GameGoCoder3_8 / trainer_state.json
Y36521478Y's picture
Add files using upload-large-folder tool
36d5c9f verified
Raw History Blame Contribute Delete
332 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 250.0,
"global_step": 1505,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000664451827242525,
"grad_norm": 0.33507779240608215,
"learning_rate": 2.173913043478261e-07,
"loss": 0.403564453125,
"step": 1,
"token_acc": 0.8677136094555559
},
{
"epoch": 0.00132890365448505,
"grad_norm": 0.3274036645889282,
"learning_rate": 4.347826086956522e-07,
"loss": 0.4091796875,
"step": 2,
"token_acc": 0.8667182948946773
},
{
"epoch": 0.0019933554817275745,
"grad_norm": 0.33733829855918884,
"learning_rate": 6.521739130434783e-07,
"loss": 0.39990234375,
"step": 3,
"token_acc": 0.869089347749717
},
{
"epoch": 0.0026578073089701,
"grad_norm": 0.3406624495983124,
"learning_rate": 8.695652173913044e-07,
"loss": 0.39794921875,
"step": 4,
"token_acc": 0.8696012334332952
},
{
"epoch": 0.0033222591362126247,
"grad_norm": 0.4239804446697235,
"learning_rate": 1.0869565217391306e-06,
"loss": 0.392822265625,
"step": 5,
"token_acc": 0.8707661255513122
},
{
"epoch": 0.003986710963455149,
"grad_norm": 0.32294777035713196,
"learning_rate": 1.3043478260869566e-06,
"loss": 0.395263671875,
"step": 6,
"token_acc": 0.8702375038584558
},
{
"epoch": 0.004651162790697674,
"grad_norm": 0.3336384892463684,
"learning_rate": 1.521739130434783e-06,
"loss": 0.4013671875,
"step": 7,
"token_acc": 0.8692256715347048
},
{
"epoch": 0.0053156146179402,
"grad_norm": 0.32594093680381775,
"learning_rate": 1.7391304347826088e-06,
"loss": 0.3857421875,
"step": 8,
"token_acc": 0.8732306134020335
},
{
"epoch": 0.005980066445182724,
"grad_norm": 0.34246423840522766,
"learning_rate": 1.956521739130435e-06,
"loss": 0.3916015625,
"step": 9,
"token_acc": 0.8719959743791993
},
{
"epoch": 0.006644518272425249,
"grad_norm": 0.4030548632144928,
"learning_rate": 2.173913043478261e-06,
"loss": 0.4052734375,
"step": 10,
"token_acc": 0.8674930668190106
},
{
"epoch": 0.007308970099667774,
"grad_norm": 0.587324857711792,
"learning_rate": 2.391304347826087e-06,
"loss": 0.38134765625,
"step": 11,
"token_acc": 0.874481143674146
},
{
"epoch": 0.007973421926910298,
"grad_norm": 0.32525062561035156,
"learning_rate": 2.6086956521739132e-06,
"loss": 0.3876953125,
"step": 12,
"token_acc": 0.872403767919576
},
{
"epoch": 0.008637873754152824,
"grad_norm": 0.3522593677043915,
"learning_rate": 2.8260869565217393e-06,
"loss": 0.395751953125,
"step": 13,
"token_acc": 0.8703341831758403
},
{
"epoch": 0.009302325581395349,
"grad_norm": 0.9920299649238586,
"learning_rate": 3.043478260869566e-06,
"loss": 0.4033203125,
"step": 14,
"token_acc": 0.8684506435845347
},
{
"epoch": 0.009966777408637873,
"grad_norm": 0.33649641275405884,
"learning_rate": 3.2608695652173914e-06,
"loss": 0.407958984375,
"step": 15,
"token_acc": 0.8661938542148662
},
{
"epoch": 0.0106312292358804,
"grad_norm": 0.3800162672996521,
"learning_rate": 3.4782608695652175e-06,
"loss": 0.37451171875,
"step": 16,
"token_acc": 0.8770822672031487
},
{
"epoch": 0.011295681063122924,
"grad_norm": 0.35152649879455566,
"learning_rate": 3.6956521739130436e-06,
"loss": 0.39306640625,
"step": 17,
"token_acc": 0.8707390368407262
},
{
"epoch": 0.011960132890365448,
"grad_norm": 0.32991814613342285,
"learning_rate": 3.91304347826087e-06,
"loss": 0.38623046875,
"step": 18,
"token_acc": 0.8732363366834957
},
{
"epoch": 0.012624584717607974,
"grad_norm": 0.3507179617881775,
"learning_rate": 4.130434782608696e-06,
"loss": 0.3994140625,
"step": 19,
"token_acc": 0.8689937441021744
},
{
"epoch": 0.013289036544850499,
"grad_norm": 0.3807450830936432,
"learning_rate": 4.347826086956522e-06,
"loss": 0.386474609375,
"step": 20,
"token_acc": 0.8732248835998251
},
{
"epoch": 0.013953488372093023,
"grad_norm": 0.39044684171676636,
"learning_rate": 4.565217391304348e-06,
"loss": 0.40576171875,
"step": 21,
"token_acc": 0.8676612206038454
},
{
"epoch": 0.014617940199335547,
"grad_norm": 0.35150668025016785,
"learning_rate": 4.782608695652174e-06,
"loss": 0.4033203125,
"step": 22,
"token_acc": 0.86807086066518
},
{
"epoch": 0.015282392026578074,
"grad_norm": 0.40974894165992737,
"learning_rate": 5e-06,
"loss": 0.418212890625,
"step": 23,
"token_acc": 0.8651191150687132
},
{
"epoch": 0.015946843853820596,
"grad_norm": 0.42400214076042175,
"learning_rate": 5.2173913043478265e-06,
"loss": 0.4111328125,
"step": 24,
"token_acc": 0.8658044131393084
},
{
"epoch": 0.016611295681063124,
"grad_norm": 0.33786138892173767,
"learning_rate": 5.4347826086956525e-06,
"loss": 0.394775390625,
"step": 25,
"token_acc": 0.8699101291785932
},
{
"epoch": 0.01727574750830565,
"grad_norm": 0.34576690196990967,
"learning_rate": 5.652173913043479e-06,
"loss": 0.403076171875,
"step": 26,
"token_acc": 0.8680597362103007
},
{
"epoch": 0.017940199335548173,
"grad_norm": 0.30764421820640564,
"learning_rate": 5.8695652173913055e-06,
"loss": 0.39990234375,
"step": 27,
"token_acc": 0.8694097013114254
},
{
"epoch": 0.018604651162790697,
"grad_norm": 0.45521724224090576,
"learning_rate": 6.086956521739132e-06,
"loss": 0.39697265625,
"step": 28,
"token_acc": 0.8694389120685546
},
{
"epoch": 0.019269102990033222,
"grad_norm": 0.3858051896095276,
"learning_rate": 6.304347826086958e-06,
"loss": 0.40283203125,
"step": 29,
"token_acc": 0.8680464778503995
},
{
"epoch": 0.019933554817275746,
"grad_norm": 0.3429538607597351,
"learning_rate": 6.521739130434783e-06,
"loss": 0.404052734375,
"step": 30,
"token_acc": 0.8678521748334967
},
{
"epoch": 0.020598006644518274,
"grad_norm": 0.3273807466030121,
"learning_rate": 6.739130434782609e-06,
"loss": 0.40625,
"step": 31,
"token_acc": 0.867287128799456
},
{
"epoch": 0.0212624584717608,
"grad_norm": 0.3436574339866638,
"learning_rate": 6.956521739130435e-06,
"loss": 0.39013671875,
"step": 32,
"token_acc": 0.8716442561320746
},
{
"epoch": 0.021926910299003323,
"grad_norm": 0.32729777693748474,
"learning_rate": 7.173913043478261e-06,
"loss": 0.38427734375,
"step": 33,
"token_acc": 0.8740190559857992
},
{
"epoch": 0.022591362126245847,
"grad_norm": 0.33254274725914,
"learning_rate": 7.391304347826087e-06,
"loss": 0.397705078125,
"step": 34,
"token_acc": 0.8688389159199733
},
{
"epoch": 0.023255813953488372,
"grad_norm": 0.40609490871429443,
"learning_rate": 7.608695652173914e-06,
"loss": 0.4111328125,
"step": 35,
"token_acc": 0.8657248490343799
},
{
"epoch": 0.023920265780730896,
"grad_norm": 0.35102349519729614,
"learning_rate": 7.82608695652174e-06,
"loss": 0.409912109375,
"step": 36,
"token_acc": 0.8660650273911877
},
{
"epoch": 0.02458471760797342,
"grad_norm": 0.4353107810020447,
"learning_rate": 8.043478260869566e-06,
"loss": 0.400146484375,
"step": 37,
"token_acc": 0.8688639141568953
},
{
"epoch": 0.02524916943521595,
"grad_norm": 0.3355410695075989,
"learning_rate": 8.260869565217392e-06,
"loss": 0.39990234375,
"step": 38,
"token_acc": 0.8689172421161938
},
{
"epoch": 0.025913621262458473,
"grad_norm": 0.361273854970932,
"learning_rate": 8.478260869565218e-06,
"loss": 0.3955078125,
"step": 39,
"token_acc": 0.8707040034941018
},
{
"epoch": 0.026578073089700997,
"grad_norm": 0.31194832921028137,
"learning_rate": 8.695652173913044e-06,
"loss": 0.385986328125,
"step": 40,
"token_acc": 0.8729131647079037
},
{
"epoch": 0.02724252491694352,
"grad_norm": 0.38033246994018555,
"learning_rate": 8.91304347826087e-06,
"loss": 0.392333984375,
"step": 41,
"token_acc": 0.8721707209151148
},
{
"epoch": 0.027906976744186046,
"grad_norm": 0.3943629562854767,
"learning_rate": 9.130434782608697e-06,
"loss": 0.389404296875,
"step": 42,
"token_acc": 0.8717123205152076
},
{
"epoch": 0.02857142857142857,
"grad_norm": 0.5038305521011353,
"learning_rate": 9.347826086956523e-06,
"loss": 0.3994140625,
"step": 43,
"token_acc": 0.8690093584894413
},
{
"epoch": 0.029235880398671095,
"grad_norm": 0.3585200905799866,
"learning_rate": 9.565217391304349e-06,
"loss": 0.405029296875,
"step": 44,
"token_acc": 0.867361693364118
},
{
"epoch": 0.029900332225913623,
"grad_norm": 0.37307044863700867,
"learning_rate": 9.782608695652175e-06,
"loss": 0.406982421875,
"step": 45,
"token_acc": 0.8667211881943941
},
{
"epoch": 0.030564784053156147,
"grad_norm": 0.5289521813392639,
"learning_rate": 1e-05,
"loss": 0.40771484375,
"step": 46,
"token_acc": 0.8659434542347664
},
{
"epoch": 0.03122923588039867,
"grad_norm": 0.3869972229003906,
"learning_rate": 9.999988408783906e-06,
"loss": 0.393310546875,
"step": 47,
"token_acc": 0.8710683249943174
},
{
"epoch": 0.03189368770764119,
"grad_norm": 0.40658363699913025,
"learning_rate": 9.99995363518936e-06,
"loss": 0.402587890625,
"step": 48,
"token_acc": 0.8670007297604698
},
{
"epoch": 0.03255813953488372,
"grad_norm": 0.3440706133842468,
"learning_rate": 9.999895679377595e-06,
"loss": 0.396240234375,
"step": 49,
"token_acc": 0.8700892745782254
},
{
"epoch": 0.03322259136212625,
"grad_norm": 0.3560961186885834,
"learning_rate": 9.99981454161732e-06,
"loss": 0.39794921875,
"step": 50,
"token_acc": 0.8695683981895744
},
{
"epoch": 0.03388704318936877,
"grad_norm": 0.3715246319770813,
"learning_rate": 9.999710222284731e-06,
"loss": 0.395751953125,
"step": 51,
"token_acc": 0.8702689461742125
},
{
"epoch": 0.0345514950166113,
"grad_norm": 0.33247023820877075,
"learning_rate": 9.9995827218635e-06,
"loss": 0.4033203125,
"step": 52,
"token_acc": 0.8676876033179124
},
{
"epoch": 0.03521594684385382,
"grad_norm": 0.3893953859806061,
"learning_rate": 9.999432040944784e-06,
"loss": 0.384521484375,
"step": 53,
"token_acc": 0.8743975132272712
},
{
"epoch": 0.035880398671096346,
"grad_norm": 0.4291185736656189,
"learning_rate": 9.99925818022721e-06,
"loss": 0.401123046875,
"step": 54,
"token_acc": 0.8687922720267799
},
{
"epoch": 0.036544850498338874,
"grad_norm": 0.32648563385009766,
"learning_rate": 9.999061140516881e-06,
"loss": 0.391845703125,
"step": 55,
"token_acc": 0.871350750199139
},
{
"epoch": 0.037209302325581395,
"grad_norm": 0.3648381233215332,
"learning_rate": 9.998840922727372e-06,
"loss": 0.383056640625,
"step": 56,
"token_acc": 0.8740521452994802
},
{
"epoch": 0.03787375415282392,
"grad_norm": 0.36927032470703125,
"learning_rate": 9.998597527879718e-06,
"loss": 0.392822265625,
"step": 57,
"token_acc": 0.8705230446886274
},
{
"epoch": 0.038538205980066444,
"grad_norm": 0.3364102840423584,
"learning_rate": 9.998330957102416e-06,
"loss": 0.402587890625,
"step": 58,
"token_acc": 0.8686193957071804
},
{
"epoch": 0.03920265780730897,
"grad_norm": 0.3306722939014435,
"learning_rate": 9.998041211631418e-06,
"loss": 0.38623046875,
"step": 59,
"token_acc": 0.8729841499051414
},
{
"epoch": 0.03986710963455149,
"grad_norm": 1.6782549619674683,
"learning_rate": 9.997728292810122e-06,
"loss": 0.389892578125,
"step": 60,
"token_acc": 0.8720178206998086
},
{
"epoch": 0.04053156146179402,
"grad_norm": 0.3510347306728363,
"learning_rate": 9.997392202089378e-06,
"loss": 0.38671875,
"step": 61,
"token_acc": 0.8727935049452079
},
{
"epoch": 0.04119601328903655,
"grad_norm": 0.3565468490123749,
"learning_rate": 9.997032941027462e-06,
"loss": 0.4013671875,
"step": 62,
"token_acc": 0.8684921346850617
},
{
"epoch": 0.04186046511627907,
"grad_norm": 0.38575077056884766,
"learning_rate": 9.996650511290082e-06,
"loss": 0.39697265625,
"step": 63,
"token_acc": 0.8698753631935924
},
{
"epoch": 0.0425249169435216,
"grad_norm": 0.4672475755214691,
"learning_rate": 9.996244914650372e-06,
"loss": 0.41162109375,
"step": 64,
"token_acc": 0.8667054701828736
},
{
"epoch": 0.04318936877076412,
"grad_norm": 0.3279372751712799,
"learning_rate": 9.995816152988874e-06,
"loss": 0.411865234375,
"step": 65,
"token_acc": 0.8647513754918101
},
{
"epoch": 0.043853820598006646,
"grad_norm": 0.6665076017379761,
"learning_rate": 9.995364228293534e-06,
"loss": 0.395751953125,
"step": 66,
"token_acc": 0.8703015103554509
},
{
"epoch": 0.04451827242524917,
"grad_norm": 0.33411839604377747,
"learning_rate": 9.994889142659694e-06,
"loss": 0.395751953125,
"step": 67,
"token_acc": 0.8699354029338293
},
{
"epoch": 0.045182724252491695,
"grad_norm": 0.34475526213645935,
"learning_rate": 9.994390898290087e-06,
"loss": 0.407958984375,
"step": 68,
"token_acc": 0.8665927531620397
},
{
"epoch": 0.04584717607973422,
"grad_norm": 0.3182011544704437,
"learning_rate": 9.99386949749481e-06,
"loss": 0.40869140625,
"step": 69,
"token_acc": 0.8667905193607363
},
{
"epoch": 0.046511627906976744,
"grad_norm": 0.3795689046382904,
"learning_rate": 9.993324942691336e-06,
"loss": 0.407958984375,
"step": 70,
"token_acc": 0.8664710917920518
},
{
"epoch": 0.04717607973421927,
"grad_norm": 0.34782886505126953,
"learning_rate": 9.992757236404483e-06,
"loss": 0.41748046875,
"step": 71,
"token_acc": 0.8638055207497718
},
{
"epoch": 0.04784053156146179,
"grad_norm": 0.3663429617881775,
"learning_rate": 9.992166381266414e-06,
"loss": 0.4052734375,
"step": 72,
"token_acc": 0.8671082049253677
},
{
"epoch": 0.04850498338870432,
"grad_norm": 0.37814590334892273,
"learning_rate": 9.99155238001662e-06,
"loss": 0.390869140625,
"step": 73,
"token_acc": 0.8719194727847939
},
{
"epoch": 0.04916943521594684,
"grad_norm": 0.366350919008255,
"learning_rate": 9.990915235501913e-06,
"loss": 0.402587890625,
"step": 74,
"token_acc": 0.8680019407348909
},
{
"epoch": 0.04983388704318937,
"grad_norm": 0.3358443081378937,
"learning_rate": 9.990254950676401e-06,
"loss": 0.38427734375,
"step": 75,
"token_acc": 0.8741284835889634
},
{
"epoch": 0.0504983388704319,
"grad_norm": 0.3837835192680359,
"learning_rate": 9.989571528601488e-06,
"loss": 0.409912109375,
"step": 76,
"token_acc": 0.8655285226045801
},
{
"epoch": 0.05116279069767442,
"grad_norm": 0.38427668809890747,
"learning_rate": 9.988864972445848e-06,
"loss": 0.40576171875,
"step": 77,
"token_acc": 0.8675548885974658
},
{
"epoch": 0.051827242524916946,
"grad_norm": 0.3456524610519409,
"learning_rate": 9.988135285485424e-06,
"loss": 0.39794921875,
"step": 78,
"token_acc": 0.8697487072037193
},
{
"epoch": 0.05249169435215947,
"grad_norm": 0.3337782323360443,
"learning_rate": 9.987382471103396e-06,
"loss": 0.412353515625,
"step": 79,
"token_acc": 0.8651893403502204
},
{
"epoch": 0.053156146179401995,
"grad_norm": 0.32159659266471863,
"learning_rate": 9.986606532790176e-06,
"loss": 0.39306640625,
"step": 80,
"token_acc": 0.8709713933961872
},
{
"epoch": 0.053820598006644516,
"grad_norm": 0.352824330329895,
"learning_rate": 9.985807474143398e-06,
"loss": 0.407470703125,
"step": 81,
"token_acc": 0.8661421135455756
},
{
"epoch": 0.05448504983388704,
"grad_norm": 0.3196597397327423,
"learning_rate": 9.984985298867882e-06,
"loss": 0.3994140625,
"step": 82,
"token_acc": 0.8695444297984946
},
{
"epoch": 0.05514950166112957,
"grad_norm": 0.39389872550964355,
"learning_rate": 9.984140010775632e-06,
"loss": 0.392822265625,
"step": 83,
"token_acc": 0.8720013065992871
},
{
"epoch": 0.05581395348837209,
"grad_norm": 0.36133959889411926,
"learning_rate": 9.983271613785817e-06,
"loss": 0.409423828125,
"step": 84,
"token_acc": 0.8669388109133649
},
{
"epoch": 0.05647840531561462,
"grad_norm": 0.5385559797286987,
"learning_rate": 9.982380111924745e-06,
"loss": 0.40625,
"step": 85,
"token_acc": 0.8673349105161934
},
{
"epoch": 0.05714285714285714,
"grad_norm": 0.3416942059993744,
"learning_rate": 9.981465509325856e-06,
"loss": 0.395263671875,
"step": 86,
"token_acc": 0.8711604214883545
},
{
"epoch": 0.05780730897009967,
"grad_norm": 0.34966039657592773,
"learning_rate": 9.98052781022969e-06,
"loss": 0.39697265625,
"step": 87,
"token_acc": 0.8693357881463367
},
{
"epoch": 0.05847176079734219,
"grad_norm": 0.39413613080978394,
"learning_rate": 9.979567018983878e-06,
"loss": 0.399658203125,
"step": 88,
"token_acc": 0.8699227798191486
},
{
"epoch": 0.05913621262458472,
"grad_norm": 0.3239847719669342,
"learning_rate": 9.978583140043115e-06,
"loss": 0.398681640625,
"step": 89,
"token_acc": 0.8685625633682563
},
{
"epoch": 0.059800664451827246,
"grad_norm": 0.3165834844112396,
"learning_rate": 9.977576177969139e-06,
"loss": 0.38330078125,
"step": 90,
"token_acc": 0.8743781169055783
},
{
"epoch": 0.06046511627906977,
"grad_norm": 0.3304702043533325,
"learning_rate": 9.97654613743072e-06,
"loss": 0.388427734375,
"step": 91,
"token_acc": 0.872408288248837
},
{
"epoch": 0.061129568106312294,
"grad_norm": 0.3728533387184143,
"learning_rate": 9.975493023203626e-06,
"loss": 0.401611328125,
"step": 92,
"token_acc": 0.8689907695810208
},
{
"epoch": 0.061794019933554815,
"grad_norm": 0.32515856623649597,
"learning_rate": 9.974416840170606e-06,
"loss": 0.40478515625,
"step": 93,
"token_acc": 0.8678915199239129
},
{
"epoch": 0.06245847176079734,
"grad_norm": 0.3131546378135681,
"learning_rate": 9.97331759332137e-06,
"loss": 0.398681640625,
"step": 94,
"token_acc": 0.8694052639637007
},
{
"epoch": 0.06312292358803986,
"grad_norm": 0.38560986518859863,
"learning_rate": 9.97219528775256e-06,
"loss": 0.401123046875,
"step": 95,
"token_acc": 0.8701016269364199
},
{
"epoch": 0.06378737541528239,
"grad_norm": 0.36294984817504883,
"learning_rate": 9.971049928667729e-06,
"loss": 0.40625,
"step": 96,
"token_acc": 0.867136229443602
},
{
"epoch": 0.06445182724252492,
"grad_norm": 0.30629536509513855,
"learning_rate": 9.96988152137732e-06,
"loss": 0.399658203125,
"step": 97,
"token_acc": 0.8686520431609672
},
{
"epoch": 0.06511627906976744,
"grad_norm": 0.35642099380493164,
"learning_rate": 9.968690071298638e-06,
"loss": 0.39404296875,
"step": 98,
"token_acc": 0.8707742016381476
},
{
"epoch": 0.06578073089700996,
"grad_norm": 0.37405431270599365,
"learning_rate": 9.967475583955824e-06,
"loss": 0.408935546875,
"step": 99,
"token_acc": 0.8671385347751086
},
{
"epoch": 0.0664451827242525,
"grad_norm": 0.47246551513671875,
"learning_rate": 9.966238064979835e-06,
"loss": 0.408935546875,
"step": 100,
"token_acc": 0.8665384784182923
},
{
"epoch": 0.06710963455149502,
"grad_norm": 0.30980801582336426,
"learning_rate": 9.964977520108407e-06,
"loss": 0.40478515625,
"step": 101,
"token_acc": 0.8675859626648945
},
{
"epoch": 0.06777408637873754,
"grad_norm": 0.3309335708618164,
"learning_rate": 9.963693955186043e-06,
"loss": 0.38916015625,
"step": 102,
"token_acc": 0.8726074378710159
},
{
"epoch": 0.06843853820598006,
"grad_norm": 0.4001266062259674,
"learning_rate": 9.962387376163972e-06,
"loss": 0.400390625,
"step": 103,
"token_acc": 0.8692478555483947
},
{
"epoch": 0.0691029900332226,
"grad_norm": 0.5296802520751953,
"learning_rate": 9.961057789100128e-06,
"loss": 0.387939453125,
"step": 104,
"token_acc": 0.8719843640141578
},
{
"epoch": 0.06976744186046512,
"grad_norm": 0.35080987215042114,
"learning_rate": 9.95970520015913e-06,
"loss": 0.414794921875,
"step": 105,
"token_acc": 0.8644743844180658
},
{
"epoch": 0.07043189368770764,
"grad_norm": 0.36742234230041504,
"learning_rate": 9.95832961561223e-06,
"loss": 0.403564453125,
"step": 106,
"token_acc": 0.8670302288116724
},
{
"epoch": 0.07109634551495017,
"grad_norm": 0.40374043583869934,
"learning_rate": 9.956931041837313e-06,
"loss": 0.39697265625,
"step": 107,
"token_acc": 0.8697002807223317
},
{
"epoch": 0.07176079734219269,
"grad_norm": 0.37924709916114807,
"learning_rate": 9.955509485318845e-06,
"loss": 0.400146484375,
"step": 108,
"token_acc": 0.8689146729941731
},
{
"epoch": 0.07242524916943521,
"grad_norm": 0.35846924781799316,
"learning_rate": 9.954064952647854e-06,
"loss": 0.400390625,
"step": 109,
"token_acc": 0.8679311622779926
},
{
"epoch": 0.07308970099667775,
"grad_norm": 0.3705119788646698,
"learning_rate": 9.952597450521897e-06,
"loss": 0.398193359375,
"step": 110,
"token_acc": 0.8696233967497148
},
{
"epoch": 0.07375415282392027,
"grad_norm": 0.34265726804733276,
"learning_rate": 9.951106985745024e-06,
"loss": 0.409423828125,
"step": 111,
"token_acc": 0.8662913999506899
},
{
"epoch": 0.07441860465116279,
"grad_norm": 0.31674009561538696,
"learning_rate": 9.949593565227762e-06,
"loss": 0.4033203125,
"step": 112,
"token_acc": 0.8684863807879741
},
{
"epoch": 0.07508305647840531,
"grad_norm": 0.33458206057548523,
"learning_rate": 9.948057195987057e-06,
"loss": 0.39599609375,
"step": 113,
"token_acc": 0.8697776455389638
},
{
"epoch": 0.07574750830564785,
"grad_norm": 0.3613218069076538,
"learning_rate": 9.94649788514627e-06,
"loss": 0.393798828125,
"step": 114,
"token_acc": 0.8711454381728087
},
{
"epoch": 0.07641196013289037,
"grad_norm": 0.37891489267349243,
"learning_rate": 9.94491563993512e-06,
"loss": 0.402587890625,
"step": 115,
"token_acc": 0.8683016353092374
},
{
"epoch": 0.07707641196013289,
"grad_norm": 0.32539016008377075,
"learning_rate": 9.943310467689666e-06,
"loss": 0.392822265625,
"step": 116,
"token_acc": 0.8713886651078406
},
{
"epoch": 0.07774086378737542,
"grad_norm": 0.3701838254928589,
"learning_rate": 9.941682375852272e-06,
"loss": 0.3876953125,
"step": 117,
"token_acc": 0.8729166772286843
},
{
"epoch": 0.07840531561461794,
"grad_norm": 0.39926812052726746,
"learning_rate": 9.940031371971559e-06,
"loss": 0.398193359375,
"step": 118,
"token_acc": 0.8697781234823694
},
{
"epoch": 0.07906976744186046,
"grad_norm": 0.3215719759464264,
"learning_rate": 9.938357463702387e-06,
"loss": 0.3935546875,
"step": 119,
"token_acc": 0.8709026016220519
},
{
"epoch": 0.07973421926910298,
"grad_norm": 0.34168076515197754,
"learning_rate": 9.936660658805806e-06,
"loss": 0.402099609375,
"step": 120,
"token_acc": 0.8682460597614654
},
{
"epoch": 0.08039867109634552,
"grad_norm": 0.3355630040168762,
"learning_rate": 9.93494096514903e-06,
"loss": 0.406005859375,
"step": 121,
"token_acc": 0.867558401507734
},
{
"epoch": 0.08106312292358804,
"grad_norm": 0.3503526449203491,
"learning_rate": 9.933198390705397e-06,
"loss": 0.387451171875,
"step": 122,
"token_acc": 0.8730956043111542
},
{
"epoch": 0.08172757475083056,
"grad_norm": 0.42151138186454773,
"learning_rate": 9.931432943554329e-06,
"loss": 0.41552734375,
"step": 123,
"token_acc": 0.8649017752224621
},
{
"epoch": 0.0823920265780731,
"grad_norm": 0.33070817589759827,
"learning_rate": 9.929644631881296e-06,
"loss": 0.40283203125,
"step": 124,
"token_acc": 0.8677728482697427
},
{
"epoch": 0.08305647840531562,
"grad_norm": 0.3893410861492157,
"learning_rate": 9.927833463977783e-06,
"loss": 0.40771484375,
"step": 125,
"token_acc": 0.8664136977347535
},
{
"epoch": 0.08372093023255814,
"grad_norm": 0.36076223850250244,
"learning_rate": 9.925999448241245e-06,
"loss": 0.404052734375,
"step": 126,
"token_acc": 0.8675237588681122
},
{
"epoch": 0.08438538205980066,
"grad_norm": 0.3242746889591217,
"learning_rate": 9.924142593175071e-06,
"loss": 0.372802734375,
"step": 127,
"token_acc": 0.877090894024662
},
{
"epoch": 0.0850498338870432,
"grad_norm": 0.4951179623603821,
"learning_rate": 9.922262907388542e-06,
"loss": 0.388916015625,
"step": 128,
"token_acc": 0.871943738362742
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.3386238217353821,
"learning_rate": 9.920360399596798e-06,
"loss": 0.38818359375,
"step": 129,
"token_acc": 0.8729553448514529
},
{
"epoch": 0.08637873754152824,
"grad_norm": 0.311327189207077,
"learning_rate": 9.918435078620792e-06,
"loss": 0.389404296875,
"step": 130,
"token_acc": 0.8725015476427633
},
{
"epoch": 0.08704318936877077,
"grad_norm": 0.400531530380249,
"learning_rate": 9.916486953387247e-06,
"loss": 0.400146484375,
"step": 131,
"token_acc": 0.869601651486664
},
{
"epoch": 0.08770764119601329,
"grad_norm": 0.5043191909790039,
"learning_rate": 9.914516032928618e-06,
"loss": 0.3857421875,
"step": 132,
"token_acc": 0.8735046804267601
},
{
"epoch": 0.08837209302325581,
"grad_norm": 0.339206337928772,
"learning_rate": 9.912522326383052e-06,
"loss": 0.4208984375,
"step": 133,
"token_acc": 0.8626804458476187
},
{
"epoch": 0.08903654485049833,
"grad_norm": 0.32653316855430603,
"learning_rate": 9.910505842994343e-06,
"loss": 0.392822265625,
"step": 134,
"token_acc": 0.8712748254097038
},
{
"epoch": 0.08970099667774087,
"grad_norm": 0.4853458106517792,
"learning_rate": 9.908466592111887e-06,
"loss": 0.400146484375,
"step": 135,
"token_acc": 0.869519215791536
},
{
"epoch": 0.09036544850498339,
"grad_norm": 0.3116317391395569,
"learning_rate": 9.906404583190646e-06,
"loss": 0.404296875,
"step": 136,
"token_acc": 0.8679377345212573
},
{
"epoch": 0.09102990033222591,
"grad_norm": 0.3144552409648895,
"learning_rate": 9.904319825791094e-06,
"loss": 0.39306640625,
"step": 137,
"token_acc": 0.8709423808330988
},
{
"epoch": 0.09169435215946845,
"grad_norm": 0.32141605019569397,
"learning_rate": 9.902212329579182e-06,
"loss": 0.41357421875,
"step": 138,
"token_acc": 0.8640805175557202
},
{
"epoch": 0.09235880398671097,
"grad_norm": 0.438242644071579,
"learning_rate": 9.900082104326284e-06,
"loss": 0.400634765625,
"step": 139,
"token_acc": 0.8685913459333895
},
{
"epoch": 0.09302325581395349,
"grad_norm": 0.3710990250110626,
"learning_rate": 9.897929159909168e-06,
"loss": 0.410400390625,
"step": 140,
"token_acc": 0.8671641151756099
},
{
"epoch": 0.09368770764119601,
"grad_norm": 0.3444954752922058,
"learning_rate": 9.895753506309923e-06,
"loss": 0.399169921875,
"step": 141,
"token_acc": 0.8691030938913474
},
{
"epoch": 0.09435215946843854,
"grad_norm": 0.33866995573043823,
"learning_rate": 9.893555153615942e-06,
"loss": 0.39501953125,
"step": 142,
"token_acc": 0.8702185028383329
},
{
"epoch": 0.09501661129568106,
"grad_norm": 0.3861258327960968,
"learning_rate": 9.891334112019858e-06,
"loss": 0.402587890625,
"step": 143,
"token_acc": 0.8684216413194356
},
{
"epoch": 0.09568106312292358,
"grad_norm": 0.3470675051212311,
"learning_rate": 9.889090391819499e-06,
"loss": 0.418212890625,
"step": 144,
"token_acc": 0.8631844750219396
},
{
"epoch": 0.09634551495016612,
"grad_norm": 0.4245740473270416,
"learning_rate": 9.886824003417841e-06,
"loss": 0.400146484375,
"step": 145,
"token_acc": 0.8701846078343306
},
{
"epoch": 0.09700996677740864,
"grad_norm": 0.3204965889453888,
"learning_rate": 9.884534957322967e-06,
"loss": 0.388671875,
"step": 146,
"token_acc": 0.8723466490974253
},
{
"epoch": 0.09767441860465116,
"grad_norm": 0.3347446620464325,
"learning_rate": 9.882223264148007e-06,
"loss": 0.3935546875,
"step": 147,
"token_acc": 0.8707164130271097
},
{
"epoch": 0.09833887043189368,
"grad_norm": 0.31049609184265137,
"learning_rate": 9.879888934611093e-06,
"loss": 0.389892578125,
"step": 148,
"token_acc": 0.8713873504418044
},
{
"epoch": 0.09900332225913622,
"grad_norm": 0.3779807686805725,
"learning_rate": 9.877531979535315e-06,
"loss": 0.393310546875,
"step": 149,
"token_acc": 0.8705860175161906
},
{
"epoch": 0.09966777408637874,
"grad_norm": 0.3279036581516266,
"learning_rate": 9.875152409848662e-06,
"loss": 0.388671875,
"step": 150,
"token_acc": 0.8725996892462144
},
{
"epoch": 0.10033222591362126,
"grad_norm": 0.3144179880619049,
"learning_rate": 9.872750236583976e-06,
"loss": 0.41455078125,
"step": 151,
"token_acc": 0.8646503920989599
},
{
"epoch": 0.1009966777408638,
"grad_norm": 0.41906532645225525,
"learning_rate": 9.870325470878901e-06,
"loss": 0.39892578125,
"step": 152,
"token_acc": 0.8688814430403494
},
{
"epoch": 0.10166112956810631,
"grad_norm": 0.3263643682003021,
"learning_rate": 9.867878123975832e-06,
"loss": 0.389892578125,
"step": 153,
"token_acc": 0.871900640853938
},
{
"epoch": 0.10232558139534884,
"grad_norm": 0.3127242922782898,
"learning_rate": 9.865408207221858e-06,
"loss": 0.400146484375,
"step": 154,
"token_acc": 0.8692761633169367
},
{
"epoch": 0.10299003322259136,
"grad_norm": 0.40848925709724426,
"learning_rate": 9.862915732068715e-06,
"loss": 0.38916015625,
"step": 155,
"token_acc": 0.8721776990808343
},
{
"epoch": 0.10365448504983389,
"grad_norm": 0.3351116478443146,
"learning_rate": 9.86040071007273e-06,
"loss": 0.39013671875,
"step": 156,
"token_acc": 0.8715447047533551
},
{
"epoch": 0.10431893687707641,
"grad_norm": 0.2943994402885437,
"learning_rate": 9.85786315289477e-06,
"loss": 0.41357421875,
"step": 157,
"token_acc": 0.8647223259779874
},
{
"epoch": 0.10498338870431893,
"grad_norm": 0.3208179771900177,
"learning_rate": 9.85530307230018e-06,
"loss": 0.404052734375,
"step": 158,
"token_acc": 0.868371677708818
},
{
"epoch": 0.10564784053156147,
"grad_norm": 0.3213667869567871,
"learning_rate": 9.852720480158744e-06,
"loss": 0.3818359375,
"step": 159,
"token_acc": 0.8748765290041364
},
{
"epoch": 0.10631229235880399,
"grad_norm": 0.33461764454841614,
"learning_rate": 9.850115388444614e-06,
"loss": 0.40234375,
"step": 160,
"token_acc": 0.8677833028291086
},
{
"epoch": 0.10697674418604651,
"grad_norm": 0.34306567907333374,
"learning_rate": 9.84748780923626e-06,
"loss": 0.388427734375,
"step": 161,
"token_acc": 0.8719384230530794
},
{
"epoch": 0.10764119601328903,
"grad_norm": 0.3384004235267639,
"learning_rate": 9.84483775471642e-06,
"loss": 0.400146484375,
"step": 162,
"token_acc": 0.8691446067810925
},
{
"epoch": 0.10830564784053157,
"grad_norm": 0.4016912281513214,
"learning_rate": 9.842165237172034e-06,
"loss": 0.4052734375,
"step": 163,
"token_acc": 0.8673273795945037
},
{
"epoch": 0.10897009966777409,
"grad_norm": 0.3207138776779175,
"learning_rate": 9.839470268994195e-06,
"loss": 0.4111328125,
"step": 164,
"token_acc": 0.86681276275004
},
{
"epoch": 0.10963455149501661,
"grad_norm": 0.36941155791282654,
"learning_rate": 9.836752862678087e-06,
"loss": 0.394287109375,
"step": 165,
"token_acc": 0.8713484007516306
},
{
"epoch": 0.11029900332225914,
"grad_norm": 0.3264721632003784,
"learning_rate": 9.834013030822926e-06,
"loss": 0.398193359375,
"step": 166,
"token_acc": 0.8696471356235188
},
{
"epoch": 0.11096345514950166,
"grad_norm": 0.4093307554721832,
"learning_rate": 9.831250786131905e-06,
"loss": 0.393310546875,
"step": 167,
"token_acc": 0.8711054373163521
},
{
"epoch": 0.11162790697674418,
"grad_norm": 0.3767301142215729,
"learning_rate": 9.828466141412135e-06,
"loss": 0.39892578125,
"step": 168,
"token_acc": 0.8691457015417381
},
{
"epoch": 0.1122923588039867,
"grad_norm": 0.3588705360889435,
"learning_rate": 9.825659109574584e-06,
"loss": 0.40771484375,
"step": 169,
"token_acc": 0.8663953704327646
},
{
"epoch": 0.11295681063122924,
"grad_norm": 0.3255632221698761,
"learning_rate": 9.822829703634014e-06,
"loss": 0.39306640625,
"step": 170,
"token_acc": 0.8710232898057114
},
{
"epoch": 0.11362126245847176,
"grad_norm": 0.3362259268760681,
"learning_rate": 9.819977936708931e-06,
"loss": 0.411376953125,
"step": 171,
"token_acc": 0.8657624470371542
},
{
"epoch": 0.11428571428571428,
"grad_norm": 0.32704809308052063,
"learning_rate": 9.81710382202151e-06,
"loss": 0.39306640625,
"step": 172,
"token_acc": 0.8707981647178417
},
{
"epoch": 0.11495016611295682,
"grad_norm": 0.37108832597732544,
"learning_rate": 9.814207372897548e-06,
"loss": 0.39306640625,
"step": 173,
"token_acc": 0.8706603711611993
},
{
"epoch": 0.11561461794019934,
"grad_norm": 0.3386399745941162,
"learning_rate": 9.811288602766392e-06,
"loss": 0.381103515625,
"step": 174,
"token_acc": 0.8741954185390481
},
{
"epoch": 0.11627906976744186,
"grad_norm": 0.32836610078811646,
"learning_rate": 9.808347525160879e-06,
"loss": 0.399169921875,
"step": 175,
"token_acc": 0.8690814180301126
},
{
"epoch": 0.11694352159468438,
"grad_norm": 0.35498279333114624,
"learning_rate": 9.805384153717275e-06,
"loss": 0.40087890625,
"step": 176,
"token_acc": 0.8687123173225526
},
{
"epoch": 0.11760797342192691,
"grad_norm": 0.4251721501350403,
"learning_rate": 9.802398502175212e-06,
"loss": 0.39990234375,
"step": 177,
"token_acc": 0.8687494134374761
},
{
"epoch": 0.11827242524916944,
"grad_norm": 0.3648131787776947,
"learning_rate": 9.799390584377621e-06,
"loss": 0.423828125,
"step": 178,
"token_acc": 0.863310732383219
},
{
"epoch": 0.11893687707641196,
"grad_norm": 0.36038780212402344,
"learning_rate": 9.796360414270676e-06,
"loss": 0.39306640625,
"step": 179,
"token_acc": 0.8717255662084956
},
{
"epoch": 0.11960132890365449,
"grad_norm": 0.48658981919288635,
"learning_rate": 9.793308005903716e-06,
"loss": 0.40185546875,
"step": 180,
"token_acc": 0.8683223074235651
},
{
"epoch": 0.12026578073089701,
"grad_norm": 0.29339200258255005,
"learning_rate": 9.790233373429195e-06,
"loss": 0.404296875,
"step": 181,
"token_acc": 0.8671003606713319
},
{
"epoch": 0.12093023255813953,
"grad_norm": 0.3267621695995331,
"learning_rate": 9.7871365311026e-06,
"loss": 0.380859375,
"step": 182,
"token_acc": 0.8741399994297733
},
{
"epoch": 0.12159468438538205,
"grad_norm": 0.3824863135814667,
"learning_rate": 9.784017493282403e-06,
"loss": 0.396484375,
"step": 183,
"token_acc": 0.8693034466136419
},
{
"epoch": 0.12225913621262459,
"grad_norm": 0.31760460138320923,
"learning_rate": 9.780876274429978e-06,
"loss": 0.399658203125,
"step": 184,
"token_acc": 0.8689219147441392
},
{
"epoch": 0.12292358803986711,
"grad_norm": 0.37254786491394043,
"learning_rate": 9.777712889109543e-06,
"loss": 0.398193359375,
"step": 185,
"token_acc": 0.8688465648201286
},
{
"epoch": 0.12358803986710963,
"grad_norm": 0.5026144981384277,
"learning_rate": 9.774527351988092e-06,
"loss": 0.40625,
"step": 186,
"token_acc": 0.867349501178247
},
{
"epoch": 0.12425249169435217,
"grad_norm": 0.2981654703617096,
"learning_rate": 9.771319677835325e-06,
"loss": 0.40771484375,
"step": 187,
"token_acc": 0.8667493654480267
},
{
"epoch": 0.12491694352159469,
"grad_norm": 0.8839625120162964,
"learning_rate": 9.768089881523579e-06,
"loss": 0.415771484375,
"step": 188,
"token_acc": 0.8636917540624317
},
{
"epoch": 0.12558139534883722,
"grad_norm": 0.3370588719844818,
"learning_rate": 9.764837978027761e-06,
"loss": 0.394287109375,
"step": 189,
"token_acc": 0.8714053975155417
},
{
"epoch": 0.12624584717607973,
"grad_norm": 0.3549683392047882,
"learning_rate": 9.761563982425279e-06,
"loss": 0.402587890625,
"step": 190,
"token_acc": 0.8679337712583041
},
{
"epoch": 0.12691029900332226,
"grad_norm": 0.30366772413253784,
"learning_rate": 9.758267909895966e-06,
"loss": 0.380859375,
"step": 191,
"token_acc": 0.8745116376233455
},
{
"epoch": 0.12757475083056477,
"grad_norm": 0.34283390641212463,
"learning_rate": 9.754949775722022e-06,
"loss": 0.38330078125,
"step": 192,
"token_acc": 0.873324600799774
},
{
"epoch": 0.1282392026578073,
"grad_norm": 0.31559091806411743,
"learning_rate": 9.751609595287928e-06,
"loss": 0.392333984375,
"step": 193,
"token_acc": 0.8707110796125679
},
{
"epoch": 0.12890365448504984,
"grad_norm": 0.3621273636817932,
"learning_rate": 9.748247384080384e-06,
"loss": 0.40380859375,
"step": 194,
"token_acc": 0.8678270102849908
},
{
"epoch": 0.12956810631229235,
"grad_norm": 0.30913233757019043,
"learning_rate": 9.74486315768824e-06,
"loss": 0.39599609375,
"step": 195,
"token_acc": 0.8706236652094043
},
{
"epoch": 0.13023255813953488,
"grad_norm": 0.31845033168792725,
"learning_rate": 9.741456931802415e-06,
"loss": 0.40380859375,
"step": 196,
"token_acc": 0.8679240770885948
},
{
"epoch": 0.13089700996677742,
"grad_norm": 0.41279321908950806,
"learning_rate": 9.738028722215826e-06,
"loss": 0.386962890625,
"step": 197,
"token_acc": 0.8729940676156799
},
{
"epoch": 0.13156146179401992,
"grad_norm": 0.33431193232536316,
"learning_rate": 9.734578544823326e-06,
"loss": 0.39599609375,
"step": 198,
"token_acc": 0.8711745035432261
},
{
"epoch": 0.13222591362126246,
"grad_norm": 0.3859500288963318,
"learning_rate": 9.73110641562161e-06,
"loss": 0.385009765625,
"step": 199,
"token_acc": 0.8739121422238043
},
{
"epoch": 0.132890365448505,
"grad_norm": 0.35276520252227783,
"learning_rate": 9.727612350709161e-06,
"loss": 0.412109375,
"step": 200,
"token_acc": 0.8656328405866508
},
{
"epoch": 0.1335548172757475,
"grad_norm": 0.3505283296108246,
"learning_rate": 9.724096366286162e-06,
"loss": 0.400390625,
"step": 201,
"token_acc": 0.8696009140654697
},
{
"epoch": 0.13421926910299004,
"grad_norm": 0.37506866455078125,
"learning_rate": 9.720558478654429e-06,
"loss": 0.3896484375,
"step": 202,
"token_acc": 0.8721206613997008
},
{
"epoch": 0.13488372093023257,
"grad_norm": 0.3067897856235504,
"learning_rate": 9.716998704217329e-06,
"loss": 0.407958984375,
"step": 203,
"token_acc": 0.8661103584824166
},
{
"epoch": 0.13554817275747508,
"grad_norm": 0.3377469778060913,
"learning_rate": 9.713417059479708e-06,
"loss": 0.3974609375,
"step": 204,
"token_acc": 0.8699676242776936
},
{
"epoch": 0.1362126245847176,
"grad_norm": 0.341371089220047,
"learning_rate": 9.709813561047814e-06,
"loss": 0.3857421875,
"step": 205,
"token_acc": 0.872837855565821
},
{
"epoch": 0.13687707641196012,
"grad_norm": 0.40457719564437866,
"learning_rate": 9.706188225629215e-06,
"loss": 0.409423828125,
"step": 206,
"token_acc": 0.8661488329674804
},
{
"epoch": 0.13754152823920265,
"grad_norm": 0.5455163717269897,
"learning_rate": 9.702541070032736e-06,
"loss": 0.39453125,
"step": 207,
"token_acc": 0.8712232461222034
},
{
"epoch": 0.1382059800664452,
"grad_norm": 0.3177371025085449,
"learning_rate": 9.698872111168358e-06,
"loss": 0.383056640625,
"step": 208,
"token_acc": 0.8737463345789261
},
{
"epoch": 0.1388704318936877,
"grad_norm": 0.591479480266571,
"learning_rate": 9.695181366047163e-06,
"loss": 0.399658203125,
"step": 209,
"token_acc": 0.868439667393595
},
{
"epoch": 0.13953488372093023,
"grad_norm": 0.3593539893627167,
"learning_rate": 9.691468851781239e-06,
"loss": 0.407958984375,
"step": 210,
"token_acc": 0.8667547993398194
},
{
"epoch": 0.14019933554817277,
"grad_norm": 0.40368324518203735,
"learning_rate": 9.687734585583609e-06,
"loss": 0.38818359375,
"step": 211,
"token_acc": 0.8727109679463013
},
{
"epoch": 0.14086378737541527,
"grad_norm": 0.36480918526649475,
"learning_rate": 9.683978584768147e-06,
"loss": 0.390869140625,
"step": 212,
"token_acc": 0.8716076685912648
},
{
"epoch": 0.1415282392026578,
"grad_norm": 0.40862250328063965,
"learning_rate": 9.6802008667495e-06,
"loss": 0.39892578125,
"step": 213,
"token_acc": 0.86894173522342
},
{
"epoch": 0.14219269102990034,
"grad_norm": 0.327587366104126,
"learning_rate": 9.676401449043006e-06,
"loss": 0.40673828125,
"step": 214,
"token_acc": 0.8663272462649492
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.3087397813796997,
"learning_rate": 9.672580349264615e-06,
"loss": 0.3857421875,
"step": 215,
"token_acc": 0.8734414226682441
},
{
"epoch": 0.14352159468438538,
"grad_norm": 0.34060296416282654,
"learning_rate": 9.668737585130801e-06,
"loss": 0.406982421875,
"step": 216,
"token_acc": 0.8659608378226124
},
{
"epoch": 0.14418604651162792,
"grad_norm": 0.4111344516277313,
"learning_rate": 9.664873174458491e-06,
"loss": 0.4111328125,
"step": 217,
"token_acc": 0.8658226021211021
},
{
"epoch": 0.14485049833887043,
"grad_norm": 0.32795846462249756,
"learning_rate": 9.660987135164973e-06,
"loss": 0.395263671875,
"step": 218,
"token_acc": 0.8705327204292901
},
{
"epoch": 0.14551495016611296,
"grad_norm": 0.37067312002182007,
"learning_rate": 9.657079485267813e-06,
"loss": 0.402587890625,
"step": 219,
"token_acc": 0.8678936946371358
},
{
"epoch": 0.1461794019933555,
"grad_norm": 0.3332381844520569,
"learning_rate": 9.65315024288478e-06,
"loss": 0.409423828125,
"step": 220,
"token_acc": 0.8666489572941498
},
{
"epoch": 0.146843853820598,
"grad_norm": 0.3578885495662689,
"learning_rate": 9.649199426233748e-06,
"loss": 0.400146484375,
"step": 221,
"token_acc": 0.86908689696343
},
{
"epoch": 0.14750830564784054,
"grad_norm": 0.8276354670524597,
"learning_rate": 9.64522705363263e-06,
"loss": 0.395263671875,
"step": 222,
"token_acc": 0.8701266196028952
},
{
"epoch": 0.14817275747508304,
"grad_norm": 0.32939863204956055,
"learning_rate": 9.641233143499274e-06,
"loss": 0.390380859375,
"step": 223,
"token_acc": 0.8712053042477057
},
{
"epoch": 0.14883720930232558,
"grad_norm": 0.3627006709575653,
"learning_rate": 9.637217714351392e-06,
"loss": 0.396240234375,
"step": 224,
"token_acc": 0.8694965968885002
},
{
"epoch": 0.14950166112956811,
"grad_norm": 0.3268877863883972,
"learning_rate": 9.633180784806468e-06,
"loss": 0.4091796875,
"step": 225,
"token_acc": 0.8670361176542626
},
{
"epoch": 0.15016611295681062,
"grad_norm": 0.33783403038978577,
"learning_rate": 9.629122373581668e-06,
"loss": 0.391357421875,
"step": 226,
"token_acc": 0.871952160323751
},
{
"epoch": 0.15083056478405316,
"grad_norm": 0.448666512966156,
"learning_rate": 9.625042499493764e-06,
"loss": 0.39013671875,
"step": 227,
"token_acc": 0.8720324934570671
},
{
"epoch": 0.1514950166112957,
"grad_norm": 0.3673129975795746,
"learning_rate": 9.620941181459033e-06,
"loss": 0.3974609375,
"step": 228,
"token_acc": 0.8701506309362167
},
{
"epoch": 0.1521594684385382,
"grad_norm": 0.38613414764404297,
"learning_rate": 9.616818438493183e-06,
"loss": 0.379638671875,
"step": 229,
"token_acc": 0.8752439562865658
},
{
"epoch": 0.15282392026578073,
"grad_norm": 0.3849971890449524,
"learning_rate": 9.612674289711256e-06,
"loss": 0.389892578125,
"step": 230,
"token_acc": 0.8711368796387849
},
{
"epoch": 0.15348837209302327,
"grad_norm": 0.32757845520973206,
"learning_rate": 9.60850875432754e-06,
"loss": 0.419921875,
"step": 231,
"token_acc": 0.8625827880246878
},
{
"epoch": 0.15415282392026577,
"grad_norm": 0.39691653847694397,
"learning_rate": 9.604321851655485e-06,
"loss": 0.416259765625,
"step": 232,
"token_acc": 0.8648300311407564
},
{
"epoch": 0.1548172757475083,
"grad_norm": 0.34852269291877747,
"learning_rate": 9.600113601107607e-06,
"loss": 0.40771484375,
"step": 233,
"token_acc": 0.8673265464332044
},
{
"epoch": 0.15548172757475084,
"grad_norm": 0.3006671071052551,
"learning_rate": 9.595884022195406e-06,
"loss": 0.3935546875,
"step": 234,
"token_acc": 0.8706770434238698
},
{
"epoch": 0.15614617940199335,
"grad_norm": 0.36429914832115173,
"learning_rate": 9.59163313452926e-06,
"loss": 0.39599609375,
"step": 235,
"token_acc": 0.8701355795875868
},
{
"epoch": 0.1568106312292359,
"grad_norm": 0.39522895216941833,
"learning_rate": 9.58736095781836e-06,
"loss": 0.379638671875,
"step": 236,
"token_acc": 0.8751161077122315
},
{
"epoch": 0.1574750830564784,
"grad_norm": 0.3645418584346771,
"learning_rate": 9.583067511870592e-06,
"loss": 0.385498046875,
"step": 237,
"token_acc": 0.8727504814749382
},
{
"epoch": 0.15813953488372093,
"grad_norm": 0.3494720757007599,
"learning_rate": 9.578752816592458e-06,
"loss": 0.4033203125,
"step": 238,
"token_acc": 0.8692333026094972
},
{
"epoch": 0.15880398671096346,
"grad_norm": 0.34284812211990356,
"learning_rate": 9.574416891988987e-06,
"loss": 0.399169921875,
"step": 239,
"token_acc": 0.869123809356128
},
{
"epoch": 0.15946843853820597,
"grad_norm": 0.37843406200408936,
"learning_rate": 9.570059758163634e-06,
"loss": 0.3896484375,
"step": 240,
"token_acc": 0.8714420177539806
},
{
"epoch": 0.1601328903654485,
"grad_norm": 0.3323161005973816,
"learning_rate": 9.56568143531819e-06,
"loss": 0.401123046875,
"step": 241,
"token_acc": 0.8689622032030923
},
{
"epoch": 0.16079734219269104,
"grad_norm": 0.3518533408641815,
"learning_rate": 9.561281943752691e-06,
"loss": 0.4091796875,
"step": 242,
"token_acc": 0.8666717694177706
},
{
"epoch": 0.16146179401993355,
"grad_norm": 0.8659685254096985,
"learning_rate": 9.556861303865318e-06,
"loss": 0.39501953125,
"step": 243,
"token_acc": 0.869894151616078
},
{
"epoch": 0.16212624584717608,
"grad_norm": 0.3152049481868744,
"learning_rate": 9.552419536152308e-06,
"loss": 0.385986328125,
"step": 244,
"token_acc": 0.8728143765081624
},
{
"epoch": 0.16279069767441862,
"grad_norm": 0.31343042850494385,
"learning_rate": 9.54795666120786e-06,
"loss": 0.402099609375,
"step": 245,
"token_acc": 0.8687943183857197
},
{
"epoch": 0.16345514950166112,
"grad_norm": 0.32472360134124756,
"learning_rate": 9.54347269972403e-06,
"loss": 0.3857421875,
"step": 246,
"token_acc": 0.872513643513865
},
{
"epoch": 0.16411960132890366,
"grad_norm": 0.3384128510951996,
"learning_rate": 9.538967672490646e-06,
"loss": 0.4013671875,
"step": 247,
"token_acc": 0.8681260394756479
},
{
"epoch": 0.1647840531561462,
"grad_norm": 0.38958999514579773,
"learning_rate": 9.534441600395203e-06,
"loss": 0.3916015625,
"step": 248,
"token_acc": 0.8717481433482056
},
{
"epoch": 0.1654485049833887,
"grad_norm": 0.4059273600578308,
"learning_rate": 9.529894504422777e-06,
"loss": 0.41259765625,
"step": 249,
"token_acc": 0.8651882314979837
},
{
"epoch": 0.16611295681063123,
"grad_norm": 0.32635173201560974,
"learning_rate": 9.525326405655914e-06,
"loss": 0.410888671875,
"step": 250,
"token_acc": 0.865805893685962
},
{
"epoch": 0.16677740863787374,
"grad_norm": 0.3605281710624695,
"learning_rate": 9.520737325274544e-06,
"loss": 0.378173828125,
"step": 251,
"token_acc": 0.8764572310842031
},
{
"epoch": 0.16744186046511628,
"grad_norm": 0.3379956781864166,
"learning_rate": 9.516127284555874e-06,
"loss": 0.408203125,
"step": 252,
"token_acc": 0.8674066031114875
},
{
"epoch": 0.1681063122923588,
"grad_norm": 0.35810860991477966,
"learning_rate": 9.511496304874294e-06,
"loss": 0.378662109375,
"step": 253,
"token_acc": 0.8754635590573545
},
{
"epoch": 0.16877076411960132,
"grad_norm": 0.46297332644462585,
"learning_rate": 9.506844407701283e-06,
"loss": 0.376708984375,
"step": 254,
"token_acc": 0.8754675272458177
},
{
"epoch": 0.16943521594684385,
"grad_norm": 0.338838130235672,
"learning_rate": 9.502171614605295e-06,
"loss": 0.39501953125,
"step": 255,
"token_acc": 0.8701851812507865
},
{
"epoch": 0.1700996677740864,
"grad_norm": 0.345367431640625,
"learning_rate": 9.497477947251677e-06,
"loss": 0.370849609375,
"step": 256,
"token_acc": 0.8779050481535204
},
{
"epoch": 0.1707641196013289,
"grad_norm": 0.3605043292045593,
"learning_rate": 9.492763427402548e-06,
"loss": 0.38720703125,
"step": 257,
"token_acc": 0.872342182267344
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.32038503885269165,
"learning_rate": 9.488028076916717e-06,
"loss": 0.394287109375,
"step": 258,
"token_acc": 0.8699377828527334
},
{
"epoch": 0.17209302325581396,
"grad_norm": 0.421758234500885,
"learning_rate": 9.483271917749573e-06,
"loss": 0.390625,
"step": 259,
"token_acc": 0.8720226833477281
},
{
"epoch": 0.17275747508305647,
"grad_norm": 0.35105180740356445,
"learning_rate": 9.478494971952985e-06,
"loss": 0.402099609375,
"step": 260,
"token_acc": 0.8679115317150303
},
{
"epoch": 0.173421926910299,
"grad_norm": 0.43273764848709106,
"learning_rate": 9.473697261675195e-06,
"loss": 0.38134765625,
"step": 261,
"token_acc": 0.8740214525003641
},
{
"epoch": 0.17408637873754154,
"grad_norm": 0.34283486008644104,
"learning_rate": 9.468878809160723e-06,
"loss": 0.37353515625,
"step": 262,
"token_acc": 0.8771094961534953
},
{
"epoch": 0.17475083056478405,
"grad_norm": 0.30679354071617126,
"learning_rate": 9.46403963675026e-06,
"loss": 0.3994140625,
"step": 263,
"token_acc": 0.8689192446184323
},
{
"epoch": 0.17541528239202658,
"grad_norm": 0.3997681736946106,
"learning_rate": 9.459179766880559e-06,
"loss": 0.388427734375,
"step": 264,
"token_acc": 0.8721168950761063
},
{
"epoch": 0.1760797342192691,
"grad_norm": 0.3312614858150482,
"learning_rate": 9.454299222084347e-06,
"loss": 0.381103515625,
"step": 265,
"token_acc": 0.8750077053239762
},
{
"epoch": 0.17674418604651163,
"grad_norm": 0.6371876001358032,
"learning_rate": 9.449398024990197e-06,
"loss": 0.39404296875,
"step": 266,
"token_acc": 0.8708973458995228
},
{
"epoch": 0.17740863787375416,
"grad_norm": 0.3508185148239136,
"learning_rate": 9.444476198322448e-06,
"loss": 0.39404296875,
"step": 267,
"token_acc": 0.8712763483820689
},
{
"epoch": 0.17807308970099667,
"grad_norm": 0.2863066494464874,
"learning_rate": 9.439533764901079e-06,
"loss": 0.39013671875,
"step": 268,
"token_acc": 0.8717401450371054
},
{
"epoch": 0.1787375415282392,
"grad_norm": 0.2946258783340454,
"learning_rate": 9.434570747641617e-06,
"loss": 0.39404296875,
"step": 269,
"token_acc": 0.8699763240327335
},
{
"epoch": 0.17940199335548174,
"grad_norm": 0.32337528467178345,
"learning_rate": 9.429587169555025e-06,
"loss": 0.3828125,
"step": 270,
"token_acc": 0.8736828192017724
},
{
"epoch": 0.18006644518272424,
"grad_norm": 0.36138439178466797,
"learning_rate": 9.424583053747596e-06,
"loss": 0.408447265625,
"step": 271,
"token_acc": 0.8672851256777373
},
{
"epoch": 0.18073089700996678,
"grad_norm": 0.5077350735664368,
"learning_rate": 9.41955842342084e-06,
"loss": 0.392333984375,
"step": 272,
"token_acc": 0.870810201540998
},
{
"epoch": 0.1813953488372093,
"grad_norm": 0.293709397315979,
"learning_rate": 9.414513301871395e-06,
"loss": 0.386962890625,
"step": 273,
"token_acc": 0.8726319193509835
},
{
"epoch": 0.18205980066445182,
"grad_norm": 0.336428165435791,
"learning_rate": 9.409447712490893e-06,
"loss": 0.41943359375,
"step": 274,
"token_acc": 0.8634024049953899
},
{
"epoch": 0.18272425249169436,
"grad_norm": 0.3187560737133026,
"learning_rate": 9.404361678765872e-06,
"loss": 0.41552734375,
"step": 275,
"token_acc": 0.8647983931645459
},
{
"epoch": 0.1833887043189369,
"grad_norm": 0.3785070478916168,
"learning_rate": 9.399255224277658e-06,
"loss": 0.40771484375,
"step": 276,
"token_acc": 0.8664006335091688
},
{
"epoch": 0.1840531561461794,
"grad_norm": 0.38421592116355896,
"learning_rate": 9.394128372702261e-06,
"loss": 0.391357421875,
"step": 277,
"token_acc": 0.8715071357198131
},
{
"epoch": 0.18471760797342193,
"grad_norm": 0.43781402707099915,
"learning_rate": 9.388981147810254e-06,
"loss": 0.39892578125,
"step": 278,
"token_acc": 0.8685533895163209
},
{
"epoch": 0.18538205980066444,
"grad_norm": 0.3524091839790344,
"learning_rate": 9.383813573466678e-06,
"loss": 0.411376953125,
"step": 279,
"token_acc": 0.8664674660064204
},
{
"epoch": 0.18604651162790697,
"grad_norm": 0.28812122344970703,
"learning_rate": 9.37862567363092e-06,
"loss": 0.40380859375,
"step": 280,
"token_acc": 0.8691321616017808
},
{
"epoch": 0.1867109634551495,
"grad_norm": 0.32244905829429626,
"learning_rate": 9.373417472356612e-06,
"loss": 0.383056640625,
"step": 281,
"token_acc": 0.8741653762439494
},
{
"epoch": 0.18737541528239202,
"grad_norm": 0.31628721952438354,
"learning_rate": 9.368188993791502e-06,
"loss": 0.410888671875,
"step": 282,
"token_acc": 0.8654109235744497
},
{
"epoch": 0.18803986710963455,
"grad_norm": 0.4080207943916321,
"learning_rate": 9.362940262177362e-06,
"loss": 0.38134765625,
"step": 283,
"token_acc": 0.8746887170262772
},
{
"epoch": 0.18870431893687709,
"grad_norm": 0.313852995634079,
"learning_rate": 9.357671301849868e-06,
"loss": 0.40966796875,
"step": 284,
"token_acc": 0.8658474225510748
},
{
"epoch": 0.1893687707641196,
"grad_norm": 0.33525219559669495,
"learning_rate": 9.35238213723848e-06,
"loss": 0.3994140625,
"step": 285,
"token_acc": 0.8693503422613672
},
{
"epoch": 0.19003322259136213,
"grad_norm": 0.4091569185256958,
"learning_rate": 9.347072792866338e-06,
"loss": 0.4013671875,
"step": 286,
"token_acc": 0.8692311846979863
},
{
"epoch": 0.19069767441860466,
"grad_norm": 0.3129176199436188,
"learning_rate": 9.341743293350147e-06,
"loss": 0.393310546875,
"step": 287,
"token_acc": 0.8716711617925329
},
{
"epoch": 0.19136212624584717,
"grad_norm": 0.31973591446876526,
"learning_rate": 9.336393663400058e-06,
"loss": 0.39453125,
"step": 288,
"token_acc": 0.8703869996251358
},
{
"epoch": 0.1920265780730897,
"grad_norm": 0.28965264558792114,
"learning_rate": 9.331023927819559e-06,
"loss": 0.390625,
"step": 289,
"token_acc": 0.8719815331129439
},
{
"epoch": 0.19269102990033224,
"grad_norm": 0.3142789900302887,
"learning_rate": 9.325634111505356e-06,
"loss": 0.4013671875,
"step": 290,
"token_acc": 0.8677475489613987
},
{
"epoch": 0.19335548172757475,
"grad_norm": 0.39646315574645996,
"learning_rate": 9.320224239447256e-06,
"loss": 0.397216796875,
"step": 291,
"token_acc": 0.8691629104084351
},
{
"epoch": 0.19401993355481728,
"grad_norm": 0.341926634311676,
"learning_rate": 9.31479433672806e-06,
"loss": 0.39794921875,
"step": 292,
"token_acc": 0.8689977879777494
},
{
"epoch": 0.1946843853820598,
"grad_norm": 0.3450673520565033,
"learning_rate": 9.309344428523439e-06,
"loss": 0.391357421875,
"step": 293,
"token_acc": 0.8717795431800267
},
{
"epoch": 0.19534883720930232,
"grad_norm": 0.320695698261261,
"learning_rate": 9.303874540101819e-06,
"loss": 0.38232421875,
"step": 294,
"token_acc": 0.8740899658263857
},
{
"epoch": 0.19601328903654486,
"grad_norm": 0.32038599252700806,
"learning_rate": 9.29838469682426e-06,
"loss": 0.393310546875,
"step": 295,
"token_acc": 0.8706101058001551
},
{
"epoch": 0.19667774086378736,
"grad_norm": 0.3428591191768646,
"learning_rate": 9.292874924144348e-06,
"loss": 0.41162109375,
"step": 296,
"token_acc": 0.8653123737510778
},
{
"epoch": 0.1973421926910299,
"grad_norm": 0.36900264024734497,
"learning_rate": 9.287345247608071e-06,
"loss": 0.391845703125,
"step": 297,
"token_acc": 0.8710429045472483
},
{
"epoch": 0.19800664451827243,
"grad_norm": 0.31465205550193787,
"learning_rate": 9.281795692853697e-06,
"loss": 0.4072265625,
"step": 298,
"token_acc": 0.8663626584557208
},
{
"epoch": 0.19867109634551494,
"grad_norm": 0.3593561053276062,
"learning_rate": 9.27622628561166e-06,
"loss": 0.3935546875,
"step": 299,
"token_acc": 0.8706593358402859
},
{
"epoch": 0.19933554817275748,
"grad_norm": 0.37645581364631653,
"learning_rate": 9.270637051704445e-06,
"loss": 0.395263671875,
"step": 300,
"token_acc": 0.8700201018405952
},
{
"epoch": 0.2,
"grad_norm": 0.34477493166923523,
"learning_rate": 9.265028017046459e-06,
"loss": 0.394287109375,
"step": 301,
"token_acc": 0.8707742252291576
},
{
"epoch": 0.20066445182724252,
"grad_norm": 0.339771032333374,
"learning_rate": 9.25939920764391e-06,
"loss": 0.387939453125,
"step": 302,
"token_acc": 0.8727919871576206
},
{
"epoch": 0.20132890365448505,
"grad_norm": 0.33729299902915955,
"learning_rate": 9.253750649594701e-06,
"loss": 0.41650390625,
"step": 303,
"token_acc": 0.8638279714562981
},
{
"epoch": 0.2019933554817276,
"grad_norm": 0.46522781252861023,
"learning_rate": 9.248082369088296e-06,
"loss": 0.390380859375,
"step": 304,
"token_acc": 0.8714155814080209
},
{
"epoch": 0.2026578073089701,
"grad_norm": 0.30614757537841797,
"learning_rate": 9.242394392405596e-06,
"loss": 0.416748046875,
"step": 305,
"token_acc": 0.8633312592729095
},
{
"epoch": 0.20332225913621263,
"grad_norm": 0.3585188090801239,
"learning_rate": 9.23668674591883e-06,
"loss": 0.385009765625,
"step": 306,
"token_acc": 0.872746019800819
},
{
"epoch": 0.20398671096345514,
"grad_norm": 0.34231430292129517,
"learning_rate": 9.230959456091426e-06,
"loss": 0.39990234375,
"step": 307,
"token_acc": 0.8691396295635724
},
{
"epoch": 0.20465116279069767,
"grad_norm": 0.3642405867576599,
"learning_rate": 9.225212549477881e-06,
"loss": 0.393310546875,
"step": 308,
"token_acc": 0.8708897397010055
},
{
"epoch": 0.2053156146179402,
"grad_norm": 0.31996458768844604,
"learning_rate": 9.219446052723653e-06,
"loss": 0.396484375,
"step": 309,
"token_acc": 0.8699263069762397
},
{
"epoch": 0.2059800664451827,
"grad_norm": 0.39636003971099854,
"learning_rate": 9.213659992565024e-06,
"loss": 0.385498046875,
"step": 310,
"token_acc": 0.8738312618679132
},
{
"epoch": 0.20664451827242525,
"grad_norm": 0.3966636061668396,
"learning_rate": 9.207854395828985e-06,
"loss": 0.398193359375,
"step": 311,
"token_acc": 0.8695895893354993
},
{
"epoch": 0.20730897009966778,
"grad_norm": 0.33119508624076843,
"learning_rate": 9.202029289433108e-06,
"loss": 0.384521484375,
"step": 312,
"token_acc": 0.8730195559255797
},
{
"epoch": 0.2079734219269103,
"grad_norm": 0.33122289180755615,
"learning_rate": 9.196184700385415e-06,
"loss": 0.401611328125,
"step": 313,
"token_acc": 0.8682769705170305
},
{
"epoch": 0.20863787375415282,
"grad_norm": 0.3411809504032135,
"learning_rate": 9.190320655784267e-06,
"loss": 0.404541015625,
"step": 314,
"token_acc": 0.8676218272691669
},
{
"epoch": 0.20930232558139536,
"grad_norm": 0.30415788292884827,
"learning_rate": 9.184437182818227e-06,
"loss": 0.393798828125,
"step": 315,
"token_acc": 0.8710588175032765
},
{
"epoch": 0.20996677740863787,
"grad_norm": 0.43569445610046387,
"learning_rate": 9.178534308765937e-06,
"loss": 0.39794921875,
"step": 316,
"token_acc": 0.8694164214981114
},
{
"epoch": 0.2106312292358804,
"grad_norm": 0.3099321722984314,
"learning_rate": 9.172612060995993e-06,
"loss": 0.399169921875,
"step": 317,
"token_acc": 0.8694282414753117
},
{
"epoch": 0.21129568106312294,
"grad_norm": 0.3443339765071869,
"learning_rate": 9.166670466966815e-06,
"loss": 0.38134765625,
"step": 318,
"token_acc": 0.8738396323674571
},
{
"epoch": 0.21196013289036544,
"grad_norm": 0.3342459499835968,
"learning_rate": 9.160709554226527e-06,
"loss": 0.392822265625,
"step": 319,
"token_acc": 0.8716335279905706
},
{
"epoch": 0.21262458471760798,
"grad_norm": 0.37542033195495605,
"learning_rate": 9.154729350412817e-06,
"loss": 0.37841796875,
"step": 320,
"token_acc": 0.8758923262354359
},
{
"epoch": 0.21328903654485049,
"grad_norm": 0.3763517737388611,
"learning_rate": 9.148729883252818e-06,
"loss": 0.40234375,
"step": 321,
"token_acc": 0.8681850044171989
},
{
"epoch": 0.21395348837209302,
"grad_norm": 0.47176066040992737,
"learning_rate": 9.142711180562982e-06,
"loss": 0.3955078125,
"step": 322,
"token_acc": 0.8702862547927527
},
{
"epoch": 0.21461794019933556,
"grad_norm": 0.45130228996276855,
"learning_rate": 9.136673270248938e-06,
"loss": 0.393798828125,
"step": 323,
"token_acc": 0.8705882418983977
},
{
"epoch": 0.21528239202657806,
"grad_norm": 0.32351794838905334,
"learning_rate": 9.130616180305378e-06,
"loss": 0.396484375,
"step": 324,
"token_acc": 0.8694268404578186
},
{
"epoch": 0.2159468438538206,
"grad_norm": 0.3709367513656616,
"learning_rate": 9.124539938815917e-06,
"loss": 0.379150390625,
"step": 325,
"token_acc": 0.8760524280917081
},
{
"epoch": 0.21661129568106313,
"grad_norm": 0.5152716040611267,
"learning_rate": 9.118444573952965e-06,
"loss": 0.400146484375,
"step": 326,
"token_acc": 0.8685434717834305
},
{
"epoch": 0.21727574750830564,
"grad_norm": 0.32111188769340515,
"learning_rate": 9.1123301139776e-06,
"loss": 0.395263671875,
"step": 327,
"token_acc": 0.870220090713891
},
{
"epoch": 0.21794019933554817,
"grad_norm": 0.3860948085784912,
"learning_rate": 9.106196587239431e-06,
"loss": 0.39599609375,
"step": 328,
"token_acc": 0.8697702166018464
},
{
"epoch": 0.2186046511627907,
"grad_norm": 0.3669413924217224,
"learning_rate": 9.100044022176476e-06,
"loss": 0.4091796875,
"step": 329,
"token_acc": 0.8674512915454465
},
{
"epoch": 0.21926910299003322,
"grad_norm": 0.39125779271125793,
"learning_rate": 9.093872447315012e-06,
"loss": 0.38720703125,
"step": 330,
"token_acc": 0.8732742915630417
},
{
"epoch": 0.21993355481727575,
"grad_norm": 0.4837248921394348,
"learning_rate": 9.087681891269469e-06,
"loss": 0.379150390625,
"step": 331,
"token_acc": 0.8752403977639452
},
{
"epoch": 0.22059800664451829,
"grad_norm": 0.32324904203414917,
"learning_rate": 9.081472382742274e-06,
"loss": 0.3955078125,
"step": 332,
"token_acc": 0.870243037891593
},
{
"epoch": 0.2212624584717608,
"grad_norm": 0.5458261370658875,
"learning_rate": 9.075243950523726e-06,
"loss": 0.40185546875,
"step": 333,
"token_acc": 0.867798019229379
},
{
"epoch": 0.22192691029900333,
"grad_norm": 0.4391469657421112,
"learning_rate": 9.06899662349187e-06,
"loss": 0.384033203125,
"step": 334,
"token_acc": 0.8739963890898615
},
{
"epoch": 0.22259136212624583,
"grad_norm": 0.37593838572502136,
"learning_rate": 9.062730430612354e-06,
"loss": 0.404541015625,
"step": 335,
"token_acc": 0.8670665706337015
},
{
"epoch": 0.22325581395348837,
"grad_norm": 0.3412649929523468,
"learning_rate": 9.056445400938294e-06,
"loss": 0.38623046875,
"step": 336,
"token_acc": 0.8734146101123349
},
{
"epoch": 0.2239202657807309,
"grad_norm": 0.3577443063259125,
"learning_rate": 9.050141563610143e-06,
"loss": 0.4150390625,
"step": 337,
"token_acc": 0.8642848007157881
},
{
"epoch": 0.2245847176079734,
"grad_norm": 0.3862946331501007,
"learning_rate": 9.04381894785556e-06,
"loss": 0.394775390625,
"step": 338,
"token_acc": 0.8699289188342075
},
{
"epoch": 0.22524916943521595,
"grad_norm": 0.6569634675979614,
"learning_rate": 9.037477582989269e-06,
"loss": 0.39892578125,
"step": 339,
"token_acc": 0.8689581840707312
},
{
"epoch": 0.22591362126245848,
"grad_norm": 0.42135390639305115,
"learning_rate": 9.031117498412918e-06,
"loss": 0.402099609375,
"step": 340,
"token_acc": 0.8691154226499714
},
{
"epoch": 0.226578073089701,
"grad_norm": 0.33055490255355835,
"learning_rate": 9.024738723614957e-06,
"loss": 0.38427734375,
"step": 341,
"token_acc": 0.8731017779900853
},
{
"epoch": 0.22724252491694352,
"grad_norm": 0.35450488328933716,
"learning_rate": 9.018341288170485e-06,
"loss": 0.399169921875,
"step": 342,
"token_acc": 0.8696507266296402
},
{
"epoch": 0.22790697674418606,
"grad_norm": 0.3218103349208832,
"learning_rate": 9.011925221741126e-06,
"loss": 0.4140625,
"step": 343,
"token_acc": 0.8652290594067987
},
{
"epoch": 0.22857142857142856,
"grad_norm": 0.6726000905036926,
"learning_rate": 9.005490554074886e-06,
"loss": 0.388916015625,
"step": 344,
"token_acc": 0.8723326239619698
},
{
"epoch": 0.2292358803986711,
"grad_norm": 0.36025893688201904,
"learning_rate": 8.999037315006014e-06,
"loss": 0.40185546875,
"step": 345,
"token_acc": 0.8689927558863184
},
{
"epoch": 0.22990033222591363,
"grad_norm": 0.3738430440425873,
"learning_rate": 8.992565534454864e-06,
"loss": 0.39501953125,
"step": 346,
"token_acc": 0.8706620437682407
},
{
"epoch": 0.23056478405315614,
"grad_norm": 0.2935904264450073,
"learning_rate": 8.98607524242776e-06,
"loss": 0.412109375,
"step": 347,
"token_acc": 0.8663023633805766
},
{
"epoch": 0.23122923588039868,
"grad_norm": 0.3532610237598419,
"learning_rate": 8.979566469016856e-06,
"loss": 0.399169921875,
"step": 348,
"token_acc": 0.8689077619788297
},
{
"epoch": 0.23189368770764118,
"grad_norm": 0.445578396320343,
"learning_rate": 8.973039244399987e-06,
"loss": 0.386474609375,
"step": 349,
"token_acc": 0.8726528963734953
},
{
"epoch": 0.23255813953488372,
"grad_norm": 0.3290676772594452,
"learning_rate": 8.96649359884054e-06,
"loss": 0.409423828125,
"step": 350,
"token_acc": 0.8665213537496335
},
{
"epoch": 0.23322259136212625,
"grad_norm": 0.3276229500770569,
"learning_rate": 8.959929562687317e-06,
"loss": 0.4150390625,
"step": 351,
"token_acc": 0.864211410572062
},
{
"epoch": 0.23388704318936876,
"grad_norm": 0.5520330667495728,
"learning_rate": 8.95334716637438e-06,
"loss": 0.389404296875,
"step": 352,
"token_acc": 0.8722282871599095
},
{
"epoch": 0.2345514950166113,
"grad_norm": 0.3330706059932709,
"learning_rate": 8.946746440420921e-06,
"loss": 0.395751953125,
"step": 353,
"token_acc": 0.8704936407657727
},
{
"epoch": 0.23521594684385383,
"grad_norm": 0.46390780806541443,
"learning_rate": 8.940127415431117e-06,
"loss": 0.433349609375,
"step": 354,
"token_acc": 0.8599070954325339
},
{
"epoch": 0.23588039867109634,
"grad_norm": 0.3171122074127197,
"learning_rate": 8.933490122093986e-06,
"loss": 0.425048828125,
"step": 355,
"token_acc": 0.8614401387200322
},
{
"epoch": 0.23654485049833887,
"grad_norm": 0.32453131675720215,
"learning_rate": 8.92683459118325e-06,
"loss": 0.3916015625,
"step": 356,
"token_acc": 0.8711297793283567
},
{
"epoch": 0.2372093023255814,
"grad_norm": 0.38117727637290955,
"learning_rate": 8.920160853557185e-06,
"loss": 0.38671875,
"step": 357,
"token_acc": 0.8734145204288125
},
{
"epoch": 0.2378737541528239,
"grad_norm": 0.3064368665218353,
"learning_rate": 8.913468940158486e-06,
"loss": 0.400634765625,
"step": 358,
"token_acc": 0.8684743647962895
},
{
"epoch": 0.23853820598006645,
"grad_norm": 0.30961892008781433,
"learning_rate": 8.906758882014123e-06,
"loss": 0.375,
"step": 359,
"token_acc": 0.8767856037244183
},
{
"epoch": 0.23920265780730898,
"grad_norm": 0.2961668372154236,
"learning_rate": 8.900030710235185e-06,
"loss": 0.384765625,
"step": 360,
"token_acc": 0.8732013775464295
},
{
"epoch": 0.2398671096345515,
"grad_norm": 0.3818748891353607,
"learning_rate": 8.89328445601675e-06,
"loss": 0.384765625,
"step": 361,
"token_acc": 0.8736702339025925
},
{
"epoch": 0.24053156146179402,
"grad_norm": 0.35889503359794617,
"learning_rate": 8.886520150637734e-06,
"loss": 0.38330078125,
"step": 362,
"token_acc": 0.8742040277419783
},
{
"epoch": 0.24119601328903653,
"grad_norm": 0.3283149302005768,
"learning_rate": 8.87973782546075e-06,
"loss": 0.39208984375,
"step": 363,
"token_acc": 0.8710470238545619
},
{
"epoch": 0.24186046511627907,
"grad_norm": 0.3287707567214966,
"learning_rate": 8.872937511931954e-06,
"loss": 0.423828125,
"step": 364,
"token_acc": 0.8624147538371078
},
{
"epoch": 0.2425249169435216,
"grad_norm": 0.30221229791641235,
"learning_rate": 8.866119241580907e-06,
"loss": 0.3994140625,
"step": 365,
"token_acc": 0.8693933948635358
},
{
"epoch": 0.2431893687707641,
"grad_norm": 0.3303050398826599,
"learning_rate": 8.859283046020427e-06,
"loss": 0.393310546875,
"step": 366,
"token_acc": 0.8707264060666855
},
{
"epoch": 0.24385382059800664,
"grad_norm": 0.49738216400146484,
"learning_rate": 8.852428956946445e-06,
"loss": 0.38330078125,
"step": 367,
"token_acc": 0.8735883080257291
},
{
"epoch": 0.24451827242524918,
"grad_norm": 0.3504537045955658,
"learning_rate": 8.845557006137848e-06,
"loss": 0.404296875,
"step": 368,
"token_acc": 0.8679212467899506
},
{
"epoch": 0.24518272425249169,
"grad_norm": 0.2988705337047577,
"learning_rate": 8.838667225456347e-06,
"loss": 0.384033203125,
"step": 369,
"token_acc": 0.8732234278803045
},
{
"epoch": 0.24584717607973422,
"grad_norm": 0.5355086922645569,
"learning_rate": 8.831759646846312e-06,
"loss": 0.397705078125,
"step": 370,
"token_acc": 0.869398601024071
},
{
"epoch": 0.24651162790697675,
"grad_norm": 0.3267458975315094,
"learning_rate": 8.824834302334641e-06,
"loss": 0.3994140625,
"step": 371,
"token_acc": 0.8686053315347312
},
{
"epoch": 0.24717607973421926,
"grad_norm": 0.2962867319583893,
"learning_rate": 8.8178912240306e-06,
"loss": 0.38671875,
"step": 372,
"token_acc": 0.873340769627571
},
{
"epoch": 0.2478405315614618,
"grad_norm": 0.2977236807346344,
"learning_rate": 8.810930444125676e-06,
"loss": 0.38818359375,
"step": 373,
"token_acc": 0.8724758868396626
},
{
"epoch": 0.24850498338870433,
"grad_norm": 0.364019513130188,
"learning_rate": 8.803951994893431e-06,
"loss": 0.396240234375,
"step": 374,
"token_acc": 0.8703027654489587
},
{
"epoch": 0.24916943521594684,
"grad_norm": 0.36964738368988037,
"learning_rate": 8.796955908689349e-06,
"loss": 0.383544921875,
"step": 375,
"token_acc": 0.8741320037027227
},
{
"epoch": 0.24983388704318937,
"grad_norm": 0.3357184827327728,
"learning_rate": 8.789942217950692e-06,
"loss": 0.40185546875,
"step": 376,
"token_acc": 0.8689178398528716
},
{
"epoch": 0.2504983388704319,
"grad_norm": 0.30628135800361633,
"learning_rate": 8.782910955196338e-06,
"loss": 0.400390625,
"step": 377,
"token_acc": 0.8681250904175607
},
{
"epoch": 0.25116279069767444,
"grad_norm": 0.32306742668151855,
"learning_rate": 8.775862153026644e-06,
"loss": 0.400390625,
"step": 378,
"token_acc": 0.8693774665901957
},
{
"epoch": 0.25182724252491695,
"grad_norm": 0.3879261612892151,
"learning_rate": 8.768795844123285e-06,
"loss": 0.400390625,
"step": 379,
"token_acc": 0.8681822875100756
},
{
"epoch": 0.25249169435215946,
"grad_norm": 0.3530760407447815,
"learning_rate": 8.761712061249106e-06,
"loss": 0.396484375,
"step": 380,
"token_acc": 0.8702813447394693
},
{
"epoch": 0.253156146179402,
"grad_norm": 0.3367592990398407,
"learning_rate": 8.75461083724797e-06,
"loss": 0.39990234375,
"step": 381,
"token_acc": 0.8689738997139808
},
{
"epoch": 0.2538205980066445,
"grad_norm": 0.45369279384613037,
"learning_rate": 8.747492205044608e-06,
"loss": 0.404541015625,
"step": 382,
"token_acc": 0.867182436834174
},
{
"epoch": 0.25448504983388703,
"grad_norm": 0.32576996088027954,
"learning_rate": 8.740356197644459e-06,
"loss": 0.38427734375,
"step": 383,
"token_acc": 0.8728154917487133
},
{
"epoch": 0.25514950166112954,
"grad_norm": 0.340951532125473,
"learning_rate": 8.733202848133526e-06,
"loss": 0.39404296875,
"step": 384,
"token_acc": 0.870514025972045
},
{
"epoch": 0.2558139534883721,
"grad_norm": 0.28670549392700195,
"learning_rate": 8.726032189678217e-06,
"loss": 0.3896484375,
"step": 385,
"token_acc": 0.8718567392132737
},
{
"epoch": 0.2564784053156146,
"grad_norm": 0.33666831254959106,
"learning_rate": 8.718844255525192e-06,
"loss": 0.392822265625,
"step": 386,
"token_acc": 0.8717052146135552
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.3604886531829834,
"learning_rate": 8.711639079001211e-06,
"loss": 0.40771484375,
"step": 387,
"token_acc": 0.866106737272826
},
{
"epoch": 0.2578073089700997,
"grad_norm": 0.31018927693367004,
"learning_rate": 8.704416693512977e-06,
"loss": 0.396484375,
"step": 388,
"token_acc": 0.8697630229744531
},
{
"epoch": 0.2584717607973422,
"grad_norm": 0.3294845521450043,
"learning_rate": 8.69717713254698e-06,
"loss": 0.395751953125,
"step": 389,
"token_acc": 0.8697042200441872
},
{
"epoch": 0.2591362126245847,
"grad_norm": 0.35338521003723145,
"learning_rate": 8.689920429669352e-06,
"loss": 0.40087890625,
"step": 390,
"token_acc": 0.8686391482102161
},
{
"epoch": 0.25980066445182726,
"grad_norm": 0.34791299700737,
"learning_rate": 8.682646618525692e-06,
"loss": 0.394775390625,
"step": 391,
"token_acc": 0.870131833845165
},
{
"epoch": 0.26046511627906976,
"grad_norm": 0.38557422161102295,
"learning_rate": 8.675355732840926e-06,
"loss": 0.394287109375,
"step": 392,
"token_acc": 0.8718536487659404
},
{
"epoch": 0.26112956810631227,
"grad_norm": 0.29517439007759094,
"learning_rate": 8.668047806419153e-06,
"loss": 0.39111328125,
"step": 393,
"token_acc": 0.8716813152982746
},
{
"epoch": 0.26179401993355483,
"grad_norm": 0.3853927254676819,
"learning_rate": 8.660722873143468e-06,
"loss": 0.409423828125,
"step": 394,
"token_acc": 0.8667181586043303
},
{
"epoch": 0.26245847176079734,
"grad_norm": 0.35761961340904236,
"learning_rate": 8.653380966975831e-06,
"loss": 0.391845703125,
"step": 395,
"token_acc": 0.8719813875081545
},
{
"epoch": 0.26312292358803985,
"grad_norm": 0.46058517694473267,
"learning_rate": 8.646022121956885e-06,
"loss": 0.387939453125,
"step": 396,
"token_acc": 0.8726329170700005
},
{
"epoch": 0.2637873754152824,
"grad_norm": 0.3657056987285614,
"learning_rate": 8.638646372205816e-06,
"loss": 0.408203125,
"step": 397,
"token_acc": 0.8672397227838188
},
{
"epoch": 0.2644518272425249,
"grad_norm": 0.32979926466941833,
"learning_rate": 8.63125375192019e-06,
"loss": 0.401123046875,
"step": 398,
"token_acc": 0.8686166265311482
},
{
"epoch": 0.2651162790697674,
"grad_norm": 0.34247106313705444,
"learning_rate": 8.62384429537579e-06,
"loss": 0.402099609375,
"step": 399,
"token_acc": 0.8673097838149776
},
{
"epoch": 0.26578073089701,
"grad_norm": 0.517318606376648,
"learning_rate": 8.616418036926461e-06,
"loss": 0.403564453125,
"step": 400,
"token_acc": 0.8672589396693842
},
{
"epoch": 0.2664451827242525,
"grad_norm": 0.33124276995658875,
"learning_rate": 8.608975011003949e-06,
"loss": 0.397705078125,
"step": 401,
"token_acc": 0.8685659866003204
},
{
"epoch": 0.267109634551495,
"grad_norm": 0.5142866969108582,
"learning_rate": 8.60151525211774e-06,
"loss": 0.401611328125,
"step": 402,
"token_acc": 0.8681514221269666
},
{
"epoch": 0.26777408637873756,
"grad_norm": 0.4761538803577423,
"learning_rate": 8.59403879485491e-06,
"loss": 0.393310546875,
"step": 403,
"token_acc": 0.871079236812815
},
{
"epoch": 0.26843853820598007,
"grad_norm": 0.30543142557144165,
"learning_rate": 8.58654567387995e-06,
"loss": 0.39111328125,
"step": 404,
"token_acc": 0.8716362813998548
},
{
"epoch": 0.2691029900332226,
"grad_norm": 0.34164905548095703,
"learning_rate": 8.57903592393461e-06,
"loss": 0.393310546875,
"step": 405,
"token_acc": 0.8704735498009407
},
{
"epoch": 0.26976744186046514,
"grad_norm": 0.35273367166519165,
"learning_rate": 8.57150957983775e-06,
"loss": 0.3935546875,
"step": 406,
"token_acc": 0.8709483467547984
},
{
"epoch": 0.27043189368770765,
"grad_norm": 0.4245699644088745,
"learning_rate": 8.563966676485159e-06,
"loss": 0.3828125,
"step": 407,
"token_acc": 0.8734038651928907
},
{
"epoch": 0.27109634551495015,
"grad_norm": 0.2891317307949066,
"learning_rate": 8.556407248849404e-06,
"loss": 0.378662109375,
"step": 408,
"token_acc": 0.8757921484158732
},
{
"epoch": 0.2717607973421927,
"grad_norm": 0.35015439987182617,
"learning_rate": 8.548831331979673e-06,
"loss": 0.397705078125,
"step": 409,
"token_acc": 0.8685146402070962
},
{
"epoch": 0.2724252491694352,
"grad_norm": 0.28776541352272034,
"learning_rate": 8.541238961001599e-06,
"loss": 0.390625,
"step": 410,
"token_acc": 0.8708835675331352
},
{
"epoch": 0.27308970099667773,
"grad_norm": 0.3873864710330963,
"learning_rate": 8.533630171117108e-06,
"loss": 0.382568359375,
"step": 411,
"token_acc": 0.8746107397581703
},
{
"epoch": 0.27375415282392024,
"grad_norm": 0.33415311574935913,
"learning_rate": 8.526004997604252e-06,
"loss": 0.412841796875,
"step": 412,
"token_acc": 0.8648393419456966
},
{
"epoch": 0.2744186046511628,
"grad_norm": 0.34526023268699646,
"learning_rate": 8.518363475817041e-06,
"loss": 0.3857421875,
"step": 413,
"token_acc": 0.8727992852921612
},
{
"epoch": 0.2750830564784053,
"grad_norm": 0.33352288603782654,
"learning_rate": 8.510705641185293e-06,
"loss": 0.40673828125,
"step": 414,
"token_acc": 0.8664070410551516
},
{
"epoch": 0.2757475083056478,
"grad_norm": 0.324628621339798,
"learning_rate": 8.50303152921445e-06,
"loss": 0.38525390625,
"step": 415,
"token_acc": 0.873397728603858
},
{
"epoch": 0.2764119601328904,
"grad_norm": 0.3467447757720947,
"learning_rate": 8.495341175485428e-06,
"loss": 0.402587890625,
"step": 416,
"token_acc": 0.8680582834948029
},
{
"epoch": 0.2770764119601329,
"grad_norm": 0.37417587637901306,
"learning_rate": 8.48763461565445e-06,
"loss": 0.39990234375,
"step": 417,
"token_acc": 0.8695033450968103
},
{
"epoch": 0.2777408637873754,
"grad_norm": 0.3777923882007599,
"learning_rate": 8.479911885452874e-06,
"loss": 0.398193359375,
"step": 418,
"token_acc": 0.8685811375070818
},
{
"epoch": 0.27840531561461795,
"grad_norm": 0.3108659088611603,
"learning_rate": 8.472173020687038e-06,
"loss": 0.399169921875,
"step": 419,
"token_acc": 0.8693677627199434
},
{
"epoch": 0.27906976744186046,
"grad_norm": 0.3377542197704315,
"learning_rate": 8.46441805723808e-06,
"loss": 0.408935546875,
"step": 420,
"token_acc": 0.8656245534192967
},
{
"epoch": 0.27973421926910297,
"grad_norm": 0.787042498588562,
"learning_rate": 8.45664703106178e-06,
"loss": 0.414306640625,
"step": 421,
"token_acc": 0.8645070355752644
},
{
"epoch": 0.28039867109634553,
"grad_norm": 0.3024000823497772,
"learning_rate": 8.448859978188402e-06,
"loss": 0.389404296875,
"step": 422,
"token_acc": 0.8720330294153096
},
{
"epoch": 0.28106312292358804,
"grad_norm": 0.31159770488739014,
"learning_rate": 8.441056934722507e-06,
"loss": 0.385009765625,
"step": 423,
"token_acc": 0.873088334739388
},
{
"epoch": 0.28172757475083055,
"grad_norm": 0.34706103801727295,
"learning_rate": 8.4332379368428e-06,
"loss": 0.389892578125,
"step": 424,
"token_acc": 0.8721182408235104
},
{
"epoch": 0.2823920265780731,
"grad_norm": 0.37067046761512756,
"learning_rate": 8.42540302080196e-06,
"loss": 0.405029296875,
"step": 425,
"token_acc": 0.8663084993726488
},
{
"epoch": 0.2830564784053156,
"grad_norm": 0.41193196177482605,
"learning_rate": 8.41755222292647e-06,
"loss": 0.39111328125,
"step": 426,
"token_acc": 0.871035409939479
},
{
"epoch": 0.2837209302325581,
"grad_norm": 0.35378965735435486,
"learning_rate": 8.409685579616447e-06,
"loss": 0.39306640625,
"step": 427,
"token_acc": 0.8710290090518219
},
{
"epoch": 0.2843853820598007,
"grad_norm": 0.33378711342811584,
"learning_rate": 8.401803127345476e-06,
"loss": 0.395263671875,
"step": 428,
"token_acc": 0.8702138280825525
},
{
"epoch": 0.2850498338870432,
"grad_norm": 0.32489392161369324,
"learning_rate": 8.393904902660437e-06,
"loss": 0.3935546875,
"step": 429,
"token_acc": 0.869980508109881
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.3212103843688965,
"learning_rate": 8.385990942181346e-06,
"loss": 0.40478515625,
"step": 430,
"token_acc": 0.867424306434178
},
{
"epoch": 0.28637873754152826,
"grad_norm": 0.2650502324104309,
"learning_rate": 8.378061282601171e-06,
"loss": 0.39013671875,
"step": 431,
"token_acc": 0.8722599743169401
},
{
"epoch": 0.28704318936877077,
"grad_norm": 0.28905585408210754,
"learning_rate": 8.370115960685672e-06,
"loss": 0.408447265625,
"step": 432,
"token_acc": 0.8663497247539141
},
{
"epoch": 0.2877076411960133,
"grad_norm": 0.29869380593299866,
"learning_rate": 8.362155013273228e-06,
"loss": 0.40380859375,
"step": 433,
"token_acc": 0.8672495706336179
},
{
"epoch": 0.28837209302325584,
"grad_norm": 0.4402686655521393,
"learning_rate": 8.35417847727466e-06,
"loss": 0.40771484375,
"step": 434,
"token_acc": 0.8682091961474149
},
{
"epoch": 0.28903654485049834,
"grad_norm": 0.31121301651000977,
"learning_rate": 8.34618638967307e-06,
"loss": 0.3984375,
"step": 435,
"token_acc": 0.8693709499830463
},
{
"epoch": 0.28970099667774085,
"grad_norm": 0.36379125714302063,
"learning_rate": 8.338178787523667e-06,
"loss": 0.391845703125,
"step": 436,
"token_acc": 0.870583647457077
},
{
"epoch": 0.2903654485049834,
"grad_norm": 0.6674746870994568,
"learning_rate": 8.330155707953585e-06,
"loss": 0.412841796875,
"step": 437,
"token_acc": 0.8648574973885244
},
{
"epoch": 0.2910299003322259,
"grad_norm": 0.3181109130382538,
"learning_rate": 8.322117188161728e-06,
"loss": 0.385009765625,
"step": 438,
"token_acc": 0.8733631304195831
},
{
"epoch": 0.29169435215946843,
"grad_norm": 0.29766711592674255,
"learning_rate": 8.314063265418581e-06,
"loss": 0.389892578125,
"step": 439,
"token_acc": 0.8720238161272501
},
{
"epoch": 0.292358803986711,
"grad_norm": 0.34679752588272095,
"learning_rate": 8.30599397706605e-06,
"loss": 0.390869140625,
"step": 440,
"token_acc": 0.8714128118803782
},
{
"epoch": 0.2930232558139535,
"grad_norm": 0.27636924386024475,
"learning_rate": 8.297909360517279e-06,
"loss": 0.390380859375,
"step": 441,
"token_acc": 0.8711925526340393
},
{
"epoch": 0.293687707641196,
"grad_norm": 0.2973499894142151,
"learning_rate": 8.28980945325648e-06,
"loss": 0.40283203125,
"step": 442,
"token_acc": 0.8685272209932807
},
{
"epoch": 0.2943521594684385,
"grad_norm": 0.38391873240470886,
"learning_rate": 8.281694292838771e-06,
"loss": 0.39990234375,
"step": 443,
"token_acc": 0.8688891840341595
},
{
"epoch": 0.2950166112956811,
"grad_norm": 0.31040722131729126,
"learning_rate": 8.273563916889977e-06,
"loss": 0.394775390625,
"step": 444,
"token_acc": 0.8697102086608259
},
{
"epoch": 0.2956810631229236,
"grad_norm": 0.38621771335601807,
"learning_rate": 8.265418363106478e-06,
"loss": 0.398681640625,
"step": 445,
"token_acc": 0.8683468343832297
},
{
"epoch": 0.2963455149501661,
"grad_norm": 0.2828279137611389,
"learning_rate": 8.257257669255025e-06,
"loss": 0.408203125,
"step": 446,
"token_acc": 0.8658681786047119
},
{
"epoch": 0.29700996677740865,
"grad_norm": 0.3442494571208954,
"learning_rate": 8.249081873172562e-06,
"loss": 0.393798828125,
"step": 447,
"token_acc": 0.8706857197724543
},
{
"epoch": 0.29767441860465116,
"grad_norm": 0.2680087983608246,
"learning_rate": 8.240891012766057e-06,
"loss": 0.3759765625,
"step": 448,
"token_acc": 0.8755825641450888
},
{
"epoch": 0.29833887043189367,
"grad_norm": 0.3514353930950165,
"learning_rate": 8.232685126012323e-06,
"loss": 0.385498046875,
"step": 449,
"token_acc": 0.8735947798287679
},
{
"epoch": 0.29900332225913623,
"grad_norm": 0.2902641296386719,
"learning_rate": 8.224464250957845e-06,
"loss": 0.399658203125,
"step": 450,
"token_acc": 0.8681194773007642
},
{
"epoch": 0.29966777408637874,
"grad_norm": 0.5367274284362793,
"learning_rate": 8.216228425718596e-06,
"loss": 0.39111328125,
"step": 451,
"token_acc": 0.8711689423071648
},
{
"epoch": 0.30033222591362124,
"grad_norm": 0.40319305658340454,
"learning_rate": 8.207977688479869e-06,
"loss": 0.393310546875,
"step": 452,
"token_acc": 0.8711290474531138
},
{
"epoch": 0.3009966777408638,
"grad_norm": 0.3362083435058594,
"learning_rate": 8.199712077496096e-06,
"loss": 0.385498046875,
"step": 453,
"token_acc": 0.8728179090096944
},
{
"epoch": 0.3016611295681063,
"grad_norm": 0.268970787525177,
"learning_rate": 8.19143163109067e-06,
"loss": 0.387451171875,
"step": 454,
"token_acc": 0.8722459360090674
},
{
"epoch": 0.3023255813953488,
"grad_norm": 0.31765514612197876,
"learning_rate": 8.183136387655767e-06,
"loss": 0.38720703125,
"step": 455,
"token_acc": 0.8727781313767322
},
{
"epoch": 0.3029900332225914,
"grad_norm": 0.35192224383354187,
"learning_rate": 8.174826385652173e-06,
"loss": 0.403076171875,
"step": 456,
"token_acc": 0.8687942741607798
},
{
"epoch": 0.3036544850498339,
"grad_norm": 0.3015848994255066,
"learning_rate": 8.166501663609096e-06,
"loss": 0.416259765625,
"step": 457,
"token_acc": 0.8636462889283418
},
{
"epoch": 0.3043189368770764,
"grad_norm": 0.3684592545032501,
"learning_rate": 8.158162260124001e-06,
"loss": 0.395263671875,
"step": 458,
"token_acc": 0.8701718244213399
},
{
"epoch": 0.30498338870431896,
"grad_norm": 0.4808623194694519,
"learning_rate": 8.149808213862415e-06,
"loss": 0.395751953125,
"step": 459,
"token_acc": 0.8702128063852855
},
{
"epoch": 0.30564784053156147,
"grad_norm": 0.3185524344444275,
"learning_rate": 8.141439563557765e-06,
"loss": 0.388916015625,
"step": 460,
"token_acc": 0.8719736549845967
},
{
"epoch": 0.306312292358804,
"grad_norm": 0.38690608739852905,
"learning_rate": 8.13305634801118e-06,
"loss": 0.39208984375,
"step": 461,
"token_acc": 0.8710107384453176
},
{
"epoch": 0.30697674418604654,
"grad_norm": 0.30850011110305786,
"learning_rate": 8.12465860609133e-06,
"loss": 0.387939453125,
"step": 462,
"token_acc": 0.87229534062318
},
{
"epoch": 0.30764119601328904,
"grad_norm": 0.2807459235191345,
"learning_rate": 8.116246376734228e-06,
"loss": 0.396728515625,
"step": 463,
"token_acc": 0.8689401172491947
},
{
"epoch": 0.30830564784053155,
"grad_norm": 0.30543532967567444,
"learning_rate": 8.107819698943063e-06,
"loss": 0.39208984375,
"step": 464,
"token_acc": 0.8720228153348473
},
{
"epoch": 0.3089700996677741,
"grad_norm": 0.2879014313220978,
"learning_rate": 8.099378611788009e-06,
"loss": 0.385498046875,
"step": 465,
"token_acc": 0.8727484688117255
},
{
"epoch": 0.3096345514950166,
"grad_norm": 0.37806951999664307,
"learning_rate": 8.090923154406056e-06,
"loss": 0.3779296875,
"step": 466,
"token_acc": 0.8756411676110188
},
{
"epoch": 0.3102990033222591,
"grad_norm": 0.3344796597957611,
"learning_rate": 8.082453366000818e-06,
"loss": 0.39208984375,
"step": 467,
"token_acc": 0.8710247605076571
},
{
"epoch": 0.3109634551495017,
"grad_norm": 0.3528293967247009,
"learning_rate": 8.073969285842348e-06,
"loss": 0.3984375,
"step": 468,
"token_acc": 0.8694042700665687
},
{
"epoch": 0.3116279069767442,
"grad_norm": 0.3631826639175415,
"learning_rate": 8.065470953266976e-06,
"loss": 0.400634765625,
"step": 469,
"token_acc": 0.8686637855208417
},
{
"epoch": 0.3122923588039867,
"grad_norm": 0.34675952792167664,
"learning_rate": 8.056958407677103e-06,
"loss": 0.390625,
"step": 470,
"token_acc": 0.8712540230576702
},
{
"epoch": 0.3129568106312292,
"grad_norm": 0.346429705619812,
"learning_rate": 8.048431688541028e-06,
"loss": 0.391845703125,
"step": 471,
"token_acc": 0.8708429935500884
},
{
"epoch": 0.3136212624584718,
"grad_norm": 0.5807815194129944,
"learning_rate": 8.039890835392775e-06,
"loss": 0.4072265625,
"step": 472,
"token_acc": 0.8662283993677649
},
{
"epoch": 0.3142857142857143,
"grad_norm": 0.3910853862762451,
"learning_rate": 8.031335887831886e-06,
"loss": 0.3818359375,
"step": 473,
"token_acc": 0.8748760541160334
},
{
"epoch": 0.3149501661129568,
"grad_norm": 0.34056586027145386,
"learning_rate": 8.022766885523265e-06,
"loss": 0.3955078125,
"step": 474,
"token_acc": 0.8699912061658222
},
{
"epoch": 0.31561461794019935,
"grad_norm": 0.31478768587112427,
"learning_rate": 8.014183868196974e-06,
"loss": 0.40185546875,
"step": 475,
"token_acc": 0.868352650170832
},
{
"epoch": 0.31627906976744186,
"grad_norm": 0.2793700695037842,
"learning_rate": 8.005586875648055e-06,
"loss": 0.398193359375,
"step": 476,
"token_acc": 0.8694893485576792
},
{
"epoch": 0.31694352159468436,
"grad_norm": 0.3538573980331421,
"learning_rate": 7.99697594773635e-06,
"loss": 0.38525390625,
"step": 477,
"token_acc": 0.8727987788611928
},
{
"epoch": 0.3176079734219269,
"grad_norm": 0.6073012351989746,
"learning_rate": 7.988351124386306e-06,
"loss": 0.386474609375,
"step": 478,
"token_acc": 0.8741251704513623
},
{
"epoch": 0.31827242524916943,
"grad_norm": 0.2874734103679657,
"learning_rate": 7.979712445586802e-06,
"loss": 0.3935546875,
"step": 479,
"token_acc": 0.8704079940631685
},
{
"epoch": 0.31893687707641194,
"grad_norm": 0.3211022913455963,
"learning_rate": 7.971059951390956e-06,
"loss": 0.387939453125,
"step": 480,
"token_acc": 0.872145203636316
},
{
"epoch": 0.3196013289036545,
"grad_norm": 0.3656294047832489,
"learning_rate": 7.962393681915934e-06,
"loss": 0.39306640625,
"step": 481,
"token_acc": 0.8711037520807073
},
{
"epoch": 0.320265780730897,
"grad_norm": 0.46732190251350403,
"learning_rate": 7.953713677342785e-06,
"loss": 0.40625,
"step": 482,
"token_acc": 0.8665048358492684
},
{
"epoch": 0.3209302325581395,
"grad_norm": 0.3310762345790863,
"learning_rate": 7.945019977916225e-06,
"loss": 0.38623046875,
"step": 483,
"token_acc": 0.8731057003541152
},
{
"epoch": 0.3215946843853821,
"grad_norm": 0.3438909947872162,
"learning_rate": 7.936312623944483e-06,
"loss": 0.38427734375,
"step": 484,
"token_acc": 0.8730205147946636
},
{
"epoch": 0.3222591362126246,
"grad_norm": 0.3735770285129547,
"learning_rate": 7.927591655799078e-06,
"loss": 0.38623046875,
"step": 485,
"token_acc": 0.8727049877568547
},
{
"epoch": 0.3229235880398671,
"grad_norm": 0.3507101535797119,
"learning_rate": 7.918857113914665e-06,
"loss": 0.380615234375,
"step": 486,
"token_acc": 0.8746253881015057
},
{
"epoch": 0.32358803986710966,
"grad_norm": 0.3092114329338074,
"learning_rate": 7.910109038788827e-06,
"loss": 0.377197265625,
"step": 487,
"token_acc": 0.8751930298228983
},
{
"epoch": 0.32425249169435216,
"grad_norm": 0.314191997051239,
"learning_rate": 7.901347470981898e-06,
"loss": 0.401123046875,
"step": 488,
"token_acc": 0.8683606579672104
},
{
"epoch": 0.32491694352159467,
"grad_norm": 0.3186595141887665,
"learning_rate": 7.892572451116767e-06,
"loss": 0.373779296875,
"step": 489,
"token_acc": 0.8763712071860914
},
{
"epoch": 0.32558139534883723,
"grad_norm": 0.41251805424690247,
"learning_rate": 7.883784019878696e-06,
"loss": 0.399169921875,
"step": 490,
"token_acc": 0.8683118196548387
},
{
"epoch": 0.32624584717607974,
"grad_norm": 0.3053121268749237,
"learning_rate": 7.874982218015126e-06,
"loss": 0.394287109375,
"step": 491,
"token_acc": 0.869686644822123
},
{
"epoch": 0.32691029900332225,
"grad_norm": 0.3222017288208008,
"learning_rate": 7.866167086335492e-06,
"loss": 0.39111328125,
"step": 492,
"token_acc": 0.8719577887840292
},
{
"epoch": 0.3275747508305648,
"grad_norm": 0.3013986349105835,
"learning_rate": 7.857338665711033e-06,
"loss": 0.394287109375,
"step": 493,
"token_acc": 0.8708027613928162
},
{
"epoch": 0.3282392026578073,
"grad_norm": 0.3461097180843353,
"learning_rate": 7.8484969970746e-06,
"loss": 0.3994140625,
"step": 494,
"token_acc": 0.8690735270593901
},
{
"epoch": 0.3289036544850498,
"grad_norm": 0.383033812046051,
"learning_rate": 7.83964212142047e-06,
"loss": 0.384765625,
"step": 495,
"token_acc": 0.8732630086630728
},
{
"epoch": 0.3295681063122924,
"grad_norm": 0.3242224454879761,
"learning_rate": 7.830774079804155e-06,
"loss": 0.390625,
"step": 496,
"token_acc": 0.8719622594597334
},
{
"epoch": 0.3302325581395349,
"grad_norm": 0.30877241492271423,
"learning_rate": 7.821892913342212e-06,
"loss": 0.406982421875,
"step": 497,
"token_acc": 0.868283794858466
},
{
"epoch": 0.3308970099667774,
"grad_norm": 0.3052292764186859,
"learning_rate": 7.812998663212043e-06,
"loss": 0.391357421875,
"step": 498,
"token_acc": 0.8713234108801629
},
{
"epoch": 0.3315614617940199,
"grad_norm": 0.3169040381908417,
"learning_rate": 7.804091370651723e-06,
"loss": 0.39453125,
"step": 499,
"token_acc": 0.8703276302141257
},
{
"epoch": 0.33222591362126247,
"grad_norm": 0.293649286031723,
"learning_rate": 7.795171076959793e-06,
"loss": 0.3818359375,
"step": 500,
"token_acc": 0.8745513833224785
},
{
"epoch": 0.332890365448505,
"grad_norm": 0.32641100883483887,
"learning_rate": 7.78623782349507e-06,
"loss": 0.392822265625,
"step": 501,
"token_acc": 0.8716181770640528
},
{
"epoch": 0.3335548172757475,
"grad_norm": 0.40121760964393616,
"learning_rate": 7.777291651676466e-06,
"loss": 0.38623046875,
"step": 502,
"token_acc": 0.872918040828773
},
{
"epoch": 0.33421926910299005,
"grad_norm": 0.2958812117576599,
"learning_rate": 7.768332602982784e-06,
"loss": 0.399658203125,
"step": 503,
"token_acc": 0.8683412457725346
},
{
"epoch": 0.33488372093023255,
"grad_norm": 0.3184646964073181,
"learning_rate": 7.75936071895253e-06,
"loss": 0.3876953125,
"step": 504,
"token_acc": 0.8726216357325961
},
{
"epoch": 0.33554817275747506,
"grad_norm": 0.3914191424846649,
"learning_rate": 7.750376041183727e-06,
"loss": 0.38818359375,
"step": 505,
"token_acc": 0.8727839169929409
},
{
"epoch": 0.3362126245847176,
"grad_norm": 0.3151264190673828,
"learning_rate": 7.741378611333707e-06,
"loss": 0.388916015625,
"step": 506,
"token_acc": 0.8719193651579072
},
{
"epoch": 0.33687707641196013,
"grad_norm": 0.30008465051651,
"learning_rate": 7.732368471118936e-06,
"loss": 0.385498046875,
"step": 507,
"token_acc": 0.8731782886640602
},
{
"epoch": 0.33754152823920264,
"grad_norm": 0.27415311336517334,
"learning_rate": 7.723345662314803e-06,
"loss": 0.392822265625,
"step": 508,
"token_acc": 0.8704646984518797
},
{
"epoch": 0.3382059800664452,
"grad_norm": 0.33291879296302795,
"learning_rate": 7.714310226755442e-06,
"loss": 0.36865234375,
"step": 509,
"token_acc": 0.8776066119899226
},
{
"epoch": 0.3388704318936877,
"grad_norm": 0.35381653904914856,
"learning_rate": 7.705262206333524e-06,
"loss": 0.39404296875,
"step": 510,
"token_acc": 0.8710605621575209
},
{
"epoch": 0.3395348837209302,
"grad_norm": 0.307839035987854,
"learning_rate": 7.696201643000075e-06,
"loss": 0.38525390625,
"step": 511,
"token_acc": 0.8733925903251211
},
{
"epoch": 0.3401993355481728,
"grad_norm": 0.31428542733192444,
"learning_rate": 7.687128578764272e-06,
"loss": 0.403076171875,
"step": 512,
"token_acc": 0.8680911224624449
},
{
"epoch": 0.3408637873754153,
"grad_norm": 0.3964312970638275,
"learning_rate": 7.678043055693258e-06,
"loss": 0.39453125,
"step": 513,
"token_acc": 0.8699127129683107
},
{
"epoch": 0.3415282392026578,
"grad_norm": 0.2954295873641968,
"learning_rate": 7.668945115911934e-06,
"loss": 0.38818359375,
"step": 514,
"token_acc": 0.8720913485930131
},
{
"epoch": 0.34219269102990035,
"grad_norm": 0.40076667070388794,
"learning_rate": 7.659834801602776e-06,
"loss": 0.375732421875,
"step": 515,
"token_acc": 0.8758989659906561
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.38568106293678284,
"learning_rate": 7.650712155005632e-06,
"loss": 0.3818359375,
"step": 516,
"token_acc": 0.8741784407746352
},
{
"epoch": 0.34352159468438537,
"grad_norm": 0.2968316972255707,
"learning_rate": 7.641577218417532e-06,
"loss": 0.3994140625,
"step": 517,
"token_acc": 0.8687717902859868
},
{
"epoch": 0.34418604651162793,
"grad_norm": 0.3372710645198822,
"learning_rate": 7.632430034192481e-06,
"loss": 0.377197265625,
"step": 518,
"token_acc": 0.8753237592146853
},
{
"epoch": 0.34485049833887044,
"grad_norm": 0.33212795853614807,
"learning_rate": 7.6232706447412785e-06,
"loss": 0.375732421875,
"step": 519,
"token_acc": 0.8768479301376296
},
{
"epoch": 0.34551495016611294,
"grad_norm": 0.34100988507270813,
"learning_rate": 7.614099092531308e-06,
"loss": 0.401611328125,
"step": 520,
"token_acc": 0.8673532356123999
},
{
"epoch": 0.3461794019933555,
"grad_norm": 0.36628973484039307,
"learning_rate": 7.604915420086348e-06,
"loss": 0.409912109375,
"step": 521,
"token_acc": 0.8659027266993036
},
{
"epoch": 0.346843853820598,
"grad_norm": 0.3395577371120453,
"learning_rate": 7.595719669986367e-06,
"loss": 0.395263671875,
"step": 522,
"token_acc": 0.8707174499709155
},
{
"epoch": 0.3475083056478405,
"grad_norm": 0.38151076436042786,
"learning_rate": 7.58651188486734e-06,
"loss": 0.400390625,
"step": 523,
"token_acc": 0.8679777028764567
},
{
"epoch": 0.3481727574750831,
"grad_norm": 0.3576848804950714,
"learning_rate": 7.577292107421037e-06,
"loss": 0.40771484375,
"step": 524,
"token_acc": 0.8661291299203514
},
{
"epoch": 0.3488372093023256,
"grad_norm": 0.34924784302711487,
"learning_rate": 7.56806038039483e-06,
"loss": 0.407470703125,
"step": 525,
"token_acc": 0.866794182618811
},
{
"epoch": 0.3495016611295681,
"grad_norm": 0.36309629678726196,
"learning_rate": 7.5588167465915e-06,
"loss": 0.385009765625,
"step": 526,
"token_acc": 0.8726410665413326
},
{
"epoch": 0.3501661129568106,
"grad_norm": 0.282292902469635,
"learning_rate": 7.549561248869022e-06,
"loss": 0.393798828125,
"step": 527,
"token_acc": 0.8711640364902128
},
{
"epoch": 0.35083056478405317,
"grad_norm": 0.38887855410575867,
"learning_rate": 7.5402939301403934e-06,
"loss": 0.372802734375,
"step": 528,
"token_acc": 0.8771155520096964
},
{
"epoch": 0.3514950166112957,
"grad_norm": 0.5633757710456848,
"learning_rate": 7.531014833373407e-06,
"loss": 0.392822265625,
"step": 529,
"token_acc": 0.8700496746854363
},
{
"epoch": 0.3521594684385382,
"grad_norm": 0.3868218958377838,
"learning_rate": 7.521724001590471e-06,
"loss": 0.388427734375,
"step": 530,
"token_acc": 0.8719286232849749
},
{
"epoch": 0.35282392026578074,
"grad_norm": 0.29915615916252136,
"learning_rate": 7.512421477868402e-06,
"loss": 0.396484375,
"step": 531,
"token_acc": 0.8689038838991365
},
{
"epoch": 0.35348837209302325,
"grad_norm": 0.3078466057777405,
"learning_rate": 7.503107305338224e-06,
"loss": 0.3837890625,
"step": 532,
"token_acc": 0.8733026764238282
},
{
"epoch": 0.35415282392026576,
"grad_norm": 0.34233367443084717,
"learning_rate": 7.493781527184969e-06,
"loss": 0.39013671875,
"step": 533,
"token_acc": 0.8720480076749342
},
{
"epoch": 0.3548172757475083,
"grad_norm": 0.327929824590683,
"learning_rate": 7.484444186647486e-06,
"loss": 0.3828125,
"step": 534,
"token_acc": 0.8739052443903288
},
{
"epoch": 0.3554817275747508,
"grad_norm": 0.38694724440574646,
"learning_rate": 7.475095327018223e-06,
"loss": 0.382568359375,
"step": 535,
"token_acc": 0.8733681248568531
},
{
"epoch": 0.35614617940199333,
"grad_norm": 0.31480443477630615,
"learning_rate": 7.465734991643045e-06,
"loss": 0.38916015625,
"step": 536,
"token_acc": 0.8721995668166425
},
{
"epoch": 0.3568106312292359,
"grad_norm": 0.3981966972351074,
"learning_rate": 7.456363223921018e-06,
"loss": 0.38427734375,
"step": 537,
"token_acc": 0.8733752726264167
},
{
"epoch": 0.3574750830564784,
"grad_norm": 0.352577269077301,
"learning_rate": 7.446980067304215e-06,
"loss": 0.384033203125,
"step": 538,
"token_acc": 0.8738624492816579
},
{
"epoch": 0.3581395348837209,
"grad_norm": 0.32580602169036865,
"learning_rate": 7.437585565297516e-06,
"loss": 0.384033203125,
"step": 539,
"token_acc": 0.8735767017355528
},
{
"epoch": 0.3588039867109635,
"grad_norm": 0.32203784584999084,
"learning_rate": 7.428179761458401e-06,
"loss": 0.391357421875,
"step": 540,
"token_acc": 0.8710544076630969
},
{
"epoch": 0.359468438538206,
"grad_norm": 0.5275461673736572,
"learning_rate": 7.418762699396752e-06,
"loss": 0.379638671875,
"step": 541,
"token_acc": 0.8752318015914398
},
{
"epoch": 0.3601328903654485,
"grad_norm": 0.3526511490345001,
"learning_rate": 7.409334422774652e-06,
"loss": 0.3876953125,
"step": 542,
"token_acc": 0.8728525219445413
},
{
"epoch": 0.36079734219269105,
"grad_norm": 0.4518231153488159,
"learning_rate": 7.399894975306175e-06,
"loss": 0.38818359375,
"step": 543,
"token_acc": 0.8721641287233413
},
{
"epoch": 0.36146179401993356,
"grad_norm": 0.48952212929725647,
"learning_rate": 7.39044440075719e-06,
"loss": 0.403564453125,
"step": 544,
"token_acc": 0.8673913043478261
},
{
"epoch": 0.36212624584717606,
"grad_norm": 0.37286561727523804,
"learning_rate": 7.380982742945162e-06,
"loss": 0.38525390625,
"step": 545,
"token_acc": 0.8730137103335364
},
{
"epoch": 0.3627906976744186,
"grad_norm": 0.319475919008255,
"learning_rate": 7.371510045738934e-06,
"loss": 0.3935546875,
"step": 546,
"token_acc": 0.8703536831995351
},
{
"epoch": 0.36345514950166113,
"grad_norm": 0.33094334602355957,
"learning_rate": 7.3620263530585446e-06,
"loss": 0.400146484375,
"step": 547,
"token_acc": 0.8683481433557354
},
{
"epoch": 0.36411960132890364,
"grad_norm": 0.3007216453552246,
"learning_rate": 7.352531708875e-06,
"loss": 0.383056640625,
"step": 548,
"token_acc": 0.8740613932937756
},
{
"epoch": 0.3647840531561462,
"grad_norm": 0.32850325107574463,
"learning_rate": 7.343026157210093e-06,
"loss": 0.400390625,
"step": 549,
"token_acc": 0.8687056737105785
},
{
"epoch": 0.3654485049833887,
"grad_norm": 0.34344083070755005,
"learning_rate": 7.333509742136184e-06,
"loss": 0.388427734375,
"step": 550,
"token_acc": 0.872533522340498
},
{
"epoch": 0.3661129568106312,
"grad_norm": 0.3959914743900299,
"learning_rate": 7.3239825077760015e-06,
"loss": 0.380859375,
"step": 551,
"token_acc": 0.874654997123969
},
{
"epoch": 0.3667774086378738,
"grad_norm": 0.2892821729183197,
"learning_rate": 7.314444498302439e-06,
"loss": 0.392333984375,
"step": 552,
"token_acc": 0.8708767742534953
},
{
"epoch": 0.3674418604651163,
"grad_norm": 0.39982840418815613,
"learning_rate": 7.304895757938348e-06,
"loss": 0.392822265625,
"step": 553,
"token_acc": 0.8707577682507707
},
{
"epoch": 0.3681063122923588,
"grad_norm": 0.4800354540348053,
"learning_rate": 7.2953363309563355e-06,
"loss": 0.402099609375,
"step": 554,
"token_acc": 0.8680507712204328
},
{
"epoch": 0.3687707641196013,
"grad_norm": 0.5611690282821655,
"learning_rate": 7.2857662616785506e-06,
"loss": 0.3896484375,
"step": 555,
"token_acc": 0.871490019132757
},
{
"epoch": 0.36943521594684386,
"grad_norm": 0.30715134739875793,
"learning_rate": 7.276185594476495e-06,
"loss": 0.401611328125,
"step": 556,
"token_acc": 0.8686184674683073
},
{
"epoch": 0.37009966777408637,
"grad_norm": 0.2991393506526947,
"learning_rate": 7.266594373770798e-06,
"loss": 0.388916015625,
"step": 557,
"token_acc": 0.8713769999438457
},
{
"epoch": 0.3707641196013289,
"grad_norm": 0.5353915691375732,
"learning_rate": 7.256992644031027e-06,
"loss": 0.404541015625,
"step": 558,
"token_acc": 0.8675001702073455
},
{
"epoch": 0.37142857142857144,
"grad_norm": 0.30727478861808777,
"learning_rate": 7.247380449775472e-06,
"loss": 0.394775390625,
"step": 559,
"token_acc": 0.869981283633094
},
{
"epoch": 0.37209302325581395,
"grad_norm": 0.3363560140132904,
"learning_rate": 7.237757835570939e-06,
"loss": 0.3837890625,
"step": 560,
"token_acc": 0.8736303990538884
},
{
"epoch": 0.37275747508305646,
"grad_norm": 0.33175796270370483,
"learning_rate": 7.228124846032549e-06,
"loss": 0.3914794921875,
"step": 561,
"token_acc": 0.8709114003507363
},
{
"epoch": 0.373421926910299,
"grad_norm": 0.3363397717475891,
"learning_rate": 7.218481525823529e-06,
"loss": 0.404541015625,
"step": 562,
"token_acc": 0.8678010628939155
},
{
"epoch": 0.3740863787375415,
"grad_norm": 0.38896510004997253,
"learning_rate": 7.208827919654999e-06,
"loss": 0.400146484375,
"step": 563,
"token_acc": 0.8688106193834773
},
{
"epoch": 0.37475083056478403,
"grad_norm": 0.5076199173927307,
"learning_rate": 7.1991640722857785e-06,
"loss": 0.388671875,
"step": 564,
"token_acc": 0.8718067757889816
},
{
"epoch": 0.3754152823920266,
"grad_norm": 0.3255603313446045,
"learning_rate": 7.189490028522158e-06,
"loss": 0.377685546875,
"step": 565,
"token_acc": 0.8757652336218882
},
{
"epoch": 0.3760797342192691,
"grad_norm": 0.5705947279930115,
"learning_rate": 7.179805833217716e-06,
"loss": 0.408203125,
"step": 566,
"token_acc": 0.8664413780773582
},
{
"epoch": 0.3767441860465116,
"grad_norm": 0.46202248334884644,
"learning_rate": 7.17011153127309e-06,
"loss": 0.385498046875,
"step": 567,
"token_acc": 0.8731049929275496
},
{
"epoch": 0.37740863787375417,
"grad_norm": 0.3734057545661926,
"learning_rate": 7.160407167635779e-06,
"loss": 0.38427734375,
"step": 568,
"token_acc": 0.873197709089241
},
{
"epoch": 0.3780730897009967,
"grad_norm": 0.3566286563873291,
"learning_rate": 7.150692787299935e-06,
"loss": 0.3994140625,
"step": 569,
"token_acc": 0.86875350573437
},
{
"epoch": 0.3787375415282392,
"grad_norm": 0.29563984274864197,
"learning_rate": 7.140968435306151e-06,
"loss": 0.388916015625,
"step": 570,
"token_acc": 0.8724669987607966
},
{
"epoch": 0.37940199335548175,
"grad_norm": 0.36419713497161865,
"learning_rate": 7.131234156741249e-06,
"loss": 0.40380859375,
"step": 571,
"token_acc": 0.8669563998317679
},
{
"epoch": 0.38006644518272426,
"grad_norm": 0.2925023138523102,
"learning_rate": 7.121489996738086e-06,
"loss": 0.390869140625,
"step": 572,
"token_acc": 0.8710982373526266
},
{
"epoch": 0.38073089700996676,
"grad_norm": 0.3017256259918213,
"learning_rate": 7.1117360004753246e-06,
"loss": 0.391845703125,
"step": 573,
"token_acc": 0.8707588933712169
},
{
"epoch": 0.3813953488372093,
"grad_norm": 0.296383261680603,
"learning_rate": 7.101972213177233e-06,
"loss": 0.37158203125,
"step": 574,
"token_acc": 0.8770708569611532
},
{
"epoch": 0.38205980066445183,
"grad_norm": 0.28878843784332275,
"learning_rate": 7.092198680113484e-06,
"loss": 0.3828125,
"step": 575,
"token_acc": 0.8731166117655365
},
{
"epoch": 0.38272425249169434,
"grad_norm": 0.3489241600036621,
"learning_rate": 7.082415446598927e-06,
"loss": 0.400390625,
"step": 576,
"token_acc": 0.8682774202556389
},
{
"epoch": 0.3833887043189369,
"grad_norm": 0.39100080728530884,
"learning_rate": 7.072622557993394e-06,
"loss": 0.401123046875,
"step": 577,
"token_acc": 0.8684440054223894
},
{
"epoch": 0.3840531561461794,
"grad_norm": 0.3012396991252899,
"learning_rate": 7.062820059701478e-06,
"loss": 0.400390625,
"step": 578,
"token_acc": 0.8692434228515304
},
{
"epoch": 0.3847176079734219,
"grad_norm": 0.3209810256958008,
"learning_rate": 7.053007997172333e-06,
"loss": 0.3916015625,
"step": 579,
"token_acc": 0.8721328424948469
},
{
"epoch": 0.3853820598006645,
"grad_norm": 0.35491830110549927,
"learning_rate": 7.04318641589945e-06,
"loss": 0.390380859375,
"step": 580,
"token_acc": 0.8707896073356323
},
{
"epoch": 0.386046511627907,
"grad_norm": 0.3039889335632324,
"learning_rate": 7.033355361420461e-06,
"loss": 0.40380859375,
"step": 581,
"token_acc": 0.868416996887469
},
{
"epoch": 0.3867109634551495,
"grad_norm": 0.31356582045555115,
"learning_rate": 7.0235148793169115e-06,
"loss": 0.380859375,
"step": 582,
"token_acc": 0.8735155495272202
},
{
"epoch": 0.387375415282392,
"grad_norm": 0.2752210795879364,
"learning_rate": 7.01366501521407e-06,
"loss": 0.38623046875,
"step": 583,
"token_acc": 0.8727618704898681
},
{
"epoch": 0.38803986710963456,
"grad_norm": 0.32784608006477356,
"learning_rate": 7.003805814780692e-06,
"loss": 0.39306640625,
"step": 584,
"token_acc": 0.8709699212521049
},
{
"epoch": 0.38870431893687707,
"grad_norm": 0.3082878291606903,
"learning_rate": 6.993937323728829e-06,
"loss": 0.393798828125,
"step": 585,
"token_acc": 0.8704406359935686
},
{
"epoch": 0.3893687707641196,
"grad_norm": 0.29360559582710266,
"learning_rate": 6.984059587813607e-06,
"loss": 0.37548828125,
"step": 586,
"token_acc": 0.8755804498555056
},
{
"epoch": 0.39003322259136214,
"grad_norm": 0.3058871626853943,
"learning_rate": 6.974172652833013e-06,
"loss": 0.40625,
"step": 587,
"token_acc": 0.8665213996577826
},
{
"epoch": 0.39069767441860465,
"grad_norm": 0.3636281490325928,
"learning_rate": 6.9642765646276875e-06,
"loss": 0.40087890625,
"step": 588,
"token_acc": 0.8684104740676232
},
{
"epoch": 0.39136212624584715,
"grad_norm": 0.36492642760276794,
"learning_rate": 6.95437136908071e-06,
"loss": 0.4052734375,
"step": 589,
"token_acc": 0.8665030035259278
},
{
"epoch": 0.3920265780730897,
"grad_norm": 0.2816954553127289,
"learning_rate": 6.944457112117384e-06,
"loss": 0.387451171875,
"step": 590,
"token_acc": 0.8717851565836533
},
{
"epoch": 0.3926910299003322,
"grad_norm": 0.3134591281414032,
"learning_rate": 6.934533839705029e-06,
"loss": 0.383056640625,
"step": 591,
"token_acc": 0.8734602419727711
},
{
"epoch": 0.39335548172757473,
"grad_norm": 0.33944302797317505,
"learning_rate": 6.92460159785276e-06,
"loss": 0.394775390625,
"step": 592,
"token_acc": 0.8697970099469172
},
{
"epoch": 0.3940199335548173,
"grad_norm": 0.3522343635559082,
"learning_rate": 6.9146604326112856e-06,
"loss": 0.3974609375,
"step": 593,
"token_acc": 0.8697927775955429
},
{
"epoch": 0.3946843853820598,
"grad_norm": 0.30377456545829773,
"learning_rate": 6.9047103900726804e-06,
"loss": 0.380859375,
"step": 594,
"token_acc": 0.8751456771168752
},
{
"epoch": 0.3953488372093023,
"grad_norm": 0.3039657771587372,
"learning_rate": 6.894751516370184e-06,
"loss": 0.40771484375,
"step": 595,
"token_acc": 0.8660820275646793
},
{
"epoch": 0.39601328903654487,
"grad_norm": 0.4902065098285675,
"learning_rate": 6.884783857677977e-06,
"loss": 0.389404296875,
"step": 596,
"token_acc": 0.8716332073868378
},
{
"epoch": 0.3966777408637874,
"grad_norm": 0.35061872005462646,
"learning_rate": 6.874807460210975e-06,
"loss": 0.400390625,
"step": 597,
"token_acc": 0.8693967534032486
},
{
"epoch": 0.3973421926910299,
"grad_norm": 0.3162485659122467,
"learning_rate": 6.864822370224611e-06,
"loss": 0.40234375,
"step": 598,
"token_acc": 0.8678882327336122
},
{
"epoch": 0.39800664451827245,
"grad_norm": 0.3217385411262512,
"learning_rate": 6.854828634014617e-06,
"loss": 0.373779296875,
"step": 599,
"token_acc": 0.8769719193758767
},
{
"epoch": 0.39867109634551495,
"grad_norm": 0.267958402633667,
"learning_rate": 6.844826297916816e-06,
"loss": 0.389892578125,
"step": 600,
"token_acc": 0.8716151451413883
},
{
"epoch": 0.39933554817275746,
"grad_norm": 0.27999481558799744,
"learning_rate": 6.834815408306903e-06,
"loss": 0.3818359375,
"step": 601,
"token_acc": 0.8741555011951583
},
{
"epoch": 0.4,
"grad_norm": 0.3192073404788971,
"learning_rate": 6.824796011600234e-06,
"loss": 0.384033203125,
"step": 602,
"token_acc": 0.8737392804210442
},
{
"epoch": 0.40066445182724253,
"grad_norm": 0.33648890256881714,
"learning_rate": 6.814768154251605e-06,
"loss": 0.38671875,
"step": 603,
"token_acc": 0.8722198606219773
},
{
"epoch": 0.40132890365448504,
"grad_norm": 0.3265593349933624,
"learning_rate": 6.80473188275504e-06,
"loss": 0.37255859375,
"step": 604,
"token_acc": 0.8773013729961873
},
{
"epoch": 0.4019933554817276,
"grad_norm": 0.3478454351425171,
"learning_rate": 6.794687243643575e-06,
"loss": 0.390380859375,
"step": 605,
"token_acc": 0.8715753035848902
},
{
"epoch": 0.4026578073089701,
"grad_norm": 0.28909483551979065,
"learning_rate": 6.7846342834890465e-06,
"loss": 0.3916015625,
"step": 606,
"token_acc": 0.8713850870137387
},
{
"epoch": 0.4033222591362126,
"grad_norm": 0.37093815207481384,
"learning_rate": 6.774573048901864e-06,
"loss": 0.394775390625,
"step": 607,
"token_acc": 0.8708253582122208
},
{
"epoch": 0.4039867109634552,
"grad_norm": 0.41171008348464966,
"learning_rate": 6.764503586530806e-06,
"loss": 0.392822265625,
"step": 608,
"token_acc": 0.8715101398354442
},
{
"epoch": 0.4046511627906977,
"grad_norm": 0.3013271987438202,
"learning_rate": 6.7544259430628e-06,
"loss": 0.3994140625,
"step": 609,
"token_acc": 0.8695397945040207
},
{
"epoch": 0.4053156146179402,
"grad_norm": 0.35518839955329895,
"learning_rate": 6.7443401652227e-06,
"loss": 0.394775390625,
"step": 610,
"token_acc": 0.8697707087185065
},
{
"epoch": 0.4059800664451827,
"grad_norm": 0.4131809175014496,
"learning_rate": 6.734246299773084e-06,
"loss": 0.40185546875,
"step": 611,
"token_acc": 0.8675394395584051
},
{
"epoch": 0.40664451827242526,
"grad_norm": 0.3327007591724396,
"learning_rate": 6.724144393514016e-06,
"loss": 0.38623046875,
"step": 612,
"token_acc": 0.8730774317265093
},
{
"epoch": 0.40730897009966777,
"grad_norm": 0.3027367889881134,
"learning_rate": 6.714034493282851e-06,
"loss": 0.386474609375,
"step": 613,
"token_acc": 0.8725119057513185
},
{
"epoch": 0.4079734219269103,
"grad_norm": 0.2721278667449951,
"learning_rate": 6.703916645954003e-06,
"loss": 0.384765625,
"step": 614,
"token_acc": 0.8735756388836681
},
{
"epoch": 0.40863787375415284,
"grad_norm": 0.3127068877220154,
"learning_rate": 6.693790898438734e-06,
"loss": 0.38818359375,
"step": 615,
"token_acc": 0.8718159347445247
},
{
"epoch": 0.40930232558139534,
"grad_norm": 0.30806681513786316,
"learning_rate": 6.683657297684936e-06,
"loss": 0.3994140625,
"step": 616,
"token_acc": 0.8680863959835828
},
{
"epoch": 0.40996677740863785,
"grad_norm": 0.2945326566696167,
"learning_rate": 6.67351589067691e-06,
"loss": 0.3974609375,
"step": 617,
"token_acc": 0.8696792118185062
},
{
"epoch": 0.4106312292358804,
"grad_norm": 0.3044951260089874,
"learning_rate": 6.663366724435152e-06,
"loss": 0.40283203125,
"step": 618,
"token_acc": 0.8672235868482304
},
{
"epoch": 0.4112956810631229,
"grad_norm": 0.31290286779403687,
"learning_rate": 6.6532098460161364e-06,
"loss": 0.374267578125,
"step": 619,
"token_acc": 0.8767095042354799
},
{
"epoch": 0.4119601328903654,
"grad_norm": 0.3113996684551239,
"learning_rate": 6.64304530251209e-06,
"loss": 0.3779296875,
"step": 620,
"token_acc": 0.8755136111470923
},
{
"epoch": 0.412624584717608,
"grad_norm": 0.45883384346961975,
"learning_rate": 6.63287314105078e-06,
"loss": 0.393798828125,
"step": 621,
"token_acc": 0.871295235427678
},
{
"epoch": 0.4132890365448505,
"grad_norm": 0.30664464831352234,
"learning_rate": 6.622693408795297e-06,
"loss": 0.389404296875,
"step": 622,
"token_acc": 0.8711585476876454
},
{
"epoch": 0.413953488372093,
"grad_norm": 0.41184279322624207,
"learning_rate": 6.612506152943829e-06,
"loss": 0.38916015625,
"step": 623,
"token_acc": 0.8718587607681371
},
{
"epoch": 0.41461794019933557,
"grad_norm": 0.3230541944503784,
"learning_rate": 6.6023114207294536e-06,
"loss": 0.39697265625,
"step": 624,
"token_acc": 0.8688426896915903
},
{
"epoch": 0.4152823920265781,
"grad_norm": 0.4575086236000061,
"learning_rate": 6.592109259419906e-06,
"loss": 0.388671875,
"step": 625,
"token_acc": 0.8719104488285405
},
{
"epoch": 0.4159468438538206,
"grad_norm": 0.6424993872642517,
"learning_rate": 6.581899716317368e-06,
"loss": 0.406005859375,
"step": 626,
"token_acc": 0.8667359930435685
},
{
"epoch": 0.41661129568106314,
"grad_norm": 0.3573512136936188,
"learning_rate": 6.57168283875825e-06,
"loss": 0.395751953125,
"step": 627,
"token_acc": 0.8698666663787901
},
{
"epoch": 0.41727574750830565,
"grad_norm": 0.35697638988494873,
"learning_rate": 6.561458674112964e-06,
"loss": 0.395263671875,
"step": 628,
"token_acc": 0.8699431884870604
},
{
"epoch": 0.41794019933554816,
"grad_norm": 0.3066292405128479,
"learning_rate": 6.551227269785712e-06,
"loss": 0.412353515625,
"step": 629,
"token_acc": 0.8656326465691004
},
{
"epoch": 0.4186046511627907,
"grad_norm": 0.2902214825153351,
"learning_rate": 6.540988673214262e-06,
"loss": 0.390869140625,
"step": 630,
"token_acc": 0.8712683267649917
},
{
"epoch": 0.4192691029900332,
"grad_norm": 0.3683512210845947,
"learning_rate": 6.530742931869725e-06,
"loss": 0.37890625,
"step": 631,
"token_acc": 0.8744614287335267
},
{
"epoch": 0.41993355481727573,
"grad_norm": 0.29113927483558655,
"learning_rate": 6.520490093256344e-06,
"loss": 0.385986328125,
"step": 632,
"token_acc": 0.8728435879535106
},
{
"epoch": 0.4205980066445183,
"grad_norm": 0.3295769989490509,
"learning_rate": 6.5102302049112675e-06,
"loss": 0.3916015625,
"step": 633,
"token_acc": 0.8702709523735729
},
{
"epoch": 0.4212624584717608,
"grad_norm": 0.4327145218849182,
"learning_rate": 6.499963314404329e-06,
"loss": 0.382568359375,
"step": 634,
"token_acc": 0.8742313558465304
},
{
"epoch": 0.4219269102990033,
"grad_norm": 0.3222288191318512,
"learning_rate": 6.4896894693378235e-06,
"loss": 0.393798828125,
"step": 635,
"token_acc": 0.870276782926082
},
{
"epoch": 0.4225913621262459,
"grad_norm": 0.43689069151878357,
"learning_rate": 6.479408717346296e-06,
"loss": 0.387939453125,
"step": 636,
"token_acc": 0.8721931309130722
},
{
"epoch": 0.4232558139534884,
"grad_norm": 0.29585686326026917,
"learning_rate": 6.469121106096316e-06,
"loss": 0.39013671875,
"step": 637,
"token_acc": 0.871363091895331
},
{
"epoch": 0.4239202657807309,
"grad_norm": 0.3186410963535309,
"learning_rate": 6.458826683286249e-06,
"loss": 0.392822265625,
"step": 638,
"token_acc": 0.8708470894206078
},
{
"epoch": 0.4245847176079734,
"grad_norm": 0.3167760372161865,
"learning_rate": 6.44852549664605e-06,
"loss": 0.382080078125,
"step": 639,
"token_acc": 0.8741883056090236
},
{
"epoch": 0.42524916943521596,
"grad_norm": 0.310505747795105,
"learning_rate": 6.43821759393703e-06,
"loss": 0.384033203125,
"step": 640,
"token_acc": 0.8737563387312903
},
{
"epoch": 0.42591362126245846,
"grad_norm": 0.3200778067111969,
"learning_rate": 6.427903022951642e-06,
"loss": 0.40966796875,
"step": 641,
"token_acc": 0.8655387857617769
},
{
"epoch": 0.42657807308970097,
"grad_norm": 0.32216042280197144,
"learning_rate": 6.417581831513253e-06,
"loss": 0.389892578125,
"step": 642,
"token_acc": 0.872080309894943
},
{
"epoch": 0.42724252491694353,
"grad_norm": 0.6105049848556519,
"learning_rate": 6.407254067475927e-06,
"loss": 0.3857421875,
"step": 643,
"token_acc": 0.8725373998796722
},
{
"epoch": 0.42790697674418604,
"grad_norm": 0.35335054993629456,
"learning_rate": 6.396919778724201e-06,
"loss": 0.38427734375,
"step": 644,
"token_acc": 0.8735467721059893
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.28786659240722656,
"learning_rate": 6.386579013172867e-06,
"loss": 0.3837890625,
"step": 645,
"token_acc": 0.8733286167049173
},
{
"epoch": 0.4292358803986711,
"grad_norm": 0.29147157073020935,
"learning_rate": 6.37623181876674e-06,
"loss": 0.398681640625,
"step": 646,
"token_acc": 0.8683368233274052
},
{
"epoch": 0.4299003322259136,
"grad_norm": 0.37826284766197205,
"learning_rate": 6.3658782434804535e-06,
"loss": 0.39111328125,
"step": 647,
"token_acc": 0.8713434205527189
},
{
"epoch": 0.4305647840531561,
"grad_norm": 0.30985933542251587,
"learning_rate": 6.355518335318213e-06,
"loss": 0.391357421875,
"step": 648,
"token_acc": 0.8707076337043139
},
{
"epoch": 0.4312292358803987,
"grad_norm": 0.35761094093322754,
"learning_rate": 6.345152142313593e-06,
"loss": 0.387451171875,
"step": 649,
"token_acc": 0.8718756460130425
},
{
"epoch": 0.4318936877076412,
"grad_norm": 0.34080514311790466,
"learning_rate": 6.334779712529311e-06,
"loss": 0.399169921875,
"step": 650,
"token_acc": 0.8687615497210991
},
{
"epoch": 0.4325581395348837,
"grad_norm": 0.36210209131240845,
"learning_rate": 6.324401094056991e-06,
"loss": 0.376953125,
"step": 651,
"token_acc": 0.8746711222169338
},
{
"epoch": 0.43322259136212626,
"grad_norm": 0.2979786694049835,
"learning_rate": 6.314016335016961e-06,
"loss": 0.3837890625,
"step": 652,
"token_acc": 0.873991969920223
},
{
"epoch": 0.43388704318936877,
"grad_norm": 0.6792043447494507,
"learning_rate": 6.303625483558015e-06,
"loss": 0.40087890625,
"step": 653,
"token_acc": 0.8679729671969455
},
{
"epoch": 0.4345514950166113,
"grad_norm": 0.36083295941352844,
"learning_rate": 6.293228587857191e-06,
"loss": 0.373291015625,
"step": 654,
"token_acc": 0.8765258600450975
},
{
"epoch": 0.43521594684385384,
"grad_norm": 0.32064348459243774,
"learning_rate": 6.28282569611956e-06,
"loss": 0.3828125,
"step": 655,
"token_acc": 0.8733523434763866
},
{
"epoch": 0.43588039867109635,
"grad_norm": 0.27732545137405396,
"learning_rate": 6.272416856577988e-06,
"loss": 0.385498046875,
"step": 656,
"token_acc": 0.8726518342128763
},
{
"epoch": 0.43654485049833885,
"grad_norm": 0.3216395676136017,
"learning_rate": 6.2620021174929125e-06,
"loss": 0.392333984375,
"step": 657,
"token_acc": 0.8711796961113979
},
{
"epoch": 0.4372093023255814,
"grad_norm": 0.34744346141815186,
"learning_rate": 6.251581527152137e-06,
"loss": 0.396484375,
"step": 658,
"token_acc": 0.8702136010039309
},
{
"epoch": 0.4378737541528239,
"grad_norm": 0.5101602077484131,
"learning_rate": 6.241155133870584e-06,
"loss": 0.38037109375,
"step": 659,
"token_acc": 0.8740608469883542
},
{
"epoch": 0.43853820598006643,
"grad_norm": 0.4132077395915985,
"learning_rate": 6.230722985990085e-06,
"loss": 0.380859375,
"step": 660,
"token_acc": 0.8743431839241215
},
{
"epoch": 0.439202657807309,
"grad_norm": 0.34309518337249756,
"learning_rate": 6.220285131879153e-06,
"loss": 0.375,
"step": 661,
"token_acc": 0.8753362826567824
},
{
"epoch": 0.4398671096345515,
"grad_norm": 0.32569873332977295,
"learning_rate": 6.2098416199327575e-06,
"loss": 0.404052734375,
"step": 662,
"token_acc": 0.8686652799984289
},
{
"epoch": 0.440531561461794,
"grad_norm": 0.2911350429058075,
"learning_rate": 6.199392498572096e-06,
"loss": 0.40087890625,
"step": 663,
"token_acc": 0.8678586103241712
},
{
"epoch": 0.44119601328903657,
"grad_norm": 0.3359164297580719,
"learning_rate": 6.188937816244383e-06,
"loss": 0.3857421875,
"step": 664,
"token_acc": 0.8734038420502607
},
{
"epoch": 0.4418604651162791,
"grad_norm": 0.3379848599433899,
"learning_rate": 6.178477621422607e-06,
"loss": 0.39892578125,
"step": 665,
"token_acc": 0.8685960171878325
},
{
"epoch": 0.4425249169435216,
"grad_norm": 0.3262694478034973,
"learning_rate": 6.168011962605324e-06,
"loss": 0.402587890625,
"step": 666,
"token_acc": 0.8681832873540583
},
{
"epoch": 0.44318936877076415,
"grad_norm": 0.29981449246406555,
"learning_rate": 6.157540888316414e-06,
"loss": 0.373779296875,
"step": 667,
"token_acc": 0.8764062168409418
},
{
"epoch": 0.44385382059800665,
"grad_norm": 0.41969063878059387,
"learning_rate": 6.147064447104876e-06,
"loss": 0.3740234375,
"step": 668,
"token_acc": 0.8762721225811602
},
{
"epoch": 0.44451827242524916,
"grad_norm": 0.2832077145576477,
"learning_rate": 6.136582687544585e-06,
"loss": 0.3631591796875,
"step": 669,
"token_acc": 0.8792777458996663
},
{
"epoch": 0.44518272425249167,
"grad_norm": 0.3224434554576874,
"learning_rate": 6.126095658234076e-06,
"loss": 0.4052734375,
"step": 670,
"token_acc": 0.8671002052725564
},
{
"epoch": 0.44584717607973423,
"grad_norm": 0.3068777322769165,
"learning_rate": 6.11560340779632e-06,
"loss": 0.38232421875,
"step": 671,
"token_acc": 0.8738509636711964
},
{
"epoch": 0.44651162790697674,
"grad_norm": 0.304079532623291,
"learning_rate": 6.105105984878493e-06,
"loss": 0.37646484375,
"step": 672,
"token_acc": 0.8765765842775387
},
{
"epoch": 0.44717607973421925,
"grad_norm": 0.3937017619609833,
"learning_rate": 6.094603438151756e-06,
"loss": 0.38427734375,
"step": 673,
"token_acc": 0.8740672913188624
},
{
"epoch": 0.4478405315614618,
"grad_norm": 0.3639538288116455,
"learning_rate": 6.084095816311022e-06,
"loss": 0.382080078125,
"step": 674,
"token_acc": 0.8740559612864889
},
{
"epoch": 0.4485049833887043,
"grad_norm": 0.3419860899448395,
"learning_rate": 6.073583168074737e-06,
"loss": 0.37890625,
"step": 675,
"token_acc": 0.8745313785337655
},
{
"epoch": 0.4491694352159468,
"grad_norm": 0.2914302945137024,
"learning_rate": 6.063065542184654e-06,
"loss": 0.387451171875,
"step": 676,
"token_acc": 0.871966329893331
},
{
"epoch": 0.4498338870431894,
"grad_norm": 0.2973076403141022,
"learning_rate": 6.052542987405602e-06,
"loss": 0.379638671875,
"step": 677,
"token_acc": 0.8749820390148938
},
{
"epoch": 0.4504983388704319,
"grad_norm": 0.2923094928264618,
"learning_rate": 6.0420155525252625e-06,
"loss": 0.390380859375,
"step": 678,
"token_acc": 0.8714355625512789
},
{
"epoch": 0.4511627906976744,
"grad_norm": 0.3252160847187042,
"learning_rate": 6.031483286353945e-06,
"loss": 0.405517578125,
"step": 679,
"token_acc": 0.8665457434949979
},
{
"epoch": 0.45182724252491696,
"grad_norm": 0.4103677570819855,
"learning_rate": 6.02094623772436e-06,
"loss": 0.377197265625,
"step": 680,
"token_acc": 0.8755501446816646
},
{
"epoch": 0.45249169435215947,
"grad_norm": 0.32133424282073975,
"learning_rate": 6.01040445549139e-06,
"loss": 0.377685546875,
"step": 681,
"token_acc": 0.8753299249399985
},
{
"epoch": 0.453156146179402,
"grad_norm": 0.3139162063598633,
"learning_rate": 5.999857988531864e-06,
"loss": 0.3818359375,
"step": 682,
"token_acc": 0.8739043604297363
},
{
"epoch": 0.45382059800664454,
"grad_norm": 0.3147526681423187,
"learning_rate": 5.9893068857443335e-06,
"loss": 0.39794921875,
"step": 683,
"token_acc": 0.8693157407214099
},
{
"epoch": 0.45448504983388704,
"grad_norm": 0.3001363277435303,
"learning_rate": 5.9787511960488465e-06,
"loss": 0.391357421875,
"step": 684,
"token_acc": 0.8721635398954964
},
{
"epoch": 0.45514950166112955,
"grad_norm": 0.3089321553707123,
"learning_rate": 5.968190968386709e-06,
"loss": 0.391357421875,
"step": 685,
"token_acc": 0.8714237269681552
},
{
"epoch": 0.4558139534883721,
"grad_norm": 0.41252511739730835,
"learning_rate": 5.957626251720281e-06,
"loss": 0.396728515625,
"step": 686,
"token_acc": 0.8692530556144269
},
{
"epoch": 0.4564784053156146,
"grad_norm": 0.2758471667766571,
"learning_rate": 5.947057095032721e-06,
"loss": 0.376708984375,
"step": 687,
"token_acc": 0.874995811920086
},
{
"epoch": 0.45714285714285713,
"grad_norm": 0.39247530698776245,
"learning_rate": 5.936483547327785e-06,
"loss": 0.390380859375,
"step": 688,
"token_acc": 0.8712588238165934
},
{
"epoch": 0.4578073089700997,
"grad_norm": 0.3164578974246979,
"learning_rate": 5.925905657629583e-06,
"loss": 0.3798828125,
"step": 689,
"token_acc": 0.8741790819823176
},
{
"epoch": 0.4584717607973422,
"grad_norm": 0.3370855450630188,
"learning_rate": 5.915323474982354e-06,
"loss": 0.394287109375,
"step": 690,
"token_acc": 0.8704690046111708
},
{
"epoch": 0.4591362126245847,
"grad_norm": 0.3118404448032379,
"learning_rate": 5.904737048450249e-06,
"loss": 0.379150390625,
"step": 691,
"token_acc": 0.8747350934578664
},
{
"epoch": 0.45980066445182727,
"grad_norm": 0.29149729013442993,
"learning_rate": 5.894146427117089e-06,
"loss": 0.39111328125,
"step": 692,
"token_acc": 0.8711745256791332
},
{
"epoch": 0.4604651162790698,
"grad_norm": 0.48533496260643005,
"learning_rate": 5.883551660086143e-06,
"loss": 0.376708984375,
"step": 693,
"token_acc": 0.8760206938808666
},
{
"epoch": 0.4611295681063123,
"grad_norm": 0.8594257831573486,
"learning_rate": 5.872952796479911e-06,
"loss": 0.388671875,
"step": 694,
"token_acc": 0.8719096834572397
},
{
"epoch": 0.46179401993355484,
"grad_norm": 0.326411634683609,
"learning_rate": 5.8623498854398746e-06,
"loss": 0.404296875,
"step": 695,
"token_acc": 0.8669295497872951
},
{
"epoch": 0.46245847176079735,
"grad_norm": 0.30838167667388916,
"learning_rate": 5.851742976126289e-06,
"loss": 0.380859375,
"step": 696,
"token_acc": 0.8748626221608123
},
{
"epoch": 0.46312292358803986,
"grad_norm": 0.3619641065597534,
"learning_rate": 5.841132117717948e-06,
"loss": 0.389892578125,
"step": 697,
"token_acc": 0.8725761305580453
},
{
"epoch": 0.46378737541528237,
"grad_norm": 0.3062770962715149,
"learning_rate": 5.830517359411949e-06,
"loss": 0.38232421875,
"step": 698,
"token_acc": 0.8744984375413858
},
{
"epoch": 0.46445182724252493,
"grad_norm": 0.3252392113208771,
"learning_rate": 5.819898750423476e-06,
"loss": 0.38134765625,
"step": 699,
"token_acc": 0.8743573712393867
},
{
"epoch": 0.46511627906976744,
"grad_norm": 0.382646769285202,
"learning_rate": 5.809276339985568e-06,
"loss": 0.37939453125,
"step": 700,
"token_acc": 0.8749317342800242
},
{
"epoch": 0.46578073089700994,
"grad_norm": 0.3475249409675598,
"learning_rate": 5.798650177348883e-06,
"loss": 0.3896484375,
"step": 701,
"token_acc": 0.8718158168662273
},
{
"epoch": 0.4664451827242525,
"grad_norm": 0.3222896158695221,
"learning_rate": 5.788020311781483e-06,
"loss": 0.39990234375,
"step": 702,
"token_acc": 0.8685261610400652
},
{
"epoch": 0.467109634551495,
"grad_norm": 0.5257053971290588,
"learning_rate": 5.777386792568593e-06,
"loss": 0.3916015625,
"step": 703,
"token_acc": 0.8720993450252903
},
{
"epoch": 0.4677740863787375,
"grad_norm": 0.3853687047958374,
"learning_rate": 5.766749669012383e-06,
"loss": 0.38623046875,
"step": 704,
"token_acc": 0.872613637452735
},
{
"epoch": 0.4684385382059801,
"grad_norm": 0.3185330927371979,
"learning_rate": 5.7561089904317315e-06,
"loss": 0.375244140625,
"step": 705,
"token_acc": 0.8756375125497885
},
{
"epoch": 0.4691029900332226,
"grad_norm": 0.32625579833984375,
"learning_rate": 5.745464806161999e-06,
"loss": 0.3779296875,
"step": 706,
"token_acc": 0.8744300766928292
},
{
"epoch": 0.4697674418604651,
"grad_norm": 0.36841830611228943,
"learning_rate": 5.734817165554803e-06,
"loss": 0.39599609375,
"step": 707,
"token_acc": 0.8704261841574431
},
{
"epoch": 0.47043189368770766,
"grad_norm": 0.34433746337890625,
"learning_rate": 5.724166117977785e-06,
"loss": 0.370361328125,
"step": 708,
"token_acc": 0.8778510569993894
},
{
"epoch": 0.47109634551495017,
"grad_norm": 0.3421313762664795,
"learning_rate": 5.713511712814381e-06,
"loss": 0.406982421875,
"step": 709,
"token_acc": 0.8666437154028764
},
{
"epoch": 0.4717607973421927,
"grad_norm": 0.38109391927719116,
"learning_rate": 5.702853999463598e-06,
"loss": 0.39794921875,
"step": 710,
"token_acc": 0.8692400457731462
},
{
"epoch": 0.47242524916943524,
"grad_norm": 0.3573138415813446,
"learning_rate": 5.6921930273397785e-06,
"loss": 0.38671875,
"step": 711,
"token_acc": 0.8716359548096961
},
{
"epoch": 0.47308970099667774,
"grad_norm": 0.33360031247138977,
"learning_rate": 5.681528845872374e-06,
"loss": 0.400390625,
"step": 712,
"token_acc": 0.8682825622983783
},
{
"epoch": 0.47375415282392025,
"grad_norm": 0.3415568470954895,
"learning_rate": 5.6708615045057205e-06,
"loss": 0.403564453125,
"step": 713,
"token_acc": 0.8689617606253129
},
{
"epoch": 0.4744186046511628,
"grad_norm": 0.3069683909416199,
"learning_rate": 5.660191052698797e-06,
"loss": 0.402099609375,
"step": 714,
"token_acc": 0.8677227420980647
},
{
"epoch": 0.4750830564784053,
"grad_norm": 0.39527443051338196,
"learning_rate": 5.649517539925011e-06,
"loss": 0.392333984375,
"step": 715,
"token_acc": 0.8707248312837935
},
{
"epoch": 0.4757475083056478,
"grad_norm": 0.3813740611076355,
"learning_rate": 5.638841015671961e-06,
"loss": 0.386474609375,
"step": 716,
"token_acc": 0.8729125204051968
},
{
"epoch": 0.4764119601328904,
"grad_norm": 0.3547273874282837,
"learning_rate": 5.628161529441207e-06,
"loss": 0.39892578125,
"step": 717,
"token_acc": 0.8688925300022077
},
{
"epoch": 0.4770764119601329,
"grad_norm": 0.3414980173110962,
"learning_rate": 5.617479130748039e-06,
"loss": 0.389892578125,
"step": 718,
"token_acc": 0.8719824404581457
},
{
"epoch": 0.4777408637873754,
"grad_norm": 0.3076767027378082,
"learning_rate": 5.606793869121255e-06,
"loss": 0.387939453125,
"step": 719,
"token_acc": 0.8715195685461707
},
{
"epoch": 0.47840531561461797,
"grad_norm": 0.3461492359638214,
"learning_rate": 5.596105794102927e-06,
"loss": 0.373046875,
"step": 720,
"token_acc": 0.8764682993536953
},
{
"epoch": 0.4790697674418605,
"grad_norm": 0.34477221965789795,
"learning_rate": 5.58541495524817e-06,
"loss": 0.3916015625,
"step": 721,
"token_acc": 0.8705793295432094
},
{
"epoch": 0.479734219269103,
"grad_norm": 0.32059773802757263,
"learning_rate": 5.57472140212491e-06,
"loss": 0.387939453125,
"step": 722,
"token_acc": 0.8724002384201046
},
{
"epoch": 0.48039867109634554,
"grad_norm": 0.3164149522781372,
"learning_rate": 5.564025184313664e-06,
"loss": 0.379150390625,
"step": 723,
"token_acc": 0.8747237013895235
},
{
"epoch": 0.48106312292358805,
"grad_norm": 0.33556994795799255,
"learning_rate": 5.5533263514073e-06,
"loss": 0.38134765625,
"step": 724,
"token_acc": 0.8748324443074162
},
{
"epoch": 0.48172757475083056,
"grad_norm": 0.3095529079437256,
"learning_rate": 5.542624953010813e-06,
"loss": 0.398681640625,
"step": 725,
"token_acc": 0.8702529779777047
},
{
"epoch": 0.48239202657807306,
"grad_norm": 0.38230907917022705,
"learning_rate": 5.531921038741089e-06,
"loss": 0.38525390625,
"step": 726,
"token_acc": 0.8733742791504524
},
{
"epoch": 0.4830564784053156,
"grad_norm": 0.3473353385925293,
"learning_rate": 5.521214658226683e-06,
"loss": 0.390380859375,
"step": 727,
"token_acc": 0.8704748269944816
},
{
"epoch": 0.48372093023255813,
"grad_norm": 0.36739230155944824,
"learning_rate": 5.510505861107583e-06,
"loss": 0.3720703125,
"step": 728,
"token_acc": 0.8774037310915764
},
{
"epoch": 0.48438538205980064,
"grad_norm": 0.2890405058860779,
"learning_rate": 5.49979469703498e-06,
"loss": 0.38916015625,
"step": 729,
"token_acc": 0.871762295916318
},
{
"epoch": 0.4850498338870432,
"grad_norm": 0.42307355999946594,
"learning_rate": 5.489081215671045e-06,
"loss": 0.369140625,
"step": 730,
"token_acc": 0.8784715519349318
},
{
"epoch": 0.4857142857142857,
"grad_norm": 0.3188696801662445,
"learning_rate": 5.478365466688687e-06,
"loss": 0.403564453125,
"step": 731,
"token_acc": 0.8665803720796387
},
{
"epoch": 0.4863787375415282,
"grad_norm": 0.2989635765552521,
"learning_rate": 5.4676474997713256e-06,
"loss": 0.374267578125,
"step": 732,
"token_acc": 0.8766306444629269
},
{
"epoch": 0.4870431893687708,
"grad_norm": 0.3063195049762726,
"learning_rate": 5.4569273646126775e-06,
"loss": 0.3759765625,
"step": 733,
"token_acc": 0.8750181007033648
},
{
"epoch": 0.4877076411960133,
"grad_norm": 0.34909337759017944,
"learning_rate": 5.446205110916498e-06,
"loss": 0.3759765625,
"step": 734,
"token_acc": 0.8760988250877426
},
{
"epoch": 0.4883720930232558,
"grad_norm": 0.336477130651474,
"learning_rate": 5.435480788396374e-06,
"loss": 0.396728515625,
"step": 735,
"token_acc": 0.8706978486680186
},
{
"epoch": 0.48903654485049836,
"grad_norm": 0.30653026700019836,
"learning_rate": 5.424754446775481e-06,
"loss": 0.388671875,
"step": 736,
"token_acc": 0.8716993077856606
},
{
"epoch": 0.48970099667774086,
"grad_norm": 0.30163106322288513,
"learning_rate": 5.414026135786355e-06,
"loss": 0.39306640625,
"step": 737,
"token_acc": 0.8698077268643306
},
{
"epoch": 0.49036544850498337,
"grad_norm": 0.3763563930988312,
"learning_rate": 5.4032959051706656e-06,
"loss": 0.379638671875,
"step": 738,
"token_acc": 0.8747006087485963
},
{
"epoch": 0.49102990033222593,
"grad_norm": 0.3092363476753235,
"learning_rate": 5.392563804678983e-06,
"loss": 0.368408203125,
"step": 739,
"token_acc": 0.8779047995795243
},
{
"epoch": 0.49169435215946844,
"grad_norm": 0.289611279964447,
"learning_rate": 5.38182988407054e-06,
"loss": 0.389404296875,
"step": 740,
"token_acc": 0.8711265375592202
},
{
"epoch": 0.49235880398671095,
"grad_norm": 0.2679208219051361,
"learning_rate": 5.371094193113022e-06,
"loss": 0.38232421875,
"step": 741,
"token_acc": 0.8744116121555666
},
{
"epoch": 0.4930232558139535,
"grad_norm": 0.31473204493522644,
"learning_rate": 5.360356781582307e-06,
"loss": 0.3984375,
"step": 742,
"token_acc": 0.8691550096490146
},
{
"epoch": 0.493687707641196,
"grad_norm": 0.3697916269302368,
"learning_rate": 5.349617699262264e-06,
"loss": 0.385986328125,
"step": 743,
"token_acc": 0.8730578960779674
},
{
"epoch": 0.4943521594684385,
"grad_norm": 0.3465130031108856,
"learning_rate": 5.3388769959445e-06,
"loss": 0.37548828125,
"step": 744,
"token_acc": 0.875855345178418
},
{
"epoch": 0.4950166112956811,
"grad_norm": 0.4212148189544678,
"learning_rate": 5.328134721428138e-06,
"loss": 0.402099609375,
"step": 745,
"token_acc": 0.8684092603877785
},
{
"epoch": 0.4956810631229236,
"grad_norm": 0.3774820566177368,
"learning_rate": 5.31739092551959e-06,
"loss": 0.38232421875,
"step": 746,
"token_acc": 0.8730858487930495
},
{
"epoch": 0.4963455149501661,
"grad_norm": 0.29748308658599854,
"learning_rate": 5.3066456580323215e-06,
"loss": 0.36962890625,
"step": 747,
"token_acc": 0.8774447893609149
},
{
"epoch": 0.49700996677740866,
"grad_norm": 0.3974754512310028,
"learning_rate": 5.295898968786617e-06,
"loss": 0.393310546875,
"step": 748,
"token_acc": 0.8708563913096967
},
{
"epoch": 0.49767441860465117,
"grad_norm": 0.31756752729415894,
"learning_rate": 5.285150907609359e-06,
"loss": 0.390380859375,
"step": 749,
"token_acc": 0.8708239090814609
},
{
"epoch": 0.4983388704318937,
"grad_norm": 0.28215330839157104,
"learning_rate": 5.274401524333783e-06,
"loss": 0.39111328125,
"step": 750,
"token_acc": 0.8708435648001276
},
{
"epoch": 0.49900332225913624,
"grad_norm": 0.4472302794456482,
"learning_rate": 5.263650868799261e-06,
"loss": 0.371826171875,
"step": 751,
"token_acc": 0.8772024388088716
},
{
"epoch": 0.49966777408637875,
"grad_norm": 0.301045298576355,
"learning_rate": 5.252898990851063e-06,
"loss": 0.4013671875,
"step": 752,
"token_acc": 0.8675475133030515
},
{
"epoch": 0.5003322259136213,
"grad_norm": 0.40407389402389526,
"learning_rate": 5.242145940340122e-06,
"loss": 0.3720703125,
"step": 753,
"token_acc": 0.8772199530221596
},
{
"epoch": 0.5009966777408638,
"grad_norm": 0.2937738299369812,
"learning_rate": 5.231391767122813e-06,
"loss": 0.383544921875,
"step": 754,
"token_acc": 0.8739060426992744
},
{
"epoch": 0.5016611295681063,
"grad_norm": 0.40931272506713867,
"learning_rate": 5.220636521060714e-06,
"loss": 0.38720703125,
"step": 755,
"token_acc": 0.8729889261062457
},
{
"epoch": 0.5023255813953489,
"grad_norm": 0.3303198218345642,
"learning_rate": 5.209880252020377e-06,
"loss": 0.39111328125,
"step": 756,
"token_acc": 0.8710872268175126
},
{
"epoch": 0.5029900332225914,
"grad_norm": 0.3134234547615051,
"learning_rate": 5.1991230098730985e-06,
"loss": 0.39501953125,
"step": 757,
"token_acc": 0.8702504620760405
},
{
"epoch": 0.5036544850498339,
"grad_norm": 0.40432360768318176,
"learning_rate": 5.188364844494684e-06,
"loss": 0.392822265625,
"step": 758,
"token_acc": 0.8710440520401239
},
{
"epoch": 0.5043189368770764,
"grad_norm": 0.35695284605026245,
"learning_rate": 5.177605805765222e-06,
"loss": 0.383056640625,
"step": 759,
"token_acc": 0.8730054886563161
},
{
"epoch": 0.5049833887043189,
"grad_norm": 0.329895943403244,
"learning_rate": 5.166845943568853e-06,
"loss": 0.39599609375,
"step": 760,
"token_acc": 0.8697786921125015
},
{
"epoch": 0.5056478405315614,
"grad_norm": 0.4074132740497589,
"learning_rate": 5.156085307793528e-06,
"loss": 0.37353515625,
"step": 761,
"token_acc": 0.8758101207381396
},
{
"epoch": 0.506312292358804,
"grad_norm": 0.41724255681037903,
"learning_rate": 5.145323948330789e-06,
"loss": 0.396240234375,
"step": 762,
"token_acc": 0.8695308233851688
},
{
"epoch": 0.5069767441860465,
"grad_norm": 0.288788378238678,
"learning_rate": 5.134561915075536e-06,
"loss": 0.388427734375,
"step": 763,
"token_acc": 0.8730416973867453
},
{
"epoch": 0.507641196013289,
"grad_norm": 0.6547151207923889,
"learning_rate": 5.1237992579257885e-06,
"loss": 0.377197265625,
"step": 764,
"token_acc": 0.8760067666780189
},
{
"epoch": 0.5083056478405316,
"grad_norm": 0.3207000195980072,
"learning_rate": 5.113036026782461e-06,
"loss": 0.3984375,
"step": 765,
"token_acc": 0.8699715739209961
},
{
"epoch": 0.5089700996677741,
"grad_norm": 0.34421125054359436,
"learning_rate": 5.1022722715491265e-06,
"loss": 0.388427734375,
"step": 766,
"token_acc": 0.8716655221740593
},
{
"epoch": 0.5096345514950166,
"grad_norm": 0.2932033836841583,
"learning_rate": 5.0915080421317945e-06,
"loss": 0.402587890625,
"step": 767,
"token_acc": 0.8672381908725759
},
{
"epoch": 0.5102990033222591,
"grad_norm": 0.3419566750526428,
"learning_rate": 5.080743388438663e-06,
"loss": 0.389892578125,
"step": 768,
"token_acc": 0.8718522533199952
},
{
"epoch": 0.5109634551495017,
"grad_norm": 0.30821216106414795,
"learning_rate": 5.069978360379908e-06,
"loss": 0.3775634765625,
"step": 769,
"token_acc": 0.874912377727101
},
{
"epoch": 0.5116279069767442,
"grad_norm": 0.28451472520828247,
"learning_rate": 5.059213007867434e-06,
"loss": 0.3916015625,
"step": 770,
"token_acc": 0.8712850754142452
},
{
"epoch": 0.5122923588039867,
"grad_norm": 0.3742717504501343,
"learning_rate": 5.048447380814652e-06,
"loss": 0.392578125,
"step": 771,
"token_acc": 0.8721404725679209
},
{
"epoch": 0.5129568106312292,
"grad_norm": 0.3298206925392151,
"learning_rate": 5.0376815291362455e-06,
"loss": 0.392822265625,
"step": 772,
"token_acc": 0.8700899085925635
},
{
"epoch": 0.5136212624584717,
"grad_norm": 0.33941784501075745,
"learning_rate": 5.026915502747941e-06,
"loss": 0.40576171875,
"step": 773,
"token_acc": 0.8678541103169828
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.703613817691803,
"learning_rate": 5.016149351566272e-06,
"loss": 0.392822265625,
"step": 774,
"token_acc": 0.8699414183432314
},
{
"epoch": 0.5149501661129569,
"grad_norm": 0.7452443242073059,
"learning_rate": 5.005383125508355e-06,
"loss": 0.38134765625,
"step": 775,
"token_acc": 0.8740943557264637
},
{
"epoch": 0.5156146179401994,
"grad_norm": 0.33786892890930176,
"learning_rate": 4.994616874491647e-06,
"loss": 0.39306640625,
"step": 776,
"token_acc": 0.8716610517267673
},
{
"epoch": 0.5162790697674419,
"grad_norm": 0.6922521591186523,
"learning_rate": 4.983850648433729e-06,
"loss": 0.381591796875,
"step": 777,
"token_acc": 0.8736869035344099
},
{
"epoch": 0.5169435215946844,
"grad_norm": 0.32242560386657715,
"learning_rate": 4.973084497252061e-06,
"loss": 0.384521484375,
"step": 778,
"token_acc": 0.8735208873344459
},
{
"epoch": 0.5176079734219269,
"grad_norm": 0.6920672059059143,
"learning_rate": 4.962318470863755e-06,
"loss": 0.38671875,
"step": 779,
"token_acc": 0.8734270022684597
},
{
"epoch": 0.5182724252491694,
"grad_norm": 0.3302854001522064,
"learning_rate": 4.951552619185349e-06,
"loss": 0.39990234375,
"step": 780,
"token_acc": 0.8687505950195167
},
{
"epoch": 0.518936877076412,
"grad_norm": 0.40820038318634033,
"learning_rate": 4.940786992132568e-06,
"loss": 0.386474609375,
"step": 781,
"token_acc": 0.8724768741220216
},
{
"epoch": 0.5196013289036545,
"grad_norm": 0.34102770686149597,
"learning_rate": 4.930021639620093e-06,
"loss": 0.3857421875,
"step": 782,
"token_acc": 0.8722702920950264
},
{
"epoch": 0.520265780730897,
"grad_norm": 0.314437597990036,
"learning_rate": 4.919256611561338e-06,
"loss": 0.399658203125,
"step": 783,
"token_acc": 0.8689313750078201
},
{
"epoch": 0.5209302325581395,
"grad_norm": 0.35471871495246887,
"learning_rate": 4.908491957868209e-06,
"loss": 0.391357421875,
"step": 784,
"token_acc": 0.8709702633224484
},
{
"epoch": 0.521594684385382,
"grad_norm": 0.2887704074382782,
"learning_rate": 4.897727728450875e-06,
"loss": 0.380126953125,
"step": 785,
"token_acc": 0.8749094911387646
},
{
"epoch": 0.5222591362126245,
"grad_norm": 0.40969762206077576,
"learning_rate": 4.886963973217541e-06,
"loss": 0.38525390625,
"step": 786,
"token_acc": 0.873564672637792
},
{
"epoch": 0.5229235880398672,
"grad_norm": 0.34048813581466675,
"learning_rate": 4.876200742074213e-06,
"loss": 0.394287109375,
"step": 787,
"token_acc": 0.8701413022142231
},
{
"epoch": 0.5235880398671097,
"grad_norm": 0.7244746088981628,
"learning_rate": 4.865438084924466e-06,
"loss": 0.373046875,
"step": 788,
"token_acc": 0.8768182018204717
},
{
"epoch": 0.5242524916943522,
"grad_norm": 0.36498671770095825,
"learning_rate": 4.854676051669212e-06,
"loss": 0.37548828125,
"step": 789,
"token_acc": 0.8755070479943677
},
{
"epoch": 0.5249169435215947,
"grad_norm": 2.3006198406219482,
"learning_rate": 4.843914692206473e-06,
"loss": 0.38720703125,
"step": 790,
"token_acc": 0.8721521813204244
},
{
"epoch": 0.5255813953488372,
"grad_norm": 0.35911592841148376,
"learning_rate": 4.83315405643115e-06,
"loss": 0.3828125,
"step": 791,
"token_acc": 0.8737547741068734
},
{
"epoch": 0.5262458471760797,
"grad_norm": 0.3141895830631256,
"learning_rate": 4.8223941942347786e-06,
"loss": 0.39453125,
"step": 792,
"token_acc": 0.8708584865452091
},
{
"epoch": 0.5269102990033223,
"grad_norm": 0.30941760540008545,
"learning_rate": 4.8116351555053165e-06,
"loss": 0.3994140625,
"step": 793,
"token_acc": 0.8689902588248481
},
{
"epoch": 0.5275747508305648,
"grad_norm": 0.32489824295043945,
"learning_rate": 4.800876990126905e-06,
"loss": 0.38525390625,
"step": 794,
"token_acc": 0.8727224556473866
},
{
"epoch": 0.5282392026578073,
"grad_norm": 0.6129250526428223,
"learning_rate": 4.790119747979624e-06,
"loss": 0.403564453125,
"step": 795,
"token_acc": 0.8680800272497073
},
{
"epoch": 0.5289036544850498,
"grad_norm": 0.32914024591445923,
"learning_rate": 4.779363478939287e-06,
"loss": 0.4052734375,
"step": 796,
"token_acc": 0.8674836187037466
},
{
"epoch": 0.5295681063122923,
"grad_norm": 0.3632645010948181,
"learning_rate": 4.76860823287719e-06,
"loss": 0.388427734375,
"step": 797,
"token_acc": 0.8727916945828885
},
{
"epoch": 0.5302325581395348,
"grad_norm": 0.31391268968582153,
"learning_rate": 4.7578540596598794e-06,
"loss": 0.38427734375,
"step": 798,
"token_acc": 0.8730712076516778
},
{
"epoch": 0.5308970099667774,
"grad_norm": 0.3526628315448761,
"learning_rate": 4.747101009148939e-06,
"loss": 0.412353515625,
"step": 799,
"token_acc": 0.8648799509115022
},
{
"epoch": 0.53156146179402,
"grad_norm": 0.4855210483074188,
"learning_rate": 4.73634913120074e-06,
"loss": 0.383056640625,
"step": 800,
"token_acc": 0.8736788596248429
},
{
"epoch": 0.5322259136212625,
"grad_norm": 0.38573774695396423,
"learning_rate": 4.725598475666218e-06,
"loss": 0.385009765625,
"step": 801,
"token_acc": 0.8727102486085828
},
{
"epoch": 0.532890365448505,
"grad_norm": 0.3240213692188263,
"learning_rate": 4.714849092390642e-06,
"loss": 0.38037109375,
"step": 802,
"token_acc": 0.8751532575842015
},
{
"epoch": 0.5335548172757475,
"grad_norm": 0.5349907279014587,
"learning_rate": 4.7041010312133824e-06,
"loss": 0.385009765625,
"step": 803,
"token_acc": 0.8723948119994225
},
{
"epoch": 0.53421926910299,
"grad_norm": 0.3030000329017639,
"learning_rate": 4.69335434196768e-06,
"loss": 0.394775390625,
"step": 804,
"token_acc": 0.869937585960854
},
{
"epoch": 0.5348837209302325,
"grad_norm": 0.3283815383911133,
"learning_rate": 4.682609074480411e-06,
"loss": 0.372802734375,
"step": 805,
"token_acc": 0.8762922132026261
},
{
"epoch": 0.5355481727574751,
"grad_norm": 0.31167110800743103,
"learning_rate": 4.671865278571864e-06,
"loss": 0.39013671875,
"step": 806,
"token_acc": 0.8721426075184356
},
{
"epoch": 0.5362126245847176,
"grad_norm": 0.6495005488395691,
"learning_rate": 4.661123004055504e-06,
"loss": 0.386962890625,
"step": 807,
"token_acc": 0.8730969452902465
},
{
"epoch": 0.5368770764119601,
"grad_norm": 0.40925028920173645,
"learning_rate": 4.650382300737737e-06,
"loss": 0.384033203125,
"step": 808,
"token_acc": 0.8733258553302291
},
{
"epoch": 0.5375415282392026,
"grad_norm": 0.3493454158306122,
"learning_rate": 4.639643218417693e-06,
"loss": 0.398681640625,
"step": 809,
"token_acc": 0.869053211777292
},
{
"epoch": 0.5382059800664452,
"grad_norm": 0.29291215538978577,
"learning_rate": 4.628905806886981e-06,
"loss": 0.400146484375,
"step": 810,
"token_acc": 0.8680091562878994
},
{
"epoch": 0.5388704318936877,
"grad_norm": 0.7919507026672363,
"learning_rate": 4.6181701159294605e-06,
"loss": 0.38134765625,
"step": 811,
"token_acc": 0.8736790924725566
},
{
"epoch": 0.5395348837209303,
"grad_norm": 0.3286319673061371,
"learning_rate": 4.607436195321018e-06,
"loss": 0.388671875,
"step": 812,
"token_acc": 0.8716264988392528
},
{
"epoch": 0.5401993355481728,
"grad_norm": 0.2846357524394989,
"learning_rate": 4.596704094829336e-06,
"loss": 0.398681640625,
"step": 813,
"token_acc": 0.8692191698998446
},
{
"epoch": 0.5408637873754153,
"grad_norm": 0.36646029353141785,
"learning_rate": 4.585973864213647e-06,
"loss": 0.387451171875,
"step": 814,
"token_acc": 0.8719102171025211
},
{
"epoch": 0.5415282392026578,
"grad_norm": 0.38615813851356506,
"learning_rate": 4.57524555322452e-06,
"loss": 0.394287109375,
"step": 815,
"token_acc": 0.8702630725443119
},
{
"epoch": 0.5421926910299003,
"grad_norm": 0.3879084587097168,
"learning_rate": 4.564519211603627e-06,
"loss": 0.392333984375,
"step": 816,
"token_acc": 0.8716165976278216
},
{
"epoch": 0.5428571428571428,
"grad_norm": 0.3214435279369354,
"learning_rate": 4.553794889083503e-06,
"loss": 0.389404296875,
"step": 817,
"token_acc": 0.8725007459182724
},
{
"epoch": 0.5435215946843854,
"grad_norm": 0.30783379077911377,
"learning_rate": 4.543072635387324e-06,
"loss": 0.379638671875,
"step": 818,
"token_acc": 0.8741476992276104
},
{
"epoch": 0.5441860465116279,
"grad_norm": 0.3124229311943054,
"learning_rate": 4.532352500228674e-06,
"loss": 0.381103515625,
"step": 819,
"token_acc": 0.8747710632416597
},
{
"epoch": 0.5448504983388704,
"grad_norm": 0.3190343379974365,
"learning_rate": 4.521634533311317e-06,
"loss": 0.37451171875,
"step": 820,
"token_acc": 0.876820426997336
},
{
"epoch": 0.545514950166113,
"grad_norm": 0.38928207755088806,
"learning_rate": 4.510918784328956e-06,
"loss": 0.39404296875,
"step": 821,
"token_acc": 0.8705273242266256
},
{
"epoch": 0.5461794019933555,
"grad_norm": 0.33837801218032837,
"learning_rate": 4.500205302965019e-06,
"loss": 0.395751953125,
"step": 822,
"token_acc": 0.8696606287846319
},
{
"epoch": 0.546843853820598,
"grad_norm": 0.35434773564338684,
"learning_rate": 4.489494138892419e-06,
"loss": 0.382080078125,
"step": 823,
"token_acc": 0.8735803910924175
},
{
"epoch": 0.5475083056478405,
"grad_norm": 0.46649661660194397,
"learning_rate": 4.4787853417733185e-06,
"loss": 0.377197265625,
"step": 824,
"token_acc": 0.8755045940132491
},
{
"epoch": 0.5481727574750831,
"grad_norm": 0.31171658635139465,
"learning_rate": 4.468078961258912e-06,
"loss": 0.375,
"step": 825,
"token_acc": 0.8769211490242742
},
{
"epoch": 0.5488372093023256,
"grad_norm": 0.38786810636520386,
"learning_rate": 4.45737504698919e-06,
"loss": 0.376953125,
"step": 826,
"token_acc": 0.8761173416326035
},
{
"epoch": 0.5495016611295681,
"grad_norm": 0.5140872001647949,
"learning_rate": 4.446673648592701e-06,
"loss": 0.392333984375,
"step": 827,
"token_acc": 0.8710215785965999
},
{
"epoch": 0.5501661129568106,
"grad_norm": 0.33795762062072754,
"learning_rate": 4.435974815686338e-06,
"loss": 0.375732421875,
"step": 828,
"token_acc": 0.8752187064319666
},
{
"epoch": 0.5508305647840531,
"grad_norm": 0.2884729504585266,
"learning_rate": 4.425278597875091e-06,
"loss": 0.38525390625,
"step": 829,
"token_acc": 0.8723986058897664
},
{
"epoch": 0.5514950166112956,
"grad_norm": 0.3340379297733307,
"learning_rate": 4.414585044751834e-06,
"loss": 0.37548828125,
"step": 830,
"token_acc": 0.8753380818652078
},
{
"epoch": 0.5521594684385382,
"grad_norm": 0.3369429409503937,
"learning_rate": 4.4038942058970735e-06,
"loss": 0.3896484375,
"step": 831,
"token_acc": 0.8713445469629845
},
{
"epoch": 0.5528239202657808,
"grad_norm": 0.3095065653324127,
"learning_rate": 4.3932061308787456e-06,
"loss": 0.380615234375,
"step": 832,
"token_acc": 0.8738095625291248
},
{
"epoch": 0.5534883720930233,
"grad_norm": 0.3121756911277771,
"learning_rate": 4.382520869251964e-06,
"loss": 0.376708984375,
"step": 833,
"token_acc": 0.8753992388274495
},
{
"epoch": 0.5541528239202658,
"grad_norm": 0.29716700315475464,
"learning_rate": 4.371838470558795e-06,
"loss": 0.396240234375,
"step": 834,
"token_acc": 0.8697747510051422
},
{
"epoch": 0.5548172757475083,
"grad_norm": 0.3395397961139679,
"learning_rate": 4.361158984328039e-06,
"loss": 0.3994140625,
"step": 835,
"token_acc": 0.8691536186667476
},
{
"epoch": 0.5554817275747508,
"grad_norm": 0.3297097086906433,
"learning_rate": 4.35048246007499e-06,
"loss": 0.3955078125,
"step": 836,
"token_acc": 0.8696777944689785
},
{
"epoch": 0.5561461794019934,
"grad_norm": 0.28758999705314636,
"learning_rate": 4.339808947301205e-06,
"loss": 0.38916015625,
"step": 837,
"token_acc": 0.872871883463279
},
{
"epoch": 0.5568106312292359,
"grad_norm": 0.5280511975288391,
"learning_rate": 4.329138495494282e-06,
"loss": 0.374267578125,
"step": 838,
"token_acc": 0.8759839626384289
},
{
"epoch": 0.5574750830564784,
"grad_norm": 0.28693413734436035,
"learning_rate": 4.318471154127626e-06,
"loss": 0.376708984375,
"step": 839,
"token_acc": 0.8763690217252232
},
{
"epoch": 0.5581395348837209,
"grad_norm": 0.2820129096508026,
"learning_rate": 4.307806972660223e-06,
"loss": 0.38720703125,
"step": 840,
"token_acc": 0.8717736548038382
},
{
"epoch": 0.5588039867109634,
"grad_norm": 0.3070831596851349,
"learning_rate": 4.297146000536403e-06,
"loss": 0.37646484375,
"step": 841,
"token_acc": 0.8755009773084885
},
{
"epoch": 0.5594684385382059,
"grad_norm": 0.3543018698692322,
"learning_rate": 4.2864882871856196e-06,
"loss": 0.383544921875,
"step": 842,
"token_acc": 0.8741183540146434
},
{
"epoch": 0.5601328903654486,
"grad_norm": 0.2950226068496704,
"learning_rate": 4.2758338820222165e-06,
"loss": 0.399658203125,
"step": 843,
"token_acc": 0.869290045928354
},
{
"epoch": 0.5607973421926911,
"grad_norm": 0.2855764925479889,
"learning_rate": 4.2651828344451984e-06,
"loss": 0.410400390625,
"step": 844,
"token_acc": 0.8654072715837774
},
{
"epoch": 0.5614617940199336,
"grad_norm": 0.26335713267326355,
"learning_rate": 4.254535193838002e-06,
"loss": 0.374267578125,
"step": 845,
"token_acc": 0.8762017483986584
},
{
"epoch": 0.5621262458471761,
"grad_norm": 0.3156571388244629,
"learning_rate": 4.243891009568271e-06,
"loss": 0.380859375,
"step": 846,
"token_acc": 0.8740253195890871
},
{
"epoch": 0.5627906976744186,
"grad_norm": 0.49814924597740173,
"learning_rate": 4.233250330987619e-06,
"loss": 0.3818359375,
"step": 847,
"token_acc": 0.8739868074261532
},
{
"epoch": 0.5634551495016611,
"grad_norm": 0.2921030819416046,
"learning_rate": 4.222613207431408e-06,
"loss": 0.400390625,
"step": 848,
"token_acc": 0.8679156778095916
},
{
"epoch": 0.5641196013289037,
"grad_norm": 0.30464643239974976,
"learning_rate": 4.211979688218521e-06,
"loss": 0.3837890625,
"step": 849,
"token_acc": 0.8738038445197369
},
{
"epoch": 0.5647840531561462,
"grad_norm": 0.3340986371040344,
"learning_rate": 4.20134982265112e-06,
"loss": 0.3896484375,
"step": 850,
"token_acc": 0.8728207481650091
},
{
"epoch": 0.5654485049833887,
"grad_norm": 0.3704366385936737,
"learning_rate": 4.190723660014434e-06,
"loss": 0.404296875,
"step": 851,
"token_acc": 0.8679423099106404
},
{
"epoch": 0.5661129568106312,
"grad_norm": 0.3745676875114441,
"learning_rate": 4.1801012495765234e-06,
"loss": 0.3984375,
"step": 852,
"token_acc": 0.8692431459651846
},
{
"epoch": 0.5667774086378737,
"grad_norm": 0.3800630569458008,
"learning_rate": 4.169482640588052e-06,
"loss": 0.392578125,
"step": 853,
"token_acc": 0.8708535396924071
},
{
"epoch": 0.5674418604651162,
"grad_norm": 0.5096917152404785,
"learning_rate": 4.158867882282054e-06,
"loss": 0.384765625,
"step": 854,
"token_acc": 0.8731915639729446
},
{
"epoch": 0.5681063122923588,
"grad_norm": 0.32878899574279785,
"learning_rate": 4.1482570238737105e-06,
"loss": 0.39306640625,
"step": 855,
"token_acc": 0.8706792207410954
},
{
"epoch": 0.5687707641196014,
"grad_norm": 0.4290892481803894,
"learning_rate": 4.137650114560127e-06,
"loss": 0.395263671875,
"step": 856,
"token_acc": 0.869753956171144
},
{
"epoch": 0.5694352159468439,
"grad_norm": 0.31203436851501465,
"learning_rate": 4.127047203520092e-06,
"loss": 0.38720703125,
"step": 857,
"token_acc": 0.8721878598314757
},
{
"epoch": 0.5700996677740864,
"grad_norm": 0.45187118649482727,
"learning_rate": 4.116448339913858e-06,
"loss": 0.39208984375,
"step": 858,
"token_acc": 0.8709106108443686
},
{
"epoch": 0.5707641196013289,
"grad_norm": 0.393007755279541,
"learning_rate": 4.105853572882914e-06,
"loss": 0.369873046875,
"step": 859,
"token_acc": 0.8770088782693295
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.3900320827960968,
"learning_rate": 4.095262951549753e-06,
"loss": 0.387939453125,
"step": 860,
"token_acc": 0.8731667902036115
},
{
"epoch": 0.5720930232558139,
"grad_norm": 0.3454941213130951,
"learning_rate": 4.0846765250176466e-06,
"loss": 0.39599609375,
"step": 861,
"token_acc": 0.869809046097487
},
{
"epoch": 0.5727574750830565,
"grad_norm": 0.3339519500732422,
"learning_rate": 4.07409434237042e-06,
"loss": 0.3759765625,
"step": 862,
"token_acc": 0.8754002975763912
},
{
"epoch": 0.573421926910299,
"grad_norm": 0.27745386958122253,
"learning_rate": 4.0635164526722165e-06,
"loss": 0.36279296875,
"step": 863,
"token_acc": 0.8794872204270557
},
{
"epoch": 0.5740863787375415,
"grad_norm": 0.6631693840026855,
"learning_rate": 4.052942904967281e-06,
"loss": 0.375732421875,
"step": 864,
"token_acc": 0.8762938823779531
},
{
"epoch": 0.574750830564784,
"grad_norm": 0.4128742218017578,
"learning_rate": 4.04237374827972e-06,
"loss": 0.3876953125,
"step": 865,
"token_acc": 0.8722399539484105
},
{
"epoch": 0.5754152823920266,
"grad_norm": 0.43200257420539856,
"learning_rate": 4.031809031613292e-06,
"loss": 0.389892578125,
"step": 866,
"token_acc": 0.8722731615792924
},
{
"epoch": 0.5760797342192691,
"grad_norm": 0.30478841066360474,
"learning_rate": 4.021248803951155e-06,
"loss": 0.38525390625,
"step": 867,
"token_acc": 0.8728877517108614
},
{
"epoch": 0.5767441860465117,
"grad_norm": 0.38282132148742676,
"learning_rate": 4.0106931142556665e-06,
"loss": 0.37890625,
"step": 868,
"token_acc": 0.8746901966735361
},
{
"epoch": 0.5774086378737542,
"grad_norm": 0.33578863739967346,
"learning_rate": 4.000142011468139e-06,
"loss": 0.375732421875,
"step": 869,
"token_acc": 0.8754913820385909
},
{
"epoch": 0.5780730897009967,
"grad_norm": 0.3190770745277405,
"learning_rate": 3.989595544508612e-06,
"loss": 0.397216796875,
"step": 870,
"token_acc": 0.8690329241562147
},
{
"epoch": 0.5787375415282392,
"grad_norm": 0.37079060077667236,
"learning_rate": 3.979053762275641e-06,
"loss": 0.375,
"step": 871,
"token_acc": 0.8757560324130653
},
{
"epoch": 0.5794019933554817,
"grad_norm": 0.32281115651130676,
"learning_rate": 3.968516713646056e-06,
"loss": 0.381103515625,
"step": 872,
"token_acc": 0.875248737676547
},
{
"epoch": 0.5800664451827242,
"grad_norm": 0.4825950264930725,
"learning_rate": 3.957984447474739e-06,
"loss": 0.394287109375,
"step": 873,
"token_acc": 0.8701817803833048
},
{
"epoch": 0.5807308970099668,
"grad_norm": 0.3028841018676758,
"learning_rate": 3.9474570125944e-06,
"loss": 0.38134765625,
"step": 874,
"token_acc": 0.874109135587848
},
{
"epoch": 0.5813953488372093,
"grad_norm": 0.31085649132728577,
"learning_rate": 3.936934457815348e-06,
"loss": 0.382568359375,
"step": 875,
"token_acc": 0.8749561108631291
},
{
"epoch": 0.5820598006644518,
"grad_norm": 0.2889193892478943,
"learning_rate": 3.926416831925264e-06,
"loss": 0.397216796875,
"step": 876,
"token_acc": 0.8690166031518529
},
{
"epoch": 0.5827242524916944,
"grad_norm": 0.28167930245399475,
"learning_rate": 3.91590418368898e-06,
"loss": 0.3837890625,
"step": 877,
"token_acc": 0.8732960317332344
},
{
"epoch": 0.5833887043189369,
"grad_norm": 0.290958046913147,
"learning_rate": 3.905396561848245e-06,
"loss": 0.3896484375,
"step": 878,
"token_acc": 0.8717326989523884
},
{
"epoch": 0.5840531561461794,
"grad_norm": 0.29875558614730835,
"learning_rate": 3.8948940151215075e-06,
"loss": 0.384033203125,
"step": 879,
"token_acc": 0.8729849038859685
},
{
"epoch": 0.584717607973422,
"grad_norm": 0.4902196526527405,
"learning_rate": 3.884396592203682e-06,
"loss": 0.38916015625,
"step": 880,
"token_acc": 0.8718779556036169
},
{
"epoch": 0.5853820598006645,
"grad_norm": 0.3291551470756531,
"learning_rate": 3.873904341765925e-06,
"loss": 0.369140625,
"step": 881,
"token_acc": 0.8777643392560298
},
{
"epoch": 0.586046511627907,
"grad_norm": 0.29090529680252075,
"learning_rate": 3.863417312455418e-06,
"loss": 0.388427734375,
"step": 882,
"token_acc": 0.8710877020118848
},
{
"epoch": 0.5867109634551495,
"grad_norm": 0.33608728647232056,
"learning_rate": 3.852935552895126e-06,
"loss": 0.381591796875,
"step": 883,
"token_acc": 0.8743233534278562
},
{
"epoch": 0.587375415282392,
"grad_norm": 0.36965152621269226,
"learning_rate": 3.842459111683586e-06,
"loss": 0.3974609375,
"step": 884,
"token_acc": 0.8693265177961755
},
{
"epoch": 0.5880398671096345,
"grad_norm": 0.35143500566482544,
"learning_rate": 3.83198803739468e-06,
"loss": 0.383544921875,
"step": 885,
"token_acc": 0.8738437847848171
},
{
"epoch": 0.588704318936877,
"grad_norm": 0.32411524653434753,
"learning_rate": 3.821522378577395e-06,
"loss": 0.385498046875,
"step": 886,
"token_acc": 0.8740600978894336
},
{
"epoch": 0.5893687707641196,
"grad_norm": 0.3668898642063141,
"learning_rate": 3.811062183755618e-06,
"loss": 0.39404296875,
"step": 887,
"token_acc": 0.8699773543776829
},
{
"epoch": 0.5900332225913621,
"grad_norm": 0.31068772077560425,
"learning_rate": 3.8006075014279063e-06,
"loss": 0.383056640625,
"step": 888,
"token_acc": 0.8733143939802637
},
{
"epoch": 0.5906976744186047,
"grad_norm": 0.37606289982795715,
"learning_rate": 3.7901583800672446e-06,
"loss": 0.390380859375,
"step": 889,
"token_acc": 0.8716804924834238
},
{
"epoch": 0.5913621262458472,
"grad_norm": 0.39699459075927734,
"learning_rate": 3.779714868120847e-06,
"loss": 0.402587890625,
"step": 890,
"token_acc": 0.8686405866919007
},
{
"epoch": 0.5920265780730897,
"grad_norm": 0.3163547217845917,
"learning_rate": 3.769277014009915e-06,
"loss": 0.382080078125,
"step": 891,
"token_acc": 0.8739300155987855
},
{
"epoch": 0.5926910299003322,
"grad_norm": 0.32541710138320923,
"learning_rate": 3.7588448661294167e-06,
"loss": 0.3974609375,
"step": 892,
"token_acc": 0.8686309628919553
},
{
"epoch": 0.5933554817275748,
"grad_norm": 0.31581565737724304,
"learning_rate": 3.748418472847864e-06,
"loss": 0.38134765625,
"step": 893,
"token_acc": 0.8737587071794927
},
{
"epoch": 0.5940199335548173,
"grad_norm": 0.3316781222820282,
"learning_rate": 3.737997882507088e-06,
"loss": 0.389404296875,
"step": 894,
"token_acc": 0.872427138713373
},
{
"epoch": 0.5946843853820598,
"grad_norm": 0.3603745102882385,
"learning_rate": 3.7275831434220156e-06,
"loss": 0.406494140625,
"step": 895,
"token_acc": 0.8663458650551
},
{
"epoch": 0.5953488372093023,
"grad_norm": 0.3324991464614868,
"learning_rate": 3.717174303880441e-06,
"loss": 0.367431640625,
"step": 896,
"token_acc": 0.877969008307758
},
{
"epoch": 0.5960132890365448,
"grad_norm": 0.35945600271224976,
"learning_rate": 3.70677141214281e-06,
"loss": 0.383056640625,
"step": 897,
"token_acc": 0.8734785014118006
},
{
"epoch": 0.5966777408637873,
"grad_norm": 0.36439332365989685,
"learning_rate": 3.6963745164419883e-06,
"loss": 0.37548828125,
"step": 898,
"token_acc": 0.8757024997465536
},
{
"epoch": 0.59734219269103,
"grad_norm": 0.3292514383792877,
"learning_rate": 3.6859836649830406e-06,
"loss": 0.391845703125,
"step": 899,
"token_acc": 0.870448235459477
},
{
"epoch": 0.5980066445182725,
"grad_norm": 0.28453198075294495,
"learning_rate": 3.6755989059430104e-06,
"loss": 0.382080078125,
"step": 900,
"token_acc": 0.8737533840849666
},
{
"epoch": 0.598671096345515,
"grad_norm": 0.3494807481765747,
"learning_rate": 3.665220287470692e-06,
"loss": 0.3896484375,
"step": 901,
"token_acc": 0.8713102318576093
},
{
"epoch": 0.5993355481727575,
"grad_norm": 0.3220234215259552,
"learning_rate": 3.6548478576864075e-06,
"loss": 0.381591796875,
"step": 902,
"token_acc": 0.8732797832188135
},
{
"epoch": 0.6,
"grad_norm": 0.29791343212127686,
"learning_rate": 3.6444816646817887e-06,
"loss": 0.385498046875,
"step": 903,
"token_acc": 0.8730208498397619
},
{
"epoch": 0.6006644518272425,
"grad_norm": 0.3066873252391815,
"learning_rate": 3.634121756519547e-06,
"loss": 0.3828125,
"step": 904,
"token_acc": 0.873344883898723
},
{
"epoch": 0.6013289036544851,
"grad_norm": 0.31713443994522095,
"learning_rate": 3.62376818123326e-06,
"loss": 0.3935546875,
"step": 905,
"token_acc": 0.8705390785508123
},
{
"epoch": 0.6019933554817276,
"grad_norm": 0.4110839366912842,
"learning_rate": 3.6134209868271346e-06,
"loss": 0.390869140625,
"step": 906,
"token_acc": 0.8711533544072197
},
{
"epoch": 0.6026578073089701,
"grad_norm": 0.2898472249507904,
"learning_rate": 3.6030802212758e-06,
"loss": 0.39013671875,
"step": 907,
"token_acc": 0.8717561660100384
},
{
"epoch": 0.6033222591362126,
"grad_norm": 0.3309660851955414,
"learning_rate": 3.5927459325240767e-06,
"loss": 0.385986328125,
"step": 908,
"token_acc": 0.8731243614404345
},
{
"epoch": 0.6039867109634551,
"grad_norm": 0.401226669549942,
"learning_rate": 3.582418168486749e-06,
"loss": 0.392333984375,
"step": 909,
"token_acc": 0.8703464293693354
},
{
"epoch": 0.6046511627906976,
"grad_norm": 0.29853856563568115,
"learning_rate": 3.5720969770483584e-06,
"loss": 0.383544921875,
"step": 910,
"token_acc": 0.8727676733515584
},
{
"epoch": 0.6053156146179401,
"grad_norm": 0.2967441976070404,
"learning_rate": 3.561782406062971e-06,
"loss": 0.39794921875,
"step": 911,
"token_acc": 0.8703420705845875
},
{
"epoch": 0.6059800664451828,
"grad_norm": 0.34501656889915466,
"learning_rate": 3.551474503353951e-06,
"loss": 0.384521484375,
"step": 912,
"token_acc": 0.8727933287958013
},
{
"epoch": 0.6066445182724253,
"grad_norm": 0.35793909430503845,
"learning_rate": 3.5411733167137526e-06,
"loss": 0.38427734375,
"step": 913,
"token_acc": 0.8733416234341119
},
{
"epoch": 0.6073089700996678,
"grad_norm": 0.29498714208602905,
"learning_rate": 3.5308788939036875e-06,
"loss": 0.376953125,
"step": 914,
"token_acc": 0.8749369788580423
},
{
"epoch": 0.6079734219269103,
"grad_norm": 0.27559006214141846,
"learning_rate": 3.520591282653706e-06,
"loss": 0.392333984375,
"step": 915,
"token_acc": 0.8701707487510931
},
{
"epoch": 0.6086378737541528,
"grad_norm": 0.2842247784137726,
"learning_rate": 3.5103105306621785e-06,
"loss": 0.38037109375,
"step": 916,
"token_acc": 0.8741277872854895
},
{
"epoch": 0.6093023255813953,
"grad_norm": 0.2952902913093567,
"learning_rate": 3.500036685595673e-06,
"loss": 0.3896484375,
"step": 917,
"token_acc": 0.8721277787651589
},
{
"epoch": 0.6099667774086379,
"grad_norm": 0.3610007166862488,
"learning_rate": 3.4897697950887333e-06,
"loss": 0.368408203125,
"step": 918,
"token_acc": 0.8779961638296866
},
{
"epoch": 0.6106312292358804,
"grad_norm": 0.3210753798484802,
"learning_rate": 3.4795099067436564e-06,
"loss": 0.3857421875,
"step": 919,
"token_acc": 0.8722618254310466
},
{
"epoch": 0.6112956810631229,
"grad_norm": 0.272749662399292,
"learning_rate": 3.4692570681302755e-06,
"loss": 0.394287109375,
"step": 920,
"token_acc": 0.8719380684101328
},
{
"epoch": 0.6119601328903654,
"grad_norm": 0.37857234477996826,
"learning_rate": 3.4590113267857417e-06,
"loss": 0.382080078125,
"step": 921,
"token_acc": 0.8736996408948615
},
{
"epoch": 0.612624584717608,
"grad_norm": 0.28992587327957153,
"learning_rate": 3.4487727302142903e-06,
"loss": 0.384033203125,
"step": 922,
"token_acc": 0.8736269353088785
},
{
"epoch": 0.6132890365448505,
"grad_norm": 0.28929999470710754,
"learning_rate": 3.438541325887037e-06,
"loss": 0.391845703125,
"step": 923,
"token_acc": 0.8703415930483477
},
{
"epoch": 0.6139534883720931,
"grad_norm": 0.2831418812274933,
"learning_rate": 3.428317161241753e-06,
"loss": 0.38525390625,
"step": 924,
"token_acc": 0.8722696312534252
},
{
"epoch": 0.6146179401993356,
"grad_norm": 0.3165985643863678,
"learning_rate": 3.4181002836826325e-06,
"loss": 0.408203125,
"step": 925,
"token_acc": 0.8664361546164188
},
{
"epoch": 0.6152823920265781,
"grad_norm": 0.32187098264694214,
"learning_rate": 3.4078907405800955e-06,
"loss": 0.401123046875,
"step": 926,
"token_acc": 0.8694590937400585
},
{
"epoch": 0.6159468438538206,
"grad_norm": 0.3815533220767975,
"learning_rate": 3.397688579270549e-06,
"loss": 0.39013671875,
"step": 927,
"token_acc": 0.8715421241840831
},
{
"epoch": 0.6166112956810631,
"grad_norm": 0.31231164932250977,
"learning_rate": 3.3874938470561714e-06,
"loss": 0.35791015625,
"step": 928,
"token_acc": 0.8811058330821064
},
{
"epoch": 0.6172757475083056,
"grad_norm": 0.46553581953048706,
"learning_rate": 3.3773065912047043e-06,
"loss": 0.392333984375,
"step": 929,
"token_acc": 0.8707905181936746
},
{
"epoch": 0.6179401993355482,
"grad_norm": 0.39907732605934143,
"learning_rate": 3.3671268589492213e-06,
"loss": 0.37744140625,
"step": 930,
"token_acc": 0.8747654605705074
},
{
"epoch": 0.6186046511627907,
"grad_norm": 0.29751378297805786,
"learning_rate": 3.356954697487912e-06,
"loss": 0.3828125,
"step": 931,
"token_acc": 0.8736641708956853
},
{
"epoch": 0.6192691029900332,
"grad_norm": 0.3434341251850128,
"learning_rate": 3.346790153983865e-06,
"loss": 0.3671875,
"step": 932,
"token_acc": 0.8792810737253353
},
{
"epoch": 0.6199335548172757,
"grad_norm": 0.3236950635910034,
"learning_rate": 3.336633275564848e-06,
"loss": 0.39111328125,
"step": 933,
"token_acc": 0.8712758575766607
},
{
"epoch": 0.6205980066445183,
"grad_norm": 0.3232583701610565,
"learning_rate": 3.3264841093230915e-06,
"loss": 0.392822265625,
"step": 934,
"token_acc": 0.8717911880082384
},
{
"epoch": 0.6212624584717608,
"grad_norm": 0.6158249974250793,
"learning_rate": 3.316342702315066e-06,
"loss": 0.38818359375,
"step": 935,
"token_acc": 0.8723577765812874
},
{
"epoch": 0.6219269102990034,
"grad_norm": 0.3831617832183838,
"learning_rate": 3.3062091015612674e-06,
"loss": 0.37060546875,
"step": 936,
"token_acc": 0.8776652001241744
},
{
"epoch": 0.6225913621262459,
"grad_norm": 0.39332976937294006,
"learning_rate": 3.296083354045999e-06,
"loss": 0.400634765625,
"step": 937,
"token_acc": 0.8669751998351086
},
{
"epoch": 0.6232558139534884,
"grad_norm": 0.6005001068115234,
"learning_rate": 3.285965506717151e-06,
"loss": 0.392333984375,
"step": 938,
"token_acc": 0.8719144616131818
},
{
"epoch": 0.6239202657807309,
"grad_norm": 0.3289591670036316,
"learning_rate": 3.2758556064859855e-06,
"loss": 0.369873046875,
"step": 939,
"token_acc": 0.8769991341383115
},
{
"epoch": 0.6245847176079734,
"grad_norm": 0.3084999620914459,
"learning_rate": 3.265753700226919e-06,
"loss": 0.379150390625,
"step": 940,
"token_acc": 0.8747854833271373
},
{
"epoch": 0.6252491694352159,
"grad_norm": 0.4383425712585449,
"learning_rate": 3.2556598347773003e-06,
"loss": 0.38720703125,
"step": 941,
"token_acc": 0.8721149930232402
},
{
"epoch": 0.6259136212624584,
"grad_norm": 0.4397106170654297,
"learning_rate": 3.245574056937201e-06,
"loss": 0.395263671875,
"step": 942,
"token_acc": 0.8700283046301255
},
{
"epoch": 0.626578073089701,
"grad_norm": 0.38269972801208496,
"learning_rate": 3.2354964134691946e-06,
"loss": 0.367919921875,
"step": 943,
"token_acc": 0.8779107889924574
},
{
"epoch": 0.6272425249169435,
"grad_norm": 0.39794328808784485,
"learning_rate": 3.225426951098139e-06,
"loss": 0.38671875,
"step": 944,
"token_acc": 0.872913267976196
},
{
"epoch": 0.627906976744186,
"grad_norm": 0.3000463843345642,
"learning_rate": 3.215365716510955e-06,
"loss": 0.38037109375,
"step": 945,
"token_acc": 0.8743941210773873
},
{
"epoch": 0.6285714285714286,
"grad_norm": 0.4366755187511444,
"learning_rate": 3.2053127563564244e-06,
"loss": 0.376953125,
"step": 946,
"token_acc": 0.8753270322032084
},
{
"epoch": 0.6292358803986711,
"grad_norm": 0.3466312289237976,
"learning_rate": 3.195268117244962e-06,
"loss": 0.375244140625,
"step": 947,
"token_acc": 0.8755791710004109
},
{
"epoch": 0.6299003322259136,
"grad_norm": 0.3431652784347534,
"learning_rate": 3.1852318457483966e-06,
"loss": 0.38818359375,
"step": 948,
"token_acc": 0.8714014183950517
},
{
"epoch": 0.6305647840531562,
"grad_norm": 0.34940963983535767,
"learning_rate": 3.1752039883997667e-06,
"loss": 0.37841796875,
"step": 949,
"token_acc": 0.8749744356988104
},
{
"epoch": 0.6312292358803987,
"grad_norm": 0.34093204140663147,
"learning_rate": 3.1651845916930977e-06,
"loss": 0.378662109375,
"step": 950,
"token_acc": 0.875092155789645
},
{
"epoch": 0.6318936877076412,
"grad_norm": 0.303280234336853,
"learning_rate": 3.155173702083186e-06,
"loss": 0.389892578125,
"step": 951,
"token_acc": 0.8709275635565061
},
{
"epoch": 0.6325581395348837,
"grad_norm": 0.38247182965278625,
"learning_rate": 3.1451713659853845e-06,
"loss": 0.384033203125,
"step": 952,
"token_acc": 0.8733762374556384
},
{
"epoch": 0.6332225913621262,
"grad_norm": 0.40081143379211426,
"learning_rate": 3.135177629775391e-06,
"loss": 0.38720703125,
"step": 953,
"token_acc": 0.8717068911865253
},
{
"epoch": 0.6338870431893687,
"grad_norm": 0.27208828926086426,
"learning_rate": 3.125192539789026e-06,
"loss": 0.37451171875,
"step": 954,
"token_acc": 0.8770672793041339
},
{
"epoch": 0.6345514950166113,
"grad_norm": 0.5289908051490784,
"learning_rate": 3.115216142322024e-06,
"loss": 0.36376953125,
"step": 955,
"token_acc": 0.8790929869081294
},
{
"epoch": 0.6352159468438539,
"grad_norm": 0.3113231658935547,
"learning_rate": 3.105248483629817e-06,
"loss": 0.381591796875,
"step": 956,
"token_acc": 0.8743655776482113
},
{
"epoch": 0.6358803986710964,
"grad_norm": 0.2754930853843689,
"learning_rate": 3.0952896099273212e-06,
"loss": 0.380859375,
"step": 957,
"token_acc": 0.8736905236130175
},
{
"epoch": 0.6365448504983389,
"grad_norm": 0.31617531180381775,
"learning_rate": 3.0853395673887165e-06,
"loss": 0.399658203125,
"step": 958,
"token_acc": 0.8681249724902969
},
{
"epoch": 0.6372093023255814,
"grad_norm": 0.29444652795791626,
"learning_rate": 3.0753984021472395e-06,
"loss": 0.394287109375,
"step": 959,
"token_acc": 0.8706633216634728
},
{
"epoch": 0.6378737541528239,
"grad_norm": 0.4321066439151764,
"learning_rate": 3.0654661602949735e-06,
"loss": 0.38818359375,
"step": 960,
"token_acc": 0.871793530699783
},
{
"epoch": 0.6385382059800665,
"grad_norm": 0.27616217732429504,
"learning_rate": 3.0555428878826164e-06,
"loss": 0.3818359375,
"step": 961,
"token_acc": 0.8744280756580367
},
{
"epoch": 0.639202657807309,
"grad_norm": 0.43737372756004333,
"learning_rate": 3.0456286309192908e-06,
"loss": 0.377197265625,
"step": 962,
"token_acc": 0.8758702563927245
},
{
"epoch": 0.6398671096345515,
"grad_norm": 0.2963312864303589,
"learning_rate": 3.035723435372314e-06,
"loss": 0.3779296875,
"step": 963,
"token_acc": 0.8748599709666324
},
{
"epoch": 0.640531561461794,
"grad_norm": 0.2736877501010895,
"learning_rate": 3.0258273471669876e-06,
"loss": 0.37744140625,
"step": 964,
"token_acc": 0.8755551378913105
},
{
"epoch": 0.6411960132890365,
"grad_norm": 0.3271864354610443,
"learning_rate": 3.0159404121863933e-06,
"loss": 0.382568359375,
"step": 965,
"token_acc": 0.873968423160109
},
{
"epoch": 0.641860465116279,
"grad_norm": 0.3905524015426636,
"learning_rate": 3.006062676271171e-06,
"loss": 0.388916015625,
"step": 966,
"token_acc": 0.8715135471850214
},
{
"epoch": 0.6425249169435215,
"grad_norm": 0.33021900057792664,
"learning_rate": 2.9961941852193097e-06,
"loss": 0.384033203125,
"step": 967,
"token_acc": 0.8735358377073525
},
{
"epoch": 0.6431893687707642,
"grad_norm": 0.32186460494995117,
"learning_rate": 2.9863349847859326e-06,
"loss": 0.4033203125,
"step": 968,
"token_acc": 0.8672738997172688
},
{
"epoch": 0.6438538205980067,
"grad_norm": 0.34157463908195496,
"learning_rate": 2.9764851206830893e-06,
"loss": 0.3828125,
"step": 969,
"token_acc": 0.8735361755490644
},
{
"epoch": 0.6445182724252492,
"grad_norm": 0.3767755627632141,
"learning_rate": 2.966644638579542e-06,
"loss": 0.376220703125,
"step": 970,
"token_acc": 0.8749788095072504
},
{
"epoch": 0.6451827242524917,
"grad_norm": 0.583545982837677,
"learning_rate": 2.9568135841005512e-06,
"loss": 0.394287109375,
"step": 971,
"token_acc": 0.8690517114239488
},
{
"epoch": 0.6458471760797342,
"grad_norm": 0.29861125349998474,
"learning_rate": 2.946992002827669e-06,
"loss": 0.38427734375,
"step": 972,
"token_acc": 0.8728235632157273
},
{
"epoch": 0.6465116279069767,
"grad_norm": 0.3400108516216278,
"learning_rate": 2.9371799402985233e-06,
"loss": 0.399169921875,
"step": 973,
"token_acc": 0.8680274698087662
},
{
"epoch": 0.6471760797342193,
"grad_norm": 0.4727543294429779,
"learning_rate": 2.927377442006608e-06,
"loss": 0.392333984375,
"step": 974,
"token_acc": 0.8706816989595402
},
{
"epoch": 0.6478405315614618,
"grad_norm": 0.3096235394477844,
"learning_rate": 2.9175845534010748e-06,
"loss": 0.37841796875,
"step": 975,
"token_acc": 0.8745381842695543
},
{
"epoch": 0.6485049833887043,
"grad_norm": 0.39717692136764526,
"learning_rate": 2.9078013198865197e-06,
"loss": 0.374267578125,
"step": 976,
"token_acc": 0.8761527983926438
},
{
"epoch": 0.6491694352159468,
"grad_norm": 0.3213733434677124,
"learning_rate": 2.898027786822768e-06,
"loss": 0.371337890625,
"step": 977,
"token_acc": 0.8776821465968295
},
{
"epoch": 0.6498338870431893,
"grad_norm": 0.2882896959781647,
"learning_rate": 2.8882639995246788e-06,
"loss": 0.375732421875,
"step": 978,
"token_acc": 0.8754159672289581
},
{
"epoch": 0.6504983388704318,
"grad_norm": 0.2749546468257904,
"learning_rate": 2.878510003261914e-06,
"loss": 0.39599609375,
"step": 979,
"token_acc": 0.8693969785839646
},
{
"epoch": 0.6511627906976745,
"grad_norm": 0.34719347953796387,
"learning_rate": 2.8687658432587506e-06,
"loss": 0.385498046875,
"step": 980,
"token_acc": 0.8728551555235357
},
{
"epoch": 0.651827242524917,
"grad_norm": 0.3455126881599426,
"learning_rate": 2.8590315646938515e-06,
"loss": 0.406494140625,
"step": 981,
"token_acc": 0.8662601288752454
},
{
"epoch": 0.6524916943521595,
"grad_norm": 0.3628726601600647,
"learning_rate": 2.8493072127000654e-06,
"loss": 0.3779296875,
"step": 982,
"token_acc": 0.8752247585165109
},
{
"epoch": 0.653156146179402,
"grad_norm": 0.3164879381656647,
"learning_rate": 2.8395928323642218e-06,
"loss": 0.40185546875,
"step": 983,
"token_acc": 0.8679627704575852
},
{
"epoch": 0.6538205980066445,
"grad_norm": 0.33283731341362,
"learning_rate": 2.8298884687269126e-06,
"loss": 0.3984375,
"step": 984,
"token_acc": 0.8688157064563792
},
{
"epoch": 0.654485049833887,
"grad_norm": 0.3106726109981537,
"learning_rate": 2.8201941667822852e-06,
"loss": 0.376953125,
"step": 985,
"token_acc": 0.8748764860046191
},
{
"epoch": 0.6551495016611296,
"grad_norm": 0.3116738498210907,
"learning_rate": 2.810509971477843e-06,
"loss": 0.39013671875,
"step": 986,
"token_acc": 0.8717138159520376
},
{
"epoch": 0.6558139534883721,
"grad_norm": 0.4192024767398834,
"learning_rate": 2.800835927714225e-06,
"loss": 0.37353515625,
"step": 987,
"token_acc": 0.8766885718615182
},
{
"epoch": 0.6564784053156146,
"grad_norm": 0.28012949228286743,
"learning_rate": 2.7911720803450016e-06,
"loss": 0.389404296875,
"step": 988,
"token_acc": 0.8721721704334875
},
{
"epoch": 0.6571428571428571,
"grad_norm": 0.29593712091445923,
"learning_rate": 2.7815184741764732e-06,
"loss": 0.38037109375,
"step": 989,
"token_acc": 0.8753399860172347
},
{
"epoch": 0.6578073089700996,
"grad_norm": 0.3140341341495514,
"learning_rate": 2.7718751539674514e-06,
"loss": 0.365234375,
"step": 990,
"token_acc": 0.8786881223881167
},
{
"epoch": 0.6584717607973422,
"grad_norm": 0.8767445683479309,
"learning_rate": 2.7622421644290633e-06,
"loss": 0.384765625,
"step": 991,
"token_acc": 0.8730477664716385
},
{
"epoch": 0.6591362126245848,
"grad_norm": 0.283646821975708,
"learning_rate": 2.752619550224529e-06,
"loss": 0.396484375,
"step": 992,
"token_acc": 0.8690879316474787
},
{
"epoch": 0.6598006644518273,
"grad_norm": 0.33079198002815247,
"learning_rate": 2.7430073559689734e-06,
"loss": 0.384765625,
"step": 993,
"token_acc": 0.8727129734525654
},
{
"epoch": 0.6604651162790698,
"grad_norm": 0.29815447330474854,
"learning_rate": 2.733405626229203e-06,
"loss": 0.39208984375,
"step": 994,
"token_acc": 0.8707286540619874
},
{
"epoch": 0.6611295681063123,
"grad_norm": 0.28929591178894043,
"learning_rate": 2.723814405523506e-06,
"loss": 0.39599609375,
"step": 995,
"token_acc": 0.8692337273562085
},
{
"epoch": 0.6617940199335548,
"grad_norm": 0.29791194200515747,
"learning_rate": 2.7142337383214503e-06,
"loss": 0.386962890625,
"step": 996,
"token_acc": 0.8721859228550829
},
{
"epoch": 0.6624584717607973,
"grad_norm": 0.27821964025497437,
"learning_rate": 2.704663669043668e-06,
"loss": 0.3790283203125,
"step": 997,
"token_acc": 0.8745588308395884
},
{
"epoch": 0.6631229235880398,
"grad_norm": 0.5230095386505127,
"learning_rate": 2.6951042420616523e-06,
"loss": 0.386962890625,
"step": 998,
"token_acc": 0.8718097387398595
},
{
"epoch": 0.6637873754152824,
"grad_norm": 0.38558128476142883,
"learning_rate": 2.6855555016975626e-06,
"loss": 0.381591796875,
"step": 999,
"token_acc": 0.873790639706809
},
{
"epoch": 0.6644518272425249,
"grad_norm": 0.3754706382751465,
"learning_rate": 2.676017492224001e-06,
"loss": 0.3935546875,
"step": 1000,
"token_acc": 0.8706534240884692
},
{
"epoch": 0.6651162790697674,
"grad_norm": 0.2639864981174469,
"learning_rate": 2.6664902578638173e-06,
"loss": 0.36376953125,
"step": 1001,
"token_acc": 0.8798564021591881
},
{
"epoch": 0.66578073089701,
"grad_norm": 0.5395474433898926,
"learning_rate": 2.6569738427899085e-06,
"loss": 0.3681640625,
"step": 1002,
"token_acc": 0.8778510111089505
},
{
"epoch": 0.6664451827242525,
"grad_norm": 0.38540104031562805,
"learning_rate": 2.6474682911250017e-06,
"loss": 0.404296875,
"step": 1003,
"token_acc": 0.8669733657265208
},
{
"epoch": 0.667109634551495,
"grad_norm": 0.3216140866279602,
"learning_rate": 2.6379736469414567e-06,
"loss": 0.401123046875,
"step": 1004,
"token_acc": 0.8684741148507255
},
{
"epoch": 0.6677740863787376,
"grad_norm": 0.2954925000667572,
"learning_rate": 2.628489954261064e-06,
"loss": 0.388671875,
"step": 1005,
"token_acc": 0.8720452736029899
},
{
"epoch": 0.6684385382059801,
"grad_norm": 0.2883545160293579,
"learning_rate": 2.6190172570548412e-06,
"loss": 0.397705078125,
"step": 1006,
"token_acc": 0.8689163487927173
},
{
"epoch": 0.6691029900332226,
"grad_norm": 0.3036265969276428,
"learning_rate": 2.6095555992428113e-06,
"loss": 0.392578125,
"step": 1007,
"token_acc": 0.8703198320020059
},
{
"epoch": 0.6697674418604651,
"grad_norm": 0.29908788204193115,
"learning_rate": 2.6001050246938266e-06,
"loss": 0.394287109375,
"step": 1008,
"token_acc": 0.8696443725993337
},
{
"epoch": 0.6704318936877076,
"grad_norm": 0.3026101291179657,
"learning_rate": 2.5906655772253514e-06,
"loss": 0.40869140625,
"step": 1009,
"token_acc": 0.8657560353615421
},
{
"epoch": 0.6710963455149501,
"grad_norm": 0.34179800748825073,
"learning_rate": 2.5812373006032486e-06,
"loss": 0.3753662109375,
"step": 1010,
"token_acc": 0.8755554669466707
},
{
"epoch": 0.6717607973421927,
"grad_norm": 0.33058059215545654,
"learning_rate": 2.5718202385415997e-06,
"loss": 0.376220703125,
"step": 1011,
"token_acc": 0.875046559630136
},
{
"epoch": 0.6724252491694352,
"grad_norm": 0.34902411699295044,
"learning_rate": 2.562414434702486e-06,
"loss": 0.39208984375,
"step": 1012,
"token_acc": 0.8714921302244089
},
{
"epoch": 0.6730897009966778,
"grad_norm": 0.31813502311706543,
"learning_rate": 2.553019932695787e-06,
"loss": 0.374755859375,
"step": 1013,
"token_acc": 0.8760660328347528
},
{
"epoch": 0.6737541528239203,
"grad_norm": 0.3143270015716553,
"learning_rate": 2.5436367760789834e-06,
"loss": 0.3583984375,
"step": 1014,
"token_acc": 0.8808547504710458
},
{
"epoch": 0.6744186046511628,
"grad_norm": 0.39863359928131104,
"learning_rate": 2.5342650083569564e-06,
"loss": 0.3896484375,
"step": 1015,
"token_acc": 0.8708560833663153
},
{
"epoch": 0.6750830564784053,
"grad_norm": 0.33715155720710754,
"learning_rate": 2.5249046729817783e-06,
"loss": 0.393310546875,
"step": 1016,
"token_acc": 0.8708073258325714
},
{
"epoch": 0.6757475083056479,
"grad_norm": 0.2811284363269806,
"learning_rate": 2.515555813352515e-06,
"loss": 0.37939453125,
"step": 1017,
"token_acc": 0.8750559027232181
},
{
"epoch": 0.6764119601328904,
"grad_norm": 0.43859854340553284,
"learning_rate": 2.506218472815032e-06,
"loss": 0.386474609375,
"step": 1018,
"token_acc": 0.8732891365355676
},
{
"epoch": 0.6770764119601329,
"grad_norm": 0.2960417866706848,
"learning_rate": 2.496892694661779e-06,
"loss": 0.380126953125,
"step": 1019,
"token_acc": 0.8737798961669088
},
{
"epoch": 0.6777408637873754,
"grad_norm": 0.28645816445350647,
"learning_rate": 2.487578522131599e-06,
"loss": 0.3759765625,
"step": 1020,
"token_acc": 0.8761383209620984
},
{
"epoch": 0.6784053156146179,
"grad_norm": 0.30876675248146057,
"learning_rate": 2.4782759984095277e-06,
"loss": 0.38720703125,
"step": 1021,
"token_acc": 0.8726303149336714
},
{
"epoch": 0.6790697674418604,
"grad_norm": 0.3088856041431427,
"learning_rate": 2.4689851666265953e-06,
"loss": 0.386474609375,
"step": 1022,
"token_acc": 0.8724926542292043
},
{
"epoch": 0.6797342192691029,
"grad_norm": 0.30618909001350403,
"learning_rate": 2.4597060698596082e-06,
"loss": 0.406005859375,
"step": 1023,
"token_acc": 0.8669400534277065
},
{
"epoch": 0.6803986710963456,
"grad_norm": 0.677135705947876,
"learning_rate": 2.4504387511309775e-06,
"loss": 0.3935546875,
"step": 1024,
"token_acc": 0.8704557752151251
},
{
"epoch": 0.6810631229235881,
"grad_norm": 0.3105831444263458,
"learning_rate": 2.441183253408504e-06,
"loss": 0.39013671875,
"step": 1025,
"token_acc": 0.8720845643854263
},
{
"epoch": 0.6817275747508306,
"grad_norm": 0.3032550513744354,
"learning_rate": 2.4319396196051705e-06,
"loss": 0.379150390625,
"step": 1026,
"token_acc": 0.8745262228575974
},
{
"epoch": 0.6823920265780731,
"grad_norm": 0.3600805401802063,
"learning_rate": 2.4227078925789626e-06,
"loss": 0.39208984375,
"step": 1027,
"token_acc": 0.8712503038027861
},
{
"epoch": 0.6830564784053156,
"grad_norm": 0.30694758892059326,
"learning_rate": 2.4134881151326623e-06,
"loss": 0.38037109375,
"step": 1028,
"token_acc": 0.8746613819745268
},
{
"epoch": 0.6837209302325581,
"grad_norm": 0.4459408223628998,
"learning_rate": 2.4042803300136343e-06,
"loss": 0.379638671875,
"step": 1029,
"token_acc": 0.8748690402752607
},
{
"epoch": 0.6843853820598007,
"grad_norm": 0.34254878759384155,
"learning_rate": 2.3950845799136536e-06,
"loss": 0.38623046875,
"step": 1030,
"token_acc": 0.8733587442215238
},
{
"epoch": 0.6850498338870432,
"grad_norm": 0.5148606896400452,
"learning_rate": 2.385900907468693e-06,
"loss": 0.388671875,
"step": 1031,
"token_acc": 0.8717846106436343
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.34459808468818665,
"learning_rate": 2.3767293552587223e-06,
"loss": 0.3955078125,
"step": 1032,
"token_acc": 0.8696855367193403
},
{
"epoch": 0.6863787375415282,
"grad_norm": 0.29320529103279114,
"learning_rate": 2.3675699658075186e-06,
"loss": 0.3819580078125,
"step": 1033,
"token_acc": 0.8739500688419246
},
{
"epoch": 0.6870431893687707,
"grad_norm": 0.3068685531616211,
"learning_rate": 2.3584227815824695e-06,
"loss": 0.377197265625,
"step": 1034,
"token_acc": 0.8746737421319108
},
{
"epoch": 0.6877076411960132,
"grad_norm": 0.3036400079727173,
"learning_rate": 2.3492878449943685e-06,
"loss": 0.378662109375,
"step": 1035,
"token_acc": 0.8750918142495715
},
{
"epoch": 0.6883720930232559,
"grad_norm": 0.30678805708885193,
"learning_rate": 2.3401651983972244e-06,
"loss": 0.368896484375,
"step": 1036,
"token_acc": 0.8780785691736833
},
{
"epoch": 0.6890365448504984,
"grad_norm": 0.324139803647995,
"learning_rate": 2.3310548840880675e-06,
"loss": 0.37255859375,
"step": 1037,
"token_acc": 0.8765525279110974
},
{
"epoch": 0.6897009966777409,
"grad_norm": 0.35619276762008667,
"learning_rate": 2.3219569443067446e-06,
"loss": 0.3876953125,
"step": 1038,
"token_acc": 0.8730482221836231
},
{
"epoch": 0.6903654485049834,
"grad_norm": 0.3321426808834076,
"learning_rate": 2.3128714212357287e-06,
"loss": 0.389404296875,
"step": 1039,
"token_acc": 0.8711051201653471
},
{
"epoch": 0.6910299003322259,
"grad_norm": 0.291660875082016,
"learning_rate": 2.3037983569999277e-06,
"loss": 0.384033203125,
"step": 1040,
"token_acc": 0.8728744532804791
},
{
"epoch": 0.6916943521594684,
"grad_norm": 0.37554797530174255,
"learning_rate": 2.2947377936664794e-06,
"loss": 0.381591796875,
"step": 1041,
"token_acc": 0.8742432355986148
},
{
"epoch": 0.692358803986711,
"grad_norm": 0.29697081446647644,
"learning_rate": 2.2856897732445605e-06,
"loss": 0.38818359375,
"step": 1042,
"token_acc": 0.871634672872267
},
{
"epoch": 0.6930232558139535,
"grad_norm": 0.36800241470336914,
"learning_rate": 2.2766543376851963e-06,
"loss": 0.3740234375,
"step": 1043,
"token_acc": 0.8766716476548467
},
{
"epoch": 0.693687707641196,
"grad_norm": 0.420035183429718,
"learning_rate": 2.2676315288810647e-06,
"loss": 0.397705078125,
"step": 1044,
"token_acc": 0.8694964250466533
},
{
"epoch": 0.6943521594684385,
"grad_norm": 0.3394708037376404,
"learning_rate": 2.2586213886662934e-06,
"loss": 0.369384765625,
"step": 1045,
"token_acc": 0.8770826116282057
},
{
"epoch": 0.695016611295681,
"grad_norm": 0.4120398163795471,
"learning_rate": 2.2496239588162733e-06,
"loss": 0.39208984375,
"step": 1046,
"token_acc": 0.87026955236869
},
{
"epoch": 0.6956810631229235,
"grad_norm": 0.3215067684650421,
"learning_rate": 2.2406392810474697e-06,
"loss": 0.39794921875,
"step": 1047,
"token_acc": 0.8693076179792751
},
{
"epoch": 0.6963455149501662,
"grad_norm": 0.3982025384902954,
"learning_rate": 2.231667397017218e-06,
"loss": 0.375244140625,
"step": 1048,
"token_acc": 0.8763693235018393
},
{
"epoch": 0.6970099667774087,
"grad_norm": 0.33715739846229553,
"learning_rate": 2.2227083483235345e-06,
"loss": 0.392333984375,
"step": 1049,
"token_acc": 0.8706322027922027
},
{
"epoch": 0.6976744186046512,
"grad_norm": 0.3148171305656433,
"learning_rate": 2.213762176504931e-06,
"loss": 0.397705078125,
"step": 1050,
"token_acc": 0.8698013381550569
},
{
"epoch": 0.6983388704318937,
"grad_norm": 0.5316635966300964,
"learning_rate": 2.204828923040209e-06,
"loss": 0.371826171875,
"step": 1051,
"token_acc": 0.8764922080049348
},
{
"epoch": 0.6990033222591362,
"grad_norm": 0.3353416919708252,
"learning_rate": 2.195908629348277e-06,
"loss": 0.380859375,
"step": 1052,
"token_acc": 0.8741374734962915
},
{
"epoch": 0.6996677740863787,
"grad_norm": 0.3123927414417267,
"learning_rate": 2.1870013367879572e-06,
"loss": 0.380859375,
"step": 1053,
"token_acc": 0.8737418756707697
},
{
"epoch": 0.7003322259136212,
"grad_norm": 0.30552539229393005,
"learning_rate": 2.178107086657791e-06,
"loss": 0.39306640625,
"step": 1054,
"token_acc": 0.8710344094274415
},
{
"epoch": 0.7009966777408638,
"grad_norm": 0.28891652822494507,
"learning_rate": 2.169225920195845e-06,
"loss": 0.39208984375,
"step": 1055,
"token_acc": 0.8706503431972519
},
{
"epoch": 0.7016611295681063,
"grad_norm": 0.3302091360092163,
"learning_rate": 2.1603578785795315e-06,
"loss": 0.386474609375,
"step": 1056,
"token_acc": 0.8729953183661939
},
{
"epoch": 0.7023255813953488,
"grad_norm": 0.34511086344718933,
"learning_rate": 2.151503002925402e-06,
"loss": 0.378173828125,
"step": 1057,
"token_acc": 0.8749023999259558
},
{
"epoch": 0.7029900332225913,
"grad_norm": 0.3088017702102661,
"learning_rate": 2.1426613342889695e-06,
"loss": 0.384033203125,
"step": 1058,
"token_acc": 0.8734898216038205
},
{
"epoch": 0.7036544850498339,
"grad_norm": 0.3544534146785736,
"learning_rate": 2.133832913664511e-06,
"loss": 0.380615234375,
"step": 1059,
"token_acc": 0.8737792302949123
},
{
"epoch": 0.7043189368770764,
"grad_norm": 0.320802241563797,
"learning_rate": 2.1250177819848757e-06,
"loss": 0.39404296875,
"step": 1060,
"token_acc": 0.870122918135072
},
{
"epoch": 0.704983388704319,
"grad_norm": 0.29903921484947205,
"learning_rate": 2.1162159801213054e-06,
"loss": 0.381591796875,
"step": 1061,
"token_acc": 0.8737916041681809
},
{
"epoch": 0.7056478405315615,
"grad_norm": 0.29743799567222595,
"learning_rate": 2.1074275488832346e-06,
"loss": 0.39306640625,
"step": 1062,
"token_acc": 0.870324933468411
},
{
"epoch": 0.706312292358804,
"grad_norm": 0.37130364775657654,
"learning_rate": 2.098652529018103e-06,
"loss": 0.388427734375,
"step": 1063,
"token_acc": 0.8714531597918419
},
{
"epoch": 0.7069767441860465,
"grad_norm": 0.29066744446754456,
"learning_rate": 2.0898909612111744e-06,
"loss": 0.385986328125,
"step": 1064,
"token_acc": 0.8718642580664777
},
{
"epoch": 0.707641196013289,
"grad_norm": 0.3118491470813751,
"learning_rate": 2.0811428860853367e-06,
"loss": 0.377685546875,
"step": 1065,
"token_acc": 0.8753864769016335
},
{
"epoch": 0.7083056478405315,
"grad_norm": 0.287941038608551,
"learning_rate": 2.072408344200924e-06,
"loss": 0.389892578125,
"step": 1066,
"token_acc": 0.8709145984433552
},
{
"epoch": 0.7089700996677741,
"grad_norm": 0.38713309168815613,
"learning_rate": 2.0636873760555202e-06,
"loss": 0.387451171875,
"step": 1067,
"token_acc": 0.8724623965926955
},
{
"epoch": 0.7096345514950166,
"grad_norm": 0.44511380791664124,
"learning_rate": 2.054980022083774e-06,
"loss": 0.392333984375,
"step": 1068,
"token_acc": 0.8703731571214868
},
{
"epoch": 0.7102990033222591,
"grad_norm": 0.41912221908569336,
"learning_rate": 2.046286322657217e-06,
"loss": 0.3837890625,
"step": 1069,
"token_acc": 0.873116074851878
},
{
"epoch": 0.7109634551495017,
"grad_norm": 0.346162885427475,
"learning_rate": 2.0376063180840655e-06,
"loss": 0.3818359375,
"step": 1070,
"token_acc": 0.8731479143249966
},
{
"epoch": 0.7116279069767442,
"grad_norm": 0.3301094174385071,
"learning_rate": 2.0289400486090465e-06,
"loss": 0.37353515625,
"step": 1071,
"token_acc": 0.8762124021499154
},
{
"epoch": 0.7122923588039867,
"grad_norm": 0.31889331340789795,
"learning_rate": 2.0202875544131995e-06,
"loss": 0.39794921875,
"step": 1072,
"token_acc": 0.8685795383757021
},
{
"epoch": 0.7129568106312293,
"grad_norm": 0.33297181129455566,
"learning_rate": 2.0116488756136943e-06,
"loss": 0.38232421875,
"step": 1073,
"token_acc": 0.8732056254341833
},
{
"epoch": 0.7136212624584718,
"grad_norm": 0.3093036115169525,
"learning_rate": 2.003024052263652e-06,
"loss": 0.380859375,
"step": 1074,
"token_acc": 0.873784639776853
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.39456215500831604,
"learning_rate": 1.994413124351946e-06,
"loss": 0.389404296875,
"step": 1075,
"token_acc": 0.8724909814591449
},
{
"epoch": 0.7149501661129568,
"grad_norm": 0.3340488374233246,
"learning_rate": 1.9858161318030265e-06,
"loss": 0.397216796875,
"step": 1076,
"token_acc": 0.8699360293770434
},
{
"epoch": 0.7156146179401993,
"grad_norm": 0.3379814922809601,
"learning_rate": 1.9772331144767363e-06,
"loss": 0.406494140625,
"step": 1077,
"token_acc": 0.8668741969991114
},
{
"epoch": 0.7162790697674418,
"grad_norm": 0.2756786048412323,
"learning_rate": 1.968664112168116e-06,
"loss": 0.38916015625,
"step": 1078,
"token_acc": 0.8707154283254509
},
{
"epoch": 0.7169435215946844,
"grad_norm": 0.5560223460197449,
"learning_rate": 1.960109164607228e-06,
"loss": 0.391845703125,
"step": 1079,
"token_acc": 0.8711092805824818
},
{
"epoch": 0.717607973421927,
"grad_norm": 0.2835395336151123,
"learning_rate": 1.9515683114589716e-06,
"loss": 0.396728515625,
"step": 1080,
"token_acc": 0.8696731223891356
},
{
"epoch": 0.7182724252491695,
"grad_norm": 0.2758549153804779,
"learning_rate": 1.9430415923229e-06,
"loss": 0.388427734375,
"step": 1081,
"token_acc": 0.8719249589958386
},
{
"epoch": 0.718936877076412,
"grad_norm": 0.3115196228027344,
"learning_rate": 1.934529046733025e-06,
"loss": 0.390869140625,
"step": 1082,
"token_acc": 0.871772807912051
},
{
"epoch": 0.7196013289036545,
"grad_norm": 0.3071199655532837,
"learning_rate": 1.9260307141576507e-06,
"loss": 0.39111328125,
"step": 1083,
"token_acc": 0.8717110465226109
},
{
"epoch": 0.720265780730897,
"grad_norm": 0.3712564706802368,
"learning_rate": 1.9175466339991837e-06,
"loss": 0.38720703125,
"step": 1084,
"token_acc": 0.8728024565796927
},
{
"epoch": 0.7209302325581395,
"grad_norm": 0.43466246128082275,
"learning_rate": 1.9090768455939444e-06,
"loss": 0.3720703125,
"step": 1085,
"token_acc": 0.876797862161529
},
{
"epoch": 0.7215946843853821,
"grad_norm": 0.30820825695991516,
"learning_rate": 1.9006213882119907e-06,
"loss": 0.386474609375,
"step": 1086,
"token_acc": 0.8731683904976728
},
{
"epoch": 0.7222591362126246,
"grad_norm": 0.3936403691768646,
"learning_rate": 1.892180301056939e-06,
"loss": 0.3779296875,
"step": 1087,
"token_acc": 0.874878237357434
},
{
"epoch": 0.7229235880398671,
"grad_norm": 0.32604989409446716,
"learning_rate": 1.8837536232657732e-06,
"loss": 0.3662109375,
"step": 1088,
"token_acc": 0.878786531482156
},
{
"epoch": 0.7235880398671096,
"grad_norm": 0.363981693983078,
"learning_rate": 1.87534139390867e-06,
"loss": 0.38134765625,
"step": 1089,
"token_acc": 0.8739249941402542
},
{
"epoch": 0.7242524916943521,
"grad_norm": 0.35852470993995667,
"learning_rate": 1.8669436519888196e-06,
"loss": 0.38232421875,
"step": 1090,
"token_acc": 0.873733629433873
},
{
"epoch": 0.7249169435215946,
"grad_norm": 0.28563958406448364,
"learning_rate": 1.8585604364422367e-06,
"loss": 0.389404296875,
"step": 1091,
"token_acc": 0.8719896551224374
},
{
"epoch": 0.7255813953488373,
"grad_norm": 0.5145037770271301,
"learning_rate": 1.8501917861375846e-06,
"loss": 0.394287109375,
"step": 1092,
"token_acc": 0.8702466541747602
},
{
"epoch": 0.7262458471760798,
"grad_norm": 0.40767931938171387,
"learning_rate": 1.8418377398760011e-06,
"loss": 0.389892578125,
"step": 1093,
"token_acc": 0.871703726314039
},
{
"epoch": 0.7269102990033223,
"grad_norm": 0.26306378841400146,
"learning_rate": 1.8334983363909066e-06,
"loss": 0.366943359375,
"step": 1094,
"token_acc": 0.8776835042762154
},
{
"epoch": 0.7275747508305648,
"grad_norm": 0.3455905616283417,
"learning_rate": 1.8251736143478293e-06,
"loss": 0.3828125,
"step": 1095,
"token_acc": 0.8732222373773438
},
{
"epoch": 0.7282392026578073,
"grad_norm": 0.2687048316001892,
"learning_rate": 1.8168636123442334e-06,
"loss": 0.380859375,
"step": 1096,
"token_acc": 0.8734140268191388
},
{
"epoch": 0.7289036544850498,
"grad_norm": 0.34798869490623474,
"learning_rate": 1.808568368909333e-06,
"loss": 0.387451171875,
"step": 1097,
"token_acc": 0.8724195375865202
},
{
"epoch": 0.7295681063122924,
"grad_norm": 0.3248394727706909,
"learning_rate": 1.800287922503905e-06,
"loss": 0.38037109375,
"step": 1098,
"token_acc": 0.8749429728928415
},
{
"epoch": 0.7302325581395349,
"grad_norm": 0.3083460032939911,
"learning_rate": 1.7920223115201302e-06,
"loss": 0.3623046875,
"step": 1099,
"token_acc": 0.8806331996591165
},
{
"epoch": 0.7308970099667774,
"grad_norm": 0.32583126425743103,
"learning_rate": 1.783771574281406e-06,
"loss": 0.372314453125,
"step": 1100,
"token_acc": 0.8772325263845852
},
{
"epoch": 0.7315614617940199,
"grad_norm": 0.4577086567878723,
"learning_rate": 1.775535749042156e-06,
"loss": 0.3779296875,
"step": 1101,
"token_acc": 0.8745483817389174
},
{
"epoch": 0.7322259136212624,
"grad_norm": 0.3849150240421295,
"learning_rate": 1.767314873987676e-06,
"loss": 0.384521484375,
"step": 1102,
"token_acc": 0.8733271990661264
},
{
"epoch": 0.7328903654485049,
"grad_norm": 0.2988218069076538,
"learning_rate": 1.7591089872339455e-06,
"loss": 0.375732421875,
"step": 1103,
"token_acc": 0.8761871190264431
},
{
"epoch": 0.7335548172757476,
"grad_norm": 0.39509931206703186,
"learning_rate": 1.7509181268274395e-06,
"loss": 0.398193359375,
"step": 1104,
"token_acc": 0.8691288114162826
},
{
"epoch": 0.7342192691029901,
"grad_norm": 0.32108527421951294,
"learning_rate": 1.7427423307449753e-06,
"loss": 0.37548828125,
"step": 1105,
"token_acc": 0.8751391198833848
},
{
"epoch": 0.7348837209302326,
"grad_norm": 0.7615081667900085,
"learning_rate": 1.7345816368935219e-06,
"loss": 0.385498046875,
"step": 1106,
"token_acc": 0.8722917005209706
},
{
"epoch": 0.7355481727574751,
"grad_norm": 0.34453099966049194,
"learning_rate": 1.726436083110024e-06,
"loss": 0.36572265625,
"step": 1107,
"token_acc": 0.8785895430593309
},
{
"epoch": 0.7362126245847176,
"grad_norm": 0.28278711438179016,
"learning_rate": 1.7183057071612297e-06,
"loss": 0.396728515625,
"step": 1108,
"token_acc": 0.8687678442097374
},
{
"epoch": 0.7368770764119601,
"grad_norm": 0.3341676592826843,
"learning_rate": 1.7101905467435204e-06,
"loss": 0.404296875,
"step": 1109,
"token_acc": 0.8671383727548876
},
{
"epoch": 0.7375415282392026,
"grad_norm": 0.3421618938446045,
"learning_rate": 1.7020906394827247e-06,
"loss": 0.392822265625,
"step": 1110,
"token_acc": 0.870983932642746
},
{
"epoch": 0.7382059800664452,
"grad_norm": 0.31708911061286926,
"learning_rate": 1.6940060229339521e-06,
"loss": 0.3779296875,
"step": 1111,
"token_acc": 0.874587334321799
},
{
"epoch": 0.7388704318936877,
"grad_norm": 0.4139288663864136,
"learning_rate": 1.6859367345814204e-06,
"loss": 0.3837890625,
"step": 1112,
"token_acc": 0.8727931927326881
},
{
"epoch": 0.7395348837209302,
"grad_norm": 0.2894636392593384,
"learning_rate": 1.6778828118382745e-06,
"loss": 0.380615234375,
"step": 1113,
"token_acc": 0.8746002029793452
},
{
"epoch": 0.7401993355481727,
"grad_norm": 0.31175217032432556,
"learning_rate": 1.6698442920464153e-06,
"loss": 0.366943359375,
"step": 1114,
"token_acc": 0.8785560648972719
},
{
"epoch": 0.7408637873754153,
"grad_norm": 0.4698346257209778,
"learning_rate": 1.6618212124763338e-06,
"loss": 0.383544921875,
"step": 1115,
"token_acc": 0.8729794906273443
},
{
"epoch": 0.7415282392026578,
"grad_norm": 0.3082406520843506,
"learning_rate": 1.653813610326932e-06,
"loss": 0.392333984375,
"step": 1116,
"token_acc": 0.8714767625735201
},
{
"epoch": 0.7421926910299004,
"grad_norm": 0.2789202332496643,
"learning_rate": 1.6458215227253422e-06,
"loss": 0.37744140625,
"step": 1117,
"token_acc": 0.8747277908438172
},
{
"epoch": 0.7428571428571429,
"grad_norm": 0.32935434579849243,
"learning_rate": 1.6378449867267733e-06,
"loss": 0.387939453125,
"step": 1118,
"token_acc": 0.8722359931907828
},
{
"epoch": 0.7435215946843854,
"grad_norm": 0.3148227334022522,
"learning_rate": 1.6298840393143283e-06,
"loss": 0.379638671875,
"step": 1119,
"token_acc": 0.875069708620793
},
{
"epoch": 0.7441860465116279,
"grad_norm": 0.3487522304058075,
"learning_rate": 1.62193871739883e-06,
"loss": 0.369384765625,
"step": 1120,
"token_acc": 0.8766172773318518
},
{
"epoch": 0.7448504983388704,
"grad_norm": 0.3452828526496887,
"learning_rate": 1.6140090578186546e-06,
"loss": 0.37255859375,
"step": 1121,
"token_acc": 0.8764444129431803
},
{
"epoch": 0.7455149501661129,
"grad_norm": 0.3665177822113037,
"learning_rate": 1.606095097339564e-06,
"loss": 0.37548828125,
"step": 1122,
"token_acc": 0.8759034374857425
},
{
"epoch": 0.7461794019933555,
"grad_norm": 0.3121078908443451,
"learning_rate": 1.5981968726545272e-06,
"loss": 0.383544921875,
"step": 1123,
"token_acc": 0.8731846425967577
},
{
"epoch": 0.746843853820598,
"grad_norm": 0.37220343947410583,
"learning_rate": 1.5903144203835535e-06,
"loss": 0.37744140625,
"step": 1124,
"token_acc": 0.8750402188770674
},
{
"epoch": 0.7475083056478405,
"grad_norm": 0.35911527276039124,
"learning_rate": 1.5824477770735302e-06,
"loss": 0.37548828125,
"step": 1125,
"token_acc": 0.875692820506195
},
{
"epoch": 0.748172757475083,
"grad_norm": 0.25672146677970886,
"learning_rate": 1.5745969791980404e-06,
"loss": 0.367919921875,
"step": 1126,
"token_acc": 0.8778371429937455
},
{
"epoch": 0.7488372093023256,
"grad_norm": 0.2689114212989807,
"learning_rate": 1.5667620631572e-06,
"loss": 0.389892578125,
"step": 1127,
"token_acc": 0.8717312435335338
},
{
"epoch": 0.7495016611295681,
"grad_norm": 0.3029068410396576,
"learning_rate": 1.558943065277495e-06,
"loss": 0.382568359375,
"step": 1128,
"token_acc": 0.8735031297889485
},
{
"epoch": 0.7501661129568107,
"grad_norm": 0.3315061628818512,
"learning_rate": 1.5511400218116002e-06,
"loss": 0.381591796875,
"step": 1129,
"token_acc": 0.8743329439997561
},
{
"epoch": 0.7508305647840532,
"grad_norm": 0.3146354556083679,
"learning_rate": 1.5433529689382205e-06,
"loss": 0.379150390625,
"step": 1130,
"token_acc": 0.8745682269754571
},
{
"epoch": 0.7514950166112957,
"grad_norm": 0.2947503924369812,
"learning_rate": 1.5355819427619228e-06,
"loss": 0.373046875,
"step": 1131,
"token_acc": 0.8760884406334796
},
{
"epoch": 0.7521594684385382,
"grad_norm": 0.4309074282646179,
"learning_rate": 1.527826979312963e-06,
"loss": 0.38330078125,
"step": 1132,
"token_acc": 0.8730510924037578
},
{
"epoch": 0.7528239202657807,
"grad_norm": 0.34966975450515747,
"learning_rate": 1.5200881145471258e-06,
"loss": 0.38134765625,
"step": 1133,
"token_acc": 0.8736989416601068
},
{
"epoch": 0.7534883720930232,
"grad_norm": 0.26846665143966675,
"learning_rate": 1.5123653843455517e-06,
"loss": 0.37060546875,
"step": 1134,
"token_acc": 0.876832782611381
},
{
"epoch": 0.7541528239202658,
"grad_norm": 0.3876972794532776,
"learning_rate": 1.5046588245145722e-06,
"loss": 0.37744140625,
"step": 1135,
"token_acc": 0.8750272125466501
},
{
"epoch": 0.7548172757475083,
"grad_norm": 0.30109280347824097,
"learning_rate": 1.496968470785552e-06,
"loss": 0.36376953125,
"step": 1136,
"token_acc": 0.8791135649567425
},
{
"epoch": 0.7554817275747508,
"grad_norm": 0.508131206035614,
"learning_rate": 1.489294358814708e-06,
"loss": 0.3984375,
"step": 1137,
"token_acc": 0.8689157861936827
},
{
"epoch": 0.7561461794019934,
"grad_norm": 0.28765177726745605,
"learning_rate": 1.481636524182959e-06,
"loss": 0.39111328125,
"step": 1138,
"token_acc": 0.8710334520023996
},
{
"epoch": 0.7568106312292359,
"grad_norm": 0.44306522607803345,
"learning_rate": 1.4739950023957506e-06,
"loss": 0.381103515625,
"step": 1139,
"token_acc": 0.8739195420049417
},
{
"epoch": 0.7574750830564784,
"grad_norm": 0.4288807511329651,
"learning_rate": 1.4663698288828926e-06,
"loss": 0.38037109375,
"step": 1140,
"token_acc": 0.8735021123205413
},
{
"epoch": 0.7581395348837209,
"grad_norm": 0.3494960367679596,
"learning_rate": 1.4587610389984024e-06,
"loss": 0.377685546875,
"step": 1141,
"token_acc": 0.8750925761931362
},
{
"epoch": 0.7588039867109635,
"grad_norm": 0.33552059531211853,
"learning_rate": 1.451168668020329e-06,
"loss": 0.38037109375,
"step": 1142,
"token_acc": 0.8738454843526084
},
{
"epoch": 0.759468438538206,
"grad_norm": 0.3189030885696411,
"learning_rate": 1.4435927511505964e-06,
"loss": 0.390625,
"step": 1143,
"token_acc": 0.8717311617783217
},
{
"epoch": 0.7601328903654485,
"grad_norm": 0.26453542709350586,
"learning_rate": 1.4360333235148437e-06,
"loss": 0.38525390625,
"step": 1144,
"token_acc": 0.8725015548790468
},
{
"epoch": 0.760797342192691,
"grad_norm": 0.3199431598186493,
"learning_rate": 1.4284904201622508e-06,
"loss": 0.381591796875,
"step": 1145,
"token_acc": 0.8743346255852716
},
{
"epoch": 0.7614617940199335,
"grad_norm": 0.2772771716117859,
"learning_rate": 1.4209640760653903e-06,
"loss": 0.3759765625,
"step": 1146,
"token_acc": 0.8756817895648706
},
{
"epoch": 0.762126245847176,
"grad_norm": 0.2738794982433319,
"learning_rate": 1.4134543261200527e-06,
"loss": 0.400146484375,
"step": 1147,
"token_acc": 0.8687867163075026
},
{
"epoch": 0.7627906976744186,
"grad_norm": 0.3171127736568451,
"learning_rate": 1.4059612051450906e-06,
"loss": 0.394775390625,
"step": 1148,
"token_acc": 0.8692206523918221
},
{
"epoch": 0.7634551495016612,
"grad_norm": 0.2893490791320801,
"learning_rate": 1.3984847478822605e-06,
"loss": 0.38330078125,
"step": 1149,
"token_acc": 0.8733710449541254
},
{
"epoch": 0.7641196013289037,
"grad_norm": 0.27160024642944336,
"learning_rate": 1.3910249889960541e-06,
"loss": 0.39111328125,
"step": 1150,
"token_acc": 0.8710185174714311
},
{
"epoch": 0.7647840531561462,
"grad_norm": 0.3450276553630829,
"learning_rate": 1.3835819630735403e-06,
"loss": 0.397216796875,
"step": 1151,
"token_acc": 0.8693882081111487
},
{
"epoch": 0.7654485049833887,
"grad_norm": 0.28914159536361694,
"learning_rate": 1.3761557046242109e-06,
"loss": 0.3896484375,
"step": 1152,
"token_acc": 0.8723300052251769
},
{
"epoch": 0.7661129568106312,
"grad_norm": 0.39669132232666016,
"learning_rate": 1.3687462480798114e-06,
"loss": 0.36865234375,
"step": 1153,
"token_acc": 0.8776199361775024
},
{
"epoch": 0.7667774086378738,
"grad_norm": 0.3241809606552124,
"learning_rate": 1.3613536277941847e-06,
"loss": 0.386962890625,
"step": 1154,
"token_acc": 0.8721814309209048
},
{
"epoch": 0.7674418604651163,
"grad_norm": 0.363781213760376,
"learning_rate": 1.3539778780431172e-06,
"loss": 0.385009765625,
"step": 1155,
"token_acc": 0.873845333948679
},
{
"epoch": 0.7681063122923588,
"grad_norm": 0.37265634536743164,
"learning_rate": 1.3466190330241708e-06,
"loss": 0.391845703125,
"step": 1156,
"token_acc": 0.8704928759407707
},
{
"epoch": 0.7687707641196013,
"grad_norm": 0.3304122984409332,
"learning_rate": 1.3392771268565325e-06,
"loss": 0.382080078125,
"step": 1157,
"token_acc": 0.874579429200134
},
{
"epoch": 0.7694352159468438,
"grad_norm": 0.3408391773700714,
"learning_rate": 1.3319521935808478e-06,
"loss": 0.392822265625,
"step": 1158,
"token_acc": 0.8706472485495069
},
{
"epoch": 0.7700996677740863,
"grad_norm": 0.327499121427536,
"learning_rate": 1.3246442671590736e-06,
"loss": 0.37744140625,
"step": 1159,
"token_acc": 0.875521906983106
},
{
"epoch": 0.770764119601329,
"grad_norm": 0.31220144033432007,
"learning_rate": 1.3173533814743106e-06,
"loss": 0.369873046875,
"step": 1160,
"token_acc": 0.8782142229640693
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.32577019929885864,
"learning_rate": 1.310079570330649e-06,
"loss": 0.38232421875,
"step": 1161,
"token_acc": 0.873654731363687
},
{
"epoch": 0.772093023255814,
"grad_norm": 0.3986765146255493,
"learning_rate": 1.3028228674530196e-06,
"loss": 0.369873046875,
"step": 1162,
"token_acc": 0.8777726940024603
},
{
"epoch": 0.7727574750830565,
"grad_norm": 0.2925492227077484,
"learning_rate": 1.2955833064870248e-06,
"loss": 0.3916015625,
"step": 1163,
"token_acc": 0.8706416750427621
},
{
"epoch": 0.773421926910299,
"grad_norm": 0.3789617419242859,
"learning_rate": 1.288360920998789e-06,
"loss": 0.389404296875,
"step": 1164,
"token_acc": 0.8714601254344103
},
{
"epoch": 0.7740863787375415,
"grad_norm": 0.3079700171947479,
"learning_rate": 1.2811557444748084e-06,
"loss": 0.38037109375,
"step": 1165,
"token_acc": 0.8735291679300974
},
{
"epoch": 0.774750830564784,
"grad_norm": 0.29724666476249695,
"learning_rate": 1.273967810321784e-06,
"loss": 0.380859375,
"step": 1166,
"token_acc": 0.8740567596689791
},
{
"epoch": 0.7754152823920266,
"grad_norm": 0.31534767150878906,
"learning_rate": 1.266797151866474e-06,
"loss": 0.385498046875,
"step": 1167,
"token_acc": 0.8737752420418462
},
{
"epoch": 0.7760797342192691,
"grad_norm": 0.28609466552734375,
"learning_rate": 1.2596438023555413e-06,
"loss": 0.377685546875,
"step": 1168,
"token_acc": 0.8754789145702133
},
{
"epoch": 0.7767441860465116,
"grad_norm": 0.43401893973350525,
"learning_rate": 1.2525077949553938e-06,
"loss": 0.38330078125,
"step": 1169,
"token_acc": 0.8734114416779405
},
{
"epoch": 0.7774086378737541,
"grad_norm": 0.40329593420028687,
"learning_rate": 1.2453891627520304e-06,
"loss": 0.368896484375,
"step": 1170,
"token_acc": 0.8775193509299581
},
{
"epoch": 0.7780730897009966,
"grad_norm": 0.32938674092292786,
"learning_rate": 1.2382879387508944e-06,
"loss": 0.3837890625,
"step": 1171,
"token_acc": 0.8735023541200533
},
{
"epoch": 0.7787375415282392,
"grad_norm": 0.28208550810813904,
"learning_rate": 1.231204155876718e-06,
"loss": 0.39111328125,
"step": 1172,
"token_acc": 0.8706224000629372
},
{
"epoch": 0.7794019933554818,
"grad_norm": 0.3034462630748749,
"learning_rate": 1.2241378469733579e-06,
"loss": 0.3955078125,
"step": 1173,
"token_acc": 0.8696003320887176
},
{
"epoch": 0.7800664451827243,
"grad_norm": 0.36165231466293335,
"learning_rate": 1.2170890448036626e-06,
"loss": 0.37548828125,
"step": 1174,
"token_acc": 0.8755930944267696
},
{
"epoch": 0.7807308970099668,
"grad_norm": 0.34481844305992126,
"learning_rate": 1.2100577820493115e-06,
"loss": 0.370849609375,
"step": 1175,
"token_acc": 0.8777091829188115
},
{
"epoch": 0.7813953488372093,
"grad_norm": 0.2787436842918396,
"learning_rate": 1.2030440913106522e-06,
"loss": 0.38720703125,
"step": 1176,
"token_acc": 0.8724482610629395
},
{
"epoch": 0.7820598006644518,
"grad_norm": 0.33721408247947693,
"learning_rate": 1.19604800510657e-06,
"loss": 0.3818359375,
"step": 1177,
"token_acc": 0.8737617435543694
},
{
"epoch": 0.7827242524916943,
"grad_norm": 0.39757654070854187,
"learning_rate": 1.1890695558743247e-06,
"loss": 0.389892578125,
"step": 1178,
"token_acc": 0.8716592784426509
},
{
"epoch": 0.7833887043189369,
"grad_norm": 0.3004460036754608,
"learning_rate": 1.182108775969401e-06,
"loss": 0.39501953125,
"step": 1179,
"token_acc": 0.870508968807988
},
{
"epoch": 0.7840531561461794,
"grad_norm": 0.2899855375289917,
"learning_rate": 1.1751656976653585e-06,
"loss": 0.381103515625,
"step": 1180,
"token_acc": 0.8734209739428793
},
{
"epoch": 0.7847176079734219,
"grad_norm": 0.35570091009140015,
"learning_rate": 1.1682403531536885e-06,
"loss": 0.39990234375,
"step": 1181,
"token_acc": 0.8680996162495994
},
{
"epoch": 0.7853820598006644,
"grad_norm": 0.31673797965049744,
"learning_rate": 1.1613327745436553e-06,
"loss": 0.385986328125,
"step": 1182,
"token_acc": 0.8730136402101517
},
{
"epoch": 0.786046511627907,
"grad_norm": 0.3683463931083679,
"learning_rate": 1.1544429938621526e-06,
"loss": 0.383056640625,
"step": 1183,
"token_acc": 0.8734025174054175
},
{
"epoch": 0.7867109634551495,
"grad_norm": 0.3557979166507721,
"learning_rate": 1.147571043053557e-06,
"loss": 0.386962890625,
"step": 1184,
"token_acc": 0.8731342779875176
},
{
"epoch": 0.7873754152823921,
"grad_norm": 0.3993588089942932,
"learning_rate": 1.1407169539795749e-06,
"loss": 0.38330078125,
"step": 1185,
"token_acc": 0.8730942507676056
},
{
"epoch": 0.7880398671096346,
"grad_norm": 0.3118077516555786,
"learning_rate": 1.1338807584190953e-06,
"loss": 0.37060546875,
"step": 1186,
"token_acc": 0.8768334239001117
},
{
"epoch": 0.7887043189368771,
"grad_norm": 0.3000051975250244,
"learning_rate": 1.1270624880680486e-06,
"loss": 0.38671875,
"step": 1187,
"token_acc": 0.8727079861395148
},
{
"epoch": 0.7893687707641196,
"grad_norm": 0.30322760343551636,
"learning_rate": 1.1202621745392528e-06,
"loss": 0.39111328125,
"step": 1188,
"token_acc": 0.8716584431145505
},
{
"epoch": 0.7900332225913621,
"grad_norm": 0.301791787147522,
"learning_rate": 1.1134798493622668e-06,
"loss": 0.37939453125,
"step": 1189,
"token_acc": 0.8742690138076833
},
{
"epoch": 0.7906976744186046,
"grad_norm": 0.3628864288330078,
"learning_rate": 1.1067155439832505e-06,
"loss": 0.3759765625,
"step": 1190,
"token_acc": 0.8752183013950222
},
{
"epoch": 0.7913621262458472,
"grad_norm": 0.30299609899520874,
"learning_rate": 1.0999692897648173e-06,
"loss": 0.38037109375,
"step": 1191,
"token_acc": 0.8746300641222188
},
{
"epoch": 0.7920265780730897,
"grad_norm": 0.2681407034397125,
"learning_rate": 1.093241117985878e-06,
"loss": 0.400146484375,
"step": 1192,
"token_acc": 0.8682454175295463
},
{
"epoch": 0.7926910299003322,
"grad_norm": 0.6482842564582825,
"learning_rate": 1.086531059841513e-06,
"loss": 0.394287109375,
"step": 1193,
"token_acc": 0.8715658212383007
},
{
"epoch": 0.7933554817275748,
"grad_norm": 0.326078861951828,
"learning_rate": 1.0798391464428175e-06,
"loss": 0.39892578125,
"step": 1194,
"token_acc": 0.8682886918505331
},
{
"epoch": 0.7940199335548173,
"grad_norm": 0.31917959451675415,
"learning_rate": 1.0731654088167526e-06,
"loss": 0.352294921875,
"step": 1195,
"token_acc": 0.8824699424472363
},
{
"epoch": 0.7946843853820598,
"grad_norm": 0.3042660653591156,
"learning_rate": 1.0665098779060146e-06,
"loss": 0.364990234375,
"step": 1196,
"token_acc": 0.8790005899352478
},
{
"epoch": 0.7953488372093023,
"grad_norm": 0.2974323630332947,
"learning_rate": 1.059872584568884e-06,
"loss": 0.384765625,
"step": 1197,
"token_acc": 0.8726201053587809
},
{
"epoch": 0.7960132890365449,
"grad_norm": 0.306975394487381,
"learning_rate": 1.0532535595790793e-06,
"loss": 0.375244140625,
"step": 1198,
"token_acc": 0.8759255399668725
},
{
"epoch": 0.7966777408637874,
"grad_norm": 0.3274289071559906,
"learning_rate": 1.0466528336256198e-06,
"loss": 0.3837890625,
"step": 1199,
"token_acc": 0.8734283402088309
},
{
"epoch": 0.7973421926910299,
"grad_norm": 0.3050541281700134,
"learning_rate": 1.0400704373126835e-06,
"loss": 0.38330078125,
"step": 1200,
"token_acc": 0.8735594895497224
},
{
"epoch": 0.7980066445182724,
"grad_norm": 0.27089229226112366,
"learning_rate": 1.0335064011594615e-06,
"loss": 0.36669921875,
"step": 1201,
"token_acc": 0.8781545027742211
},
{
"epoch": 0.7986710963455149,
"grad_norm": 2.277129650115967,
"learning_rate": 1.0269607556000156e-06,
"loss": 0.371826171875,
"step": 1202,
"token_acc": 0.8771161076266152
},
{
"epoch": 0.7993355481727574,
"grad_norm": 0.33770063519477844,
"learning_rate": 1.0204335309831464e-06,
"loss": 0.38818359375,
"step": 1203,
"token_acc": 0.872407565677866
},
{
"epoch": 0.8,
"grad_norm": 0.3786022365093231,
"learning_rate": 1.0139247575722405e-06,
"loss": 0.388427734375,
"step": 1204,
"token_acc": 0.8715833077944083
},
{
"epoch": 0.8006644518272426,
"grad_norm": 0.40283411741256714,
"learning_rate": 1.0074344655451363e-06,
"loss": 0.3916015625,
"step": 1205,
"token_acc": 0.8706759935822771
},
{
"epoch": 0.8013289036544851,
"grad_norm": 0.5756114721298218,
"learning_rate": 1.000962684993988e-06,
"loss": 0.38037109375,
"step": 1206,
"token_acc": 0.8752329850636045
},
{
"epoch": 0.8019933554817276,
"grad_norm": 0.3577381670475006,
"learning_rate": 9.945094459251148e-07,
"loss": 0.37744140625,
"step": 1207,
"token_acc": 0.8746345346608756
},
{
"epoch": 0.8026578073089701,
"grad_norm": 0.2951071560382843,
"learning_rate": 9.880747782588756e-07,
"loss": 0.3779296875,
"step": 1208,
"token_acc": 0.8745985800583252
},
{
"epoch": 0.8033222591362126,
"grad_norm": 0.4758109152317047,
"learning_rate": 9.816587118295162e-07,
"loss": 0.388427734375,
"step": 1209,
"token_acc": 0.8721630353922298
},
{
"epoch": 0.8039867109634552,
"grad_norm": 0.3398865759372711,
"learning_rate": 9.75261276385045e-07,
"loss": 0.38916015625,
"step": 1210,
"token_acc": 0.8709046090390224
},
{
"epoch": 0.8046511627906977,
"grad_norm": 0.32573628425598145,
"learning_rate": 9.688825015870829e-07,
"loss": 0.3857421875,
"step": 1211,
"token_acc": 0.8734390877582295
},
{
"epoch": 0.8053156146179402,
"grad_norm": 0.4255017340183258,
"learning_rate": 9.625224170107317e-07,
"loss": 0.37255859375,
"step": 1212,
"token_acc": 0.8768817821366056
},
{
"epoch": 0.8059800664451827,
"grad_norm": 0.29962700605392456,
"learning_rate": 9.561810521444404e-07,
"loss": 0.370849609375,
"step": 1213,
"token_acc": 0.8770515616115646
},
{
"epoch": 0.8066445182724252,
"grad_norm": 0.3096730709075928,
"learning_rate": 9.498584363898584e-07,
"loss": 0.378173828125,
"step": 1214,
"token_acc": 0.8751878758877204
},
{
"epoch": 0.8073089700996677,
"grad_norm": 0.3532928228378296,
"learning_rate": 9.435545990617078e-07,
"loss": 0.365966796875,
"step": 1215,
"token_acc": 0.8789590019899557
},
{
"epoch": 0.8079734219269104,
"grad_norm": 0.3021105229854584,
"learning_rate": 9.372695693876476e-07,
"loss": 0.371826171875,
"step": 1216,
"token_acc": 0.8765059414834167
},
{
"epoch": 0.8086378737541529,
"grad_norm": 0.27690646052360535,
"learning_rate": 9.310033765081311e-07,
"loss": 0.3759765625,
"step": 1217,
"token_acc": 0.8755445842001145
},
{
"epoch": 0.8093023255813954,
"grad_norm": 0.3120494782924652,
"learning_rate": 9.247560494762747e-07,
"loss": 0.3916015625,
"step": 1218,
"token_acc": 0.8714610361032331
},
{
"epoch": 0.8099667774086379,
"grad_norm": 0.3504036068916321,
"learning_rate": 9.185276172577284e-07,
"loss": 0.40380859375,
"step": 1219,
"token_acc": 0.8658834114179658
},
{
"epoch": 0.8106312292358804,
"grad_norm": 0.3097398579120636,
"learning_rate": 9.123181087305316e-07,
"loss": 0.376708984375,
"step": 1220,
"token_acc": 0.875268352055656
},
{
"epoch": 0.8112956810631229,
"grad_norm": 0.3063299059867859,
"learning_rate": 9.061275526849883e-07,
"loss": 0.388916015625,
"step": 1221,
"token_acc": 0.8715648631456634
},
{
"epoch": 0.8119601328903654,
"grad_norm": 0.3312222361564636,
"learning_rate": 8.999559778235268e-07,
"loss": 0.38671875,
"step": 1222,
"token_acc": 0.8721399209084769
},
{
"epoch": 0.812624584717608,
"grad_norm": 0.30489465594291687,
"learning_rate": 8.938034127605688e-07,
"loss": 0.385986328125,
"step": 1223,
"token_acc": 0.8721797444700601
},
{
"epoch": 0.8132890365448505,
"grad_norm": 0.3397602140903473,
"learning_rate": 8.876698860224015e-07,
"loss": 0.381103515625,
"step": 1224,
"token_acc": 0.8744274614501693
},
{
"epoch": 0.813953488372093,
"grad_norm": 0.43344464898109436,
"learning_rate": 8.815554260470366e-07,
"loss": 0.38671875,
"step": 1225,
"token_acc": 0.8721378580377587
},
{
"epoch": 0.8146179401993355,
"grad_norm": 0.34638768434524536,
"learning_rate": 8.754600611840841e-07,
"loss": 0.379638671875,
"step": 1226,
"token_acc": 0.8738791590511729
},
{
"epoch": 0.815282392026578,
"grad_norm": 0.3247945010662079,
"learning_rate": 8.693838196946236e-07,
"loss": 0.3818359375,
"step": 1227,
"token_acc": 0.8740240912843283
},
{
"epoch": 0.8159468438538205,
"grad_norm": 0.37681135535240173,
"learning_rate": 8.633267297510639e-07,
"loss": 0.3818359375,
"step": 1228,
"token_acc": 0.8737982972790497
},
{
"epoch": 0.8166112956810632,
"grad_norm": 0.2836933732032776,
"learning_rate": 8.572888194370194e-07,
"loss": 0.38037109375,
"step": 1229,
"token_acc": 0.8741258509268965
},
{
"epoch": 0.8172757475083057,
"grad_norm": 0.3912053108215332,
"learning_rate": 8.512701167471826e-07,
"loss": 0.35595703125,
"step": 1230,
"token_acc": 0.8824407969115706
},
{
"epoch": 0.8179401993355482,
"grad_norm": 0.33365240693092346,
"learning_rate": 8.452706495871837e-07,
"loss": 0.38037109375,
"step": 1231,
"token_acc": 0.8747183967387661
},
{
"epoch": 0.8186046511627907,
"grad_norm": 0.5955530405044556,
"learning_rate": 8.392904457734741e-07,
"loss": 0.38037109375,
"step": 1232,
"token_acc": 0.8744716035717695
},
{
"epoch": 0.8192691029900332,
"grad_norm": 0.42688819766044617,
"learning_rate": 8.333295330331842e-07,
"loss": 0.369873046875,
"step": 1233,
"token_acc": 0.877949202659151
},
{
"epoch": 0.8199335548172757,
"grad_norm": 0.3673070967197418,
"learning_rate": 8.273879390040079e-07,
"loss": 0.3916015625,
"step": 1234,
"token_acc": 0.8703453784289964
},
{
"epoch": 0.8205980066445183,
"grad_norm": 0.26837456226348877,
"learning_rate": 8.214656912340646e-07,
"loss": 0.391357421875,
"step": 1235,
"token_acc": 0.8714784709481479
},
{
"epoch": 0.8212624584717608,
"grad_norm": 0.2836339771747589,
"learning_rate": 8.155628171817742e-07,
"loss": 0.3779296875,
"step": 1236,
"token_acc": 0.8742186668165601
},
{
"epoch": 0.8219269102990033,
"grad_norm": 0.44302648305892944,
"learning_rate": 8.096793442157347e-07,
"loss": 0.376220703125,
"step": 1237,
"token_acc": 0.875314297542571
},
{
"epoch": 0.8225913621262458,
"grad_norm": 0.4308009743690491,
"learning_rate": 8.03815299614587e-07,
"loss": 0.398193359375,
"step": 1238,
"token_acc": 0.8689362606509562
},
{
"epoch": 0.8232558139534883,
"grad_norm": 0.37192147970199585,
"learning_rate": 7.979707105668938e-07,
"loss": 0.373291015625,
"step": 1239,
"token_acc": 0.8765551589607371
},
{
"epoch": 0.8239202657807309,
"grad_norm": 0.3070065379142761,
"learning_rate": 7.921456041710152e-07,
"loss": 0.408447265625,
"step": 1240,
"token_acc": 0.8665527557646878
},
{
"epoch": 0.8245847176079735,
"grad_norm": 0.27934256196022034,
"learning_rate": 7.863400074349764e-07,
"loss": 0.4091796875,
"step": 1241,
"token_acc": 0.8660412780744916
},
{
"epoch": 0.825249169435216,
"grad_norm": 0.2969536781311035,
"learning_rate": 7.805539472763474e-07,
"loss": 0.390380859375,
"step": 1242,
"token_acc": 0.8720340685258138
},
{
"epoch": 0.8259136212624585,
"grad_norm": 0.2909843623638153,
"learning_rate": 7.747874505221198e-07,
"loss": 0.37353515625,
"step": 1243,
"token_acc": 0.8768626943800225
},
{
"epoch": 0.826578073089701,
"grad_norm": 0.42260709404945374,
"learning_rate": 7.690405439085758e-07,
"loss": 0.384765625,
"step": 1244,
"token_acc": 0.8729018845778774
},
{
"epoch": 0.8272425249169435,
"grad_norm": 0.30452868342399597,
"learning_rate": 7.6331325408117e-07,
"loss": 0.372802734375,
"step": 1245,
"token_acc": 0.8758483116028463
},
{
"epoch": 0.827906976744186,
"grad_norm": 0.35014018416404724,
"learning_rate": 7.576056075944039e-07,
"loss": 0.37451171875,
"step": 1246,
"token_acc": 0.8766483999941714
},
{
"epoch": 0.8285714285714286,
"grad_norm": 0.35678476095199585,
"learning_rate": 7.519176309117065e-07,
"loss": 0.40087890625,
"step": 1247,
"token_acc": 0.868091279342796
},
{
"epoch": 0.8292358803986711,
"grad_norm": 0.5073249936103821,
"learning_rate": 7.462493504052986e-07,
"loss": 0.388427734375,
"step": 1248,
"token_acc": 0.8713226483548562
},
{
"epoch": 0.8299003322259136,
"grad_norm": 0.35578206181526184,
"learning_rate": 7.406007923560899e-07,
"loss": 0.37841796875,
"step": 1249,
"token_acc": 0.8744727915574859
},
{
"epoch": 0.8305647840531561,
"grad_norm": 0.35876113176345825,
"learning_rate": 7.349719829535429e-07,
"loss": 0.38134765625,
"step": 1250,
"token_acc": 0.874719353390211
},
{
"epoch": 0.8312292358803987,
"grad_norm": 0.3167843818664551,
"learning_rate": 7.293629482955555e-07,
"loss": 0.37353515625,
"step": 1251,
"token_acc": 0.8766111465434263
},
{
"epoch": 0.8318936877076412,
"grad_norm": 0.3053934574127197,
"learning_rate": 7.237737143883399e-07,
"loss": 0.374755859375,
"step": 1252,
"token_acc": 0.8751133230240283
},
{
"epoch": 0.8325581395348837,
"grad_norm": 0.34963318705558777,
"learning_rate": 7.182043071463046e-07,
"loss": 0.384521484375,
"step": 1253,
"token_acc": 0.8730468348972342
},
{
"epoch": 0.8332225913621263,
"grad_norm": 0.5128093957901001,
"learning_rate": 7.126547523919309e-07,
"loss": 0.39306640625,
"step": 1254,
"token_acc": 0.8698373309271505
},
{
"epoch": 0.8338870431893688,
"grad_norm": 0.6777568459510803,
"learning_rate": 7.071250758556524e-07,
"loss": 0.3876953125,
"step": 1255,
"token_acc": 0.8713588198227106
},
{
"epoch": 0.8345514950166113,
"grad_norm": 0.42908722162246704,
"learning_rate": 7.016153031757417e-07,
"loss": 0.38525390625,
"step": 1256,
"token_acc": 0.8730248837289001
},
{
"epoch": 0.8352159468438538,
"grad_norm": 0.2947397530078888,
"learning_rate": 6.961254598981837e-07,
"loss": 0.377197265625,
"step": 1257,
"token_acc": 0.8745799131403624
},
{
"epoch": 0.8358803986710963,
"grad_norm": 0.4705217182636261,
"learning_rate": 6.906555714765617e-07,
"loss": 0.383056640625,
"step": 1258,
"token_acc": 0.8736043838591193
},
{
"epoch": 0.8365448504983388,
"grad_norm": 0.3343084156513214,
"learning_rate": 6.852056632719411e-07,
"loss": 0.3759765625,
"step": 1259,
"token_acc": 0.8751265020677622
},
{
"epoch": 0.8372093023255814,
"grad_norm": 0.36735478043556213,
"learning_rate": 6.797757605527461e-07,
"loss": 0.386474609375,
"step": 1260,
"token_acc": 0.8727779043652727
},
{
"epoch": 0.837873754152824,
"grad_norm": 0.312859445810318,
"learning_rate": 6.743658884946464e-07,
"loss": 0.386474609375,
"step": 1261,
"token_acc": 0.8719229809046928
},
{
"epoch": 0.8385382059800665,
"grad_norm": 0.3149671256542206,
"learning_rate": 6.689760721804411e-07,
"loss": 0.37353515625,
"step": 1262,
"token_acc": 0.8770718559932074
},
{
"epoch": 0.839202657807309,
"grad_norm": 0.3847261965274811,
"learning_rate": 6.636063365999428e-07,
"loss": 0.3955078125,
"step": 1263,
"token_acc": 0.8695118437968947
},
{
"epoch": 0.8398671096345515,
"grad_norm": 0.3892330229282379,
"learning_rate": 6.58256706649853e-07,
"loss": 0.377685546875,
"step": 1264,
"token_acc": 0.8754673369612649
},
{
"epoch": 0.840531561461794,
"grad_norm": 0.2919650375843048,
"learning_rate": 6.529272071336617e-07,
"loss": 0.381103515625,
"step": 1265,
"token_acc": 0.873926429549512
},
{
"epoch": 0.8411960132890366,
"grad_norm": 0.32304656505584717,
"learning_rate": 6.476178627615221e-07,
"loss": 0.392578125,
"step": 1266,
"token_acc": 0.8701357175017689
},
{
"epoch": 0.8418604651162791,
"grad_norm": 0.36925968527793884,
"learning_rate": 6.423286981501331e-07,
"loss": 0.384521484375,
"step": 1267,
"token_acc": 0.872818192253415
},
{
"epoch": 0.8425249169435216,
"grad_norm": 0.3188249170780182,
"learning_rate": 6.370597378226378e-07,
"loss": 0.370361328125,
"step": 1268,
"token_acc": 0.8770335124942099
},
{
"epoch": 0.8431893687707641,
"grad_norm": 0.26249292492866516,
"learning_rate": 6.318110062085004e-07,
"loss": 0.376708984375,
"step": 1269,
"token_acc": 0.8757115238302559
},
{
"epoch": 0.8438538205980066,
"grad_norm": 0.4551878273487091,
"learning_rate": 6.265825276433901e-07,
"loss": 0.382080078125,
"step": 1270,
"token_acc": 0.8735472692376917
},
{
"epoch": 0.8445182724252491,
"grad_norm": 0.6194983124732971,
"learning_rate": 6.213743263690791e-07,
"loss": 0.379638671875,
"step": 1271,
"token_acc": 0.8734519942399785
},
{
"epoch": 0.8451827242524917,
"grad_norm": 0.34169629216194153,
"learning_rate": 6.161864265333229e-07,
"loss": 0.38134765625,
"step": 1272,
"token_acc": 0.8745173797983677
},
{
"epoch": 0.8458471760797343,
"grad_norm": 0.36448922753334045,
"learning_rate": 6.110188521897475e-07,
"loss": 0.3662109375,
"step": 1273,
"token_acc": 0.8787062527241479
},
{
"epoch": 0.8465116279069768,
"grad_norm": 0.37746477127075195,
"learning_rate": 6.058716272977405e-07,
"loss": 0.39208984375,
"step": 1274,
"token_acc": 0.8710535336799405
},
{
"epoch": 0.8471760797342193,
"grad_norm": 0.30327391624450684,
"learning_rate": 6.007447757223422e-07,
"loss": 0.388671875,
"step": 1275,
"token_acc": 0.871620327221594
},
{
"epoch": 0.8478405315614618,
"grad_norm": 0.3760018050670624,
"learning_rate": 5.956383212341294e-07,
"loss": 0.37744140625,
"step": 1276,
"token_acc": 0.8750456564368868
},
{
"epoch": 0.8485049833887043,
"grad_norm": 0.32718685269355774,
"learning_rate": 5.90552287509108e-07,
"loss": 0.37841796875,
"step": 1277,
"token_acc": 0.8751531445220007
},
{
"epoch": 0.8491694352159468,
"grad_norm": 0.3206216096878052,
"learning_rate": 5.854866981286061e-07,
"loss": 0.389404296875,
"step": 1278,
"token_acc": 0.8736482460408137
},
{
"epoch": 0.8498338870431894,
"grad_norm": 0.28997111320495605,
"learning_rate": 5.804415765791599e-07,
"loss": 0.380615234375,
"step": 1279,
"token_acc": 0.8743113231511498
},
{
"epoch": 0.8504983388704319,
"grad_norm": 0.29933151602745056,
"learning_rate": 5.754169462524056e-07,
"loss": 0.383544921875,
"step": 1280,
"token_acc": 0.8735327092004999
},
{
"epoch": 0.8511627906976744,
"grad_norm": 0.2939201593399048,
"learning_rate": 5.704128304449758e-07,
"loss": 0.377197265625,
"step": 1281,
"token_acc": 0.8750252635341554
},
{
"epoch": 0.8518272425249169,
"grad_norm": 0.3173629939556122,
"learning_rate": 5.654292523583843e-07,
"loss": 0.367431640625,
"step": 1282,
"token_acc": 0.8777343077320475
},
{
"epoch": 0.8524916943521594,
"grad_norm": 0.31019753217697144,
"learning_rate": 5.604662350989226e-07,
"loss": 0.376953125,
"step": 1283,
"token_acc": 0.8753165176060487
},
{
"epoch": 0.8531561461794019,
"grad_norm": 0.352583110332489,
"learning_rate": 5.555238016775538e-07,
"loss": 0.37646484375,
"step": 1284,
"token_acc": 0.8754865795914385
},
{
"epoch": 0.8538205980066446,
"grad_norm": 0.36153319478034973,
"learning_rate": 5.50601975009804e-07,
"loss": 0.3681640625,
"step": 1285,
"token_acc": 0.8777243860433769
},
{
"epoch": 0.8544850498338871,
"grad_norm": 0.3376915156841278,
"learning_rate": 5.457007779156553e-07,
"loss": 0.365966796875,
"step": 1286,
"token_acc": 0.8784676225250997
},
{
"epoch": 0.8551495016611296,
"grad_norm": 0.343122273683548,
"learning_rate": 5.408202331194406e-07,
"loss": 0.384033203125,
"step": 1287,
"token_acc": 0.8731561616986003
},
{
"epoch": 0.8558139534883721,
"grad_norm": 0.40341123938560486,
"learning_rate": 5.359603632497412e-07,
"loss": 0.37841796875,
"step": 1288,
"token_acc": 0.8741674769773252
},
{
"epoch": 0.8564784053156146,
"grad_norm": 0.44343695044517517,
"learning_rate": 5.311211908392772e-07,
"loss": 0.375244140625,
"step": 1289,
"token_acc": 0.8757120412701676
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.34076252579689026,
"learning_rate": 5.263027383248049e-07,
"loss": 0.376220703125,
"step": 1290,
"token_acc": 0.8759763555365231
},
{
"epoch": 0.8578073089700997,
"grad_norm": 0.47132420539855957,
"learning_rate": 5.215050280470163e-07,
"loss": 0.362548828125,
"step": 1291,
"token_acc": 0.8791573124280953
},
{
"epoch": 0.8584717607973422,
"grad_norm": 0.3350446820259094,
"learning_rate": 5.167280822504278e-07,
"loss": 0.38232421875,
"step": 1292,
"token_acc": 0.8741942497461053
},
{
"epoch": 0.8591362126245847,
"grad_norm": 0.3054424226284027,
"learning_rate": 5.119719230832842e-07,
"loss": 0.383544921875,
"step": 1293,
"token_acc": 0.8726561735504219
},
{
"epoch": 0.8598006644518272,
"grad_norm": 0.35802385210990906,
"learning_rate": 5.072365725974543e-07,
"loss": 0.39501953125,
"step": 1294,
"token_acc": 0.8702259064603595
},
{
"epoch": 0.8604651162790697,
"grad_norm": 0.30999553203582764,
"learning_rate": 5.02522052748326e-07,
"loss": 0.381591796875,
"step": 1295,
"token_acc": 0.873656251652827
},
{
"epoch": 0.8611295681063122,
"grad_norm": 0.3984152376651764,
"learning_rate": 4.978283853947047e-07,
"loss": 0.3662109375,
"step": 1296,
"token_acc": 0.8781994055779164
},
{
"epoch": 0.8617940199335549,
"grad_norm": 0.2798607349395752,
"learning_rate": 4.93155592298718e-07,
"loss": 0.3916015625,
"step": 1297,
"token_acc": 0.8708766713782946
},
{
"epoch": 0.8624584717607974,
"grad_norm": 0.38614749908447266,
"learning_rate": 4.885036951257055e-07,
"loss": 0.3828125,
"step": 1298,
"token_acc": 0.8730406887920056
},
{
"epoch": 0.8631229235880399,
"grad_norm": 0.2836533188819885,
"learning_rate": 4.83872715444128e-07,
"loss": 0.390869140625,
"step": 1299,
"token_acc": 0.8711342830121447
},
{
"epoch": 0.8637873754152824,
"grad_norm": 0.4328776001930237,
"learning_rate": 4.79262674725458e-07,
"loss": 0.38330078125,
"step": 1300,
"token_acc": 0.8731471780923329
},
{
"epoch": 0.8644518272425249,
"grad_norm": 0.3445742130279541,
"learning_rate": 4.7467359434408613e-07,
"loss": 0.38916015625,
"step": 1301,
"token_acc": 0.8719817346732289
},
{
"epoch": 0.8651162790697674,
"grad_norm": 0.2879124879837036,
"learning_rate": 4.7010549557722387e-07,
"loss": 0.378173828125,
"step": 1302,
"token_acc": 0.8750029351930717
},
{
"epoch": 0.86578073089701,
"grad_norm": 0.33957037329673767,
"learning_rate": 4.655583996047969e-07,
"loss": 0.37744140625,
"step": 1303,
"token_acc": 0.8746497665857438
},
{
"epoch": 0.8664451827242525,
"grad_norm": 0.31891846656799316,
"learning_rate": 4.6103232750935534e-07,
"loss": 0.3779296875,
"step": 1304,
"token_acc": 0.8747997745287084
},
{
"epoch": 0.867109634551495,
"grad_norm": 0.30569517612457275,
"learning_rate": 4.5652730027597125e-07,
"loss": 0.375,
"step": 1305,
"token_acc": 0.8756583803462443
},
{
"epoch": 0.8677740863787375,
"grad_norm": 0.32025405764579773,
"learning_rate": 4.5204333879214024e-07,
"loss": 0.383056640625,
"step": 1306,
"token_acc": 0.8730913222037922
},
{
"epoch": 0.86843853820598,
"grad_norm": 0.32102110981941223,
"learning_rate": 4.475804638476916e-07,
"loss": 0.380126953125,
"step": 1307,
"token_acc": 0.8747431122271047
},
{
"epoch": 0.8691029900332226,
"grad_norm": 0.3128818869590759,
"learning_rate": 4.431386961346834e-07,
"loss": 0.384033203125,
"step": 1308,
"token_acc": 0.8728727572695401
},
{
"epoch": 0.8697674418604651,
"grad_norm": 0.33831605315208435,
"learning_rate": 4.387180562473103e-07,
"loss": 0.380859375,
"step": 1309,
"token_acc": 0.8745330294652742
},
{
"epoch": 0.8704318936877077,
"grad_norm": 0.3238200843334198,
"learning_rate": 4.34318564681811e-07,
"loss": 0.37451171875,
"step": 1310,
"token_acc": 0.8761486146224425
},
{
"epoch": 0.8710963455149502,
"grad_norm": 0.39618921279907227,
"learning_rate": 4.299402418363663e-07,
"loss": 0.3779296875,
"step": 1311,
"token_acc": 0.8751816503672283
},
{
"epoch": 0.8717607973421927,
"grad_norm": 0.4341770112514496,
"learning_rate": 4.255831080110134e-07,
"loss": 0.370849609375,
"step": 1312,
"token_acc": 0.8774356936973166
},
{
"epoch": 0.8724252491694352,
"grad_norm": 0.3090074062347412,
"learning_rate": 4.212471834075432e-07,
"loss": 0.3701171875,
"step": 1313,
"token_acc": 0.8776930272760397
},
{
"epoch": 0.8730897009966777,
"grad_norm": 0.316762238740921,
"learning_rate": 4.169324881294096e-07,
"loss": 0.36669921875,
"step": 1314,
"token_acc": 0.8785468260215464
},
{
"epoch": 0.8737541528239202,
"grad_norm": 0.27769917249679565,
"learning_rate": 4.1263904218164064e-07,
"loss": 0.37646484375,
"step": 1315,
"token_acc": 0.8757907413851597
},
{
"epoch": 0.8744186046511628,
"grad_norm": 0.5921364426612854,
"learning_rate": 4.083668654707401e-07,
"loss": 0.39990234375,
"step": 1316,
"token_acc": 0.8684599072693269
},
{
"epoch": 0.8750830564784053,
"grad_norm": 0.27960383892059326,
"learning_rate": 4.041159778045961e-07,
"loss": 0.375,
"step": 1317,
"token_acc": 0.8757776642877988
},
{
"epoch": 0.8757475083056478,
"grad_norm": 0.35360684990882874,
"learning_rate": 3.9988639889239344e-07,
"loss": 0.3740234375,
"step": 1318,
"token_acc": 0.8759175045814628
},
{
"epoch": 0.8764119601328904,
"grad_norm": 0.28389135003089905,
"learning_rate": 3.956781483445166e-07,
"loss": 0.375732421875,
"step": 1319,
"token_acc": 0.8762192928510882
},
{
"epoch": 0.8770764119601329,
"grad_norm": 0.3011752665042877,
"learning_rate": 3.9149124567246066e-07,
"loss": 0.3759765625,
"step": 1320,
"token_acc": 0.8761518185194964
},
{
"epoch": 0.8777408637873754,
"grad_norm": 0.3191356658935547,
"learning_rate": 3.8732571028874566e-07,
"loss": 0.364013671875,
"step": 1321,
"token_acc": 0.8786125958044824
},
{
"epoch": 0.878405315614618,
"grad_norm": 0.4669843018054962,
"learning_rate": 3.8318156150681853e-07,
"loss": 0.37353515625,
"step": 1322,
"token_acc": 0.8761214781552636
},
{
"epoch": 0.8790697674418605,
"grad_norm": 0.3119755983352661,
"learning_rate": 3.7905881854096824e-07,
"loss": 0.382080078125,
"step": 1323,
"token_acc": 0.8743903942895725
},
{
"epoch": 0.879734219269103,
"grad_norm": 0.2912071943283081,
"learning_rate": 3.7495750050623724e-07,
"loss": 0.383544921875,
"step": 1324,
"token_acc": 0.8734287095952878
},
{
"epoch": 0.8803986710963455,
"grad_norm": 0.3796652555465698,
"learning_rate": 3.708776264183322e-07,
"loss": 0.391357421875,
"step": 1325,
"token_acc": 0.8712554734630245
},
{
"epoch": 0.881063122923588,
"grad_norm": 0.40220367908477783,
"learning_rate": 3.668192151935335e-07,
"loss": 0.372314453125,
"step": 1326,
"token_acc": 0.8760620493811198
},
{
"epoch": 0.8817275747508305,
"grad_norm": 0.2922413647174835,
"learning_rate": 3.627822856486074e-07,
"loss": 0.38427734375,
"step": 1327,
"token_acc": 0.8740167505849477
},
{
"epoch": 0.8823920265780731,
"grad_norm": 0.49747946858406067,
"learning_rate": 3.587668565007263e-07,
"loss": 0.37890625,
"step": 1328,
"token_acc": 0.8745099300710351
},
{
"epoch": 0.8830564784053156,
"grad_norm": 0.42985284328460693,
"learning_rate": 3.5477294636737157e-07,
"loss": 0.38037109375,
"step": 1329,
"token_acc": 0.8746712801206689
},
{
"epoch": 0.8837209302325582,
"grad_norm": 0.29122525453567505,
"learning_rate": 3.508005737662523e-07,
"loss": 0.37939453125,
"step": 1330,
"token_acc": 0.87477482644583
},
{
"epoch": 0.8843853820598007,
"grad_norm": 0.31570306420326233,
"learning_rate": 3.468497571152218e-07,
"loss": 0.39404296875,
"step": 1331,
"token_acc": 0.8707401958631593
},
{
"epoch": 0.8850498338870432,
"grad_norm": 0.28482794761657715,
"learning_rate": 3.429205147321879e-07,
"loss": 0.37548828125,
"step": 1332,
"token_acc": 0.875891402249042
},
{
"epoch": 0.8857142857142857,
"grad_norm": 0.3224320411682129,
"learning_rate": 3.390128648350277e-07,
"loss": 0.385986328125,
"step": 1333,
"token_acc": 0.8724705915674312
},
{
"epoch": 0.8863787375415283,
"grad_norm": 0.5030568838119507,
"learning_rate": 3.3512682554150857e-07,
"loss": 0.380126953125,
"step": 1334,
"token_acc": 0.8735955505406342
},
{
"epoch": 0.8870431893687708,
"grad_norm": 0.4163050651550293,
"learning_rate": 3.312624148692001e-07,
"loss": 0.383056640625,
"step": 1335,
"token_acc": 0.8739466357081382
},
{
"epoch": 0.8877076411960133,
"grad_norm": 0.28100189566612244,
"learning_rate": 3.274196507353866e-07,
"loss": 0.371826171875,
"step": 1336,
"token_acc": 0.8768274281602974
},
{
"epoch": 0.8883720930232558,
"grad_norm": 0.3007696568965912,
"learning_rate": 3.2359855095699444e-07,
"loss": 0.35888671875,
"step": 1337,
"token_acc": 0.8808602913441478
},
{
"epoch": 0.8890365448504983,
"grad_norm": 0.3327014446258545,
"learning_rate": 3.197991332505018e-07,
"loss": 0.378173828125,
"step": 1338,
"token_acc": 0.8761005351254872
},
{
"epoch": 0.8897009966777408,
"grad_norm": 0.34877797961235046,
"learning_rate": 3.1602141523185414e-07,
"loss": 0.376708984375,
"step": 1339,
"token_acc": 0.875227462745291
},
{
"epoch": 0.8903654485049833,
"grad_norm": 0.29543280601501465,
"learning_rate": 3.1226541441639114e-07,
"loss": 0.369873046875,
"step": 1340,
"token_acc": 0.8783349380027714
},
{
"epoch": 0.891029900332226,
"grad_norm": 0.3245175778865814,
"learning_rate": 3.0853114821876193e-07,
"loss": 0.401123046875,
"step": 1341,
"token_acc": 0.8676733206125544
},
{
"epoch": 0.8916943521594685,
"grad_norm": 0.2916678190231323,
"learning_rate": 3.0481863395283807e-07,
"loss": 0.383056640625,
"step": 1342,
"token_acc": 0.8734475975472302
},
{
"epoch": 0.892358803986711,
"grad_norm": 0.34900346398353577,
"learning_rate": 3.011278888316421e-07,
"loss": 0.386474609375,
"step": 1343,
"token_acc": 0.8732377106379019
},
{
"epoch": 0.8930232558139535,
"grad_norm": 0.29604265093803406,
"learning_rate": 2.9745892996726535e-07,
"loss": 0.3955078125,
"step": 1344,
"token_acc": 0.8708308376244344
},
{
"epoch": 0.893687707641196,
"grad_norm": 0.3510962426662445,
"learning_rate": 2.938117743707847e-07,
"loss": 0.37841796875,
"step": 1345,
"token_acc": 0.8746022741556626
},
{
"epoch": 0.8943521594684385,
"grad_norm": 0.38254493474960327,
"learning_rate": 2.901864389521869e-07,
"loss": 0.37890625,
"step": 1346,
"token_acc": 0.8743936573579507
},
{
"epoch": 0.8950166112956811,
"grad_norm": 0.46308013796806335,
"learning_rate": 2.8658294052029246e-07,
"loss": 0.36865234375,
"step": 1347,
"token_acc": 0.877563561574292
},
{
"epoch": 0.8956810631229236,
"grad_norm": 0.41284096240997314,
"learning_rate": 2.8300129578267164e-07,
"loss": 0.38916015625,
"step": 1348,
"token_acc": 0.8717849869863984
},
{
"epoch": 0.8963455149501661,
"grad_norm": 0.36988887190818787,
"learning_rate": 2.794415213455709e-07,
"loss": 0.38818359375,
"step": 1349,
"token_acc": 0.8714112030664497
},
{
"epoch": 0.8970099667774086,
"grad_norm": 0.30463045835494995,
"learning_rate": 2.759036337138382e-07,
"loss": 0.384521484375,
"step": 1350,
"token_acc": 0.8729870218489023
},
{
"epoch": 0.8976744186046511,
"grad_norm": 0.3195222020149231,
"learning_rate": 2.723876492908406e-07,
"loss": 0.389404296875,
"step": 1351,
"token_acc": 0.8715461150970314
},
{
"epoch": 0.8983388704318936,
"grad_norm": 0.425835520029068,
"learning_rate": 2.6889358437839074e-07,
"loss": 0.365234375,
"step": 1352,
"token_acc": 0.8779056917176065
},
{
"epoch": 0.8990033222591363,
"grad_norm": 0.36828169226646423,
"learning_rate": 2.654214551766759e-07,
"loss": 0.3671875,
"step": 1353,
"token_acc": 0.8780839997151766
},
{
"epoch": 0.8996677740863788,
"grad_norm": 0.2974161207675934,
"learning_rate": 2.619712777841743e-07,
"loss": 0.3740234375,
"step": 1354,
"token_acc": 0.8758527779578423
},
{
"epoch": 0.9003322259136213,
"grad_norm": 0.3034202754497528,
"learning_rate": 2.5854306819758647e-07,
"loss": 0.374267578125,
"step": 1355,
"token_acc": 0.8768627711724564
},
{
"epoch": 0.9009966777408638,
"grad_norm": 0.3092987835407257,
"learning_rate": 2.551368423117601e-07,
"loss": 0.381591796875,
"step": 1356,
"token_acc": 0.8738119371194147
},
{
"epoch": 0.9016611295681063,
"grad_norm": 0.3701721429824829,
"learning_rate": 2.517526159196171e-07,
"loss": 0.38134765625,
"step": 1357,
"token_acc": 0.873053678535756
},
{
"epoch": 0.9023255813953488,
"grad_norm": 0.3825627863407135,
"learning_rate": 2.4839040471207386e-07,
"loss": 0.36962890625,
"step": 1358,
"token_acc": 0.8784785814874531
},
{
"epoch": 0.9029900332225914,
"grad_norm": 0.29752489924430847,
"learning_rate": 2.4505022427797843e-07,
"loss": 0.381591796875,
"step": 1359,
"token_acc": 0.8728851190466216
},
{
"epoch": 0.9036544850498339,
"grad_norm": 0.31795910000801086,
"learning_rate": 2.4173209010403374e-07,
"loss": 0.373779296875,
"step": 1360,
"token_acc": 0.8762188627570316
},
{
"epoch": 0.9043189368770764,
"grad_norm": 0.3094518482685089,
"learning_rate": 2.3843601757472193e-07,
"loss": 0.380126953125,
"step": 1361,
"token_acc": 0.8745120278396085
},
{
"epoch": 0.9049833887043189,
"grad_norm": 0.27690577507019043,
"learning_rate": 2.3516202197223892e-07,
"loss": 0.371826171875,
"step": 1362,
"token_acc": 0.8774561899623641
},
{
"epoch": 0.9056478405315614,
"grad_norm": 0.4556111991405487,
"learning_rate": 2.319101184764222e-07,
"loss": 0.386962890625,
"step": 1363,
"token_acc": 0.8721980004219637
},
{
"epoch": 0.906312292358804,
"grad_norm": 0.3109835684299469,
"learning_rate": 2.286803221646766e-07,
"loss": 0.39892578125,
"step": 1364,
"token_acc": 0.8687639809744228
},
{
"epoch": 0.9069767441860465,
"grad_norm": 0.35494211316108704,
"learning_rate": 2.2547264801190904e-07,
"loss": 0.38037109375,
"step": 1365,
"token_acc": 0.8745361044960646
},
{
"epoch": 0.9076411960132891,
"grad_norm": 0.32149437069892883,
"learning_rate": 2.222871108904584e-07,
"loss": 0.367431640625,
"step": 1366,
"token_acc": 0.878311461998417
},
{
"epoch": 0.9083056478405316,
"grad_norm": 0.3397005498409271,
"learning_rate": 2.1912372557002404e-07,
"loss": 0.395751953125,
"step": 1367,
"token_acc": 0.8687993679998295
},
{
"epoch": 0.9089700996677741,
"grad_norm": 0.4117109179496765,
"learning_rate": 2.1598250671759802e-07,
"loss": 0.399169921875,
"step": 1368,
"token_acc": 0.8689159996311729
},
{
"epoch": 0.9096345514950166,
"grad_norm": 0.28853103518486023,
"learning_rate": 2.128634688973996e-07,
"loss": 0.380859375,
"step": 1369,
"token_acc": 0.8738052555685764
},
{
"epoch": 0.9102990033222591,
"grad_norm": 0.3301659822463989,
"learning_rate": 2.0976662657080594e-07,
"loss": 0.38330078125,
"step": 1370,
"token_acc": 0.8730482484606659
},
{
"epoch": 0.9109634551495016,
"grad_norm": 0.5126007795333862,
"learning_rate": 2.066919940962836e-07,
"loss": 0.38037109375,
"step": 1371,
"token_acc": 0.8741626388068127
},
{
"epoch": 0.9116279069767442,
"grad_norm": 0.3557790517807007,
"learning_rate": 2.0363958572932495e-07,
"loss": 0.368408203125,
"step": 1372,
"token_acc": 0.8776367255364697
},
{
"epoch": 0.9122923588039867,
"grad_norm": 0.6232784390449524,
"learning_rate": 2.0060941562237923e-07,
"loss": 0.376953125,
"step": 1373,
"token_acc": 0.8756102461306816
},
{
"epoch": 0.9129568106312292,
"grad_norm": 0.3251217305660248,
"learning_rate": 1.9760149782478976e-07,
"loss": 0.381103515625,
"step": 1374,
"token_acc": 0.8736269346196583
},
{
"epoch": 0.9136212624584718,
"grad_norm": 0.263487845659256,
"learning_rate": 1.9461584628272633e-07,
"loss": 0.375244140625,
"step": 1375,
"token_acc": 0.8753018952273867
},
{
"epoch": 0.9142857142857143,
"grad_norm": 0.3114076256752014,
"learning_rate": 1.9165247483912243e-07,
"loss": 0.36962890625,
"step": 1376,
"token_acc": 0.8776292507087712
},
{
"epoch": 0.9149501661129568,
"grad_norm": 0.2793143391609192,
"learning_rate": 1.887113972336091e-07,
"loss": 0.3681640625,
"step": 1377,
"token_acc": 0.8777658774836039
},
{
"epoch": 0.9156146179401994,
"grad_norm": 0.2802167534828186,
"learning_rate": 1.8579262710245184e-07,
"loss": 0.393310546875,
"step": 1378,
"token_acc": 0.8707697280227205
},
{
"epoch": 0.9162790697674419,
"grad_norm": 0.30410581827163696,
"learning_rate": 1.8289617797849045e-07,
"loss": 0.383056640625,
"step": 1379,
"token_acc": 0.8738370594476301
},
{
"epoch": 0.9169435215946844,
"grad_norm": 0.3064866065979004,
"learning_rate": 1.8002206329107097e-07,
"loss": 0.38525390625,
"step": 1380,
"token_acc": 0.8735168523477396
},
{
"epoch": 0.9176079734219269,
"grad_norm": 0.2896842956542969,
"learning_rate": 1.7717029636598714e-07,
"loss": 0.363525390625,
"step": 1381,
"token_acc": 0.8786317411045219
},
{
"epoch": 0.9182724252491694,
"grad_norm": 0.3583877384662628,
"learning_rate": 1.7434089042541791e-07,
"loss": 0.385498046875,
"step": 1382,
"token_acc": 0.8727720863717094
},
{
"epoch": 0.9189368770764119,
"grad_norm": 0.28602802753448486,
"learning_rate": 1.715338585878662e-07,
"loss": 0.375732421875,
"step": 1383,
"token_acc": 0.8759104169311128
},
{
"epoch": 0.9196013289036545,
"grad_norm": 0.4100158214569092,
"learning_rate": 1.6874921386809572e-07,
"loss": 0.384765625,
"step": 1384,
"token_acc": 0.8728298537065359
},
{
"epoch": 0.920265780730897,
"grad_norm": 0.3555079400539398,
"learning_rate": 1.6598696917707492e-07,
"loss": 0.385009765625,
"step": 1385,
"token_acc": 0.8724703372883615
},
{
"epoch": 0.9209302325581395,
"grad_norm": 0.2780778706073761,
"learning_rate": 1.63247137321913e-07,
"loss": 0.376708984375,
"step": 1386,
"token_acc": 0.8751757381540513
},
{
"epoch": 0.9215946843853821,
"grad_norm": 0.2802024185657501,
"learning_rate": 1.605297310058046e-07,
"loss": 0.380615234375,
"step": 1387,
"token_acc": 0.8743334654540756
},
{
"epoch": 0.9222591362126246,
"grad_norm": 0.446336030960083,
"learning_rate": 1.578347628279664e-07,
"loss": 0.373046875,
"step": 1388,
"token_acc": 0.8765628282604438
},
{
"epoch": 0.9229235880398671,
"grad_norm": 0.3086842894554138,
"learning_rate": 1.5516224528358103e-07,
"loss": 0.38623046875,
"step": 1389,
"token_acc": 0.8722976329791634
},
{
"epoch": 0.9235880398671097,
"grad_norm": 0.302816778421402,
"learning_rate": 1.5251219076374114e-07,
"loss": 0.39306640625,
"step": 1390,
"token_acc": 0.8700126089763742
},
{
"epoch": 0.9242524916943522,
"grad_norm": 0.39176246523857117,
"learning_rate": 1.4988461155538813e-07,
"loss": 0.396484375,
"step": 1391,
"token_acc": 0.8694319745150793
},
{
"epoch": 0.9249169435215947,
"grad_norm": 0.2719256579875946,
"learning_rate": 1.4727951984125688e-07,
"loss": 0.386962890625,
"step": 1392,
"token_acc": 0.8718147325484581
},
{
"epoch": 0.9255813953488372,
"grad_norm": 0.48872116208076477,
"learning_rate": 1.4469692769982057e-07,
"loss": 0.368408203125,
"step": 1393,
"token_acc": 0.8781359035213054
},
{
"epoch": 0.9262458471760797,
"grad_norm": 0.31115520000457764,
"learning_rate": 1.4213684710523257e-07,
"loss": 0.3798828125,
"step": 1394,
"token_acc": 0.8740537002780212
},
{
"epoch": 0.9269102990033222,
"grad_norm": 0.2896758019924164,
"learning_rate": 1.3959928992727078e-07,
"loss": 0.385498046875,
"step": 1395,
"token_acc": 0.8723670574825491
},
{
"epoch": 0.9275747508305647,
"grad_norm": 0.32626035809516907,
"learning_rate": 1.3708426793128615e-07,
"loss": 0.383056640625,
"step": 1396,
"token_acc": 0.8725020495523114
},
{
"epoch": 0.9282392026578073,
"grad_norm": 0.3293090760707855,
"learning_rate": 1.345917927781426e-07,
"loss": 0.389404296875,
"step": 1397,
"token_acc": 0.8719327185935474
},
{
"epoch": 0.9289036544850499,
"grad_norm": 0.3028724491596222,
"learning_rate": 1.321218760241688e-07,
"loss": 0.386474609375,
"step": 1398,
"token_acc": 0.8721158611774174
},
{
"epoch": 0.9295681063122924,
"grad_norm": 0.2943212389945984,
"learning_rate": 1.2967452912109878e-07,
"loss": 0.383056640625,
"step": 1399,
"token_acc": 0.872888207173237
},
{
"epoch": 0.9302325581395349,
"grad_norm": 0.32148775458335876,
"learning_rate": 1.272497634160247e-07,
"loss": 0.376220703125,
"step": 1400,
"token_acc": 0.8750666746344238
},
{
"epoch": 0.9308970099667774,
"grad_norm": 0.3126775324344635,
"learning_rate": 1.2484759015133906e-07,
"loss": 0.35693359375,
"step": 1401,
"token_acc": 0.8815815193829603
},
{
"epoch": 0.9315614617940199,
"grad_norm": 0.30983248353004456,
"learning_rate": 1.2246802046468553e-07,
"loss": 0.379150390625,
"step": 1402,
"token_acc": 0.8753562041141946
},
{
"epoch": 0.9322259136212625,
"grad_norm": 0.588629961013794,
"learning_rate": 1.201110653889076e-07,
"loss": 0.37060546875,
"step": 1403,
"token_acc": 0.8773083623932978
},
{
"epoch": 0.932890365448505,
"grad_norm": 0.29358670115470886,
"learning_rate": 1.1777673585199434e-07,
"loss": 0.381103515625,
"step": 1404,
"token_acc": 0.8743539051787049
},
{
"epoch": 0.9335548172757475,
"grad_norm": 0.3109745979309082,
"learning_rate": 1.1546504267703373e-07,
"loss": 0.3896484375,
"step": 1405,
"token_acc": 0.87122350951327
},
{
"epoch": 0.93421926910299,
"grad_norm": 0.37773677706718445,
"learning_rate": 1.1317599658215938e-07,
"loss": 0.390869140625,
"step": 1406,
"token_acc": 0.8709489433768721
},
{
"epoch": 0.9348837209302325,
"grad_norm": 0.3383554220199585,
"learning_rate": 1.1090960818050334e-07,
"loss": 0.375,
"step": 1407,
"token_acc": 0.8757682369201689
},
{
"epoch": 0.935548172757475,
"grad_norm": 0.3804529011249542,
"learning_rate": 1.0866588798014277e-07,
"loss": 0.372314453125,
"step": 1408,
"token_acc": 0.8764581480924175
},
{
"epoch": 0.9362126245847177,
"grad_norm": 0.3397970497608185,
"learning_rate": 1.0644484638405839e-07,
"loss": 0.3896484375,
"step": 1409,
"token_acc": 0.871045389634286
},
{
"epoch": 0.9368770764119602,
"grad_norm": 0.4976058602333069,
"learning_rate": 1.0424649369007778e-07,
"loss": 0.388427734375,
"step": 1410,
"token_acc": 0.8725011091206217
},
{
"epoch": 0.9375415282392027,
"grad_norm": 0.29305267333984375,
"learning_rate": 1.0207084009083379e-07,
"loss": 0.377685546875,
"step": 1411,
"token_acc": 0.8750520366737825
},
{
"epoch": 0.9382059800664452,
"grad_norm": 0.2585095763206482,
"learning_rate": 9.991789567371513e-08,
"loss": 0.37744140625,
"step": 1412,
"token_acc": 0.874342532800016
},
{
"epoch": 0.9388704318936877,
"grad_norm": 0.31076642870903015,
"learning_rate": 9.778767042081972e-08,
"loss": 0.376708984375,
"step": 1413,
"token_acc": 0.8758435061428568
},
{
"epoch": 0.9395348837209302,
"grad_norm": 0.2998356223106384,
"learning_rate": 9.568017420890697e-08,
"loss": 0.385986328125,
"step": 1414,
"token_acc": 0.8722238079741975
},
{
"epoch": 0.9401993355481728,
"grad_norm": 0.3763675093650818,
"learning_rate": 9.359541680935447e-08,
"loss": 0.373291015625,
"step": 1415,
"token_acc": 0.8759384131390651
},
{
"epoch": 0.9408637873754153,
"grad_norm": 0.26735082268714905,
"learning_rate": 9.15334078881136e-08,
"loss": 0.3740234375,
"step": 1416,
"token_acc": 0.8765960487822171
},
{
"epoch": 0.9415282392026578,
"grad_norm": 0.6305362582206726,
"learning_rate": 8.949415700565844e-08,
"loss": 0.37646484375,
"step": 1417,
"token_acc": 0.8753774189152733
},
{
"epoch": 0.9421926910299003,
"grad_norm": 0.37995344400405884,
"learning_rate": 8.747767361694859e-08,
"loss": 0.392822265625,
"step": 1418,
"token_acc": 0.8702797785531599
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.3863162696361542,
"learning_rate": 8.548396707138307e-08,
"loss": 0.374755859375,
"step": 1419,
"token_acc": 0.8756256780365944
},
{
"epoch": 0.9435215946843853,
"grad_norm": 0.3179466426372528,
"learning_rate": 8.351304661275428e-08,
"loss": 0.385498046875,
"step": 1420,
"token_acc": 0.872511910982866
},
{
"epoch": 0.9441860465116279,
"grad_norm": 3.177119731903076,
"learning_rate": 8.156492137920857e-08,
"loss": 0.378662109375,
"step": 1421,
"token_acc": 0.874533316945012
},
{
"epoch": 0.9448504983388705,
"grad_norm": 0.28625378012657166,
"learning_rate": 7.963960040320184e-08,
"loss": 0.369384765625,
"step": 1422,
"token_acc": 0.8776342868589877
},
{
"epoch": 0.945514950166113,
"grad_norm": 0.28517627716064453,
"learning_rate": 7.773709261145901e-08,
"loss": 0.38427734375,
"step": 1423,
"token_acc": 0.8738082949621506
},
{
"epoch": 0.9461794019933555,
"grad_norm": 0.34828436374664307,
"learning_rate": 7.58574068249307e-08,
"loss": 0.373291015625,
"step": 1424,
"token_acc": 0.8758578645516103
},
{
"epoch": 0.946843853820598,
"grad_norm": 0.4418569505214691,
"learning_rate": 7.400055175875609e-08,
"loss": 0.39013671875,
"step": 1425,
"token_acc": 0.870799168882236
},
{
"epoch": 0.9475083056478405,
"grad_norm": 0.32560256123542786,
"learning_rate": 7.21665360222179e-08,
"loss": 0.38671875,
"step": 1426,
"token_acc": 0.8724642832256884
},
{
"epoch": 0.948172757475083,
"grad_norm": 0.7012158632278442,
"learning_rate": 7.035536811870469e-08,
"loss": 0.38623046875,
"step": 1427,
"token_acc": 0.872270714862182
},
{
"epoch": 0.9488372093023256,
"grad_norm": 0.5078062415122986,
"learning_rate": 6.856705644567197e-08,
"loss": 0.374267578125,
"step": 1428,
"token_acc": 0.8761808479718616
},
{
"epoch": 0.9495016611295681,
"grad_norm": 0.29933974146842957,
"learning_rate": 6.680160929460389e-08,
"loss": 0.376953125,
"step": 1429,
"token_acc": 0.874678032896975
},
{
"epoch": 0.9501661129568106,
"grad_norm": 0.32025569677352905,
"learning_rate": 6.505903485097054e-08,
"loss": 0.385498046875,
"step": 1430,
"token_acc": 0.8725670198361429
},
{
"epoch": 0.9508305647840531,
"grad_norm": 0.2978005111217499,
"learning_rate": 6.333934119419516e-08,
"loss": 0.3740234375,
"step": 1431,
"token_acc": 0.8768291003424324
},
{
"epoch": 0.9514950166112957,
"grad_norm": 0.36393991112709045,
"learning_rate": 6.16425362976153e-08,
"loss": 0.380859375,
"step": 1432,
"token_acc": 0.8740101476293308
},
{
"epoch": 0.9521594684385382,
"grad_norm": 0.2956557273864746,
"learning_rate": 5.996862802844172e-08,
"loss": 0.395751953125,
"step": 1433,
"token_acc": 0.8699019810976709
},
{
"epoch": 0.9528239202657808,
"grad_norm": 0.2986431121826172,
"learning_rate": 5.831762414772901e-08,
"loss": 0.3671875,
"step": 1434,
"token_acc": 0.8783788833498961
},
{
"epoch": 0.9534883720930233,
"grad_norm": 0.31039679050445557,
"learning_rate": 5.6689532310333916e-08,
"loss": 0.389404296875,
"step": 1435,
"token_acc": 0.8721187268287256
},
{
"epoch": 0.9541528239202658,
"grad_norm": 0.3323787450790405,
"learning_rate": 5.508436006488205e-08,
"loss": 0.37890625,
"step": 1436,
"token_acc": 0.8744001762373645
},
{
"epoch": 0.9548172757475083,
"grad_norm": 0.30805689096450806,
"learning_rate": 5.35021148537318e-08,
"loss": 0.375,
"step": 1437,
"token_acc": 0.8763286377213599
},
{
"epoch": 0.9554817275747508,
"grad_norm": 0.43341490626335144,
"learning_rate": 5.194280401294383e-08,
"loss": 0.406494140625,
"step": 1438,
"token_acc": 0.8667193839765013
},
{
"epoch": 0.9561461794019933,
"grad_norm": 0.34538954496383667,
"learning_rate": 5.0406434772239946e-08,
"loss": 0.366943359375,
"step": 1439,
"token_acc": 0.8789954498008108
},
{
"epoch": 0.9568106312292359,
"grad_norm": 0.3387588560581207,
"learning_rate": 4.889301425497539e-08,
"loss": 0.369384765625,
"step": 1440,
"token_acc": 0.8774138790214302
},
{
"epoch": 0.9574750830564784,
"grad_norm": 0.3314010500907898,
"learning_rate": 4.740254947810441e-08,
"loss": 0.38671875,
"step": 1441,
"token_acc": 0.8725674177639021
},
{
"epoch": 0.958139534883721,
"grad_norm": 0.41329798102378845,
"learning_rate": 4.593504735214693e-08,
"loss": 0.376708984375,
"step": 1442,
"token_acc": 0.8754655843763558
},
{
"epoch": 0.9588039867109635,
"grad_norm": 0.30026888847351074,
"learning_rate": 4.4490514681156396e-08,
"loss": 0.371337890625,
"step": 1443,
"token_acc": 0.8770908944445291
},
{
"epoch": 0.959468438538206,
"grad_norm": 0.3254265785217285,
"learning_rate": 4.306895816268863e-08,
"loss": 0.379150390625,
"step": 1444,
"token_acc": 0.8746045558019201
},
{
"epoch": 0.9601328903654485,
"grad_norm": 0.2955619990825653,
"learning_rate": 4.167038438777138e-08,
"loss": 0.382080078125,
"step": 1445,
"token_acc": 0.8736097582888591
},
{
"epoch": 0.9607973421926911,
"grad_norm": 0.2893226444721222,
"learning_rate": 4.029479984087259e-08,
"loss": 0.384521484375,
"step": 1446,
"token_acc": 0.8733503644159181
},
{
"epoch": 0.9614617940199336,
"grad_norm": 0.3477460741996765,
"learning_rate": 3.894221089987216e-08,
"loss": 0.39208984375,
"step": 1447,
"token_acc": 0.870546825360361
},
{
"epoch": 0.9621262458471761,
"grad_norm": 0.5195234417915344,
"learning_rate": 3.761262383603026e-08,
"loss": 0.410400390625,
"step": 1448,
"token_acc": 0.8669085525447312
},
{
"epoch": 0.9627906976744186,
"grad_norm": 0.33097296953201294,
"learning_rate": 3.6306044813958496e-08,
"loss": 0.3818359375,
"step": 1449,
"token_acc": 0.8740250865585799
},
{
"epoch": 0.9634551495016611,
"grad_norm": 0.42080700397491455,
"learning_rate": 3.5022479891593244e-08,
"loss": 0.40771484375,
"step": 1450,
"token_acc": 0.8666994068807355
},
{
"epoch": 0.9641196013289036,
"grad_norm": 0.3253667652606964,
"learning_rate": 3.3761935020166224e-08,
"loss": 0.374755859375,
"step": 1451,
"token_acc": 0.8763803044203223
},
{
"epoch": 0.9647840531561461,
"grad_norm": 0.530604362487793,
"learning_rate": 3.2524416044176223e-08,
"loss": 0.374267578125,
"step": 1452,
"token_acc": 0.876452379539064
},
{
"epoch": 0.9654485049833887,
"grad_norm": 0.30972152948379517,
"learning_rate": 3.130992870136296e-08,
"loss": 0.376953125,
"step": 1453,
"token_acc": 0.8750417070541756
},
{
"epoch": 0.9661129568106313,
"grad_norm": 0.299221932888031,
"learning_rate": 3.011847862268158e-08,
"loss": 0.390380859375,
"step": 1454,
"token_acc": 0.8715677833802769
},
{
"epoch": 0.9667774086378738,
"grad_norm": 0.5703691244125366,
"learning_rate": 2.895007133227268e-08,
"loss": 0.369873046875,
"step": 1455,
"token_acc": 0.8779134549510433
},
{
"epoch": 0.9674418604651163,
"grad_norm": 0.2774394750595093,
"learning_rate": 2.7804712247441744e-08,
"loss": 0.368408203125,
"step": 1456,
"token_acc": 0.8787926549686976
},
{
"epoch": 0.9681063122923588,
"grad_norm": 0.30305591225624084,
"learning_rate": 2.6682406678630867e-08,
"loss": 0.376708984375,
"step": 1457,
"token_acc": 0.8753114331048376
},
{
"epoch": 0.9687707641196013,
"grad_norm": 0.31456899642944336,
"learning_rate": 2.55831598293943e-08,
"loss": 0.38232421875,
"step": 1458,
"token_acc": 0.8731603781064324
},
{
"epoch": 0.9694352159468439,
"grad_norm": 0.5278499126434326,
"learning_rate": 2.4506976796374595e-08,
"loss": 0.378173828125,
"step": 1459,
"token_acc": 0.8756903259893628
},
{
"epoch": 0.9700996677740864,
"grad_norm": 0.34070995450019836,
"learning_rate": 2.3453862569280393e-08,
"loss": 0.36962890625,
"step": 1460,
"token_acc": 0.877277051685954
},
{
"epoch": 0.9707641196013289,
"grad_norm": 0.29770493507385254,
"learning_rate": 2.2423822030861462e-08,
"loss": 0.396484375,
"step": 1461,
"token_acc": 0.870039044248358
},
{
"epoch": 0.9714285714285714,
"grad_norm": 0.39425668120384216,
"learning_rate": 2.1416859956887026e-08,
"loss": 0.4013671875,
"step": 1462,
"token_acc": 0.8684328431336453
},
{
"epoch": 0.9720930232558139,
"grad_norm": 0.3682233989238739,
"learning_rate": 2.0432981016122454e-08,
"loss": 0.378662109375,
"step": 1463,
"token_acc": 0.8741033022747805
},
{
"epoch": 0.9727574750830564,
"grad_norm": 0.27213603258132935,
"learning_rate": 1.9472189770309846e-08,
"loss": 0.393310546875,
"step": 1464,
"token_acc": 0.8706905738292409
},
{
"epoch": 0.973421926910299,
"grad_norm": 0.4639448821544647,
"learning_rate": 1.8534490674144146e-08,
"loss": 0.37060546875,
"step": 1465,
"token_acc": 0.8770055644781882
},
{
"epoch": 0.9740863787375416,
"grad_norm": 0.32525479793548584,
"learning_rate": 1.7619888075254833e-08,
"loss": 0.375732421875,
"step": 1466,
"token_acc": 0.8754263123310101
},
{
"epoch": 0.9747508305647841,
"grad_norm": 0.3301774859428406,
"learning_rate": 1.6728386214184268e-08,
"loss": 0.40234375,
"step": 1467,
"token_acc": 0.8671453338684005
},
{
"epoch": 0.9754152823920266,
"grad_norm": 0.3300977945327759,
"learning_rate": 1.585998922436882e-08,
"loss": 0.3818359375,
"step": 1468,
"token_acc": 0.8733268782626322
},
{
"epoch": 0.9760797342192691,
"grad_norm": 0.6083729863166809,
"learning_rate": 1.5014701132118892e-08,
"loss": 0.3720703125,
"step": 1469,
"token_acc": 0.8774909729952703
},
{
"epoch": 0.9767441860465116,
"grad_norm": 0.31625863909721375,
"learning_rate": 1.4192525856602247e-08,
"loss": 0.37353515625,
"step": 1470,
"token_acc": 0.8761668691962469
},
{
"epoch": 0.9774086378737542,
"grad_norm": 0.3311670124530792,
"learning_rate": 1.339346720982293e-08,
"loss": 0.38671875,
"step": 1471,
"token_acc": 0.8736315822959303
},
{
"epoch": 0.9780730897009967,
"grad_norm": 0.31296882033348083,
"learning_rate": 1.2617528896605724e-08,
"loss": 0.38427734375,
"step": 1472,
"token_acc": 0.8730298579405933
},
{
"epoch": 0.9787375415282392,
"grad_norm": 0.2854900062084198,
"learning_rate": 1.1864714514577269e-08,
"loss": 0.38525390625,
"step": 1473,
"token_acc": 0.872162147149479
},
{
"epoch": 0.9794019933554817,
"grad_norm": 0.27861928939819336,
"learning_rate": 1.1135027554152188e-08,
"loss": 0.37109375,
"step": 1474,
"token_acc": 0.8781943064438344
},
{
"epoch": 0.9800664451827242,
"grad_norm": 0.32604750990867615,
"learning_rate": 1.0428471398513663e-08,
"loss": 0.385498046875,
"step": 1475,
"token_acc": 0.8734655179066549
},
{
"epoch": 0.9807308970099667,
"grad_norm": 0.29312658309936523,
"learning_rate": 9.745049323600098e-09,
"loss": 0.381591796875,
"step": 1476,
"token_acc": 0.8739668313525348
},
{
"epoch": 0.9813953488372092,
"grad_norm": 0.29105284810066223,
"learning_rate": 9.084764498087928e-09,
"loss": 0.384765625,
"step": 1477,
"token_acc": 0.8726608728694136
},
{
"epoch": 0.9820598006644519,
"grad_norm": 0.2852209806442261,
"learning_rate": 8.447619983379952e-09,
"loss": 0.385009765625,
"step": 1478,
"token_acc": 0.8719428998865484
},
{
"epoch": 0.9827242524916944,
"grad_norm": 0.30840080976486206,
"learning_rate": 7.833618733587012e-09,
"loss": 0.377197265625,
"step": 1479,
"token_acc": 0.8748723848641325
},
{
"epoch": 0.9833887043189369,
"grad_norm": 0.36424270272254944,
"learning_rate": 7.24276359551801e-09,
"loss": 0.385986328125,
"step": 1480,
"token_acc": 0.8732768110767236
},
{
"epoch": 0.9840531561461794,
"grad_norm": 0.2770603895187378,
"learning_rate": 6.6750573086649116e-09,
"loss": 0.380859375,
"step": 1481,
"token_acc": 0.8747444478980155
},
{
"epoch": 0.9847176079734219,
"grad_norm": 0.3414585292339325,
"learning_rate": 6.130502505190538e-09,
"loss": 0.375,
"step": 1482,
"token_acc": 0.8750408707759443
},
{
"epoch": 0.9853820598006644,
"grad_norm": 0.46800869703292847,
"learning_rate": 5.609101709914688e-09,
"loss": 0.386962890625,
"step": 1483,
"token_acc": 0.872683679819398
},
{
"epoch": 0.986046511627907,
"grad_norm": 0.287490576505661,
"learning_rate": 5.110857340305808e-09,
"loss": 0.37109375,
"step": 1484,
"token_acc": 0.8766024418055514
},
{
"epoch": 0.9867109634551495,
"grad_norm": 0.49029654264450073,
"learning_rate": 4.635771706467673e-09,
"loss": 0.4013671875,
"step": 1485,
"token_acc": 0.86806617460139
},
{
"epoch": 0.987375415282392,
"grad_norm": 0.28298091888427734,
"learning_rate": 4.183847011127174e-09,
"loss": 0.387939453125,
"step": 1486,
"token_acc": 0.8721849193146722
},
{
"epoch": 0.9880398671096345,
"grad_norm": 0.28193357586860657,
"learning_rate": 3.7550853496282066e-09,
"loss": 0.371337890625,
"step": 1487,
"token_acc": 0.8766369308824696
},
{
"epoch": 0.988704318936877,
"grad_norm": 0.3200041353702545,
"learning_rate": 3.349488709917803e-09,
"loss": 0.397705078125,
"step": 1488,
"token_acc": 0.8688498239075328
},
{
"epoch": 0.9893687707641196,
"grad_norm": 0.46333765983581543,
"learning_rate": 2.9670589725389052e-09,
"loss": 0.37060546875,
"step": 1489,
"token_acc": 0.8766124450820014
},
{
"epoch": 0.9900332225913622,
"grad_norm": 0.35854655504226685,
"learning_rate": 2.6077979106226003e-09,
"loss": 0.3876953125,
"step": 1490,
"token_acc": 0.8717099868396596
},
{
"epoch": 0.9906976744186047,
"grad_norm": 0.29480305314064026,
"learning_rate": 2.27170718987757e-09,
"loss": 0.384033203125,
"step": 1491,
"token_acc": 0.8725521139849924
},
{
"epoch": 0.9913621262458472,
"grad_norm": 0.36185455322265625,
"learning_rate": 1.958788368583986e-09,
"loss": 0.3837890625,
"step": 1492,
"token_acc": 0.8732850984695618
},
{
"epoch": 0.9920265780730897,
"grad_norm": 0.35521650314331055,
"learning_rate": 1.6690428975857375e-09,
"loss": 0.380615234375,
"step": 1493,
"token_acc": 0.8742024707297091
},
{
"epoch": 0.9926910299003322,
"grad_norm": 0.4131629168987274,
"learning_rate": 1.4024721202832158e-09,
"loss": 0.378173828125,
"step": 1494,
"token_acc": 0.8751080733762644
},
{
"epoch": 0.9933554817275747,
"grad_norm": 0.4193948209285736,
"learning_rate": 1.1590772726294274e-09,
"loss": 0.38720703125,
"step": 1495,
"token_acc": 0.8722148817572412
},
{
"epoch": 0.9940199335548173,
"grad_norm": 0.3367873728275299,
"learning_rate": 9.388594831200026e-10,
"loss": 0.398193359375,
"step": 1496,
"token_acc": 0.869617563857203
},
{
"epoch": 0.9946843853820598,
"grad_norm": 0.3175390958786011,
"learning_rate": 7.41819772792085e-10,
"loss": 0.37353515625,
"step": 1497,
"token_acc": 0.8767354821143514
},
{
"epoch": 0.9953488372093023,
"grad_norm": 0.2700347900390625,
"learning_rate": 5.679590552182257e-10,
"loss": 0.38427734375,
"step": 1498,
"token_acc": 0.8722841141234722
},
{
"epoch": 0.9960132890365448,
"grad_norm": 0.6770975589752197,
"learning_rate": 4.172781365008316e-10,
"loss": 0.3798828125,
"step": 1499,
"token_acc": 0.8745905000492968
},
{
"epoch": 0.9966777408637874,
"grad_norm": 0.35159316658973694,
"learning_rate": 2.897777152699455e-10,
"loss": 0.379150390625,
"step": 1500,
"token_acc": 0.8742949943990882
},
{
"epoch": 0.9973421926910299,
"grad_norm": 0.3415471613407135,
"learning_rate": 1.854583826793599e-10,
"loss": 0.3720703125,
"step": 1501,
"token_acc": 0.876589784031982
},
{
"epoch": 0.9980066445182725,
"grad_norm": 0.33668121695518494,
"learning_rate": 1.0432062240439688e-10,
"loss": 0.385009765625,
"step": 1502,
"token_acc": 0.8727172695173178
},
{
"epoch": 0.998671096345515,
"grad_norm": 0.33050602674484253,
"learning_rate": 4.636481063913234e-11,
"loss": 0.387939453125,
"step": 1503,
"token_acc": 0.8721835738184512
},
{
"epoch": 0.9993355481727575,
"grad_norm": 0.31427040696144104,
"learning_rate": 1.1591216095285796e-11,
"loss": 0.400146484375,
"step": 1504,
"token_acc": 0.8684785987543214
},
{
"epoch": 1.0,
"grad_norm": 0.267340749502182,
"learning_rate": 0.0,
"loss": 0.388427734375,
"step": 1505,
"token_acc": 0.8713658906442271
}
],
"logging_steps": 1,
"max_steps": 1505,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 250,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.01854706681643e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}