GameGoCoder3_5 / trainer_state.json
Y36521478Y's picture
Add files using upload-large-folder tool
713538b verified
Raw History Blame Contribute Delete
257 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 250.0,
"global_step": 1166,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000858000858000858,
"grad_norm": 0.2866896986961365,
"learning_rate": 2.8571428571428575e-07,
"loss": 0.417236328125,
"step": 1,
"token_acc": 0.8659390191456583
},
{
"epoch": 0.001716001716001716,
"grad_norm": 0.28816020488739014,
"learning_rate": 5.714285714285715e-07,
"loss": 0.43994140625,
"step": 2,
"token_acc": 0.8584008617899913
},
{
"epoch": 0.002574002574002574,
"grad_norm": 0.31681931018829346,
"learning_rate": 8.571428571428572e-07,
"loss": 0.418212890625,
"step": 3,
"token_acc": 0.8648418071917373
},
{
"epoch": 0.003432003432003432,
"grad_norm": 0.35889744758605957,
"learning_rate": 1.142857142857143e-06,
"loss": 0.442626953125,
"step": 4,
"token_acc": 0.8582006543430963
},
{
"epoch": 0.00429000429000429,
"grad_norm": 0.4070545732975006,
"learning_rate": 1.4285714285714286e-06,
"loss": 0.438232421875,
"step": 5,
"token_acc": 0.859456274904666
},
{
"epoch": 0.005148005148005148,
"grad_norm": 0.33458247780799866,
"learning_rate": 1.7142857142857145e-06,
"loss": 0.421630859375,
"step": 6,
"token_acc": 0.8637136943918711
},
{
"epoch": 0.006006006006006006,
"grad_norm": 0.2552067041397095,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.431640625,
"step": 7,
"token_acc": 0.8609742875264959
},
{
"epoch": 0.006864006864006864,
"grad_norm": 0.2664823532104492,
"learning_rate": 2.285714285714286e-06,
"loss": 0.423828125,
"step": 8,
"token_acc": 0.8642358217888627
},
{
"epoch": 0.007722007722007722,
"grad_norm": 0.26748034358024597,
"learning_rate": 2.571428571428571e-06,
"loss": 0.422119140625,
"step": 9,
"token_acc": 0.8647667496578417
},
{
"epoch": 0.00858000858000858,
"grad_norm": 0.28847187757492065,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.430419921875,
"step": 10,
"token_acc": 0.8617803144852523
},
{
"epoch": 0.009438009438009438,
"grad_norm": 0.3367220163345337,
"learning_rate": 3.142857142857143e-06,
"loss": 0.43701171875,
"step": 11,
"token_acc": 0.8595595335148856
},
{
"epoch": 0.010296010296010296,
"grad_norm": 0.2838299870491028,
"learning_rate": 3.428571428571429e-06,
"loss": 0.444091796875,
"step": 12,
"token_acc": 0.8572038793160246
},
{
"epoch": 0.011154011154011155,
"grad_norm": 0.27047035098075867,
"learning_rate": 3.7142857142857146e-06,
"loss": 0.436767578125,
"step": 13,
"token_acc": 0.8598291050739676
},
{
"epoch": 0.012012012012012012,
"grad_norm": 0.3085128366947174,
"learning_rate": 4.000000000000001e-06,
"loss": 0.424072265625,
"step": 14,
"token_acc": 0.862984053742597
},
{
"epoch": 0.01287001287001287,
"grad_norm": 0.30077311396598816,
"learning_rate": 4.2857142857142855e-06,
"loss": 0.42724609375,
"step": 15,
"token_acc": 0.8623064841198137
},
{
"epoch": 0.013728013728013728,
"grad_norm": 0.2978106439113617,
"learning_rate": 4.571428571428572e-06,
"loss": 0.42724609375,
"step": 16,
"token_acc": 0.863008367818131
},
{
"epoch": 0.014586014586014585,
"grad_norm": 0.3563530445098877,
"learning_rate": 4.857142857142858e-06,
"loss": 0.4375,
"step": 17,
"token_acc": 0.8604867461576979
},
{
"epoch": 0.015444015444015444,
"grad_norm": 0.34114640951156616,
"learning_rate": 5.142857142857142e-06,
"loss": 0.4375,
"step": 18,
"token_acc": 0.8596210626305305
},
{
"epoch": 0.016302016302016303,
"grad_norm": 0.2918979227542877,
"learning_rate": 5.428571428571429e-06,
"loss": 0.42236328125,
"step": 19,
"token_acc": 0.8639430871007112
},
{
"epoch": 0.01716001716001716,
"grad_norm": 0.2939453125,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.4130859375,
"step": 20,
"token_acc": 0.8666282904167684
},
{
"epoch": 0.018018018018018018,
"grad_norm": 0.26655861735343933,
"learning_rate": 6e-06,
"loss": 0.427978515625,
"step": 21,
"token_acc": 0.8618692753155065
},
{
"epoch": 0.018876018876018877,
"grad_norm": 0.34131887555122375,
"learning_rate": 6.285714285714286e-06,
"loss": 0.428955078125,
"step": 22,
"token_acc": 0.8621614949499287
},
{
"epoch": 0.019734019734019732,
"grad_norm": 0.3618893027305603,
"learning_rate": 6.571428571428572e-06,
"loss": 0.4306640625,
"step": 23,
"token_acc": 0.8622036146576024
},
{
"epoch": 0.02059202059202059,
"grad_norm": 0.31468334794044495,
"learning_rate": 6.857142857142858e-06,
"loss": 0.42724609375,
"step": 24,
"token_acc": 0.8622572859332863
},
{
"epoch": 0.02145002145002145,
"grad_norm": 0.32955652475357056,
"learning_rate": 7.1428571428571436e-06,
"loss": 0.404296875,
"step": 25,
"token_acc": 0.8686943704163261
},
{
"epoch": 0.02230802230802231,
"grad_norm": 0.2980363965034485,
"learning_rate": 7.428571428571429e-06,
"loss": 0.434326171875,
"step": 26,
"token_acc": 0.8606818522161783
},
{
"epoch": 0.023166023166023165,
"grad_norm": 0.26264268159866333,
"learning_rate": 7.714285714285716e-06,
"loss": 0.430908203125,
"step": 27,
"token_acc": 0.860975401935843
},
{
"epoch": 0.024024024024024024,
"grad_norm": 2.648308277130127,
"learning_rate": 8.000000000000001e-06,
"loss": 0.431396484375,
"step": 28,
"token_acc": 0.8609830888996377
},
{
"epoch": 0.024882024882024883,
"grad_norm": 0.29543536901474,
"learning_rate": 8.285714285714287e-06,
"loss": 0.43017578125,
"step": 29,
"token_acc": 0.8615871081521881
},
{
"epoch": 0.02574002574002574,
"grad_norm": 0.28719252347946167,
"learning_rate": 8.571428571428571e-06,
"loss": 0.43408203125,
"step": 30,
"token_acc": 0.8603286205838111
},
{
"epoch": 0.026598026598026597,
"grad_norm": 0.2703489065170288,
"learning_rate": 8.857142857142858e-06,
"loss": 0.412353515625,
"step": 31,
"token_acc": 0.8671479658719087
},
{
"epoch": 0.027456027456027456,
"grad_norm": 0.29916954040527344,
"learning_rate": 9.142857142857144e-06,
"loss": 0.428466796875,
"step": 32,
"token_acc": 0.8626973978594102
},
{
"epoch": 0.028314028314028315,
"grad_norm": 0.3420413136482239,
"learning_rate": 9.42857142857143e-06,
"loss": 0.4365234375,
"step": 33,
"token_acc": 0.8599827915239731
},
{
"epoch": 0.02917202917202917,
"grad_norm": 0.3698040544986725,
"learning_rate": 9.714285714285715e-06,
"loss": 0.433349609375,
"step": 34,
"token_acc": 0.8605194210218615
},
{
"epoch": 0.03003003003003003,
"grad_norm": 0.2836638391017914,
"learning_rate": 1e-05,
"loss": 0.43603515625,
"step": 35,
"token_acc": 0.8599329162916195
},
{
"epoch": 0.03088803088803089,
"grad_norm": 0.3872542381286621,
"learning_rate": 9.99998071079783e-06,
"loss": 0.44970703125,
"step": 36,
"token_acc": 0.8565768523300122
},
{
"epoch": 0.031746031746031744,
"grad_norm": 0.2761880159378052,
"learning_rate": 9.999922843340147e-06,
"loss": 0.418701171875,
"step": 37,
"token_acc": 0.8653445481904468
},
{
"epoch": 0.03260403260403261,
"grad_norm": 0.3571472764015198,
"learning_rate": 9.999826398073438e-06,
"loss": 0.42578125,
"step": 38,
"token_acc": 0.8623041822562201
},
{
"epoch": 0.03346203346203346,
"grad_norm": 0.36762535572052,
"learning_rate": 9.999691375741846e-06,
"loss": 0.432861328125,
"step": 39,
"token_acc": 0.860566157930674
},
{
"epoch": 0.03432003432003432,
"grad_norm": 0.31121692061424255,
"learning_rate": 9.999517777387157e-06,
"loss": 0.433837890625,
"step": 40,
"token_acc": 0.8606299537989801
},
{
"epoch": 0.03517803517803518,
"grad_norm": 0.3051407039165497,
"learning_rate": 9.999305604348804e-06,
"loss": 0.442138671875,
"step": 41,
"token_acc": 0.8571202388232311
},
{
"epoch": 0.036036036036036036,
"grad_norm": 0.3610869348049164,
"learning_rate": 9.999054858263843e-06,
"loss": 0.431884765625,
"step": 42,
"token_acc": 0.8609604406819787
},
{
"epoch": 0.03689403689403689,
"grad_norm": 0.2832593023777008,
"learning_rate": 9.998765541066953e-06,
"loss": 0.419921875,
"step": 43,
"token_acc": 0.8645624517798693
},
{
"epoch": 0.037752037752037754,
"grad_norm": 0.3245987892150879,
"learning_rate": 9.998437654990412e-06,
"loss": 0.442138671875,
"step": 44,
"token_acc": 0.8581355942640042
},
{
"epoch": 0.03861003861003861,
"grad_norm": 0.3099849224090576,
"learning_rate": 9.998071202564086e-06,
"loss": 0.43505859375,
"step": 45,
"token_acc": 0.859622470127677
},
{
"epoch": 0.039468039468039465,
"grad_norm": 0.3080761432647705,
"learning_rate": 9.997666186615405e-06,
"loss": 0.432373046875,
"step": 46,
"token_acc": 0.8606909896763526
},
{
"epoch": 0.04032604032604033,
"grad_norm": 0.27880868315696716,
"learning_rate": 9.997222610269339e-06,
"loss": 0.427001953125,
"step": 47,
"token_acc": 0.8629267473482345
},
{
"epoch": 0.04118404118404118,
"grad_norm": 0.341497004032135,
"learning_rate": 9.996740476948386e-06,
"loss": 0.4501953125,
"step": 48,
"token_acc": 0.8556378060612979
},
{
"epoch": 0.042042042042042045,
"grad_norm": 0.3289513885974884,
"learning_rate": 9.99621979037253e-06,
"loss": 0.427490234375,
"step": 49,
"token_acc": 0.8628448142122482
},
{
"epoch": 0.0429000429000429,
"grad_norm": 0.2966715097427368,
"learning_rate": 9.995660554559225e-06,
"loss": 0.421875,
"step": 50,
"token_acc": 0.8633909547038404
},
{
"epoch": 0.043758043758043756,
"grad_norm": 0.3216015100479126,
"learning_rate": 9.995062773823352e-06,
"loss": 0.41748046875,
"step": 51,
"token_acc": 0.8650502073408959
},
{
"epoch": 0.04461604461604462,
"grad_norm": 0.3182523846626282,
"learning_rate": 9.994426452777201e-06,
"loss": 0.45458984375,
"step": 52,
"token_acc": 0.8540297519766729
},
{
"epoch": 0.045474045474045474,
"grad_norm": 0.28444159030914307,
"learning_rate": 9.993751596330421e-06,
"loss": 0.4462890625,
"step": 53,
"token_acc": 0.8570871122315712
},
{
"epoch": 0.04633204633204633,
"grad_norm": 0.319011926651001,
"learning_rate": 9.993038209689987e-06,
"loss": 0.443359375,
"step": 54,
"token_acc": 0.8574297247176856
},
{
"epoch": 0.04719004719004719,
"grad_norm": 0.32871705293655396,
"learning_rate": 9.992286298360164e-06,
"loss": 0.454833984375,
"step": 55,
"token_acc": 0.8541367885430617
},
{
"epoch": 0.04804804804804805,
"grad_norm": 0.2887991666793823,
"learning_rate": 9.991495868142457e-06,
"loss": 0.43310546875,
"step": 56,
"token_acc": 0.8608472410524005
},
{
"epoch": 0.0489060489060489,
"grad_norm": 0.29564040899276733,
"learning_rate": 9.99066692513558e-06,
"loss": 0.4326171875,
"step": 57,
"token_acc": 0.860788866796677
},
{
"epoch": 0.049764049764049766,
"grad_norm": 0.4187169373035431,
"learning_rate": 9.989799475735385e-06,
"loss": 0.439453125,
"step": 58,
"token_acc": 0.8589074672466088
},
{
"epoch": 0.05062205062205062,
"grad_norm": 0.30474570393562317,
"learning_rate": 9.98889352663484e-06,
"loss": 0.421875,
"step": 59,
"token_acc": 0.8631691535792372
},
{
"epoch": 0.05148005148005148,
"grad_norm": 0.3035092055797577,
"learning_rate": 9.987949084823958e-06,
"loss": 0.427490234375,
"step": 60,
"token_acc": 0.8622532215140132
},
{
"epoch": 0.05233805233805234,
"grad_norm": 0.2762581408023834,
"learning_rate": 9.986966157589751e-06,
"loss": 0.422607421875,
"step": 61,
"token_acc": 0.8633960461009306
},
{
"epoch": 0.053196053196053195,
"grad_norm": 0.3041031062602997,
"learning_rate": 9.985944752516168e-06,
"loss": 0.43408203125,
"step": 62,
"token_acc": 0.8613044748299509
},
{
"epoch": 0.05405405405405406,
"grad_norm": 0.30731523036956787,
"learning_rate": 9.984884877484049e-06,
"loss": 0.433837890625,
"step": 63,
"token_acc": 0.8596596491209223
},
{
"epoch": 0.05491205491205491,
"grad_norm": 0.3898373544216156,
"learning_rate": 9.983786540671052e-06,
"loss": 0.453125,
"step": 64,
"token_acc": 0.8555875432849217
},
{
"epoch": 0.05577005577005577,
"grad_norm": 0.2955479323863983,
"learning_rate": 9.982649750551589e-06,
"loss": 0.415283203125,
"step": 65,
"token_acc": 0.8665281042063112
},
{
"epoch": 0.05662805662805663,
"grad_norm": 0.2954164743423462,
"learning_rate": 9.981474515896772e-06,
"loss": 0.429931640625,
"step": 66,
"token_acc": 0.8625056155444735
},
{
"epoch": 0.057486057486057486,
"grad_norm": 0.2794334888458252,
"learning_rate": 9.980260845774336e-06,
"loss": 0.445068359375,
"step": 67,
"token_acc": 0.8562036524626453
},
{
"epoch": 0.05834405834405834,
"grad_norm": 0.2966383099555969,
"learning_rate": 9.979008749548575e-06,
"loss": 0.42724609375,
"step": 68,
"token_acc": 0.8628057083719157
},
{
"epoch": 0.059202059202059204,
"grad_norm": 0.8522504568099976,
"learning_rate": 9.977718236880262e-06,
"loss": 0.428955078125,
"step": 69,
"token_acc": 0.8629912660795612
},
{
"epoch": 0.06006006006006006,
"grad_norm": 0.3126501441001892,
"learning_rate": 9.97638931772658e-06,
"loss": 0.427001953125,
"step": 70,
"token_acc": 0.8629768460179474
},
{
"epoch": 0.060918060918060915,
"grad_norm": 0.28728997707366943,
"learning_rate": 9.975022002341045e-06,
"loss": 0.450439453125,
"step": 71,
"token_acc": 0.8559215975899666
},
{
"epoch": 0.06177606177606178,
"grad_norm": 0.3449382781982422,
"learning_rate": 9.97361630127343e-06,
"loss": 0.423095703125,
"step": 72,
"token_acc": 0.863885778698658
},
{
"epoch": 0.06263406263406264,
"grad_norm": 0.3375260829925537,
"learning_rate": 9.972172225369671e-06,
"loss": 0.42333984375,
"step": 73,
"token_acc": 0.8634253157093073
},
{
"epoch": 0.06349206349206349,
"grad_norm": 0.28931760787963867,
"learning_rate": 9.970689785771798e-06,
"loss": 0.44970703125,
"step": 74,
"token_acc": 0.8564562992038663
},
{
"epoch": 0.06435006435006435,
"grad_norm": 3.0931973457336426,
"learning_rate": 9.969168993917844e-06,
"loss": 0.450439453125,
"step": 75,
"token_acc": 0.8559120096878268
},
{
"epoch": 0.06520806520806521,
"grad_norm": 0.3273981213569641,
"learning_rate": 9.967609861541751e-06,
"loss": 0.4248046875,
"step": 76,
"token_acc": 0.8635447966833478
},
{
"epoch": 0.06606606606606606,
"grad_norm": 0.3380928635597229,
"learning_rate": 9.966012400673291e-06,
"loss": 0.441162109375,
"step": 77,
"token_acc": 0.8580933536372612
},
{
"epoch": 0.06692406692406692,
"grad_norm": 0.34710147976875305,
"learning_rate": 9.964376623637955e-06,
"loss": 0.429931640625,
"step": 78,
"token_acc": 0.8617754903528637
},
{
"epoch": 0.06778206778206779,
"grad_norm": 0.30178025364875793,
"learning_rate": 9.962702543056884e-06,
"loss": 0.427490234375,
"step": 79,
"token_acc": 0.8619628835376251
},
{
"epoch": 0.06864006864006864,
"grad_norm": 0.2820201814174652,
"learning_rate": 9.960990171846745e-06,
"loss": 0.417724609375,
"step": 80,
"token_acc": 0.8650374974737681
},
{
"epoch": 0.0694980694980695,
"grad_norm": 0.347827285528183,
"learning_rate": 9.95923952321965e-06,
"loss": 0.446044921875,
"step": 81,
"token_acc": 0.8573285744675821
},
{
"epoch": 0.07035607035607036,
"grad_norm": 0.33719682693481445,
"learning_rate": 9.957450610683044e-06,
"loss": 0.4189453125,
"step": 82,
"token_acc": 0.8653641047271851
},
{
"epoch": 0.07121407121407121,
"grad_norm": 0.29275792837142944,
"learning_rate": 9.955623448039605e-06,
"loss": 0.45361328125,
"step": 83,
"token_acc": 0.8552737569398858
},
{
"epoch": 0.07207207207207207,
"grad_norm": 0.2906016409397125,
"learning_rate": 9.953758049387138e-06,
"loss": 0.43701171875,
"step": 84,
"token_acc": 0.8588033245080293
},
{
"epoch": 0.07293007293007293,
"grad_norm": 0.5485277771949768,
"learning_rate": 9.951854429118463e-06,
"loss": 0.4306640625,
"step": 85,
"token_acc": 0.8614512031562757
},
{
"epoch": 0.07378807378807378,
"grad_norm": 0.30742642283439636,
"learning_rate": 9.949912601921306e-06,
"loss": 0.428466796875,
"step": 86,
"token_acc": 0.8614272252242766
},
{
"epoch": 0.07464607464607464,
"grad_norm": 0.2804388403892517,
"learning_rate": 9.947932582778188e-06,
"loss": 0.4208984375,
"step": 87,
"token_acc": 0.8639668348313108
},
{
"epoch": 0.07550407550407551,
"grad_norm": 0.31447505950927734,
"learning_rate": 9.945914386966301e-06,
"loss": 0.42529296875,
"step": 88,
"token_acc": 0.8628242451023378
},
{
"epoch": 0.07636207636207636,
"grad_norm": 0.38147038221359253,
"learning_rate": 9.943858030057404e-06,
"loss": 0.4306640625,
"step": 89,
"token_acc": 0.8613532756292224
},
{
"epoch": 0.07722007722007722,
"grad_norm": 0.3168240487575531,
"learning_rate": 9.94176352791769e-06,
"loss": 0.429931640625,
"step": 90,
"token_acc": 0.8612591455645956
},
{
"epoch": 0.07807807807807808,
"grad_norm": 0.29199087619781494,
"learning_rate": 9.939630896707665e-06,
"loss": 0.421630859375,
"step": 91,
"token_acc": 0.8631643219412931
},
{
"epoch": 0.07893607893607893,
"grad_norm": 0.49767443537712097,
"learning_rate": 9.937460152882035e-06,
"loss": 0.423828125,
"step": 92,
"token_acc": 0.863237554778442
},
{
"epoch": 0.07979407979407979,
"grad_norm": 0.2916853129863739,
"learning_rate": 9.935251313189564e-06,
"loss": 0.42724609375,
"step": 93,
"token_acc": 0.8618807920581697
},
{
"epoch": 0.08065208065208065,
"grad_norm": 0.2920651435852051,
"learning_rate": 9.933004394672958e-06,
"loss": 0.406494140625,
"step": 94,
"token_acc": 0.8693244848795153
},
{
"epoch": 0.08151008151008152,
"grad_norm": 0.2903677821159363,
"learning_rate": 9.93071941466872e-06,
"loss": 0.436767578125,
"step": 95,
"token_acc": 0.8592656595369684
},
{
"epoch": 0.08236808236808237,
"grad_norm": 0.32656461000442505,
"learning_rate": 9.928396390807026e-06,
"loss": 0.439453125,
"step": 96,
"token_acc": 0.8590200209328654
},
{
"epoch": 0.08322608322608323,
"grad_norm": 1.9109225273132324,
"learning_rate": 9.926035341011589e-06,
"loss": 0.42626953125,
"step": 97,
"token_acc": 0.8617394337700754
},
{
"epoch": 0.08408408408408409,
"grad_norm": 0.27664613723754883,
"learning_rate": 9.923636283499513e-06,
"loss": 0.4365234375,
"step": 98,
"token_acc": 0.8599078524886146
},
{
"epoch": 0.08494208494208494,
"grad_norm": 0.30498018860816956,
"learning_rate": 9.921199236781165e-06,
"loss": 0.43017578125,
"step": 99,
"token_acc": 0.8627635157143615
},
{
"epoch": 0.0858000858000858,
"grad_norm": 0.33257657289505005,
"learning_rate": 9.918724219660013e-06,
"loss": 0.439697265625,
"step": 100,
"token_acc": 0.8581050168508915
},
{
"epoch": 0.08665808665808666,
"grad_norm": 0.32996806502342224,
"learning_rate": 9.916211251232507e-06,
"loss": 0.427734375,
"step": 101,
"token_acc": 0.8625372932189703
},
{
"epoch": 0.08751608751608751,
"grad_norm": 0.3133423924446106,
"learning_rate": 9.913660350887903e-06,
"loss": 0.440673828125,
"step": 102,
"token_acc": 0.8591320939069387
},
{
"epoch": 0.08837408837408837,
"grad_norm": 0.27616122364997864,
"learning_rate": 9.911071538308135e-06,
"loss": 0.419677734375,
"step": 103,
"token_acc": 0.8650150464302567
},
{
"epoch": 0.08923208923208924,
"grad_norm": 0.28254660964012146,
"learning_rate": 9.908444833467659e-06,
"loss": 0.4306640625,
"step": 104,
"token_acc": 0.8617095279920655
},
{
"epoch": 0.09009009009009009,
"grad_norm": 0.4568648636341095,
"learning_rate": 9.905780256633286e-06,
"loss": 0.417724609375,
"step": 105,
"token_acc": 0.8650285820610095
},
{
"epoch": 0.09094809094809095,
"grad_norm": 0.434441477060318,
"learning_rate": 9.903077828364043e-06,
"loss": 0.415771484375,
"step": 106,
"token_acc": 0.8654695216655324
},
{
"epoch": 0.09180609180609181,
"grad_norm": 0.34304696321487427,
"learning_rate": 9.900337569511003e-06,
"loss": 0.448974609375,
"step": 107,
"token_acc": 0.8564676608409104
},
{
"epoch": 0.09266409266409266,
"grad_norm": 0.303996205329895,
"learning_rate": 9.897559501217131e-06,
"loss": 0.438720703125,
"step": 108,
"token_acc": 0.8586671700672731
},
{
"epoch": 0.09352209352209352,
"grad_norm": 0.2625811696052551,
"learning_rate": 9.894743644917115e-06,
"loss": 0.429443359375,
"step": 109,
"token_acc": 0.8618800023557979
},
{
"epoch": 0.09438009438009438,
"grad_norm": 0.7613674402236938,
"learning_rate": 9.891890022337201e-06,
"loss": 0.406005859375,
"step": 110,
"token_acc": 0.8684085825793044
},
{
"epoch": 0.09523809523809523,
"grad_norm": 0.4227883815765381,
"learning_rate": 9.888998655495033e-06,
"loss": 0.4541015625,
"step": 111,
"token_acc": 0.8544713167964341
},
{
"epoch": 0.0960960960960961,
"grad_norm": 0.5801519155502319,
"learning_rate": 9.886069566699472e-06,
"loss": 0.438720703125,
"step": 112,
"token_acc": 0.8589787700604063
},
{
"epoch": 0.09695409695409696,
"grad_norm": 0.289485901594162,
"learning_rate": 9.883102778550434e-06,
"loss": 0.425537109375,
"step": 113,
"token_acc": 0.8629462269697322
},
{
"epoch": 0.0978120978120978,
"grad_norm": 0.3218851387500763,
"learning_rate": 9.880098313938711e-06,
"loss": 0.4501953125,
"step": 114,
"token_acc": 0.8556671000764572
},
{
"epoch": 0.09867009867009867,
"grad_norm": 0.3377731442451477,
"learning_rate": 9.87705619604579e-06,
"loss": 0.439208984375,
"step": 115,
"token_acc": 0.8599389304977834
},
{
"epoch": 0.09952809952809953,
"grad_norm": 0.29411622881889343,
"learning_rate": 9.873976448343685e-06,
"loss": 0.4521484375,
"step": 116,
"token_acc": 0.8544804775551352
},
{
"epoch": 0.10038610038610038,
"grad_norm": 0.3255802392959595,
"learning_rate": 9.870859094594744e-06,
"loss": 0.449951171875,
"step": 117,
"token_acc": 0.8551571620078223
},
{
"epoch": 0.10124410124410124,
"grad_norm": 0.26449504494667053,
"learning_rate": 9.867704158851474e-06,
"loss": 0.426025390625,
"step": 118,
"token_acc": 0.8631648397770266
},
{
"epoch": 0.1021021021021021,
"grad_norm": 0.30522894859313965,
"learning_rate": 9.864511665456355e-06,
"loss": 0.4296875,
"step": 119,
"token_acc": 0.8609904774105389
},
{
"epoch": 0.10296010296010295,
"grad_norm": 0.2805873155593872,
"learning_rate": 9.861281639041643e-06,
"loss": 0.448486328125,
"step": 120,
"token_acc": 0.8561486803522393
},
{
"epoch": 0.10381810381810382,
"grad_norm": 0.2855660021305084,
"learning_rate": 9.858014104529195e-06,
"loss": 0.443603515625,
"step": 121,
"token_acc": 0.858334287173961
},
{
"epoch": 0.10467610467610468,
"grad_norm": 0.30721303820610046,
"learning_rate": 9.854709087130261e-06,
"loss": 0.43310546875,
"step": 122,
"token_acc": 0.8612063788616802
},
{
"epoch": 0.10553410553410554,
"grad_norm": 0.309182733297348,
"learning_rate": 9.851366612345304e-06,
"loss": 0.4228515625,
"step": 123,
"token_acc": 0.8639700842376264
},
{
"epoch": 0.10639210639210639,
"grad_norm": 0.30527999997138977,
"learning_rate": 9.847986705963789e-06,
"loss": 0.424560546875,
"step": 124,
"token_acc": 0.8631246825535072
},
{
"epoch": 0.10725010725010725,
"grad_norm": 0.33542191982269287,
"learning_rate": 9.844569394063997e-06,
"loss": 0.444091796875,
"step": 125,
"token_acc": 0.857084798619866
},
{
"epoch": 0.10810810810810811,
"grad_norm": 0.2956825792789459,
"learning_rate": 9.841114703012817e-06,
"loss": 0.439208984375,
"step": 126,
"token_acc": 0.8585802075702208
},
{
"epoch": 0.10896610896610896,
"grad_norm": 0.28136518597602844,
"learning_rate": 9.837622659465542e-06,
"loss": 0.43603515625,
"step": 127,
"token_acc": 0.860400479965134
},
{
"epoch": 0.10982410982410983,
"grad_norm": 0.8990980386734009,
"learning_rate": 9.834093290365665e-06,
"loss": 0.456298828125,
"step": 128,
"token_acc": 0.8547015410140556
},
{
"epoch": 0.11068211068211069,
"grad_norm": 0.2926611006259918,
"learning_rate": 9.830526622944672e-06,
"loss": 0.4296875,
"step": 129,
"token_acc": 0.8617054450042543
},
{
"epoch": 0.11154011154011154,
"grad_norm": 0.315525084733963,
"learning_rate": 9.826922684721828e-06,
"loss": 0.426025390625,
"step": 130,
"token_acc": 0.8627010621126744
},
{
"epoch": 0.1123981123981124,
"grad_norm": 0.5347230434417725,
"learning_rate": 9.823281503503976e-06,
"loss": 0.423095703125,
"step": 131,
"token_acc": 0.8635265770435971
},
{
"epoch": 0.11325611325611326,
"grad_norm": 0.371747761964798,
"learning_rate": 9.819603107385304e-06,
"loss": 0.429443359375,
"step": 132,
"token_acc": 0.8621341662558797
},
{
"epoch": 0.11411411411411411,
"grad_norm": 0.3243626356124878,
"learning_rate": 9.815887524747143e-06,
"loss": 0.44677734375,
"step": 133,
"token_acc": 0.8569062864269701
},
{
"epoch": 0.11497211497211497,
"grad_norm": 0.5298293828964233,
"learning_rate": 9.812134784257743e-06,
"loss": 0.437744140625,
"step": 134,
"token_acc": 0.8591547716823851
},
{
"epoch": 0.11583011583011583,
"grad_norm": 0.36959308385849,
"learning_rate": 9.808344914872052e-06,
"loss": 0.434326171875,
"step": 135,
"token_acc": 0.8606646695660967
},
{
"epoch": 0.11668811668811668,
"grad_norm": 0.3174014985561371,
"learning_rate": 9.804517945831496e-06,
"loss": 0.432373046875,
"step": 136,
"token_acc": 0.859926808497758
},
{
"epoch": 0.11754611754611755,
"grad_norm": 0.287353515625,
"learning_rate": 9.80065390666374e-06,
"loss": 0.42236328125,
"step": 137,
"token_acc": 0.8635208120658386
},
{
"epoch": 0.11840411840411841,
"grad_norm": 0.27945515513420105,
"learning_rate": 9.796752827182482e-06,
"loss": 0.43310546875,
"step": 138,
"token_acc": 0.8607503702353102
},
{
"epoch": 0.11926211926211926,
"grad_norm": 0.3561578392982483,
"learning_rate": 9.792814737487207e-06,
"loss": 0.447998046875,
"step": 139,
"token_acc": 0.8558888047891007
},
{
"epoch": 0.12012012012012012,
"grad_norm": 0.43907490372657776,
"learning_rate": 9.788839667962956e-06,
"loss": 0.424560546875,
"step": 140,
"token_acc": 0.8635364206281559
},
{
"epoch": 0.12097812097812098,
"grad_norm": 0.3326631188392639,
"learning_rate": 9.784827649280097e-06,
"loss": 0.439208984375,
"step": 141,
"token_acc": 0.8586229692012771
},
{
"epoch": 0.12183612183612183,
"grad_norm": 0.5196930766105652,
"learning_rate": 9.780778712394085e-06,
"loss": 0.433349609375,
"step": 142,
"token_acc": 0.8607700267039842
},
{
"epoch": 0.12269412269412269,
"grad_norm": 0.38644012808799744,
"learning_rate": 9.77669288854523e-06,
"loss": 0.433837890625,
"step": 143,
"token_acc": 0.8609724672508361
},
{
"epoch": 0.12355212355212356,
"grad_norm": 0.3500310480594635,
"learning_rate": 9.772570209258437e-06,
"loss": 0.42138671875,
"step": 144,
"token_acc": 0.8650113555684986
},
{
"epoch": 0.1244101244101244,
"grad_norm": 0.6358687281608582,
"learning_rate": 9.76841070634299e-06,
"loss": 0.44189453125,
"step": 145,
"token_acc": 0.8579567977768892
},
{
"epoch": 0.12526812526812528,
"grad_norm": 0.28797560930252075,
"learning_rate": 9.764214411892283e-06,
"loss": 0.419677734375,
"step": 146,
"token_acc": 0.8643177930142651
},
{
"epoch": 0.12612612612612611,
"grad_norm": 0.3438848853111267,
"learning_rate": 9.759981358283586e-06,
"loss": 0.4228515625,
"step": 147,
"token_acc": 0.8635684403350091
},
{
"epoch": 0.12698412698412698,
"grad_norm": 0.307162344455719,
"learning_rate": 9.755711578177789e-06,
"loss": 0.436279296875,
"step": 148,
"token_acc": 0.8602330362200822
},
{
"epoch": 0.12784212784212784,
"grad_norm": 0.3102457523345947,
"learning_rate": 9.751405104519151e-06,
"loss": 0.4228515625,
"step": 149,
"token_acc": 0.8635288789939924
},
{
"epoch": 0.1287001287001287,
"grad_norm": 0.4492000937461853,
"learning_rate": 9.747061970535054e-06,
"loss": 0.423583984375,
"step": 150,
"token_acc": 0.8625032608695652
},
{
"epoch": 0.12955812955812956,
"grad_norm": 0.2836586833000183,
"learning_rate": 9.742682209735727e-06,
"loss": 0.42431640625,
"step": 151,
"token_acc": 0.8641671049092974
},
{
"epoch": 0.13041613041613043,
"grad_norm": 0.29926013946533203,
"learning_rate": 9.738265855914014e-06,
"loss": 0.42333984375,
"step": 152,
"token_acc": 0.8644063622140684
},
{
"epoch": 0.13127413127413126,
"grad_norm": 0.29115450382232666,
"learning_rate": 9.733812943145084e-06,
"loss": 0.406494140625,
"step": 153,
"token_acc": 0.8688271440873476
},
{
"epoch": 0.13213213213213212,
"grad_norm": 0.3262125551700592,
"learning_rate": 9.729323505786195e-06,
"loss": 0.453125,
"step": 154,
"token_acc": 0.8551171400298111
},
{
"epoch": 0.132990132990133,
"grad_norm": 0.34598642587661743,
"learning_rate": 9.724797578476414e-06,
"loss": 0.4228515625,
"step": 155,
"token_acc": 0.8643666068375494
},
{
"epoch": 0.13384813384813385,
"grad_norm": 0.29481667280197144,
"learning_rate": 9.720235196136348e-06,
"loss": 0.406982421875,
"step": 156,
"token_acc": 0.8674880183995566
},
{
"epoch": 0.1347061347061347,
"grad_norm": 0.30502384901046753,
"learning_rate": 9.715636393967886e-06,
"loss": 0.42724609375,
"step": 157,
"token_acc": 0.863166064395743
},
{
"epoch": 0.13556413556413557,
"grad_norm": 0.6529213190078735,
"learning_rate": 9.711001207453919e-06,
"loss": 0.430908203125,
"step": 158,
"token_acc": 0.8613759993071831
},
{
"epoch": 0.1364221364221364,
"grad_norm": 0.33587655425071716,
"learning_rate": 9.706329672358062e-06,
"loss": 0.440185546875,
"step": 159,
"token_acc": 0.8586738032977728
},
{
"epoch": 0.13728013728013727,
"grad_norm": 0.35240015387535095,
"learning_rate": 9.701621824724394e-06,
"loss": 0.443359375,
"step": 160,
"token_acc": 0.8575893885982059
},
{
"epoch": 0.13813813813813813,
"grad_norm": 0.30771923065185547,
"learning_rate": 9.696877700877162e-06,
"loss": 0.4248046875,
"step": 161,
"token_acc": 0.863541263164223
},
{
"epoch": 0.138996138996139,
"grad_norm": 0.3204922378063202,
"learning_rate": 9.692097337420513e-06,
"loss": 0.43408203125,
"step": 162,
"token_acc": 0.8605713765677119
},
{
"epoch": 0.13985413985413986,
"grad_norm": 0.2962246239185333,
"learning_rate": 9.687280771238206e-06,
"loss": 0.407470703125,
"step": 163,
"token_acc": 0.8683413762936265
},
{
"epoch": 0.14071214071214072,
"grad_norm": 0.290865421295166,
"learning_rate": 9.682428039493325e-06,
"loss": 0.42041015625,
"step": 164,
"token_acc": 0.8647953851453527
},
{
"epoch": 0.14157014157014158,
"grad_norm": 0.2946326732635498,
"learning_rate": 9.677539179628005e-06,
"loss": 0.4306640625,
"step": 165,
"token_acc": 0.8619105384048139
},
{
"epoch": 0.14242814242814242,
"grad_norm": 0.30827391147613525,
"learning_rate": 9.672614229363127e-06,
"loss": 0.4501953125,
"step": 166,
"token_acc": 0.8559948327280084
},
{
"epoch": 0.14328614328614328,
"grad_norm": 0.33036574721336365,
"learning_rate": 9.667653226698033e-06,
"loss": 0.4287109375,
"step": 167,
"token_acc": 0.8612697143801372
},
{
"epoch": 0.14414414414414414,
"grad_norm": 0.33519428968429565,
"learning_rate": 9.662656209910237e-06,
"loss": 0.44189453125,
"step": 168,
"token_acc": 0.8577209057951392
},
{
"epoch": 0.145002145002145,
"grad_norm": 0.2916140854358673,
"learning_rate": 9.657623217555127e-06,
"loss": 0.431640625,
"step": 169,
"token_acc": 0.8608554884502833
},
{
"epoch": 0.14586014586014587,
"grad_norm": 0.33733654022216797,
"learning_rate": 9.652554288465668e-06,
"loss": 0.450439453125,
"step": 170,
"token_acc": 0.8552735343800931
},
{
"epoch": 0.14671814671814673,
"grad_norm": 0.3312537670135498,
"learning_rate": 9.647449461752094e-06,
"loss": 0.42529296875,
"step": 171,
"token_acc": 0.8625212401313058
},
{
"epoch": 0.14757614757614756,
"grad_norm": 0.333163321018219,
"learning_rate": 9.642308776801621e-06,
"loss": 0.4376220703125,
"step": 172,
"token_acc": 0.8598716269936951
},
{
"epoch": 0.14843414843414843,
"grad_norm": 0.3010820746421814,
"learning_rate": 9.637132273278135e-06,
"loss": 0.431884765625,
"step": 173,
"token_acc": 0.8611986803938672
},
{
"epoch": 0.1492921492921493,
"grad_norm": 0.34259986877441406,
"learning_rate": 9.631919991121885e-06,
"loss": 0.424072265625,
"step": 174,
"token_acc": 0.862877672056048
},
{
"epoch": 0.15015015015015015,
"grad_norm": 0.3133125603199005,
"learning_rate": 9.626671970549175e-06,
"loss": 0.43505859375,
"step": 175,
"token_acc": 0.8597293753695594
},
{
"epoch": 0.15100815100815101,
"grad_norm": 0.36292973160743713,
"learning_rate": 9.62138825205206e-06,
"loss": 0.425537109375,
"step": 176,
"token_acc": 0.8621155247863155
},
{
"epoch": 0.15186615186615188,
"grad_norm": 0.2830241322517395,
"learning_rate": 9.616068876398021e-06,
"loss": 0.419677734375,
"step": 177,
"token_acc": 0.8632545273964338
},
{
"epoch": 0.1527241527241527,
"grad_norm": 0.29340943694114685,
"learning_rate": 9.610713884629667e-06,
"loss": 0.416259765625,
"step": 178,
"token_acc": 0.8656306113394333
},
{
"epoch": 0.15358215358215357,
"grad_norm": 0.5450041890144348,
"learning_rate": 9.605323318064403e-06,
"loss": 0.425537109375,
"step": 179,
"token_acc": 0.8628726012628118
},
{
"epoch": 0.15444015444015444,
"grad_norm": 0.28800562024116516,
"learning_rate": 9.599897218294122e-06,
"loss": 0.429443359375,
"step": 180,
"token_acc": 0.8615286764775196
},
{
"epoch": 0.1552981552981553,
"grad_norm": 0.289815217256546,
"learning_rate": 9.594435627184877e-06,
"loss": 0.414306640625,
"step": 181,
"token_acc": 0.865961407129698
},
{
"epoch": 0.15615615615615616,
"grad_norm": 0.29922357201576233,
"learning_rate": 9.588938586876564e-06,
"loss": 0.439208984375,
"step": 182,
"token_acc": 0.8580632541072037
},
{
"epoch": 0.15701415701415702,
"grad_norm": 0.26317358016967773,
"learning_rate": 9.58340613978259e-06,
"loss": 0.421630859375,
"step": 183,
"token_acc": 0.8639203538697734
},
{
"epoch": 0.15787215787215786,
"grad_norm": 0.3301839530467987,
"learning_rate": 9.577838328589551e-06,
"loss": 0.443115234375,
"step": 184,
"token_acc": 0.8589078510498724
},
{
"epoch": 0.15873015873015872,
"grad_norm": 0.305098295211792,
"learning_rate": 9.5722351962569e-06,
"loss": 0.423828125,
"step": 185,
"token_acc": 0.8633081519752234
},
{
"epoch": 0.15958815958815958,
"grad_norm": 0.30107805132865906,
"learning_rate": 9.566596786016622e-06,
"loss": 0.3994140625,
"step": 186,
"token_acc": 0.8696676163560985
},
{
"epoch": 0.16044616044616045,
"grad_norm": 0.2985714375972748,
"learning_rate": 9.560923141372889e-06,
"loss": 0.420654296875,
"step": 187,
"token_acc": 0.8641579857943917
},
{
"epoch": 0.1613041613041613,
"grad_norm": 0.37831997871398926,
"learning_rate": 9.555214306101732e-06,
"loss": 0.414794921875,
"step": 188,
"token_acc": 0.8657206555629284
},
{
"epoch": 0.16216216216216217,
"grad_norm": 0.35076069831848145,
"learning_rate": 9.549470324250702e-06,
"loss": 0.415771484375,
"step": 189,
"token_acc": 0.8659297283567602
},
{
"epoch": 0.16302016302016303,
"grad_norm": 0.37489020824432373,
"learning_rate": 9.54369124013853e-06,
"loss": 0.430908203125,
"step": 190,
"token_acc": 0.86083620683187
},
{
"epoch": 0.16387816387816387,
"grad_norm": 0.29684630036354065,
"learning_rate": 9.537877098354787e-06,
"loss": 0.42333984375,
"step": 191,
"token_acc": 0.8633850161532511
},
{
"epoch": 0.16473616473616473,
"grad_norm": 0.28190863132476807,
"learning_rate": 9.53202794375953e-06,
"loss": 0.43798828125,
"step": 192,
"token_acc": 0.859159046623762
},
{
"epoch": 0.1655941655941656,
"grad_norm": 0.3336430490016937,
"learning_rate": 9.526143821482975e-06,
"loss": 0.43408203125,
"step": 193,
"token_acc": 0.8602687551811895
},
{
"epoch": 0.16645216645216646,
"grad_norm": 0.3207132816314697,
"learning_rate": 9.52022477692513e-06,
"loss": 0.43701171875,
"step": 194,
"token_acc": 0.8597600655803189
},
{
"epoch": 0.16731016731016732,
"grad_norm": 0.33097460865974426,
"learning_rate": 9.514270855755451e-06,
"loss": 0.429931640625,
"step": 195,
"token_acc": 0.8609641657849947
},
{
"epoch": 0.16816816816816818,
"grad_norm": 0.3455677330493927,
"learning_rate": 9.508282103912497e-06,
"loss": 0.44580078125,
"step": 196,
"token_acc": 0.8570423522076971
},
{
"epoch": 0.16902616902616902,
"grad_norm": 0.3299466371536255,
"learning_rate": 9.502258567603563e-06,
"loss": 0.440673828125,
"step": 197,
"token_acc": 0.8582987573677376
},
{
"epoch": 0.16988416988416988,
"grad_norm": 1.0264750719070435,
"learning_rate": 9.496200293304339e-06,
"loss": 0.4443359375,
"step": 198,
"token_acc": 0.8581876996648996
},
{
"epoch": 0.17074217074217074,
"grad_norm": 0.2721017003059387,
"learning_rate": 9.490107327758528e-06,
"loss": 0.431640625,
"step": 199,
"token_acc": 0.8619042995870427
},
{
"epoch": 0.1716001716001716,
"grad_norm": 0.26176390051841736,
"learning_rate": 9.483979717977513e-06,
"loss": 0.45166015625,
"step": 200,
"token_acc": 0.8552887812873359
},
{
"epoch": 0.17245817245817247,
"grad_norm": 0.27081790566444397,
"learning_rate": 9.477817511239975e-06,
"loss": 0.426513671875,
"step": 201,
"token_acc": 0.8632319279231626
},
{
"epoch": 0.17331617331617333,
"grad_norm": 0.3169817626476288,
"learning_rate": 9.471620755091531e-06,
"loss": 0.4267578125,
"step": 202,
"token_acc": 0.8624886674328791
},
{
"epoch": 0.17417417417417416,
"grad_norm": 0.4112089276313782,
"learning_rate": 9.46538949734438e-06,
"loss": 0.429931640625,
"step": 203,
"token_acc": 0.8624112844761109
},
{
"epoch": 0.17503217503217502,
"grad_norm": 0.27956825494766235,
"learning_rate": 9.459123786076911e-06,
"loss": 0.43359375,
"step": 204,
"token_acc": 0.8601894168572344
},
{
"epoch": 0.1758901758901759,
"grad_norm": 0.27259179949760437,
"learning_rate": 9.45282366963336e-06,
"loss": 0.426513671875,
"step": 205,
"token_acc": 0.8615424963628182
},
{
"epoch": 0.17674817674817675,
"grad_norm": 0.2905864715576172,
"learning_rate": 9.44648919662341e-06,
"loss": 0.43701171875,
"step": 206,
"token_acc": 0.860450626306242
},
{
"epoch": 0.1776061776061776,
"grad_norm": 0.28907889127731323,
"learning_rate": 9.440120415921833e-06,
"loss": 0.440673828125,
"step": 207,
"token_acc": 0.8582661859050449
},
{
"epoch": 0.17846417846417847,
"grad_norm": 0.27410227060317993,
"learning_rate": 9.433717376668112e-06,
"loss": 0.424072265625,
"step": 208,
"token_acc": 0.8628683258008377
},
{
"epoch": 0.1793221793221793,
"grad_norm": 0.2896680533885956,
"learning_rate": 9.427280128266049e-06,
"loss": 0.426025390625,
"step": 209,
"token_acc": 0.8627354263731682
},
{
"epoch": 0.18018018018018017,
"grad_norm": 0.2696223855018616,
"learning_rate": 9.420808720383405e-06,
"loss": 0.42431640625,
"step": 210,
"token_acc": 0.8635049042199606
},
{
"epoch": 0.18103818103818103,
"grad_norm": 0.34673529863357544,
"learning_rate": 9.414303202951493e-06,
"loss": 0.425537109375,
"step": 211,
"token_acc": 0.8622429746353655
},
{
"epoch": 0.1818961818961819,
"grad_norm": 0.2884232997894287,
"learning_rate": 9.407763626164812e-06,
"loss": 0.429931640625,
"step": 212,
"token_acc": 0.8619582910351105
},
{
"epoch": 0.18275418275418276,
"grad_norm": 0.283399373292923,
"learning_rate": 9.401190040480648e-06,
"loss": 0.4326171875,
"step": 213,
"token_acc": 0.8604622419255632
},
{
"epoch": 0.18361218361218362,
"grad_norm": 0.27398231625556946,
"learning_rate": 9.394582496618692e-06,
"loss": 0.422607421875,
"step": 214,
"token_acc": 0.8632756390930837
},
{
"epoch": 0.18447018447018448,
"grad_norm": 0.29359328746795654,
"learning_rate": 9.387941045560641e-06,
"loss": 0.427978515625,
"step": 215,
"token_acc": 0.861757820674842
},
{
"epoch": 0.18532818532818532,
"grad_norm": 0.3070027232170105,
"learning_rate": 9.381265738549814e-06,
"loss": 0.42724609375,
"step": 216,
"token_acc": 0.8621950975086685
},
{
"epoch": 0.18618618618618618,
"grad_norm": 0.29027625918388367,
"learning_rate": 9.374556627090749e-06,
"loss": 0.4267578125,
"step": 217,
"token_acc": 0.862811361336732
},
{
"epoch": 0.18704418704418704,
"grad_norm": 0.27935290336608887,
"learning_rate": 9.367813762948809e-06,
"loss": 0.422607421875,
"step": 218,
"token_acc": 0.8638325115686148
},
{
"epoch": 0.1879021879021879,
"grad_norm": 0.31722792983055115,
"learning_rate": 9.361037198149782e-06,
"loss": 0.44287109375,
"step": 219,
"token_acc": 0.8574684724484869
},
{
"epoch": 0.18876018876018877,
"grad_norm": 0.34204453229904175,
"learning_rate": 9.35422698497948e-06,
"loss": 0.4317626953125,
"step": 220,
"token_acc": 0.8609452030193664
},
{
"epoch": 0.18961818961818963,
"grad_norm": 0.3174639940261841,
"learning_rate": 9.347383175983333e-06,
"loss": 0.40478515625,
"step": 221,
"token_acc": 0.8695400848669389
},
{
"epoch": 0.19047619047619047,
"grad_norm": 0.30405423045158386,
"learning_rate": 9.340505823965987e-06,
"loss": 0.424072265625,
"step": 222,
"token_acc": 0.8631061084180419
},
{
"epoch": 0.19133419133419133,
"grad_norm": 0.3104971945285797,
"learning_rate": 9.333594981990897e-06,
"loss": 0.42529296875,
"step": 223,
"token_acc": 0.8631241306877856
},
{
"epoch": 0.1921921921921922,
"grad_norm": 0.2984095513820648,
"learning_rate": 9.326650703379913e-06,
"loss": 0.44677734375,
"step": 224,
"token_acc": 0.8566404286463943
},
{
"epoch": 0.19305019305019305,
"grad_norm": 0.39514392614364624,
"learning_rate": 9.319673041712874e-06,
"loss": 0.4248046875,
"step": 225,
"token_acc": 0.8637497837456583
},
{
"epoch": 0.19390819390819392,
"grad_norm": 0.308226078748703,
"learning_rate": 9.312662050827189e-06,
"loss": 0.438232421875,
"step": 226,
"token_acc": 0.8585405191648858
},
{
"epoch": 0.19476619476619478,
"grad_norm": 0.297770619392395,
"learning_rate": 9.305617784817426e-06,
"loss": 0.426025390625,
"step": 227,
"token_acc": 0.8628036504796963
},
{
"epoch": 0.1956241956241956,
"grad_norm": 0.34227249026298523,
"learning_rate": 9.298540298034897e-06,
"loss": 0.419189453125,
"step": 228,
"token_acc": 0.8642064342656307
},
{
"epoch": 0.19648219648219648,
"grad_norm": 0.2757626473903656,
"learning_rate": 9.291429645087226e-06,
"loss": 0.413330078125,
"step": 229,
"token_acc": 0.8665561458874286
},
{
"epoch": 0.19734019734019734,
"grad_norm": 0.36272475123405457,
"learning_rate": 9.284285880837947e-06,
"loss": 0.42431640625,
"step": 230,
"token_acc": 0.863536659887088
},
{
"epoch": 0.1981981981981982,
"grad_norm": 0.32731205224990845,
"learning_rate": 9.277109060406062e-06,
"loss": 0.441650390625,
"step": 231,
"token_acc": 0.8589945287119087
},
{
"epoch": 0.19905619905619906,
"grad_norm": 0.3010721802711487,
"learning_rate": 9.269899239165627e-06,
"loss": 0.43505859375,
"step": 232,
"token_acc": 0.8596922831928291
},
{
"epoch": 0.19991419991419992,
"grad_norm": 0.26902228593826294,
"learning_rate": 9.262656472745324e-06,
"loss": 0.42529296875,
"step": 233,
"token_acc": 0.8636181593680515
},
{
"epoch": 0.20077220077220076,
"grad_norm": 0.27278515696525574,
"learning_rate": 9.255380817028026e-06,
"loss": 0.426513671875,
"step": 234,
"token_acc": 0.8629538312241525
},
{
"epoch": 0.20163020163020162,
"grad_norm": 0.33869463205337524,
"learning_rate": 9.24807232815037e-06,
"loss": 0.425048828125,
"step": 235,
"token_acc": 0.8627419094304363
},
{
"epoch": 0.20248820248820248,
"grad_norm": 0.34398311376571655,
"learning_rate": 9.240731062502323e-06,
"loss": 0.42626953125,
"step": 236,
"token_acc": 0.8630947289684516
},
{
"epoch": 0.20334620334620335,
"grad_norm": 0.30215585231781006,
"learning_rate": 9.233357076726753e-06,
"loss": 0.441162109375,
"step": 237,
"token_acc": 0.8585489014051211
},
{
"epoch": 0.2042042042042042,
"grad_norm": 0.3717430830001831,
"learning_rate": 9.225950427718974e-06,
"loss": 0.43115234375,
"step": 238,
"token_acc": 0.8603584266523683
},
{
"epoch": 0.20506220506220507,
"grad_norm": 0.42662763595581055,
"learning_rate": 9.218511172626333e-06,
"loss": 0.435791015625,
"step": 239,
"token_acc": 0.8591697501989751
},
{
"epoch": 0.2059202059202059,
"grad_norm": 0.27374520897865295,
"learning_rate": 9.211039368847741e-06,
"loss": 0.41748046875,
"step": 240,
"token_acc": 0.8649133719216938
},
{
"epoch": 0.20677820677820677,
"grad_norm": 0.3366905450820923,
"learning_rate": 9.203535074033256e-06,
"loss": 0.42578125,
"step": 241,
"token_acc": 0.8633633325702808
},
{
"epoch": 0.20763620763620763,
"grad_norm": 0.312176376581192,
"learning_rate": 9.195998346083621e-06,
"loss": 0.438232421875,
"step": 242,
"token_acc": 0.8589485348142376
},
{
"epoch": 0.2084942084942085,
"grad_norm": 0.30048805475234985,
"learning_rate": 9.188429243149824e-06,
"loss": 0.42333984375,
"step": 243,
"token_acc": 0.8636859775180926
},
{
"epoch": 0.20935220935220936,
"grad_norm": 0.29961898922920227,
"learning_rate": 9.180827823632648e-06,
"loss": 0.409423828125,
"step": 244,
"token_acc": 0.8674214924456969
},
{
"epoch": 0.21021021021021022,
"grad_norm": 0.3023031949996948,
"learning_rate": 9.173194146182219e-06,
"loss": 0.420166015625,
"step": 245,
"token_acc": 0.8642340165573618
},
{
"epoch": 0.21106821106821108,
"grad_norm": 0.2820834815502167,
"learning_rate": 9.165528269697556e-06,
"loss": 0.4228515625,
"step": 246,
"token_acc": 0.8637591516192752
},
{
"epoch": 0.21192621192621192,
"grad_norm": 0.27298504114151,
"learning_rate": 9.157830253326117e-06,
"loss": 0.45751953125,
"step": 247,
"token_acc": 0.8540696435164271
},
{
"epoch": 0.21278421278421278,
"grad_norm": 0.29238638281822205,
"learning_rate": 9.150100156463337e-06,
"loss": 0.419921875,
"step": 248,
"token_acc": 0.8637033878248579
},
{
"epoch": 0.21364221364221364,
"grad_norm": 0.3810073435306549,
"learning_rate": 9.14233803875218e-06,
"loss": 0.412353515625,
"step": 249,
"token_acc": 0.8675932059553406
},
{
"epoch": 0.2145002145002145,
"grad_norm": 0.29363319277763367,
"learning_rate": 9.134543960082667e-06,
"loss": 0.448974609375,
"step": 250,
"token_acc": 0.856670613584936
},
{
"epoch": 0.21535821535821537,
"grad_norm": 0.29492416977882385,
"learning_rate": 9.126717980591422e-06,
"loss": 0.4453125,
"step": 251,
"token_acc": 0.8560191587117495
},
{
"epoch": 0.21621621621621623,
"grad_norm": 0.3694521188735962,
"learning_rate": 9.118860160661205e-06,
"loss": 0.44189453125,
"step": 252,
"token_acc": 0.8584528598352316
},
{
"epoch": 0.21707421707421706,
"grad_norm": 0.4257165789604187,
"learning_rate": 9.110970560920447e-06,
"loss": 0.42822265625,
"step": 253,
"token_acc": 0.8612820618279977
},
{
"epoch": 0.21793221793221793,
"grad_norm": 0.30233731865882874,
"learning_rate": 9.103049242242781e-06,
"loss": 0.415283203125,
"step": 254,
"token_acc": 0.8658771368165404
},
{
"epoch": 0.2187902187902188,
"grad_norm": 0.3978073000907898,
"learning_rate": 9.095096265746576e-06,
"loss": 0.40869140625,
"step": 255,
"token_acc": 0.8673554366513878
},
{
"epoch": 0.21964821964821965,
"grad_norm": 0.3357275426387787,
"learning_rate": 9.08711169279446e-06,
"loss": 0.434814453125,
"step": 256,
"token_acc": 0.8598399637698556
},
{
"epoch": 0.2205062205062205,
"grad_norm": 0.40367862582206726,
"learning_rate": 9.079095584992848e-06,
"loss": 0.427001953125,
"step": 257,
"token_acc": 0.8626430558304076
},
{
"epoch": 0.22136422136422138,
"grad_norm": 0.3087162971496582,
"learning_rate": 9.071048004191471e-06,
"loss": 0.416748046875,
"step": 258,
"token_acc": 0.8649556625710392
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.31273365020751953,
"learning_rate": 9.062969012482897e-06,
"loss": 0.42529296875,
"step": 259,
"token_acc": 0.8629899912994479
},
{
"epoch": 0.22308022308022307,
"grad_norm": 0.30572712421417236,
"learning_rate": 9.05485867220204e-06,
"loss": 0.443359375,
"step": 260,
"token_acc": 0.8575260270778295
},
{
"epoch": 0.22393822393822393,
"grad_norm": 0.4769786298274994,
"learning_rate": 9.046717045925705e-06,
"loss": 0.430419921875,
"step": 261,
"token_acc": 0.8606498268936924
},
{
"epoch": 0.2247962247962248,
"grad_norm": 0.3530537784099579,
"learning_rate": 9.03854419647208e-06,
"loss": 0.41552734375,
"step": 262,
"token_acc": 0.8654210977947486
},
{
"epoch": 0.22565422565422566,
"grad_norm": 0.2875154912471771,
"learning_rate": 9.03034018690026e-06,
"loss": 0.418701171875,
"step": 263,
"token_acc": 0.8648342742238697
},
{
"epoch": 0.22651222651222652,
"grad_norm": 0.30149972438812256,
"learning_rate": 9.022105080509768e-06,
"loss": 0.432373046875,
"step": 264,
"token_acc": 0.8612747447886625
},
{
"epoch": 0.22737022737022736,
"grad_norm": 0.2742672264575958,
"learning_rate": 9.013838940840056e-06,
"loss": 0.43408203125,
"step": 265,
"token_acc": 0.8600692831171193
},
{
"epoch": 0.22822822822822822,
"grad_norm": 0.31606417894363403,
"learning_rate": 9.00554183167002e-06,
"loss": 0.42236328125,
"step": 266,
"token_acc": 0.8632177753696536
},
{
"epoch": 0.22908622908622908,
"grad_norm": 0.5377671122550964,
"learning_rate": 8.997213817017508e-06,
"loss": 0.432373046875,
"step": 267,
"token_acc": 0.8603348820938024
},
{
"epoch": 0.22994422994422994,
"grad_norm": 0.2777087986469269,
"learning_rate": 8.988854961138818e-06,
"loss": 0.425537109375,
"step": 268,
"token_acc": 0.8631114169141519
},
{
"epoch": 0.2308022308022308,
"grad_norm": 0.2877535820007324,
"learning_rate": 8.98046532852822e-06,
"loss": 0.42333984375,
"step": 269,
"token_acc": 0.8634196437129438
},
{
"epoch": 0.23166023166023167,
"grad_norm": 0.3389730453491211,
"learning_rate": 8.97204498391744e-06,
"loss": 0.442138671875,
"step": 270,
"token_acc": 0.8578030733953601
},
{
"epoch": 0.23251823251823253,
"grad_norm": 0.27342525124549866,
"learning_rate": 8.963593992275167e-06,
"loss": 0.41162109375,
"step": 271,
"token_acc": 0.8666547650313934
},
{
"epoch": 0.23337623337623337,
"grad_norm": 0.37829023599624634,
"learning_rate": 8.95511241880656e-06,
"loss": 0.428466796875,
"step": 272,
"token_acc": 0.8620087523026672
},
{
"epoch": 0.23423423423423423,
"grad_norm": 0.2733011543750763,
"learning_rate": 8.946600328952731e-06,
"loss": 0.4169921875,
"step": 273,
"token_acc": 0.8656288466106636
},
{
"epoch": 0.2350922350922351,
"grad_norm": 0.2832958400249481,
"learning_rate": 8.938057788390248e-06,
"loss": 0.41064453125,
"step": 274,
"token_acc": 0.86768306235851
},
{
"epoch": 0.23595023595023595,
"grad_norm": 0.3167809844017029,
"learning_rate": 8.929484863030631e-06,
"loss": 0.445068359375,
"step": 275,
"token_acc": 0.8570561597926434
},
{
"epoch": 0.23680823680823682,
"grad_norm": 0.4739546477794647,
"learning_rate": 8.920881619019832e-06,
"loss": 0.416748046875,
"step": 276,
"token_acc": 0.8656276045192027
},
{
"epoch": 0.23766623766623768,
"grad_norm": 0.34427839517593384,
"learning_rate": 8.91224812273774e-06,
"loss": 0.43115234375,
"step": 277,
"token_acc": 0.8609857277395802
},
{
"epoch": 0.2385242385242385,
"grad_norm": 0.26988452672958374,
"learning_rate": 8.903584440797652e-06,
"loss": 0.422607421875,
"step": 278,
"token_acc": 0.8637565348758622
},
{
"epoch": 0.23938223938223938,
"grad_norm": 0.3095287084579468,
"learning_rate": 8.894890640045779e-06,
"loss": 0.41455078125,
"step": 279,
"token_acc": 0.8659597385212925
},
{
"epoch": 0.24024024024024024,
"grad_norm": 0.33578675985336304,
"learning_rate": 8.886166787560711e-06,
"loss": 0.409912109375,
"step": 280,
"token_acc": 0.8670272675999264
},
{
"epoch": 0.2410982410982411,
"grad_norm": 0.28938567638397217,
"learning_rate": 8.877412950652907e-06,
"loss": 0.43115234375,
"step": 281,
"token_acc": 0.8613937329137703
},
{
"epoch": 0.24195624195624196,
"grad_norm": 0.2799420952796936,
"learning_rate": 8.868629196864182e-06,
"loss": 0.4306640625,
"step": 282,
"token_acc": 0.8604864965444499
},
{
"epoch": 0.24281424281424283,
"grad_norm": 0.27353528141975403,
"learning_rate": 8.859815593967176e-06,
"loss": 0.427490234375,
"step": 283,
"token_acc": 0.861573064451245
},
{
"epoch": 0.24367224367224366,
"grad_norm": 0.31159836053848267,
"learning_rate": 8.850972209964837e-06,
"loss": 0.433349609375,
"step": 284,
"token_acc": 0.8612517098583524
},
{
"epoch": 0.24453024453024452,
"grad_norm": 0.29676052927970886,
"learning_rate": 8.842099113089893e-06,
"loss": 0.427490234375,
"step": 285,
"token_acc": 0.8618771352765865
},
{
"epoch": 0.24538824538824539,
"grad_norm": 0.295328825712204,
"learning_rate": 8.833196371804327e-06,
"loss": 0.422607421875,
"step": 286,
"token_acc": 0.8638266581426168
},
{
"epoch": 0.24624624624624625,
"grad_norm": 0.282305508852005,
"learning_rate": 8.824264054798852e-06,
"loss": 0.416259765625,
"step": 287,
"token_acc": 0.865435456238805
},
{
"epoch": 0.2471042471042471,
"grad_norm": 0.3199853003025055,
"learning_rate": 8.815302230992374e-06,
"loss": 0.419189453125,
"step": 288,
"token_acc": 0.8649335633740404
},
{
"epoch": 0.24796224796224797,
"grad_norm": 0.36096251010894775,
"learning_rate": 8.806310969531463e-06,
"loss": 0.4267578125,
"step": 289,
"token_acc": 0.8616157788497647
},
{
"epoch": 0.2488202488202488,
"grad_norm": 0.2619752287864685,
"learning_rate": 8.797290339789827e-06,
"loss": 0.43359375,
"step": 290,
"token_acc": 0.8608507669849342
},
{
"epoch": 0.24967824967824967,
"grad_norm": 0.2661902606487274,
"learning_rate": 8.788240411367767e-06,
"loss": 0.412353515625,
"step": 291,
"token_acc": 0.8666291741914027
},
{
"epoch": 0.25053625053625056,
"grad_norm": 0.4570387899875641,
"learning_rate": 8.779161254091638e-06,
"loss": 0.429931640625,
"step": 292,
"token_acc": 0.8613880917923648
},
{
"epoch": 0.25139425139425137,
"grad_norm": 0.3083130717277527,
"learning_rate": 8.770052938013323e-06,
"loss": 0.42529296875,
"step": 293,
"token_acc": 0.8630682286260359
},
{
"epoch": 0.25225225225225223,
"grad_norm": 0.33393871784210205,
"learning_rate": 8.760915533409682e-06,
"loss": 0.430908203125,
"step": 294,
"token_acc": 0.8609906923371159
},
{
"epoch": 0.2531102531102531,
"grad_norm": 0.4008459448814392,
"learning_rate": 8.751749110782013e-06,
"loss": 0.425048828125,
"step": 295,
"token_acc": 0.8623376252439027
},
{
"epoch": 0.25396825396825395,
"grad_norm": 0.2997443675994873,
"learning_rate": 8.742553740855507e-06,
"loss": 0.435546875,
"step": 296,
"token_acc": 0.8595860250262032
},
{
"epoch": 0.2548262548262548,
"grad_norm": 0.3301294445991516,
"learning_rate": 8.733329494578703e-06,
"loss": 0.421630859375,
"step": 297,
"token_acc": 0.8644136720907182
},
{
"epoch": 0.2556842556842557,
"grad_norm": 0.2914096713066101,
"learning_rate": 8.724076443122945e-06,
"loss": 0.445068359375,
"step": 298,
"token_acc": 0.8568526303583996
},
{
"epoch": 0.25654225654225654,
"grad_norm": 0.31789496541023254,
"learning_rate": 8.714794657881818e-06,
"loss": 0.427734375,
"step": 299,
"token_acc": 0.861181177553491
},
{
"epoch": 0.2574002574002574,
"grad_norm": 0.3003808557987213,
"learning_rate": 8.705484210470623e-06,
"loss": 0.4130859375,
"step": 300,
"token_acc": 0.86617728719442
},
{
"epoch": 0.25825825825825827,
"grad_norm": 0.28610342741012573,
"learning_rate": 8.696145172725796e-06,
"loss": 0.42431640625,
"step": 301,
"token_acc": 0.8632849043782053
},
{
"epoch": 0.25911625911625913,
"grad_norm": 0.2947930097579956,
"learning_rate": 8.686777616704375e-06,
"loss": 0.43310546875,
"step": 302,
"token_acc": 0.860834719684972
},
{
"epoch": 0.25997425997426,
"grad_norm": 0.37548524141311646,
"learning_rate": 8.67738161468343e-06,
"loss": 0.420166015625,
"step": 303,
"token_acc": 0.8640671640357056
},
{
"epoch": 0.26083226083226085,
"grad_norm": 0.2651106119155884,
"learning_rate": 8.667957239159515e-06,
"loss": 0.42236328125,
"step": 304,
"token_acc": 0.8629914651632773
},
{
"epoch": 0.2616902616902617,
"grad_norm": 0.3956770598888397,
"learning_rate": 8.658504562848104e-06,
"loss": 0.416748046875,
"step": 305,
"token_acc": 0.8649268797085036
},
{
"epoch": 0.2625482625482625,
"grad_norm": 0.3101435601711273,
"learning_rate": 8.649023658683031e-06,
"loss": 0.431640625,
"step": 306,
"token_acc": 0.8618792360148243
},
{
"epoch": 0.2634062634062634,
"grad_norm": 0.3215412199497223,
"learning_rate": 8.639514599815928e-06,
"loss": 0.404296875,
"step": 307,
"token_acc": 0.8686906891640934
},
{
"epoch": 0.26426426426426425,
"grad_norm": 0.28221818804740906,
"learning_rate": 8.629977459615655e-06,
"loss": 0.417236328125,
"step": 308,
"token_acc": 0.8651770568188901
},
{
"epoch": 0.2651222651222651,
"grad_norm": 0.2966579794883728,
"learning_rate": 8.620412311667746e-06,
"loss": 0.4208984375,
"step": 309,
"token_acc": 0.8643197137295059
},
{
"epoch": 0.265980265980266,
"grad_norm": 0.3312734365463257,
"learning_rate": 8.610819229773827e-06,
"loss": 0.4228515625,
"step": 310,
"token_acc": 0.8635979455171965
},
{
"epoch": 0.26683826683826684,
"grad_norm": 0.27181246876716614,
"learning_rate": 8.601198287951059e-06,
"loss": 0.432373046875,
"step": 311,
"token_acc": 0.8606933037875139
},
{
"epoch": 0.2676962676962677,
"grad_norm": 0.2824406921863556,
"learning_rate": 8.591549560431558e-06,
"loss": 0.412353515625,
"step": 312,
"token_acc": 0.8666222116990656
},
{
"epoch": 0.26855426855426856,
"grad_norm": 0.3221742808818817,
"learning_rate": 8.581873121661825e-06,
"loss": 0.425537109375,
"step": 313,
"token_acc": 0.8628089370735573
},
{
"epoch": 0.2694122694122694,
"grad_norm": 0.3058890402317047,
"learning_rate": 8.572169046302174e-06,
"loss": 0.431396484375,
"step": 314,
"token_acc": 0.8607610967953286
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.3190813958644867,
"learning_rate": 8.562437409226156e-06,
"loss": 0.403564453125,
"step": 315,
"token_acc": 0.8696512239363305
},
{
"epoch": 0.27112827112827115,
"grad_norm": 0.32738161087036133,
"learning_rate": 8.552678285519973e-06,
"loss": 0.412841796875,
"step": 316,
"token_acc": 0.8670594776720139
},
{
"epoch": 0.271986271986272,
"grad_norm": 0.29337015748023987,
"learning_rate": 8.542891750481913e-06,
"loss": 0.420166015625,
"step": 317,
"token_acc": 0.8636410422667469
},
{
"epoch": 0.2728442728442728,
"grad_norm": 0.29130426049232483,
"learning_rate": 8.533077879621754e-06,
"loss": 0.420166015625,
"step": 318,
"token_acc": 0.8637828170239334
},
{
"epoch": 0.2737022737022737,
"grad_norm": 0.3404424488544464,
"learning_rate": 8.523236748660193e-06,
"loss": 0.423095703125,
"step": 319,
"token_acc": 0.8641675218416308
},
{
"epoch": 0.27456027456027454,
"grad_norm": 0.2795577049255371,
"learning_rate": 8.513368433528255e-06,
"loss": 0.41748046875,
"step": 320,
"token_acc": 0.8645699931041276
},
{
"epoch": 0.2754182754182754,
"grad_norm": 0.2919906973838806,
"learning_rate": 8.503473010366713e-06,
"loss": 0.4326171875,
"step": 321,
"token_acc": 0.8596956770011085
},
{
"epoch": 0.27627627627627627,
"grad_norm": 0.3152264654636383,
"learning_rate": 8.493550555525492e-06,
"loss": 0.433349609375,
"step": 322,
"token_acc": 0.8612057608053099
},
{
"epoch": 0.27713427713427713,
"grad_norm": 0.3046569228172302,
"learning_rate": 8.483601145563087e-06,
"loss": 0.425048828125,
"step": 323,
"token_acc": 0.8626004640854696
},
{
"epoch": 0.277992277992278,
"grad_norm": 0.3702789545059204,
"learning_rate": 8.47362485724597e-06,
"loss": 0.41650390625,
"step": 324,
"token_acc": 0.8655047600292064
},
{
"epoch": 0.27885027885027885,
"grad_norm": 0.4033508598804474,
"learning_rate": 8.463621767547998e-06,
"loss": 0.444091796875,
"step": 325,
"token_acc": 0.8575443104716496
},
{
"epoch": 0.2797082797082797,
"grad_norm": 0.2806128263473511,
"learning_rate": 8.45359195364982e-06,
"loss": 0.416748046875,
"step": 326,
"token_acc": 0.8650138979044956
},
{
"epoch": 0.2805662805662806,
"grad_norm": 0.32408013939857483,
"learning_rate": 8.443535492938278e-06,
"loss": 0.420166015625,
"step": 327,
"token_acc": 0.8636033907659756
},
{
"epoch": 0.28142428142428144,
"grad_norm": 0.32515639066696167,
"learning_rate": 8.43345246300581e-06,
"loss": 0.430419921875,
"step": 328,
"token_acc": 0.8611928652051855
},
{
"epoch": 0.2822822822822823,
"grad_norm": 0.2969781756401062,
"learning_rate": 8.423342941649866e-06,
"loss": 0.434326171875,
"step": 329,
"token_acc": 0.8602261482034155
},
{
"epoch": 0.28314028314028317,
"grad_norm": 0.48921525478363037,
"learning_rate": 8.41320700687228e-06,
"loss": 0.42041015625,
"step": 330,
"token_acc": 0.8649948676900652
},
{
"epoch": 0.283998283998284,
"grad_norm": 0.288290411233902,
"learning_rate": 8.403044736878692e-06,
"loss": 0.4208984375,
"step": 331,
"token_acc": 0.864530861478892
},
{
"epoch": 0.28485628485628484,
"grad_norm": 0.3239724636077881,
"learning_rate": 8.392856210077932e-06,
"loss": 0.4326171875,
"step": 332,
"token_acc": 0.8604911277389042
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.31977906823158264,
"learning_rate": 8.382641505081424e-06,
"loss": 0.43505859375,
"step": 333,
"token_acc": 0.8604721429447038
},
{
"epoch": 0.28657228657228656,
"grad_norm": 0.2983318567276001,
"learning_rate": 8.372400700702569e-06,
"loss": 0.41796875,
"step": 334,
"token_acc": 0.864367145902268
},
{
"epoch": 0.2874302874302874,
"grad_norm": 0.2915947437286377,
"learning_rate": 8.36213387595615e-06,
"loss": 0.40966796875,
"step": 335,
"token_acc": 0.8670392902493642
},
{
"epoch": 0.2882882882882883,
"grad_norm": 0.36441272497177124,
"learning_rate": 8.351841110057707e-06,
"loss": 0.435546875,
"step": 336,
"token_acc": 0.8594735058308641
},
{
"epoch": 0.28914628914628915,
"grad_norm": 0.27377113699913025,
"learning_rate": 8.341522482422938e-06,
"loss": 0.435791015625,
"step": 337,
"token_acc": 0.859004367068865
},
{
"epoch": 0.29000429000429,
"grad_norm": 0.3199476897716522,
"learning_rate": 8.331178072667079e-06,
"loss": 0.43359375,
"step": 338,
"token_acc": 0.8601934077755304
},
{
"epoch": 0.2908622908622909,
"grad_norm": 0.2899761497974396,
"learning_rate": 8.320807960604296e-06,
"loss": 0.413818359375,
"step": 339,
"token_acc": 0.8660299447860077
},
{
"epoch": 0.29172029172029174,
"grad_norm": 0.3697011470794678,
"learning_rate": 8.310412226247064e-06,
"loss": 0.4130859375,
"step": 340,
"token_acc": 0.8667535835000577
},
{
"epoch": 0.2925782925782926,
"grad_norm": 0.3079642951488495,
"learning_rate": 8.299990949805551e-06,
"loss": 0.432373046875,
"step": 341,
"token_acc": 0.8617484385186431
},
{
"epoch": 0.29343629343629346,
"grad_norm": 0.304176926612854,
"learning_rate": 8.289544211687003e-06,
"loss": 0.427490234375,
"step": 342,
"token_acc": 0.8618487337368235
},
{
"epoch": 0.29429429429429427,
"grad_norm": 0.29058513045310974,
"learning_rate": 8.279072092495114e-06,
"loss": 0.450439453125,
"step": 343,
"token_acc": 0.8550138582464248
},
{
"epoch": 0.29515229515229513,
"grad_norm": 0.2774716913700104,
"learning_rate": 8.268574673029415e-06,
"loss": 0.432861328125,
"step": 344,
"token_acc": 0.8600389987736091
},
{
"epoch": 0.296010296010296,
"grad_norm": 0.3053390383720398,
"learning_rate": 8.258052034284645e-06,
"loss": 0.437255859375,
"step": 345,
"token_acc": 0.8590779219335402
},
{
"epoch": 0.29686829686829685,
"grad_norm": 0.3205716609954834,
"learning_rate": 8.247504257450128e-06,
"loss": 0.421875,
"step": 346,
"token_acc": 0.8634834290771917
},
{
"epoch": 0.2977262977262977,
"grad_norm": 0.2925533652305603,
"learning_rate": 8.23693142390914e-06,
"loss": 0.42138671875,
"step": 347,
"token_acc": 0.8644739285419111
},
{
"epoch": 0.2985842985842986,
"grad_norm": 0.4072161614894867,
"learning_rate": 8.226333615238292e-06,
"loss": 0.427001953125,
"step": 348,
"token_acc": 0.862811044173086
},
{
"epoch": 0.29944229944229944,
"grad_norm": 0.2827335000038147,
"learning_rate": 8.215710913206894e-06,
"loss": 0.417724609375,
"step": 349,
"token_acc": 0.8643564819785223
},
{
"epoch": 0.3003003003003003,
"grad_norm": 0.2752941846847534,
"learning_rate": 8.205063399776326e-06,
"loss": 0.435546875,
"step": 350,
"token_acc": 0.859170401543283
},
{
"epoch": 0.30115830115830117,
"grad_norm": 0.32525724172592163,
"learning_rate": 8.194391157099403e-06,
"loss": 0.4375,
"step": 351,
"token_acc": 0.8596791058026442
},
{
"epoch": 0.30201630201630203,
"grad_norm": 0.30612438917160034,
"learning_rate": 8.183694267519742e-06,
"loss": 0.43896484375,
"step": 352,
"token_acc": 0.8586553616331049
},
{
"epoch": 0.3028743028743029,
"grad_norm": 0.2770445644855499,
"learning_rate": 8.172972813571132e-06,
"loss": 0.424560546875,
"step": 353,
"token_acc": 0.8631655714075062
},
{
"epoch": 0.30373230373230375,
"grad_norm": 0.2723534107208252,
"learning_rate": 8.162226877976886e-06,
"loss": 0.415771484375,
"step": 354,
"token_acc": 0.8650982965239867
},
{
"epoch": 0.3045903045903046,
"grad_norm": 0.2806825637817383,
"learning_rate": 8.151456543649218e-06,
"loss": 0.433349609375,
"step": 355,
"token_acc": 0.8598273171084829
},
{
"epoch": 0.3054483054483054,
"grad_norm": 0.28828513622283936,
"learning_rate": 8.14066189368859e-06,
"loss": 0.423095703125,
"step": 356,
"token_acc": 0.8635797593457584
},
{
"epoch": 0.3063063063063063,
"grad_norm": 0.28111907839775085,
"learning_rate": 8.129843011383075e-06,
"loss": 0.43359375,
"step": 357,
"token_acc": 0.8606448354797948
},
{
"epoch": 0.30716430716430715,
"grad_norm": 0.2796931564807892,
"learning_rate": 8.118999980207713e-06,
"loss": 0.410400390625,
"step": 358,
"token_acc": 0.8667720416856431
},
{
"epoch": 0.308022308022308,
"grad_norm": 0.27662715315818787,
"learning_rate": 8.108132883823878e-06,
"loss": 0.421875,
"step": 359,
"token_acc": 0.8636113427856548
},
{
"epoch": 0.3088803088803089,
"grad_norm": 0.3314023017883301,
"learning_rate": 8.097241806078616e-06,
"loss": 0.42822265625,
"step": 360,
"token_acc": 0.8621326873127418
},
{
"epoch": 0.30973830973830974,
"grad_norm": 0.2847985029220581,
"learning_rate": 8.086326831004006e-06,
"loss": 0.42626953125,
"step": 361,
"token_acc": 0.8612148324440947
},
{
"epoch": 0.3105963105963106,
"grad_norm": 0.2904377281665802,
"learning_rate": 8.07538804281651e-06,
"loss": 0.431640625,
"step": 362,
"token_acc": 0.8609556749775018
},
{
"epoch": 0.31145431145431146,
"grad_norm": 0.2867021858692169,
"learning_rate": 8.064425525916332e-06,
"loss": 0.421142578125,
"step": 363,
"token_acc": 0.8635489180622234
},
{
"epoch": 0.3123123123123123,
"grad_norm": 0.3181120455265045,
"learning_rate": 8.05343936488675e-06,
"loss": 0.421875,
"step": 364,
"token_acc": 0.8633504275971245
},
{
"epoch": 0.3131703131703132,
"grad_norm": 0.2938002645969391,
"learning_rate": 8.042429644493479e-06,
"loss": 0.417724609375,
"step": 365,
"token_acc": 0.8645204009875833
},
{
"epoch": 0.31402831402831405,
"grad_norm": 0.31147557497024536,
"learning_rate": 8.031396449684005e-06,
"loss": 0.4169921875,
"step": 366,
"token_acc": 0.8649244036489444
},
{
"epoch": 0.3148863148863149,
"grad_norm": 0.30907371640205383,
"learning_rate": 8.020339865586942e-06,
"loss": 0.421875,
"step": 367,
"token_acc": 0.8641379104876975
},
{
"epoch": 0.3157443157443157,
"grad_norm": 0.26018059253692627,
"learning_rate": 8.00925997751136e-06,
"loss": 0.421630859375,
"step": 368,
"token_acc": 0.8642922461673394
},
{
"epoch": 0.3166023166023166,
"grad_norm": 0.2818809151649475,
"learning_rate": 7.998156870946143e-06,
"loss": 0.424072265625,
"step": 369,
"token_acc": 0.863478152466625
},
{
"epoch": 0.31746031746031744,
"grad_norm": 0.30213281512260437,
"learning_rate": 7.987030631559318e-06,
"loss": 0.40625,
"step": 370,
"token_acc": 0.868319543070386
},
{
"epoch": 0.3183183183183183,
"grad_norm": 0.28798431158065796,
"learning_rate": 7.975881345197394e-06,
"loss": 0.412841796875,
"step": 371,
"token_acc": 0.8663304894000965
},
{
"epoch": 0.31917631917631917,
"grad_norm": 0.3620336353778839,
"learning_rate": 7.96470909788471e-06,
"loss": 0.440673828125,
"step": 372,
"token_acc": 0.8588102308457176
},
{
"epoch": 0.32003432003432003,
"grad_norm": 0.29224729537963867,
"learning_rate": 7.953513975822755e-06,
"loss": 0.431396484375,
"step": 373,
"token_acc": 0.8614828345834136
},
{
"epoch": 0.3208923208923209,
"grad_norm": 0.2611728012561798,
"learning_rate": 7.942296065389528e-06,
"loss": 0.43017578125,
"step": 374,
"token_acc": 0.860562192171493
},
{
"epoch": 0.32175032175032175,
"grad_norm": 0.40786322951316833,
"learning_rate": 7.931055453138838e-06,
"loss": 0.41748046875,
"step": 375,
"token_acc": 0.8642663093815542
},
{
"epoch": 0.3226083226083226,
"grad_norm": 0.2994734048843384,
"learning_rate": 7.919792225799664e-06,
"loss": 0.425537109375,
"step": 376,
"token_acc": 0.8628911987346063
},
{
"epoch": 0.3234663234663235,
"grad_norm": 0.3602111339569092,
"learning_rate": 7.908506470275474e-06,
"loss": 0.4228515625,
"step": 377,
"token_acc": 0.8633750299903371
},
{
"epoch": 0.32432432432432434,
"grad_norm": 0.36422574520111084,
"learning_rate": 7.897198273643556e-06,
"loss": 0.4189453125,
"step": 378,
"token_acc": 0.864579499822505
},
{
"epoch": 0.3251823251823252,
"grad_norm": 0.3478303849697113,
"learning_rate": 7.885867723154346e-06,
"loss": 0.42578125,
"step": 379,
"token_acc": 0.8627650224119422
},
{
"epoch": 0.32604032604032607,
"grad_norm": 0.3177792429924011,
"learning_rate": 7.874514906230757e-06,
"loss": 0.41845703125,
"step": 380,
"token_acc": 0.8647462649751946
},
{
"epoch": 0.3268983268983269,
"grad_norm": 0.27790436148643494,
"learning_rate": 7.863139910467501e-06,
"loss": 0.4169921875,
"step": 381,
"token_acc": 0.8645280999603884
},
{
"epoch": 0.32775632775632774,
"grad_norm": 0.28227806091308594,
"learning_rate": 7.851742823630412e-06,
"loss": 0.415771484375,
"step": 382,
"token_acc": 0.8655827114077801
},
{
"epoch": 0.3286143286143286,
"grad_norm": 0.28753653168678284,
"learning_rate": 7.84032373365578e-06,
"loss": 0.4219970703125,
"step": 383,
"token_acc": 0.8639406972229663
},
{
"epoch": 0.32947232947232946,
"grad_norm": 0.2792826294898987,
"learning_rate": 7.828882728649655e-06,
"loss": 0.4150390625,
"step": 384,
"token_acc": 0.8651572381812838
},
{
"epoch": 0.3303303303303303,
"grad_norm": 0.27523496747016907,
"learning_rate": 7.817419896887182e-06,
"loss": 0.41748046875,
"step": 385,
"token_acc": 0.8643428486785026
},
{
"epoch": 0.3311883311883312,
"grad_norm": 0.33246752619743347,
"learning_rate": 7.805935326811913e-06,
"loss": 0.437744140625,
"step": 386,
"token_acc": 0.8585107582037917
},
{
"epoch": 0.33204633204633205,
"grad_norm": 0.287202388048172,
"learning_rate": 7.794429107035124e-06,
"loss": 0.424560546875,
"step": 387,
"token_acc": 0.8635949895660526
},
{
"epoch": 0.3329043329043329,
"grad_norm": 0.29253578186035156,
"learning_rate": 7.782901326335137e-06,
"loss": 0.422119140625,
"step": 388,
"token_acc": 0.8635815595184542
},
{
"epoch": 0.3337623337623338,
"grad_norm": 0.35036778450012207,
"learning_rate": 7.771352073656628e-06,
"loss": 0.425537109375,
"step": 389,
"token_acc": 0.862357175894677
},
{
"epoch": 0.33462033462033464,
"grad_norm": 0.25542062520980835,
"learning_rate": 7.759781438109944e-06,
"loss": 0.418701171875,
"step": 390,
"token_acc": 0.8643610858844032
},
{
"epoch": 0.3354783354783355,
"grad_norm": 0.26359203457832336,
"learning_rate": 7.748189508970419e-06,
"loss": 0.41357421875,
"step": 391,
"token_acc": 0.865563230761386
},
{
"epoch": 0.33633633633633636,
"grad_norm": 0.28748592734336853,
"learning_rate": 7.736576375677676e-06,
"loss": 0.422119140625,
"step": 392,
"token_acc": 0.8639616828226943
},
{
"epoch": 0.33719433719433717,
"grad_norm": 0.2941490113735199,
"learning_rate": 7.724942127834947e-06,
"loss": 0.42724609375,
"step": 393,
"token_acc": 0.8612426827358655
},
{
"epoch": 0.33805233805233803,
"grad_norm": 0.29300469160079956,
"learning_rate": 7.713286855208373e-06,
"loss": 0.42626953125,
"step": 394,
"token_acc": 0.863123458035744
},
{
"epoch": 0.3389103389103389,
"grad_norm": 0.2941628098487854,
"learning_rate": 7.701610647726323e-06,
"loss": 0.411865234375,
"step": 395,
"token_acc": 0.867098092266917
},
{
"epoch": 0.33976833976833976,
"grad_norm": 0.2966812551021576,
"learning_rate": 7.689913595478683e-06,
"loss": 0.42724609375,
"step": 396,
"token_acc": 0.861284196108984
},
{
"epoch": 0.3406263406263406,
"grad_norm": 0.320842981338501,
"learning_rate": 7.678195788716177e-06,
"loss": 0.4267578125,
"step": 397,
"token_acc": 0.8626256965116527
},
{
"epoch": 0.3414843414843415,
"grad_norm": 0.30739083886146545,
"learning_rate": 7.666457317849663e-06,
"loss": 0.42529296875,
"step": 398,
"token_acc": 0.8627222519982289
},
{
"epoch": 0.34234234234234234,
"grad_norm": 0.3250690996646881,
"learning_rate": 7.654698273449435e-06,
"loss": 0.408203125,
"step": 399,
"token_acc": 0.8673611048406757
},
{
"epoch": 0.3432003432003432,
"grad_norm": 0.3004262149333954,
"learning_rate": 7.642918746244528e-06,
"loss": 0.4296875,
"step": 400,
"token_acc": 0.8611569453016488
},
{
"epoch": 0.34405834405834407,
"grad_norm": 0.2825751304626465,
"learning_rate": 7.631118827122013e-06,
"loss": 0.418212890625,
"step": 401,
"token_acc": 0.8640101274594946
},
{
"epoch": 0.34491634491634493,
"grad_norm": 0.31254473328590393,
"learning_rate": 7.619298607126302e-06,
"loss": 0.425537109375,
"step": 402,
"token_acc": 0.8631938266123519
},
{
"epoch": 0.3457743457743458,
"grad_norm": 0.2921868562698364,
"learning_rate": 7.60745817745844e-06,
"loss": 0.41552734375,
"step": 403,
"token_acc": 0.8661184055000404
},
{
"epoch": 0.34663234663234666,
"grad_norm": 0.3001807630062103,
"learning_rate": 7.595597629475402e-06,
"loss": 0.4365234375,
"step": 404,
"token_acc": 0.8585014297140403
},
{
"epoch": 0.3474903474903475,
"grad_norm": 0.29896873235702515,
"learning_rate": 7.583717054689394e-06,
"loss": 0.413818359375,
"step": 405,
"token_acc": 0.8657269041137614
},
{
"epoch": 0.3483483483483483,
"grad_norm": 0.36678025126457214,
"learning_rate": 7.5718165447671365e-06,
"loss": 0.424560546875,
"step": 406,
"token_acc": 0.8627396783299475
},
{
"epoch": 0.3492063492063492,
"grad_norm": 0.29485970735549927,
"learning_rate": 7.559896191529169e-06,
"loss": 0.4306640625,
"step": 407,
"token_acc": 0.8600888600921435
},
{
"epoch": 0.35006435006435005,
"grad_norm": 0.2919752299785614,
"learning_rate": 7.547956086949131e-06,
"loss": 0.42529296875,
"step": 408,
"token_acc": 0.8638425129868096
},
{
"epoch": 0.3509223509223509,
"grad_norm": 0.2772597372531891,
"learning_rate": 7.5359963231530595e-06,
"loss": 0.420166015625,
"step": 409,
"token_acc": 0.8639821663882852
},
{
"epoch": 0.3517803517803518,
"grad_norm": 0.2919415831565857,
"learning_rate": 7.524016992418676e-06,
"loss": 0.424560546875,
"step": 410,
"token_acc": 0.8629090691574609
},
{
"epoch": 0.35263835263835264,
"grad_norm": 0.2867894172668457,
"learning_rate": 7.512018187174672e-06,
"loss": 0.4326171875,
"step": 411,
"token_acc": 0.8605257974722818
},
{
"epoch": 0.3534963534963535,
"grad_norm": 0.3059645891189575,
"learning_rate": 7.500000000000001e-06,
"loss": 0.4228515625,
"step": 412,
"token_acc": 0.8629962185900373
},
{
"epoch": 0.35435435435435436,
"grad_norm": 0.3137739300727844,
"learning_rate": 7.487962523623159e-06,
"loss": 0.42919921875,
"step": 413,
"token_acc": 0.8609549737728388
},
{
"epoch": 0.3552123552123552,
"grad_norm": 0.2837717831134796,
"learning_rate": 7.4759058509214724e-06,
"loss": 0.414306640625,
"step": 414,
"token_acc": 0.8657728866688467
},
{
"epoch": 0.3560703560703561,
"grad_norm": 0.35152533650398254,
"learning_rate": 7.463830074920381e-06,
"loss": 0.43115234375,
"step": 415,
"token_acc": 0.8603900214912119
},
{
"epoch": 0.35692835692835695,
"grad_norm": 0.3622879385948181,
"learning_rate": 7.451735288792716e-06,
"loss": 0.426025390625,
"step": 416,
"token_acc": 0.8618766421090386
},
{
"epoch": 0.3577863577863578,
"grad_norm": 0.2967289090156555,
"learning_rate": 7.43962158585799e-06,
"loss": 0.43408203125,
"step": 417,
"token_acc": 0.8598227153242162
},
{
"epoch": 0.3586443586443586,
"grad_norm": 0.2888059914112091,
"learning_rate": 7.427489059581666e-06,
"loss": 0.448486328125,
"step": 418,
"token_acc": 0.8559363846315348
},
{
"epoch": 0.3595023595023595,
"grad_norm": 0.28090888261795044,
"learning_rate": 7.415337803574449e-06,
"loss": 0.42919921875,
"step": 419,
"token_acc": 0.8605889852444016
},
{
"epoch": 0.36036036036036034,
"grad_norm": 0.31645599007606506,
"learning_rate": 7.403167911591551e-06,
"loss": 0.4169921875,
"step": 420,
"token_acc": 0.8644447992120551
},
{
"epoch": 0.3612183612183612,
"grad_norm": 0.382446825504303,
"learning_rate": 7.390979477531973e-06,
"loss": 0.42236328125,
"step": 421,
"token_acc": 0.8638672675133142
},
{
"epoch": 0.36207636207636207,
"grad_norm": 0.3774675726890564,
"learning_rate": 7.378772595437785e-06,
"loss": 0.426025390625,
"step": 422,
"token_acc": 0.8633789780229759
},
{
"epoch": 0.36293436293436293,
"grad_norm": 0.3114461898803711,
"learning_rate": 7.3665473594933925e-06,
"loss": 0.420166015625,
"step": 423,
"token_acc": 0.8635127463497713
},
{
"epoch": 0.3637923637923638,
"grad_norm": 0.2735271751880646,
"learning_rate": 7.354303864024812e-06,
"loss": 0.427490234375,
"step": 424,
"token_acc": 0.8626561961587986
},
{
"epoch": 0.36465036465036466,
"grad_norm": 0.29256993532180786,
"learning_rate": 7.342042203498952e-06,
"loss": 0.43505859375,
"step": 425,
"token_acc": 0.8598236219062487
},
{
"epoch": 0.3655083655083655,
"grad_norm": 0.32714495062828064,
"learning_rate": 7.3297624725228674e-06,
"loss": 0.419677734375,
"step": 426,
"token_acc": 0.8647328487109456
},
{
"epoch": 0.3663663663663664,
"grad_norm": 0.2921735942363739,
"learning_rate": 7.3174647658430475e-06,
"loss": 0.415283203125,
"step": 427,
"token_acc": 0.8658639537824117
},
{
"epoch": 0.36722436722436724,
"grad_norm": 0.3107047379016876,
"learning_rate": 7.3051491783446705e-06,
"loss": 0.410400390625,
"step": 428,
"token_acc": 0.8672357931131635
},
{
"epoch": 0.3680823680823681,
"grad_norm": 0.43121880292892456,
"learning_rate": 7.29281580505088e-06,
"loss": 0.433349609375,
"step": 429,
"token_acc": 0.8608842947468954
},
{
"epoch": 0.36894036894036897,
"grad_norm": 0.3090295195579529,
"learning_rate": 7.280464741122047e-06,
"loss": 0.421875,
"step": 430,
"token_acc": 0.8633477764159068
},
{
"epoch": 0.3697983697983698,
"grad_norm": 0.3306712806224823,
"learning_rate": 7.26809608185504e-06,
"loss": 0.435302734375,
"step": 431,
"token_acc": 0.8597069146702732
},
{
"epoch": 0.37065637065637064,
"grad_norm": 0.3319445550441742,
"learning_rate": 7.2557099226824875e-06,
"loss": 0.440185546875,
"step": 432,
"token_acc": 0.8580366356017717
},
{
"epoch": 0.3715143715143715,
"grad_norm": 0.4724389612674713,
"learning_rate": 7.243306359172041e-06,
"loss": 0.4296875,
"step": 433,
"token_acc": 0.8612393033288307
},
{
"epoch": 0.37237237237237236,
"grad_norm": 0.27391496300697327,
"learning_rate": 7.230885487025635e-06,
"loss": 0.423095703125,
"step": 434,
"token_acc": 0.8623588650353762
},
{
"epoch": 0.3732303732303732,
"grad_norm": 0.31295040249824524,
"learning_rate": 7.218447402078759e-06,
"loss": 0.43310546875,
"step": 435,
"token_acc": 0.8611159254509111
},
{
"epoch": 0.3740883740883741,
"grad_norm": 0.32576873898506165,
"learning_rate": 7.205992200299704e-06,
"loss": 0.428955078125,
"step": 436,
"token_acc": 0.8624324857948904
},
{
"epoch": 0.37494637494637495,
"grad_norm": 0.5096105933189392,
"learning_rate": 7.193519977788834e-06,
"loss": 0.406982421875,
"step": 437,
"token_acc": 0.8677498067189938
},
{
"epoch": 0.3758043758043758,
"grad_norm": 0.29668256640434265,
"learning_rate": 7.181030830777838e-06,
"loss": 0.42041015625,
"step": 438,
"token_acc": 0.863582698352684
},
{
"epoch": 0.3766623766623767,
"grad_norm": 0.27826017141342163,
"learning_rate": 7.1685248556289865e-06,
"loss": 0.40869140625,
"step": 439,
"token_acc": 0.8671674371920951
},
{
"epoch": 0.37752037752037754,
"grad_norm": 0.27628570795059204,
"learning_rate": 7.1560021488343956e-06,
"loss": 0.4208984375,
"step": 440,
"token_acc": 0.863249857416913
},
{
"epoch": 0.3783783783783784,
"grad_norm": 0.2907283902168274,
"learning_rate": 7.143462807015271e-06,
"loss": 0.39697265625,
"step": 441,
"token_acc": 0.8707495300153913
},
{
"epoch": 0.37923637923637926,
"grad_norm": 0.31003352999687195,
"learning_rate": 7.130906926921176e-06,
"loss": 0.42138671875,
"step": 442,
"token_acc": 0.8637613179118976
},
{
"epoch": 0.38009438009438007,
"grad_norm": 0.4362795948982239,
"learning_rate": 7.118334605429272e-06,
"loss": 0.410888671875,
"step": 443,
"token_acc": 0.8663865218408939
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.388886421918869,
"learning_rate": 7.10574593954358e-06,
"loss": 0.411865234375,
"step": 444,
"token_acc": 0.8668051535804313
},
{
"epoch": 0.3818103818103818,
"grad_norm": 0.28607437014579773,
"learning_rate": 7.093141026394231e-06,
"loss": 0.43017578125,
"step": 445,
"token_acc": 0.8618197152919455
},
{
"epoch": 0.38266838266838266,
"grad_norm": 0.31647562980651855,
"learning_rate": 7.080519963236706e-06,
"loss": 0.424072265625,
"step": 446,
"token_acc": 0.8630563826102832
},
{
"epoch": 0.3835263835263835,
"grad_norm": 0.2860400080680847,
"learning_rate": 7.067882847451107e-06,
"loss": 0.419189453125,
"step": 447,
"token_acc": 0.8656138751039955
},
{
"epoch": 0.3843843843843844,
"grad_norm": 0.3233451843261719,
"learning_rate": 7.055229776541384e-06,
"loss": 0.42626953125,
"step": 448,
"token_acc": 0.8624596659428655
},
{
"epoch": 0.38524238524238524,
"grad_norm": 0.3029963970184326,
"learning_rate": 7.042560848134592e-06,
"loss": 0.42626953125,
"step": 449,
"token_acc": 0.8617070662121306
},
{
"epoch": 0.3861003861003861,
"grad_norm": 0.3818403482437134,
"learning_rate": 7.029876159980145e-06,
"loss": 0.4111328125,
"step": 450,
"token_acc": 0.8668188138348728
},
{
"epoch": 0.38695838695838697,
"grad_norm": 0.32453271746635437,
"learning_rate": 7.017175809949044e-06,
"loss": 0.415283203125,
"step": 451,
"token_acc": 0.8653696180892124
},
{
"epoch": 0.38781638781638783,
"grad_norm": 0.27507954835891724,
"learning_rate": 7.004459896033137e-06,
"loss": 0.427734375,
"step": 452,
"token_acc": 0.8626328579131244
},
{
"epoch": 0.3886743886743887,
"grad_norm": 0.2704783082008362,
"learning_rate": 6.9917285163443596e-06,
"loss": 0.443603515625,
"step": 453,
"token_acc": 0.8566695544198688
},
{
"epoch": 0.38953238953238956,
"grad_norm": 0.361786425113678,
"learning_rate": 6.978981769113975e-06,
"loss": 0.406982421875,
"step": 454,
"token_acc": 0.8676819311051491
},
{
"epoch": 0.39039039039039036,
"grad_norm": 0.2781888544559479,
"learning_rate": 6.966219752691814e-06,
"loss": 0.413818359375,
"step": 455,
"token_acc": 0.8651284655693806
},
{
"epoch": 0.3912483912483912,
"grad_norm": 0.41885700821876526,
"learning_rate": 6.953442565545525e-06,
"loss": 0.419189453125,
"step": 456,
"token_acc": 0.8643575506441669
},
{
"epoch": 0.3921063921063921,
"grad_norm": 0.2842484414577484,
"learning_rate": 6.940650306259806e-06,
"loss": 0.41650390625,
"step": 457,
"token_acc": 0.8651691193086337
},
{
"epoch": 0.39296439296439295,
"grad_norm": 0.3224317729473114,
"learning_rate": 6.927843073535645e-06,
"loss": 0.4111328125,
"step": 458,
"token_acc": 0.8667047228398957
},
{
"epoch": 0.3938223938223938,
"grad_norm": 0.288857102394104,
"learning_rate": 6.915020966189566e-06,
"loss": 0.41845703125,
"step": 459,
"token_acc": 0.8642539516420452
},
{
"epoch": 0.3946803946803947,
"grad_norm": 0.2869710624217987,
"learning_rate": 6.902184083152856e-06,
"loss": 0.42041015625,
"step": 460,
"token_acc": 0.8636609554214343
},
{
"epoch": 0.39553839553839554,
"grad_norm": 0.2962559759616852,
"learning_rate": 6.889332523470808e-06,
"loss": 0.4443359375,
"step": 461,
"token_acc": 0.8566909519052762
},
{
"epoch": 0.3963963963963964,
"grad_norm": 0.41291236877441406,
"learning_rate": 6.876466386301953e-06,
"loss": 0.4296875,
"step": 462,
"token_acc": 0.8616678297049096
},
{
"epoch": 0.39725439725439726,
"grad_norm": 0.48691433668136597,
"learning_rate": 6.8635857709173025e-06,
"loss": 0.419921875,
"step": 463,
"token_acc": 0.8636058094944241
},
{
"epoch": 0.3981123981123981,
"grad_norm": 0.30880242586135864,
"learning_rate": 6.850690776699574e-06,
"loss": 0.407958984375,
"step": 464,
"token_acc": 0.8677704859144227
},
{
"epoch": 0.398970398970399,
"grad_norm": 0.2732425332069397,
"learning_rate": 6.837781503142425e-06,
"loss": 0.426025390625,
"step": 465,
"token_acc": 0.8619937801889473
},
{
"epoch": 0.39982839982839985,
"grad_norm": 0.5357620716094971,
"learning_rate": 6.8248580498496895e-06,
"loss": 0.423583984375,
"step": 466,
"token_acc": 0.8623165677037603
},
{
"epoch": 0.4006864006864007,
"grad_norm": 0.3567543923854828,
"learning_rate": 6.811920516534616e-06,
"loss": 0.4337158203125,
"step": 467,
"token_acc": 0.8607761147510746
},
{
"epoch": 0.4015444015444015,
"grad_norm": 0.312417596578598,
"learning_rate": 6.798969003019076e-06,
"loss": 0.420166015625,
"step": 468,
"token_acc": 0.8649994542826683
},
{
"epoch": 0.4024024024024024,
"grad_norm": 0.3167417645454407,
"learning_rate": 6.786003609232816e-06,
"loss": 0.418212890625,
"step": 469,
"token_acc": 0.8652817576730806
},
{
"epoch": 0.40326040326040324,
"grad_norm": 0.29941660165786743,
"learning_rate": 6.773024435212678e-06,
"loss": 0.4208984375,
"step": 470,
"token_acc": 0.8639409832813086
},
{
"epoch": 0.4041184041184041,
"grad_norm": 0.40100914239883423,
"learning_rate": 6.760031581101828e-06,
"loss": 0.428955078125,
"step": 471,
"token_acc": 0.86214893998633
},
{
"epoch": 0.40497640497640497,
"grad_norm": 0.29488709568977356,
"learning_rate": 6.747025147148978e-06,
"loss": 0.420654296875,
"step": 472,
"token_acc": 0.8645620687165905
},
{
"epoch": 0.40583440583440583,
"grad_norm": 0.2635532021522522,
"learning_rate": 6.734005233707624e-06,
"loss": 0.4140625,
"step": 473,
"token_acc": 0.8661044469208886
},
{
"epoch": 0.4066924066924067,
"grad_norm": 0.2757095396518707,
"learning_rate": 6.720971941235264e-06,
"loss": 0.421142578125,
"step": 474,
"token_acc": 0.863422756479095
},
{
"epoch": 0.40755040755040756,
"grad_norm": 0.30702444911003113,
"learning_rate": 6.70792537029262e-06,
"loss": 0.41259765625,
"step": 475,
"token_acc": 0.8665416599197983
},
{
"epoch": 0.4084084084084084,
"grad_norm": 0.2938397228717804,
"learning_rate": 6.694865621542873e-06,
"loss": 0.424560546875,
"step": 476,
"token_acc": 0.8630716849176405
},
{
"epoch": 0.4092664092664093,
"grad_norm": 0.3684979975223541,
"learning_rate": 6.681792795750876e-06,
"loss": 0.404541015625,
"step": 477,
"token_acc": 0.8691710726236376
},
{
"epoch": 0.41012441012441014,
"grad_norm": 0.4328111708164215,
"learning_rate": 6.668706993782381e-06,
"loss": 0.424072265625,
"step": 478,
"token_acc": 0.8632107505427032
},
{
"epoch": 0.410982410982411,
"grad_norm": 0.28654247522354126,
"learning_rate": 6.655608316603257e-06,
"loss": 0.419677734375,
"step": 479,
"token_acc": 0.8640558463478825
},
{
"epoch": 0.4118404118404118,
"grad_norm": 0.3132862448692322,
"learning_rate": 6.64249686527872e-06,
"loss": 0.413818359375,
"step": 480,
"token_acc": 0.8654621401367787
},
{
"epoch": 0.4126984126984127,
"grad_norm": 0.3217681646347046,
"learning_rate": 6.629372740972545e-06,
"loss": 0.4169921875,
"step": 481,
"token_acc": 0.8642020548863911
},
{
"epoch": 0.41355641355641354,
"grad_norm": 0.3765645921230316,
"learning_rate": 6.616236044946283e-06,
"loss": 0.429931640625,
"step": 482,
"token_acc": 0.8613728937348264
},
{
"epoch": 0.4144144144144144,
"grad_norm": 0.30360957980155945,
"learning_rate": 6.603086878558492e-06,
"loss": 0.406005859375,
"step": 483,
"token_acc": 0.8682184843493125
},
{
"epoch": 0.41527241527241526,
"grad_norm": 0.3170628547668457,
"learning_rate": 6.589925343263941e-06,
"loss": 0.4296875,
"step": 484,
"token_acc": 0.8610683087974459
},
{
"epoch": 0.4161304161304161,
"grad_norm": 0.37134185433387756,
"learning_rate": 6.576751540612835e-06,
"loss": 0.42041015625,
"step": 485,
"token_acc": 0.865468744085295
},
{
"epoch": 0.416988416988417,
"grad_norm": 0.2947823107242584,
"learning_rate": 6.563565572250036e-06,
"loss": 0.421630859375,
"step": 486,
"token_acc": 0.8636148880916772
},
{
"epoch": 0.41784641784641785,
"grad_norm": 0.32601526379585266,
"learning_rate": 6.550367539914264e-06,
"loss": 0.42724609375,
"step": 487,
"token_acc": 0.8623716990591023
},
{
"epoch": 0.4187044187044187,
"grad_norm": 0.3742155432701111,
"learning_rate": 6.537157545437326e-06,
"loss": 0.41259765625,
"step": 488,
"token_acc": 0.8659029294468573
},
{
"epoch": 0.4195624195624196,
"grad_norm": 0.3504475951194763,
"learning_rate": 6.523935690743321e-06,
"loss": 0.4228515625,
"step": 489,
"token_acc": 0.8636904826301324
},
{
"epoch": 0.42042042042042044,
"grad_norm": 0.33060625195503235,
"learning_rate": 6.510702077847864e-06,
"loss": 0.435546875,
"step": 490,
"token_acc": 0.8600225913722529
},
{
"epoch": 0.4212784212784213,
"grad_norm": 0.3173463046550751,
"learning_rate": 6.497456808857286e-06,
"loss": 0.435546875,
"step": 491,
"token_acc": 0.8604880763776945
},
{
"epoch": 0.42213642213642216,
"grad_norm": 0.31517285108566284,
"learning_rate": 6.48419998596786e-06,
"loss": 0.424072265625,
"step": 492,
"token_acc": 0.8624595241033597
},
{
"epoch": 0.42299442299442297,
"grad_norm": 0.4236738085746765,
"learning_rate": 6.470931711464994e-06,
"loss": 0.4189453125,
"step": 493,
"token_acc": 0.8648304181510655
},
{
"epoch": 0.42385242385242383,
"grad_norm": 0.2980448603630066,
"learning_rate": 6.4576520877224644e-06,
"loss": 0.41162109375,
"step": 494,
"token_acc": 0.86702927392545
},
{
"epoch": 0.4247104247104247,
"grad_norm": 0.30343005061149597,
"learning_rate": 6.444361217201609e-06,
"loss": 0.433837890625,
"step": 495,
"token_acc": 0.8596316220741743
},
{
"epoch": 0.42556842556842556,
"grad_norm": 0.2810531556606293,
"learning_rate": 6.431059202450542e-06,
"loss": 0.394287109375,
"step": 496,
"token_acc": 0.8710522037829573
},
{
"epoch": 0.4264264264264264,
"grad_norm": 0.2753387689590454,
"learning_rate": 6.4177461461033675e-06,
"loss": 0.415283203125,
"step": 497,
"token_acc": 0.8667317945933436
},
{
"epoch": 0.4272844272844273,
"grad_norm": 0.28141921758651733,
"learning_rate": 6.4044221508793745e-06,
"loss": 0.427001953125,
"step": 498,
"token_acc": 0.8620292660768748
},
{
"epoch": 0.42814242814242814,
"grad_norm": 0.37034013867378235,
"learning_rate": 6.391087319582264e-06,
"loss": 0.40771484375,
"step": 499,
"token_acc": 0.8673679823091288
},
{
"epoch": 0.429000429000429,
"grad_norm": 0.3202304542064667,
"learning_rate": 6.377741755099334e-06,
"loss": 0.41796875,
"step": 500,
"token_acc": 0.8650470133946994
},
{
"epoch": 0.42985842985842987,
"grad_norm": 0.31799107789993286,
"learning_rate": 6.364385560400703e-06,
"loss": 0.42529296875,
"step": 501,
"token_acc": 0.8632238871242461
},
{
"epoch": 0.43071643071643073,
"grad_norm": 0.2863190472126007,
"learning_rate": 6.351018838538508e-06,
"loss": 0.4111328125,
"step": 502,
"token_acc": 0.8666314106129861
},
{
"epoch": 0.4315744315744316,
"grad_norm": 0.35236307978630066,
"learning_rate": 6.337641692646106e-06,
"loss": 0.433837890625,
"step": 503,
"token_acc": 0.8612089935409659
},
{
"epoch": 0.43243243243243246,
"grad_norm": 0.33954450488090515,
"learning_rate": 6.324254225937288e-06,
"loss": 0.41552734375,
"step": 504,
"token_acc": 0.8660511194093474
},
{
"epoch": 0.43329043329043326,
"grad_norm": 0.3274078965187073,
"learning_rate": 6.3108565417054715e-06,
"loss": 0.421142578125,
"step": 505,
"token_acc": 0.8637101862694171
},
{
"epoch": 0.4341484341484341,
"grad_norm": 0.4209599494934082,
"learning_rate": 6.297448743322918e-06,
"loss": 0.429443359375,
"step": 506,
"token_acc": 0.8614532845776733
},
{
"epoch": 0.435006435006435,
"grad_norm": 0.2969057559967041,
"learning_rate": 6.284030934239917e-06,
"loss": 0.4296875,
"step": 507,
"token_acc": 0.8618715702179741
},
{
"epoch": 0.43586443586443585,
"grad_norm": 0.3699609637260437,
"learning_rate": 6.270603217984002e-06,
"loss": 0.41943359375,
"step": 508,
"token_acc": 0.8639296283708636
},
{
"epoch": 0.4367224367224367,
"grad_norm": 0.34718459844589233,
"learning_rate": 6.257165698159149e-06,
"loss": 0.433349609375,
"step": 509,
"token_acc": 0.8598112426851615
},
{
"epoch": 0.4375804375804376,
"grad_norm": 0.28890863060951233,
"learning_rate": 6.243718478444969e-06,
"loss": 0.433349609375,
"step": 510,
"token_acc": 0.8606054698039735
},
{
"epoch": 0.43843843843843844,
"grad_norm": 0.31021833419799805,
"learning_rate": 6.2302616625959185e-06,
"loss": 0.425048828125,
"step": 511,
"token_acc": 0.8623897085325062
},
{
"epoch": 0.4392964392964393,
"grad_norm": 0.2952280640602112,
"learning_rate": 6.2167953544404955e-06,
"loss": 0.404296875,
"step": 512,
"token_acc": 0.8685989954799906
},
{
"epoch": 0.44015444015444016,
"grad_norm": 0.32835862040519714,
"learning_rate": 6.203319657880437e-06,
"loss": 0.42138671875,
"step": 513,
"token_acc": 0.8629502293654742
},
{
"epoch": 0.441012441012441,
"grad_norm": 0.28275251388549805,
"learning_rate": 6.189834676889913e-06,
"loss": 0.43505859375,
"step": 514,
"token_acc": 0.8598334888624726
},
{
"epoch": 0.4418704418704419,
"grad_norm": 0.26258227229118347,
"learning_rate": 6.176340515514738e-06,
"loss": 0.424560546875,
"step": 515,
"token_acc": 0.862342154817124
},
{
"epoch": 0.44272844272844275,
"grad_norm": 0.3214159309864044,
"learning_rate": 6.162837277871553e-06,
"loss": 0.41064453125,
"step": 516,
"token_acc": 0.8664867184933283
},
{
"epoch": 0.4435864435864436,
"grad_norm": 0.33965152502059937,
"learning_rate": 6.149325068147029e-06,
"loss": 0.418701171875,
"step": 517,
"token_acc": 0.8648304969048278
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.2621113657951355,
"learning_rate": 6.135803990597066e-06,
"loss": 0.416748046875,
"step": 518,
"token_acc": 0.8661370297727924
},
{
"epoch": 0.4453024453024453,
"grad_norm": 0.3774579167366028,
"learning_rate": 6.122274149545984e-06,
"loss": 0.42041015625,
"step": 519,
"token_acc": 0.8650384210550092
},
{
"epoch": 0.44616044616044614,
"grad_norm": 0.8083230257034302,
"learning_rate": 6.108735649385714e-06,
"loss": 0.4287109375,
"step": 520,
"token_acc": 0.8609615911947808
},
{
"epoch": 0.447018447018447,
"grad_norm": 0.3356691002845764,
"learning_rate": 6.095188594575008e-06,
"loss": 0.42431640625,
"step": 521,
"token_acc": 0.8630834450719868
},
{
"epoch": 0.44787644787644787,
"grad_norm": 0.49074333906173706,
"learning_rate": 6.081633089638616e-06,
"loss": 0.41455078125,
"step": 522,
"token_acc": 0.8670473434692649
},
{
"epoch": 0.44873444873444873,
"grad_norm": 0.2920239269733429,
"learning_rate": 6.068069239166486e-06,
"loss": 0.429443359375,
"step": 523,
"token_acc": 0.8609085373973879
},
{
"epoch": 0.4495924495924496,
"grad_norm": 0.2840779721736908,
"learning_rate": 6.054497147812962e-06,
"loss": 0.42236328125,
"step": 524,
"token_acc": 0.862967362985908
},
{
"epoch": 0.45045045045045046,
"grad_norm": 0.2790270149707794,
"learning_rate": 6.04091692029597e-06,
"loss": 0.4248046875,
"step": 525,
"token_acc": 0.8626141416294594
},
{
"epoch": 0.4513084513084513,
"grad_norm": 0.2798489034175873,
"learning_rate": 6.02732866139621e-06,
"loss": 0.411865234375,
"step": 526,
"token_acc": 0.8662072555926823
},
{
"epoch": 0.4521664521664522,
"grad_norm": 0.5632247924804688,
"learning_rate": 6.013732475956352e-06,
"loss": 0.419921875,
"step": 527,
"token_acc": 0.8642938195410739
},
{
"epoch": 0.45302445302445304,
"grad_norm": 0.290154367685318,
"learning_rate": 6.000128468880223e-06,
"loss": 0.4287109375,
"step": 528,
"token_acc": 0.8617370491908175
},
{
"epoch": 0.4538824538824539,
"grad_norm": 0.31333526968955994,
"learning_rate": 5.986516745132e-06,
"loss": 0.416015625,
"step": 529,
"token_acc": 0.8647680732144888
},
{
"epoch": 0.4547404547404547,
"grad_norm": 0.2911708652973175,
"learning_rate": 5.972897409735403e-06,
"loss": 0.435546875,
"step": 530,
"token_acc": 0.8590874926019303
},
{
"epoch": 0.4555984555984556,
"grad_norm": 0.30912768840789795,
"learning_rate": 5.959270567772874e-06,
"loss": 0.412353515625,
"step": 531,
"token_acc": 0.8658990706703001
},
{
"epoch": 0.45645645645645644,
"grad_norm": 0.2619702219963074,
"learning_rate": 5.945636324384776e-06,
"loss": 0.4052734375,
"step": 532,
"token_acc": 0.8672058471320894
},
{
"epoch": 0.4573144573144573,
"grad_norm": 0.3613792359828949,
"learning_rate": 5.931994784768582e-06,
"loss": 0.4345703125,
"step": 533,
"token_acc": 0.8604419788206061
},
{
"epoch": 0.45817245817245816,
"grad_norm": 0.3207135498523712,
"learning_rate": 5.918346054178059e-06,
"loss": 0.421142578125,
"step": 534,
"token_acc": 0.8632203477958804
},
{
"epoch": 0.459030459030459,
"grad_norm": 0.393178254365921,
"learning_rate": 5.904690237922455e-06,
"loss": 0.412109375,
"step": 535,
"token_acc": 0.8660278616112931
},
{
"epoch": 0.4598884598884599,
"grad_norm": 0.2876410186290741,
"learning_rate": 5.891027441365689e-06,
"loss": 0.40087890625,
"step": 536,
"token_acc": 0.8695650340108797
},
{
"epoch": 0.46074646074646075,
"grad_norm": 0.4405011236667633,
"learning_rate": 5.877357769925542e-06,
"loss": 0.419677734375,
"step": 537,
"token_acc": 0.8634989791485539
},
{
"epoch": 0.4616044616044616,
"grad_norm": 0.31729942560195923,
"learning_rate": 5.863681329072835e-06,
"loss": 0.406494140625,
"step": 538,
"token_acc": 0.8676505038854704
},
{
"epoch": 0.4624624624624625,
"grad_norm": 0.3226943016052246,
"learning_rate": 5.849998224330621e-06,
"loss": 0.404052734375,
"step": 539,
"token_acc": 0.8691325052420007
},
{
"epoch": 0.46332046332046334,
"grad_norm": 0.378424733877182,
"learning_rate": 5.836308561273369e-06,
"loss": 0.4189453125,
"step": 540,
"token_acc": 0.8641706600886002
},
{
"epoch": 0.4641784641784642,
"grad_norm": 0.2984580993652344,
"learning_rate": 5.8226124455261516e-06,
"loss": 0.420166015625,
"step": 541,
"token_acc": 0.8641534333977945
},
{
"epoch": 0.46503646503646506,
"grad_norm": 0.29600897431373596,
"learning_rate": 5.808909982763825e-06,
"loss": 0.416015625,
"step": 542,
"token_acc": 0.8652731184015914
},
{
"epoch": 0.46589446589446587,
"grad_norm": 0.28871870040893555,
"learning_rate": 5.79520127871022e-06,
"loss": 0.41845703125,
"step": 543,
"token_acc": 0.8643925010301255
},
{
"epoch": 0.46675246675246673,
"grad_norm": 0.39704445004463196,
"learning_rate": 5.781486439137323e-06,
"loss": 0.417236328125,
"step": 544,
"token_acc": 0.8645539504438952
},
{
"epoch": 0.4676104676104676,
"grad_norm": 0.3399257957935333,
"learning_rate": 5.767765569864459e-06,
"loss": 0.403564453125,
"step": 545,
"token_acc": 0.8686296663113595
},
{
"epoch": 0.46846846846846846,
"grad_norm": 0.34662899374961853,
"learning_rate": 5.754038776757476e-06,
"loss": 0.418212890625,
"step": 546,
"token_acc": 0.8640291621562747
},
{
"epoch": 0.4693264693264693,
"grad_norm": 0.39737239480018616,
"learning_rate": 5.740306165727929e-06,
"loss": 0.435546875,
"step": 547,
"token_acc": 0.8606249359339252
},
{
"epoch": 0.4701844701844702,
"grad_norm": 0.2816781997680664,
"learning_rate": 5.726567842732262e-06,
"loss": 0.418212890625,
"step": 548,
"token_acc": 0.8651664874959102
},
{
"epoch": 0.47104247104247104,
"grad_norm": 0.31325563788414,
"learning_rate": 5.712823913770992e-06,
"loss": 0.408935546875,
"step": 549,
"token_acc": 0.867751615015485
},
{
"epoch": 0.4719004719004719,
"grad_norm": 0.2923162579536438,
"learning_rate": 5.6990744848878874e-06,
"loss": 0.40869140625,
"step": 550,
"token_acc": 0.8675126060332564
},
{
"epoch": 0.47275847275847277,
"grad_norm": 0.27962011098861694,
"learning_rate": 5.685319662169157e-06,
"loss": 0.419677734375,
"step": 551,
"token_acc": 0.8639630530429318
},
{
"epoch": 0.47361647361647363,
"grad_norm": 0.313423752784729,
"learning_rate": 5.671559551742617e-06,
"loss": 0.4169921875,
"step": 552,
"token_acc": 0.8654947914538325
},
{
"epoch": 0.4744744744744745,
"grad_norm": 0.3126436471939087,
"learning_rate": 5.657794259776892e-06,
"loss": 0.409912109375,
"step": 553,
"token_acc": 0.8668536544199408
},
{
"epoch": 0.47533247533247536,
"grad_norm": 0.43497735261917114,
"learning_rate": 5.644023892480583e-06,
"loss": 0.42138671875,
"step": 554,
"token_acc": 0.8632415418119503
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.3333779573440552,
"learning_rate": 5.630248556101448e-06,
"loss": 0.42431640625,
"step": 555,
"token_acc": 0.8621689355435327
},
{
"epoch": 0.477048477048477,
"grad_norm": 0.3501513600349426,
"learning_rate": 5.6164683569255854e-06,
"loss": 0.418212890625,
"step": 556,
"token_acc": 0.8647723353126131
},
{
"epoch": 0.4779064779064779,
"grad_norm": 0.30327025055885315,
"learning_rate": 5.6026834012766155e-06,
"loss": 0.423583984375,
"step": 557,
"token_acc": 0.8636040356671468
},
{
"epoch": 0.47876447876447875,
"grad_norm": 0.31263449788093567,
"learning_rate": 5.588893795514858e-06,
"loss": 0.42041015625,
"step": 558,
"token_acc": 0.8639130473695162
},
{
"epoch": 0.4796224796224796,
"grad_norm": 0.3397209346294403,
"learning_rate": 5.575099646036508e-06,
"loss": 0.410888671875,
"step": 559,
"token_acc": 0.8662212705407617
},
{
"epoch": 0.4804804804804805,
"grad_norm": 0.30478543043136597,
"learning_rate": 5.561301059272821e-06,
"loss": 0.424560546875,
"step": 560,
"token_acc": 0.8622620368610338
},
{
"epoch": 0.48133848133848134,
"grad_norm": 0.34290942549705505,
"learning_rate": 5.5474981416892914e-06,
"loss": 0.417724609375,
"step": 561,
"token_acc": 0.8645334084357782
},
{
"epoch": 0.4821964821964822,
"grad_norm": 0.2868536710739136,
"learning_rate": 5.533690999784822e-06,
"loss": 0.435302734375,
"step": 562,
"token_acc": 0.8605640768716921
},
{
"epoch": 0.48305448305448306,
"grad_norm": 0.30824825167655945,
"learning_rate": 5.519879740090918e-06,
"loss": 0.438720703125,
"step": 563,
"token_acc": 0.8598180591280223
},
{
"epoch": 0.4839124839124839,
"grad_norm": 0.3504210412502289,
"learning_rate": 5.5060644691708485e-06,
"loss": 0.42626953125,
"step": 564,
"token_acc": 0.8621639597187142
},
{
"epoch": 0.4847704847704848,
"grad_norm": 0.306574285030365,
"learning_rate": 5.492245293618838e-06,
"loss": 0.41455078125,
"step": 565,
"token_acc": 0.866405955635539
},
{
"epoch": 0.48562848562848565,
"grad_norm": 0.2997839152812958,
"learning_rate": 5.478422320059231e-06,
"loss": 0.408447265625,
"step": 566,
"token_acc": 0.8676499238864471
},
{
"epoch": 0.4864864864864865,
"grad_norm": 0.34185224771499634,
"learning_rate": 5.464595655145682e-06,
"loss": 0.416748046875,
"step": 567,
"token_acc": 0.8647140641118203
},
{
"epoch": 0.4873444873444873,
"grad_norm": 0.4168187975883484,
"learning_rate": 5.450765405560328e-06,
"loss": 0.412841796875,
"step": 568,
"token_acc": 0.8657951826771015
},
{
"epoch": 0.4882024882024882,
"grad_norm": 0.47992414236068726,
"learning_rate": 5.436931678012956e-06,
"loss": 0.418212890625,
"step": 569,
"token_acc": 0.8633498047387672
},
{
"epoch": 0.48906048906048905,
"grad_norm": 0.33771997690200806,
"learning_rate": 5.4230945792401945e-06,
"loss": 0.42919921875,
"step": 570,
"token_acc": 0.86111149176419
},
{
"epoch": 0.4899184899184899,
"grad_norm": 0.3674052655696869,
"learning_rate": 5.409254216004682e-06,
"loss": 0.42431640625,
"step": 571,
"token_acc": 0.862938606645429
},
{
"epoch": 0.49077649077649077,
"grad_norm": 0.39429277181625366,
"learning_rate": 5.395410695094246e-06,
"loss": 0.425537109375,
"step": 572,
"token_acc": 0.8624165010373479
},
{
"epoch": 0.49163449163449163,
"grad_norm": 0.32568177580833435,
"learning_rate": 5.381564123321076e-06,
"loss": 0.418701171875,
"step": 573,
"token_acc": 0.8643937980753404
},
{
"epoch": 0.4924924924924925,
"grad_norm": 0.4088405668735504,
"learning_rate": 5.367714607520898e-06,
"loss": 0.4091796875,
"step": 574,
"token_acc": 0.8664232821988668
},
{
"epoch": 0.49335049335049336,
"grad_norm": 0.3675963282585144,
"learning_rate": 5.353862254552159e-06,
"loss": 0.422607421875,
"step": 575,
"token_acc": 0.8628087562830896
},
{
"epoch": 0.4942084942084942,
"grad_norm": 0.31272849440574646,
"learning_rate": 5.340007171295191e-06,
"loss": 0.4228515625,
"step": 576,
"token_acc": 0.8631520564616009
},
{
"epoch": 0.4950664950664951,
"grad_norm": 0.3368191421031952,
"learning_rate": 5.326149464651397e-06,
"loss": 0.424072265625,
"step": 577,
"token_acc": 0.8631390186505763
},
{
"epoch": 0.49592449592449594,
"grad_norm": 0.29833096265792847,
"learning_rate": 5.31228924154242e-06,
"loss": 0.418701171875,
"step": 578,
"token_acc": 0.8644870936881016
},
{
"epoch": 0.4967824967824968,
"grad_norm": 0.3654702305793762,
"learning_rate": 5.298426608909314e-06,
"loss": 0.437744140625,
"step": 579,
"token_acc": 0.858501892141884
},
{
"epoch": 0.4976404976404976,
"grad_norm": 0.33899977803230286,
"learning_rate": 5.2845616737117325e-06,
"loss": 0.427978515625,
"step": 580,
"token_acc": 0.8618060405175653
},
{
"epoch": 0.4984984984984985,
"grad_norm": 0.3489997982978821,
"learning_rate": 5.270694542927089e-06,
"loss": 0.42333984375,
"step": 581,
"token_acc": 0.8628186861688869
},
{
"epoch": 0.49935649935649934,
"grad_norm": 0.26761311292648315,
"learning_rate": 5.2568253235497395e-06,
"loss": 0.4052734375,
"step": 582,
"token_acc": 0.86768693283179
},
{
"epoch": 0.5002145002145002,
"grad_norm": 0.3110455870628357,
"learning_rate": 5.242954122590154e-06,
"loss": 0.419677734375,
"step": 583,
"token_acc": 0.8632653049826955
},
{
"epoch": 0.5010725010725011,
"grad_norm": 0.28550007939338684,
"learning_rate": 5.2290810470740925e-06,
"loss": 0.413818359375,
"step": 584,
"token_acc": 0.8658714297833681
},
{
"epoch": 0.5019305019305019,
"grad_norm": 0.28169047832489014,
"learning_rate": 5.2152062040417804e-06,
"loss": 0.408203125,
"step": 585,
"token_acc": 0.8675125065917934
},
{
"epoch": 0.5027885027885027,
"grad_norm": 0.31631919741630554,
"learning_rate": 5.201329700547077e-06,
"loss": 0.4228515625,
"step": 586,
"token_acc": 0.8635696536642311
},
{
"epoch": 0.5036465036465037,
"grad_norm": 0.30992192029953003,
"learning_rate": 5.187451643656654e-06,
"loss": 0.402099609375,
"step": 587,
"token_acc": 0.8692920409029211
},
{
"epoch": 0.5045045045045045,
"grad_norm": 0.3040684163570404,
"learning_rate": 5.17357214044917e-06,
"loss": 0.41650390625,
"step": 588,
"token_acc": 0.8644617220571275
},
{
"epoch": 0.5053625053625054,
"grad_norm": 0.29021555185317993,
"learning_rate": 5.159691298014444e-06,
"loss": 0.424560546875,
"step": 589,
"token_acc": 0.862678545870133
},
{
"epoch": 0.5062205062205062,
"grad_norm": 0.28256526589393616,
"learning_rate": 5.145809223452625e-06,
"loss": 0.4189453125,
"step": 590,
"token_acc": 0.8644155657464713
},
{
"epoch": 0.5070785070785071,
"grad_norm": 0.304729700088501,
"learning_rate": 5.131926023873368e-06,
"loss": 0.413330078125,
"step": 591,
"token_acc": 0.86640063435446
},
{
"epoch": 0.5079365079365079,
"grad_norm": 0.3553517460823059,
"learning_rate": 5.118041806395014e-06,
"loss": 0.437255859375,
"step": 592,
"token_acc": 0.8592179123124225
},
{
"epoch": 0.5087945087945088,
"grad_norm": 0.303347110748291,
"learning_rate": 5.1041566781437525e-06,
"loss": 0.435791015625,
"step": 593,
"token_acc": 0.859476294830828
},
{
"epoch": 0.5096525096525096,
"grad_norm": 0.29912278056144714,
"learning_rate": 5.090270746252803e-06,
"loss": 0.42138671875,
"step": 594,
"token_acc": 0.8631013023630877
},
{
"epoch": 0.5105105105105106,
"grad_norm": 0.28627195954322815,
"learning_rate": 5.0763841178615825e-06,
"loss": 0.426025390625,
"step": 595,
"token_acc": 0.8622862797033917
},
{
"epoch": 0.5113685113685114,
"grad_norm": 0.29345667362213135,
"learning_rate": 5.062496900114887e-06,
"loss": 0.426025390625,
"step": 596,
"token_acc": 0.8622539972350235
},
{
"epoch": 0.5122265122265123,
"grad_norm": 0.33273833990097046,
"learning_rate": 5.048609200162053e-06,
"loss": 0.406005859375,
"step": 597,
"token_acc": 0.86791046225597
},
{
"epoch": 0.5130845130845131,
"grad_norm": 0.8618232607841492,
"learning_rate": 5.0347211251561435e-06,
"loss": 0.406494140625,
"step": 598,
"token_acc": 0.8679497287867933
},
{
"epoch": 0.5139425139425139,
"grad_norm": 0.4583604633808136,
"learning_rate": 5.020832782253115e-06,
"loss": 0.407470703125,
"step": 599,
"token_acc": 0.8669706864576162
},
{
"epoch": 0.5148005148005148,
"grad_norm": 0.31036147475242615,
"learning_rate": 5.0069442786109845e-06,
"loss": 0.41943359375,
"step": 600,
"token_acc": 0.8638199501971411
},
{
"epoch": 0.5156585156585156,
"grad_norm": 0.2883226275444031,
"learning_rate": 4.993055721389017e-06,
"loss": 0.416748046875,
"step": 601,
"token_acc": 0.864906679723345
},
{
"epoch": 0.5165165165165165,
"grad_norm": 0.32805296778678894,
"learning_rate": 4.979167217746888e-06,
"loss": 0.41748046875,
"step": 602,
"token_acc": 0.8652719727100879
},
{
"epoch": 0.5173745173745173,
"grad_norm": 0.30469661951065063,
"learning_rate": 4.965278874843857e-06,
"loss": 0.438232421875,
"step": 603,
"token_acc": 0.8585304744094846
},
{
"epoch": 0.5182325182325183,
"grad_norm": 0.38189372420310974,
"learning_rate": 4.9513907998379484e-06,
"loss": 0.43359375,
"step": 604,
"token_acc": 0.8597160351264754
},
{
"epoch": 0.5190905190905191,
"grad_norm": 0.3296349346637726,
"learning_rate": 4.937503099885115e-06,
"loss": 0.4228515625,
"step": 605,
"token_acc": 0.8627848284731273
},
{
"epoch": 0.51994851994852,
"grad_norm": 0.33234184980392456,
"learning_rate": 4.9236158821384174e-06,
"loss": 0.421630859375,
"step": 606,
"token_acc": 0.8633299337471668
},
{
"epoch": 0.5208065208065208,
"grad_norm": 0.32945409417152405,
"learning_rate": 4.909729253747197e-06,
"loss": 0.423095703125,
"step": 607,
"token_acc": 0.8617937681779648
},
{
"epoch": 0.5216645216645217,
"grad_norm": 0.31619691848754883,
"learning_rate": 4.895843321856249e-06,
"loss": 0.408447265625,
"step": 608,
"token_acc": 0.8669882635883708
},
{
"epoch": 0.5225225225225225,
"grad_norm": 0.5689969062805176,
"learning_rate": 4.8819581936049885e-06,
"loss": 0.40380859375,
"step": 609,
"token_acc": 0.869054745873051
},
{
"epoch": 0.5233805233805234,
"grad_norm": 0.29553133249282837,
"learning_rate": 4.868073976126633e-06,
"loss": 0.408935546875,
"step": 610,
"token_acc": 0.8672594416928496
},
{
"epoch": 0.5242385242385242,
"grad_norm": 0.29151904582977295,
"learning_rate": 4.854190776547377e-06,
"loss": 0.414306640625,
"step": 611,
"token_acc": 0.8656930497965618
},
{
"epoch": 0.525096525096525,
"grad_norm": 0.3068526089191437,
"learning_rate": 4.840308701985557e-06,
"loss": 0.4248046875,
"step": 612,
"token_acc": 0.8625334981188753
},
{
"epoch": 0.525954525954526,
"grad_norm": 0.31919997930526733,
"learning_rate": 4.82642785955083e-06,
"loss": 0.41455078125,
"step": 613,
"token_acc": 0.8658660227000503
},
{
"epoch": 0.5268125268125268,
"grad_norm": 0.3123633563518524,
"learning_rate": 4.812548356343347e-06,
"loss": 0.421630859375,
"step": 614,
"token_acc": 0.8632446965493289
},
{
"epoch": 0.5276705276705277,
"grad_norm": 0.33854490518569946,
"learning_rate": 4.798670299452926e-06,
"loss": 0.420654296875,
"step": 615,
"token_acc": 0.8638141003124993
},
{
"epoch": 0.5285285285285285,
"grad_norm": 0.3269369900226593,
"learning_rate": 4.784793795958222e-06,
"loss": 0.4169921875,
"step": 616,
"token_acc": 0.8648783839401198
},
{
"epoch": 0.5293865293865294,
"grad_norm": 0.30242738127708435,
"learning_rate": 4.770918952925908e-06,
"loss": 0.43408203125,
"step": 617,
"token_acc": 0.8598976132338554
},
{
"epoch": 0.5302445302445302,
"grad_norm": 0.28513282537460327,
"learning_rate": 4.7570458774098486e-06,
"loss": 0.4033203125,
"step": 618,
"token_acc": 0.8685605986532908
},
{
"epoch": 0.5311025311025311,
"grad_norm": 0.33774495124816895,
"learning_rate": 4.743174676450263e-06,
"loss": 0.421142578125,
"step": 619,
"token_acc": 0.8633870617882
},
{
"epoch": 0.531960531960532,
"grad_norm": 0.2745485305786133,
"learning_rate": 4.729305457072913e-06,
"loss": 0.41162109375,
"step": 620,
"token_acc": 0.8668837967794523
},
{
"epoch": 0.5328185328185329,
"grad_norm": 0.35487911105155945,
"learning_rate": 4.715438326288269e-06,
"loss": 0.418701171875,
"step": 621,
"token_acc": 0.8643853491265514
},
{
"epoch": 0.5336765336765337,
"grad_norm": 0.2786436080932617,
"learning_rate": 4.701573391090688e-06,
"loss": 0.40283203125,
"step": 622,
"token_acc": 0.8687059507779626
},
{
"epoch": 0.5345345345345346,
"grad_norm": 0.33550283312797546,
"learning_rate": 4.687710758457583e-06,
"loss": 0.417236328125,
"step": 623,
"token_acc": 0.8653365592385013
},
{
"epoch": 0.5353925353925354,
"grad_norm": 0.3094243109226227,
"learning_rate": 4.673850535348604e-06,
"loss": 0.412841796875,
"step": 624,
"token_acc": 0.8664694911720932
},
{
"epoch": 0.5362505362505362,
"grad_norm": 0.38066813349723816,
"learning_rate": 4.65999282870481e-06,
"loss": 0.431396484375,
"step": 625,
"token_acc": 0.8612029004637671
},
{
"epoch": 0.5371085371085371,
"grad_norm": 0.40698790550231934,
"learning_rate": 4.646137745447843e-06,
"loss": 0.42919921875,
"step": 626,
"token_acc": 0.8610544541943608
},
{
"epoch": 0.5379665379665379,
"grad_norm": 0.32349613308906555,
"learning_rate": 4.632285392479103e-06,
"loss": 0.425537109375,
"step": 627,
"token_acc": 0.86263342845428
},
{
"epoch": 0.5388245388245388,
"grad_norm": 0.29553911089897156,
"learning_rate": 4.618435876678925e-06,
"loss": 0.404052734375,
"step": 628,
"token_acc": 0.8681626959090244
},
{
"epoch": 0.5396825396825397,
"grad_norm": 0.3188212811946869,
"learning_rate": 4.6045893049057544e-06,
"loss": 0.440673828125,
"step": 629,
"token_acc": 0.8585953233070159
},
{
"epoch": 0.5405405405405406,
"grad_norm": 0.2974208891391754,
"learning_rate": 4.5907457839953185e-06,
"loss": 0.418212890625,
"step": 630,
"token_acc": 0.8645767017604158
},
{
"epoch": 0.5413985413985414,
"grad_norm": 0.36264148354530334,
"learning_rate": 4.576905420759807e-06,
"loss": 0.4208984375,
"step": 631,
"token_acc": 0.8639826789674269
},
{
"epoch": 0.5422565422565423,
"grad_norm": 0.3538433909416199,
"learning_rate": 4.563068321987047e-06,
"loss": 0.40625,
"step": 632,
"token_acc": 0.8683869778009743
},
{
"epoch": 0.5431145431145431,
"grad_norm": 0.3371064364910126,
"learning_rate": 4.549234594439674e-06,
"loss": 0.429931640625,
"step": 633,
"token_acc": 0.8605667096602871
},
{
"epoch": 0.543972543972544,
"grad_norm": 0.4398404359817505,
"learning_rate": 4.535404344854318e-06,
"loss": 0.42626953125,
"step": 634,
"token_acc": 0.8624168352295182
},
{
"epoch": 0.5448305448305448,
"grad_norm": 0.3018925189971924,
"learning_rate": 4.521577679940769e-06,
"loss": 0.416748046875,
"step": 635,
"token_acc": 0.8647790047876514
},
{
"epoch": 0.5456885456885456,
"grad_norm": 0.3857707381248474,
"learning_rate": 4.507754706381165e-06,
"loss": 0.427490234375,
"step": 636,
"token_acc": 0.8617468588432567
},
{
"epoch": 0.5465465465465466,
"grad_norm": 0.36081254482269287,
"learning_rate": 4.493935530829152e-06,
"loss": 0.408203125,
"step": 637,
"token_acc": 0.8670829153168602
},
{
"epoch": 0.5474045474045474,
"grad_norm": 0.29515862464904785,
"learning_rate": 4.480120259909084e-06,
"loss": 0.419189453125,
"step": 638,
"token_acc": 0.8645933122670278
},
{
"epoch": 0.5482625482625483,
"grad_norm": 0.35486963391304016,
"learning_rate": 4.466309000215179e-06,
"loss": 0.420166015625,
"step": 639,
"token_acc": 0.8633597659410697
},
{
"epoch": 0.5491205491205491,
"grad_norm": 0.5018385648727417,
"learning_rate": 4.45250185831071e-06,
"loss": 0.421142578125,
"step": 640,
"token_acc": 0.8637495560887303
},
{
"epoch": 0.54997854997855,
"grad_norm": 0.32012471556663513,
"learning_rate": 4.438698940727179e-06,
"loss": 0.429931640625,
"step": 641,
"token_acc": 0.8611554092862992
},
{
"epoch": 0.5508365508365508,
"grad_norm": 0.656898021697998,
"learning_rate": 4.424900353963493e-06,
"loss": 0.414306640625,
"step": 642,
"token_acc": 0.8654221668522151
},
{
"epoch": 0.5516945516945517,
"grad_norm": 0.6136103272438049,
"learning_rate": 4.411106204485144e-06,
"loss": 0.431640625,
"step": 643,
"token_acc": 0.8616598681166455
},
{
"epoch": 0.5525525525525525,
"grad_norm": 0.2826859951019287,
"learning_rate": 4.397316598723385e-06,
"loss": 0.407958984375,
"step": 644,
"token_acc": 0.8671457775646916
},
{
"epoch": 0.5534105534105535,
"grad_norm": 0.31794071197509766,
"learning_rate": 4.383531643074416e-06,
"loss": 0.411376953125,
"step": 645,
"token_acc": 0.8667780808989106
},
{
"epoch": 0.5542685542685543,
"grad_norm": 0.3432675898075104,
"learning_rate": 4.369751443898554e-06,
"loss": 0.412353515625,
"step": 646,
"token_acc": 0.8661712115376122
},
{
"epoch": 0.5551265551265552,
"grad_norm": 0.3500617444515228,
"learning_rate": 4.3559761075194185e-06,
"loss": 0.422607421875,
"step": 647,
"token_acc": 0.8633065010858607
},
{
"epoch": 0.555984555984556,
"grad_norm": 0.3480101227760315,
"learning_rate": 4.342205740223109e-06,
"loss": 0.417724609375,
"step": 648,
"token_acc": 0.8651174415049121
},
{
"epoch": 0.5568425568425568,
"grad_norm": 0.414084255695343,
"learning_rate": 4.328440448257385e-06,
"loss": 0.433837890625,
"step": 649,
"token_acc": 0.8601565472662416
},
{
"epoch": 0.5577005577005577,
"grad_norm": 0.6094998717308044,
"learning_rate": 4.314680337830847e-06,
"loss": 0.4375,
"step": 650,
"token_acc": 0.8589042472734703
},
{
"epoch": 0.5585585585585585,
"grad_norm": 0.43623489141464233,
"learning_rate": 4.300925515112113e-06,
"loss": 0.423828125,
"step": 651,
"token_acc": 0.8628781388706055
},
{
"epoch": 0.5594165594165594,
"grad_norm": 0.2918865978717804,
"learning_rate": 4.287176086229009e-06,
"loss": 0.41943359375,
"step": 652,
"token_acc": 0.8643799656364735
},
{
"epoch": 0.5602745602745602,
"grad_norm": 0.36064180731773376,
"learning_rate": 4.273432157267739e-06,
"loss": 0.432373046875,
"step": 653,
"token_acc": 0.860825219695913
},
{
"epoch": 0.5611325611325612,
"grad_norm": 0.3680606782436371,
"learning_rate": 4.259693834272072e-06,
"loss": 0.4306640625,
"step": 654,
"token_acc": 0.8615323449666296
},
{
"epoch": 0.561990561990562,
"grad_norm": 0.2901996970176697,
"learning_rate": 4.245961223242525e-06,
"loss": 0.41455078125,
"step": 655,
"token_acc": 0.8656067230452077
},
{
"epoch": 0.5628485628485629,
"grad_norm": 0.4935920536518097,
"learning_rate": 4.232234430135542e-06,
"loss": 0.407470703125,
"step": 656,
"token_acc": 0.8668436284055034
},
{
"epoch": 0.5637065637065637,
"grad_norm": 0.3205684423446655,
"learning_rate": 4.218513560862679e-06,
"loss": 0.435791015625,
"step": 657,
"token_acc": 0.8585924216806615
},
{
"epoch": 0.5645645645645646,
"grad_norm": 0.3080020546913147,
"learning_rate": 4.204798721289781e-06,
"loss": 0.408447265625,
"step": 658,
"token_acc": 0.8670235699296596
},
{
"epoch": 0.5654225654225654,
"grad_norm": 0.29078367352485657,
"learning_rate": 4.191090017236177e-06,
"loss": 0.427978515625,
"step": 659,
"token_acc": 0.8630666541361139
},
{
"epoch": 0.5662805662805663,
"grad_norm": 0.30470749735832214,
"learning_rate": 4.17738755447385e-06,
"loss": 0.4287109375,
"step": 660,
"token_acc": 0.86123956020604
},
{
"epoch": 0.5671385671385671,
"grad_norm": 0.3899340331554413,
"learning_rate": 4.1636914387266316e-06,
"loss": 0.410888671875,
"step": 661,
"token_acc": 0.866619946074086
},
{
"epoch": 0.567996567996568,
"grad_norm": 0.30479905009269714,
"learning_rate": 4.15000177566938e-06,
"loss": 0.414306640625,
"step": 662,
"token_acc": 0.8653435575189851
},
{
"epoch": 0.5688545688545689,
"grad_norm": 0.5120990872383118,
"learning_rate": 4.136318670927167e-06,
"loss": 0.4189453125,
"step": 663,
"token_acc": 0.8639119775624726
},
{
"epoch": 0.5697125697125697,
"grad_norm": 0.30492648482322693,
"learning_rate": 4.1226422300744595e-06,
"loss": 0.41552734375,
"step": 664,
"token_acc": 0.8646854408233237
},
{
"epoch": 0.5705705705705706,
"grad_norm": 0.3271532952785492,
"learning_rate": 4.108972558634312e-06,
"loss": 0.43505859375,
"step": 665,
"token_acc": 0.8602931194765159
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.29384005069732666,
"learning_rate": 4.095309762077548e-06,
"loss": 0.416748046875,
"step": 666,
"token_acc": 0.8649318225139836
},
{
"epoch": 0.5722865722865723,
"grad_norm": 0.2706664204597473,
"learning_rate": 4.0816539458219425e-06,
"loss": 0.412841796875,
"step": 667,
"token_acc": 0.8657289362879999
},
{
"epoch": 0.5731445731445731,
"grad_norm": 0.30048269033432007,
"learning_rate": 4.0680052152314185e-06,
"loss": 0.429931640625,
"step": 668,
"token_acc": 0.8611538613644099
},
{
"epoch": 0.574002574002574,
"grad_norm": 0.27609485387802124,
"learning_rate": 4.054363675615226e-06,
"loss": 0.40673828125,
"step": 669,
"token_acc": 0.8681813297343104
},
{
"epoch": 0.5748605748605748,
"grad_norm": 0.3386572003364563,
"learning_rate": 4.0407294322271295e-06,
"loss": 0.42822265625,
"step": 670,
"token_acc": 0.861949839775031
},
{
"epoch": 0.5757185757185758,
"grad_norm": 0.3223874568939209,
"learning_rate": 4.0271025902646e-06,
"loss": 0.406494140625,
"step": 671,
"token_acc": 0.8676797107123938
},
{
"epoch": 0.5765765765765766,
"grad_norm": 0.35459455847740173,
"learning_rate": 4.013483254868001e-06,
"loss": 0.429443359375,
"step": 672,
"token_acc": 0.8606541285269002
},
{
"epoch": 0.5774345774345775,
"grad_norm": 0.28879350423812866,
"learning_rate": 3.999871531119779e-06,
"loss": 0.423583984375,
"step": 673,
"token_acc": 0.863517647733072
},
{
"epoch": 0.5782925782925783,
"grad_norm": 0.32608532905578613,
"learning_rate": 3.98626752404365e-06,
"loss": 0.415771484375,
"step": 674,
"token_acc": 0.8651042576150371
},
{
"epoch": 0.5791505791505791,
"grad_norm": 0.335490345954895,
"learning_rate": 3.9726713386037914e-06,
"loss": 0.418212890625,
"step": 675,
"token_acc": 0.8647293252866424
},
{
"epoch": 0.58000858000858,
"grad_norm": 0.2842903435230255,
"learning_rate": 3.959083079704031e-06,
"loss": 0.441162109375,
"step": 676,
"token_acc": 0.8582060869057603
},
{
"epoch": 0.5808665808665808,
"grad_norm": 0.3505149483680725,
"learning_rate": 3.94550285218704e-06,
"loss": 0.424560546875,
"step": 677,
"token_acc": 0.8627775255391601
},
{
"epoch": 0.5817245817245817,
"grad_norm": 0.2863593101501465,
"learning_rate": 3.931930760833515e-06,
"loss": 0.43505859375,
"step": 678,
"token_acc": 0.8588072294645009
},
{
"epoch": 0.5825825825825826,
"grad_norm": 0.30225133895874023,
"learning_rate": 3.918366910361387e-06,
"loss": 0.419189453125,
"step": 679,
"token_acc": 0.8644833976161195
},
{
"epoch": 0.5834405834405835,
"grad_norm": 0.3021388053894043,
"learning_rate": 3.904811405424993e-06,
"loss": 0.4296875,
"step": 680,
"token_acc": 0.8606600135067523
},
{
"epoch": 0.5842985842985843,
"grad_norm": 0.2834121286869049,
"learning_rate": 3.891264350614287e-06,
"loss": 0.424072265625,
"step": 681,
"token_acc": 0.8623092963295642
},
{
"epoch": 0.5851565851565852,
"grad_norm": 0.3101329207420349,
"learning_rate": 3.877725850454019e-06,
"loss": 0.416015625,
"step": 682,
"token_acc": 0.8662042639049187
},
{
"epoch": 0.586014586014586,
"grad_norm": 0.2995108366012573,
"learning_rate": 3.864196009402935e-06,
"loss": 0.435302734375,
"step": 683,
"token_acc": 0.8594428658074635
},
{
"epoch": 0.5868725868725869,
"grad_norm": 0.3114798665046692,
"learning_rate": 3.850674931852973e-06,
"loss": 0.4228515625,
"step": 684,
"token_acc": 0.8636934155963774
},
{
"epoch": 0.5877305877305877,
"grad_norm": 0.3150714933872223,
"learning_rate": 3.8371627221284495e-06,
"loss": 0.4208984375,
"step": 685,
"token_acc": 0.8635530872595878
},
{
"epoch": 0.5885885885885885,
"grad_norm": 0.2810271084308624,
"learning_rate": 3.823659484485264e-06,
"loss": 0.419921875,
"step": 686,
"token_acc": 0.8634085956147243
},
{
"epoch": 0.5894465894465895,
"grad_norm": 0.2742871940135956,
"learning_rate": 3.8101653231100877e-06,
"loss": 0.425048828125,
"step": 687,
"token_acc": 0.862476988481855
},
{
"epoch": 0.5903045903045903,
"grad_norm": 0.2745487093925476,
"learning_rate": 3.7966803421195643e-06,
"loss": 0.41064453125,
"step": 688,
"token_acc": 0.8672722651590382
},
{
"epoch": 0.5911625911625912,
"grad_norm": 0.27975040674209595,
"learning_rate": 3.783204645559504e-06,
"loss": 0.4130859375,
"step": 689,
"token_acc": 0.8653004679571757
},
{
"epoch": 0.592020592020592,
"grad_norm": 0.2877062261104584,
"learning_rate": 3.7697383374040806e-06,
"loss": 0.412109375,
"step": 690,
"token_acc": 0.8664390009907603
},
{
"epoch": 0.5928785928785929,
"grad_norm": 0.29905879497528076,
"learning_rate": 3.756281521555033e-06,
"loss": 0.40869140625,
"step": 691,
"token_acc": 0.8673086581554044
},
{
"epoch": 0.5937365937365937,
"grad_norm": 0.2831152081489563,
"learning_rate": 3.742834301840853e-06,
"loss": 0.424072265625,
"step": 692,
"token_acc": 0.8625201104107426
},
{
"epoch": 0.5945945945945946,
"grad_norm": 0.3023799955844879,
"learning_rate": 3.729396782015998e-06,
"loss": 0.427490234375,
"step": 693,
"token_acc": 0.8615896284347432
},
{
"epoch": 0.5954525954525954,
"grad_norm": 0.4037996530532837,
"learning_rate": 3.7159690657600837e-06,
"loss": 0.42333984375,
"step": 694,
"token_acc": 0.8636764778441126
},
{
"epoch": 0.5963105963105964,
"grad_norm": 0.3710002303123474,
"learning_rate": 3.702551256677083e-06,
"loss": 0.43310546875,
"step": 695,
"token_acc": 0.8595120419062663
},
{
"epoch": 0.5971685971685972,
"grad_norm": 0.38277384638786316,
"learning_rate": 3.689143458294529e-06,
"loss": 0.41650390625,
"step": 696,
"token_acc": 0.8639440904033985
},
{
"epoch": 0.5980265980265981,
"grad_norm": 0.36992019414901733,
"learning_rate": 3.6757457740627144e-06,
"loss": 0.44189453125,
"step": 697,
"token_acc": 0.8580431337921691
},
{
"epoch": 0.5988845988845989,
"grad_norm": 0.2937336266040802,
"learning_rate": 3.662358307353897e-06,
"loss": 0.42578125,
"step": 698,
"token_acc": 0.8622419400597839
},
{
"epoch": 0.5997425997425997,
"grad_norm": 0.2683764696121216,
"learning_rate": 3.648981161461495e-06,
"loss": 0.407958984375,
"step": 699,
"token_acc": 0.8668515614357621
},
{
"epoch": 0.6006006006006006,
"grad_norm": 0.48572370409965515,
"learning_rate": 3.6356144395992986e-06,
"loss": 0.4033203125,
"step": 700,
"token_acc": 0.8686737289643149
},
{
"epoch": 0.6014586014586014,
"grad_norm": 0.39991822838783264,
"learning_rate": 3.6222582449006673e-06,
"loss": 0.419921875,
"step": 701,
"token_acc": 0.8643231684128129
},
{
"epoch": 0.6023166023166023,
"grad_norm": 0.36240869760513306,
"learning_rate": 3.6089126804177373e-06,
"loss": 0.4296875,
"step": 702,
"token_acc": 0.8623647521716091
},
{
"epoch": 0.6031746031746031,
"grad_norm": 0.32131874561309814,
"learning_rate": 3.595577849120625e-06,
"loss": 0.43017578125,
"step": 703,
"token_acc": 0.8607554432476436
},
{
"epoch": 0.6040326040326041,
"grad_norm": 0.30051231384277344,
"learning_rate": 3.5822538538966333e-06,
"loss": 0.4091796875,
"step": 704,
"token_acc": 0.8672732198616467
},
{
"epoch": 0.6048906048906049,
"grad_norm": 0.3076333999633789,
"learning_rate": 3.5689407975494596e-06,
"loss": 0.4111328125,
"step": 705,
"token_acc": 0.8659222770666966
},
{
"epoch": 0.6057486057486058,
"grad_norm": 0.3169800937175751,
"learning_rate": 3.5556387827983923e-06,
"loss": 0.418701171875,
"step": 706,
"token_acc": 0.8640093881909691
},
{
"epoch": 0.6066066066066066,
"grad_norm": 0.30912867188453674,
"learning_rate": 3.542347912277537e-06,
"loss": 0.4091796875,
"step": 707,
"token_acc": 0.8665864125309957
},
{
"epoch": 0.6074646074646075,
"grad_norm": 0.26029857993125916,
"learning_rate": 3.5290682885350067e-06,
"loss": 0.42529296875,
"step": 708,
"token_acc": 0.8623228656900614
},
{
"epoch": 0.6083226083226083,
"grad_norm": 0.28922978043556213,
"learning_rate": 3.515800014032142e-06,
"loss": 0.414306640625,
"step": 709,
"token_acc": 0.8657667288605843
},
{
"epoch": 0.6091806091806092,
"grad_norm": 0.2963823974132538,
"learning_rate": 3.502543191142713e-06,
"loss": 0.4189453125,
"step": 710,
"token_acc": 0.8643723855389345
},
{
"epoch": 0.61003861003861,
"grad_norm": 0.4521320164203644,
"learning_rate": 3.489297922152136e-06,
"loss": 0.428466796875,
"step": 711,
"token_acc": 0.8612340860380563
},
{
"epoch": 0.6108966108966108,
"grad_norm": 0.3216448724269867,
"learning_rate": 3.4760643092566803e-06,
"loss": 0.432373046875,
"step": 712,
"token_acc": 0.8589549675980871
},
{
"epoch": 0.6117546117546118,
"grad_norm": 0.2792559564113617,
"learning_rate": 3.462842454562677e-06,
"loss": 0.41748046875,
"step": 713,
"token_acc": 0.8649079378816019
},
{
"epoch": 0.6126126126126126,
"grad_norm": 0.26431983709335327,
"learning_rate": 3.449632460085738e-06,
"loss": 0.44287109375,
"step": 714,
"token_acc": 0.8577891652222631
},
{
"epoch": 0.6134706134706135,
"grad_norm": 0.29708003997802734,
"learning_rate": 3.436434427749965e-06,
"loss": 0.406494140625,
"step": 715,
"token_acc": 0.8676337528653605
},
{
"epoch": 0.6143286143286143,
"grad_norm": 0.2837906777858734,
"learning_rate": 3.423248459387165e-06,
"loss": 0.42529296875,
"step": 716,
"token_acc": 0.8618076270998776
},
{
"epoch": 0.6151866151866152,
"grad_norm": 0.30335840582847595,
"learning_rate": 3.4100746567360608e-06,
"loss": 0.439697265625,
"step": 717,
"token_acc": 0.8575965582053366
},
{
"epoch": 0.616044616044616,
"grad_norm": 0.2720887064933777,
"learning_rate": 3.3969131214415097e-06,
"loss": 0.42431640625,
"step": 718,
"token_acc": 0.8621560805339173
},
{
"epoch": 0.6169026169026169,
"grad_norm": 0.308821439743042,
"learning_rate": 3.3837639550537183e-06,
"loss": 0.42431640625,
"step": 719,
"token_acc": 0.8622098166692779
},
{
"epoch": 0.6177606177606177,
"grad_norm": 0.29398998618125916,
"learning_rate": 3.370627259027457e-06,
"loss": 0.4169921875,
"step": 720,
"token_acc": 0.8651638161868784
},
{
"epoch": 0.6186186186186187,
"grad_norm": 0.31248271465301514,
"learning_rate": 3.3575031347212805e-06,
"loss": 0.410888671875,
"step": 721,
"token_acc": 0.8661870907297451
},
{
"epoch": 0.6194766194766195,
"grad_norm": 0.49209561944007874,
"learning_rate": 3.344391683396744e-06,
"loss": 0.416748046875,
"step": 722,
"token_acc": 0.8646008249214202
},
{
"epoch": 0.6203346203346203,
"grad_norm": 0.3146926164627075,
"learning_rate": 3.3312930062176206e-06,
"loss": 0.427734375,
"step": 723,
"token_acc": 0.8611961522764613
},
{
"epoch": 0.6211926211926212,
"grad_norm": 0.3497059941291809,
"learning_rate": 3.3182072042491244e-06,
"loss": 0.4306640625,
"step": 724,
"token_acc": 0.8606771928206602
},
{
"epoch": 0.622050622050622,
"grad_norm": 0.33833208680152893,
"learning_rate": 3.305134378457127e-06,
"loss": 0.4169921875,
"step": 725,
"token_acc": 0.8645796240165519
},
{
"epoch": 0.6229086229086229,
"grad_norm": 0.3027627468109131,
"learning_rate": 3.2920746297073813e-06,
"loss": 0.431884765625,
"step": 726,
"token_acc": 0.8596897059671885
},
{
"epoch": 0.6237666237666237,
"grad_norm": 0.35056594014167786,
"learning_rate": 3.2790280587647384e-06,
"loss": 0.41162109375,
"step": 727,
"token_acc": 0.8662333647476264
},
{
"epoch": 0.6246246246246246,
"grad_norm": 0.2903030216693878,
"learning_rate": 3.2659947662923767e-06,
"loss": 0.427734375,
"step": 728,
"token_acc": 0.8612788028933391
},
{
"epoch": 0.6254826254826255,
"grad_norm": 0.2940883934497833,
"learning_rate": 3.252974852851023e-06,
"loss": 0.427490234375,
"step": 729,
"token_acc": 0.8616075585346563
},
{
"epoch": 0.6263406263406264,
"grad_norm": 0.6840419769287109,
"learning_rate": 3.2399684188981733e-06,
"loss": 0.43017578125,
"step": 730,
"token_acc": 0.8605299073003841
},
{
"epoch": 0.6271986271986272,
"grad_norm": 0.3573523163795471,
"learning_rate": 3.226975564787322e-06,
"loss": 0.408203125,
"step": 731,
"token_acc": 0.8672588424572346
},
{
"epoch": 0.6280566280566281,
"grad_norm": 0.2727561891078949,
"learning_rate": 3.213996390767184e-06,
"loss": 0.40673828125,
"step": 732,
"token_acc": 0.8668989109625584
},
{
"epoch": 0.6289146289146289,
"grad_norm": 0.28537923097610474,
"learning_rate": 3.2010309969809274e-06,
"loss": 0.41650390625,
"step": 733,
"token_acc": 0.8646293566939277
},
{
"epoch": 0.6297726297726298,
"grad_norm": 0.3011501133441925,
"learning_rate": 3.1880794834653872e-06,
"loss": 0.4150390625,
"step": 734,
"token_acc": 0.864918531795058
},
{
"epoch": 0.6306306306306306,
"grad_norm": 0.313281387090683,
"learning_rate": 3.1751419501503113e-06,
"loss": 0.412109375,
"step": 735,
"token_acc": 0.8661696113154662
},
{
"epoch": 0.6314886314886314,
"grad_norm": 0.31124812364578247,
"learning_rate": 3.1622184968575774e-06,
"loss": 0.4208984375,
"step": 736,
"token_acc": 0.864574461301621
},
{
"epoch": 0.6323466323466324,
"grad_norm": 0.3466483950614929,
"learning_rate": 3.149309223300428e-06,
"loss": 0.4111328125,
"step": 737,
"token_acc": 0.8665072941390753
},
{
"epoch": 0.6332046332046332,
"grad_norm": 0.26968225836753845,
"learning_rate": 3.1364142290826984e-06,
"loss": 0.410888671875,
"step": 738,
"token_acc": 0.8665805387383462
},
{
"epoch": 0.6340626340626341,
"grad_norm": 0.3164491057395935,
"learning_rate": 3.1235336136980467e-06,
"loss": 0.40576171875,
"step": 739,
"token_acc": 0.8679546589902324
},
{
"epoch": 0.6349206349206349,
"grad_norm": 0.2797950506210327,
"learning_rate": 3.1106674765291943e-06,
"loss": 0.411376953125,
"step": 740,
"token_acc": 0.8673922043803215
},
{
"epoch": 0.6357786357786358,
"grad_norm": 0.31588879227638245,
"learning_rate": 3.0978159168471455e-06,
"loss": 0.423095703125,
"step": 741,
"token_acc": 0.8636581379308815
},
{
"epoch": 0.6366366366366366,
"grad_norm": 0.2784661054611206,
"learning_rate": 3.0849790338104354e-06,
"loss": 0.40673828125,
"step": 742,
"token_acc": 0.8672910157275185
},
{
"epoch": 0.6374946374946375,
"grad_norm": 0.45226141810417175,
"learning_rate": 3.072156926464356e-06,
"loss": 0.4228515625,
"step": 743,
"token_acc": 0.8640519870780257
},
{
"epoch": 0.6383526383526383,
"grad_norm": 0.38720688223838806,
"learning_rate": 3.059349693740196e-06,
"loss": 0.4296875,
"step": 744,
"token_acc": 0.8611537296528473
},
{
"epoch": 0.6392106392106393,
"grad_norm": 0.32016894221305847,
"learning_rate": 3.046557434454477e-06,
"loss": 0.421875,
"step": 745,
"token_acc": 0.8629133889521484
},
{
"epoch": 0.6400686400686401,
"grad_norm": 0.302832692861557,
"learning_rate": 3.033780247308187e-06,
"loss": 0.417236328125,
"step": 746,
"token_acc": 0.8648892587656055
},
{
"epoch": 0.640926640926641,
"grad_norm": 0.32734689116477966,
"learning_rate": 3.021018230886028e-06,
"loss": 0.410888671875,
"step": 747,
"token_acc": 0.8668939505568416
},
{
"epoch": 0.6417846417846418,
"grad_norm": 0.38975128531455994,
"learning_rate": 3.0082714836556417e-06,
"loss": 0.434814453125,
"step": 748,
"token_acc": 0.8601097404323175
},
{
"epoch": 0.6426426426426426,
"grad_norm": 0.29173365235328674,
"learning_rate": 2.9955401039668642e-06,
"loss": 0.410888671875,
"step": 749,
"token_acc": 0.8658020099984889
},
{
"epoch": 0.6435006435006435,
"grad_norm": 0.28504666686058044,
"learning_rate": 2.982824190050958e-06,
"loss": 0.416015625,
"step": 750,
"token_acc": 0.8655427296335081
},
{
"epoch": 0.6443586443586443,
"grad_norm": 0.42865467071533203,
"learning_rate": 2.970123840019857e-06,
"loss": 0.410888671875,
"step": 751,
"token_acc": 0.8664588016202136
},
{
"epoch": 0.6452166452166452,
"grad_norm": 0.296321302652359,
"learning_rate": 2.9574391518654077e-06,
"loss": 0.431884765625,
"step": 752,
"token_acc": 0.8596406403820509
},
{
"epoch": 0.646074646074646,
"grad_norm": 0.269500195980072,
"learning_rate": 2.9447702234586173e-06,
"loss": 0.4150390625,
"step": 753,
"token_acc": 0.8657088665173323
},
{
"epoch": 0.646932646932647,
"grad_norm": 0.3641909956932068,
"learning_rate": 2.9321171525488945e-06,
"loss": 0.421142578125,
"step": 754,
"token_acc": 0.8637453910387206
},
{
"epoch": 0.6477906477906478,
"grad_norm": 0.5789368748664856,
"learning_rate": 2.9194800367632946e-06,
"loss": 0.424072265625,
"step": 755,
"token_acc": 0.8632654896435958
},
{
"epoch": 0.6486486486486487,
"grad_norm": 0.2990999221801758,
"learning_rate": 2.906858973605772e-06,
"loss": 0.424072265625,
"step": 756,
"token_acc": 0.8630561550117085
},
{
"epoch": 0.6495066495066495,
"grad_norm": 0.3107726275920868,
"learning_rate": 2.8942540604564218e-06,
"loss": 0.421630859375,
"step": 757,
"token_acc": 0.8639170489279429
},
{
"epoch": 0.6503646503646504,
"grad_norm": 0.3139874339103699,
"learning_rate": 2.8816653945707286e-06,
"loss": 0.419921875,
"step": 758,
"token_acc": 0.8637637956561667
},
{
"epoch": 0.6512226512226512,
"grad_norm": 0.29500311613082886,
"learning_rate": 2.8690930730788257e-06,
"loss": 0.422607421875,
"step": 759,
"token_acc": 0.8621882364149395
},
{
"epoch": 0.6520806520806521,
"grad_norm": 0.2934010922908783,
"learning_rate": 2.8565371929847286e-06,
"loss": 0.42529296875,
"step": 760,
"token_acc": 0.8625855857868451
},
{
"epoch": 0.6529386529386529,
"grad_norm": 0.27664071321487427,
"learning_rate": 2.8439978511656057e-06,
"loss": 0.411865234375,
"step": 761,
"token_acc": 0.8654579004815126
},
{
"epoch": 0.6537966537966537,
"grad_norm": 0.26708412170410156,
"learning_rate": 2.8314751443710148e-06,
"loss": 0.424072265625,
"step": 762,
"token_acc": 0.8632256607830429
},
{
"epoch": 0.6546546546546547,
"grad_norm": 0.2842220366001129,
"learning_rate": 2.8189691692221627e-06,
"loss": 0.40283203125,
"step": 763,
"token_acc": 0.8682881444563735
},
{
"epoch": 0.6555126555126555,
"grad_norm": 0.2746691107749939,
"learning_rate": 2.8064800222111673e-06,
"loss": 0.4248046875,
"step": 764,
"token_acc": 0.86134307930056
},
{
"epoch": 0.6563706563706564,
"grad_norm": 0.28123152256011963,
"learning_rate": 2.7940077997002962e-06,
"loss": 0.404296875,
"step": 765,
"token_acc": 0.8677211057748204
},
{
"epoch": 0.6572286572286572,
"grad_norm": 0.2980206310749054,
"learning_rate": 2.781552597921243e-06,
"loss": 0.424072265625,
"step": 766,
"token_acc": 0.8629135703546214
},
{
"epoch": 0.6580866580866581,
"grad_norm": 0.3012925088405609,
"learning_rate": 2.7691145129743645e-06,
"loss": 0.40380859375,
"step": 767,
"token_acc": 0.8685964346195325
},
{
"epoch": 0.6589446589446589,
"grad_norm": 0.2583615779876709,
"learning_rate": 2.7566936408279633e-06,
"loss": 0.409912109375,
"step": 768,
"token_acc": 0.8664659216904965
},
{
"epoch": 0.6598026598026598,
"grad_norm": 0.3311903774738312,
"learning_rate": 2.744290077317514e-06,
"loss": 0.42822265625,
"step": 769,
"token_acc": 0.8605827342706279
},
{
"epoch": 0.6606606606606606,
"grad_norm": 0.28522440791130066,
"learning_rate": 2.7319039181449604e-06,
"loss": 0.40380859375,
"step": 770,
"token_acc": 0.8690445782124863
},
{
"epoch": 0.6615186615186616,
"grad_norm": 0.27327582240104675,
"learning_rate": 2.7195352588779545e-06,
"loss": 0.419677734375,
"step": 771,
"token_acc": 0.8643136174484524
},
{
"epoch": 0.6623766623766624,
"grad_norm": 0.6555838584899902,
"learning_rate": 2.7071841949491205e-06,
"loss": 0.412841796875,
"step": 772,
"token_acc": 0.8654658461078394
},
{
"epoch": 0.6632346632346632,
"grad_norm": 0.31466037034988403,
"learning_rate": 2.6948508216553304e-06,
"loss": 0.422607421875,
"step": 773,
"token_acc": 0.8630569918929631
},
{
"epoch": 0.6640926640926641,
"grad_norm": 0.2725640535354614,
"learning_rate": 2.6825352341569538e-06,
"loss": 0.41015625,
"step": 774,
"token_acc": 0.8672905489444152
},
{
"epoch": 0.6649506649506649,
"grad_norm": 0.2693732976913452,
"learning_rate": 2.6702375274771342e-06,
"loss": 0.414306640625,
"step": 775,
"token_acc": 0.8649985366480761
},
{
"epoch": 0.6658086658086658,
"grad_norm": 0.3178979456424713,
"learning_rate": 2.65795779650105e-06,
"loss": 0.421875,
"step": 776,
"token_acc": 0.8641876392350619
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.287675678730011,
"learning_rate": 2.64569613597519e-06,
"loss": 0.431640625,
"step": 777,
"token_acc": 0.8613056562830759
},
{
"epoch": 0.6675246675246675,
"grad_norm": 0.44260233640670776,
"learning_rate": 2.6334526405066096e-06,
"loss": 0.42138671875,
"step": 778,
"token_acc": 0.8638384766368562
},
{
"epoch": 0.6683826683826684,
"grad_norm": 0.2804744243621826,
"learning_rate": 2.6212274045622167e-06,
"loss": 0.4248046875,
"step": 779,
"token_acc": 0.8620642900764998
},
{
"epoch": 0.6692406692406693,
"grad_norm": 0.3039637804031372,
"learning_rate": 2.6090205224680264e-06,
"loss": 0.426025390625,
"step": 780,
"token_acc": 0.862080212734873
},
{
"epoch": 0.6700986700986701,
"grad_norm": 0.28121185302734375,
"learning_rate": 2.59683208840845e-06,
"loss": 0.422607421875,
"step": 781,
"token_acc": 0.8629817051677545
},
{
"epoch": 0.670956670956671,
"grad_norm": 0.28979820013046265,
"learning_rate": 2.5846621964255524e-06,
"loss": 0.424072265625,
"step": 782,
"token_acc": 0.8634703984567854
},
{
"epoch": 0.6718146718146718,
"grad_norm": 0.27983832359313965,
"learning_rate": 2.572510940418334e-06,
"loss": 0.414306640625,
"step": 783,
"token_acc": 0.8656708320119115
},
{
"epoch": 0.6726726726726727,
"grad_norm": 0.28270334005355835,
"learning_rate": 2.560378414142013e-06,
"loss": 0.440185546875,
"step": 784,
"token_acc": 0.8578284638548317
},
{
"epoch": 0.6735306735306735,
"grad_norm": 0.27283400297164917,
"learning_rate": 2.5482647112072857e-06,
"loss": 0.416259765625,
"step": 785,
"token_acc": 0.8652095424069042
},
{
"epoch": 0.6743886743886743,
"grad_norm": 0.28655433654785156,
"learning_rate": 2.5361699250796224e-06,
"loss": 0.42333984375,
"step": 786,
"token_acc": 0.8624020327074378
},
{
"epoch": 0.6752466752466753,
"grad_norm": 0.2862057387828827,
"learning_rate": 2.524094149078529e-06,
"loss": 0.41162109375,
"step": 787,
"token_acc": 0.8665559561479422
},
{
"epoch": 0.6761046761046761,
"grad_norm": 0.34024739265441895,
"learning_rate": 2.5120374763768422e-06,
"loss": 0.404296875,
"step": 788,
"token_acc": 0.8685195191942949
},
{
"epoch": 0.676962676962677,
"grad_norm": 0.2708181142807007,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.41455078125,
"step": 789,
"token_acc": 0.865521477686641
},
{
"epoch": 0.6778206778206778,
"grad_norm": 0.3435003459453583,
"learning_rate": 2.4879818128253284e-06,
"loss": 0.40625,
"step": 790,
"token_acc": 0.8683441898155363
},
{
"epoch": 0.6786786786786787,
"grad_norm": 0.296457439661026,
"learning_rate": 2.475983007581326e-06,
"loss": 0.429443359375,
"step": 791,
"token_acc": 0.8611306908386638
},
{
"epoch": 0.6795366795366795,
"grad_norm": 0.29154929518699646,
"learning_rate": 2.4640036768469404e-06,
"loss": 0.418701171875,
"step": 792,
"token_acc": 0.8642145393518053
},
{
"epoch": 0.6803946803946804,
"grad_norm": 0.3181299865245819,
"learning_rate": 2.4520439130508706e-06,
"loss": 0.4228515625,
"step": 793,
"token_acc": 0.8619425349712831
},
{
"epoch": 0.6812526812526812,
"grad_norm": 0.4793683886528015,
"learning_rate": 2.4401038084708313e-06,
"loss": 0.41064453125,
"step": 794,
"token_acc": 0.8660497254065819
},
{
"epoch": 0.6821106821106822,
"grad_norm": 0.2871720492839813,
"learning_rate": 2.428183455232866e-06,
"loss": 0.41162109375,
"step": 795,
"token_acc": 0.8662074313243078
},
{
"epoch": 0.682968682968683,
"grad_norm": 0.28190600872039795,
"learning_rate": 2.4162829453106077e-06,
"loss": 0.421142578125,
"step": 796,
"token_acc": 0.8633124912379083
},
{
"epoch": 0.6838266838266839,
"grad_norm": 0.2788940966129303,
"learning_rate": 2.4044023705246e-06,
"loss": 0.42041015625,
"step": 797,
"token_acc": 0.8640638261185022
},
{
"epoch": 0.6846846846846847,
"grad_norm": 0.3039623200893402,
"learning_rate": 2.3925418225415614e-06,
"loss": 0.411865234375,
"step": 798,
"token_acc": 0.8659021620657985
},
{
"epoch": 0.6855426855426855,
"grad_norm": 0.7723171710968018,
"learning_rate": 2.3807013928737e-06,
"loss": 0.423583984375,
"step": 799,
"token_acc": 0.8632796534188545
},
{
"epoch": 0.6864006864006864,
"grad_norm": 0.27127009630203247,
"learning_rate": 2.3688811728779875e-06,
"loss": 0.4150390625,
"step": 800,
"token_acc": 0.8648742277670001
},
{
"epoch": 0.6872586872586872,
"grad_norm": 0.25803831219673157,
"learning_rate": 2.357081253755472e-06,
"loss": 0.39892578125,
"step": 801,
"token_acc": 0.869495461661277
},
{
"epoch": 0.6881166881166881,
"grad_norm": 0.25958219170570374,
"learning_rate": 2.345301726550567e-06,
"loss": 0.4033203125,
"step": 802,
"token_acc": 0.8684733017339952
},
{
"epoch": 0.6889746889746889,
"grad_norm": 0.35863733291625977,
"learning_rate": 2.333542682150339e-06,
"loss": 0.420166015625,
"step": 803,
"token_acc": 0.86437048819283
},
{
"epoch": 0.6898326898326899,
"grad_norm": 0.27840012311935425,
"learning_rate": 2.321804211283825e-06,
"loss": 0.420654296875,
"step": 804,
"token_acc": 0.8639976281146292
},
{
"epoch": 0.6906906906906907,
"grad_norm": 0.2807696759700775,
"learning_rate": 2.3100864045213182e-06,
"loss": 0.414794921875,
"step": 805,
"token_acc": 0.8649715626442518
},
{
"epoch": 0.6915486915486916,
"grad_norm": 0.2947477102279663,
"learning_rate": 2.2983893522736795e-06,
"loss": 0.42578125,
"step": 806,
"token_acc": 0.8623342530579099
},
{
"epoch": 0.6924066924066924,
"grad_norm": 0.30956754088401794,
"learning_rate": 2.2867131447916267e-06,
"loss": 0.42138671875,
"step": 807,
"token_acc": 0.8634406767643644
},
{
"epoch": 0.6932646932646933,
"grad_norm": 0.6084207892417908,
"learning_rate": 2.275057872165055e-06,
"loss": 0.4140625,
"step": 808,
"token_acc": 0.8653596495887442
},
{
"epoch": 0.6941226941226941,
"grad_norm": 0.3165799677371979,
"learning_rate": 2.263423624322326e-06,
"loss": 0.408935546875,
"step": 809,
"token_acc": 0.8666709511852974
},
{
"epoch": 0.694980694980695,
"grad_norm": 0.32238486409187317,
"learning_rate": 2.2518104910295824e-06,
"loss": 0.404541015625,
"step": 810,
"token_acc": 0.8676245486143411
},
{
"epoch": 0.6958386958386958,
"grad_norm": 0.28721731901168823,
"learning_rate": 2.240218561890057e-06,
"loss": 0.403564453125,
"step": 811,
"token_acc": 0.8687821833299878
},
{
"epoch": 0.6966966966966966,
"grad_norm": 0.3454531729221344,
"learning_rate": 2.228647926343373e-06,
"loss": 0.401611328125,
"step": 812,
"token_acc": 0.869002849758688
},
{
"epoch": 0.6975546975546976,
"grad_norm": 0.2890348732471466,
"learning_rate": 2.217098673664864e-06,
"loss": 0.41943359375,
"step": 813,
"token_acc": 0.8641014681801782
},
{
"epoch": 0.6984126984126984,
"grad_norm": 0.414209246635437,
"learning_rate": 2.205570892964876e-06,
"loss": 0.40234375,
"step": 814,
"token_acc": 0.870047103077512
},
{
"epoch": 0.6992706992706993,
"grad_norm": 0.30316129326820374,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.430908203125,
"step": 815,
"token_acc": 0.8610738504684696
},
{
"epoch": 0.7001287001287001,
"grad_norm": 0.34405311942100525,
"learning_rate": 2.1825801031128197e-06,
"loss": 0.42578125,
"step": 816,
"token_acc": 0.8622185891003762
},
{
"epoch": 0.700986700986701,
"grad_norm": 0.7282266616821289,
"learning_rate": 2.171117271350346e-06,
"loss": 0.419921875,
"step": 817,
"token_acc": 0.8639200664034095
},
{
"epoch": 0.7018447018447018,
"grad_norm": 0.27730464935302734,
"learning_rate": 2.159676266344222e-06,
"loss": 0.41259765625,
"step": 818,
"token_acc": 0.8663648141484874
},
{
"epoch": 0.7027027027027027,
"grad_norm": 0.33068954944610596,
"learning_rate": 2.1482571763695875e-06,
"loss": 0.442626953125,
"step": 819,
"token_acc": 0.8570633832352896
},
{
"epoch": 0.7035607035607035,
"grad_norm": 0.39260005950927734,
"learning_rate": 2.136860089532501e-06,
"loss": 0.426513671875,
"step": 820,
"token_acc": 0.8616010779455495
},
{
"epoch": 0.7044187044187045,
"grad_norm": 0.27897241711616516,
"learning_rate": 2.125485093769242e-06,
"loss": 0.416015625,
"step": 821,
"token_acc": 0.8645756209934795
},
{
"epoch": 0.7052767052767053,
"grad_norm": 0.31244340538978577,
"learning_rate": 2.114132276845654e-06,
"loss": 0.41650390625,
"step": 822,
"token_acc": 0.8641173378242585
},
{
"epoch": 0.7061347061347061,
"grad_norm": 0.30072924494743347,
"learning_rate": 2.1028017263564456e-06,
"loss": 0.421630859375,
"step": 823,
"token_acc": 0.8630218046491103
},
{
"epoch": 0.706992706992707,
"grad_norm": 0.3274608850479126,
"learning_rate": 2.091493529724528e-06,
"loss": 0.42236328125,
"step": 824,
"token_acc": 0.8631176416405445
},
{
"epoch": 0.7078507078507078,
"grad_norm": 0.2824763059616089,
"learning_rate": 2.0802077742003373e-06,
"loss": 0.42138671875,
"step": 825,
"token_acc": 0.8638072939034804
},
{
"epoch": 0.7087087087087087,
"grad_norm": 0.2967549264431,
"learning_rate": 2.0689445468611647e-06,
"loss": 0.431396484375,
"step": 826,
"token_acc": 0.8605155588496222
},
{
"epoch": 0.7095667095667095,
"grad_norm": 0.2793164551258087,
"learning_rate": 2.057703934610474e-06,
"loss": 0.418212890625,
"step": 827,
"token_acc": 0.8628495436678834
},
{
"epoch": 0.7104247104247104,
"grad_norm": 0.30443885922431946,
"learning_rate": 2.0464860241772454e-06,
"loss": 0.41455078125,
"step": 828,
"token_acc": 0.8650488103970252
},
{
"epoch": 0.7112827112827113,
"grad_norm": 0.296432226896286,
"learning_rate": 2.0352909021152927e-06,
"loss": 0.3828125,
"step": 829,
"token_acc": 0.874715284189889
},
{
"epoch": 0.7121407121407122,
"grad_norm": 0.3610222041606903,
"learning_rate": 2.024118654802608e-06,
"loss": 0.41796875,
"step": 830,
"token_acc": 0.863839041629732
},
{
"epoch": 0.712998712998713,
"grad_norm": 0.29008617997169495,
"learning_rate": 2.0129693684406853e-06,
"loss": 0.413818359375,
"step": 831,
"token_acc": 0.8660629574033077
},
{
"epoch": 0.7138567138567139,
"grad_norm": 0.40345442295074463,
"learning_rate": 2.0018431290538583e-06,
"loss": 0.40673828125,
"step": 832,
"token_acc": 0.8675448742187326
},
{
"epoch": 0.7147147147147147,
"grad_norm": 0.5799405574798584,
"learning_rate": 1.990740022488642e-06,
"loss": 0.414306640625,
"step": 833,
"token_acc": 0.8653047122137777
},
{
"epoch": 0.7155727155727156,
"grad_norm": 0.3146010935306549,
"learning_rate": 1.97966013441306e-06,
"loss": 0.42919921875,
"step": 834,
"token_acc": 0.8609076976682918
},
{
"epoch": 0.7164307164307164,
"grad_norm": 0.2936657667160034,
"learning_rate": 1.9686035503159967e-06,
"loss": 0.408447265625,
"step": 835,
"token_acc": 0.8675391307268574
},
{
"epoch": 0.7172887172887172,
"grad_norm": 0.3349025547504425,
"learning_rate": 1.957570355506522e-06,
"loss": 0.42626953125,
"step": 836,
"token_acc": 0.8617369111224302
},
{
"epoch": 0.7181467181467182,
"grad_norm": 0.27934983372688293,
"learning_rate": 1.9465606351132514e-06,
"loss": 0.430908203125,
"step": 837,
"token_acc": 0.861690358947928
},
{
"epoch": 0.719004719004719,
"grad_norm": 0.43426623940467834,
"learning_rate": 1.93557447408367e-06,
"loss": 0.4267578125,
"step": 838,
"token_acc": 0.8622005475701574
},
{
"epoch": 0.7198627198627199,
"grad_norm": 0.380607008934021,
"learning_rate": 1.9246119571834904e-06,
"loss": 0.4072265625,
"step": 839,
"token_acc": 0.867663355044301
},
{
"epoch": 0.7207207207207207,
"grad_norm": 0.3182547092437744,
"learning_rate": 1.913673168995997e-06,
"loss": 0.4033203125,
"step": 840,
"token_acc": 0.8682006175400593
},
{
"epoch": 0.7215787215787216,
"grad_norm": 0.8427750468254089,
"learning_rate": 1.9027581939213852e-06,
"loss": 0.4228515625,
"step": 841,
"token_acc": 0.8644143962869062
},
{
"epoch": 0.7224367224367224,
"grad_norm": 0.2900392413139343,
"learning_rate": 1.8918671161761227e-06,
"loss": 0.40673828125,
"step": 842,
"token_acc": 0.8682524844081968
},
{
"epoch": 0.7232947232947233,
"grad_norm": 0.3022124469280243,
"learning_rate": 1.8810000197922863e-06,
"loss": 0.41650390625,
"step": 843,
"token_acc": 0.8648238149517705
},
{
"epoch": 0.7241527241527241,
"grad_norm": 0.3630630373954773,
"learning_rate": 1.8701569886169286e-06,
"loss": 0.412841796875,
"step": 844,
"token_acc": 0.8662471835637499
},
{
"epoch": 0.725010725010725,
"grad_norm": 0.27876517176628113,
"learning_rate": 1.8593381063114113e-06,
"loss": 0.435546875,
"step": 845,
"token_acc": 0.858891224452024
},
{
"epoch": 0.7258687258687259,
"grad_norm": 0.3557242751121521,
"learning_rate": 1.848543456350783e-06,
"loss": 0.4169921875,
"step": 846,
"token_acc": 0.8653168186044042
},
{
"epoch": 0.7267267267267268,
"grad_norm": 0.2789200246334076,
"learning_rate": 1.8377731220231144e-06,
"loss": 0.401611328125,
"step": 847,
"token_acc": 0.8693312644186286
},
{
"epoch": 0.7275847275847276,
"grad_norm": 0.3069145083427429,
"learning_rate": 1.827027186428869e-06,
"loss": 0.411376953125,
"step": 848,
"token_acc": 0.8661141619090758
},
{
"epoch": 0.7284427284427284,
"grad_norm": 0.30628782510757446,
"learning_rate": 1.8163057324802591e-06,
"loss": 0.39990234375,
"step": 849,
"token_acc": 0.8693368573640793
},
{
"epoch": 0.7293007293007293,
"grad_norm": 0.302652508020401,
"learning_rate": 1.8056088429005974e-06,
"loss": 0.4169921875,
"step": 850,
"token_acc": 0.8654619772096223
},
{
"epoch": 0.7301587301587301,
"grad_norm": 0.30071836709976196,
"learning_rate": 1.7949366002236762e-06,
"loss": 0.424560546875,
"step": 851,
"token_acc": 0.8617374560170042
},
{
"epoch": 0.731016731016731,
"grad_norm": 0.30053451657295227,
"learning_rate": 1.7842890867931068e-06,
"loss": 0.40966796875,
"step": 852,
"token_acc": 0.8673868909100321
},
{
"epoch": 0.7318747318747318,
"grad_norm": 0.29654398560523987,
"learning_rate": 1.7736663847617104e-06,
"loss": 0.394287109375,
"step": 853,
"token_acc": 0.870432473045101
},
{
"epoch": 0.7327327327327328,
"grad_norm": 0.46439477801322937,
"learning_rate": 1.7630685760908623e-06,
"loss": 0.41259765625,
"step": 854,
"token_acc": 0.8656178162246
},
{
"epoch": 0.7335907335907336,
"grad_norm": 0.2706488072872162,
"learning_rate": 1.7524957425498751e-06,
"loss": 0.42529296875,
"step": 855,
"token_acc": 0.8615482670367995
},
{
"epoch": 0.7344487344487345,
"grad_norm": 0.32726287841796875,
"learning_rate": 1.741947965715355e-06,
"loss": 0.41064453125,
"step": 856,
"token_acc": 0.8665712661763014
},
{
"epoch": 0.7353067353067353,
"grad_norm": 0.39380475878715515,
"learning_rate": 1.7314253269705854e-06,
"loss": 0.42138671875,
"step": 857,
"token_acc": 0.8643379100537171
},
{
"epoch": 0.7361647361647362,
"grad_norm": 0.32866552472114563,
"learning_rate": 1.720927907504888e-06,
"loss": 0.414306640625,
"step": 858,
"token_acc": 0.8664005399354712
},
{
"epoch": 0.737022737022737,
"grad_norm": 0.46486541628837585,
"learning_rate": 1.710455788312998e-06,
"loss": 0.4130859375,
"step": 859,
"token_acc": 0.8659887986487884
},
{
"epoch": 0.7378807378807379,
"grad_norm": 0.29456764459609985,
"learning_rate": 1.70000905019445e-06,
"loss": 0.424072265625,
"step": 860,
"token_acc": 0.8627137347390286
},
{
"epoch": 0.7387387387387387,
"grad_norm": 0.26814281940460205,
"learning_rate": 1.6895877737529364e-06,
"loss": 0.419189453125,
"step": 861,
"token_acc": 0.864491793914385
},
{
"epoch": 0.7395967395967395,
"grad_norm": 0.35027414560317993,
"learning_rate": 1.6791920393957056e-06,
"loss": 0.416259765625,
"step": 862,
"token_acc": 0.8654046540125019
},
{
"epoch": 0.7404547404547405,
"grad_norm": 0.2898845076560974,
"learning_rate": 1.6688219273329215e-06,
"loss": 0.4091796875,
"step": 863,
"token_acc": 0.8661562992054129
},
{
"epoch": 0.7413127413127413,
"grad_norm": 1.0104628801345825,
"learning_rate": 1.658477517577064e-06,
"loss": 0.416748046875,
"step": 864,
"token_acc": 0.8644212766348561
},
{
"epoch": 0.7421707421707422,
"grad_norm": 0.29417651891708374,
"learning_rate": 1.6481588899422945e-06,
"loss": 0.413330078125,
"step": 865,
"token_acc": 0.8652554130540487
},
{
"epoch": 0.743028743028743,
"grad_norm": 0.3112063407897949,
"learning_rate": 1.6378661240438498e-06,
"loss": 0.388916015625,
"step": 866,
"token_acc": 0.8730113186020865
},
{
"epoch": 0.7438867438867439,
"grad_norm": 0.27159684896469116,
"learning_rate": 1.627599299297431e-06,
"loss": 0.421875,
"step": 867,
"token_acc": 0.8653535070902529
},
{
"epoch": 0.7447447447447447,
"grad_norm": 0.34600740671157837,
"learning_rate": 1.6173584949185767e-06,
"loss": 0.428466796875,
"step": 868,
"token_acc": 0.8616534225156063
},
{
"epoch": 0.7456027456027456,
"grad_norm": 0.47425681352615356,
"learning_rate": 1.6071437899220688e-06,
"loss": 0.4072265625,
"step": 869,
"token_acc": 0.8674800444469523
},
{
"epoch": 0.7464607464607464,
"grad_norm": 0.2758917510509491,
"learning_rate": 1.5969552631213086e-06,
"loss": 0.410888671875,
"step": 870,
"token_acc": 0.8668827773711179
},
{
"epoch": 0.7473187473187474,
"grad_norm": 0.31752821803092957,
"learning_rate": 1.586792993127721e-06,
"loss": 0.41064453125,
"step": 871,
"token_acc": 0.8666534093546574
},
{
"epoch": 0.7481767481767482,
"grad_norm": 0.30074673891067505,
"learning_rate": 1.576657058350135e-06,
"loss": 0.414306640625,
"step": 872,
"token_acc": 0.8656342478275765
},
{
"epoch": 0.749034749034749,
"grad_norm": 0.2995446026325226,
"learning_rate": 1.5665475369941901e-06,
"loss": 0.414306640625,
"step": 873,
"token_acc": 0.8653630710417538
},
{
"epoch": 0.7498927498927499,
"grad_norm": 0.29835230112075806,
"learning_rate": 1.5564645070617245e-06,
"loss": 0.424072265625,
"step": 874,
"token_acc": 0.8620988126604653
},
{
"epoch": 0.7507507507507507,
"grad_norm": 0.280883252620697,
"learning_rate": 1.546408046350183e-06,
"loss": 0.404541015625,
"step": 875,
"token_acc": 0.8691573397036383
},
{
"epoch": 0.7516087516087516,
"grad_norm": 0.4191594421863556,
"learning_rate": 1.5363782324520033e-06,
"loss": 0.4345703125,
"step": 876,
"token_acc": 0.859257118047358
},
{
"epoch": 0.7524667524667524,
"grad_norm": 0.2688054144382477,
"learning_rate": 1.5263751427540318e-06,
"loss": 0.4248046875,
"step": 877,
"token_acc": 0.8616883519440272
},
{
"epoch": 0.7533247533247533,
"grad_norm": 0.30539417266845703,
"learning_rate": 1.516398854436914e-06,
"loss": 0.427001953125,
"step": 878,
"token_acc": 0.8615781425070584
},
{
"epoch": 0.7541827541827542,
"grad_norm": 0.30050891637802124,
"learning_rate": 1.5064494444745099e-06,
"loss": 0.42724609375,
"step": 879,
"token_acc": 0.8613657065573752
},
{
"epoch": 0.7550407550407551,
"grad_norm": 0.29440322518348694,
"learning_rate": 1.4965269896332884e-06,
"loss": 0.423583984375,
"step": 880,
"token_acc": 0.8631351780564933
},
{
"epoch": 0.7558987558987559,
"grad_norm": 0.4638172388076782,
"learning_rate": 1.486631566471745e-06,
"loss": 0.41064453125,
"step": 881,
"token_acc": 0.8670753527601451
},
{
"epoch": 0.7567567567567568,
"grad_norm": 0.32703155279159546,
"learning_rate": 1.4767632513398089e-06,
"loss": 0.40771484375,
"step": 882,
"token_acc": 0.8670930778732017
},
{
"epoch": 0.7576147576147576,
"grad_norm": 0.32005804777145386,
"learning_rate": 1.4669221203782469e-06,
"loss": 0.42431640625,
"step": 883,
"token_acc": 0.8622962922714718
},
{
"epoch": 0.7584727584727585,
"grad_norm": 0.3853223919868469,
"learning_rate": 1.457108249518089e-06,
"loss": 0.423828125,
"step": 884,
"token_acc": 0.863350812406021
},
{
"epoch": 0.7593307593307593,
"grad_norm": 0.3030143678188324,
"learning_rate": 1.447321714480029e-06,
"loss": 0.4111328125,
"step": 885,
"token_acc": 0.8666975537537475
},
{
"epoch": 0.7601887601887601,
"grad_norm": 0.2908580005168915,
"learning_rate": 1.4375625907738455e-06,
"loss": 0.436767578125,
"step": 886,
"token_acc": 0.8586488332754434
},
{
"epoch": 0.7610467610467611,
"grad_norm": 0.27759864926338196,
"learning_rate": 1.4278309536978275e-06,
"loss": 0.39501953125,
"step": 887,
"token_acc": 0.8704416481618554
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.33146974444389343,
"learning_rate": 1.4181268783381763e-06,
"loss": 0.426513671875,
"step": 888,
"token_acc": 0.8604349975225847
},
{
"epoch": 0.7627627627627628,
"grad_norm": 0.297797292470932,
"learning_rate": 1.4084504395684439e-06,
"loss": 0.40234375,
"step": 889,
"token_acc": 0.8695453530395628
},
{
"epoch": 0.7636207636207636,
"grad_norm": 0.2632818818092346,
"learning_rate": 1.3988017120489417e-06,
"loss": 0.409423828125,
"step": 890,
"token_acc": 0.8670055764432903
},
{
"epoch": 0.7644787644787645,
"grad_norm": 0.3324565887451172,
"learning_rate": 1.389180770226174e-06,
"loss": 0.42919921875,
"step": 891,
"token_acc": 0.8616003507204737
},
{
"epoch": 0.7653367653367653,
"grad_norm": 0.4445740282535553,
"learning_rate": 1.3795876883322562e-06,
"loss": 0.435791015625,
"step": 892,
"token_acc": 0.859546766064274
},
{
"epoch": 0.7661947661947662,
"grad_norm": 0.2636471390724182,
"learning_rate": 1.370022540384347e-06,
"loss": 0.418212890625,
"step": 893,
"token_acc": 0.8636034501796438
},
{
"epoch": 0.767052767052767,
"grad_norm": 0.47020813822746277,
"learning_rate": 1.3604854001840746e-06,
"loss": 0.40234375,
"step": 894,
"token_acc": 0.8691988583454077
},
{
"epoch": 0.767910767910768,
"grad_norm": 0.36438074707984924,
"learning_rate": 1.3509763413169709e-06,
"loss": 0.4150390625,
"step": 895,
"token_acc": 0.8650719656824226
},
{
"epoch": 0.7687687687687688,
"grad_norm": 0.2962028384208679,
"learning_rate": 1.3414954371518968e-06,
"loss": 0.423583984375,
"step": 896,
"token_acc": 0.8626113064923734
},
{
"epoch": 0.7696267696267697,
"grad_norm": 0.2903344929218292,
"learning_rate": 1.3320427608404852e-06,
"loss": 0.4111328125,
"step": 897,
"token_acc": 0.8663921371446122
},
{
"epoch": 0.7704847704847705,
"grad_norm": 0.2816446125507355,
"learning_rate": 1.3226183853165709e-06,
"loss": 0.412353515625,
"step": 898,
"token_acc": 0.8658415351098375
},
{
"epoch": 0.7713427713427713,
"grad_norm": 0.307173490524292,
"learning_rate": 1.3132223832956265e-06,
"loss": 0.430419921875,
"step": 899,
"token_acc": 0.8615660717990468
},
{
"epoch": 0.7722007722007722,
"grad_norm": 0.2822801172733307,
"learning_rate": 1.3038548272742052e-06,
"loss": 0.419677734375,
"step": 900,
"token_acc": 0.8634953949821185
},
{
"epoch": 0.773058773058773,
"grad_norm": 0.351273775100708,
"learning_rate": 1.294515789529378e-06,
"loss": 0.40625,
"step": 901,
"token_acc": 0.8679130064819681
},
{
"epoch": 0.7739167739167739,
"grad_norm": 0.2973540723323822,
"learning_rate": 1.2852053421181826e-06,
"loss": 0.4072265625,
"step": 902,
"token_acc": 0.8686016479864094
},
{
"epoch": 0.7747747747747747,
"grad_norm": 0.2685225009918213,
"learning_rate": 1.2759235568770578e-06,
"loss": 0.409423828125,
"step": 903,
"token_acc": 0.8671033462644079
},
{
"epoch": 0.7756327756327757,
"grad_norm": 0.3347790837287903,
"learning_rate": 1.2666705054212984e-06,
"loss": 0.431640625,
"step": 904,
"token_acc": 0.8597632208240229
},
{
"epoch": 0.7764907764907765,
"grad_norm": 0.28766319155693054,
"learning_rate": 1.257446259144494e-06,
"loss": 0.422119140625,
"step": 905,
"token_acc": 0.8637521110407431
},
{
"epoch": 0.7773487773487774,
"grad_norm": 0.48495161533355713,
"learning_rate": 1.2482508892179884e-06,
"loss": 0.4169921875,
"step": 906,
"token_acc": 0.8645826735258116
},
{
"epoch": 0.7782067782067782,
"grad_norm": 0.2951744496822357,
"learning_rate": 1.2390844665903196e-06,
"loss": 0.410400390625,
"step": 907,
"token_acc": 0.8672450166956176
},
{
"epoch": 0.7790647790647791,
"grad_norm": 0.2917865812778473,
"learning_rate": 1.2299470619866778e-06,
"loss": 0.43359375,
"step": 908,
"token_acc": 0.8597884433217556
},
{
"epoch": 0.7799227799227799,
"grad_norm": 0.3249529302120209,
"learning_rate": 1.220838745908363e-06,
"loss": 0.41455078125,
"step": 909,
"token_acc": 0.8658070987414782
},
{
"epoch": 0.7807807807807807,
"grad_norm": 0.43250909447669983,
"learning_rate": 1.2117595886322342e-06,
"loss": 0.405517578125,
"step": 910,
"token_acc": 0.8675919827621255
},
{
"epoch": 0.7816387816387816,
"grad_norm": 0.34526872634887695,
"learning_rate": 1.2027096602101728e-06,
"loss": 0.417236328125,
"step": 911,
"token_acc": 0.8638038004868782
},
{
"epoch": 0.7824967824967825,
"grad_norm": 0.2916424870491028,
"learning_rate": 1.1936890304685362e-06,
"loss": 0.408447265625,
"step": 912,
"token_acc": 0.8670675240244716
},
{
"epoch": 0.7833547833547834,
"grad_norm": 0.3251696527004242,
"learning_rate": 1.1846977690076279e-06,
"loss": 0.41943359375,
"step": 913,
"token_acc": 0.8641853692216942
},
{
"epoch": 0.7842127842127842,
"grad_norm": 0.275813490152359,
"learning_rate": 1.1757359452011497e-06,
"loss": 0.412109375,
"step": 914,
"token_acc": 0.8655620786741391
},
{
"epoch": 0.7850707850707851,
"grad_norm": 0.2840125858783722,
"learning_rate": 1.1668036281956729e-06,
"loss": 0.40185546875,
"step": 915,
"token_acc": 0.8685523029157037
},
{
"epoch": 0.7859287859287859,
"grad_norm": 0.28590840101242065,
"learning_rate": 1.1579008869101083e-06,
"loss": 0.4228515625,
"step": 916,
"token_acc": 0.8628419620101591
},
{
"epoch": 0.7867867867867868,
"grad_norm": 0.3049492835998535,
"learning_rate": 1.1490277900351637e-06,
"loss": 0.41064453125,
"step": 917,
"token_acc": 0.8662476636124057
},
{
"epoch": 0.7876447876447876,
"grad_norm": 0.29001182317733765,
"learning_rate": 1.140184406032825e-06,
"loss": 0.4140625,
"step": 918,
"token_acc": 0.8652598311657403
},
{
"epoch": 0.7885027885027885,
"grad_norm": 0.2806450426578522,
"learning_rate": 1.1313708031358183e-06,
"loss": 0.414306640625,
"step": 919,
"token_acc": 0.8646419358268118
},
{
"epoch": 0.7893607893607893,
"grad_norm": 0.3616209626197815,
"learning_rate": 1.1225870493470952e-06,
"loss": 0.42578125,
"step": 920,
"token_acc": 0.86145654530734
},
{
"epoch": 0.7902187902187903,
"grad_norm": 0.28786996006965637,
"learning_rate": 1.1138332124392914e-06,
"loss": 0.4276123046875,
"step": 921,
"token_acc": 0.8610919876296863
},
{
"epoch": 0.7910767910767911,
"grad_norm": 0.32155054807662964,
"learning_rate": 1.1051093599542228e-06,
"loss": 0.406494140625,
"step": 922,
"token_acc": 0.8678009596274963
},
{
"epoch": 0.7919347919347919,
"grad_norm": 0.49674251675605774,
"learning_rate": 1.0964155592023483e-06,
"loss": 0.420654296875,
"step": 923,
"token_acc": 0.8646659507687845
},
{
"epoch": 0.7927927927927928,
"grad_norm": 0.28542017936706543,
"learning_rate": 1.087751877262263e-06,
"loss": 0.431640625,
"step": 924,
"token_acc": 0.8599984952288943
},
{
"epoch": 0.7936507936507936,
"grad_norm": 0.2843116819858551,
"learning_rate": 1.079118380980169e-06,
"loss": 0.394775390625,
"step": 925,
"token_acc": 0.8713351343435058
},
{
"epoch": 0.7945087945087945,
"grad_norm": 0.2798040509223938,
"learning_rate": 1.0705151369693712e-06,
"loss": 0.412109375,
"step": 926,
"token_acc": 0.8654249918057023
},
{
"epoch": 0.7953667953667953,
"grad_norm": 0.4611339569091797,
"learning_rate": 1.0619422116097533e-06,
"loss": 0.40283203125,
"step": 927,
"token_acc": 0.867897190750798
},
{
"epoch": 0.7962247962247962,
"grad_norm": 0.2580731511116028,
"learning_rate": 1.0533996710472705e-06,
"loss": 0.41015625,
"step": 928,
"token_acc": 0.866153341522437
},
{
"epoch": 0.7970827970827971,
"grad_norm": 0.2770918309688568,
"learning_rate": 1.0448875811934417e-06,
"loss": 0.41943359375,
"step": 929,
"token_acc": 0.8638795017429356
},
{
"epoch": 0.797940797940798,
"grad_norm": 0.26049456000328064,
"learning_rate": 1.0364060077248339e-06,
"loss": 0.396728515625,
"step": 930,
"token_acc": 0.8708342693897806
},
{
"epoch": 0.7987987987987988,
"grad_norm": 0.2962293326854706,
"learning_rate": 1.027955016082563e-06,
"loss": 0.421875,
"step": 931,
"token_acc": 0.8631873822764875
},
{
"epoch": 0.7996567996567997,
"grad_norm": 0.2695413827896118,
"learning_rate": 1.0195346714717813e-06,
"loss": 0.4190673828125,
"step": 932,
"token_acc": 0.8637831680395592
},
{
"epoch": 0.8005148005148005,
"grad_norm": 0.27354905009269714,
"learning_rate": 1.0111450388611831e-06,
"loss": 0.40234375,
"step": 933,
"token_acc": 0.8685072780264218
},
{
"epoch": 0.8013728013728014,
"grad_norm": 0.3950987160205841,
"learning_rate": 1.0027861829824953e-06,
"loss": 0.4072265625,
"step": 934,
"token_acc": 0.8675458892401569
},
{
"epoch": 0.8022308022308022,
"grad_norm": 0.36916041374206543,
"learning_rate": 9.944581683299804e-07,
"loss": 0.40673828125,
"step": 935,
"token_acc": 0.8673257676752966
},
{
"epoch": 0.803088803088803,
"grad_norm": 0.2757178843021393,
"learning_rate": 9.861610591599453e-07,
"loss": 0.411865234375,
"step": 936,
"token_acc": 0.8664066328296747
},
{
"epoch": 0.803946803946804,
"grad_norm": 0.2859044075012207,
"learning_rate": 9.778949194902327e-07,
"loss": 0.394287109375,
"step": 937,
"token_acc": 0.8713579746078081
},
{
"epoch": 0.8048048048048048,
"grad_norm": 0.30671146512031555,
"learning_rate": 9.696598130997415e-07,
"loss": 0.43115234375,
"step": 938,
"token_acc": 0.860419626782627
},
{
"epoch": 0.8056628056628057,
"grad_norm": 0.27702656388282776,
"learning_rate": 9.614558035279214e-07,
"loss": 0.413330078125,
"step": 939,
"token_acc": 0.8653098730187295
},
{
"epoch": 0.8065208065208065,
"grad_norm": 0.3733308017253876,
"learning_rate": 9.532829540742961e-07,
"loss": 0.400634765625,
"step": 940,
"token_acc": 0.8688922148008784
},
{
"epoch": 0.8073788073788074,
"grad_norm": 0.2657637596130371,
"learning_rate": 9.45141327797961e-07,
"loss": 0.423095703125,
"step": 941,
"token_acc": 0.8628918402011528
},
{
"epoch": 0.8082368082368082,
"grad_norm": 0.30824875831604004,
"learning_rate": 9.370309875171069e-07,
"loss": 0.417236328125,
"step": 942,
"token_acc": 0.8642091777636981
},
{
"epoch": 0.8090948090948091,
"grad_norm": 0.2820126712322235,
"learning_rate": 9.289519958085296e-07,
"loss": 0.423828125,
"step": 943,
"token_acc": 0.8628594164887009
},
{
"epoch": 0.8099528099528099,
"grad_norm": 0.3057509958744049,
"learning_rate": 9.209044150071522e-07,
"loss": 0.421630859375,
"step": 944,
"token_acc": 0.864045873643246
},
{
"epoch": 0.8108108108108109,
"grad_norm": 0.2739517092704773,
"learning_rate": 9.128883072055411e-07,
"loss": 0.4189453125,
"step": 945,
"token_acc": 0.8645221328133311
},
{
"epoch": 0.8116688116688117,
"grad_norm": 0.311347097158432,
"learning_rate": 9.049037342534239e-07,
"loss": 0.425537109375,
"step": 946,
"token_acc": 0.8622799237851106
},
{
"epoch": 0.8125268125268126,
"grad_norm": 0.4359687566757202,
"learning_rate": 8.969507577572189e-07,
"loss": 0.423828125,
"step": 947,
"token_acc": 0.8641154101185045
},
{
"epoch": 0.8133848133848134,
"grad_norm": 0.3056384325027466,
"learning_rate": 8.890294390795545e-07,
"loss": 0.415283203125,
"step": 948,
"token_acc": 0.8655452195683674
},
{
"epoch": 0.8142428142428142,
"grad_norm": 0.4747455418109894,
"learning_rate": 8.811398393387971e-07,
"loss": 0.418701171875,
"step": 949,
"token_acc": 0.8650039013990087
},
{
"epoch": 0.8151008151008151,
"grad_norm": 0.4359639585018158,
"learning_rate": 8.732820194085794e-07,
"loss": 0.409912109375,
"step": 950,
"token_acc": 0.8670454725027146
},
{
"epoch": 0.8159588159588159,
"grad_norm": 0.3213958442211151,
"learning_rate": 8.654560399173346e-07,
"loss": 0.4072265625,
"step": 951,
"token_acc": 0.8682998553608957
},
{
"epoch": 0.8168168168168168,
"grad_norm": 0.286877304315567,
"learning_rate": 8.576619612478204e-07,
"loss": 0.42529296875,
"step": 952,
"token_acc": 0.8634565284049422
},
{
"epoch": 0.8176748176748176,
"grad_norm": 0.36448150873184204,
"learning_rate": 8.498998435366634e-07,
"loss": 0.397216796875,
"step": 953,
"token_acc": 0.8702433285107263
},
{
"epoch": 0.8185328185328186,
"grad_norm": 0.2646366059780121,
"learning_rate": 8.421697466738838e-07,
"loss": 0.416015625,
"step": 954,
"token_acc": 0.8648188094493126
},
{
"epoch": 0.8193908193908194,
"grad_norm": 0.2676806151866913,
"learning_rate": 8.344717303024446e-07,
"loss": 0.42626953125,
"step": 955,
"token_acc": 0.8617925332518506
},
{
"epoch": 0.8202488202488203,
"grad_norm": 0.2954365313053131,
"learning_rate": 8.268058538177826e-07,
"loss": 0.41650390625,
"step": 956,
"token_acc": 0.8642942738635173
},
{
"epoch": 0.8211068211068211,
"grad_norm": 0.30436232686042786,
"learning_rate": 8.191721763673527e-07,
"loss": 0.41015625,
"step": 957,
"token_acc": 0.8661095411055494
},
{
"epoch": 0.821964821964822,
"grad_norm": 0.27682730555534363,
"learning_rate": 8.115707568501768e-07,
"loss": 0.430908203125,
"step": 958,
"token_acc": 0.8609907567467991
},
{
"epoch": 0.8228228228228228,
"grad_norm": 0.27035632729530334,
"learning_rate": 8.040016539163792e-07,
"loss": 0.4267578125,
"step": 959,
"token_acc": 0.8616411714454256
},
{
"epoch": 0.8236808236808236,
"grad_norm": 0.30002471804618835,
"learning_rate": 7.964649259667451e-07,
"loss": 0.41064453125,
"step": 960,
"token_acc": 0.8666265365642644
},
{
"epoch": 0.8245388245388245,
"grad_norm": 0.27749699354171753,
"learning_rate": 7.889606311522596e-07,
"loss": 0.416748046875,
"step": 961,
"token_acc": 0.8649290289263608
},
{
"epoch": 0.8253968253968254,
"grad_norm": 0.29499995708465576,
"learning_rate": 7.814888273736698e-07,
"loss": 0.41064453125,
"step": 962,
"token_acc": 0.8656183513616799
},
{
"epoch": 0.8262548262548263,
"grad_norm": 0.4135013222694397,
"learning_rate": 7.740495722810271e-07,
"loss": 0.416259765625,
"step": 963,
"token_acc": 0.8647694756154567
},
{
"epoch": 0.8271128271128271,
"grad_norm": 0.3184439539909363,
"learning_rate": 7.666429232732486e-07,
"loss": 0.394775390625,
"step": 964,
"token_acc": 0.8714882721371406
},
{
"epoch": 0.827970827970828,
"grad_norm": 0.29979202151298523,
"learning_rate": 7.592689374976769e-07,
"loss": 0.425537109375,
"step": 965,
"token_acc": 0.8618100726069459
},
{
"epoch": 0.8288288288288288,
"grad_norm": 0.2764367461204529,
"learning_rate": 7.51927671849631e-07,
"loss": 0.409423828125,
"step": 966,
"token_acc": 0.8662542884445961
},
{
"epoch": 0.8296868296868297,
"grad_norm": 0.28934308886528015,
"learning_rate": 7.446191829719757e-07,
"loss": 0.411376953125,
"step": 967,
"token_acc": 0.8658847244494964
},
{
"epoch": 0.8305448305448305,
"grad_norm": 0.2724076807498932,
"learning_rate": 7.373435272546764e-07,
"loss": 0.433837890625,
"step": 968,
"token_acc": 0.8599486872572258
},
{
"epoch": 0.8314028314028314,
"grad_norm": 0.2646074891090393,
"learning_rate": 7.301007608343747e-07,
"loss": 0.404052734375,
"step": 969,
"token_acc": 0.8679992643297019
},
{
"epoch": 0.8322608322608323,
"grad_norm": 0.33700594305992126,
"learning_rate": 7.228909395939393e-07,
"loss": 0.41748046875,
"step": 970,
"token_acc": 0.8635573676966715
},
{
"epoch": 0.8331188331188332,
"grad_norm": 0.34065505862236023,
"learning_rate": 7.157141191620548e-07,
"loss": 0.3876953125,
"step": 971,
"token_acc": 0.8730874222413681
},
{
"epoch": 0.833976833976834,
"grad_norm": 0.30134207010269165,
"learning_rate": 7.085703549127737e-07,
"loss": 0.417724609375,
"step": 972,
"token_acc": 0.8644828194788001
},
{
"epoch": 0.8348348348348348,
"grad_norm": 0.5055956244468689,
"learning_rate": 7.014597019651048e-07,
"loss": 0.409423828125,
"step": 973,
"token_acc": 0.8669675574224684
},
{
"epoch": 0.8356928356928357,
"grad_norm": 0.3429611623287201,
"learning_rate": 6.943822151825735e-07,
"loss": 0.384765625,
"step": 974,
"token_acc": 0.8736839701153984
},
{
"epoch": 0.8365508365508365,
"grad_norm": 0.3726073205471039,
"learning_rate": 6.87337949172811e-07,
"loss": 0.425048828125,
"step": 975,
"token_acc": 0.8615751598842198
},
{
"epoch": 0.8374088374088374,
"grad_norm": 0.27319180965423584,
"learning_rate": 6.803269582871275e-07,
"loss": 0.42041015625,
"step": 976,
"token_acc": 0.864003475920196
},
{
"epoch": 0.8382668382668382,
"grad_norm": 0.34678494930267334,
"learning_rate": 6.733492966200872e-07,
"loss": 0.403564453125,
"step": 977,
"token_acc": 0.8688514873666546
},
{
"epoch": 0.8391248391248392,
"grad_norm": 0.297771155834198,
"learning_rate": 6.664050180091042e-07,
"loss": 0.4248046875,
"step": 978,
"token_acc": 0.8617976777083449
},
{
"epoch": 0.83998283998284,
"grad_norm": 0.3375436067581177,
"learning_rate": 6.594941760340134e-07,
"loss": 0.40966796875,
"step": 979,
"token_acc": 0.8668877545180895
},
{
"epoch": 0.8408408408408409,
"grad_norm": 0.29496142268180847,
"learning_rate": 6.526168240166686e-07,
"loss": 0.3994140625,
"step": 980,
"token_acc": 0.8700063093332461
},
{
"epoch": 0.8416988416988417,
"grad_norm": 0.2900641858577728,
"learning_rate": 6.45773015020521e-07,
"loss": 0.408935546875,
"step": 981,
"token_acc": 0.8665054590836483
},
{
"epoch": 0.8425568425568426,
"grad_norm": 0.3049462139606476,
"learning_rate": 6.389628018502186e-07,
"loss": 0.428466796875,
"step": 982,
"token_acc": 0.8610476826222565
},
{
"epoch": 0.8434148434148434,
"grad_norm": 0.28858712315559387,
"learning_rate": 6.321862370511922e-07,
"loss": 0.42431640625,
"step": 983,
"token_acc": 0.8623245665896564
},
{
"epoch": 0.8442728442728443,
"grad_norm": 0.31681257486343384,
"learning_rate": 6.254433729092518e-07,
"loss": 0.41943359375,
"step": 984,
"token_acc": 0.8645553238700971
},
{
"epoch": 0.8451308451308451,
"grad_norm": 0.27467861771583557,
"learning_rate": 6.187342614501873e-07,
"loss": 0.417724609375,
"step": 985,
"token_acc": 0.8642234558315419
},
{
"epoch": 0.8459888459888459,
"grad_norm": 0.3670130670070648,
"learning_rate": 6.120589544393596e-07,
"loss": 0.40185546875,
"step": 986,
"token_acc": 0.8687367253057697
},
{
"epoch": 0.8468468468468469,
"grad_norm": 0.28358694911003113,
"learning_rate": 6.054175033813098e-07,
"loss": 0.41845703125,
"step": 987,
"token_acc": 0.864815904024953
},
{
"epoch": 0.8477048477048477,
"grad_norm": 0.3300946056842804,
"learning_rate": 5.988099595193519e-07,
"loss": 0.421630859375,
"step": 988,
"token_acc": 0.8623403293081285
},
{
"epoch": 0.8485628485628486,
"grad_norm": 0.3519716262817383,
"learning_rate": 5.922363738351888e-07,
"loss": 0.40283203125,
"step": 989,
"token_acc": 0.8688500635662281
},
{
"epoch": 0.8494208494208494,
"grad_norm": 0.3716641366481781,
"learning_rate": 5.856967970485078e-07,
"loss": 0.393310546875,
"step": 990,
"token_acc": 0.8708185566224788
},
{
"epoch": 0.8502788502788503,
"grad_norm": 0.2787734270095825,
"learning_rate": 5.791912796165966e-07,
"loss": 0.395263671875,
"step": 991,
"token_acc": 0.8714353319714222
},
{
"epoch": 0.8511368511368511,
"grad_norm": 0.32798242568969727,
"learning_rate": 5.727198717339511e-07,
"loss": 0.401611328125,
"step": 992,
"token_acc": 0.8702026714652132
},
{
"epoch": 0.851994851994852,
"grad_norm": 0.2704668343067169,
"learning_rate": 5.662826233318897e-07,
"loss": 0.396728515625,
"step": 993,
"token_acc": 0.8713875974835537
},
{
"epoch": 0.8528528528528528,
"grad_norm": 0.4881078600883484,
"learning_rate": 5.598795840781679e-07,
"loss": 0.411865234375,
"step": 994,
"token_acc": 0.8664908657561294
},
{
"epoch": 0.8537108537108538,
"grad_norm": 0.2899569272994995,
"learning_rate": 5.535108033765913e-07,
"loss": 0.385498046875,
"step": 995,
"token_acc": 0.8735394734377342
},
{
"epoch": 0.8545688545688546,
"grad_norm": 0.3312140703201294,
"learning_rate": 5.471763303666411e-07,
"loss": 0.428466796875,
"step": 996,
"token_acc": 0.8611803292778036
},
{
"epoch": 0.8554268554268555,
"grad_norm": 0.3047131896018982,
"learning_rate": 5.408762139230889e-07,
"loss": 0.421630859375,
"step": 997,
"token_acc": 0.8632970783853194
},
{
"epoch": 0.8562848562848563,
"grad_norm": 0.34085360169410706,
"learning_rate": 5.346105026556226e-07,
"loss": 0.411376953125,
"step": 998,
"token_acc": 0.8649278678961657
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.2969898581504822,
"learning_rate": 5.283792449084691e-07,
"loss": 0.4169921875,
"step": 999,
"token_acc": 0.8639748630481856
},
{
"epoch": 0.858000858000858,
"grad_norm": 0.3059532940387726,
"learning_rate": 5.221824887600268e-07,
"loss": 0.395751953125,
"step": 1000,
"token_acc": 0.8709263672837759
},
{
"epoch": 0.8588588588588588,
"grad_norm": 0.46598953008651733,
"learning_rate": 5.160202820224875e-07,
"loss": 0.431884765625,
"step": 1001,
"token_acc": 0.8611318350051439
},
{
"epoch": 0.8597168597168597,
"grad_norm": 0.5253129005432129,
"learning_rate": 5.098926722414727e-07,
"loss": 0.4267578125,
"step": 1002,
"token_acc": 0.8622847561618491
},
{
"epoch": 0.8605748605748605,
"grad_norm": 0.32271358370780945,
"learning_rate": 5.037997066956634e-07,
"loss": 0.416748046875,
"step": 1003,
"token_acc": 0.8635557961881366
},
{
"epoch": 0.8614328614328615,
"grad_norm": 0.32044994831085205,
"learning_rate": 4.977414323964364e-07,
"loss": 0.4072265625,
"step": 1004,
"token_acc": 0.8677507003509481
},
{
"epoch": 0.8622908622908623,
"grad_norm": 0.29807642102241516,
"learning_rate": 4.917178960875046e-07,
"loss": 0.4228515625,
"step": 1005,
"token_acc": 0.8622046322100185
},
{
"epoch": 0.8631488631488632,
"grad_norm": 0.3051440119743347,
"learning_rate": 4.8572914424455e-07,
"loss": 0.43359375,
"step": 1006,
"token_acc": 0.8595431365178888
},
{
"epoch": 0.864006864006864,
"grad_norm": 0.32553502917289734,
"learning_rate": 4.797752230748721e-07,
"loss": 0.406494140625,
"step": 1007,
"token_acc": 0.8678012290634778
},
{
"epoch": 0.8648648648648649,
"grad_norm": 0.29381072521209717,
"learning_rate": 4.7385617851702535e-07,
"loss": 0.417236328125,
"step": 1008,
"token_acc": 0.8651307231589168
},
{
"epoch": 0.8657228657228657,
"grad_norm": 0.28218135237693787,
"learning_rate": 4.679720562404705e-07,
"loss": 0.4052734375,
"step": 1009,
"token_acc": 0.8671818810326439
},
{
"epoch": 0.8665808665808665,
"grad_norm": 0.41088882088661194,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.403076171875,
"step": 1010,
"token_acc": 0.868129077239852
},
{
"epoch": 0.8674388674388674,
"grad_norm": 0.3360867500305176,
"learning_rate": 4.563087598614702e-07,
"loss": 0.41015625,
"step": 1011,
"token_acc": 0.8670573352905148
},
{
"epoch": 0.8682968682968683,
"grad_norm": 0.294415146112442,
"learning_rate": 4.5052967574929883e-07,
"loss": 0.440185546875,
"step": 1012,
"token_acc": 0.8587451822877082
},
{
"epoch": 0.8691548691548692,
"grad_norm": 0.3140941858291626,
"learning_rate": 4.4478569389826864e-07,
"loss": 0.40966796875,
"step": 1013,
"token_acc": 0.8676810481833931
},
{
"epoch": 0.87001287001287,
"grad_norm": 0.35810449719429016,
"learning_rate": 4.3907685862711156e-07,
"loss": 0.41552734375,
"step": 1014,
"token_acc": 0.8651982007569198
},
{
"epoch": 0.8708708708708709,
"grad_norm": 0.2956278622150421,
"learning_rate": 4.334032139833777e-07,
"loss": 0.4248046875,
"step": 1015,
"token_acc": 0.8622928278590415
},
{
"epoch": 0.8717288717288717,
"grad_norm": 0.3053353726863861,
"learning_rate": 4.277648037430998e-07,
"loss": 0.4208984375,
"step": 1016,
"token_acc": 0.8640979331924354
},
{
"epoch": 0.8725868725868726,
"grad_norm": 0.3300248086452484,
"learning_rate": 4.2216167141045093e-07,
"loss": 0.41015625,
"step": 1017,
"token_acc": 0.8662587441645548
},
{
"epoch": 0.8734448734448734,
"grad_norm": 0.32913336157798767,
"learning_rate": 4.165938602174124e-07,
"loss": 0.415283203125,
"step": 1018,
"token_acc": 0.8650453064438248
},
{
"epoch": 0.8743028743028743,
"grad_norm": 0.28351670503616333,
"learning_rate": 4.110614131234375e-07,
"loss": 0.41845703125,
"step": 1019,
"token_acc": 0.8642422402055685
},
{
"epoch": 0.8751608751608752,
"grad_norm": 0.3357718884944916,
"learning_rate": 4.055643728151243e-07,
"loss": 0.4130859375,
"step": 1020,
"token_acc": 0.8648513811431869
},
{
"epoch": 0.8760188760188761,
"grad_norm": 0.27371037006378174,
"learning_rate": 4.001027817058789e-07,
"loss": 0.40625,
"step": 1021,
"token_acc": 0.867367419067485
},
{
"epoch": 0.8768768768768769,
"grad_norm": 0.32762446999549866,
"learning_rate": 3.946766819355985e-07,
"loss": 0.40673828125,
"step": 1022,
"token_acc": 0.8676906014862154
},
{
"epoch": 0.8777348777348777,
"grad_norm": 0.3210776448249817,
"learning_rate": 3.8928611537033424e-07,
"loss": 0.39599609375,
"step": 1023,
"token_acc": 0.8711074912644162
},
{
"epoch": 0.8785928785928786,
"grad_norm": 0.2842090427875519,
"learning_rate": 3.8393112360197993e-07,
"loss": 0.42333984375,
"step": 1024,
"token_acc": 0.8628600963787953
},
{
"epoch": 0.8794508794508794,
"grad_norm": 0.2685863673686981,
"learning_rate": 3.786117479479423e-07,
"loss": 0.415283203125,
"step": 1025,
"token_acc": 0.8642774685655182
},
{
"epoch": 0.8803088803088803,
"grad_norm": 0.2958797812461853,
"learning_rate": 3.7332802945082515e-07,
"loss": 0.400146484375,
"step": 1026,
"token_acc": 0.869784812738707
},
{
"epoch": 0.8811668811668811,
"grad_norm": 0.7484316825866699,
"learning_rate": 3.680800088781161e-07,
"loss": 0.41796875,
"step": 1027,
"token_acc": 0.8642463989916682
},
{
"epoch": 0.882024882024882,
"grad_norm": 0.2952496111392975,
"learning_rate": 3.62867726721865e-07,
"loss": 0.40771484375,
"step": 1028,
"token_acc": 0.8670288973894672
},
{
"epoch": 0.8828828828828829,
"grad_norm": 0.30801525712013245,
"learning_rate": 3.5769122319837926e-07,
"loss": 0.42822265625,
"step": 1029,
"token_acc": 0.8616405906306753
},
{
"epoch": 0.8837408837408838,
"grad_norm": 0.28690844774246216,
"learning_rate": 3.525505382479072e-07,
"loss": 0.410400390625,
"step": 1030,
"token_acc": 0.8663898112538496
},
{
"epoch": 0.8845988845988846,
"grad_norm": 0.2760053277015686,
"learning_rate": 3.474457115343344e-07,
"loss": 0.4267578125,
"step": 1031,
"token_acc": 0.8609780043594963
},
{
"epoch": 0.8854568854568855,
"grad_norm": 0.3268655836582184,
"learning_rate": 3.423767824448737e-07,
"loss": 0.408203125,
"step": 1032,
"token_acc": 0.8669844818221403
},
{
"epoch": 0.8863148863148863,
"grad_norm": 0.2688267230987549,
"learning_rate": 3.373437900897636e-07,
"loss": 0.4130859375,
"step": 1033,
"token_acc": 0.8655052750378222
},
{
"epoch": 0.8871728871728872,
"grad_norm": 0.31358444690704346,
"learning_rate": 3.3234677330196865e-07,
"loss": 0.412841796875,
"step": 1034,
"token_acc": 0.8651584612318118
},
{
"epoch": 0.888030888030888,
"grad_norm": 0.2609347701072693,
"learning_rate": 3.2738577063687436e-07,
"loss": 0.401123046875,
"step": 1035,
"token_acc": 0.8689552700530122
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.32275745272636414,
"learning_rate": 3.224608203719953e-07,
"loss": 0.41455078125,
"step": 1036,
"token_acc": 0.865463242901869
},
{
"epoch": 0.8897468897468898,
"grad_norm": 0.32432234287261963,
"learning_rate": 3.175719605066746e-07,
"loss": 0.420166015625,
"step": 1037,
"token_acc": 0.864319296146493
},
{
"epoch": 0.8906048906048906,
"grad_norm": 0.31731492280960083,
"learning_rate": 3.127192287617964e-07,
"loss": 0.410400390625,
"step": 1038,
"token_acc": 0.8671769071978883
},
{
"epoch": 0.8914628914628915,
"grad_norm": 0.2990749478340149,
"learning_rate": 3.079026625794884e-07,
"loss": 0.410888671875,
"step": 1039,
"token_acc": 0.8672046090182417
},
{
"epoch": 0.8923208923208923,
"grad_norm": 0.31309205293655396,
"learning_rate": 3.0312229912283884e-07,
"loss": 0.431396484375,
"step": 1040,
"token_acc": 0.8613155975368504
},
{
"epoch": 0.8931788931788932,
"grad_norm": 0.301973819732666,
"learning_rate": 2.983781752756071e-07,
"loss": 0.417724609375,
"step": 1041,
"token_acc": 0.8644135308850599
},
{
"epoch": 0.894036894036894,
"grad_norm": 0.5152493119239807,
"learning_rate": 2.9367032764193835e-07,
"loss": 0.4208984375,
"step": 1042,
"token_acc": 0.8639017099294267
},
{
"epoch": 0.8948948948948949,
"grad_norm": 0.34405985474586487,
"learning_rate": 2.88998792546083e-07,
"loss": 0.42529296875,
"step": 1043,
"token_acc": 0.8617402814608777
},
{
"epoch": 0.8957528957528957,
"grad_norm": 0.29931503534317017,
"learning_rate": 2.8436360603211366e-07,
"loss": 0.4052734375,
"step": 1044,
"token_acc": 0.8684612089590144
},
{
"epoch": 0.8966108966108967,
"grad_norm": 0.6099777817726135,
"learning_rate": 2.79764803863653e-07,
"loss": 0.4140625,
"step": 1045,
"token_acc": 0.8651979232904671
},
{
"epoch": 0.8974688974688975,
"grad_norm": 0.33137428760528564,
"learning_rate": 2.7520242152358767e-07,
"loss": 0.436767578125,
"step": 1046,
"token_acc": 0.8593333248006269
},
{
"epoch": 0.8983268983268984,
"grad_norm": 0.32491636276245117,
"learning_rate": 2.706764942138057e-07,
"loss": 0.4091796875,
"step": 1047,
"token_acc": 0.8670189105819215
},
{
"epoch": 0.8991848991848992,
"grad_norm": 0.2969415783882141,
"learning_rate": 2.6618705685491686e-07,
"loss": 0.415771484375,
"step": 1048,
"token_acc": 0.864761367324273
},
{
"epoch": 0.9000429000429,
"grad_norm": 0.2755189538002014,
"learning_rate": 2.617341440859883e-07,
"loss": 0.413818359375,
"step": 1049,
"token_acc": 0.866105726975496
},
{
"epoch": 0.9009009009009009,
"grad_norm": 0.3160327076911926,
"learning_rate": 2.573177902642726e-07,
"loss": 0.40234375,
"step": 1050,
"token_acc": 0.8681739447018573
},
{
"epoch": 0.9017589017589017,
"grad_norm": 0.27056434750556946,
"learning_rate": 2.529380294649475e-07,
"loss": 0.412353515625,
"step": 1051,
"token_acc": 0.8660504943369476
},
{
"epoch": 0.9026169026169026,
"grad_norm": 0.27849081158638,
"learning_rate": 2.485948954808493e-07,
"loss": 0.39892578125,
"step": 1052,
"token_acc": 0.8700607588780325
},
{
"epoch": 0.9034749034749034,
"grad_norm": 0.33912602066993713,
"learning_rate": 2.44288421822213e-07,
"loss": 0.412353515625,
"step": 1053,
"token_acc": 0.865429735189008
},
{
"epoch": 0.9043329043329044,
"grad_norm": 0.3500686287879944,
"learning_rate": 2.4001864171641633e-07,
"loss": 0.427734375,
"step": 1054,
"token_acc": 0.8616763100885733
},
{
"epoch": 0.9051909051909052,
"grad_norm": 0.3614010214805603,
"learning_rate": 2.357855881077181e-07,
"loss": 0.4306640625,
"step": 1055,
"token_acc": 0.8607087962916202
},
{
"epoch": 0.9060489060489061,
"grad_norm": 0.38286301493644714,
"learning_rate": 2.3158929365701188e-07,
"loss": 0.422607421875,
"step": 1056,
"token_acc": 0.8632687336962348
},
{
"epoch": 0.9069069069069069,
"grad_norm": 0.2997244596481323,
"learning_rate": 2.2742979074156347e-07,
"loss": 0.405517578125,
"step": 1057,
"token_acc": 0.8678012287234929
},
{
"epoch": 0.9077649077649078,
"grad_norm": 0.433338463306427,
"learning_rate": 2.2330711145477247e-07,
"loss": 0.41552734375,
"step": 1058,
"token_acc": 0.8648981278275284
},
{
"epoch": 0.9086229086229086,
"grad_norm": 0.31245657801628113,
"learning_rate": 2.192212876059152e-07,
"loss": 0.406494140625,
"step": 1059,
"token_acc": 0.8673288338727287
},
{
"epoch": 0.9094809094809094,
"grad_norm": 0.31379234790802,
"learning_rate": 2.1517235071990383e-07,
"loss": 0.425048828125,
"step": 1060,
"token_acc": 0.8619572358597622
},
{
"epoch": 0.9103389103389103,
"grad_norm": 0.322185754776001,
"learning_rate": 2.1116033203704534e-07,
"loss": 0.411376953125,
"step": 1061,
"token_acc": 0.865651275731082
},
{
"epoch": 0.9111969111969112,
"grad_norm": 0.3562609553337097,
"learning_rate": 2.0718526251279346e-07,
"loss": 0.4150390625,
"step": 1062,
"token_acc": 0.8650804520512844
},
{
"epoch": 0.9120549120549121,
"grad_norm": 0.3134714663028717,
"learning_rate": 2.0324717281751783e-07,
"loss": 0.414306640625,
"step": 1063,
"token_acc": 0.8646337805906936
},
{
"epoch": 0.9129129129129129,
"grad_norm": 0.36550575494766235,
"learning_rate": 1.993460933362601e-07,
"loss": 0.41552734375,
"step": 1064,
"token_acc": 0.8646337323386083
},
{
"epoch": 0.9137709137709138,
"grad_norm": 0.28220149874687195,
"learning_rate": 1.9548205416850597e-07,
"loss": 0.421630859375,
"step": 1065,
"token_acc": 0.8635548557807956
},
{
"epoch": 0.9146289146289146,
"grad_norm": 0.2804998755455017,
"learning_rate": 1.9165508512794805e-07,
"loss": 0.421142578125,
"step": 1066,
"token_acc": 0.8639763939543378
},
{
"epoch": 0.9154869154869155,
"grad_norm": 0.2933475971221924,
"learning_rate": 1.8786521574225837e-07,
"loss": 0.4208984375,
"step": 1067,
"token_acc": 0.8628453604604033
},
{
"epoch": 0.9163449163449163,
"grad_norm": 0.315929114818573,
"learning_rate": 1.8411247525285837e-07,
"loss": 0.4150390625,
"step": 1068,
"token_acc": 0.8647692310211407
},
{
"epoch": 0.9172029172029172,
"grad_norm": 0.2993037700653076,
"learning_rate": 1.803968926146976e-07,
"loss": 0.417724609375,
"step": 1069,
"token_acc": 0.8654062548446758
},
{
"epoch": 0.918060918060918,
"grad_norm": 0.41158023476600647,
"learning_rate": 1.7671849649602502e-07,
"loss": 0.409423828125,
"step": 1070,
"token_acc": 0.8677041179637702
},
{
"epoch": 0.918918918918919,
"grad_norm": 0.2758474051952362,
"learning_rate": 1.7307731527817117e-07,
"loss": 0.422607421875,
"step": 1071,
"token_acc": 0.8636651478794216
},
{
"epoch": 0.9197769197769198,
"grad_norm": 0.3757152855396271,
"learning_rate": 1.6947337705532974e-07,
"loss": 0.41162109375,
"step": 1072,
"token_acc": 0.8666242194251447
},
{
"epoch": 0.9206349206349206,
"grad_norm": 0.35898837447166443,
"learning_rate": 1.6590670963433642e-07,
"loss": 0.421142578125,
"step": 1073,
"token_acc": 0.8634506185673892
},
{
"epoch": 0.9214929214929215,
"grad_norm": 0.2777307331562042,
"learning_rate": 1.623773405344592e-07,
"loss": 0.42578125,
"step": 1074,
"token_acc": 0.8618974366268377
},
{
"epoch": 0.9223509223509223,
"grad_norm": 0.2766513228416443,
"learning_rate": 1.5888529698718347e-07,
"loss": 0.41455078125,
"step": 1075,
"token_acc": 0.8650565836153001
},
{
"epoch": 0.9232089232089232,
"grad_norm": 0.29199716448783875,
"learning_rate": 1.5543060593600334e-07,
"loss": 0.41943359375,
"step": 1076,
"token_acc": 0.8635794231204237
},
{
"epoch": 0.924066924066924,
"grad_norm": 0.29139086604118347,
"learning_rate": 1.5201329403621233e-07,
"loss": 0.40966796875,
"step": 1077,
"token_acc": 0.8664450272797488
},
{
"epoch": 0.924924924924925,
"grad_norm": 0.3384758532047272,
"learning_rate": 1.4863338765469803e-07,
"loss": 0.40234375,
"step": 1078,
"token_acc": 0.8689504787648096
},
{
"epoch": 0.9257829257829258,
"grad_norm": 0.2721219062805176,
"learning_rate": 1.4529091286973994e-07,
"loss": 0.39208984375,
"step": 1079,
"token_acc": 0.872718497625521
},
{
"epoch": 0.9266409266409267,
"grad_norm": 0.3182665705680847,
"learning_rate": 1.4198589547080643e-07,
"loss": 0.41357421875,
"step": 1080,
"token_acc": 0.8659815285577852
},
{
"epoch": 0.9274989274989275,
"grad_norm": 0.28349822759628296,
"learning_rate": 1.387183609583581e-07,
"loss": 0.421142578125,
"step": 1081,
"token_acc": 0.8636106168742461
},
{
"epoch": 0.9283569283569284,
"grad_norm": 1.4684706926345825,
"learning_rate": 1.3548833454364641e-07,
"loss": 0.42578125,
"step": 1082,
"token_acc": 0.8615470296958864
},
{
"epoch": 0.9292149292149292,
"grad_norm": 0.33644166588783264,
"learning_rate": 1.3229584114852645e-07,
"loss": 0.4169921875,
"step": 1083,
"token_acc": 0.8644024621200849
},
{
"epoch": 0.9300729300729301,
"grad_norm": 0.27347779273986816,
"learning_rate": 1.291409054052567e-07,
"loss": 0.41796875,
"step": 1084,
"token_acc": 0.8649815833288487
},
{
"epoch": 0.9309309309309309,
"grad_norm": 0.266899436712265,
"learning_rate": 1.260235516563163e-07,
"loss": 0.408203125,
"step": 1085,
"token_acc": 0.8669934728884227
},
{
"epoch": 0.9317889317889317,
"grad_norm": 0.4451451897621155,
"learning_rate": 1.2294380395421024e-07,
"loss": 0.427734375,
"step": 1086,
"token_acc": 0.8619209262827072
},
{
"epoch": 0.9326469326469327,
"grad_norm": 0.37055444717407227,
"learning_rate": 1.1990168606129115e-07,
"loss": 0.4130859375,
"step": 1087,
"token_acc": 0.8658049020423408
},
{
"epoch": 0.9335049335049335,
"grad_norm": 0.30912309885025024,
"learning_rate": 1.1689722144956672e-07,
"loss": 0.41162109375,
"step": 1088,
"token_acc": 0.8656181012432401
},
{
"epoch": 0.9343629343629344,
"grad_norm": 0.3882233798503876,
"learning_rate": 1.1393043330052922e-07,
"loss": 0.4150390625,
"step": 1089,
"token_acc": 0.8647871633948971
},
{
"epoch": 0.9352209352209352,
"grad_norm": 0.2974086403846741,
"learning_rate": 1.1100134450496902e-07,
"loss": 0.4111328125,
"step": 1090,
"token_acc": 0.8671302228734137
},
{
"epoch": 0.9360789360789361,
"grad_norm": 0.3070789873600006,
"learning_rate": 1.0810997766279974e-07,
"loss": 0.416259765625,
"step": 1091,
"token_acc": 0.864775563911278
},
{
"epoch": 0.9369369369369369,
"grad_norm": 0.32751378417015076,
"learning_rate": 1.0525635508288668e-07,
"loss": 0.4091796875,
"step": 1092,
"token_acc": 0.8666908818915857
},
{
"epoch": 0.9377949377949378,
"grad_norm": 0.29168492555618286,
"learning_rate": 1.0244049878286921e-07,
"loss": 0.40771484375,
"step": 1093,
"token_acc": 0.8676630642542646
},
{
"epoch": 0.9386529386529386,
"grad_norm": 0.3586080074310303,
"learning_rate": 9.966243048899704e-08,
"loss": 0.41162109375,
"step": 1094,
"token_acc": 0.8672284017371303
},
{
"epoch": 0.9395109395109396,
"grad_norm": 0.2893342077732086,
"learning_rate": 9.692217163595808e-08,
"loss": 0.404052734375,
"step": 1095,
"token_acc": 0.8675381905625277
},
{
"epoch": 0.9403689403689404,
"grad_norm": 1.0185339450836182,
"learning_rate": 9.42197433667158e-08,
"loss": 0.403076171875,
"step": 1096,
"token_acc": 0.8681907247271807
},
{
"epoch": 0.9412269412269412,
"grad_norm": 0.3057374656200409,
"learning_rate": 9.155516653234276e-08,
"loss": 0.414306640625,
"step": 1097,
"token_acc": 0.864623286851977
},
{
"epoch": 0.9420849420849421,
"grad_norm": 0.3293688893318176,
"learning_rate": 8.892846169186509e-08,
"loss": 0.39599609375,
"step": 1098,
"token_acc": 0.8706257064147132
},
{
"epoch": 0.9429429429429429,
"grad_norm": 0.31847789883613586,
"learning_rate": 8.633964911209825e-08,
"loss": 0.4140625,
"step": 1099,
"token_acc": 0.8658178417989265
},
{
"epoch": 0.9438009438009438,
"grad_norm": 0.30129218101501465,
"learning_rate": 8.378874876749433e-08,
"loss": 0.407470703125,
"step": 1100,
"token_acc": 0.8677131600787381
},
{
"epoch": 0.9446589446589446,
"grad_norm": 0.3038902282714844,
"learning_rate": 8.127578033998663e-08,
"loss": 0.409423828125,
"step": 1101,
"token_acc": 0.8667997782306401
},
{
"epoch": 0.9455169455169455,
"grad_norm": 0.31644073128700256,
"learning_rate": 7.880076321883589e-08,
"loss": 0.408447265625,
"step": 1102,
"token_acc": 0.8669392931193515
},
{
"epoch": 0.9463749463749463,
"grad_norm": 0.3241233825683594,
"learning_rate": 7.636371650048658e-08,
"loss": 0.4228515625,
"step": 1103,
"token_acc": 0.8628125951376506
},
{
"epoch": 0.9472329472329473,
"grad_norm": 0.29971325397491455,
"learning_rate": 7.396465898841187e-08,
"loss": 0.418212890625,
"step": 1104,
"token_acc": 0.8637386516968073
},
{
"epoch": 0.9480909480909481,
"grad_norm": 0.2797969877719879,
"learning_rate": 7.160360919297448e-08,
"loss": 0.403564453125,
"step": 1105,
"token_acc": 0.867952818366678
},
{
"epoch": 0.948948948948949,
"grad_norm": 0.3030215799808502,
"learning_rate": 6.928058533128112e-08,
"loss": 0.407958984375,
"step": 1106,
"token_acc": 0.8669325507729337
},
{
"epoch": 0.9498069498069498,
"grad_norm": 0.3026755452156067,
"learning_rate": 6.699560532704319e-08,
"loss": 0.42431640625,
"step": 1107,
"token_acc": 0.8623879071404315
},
{
"epoch": 0.9506649506649507,
"grad_norm": 0.2870003581047058,
"learning_rate": 6.474868681043578e-08,
"loss": 0.419677734375,
"step": 1108,
"token_acc": 0.8627811772444414
},
{
"epoch": 0.9515229515229515,
"grad_norm": 0.2803478538990021,
"learning_rate": 6.253984711796612e-08,
"loss": 0.412841796875,
"step": 1109,
"token_acc": 0.8657546419880796
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.329607218503952,
"learning_rate": 6.036910329233592e-08,
"loss": 0.40380859375,
"step": 1110,
"token_acc": 0.8675632236307634
},
{
"epoch": 0.9532389532389532,
"grad_norm": 1.0581337213516235,
"learning_rate": 5.823647208231198e-08,
"loss": 0.419677734375,
"step": 1111,
"token_acc": 0.8629242213834255
},
{
"epoch": 0.954096954096954,
"grad_norm": 0.35133951902389526,
"learning_rate": 5.6141969942596906e-08,
"loss": 0.412841796875,
"step": 1112,
"token_acc": 0.866155725740221
},
{
"epoch": 0.954954954954955,
"grad_norm": 0.7583909630775452,
"learning_rate": 5.408561303369919e-08,
"loss": 0.429443359375,
"step": 1113,
"token_acc": 0.8624947205246751
},
{
"epoch": 0.9558129558129558,
"grad_norm": 0.29131636023521423,
"learning_rate": 5.206741722181385e-08,
"loss": 0.4052734375,
"step": 1114,
"token_acc": 0.8682627062312286
},
{
"epoch": 0.9566709566709567,
"grad_norm": 0.3524489998817444,
"learning_rate": 5.0087398078694785e-08,
"loss": 0.419189453125,
"step": 1115,
"token_acc": 0.8634274672473365
},
{
"epoch": 0.9575289575289575,
"grad_norm": 0.30765748023986816,
"learning_rate": 4.814557088153815e-08,
"loss": 0.41064453125,
"step": 1116,
"token_acc": 0.8668441758753972
},
{
"epoch": 0.9583869583869584,
"grad_norm": 0.31046169996261597,
"learning_rate": 4.6241950612863074e-08,
"loss": 0.446044921875,
"step": 1117,
"token_acc": 0.8569488543235823
},
{
"epoch": 0.9592449592449592,
"grad_norm": 0.3297596573829651,
"learning_rate": 4.437655196039559e-08,
"loss": 0.4052734375,
"step": 1118,
"token_acc": 0.8670191989572303
},
{
"epoch": 0.9601029601029601,
"grad_norm": 0.3172093629837036,
"learning_rate": 4.254938931695707e-08,
"loss": 0.3994140625,
"step": 1119,
"token_acc": 0.8691783707026856
},
{
"epoch": 0.960960960960961,
"grad_norm": 0.35847461223602295,
"learning_rate": 4.0760476780351e-08,
"loss": 0.41796875,
"step": 1120,
"token_acc": 0.8643322387717536
},
{
"epoch": 0.9618189618189619,
"grad_norm": 0.3244157135486603,
"learning_rate": 3.900982815325582e-08,
"loss": 0.426513671875,
"step": 1121,
"token_acc": 0.8617169949250778
},
{
"epoch": 0.9626769626769627,
"grad_norm": 0.3464740216732025,
"learning_rate": 3.7297456943116705e-08,
"loss": 0.4072265625,
"step": 1122,
"token_acc": 0.8674503960104255
},
{
"epoch": 0.9635349635349635,
"grad_norm": 0.32333439588546753,
"learning_rate": 3.562337636204505e-08,
"loss": 0.40673828125,
"step": 1123,
"token_acc": 0.8683804206733173
},
{
"epoch": 0.9643929643929644,
"grad_norm": 0.2892231047153473,
"learning_rate": 3.3987599326710806e-08,
"loss": 0.4169921875,
"step": 1124,
"token_acc": 0.8643624859244141
},
{
"epoch": 0.9652509652509652,
"grad_norm": 0.3944212794303894,
"learning_rate": 3.2390138458248674e-08,
"loss": 0.405029296875,
"step": 1125,
"token_acc": 0.8679199179070558
},
{
"epoch": 0.9661089661089661,
"grad_norm": 0.2932316064834595,
"learning_rate": 3.08310060821565e-08,
"loss": 0.407958984375,
"step": 1126,
"token_acc": 0.8667499741611159
},
{
"epoch": 0.9669669669669669,
"grad_norm": 0.30061134696006775,
"learning_rate": 2.9310214228202016e-08,
"loss": 0.406494140625,
"step": 1127,
"token_acc": 0.867972085238269
},
{
"epoch": 0.9678249678249679,
"grad_norm": 0.36009982228279114,
"learning_rate": 2.7827774630330152e-08,
"loss": 0.404052734375,
"step": 1128,
"token_acc": 0.8684103234186574
},
{
"epoch": 0.9686829686829687,
"grad_norm": 0.2809729278087616,
"learning_rate": 2.6383698726570872e-08,
"loss": 0.432373046875,
"step": 1129,
"token_acc": 0.8606503319631532
},
{
"epoch": 0.9695409695409696,
"grad_norm": 0.3869607150554657,
"learning_rate": 2.4977997658954257e-08,
"loss": 0.4130859375,
"step": 1130,
"token_acc": 0.8661074697705955
},
{
"epoch": 0.9703989703989704,
"grad_norm": 0.2741890549659729,
"learning_rate": 2.361068227342056e-08,
"loss": 0.42041015625,
"step": 1131,
"token_acc": 0.8644095607941804
},
{
"epoch": 0.9712569712569713,
"grad_norm": 0.32328709959983826,
"learning_rate": 2.228176311973862e-08,
"loss": 0.396240234375,
"step": 1132,
"token_acc": 0.8701593215177106
},
{
"epoch": 0.9721149721149721,
"grad_norm": 0.29675012826919556,
"learning_rate": 2.0991250451424806e-08,
"loss": 0.419677734375,
"step": 1133,
"token_acc": 0.8634008675780744
},
{
"epoch": 0.972972972972973,
"grad_norm": 0.3162553310394287,
"learning_rate": 1.9739154225663638e-08,
"loss": 0.409423828125,
"step": 1134,
"token_acc": 0.8663221422953336
},
{
"epoch": 0.9738309738309738,
"grad_norm": 0.2855226695537567,
"learning_rate": 1.8525484103228965e-08,
"loss": 0.41845703125,
"step": 1135,
"token_acc": 0.8636003154554955
},
{
"epoch": 0.9746889746889746,
"grad_norm": 0.2870618402957916,
"learning_rate": 1.735024944841235e-08,
"loss": 0.416015625,
"step": 1136,
"token_acc": 0.8647517183589498
},
{
"epoch": 0.9755469755469756,
"grad_norm": 0.3138873875141144,
"learning_rate": 1.6213459328950355e-08,
"loss": 0.402099609375,
"step": 1137,
"token_acc": 0.8689142424052109
},
{
"epoch": 0.9764049764049764,
"grad_norm": 0.30583125352859497,
"learning_rate": 1.5115122515951263e-08,
"loss": 0.420654296875,
"step": 1138,
"token_acc": 0.8632624206243414
},
{
"epoch": 0.9772629772629773,
"grad_norm": 0.30399248003959656,
"learning_rate": 1.4055247483832356e-08,
"loss": 0.428955078125,
"step": 1139,
"token_acc": 0.8602564296110167
},
{
"epoch": 0.9781209781209781,
"grad_norm": 0.29383546113967896,
"learning_rate": 1.3033842410251074e-08,
"loss": 0.40625,
"step": 1140,
"token_acc": 0.8674999340739864
},
{
"epoch": 0.978978978978979,
"grad_norm": 0.3356133699417114,
"learning_rate": 1.2050915176042288e-08,
"loss": 0.443359375,
"step": 1141,
"token_acc": 0.8558928357355613
},
{
"epoch": 0.9798369798369798,
"grad_norm": 0.2824721336364746,
"learning_rate": 1.110647336516002e-08,
"loss": 0.41357421875,
"step": 1142,
"token_acc": 0.8659241496248641
},
{
"epoch": 0.9806949806949807,
"grad_norm": 0.29556241631507874,
"learning_rate": 1.0200524264615264e-08,
"loss": 0.410888671875,
"step": 1143,
"token_acc": 0.8665555714890875
},
{
"epoch": 0.9815529815529815,
"grad_norm": 0.2698670029640198,
"learning_rate": 9.333074864421588e-09,
"loss": 0.417724609375,
"step": 1144,
"token_acc": 0.8642227075952139
},
{
"epoch": 0.9824109824109825,
"grad_norm": 0.30624091625213623,
"learning_rate": 8.504131857542952e-09,
"loss": 0.42919921875,
"step": 1145,
"token_acc": 0.8609530724870911
},
{
"epoch": 0.9832689832689833,
"grad_norm": 0.2660980224609375,
"learning_rate": 7.7137016398382e-09,
"loss": 0.4140625,
"step": 1146,
"token_acc": 0.8643757104423266
},
{
"epoch": 0.9841269841269841,
"grad_norm": 0.27201172709465027,
"learning_rate": 6.961790310014427e-09,
"loss": 0.4130859375,
"step": 1147,
"token_acc": 0.865659150441764
},
{
"epoch": 0.984984984984985,
"grad_norm": 0.274884968996048,
"learning_rate": 6.24840366958035e-09,
"loss": 0.40185546875,
"step": 1148,
"token_acc": 0.8686461434331962
},
{
"epoch": 0.9858429858429858,
"grad_norm": 0.30692675709724426,
"learning_rate": 5.573547222799125e-09,
"loss": 0.393798828125,
"step": 1149,
"token_acc": 0.8709112518287344
},
{
"epoch": 0.9867009867009867,
"grad_norm": 0.2824662923812866,
"learning_rate": 4.937226176647824e-09,
"loss": 0.411865234375,
"step": 1150,
"token_acc": 0.8657978819239549
},
{
"epoch": 0.9875589875589875,
"grad_norm": 0.3064286410808563,
"learning_rate": 4.339445440776358e-09,
"loss": 0.409423828125,
"step": 1151,
"token_acc": 0.866976162941687
},
{
"epoch": 0.9884169884169884,
"grad_norm": 0.41891413927078247,
"learning_rate": 3.780209627470832e-09,
"loss": 0.41064453125,
"step": 1152,
"token_acc": 0.8660931573801441
},
{
"epoch": 0.9892749892749892,
"grad_norm": 0.3276737630367279,
"learning_rate": 3.2595230516152543e-09,
"loss": 0.415771484375,
"step": 1153,
"token_acc": 0.8649244170037166
},
{
"epoch": 0.9901329901329902,
"grad_norm": 0.2648158669471741,
"learning_rate": 2.7773897306615504e-09,
"loss": 0.38427734375,
"step": 1154,
"token_acc": 0.8739889476879696
},
{
"epoch": 0.990990990990991,
"grad_norm": 0.3036111295223236,
"learning_rate": 2.3338133845968168e-09,
"loss": 0.41748046875,
"step": 1155,
"token_acc": 0.8639755354623959
},
{
"epoch": 0.9918489918489919,
"grad_norm": 0.2894406318664551,
"learning_rate": 1.9287974359144536e-09,
"loss": 0.413818359375,
"step": 1156,
"token_acc": 0.8646087713611794
},
{
"epoch": 0.9927069927069927,
"grad_norm": 0.30504080653190613,
"learning_rate": 1.5623450095880731e-09,
"loss": 0.4052734375,
"step": 1157,
"token_acc": 0.8677748353246193
},
{
"epoch": 0.9935649935649936,
"grad_norm": 0.2910107970237732,
"learning_rate": 1.2344589330476331e-09,
"loss": 0.401611328125,
"step": 1158,
"token_acc": 0.8691577375213506
},
{
"epoch": 0.9944229944229944,
"grad_norm": 0.3135044276714325,
"learning_rate": 9.451417361577841e-10,
"loss": 0.407958984375,
"step": 1159,
"token_acc": 0.86685201714348
},
{
"epoch": 0.9952809952809952,
"grad_norm": 0.29154089093208313,
"learning_rate": 6.943956511973326e-10,
"loss": 0.400634765625,
"step": 1160,
"token_acc": 0.8696246181748759
},
{
"epoch": 0.9961389961389961,
"grad_norm": 0.2961388826370239,
"learning_rate": 4.822226128436969e-10,
"loss": 0.4013671875,
"step": 1161,
"token_acc": 0.8696908936610905
},
{
"epoch": 0.996996996996997,
"grad_norm": 0.25889694690704346,
"learning_rate": 3.086242581551435e-10,
"loss": 0.405029296875,
"step": 1162,
"token_acc": 0.8680250850316359
},
{
"epoch": 0.9978549978549979,
"grad_norm": 0.2958817481994629,
"learning_rate": 1.7360192656246112e-10,
"loss": 0.398681640625,
"step": 1163,
"token_acc": 0.8701747271647156
},
{
"epoch": 0.9987129987129987,
"grad_norm": 0.31657740473747253,
"learning_rate": 7.715665985397192e-11,
"loss": 0.40380859375,
"step": 1164,
"token_acc": 0.8679068373003509
},
{
"epoch": 0.9995709995709996,
"grad_norm": 0.2774425745010376,
"learning_rate": 1.9289202170535982e-11,
"loss": 0.396484375,
"step": 1165,
"token_acc": 0.8697087594551153
},
{
"epoch": 1.0,
"grad_norm": 0.390720933675766,
"learning_rate": 0.0,
"loss": 0.3974609375,
"step": 1166,
"token_acc": 0.8702236900115369
}
],
"logging_steps": 1,
"max_steps": 1166,
"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": 1.613836070972031e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}