 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7535688265883976e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |