MileTone_2 / models /sft /sft_f3f4_instruct /trainer_state.json
SciCode's picture
Add selected SFT variants S1-S4
3eea076 verified
Raw History Blame Contribute Delete
324 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500.0,
"global_step": 15033,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.652142821506377e-05,
"grad_norm": 6.46875,
"learning_rate": 4.4345898004434594e-08,
"loss": 1.0032552480697632,
"step": 1,
"token_acc": 0.7789563003818413
},
{
"epoch": 0.0006652142821506377,
"grad_norm": 5.6875,
"learning_rate": 4.4345898004434597e-07,
"loss": 1.0671126047770183,
"step": 10,
"token_acc": 0.7644378405151064
},
{
"epoch": 0.0013304285643012754,
"grad_norm": 5.84375,
"learning_rate": 8.869179600886919e-07,
"loss": 1.0109123229980468,
"step": 20,
"token_acc": 0.7762102563120921
},
{
"epoch": 0.0019956428464519135,
"grad_norm": 5.78125,
"learning_rate": 1.3303769401330377e-06,
"loss": 1.0621016502380372,
"step": 30,
"token_acc": 0.7661449409901638
},
{
"epoch": 0.002660857128602551,
"grad_norm": 5.96875,
"learning_rate": 1.7738359201773839e-06,
"loss": 1.0493683815002441,
"step": 40,
"token_acc": 0.7639085950589997
},
{
"epoch": 0.0033260714107531887,
"grad_norm": 4.8125,
"learning_rate": 2.2172949002217296e-06,
"loss": 1.032841682434082,
"step": 50,
"token_acc": 0.7689052697423695
},
{
"epoch": 0.003991285692903827,
"grad_norm": 4.46875,
"learning_rate": 2.6607538802660755e-06,
"loss": 0.9852850914001465,
"step": 60,
"token_acc": 0.7744265160263413
},
{
"epoch": 0.004656499975054465,
"grad_norm": 4.625,
"learning_rate": 3.1042128603104214e-06,
"loss": 0.9635690689086914,
"step": 70,
"token_acc": 0.7782710343522798
},
{
"epoch": 0.005321714257205102,
"grad_norm": 3.671875,
"learning_rate": 3.5476718403547677e-06,
"loss": 1.0110140800476075,
"step": 80,
"token_acc": 0.7660821802049224
},
{
"epoch": 0.00598692853935574,
"grad_norm": 3.9375,
"learning_rate": 3.991130820399114e-06,
"loss": 0.9889877319335938,
"step": 90,
"token_acc": 0.7712937530812028
},
{
"epoch": 0.0066521428215063775,
"grad_norm": 2.453125,
"learning_rate": 4.434589800443459e-06,
"loss": 0.9471888542175293,
"step": 100,
"token_acc": 0.77793120930729
},
{
"epoch": 0.007317357103657015,
"grad_norm": 1.9765625,
"learning_rate": 4.8780487804878055e-06,
"loss": 0.9458837509155273,
"step": 110,
"token_acc": 0.7781413113549559
},
{
"epoch": 0.007982571385807654,
"grad_norm": 2.390625,
"learning_rate": 5.321507760532151e-06,
"loss": 0.99730224609375,
"step": 120,
"token_acc": 0.7645416008644336
},
{
"epoch": 0.008647785667958291,
"grad_norm": 2.078125,
"learning_rate": 5.764966740576497e-06,
"loss": 0.9386472702026367,
"step": 130,
"token_acc": 0.7759279222679927
},
{
"epoch": 0.00931299995010893,
"grad_norm": 2.296875,
"learning_rate": 6.208425720620843e-06,
"loss": 0.9167892456054687,
"step": 140,
"token_acc": 0.7838547282475331
},
{
"epoch": 0.009978214232259567,
"grad_norm": 2.21875,
"learning_rate": 6.651884700665189e-06,
"loss": 0.9006868362426758,
"step": 150,
"token_acc": 0.7854545985486721
},
{
"epoch": 0.010643428514410204,
"grad_norm": 2.140625,
"learning_rate": 7.0953436807095355e-06,
"loss": 0.8818325996398926,
"step": 160,
"token_acc": 0.7893832441186288
},
{
"epoch": 0.011308642796560842,
"grad_norm": 2.15625,
"learning_rate": 7.538802660753881e-06,
"loss": 0.9082184791564941,
"step": 170,
"token_acc": 0.7821340264008152
},
{
"epoch": 0.01197385707871148,
"grad_norm": 2.234375,
"learning_rate": 7.982261640798227e-06,
"loss": 0.9012106895446778,
"step": 180,
"token_acc": 0.7873876730393676
},
{
"epoch": 0.012639071360862118,
"grad_norm": 2.21875,
"learning_rate": 8.425720620842573e-06,
"loss": 0.9063202857971191,
"step": 190,
"token_acc": 0.7864864285561184
},
{
"epoch": 0.013304285643012755,
"grad_norm": 2.234375,
"learning_rate": 8.869179600886918e-06,
"loss": 0.9235092163085937,
"step": 200,
"token_acc": 0.7807251133634718
},
{
"epoch": 0.013969499925163394,
"grad_norm": 2.03125,
"learning_rate": 9.312638580931265e-06,
"loss": 0.9070497512817383,
"step": 210,
"token_acc": 0.7842770375459549
},
{
"epoch": 0.01463471420731403,
"grad_norm": 1.9765625,
"learning_rate": 9.756097560975611e-06,
"loss": 0.9458281517028808,
"step": 220,
"token_acc": 0.7789438760655694
},
{
"epoch": 0.01529992848946467,
"grad_norm": 1.8203125,
"learning_rate": 1.0199556541019956e-05,
"loss": 0.9144332885742188,
"step": 230,
"token_acc": 0.7836323093819683
},
{
"epoch": 0.015965142771615308,
"grad_norm": 2.015625,
"learning_rate": 1.0643015521064302e-05,
"loss": 0.9030343055725097,
"step": 240,
"token_acc": 0.7827914649071462
},
{
"epoch": 0.016630357053765945,
"grad_norm": 1.96875,
"learning_rate": 1.1086474501108649e-05,
"loss": 0.8824579238891601,
"step": 250,
"token_acc": 0.7905821852093488
},
{
"epoch": 0.017295571335916582,
"grad_norm": 2.203125,
"learning_rate": 1.1529933481152995e-05,
"loss": 0.9404327392578125,
"step": 260,
"token_acc": 0.7759785743716523
},
{
"epoch": 0.01796078561806722,
"grad_norm": 2.1875,
"learning_rate": 1.197339246119734e-05,
"loss": 0.9133252143859864,
"step": 270,
"token_acc": 0.7808589002021732
},
{
"epoch": 0.01862599990021786,
"grad_norm": 1.984375,
"learning_rate": 1.2416851441241686e-05,
"loss": 0.8845050811767579,
"step": 280,
"token_acc": 0.7904191185991971
},
{
"epoch": 0.019291214182368496,
"grad_norm": 2.171875,
"learning_rate": 1.2860310421286033e-05,
"loss": 0.8647794723510742,
"step": 290,
"token_acc": 0.793174395569935
},
{
"epoch": 0.019956428464519133,
"grad_norm": 2.125,
"learning_rate": 1.3303769401330378e-05,
"loss": 0.9063952445983887,
"step": 300,
"token_acc": 0.7849687140492158
},
{
"epoch": 0.02062164274666977,
"grad_norm": 2.109375,
"learning_rate": 1.3747228381374724e-05,
"loss": 0.9172356605529786,
"step": 310,
"token_acc": 0.782409823068218
},
{
"epoch": 0.021286857028820407,
"grad_norm": 2.15625,
"learning_rate": 1.4190687361419071e-05,
"loss": 0.9081380844116211,
"step": 320,
"token_acc": 0.7856550752269242
},
{
"epoch": 0.021952071310971048,
"grad_norm": 2.171875,
"learning_rate": 1.4634146341463415e-05,
"loss": 0.8435260772705078,
"step": 330,
"token_acc": 0.8008349415147099
},
{
"epoch": 0.022617285593121685,
"grad_norm": 2.59375,
"learning_rate": 1.5077605321507762e-05,
"loss": 0.8369804382324219,
"step": 340,
"token_acc": 0.7970755893824314
},
{
"epoch": 0.02328249987527232,
"grad_norm": 2.328125,
"learning_rate": 1.5521064301552106e-05,
"loss": 0.8634052276611328,
"step": 350,
"token_acc": 0.790367588062796
},
{
"epoch": 0.02394771415742296,
"grad_norm": 1.75,
"learning_rate": 1.5964523281596455e-05,
"loss": 0.8523602485656738,
"step": 360,
"token_acc": 0.7950500029394282
},
{
"epoch": 0.0246129284395736,
"grad_norm": 1.90625,
"learning_rate": 1.64079822616408e-05,
"loss": 0.8734794616699219,
"step": 370,
"token_acc": 0.7913562047708389
},
{
"epoch": 0.025278142721724236,
"grad_norm": 2.25,
"learning_rate": 1.6851441241685146e-05,
"loss": 0.8646720886230469,
"step": 380,
"token_acc": 0.7947544504023203
},
{
"epoch": 0.025943357003874873,
"grad_norm": 1.9296875,
"learning_rate": 1.729490022172949e-05,
"loss": 0.881674861907959,
"step": 390,
"token_acc": 0.7888156529331358
},
{
"epoch": 0.02660857128602551,
"grad_norm": 2.078125,
"learning_rate": 1.7738359201773837e-05,
"loss": 0.8686661720275879,
"step": 400,
"token_acc": 0.7893515376012515
},
{
"epoch": 0.02727378556817615,
"grad_norm": 2.1875,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.8588180541992188,
"step": 410,
"token_acc": 0.7935298632629275
},
{
"epoch": 0.027938999850326787,
"grad_norm": 2.03125,
"learning_rate": 1.862527716186253e-05,
"loss": 0.8464418411254883,
"step": 420,
"token_acc": 0.7971932114882506
},
{
"epoch": 0.028604214132477424,
"grad_norm": 2.1875,
"learning_rate": 1.9068736141906876e-05,
"loss": 0.8996849060058594,
"step": 430,
"token_acc": 0.7864237731047599
},
{
"epoch": 0.02926942841462806,
"grad_norm": 1.796875,
"learning_rate": 1.9512195121951222e-05,
"loss": 0.8839289665222168,
"step": 440,
"token_acc": 0.788282809587393
},
{
"epoch": 0.029934642696778698,
"grad_norm": 1.8125,
"learning_rate": 1.9955654101995567e-05,
"loss": 0.8282587051391601,
"step": 450,
"token_acc": 0.801934299848228
},
{
"epoch": 0.03059985697892934,
"grad_norm": 2.546875,
"learning_rate": 1.9999981201619123e-05,
"loss": 0.8479324340820312,
"step": 460,
"token_acc": 0.7970263005162355
},
{
"epoch": 0.031265071261079976,
"grad_norm": 2.28125,
"learning_rate": 1.9999916219652494e-05,
"loss": 0.8353096008300781,
"step": 470,
"token_acc": 0.7954245057510053
},
{
"epoch": 0.031930285543230616,
"grad_norm": 1.953125,
"learning_rate": 1.999980482232289e-05,
"loss": 0.871000099182129,
"step": 480,
"token_acc": 0.7964856672075268
},
{
"epoch": 0.03259549982538125,
"grad_norm": 1.90625,
"learning_rate": 1.9999647010147373e-05,
"loss": 0.8139250755310059,
"step": 490,
"token_acc": 0.8040610068622889
},
{
"epoch": 0.03326071410753189,
"grad_norm": 2.109375,
"learning_rate": 1.9999442783858437e-05,
"loss": 0.8422445297241211,
"step": 500,
"token_acc": 0.7948968682364599
},
{
"epoch": 0.03392592838968252,
"grad_norm": 2.15625,
"learning_rate": 1.9999192144404008e-05,
"loss": 0.8766986846923828,
"step": 510,
"token_acc": 0.7926061344708512
},
{
"epoch": 0.034591142671833164,
"grad_norm": 2.109375,
"learning_rate": 1.999889509294746e-05,
"loss": 0.9220952033996582,
"step": 520,
"token_acc": 0.7823761335260875
},
{
"epoch": 0.035256356953983804,
"grad_norm": 2.015625,
"learning_rate": 1.999855163086757e-05,
"loss": 0.8473668098449707,
"step": 530,
"token_acc": 0.7985852729947218
},
{
"epoch": 0.03592157123613444,
"grad_norm": 2.265625,
"learning_rate": 1.999816175975854e-05,
"loss": 0.8338323593139648,
"step": 540,
"token_acc": 0.799237684286228
},
{
"epoch": 0.03658678551828508,
"grad_norm": 2.359375,
"learning_rate": 1.999772548143e-05,
"loss": 0.8823687553405761,
"step": 550,
"token_acc": 0.7876458457512041
},
{
"epoch": 0.03725199980043572,
"grad_norm": 2.34375,
"learning_rate": 1.9997242797906954e-05,
"loss": 0.9371931076049804,
"step": 560,
"token_acc": 0.7758809769827133
},
{
"epoch": 0.03791721408258635,
"grad_norm": 2.125,
"learning_rate": 1.9996713711429823e-05,
"loss": 0.8702743530273438,
"step": 570,
"token_acc": 0.7939736372094287
},
{
"epoch": 0.03858242836473699,
"grad_norm": 2.125,
"learning_rate": 1.99961382244544e-05,
"loss": 0.8530454635620117,
"step": 580,
"token_acc": 0.7946033452094239
},
{
"epoch": 0.039247642646887626,
"grad_norm": 2.140625,
"learning_rate": 1.999551633965185e-05,
"loss": 0.8797110557556153,
"step": 590,
"token_acc": 0.7889623075155137
},
{
"epoch": 0.039912856929038266,
"grad_norm": 1.71875,
"learning_rate": 1.9994848059908697e-05,
"loss": 0.851103401184082,
"step": 600,
"token_acc": 0.7971391741342483
},
{
"epoch": 0.04057807121118891,
"grad_norm": 2.203125,
"learning_rate": 1.9994133388326814e-05,
"loss": 0.8700343132019043,
"step": 610,
"token_acc": 0.7902323348831878
},
{
"epoch": 0.04124328549333954,
"grad_norm": 2.03125,
"learning_rate": 1.99933723282234e-05,
"loss": 0.8223074913024903,
"step": 620,
"token_acc": 0.7987239129869792
},
{
"epoch": 0.04190849977549018,
"grad_norm": 2.15625,
"learning_rate": 1.9992564883130975e-05,
"loss": 0.8797379493713379,
"step": 630,
"token_acc": 0.7910438131858916
},
{
"epoch": 0.042573714057640814,
"grad_norm": 1.9140625,
"learning_rate": 1.9991711056797358e-05,
"loss": 0.8693501472473144,
"step": 640,
"token_acc": 0.7921797572772321
},
{
"epoch": 0.043238928339791455,
"grad_norm": 2.078125,
"learning_rate": 1.9990810853185645e-05,
"loss": 0.7954109191894532,
"step": 650,
"token_acc": 0.8092031263519165
},
{
"epoch": 0.043904142621942095,
"grad_norm": 1.921875,
"learning_rate": 1.9989864276474198e-05,
"loss": 0.8263605117797852,
"step": 660,
"token_acc": 0.7994725001939338
},
{
"epoch": 0.04456935690409273,
"grad_norm": 2.375,
"learning_rate": 1.9988871331056625e-05,
"loss": 0.8481286048889161,
"step": 670,
"token_acc": 0.7953266446615902
},
{
"epoch": 0.04523457118624337,
"grad_norm": 2.0,
"learning_rate": 1.998783202154176e-05,
"loss": 0.8636644363403321,
"step": 680,
"token_acc": 0.7941210831018458
},
{
"epoch": 0.04589978546839401,
"grad_norm": 2.046875,
"learning_rate": 1.998674635275363e-05,
"loss": 0.8527099609375,
"step": 690,
"token_acc": 0.795036709343649
},
{
"epoch": 0.04656499975054464,
"grad_norm": 2.421875,
"learning_rate": 1.998561432973145e-05,
"loss": 0.8760289192199707,
"step": 700,
"token_acc": 0.7904941760821622
},
{
"epoch": 0.047230214032695284,
"grad_norm": 2.15625,
"learning_rate": 1.9984435957729596e-05,
"loss": 0.8014123916625977,
"step": 710,
"token_acc": 0.8056973809693722
},
{
"epoch": 0.04789542831484592,
"grad_norm": 1.703125,
"learning_rate": 1.9983211242217564e-05,
"loss": 0.8793704032897949,
"step": 720,
"token_acc": 0.7895839000904703
},
{
"epoch": 0.04856064259699656,
"grad_norm": 2.390625,
"learning_rate": 1.9981940188879964e-05,
"loss": 0.8566852569580078,
"step": 730,
"token_acc": 0.7944913754833397
},
{
"epoch": 0.0492258568791472,
"grad_norm": 2.21875,
"learning_rate": 1.998062280361649e-05,
"loss": 0.8718212127685547,
"step": 740,
"token_acc": 0.7928690363153477
},
{
"epoch": 0.04989107116129783,
"grad_norm": 2.203125,
"learning_rate": 1.997925909254188e-05,
"loss": 0.8628096580505371,
"step": 750,
"token_acc": 0.7908997988294347
},
{
"epoch": 0.05055628544344847,
"grad_norm": 1.984375,
"learning_rate": 1.9977849061985903e-05,
"loss": 0.8801427841186523,
"step": 760,
"token_acc": 0.78870904119114
},
{
"epoch": 0.051221499725599105,
"grad_norm": 2.078125,
"learning_rate": 1.997639271849332e-05,
"loss": 0.8521597862243653,
"step": 770,
"token_acc": 0.7962424766401756
},
{
"epoch": 0.051886714007749746,
"grad_norm": 2.0,
"learning_rate": 1.9974890068823863e-05,
"loss": 0.8868481636047363,
"step": 780,
"token_acc": 0.7896258362930536
},
{
"epoch": 0.052551928289900386,
"grad_norm": 2.171875,
"learning_rate": 1.997334111995219e-05,
"loss": 0.88748779296875,
"step": 790,
"token_acc": 0.7867539767540487
},
{
"epoch": 0.05321714257205102,
"grad_norm": 2.09375,
"learning_rate": 1.9971745879067862e-05,
"loss": 0.8355445861816406,
"step": 800,
"token_acc": 0.7978200352871986
},
{
"epoch": 0.05388235685420166,
"grad_norm": 2.078125,
"learning_rate": 1.9970104353575318e-05,
"loss": 0.8657492637634278,
"step": 810,
"token_acc": 0.7897543754225194
},
{
"epoch": 0.0545475711363523,
"grad_norm": 1.9921875,
"learning_rate": 1.996841655109381e-05,
"loss": 0.8115781784057617,
"step": 820,
"token_acc": 0.803683813894754
},
{
"epoch": 0.055212785418502934,
"grad_norm": 2.625,
"learning_rate": 1.996668247945741e-05,
"loss": 0.857795524597168,
"step": 830,
"token_acc": 0.7978350584208226
},
{
"epoch": 0.055877999700653574,
"grad_norm": 2.375,
"learning_rate": 1.9964902146714937e-05,
"loss": 0.8655693054199218,
"step": 840,
"token_acc": 0.792825412280168
},
{
"epoch": 0.05654321398280421,
"grad_norm": 2.015625,
"learning_rate": 1.9963075561129943e-05,
"loss": 0.7916995525360108,
"step": 850,
"token_acc": 0.8062171554500763
},
{
"epoch": 0.05720842826495485,
"grad_norm": 2.453125,
"learning_rate": 1.9961202731180656e-05,
"loss": 0.8283356666564942,
"step": 860,
"token_acc": 0.8012577081284413
},
{
"epoch": 0.05787364254710549,
"grad_norm": 1.9765625,
"learning_rate": 1.995928366555996e-05,
"loss": 0.8634213447570801,
"step": 870,
"token_acc": 0.7945368503584229
},
{
"epoch": 0.05853885682925612,
"grad_norm": 2.0,
"learning_rate": 1.9957318373175346e-05,
"loss": 0.8153613090515137,
"step": 880,
"token_acc": 0.8038088633423576
},
{
"epoch": 0.05920407111140676,
"grad_norm": 3.5,
"learning_rate": 1.9955306863148865e-05,
"loss": 0.8488476753234864,
"step": 890,
"token_acc": 0.7956926619020537
},
{
"epoch": 0.059869285393557396,
"grad_norm": 2.015625,
"learning_rate": 1.995324914481709e-05,
"loss": 0.8491480827331543,
"step": 900,
"token_acc": 0.7961175428414332
},
{
"epoch": 0.06053449967570804,
"grad_norm": 2.109375,
"learning_rate": 1.9951145227731072e-05,
"loss": 0.8101947784423829,
"step": 910,
"token_acc": 0.805350822402665
},
{
"epoch": 0.06119971395785868,
"grad_norm": 2.25,
"learning_rate": 1.9948995121656304e-05,
"loss": 0.7924930095672608,
"step": 920,
"token_acc": 0.8049354198064707
},
{
"epoch": 0.06186492824000931,
"grad_norm": 2.078125,
"learning_rate": 1.9946798836572668e-05,
"loss": 0.8746245384216309,
"step": 930,
"token_acc": 0.7934826283785594
},
{
"epoch": 0.06253014252215995,
"grad_norm": 2.359375,
"learning_rate": 1.9944556382674386e-05,
"loss": 0.8264752388000488,
"step": 940,
"token_acc": 0.8021613162458233
},
{
"epoch": 0.06319535680431058,
"grad_norm": 2.125,
"learning_rate": 1.994226777036997e-05,
"loss": 0.8821484565734863,
"step": 950,
"token_acc": 0.7902393712040015
},
{
"epoch": 0.06386057108646123,
"grad_norm": 1.765625,
"learning_rate": 1.993993301028219e-05,
"loss": 0.8773292541503906,
"step": 960,
"token_acc": 0.7869990048555037
},
{
"epoch": 0.06452578536861187,
"grad_norm": 1.9296875,
"learning_rate": 1.9937552113248013e-05,
"loss": 0.8283615112304688,
"step": 970,
"token_acc": 0.7993306288032455
},
{
"epoch": 0.0651909996507625,
"grad_norm": 2.46875,
"learning_rate": 1.9935125090318547e-05,
"loss": 0.894932746887207,
"step": 980,
"token_acc": 0.7893195225682536
},
{
"epoch": 0.06585621393291315,
"grad_norm": 2.265625,
"learning_rate": 1.9932651952759002e-05,
"loss": 0.8480783462524414,
"step": 990,
"token_acc": 0.7977990610328638
},
{
"epoch": 0.06652142821506378,
"grad_norm": 1.8984375,
"learning_rate": 1.9930132712048637e-05,
"loss": 0.8316510200500489,
"step": 1000,
"token_acc": 0.8002888068189079
},
{
"epoch": 0.06718664249721441,
"grad_norm": 3.046875,
"learning_rate": 1.992756737988069e-05,
"loss": 0.8458746910095215,
"step": 1010,
"token_acc": 0.7962315118235763
},
{
"epoch": 0.06785185677936505,
"grad_norm": 2.46875,
"learning_rate": 1.992495596816235e-05,
"loss": 0.8479302406311036,
"step": 1020,
"token_acc": 0.794713445889201
},
{
"epoch": 0.0685170710615157,
"grad_norm": 2.078125,
"learning_rate": 1.9922298489014674e-05,
"loss": 0.8340811729431152,
"step": 1030,
"token_acc": 0.7964420739940589
},
{
"epoch": 0.06918228534366633,
"grad_norm": 2.046875,
"learning_rate": 1.9919594954772555e-05,
"loss": 0.8054445266723633,
"step": 1040,
"token_acc": 0.8050911345494001
},
{
"epoch": 0.06984749962581696,
"grad_norm": 2.015625,
"learning_rate": 1.9916845377984653e-05,
"loss": 0.8424126625061035,
"step": 1050,
"token_acc": 0.8002311917318176
},
{
"epoch": 0.07051271390796761,
"grad_norm": 2.0625,
"learning_rate": 1.9914049771413332e-05,
"loss": 0.8628503799438476,
"step": 1060,
"token_acc": 0.7932705782626827
},
{
"epoch": 0.07117792819011824,
"grad_norm": 2.21875,
"learning_rate": 1.991120814803461e-05,
"loss": 0.8279478073120117,
"step": 1070,
"token_acc": 0.8023755039773346
},
{
"epoch": 0.07184314247226888,
"grad_norm": 1.9765625,
"learning_rate": 1.9908320521038096e-05,
"loss": 0.8544173240661621,
"step": 1080,
"token_acc": 0.7953938703591642
},
{
"epoch": 0.07250835675441952,
"grad_norm": 2.0625,
"learning_rate": 1.990538690382693e-05,
"loss": 0.8110973358154296,
"step": 1090,
"token_acc": 0.805195309215335
},
{
"epoch": 0.07317357103657016,
"grad_norm": 2.28125,
"learning_rate": 1.990240731001771e-05,
"loss": 0.8267485618591308,
"step": 1100,
"token_acc": 0.8003877764867735
},
{
"epoch": 0.07383878531872079,
"grad_norm": 2.53125,
"learning_rate": 1.9899381753440458e-05,
"loss": 0.8429806709289551,
"step": 1110,
"token_acc": 0.7991725428119154
},
{
"epoch": 0.07450399960087144,
"grad_norm": 1.9609375,
"learning_rate": 1.9896310248138507e-05,
"loss": 0.8594174385070801,
"step": 1120,
"token_acc": 0.7951964878597589
},
{
"epoch": 0.07516921388302207,
"grad_norm": 1.75,
"learning_rate": 1.9893192808368488e-05,
"loss": 0.8257651329040527,
"step": 1130,
"token_acc": 0.8046344386735917
},
{
"epoch": 0.0758344281651727,
"grad_norm": 2.015625,
"learning_rate": 1.9890029448600233e-05,
"loss": 0.8417659759521484,
"step": 1140,
"token_acc": 0.7985600742414944
},
{
"epoch": 0.07649964244732334,
"grad_norm": 1.953125,
"learning_rate": 1.9886820183516707e-05,
"loss": 0.8185996055603028,
"step": 1150,
"token_acc": 0.79997593809759
},
{
"epoch": 0.07716485672947399,
"grad_norm": 2.265625,
"learning_rate": 1.9883565028013966e-05,
"loss": 0.7665432929992676,
"step": 1160,
"token_acc": 0.8132734241850627
},
{
"epoch": 0.07783007101162462,
"grad_norm": 1.8984375,
"learning_rate": 1.988026399720105e-05,
"loss": 0.8537595748901368,
"step": 1170,
"token_acc": 0.7958463445528995
},
{
"epoch": 0.07849528529377525,
"grad_norm": 2.671875,
"learning_rate": 1.9876917106399948e-05,
"loss": 0.8190966606140136,
"step": 1180,
"token_acc": 0.8051628114349624
},
{
"epoch": 0.0791604995759259,
"grad_norm": 2.28125,
"learning_rate": 1.9873524371145498e-05,
"loss": 0.8334413528442383,
"step": 1190,
"token_acc": 0.7986840423313173
},
{
"epoch": 0.07982571385807653,
"grad_norm": 1.921875,
"learning_rate": 1.9870085807185343e-05,
"loss": 0.8066576957702637,
"step": 1200,
"token_acc": 0.8089597417011402
},
{
"epoch": 0.08049092814022717,
"grad_norm": 2.09375,
"learning_rate": 1.986660143047983e-05,
"loss": 0.8288675308227539,
"step": 1210,
"token_acc": 0.8
},
{
"epoch": 0.08115614242237781,
"grad_norm": 1.96875,
"learning_rate": 1.986307125720196e-05,
"loss": 0.8255479812622071,
"step": 1220,
"token_acc": 0.8017545421548955
},
{
"epoch": 0.08182135670452845,
"grad_norm": 1.984375,
"learning_rate": 1.98594953037373e-05,
"loss": 0.819053840637207,
"step": 1230,
"token_acc": 0.8010844359568954
},
{
"epoch": 0.08248657098667908,
"grad_norm": 2.1875,
"learning_rate": 1.9855873586683897e-05,
"loss": 0.8349920272827148,
"step": 1240,
"token_acc": 0.801878595595108
},
{
"epoch": 0.08315178526882973,
"grad_norm": 2.203125,
"learning_rate": 1.985220612285223e-05,
"loss": 0.8476706504821777,
"step": 1250,
"token_acc": 0.7967870552109478
},
{
"epoch": 0.08381699955098036,
"grad_norm": 2.09375,
"learning_rate": 1.9848492929265114e-05,
"loss": 0.8094767570495606,
"step": 1260,
"token_acc": 0.8043880993198032
},
{
"epoch": 0.084482213833131,
"grad_norm": 2.171875,
"learning_rate": 1.9844734023157603e-05,
"loss": 0.8164218902587891,
"step": 1270,
"token_acc": 0.8040357215897471
},
{
"epoch": 0.08514742811528163,
"grad_norm": 2.234375,
"learning_rate": 1.9840929421976948e-05,
"loss": 0.8524214744567871,
"step": 1280,
"token_acc": 0.7953319021487344
},
{
"epoch": 0.08581264239743228,
"grad_norm": 2.25,
"learning_rate": 1.9837079143382498e-05,
"loss": 0.7957529067993164,
"step": 1290,
"token_acc": 0.8052775378045611
},
{
"epoch": 0.08647785667958291,
"grad_norm": 2.15625,
"learning_rate": 1.98331832052456e-05,
"loss": 0.8511330604553222,
"step": 1300,
"token_acc": 0.8005637095342368
},
{
"epoch": 0.08714307096173354,
"grad_norm": 2.296875,
"learning_rate": 1.982924162564955e-05,
"loss": 0.8577371597290039,
"step": 1310,
"token_acc": 0.7960172189000008
},
{
"epoch": 0.08780828524388419,
"grad_norm": 2.078125,
"learning_rate": 1.9825254422889482e-05,
"loss": 0.782780933380127,
"step": 1320,
"token_acc": 0.8116809784577358
},
{
"epoch": 0.08847349952603482,
"grad_norm": 2.015625,
"learning_rate": 1.9821221615472303e-05,
"loss": 0.7945643424987793,
"step": 1330,
"token_acc": 0.8064990639208345
},
{
"epoch": 0.08913871380818546,
"grad_norm": 2.234375,
"learning_rate": 1.9817143222116587e-05,
"loss": 0.7945376873016358,
"step": 1340,
"token_acc": 0.8035951628717726
},
{
"epoch": 0.0898039280903361,
"grad_norm": 2.25,
"learning_rate": 1.9813019261752507e-05,
"loss": 0.8179100036621094,
"step": 1350,
"token_acc": 0.8037745691413591
},
{
"epoch": 0.09046914237248674,
"grad_norm": 2.171875,
"learning_rate": 1.980884975352173e-05,
"loss": 0.7726712703704834,
"step": 1360,
"token_acc": 0.8100709971105048
},
{
"epoch": 0.09113435665463737,
"grad_norm": 2.109375,
"learning_rate": 1.980463471677735e-05,
"loss": 0.7836864471435547,
"step": 1370,
"token_acc": 0.8081100023362147
},
{
"epoch": 0.09179957093678802,
"grad_norm": 2.0,
"learning_rate": 1.980037417108377e-05,
"loss": 0.8499679565429688,
"step": 1380,
"token_acc": 0.7917732119759908
},
{
"epoch": 0.09246478521893865,
"grad_norm": 2.0625,
"learning_rate": 1.9796068136216634e-05,
"loss": 0.8247855186462403,
"step": 1390,
"token_acc": 0.801626375687425
},
{
"epoch": 0.09312999950108929,
"grad_norm": 2.078125,
"learning_rate": 1.9791716632162728e-05,
"loss": 0.8642170906066895,
"step": 1400,
"token_acc": 0.7970766339528085
},
{
"epoch": 0.09379521378323992,
"grad_norm": 2.40625,
"learning_rate": 1.978731967911989e-05,
"loss": 0.8169401168823243,
"step": 1410,
"token_acc": 0.8036579668509828
},
{
"epoch": 0.09446042806539057,
"grad_norm": 1.921875,
"learning_rate": 1.9782877297496898e-05,
"loss": 0.8450931549072266,
"step": 1420,
"token_acc": 0.7975495699108597
},
{
"epoch": 0.0951256423475412,
"grad_norm": 1.9140625,
"learning_rate": 1.9778389507913403e-05,
"loss": 0.8354745864868164,
"step": 1430,
"token_acc": 0.7968114385446734
},
{
"epoch": 0.09579085662969183,
"grad_norm": 2.171875,
"learning_rate": 1.9773856331199823e-05,
"loss": 0.7920023441314697,
"step": 1440,
"token_acc": 0.8089834320259145
},
{
"epoch": 0.09645607091184248,
"grad_norm": 2.078125,
"learning_rate": 1.9769277788397238e-05,
"loss": 0.8014390945434571,
"step": 1450,
"token_acc": 0.8047444315694605
},
{
"epoch": 0.09712128519399311,
"grad_norm": 2.09375,
"learning_rate": 1.9764653900757295e-05,
"loss": 0.8448644638061523,
"step": 1460,
"token_acc": 0.7981137488345407
},
{
"epoch": 0.09778649947614375,
"grad_norm": 1.9140625,
"learning_rate": 1.9759984689742117e-05,
"loss": 0.807799243927002,
"step": 1470,
"token_acc": 0.8051571252731794
},
{
"epoch": 0.0984517137582944,
"grad_norm": 2.09375,
"learning_rate": 1.9755270177024202e-05,
"loss": 0.8102557182312011,
"step": 1480,
"token_acc": 0.8036170578967576
},
{
"epoch": 0.09911692804044503,
"grad_norm": 2.125,
"learning_rate": 1.9750510384486307e-05,
"loss": 0.8074784278869629,
"step": 1490,
"token_acc": 0.8056646545588739
},
{
"epoch": 0.09978214232259566,
"grad_norm": 2.28125,
"learning_rate": 1.9745705334221376e-05,
"loss": 0.848141098022461,
"step": 1500,
"token_acc": 0.7973428204677105
},
{
"epoch": 0.10044735660474631,
"grad_norm": 2.265625,
"learning_rate": 1.9740855048532406e-05,
"loss": 0.8179927825927734,
"step": 1510,
"token_acc": 0.8025347091388655
},
{
"epoch": 0.10111257088689694,
"grad_norm": 1.8515625,
"learning_rate": 1.9735959549932363e-05,
"loss": 0.7876014709472656,
"step": 1520,
"token_acc": 0.8106710708146551
},
{
"epoch": 0.10177778516904758,
"grad_norm": 2.125,
"learning_rate": 1.973101886114407e-05,
"loss": 0.7852612972259522,
"step": 1530,
"token_acc": 0.811614069882751
},
{
"epoch": 0.10244299945119821,
"grad_norm": 2.125,
"learning_rate": 1.972603300510011e-05,
"loss": 0.8401516914367676,
"step": 1540,
"token_acc": 0.7986809208812959
},
{
"epoch": 0.10310821373334886,
"grad_norm": 1.6015625,
"learning_rate": 1.972100200494271e-05,
"loss": 0.8186181068420411,
"step": 1550,
"token_acc": 0.8040994765132696
},
{
"epoch": 0.10377342801549949,
"grad_norm": 2.25,
"learning_rate": 1.971592588402363e-05,
"loss": 0.7895570278167725,
"step": 1560,
"token_acc": 0.8068386002177558
},
{
"epoch": 0.10443864229765012,
"grad_norm": 2.171875,
"learning_rate": 1.9710804665904068e-05,
"loss": 0.7993306159973145,
"step": 1570,
"token_acc": 0.8084423366040366
},
{
"epoch": 0.10510385657980077,
"grad_norm": 2.390625,
"learning_rate": 1.970563837435454e-05,
"loss": 0.8110671997070312,
"step": 1580,
"token_acc": 0.8055522383865914
},
{
"epoch": 0.1057690708619514,
"grad_norm": 2.390625,
"learning_rate": 1.9700427033354784e-05,
"loss": 0.8436463356018067,
"step": 1590,
"token_acc": 0.7976655913289323
},
{
"epoch": 0.10643428514410204,
"grad_norm": 1.7734375,
"learning_rate": 1.9695170667093627e-05,
"loss": 0.8028373718261719,
"step": 1600,
"token_acc": 0.8030467410912032
},
{
"epoch": 0.10709949942625269,
"grad_norm": 1.90625,
"learning_rate": 1.968986929996889e-05,
"loss": 0.8472848892211914,
"step": 1610,
"token_acc": 0.7972256550130528
},
{
"epoch": 0.10776471370840332,
"grad_norm": 1.8828125,
"learning_rate": 1.9684522956587265e-05,
"loss": 0.8356766700744629,
"step": 1620,
"token_acc": 0.8029545793847707
},
{
"epoch": 0.10842992799055395,
"grad_norm": 2.1875,
"learning_rate": 1.967913166176421e-05,
"loss": 0.7962865829467773,
"step": 1630,
"token_acc": 0.8064048102343037
},
{
"epoch": 0.1090951422727046,
"grad_norm": 2.140625,
"learning_rate": 1.9673695440523822e-05,
"loss": 0.774437665939331,
"step": 1640,
"token_acc": 0.8092770331667424
},
{
"epoch": 0.10976035655485523,
"grad_norm": 2.109375,
"learning_rate": 1.9668214318098728e-05,
"loss": 0.831325626373291,
"step": 1650,
"token_acc": 0.7991957761236681
},
{
"epoch": 0.11042557083700587,
"grad_norm": 2.328125,
"learning_rate": 1.9662688319929976e-05,
"loss": 0.8110508918762207,
"step": 1660,
"token_acc": 0.8059353515775872
},
{
"epoch": 0.1110907851191565,
"grad_norm": 2.3125,
"learning_rate": 1.9657117471666897e-05,
"loss": 0.8056949615478516,
"step": 1670,
"token_acc": 0.8045530144071187
},
{
"epoch": 0.11175599940130715,
"grad_norm": 2.234375,
"learning_rate": 1.9651501799167006e-05,
"loss": 0.7650763988494873,
"step": 1680,
"token_acc": 0.8165312454850051
},
{
"epoch": 0.11242121368345778,
"grad_norm": 2.03125,
"learning_rate": 1.964584132849587e-05,
"loss": 0.7955361366271972,
"step": 1690,
"token_acc": 0.8069374277920959
},
{
"epoch": 0.11308642796560842,
"grad_norm": 1.953125,
"learning_rate": 1.9640136085926983e-05,
"loss": 0.8545634269714355,
"step": 1700,
"token_acc": 0.7934587754995224
},
{
"epoch": 0.11375164224775906,
"grad_norm": 2.171875,
"learning_rate": 1.9634386097941665e-05,
"loss": 0.7969943523406983,
"step": 1710,
"token_acc": 0.80630573490797
},
{
"epoch": 0.1144168565299097,
"grad_norm": 2.375,
"learning_rate": 1.9628591391228912e-05,
"loss": 0.8716401100158692,
"step": 1720,
"token_acc": 0.794556000426264
},
{
"epoch": 0.11508207081206033,
"grad_norm": 2.234375,
"learning_rate": 1.962275199268529e-05,
"loss": 0.8226058959960938,
"step": 1730,
"token_acc": 0.8028034316907848
},
{
"epoch": 0.11574728509421098,
"grad_norm": 1.96875,
"learning_rate": 1.961686792941481e-05,
"loss": 0.8571075439453125,
"step": 1740,
"token_acc": 0.7926490755033223
},
{
"epoch": 0.11641249937636161,
"grad_norm": 2.171875,
"learning_rate": 1.9610939228728795e-05,
"loss": 0.7975288391113281,
"step": 1750,
"token_acc": 0.8071410306447923
},
{
"epoch": 0.11707771365851224,
"grad_norm": 1.8828125,
"learning_rate": 1.960496591814575e-05,
"loss": 0.8235790252685546,
"step": 1760,
"token_acc": 0.7998536809597493
},
{
"epoch": 0.11774292794066289,
"grad_norm": 2.21875,
"learning_rate": 1.959894802539125e-05,
"loss": 0.8125411033630371,
"step": 1770,
"token_acc": 0.8049061092369791
},
{
"epoch": 0.11840814222281353,
"grad_norm": 1.8046875,
"learning_rate": 1.9592885578397792e-05,
"loss": 0.7516975402832031,
"step": 1780,
"token_acc": 0.8191770454797523
},
{
"epoch": 0.11907335650496416,
"grad_norm": 2.53125,
"learning_rate": 1.9586778605304686e-05,
"loss": 0.8061980247497559,
"step": 1790,
"token_acc": 0.8080048078799279
},
{
"epoch": 0.11973857078711479,
"grad_norm": 2.171875,
"learning_rate": 1.9580627134457902e-05,
"loss": 0.848361587524414,
"step": 1800,
"token_acc": 0.7966022244634157
},
{
"epoch": 0.12040378506926544,
"grad_norm": 2.453125,
"learning_rate": 1.9574431194409957e-05,
"loss": 0.8258939743041992,
"step": 1810,
"token_acc": 0.8024224929603373
},
{
"epoch": 0.12106899935141607,
"grad_norm": 2.109375,
"learning_rate": 1.9568190813919766e-05,
"loss": 0.7854766845703125,
"step": 1820,
"token_acc": 0.8081827879288394
},
{
"epoch": 0.1217342136335667,
"grad_norm": 2.21875,
"learning_rate": 1.9561906021952532e-05,
"loss": 0.8165424346923829,
"step": 1830,
"token_acc": 0.8009464719146309
},
{
"epoch": 0.12239942791571735,
"grad_norm": 1.71875,
"learning_rate": 1.9555576847679586e-05,
"loss": 0.7650991439819336,
"step": 1840,
"token_acc": 0.8129558643454188
},
{
"epoch": 0.12306464219786799,
"grad_norm": 2.0625,
"learning_rate": 1.954920332047827e-05,
"loss": 0.8019403457641602,
"step": 1850,
"token_acc": 0.8073100758165758
},
{
"epoch": 0.12372985648001862,
"grad_norm": 2.296875,
"learning_rate": 1.9542785469931783e-05,
"loss": 0.8040363311767578,
"step": 1860,
"token_acc": 0.8084670559253059
},
{
"epoch": 0.12439507076216927,
"grad_norm": 2.921875,
"learning_rate": 1.9536323325829066e-05,
"loss": 0.8171208381652832,
"step": 1870,
"token_acc": 0.8018721287692998
},
{
"epoch": 0.1250602850443199,
"grad_norm": 2.109375,
"learning_rate": 1.9529816918164644e-05,
"loss": 0.8484137535095215,
"step": 1880,
"token_acc": 0.8000041179659994
},
{
"epoch": 0.12572549932647054,
"grad_norm": 1.9375,
"learning_rate": 1.95232662771385e-05,
"loss": 0.8055267333984375,
"step": 1890,
"token_acc": 0.8076957574670374
},
{
"epoch": 0.12639071360862117,
"grad_norm": 2.015625,
"learning_rate": 1.951667143315593e-05,
"loss": 0.7828092098236084,
"step": 1900,
"token_acc": 0.8080822681561939
},
{
"epoch": 0.1270559278907718,
"grad_norm": 2.53125,
"learning_rate": 1.9510032416827385e-05,
"loss": 0.7813683032989502,
"step": 1910,
"token_acc": 0.8081794949126176
},
{
"epoch": 0.12772114217292246,
"grad_norm": 2.125,
"learning_rate": 1.950334925896837e-05,
"loss": 0.8153127670288086,
"step": 1920,
"token_acc": 0.8027402225524666
},
{
"epoch": 0.1283863564550731,
"grad_norm": 2.046875,
"learning_rate": 1.9496621990599265e-05,
"loss": 0.7965798854827881,
"step": 1930,
"token_acc": 0.8080318754389765
},
{
"epoch": 0.12905157073722373,
"grad_norm": 2.171875,
"learning_rate": 1.9489850642945184e-05,
"loss": 0.8252116203308105,
"step": 1940,
"token_acc": 0.8032542067870957
},
{
"epoch": 0.12971678501937436,
"grad_norm": 2.265625,
"learning_rate": 1.9483035247435853e-05,
"loss": 0.8026675224304199,
"step": 1950,
"token_acc": 0.8078038629121415
},
{
"epoch": 0.130381999301525,
"grad_norm": 2.65625,
"learning_rate": 1.947617583570544e-05,
"loss": 0.8441123008728028,
"step": 1960,
"token_acc": 0.7952795779129685
},
{
"epoch": 0.13104721358367563,
"grad_norm": 2.140625,
"learning_rate": 1.946927243959242e-05,
"loss": 0.7658082962036132,
"step": 1970,
"token_acc": 0.8148987580026442
},
{
"epoch": 0.1317124278658263,
"grad_norm": 1.9140625,
"learning_rate": 1.946232509113943e-05,
"loss": 0.8077128410339356,
"step": 1980,
"token_acc": 0.8047300183248598
},
{
"epoch": 0.13237764214797693,
"grad_norm": 2.09375,
"learning_rate": 1.9455333822593103e-05,
"loss": 0.8423896789550781,
"step": 1990,
"token_acc": 0.7981230840418764
},
{
"epoch": 0.13304285643012756,
"grad_norm": 1.8671875,
"learning_rate": 1.9448298666403936e-05,
"loss": 0.7843271732330322,
"step": 2000,
"token_acc": 0.8069620921474077
},
{
"epoch": 0.1337080707122782,
"grad_norm": 2.09375,
"learning_rate": 1.9441219655226146e-05,
"loss": 0.8419926643371582,
"step": 2010,
"token_acc": 0.7968043168094558
},
{
"epoch": 0.13437328499442883,
"grad_norm": 2.234375,
"learning_rate": 1.943409682191749e-05,
"loss": 0.8484352111816407,
"step": 2020,
"token_acc": 0.7962351668990638
},
{
"epoch": 0.13503849927657946,
"grad_norm": 2.15625,
"learning_rate": 1.942693019953913e-05,
"loss": 0.7635398387908936,
"step": 2030,
"token_acc": 0.8135594371400631
},
{
"epoch": 0.1357037135587301,
"grad_norm": 2.078125,
"learning_rate": 1.941971982135549e-05,
"loss": 0.8179874420166016,
"step": 2040,
"token_acc": 0.803985859240069
},
{
"epoch": 0.13636892784088075,
"grad_norm": 2.0,
"learning_rate": 1.9412465720834076e-05,
"loss": 0.8109594345092773,
"step": 2050,
"token_acc": 0.8048407883114438
},
{
"epoch": 0.1370341421230314,
"grad_norm": 2.28125,
"learning_rate": 1.9405167931645347e-05,
"loss": 0.8032848358154296,
"step": 2060,
"token_acc": 0.8027130279920146
},
{
"epoch": 0.13769935640518202,
"grad_norm": 2.421875,
"learning_rate": 1.9397826487662533e-05,
"loss": 0.8114719390869141,
"step": 2070,
"token_acc": 0.7992189932186413
},
{
"epoch": 0.13836457068733266,
"grad_norm": 2.390625,
"learning_rate": 1.9390441422961506e-05,
"loss": 0.809328556060791,
"step": 2080,
"token_acc": 0.8043400038750035
},
{
"epoch": 0.1390297849694833,
"grad_norm": 2.109375,
"learning_rate": 1.9383012771820596e-05,
"loss": 0.7741396427154541,
"step": 2090,
"token_acc": 0.8151622567631703
},
{
"epoch": 0.13969499925163392,
"grad_norm": 2.484375,
"learning_rate": 1.9375540568720446e-05,
"loss": 0.838450813293457,
"step": 2100,
"token_acc": 0.8012097118919381
},
{
"epoch": 0.14036021353378458,
"grad_norm": 2.0625,
"learning_rate": 1.9368024848343846e-05,
"loss": 0.8129657745361328,
"step": 2110,
"token_acc": 0.8065105403529282
},
{
"epoch": 0.14102542781593522,
"grad_norm": 2.15625,
"learning_rate": 1.9360465645575576e-05,
"loss": 0.8476659774780273,
"step": 2120,
"token_acc": 0.7989302262196784
},
{
"epoch": 0.14169064209808585,
"grad_norm": 1.9765625,
"learning_rate": 1.935286299550225e-05,
"loss": 0.79197096824646,
"step": 2130,
"token_acc": 0.806053341324543
},
{
"epoch": 0.14235585638023648,
"grad_norm": 2.28125,
"learning_rate": 1.9345216933412137e-05,
"loss": 0.7976673603057861,
"step": 2140,
"token_acc": 0.8061879282089759
},
{
"epoch": 0.14302107066238712,
"grad_norm": 2.078125,
"learning_rate": 1.9337527494795007e-05,
"loss": 0.8158488273620605,
"step": 2150,
"token_acc": 0.8016826321173837
},
{
"epoch": 0.14368628494453775,
"grad_norm": 2.078125,
"learning_rate": 1.9329794715341973e-05,
"loss": 0.8265849113464355,
"step": 2160,
"token_acc": 0.7981114630856208
},
{
"epoch": 0.14435149922668838,
"grad_norm": 1.8828125,
"learning_rate": 1.9322018630945303e-05,
"loss": 0.7581172466278077,
"step": 2170,
"token_acc": 0.8130266186503355
},
{
"epoch": 0.14501671350883905,
"grad_norm": 2.3125,
"learning_rate": 1.9314199277698288e-05,
"loss": 0.7884756565093994,
"step": 2180,
"token_acc": 0.8089428173689565
},
{
"epoch": 0.14568192779098968,
"grad_norm": 1.859375,
"learning_rate": 1.9306336691895035e-05,
"loss": 0.8101030349731445,
"step": 2190,
"token_acc": 0.807570256439578
},
{
"epoch": 0.1463471420731403,
"grad_norm": 2.15625,
"learning_rate": 1.929843091003033e-05,
"loss": 0.8203252792358399,
"step": 2200,
"token_acc": 0.8024444592503757
},
{
"epoch": 0.14701235635529095,
"grad_norm": 2.1875,
"learning_rate": 1.9290481968799462e-05,
"loss": 0.7899667739868164,
"step": 2210,
"token_acc": 0.8102472466347759
},
{
"epoch": 0.14767757063744158,
"grad_norm": 2.21875,
"learning_rate": 1.928248990509803e-05,
"loss": 0.7989044666290284,
"step": 2220,
"token_acc": 0.8069099273826169
},
{
"epoch": 0.1483427849195922,
"grad_norm": 2.125,
"learning_rate": 1.9274454756021795e-05,
"loss": 0.8415334701538086,
"step": 2230,
"token_acc": 0.7967290808277808
},
{
"epoch": 0.14900799920174287,
"grad_norm": 2.078125,
"learning_rate": 1.9266376558866518e-05,
"loss": 0.811655330657959,
"step": 2240,
"token_acc": 0.8017559367543748
},
{
"epoch": 0.1496732134838935,
"grad_norm": 2.140625,
"learning_rate": 1.925825535112775e-05,
"loss": 0.7772735595703125,
"step": 2250,
"token_acc": 0.809683578832515
},
{
"epoch": 0.15033842776604414,
"grad_norm": 2.453125,
"learning_rate": 1.925009117050069e-05,
"loss": 0.8000727653503418,
"step": 2260,
"token_acc": 0.8055789863115057
},
{
"epoch": 0.15100364204819477,
"grad_norm": 2.1875,
"learning_rate": 1.9241884054879992e-05,
"loss": 0.7723996639251709,
"step": 2270,
"token_acc": 0.811688131067286
},
{
"epoch": 0.1516688563303454,
"grad_norm": 2.328125,
"learning_rate": 1.923363404235961e-05,
"loss": 0.7946413516998291,
"step": 2280,
"token_acc": 0.8057864584795978
},
{
"epoch": 0.15233407061249604,
"grad_norm": 2.453125,
"learning_rate": 1.9225341171232585e-05,
"loss": 0.8027899742126465,
"step": 2290,
"token_acc": 0.8040313472238583
},
{
"epoch": 0.15299928489464668,
"grad_norm": 2.1875,
"learning_rate": 1.921700547999091e-05,
"loss": 0.8065752983093262,
"step": 2300,
"token_acc": 0.8054443125180281
},
{
"epoch": 0.15366449917679734,
"grad_norm": 1.9296875,
"learning_rate": 1.9208627007325322e-05,
"loss": 0.7878462791442871,
"step": 2310,
"token_acc": 0.8112825997430744
},
{
"epoch": 0.15432971345894797,
"grad_norm": 2.203125,
"learning_rate": 1.9200205792125127e-05,
"loss": 0.8106060981750488,
"step": 2320,
"token_acc": 0.8014337887190586
},
{
"epoch": 0.1549949277410986,
"grad_norm": 2.015625,
"learning_rate": 1.9191741873478034e-05,
"loss": 0.804102897644043,
"step": 2330,
"token_acc": 0.8034365978236732
},
{
"epoch": 0.15566014202324924,
"grad_norm": 2.578125,
"learning_rate": 1.9183235290669956e-05,
"loss": 0.8324645042419434,
"step": 2340,
"token_acc": 0.7973761731862712
},
{
"epoch": 0.15632535630539987,
"grad_norm": 2.109375,
"learning_rate": 1.9174686083184835e-05,
"loss": 0.875648307800293,
"step": 2350,
"token_acc": 0.7907337696996938
},
{
"epoch": 0.1569905705875505,
"grad_norm": 1.8125,
"learning_rate": 1.916609429070446e-05,
"loss": 0.7985317230224609,
"step": 2360,
"token_acc": 0.8065679463978777
},
{
"epoch": 0.15765578486970117,
"grad_norm": 3.171875,
"learning_rate": 1.9157459953108288e-05,
"loss": 0.775685453414917,
"step": 2370,
"token_acc": 0.8132343265344487
},
{
"epoch": 0.1583209991518518,
"grad_norm": 2.171875,
"learning_rate": 1.9148783110473238e-05,
"loss": 0.8247651100158692,
"step": 2380,
"token_acc": 0.7999805019985452
},
{
"epoch": 0.15898621343400243,
"grad_norm": 1.9296875,
"learning_rate": 1.9140063803073535e-05,
"loss": 0.7709686279296875,
"step": 2390,
"token_acc": 0.8115176587642979
},
{
"epoch": 0.15965142771615307,
"grad_norm": 2.375,
"learning_rate": 1.9131302071380493e-05,
"loss": 0.7848646163940429,
"step": 2400,
"token_acc": 0.80793707733801
},
{
"epoch": 0.1603166419983037,
"grad_norm": 2.171875,
"learning_rate": 1.9122497956062348e-05,
"loss": 0.8096919059753418,
"step": 2410,
"token_acc": 0.8036021268940151
},
{
"epoch": 0.16098185628045433,
"grad_norm": 2.125,
"learning_rate": 1.9113651497984072e-05,
"loss": 0.835840892791748,
"step": 2420,
"token_acc": 0.8007810616653006
},
{
"epoch": 0.16164707056260497,
"grad_norm": 2.09375,
"learning_rate": 1.9104762738207157e-05,
"loss": 0.7337335109710693,
"step": 2430,
"token_acc": 0.8202393617021276
},
{
"epoch": 0.16231228484475563,
"grad_norm": 1.953125,
"learning_rate": 1.909583171798945e-05,
"loss": 0.8023372650146484,
"step": 2440,
"token_acc": 0.8073231707317073
},
{
"epoch": 0.16297749912690626,
"grad_norm": 2.84375,
"learning_rate": 1.9086858478784957e-05,
"loss": 0.8320133209228515,
"step": 2450,
"token_acc": 0.8007640359411664
},
{
"epoch": 0.1636427134090569,
"grad_norm": 2.3125,
"learning_rate": 1.9077843062243643e-05,
"loss": 0.8615562438964843,
"step": 2460,
"token_acc": 0.7924460100684815
},
{
"epoch": 0.16430792769120753,
"grad_norm": 2.0625,
"learning_rate": 1.9068785510211236e-05,
"loss": 0.7892309188842773,
"step": 2470,
"token_acc": 0.81098724151187
},
{
"epoch": 0.16497314197335816,
"grad_norm": 2.0625,
"learning_rate": 1.905968586472905e-05,
"loss": 0.7737140655517578,
"step": 2480,
"token_acc": 0.8086993578770215
},
{
"epoch": 0.1656383562555088,
"grad_norm": 2.421875,
"learning_rate": 1.905054416803377e-05,
"loss": 0.7670929431915283,
"step": 2490,
"token_acc": 0.813709562491093
},
{
"epoch": 0.16630357053765946,
"grad_norm": 2.171875,
"learning_rate": 1.9041360462557273e-05,
"loss": 0.812620735168457,
"step": 2500,
"token_acc": 0.8054372663066057
},
{
"epoch": 0.1669687848198101,
"grad_norm": 2.5625,
"learning_rate": 1.9032134790926413e-05,
"loss": 0.7855628967285156,
"step": 2510,
"token_acc": 0.8151150511865543
},
{
"epoch": 0.16763399910196072,
"grad_norm": 2.125,
"learning_rate": 1.9022867195962845e-05,
"loss": 0.7644612789154053,
"step": 2520,
"token_acc": 0.8143507147701607
},
{
"epoch": 0.16829921338411136,
"grad_norm": 1.8671875,
"learning_rate": 1.9013557720682804e-05,
"loss": 0.773519229888916,
"step": 2530,
"token_acc": 0.8161502978928601
},
{
"epoch": 0.168964427666262,
"grad_norm": 1.859375,
"learning_rate": 1.9004206408296914e-05,
"loss": 0.8248126029968261,
"step": 2540,
"token_acc": 0.8028959039916514
},
{
"epoch": 0.16962964194841262,
"grad_norm": 1.9609375,
"learning_rate": 1.8994813302210004e-05,
"loss": 0.7783886909484863,
"step": 2550,
"token_acc": 0.8098294218063826
},
{
"epoch": 0.17029485623056326,
"grad_norm": 2.171875,
"learning_rate": 1.8985378446020878e-05,
"loss": 0.806661319732666,
"step": 2560,
"token_acc": 0.8059421513242859
},
{
"epoch": 0.17096007051271392,
"grad_norm": 2.046875,
"learning_rate": 1.897590188352213e-05,
"loss": 0.7482129096984863,
"step": 2570,
"token_acc": 0.8153992196492906
},
{
"epoch": 0.17162528479486455,
"grad_norm": 2.46875,
"learning_rate": 1.8966383658699937e-05,
"loss": 0.8097509384155274,
"step": 2580,
"token_acc": 0.8038566113337149
},
{
"epoch": 0.17229049907701519,
"grad_norm": 2.125,
"learning_rate": 1.8956823815733858e-05,
"loss": 0.8065197944641114,
"step": 2590,
"token_acc": 0.8038830715532286
},
{
"epoch": 0.17295571335916582,
"grad_norm": 2.5625,
"learning_rate": 1.894722239899662e-05,
"loss": 0.8259807586669922,
"step": 2600,
"token_acc": 0.7990571596935769
},
{
"epoch": 0.17362092764131645,
"grad_norm": 1.890625,
"learning_rate": 1.893757945305392e-05,
"loss": 0.833931827545166,
"step": 2610,
"token_acc": 0.8015678206121533
},
{
"epoch": 0.17428614192346709,
"grad_norm": 1.96875,
"learning_rate": 1.892789502266422e-05,
"loss": 0.8023898124694824,
"step": 2620,
"token_acc": 0.8068236800910773
},
{
"epoch": 0.17495135620561775,
"grad_norm": 2.234375,
"learning_rate": 1.891816915277853e-05,
"loss": 0.7992527961730957,
"step": 2630,
"token_acc": 0.8043180003139867
},
{
"epoch": 0.17561657048776838,
"grad_norm": 2.453125,
"learning_rate": 1.8908401888540204e-05,
"loss": 0.7782867431640625,
"step": 2640,
"token_acc": 0.8091594152200213
},
{
"epoch": 0.17628178476991901,
"grad_norm": 1.828125,
"learning_rate": 1.889859327528474e-05,
"loss": 0.8014581680297852,
"step": 2650,
"token_acc": 0.8070504712554571
},
{
"epoch": 0.17694699905206965,
"grad_norm": 2.34375,
"learning_rate": 1.8888743358539545e-05,
"loss": 0.8105681419372559,
"step": 2660,
"token_acc": 0.8034869844349286
},
{
"epoch": 0.17761221333422028,
"grad_norm": 2.171875,
"learning_rate": 1.8878852184023754e-05,
"loss": 0.8274518013000488,
"step": 2670,
"token_acc": 0.8037657567006898
},
{
"epoch": 0.17827742761637091,
"grad_norm": 2.265625,
"learning_rate": 1.8868919797647996e-05,
"loss": 0.8177736282348633,
"step": 2680,
"token_acc": 0.8061188292273277
},
{
"epoch": 0.17894264189852155,
"grad_norm": 2.125,
"learning_rate": 1.885894624551419e-05,
"loss": 0.734040641784668,
"step": 2690,
"token_acc": 0.816507944982415
},
{
"epoch": 0.1796078561806722,
"grad_norm": 2.46875,
"learning_rate": 1.8848931573915322e-05,
"loss": 0.818148136138916,
"step": 2700,
"token_acc": 0.8061761058836792
},
{
"epoch": 0.18027307046282284,
"grad_norm": 1.875,
"learning_rate": 1.8838875829335253e-05,
"loss": 0.7727782249450683,
"step": 2710,
"token_acc": 0.8115920976176642
},
{
"epoch": 0.18093828474497348,
"grad_norm": 1.7265625,
"learning_rate": 1.8828779058448473e-05,
"loss": 0.7757514476776123,
"step": 2720,
"token_acc": 0.8101909959072305
},
{
"epoch": 0.1816034990271241,
"grad_norm": 1.9765625,
"learning_rate": 1.8818641308119902e-05,
"loss": 0.8236318588256836,
"step": 2730,
"token_acc": 0.8017989679526067
},
{
"epoch": 0.18226871330927474,
"grad_norm": 2.234375,
"learning_rate": 1.880846262540467e-05,
"loss": 0.8090157508850098,
"step": 2740,
"token_acc": 0.8051376146788991
},
{
"epoch": 0.18293392759142538,
"grad_norm": 2.46875,
"learning_rate": 1.87982430575479e-05,
"loss": 0.749823522567749,
"step": 2750,
"token_acc": 0.8154171173852754
},
{
"epoch": 0.18359914187357604,
"grad_norm": 2.0625,
"learning_rate": 1.8787982651984483e-05,
"loss": 0.8127921104431153,
"step": 2760,
"token_acc": 0.80385509245071
},
{
"epoch": 0.18426435615572667,
"grad_norm": 2.265625,
"learning_rate": 1.8777681456338864e-05,
"loss": 0.7437403678894043,
"step": 2770,
"token_acc": 0.817393841489884
},
{
"epoch": 0.1849295704378773,
"grad_norm": 2.328125,
"learning_rate": 1.8767339518424817e-05,
"loss": 0.7891062259674072,
"step": 2780,
"token_acc": 0.8092848967560873
},
{
"epoch": 0.18559478472002794,
"grad_norm": 2.03125,
"learning_rate": 1.8756956886245223e-05,
"loss": 0.7623389720916748,
"step": 2790,
"token_acc": 0.8133009695681992
},
{
"epoch": 0.18625999900217857,
"grad_norm": 2.359375,
"learning_rate": 1.874653360799185e-05,
"loss": 0.762004804611206,
"step": 2800,
"token_acc": 0.8137980856059238
},
{
"epoch": 0.1869252132843292,
"grad_norm": 2.34375,
"learning_rate": 1.8736069732045135e-05,
"loss": 0.8272488594055176,
"step": 2810,
"token_acc": 0.8052929089060981
},
{
"epoch": 0.18759042756647984,
"grad_norm": 2.640625,
"learning_rate": 1.8725565306973935e-05,
"loss": 0.7898888111114502,
"step": 2820,
"token_acc": 0.8082411026243775
},
{
"epoch": 0.1882556418486305,
"grad_norm": 2.0625,
"learning_rate": 1.8715020381535333e-05,
"loss": 0.7798984050750732,
"step": 2830,
"token_acc": 0.809485695667264
},
{
"epoch": 0.18892085613078113,
"grad_norm": 2.265625,
"learning_rate": 1.870443500467439e-05,
"loss": 0.7661069393157959,
"step": 2840,
"token_acc": 0.8130625832223701
},
{
"epoch": 0.18958607041293177,
"grad_norm": 1.9921875,
"learning_rate": 1.8693809225523933e-05,
"loss": 0.7988604068756103,
"step": 2850,
"token_acc": 0.8079311261800293
},
{
"epoch": 0.1902512846950824,
"grad_norm": 2.375,
"learning_rate": 1.8683143093404314e-05,
"loss": 0.7994510173797608,
"step": 2860,
"token_acc": 0.8060318243493277
},
{
"epoch": 0.19091649897723303,
"grad_norm": 2.34375,
"learning_rate": 1.8672436657823184e-05,
"loss": 0.8280925750732422,
"step": 2870,
"token_acc": 0.8011194973095952
},
{
"epoch": 0.19158171325938367,
"grad_norm": 2.46875,
"learning_rate": 1.8661689968475274e-05,
"loss": 0.7538088798522949,
"step": 2880,
"token_acc": 0.8160597224190265
},
{
"epoch": 0.19224692754153433,
"grad_norm": 2.3125,
"learning_rate": 1.8650903075242143e-05,
"loss": 0.7606218338012696,
"step": 2890,
"token_acc": 0.8121323529411765
},
{
"epoch": 0.19291214182368496,
"grad_norm": 2.078125,
"learning_rate": 1.8640076028191976e-05,
"loss": 0.767609977722168,
"step": 2900,
"token_acc": 0.8157092962770306
},
{
"epoch": 0.1935773561058356,
"grad_norm": 1.96875,
"learning_rate": 1.862920887757932e-05,
"loss": 0.7846102714538574,
"step": 2910,
"token_acc": 0.8117420468884904
},
{
"epoch": 0.19424257038798623,
"grad_norm": 2.1875,
"learning_rate": 1.861830167384487e-05,
"loss": 0.7808233737945557,
"step": 2920,
"token_acc": 0.8104998253356052
},
{
"epoch": 0.19490778467013686,
"grad_norm": 2.03125,
"learning_rate": 1.860735446761524e-05,
"loss": 0.7852920532226563,
"step": 2930,
"token_acc": 0.808852383594268
},
{
"epoch": 0.1955729989522875,
"grad_norm": 1.890625,
"learning_rate": 1.8596367309702703e-05,
"loss": 0.7990771293640136,
"step": 2940,
"token_acc": 0.8052453389915061
},
{
"epoch": 0.19623821323443813,
"grad_norm": 2.3125,
"learning_rate": 1.8585340251104983e-05,
"loss": 0.7932301521301269,
"step": 2950,
"token_acc": 0.8096279459951674
},
{
"epoch": 0.1969034275165888,
"grad_norm": 2.9375,
"learning_rate": 1.8574273343004998e-05,
"loss": 0.7561912536621094,
"step": 2960,
"token_acc": 0.8140277440461734
},
{
"epoch": 0.19756864179873942,
"grad_norm": 2.296875,
"learning_rate": 1.8563166636770637e-05,
"loss": 0.7565604686737061,
"step": 2970,
"token_acc": 0.8153963773229829
},
{
"epoch": 0.19823385608089006,
"grad_norm": 2.359375,
"learning_rate": 1.8552020183954512e-05,
"loss": 0.8498549461364746,
"step": 2980,
"token_acc": 0.7987184191571194
},
{
"epoch": 0.1988990703630407,
"grad_norm": 3.109375,
"learning_rate": 1.854083403629372e-05,
"loss": 0.7454395294189453,
"step": 2990,
"token_acc": 0.8169002486783814
},
{
"epoch": 0.19956428464519133,
"grad_norm": 2.25,
"learning_rate": 1.8529608245709606e-05,
"loss": 0.7931854248046875,
"step": 3000,
"token_acc": 0.8087008921150329
},
{
"epoch": 0.20022949892734196,
"grad_norm": 2.484375,
"learning_rate": 1.8518342864307524e-05,
"loss": 0.7879324436187745,
"step": 3010,
"token_acc": 0.8077937428434233
},
{
"epoch": 0.20089471320949262,
"grad_norm": 2.296875,
"learning_rate": 1.8507037944376588e-05,
"loss": 0.7776303291320801,
"step": 3020,
"token_acc": 0.8116748344736697
},
{
"epoch": 0.20155992749164325,
"grad_norm": 2.125,
"learning_rate": 1.849569353838943e-05,
"loss": 0.7909939765930176,
"step": 3030,
"token_acc": 0.8066300945713997
},
{
"epoch": 0.2022251417737939,
"grad_norm": 2.15625,
"learning_rate": 1.848430969900197e-05,
"loss": 0.7959461688995362,
"step": 3040,
"token_acc": 0.8050304674643064
},
{
"epoch": 0.20289035605594452,
"grad_norm": 2.203125,
"learning_rate": 1.8472886479053147e-05,
"loss": 0.8168770790100097,
"step": 3050,
"token_acc": 0.805860330386544
},
{
"epoch": 0.20355557033809515,
"grad_norm": 2.25,
"learning_rate": 1.84614239315647e-05,
"loss": 0.8059884071350097,
"step": 3060,
"token_acc": 0.8087095386365459
},
{
"epoch": 0.2042207846202458,
"grad_norm": 2.046875,
"learning_rate": 1.8449922109740902e-05,
"loss": 0.8091599464416503,
"step": 3070,
"token_acc": 0.8053880091221041
},
{
"epoch": 0.20488599890239642,
"grad_norm": 2.234375,
"learning_rate": 1.843838106696833e-05,
"loss": 0.8371237754821778,
"step": 3080,
"token_acc": 0.7995299214883932
},
{
"epoch": 0.20555121318454708,
"grad_norm": 2.046875,
"learning_rate": 1.8426800856815593e-05,
"loss": 0.8258884429931641,
"step": 3090,
"token_acc": 0.8028408434136358
},
{
"epoch": 0.20621642746669772,
"grad_norm": 2.125,
"learning_rate": 1.841518153303311e-05,
"loss": 0.7747116565704346,
"step": 3100,
"token_acc": 0.8109330124970892
},
{
"epoch": 0.20688164174884835,
"grad_norm": 2.6875,
"learning_rate": 1.8403523149552856e-05,
"loss": 0.7323533058166504,
"step": 3110,
"token_acc": 0.8201642520270579
},
{
"epoch": 0.20754685603099898,
"grad_norm": 1.8125,
"learning_rate": 1.839182576048808e-05,
"loss": 0.7797468185424805,
"step": 3120,
"token_acc": 0.8122121232829905
},
{
"epoch": 0.20821207031314962,
"grad_norm": 2.234375,
"learning_rate": 1.83800894201331e-05,
"loss": 0.7735537052154541,
"step": 3130,
"token_acc": 0.8082956984514967
},
{
"epoch": 0.20887728459530025,
"grad_norm": 2.046875,
"learning_rate": 1.836831418296302e-05,
"loss": 0.7757162570953369,
"step": 3140,
"token_acc": 0.8098400811841691
},
{
"epoch": 0.2095424988774509,
"grad_norm": 2.03125,
"learning_rate": 1.8356500103633488e-05,
"loss": 0.7793453216552735,
"step": 3150,
"token_acc": 0.8098837947100307
},
{
"epoch": 0.21020771315960154,
"grad_norm": 2.28125,
"learning_rate": 1.834464723698044e-05,
"loss": 0.7601890563964844,
"step": 3160,
"token_acc": 0.8152475040510166
},
{
"epoch": 0.21087292744175218,
"grad_norm": 2.515625,
"learning_rate": 1.8332755638019858e-05,
"loss": 0.7647199630737305,
"step": 3170,
"token_acc": 0.8139656416069246
},
{
"epoch": 0.2115381417239028,
"grad_norm": 1.8203125,
"learning_rate": 1.832082536194748e-05,
"loss": 0.7917447566986084,
"step": 3180,
"token_acc": 0.8084312871861848
},
{
"epoch": 0.21220335600605345,
"grad_norm": 2.046875,
"learning_rate": 1.8308856464138588e-05,
"loss": 0.7848927497863769,
"step": 3190,
"token_acc": 0.8077341100773846
},
{
"epoch": 0.21286857028820408,
"grad_norm": 2.0625,
"learning_rate": 1.8296849000147714e-05,
"loss": 0.7667469501495361,
"step": 3200,
"token_acc": 0.8130416334045323
},
{
"epoch": 0.2135337845703547,
"grad_norm": 2.21875,
"learning_rate": 1.828480302570841e-05,
"loss": 0.7721033096313477,
"step": 3210,
"token_acc": 0.8108323347499572
},
{
"epoch": 0.21419899885250537,
"grad_norm": 2.8125,
"learning_rate": 1.827271859673297e-05,
"loss": 0.760159683227539,
"step": 3220,
"token_acc": 0.8129236024507943
},
{
"epoch": 0.214864213134656,
"grad_norm": 2.390625,
"learning_rate": 1.826059576931218e-05,
"loss": 0.7689784526824951,
"step": 3230,
"token_acc": 0.8150187362183953
},
{
"epoch": 0.21552942741680664,
"grad_norm": 2.328125,
"learning_rate": 1.824843459971506e-05,
"loss": 0.8144923210144043,
"step": 3240,
"token_acc": 0.8031795633530451
},
{
"epoch": 0.21619464169895727,
"grad_norm": 3.53125,
"learning_rate": 1.8236235144388583e-05,
"loss": 0.796943187713623,
"step": 3250,
"token_acc": 0.8018266057798074
},
{
"epoch": 0.2168598559811079,
"grad_norm": 2.5625,
"learning_rate": 1.8223997459957443e-05,
"loss": 0.7617924690246582,
"step": 3260,
"token_acc": 0.814580680709749
},
{
"epoch": 0.21752507026325854,
"grad_norm": 2.28125,
"learning_rate": 1.8211721603223774e-05,
"loss": 0.7788496494293213,
"step": 3270,
"token_acc": 0.8116737597401262
},
{
"epoch": 0.2181902845454092,
"grad_norm": 2.1875,
"learning_rate": 1.819940763116689e-05,
"loss": 0.8145605087280273,
"step": 3280,
"token_acc": 0.8055434812138336
},
{
"epoch": 0.21885549882755984,
"grad_norm": 2.421875,
"learning_rate": 1.818705560094301e-05,
"loss": 0.8086992263793945,
"step": 3290,
"token_acc": 0.805947115318369
},
{
"epoch": 0.21952071310971047,
"grad_norm": 2.109375,
"learning_rate": 1.817466556988502e-05,
"loss": 0.7621450424194336,
"step": 3300,
"token_acc": 0.8134629547797908
},
{
"epoch": 0.2201859273918611,
"grad_norm": 1.8515625,
"learning_rate": 1.816223759550217e-05,
"loss": 0.8148023605346679,
"step": 3310,
"token_acc": 0.8055541702585439
},
{
"epoch": 0.22085114167401174,
"grad_norm": 2.703125,
"learning_rate": 1.8149771735479847e-05,
"loss": 0.7908721923828125,
"step": 3320,
"token_acc": 0.8103130755064457
},
{
"epoch": 0.22151635595616237,
"grad_norm": 2.21875,
"learning_rate": 1.8137268047679274e-05,
"loss": 0.7743474960327148,
"step": 3330,
"token_acc": 0.8109734973150875
},
{
"epoch": 0.222181570238313,
"grad_norm": 2.125,
"learning_rate": 1.812472659013726e-05,
"loss": 0.7622000217437744,
"step": 3340,
"token_acc": 0.8149303105486384
},
{
"epoch": 0.22284678452046366,
"grad_norm": 2.515625,
"learning_rate": 1.8112147421065923e-05,
"loss": 0.7876116275787354,
"step": 3350,
"token_acc": 0.8091663402300487
},
{
"epoch": 0.2235119988026143,
"grad_norm": 2.296875,
"learning_rate": 1.809953059885242e-05,
"loss": 0.7649473190307617,
"step": 3360,
"token_acc": 0.8109314333746948
},
{
"epoch": 0.22417721308476493,
"grad_norm": 2.265625,
"learning_rate": 1.808687618205868e-05,
"loss": 0.7231990337371826,
"step": 3370,
"token_acc": 0.8238119845989242
},
{
"epoch": 0.22484242736691556,
"grad_norm": 2.109375,
"learning_rate": 1.8074184229421127e-05,
"loss": 0.8160101890563964,
"step": 3380,
"token_acc": 0.8041415389086681
},
{
"epoch": 0.2255076416490662,
"grad_norm": 2.5625,
"learning_rate": 1.806145479985042e-05,
"loss": 0.7418264389038086,
"step": 3390,
"token_acc": 0.81832327219813
},
{
"epoch": 0.22617285593121683,
"grad_norm": 2.21875,
"learning_rate": 1.8048687952431158e-05,
"loss": 0.7653279781341553,
"step": 3400,
"token_acc": 0.8161176278106972
},
{
"epoch": 0.2268380702133675,
"grad_norm": 2.15625,
"learning_rate": 1.8035883746421626e-05,
"loss": 0.7776473045349122,
"step": 3410,
"token_acc": 0.8104045850713874
},
{
"epoch": 0.22750328449551813,
"grad_norm": 2.296875,
"learning_rate": 1.802304224125351e-05,
"loss": 0.7973399639129639,
"step": 3420,
"token_acc": 0.808518847177746
},
{
"epoch": 0.22816849877766876,
"grad_norm": 1.9453125,
"learning_rate": 1.8010163496531623e-05,
"loss": 0.81991548538208,
"step": 3430,
"token_acc": 0.8046815516669161
},
{
"epoch": 0.2288337130598194,
"grad_norm": 2.328125,
"learning_rate": 1.7997247572033617e-05,
"loss": 0.7869620800018311,
"step": 3440,
"token_acc": 0.8107487625934637
},
{
"epoch": 0.22949892734197003,
"grad_norm": 2.03125,
"learning_rate": 1.798429452770974e-05,
"loss": 0.7722719192504883,
"step": 3450,
"token_acc": 0.8113003457125284
},
{
"epoch": 0.23016414162412066,
"grad_norm": 2.09375,
"learning_rate": 1.7971304423682512e-05,
"loss": 0.7793629169464111,
"step": 3460,
"token_acc": 0.8130648394029073
},
{
"epoch": 0.2308293559062713,
"grad_norm": 2.109375,
"learning_rate": 1.795827732024648e-05,
"loss": 0.8005661010742188,
"step": 3470,
"token_acc": 0.8045256446037914
},
{
"epoch": 0.23149457018842196,
"grad_norm": 2.21875,
"learning_rate": 1.7945213277867923e-05,
"loss": 0.7839313983917237,
"step": 3480,
"token_acc": 0.8125887055821039
},
{
"epoch": 0.2321597844705726,
"grad_norm": 2.0625,
"learning_rate": 1.793211235718458e-05,
"loss": 0.7761583805084229,
"step": 3490,
"token_acc": 0.8092856252010266
},
{
"epoch": 0.23282499875272322,
"grad_norm": 2.359375,
"learning_rate": 1.7918974619005353e-05,
"loss": 0.8088750839233398,
"step": 3500,
"token_acc": 0.8046893884457337
},
{
"epoch": 0.23349021303487386,
"grad_norm": 2.171875,
"learning_rate": 1.7905800124310048e-05,
"loss": 0.7618515014648437,
"step": 3510,
"token_acc": 0.816849095360027
},
{
"epoch": 0.2341554273170245,
"grad_norm": 2.3125,
"learning_rate": 1.789258893424907e-05,
"loss": 0.8020499229431153,
"step": 3520,
"token_acc": 0.8110408992565443
},
{
"epoch": 0.23482064159917512,
"grad_norm": 2.34375,
"learning_rate": 1.7879341110143146e-05,
"loss": 0.7574660778045654,
"step": 3530,
"token_acc": 0.8170663232838972
},
{
"epoch": 0.23548585588132578,
"grad_norm": 2.328125,
"learning_rate": 1.7866056713483056e-05,
"loss": 0.7475795269012451,
"step": 3540,
"token_acc": 0.81980980874025
},
{
"epoch": 0.23615107016347642,
"grad_norm": 2.015625,
"learning_rate": 1.7852735805929323e-05,
"loss": 0.8310126304626465,
"step": 3550,
"token_acc": 0.8012745497099827
},
{
"epoch": 0.23681628444562705,
"grad_norm": 2.109375,
"learning_rate": 1.783937844931194e-05,
"loss": 0.8070357322692872,
"step": 3560,
"token_acc": 0.8029723339576872
},
{
"epoch": 0.23748149872777768,
"grad_norm": 2.25,
"learning_rate": 1.7825984705630078e-05,
"loss": 0.757973575592041,
"step": 3570,
"token_acc": 0.8166404623294947
},
{
"epoch": 0.23814671300992832,
"grad_norm": 2.375,
"learning_rate": 1.7812554637051813e-05,
"loss": 0.7936281204223633,
"step": 3580,
"token_acc": 0.8034958847889607
},
{
"epoch": 0.23881192729207895,
"grad_norm": 2.171875,
"learning_rate": 1.7799088305913814e-05,
"loss": 0.8253312110900879,
"step": 3590,
"token_acc": 0.8015503975957229
},
{
"epoch": 0.23947714157422959,
"grad_norm": 2.234375,
"learning_rate": 1.7785585774721067e-05,
"loss": 0.7698770046234131,
"step": 3600,
"token_acc": 0.8139664313541697
},
{
"epoch": 0.24014235585638025,
"grad_norm": 2.3125,
"learning_rate": 1.777204710614659e-05,
"loss": 0.8286229133605957,
"step": 3610,
"token_acc": 0.800103469460342
},
{
"epoch": 0.24080757013853088,
"grad_norm": 2.375,
"learning_rate": 1.7758472363031135e-05,
"loss": 0.7958843231201171,
"step": 3620,
"token_acc": 0.8059600852547956
},
{
"epoch": 0.2414727844206815,
"grad_norm": 2.0,
"learning_rate": 1.774486160838288e-05,
"loss": 0.8067877769470215,
"step": 3630,
"token_acc": 0.8051312578908463
},
{
"epoch": 0.24213799870283215,
"grad_norm": 2.125,
"learning_rate": 1.773121490537718e-05,
"loss": 0.787751293182373,
"step": 3640,
"token_acc": 0.8102939412117577
},
{
"epoch": 0.24280321298498278,
"grad_norm": 1.8984375,
"learning_rate": 1.771753231735622e-05,
"loss": 0.7512083530426026,
"step": 3650,
"token_acc": 0.8175453531380262
},
{
"epoch": 0.2434684272671334,
"grad_norm": 2.1875,
"learning_rate": 1.770381390782877e-05,
"loss": 0.794468879699707,
"step": 3660,
"token_acc": 0.810895679662803
},
{
"epoch": 0.24413364154928408,
"grad_norm": 2.125,
"learning_rate": 1.769005974046986e-05,
"loss": 0.7916010856628418,
"step": 3670,
"token_acc": 0.8085486789721318
},
{
"epoch": 0.2447988558314347,
"grad_norm": 2.140625,
"learning_rate": 1.7676269879120484e-05,
"loss": 0.759503698348999,
"step": 3680,
"token_acc": 0.8145161906070809
},
{
"epoch": 0.24546407011358534,
"grad_norm": 2.1875,
"learning_rate": 1.766244438778733e-05,
"loss": 0.7657989501953125,
"step": 3690,
"token_acc": 0.8122024972148676
},
{
"epoch": 0.24612928439573598,
"grad_norm": 2.046875,
"learning_rate": 1.7648583330642448e-05,
"loss": 0.7769675254821777,
"step": 3700,
"token_acc": 0.8108891928864569
},
{
"epoch": 0.2467944986778866,
"grad_norm": 2.3125,
"learning_rate": 1.7634686772022976e-05,
"loss": 0.8191388130187989,
"step": 3710,
"token_acc": 0.8017965253595278
},
{
"epoch": 0.24745971296003724,
"grad_norm": 2.328125,
"learning_rate": 1.762075477643084e-05,
"loss": 0.7756865501403809,
"step": 3720,
"token_acc": 0.8136545117748208
},
{
"epoch": 0.24812492724218788,
"grad_norm": 2.0625,
"learning_rate": 1.7606787408532447e-05,
"loss": 0.7772349834442138,
"step": 3730,
"token_acc": 0.8111197310576674
},
{
"epoch": 0.24879014152433854,
"grad_norm": 1.8125,
"learning_rate": 1.7592784733158378e-05,
"loss": 0.7693561553955078,
"step": 3740,
"token_acc": 0.8133991330629681
},
{
"epoch": 0.24945535580648917,
"grad_norm": 2.078125,
"learning_rate": 1.757874681530311e-05,
"loss": 0.821525764465332,
"step": 3750,
"token_acc": 0.8028119388826778
},
{
"epoch": 0.2501205700886398,
"grad_norm": 2.171875,
"learning_rate": 1.7564673720124695e-05,
"loss": 0.7302066802978515,
"step": 3760,
"token_acc": 0.8212747782126778
},
{
"epoch": 0.25078578437079047,
"grad_norm": 2.078125,
"learning_rate": 1.7550565512944456e-05,
"loss": 0.7382803440093995,
"step": 3770,
"token_acc": 0.8218470407666679
},
{
"epoch": 0.25145099865294107,
"grad_norm": 2.171875,
"learning_rate": 1.75364222592467e-05,
"loss": 0.8016642570495606,
"step": 3780,
"token_acc": 0.8071722591086926
},
{
"epoch": 0.25211621293509173,
"grad_norm": 2.515625,
"learning_rate": 1.7522244024678407e-05,
"loss": 0.8302186965942383,
"step": 3790,
"token_acc": 0.8041509772279003
},
{
"epoch": 0.25278142721724234,
"grad_norm": 1.9765625,
"learning_rate": 1.750803087504891e-05,
"loss": 0.7606295585632324,
"step": 3800,
"token_acc": 0.8144110646328925
},
{
"epoch": 0.253446641499393,
"grad_norm": 2.171875,
"learning_rate": 1.7493782876329617e-05,
"loss": 0.7908958435058594,
"step": 3810,
"token_acc": 0.811584005003767
},
{
"epoch": 0.2541118557815436,
"grad_norm": 2.203125,
"learning_rate": 1.7479500094653686e-05,
"loss": 0.826467227935791,
"step": 3820,
"token_acc": 0.8010638623093149
},
{
"epoch": 0.25477707006369427,
"grad_norm": 1.671875,
"learning_rate": 1.746518259631572e-05,
"loss": 0.7892783641815185,
"step": 3830,
"token_acc": 0.8094154144938868
},
{
"epoch": 0.2554422843458449,
"grad_norm": 1.9765625,
"learning_rate": 1.7450830447771466e-05,
"loss": 0.7922129154205322,
"step": 3840,
"token_acc": 0.8099492041991195
},
{
"epoch": 0.25610749862799553,
"grad_norm": 2.078125,
"learning_rate": 1.7436443715637496e-05,
"loss": 0.7516029834747314,
"step": 3850,
"token_acc": 0.817713866631939
},
{
"epoch": 0.2567727129101462,
"grad_norm": 2.78125,
"learning_rate": 1.7422022466690916e-05,
"loss": 0.7809311866760253,
"step": 3860,
"token_acc": 0.8044878710353544
},
{
"epoch": 0.2574379271922968,
"grad_norm": 1.96875,
"learning_rate": 1.7407566767869027e-05,
"loss": 0.7906168937683106,
"step": 3870,
"token_acc": 0.8062555925050416
},
{
"epoch": 0.25810314147444746,
"grad_norm": 2.078125,
"learning_rate": 1.7393076686269057e-05,
"loss": 0.8101313591003418,
"step": 3880,
"token_acc": 0.8034989684805924
},
{
"epoch": 0.25876835575659807,
"grad_norm": 2.359375,
"learning_rate": 1.7378552289147794e-05,
"loss": 0.7807673931121826,
"step": 3890,
"token_acc": 0.8141973767313426
},
{
"epoch": 0.25943357003874873,
"grad_norm": 1.9921875,
"learning_rate": 1.7363993643921327e-05,
"loss": 0.8134469032287598,
"step": 3900,
"token_acc": 0.8059051666493305
},
{
"epoch": 0.2600987843208994,
"grad_norm": 2.15625,
"learning_rate": 1.7349400818164703e-05,
"loss": 0.7672461986541748,
"step": 3910,
"token_acc": 0.8150026331828376
},
{
"epoch": 0.26076399860305,
"grad_norm": 2.15625,
"learning_rate": 1.7334773879611615e-05,
"loss": 0.8661992073059082,
"step": 3920,
"token_acc": 0.7925226316914962
},
{
"epoch": 0.26142921288520066,
"grad_norm": 2.3125,
"learning_rate": 1.7320112896154102e-05,
"loss": 0.7743549823760987,
"step": 3930,
"token_acc": 0.811169525777582
},
{
"epoch": 0.26209442716735126,
"grad_norm": 2.046875,
"learning_rate": 1.7305417935842223e-05,
"loss": 0.7447798252105713,
"step": 3940,
"token_acc": 0.8162844021714278
},
{
"epoch": 0.2627596414495019,
"grad_norm": 2.15625,
"learning_rate": 1.729068906688373e-05,
"loss": 0.7488425254821778,
"step": 3950,
"token_acc": 0.8189520231666275
},
{
"epoch": 0.2634248557316526,
"grad_norm": 2.171875,
"learning_rate": 1.727592635764379e-05,
"loss": 0.8285188674926758,
"step": 3960,
"token_acc": 0.8013635656392775
},
{
"epoch": 0.2640900700138032,
"grad_norm": 2.15625,
"learning_rate": 1.7261129876644625e-05,
"loss": 0.779146957397461,
"step": 3970,
"token_acc": 0.809040986185396
},
{
"epoch": 0.26475528429595385,
"grad_norm": 2.4375,
"learning_rate": 1.7246299692565202e-05,
"loss": 0.8148973464965821,
"step": 3980,
"token_acc": 0.8051342499682933
},
{
"epoch": 0.26542049857810446,
"grad_norm": 2.875,
"learning_rate": 1.723143587424095e-05,
"loss": 0.7691033840179443,
"step": 3990,
"token_acc": 0.8132017160666084
},
{
"epoch": 0.2660857128602551,
"grad_norm": 1.921875,
"learning_rate": 1.7216538490663392e-05,
"loss": 0.7480905532836915,
"step": 4000,
"token_acc": 0.8173418431383022
},
{
"epoch": 0.2667509271424057,
"grad_norm": 2.03125,
"learning_rate": 1.7201607610979855e-05,
"loss": 0.7656041622161865,
"step": 4010,
"token_acc": 0.8140736559373236
},
{
"epoch": 0.2674161414245564,
"grad_norm": 2.03125,
"learning_rate": 1.718664330449314e-05,
"loss": 0.8032284736633301,
"step": 4020,
"token_acc": 0.8031014184581076
},
{
"epoch": 0.26808135570670705,
"grad_norm": 1.984375,
"learning_rate": 1.71716456406612e-05,
"loss": 0.7277391910552978,
"step": 4030,
"token_acc": 0.8213080014614541
},
{
"epoch": 0.26874656998885765,
"grad_norm": 2.34375,
"learning_rate": 1.7156614689096823e-05,
"loss": 0.7862032413482666,
"step": 4040,
"token_acc": 0.8087737289823743
},
{
"epoch": 0.2694117842710083,
"grad_norm": 2.453125,
"learning_rate": 1.714155051956729e-05,
"loss": 0.7865857601165771,
"step": 4050,
"token_acc": 0.8099318707419214
},
{
"epoch": 0.2700769985531589,
"grad_norm": 2.625,
"learning_rate": 1.7126453201994092e-05,
"loss": 0.8205173492431641,
"step": 4060,
"token_acc": 0.8043354039556875
},
{
"epoch": 0.2707422128353096,
"grad_norm": 2.015625,
"learning_rate": 1.7111322806452554e-05,
"loss": 0.795978307723999,
"step": 4070,
"token_acc": 0.8094168878002314
},
{
"epoch": 0.2714074271174602,
"grad_norm": 2.125,
"learning_rate": 1.7096159403171544e-05,
"loss": 0.8102274894714355,
"step": 4080,
"token_acc": 0.80399331183232
},
{
"epoch": 0.27207264139961085,
"grad_norm": 2.3125,
"learning_rate": 1.708096306253314e-05,
"loss": 0.7948460578918457,
"step": 4090,
"token_acc": 0.8091828731170686
},
{
"epoch": 0.2727378556817615,
"grad_norm": 2.09375,
"learning_rate": 1.7065733855072298e-05,
"loss": 0.796823787689209,
"step": 4100,
"token_acc": 0.8075643415669825
},
{
"epoch": 0.2734030699639121,
"grad_norm": 1.8046875,
"learning_rate": 1.705047185147654e-05,
"loss": 0.7659366130828857,
"step": 4110,
"token_acc": 0.8163859684937566
},
{
"epoch": 0.2740682842460628,
"grad_norm": 2.015625,
"learning_rate": 1.703517712258559e-05,
"loss": 0.8005739212036133,
"step": 4120,
"token_acc": 0.8054007426526583
},
{
"epoch": 0.2747334985282134,
"grad_norm": 2.3125,
"learning_rate": 1.7019849739391085e-05,
"loss": 0.8085825920104981,
"step": 4130,
"token_acc": 0.8019367805591083
},
{
"epoch": 0.27539871281036404,
"grad_norm": 2.640625,
"learning_rate": 1.7004489773036226e-05,
"loss": 0.8150156021118165,
"step": 4140,
"token_acc": 0.8042475597983482
},
{
"epoch": 0.27606392709251465,
"grad_norm": 2.625,
"learning_rate": 1.698909729481546e-05,
"loss": 0.8131344795227051,
"step": 4150,
"token_acc": 0.805886454331024
},
{
"epoch": 0.2767291413746653,
"grad_norm": 2.59375,
"learning_rate": 1.6973672376174125e-05,
"loss": 0.7892002105712891,
"step": 4160,
"token_acc": 0.8103828071721274
},
{
"epoch": 0.27739435565681597,
"grad_norm": 1.953125,
"learning_rate": 1.6958215088708142e-05,
"loss": 0.7523533344268799,
"step": 4170,
"token_acc": 0.8182899414470932
},
{
"epoch": 0.2780595699389666,
"grad_norm": 2.234375,
"learning_rate": 1.6942725504163668e-05,
"loss": 0.7526955604553223,
"step": 4180,
"token_acc": 0.8171251692783904
},
{
"epoch": 0.27872478422111724,
"grad_norm": 2.46875,
"learning_rate": 1.692720369443678e-05,
"loss": 0.7563735485076905,
"step": 4190,
"token_acc": 0.8163335504504571
},
{
"epoch": 0.27938999850326784,
"grad_norm": 2.46875,
"learning_rate": 1.6911649731573127e-05,
"loss": 0.7967534542083741,
"step": 4200,
"token_acc": 0.8075570596915216
},
{
"epoch": 0.2800552127854185,
"grad_norm": 2.40625,
"learning_rate": 1.6896063687767593e-05,
"loss": 0.775852632522583,
"step": 4210,
"token_acc": 0.813615306313231
},
{
"epoch": 0.28072042706756917,
"grad_norm": 1.8359375,
"learning_rate": 1.688044563536397e-05,
"loss": 0.7542562007904052,
"step": 4220,
"token_acc": 0.8142903527197789
},
{
"epoch": 0.2813856413497198,
"grad_norm": 1.96875,
"learning_rate": 1.6864795646854624e-05,
"loss": 0.7186538696289062,
"step": 4230,
"token_acc": 0.8208796846121953
},
{
"epoch": 0.28205085563187043,
"grad_norm": 2.09375,
"learning_rate": 1.684911379488016e-05,
"loss": 0.7625515460968018,
"step": 4240,
"token_acc": 0.8155285118219749
},
{
"epoch": 0.28271606991402104,
"grad_norm": 2.578125,
"learning_rate": 1.6833400152229063e-05,
"loss": 0.7104531764984131,
"step": 4250,
"token_acc": 0.8260406678323651
},
{
"epoch": 0.2833812841961717,
"grad_norm": 2.328125,
"learning_rate": 1.6817654791837395e-05,
"loss": 0.7592766284942627,
"step": 4260,
"token_acc": 0.8139488751017504
},
{
"epoch": 0.2840464984783223,
"grad_norm": 2.234375,
"learning_rate": 1.6801877786788423e-05,
"loss": 0.7691193580627441,
"step": 4270,
"token_acc": 0.8116587510993843
},
{
"epoch": 0.28471171276047297,
"grad_norm": 2.546875,
"learning_rate": 1.6786069210312308e-05,
"loss": 0.7967219352722168,
"step": 4280,
"token_acc": 0.8051242866030132
},
{
"epoch": 0.28537692704262363,
"grad_norm": 1.8828125,
"learning_rate": 1.677022913578574e-05,
"loss": 0.7573229789733886,
"step": 4290,
"token_acc": 0.8155270655270656
},
{
"epoch": 0.28604214132477424,
"grad_norm": 2.359375,
"learning_rate": 1.6754357636731623e-05,
"loss": 0.7990345001220703,
"step": 4300,
"token_acc": 0.8084769261239849
},
{
"epoch": 0.2867073556069249,
"grad_norm": 2.234375,
"learning_rate": 1.673845478681871e-05,
"loss": 0.7868768215179444,
"step": 4310,
"token_acc": 0.8099180878801084
},
{
"epoch": 0.2873725698890755,
"grad_norm": 1.9765625,
"learning_rate": 1.672252065986127e-05,
"loss": 0.8173232078552246,
"step": 4320,
"token_acc": 0.8034123044052033
},
{
"epoch": 0.28803778417122616,
"grad_norm": 1.9921875,
"learning_rate": 1.670655532981876e-05,
"loss": 0.7915122985839844,
"step": 4330,
"token_acc": 0.8068877785209374
},
{
"epoch": 0.28870299845337677,
"grad_norm": 2.5,
"learning_rate": 1.6690558870795455e-05,
"loss": 0.757099723815918,
"step": 4340,
"token_acc": 0.8148699595672604
},
{
"epoch": 0.28936821273552743,
"grad_norm": 2.671875,
"learning_rate": 1.667453135704012e-05,
"loss": 0.7925323009490967,
"step": 4350,
"token_acc": 0.8073955490237246
},
{
"epoch": 0.2900334270176781,
"grad_norm": 2.5,
"learning_rate": 1.665847286294567e-05,
"loss": 0.7471329212188721,
"step": 4360,
"token_acc": 0.8184243273250226
},
{
"epoch": 0.2906986412998287,
"grad_norm": 2.1875,
"learning_rate": 1.664238346304881e-05,
"loss": 0.8204757690429687,
"step": 4370,
"token_acc": 0.8024813927569465
},
{
"epoch": 0.29136385558197936,
"grad_norm": 1.9375,
"learning_rate": 1.6626263232029703e-05,
"loss": 0.7315850734710694,
"step": 4380,
"token_acc": 0.8222136101875838
},
{
"epoch": 0.29202906986412996,
"grad_norm": 2.25,
"learning_rate": 1.66101122447116e-05,
"loss": 0.7524087429046631,
"step": 4390,
"token_acc": 0.8182181593278122
},
{
"epoch": 0.2926942841462806,
"grad_norm": 2.0,
"learning_rate": 1.6593930576060544e-05,
"loss": 0.7842605590820313,
"step": 4400,
"token_acc": 0.8077805397989216
},
{
"epoch": 0.29335949842843123,
"grad_norm": 2.09375,
"learning_rate": 1.657771830118495e-05,
"loss": 0.7627501010894775,
"step": 4410,
"token_acc": 0.8182028827478107
},
{
"epoch": 0.2940247127105819,
"grad_norm": 2.15625,
"learning_rate": 1.656147549533532e-05,
"loss": 0.7834118366241455,
"step": 4420,
"token_acc": 0.8122461328996634
},
{
"epoch": 0.29468992699273255,
"grad_norm": 2.265625,
"learning_rate": 1.6545202233903846e-05,
"loss": 0.7842981338500976,
"step": 4430,
"token_acc": 0.8096490404182712
},
{
"epoch": 0.29535514127488316,
"grad_norm": 2.125,
"learning_rate": 1.652889859242411e-05,
"loss": 0.7316971778869629,
"step": 4440,
"token_acc": 0.8236301630558897
},
{
"epoch": 0.2960203555570338,
"grad_norm": 2.78125,
"learning_rate": 1.6512564646570684e-05,
"loss": 0.8081085205078125,
"step": 4450,
"token_acc": 0.8023503047566334
},
{
"epoch": 0.2966855698391844,
"grad_norm": 2.328125,
"learning_rate": 1.6496200472158804e-05,
"loss": 0.8540179252624511,
"step": 4460,
"token_acc": 0.7977384577638587
},
{
"epoch": 0.2973507841213351,
"grad_norm": 2.546875,
"learning_rate": 1.6479806145144016e-05,
"loss": 0.7860984802246094,
"step": 4470,
"token_acc": 0.8087036131865404
},
{
"epoch": 0.29801599840348575,
"grad_norm": 2.453125,
"learning_rate": 1.646338174162182e-05,
"loss": 0.7386975288391113,
"step": 4480,
"token_acc": 0.8204589079153407
},
{
"epoch": 0.29868121268563635,
"grad_norm": 1.96875,
"learning_rate": 1.6446927337827328e-05,
"loss": 0.7750612735748291,
"step": 4490,
"token_acc": 0.8106426435188562
},
{
"epoch": 0.299346426967787,
"grad_norm": 2.375,
"learning_rate": 1.6430443010134883e-05,
"loss": 0.7478364467620849,
"step": 4500,
"token_acc": 0.8163283976109884
},
{
"epoch": 0.3000116412499376,
"grad_norm": 1.9609375,
"learning_rate": 1.6413928835057733e-05,
"loss": 0.833950424194336,
"step": 4510,
"token_acc": 0.7994890930733325
},
{
"epoch": 0.3006768555320883,
"grad_norm": 2.09375,
"learning_rate": 1.6397384889247666e-05,
"loss": 0.7879319190979004,
"step": 4520,
"token_acc": 0.8123387945071254
},
{
"epoch": 0.3013420698142389,
"grad_norm": 2.53125,
"learning_rate": 1.6380811249494646e-05,
"loss": 0.819491195678711,
"step": 4530,
"token_acc": 0.8037464788732395
},
{
"epoch": 0.30200728409638955,
"grad_norm": 2.0625,
"learning_rate": 1.6364207992726474e-05,
"loss": 0.7784176826477051,
"step": 4540,
"token_acc": 0.8114799267962473
},
{
"epoch": 0.3026724983785402,
"grad_norm": 2.40625,
"learning_rate": 1.6347575196008412e-05,
"loss": 0.7752568244934082,
"step": 4550,
"token_acc": 0.8125076908352589
},
{
"epoch": 0.3033377126606908,
"grad_norm": 2.140625,
"learning_rate": 1.6330912936542838e-05,
"loss": 0.7748056411743164,
"step": 4560,
"token_acc": 0.813531780270348
},
{
"epoch": 0.3040029269428415,
"grad_norm": 2.21875,
"learning_rate": 1.6314221291668878e-05,
"loss": 0.762264347076416,
"step": 4570,
"token_acc": 0.8078399105589438
},
{
"epoch": 0.3046681412249921,
"grad_norm": 2.3125,
"learning_rate": 1.629750033886206e-05,
"loss": 0.7395438194274903,
"step": 4580,
"token_acc": 0.8193629538814275
},
{
"epoch": 0.30533335550714275,
"grad_norm": 2.96875,
"learning_rate": 1.628075015573394e-05,
"loss": 0.7874424934387207,
"step": 4590,
"token_acc": 0.8102974734569504
},
{
"epoch": 0.30599856978929335,
"grad_norm": 2.0625,
"learning_rate": 1.626397082003176e-05,
"loss": 0.8337896347045899,
"step": 4600,
"token_acc": 0.7979659977740605
},
{
"epoch": 0.306663784071444,
"grad_norm": 2.234375,
"learning_rate": 1.6247162409638058e-05,
"loss": 0.7514512538909912,
"step": 4610,
"token_acc": 0.8198861340679523
},
{
"epoch": 0.3073289983535947,
"grad_norm": 2.359375,
"learning_rate": 1.6230325002570343e-05,
"loss": 0.7858680248260498,
"step": 4620,
"token_acc": 0.8111606090312333
},
{
"epoch": 0.3079942126357453,
"grad_norm": 2.75,
"learning_rate": 1.62134586769807e-05,
"loss": 0.7416365623474122,
"step": 4630,
"token_acc": 0.821387374917092
},
{
"epoch": 0.30865942691789594,
"grad_norm": 2.53125,
"learning_rate": 1.619656351115545e-05,
"loss": 0.8069935798645019,
"step": 4640,
"token_acc": 0.803636802224934
},
{
"epoch": 0.30932464120004655,
"grad_norm": 2.4375,
"learning_rate": 1.617963958351478e-05,
"loss": 0.7833602428436279,
"step": 4650,
"token_acc": 0.8066258707395637
},
{
"epoch": 0.3099898554821972,
"grad_norm": 2.265625,
"learning_rate": 1.6162686972612363e-05,
"loss": 0.8067462921142579,
"step": 4660,
"token_acc": 0.8048518974557629
},
{
"epoch": 0.3106550697643478,
"grad_norm": 1.9375,
"learning_rate": 1.614570575713502e-05,
"loss": 0.7825945377349853,
"step": 4670,
"token_acc": 0.8117888686203231
},
{
"epoch": 0.3113202840464985,
"grad_norm": 2.046875,
"learning_rate": 1.612869601590235e-05,
"loss": 0.7616611003875733,
"step": 4680,
"token_acc": 0.8173058245691928
},
{
"epoch": 0.31198549832864914,
"grad_norm": 2.265625,
"learning_rate": 1.611165782786633e-05,
"loss": 0.8060089111328125,
"step": 4690,
"token_acc": 0.806690006738347
},
{
"epoch": 0.31265071261079974,
"grad_norm": 2.25,
"learning_rate": 1.6094591272110997e-05,
"loss": 0.7565433502197265,
"step": 4700,
"token_acc": 0.8159998931202864
},
{
"epoch": 0.3133159268929504,
"grad_norm": 1.9609375,
"learning_rate": 1.6077496427852058e-05,
"loss": 0.7293829441070556,
"step": 4710,
"token_acc": 0.8224345712590964
},
{
"epoch": 0.313981141175101,
"grad_norm": 2.40625,
"learning_rate": 1.606037337443651e-05,
"loss": 0.777108097076416,
"step": 4720,
"token_acc": 0.8124011861060031
},
{
"epoch": 0.31464635545725167,
"grad_norm": 2.265625,
"learning_rate": 1.60432221913423e-05,
"loss": 0.7429892539978027,
"step": 4730,
"token_acc": 0.8182714426552744
},
{
"epoch": 0.31531156973940233,
"grad_norm": 3.4375,
"learning_rate": 1.6026042958177927e-05,
"loss": 0.7430708885192872,
"step": 4740,
"token_acc": 0.8215915841942822
},
{
"epoch": 0.31597678402155294,
"grad_norm": 2.015625,
"learning_rate": 1.60088357546821e-05,
"loss": 0.7003101348876953,
"step": 4750,
"token_acc": 0.8280005858698837
},
{
"epoch": 0.3166419983037036,
"grad_norm": 2.390625,
"learning_rate": 1.599160066072334e-05,
"loss": 0.781365156173706,
"step": 4760,
"token_acc": 0.8110841394281189
},
{
"epoch": 0.3173072125858542,
"grad_norm": 2.09375,
"learning_rate": 1.5974337756299637e-05,
"loss": 0.7652011394500733,
"step": 4770,
"token_acc": 0.8145812110309152
},
{
"epoch": 0.31797242686800486,
"grad_norm": 2.390625,
"learning_rate": 1.5957047121538062e-05,
"loss": 0.7675495624542237,
"step": 4780,
"token_acc": 0.8137566137566138
},
{
"epoch": 0.31863764115015547,
"grad_norm": 2.0625,
"learning_rate": 1.593972883669439e-05,
"loss": 0.8103490829467773,
"step": 4790,
"token_acc": 0.800842649078039
},
{
"epoch": 0.31930285543230613,
"grad_norm": 2.125,
"learning_rate": 1.5922382982152743e-05,
"loss": 0.7895593643188477,
"step": 4800,
"token_acc": 0.8100408246879618
},
{
"epoch": 0.3199680697144568,
"grad_norm": 2.71875,
"learning_rate": 1.5905009638425215e-05,
"loss": 0.7629838466644288,
"step": 4810,
"token_acc": 0.8150176566365693
},
{
"epoch": 0.3206332839966074,
"grad_norm": 2.953125,
"learning_rate": 1.588760888615148e-05,
"loss": 0.747516393661499,
"step": 4820,
"token_acc": 0.8163366687956852
},
{
"epoch": 0.32129849827875806,
"grad_norm": 2.0625,
"learning_rate": 1.587018080609844e-05,
"loss": 0.757738447189331,
"step": 4830,
"token_acc": 0.8135975952853377
},
{
"epoch": 0.32196371256090867,
"grad_norm": 2.25,
"learning_rate": 1.5852725479159843e-05,
"loss": 0.7620871543884278,
"step": 4840,
"token_acc": 0.8172563978895369
},
{
"epoch": 0.3226289268430593,
"grad_norm": 1.96875,
"learning_rate": 1.58352429863559e-05,
"loss": 0.7638280391693115,
"step": 4850,
"token_acc": 0.8149640363797283
},
{
"epoch": 0.32329414112520993,
"grad_norm": 2.171875,
"learning_rate": 1.5817733408832906e-05,
"loss": 0.8232944488525391,
"step": 4860,
"token_acc": 0.8025514192522306
},
{
"epoch": 0.3239593554073606,
"grad_norm": 2.234375,
"learning_rate": 1.5800196827862898e-05,
"loss": 0.8071296691894532,
"step": 4870,
"token_acc": 0.8019072122845707
},
{
"epoch": 0.32462456968951126,
"grad_norm": 2.25,
"learning_rate": 1.578263332484322e-05,
"loss": 0.7384862899780273,
"step": 4880,
"token_acc": 0.8192171486827279
},
{
"epoch": 0.32528978397166186,
"grad_norm": 1.9296875,
"learning_rate": 1.57650429812962e-05,
"loss": 0.7584771633148193,
"step": 4890,
"token_acc": 0.8134965912656531
},
{
"epoch": 0.3259549982538125,
"grad_norm": 2.140625,
"learning_rate": 1.574742587886874e-05,
"loss": 0.7765599250793457,
"step": 4900,
"token_acc": 0.8157806191117093
},
{
"epoch": 0.32662021253596313,
"grad_norm": 2.21875,
"learning_rate": 1.5729782099331944e-05,
"loss": 0.7212686538696289,
"step": 4910,
"token_acc": 0.8188633324820095
},
{
"epoch": 0.3272854268181138,
"grad_norm": 2.21875,
"learning_rate": 1.5712111724580743e-05,
"loss": 0.7544676780700683,
"step": 4920,
"token_acc": 0.8164851403864047
},
{
"epoch": 0.3279506411002644,
"grad_norm": 2.5,
"learning_rate": 1.5694414836633505e-05,
"loss": 0.7366301059722901,
"step": 4930,
"token_acc": 0.8196999695965236
},
{
"epoch": 0.32861585538241506,
"grad_norm": 2.234375,
"learning_rate": 1.567669151763167e-05,
"loss": 0.7623087882995605,
"step": 4940,
"token_acc": 0.8159737248840804
},
{
"epoch": 0.3292810696645657,
"grad_norm": 2.265625,
"learning_rate": 1.5658941849839356e-05,
"loss": 0.7852182388305664,
"step": 4950,
"token_acc": 0.807179205061202
},
{
"epoch": 0.3299462839467163,
"grad_norm": 2.171875,
"learning_rate": 1.5641165915642978e-05,
"loss": 0.7616226673126221,
"step": 4960,
"token_acc": 0.814939590310669
},
{
"epoch": 0.330611498228867,
"grad_norm": 2.140625,
"learning_rate": 1.5623363797550874e-05,
"loss": 0.7610100269317627,
"step": 4970,
"token_acc": 0.8149767661250741
},
{
"epoch": 0.3312767125110176,
"grad_norm": 1.796875,
"learning_rate": 1.560553557819291e-05,
"loss": 0.767405366897583,
"step": 4980,
"token_acc": 0.814142556071962
},
{
"epoch": 0.33194192679316825,
"grad_norm": 2.046875,
"learning_rate": 1.5587681340320106e-05,
"loss": 0.7742373943328857,
"step": 4990,
"token_acc": 0.812881020696296
},
{
"epoch": 0.3326071410753189,
"grad_norm": 1.890625,
"learning_rate": 1.5569801166804258e-05,
"loss": 0.7837523937225341,
"step": 5000,
"token_acc": 0.8127592587066161
},
{
"epoch": 0.3332723553574695,
"grad_norm": 1.90625,
"learning_rate": 1.5551895140637524e-05,
"loss": 0.7373005867004394,
"step": 5010,
"token_acc": 0.820724333370171
},
{
"epoch": 0.3339375696396202,
"grad_norm": 2.734375,
"learning_rate": 1.553396334493208e-05,
"loss": 0.7434481620788574,
"step": 5020,
"token_acc": 0.8228115358468859
},
{
"epoch": 0.3346027839217708,
"grad_norm": 2.03125,
"learning_rate": 1.55160058629197e-05,
"loss": 0.7629130363464356,
"step": 5030,
"token_acc": 0.8155894717223384
},
{
"epoch": 0.33526799820392145,
"grad_norm": 2.0,
"learning_rate": 1.5498022777951386e-05,
"loss": 0.8007923126220703,
"step": 5040,
"token_acc": 0.8089978844297867
},
{
"epoch": 0.33593321248607205,
"grad_norm": 1.984375,
"learning_rate": 1.548001417349698e-05,
"loss": 0.8071075439453125,
"step": 5050,
"token_acc": 0.8044813616394392
},
{
"epoch": 0.3365984267682227,
"grad_norm": 2.15625,
"learning_rate": 1.5461980133144778e-05,
"loss": 0.710124397277832,
"step": 5060,
"token_acc": 0.8271787195473647
},
{
"epoch": 0.3372636410503734,
"grad_norm": 1.9453125,
"learning_rate": 1.544392074060112e-05,
"loss": 0.7598032474517822,
"step": 5070,
"token_acc": 0.8148161234700512
},
{
"epoch": 0.337928855332524,
"grad_norm": 2.390625,
"learning_rate": 1.542583607969005e-05,
"loss": 0.7603258609771728,
"step": 5080,
"token_acc": 0.8175900435879789
},
{
"epoch": 0.33859406961467464,
"grad_norm": 2.453125,
"learning_rate": 1.540772623435288e-05,
"loss": 0.7957706451416016,
"step": 5090,
"token_acc": 0.8095198500287243
},
{
"epoch": 0.33925928389682525,
"grad_norm": 2.546875,
"learning_rate": 1.538959128864781e-05,
"loss": 0.7773075580596924,
"step": 5100,
"token_acc": 0.8102699979989926
},
{
"epoch": 0.3399244981789759,
"grad_norm": 2.125,
"learning_rate": 1.537143132674956e-05,
"loss": 0.8099418640136719,
"step": 5110,
"token_acc": 0.8035703807058608
},
{
"epoch": 0.3405897124611265,
"grad_norm": 3.71875,
"learning_rate": 1.5353246432948954e-05,
"loss": 0.7462313175201416,
"step": 5120,
"token_acc": 0.8159962132451641
},
{
"epoch": 0.3412549267432772,
"grad_norm": 1.9140625,
"learning_rate": 1.5335036691652546e-05,
"loss": 0.7446832656860352,
"step": 5130,
"token_acc": 0.8197325925114956
},
{
"epoch": 0.34192014102542784,
"grad_norm": 2.0,
"learning_rate": 1.5316802187382222e-05,
"loss": 0.7786159515380859,
"step": 5140,
"token_acc": 0.8108305197220176
},
{
"epoch": 0.34258535530757844,
"grad_norm": 1.9453125,
"learning_rate": 1.52985430047748e-05,
"loss": 0.7127742290496826,
"step": 5150,
"token_acc": 0.8271370288371834
},
{
"epoch": 0.3432505695897291,
"grad_norm": 2.28125,
"learning_rate": 1.528025922858165e-05,
"loss": 0.7960270881652832,
"step": 5160,
"token_acc": 0.8098947054521701
},
{
"epoch": 0.3439157838718797,
"grad_norm": 2.125,
"learning_rate": 1.52619509436683e-05,
"loss": 0.7467900276184082,
"step": 5170,
"token_acc": 0.8191598541954206
},
{
"epoch": 0.34458099815403037,
"grad_norm": 2.46875,
"learning_rate": 1.5243618235014026e-05,
"loss": 0.7991170406341552,
"step": 5180,
"token_acc": 0.8074188735248825
},
{
"epoch": 0.34524621243618103,
"grad_norm": 2.109375,
"learning_rate": 1.522526118771147e-05,
"loss": 0.7548968315124511,
"step": 5190,
"token_acc": 0.8161089595753014
},
{
"epoch": 0.34591142671833164,
"grad_norm": 2.421875,
"learning_rate": 1.5206879886966252e-05,
"loss": 0.7707726955413818,
"step": 5200,
"token_acc": 0.814867099320955
},
{
"epoch": 0.3465766410004823,
"grad_norm": 2.015625,
"learning_rate": 1.518847441809656e-05,
"loss": 0.7189849853515625,
"step": 5210,
"token_acc": 0.8199394362916376
},
{
"epoch": 0.3472418552826329,
"grad_norm": 2.015625,
"learning_rate": 1.5170044866532761e-05,
"loss": 0.7689151287078857,
"step": 5220,
"token_acc": 0.8110174515669613
},
{
"epoch": 0.34790706956478357,
"grad_norm": 2.28125,
"learning_rate": 1.5151591317817005e-05,
"loss": 0.8085298538208008,
"step": 5230,
"token_acc": 0.8024237434766835
},
{
"epoch": 0.34857228384693417,
"grad_norm": 2.421875,
"learning_rate": 1.5133113857602827e-05,
"loss": 0.7422623634338379,
"step": 5240,
"token_acc": 0.819141815488906
},
{
"epoch": 0.34923749812908483,
"grad_norm": 2.015625,
"learning_rate": 1.511461257165475e-05,
"loss": 0.7768805027008057,
"step": 5250,
"token_acc": 0.8104368099842282
},
{
"epoch": 0.3499027124112355,
"grad_norm": 2.234375,
"learning_rate": 1.5096087545847873e-05,
"loss": 0.7796378612518311,
"step": 5260,
"token_acc": 0.8125205164678849
},
{
"epoch": 0.3505679266933861,
"grad_norm": 1.921875,
"learning_rate": 1.507753886616751e-05,
"loss": 0.6986016273498535,
"step": 5270,
"token_acc": 0.8319849453575092
},
{
"epoch": 0.35123314097553676,
"grad_norm": 2.6875,
"learning_rate": 1.5058966618708741e-05,
"loss": 0.7538122653961181,
"step": 5280,
"token_acc": 0.8151618219432659
},
{
"epoch": 0.35189835525768737,
"grad_norm": 1.8046875,
"learning_rate": 1.5040370889676054e-05,
"loss": 0.7885189533233643,
"step": 5290,
"token_acc": 0.8066509951418273
},
{
"epoch": 0.35256356953983803,
"grad_norm": 2.265625,
"learning_rate": 1.5021751765382923e-05,
"loss": 0.7235066890716553,
"step": 5300,
"token_acc": 0.8234249471458773
},
{
"epoch": 0.35322878382198863,
"grad_norm": 2.5,
"learning_rate": 1.5003109332251415e-05,
"loss": 0.7457905292510987,
"step": 5310,
"token_acc": 0.8176441596845737
},
{
"epoch": 0.3538939981041393,
"grad_norm": 2.546875,
"learning_rate": 1.4984443676811786e-05,
"loss": 0.8013957023620606,
"step": 5320,
"token_acc": 0.8087212687973144
},
{
"epoch": 0.35455921238628996,
"grad_norm": 2.296875,
"learning_rate": 1.496575488570207e-05,
"loss": 0.7977571964263916,
"step": 5330,
"token_acc": 0.8080837693186602
},
{
"epoch": 0.35522442666844056,
"grad_norm": 2.8125,
"learning_rate": 1.494704304566771e-05,
"loss": 0.7680302143096924,
"step": 5340,
"token_acc": 0.813203654582965
},
{
"epoch": 0.3558896409505912,
"grad_norm": 2.140625,
"learning_rate": 1.4928308243561108e-05,
"loss": 0.753073263168335,
"step": 5350,
"token_acc": 0.8193147266951175
},
{
"epoch": 0.35655485523274183,
"grad_norm": 2.546875,
"learning_rate": 1.4909550566341255e-05,
"loss": 0.8295683860778809,
"step": 5360,
"token_acc": 0.8040960408527394
},
{
"epoch": 0.3572200695148925,
"grad_norm": 2.671875,
"learning_rate": 1.489077010107333e-05,
"loss": 0.7819873332977295,
"step": 5370,
"token_acc": 0.8148921892607083
},
{
"epoch": 0.3578852837970431,
"grad_norm": 1.984375,
"learning_rate": 1.4871966934928267e-05,
"loss": 0.7685206413269043,
"step": 5380,
"token_acc": 0.8132901112584933
},
{
"epoch": 0.35855049807919376,
"grad_norm": 2.03125,
"learning_rate": 1.4853141155182378e-05,
"loss": 0.7756966590881348,
"step": 5390,
"token_acc": 0.8099424562870262
},
{
"epoch": 0.3592157123613444,
"grad_norm": 2.046875,
"learning_rate": 1.4834292849216931e-05,
"loss": 0.7498853206634521,
"step": 5400,
"token_acc": 0.8176295189346592
},
{
"epoch": 0.359880926643495,
"grad_norm": 2.4375,
"learning_rate": 1.4815422104517764e-05,
"loss": 0.7730533123016358,
"step": 5410,
"token_acc": 0.815777454555675
},
{
"epoch": 0.3605461409256457,
"grad_norm": 2.234375,
"learning_rate": 1.479652900867485e-05,
"loss": 0.7650018692016601,
"step": 5420,
"token_acc": 0.8136319816216439
},
{
"epoch": 0.3612113552077963,
"grad_norm": 2.359375,
"learning_rate": 1.4777613649381915e-05,
"loss": 0.7958643436431885,
"step": 5430,
"token_acc": 0.8073857830973581
},
{
"epoch": 0.36187656948994695,
"grad_norm": 2.359375,
"learning_rate": 1.4758676114436024e-05,
"loss": 0.7728441715240478,
"step": 5440,
"token_acc": 0.8122048986818807
},
{
"epoch": 0.3625417837720976,
"grad_norm": 2.078125,
"learning_rate": 1.4739716491737165e-05,
"loss": 0.7837907314300537,
"step": 5450,
"token_acc": 0.8112753284346471
},
{
"epoch": 0.3632069980542482,
"grad_norm": 2.125,
"learning_rate": 1.4720734869287858e-05,
"loss": 0.8208415031433105,
"step": 5460,
"token_acc": 0.805622417003497
},
{
"epoch": 0.3638722123363989,
"grad_norm": 2.390625,
"learning_rate": 1.4701731335192726e-05,
"loss": 0.7568668842315673,
"step": 5470,
"token_acc": 0.8174104314523879
},
{
"epoch": 0.3645374266185495,
"grad_norm": 2.390625,
"learning_rate": 1.4682705977658102e-05,
"loss": 0.747721529006958,
"step": 5480,
"token_acc": 0.8189920847837173
},
{
"epoch": 0.36520264090070015,
"grad_norm": 2.296875,
"learning_rate": 1.4663658884991616e-05,
"loss": 0.8135316848754883,
"step": 5490,
"token_acc": 0.8030144442118484
},
{
"epoch": 0.36586785518285075,
"grad_norm": 2.8125,
"learning_rate": 1.4644590145601778e-05,
"loss": 0.7865697383880615,
"step": 5500,
"token_acc": 0.8114454847330345
},
{
"epoch": 0.3665330694650014,
"grad_norm": 2.078125,
"learning_rate": 1.4625499847997575e-05,
"loss": 0.7308026313781738,
"step": 5510,
"token_acc": 0.8203482511295317
},
{
"epoch": 0.3671982837471521,
"grad_norm": 2.5625,
"learning_rate": 1.4606388080788061e-05,
"loss": 0.7700204372406005,
"step": 5520,
"token_acc": 0.8083365625753998
},
{
"epoch": 0.3678634980293027,
"grad_norm": 2.234375,
"learning_rate": 1.4587254932681942e-05,
"loss": 0.7759500026702881,
"step": 5530,
"token_acc": 0.8129547291835085
},
{
"epoch": 0.36852871231145334,
"grad_norm": 2.5625,
"learning_rate": 1.4568100492487157e-05,
"loss": 0.8027178764343261,
"step": 5540,
"token_acc": 0.8075857506827961
},
{
"epoch": 0.36919392659360395,
"grad_norm": 1.9765625,
"learning_rate": 1.4548924849110487e-05,
"loss": 0.7384266376495361,
"step": 5550,
"token_acc": 0.8194945076863897
},
{
"epoch": 0.3698591408757546,
"grad_norm": 2.234375,
"learning_rate": 1.4529728091557117e-05,
"loss": 0.7339845180511475,
"step": 5560,
"token_acc": 0.8214392539133503
},
{
"epoch": 0.3705243551579052,
"grad_norm": 2.625,
"learning_rate": 1.4510510308930243e-05,
"loss": 0.756334638595581,
"step": 5570,
"token_acc": 0.8162526526026713
},
{
"epoch": 0.3711895694400559,
"grad_norm": 2.421875,
"learning_rate": 1.449127159043065e-05,
"loss": 0.7691397190093994,
"step": 5580,
"token_acc": 0.8140170760403042
},
{
"epoch": 0.37185478372220654,
"grad_norm": 2.453125,
"learning_rate": 1.4472012025356295e-05,
"loss": 0.7440759658813476,
"step": 5590,
"token_acc": 0.8188098545215293
},
{
"epoch": 0.37251999800435714,
"grad_norm": 2.578125,
"learning_rate": 1.4452731703101896e-05,
"loss": 0.7513597488403321,
"step": 5600,
"token_acc": 0.8185311670865941
},
{
"epoch": 0.3731852122865078,
"grad_norm": 2.390625,
"learning_rate": 1.4433430713158518e-05,
"loss": 0.7484111785888672,
"step": 5610,
"token_acc": 0.8182578461080211
},
{
"epoch": 0.3738504265686584,
"grad_norm": 1.9453125,
"learning_rate": 1.441410914511316e-05,
"loss": 0.8048624038696289,
"step": 5620,
"token_acc": 0.8052095618905157
},
{
"epoch": 0.3745156408508091,
"grad_norm": 2.09375,
"learning_rate": 1.4394767088648326e-05,
"loss": 0.7539636135101319,
"step": 5630,
"token_acc": 0.8176988938191363
},
{
"epoch": 0.3751808551329597,
"grad_norm": 2.203125,
"learning_rate": 1.437540463354164e-05,
"loss": 0.7617098331451416,
"step": 5640,
"token_acc": 0.8117872002369828
},
{
"epoch": 0.37584606941511034,
"grad_norm": 3.0625,
"learning_rate": 1.4356021869665375e-05,
"loss": 0.7500715255737305,
"step": 5650,
"token_acc": 0.8177911176115844
},
{
"epoch": 0.376511283697261,
"grad_norm": 3.828125,
"learning_rate": 1.4336618886986097e-05,
"loss": 0.7587893962860107,
"step": 5660,
"token_acc": 0.8177532021744066
},
{
"epoch": 0.3771764979794116,
"grad_norm": 2.640625,
"learning_rate": 1.431719577556421e-05,
"loss": 0.7875843048095703,
"step": 5670,
"token_acc": 0.8089719524470198
},
{
"epoch": 0.37784171226156227,
"grad_norm": 1.9375,
"learning_rate": 1.4297752625553538e-05,
"loss": 0.732838487625122,
"step": 5680,
"token_acc": 0.8183847374110313
},
{
"epoch": 0.3785069265437129,
"grad_norm": 2.265625,
"learning_rate": 1.4278289527200933e-05,
"loss": 0.7232116222381592,
"step": 5690,
"token_acc": 0.8237105197017509
},
{
"epoch": 0.37917214082586354,
"grad_norm": 2.53125,
"learning_rate": 1.4258806570845823e-05,
"loss": 0.7606457233428955,
"step": 5700,
"token_acc": 0.8141448555630946
},
{
"epoch": 0.3798373551080142,
"grad_norm": 2.046875,
"learning_rate": 1.4239303846919817e-05,
"loss": 0.7421871662139893,
"step": 5710,
"token_acc": 0.8187418104205222
},
{
"epoch": 0.3805025693901648,
"grad_norm": 2.40625,
"learning_rate": 1.4219781445946272e-05,
"loss": 0.7614599704742432,
"step": 5720,
"token_acc": 0.8143887131809273
},
{
"epoch": 0.38116778367231546,
"grad_norm": 2.125,
"learning_rate": 1.4200239458539883e-05,
"loss": 0.7287185192108154,
"step": 5730,
"token_acc": 0.8236473351692856
},
{
"epoch": 0.38183299795446607,
"grad_norm": 2.375,
"learning_rate": 1.4180677975406255e-05,
"loss": 0.7498127460479737,
"step": 5740,
"token_acc": 0.8137472438042109
},
{
"epoch": 0.38249821223661673,
"grad_norm": 2.390625,
"learning_rate": 1.416109708734148e-05,
"loss": 0.7529792308807373,
"step": 5750,
"token_acc": 0.8162950318290124
},
{
"epoch": 0.38316342651876734,
"grad_norm": 2.65625,
"learning_rate": 1.4141496885231723e-05,
"loss": 0.7759263515472412,
"step": 5760,
"token_acc": 0.8104581527825113
},
{
"epoch": 0.383828640800918,
"grad_norm": 2.65625,
"learning_rate": 1.4121877460052792e-05,
"loss": 0.7161035060882568,
"step": 5770,
"token_acc": 0.8235763899065092
},
{
"epoch": 0.38449385508306866,
"grad_norm": 1.9140625,
"learning_rate": 1.4102238902869731e-05,
"loss": 0.7589551448822022,
"step": 5780,
"token_acc": 0.8131274541721758
},
{
"epoch": 0.38515906936521926,
"grad_norm": 1.90625,
"learning_rate": 1.4082581304836376e-05,
"loss": 0.7821749687194824,
"step": 5790,
"token_acc": 0.8125990542334007
},
{
"epoch": 0.3858242836473699,
"grad_norm": 1.96875,
"learning_rate": 1.4062904757194944e-05,
"loss": 0.7561357498168946,
"step": 5800,
"token_acc": 0.8151680762490562
},
{
"epoch": 0.38648949792952053,
"grad_norm": 2.109375,
"learning_rate": 1.4043209351275615e-05,
"loss": 0.7613236427307128,
"step": 5810,
"token_acc": 0.8130419531359618
},
{
"epoch": 0.3871547122116712,
"grad_norm": 2.234375,
"learning_rate": 1.4023495178496092e-05,
"loss": 0.7884667396545411,
"step": 5820,
"token_acc": 0.8118551754716856
},
{
"epoch": 0.3878199264938218,
"grad_norm": 2.5625,
"learning_rate": 1.4003762330361195e-05,
"loss": 0.769109058380127,
"step": 5830,
"token_acc": 0.8163337834956287
},
{
"epoch": 0.38848514077597246,
"grad_norm": 2.5,
"learning_rate": 1.3984010898462417e-05,
"loss": 0.7546240329742432,
"step": 5840,
"token_acc": 0.8163226027201962
},
{
"epoch": 0.3891503550581231,
"grad_norm": 2.15625,
"learning_rate": 1.3964240974477516e-05,
"loss": 0.737033462524414,
"step": 5850,
"token_acc": 0.8214069267268777
},
{
"epoch": 0.3898155693402737,
"grad_norm": 2.4375,
"learning_rate": 1.3944452650170082e-05,
"loss": 0.7331501960754394,
"step": 5860,
"token_acc": 0.8185497290892874
},
{
"epoch": 0.3904807836224244,
"grad_norm": 2.40625,
"learning_rate": 1.392464601738911e-05,
"loss": 0.7711932182312011,
"step": 5870,
"token_acc": 0.8136004200901958
},
{
"epoch": 0.391145997904575,
"grad_norm": 2.359375,
"learning_rate": 1.3904821168068572e-05,
"loss": 0.756660270690918,
"step": 5880,
"token_acc": 0.8204782851657091
},
{
"epoch": 0.39181121218672565,
"grad_norm": 1.7890625,
"learning_rate": 1.3884978194227001e-05,
"loss": 0.794218111038208,
"step": 5890,
"token_acc": 0.8088975138222694
},
{
"epoch": 0.39247642646887626,
"grad_norm": 1.96875,
"learning_rate": 1.3865117187967052e-05,
"loss": 0.7816334247589112,
"step": 5900,
"token_acc": 0.8118641445205215
},
{
"epoch": 0.3931416407510269,
"grad_norm": 2.0625,
"learning_rate": 1.3845238241475075e-05,
"loss": 0.784235143661499,
"step": 5910,
"token_acc": 0.8092448850021504
},
{
"epoch": 0.3938068550331776,
"grad_norm": 2.1875,
"learning_rate": 1.3825341447020694e-05,
"loss": 0.7344516754150391,
"step": 5920,
"token_acc": 0.8214299118033402
},
{
"epoch": 0.3944720693153282,
"grad_norm": 1.9609375,
"learning_rate": 1.3805426896956383e-05,
"loss": 0.7884132385253906,
"step": 5930,
"token_acc": 0.8109081389632032
},
{
"epoch": 0.39513728359747885,
"grad_norm": 2.484375,
"learning_rate": 1.3785494683717015e-05,
"loss": 0.777791690826416,
"step": 5940,
"token_acc": 0.8102902804957599
},
{
"epoch": 0.39580249787962946,
"grad_norm": 2.28125,
"learning_rate": 1.3765544899819462e-05,
"loss": 0.7294783115386962,
"step": 5950,
"token_acc": 0.8231658829496146
},
{
"epoch": 0.3964677121617801,
"grad_norm": 2.421875,
"learning_rate": 1.3745577637862147e-05,
"loss": 0.7474365234375,
"step": 5960,
"token_acc": 0.818214882167378
},
{
"epoch": 0.3971329264439308,
"grad_norm": 2.40625,
"learning_rate": 1.3725592990524617e-05,
"loss": 0.7937293529510498,
"step": 5970,
"token_acc": 0.8091482649842271
},
{
"epoch": 0.3977981407260814,
"grad_norm": 2.109375,
"learning_rate": 1.3705591050567108e-05,
"loss": 0.7778053283691406,
"step": 5980,
"token_acc": 0.8103268498095048
},
{
"epoch": 0.39846335500823205,
"grad_norm": 2.15625,
"learning_rate": 1.3685571910830136e-05,
"loss": 0.7686887741088867,
"step": 5990,
"token_acc": 0.8122586139738164
},
{
"epoch": 0.39912856929038265,
"grad_norm": 2.328125,
"learning_rate": 1.3665535664234039e-05,
"loss": 0.7213515281677246,
"step": 6000,
"token_acc": 0.8259002081041502
},
{
"epoch": 0.3997937835725333,
"grad_norm": 2.25,
"learning_rate": 1.3645482403778567e-05,
"loss": 0.7145774364471436,
"step": 6010,
"token_acc": 0.8245762840222347
},
{
"epoch": 0.4004589978546839,
"grad_norm": 2.765625,
"learning_rate": 1.3625412222542431e-05,
"loss": 0.7489419460296631,
"step": 6020,
"token_acc": 0.8173777787077919
},
{
"epoch": 0.4011242121368346,
"grad_norm": 2.609375,
"learning_rate": 1.3605325213682887e-05,
"loss": 0.7784491062164307,
"step": 6030,
"token_acc": 0.8105659886932224
},
{
"epoch": 0.40178942641898524,
"grad_norm": 2.109375,
"learning_rate": 1.3585221470435301e-05,
"loss": 0.7437080383300781,
"step": 6040,
"token_acc": 0.8193154169431541
},
{
"epoch": 0.40245464070113585,
"grad_norm": 2.46875,
"learning_rate": 1.3565101086112704e-05,
"loss": 0.7766180992126465,
"step": 6050,
"token_acc": 0.8093546825739439
},
{
"epoch": 0.4031198549832865,
"grad_norm": 1.9609375,
"learning_rate": 1.3544964154105373e-05,
"loss": 0.7108688354492188,
"step": 6060,
"token_acc": 0.8262512420898489
},
{
"epoch": 0.4037850692654371,
"grad_norm": 2.421875,
"learning_rate": 1.3524810767880394e-05,
"loss": 0.713167667388916,
"step": 6070,
"token_acc": 0.8239566598169251
},
{
"epoch": 0.4044502835475878,
"grad_norm": 2.3125,
"learning_rate": 1.3504641020981225e-05,
"loss": 0.7160182476043702,
"step": 6080,
"token_acc": 0.8251359003009343
},
{
"epoch": 0.4051154978297384,
"grad_norm": 2.171875,
"learning_rate": 1.3484455007027258e-05,
"loss": 0.730893325805664,
"step": 6090,
"token_acc": 0.8233868049692438
},
{
"epoch": 0.40578071211188904,
"grad_norm": 2.109375,
"learning_rate": 1.3464252819713402e-05,
"loss": 0.7251900672912598,
"step": 6100,
"token_acc": 0.8223410576351753
},
{
"epoch": 0.4064459263940397,
"grad_norm": 2.75,
"learning_rate": 1.3444034552809622e-05,
"loss": 0.7555287837982178,
"step": 6110,
"token_acc": 0.8191262692313344
},
{
"epoch": 0.4071111406761903,
"grad_norm": 2.328125,
"learning_rate": 1.3423800300160523e-05,
"loss": 0.766284704208374,
"step": 6120,
"token_acc": 0.813507015718584
},
{
"epoch": 0.40777635495834097,
"grad_norm": 2.3125,
"learning_rate": 1.3403550155684916e-05,
"loss": 0.7406195640563965,
"step": 6130,
"token_acc": 0.8199775161559524
},
{
"epoch": 0.4084415692404916,
"grad_norm": 2.09375,
"learning_rate": 1.3383284213375366e-05,
"loss": 0.7269672870635986,
"step": 6140,
"token_acc": 0.8226558940363352
},
{
"epoch": 0.40910678352264224,
"grad_norm": 2.3125,
"learning_rate": 1.3363002567297765e-05,
"loss": 0.7829487323760986,
"step": 6150,
"token_acc": 0.8100373091062866
},
{
"epoch": 0.40977199780479284,
"grad_norm": 1.984375,
"learning_rate": 1.3342705311590903e-05,
"loss": 0.7125879764556885,
"step": 6160,
"token_acc": 0.8256285482562855
},
{
"epoch": 0.4104372120869435,
"grad_norm": 2.328125,
"learning_rate": 1.332239254046602e-05,
"loss": 0.7735970973968506,
"step": 6170,
"token_acc": 0.8118288621308055
},
{
"epoch": 0.41110242636909416,
"grad_norm": 2.484375,
"learning_rate": 1.330206434820636e-05,
"loss": 0.8025568962097168,
"step": 6180,
"token_acc": 0.8065373168644382
},
{
"epoch": 0.41176764065124477,
"grad_norm": 2.1875,
"learning_rate": 1.328172082916677e-05,
"loss": 0.7814645290374755,
"step": 6190,
"token_acc": 0.8108128173907879
},
{
"epoch": 0.41243285493339543,
"grad_norm": 2.015625,
"learning_rate": 1.3261362077773209e-05,
"loss": 0.7583053588867188,
"step": 6200,
"token_acc": 0.8147104487411856
},
{
"epoch": 0.41309806921554604,
"grad_norm": 2.328125,
"learning_rate": 1.3240988188522364e-05,
"loss": 0.7658724308013916,
"step": 6210,
"token_acc": 0.8133624925602447
},
{
"epoch": 0.4137632834976967,
"grad_norm": 2.21875,
"learning_rate": 1.3220599255981165e-05,
"loss": 0.7211755752563477,
"step": 6220,
"token_acc": 0.8243644161146768
},
{
"epoch": 0.41442849777984736,
"grad_norm": 2.140625,
"learning_rate": 1.320019537478638e-05,
"loss": 0.7329001903533936,
"step": 6230,
"token_acc": 0.818542354196047
},
{
"epoch": 0.41509371206199797,
"grad_norm": 2.125,
"learning_rate": 1.317977663964416e-05,
"loss": 0.7090003490447998,
"step": 6240,
"token_acc": 0.8252571253134114
},
{
"epoch": 0.4157589263441486,
"grad_norm": 2.203125,
"learning_rate": 1.3159343145329592e-05,
"loss": 0.7817197322845459,
"step": 6250,
"token_acc": 0.8112364109523876
},
{
"epoch": 0.41642414062629923,
"grad_norm": 2.421875,
"learning_rate": 1.3138894986686284e-05,
"loss": 0.7124030113220214,
"step": 6260,
"token_acc": 0.8240639719861237
},
{
"epoch": 0.4170893549084499,
"grad_norm": 2.5625,
"learning_rate": 1.3118432258625895e-05,
"loss": 0.7548107624053955,
"step": 6270,
"token_acc": 0.8181544809259065
},
{
"epoch": 0.4177545691906005,
"grad_norm": 2.390625,
"learning_rate": 1.3097955056127721e-05,
"loss": 0.757051658630371,
"step": 6280,
"token_acc": 0.8140085990629028
},
{
"epoch": 0.41841978347275116,
"grad_norm": 2.15625,
"learning_rate": 1.3077463474238233e-05,
"loss": 0.7060974597930908,
"step": 6290,
"token_acc": 0.8250304692260817
},
{
"epoch": 0.4190849977549018,
"grad_norm": 2.5625,
"learning_rate": 1.3056957608070651e-05,
"loss": 0.7902791500091553,
"step": 6300,
"token_acc": 0.8117200062612953
},
{
"epoch": 0.41975021203705243,
"grad_norm": 2.09375,
"learning_rate": 1.3036437552804495e-05,
"loss": 0.7837092876434326,
"step": 6310,
"token_acc": 0.8118354011636235
},
{
"epoch": 0.4204154263192031,
"grad_norm": 2.15625,
"learning_rate": 1.301590340368514e-05,
"loss": 0.7201298713684082,
"step": 6320,
"token_acc": 0.8249057715353048
},
{
"epoch": 0.4210806406013537,
"grad_norm": 2.46875,
"learning_rate": 1.2995355256023392e-05,
"loss": 0.8000015258789063,
"step": 6330,
"token_acc": 0.8060695477551689
},
{
"epoch": 0.42174585488350436,
"grad_norm": 2.1875,
"learning_rate": 1.2974793205195013e-05,
"loss": 0.6971353054046631,
"step": 6340,
"token_acc": 0.8295884662820204
},
{
"epoch": 0.42241106916565496,
"grad_norm": 4.625,
"learning_rate": 1.2954217346640316e-05,
"loss": 0.7680907249450684,
"step": 6350,
"token_acc": 0.8150536625260604
},
{
"epoch": 0.4230762834478056,
"grad_norm": 2.21875,
"learning_rate": 1.293362777586369e-05,
"loss": 0.7920069694519043,
"step": 6360,
"token_acc": 0.8105222093886012
},
{
"epoch": 0.4237414977299563,
"grad_norm": 2.21875,
"learning_rate": 1.291302458843318e-05,
"loss": 0.7631069183349609,
"step": 6370,
"token_acc": 0.8132847366855103
},
{
"epoch": 0.4244067120121069,
"grad_norm": 2.640625,
"learning_rate": 1.289240787998003e-05,
"loss": 0.7506068229675293,
"step": 6380,
"token_acc": 0.8176727599596236
},
{
"epoch": 0.42507192629425755,
"grad_norm": 1.953125,
"learning_rate": 1.2871777746198233e-05,
"loss": 0.7209974765777588,
"step": 6390,
"token_acc": 0.8239896274745431
},
{
"epoch": 0.42573714057640816,
"grad_norm": 3.640625,
"learning_rate": 1.2851134282844118e-05,
"loss": 0.7401516437530518,
"step": 6400,
"token_acc": 0.8163423607109614
},
{
"epoch": 0.4264023548585588,
"grad_norm": 2.53125,
"learning_rate": 1.2830477585735866e-05,
"loss": 0.7525502204895019,
"step": 6410,
"token_acc": 0.8165922763438773
},
{
"epoch": 0.4270675691407094,
"grad_norm": 1.984375,
"learning_rate": 1.2809807750753089e-05,
"loss": 0.7916851043701172,
"step": 6420,
"token_acc": 0.809606554127713
},
{
"epoch": 0.4277327834228601,
"grad_norm": 2.140625,
"learning_rate": 1.2789124873836383e-05,
"loss": 0.7735728263854981,
"step": 6430,
"token_acc": 0.8114306775123825
},
{
"epoch": 0.42839799770501075,
"grad_norm": 1.828125,
"learning_rate": 1.2768429050986874e-05,
"loss": 0.7592185497283935,
"step": 6440,
"token_acc": 0.8150727620593692
},
{
"epoch": 0.42906321198716135,
"grad_norm": 2.140625,
"learning_rate": 1.2747720378265784e-05,
"loss": 0.7871395587921143,
"step": 6450,
"token_acc": 0.8098016764287077
},
{
"epoch": 0.429728426269312,
"grad_norm": 2.171875,
"learning_rate": 1.2726998951793967e-05,
"loss": 0.7368836402893066,
"step": 6460,
"token_acc": 0.8210042712034744
},
{
"epoch": 0.4303936405514626,
"grad_norm": 2.390625,
"learning_rate": 1.2706264867751492e-05,
"loss": 0.7815388679504395,
"step": 6470,
"token_acc": 0.8122860810039931
},
{
"epoch": 0.4310588548336133,
"grad_norm": 1.9765625,
"learning_rate": 1.268551822237716e-05,
"loss": 0.7684689998626709,
"step": 6480,
"token_acc": 0.8136899081162793
},
{
"epoch": 0.43172406911576394,
"grad_norm": 2.03125,
"learning_rate": 1.2664759111968088e-05,
"loss": 0.7552419662475586,
"step": 6490,
"token_acc": 0.8170038260722514
},
{
"epoch": 0.43238928339791455,
"grad_norm": 1.9921875,
"learning_rate": 1.264398763287925e-05,
"loss": 0.7823434352874756,
"step": 6500,
"token_acc": 0.8106638202704076
},
{
"epoch": 0.4330544976800652,
"grad_norm": 2.53125,
"learning_rate": 1.2623203881523026e-05,
"loss": 0.7521623134613037,
"step": 6510,
"token_acc": 0.8183073898953408
},
{
"epoch": 0.4337197119622158,
"grad_norm": 2.390625,
"learning_rate": 1.260240795436876e-05,
"loss": 0.7537161350250244,
"step": 6520,
"token_acc": 0.8169386887217163
},
{
"epoch": 0.4343849262443665,
"grad_norm": 2.015625,
"learning_rate": 1.258159994794231e-05,
"loss": 0.7503443717956543,
"step": 6530,
"token_acc": 0.8159698203626976
},
{
"epoch": 0.4350501405265171,
"grad_norm": 2.09375,
"learning_rate": 1.2560779958825609e-05,
"loss": 0.7219661712646485,
"step": 6540,
"token_acc": 0.824494055099818
},
{
"epoch": 0.43571535480866774,
"grad_norm": 2.359375,
"learning_rate": 1.253994808365619e-05,
"loss": 0.7588708400726318,
"step": 6550,
"token_acc": 0.8192698000371095
},
{
"epoch": 0.4363805690908184,
"grad_norm": 2.359375,
"learning_rate": 1.2519104419126784e-05,
"loss": 0.7819123268127441,
"step": 6560,
"token_acc": 0.8084934663274045
},
{
"epoch": 0.437045783372969,
"grad_norm": 2.78125,
"learning_rate": 1.2498249061984813e-05,
"loss": 0.7913288593292236,
"step": 6570,
"token_acc": 0.8077926004308227
},
{
"epoch": 0.43771099765511967,
"grad_norm": 2.203125,
"learning_rate": 1.247738210903199e-05,
"loss": 0.7963505268096924,
"step": 6580,
"token_acc": 0.8095587043678615
},
{
"epoch": 0.4383762119372703,
"grad_norm": 2.203125,
"learning_rate": 1.245650365712385e-05,
"loss": 0.8252696037292481,
"step": 6590,
"token_acc": 0.8008660568785155
},
{
"epoch": 0.43904142621942094,
"grad_norm": 2.6875,
"learning_rate": 1.243561380316929e-05,
"loss": 0.8045899391174316,
"step": 6600,
"token_acc": 0.8077402028446258
},
{
"epoch": 0.43970664050157154,
"grad_norm": 2.328125,
"learning_rate": 1.2414712644130145e-05,
"loss": 0.767204999923706,
"step": 6610,
"token_acc": 0.8151550558582619
},
{
"epoch": 0.4403718547837222,
"grad_norm": 2.1875,
"learning_rate": 1.2393800277020707e-05,
"loss": 0.7272262096405029,
"step": 6620,
"token_acc": 0.8223925555023264
},
{
"epoch": 0.44103706906587287,
"grad_norm": 2.421875,
"learning_rate": 1.2372876798907313e-05,
"loss": 0.7872851371765137,
"step": 6630,
"token_acc": 0.8084020190403169
},
{
"epoch": 0.4417022833480235,
"grad_norm": 2.640625,
"learning_rate": 1.2351942306907848e-05,
"loss": 0.7698792934417724,
"step": 6640,
"token_acc": 0.813365500247154
},
{
"epoch": 0.44236749763017413,
"grad_norm": 2.359375,
"learning_rate": 1.2330996898191333e-05,
"loss": 0.712770652770996,
"step": 6650,
"token_acc": 0.8248955404767441
},
{
"epoch": 0.44303271191232474,
"grad_norm": 2.1875,
"learning_rate": 1.2310040669977464e-05,
"loss": 0.7811156272888183,
"step": 6660,
"token_acc": 0.8113162090345438
},
{
"epoch": 0.4436979261944754,
"grad_norm": 2.59375,
"learning_rate": 1.228907371953614e-05,
"loss": 0.7807763576507568,
"step": 6670,
"token_acc": 0.8096743724921457
},
{
"epoch": 0.444363140476626,
"grad_norm": 2.078125,
"learning_rate": 1.226809614418705e-05,
"loss": 0.7639223098754883,
"step": 6680,
"token_acc": 0.8164366504098786
},
{
"epoch": 0.44502835475877667,
"grad_norm": 2.28125,
"learning_rate": 1.2247108041299174e-05,
"loss": 0.7375510692596435,
"step": 6690,
"token_acc": 0.8202618099032442
},
{
"epoch": 0.44569356904092733,
"grad_norm": 2.125,
"learning_rate": 1.2226109508290378e-05,
"loss": 0.7244351387023926,
"step": 6700,
"token_acc": 0.8229697803166544
},
{
"epoch": 0.44635878332307793,
"grad_norm": 2.125,
"learning_rate": 1.220510064262693e-05,
"loss": 0.7835217952728272,
"step": 6710,
"token_acc": 0.8101741664256956
},
{
"epoch": 0.4470239976052286,
"grad_norm": 2.0,
"learning_rate": 1.2184081541823058e-05,
"loss": 0.7484204292297363,
"step": 6720,
"token_acc": 0.8169018161607624
},
{
"epoch": 0.4476892118873792,
"grad_norm": 2.125,
"learning_rate": 1.2163052303440503e-05,
"loss": 0.7202248096466064,
"step": 6730,
"token_acc": 0.8241470009651727
},
{
"epoch": 0.44835442616952986,
"grad_norm": 1.96875,
"learning_rate": 1.214201302508805e-05,
"loss": 0.7441082000732422,
"step": 6740,
"token_acc": 0.8192728556300741
},
{
"epoch": 0.4490196404516805,
"grad_norm": 1.9921875,
"learning_rate": 1.2120963804421098e-05,
"loss": 0.7845107555389405,
"step": 6750,
"token_acc": 0.8096567737763702
},
{
"epoch": 0.44968485473383113,
"grad_norm": 2.125,
"learning_rate": 1.2099904739141177e-05,
"loss": 0.7370713710784912,
"step": 6760,
"token_acc": 0.82144034846893
},
{
"epoch": 0.4503500690159818,
"grad_norm": 2.53125,
"learning_rate": 1.2078835926995533e-05,
"loss": 0.7602892875671386,
"step": 6770,
"token_acc": 0.8142412389239243
},
{
"epoch": 0.4510152832981324,
"grad_norm": 1.828125,
"learning_rate": 1.2057757465776634e-05,
"loss": 0.7549887657165527,
"step": 6780,
"token_acc": 0.8162794641343056
},
{
"epoch": 0.45168049758028306,
"grad_norm": 2.203125,
"learning_rate": 1.2036669453321748e-05,
"loss": 0.7261628150939942,
"step": 6790,
"token_acc": 0.8255521485396148
},
{
"epoch": 0.45234571186243366,
"grad_norm": 2.265625,
"learning_rate": 1.2015571987512467e-05,
"loss": 0.772891616821289,
"step": 6800,
"token_acc": 0.8109620538960725
},
{
"epoch": 0.4530109261445843,
"grad_norm": 2.03125,
"learning_rate": 1.1994465166274263e-05,
"loss": 0.7716512680053711,
"step": 6810,
"token_acc": 0.8138159193481412
},
{
"epoch": 0.453676140426735,
"grad_norm": 2.828125,
"learning_rate": 1.1973349087576041e-05,
"loss": 0.7313772678375244,
"step": 6820,
"token_acc": 0.8214938941338543
},
{
"epoch": 0.4543413547088856,
"grad_norm": 2.03125,
"learning_rate": 1.1952223849429661e-05,
"loss": 0.7653038024902343,
"step": 6830,
"token_acc": 0.8130000584009811
},
{
"epoch": 0.45500656899103625,
"grad_norm": 1.9921875,
"learning_rate": 1.1931089549889503e-05,
"loss": 0.7310605525970459,
"step": 6840,
"token_acc": 0.8206296075182624
},
{
"epoch": 0.45567178327318686,
"grad_norm": 1.9921875,
"learning_rate": 1.1909946287052014e-05,
"loss": 0.7747984409332276,
"step": 6850,
"token_acc": 0.8128264543219992
},
{
"epoch": 0.4563369975553375,
"grad_norm": 2.796875,
"learning_rate": 1.1888794159055233e-05,
"loss": 0.6967289447784424,
"step": 6860,
"token_acc": 0.8277389932349191
},
{
"epoch": 0.4570022118374881,
"grad_norm": 2.234375,
"learning_rate": 1.1867633264078356e-05,
"loss": 0.8147965431213379,
"step": 6870,
"token_acc": 0.8033662837296286
},
{
"epoch": 0.4576674261196388,
"grad_norm": 2.59375,
"learning_rate": 1.1846463700341264e-05,
"loss": 0.7320817947387696,
"step": 6880,
"token_acc": 0.8221839852274635
},
{
"epoch": 0.45833264040178945,
"grad_norm": 2.359375,
"learning_rate": 1.1825285566104083e-05,
"loss": 0.7443554401397705,
"step": 6890,
"token_acc": 0.8217125270215806
},
{
"epoch": 0.45899785468394005,
"grad_norm": 2.421875,
"learning_rate": 1.1804098959666712e-05,
"loss": 0.767994499206543,
"step": 6900,
"token_acc": 0.8141911754652228
},
{
"epoch": 0.4596630689660907,
"grad_norm": 2.4375,
"learning_rate": 1.178290397936838e-05,
"loss": 0.7243148803710937,
"step": 6910,
"token_acc": 0.8221328595957869
},
{
"epoch": 0.4603282832482413,
"grad_norm": 1.9453125,
"learning_rate": 1.1761700723587177e-05,
"loss": 0.8029426574707031,
"step": 6920,
"token_acc": 0.808854180236042
},
{
"epoch": 0.460993497530392,
"grad_norm": 2.125,
"learning_rate": 1.1740489290739614e-05,
"loss": 0.7387587070465088,
"step": 6930,
"token_acc": 0.8195949377106264
},
{
"epoch": 0.4616587118125426,
"grad_norm": 2.171875,
"learning_rate": 1.1719269779280149e-05,
"loss": 0.764794921875,
"step": 6940,
"token_acc": 0.815636970828013
},
{
"epoch": 0.46232392609469325,
"grad_norm": 2.4375,
"learning_rate": 1.1698042287700741e-05,
"loss": 0.7780982971191406,
"step": 6950,
"token_acc": 0.8115250073754748
},
{
"epoch": 0.4629891403768439,
"grad_norm": 2.296875,
"learning_rate": 1.167680691453039e-05,
"loss": 0.767616605758667,
"step": 6960,
"token_acc": 0.815699249921399
},
{
"epoch": 0.4636543546589945,
"grad_norm": 1.828125,
"learning_rate": 1.1655563758334672e-05,
"loss": 0.7627209186553955,
"step": 6970,
"token_acc": 0.8174399135123732
},
{
"epoch": 0.4643195689411452,
"grad_norm": 2.09375,
"learning_rate": 1.1634312917715296e-05,
"loss": 0.8080660820007324,
"step": 6980,
"token_acc": 0.8014202567235558
},
{
"epoch": 0.4649847832232958,
"grad_norm": 2.125,
"learning_rate": 1.1613054491309638e-05,
"loss": 0.7456583499908447,
"step": 6990,
"token_acc": 0.817428678607079
},
{
"epoch": 0.46564999750544644,
"grad_norm": 2.578125,
"learning_rate": 1.1591788577790281e-05,
"loss": 0.7510671138763427,
"step": 7000,
"token_acc": 0.8172793112393345
},
{
"epoch": 0.4663152117875971,
"grad_norm": 2.296875,
"learning_rate": 1.1570515275864561e-05,
"loss": 0.7780903339385986,
"step": 7010,
"token_acc": 0.810295456058958
},
{
"epoch": 0.4669804260697477,
"grad_norm": 2.65625,
"learning_rate": 1.154923468427411e-05,
"loss": 0.7584575653076172,
"step": 7020,
"token_acc": 0.8181353181882319
},
{
"epoch": 0.4676456403518984,
"grad_norm": 2.015625,
"learning_rate": 1.1527946901794396e-05,
"loss": 0.7633735656738281,
"step": 7030,
"token_acc": 0.8135646958578006
},
{
"epoch": 0.468310854634049,
"grad_norm": 2.078125,
"learning_rate": 1.1506652027234255e-05,
"loss": 0.7331698417663575,
"step": 7040,
"token_acc": 0.8174156101595813
},
{
"epoch": 0.46897606891619964,
"grad_norm": 2.5,
"learning_rate": 1.1485350159435453e-05,
"loss": 0.7501302719116211,
"step": 7050,
"token_acc": 0.819096345405641
},
{
"epoch": 0.46964128319835025,
"grad_norm": 2.109375,
"learning_rate": 1.146404139727221e-05,
"loss": 0.7476665496826171,
"step": 7060,
"token_acc": 0.8205816420629625
},
{
"epoch": 0.4703064974805009,
"grad_norm": 2.5,
"learning_rate": 1.1442725839650748e-05,
"loss": 0.7631318092346191,
"step": 7070,
"token_acc": 0.814093670764962
},
{
"epoch": 0.47097171176265157,
"grad_norm": 2.046875,
"learning_rate": 1.142140358550883e-05,
"loss": 0.7268123626708984,
"step": 7080,
"token_acc": 0.8212153381160704
},
{
"epoch": 0.4716369260448022,
"grad_norm": 2.34375,
"learning_rate": 1.1400074733815303e-05,
"loss": 0.7570295333862305,
"step": 7090,
"token_acc": 0.8191013994598576
},
{
"epoch": 0.47230214032695284,
"grad_norm": 2.328125,
"learning_rate": 1.1378739383569632e-05,
"loss": 0.7755563259124756,
"step": 7100,
"token_acc": 0.8169521704426843
},
{
"epoch": 0.47296735460910344,
"grad_norm": 2.6875,
"learning_rate": 1.1357397633801455e-05,
"loss": 0.7698848724365235,
"step": 7110,
"token_acc": 0.8148145476058207
},
{
"epoch": 0.4736325688912541,
"grad_norm": 2.421875,
"learning_rate": 1.1336049583570104e-05,
"loss": 0.7453318119049073,
"step": 7120,
"token_acc": 0.817314608998827
},
{
"epoch": 0.4742977831734047,
"grad_norm": 2.40625,
"learning_rate": 1.131469533196416e-05,
"loss": 0.7299962043762207,
"step": 7130,
"token_acc": 0.8217870504567056
},
{
"epoch": 0.47496299745555537,
"grad_norm": 2.515625,
"learning_rate": 1.1293334978100988e-05,
"loss": 0.7653594017028809,
"step": 7140,
"token_acc": 0.8127470987991082
},
{
"epoch": 0.47562821173770603,
"grad_norm": 2.234375,
"learning_rate": 1.1271968621126273e-05,
"loss": 0.7905018329620361,
"step": 7150,
"token_acc": 0.809242575035357
},
{
"epoch": 0.47629342601985664,
"grad_norm": 2.140625,
"learning_rate": 1.1250596360213574e-05,
"loss": 0.7540499687194824,
"step": 7160,
"token_acc": 0.8192516287478255
},
{
"epoch": 0.4769586403020073,
"grad_norm": 2.5625,
"learning_rate": 1.1229218294563839e-05,
"loss": 0.7438382148742676,
"step": 7170,
"token_acc": 0.8179886041877862
},
{
"epoch": 0.4776238545841579,
"grad_norm": 2.375,
"learning_rate": 1.1207834523404976e-05,
"loss": 0.7405606746673584,
"step": 7180,
"token_acc": 0.8231673067873029
},
{
"epoch": 0.47828906886630856,
"grad_norm": 2.390625,
"learning_rate": 1.118644514599136e-05,
"loss": 0.7483702659606933,
"step": 7190,
"token_acc": 0.8163572955338059
},
{
"epoch": 0.47895428314845917,
"grad_norm": 2.140625,
"learning_rate": 1.1165050261603396e-05,
"loss": 0.7889360904693603,
"step": 7200,
"token_acc": 0.8080279354238249
},
{
"epoch": 0.47961949743060983,
"grad_norm": 1.7421875,
"learning_rate": 1.1143649969547048e-05,
"loss": 0.6966003894805908,
"step": 7210,
"token_acc": 0.8292404040138527
},
{
"epoch": 0.4802847117127605,
"grad_norm": 2.40625,
"learning_rate": 1.1122244369153381e-05,
"loss": 0.7628078460693359,
"step": 7220,
"token_acc": 0.8133731369429076
},
{
"epoch": 0.4809499259949111,
"grad_norm": 2.296875,
"learning_rate": 1.1100833559778102e-05,
"loss": 0.7877589702606201,
"step": 7230,
"token_acc": 0.8112321994359528
},
{
"epoch": 0.48161514027706176,
"grad_norm": 2.203125,
"learning_rate": 1.1079417640801085e-05,
"loss": 0.733671760559082,
"step": 7240,
"token_acc": 0.8191814878561866
},
{
"epoch": 0.48228035455921237,
"grad_norm": 2.15625,
"learning_rate": 1.1057996711625936e-05,
"loss": 0.7811990261077881,
"step": 7250,
"token_acc": 0.8133242817036864
},
{
"epoch": 0.482945568841363,
"grad_norm": 2.140625,
"learning_rate": 1.1036570871679502e-05,
"loss": 0.7443314552307129,
"step": 7260,
"token_acc": 0.8209584526154076
},
{
"epoch": 0.4836107831235137,
"grad_norm": 2.4375,
"learning_rate": 1.1015140220411434e-05,
"loss": 0.7315757751464844,
"step": 7270,
"token_acc": 0.8229872997478741
},
{
"epoch": 0.4842759974056643,
"grad_norm": 2.328125,
"learning_rate": 1.0993704857293708e-05,
"loss": 0.774696683883667,
"step": 7280,
"token_acc": 0.8089383718057188
},
{
"epoch": 0.48494121168781495,
"grad_norm": 2.328125,
"learning_rate": 1.0972264881820177e-05,
"loss": 0.7230620384216309,
"step": 7290,
"token_acc": 0.8239979674378043
},
{
"epoch": 0.48560642596996556,
"grad_norm": 2.515625,
"learning_rate": 1.0950820393506098e-05,
"loss": 0.7940397739410401,
"step": 7300,
"token_acc": 0.8083860405239002
},
{
"epoch": 0.4862716402521162,
"grad_norm": 2.109375,
"learning_rate": 1.0929371491887672e-05,
"loss": 0.7397249698638916,
"step": 7310,
"token_acc": 0.8211771995877983
},
{
"epoch": 0.4869368545342668,
"grad_norm": 2.5,
"learning_rate": 1.0907918276521597e-05,
"loss": 0.73631272315979,
"step": 7320,
"token_acc": 0.8179431806908971
},
{
"epoch": 0.4876020688164175,
"grad_norm": 2.0625,
"learning_rate": 1.0886460846984577e-05,
"loss": 0.7318982601165771,
"step": 7330,
"token_acc": 0.8215699162319773
},
{
"epoch": 0.48826728309856815,
"grad_norm": 1.9765625,
"learning_rate": 1.0864999302872887e-05,
"loss": 0.7128865718841553,
"step": 7340,
"token_acc": 0.8235332114643016
},
{
"epoch": 0.48893249738071876,
"grad_norm": 2.21875,
"learning_rate": 1.0843533743801897e-05,
"loss": 0.7685551643371582,
"step": 7350,
"token_acc": 0.8107021279481372
},
{
"epoch": 0.4895977116628694,
"grad_norm": 2.09375,
"learning_rate": 1.0822064269405614e-05,
"loss": 0.7862318992614746,
"step": 7360,
"token_acc": 0.8098627665424707
},
{
"epoch": 0.49026292594502,
"grad_norm": 2.65625,
"learning_rate": 1.0800590979336223e-05,
"loss": 0.7437362194061279,
"step": 7370,
"token_acc": 0.8188003768449702
},
{
"epoch": 0.4909281402271707,
"grad_norm": 1.984375,
"learning_rate": 1.0779113973263601e-05,
"loss": 0.7623642921447754,
"step": 7380,
"token_acc": 0.8179193113405432
},
{
"epoch": 0.4915933545093213,
"grad_norm": 1.9296875,
"learning_rate": 1.0757633350874901e-05,
"loss": 0.7804345607757568,
"step": 7390,
"token_acc": 0.8099599479541473
},
{
"epoch": 0.49225856879147195,
"grad_norm": 1.984375,
"learning_rate": 1.073614921187404e-05,
"loss": 0.7388281345367431,
"step": 7400,
"token_acc": 0.8226934278492142
},
{
"epoch": 0.4929237830736226,
"grad_norm": 1.9609375,
"learning_rate": 1.071466165598126e-05,
"loss": 0.760498046875,
"step": 7410,
"token_acc": 0.8152170534443208
},
{
"epoch": 0.4935889973557732,
"grad_norm": 2.03125,
"learning_rate": 1.0693170782932676e-05,
"loss": 0.7665748596191406,
"step": 7420,
"token_acc": 0.8131596014385944
},
{
"epoch": 0.4942542116379239,
"grad_norm": 2.34375,
"learning_rate": 1.0671676692479784e-05,
"loss": 0.7521234035491944,
"step": 7430,
"token_acc": 0.8147526100771675
},
{
"epoch": 0.4949194259200745,
"grad_norm": 2.609375,
"learning_rate": 1.065017948438903e-05,
"loss": 0.7640196800231933,
"step": 7440,
"token_acc": 0.8109170561890047
},
{
"epoch": 0.49558464020222515,
"grad_norm": 2.265625,
"learning_rate": 1.0628679258441307e-05,
"loss": 0.7439335346221924,
"step": 7450,
"token_acc": 0.8207271789941549
},
{
"epoch": 0.49624985448437575,
"grad_norm": 1.890625,
"learning_rate": 1.0607176114431547e-05,
"loss": 0.7629217147827149,
"step": 7460,
"token_acc": 0.8168265325028862
},
{
"epoch": 0.4969150687665264,
"grad_norm": 2.3125,
"learning_rate": 1.0585670152168196e-05,
"loss": 0.7806074142456054,
"step": 7470,
"token_acc": 0.8122436620881389
},
{
"epoch": 0.4975802830486771,
"grad_norm": 3.0,
"learning_rate": 1.0564161471472802e-05,
"loss": 0.7082361698150634,
"step": 7480,
"token_acc": 0.8246280765264548
},
{
"epoch": 0.4982454973308277,
"grad_norm": 2.4375,
"learning_rate": 1.0542650172179523e-05,
"loss": 0.727830171585083,
"step": 7490,
"token_acc": 0.8229573061066379
},
{
"epoch": 0.49891071161297834,
"grad_norm": 2.0,
"learning_rate": 1.0521136354134668e-05,
"loss": 0.7432070732116699,
"step": 7500,
"token_acc": 0.8213223102954871
},
{
"epoch": 0.49957592589512895,
"grad_norm": 1.984375,
"learning_rate": 1.0499620117196248e-05,
"loss": 0.7435440063476563,
"step": 7510,
"token_acc": 0.8190738741517581
},
{
"epoch": 0.5002411401772796,
"grad_norm": 1.9609375,
"learning_rate": 1.0478101561233485e-05,
"loss": 0.7368072509765625,
"step": 7520,
"token_acc": 0.8181556754876981
},
{
"epoch": 0.5009063544594302,
"grad_norm": 1.96875,
"learning_rate": 1.0456580786126382e-05,
"loss": 0.7748026371002197,
"step": 7530,
"token_acc": 0.8107216374439756
},
{
"epoch": 0.5015715687415809,
"grad_norm": 2.203125,
"learning_rate": 1.043505789176523e-05,
"loss": 0.7599535465240479,
"step": 7540,
"token_acc": 0.8144607214414964
},
{
"epoch": 0.5022367830237315,
"grad_norm": 2.5625,
"learning_rate": 1.041353297805017e-05,
"loss": 0.7855841159820557,
"step": 7550,
"token_acc": 0.810567859446637
},
{
"epoch": 0.5029019973058821,
"grad_norm": 2.015625,
"learning_rate": 1.0392006144890696e-05,
"loss": 0.7034368515014648,
"step": 7560,
"token_acc": 0.8278685287807189
},
{
"epoch": 0.5035672115880327,
"grad_norm": 2.0,
"learning_rate": 1.0370477492205227e-05,
"loss": 0.7780855178833008,
"step": 7570,
"token_acc": 0.8109573886824016
},
{
"epoch": 0.5042324258701835,
"grad_norm": 2.1875,
"learning_rate": 1.0348947119920628e-05,
"loss": 0.7588325500488281,
"step": 7580,
"token_acc": 0.815200252286345
},
{
"epoch": 0.5048976401523341,
"grad_norm": 2.203125,
"learning_rate": 1.032741512797173e-05,
"loss": 0.8076597213745117,
"step": 7590,
"token_acc": 0.8048396815832038
},
{
"epoch": 0.5055628544344847,
"grad_norm": 2.296875,
"learning_rate": 1.0305881616300903e-05,
"loss": 0.7575117111206054,
"step": 7600,
"token_acc": 0.8191114222767476
},
{
"epoch": 0.5062280687166354,
"grad_norm": 1.96875,
"learning_rate": 1.0284346684857554e-05,
"loss": 0.7690659523010254,
"step": 7610,
"token_acc": 0.8089141967595912
},
{
"epoch": 0.506893282998786,
"grad_norm": 2.484375,
"learning_rate": 1.0262810433597692e-05,
"loss": 0.7724231243133545,
"step": 7620,
"token_acc": 0.8145517801562714
},
{
"epoch": 0.5075584972809366,
"grad_norm": 2.0625,
"learning_rate": 1.0241272962483441e-05,
"loss": 0.7463849067687989,
"step": 7630,
"token_acc": 0.8154514918000395
},
{
"epoch": 0.5082237115630872,
"grad_norm": 2.640625,
"learning_rate": 1.0219734371482595e-05,
"loss": 0.8022209167480469,
"step": 7640,
"token_acc": 0.8094209514478069
},
{
"epoch": 0.5088889258452379,
"grad_norm": 2.140625,
"learning_rate": 1.0198194760568144e-05,
"loss": 0.7333521366119384,
"step": 7650,
"token_acc": 0.8202052912688934
},
{
"epoch": 0.5095541401273885,
"grad_norm": 2.609375,
"learning_rate": 1.0176654229717806e-05,
"loss": 0.7575548648834228,
"step": 7660,
"token_acc": 0.8145545699961435
},
{
"epoch": 0.5102193544095391,
"grad_norm": 2.15625,
"learning_rate": 1.0155112878913587e-05,
"loss": 0.779090690612793,
"step": 7670,
"token_acc": 0.8112764403454251
},
{
"epoch": 0.5108845686916899,
"grad_norm": 2.8125,
"learning_rate": 1.013357080814127e-05,
"loss": 0.7409786701202392,
"step": 7680,
"token_acc": 0.8206043633804468
},
{
"epoch": 0.5115497829738405,
"grad_norm": 2.28125,
"learning_rate": 1.0112028117390009e-05,
"loss": 0.7316087245941162,
"step": 7690,
"token_acc": 0.8220667565745111
},
{
"epoch": 0.5122149972559911,
"grad_norm": 2.53125,
"learning_rate": 1.009048490665182e-05,
"loss": 0.7349381923675538,
"step": 7700,
"token_acc": 0.8208499923910186
},
{
"epoch": 0.5128802115381417,
"grad_norm": 4.4375,
"learning_rate": 1.006894127592113e-05,
"loss": 0.7560619354248047,
"step": 7710,
"token_acc": 0.816128388542658
},
{
"epoch": 0.5135454258202924,
"grad_norm": 2.34375,
"learning_rate": 1.0047397325194326e-05,
"loss": 0.7384578227996826,
"step": 7720,
"token_acc": 0.8183594821438367
},
{
"epoch": 0.514210640102443,
"grad_norm": 2.171875,
"learning_rate": 1.0025853154469272e-05,
"loss": 0.7836869716644287,
"step": 7730,
"token_acc": 0.8136316654397275
},
{
"epoch": 0.5148758543845936,
"grad_norm": 1.9921875,
"learning_rate": 1.0004308863744862e-05,
"loss": 0.7435479640960694,
"step": 7740,
"token_acc": 0.8179534416345671
},
{
"epoch": 0.5155410686667443,
"grad_norm": 2.203125,
"learning_rate": 9.98276455302053e-06,
"loss": 0.7894378185272217,
"step": 7750,
"token_acc": 0.8100106333442215
},
{
"epoch": 0.5162062829488949,
"grad_norm": 2.3125,
"learning_rate": 9.961220322295828e-06,
"loss": 0.7438347339630127,
"step": 7760,
"token_acc": 0.8194342884869028
},
{
"epoch": 0.5168714972310455,
"grad_norm": 2.15625,
"learning_rate": 9.939676271569912e-06,
"loss": 0.7570628643035888,
"step": 7770,
"token_acc": 0.8176585886150032
},
{
"epoch": 0.5175367115131961,
"grad_norm": 2.171875,
"learning_rate": 9.91813250084112e-06,
"loss": 0.8156988143920898,
"step": 7780,
"token_acc": 0.8080623721529275
},
{
"epoch": 0.5182019257953469,
"grad_norm": 2.15625,
"learning_rate": 9.896589110106476e-06,
"loss": 0.7282536029815674,
"step": 7790,
"token_acc": 0.820045506429106
},
{
"epoch": 0.5188671400774975,
"grad_norm": 2.03125,
"learning_rate": 9.875046199361254e-06,
"loss": 0.7938862800598144,
"step": 7800,
"token_acc": 0.8075287570300406
},
{
"epoch": 0.5195323543596481,
"grad_norm": 2.109375,
"learning_rate": 9.853503868598496e-06,
"loss": 0.7699375629425049,
"step": 7810,
"token_acc": 0.8117042886161416
},
{
"epoch": 0.5201975686417988,
"grad_norm": 2.09375,
"learning_rate": 9.831962217808543e-06,
"loss": 0.7350882053375244,
"step": 7820,
"token_acc": 0.8208263191501712
},
{
"epoch": 0.5208627829239494,
"grad_norm": 2.109375,
"learning_rate": 9.810421346978591e-06,
"loss": 0.7731838226318359,
"step": 7830,
"token_acc": 0.8128620331021372
},
{
"epoch": 0.5215279972061,
"grad_norm": 2.0625,
"learning_rate": 9.788881356092206e-06,
"loss": 0.8244364738464356,
"step": 7840,
"token_acc": 0.7998688098803387
},
{
"epoch": 0.5221932114882507,
"grad_norm": 1.640625,
"learning_rate": 9.767342345128884e-06,
"loss": 0.7273937225341797,
"step": 7850,
"token_acc": 0.8233665284227779
},
{
"epoch": 0.5228584257704013,
"grad_norm": 1.859375,
"learning_rate": 9.745804414063559e-06,
"loss": 0.715303611755371,
"step": 7860,
"token_acc": 0.8273542282336894
},
{
"epoch": 0.5235236400525519,
"grad_norm": 2.1875,
"learning_rate": 9.724267662866159e-06,
"loss": 0.7355597496032715,
"step": 7870,
"token_acc": 0.8231373628053441
},
{
"epoch": 0.5241888543347025,
"grad_norm": 1.7421875,
"learning_rate": 9.702732191501129e-06,
"loss": 0.7122546672821045,
"step": 7880,
"token_acc": 0.8278048989992985
},
{
"epoch": 0.5248540686168532,
"grad_norm": 2.046875,
"learning_rate": 9.681198099926983e-06,
"loss": 0.7509305000305175,
"step": 7890,
"token_acc": 0.8196356385884409
},
{
"epoch": 0.5255192828990038,
"grad_norm": 2.171875,
"learning_rate": 9.659665488095828e-06,
"loss": 0.754732084274292,
"step": 7900,
"token_acc": 0.8186519614846138
},
{
"epoch": 0.5261844971811545,
"grad_norm": 2.171875,
"learning_rate": 9.638134455952897e-06,
"loss": 0.7339933395385743,
"step": 7910,
"token_acc": 0.8193130948925182
},
{
"epoch": 0.5268497114633052,
"grad_norm": 2.078125,
"learning_rate": 9.616605103436098e-06,
"loss": 0.7608344554901123,
"step": 7920,
"token_acc": 0.815434292589161
},
{
"epoch": 0.5275149257454558,
"grad_norm": 2.078125,
"learning_rate": 9.595077530475531e-06,
"loss": 0.7733577728271485,
"step": 7930,
"token_acc": 0.8104900023445089
},
{
"epoch": 0.5281801400276064,
"grad_norm": 2.0625,
"learning_rate": 9.573551836993052e-06,
"loss": 0.7812899589538574,
"step": 7940,
"token_acc": 0.8110160330298649
},
{
"epoch": 0.528845354309757,
"grad_norm": 2.1875,
"learning_rate": 9.552028122901788e-06,
"loss": 0.7332124710083008,
"step": 7950,
"token_acc": 0.8182291743092341
},
{
"epoch": 0.5295105685919077,
"grad_norm": 2.453125,
"learning_rate": 9.53050648810567e-06,
"loss": 0.773286771774292,
"step": 7960,
"token_acc": 0.8139986060314289
},
{
"epoch": 0.5301757828740583,
"grad_norm": 2.125,
"learning_rate": 9.508987032498987e-06,
"loss": 0.7026595115661621,
"step": 7970,
"token_acc": 0.8281366400736838
},
{
"epoch": 0.5308409971562089,
"grad_norm": 2.0625,
"learning_rate": 9.487469855965903e-06,
"loss": 0.7206508636474609,
"step": 7980,
"token_acc": 0.8268501107490113
},
{
"epoch": 0.5315062114383596,
"grad_norm": 2.03125,
"learning_rate": 9.465955058380024e-06,
"loss": 0.7739372730255127,
"step": 7990,
"token_acc": 0.8123664082820427
},
{
"epoch": 0.5321714257205102,
"grad_norm": 1.84375,
"learning_rate": 9.444442739603891e-06,
"loss": 0.7480909347534179,
"step": 8000,
"token_acc": 0.8190545204083829
},
{
"epoch": 0.5328366400026608,
"grad_norm": 2.25,
"learning_rate": 9.422932999488556e-06,
"loss": 0.7789316654205323,
"step": 8010,
"token_acc": 0.8093183838107609
},
{
"epoch": 0.5335018542848114,
"grad_norm": 6.28125,
"learning_rate": 9.401425937873083e-06,
"loss": 0.78959059715271,
"step": 8020,
"token_acc": 0.8069388095370422
},
{
"epoch": 0.5341670685669622,
"grad_norm": 1.9765625,
"learning_rate": 9.379921654584128e-06,
"loss": 0.7359909057617188,
"step": 8030,
"token_acc": 0.8219491461859639
},
{
"epoch": 0.5348322828491128,
"grad_norm": 2.25,
"learning_rate": 9.358420249435434e-06,
"loss": 0.7542747497558594,
"step": 8040,
"token_acc": 0.8178080894193426
},
{
"epoch": 0.5354974971312634,
"grad_norm": 2.234375,
"learning_rate": 9.336921822227389e-06,
"loss": 0.6943217754364014,
"step": 8050,
"token_acc": 0.8304381909695002
},
{
"epoch": 0.5361627114134141,
"grad_norm": 2.234375,
"learning_rate": 9.315426472746559e-06,
"loss": 0.7514155864715576,
"step": 8060,
"token_acc": 0.8186275991295938
},
{
"epoch": 0.5368279256955647,
"grad_norm": 2.453125,
"learning_rate": 9.293934300765224e-06,
"loss": 0.7083795070648193,
"step": 8070,
"token_acc": 0.8259187915426257
},
{
"epoch": 0.5374931399777153,
"grad_norm": 1.8828125,
"learning_rate": 9.272445406040918e-06,
"loss": 0.7359787940979003,
"step": 8080,
"token_acc": 0.8170696001338464
},
{
"epoch": 0.5381583542598659,
"grad_norm": 2.28125,
"learning_rate": 9.25095988831596e-06,
"loss": 0.7352677822113037,
"step": 8090,
"token_acc": 0.8227382890215229
},
{
"epoch": 0.5388235685420166,
"grad_norm": 1.9609375,
"learning_rate": 9.229477847317e-06,
"loss": 0.7010772228240967,
"step": 8100,
"token_acc": 0.8239627114207181
},
{
"epoch": 0.5394887828241672,
"grad_norm": 2.4375,
"learning_rate": 9.20799938275454e-06,
"loss": 0.7657524585723877,
"step": 8110,
"token_acc": 0.8155856959953991
},
{
"epoch": 0.5401539971063178,
"grad_norm": 2.0625,
"learning_rate": 9.186524594322492e-06,
"loss": 0.7284685134887695,
"step": 8120,
"token_acc": 0.8206250043821824
},
{
"epoch": 0.5408192113884686,
"grad_norm": 2.03125,
"learning_rate": 9.165053581697703e-06,
"loss": 0.7794826030731201,
"step": 8130,
"token_acc": 0.8156469273470086
},
{
"epoch": 0.5414844256706192,
"grad_norm": 1.859375,
"learning_rate": 9.143586444539488e-06,
"loss": 0.801294994354248,
"step": 8140,
"token_acc": 0.8071282071127278
},
{
"epoch": 0.5421496399527698,
"grad_norm": 2.296875,
"learning_rate": 9.12212328248918e-06,
"loss": 0.7626471996307373,
"step": 8150,
"token_acc": 0.8150197753270231
},
{
"epoch": 0.5428148542349204,
"grad_norm": 2.5625,
"learning_rate": 9.100664195169661e-06,
"loss": 0.7458100318908691,
"step": 8160,
"token_acc": 0.8214404116219549
},
{
"epoch": 0.5434800685170711,
"grad_norm": 2.328125,
"learning_rate": 9.079209282184894e-06,
"loss": 0.7515042781829834,
"step": 8170,
"token_acc": 0.8173397365931747
},
{
"epoch": 0.5441452827992217,
"grad_norm": 2.15625,
"learning_rate": 9.057758643119476e-06,
"loss": 0.7060615062713623,
"step": 8180,
"token_acc": 0.824671425712189
},
{
"epoch": 0.5448104970813723,
"grad_norm": 2.25,
"learning_rate": 9.036312377538156e-06,
"loss": 0.7903416633605957,
"step": 8190,
"token_acc": 0.8094326392488034
},
{
"epoch": 0.545475711363523,
"grad_norm": 2.15625,
"learning_rate": 9.014870584985392e-06,
"loss": 0.7519017219543457,
"step": 8200,
"token_acc": 0.8162207836646904
},
{
"epoch": 0.5461409256456736,
"grad_norm": 2.109375,
"learning_rate": 8.993433364984869e-06,
"loss": 0.7557108402252197,
"step": 8210,
"token_acc": 0.8128496940549035
},
{
"epoch": 0.5468061399278242,
"grad_norm": 2.296875,
"learning_rate": 8.972000817039067e-06,
"loss": 0.7452522277832031,
"step": 8220,
"token_acc": 0.8189896563590113
},
{
"epoch": 0.5474713542099748,
"grad_norm": 2.09375,
"learning_rate": 8.95057304062876e-06,
"loss": 0.7427500724792481,
"step": 8230,
"token_acc": 0.8185099846390169
},
{
"epoch": 0.5481365684921256,
"grad_norm": 2.46875,
"learning_rate": 8.92915013521259e-06,
"loss": 0.7184990882873535,
"step": 8240,
"token_acc": 0.823500494952828
},
{
"epoch": 0.5488017827742762,
"grad_norm": 1.796875,
"learning_rate": 8.907732200226575e-06,
"loss": 0.7254830360412597,
"step": 8250,
"token_acc": 0.8228620174877372
},
{
"epoch": 0.5494669970564268,
"grad_norm": 2.25,
"learning_rate": 8.886319335083674e-06,
"loss": 0.7317332267761231,
"step": 8260,
"token_acc": 0.8212584387877371
},
{
"epoch": 0.5501322113385775,
"grad_norm": 2.5625,
"learning_rate": 8.864911639173314e-06,
"loss": 0.699599313735962,
"step": 8270,
"token_acc": 0.8307829218607691
},
{
"epoch": 0.5507974256207281,
"grad_norm": 2.046875,
"learning_rate": 8.843509211860922e-06,
"loss": 0.7836018085479737,
"step": 8280,
"token_acc": 0.8090968651635784
},
{
"epoch": 0.5514626399028787,
"grad_norm": 2.234375,
"learning_rate": 8.822112152487475e-06,
"loss": 0.7782171249389649,
"step": 8290,
"token_acc": 0.8130110936113728
},
{
"epoch": 0.5521278541850293,
"grad_norm": 2.3125,
"learning_rate": 8.800720560369029e-06,
"loss": 0.7697295188903809,
"step": 8300,
"token_acc": 0.8131939046389862
},
{
"epoch": 0.55279306846718,
"grad_norm": 2.5625,
"learning_rate": 8.779334534796268e-06,
"loss": 0.7536793231964112,
"step": 8310,
"token_acc": 0.8153471255221802
},
{
"epoch": 0.5534582827493306,
"grad_norm": 2.59375,
"learning_rate": 8.757954175034043e-06,
"loss": 0.7885191917419434,
"step": 8320,
"token_acc": 0.8076694918143449
},
{
"epoch": 0.5541234970314812,
"grad_norm": 1.890625,
"learning_rate": 8.736579580320895e-06,
"loss": 0.7212279319763184,
"step": 8330,
"token_acc": 0.823265055453199
},
{
"epoch": 0.5547887113136319,
"grad_norm": 2.015625,
"learning_rate": 8.715210849868617e-06,
"loss": 0.7336255073547363,
"step": 8340,
"token_acc": 0.8192515673436479
},
{
"epoch": 0.5554539255957825,
"grad_norm": 2.0625,
"learning_rate": 8.693848082861772e-06,
"loss": 0.7297329425811767,
"step": 8350,
"token_acc": 0.8222033898305084
},
{
"epoch": 0.5561191398779332,
"grad_norm": 2.1875,
"learning_rate": 8.672491378457257e-06,
"loss": 0.7803820133209228,
"step": 8360,
"token_acc": 0.8126082251082251
},
{
"epoch": 0.5567843541600839,
"grad_norm": 2.296875,
"learning_rate": 8.651140835783816e-06,
"loss": 0.7560444831848144,
"step": 8370,
"token_acc": 0.8160776687672715
},
{
"epoch": 0.5574495684422345,
"grad_norm": 2.65625,
"learning_rate": 8.629796553941603e-06,
"loss": 0.770097303390503,
"step": 8380,
"token_acc": 0.8138637620973825
},
{
"epoch": 0.5581147827243851,
"grad_norm": 2.0,
"learning_rate": 8.6084586320017e-06,
"loss": 0.7397252082824707,
"step": 8390,
"token_acc": 0.8179836365593713
},
{
"epoch": 0.5587799970065357,
"grad_norm": 2.578125,
"learning_rate": 8.587127169005679e-06,
"loss": 0.7582157611846924,
"step": 8400,
"token_acc": 0.8182262037742549
},
{
"epoch": 0.5594452112886864,
"grad_norm": 2.140625,
"learning_rate": 8.56580226396513e-06,
"loss": 0.7597359657287598,
"step": 8410,
"token_acc": 0.8161944000672665
},
{
"epoch": 0.560110425570837,
"grad_norm": 2.484375,
"learning_rate": 8.544484015861204e-06,
"loss": 0.7027297496795655,
"step": 8420,
"token_acc": 0.830217800175159
},
{
"epoch": 0.5607756398529876,
"grad_norm": 2.671875,
"learning_rate": 8.523172523644152e-06,
"loss": 0.7605814933776855,
"step": 8430,
"token_acc": 0.8153736502619293
},
{
"epoch": 0.5614408541351383,
"grad_norm": 2.0,
"learning_rate": 8.501867886232865e-06,
"loss": 0.7516291618347168,
"step": 8440,
"token_acc": 0.8153073344879528
},
{
"epoch": 0.5621060684172889,
"grad_norm": 2.078125,
"learning_rate": 8.480570202514418e-06,
"loss": 0.83431396484375,
"step": 8450,
"token_acc": 0.7981219736919488
},
{
"epoch": 0.5627712826994395,
"grad_norm": 2.578125,
"learning_rate": 8.459279571343618e-06,
"loss": 0.8052127838134766,
"step": 8460,
"token_acc": 0.804976276387192
},
{
"epoch": 0.5634364969815902,
"grad_norm": 1.9375,
"learning_rate": 8.437996091542527e-06,
"loss": 0.7889942646026611,
"step": 8470,
"token_acc": 0.8104782132972903
},
{
"epoch": 0.5641017112637409,
"grad_norm": 2.234375,
"learning_rate": 8.416719861900014e-06,
"loss": 0.7532257080078125,
"step": 8480,
"token_acc": 0.8163232618333718
},
{
"epoch": 0.5647669255458915,
"grad_norm": 2.015625,
"learning_rate": 8.395450981171302e-06,
"loss": 0.7840494155883789,
"step": 8490,
"token_acc": 0.8108454997593454
},
{
"epoch": 0.5654321398280421,
"grad_norm": 2.0625,
"learning_rate": 8.374189548077497e-06,
"loss": 0.7142457962036133,
"step": 8500,
"token_acc": 0.8251636506356793
},
{
"epoch": 0.5660973541101928,
"grad_norm": 2.296875,
"learning_rate": 8.35293566130514e-06,
"loss": 0.769153642654419,
"step": 8510,
"token_acc": 0.8142225482123211
},
{
"epoch": 0.5667625683923434,
"grad_norm": 2.046875,
"learning_rate": 8.331689419505749e-06,
"loss": 0.7834098815917969,
"step": 8520,
"token_acc": 0.8141102921536496
},
{
"epoch": 0.567427782674494,
"grad_norm": 2.109375,
"learning_rate": 8.310450921295347e-06,
"loss": 0.7740649223327637,
"step": 8530,
"token_acc": 0.810998761865456
},
{
"epoch": 0.5680929969566446,
"grad_norm": 2.234375,
"learning_rate": 8.28922026525402e-06,
"loss": 0.768693494796753,
"step": 8540,
"token_acc": 0.8152811816917268
},
{
"epoch": 0.5687582112387953,
"grad_norm": 1.96875,
"learning_rate": 8.267997549925461e-06,
"loss": 0.7162261009216309,
"step": 8550,
"token_acc": 0.8246541624267759
},
{
"epoch": 0.5694234255209459,
"grad_norm": 2.125,
"learning_rate": 8.246782873816493e-06,
"loss": 0.764475965499878,
"step": 8560,
"token_acc": 0.8173957921405927
},
{
"epoch": 0.5700886398030965,
"grad_norm": 2.546875,
"learning_rate": 8.225576335396632e-06,
"loss": 0.7779558181762696,
"step": 8570,
"token_acc": 0.8089688816168227
},
{
"epoch": 0.5707538540852473,
"grad_norm": 2.25,
"learning_rate": 8.20437803309762e-06,
"loss": 0.735498046875,
"step": 8580,
"token_acc": 0.8221733369354071
},
{
"epoch": 0.5714190683673979,
"grad_norm": 1.96875,
"learning_rate": 8.183188065312966e-06,
"loss": 0.7885283470153809,
"step": 8590,
"token_acc": 0.8103431669326876
},
{
"epoch": 0.5720842826495485,
"grad_norm": 2.375,
"learning_rate": 8.162006530397507e-06,
"loss": 0.7489984035491943,
"step": 8600,
"token_acc": 0.8215071913352323
},
{
"epoch": 0.5727494969316991,
"grad_norm": 2.109375,
"learning_rate": 8.14083352666693e-06,
"loss": 0.7365327835083008,
"step": 8610,
"token_acc": 0.8219993450664886
},
{
"epoch": 0.5734147112138498,
"grad_norm": 2.25,
"learning_rate": 8.119669152397315e-06,
"loss": 0.7148809432983398,
"step": 8620,
"token_acc": 0.8269019529522532
},
{
"epoch": 0.5740799254960004,
"grad_norm": 2.3125,
"learning_rate": 8.098513505824706e-06,
"loss": 0.776188325881958,
"step": 8630,
"token_acc": 0.8123610885238792
},
{
"epoch": 0.574745139778151,
"grad_norm": 2.015625,
"learning_rate": 8.077366685144617e-06,
"loss": 0.8059940338134766,
"step": 8640,
"token_acc": 0.805927268384858
},
{
"epoch": 0.5754103540603017,
"grad_norm": 1.734375,
"learning_rate": 8.056228788511615e-06,
"loss": 0.7915565967559814,
"step": 8650,
"token_acc": 0.810123693459309
},
{
"epoch": 0.5760755683424523,
"grad_norm": 2.4375,
"learning_rate": 8.035099914038835e-06,
"loss": 0.7729099273681641,
"step": 8660,
"token_acc": 0.811916266358629
},
{
"epoch": 0.5767407826246029,
"grad_norm": 2.234375,
"learning_rate": 8.013980159797533e-06,
"loss": 0.7344971656799316,
"step": 8670,
"token_acc": 0.8191126279863481
},
{
"epoch": 0.5774059969067535,
"grad_norm": 1.9375,
"learning_rate": 7.992869623816636e-06,
"loss": 0.7631989002227784,
"step": 8680,
"token_acc": 0.8157645162900478
},
{
"epoch": 0.5780712111889043,
"grad_norm": 2.21875,
"learning_rate": 7.97176840408229e-06,
"loss": 0.7706439018249511,
"step": 8690,
"token_acc": 0.8129147332381141
},
{
"epoch": 0.5787364254710549,
"grad_norm": 2.390625,
"learning_rate": 7.950676598537386e-06,
"loss": 0.7392477512359619,
"step": 8700,
"token_acc": 0.816962490855045
},
{
"epoch": 0.5794016397532055,
"grad_norm": 2.265625,
"learning_rate": 7.929594305081128e-06,
"loss": 0.7533292770385742,
"step": 8710,
"token_acc": 0.818924378787784
},
{
"epoch": 0.5800668540353562,
"grad_norm": 2.203125,
"learning_rate": 7.908521621568568e-06,
"loss": 0.7768455028533936,
"step": 8720,
"token_acc": 0.8154409878232496
},
{
"epoch": 0.5807320683175068,
"grad_norm": 2.1875,
"learning_rate": 7.887458645810144e-06,
"loss": 0.7632770538330078,
"step": 8730,
"token_acc": 0.818047831469727
},
{
"epoch": 0.5813972825996574,
"grad_norm": 2.203125,
"learning_rate": 7.866405475571251e-06,
"loss": 0.7435222625732422,
"step": 8740,
"token_acc": 0.8208954149053383
},
{
"epoch": 0.582062496881808,
"grad_norm": 2.265625,
"learning_rate": 7.845362208571757e-06,
"loss": 0.7663277626037598,
"step": 8750,
"token_acc": 0.8179199772985244
},
{
"epoch": 0.5827277111639587,
"grad_norm": 1.859375,
"learning_rate": 7.824328942485567e-06,
"loss": 0.7699844837188721,
"step": 8760,
"token_acc": 0.8128193030936173
},
{
"epoch": 0.5833929254461093,
"grad_norm": 2.015625,
"learning_rate": 7.80330577494017e-06,
"loss": 0.7739941120147705,
"step": 8770,
"token_acc": 0.8128652182796431
},
{
"epoch": 0.5840581397282599,
"grad_norm": 2.421875,
"learning_rate": 7.782292803516172e-06,
"loss": 0.7097895622253418,
"step": 8780,
"token_acc": 0.8257698910682001
},
{
"epoch": 0.5847233540104106,
"grad_norm": 2.4375,
"learning_rate": 7.761290125746866e-06,
"loss": 0.6950130462646484,
"step": 8790,
"token_acc": 0.8283637794848131
},
{
"epoch": 0.5853885682925613,
"grad_norm": 2.359375,
"learning_rate": 7.740297839117763e-06,
"loss": 0.706986951828003,
"step": 8800,
"token_acc": 0.8234576261096683
},
{
"epoch": 0.5860537825747119,
"grad_norm": 2.453125,
"learning_rate": 7.71931604106613e-06,
"loss": 0.7940927028656006,
"step": 8810,
"token_acc": 0.8098673711595972
},
{
"epoch": 0.5867189968568625,
"grad_norm": 1.953125,
"learning_rate": 7.698344828980569e-06,
"loss": 0.704944658279419,
"step": 8820,
"token_acc": 0.8281979458450047
},
{
"epoch": 0.5873842111390132,
"grad_norm": 1.875,
"learning_rate": 7.677384300200528e-06,
"loss": 0.8170463562011718,
"step": 8830,
"token_acc": 0.801208413001912
},
{
"epoch": 0.5880494254211638,
"grad_norm": 2.265625,
"learning_rate": 7.656434552015888e-06,
"loss": 0.7666790962219239,
"step": 8840,
"token_acc": 0.8149460429324662
},
{
"epoch": 0.5887146397033144,
"grad_norm": 2.453125,
"learning_rate": 7.635495681666474e-06,
"loss": 0.79071946144104,
"step": 8850,
"token_acc": 0.8102691540373106
},
{
"epoch": 0.5893798539854651,
"grad_norm": 1.875,
"learning_rate": 7.614567786341631e-06,
"loss": 0.7400320529937744,
"step": 8860,
"token_acc": 0.8201200407685629
},
{
"epoch": 0.5900450682676157,
"grad_norm": 2.296875,
"learning_rate": 7.5936509631797505e-06,
"loss": 0.7384172439575195,
"step": 8870,
"token_acc": 0.8219535341464272
},
{
"epoch": 0.5907102825497663,
"grad_norm": 1.9609375,
"learning_rate": 7.572745309267849e-06,
"loss": 0.7045816421508789,
"step": 8880,
"token_acc": 0.827177484095984
},
{
"epoch": 0.591375496831917,
"grad_norm": 2.265625,
"learning_rate": 7.5518509216410885e-06,
"loss": 0.7428847789764405,
"step": 8890,
"token_acc": 0.817503874185406
},
{
"epoch": 0.5920407111140676,
"grad_norm": 2.265625,
"learning_rate": 7.5309678972823376e-06,
"loss": 0.7571064949035644,
"step": 8900,
"token_acc": 0.8163807615788082
},
{
"epoch": 0.5927059253962182,
"grad_norm": 1.984375,
"learning_rate": 7.510096333121727e-06,
"loss": 0.7353061676025391,
"step": 8910,
"token_acc": 0.8193856190058907
},
{
"epoch": 0.5933711396783689,
"grad_norm": 2.21875,
"learning_rate": 7.4892363260361845e-06,
"loss": 0.7290041446685791,
"step": 8920,
"token_acc": 0.8203972327605445
},
{
"epoch": 0.5940363539605196,
"grad_norm": 1.96875,
"learning_rate": 7.468387972849009e-06,
"loss": 0.7212344646453858,
"step": 8930,
"token_acc": 0.8269419923167812
},
{
"epoch": 0.5947015682426702,
"grad_norm": 2.03125,
"learning_rate": 7.447551370329398e-06,
"loss": 0.6939002990722656,
"step": 8940,
"token_acc": 0.8309890549099183
},
{
"epoch": 0.5953667825248208,
"grad_norm": 2.328125,
"learning_rate": 7.426726615192005e-06,
"loss": 0.8047267913818359,
"step": 8950,
"token_acc": 0.8107005163123125
},
{
"epoch": 0.5960319968069715,
"grad_norm": 2.0625,
"learning_rate": 7.4059138040964984e-06,
"loss": 0.7824573040008544,
"step": 8960,
"token_acc": 0.8097771489211177
},
{
"epoch": 0.5966972110891221,
"grad_norm": 2.0625,
"learning_rate": 7.385113033647104e-06,
"loss": 0.7517246723175048,
"step": 8970,
"token_acc": 0.8148750213891778
},
{
"epoch": 0.5973624253712727,
"grad_norm": 1.75,
"learning_rate": 7.364324400392169e-06,
"loss": 0.7484414100646972,
"step": 8980,
"token_acc": 0.8171964764458062
},
{
"epoch": 0.5980276396534233,
"grad_norm": 2.21875,
"learning_rate": 7.343548000823689e-06,
"loss": 0.7529750347137452,
"step": 8990,
"token_acc": 0.8187819580696473
},
{
"epoch": 0.598692853935574,
"grad_norm": 2.453125,
"learning_rate": 7.322783931376891e-06,
"loss": 0.7434202194213867,
"step": 9000,
"token_acc": 0.81969329112757
},
{
"epoch": 0.5993580682177246,
"grad_norm": 1.875,
"learning_rate": 7.3020322884297565e-06,
"loss": 0.7709948539733886,
"step": 9010,
"token_acc": 0.8138398367634834
},
{
"epoch": 0.6000232824998752,
"grad_norm": 2.171875,
"learning_rate": 7.281293168302606e-06,
"loss": 0.7577837944030762,
"step": 9020,
"token_acc": 0.8176888333181138
},
{
"epoch": 0.600688496782026,
"grad_norm": 2.375,
"learning_rate": 7.26056666725762e-06,
"loss": 0.7843700885772705,
"step": 9030,
"token_acc": 0.8083504885246111
},
{
"epoch": 0.6013537110641766,
"grad_norm": 2.515625,
"learning_rate": 7.239852881498411e-06,
"loss": 0.7493436813354493,
"step": 9040,
"token_acc": 0.8175673912476188
},
{
"epoch": 0.6020189253463272,
"grad_norm": 2.671875,
"learning_rate": 7.219151907169575e-06,
"loss": 0.7772694110870362,
"step": 9050,
"token_acc": 0.8153581996858218
},
{
"epoch": 0.6026841396284778,
"grad_norm": 2.15625,
"learning_rate": 7.198463840356236e-06,
"loss": 0.7057768821716308,
"step": 9060,
"token_acc": 0.8241155757396255
},
{
"epoch": 0.6033493539106285,
"grad_norm": 2.15625,
"learning_rate": 7.177788777083616e-06,
"loss": 0.7850950241088868,
"step": 9070,
"token_acc": 0.805432368360044
},
{
"epoch": 0.6040145681927791,
"grad_norm": 2.046875,
"learning_rate": 7.157126813316577e-06,
"loss": 0.7643085479736328,
"step": 9080,
"token_acc": 0.8156177983861422
},
{
"epoch": 0.6046797824749297,
"grad_norm": 2.734375,
"learning_rate": 7.136478044959176e-06,
"loss": 0.7927929878234863,
"step": 9090,
"token_acc": 0.8081547203668628
},
{
"epoch": 0.6053449967570804,
"grad_norm": 2.203125,
"learning_rate": 7.115842567854219e-06,
"loss": 0.7288604736328125,
"step": 9100,
"token_acc": 0.8196167014732415
},
{
"epoch": 0.606010211039231,
"grad_norm": 2.203125,
"learning_rate": 7.095220477782827e-06,
"loss": 0.7853884220123291,
"step": 9110,
"token_acc": 0.8126403927868533
},
{
"epoch": 0.6066754253213816,
"grad_norm": 2.71875,
"learning_rate": 7.074611870463988e-06,
"loss": 0.7841662883758544,
"step": 9120,
"token_acc": 0.8122075614491132
},
{
"epoch": 0.6073406396035322,
"grad_norm": 2.4375,
"learning_rate": 7.054016841554094e-06,
"loss": 0.7302846908569336,
"step": 9130,
"token_acc": 0.8217169118907981
},
{
"epoch": 0.608005853885683,
"grad_norm": 2.25,
"learning_rate": 7.033435486646526e-06,
"loss": 0.7206448078155517,
"step": 9140,
"token_acc": 0.8238708177763573
},
{
"epoch": 0.6086710681678336,
"grad_norm": 1.8984375,
"learning_rate": 7.012867901271185e-06,
"loss": 0.7465287208557129,
"step": 9150,
"token_acc": 0.8188363851985713
},
{
"epoch": 0.6093362824499842,
"grad_norm": 2.09375,
"learning_rate": 6.9923141808940654e-06,
"loss": 0.6879082202911377,
"step": 9160,
"token_acc": 0.8299439909891839
},
{
"epoch": 0.6100014967321349,
"grad_norm": 2.359375,
"learning_rate": 6.971774420916811e-06,
"loss": 0.7137819766998291,
"step": 9170,
"token_acc": 0.8251690037747764
},
{
"epoch": 0.6106667110142855,
"grad_norm": 2.09375,
"learning_rate": 6.951248716676257e-06,
"loss": 0.7337537288665772,
"step": 9180,
"token_acc": 0.8225165562913908
},
{
"epoch": 0.6113319252964361,
"grad_norm": 1.921875,
"learning_rate": 6.930737163444008e-06,
"loss": 0.7707431793212891,
"step": 9190,
"token_acc": 0.8144501376567758
},
{
"epoch": 0.6119971395785867,
"grad_norm": 2.234375,
"learning_rate": 6.910239856425969e-06,
"loss": 0.7895948886871338,
"step": 9200,
"token_acc": 0.8078566665305733
},
{
"epoch": 0.6126623538607374,
"grad_norm": 2.078125,
"learning_rate": 6.889756890761945e-06,
"loss": 0.7541385650634765,
"step": 9210,
"token_acc": 0.8151030438906613
},
{
"epoch": 0.613327568142888,
"grad_norm": 2.203125,
"learning_rate": 6.8692883615251546e-06,
"loss": 0.7429880142211914,
"step": 9220,
"token_acc": 0.8185094665493532
},
{
"epoch": 0.6139927824250386,
"grad_norm": 1.9765625,
"learning_rate": 6.848834363721819e-06,
"loss": 0.7507602214813233,
"step": 9230,
"token_acc": 0.815431653949504
},
{
"epoch": 0.6146579967071893,
"grad_norm": 2.390625,
"learning_rate": 6.828394992290701e-06,
"loss": 0.7422272682189941,
"step": 9240,
"token_acc": 0.817717109641608
},
{
"epoch": 0.61532321098934,
"grad_norm": 2.625,
"learning_rate": 6.807970342102681e-06,
"loss": 0.7246967315673828,
"step": 9250,
"token_acc": 0.8220103406118309
},
{
"epoch": 0.6159884252714906,
"grad_norm": 2.515625,
"learning_rate": 6.787560507960316e-06,
"loss": 0.7698272228240967,
"step": 9260,
"token_acc": 0.8139525080792469
},
{
"epoch": 0.6166536395536412,
"grad_norm": 2.0625,
"learning_rate": 6.767165584597376e-06,
"loss": 0.7683251857757568,
"step": 9270,
"token_acc": 0.8155737704918032
},
{
"epoch": 0.6173188538357919,
"grad_norm": 2.21875,
"learning_rate": 6.7467856666784385e-06,
"loss": 0.7416802883148194,
"step": 9280,
"token_acc": 0.8217928599450764
},
{
"epoch": 0.6179840681179425,
"grad_norm": 2.40625,
"learning_rate": 6.726420848798418e-06,
"loss": 0.8096532821655273,
"step": 9290,
"token_acc": 0.8060306952345087
},
{
"epoch": 0.6186492824000931,
"grad_norm": 2.375,
"learning_rate": 6.706071225482152e-06,
"loss": 0.7792798995971679,
"step": 9300,
"token_acc": 0.813065142336828
},
{
"epoch": 0.6193144966822438,
"grad_norm": 2.34375,
"learning_rate": 6.685736891183947e-06,
"loss": 0.7436950206756592,
"step": 9310,
"token_acc": 0.8191727619034731
},
{
"epoch": 0.6199797109643944,
"grad_norm": 2.328125,
"learning_rate": 6.665417940287144e-06,
"loss": 0.7397202968597412,
"step": 9320,
"token_acc": 0.8191107592361023
},
{
"epoch": 0.620644925246545,
"grad_norm": 2.046875,
"learning_rate": 6.645114467103681e-06,
"loss": 0.7595536231994628,
"step": 9330,
"token_acc": 0.8174382914591336
},
{
"epoch": 0.6213101395286956,
"grad_norm": 2.640625,
"learning_rate": 6.624826565873653e-06,
"loss": 0.775480318069458,
"step": 9340,
"token_acc": 0.8133597826555694
},
{
"epoch": 0.6219753538108463,
"grad_norm": 2.0625,
"learning_rate": 6.604554330764886e-06,
"loss": 0.7184958457946777,
"step": 9350,
"token_acc": 0.8222832793342614
},
{
"epoch": 0.622640568092997,
"grad_norm": 2.28125,
"learning_rate": 6.584297855872477e-06,
"loss": 0.7432106494903564,
"step": 9360,
"token_acc": 0.8212684083077891
},
{
"epoch": 0.6233057823751476,
"grad_norm": 2.15625,
"learning_rate": 6.564057235218381e-06,
"loss": 0.7486372947692871,
"step": 9370,
"token_acc": 0.8224119333503648
},
{
"epoch": 0.6239709966572983,
"grad_norm": 2.625,
"learning_rate": 6.543832562750956e-06,
"loss": 0.7507328510284423,
"step": 9380,
"token_acc": 0.8175133985914869
},
{
"epoch": 0.6246362109394489,
"grad_norm": 2.140625,
"learning_rate": 6.5236239323445405e-06,
"loss": 0.7337147235870362,
"step": 9390,
"token_acc": 0.8193657755593526
},
{
"epoch": 0.6253014252215995,
"grad_norm": 2.203125,
"learning_rate": 6.503431437799017e-06,
"loss": 0.7870224952697754,
"step": 9400,
"token_acc": 0.8118870145154963
},
{
"epoch": 0.6259666395037502,
"grad_norm": 2.3125,
"learning_rate": 6.483255172839364e-06,
"loss": 0.7331302642822266,
"step": 9410,
"token_acc": 0.8222046183118508
},
{
"epoch": 0.6266318537859008,
"grad_norm": 2.75,
"learning_rate": 6.463095231115233e-06,
"loss": 0.7553641319274902,
"step": 9420,
"token_acc": 0.8159465121731698
},
{
"epoch": 0.6272970680680514,
"grad_norm": 1.890625,
"learning_rate": 6.442951706200506e-06,
"loss": 0.709984827041626,
"step": 9430,
"token_acc": 0.8273408361171473
},
{
"epoch": 0.627962282350202,
"grad_norm": 2.4375,
"learning_rate": 6.4228246915928685e-06,
"loss": 0.7488089561462402,
"step": 9440,
"token_acc": 0.8161469798323039
},
{
"epoch": 0.6286274966323527,
"grad_norm": 2.234375,
"learning_rate": 6.402714280713378e-06,
"loss": 0.7871481418609619,
"step": 9450,
"token_acc": 0.8123481923481923
},
{
"epoch": 0.6292927109145033,
"grad_norm": 2.765625,
"learning_rate": 6.382620566906015e-06,
"loss": 0.7448900699615478,
"step": 9460,
"token_acc": 0.8188829975256274
},
{
"epoch": 0.629957925196654,
"grad_norm": 2.546875,
"learning_rate": 6.362543643437263e-06,
"loss": 0.7014565944671631,
"step": 9470,
"token_acc": 0.8276526868570606
},
{
"epoch": 0.6306231394788047,
"grad_norm": 2.25,
"learning_rate": 6.342483603495667e-06,
"loss": 0.7348586082458496,
"step": 9480,
"token_acc": 0.8207112611581597
},
{
"epoch": 0.6312883537609553,
"grad_norm": 1.890625,
"learning_rate": 6.322440540191421e-06,
"loss": 0.7385692119598388,
"step": 9490,
"token_acc": 0.820065766938412
},
{
"epoch": 0.6319535680431059,
"grad_norm": 2.390625,
"learning_rate": 6.302414546555902e-06,
"loss": 0.7496010303497315,
"step": 9500,
"token_acc": 0.8158516289852544
},
{
"epoch": 0.6326187823252565,
"grad_norm": 2.421875,
"learning_rate": 6.282405715541269e-06,
"loss": 0.8049209594726563,
"step": 9510,
"token_acc": 0.8063750252576278
},
{
"epoch": 0.6332839966074072,
"grad_norm": 2.0,
"learning_rate": 6.2624141400200124e-06,
"loss": 0.7773645401000977,
"step": 9520,
"token_acc": 0.815228118655538
},
{
"epoch": 0.6339492108895578,
"grad_norm": 2.328125,
"learning_rate": 6.242439912784533e-06,
"loss": 0.7698166370391846,
"step": 9530,
"token_acc": 0.8132543324400953
},
{
"epoch": 0.6346144251717084,
"grad_norm": 2.15625,
"learning_rate": 6.222483126546714e-06,
"loss": 0.7684356212615967,
"step": 9540,
"token_acc": 0.814789744681822
},
{
"epoch": 0.6352796394538591,
"grad_norm": 2.53125,
"learning_rate": 6.202543873937473e-06,
"loss": 0.7371409416198731,
"step": 9550,
"token_acc": 0.8181989154624957
},
{
"epoch": 0.6359448537360097,
"grad_norm": 2.375,
"learning_rate": 6.182622247506354e-06,
"loss": 0.7357774257659913,
"step": 9560,
"token_acc": 0.8199552127394875
},
{
"epoch": 0.6366100680181603,
"grad_norm": 2.15625,
"learning_rate": 6.162718339721081e-06,
"loss": 0.7559653282165527,
"step": 9570,
"token_acc": 0.8158920721132517
},
{
"epoch": 0.6372752823003109,
"grad_norm": 1.9453125,
"learning_rate": 6.142832242967136e-06,
"loss": 0.7724670886993408,
"step": 9580,
"token_acc": 0.8141967411323089
},
{
"epoch": 0.6379404965824617,
"grad_norm": 2.578125,
"learning_rate": 6.12296404954734e-06,
"loss": 0.8230411529541015,
"step": 9590,
"token_acc": 0.8053066562778273
},
{
"epoch": 0.6386057108646123,
"grad_norm": 2.875,
"learning_rate": 6.103113851681403e-06,
"loss": 0.7575227737426757,
"step": 9600,
"token_acc": 0.8139405617727711
},
{
"epoch": 0.6392709251467629,
"grad_norm": 2.0625,
"learning_rate": 6.083281741505509e-06,
"loss": 0.7587447166442871,
"step": 9610,
"token_acc": 0.8167771659737049
},
{
"epoch": 0.6399361394289136,
"grad_norm": 2.109375,
"learning_rate": 6.06346781107189e-06,
"loss": 0.7139963626861572,
"step": 9620,
"token_acc": 0.8278583556361334
},
{
"epoch": 0.6406013537110642,
"grad_norm": 2.296875,
"learning_rate": 6.043672152348391e-06,
"loss": 0.7447312355041504,
"step": 9630,
"token_acc": 0.820512344188293
},
{
"epoch": 0.6412665679932148,
"grad_norm": 2.125,
"learning_rate": 6.023894857218054e-06,
"loss": 0.6965029239654541,
"step": 9640,
"token_acc": 0.8294162565755981
},
{
"epoch": 0.6419317822753654,
"grad_norm": 2.421875,
"learning_rate": 6.004136017478682e-06,
"loss": 0.7055756092071533,
"step": 9650,
"token_acc": 0.828100016059546
},
{
"epoch": 0.6425969965575161,
"grad_norm": 1.8671875,
"learning_rate": 5.984395724842412e-06,
"loss": 0.6834077835083008,
"step": 9660,
"token_acc": 0.8329449876857918
},
{
"epoch": 0.6432622108396667,
"grad_norm": 2.40625,
"learning_rate": 5.964674070935295e-06,
"loss": 0.7548893928527832,
"step": 9670,
"token_acc": 0.8187081960666867
},
{
"epoch": 0.6439274251218173,
"grad_norm": 2.328125,
"learning_rate": 5.944971147296879e-06,
"loss": 0.7219256401062012,
"step": 9680,
"token_acc": 0.8269278717720392
},
{
"epoch": 0.644592639403968,
"grad_norm": 2.578125,
"learning_rate": 5.925287045379755e-06,
"loss": 0.8027442932128906,
"step": 9690,
"token_acc": 0.8053091633980367
},
{
"epoch": 0.6452578536861187,
"grad_norm": 2.328125,
"learning_rate": 5.905621856549167e-06,
"loss": 0.7774465084075928,
"step": 9700,
"token_acc": 0.8103796929462789
},
{
"epoch": 0.6459230679682693,
"grad_norm": 2.5625,
"learning_rate": 5.88597567208257e-06,
"loss": 0.7461068153381347,
"step": 9710,
"token_acc": 0.81812769653163
},
{
"epoch": 0.6465882822504199,
"grad_norm": 2.0625,
"learning_rate": 5.866348583169199e-06,
"loss": 0.7626749992370605,
"step": 9720,
"token_acc": 0.816241064298097
},
{
"epoch": 0.6472534965325706,
"grad_norm": 2.34375,
"learning_rate": 5.846740680909668e-06,
"loss": 0.6897253036499024,
"step": 9730,
"token_acc": 0.8332769223891844
},
{
"epoch": 0.6479187108147212,
"grad_norm": 2.390625,
"learning_rate": 5.827152056315533e-06,
"loss": 0.7468695640563965,
"step": 9740,
"token_acc": 0.817230041532072
},
{
"epoch": 0.6485839250968718,
"grad_norm": 2.296875,
"learning_rate": 5.80758280030886e-06,
"loss": 0.7577981948852539,
"step": 9750,
"token_acc": 0.8180070359158963
},
{
"epoch": 0.6492491393790225,
"grad_norm": 2.234375,
"learning_rate": 5.788033003721826e-06,
"loss": 0.698393726348877,
"step": 9760,
"token_acc": 0.8288517686063964
},
{
"epoch": 0.6499143536611731,
"grad_norm": 2.53125,
"learning_rate": 5.768502757296282e-06,
"loss": 0.7537515163421631,
"step": 9770,
"token_acc": 0.8159533949252596
},
{
"epoch": 0.6505795679433237,
"grad_norm": 2.171875,
"learning_rate": 5.748992151683332e-06,
"loss": 0.7410589218139648,
"step": 9780,
"token_acc": 0.8189118677260152
},
{
"epoch": 0.6512447822254743,
"grad_norm": 2.21875,
"learning_rate": 5.729501277442924e-06,
"loss": 0.7072693824768066,
"step": 9790,
"token_acc": 0.8283207650192583
},
{
"epoch": 0.651909996507625,
"grad_norm": 2.0625,
"learning_rate": 5.710030225043416e-06,
"loss": 0.7235157012939453,
"step": 9800,
"token_acc": 0.8254325722440242
},
{
"epoch": 0.6525752107897757,
"grad_norm": 2.109375,
"learning_rate": 5.690579084861152e-06,
"loss": 0.7299671649932862,
"step": 9810,
"token_acc": 0.8204680200893346
},
{
"epoch": 0.6532404250719263,
"grad_norm": 1.828125,
"learning_rate": 5.671147947180073e-06,
"loss": 0.7976999759674073,
"step": 9820,
"token_acc": 0.8062098172970257
},
{
"epoch": 0.653905639354077,
"grad_norm": 1.828125,
"learning_rate": 5.651736902191261e-06,
"loss": 0.6986201286315918,
"step": 9830,
"token_acc": 0.8271602513747054
},
{
"epoch": 0.6545708536362276,
"grad_norm": 2.125,
"learning_rate": 5.632346039992543e-06,
"loss": 0.767005443572998,
"step": 9840,
"token_acc": 0.8132597151992338
},
{
"epoch": 0.6552360679183782,
"grad_norm": 2.3125,
"learning_rate": 5.612975450588059e-06,
"loss": 0.7803658008575439,
"step": 9850,
"token_acc": 0.8118233934471186
},
{
"epoch": 0.6559012822005288,
"grad_norm": 2.03125,
"learning_rate": 5.5936252238878555e-06,
"loss": 0.7654474258422852,
"step": 9860,
"token_acc": 0.8146195374286985
},
{
"epoch": 0.6565664964826795,
"grad_norm": 2.1875,
"learning_rate": 5.574295449707477e-06,
"loss": 0.764702033996582,
"step": 9870,
"token_acc": 0.8146812572526608
},
{
"epoch": 0.6572317107648301,
"grad_norm": 2.84375,
"learning_rate": 5.554986217767508e-06,
"loss": 0.7296167373657226,
"step": 9880,
"token_acc": 0.8203848496090606
},
{
"epoch": 0.6578969250469807,
"grad_norm": 2.21875,
"learning_rate": 5.535697617693209e-06,
"loss": 0.7118094444274903,
"step": 9890,
"token_acc": 0.8290169241486702
},
{
"epoch": 0.6585621393291314,
"grad_norm": 2.34375,
"learning_rate": 5.516429739014064e-06,
"loss": 0.7266244888305664,
"step": 9900,
"token_acc": 0.8220138203356367
},
{
"epoch": 0.659227353611282,
"grad_norm": 1.875,
"learning_rate": 5.4971826711633825e-06,
"loss": 0.7320767402648926,
"step": 9910,
"token_acc": 0.8219340005585467
},
{
"epoch": 0.6598925678934326,
"grad_norm": 2.21875,
"learning_rate": 5.477956503477876e-06,
"loss": 0.7885263442993165,
"step": 9920,
"token_acc": 0.8072820499196345
},
{
"epoch": 0.6605577821755834,
"grad_norm": 2.140625,
"learning_rate": 5.458751325197248e-06,
"loss": 0.7482878208160401,
"step": 9930,
"token_acc": 0.8162340659730852
},
{
"epoch": 0.661222996457734,
"grad_norm": 2.265625,
"learning_rate": 5.439567225463782e-06,
"loss": 0.7394377231597901,
"step": 9940,
"token_acc": 0.8224641818413858
},
{
"epoch": 0.6618882107398846,
"grad_norm": 2.359375,
"learning_rate": 5.420404293321909e-06,
"loss": 0.7569956302642822,
"step": 9950,
"token_acc": 0.8151936979195409
},
{
"epoch": 0.6625534250220352,
"grad_norm": 2.453125,
"learning_rate": 5.401262617717822e-06,
"loss": 0.7362322330474853,
"step": 9960,
"token_acc": 0.820653674156683
},
{
"epoch": 0.6632186393041859,
"grad_norm": 1.9140625,
"learning_rate": 5.382142287499053e-06,
"loss": 0.7230823993682861,
"step": 9970,
"token_acc": 0.8232674605545833
},
{
"epoch": 0.6638838535863365,
"grad_norm": 2.140625,
"learning_rate": 5.363043391414053e-06,
"loss": 0.7136498928070069,
"step": 9980,
"token_acc": 0.8216297188342158
},
{
"epoch": 0.6645490678684871,
"grad_norm": 1.90625,
"learning_rate": 5.343966018111779e-06,
"loss": 0.726749849319458,
"step": 9990,
"token_acc": 0.8234268558658014
},
{
"epoch": 0.6652142821506378,
"grad_norm": 2.078125,
"learning_rate": 5.324910256141289e-06,
"loss": 0.7337868690490723,
"step": 10000,
"token_acc": 0.819446690336415
},
{
"epoch": 0.6658794964327884,
"grad_norm": 1.9765625,
"learning_rate": 5.30587619395135e-06,
"loss": 0.7817379474639893,
"step": 10010,
"token_acc": 0.8114585381842019
},
{
"epoch": 0.666544710714939,
"grad_norm": 2.03125,
"learning_rate": 5.2868639198899795e-06,
"loss": 0.7639070987701416,
"step": 10020,
"token_acc": 0.8160104370192665
},
{
"epoch": 0.6672099249970896,
"grad_norm": 1.796875,
"learning_rate": 5.267873522204081e-06,
"loss": 0.76551513671875,
"step": 10030,
"token_acc": 0.8143863179074446
},
{
"epoch": 0.6678751392792404,
"grad_norm": 2.140625,
"learning_rate": 5.248905089039015e-06,
"loss": 0.7554473400115966,
"step": 10040,
"token_acc": 0.8153805549140576
},
{
"epoch": 0.668540353561391,
"grad_norm": 2.203125,
"learning_rate": 5.2299587084381875e-06,
"loss": 0.7587243556976319,
"step": 10050,
"token_acc": 0.8171597318697003
},
{
"epoch": 0.6692055678435416,
"grad_norm": 2.234375,
"learning_rate": 5.211034468342648e-06,
"loss": 0.792900562286377,
"step": 10060,
"token_acc": 0.8090710578127797
},
{
"epoch": 0.6698707821256923,
"grad_norm": 2.09375,
"learning_rate": 5.192132456590684e-06,
"loss": 0.7637878894805908,
"step": 10070,
"token_acc": 0.8144866022998482
},
{
"epoch": 0.6705359964078429,
"grad_norm": 2.046875,
"learning_rate": 5.1732527609174e-06,
"loss": 0.7458618640899658,
"step": 10080,
"token_acc": 0.8209331237214442
},
{
"epoch": 0.6712012106899935,
"grad_norm": 2.515625,
"learning_rate": 5.154395468954328e-06,
"loss": 0.7748538970947265,
"step": 10090,
"token_acc": 0.8129401828663754
},
{
"epoch": 0.6718664249721441,
"grad_norm": 2.359375,
"learning_rate": 5.135560668228996e-06,
"loss": 0.7535116672515869,
"step": 10100,
"token_acc": 0.8169696071762892
},
{
"epoch": 0.6725316392542948,
"grad_norm": 2.5,
"learning_rate": 5.116748446164558e-06,
"loss": 0.7205764770507812,
"step": 10110,
"token_acc": 0.82615203827537
},
{
"epoch": 0.6731968535364454,
"grad_norm": 6.9375,
"learning_rate": 5.0979588900793576e-06,
"loss": 0.7572518348693847,
"step": 10120,
"token_acc": 0.8169131473993815
},
{
"epoch": 0.673862067818596,
"grad_norm": 1.9921875,
"learning_rate": 5.0791920871865245e-06,
"loss": 0.7521490573883056,
"step": 10130,
"token_acc": 0.8206472608931478
},
{
"epoch": 0.6745272821007468,
"grad_norm": 2.46875,
"learning_rate": 5.060448124593584e-06,
"loss": 0.7775327682495117,
"step": 10140,
"token_acc": 0.8125596683123756
},
{
"epoch": 0.6751924963828974,
"grad_norm": 2.15625,
"learning_rate": 5.041727089302061e-06,
"loss": 0.7625056266784668,
"step": 10150,
"token_acc": 0.8142942021464618
},
{
"epoch": 0.675857710665048,
"grad_norm": 1.9921875,
"learning_rate": 5.023029068207036e-06,
"loss": 0.7240376472473145,
"step": 10160,
"token_acc": 0.8214429805645599
},
{
"epoch": 0.6765229249471986,
"grad_norm": 2.078125,
"learning_rate": 5.004354148096784e-06,
"loss": 0.8016795158386231,
"step": 10170,
"token_acc": 0.8093808263562535
},
{
"epoch": 0.6771881392293493,
"grad_norm": 2.0625,
"learning_rate": 4.98570241565235e-06,
"loss": 0.7151380062103272,
"step": 10180,
"token_acc": 0.8250915027516654
},
{
"epoch": 0.6778533535114999,
"grad_norm": 2.1875,
"learning_rate": 4.9670739574471535e-06,
"loss": 0.7509218692779541,
"step": 10190,
"token_acc": 0.8159079072127776
},
{
"epoch": 0.6785185677936505,
"grad_norm": 2.140625,
"learning_rate": 4.948468859946584e-06,
"loss": 0.7252208232879639,
"step": 10200,
"token_acc": 0.8227971514158141
},
{
"epoch": 0.6791837820758012,
"grad_norm": 2.609375,
"learning_rate": 4.929887209507598e-06,
"loss": 0.7746740341186523,
"step": 10210,
"token_acc": 0.811070599933709
},
{
"epoch": 0.6798489963579518,
"grad_norm": 2.125,
"learning_rate": 4.9113290923783255e-06,
"loss": 0.7607236862182617,
"step": 10220,
"token_acc": 0.8164189045011024
},
{
"epoch": 0.6805142106401024,
"grad_norm": 2.8125,
"learning_rate": 4.892794594697665e-06,
"loss": 0.7487909317016601,
"step": 10230,
"token_acc": 0.8176014413285289
},
{
"epoch": 0.681179424922253,
"grad_norm": 2.34375,
"learning_rate": 4.87428380249487e-06,
"loss": 0.7471317768096923,
"step": 10240,
"token_acc": 0.8182489583768795
},
{
"epoch": 0.6818446392044037,
"grad_norm": 2.46875,
"learning_rate": 4.8557968016891866e-06,
"loss": 0.743244981765747,
"step": 10250,
"token_acc": 0.8235157545605307
},
{
"epoch": 0.6825098534865544,
"grad_norm": 2.21875,
"learning_rate": 4.837333678089418e-06,
"loss": 0.767507266998291,
"step": 10260,
"token_acc": 0.808209473819146
},
{
"epoch": 0.683175067768705,
"grad_norm": 2.03125,
"learning_rate": 4.8188945173935316e-06,
"loss": 0.7589426517486573,
"step": 10270,
"token_acc": 0.8174852251885062
},
{
"epoch": 0.6838402820508557,
"grad_norm": 2.1875,
"learning_rate": 4.800479405188285e-06,
"loss": 0.7499486923217773,
"step": 10280,
"token_acc": 0.8230619492489203
},
{
"epoch": 0.6845054963330063,
"grad_norm": 2.203125,
"learning_rate": 4.782088426948804e-06,
"loss": 0.7178757667541504,
"step": 10290,
"token_acc": 0.8246904758432619
},
{
"epoch": 0.6851707106151569,
"grad_norm": 1.9453125,
"learning_rate": 4.763721668038196e-06,
"loss": 0.7437349319458008,
"step": 10300,
"token_acc": 0.8186198683111798
},
{
"epoch": 0.6858359248973075,
"grad_norm": 2.203125,
"learning_rate": 4.745379213707155e-06,
"loss": 0.7868228435516358,
"step": 10310,
"token_acc": 0.8075274865078409
},
{
"epoch": 0.6865011391794582,
"grad_norm": 2.046875,
"learning_rate": 4.727061149093563e-06,
"loss": 0.744121789932251,
"step": 10320,
"token_acc": 0.8211395506867368
},
{
"epoch": 0.6871663534616088,
"grad_norm": 2.078125,
"learning_rate": 4.708767559222091e-06,
"loss": 0.7599831581115722,
"step": 10330,
"token_acc": 0.8177360932298928
},
{
"epoch": 0.6878315677437594,
"grad_norm": 2.3125,
"learning_rate": 4.6904985290038145e-06,
"loss": 0.7897554397583008,
"step": 10340,
"token_acc": 0.8084016186481191
},
{
"epoch": 0.6884967820259101,
"grad_norm": 1.75,
"learning_rate": 4.672254143235808e-06,
"loss": 0.6680974006652832,
"step": 10350,
"token_acc": 0.8369998309627876
},
{
"epoch": 0.6891619963080607,
"grad_norm": 2.421875,
"learning_rate": 4.654034486600762e-06,
"loss": 0.7633437633514404,
"step": 10360,
"token_acc": 0.8177921830314585
},
{
"epoch": 0.6898272105902113,
"grad_norm": 2.078125,
"learning_rate": 4.635839643666587e-06,
"loss": 0.7935458183288574,
"step": 10370,
"token_acc": 0.8080065466448445
},
{
"epoch": 0.6904924248723621,
"grad_norm": 2.15625,
"learning_rate": 4.6176696988860005e-06,
"loss": 0.7489728927612305,
"step": 10380,
"token_acc": 0.8170618784975241
},
{
"epoch": 0.6911576391545127,
"grad_norm": 2.171875,
"learning_rate": 4.599524736596181e-06,
"loss": 0.730811882019043,
"step": 10390,
"token_acc": 0.8226999937702035
},
{
"epoch": 0.6918228534366633,
"grad_norm": 2.390625,
"learning_rate": 4.581404841018334e-06,
"loss": 0.7118518829345704,
"step": 10400,
"token_acc": 0.830524180244435
},
{
"epoch": 0.6924880677188139,
"grad_norm": 2.234375,
"learning_rate": 4.563310096257309e-06,
"loss": 0.7607644557952881,
"step": 10410,
"token_acc": 0.8166649176198971
},
{
"epoch": 0.6931532820009646,
"grad_norm": 2.40625,
"learning_rate": 4.545240586301231e-06,
"loss": 0.7241078376770019,
"step": 10420,
"token_acc": 0.8239304133851227
},
{
"epoch": 0.6938184962831152,
"grad_norm": 2.21875,
"learning_rate": 4.527196395021082e-06,
"loss": 0.7327056884765625,
"step": 10430,
"token_acc": 0.8225848499143432
},
{
"epoch": 0.6944837105652658,
"grad_norm": 2.6875,
"learning_rate": 4.509177606170344e-06,
"loss": 0.7445612907409668,
"step": 10440,
"token_acc": 0.8190574267022049
},
{
"epoch": 0.6951489248474165,
"grad_norm": 2.34375,
"learning_rate": 4.4911843033845705e-06,
"loss": 0.7644867420196533,
"step": 10450,
"token_acc": 0.814488115531826
},
{
"epoch": 0.6958141391295671,
"grad_norm": 2.546875,
"learning_rate": 4.4732165701810325e-06,
"loss": 0.8187058448791504,
"step": 10460,
"token_acc": 0.8039225478724922
},
{
"epoch": 0.6964793534117177,
"grad_norm": 1.9609375,
"learning_rate": 4.455274489958314e-06,
"loss": 0.767139196395874,
"step": 10470,
"token_acc": 0.8175021371414157
},
{
"epoch": 0.6971445676938683,
"grad_norm": 2.359375,
"learning_rate": 4.4373581459959305e-06,
"loss": 0.7555941581726074,
"step": 10480,
"token_acc": 0.8174737555028784
},
{
"epoch": 0.6978097819760191,
"grad_norm": 2.046875,
"learning_rate": 4.419467621453938e-06,
"loss": 0.7371748924255371,
"step": 10490,
"token_acc": 0.8217062392330162
},
{
"epoch": 0.6984749962581697,
"grad_norm": 2.140625,
"learning_rate": 4.401602999372552e-06,
"loss": 0.7382590293884277,
"step": 10500,
"token_acc": 0.8213993453355155
},
{
"epoch": 0.6991402105403203,
"grad_norm": 2.5,
"learning_rate": 4.383764362671763e-06,
"loss": 0.7197907447814942,
"step": 10510,
"token_acc": 0.8248956671837787
},
{
"epoch": 0.699805424822471,
"grad_norm": 2.09375,
"learning_rate": 4.365951794150932e-06,
"loss": 0.734802532196045,
"step": 10520,
"token_acc": 0.8205858154892353
},
{
"epoch": 0.7004706391046216,
"grad_norm": 2.140625,
"learning_rate": 4.348165376488449e-06,
"loss": 0.686077356338501,
"step": 10530,
"token_acc": 0.83125515662843
},
{
"epoch": 0.7011358533867722,
"grad_norm": 2.5,
"learning_rate": 4.3304051922413056e-06,
"loss": 0.7473914623260498,
"step": 10540,
"token_acc": 0.8208089233344351
},
{
"epoch": 0.7018010676689228,
"grad_norm": 2.140625,
"learning_rate": 4.312671323844727e-06,
"loss": 0.7289551258087158,
"step": 10550,
"token_acc": 0.8215364959050223
},
{
"epoch": 0.7024662819510735,
"grad_norm": 2.640625,
"learning_rate": 4.2949638536118e-06,
"loss": 0.7434550762176514,
"step": 10560,
"token_acc": 0.8177236049972906
},
{
"epoch": 0.7031314962332241,
"grad_norm": 2.28125,
"learning_rate": 4.277282863733075e-06,
"loss": 0.7804749965667724,
"step": 10570,
"token_acc": 0.8103060332962312
},
{
"epoch": 0.7037967105153747,
"grad_norm": 2.765625,
"learning_rate": 4.259628436276206e-06,
"loss": 0.7388410568237305,
"step": 10580,
"token_acc": 0.8211061816858635
},
{
"epoch": 0.7044619247975255,
"grad_norm": 2.734375,
"learning_rate": 4.242000653185535e-06,
"loss": 0.7079017162322998,
"step": 10590,
"token_acc": 0.8266787206628748
},
{
"epoch": 0.7051271390796761,
"grad_norm": 2.09375,
"learning_rate": 4.224399596281747e-06,
"loss": 0.755326509475708,
"step": 10600,
"token_acc": 0.8140986041604487
},
{
"epoch": 0.7057923533618267,
"grad_norm": 2.125,
"learning_rate": 4.206825347261472e-06,
"loss": 0.7079007625579834,
"step": 10610,
"token_acc": 0.8289718944233282
},
{
"epoch": 0.7064575676439773,
"grad_norm": 1.8828125,
"learning_rate": 4.1892779876969046e-06,
"loss": 0.7745383739471435,
"step": 10620,
"token_acc": 0.8119641145048624
},
{
"epoch": 0.707122781926128,
"grad_norm": 2.203125,
"learning_rate": 4.171757599035436e-06,
"loss": 0.7729456901550293,
"step": 10630,
"token_acc": 0.8146767442971945
},
{
"epoch": 0.7077879962082786,
"grad_norm": 2.546875,
"learning_rate": 4.154264262599268e-06,
"loss": 0.7262872695922852,
"step": 10640,
"token_acc": 0.8256558594233387
},
{
"epoch": 0.7084532104904292,
"grad_norm": 2.0625,
"learning_rate": 4.136798059585039e-06,
"loss": 0.7384644031524659,
"step": 10650,
"token_acc": 0.8198253316211619
},
{
"epoch": 0.7091184247725799,
"grad_norm": 2.03125,
"learning_rate": 4.119359071063432e-06,
"loss": 0.7444841384887695,
"step": 10660,
"token_acc": 0.8199938325250203
},
{
"epoch": 0.7097836390547305,
"grad_norm": 2.296875,
"learning_rate": 4.101947377978836e-06,
"loss": 0.7999814987182617,
"step": 10670,
"token_acc": 0.8059800529483855
},
{
"epoch": 0.7104488533368811,
"grad_norm": 2.890625,
"learning_rate": 4.084563061148931e-06,
"loss": 0.7445531845092773,
"step": 10680,
"token_acc": 0.8202338843571789
},
{
"epoch": 0.7111140676190317,
"grad_norm": 2.078125,
"learning_rate": 4.067206201264331e-06,
"loss": 0.7387455463409424,
"step": 10690,
"token_acc": 0.8195726095772891
},
{
"epoch": 0.7117792819011824,
"grad_norm": 2.234375,
"learning_rate": 4.049876878888201e-06,
"loss": 0.7409853935241699,
"step": 10700,
"token_acc": 0.8176479644577386
},
{
"epoch": 0.712444496183333,
"grad_norm": 2.4375,
"learning_rate": 4.032575174455892e-06,
"loss": 0.7909274578094483,
"step": 10710,
"token_acc": 0.8091430777833994
},
{
"epoch": 0.7131097104654837,
"grad_norm": 2.640625,
"learning_rate": 4.015301168274578e-06,
"loss": 0.7491744995117188,
"step": 10720,
"token_acc": 0.8179207184616057
},
{
"epoch": 0.7137749247476344,
"grad_norm": 2.078125,
"learning_rate": 3.998054940522847e-06,
"loss": 0.7280071258544922,
"step": 10730,
"token_acc": 0.8253841117719984
},
{
"epoch": 0.714440139029785,
"grad_norm": 2.09375,
"learning_rate": 3.980836571250365e-06,
"loss": 0.7767271041870117,
"step": 10740,
"token_acc": 0.813767078007933
},
{
"epoch": 0.7151053533119356,
"grad_norm": 2.40625,
"learning_rate": 3.9636461403774876e-06,
"loss": 0.7197417259216309,
"step": 10750,
"token_acc": 0.8201179042711018
},
{
"epoch": 0.7157705675940862,
"grad_norm": 2.0625,
"learning_rate": 3.946483727694891e-06,
"loss": 0.7577385425567627,
"step": 10760,
"token_acc": 0.815292438986455
},
{
"epoch": 0.7164357818762369,
"grad_norm": 2.3125,
"learning_rate": 3.929349412863206e-06,
"loss": 0.7100510120391845,
"step": 10770,
"token_acc": 0.8235802001766656
},
{
"epoch": 0.7171009961583875,
"grad_norm": 2.484375,
"learning_rate": 3.912243275412641e-06,
"loss": 0.7816547870635986,
"step": 10780,
"token_acc": 0.8122043386983905
},
{
"epoch": 0.7177662104405381,
"grad_norm": 1.9375,
"learning_rate": 3.895165394742625e-06,
"loss": 0.7969231128692627,
"step": 10790,
"token_acc": 0.8049081996163566
},
{
"epoch": 0.7184314247226888,
"grad_norm": 2.125,
"learning_rate": 3.878115850121412e-06,
"loss": 0.7228692054748536,
"step": 10800,
"token_acc": 0.8274358191745514
},
{
"epoch": 0.7190966390048394,
"grad_norm": 2.046875,
"learning_rate": 3.861094720685758e-06,
"loss": 0.7443108081817627,
"step": 10810,
"token_acc": 0.8210665783371978
},
{
"epoch": 0.71976185328699,
"grad_norm": 2.125,
"learning_rate": 3.8441020854405105e-06,
"loss": 0.7695234775543213,
"step": 10820,
"token_acc": 0.8124020080263518
},
{
"epoch": 0.7204270675691407,
"grad_norm": 2.359375,
"learning_rate": 3.827138023258267e-06,
"loss": 0.7814039707183837,
"step": 10830,
"token_acc": 0.8128341872217291
},
{
"epoch": 0.7210922818512914,
"grad_norm": 2.15625,
"learning_rate": 3.8102026128789903e-06,
"loss": 0.7569797039031982,
"step": 10840,
"token_acc": 0.8133915020269249
},
{
"epoch": 0.721757496133442,
"grad_norm": 2.359375,
"learning_rate": 3.793295932909662e-06,
"loss": 0.7574501037597656,
"step": 10850,
"token_acc": 0.8196435840607897
},
{
"epoch": 0.7224227104155926,
"grad_norm": 2.140625,
"learning_rate": 3.7764180618239176e-06,
"loss": 0.7217781066894531,
"step": 10860,
"token_acc": 0.8250855171508384
},
{
"epoch": 0.7230879246977433,
"grad_norm": 2.375,
"learning_rate": 3.7595690779616555e-06,
"loss": 0.7153165340423584,
"step": 10870,
"token_acc": 0.8286450893634811
},
{
"epoch": 0.7237531389798939,
"grad_norm": 1.671875,
"learning_rate": 3.7427490595287044e-06,
"loss": 0.778206205368042,
"step": 10880,
"token_acc": 0.8135480615054396
},
{
"epoch": 0.7244183532620445,
"grad_norm": 2.625,
"learning_rate": 3.725958084596443e-06,
"loss": 0.7352749347686768,
"step": 10890,
"token_acc": 0.8209459694898009
},
{
"epoch": 0.7250835675441952,
"grad_norm": 2.546875,
"learning_rate": 3.709196231101444e-06,
"loss": 0.8013176918029785,
"step": 10900,
"token_acc": 0.8055780372811243
},
{
"epoch": 0.7257487818263458,
"grad_norm": 2.28125,
"learning_rate": 3.692463576845112e-06,
"loss": 0.7722053527832031,
"step": 10910,
"token_acc": 0.8136912556380038
},
{
"epoch": 0.7264139961084964,
"grad_norm": 1.96875,
"learning_rate": 3.67576019949332e-06,
"loss": 0.7346163749694824,
"step": 10920,
"token_acc": 0.8243017023746845
},
{
"epoch": 0.727079210390647,
"grad_norm": 2.1875,
"learning_rate": 3.659086176576049e-06,
"loss": 0.7361105442047119,
"step": 10930,
"token_acc": 0.8227921150232594
},
{
"epoch": 0.7277444246727978,
"grad_norm": 2.0625,
"learning_rate": 3.6424415854870334e-06,
"loss": 0.7291028022766113,
"step": 10940,
"token_acc": 0.8255149815569675
},
{
"epoch": 0.7284096389549484,
"grad_norm": 2.046875,
"learning_rate": 3.625826503483383e-06,
"loss": 0.8022925376892089,
"step": 10950,
"token_acc": 0.8053442920506692
},
{
"epoch": 0.729074853237099,
"grad_norm": 2.34375,
"learning_rate": 3.6092410076852622e-06,
"loss": 0.7500377178192139,
"step": 10960,
"token_acc": 0.8174630990092336
},
{
"epoch": 0.7297400675192497,
"grad_norm": 2.421875,
"learning_rate": 3.5926851750754952e-06,
"loss": 0.7434184074401855,
"step": 10970,
"token_acc": 0.818394365373937
},
{
"epoch": 0.7304052818014003,
"grad_norm": 1.9375,
"learning_rate": 3.5761590824992185e-06,
"loss": 0.7639784812927246,
"step": 10980,
"token_acc": 0.8136915018501102
},
{
"epoch": 0.7310704960835509,
"grad_norm": 2.015625,
"learning_rate": 3.559662806663532e-06,
"loss": 0.730387544631958,
"step": 10990,
"token_acc": 0.8222414654923579
},
{
"epoch": 0.7317357103657015,
"grad_norm": 2.359375,
"learning_rate": 3.5431964241371507e-06,
"loss": 0.7679181098937988,
"step": 11000,
"token_acc": 0.8154722036168788
},
{
"epoch": 0.7324009246478522,
"grad_norm": 2.046875,
"learning_rate": 3.526760011350018e-06,
"loss": 0.7510161876678467,
"step": 11010,
"token_acc": 0.8164189270403461
},
{
"epoch": 0.7330661389300028,
"grad_norm": 2.265625,
"learning_rate": 3.510353644592981e-06,
"loss": 0.7110666275024414,
"step": 11020,
"token_acc": 0.8278615610583587
},
{
"epoch": 0.7337313532121534,
"grad_norm": 2.296875,
"learning_rate": 3.4939774000174265e-06,
"loss": 0.779074764251709,
"step": 11030,
"token_acc": 0.810771035660486
},
{
"epoch": 0.7343965674943042,
"grad_norm": 2.453125,
"learning_rate": 3.4776313536349237e-06,
"loss": 0.7637697696685791,
"step": 11040,
"token_acc": 0.8157720085887176
},
{
"epoch": 0.7350617817764548,
"grad_norm": 2.15625,
"learning_rate": 3.4613155813168766e-06,
"loss": 0.7797583103179931,
"step": 11050,
"token_acc": 0.811097861182591
},
{
"epoch": 0.7357269960586054,
"grad_norm": 2.140625,
"learning_rate": 3.4450301587941683e-06,
"loss": 0.747354793548584,
"step": 11060,
"token_acc": 0.8201310841899678
},
{
"epoch": 0.736392210340756,
"grad_norm": 2.28125,
"learning_rate": 3.4287751616568123e-06,
"loss": 0.7813729286193848,
"step": 11070,
"token_acc": 0.8151024734982332
},
{
"epoch": 0.7370574246229067,
"grad_norm": 2.578125,
"learning_rate": 3.4125506653536035e-06,
"loss": 0.7507558822631836,
"step": 11080,
"token_acc": 0.8160673045199605
},
{
"epoch": 0.7377226389050573,
"grad_norm": 2.265625,
"learning_rate": 3.3963567451917512e-06,
"loss": 0.7712699890136718,
"step": 11090,
"token_acc": 0.815071503926855
},
{
"epoch": 0.7383878531872079,
"grad_norm": 1.90625,
"learning_rate": 3.380193476336564e-06,
"loss": 0.7626707077026367,
"step": 11100,
"token_acc": 0.8137189059639974
},
{
"epoch": 0.7390530674693586,
"grad_norm": 2.671875,
"learning_rate": 3.3640609338110685e-06,
"loss": 0.7744617462158203,
"step": 11110,
"token_acc": 0.8125275991886775
},
{
"epoch": 0.7397182817515092,
"grad_norm": 2.171875,
"learning_rate": 3.347959192495667e-06,
"loss": 0.763826322555542,
"step": 11120,
"token_acc": 0.8163371108125475
},
{
"epoch": 0.7403834960336598,
"grad_norm": 2.484375,
"learning_rate": 3.3318883271278024e-06,
"loss": 0.7611388683319091,
"step": 11130,
"token_acc": 0.8160508645018977
},
{
"epoch": 0.7410487103158104,
"grad_norm": 2.140625,
"learning_rate": 3.3158484123016165e-06,
"loss": 0.8018529891967774,
"step": 11140,
"token_acc": 0.8087114733816091
},
{
"epoch": 0.7417139245979611,
"grad_norm": 2.3125,
"learning_rate": 3.2998395224675674e-06,
"loss": 0.7451249122619629,
"step": 11150,
"token_acc": 0.8190627585906537
},
{
"epoch": 0.7423791388801118,
"grad_norm": 1.8359375,
"learning_rate": 3.2838617319321252e-06,
"loss": 0.7699327945709229,
"step": 11160,
"token_acc": 0.8160728413769058
},
{
"epoch": 0.7430443531622624,
"grad_norm": 2.15625,
"learning_rate": 3.267915114857406e-06,
"loss": 0.8020421981811523,
"step": 11170,
"token_acc": 0.8042447861807457
},
{
"epoch": 0.7437095674444131,
"grad_norm": 2.125,
"learning_rate": 3.251999745260833e-06,
"loss": 0.7627616405487061,
"step": 11180,
"token_acc": 0.8222685667941142
},
{
"epoch": 0.7443747817265637,
"grad_norm": 1.875,
"learning_rate": 3.236115697014789e-06,
"loss": 0.7809383392333984,
"step": 11190,
"token_acc": 0.8110214459429582
},
{
"epoch": 0.7450399960087143,
"grad_norm": 2.078125,
"learning_rate": 3.220263043846279e-06,
"loss": 0.7645885467529296,
"step": 11200,
"token_acc": 0.8147874525332821
},
{
"epoch": 0.7457052102908649,
"grad_norm": 1.859375,
"learning_rate": 3.2044418593365843e-06,
"loss": 0.7663979530334473,
"step": 11210,
"token_acc": 0.816506390599318
},
{
"epoch": 0.7463704245730156,
"grad_norm": 2.171875,
"learning_rate": 3.1886522169209255e-06,
"loss": 0.7316720008850097,
"step": 11220,
"token_acc": 0.8223409986673094
},
{
"epoch": 0.7470356388551662,
"grad_norm": 2.421875,
"learning_rate": 3.172894189888106e-06,
"loss": 0.7555332660675049,
"step": 11230,
"token_acc": 0.817852185490496
},
{
"epoch": 0.7477008531373168,
"grad_norm": 2.09375,
"learning_rate": 3.1571678513802017e-06,
"loss": 0.7676819324493408,
"step": 11240,
"token_acc": 0.814082749212707
},
{
"epoch": 0.7483660674194675,
"grad_norm": 2.3125,
"learning_rate": 3.141473274392196e-06,
"loss": 0.7395438194274903,
"step": 11250,
"token_acc": 0.8158539119078713
},
{
"epoch": 0.7490312817016181,
"grad_norm": 2.8125,
"learning_rate": 3.1258105317716415e-06,
"loss": 0.7378631114959717,
"step": 11260,
"token_acc": 0.8237398326790936
},
{
"epoch": 0.7496964959837688,
"grad_norm": 2.375,
"learning_rate": 3.110179696218335e-06,
"loss": 0.7674758911132813,
"step": 11270,
"token_acc": 0.8124696135819995
},
{
"epoch": 0.7503617102659194,
"grad_norm": 2.34375,
"learning_rate": 3.094580840283985e-06,
"loss": 0.7774701595306397,
"step": 11280,
"token_acc": 0.8096503319549048
},
{
"epoch": 0.7510269245480701,
"grad_norm": 1.9609375,
"learning_rate": 3.0790140363718455e-06,
"loss": 0.7329115867614746,
"step": 11290,
"token_acc": 0.8178184964231295
},
{
"epoch": 0.7516921388302207,
"grad_norm": 2.140625,
"learning_rate": 3.0634793567364084e-06,
"loss": 0.7693871021270752,
"step": 11300,
"token_acc": 0.8100678004090438
},
{
"epoch": 0.7523573531123713,
"grad_norm": 2.171875,
"learning_rate": 3.0479768734830584e-06,
"loss": 0.7337233543395996,
"step": 11310,
"token_acc": 0.8239096647318171
},
{
"epoch": 0.753022567394522,
"grad_norm": 2.109375,
"learning_rate": 3.0325066585677365e-06,
"loss": 0.7146025657653808,
"step": 11320,
"token_acc": 0.8256320547015824
},
{
"epoch": 0.7536877816766726,
"grad_norm": 1.9765625,
"learning_rate": 3.0170687837966093e-06,
"loss": 0.7362939834594726,
"step": 11330,
"token_acc": 0.819413522381064
},
{
"epoch": 0.7543529959588232,
"grad_norm": 2.1875,
"learning_rate": 3.001663320825733e-06,
"loss": 0.7551639080047607,
"step": 11340,
"token_acc": 0.8196597832317927
},
{
"epoch": 0.7550182102409738,
"grad_norm": 2.140625,
"learning_rate": 2.9862903411607212e-06,
"loss": 0.7858519077301025,
"step": 11350,
"token_acc": 0.8127863773025064
},
{
"epoch": 0.7556834245231245,
"grad_norm": 2.46875,
"learning_rate": 2.970949916156419e-06,
"loss": 0.7225425720214844,
"step": 11360,
"token_acc": 0.8228295155972971
},
{
"epoch": 0.7563486388052751,
"grad_norm": 2.34375,
"learning_rate": 2.955642117016554e-06,
"loss": 0.7415917873382568,
"step": 11370,
"token_acc": 0.8203982716263091
},
{
"epoch": 0.7570138530874257,
"grad_norm": 1.953125,
"learning_rate": 2.9403670147934325e-06,
"loss": 0.7116865158081055,
"step": 11380,
"token_acc": 0.8239005790544482
},
{
"epoch": 0.7576790673695765,
"grad_norm": 2.8125,
"learning_rate": 2.925124680387594e-06,
"loss": 0.7881548404693604,
"step": 11390,
"token_acc": 0.8085215797044203
},
{
"epoch": 0.7583442816517271,
"grad_norm": 2.140625,
"learning_rate": 2.9099151845474716e-06,
"loss": 0.7314609050750732,
"step": 11400,
"token_acc": 0.8183806944622557
},
{
"epoch": 0.7590094959338777,
"grad_norm": 2.359375,
"learning_rate": 2.894738597869087e-06,
"loss": 0.7055675983428955,
"step": 11410,
"token_acc": 0.8287423701321799
},
{
"epoch": 0.7596747102160284,
"grad_norm": 2.0625,
"learning_rate": 2.8795949907957055e-06,
"loss": 0.7391792297363281,
"step": 11420,
"token_acc": 0.818998001245126
},
{
"epoch": 0.760339924498179,
"grad_norm": 2.015625,
"learning_rate": 2.864484433617526e-06,
"loss": 0.7754724979400635,
"step": 11430,
"token_acc": 0.816148768209153
},
{
"epoch": 0.7610051387803296,
"grad_norm": 1.9296875,
"learning_rate": 2.849406996471328e-06,
"loss": 0.7594459533691407,
"step": 11440,
"token_acc": 0.81412231460769
},
{
"epoch": 0.7616703530624802,
"grad_norm": 2.25,
"learning_rate": 2.8343627493401716e-06,
"loss": 0.7270243167877197,
"step": 11450,
"token_acc": 0.8251768750083275
},
{
"epoch": 0.7623355673446309,
"grad_norm": 2.09375,
"learning_rate": 2.8193517620530617e-06,
"loss": 0.7517218589782715,
"step": 11460,
"token_acc": 0.8133500563051672
},
{
"epoch": 0.7630007816267815,
"grad_norm": 2.578125,
"learning_rate": 2.804374104284625e-06,
"loss": 0.7442570209503174,
"step": 11470,
"token_acc": 0.8202200144646188
},
{
"epoch": 0.7636659959089321,
"grad_norm": 2.234375,
"learning_rate": 2.7894298455547842e-06,
"loss": 0.7997704982757569,
"step": 11480,
"token_acc": 0.8040147006460145
},
{
"epoch": 0.7643312101910829,
"grad_norm": 2.0625,
"learning_rate": 2.774519055228442e-06,
"loss": 0.7524272918701171,
"step": 11490,
"token_acc": 0.8163572251007484
},
{
"epoch": 0.7649964244732335,
"grad_norm": 2.359375,
"learning_rate": 2.759641802515154e-06,
"loss": 0.7877228260040283,
"step": 11500,
"token_acc": 0.8114066247898539
},
{
"epoch": 0.7656616387553841,
"grad_norm": 2.4375,
"learning_rate": 2.7447981564687985e-06,
"loss": 0.7688689708709717,
"step": 11510,
"token_acc": 0.8123031871151494
},
{
"epoch": 0.7663268530375347,
"grad_norm": 2.28125,
"learning_rate": 2.7299881859872846e-06,
"loss": 0.7609755039215088,
"step": 11520,
"token_acc": 0.8175364514006823
},
{
"epoch": 0.7669920673196854,
"grad_norm": 2.25,
"learning_rate": 2.715211959812202e-06,
"loss": 0.7614534378051758,
"step": 11530,
"token_acc": 0.814420795460146
},
{
"epoch": 0.767657281601836,
"grad_norm": 2.640625,
"learning_rate": 2.7004695465285114e-06,
"loss": 0.7543790817260743,
"step": 11540,
"token_acc": 0.8155164023587336
},
{
"epoch": 0.7683224958839866,
"grad_norm": 2.25,
"learning_rate": 2.6857610145642345e-06,
"loss": 0.7579907417297364,
"step": 11550,
"token_acc": 0.8170287664422857
},
{
"epoch": 0.7689877101661373,
"grad_norm": 2.3125,
"learning_rate": 2.6710864321901255e-06,
"loss": 0.7733065128326416,
"step": 11560,
"token_acc": 0.8113401606501726
},
{
"epoch": 0.7696529244482879,
"grad_norm": 2.078125,
"learning_rate": 2.6564458675193707e-06,
"loss": 0.7617386817932129,
"step": 11570,
"token_acc": 0.8152243030912186
},
{
"epoch": 0.7703181387304385,
"grad_norm": 2.09375,
"learning_rate": 2.6418393885072436e-06,
"loss": 0.7648447513580322,
"step": 11580,
"token_acc": 0.8156920469244837
},
{
"epoch": 0.7709833530125891,
"grad_norm": 2.40625,
"learning_rate": 2.6272670629508156e-06,
"loss": 0.7560097217559815,
"step": 11590,
"token_acc": 0.8161208314640347
},
{
"epoch": 0.7716485672947399,
"grad_norm": 2.140625,
"learning_rate": 2.6127289584886328e-06,
"loss": 0.7519503116607666,
"step": 11600,
"token_acc": 0.8140218138164701
},
{
"epoch": 0.7723137815768905,
"grad_norm": 2.671875,
"learning_rate": 2.5982251426004014e-06,
"loss": 0.7794088840484619,
"step": 11610,
"token_acc": 0.8126437136375562
},
{
"epoch": 0.7729789958590411,
"grad_norm": 2.078125,
"learning_rate": 2.58375568260667e-06,
"loss": 0.7899683475494385,
"step": 11620,
"token_acc": 0.8009139550041902
},
{
"epoch": 0.7736442101411918,
"grad_norm": 2.046875,
"learning_rate": 2.5693206456685283e-06,
"loss": 0.7305837631225586,
"step": 11630,
"token_acc": 0.8244910483013537
},
{
"epoch": 0.7743094244233424,
"grad_norm": 2.203125,
"learning_rate": 2.5549200987872868e-06,
"loss": 0.7424963474273681,
"step": 11640,
"token_acc": 0.819509526728223
},
{
"epoch": 0.774974638705493,
"grad_norm": 2.296875,
"learning_rate": 2.5405541088041572e-06,
"loss": 0.704157829284668,
"step": 11650,
"token_acc": 0.830157256114876
},
{
"epoch": 0.7756398529876436,
"grad_norm": 2.25,
"learning_rate": 2.526222742399973e-06,
"loss": 0.7381947040557861,
"step": 11660,
"token_acc": 0.8204624401496761
},
{
"epoch": 0.7763050672697943,
"grad_norm": 2.390625,
"learning_rate": 2.5119260660948443e-06,
"loss": 0.7371403694152832,
"step": 11670,
"token_acc": 0.8205351111633234
},
{
"epoch": 0.7769702815519449,
"grad_norm": 1.890625,
"learning_rate": 2.4976641462478723e-06,
"loss": 0.7498542785644531,
"step": 11680,
"token_acc": 0.8192247064500563
},
{
"epoch": 0.7776354958340955,
"grad_norm": 2.234375,
"learning_rate": 2.4834370490568247e-06,
"loss": 0.7635834693908692,
"step": 11690,
"token_acc": 0.8172850881055777
},
{
"epoch": 0.7783007101162462,
"grad_norm": 2.21875,
"learning_rate": 2.469244840557843e-06,
"loss": 0.7587650775909424,
"step": 11700,
"token_acc": 0.815227728683193
},
{
"epoch": 0.7789659243983968,
"grad_norm": 2.203125,
"learning_rate": 2.455087586625138e-06,
"loss": 0.78086256980896,
"step": 11710,
"token_acc": 0.8110098493104094
},
{
"epoch": 0.7796311386805475,
"grad_norm": 2.359375,
"learning_rate": 2.4409653529706588e-06,
"loss": 0.7618659973144531,
"step": 11720,
"token_acc": 0.8148888969705786
},
{
"epoch": 0.7802963529626981,
"grad_norm": 1.96875,
"learning_rate": 2.42687820514382e-06,
"loss": 0.7179902553558349,
"step": 11730,
"token_acc": 0.8233276634151422
},
{
"epoch": 0.7809615672448488,
"grad_norm": 2.546875,
"learning_rate": 2.412826208531175e-06,
"loss": 0.7634764194488526,
"step": 11740,
"token_acc": 0.8167271591929126
},
{
"epoch": 0.7816267815269994,
"grad_norm": 2.40625,
"learning_rate": 2.3988094283561245e-06,
"loss": 0.7151909351348877,
"step": 11750,
"token_acc": 0.828529149021774
},
{
"epoch": 0.78229199580915,
"grad_norm": 2.09375,
"learning_rate": 2.384827929678606e-06,
"loss": 0.7736407279968261,
"step": 11760,
"token_acc": 0.8135413621748027
},
{
"epoch": 0.7829572100913007,
"grad_norm": 2.4375,
"learning_rate": 2.3708817773947977e-06,
"loss": 0.7910758495330811,
"step": 11770,
"token_acc": 0.8099270610041669
},
{
"epoch": 0.7836224243734513,
"grad_norm": 2.140625,
"learning_rate": 2.356971036236817e-06,
"loss": 0.7243244647979736,
"step": 11780,
"token_acc": 0.821688120457892
},
{
"epoch": 0.7842876386556019,
"grad_norm": 1.8671875,
"learning_rate": 2.3430957707724057e-06,
"loss": 0.7612554550170898,
"step": 11790,
"token_acc": 0.8176047654023166
},
{
"epoch": 0.7849528529377525,
"grad_norm": 2.109375,
"learning_rate": 2.32925604540466e-06,
"loss": 0.7582258224487305,
"step": 11800,
"token_acc": 0.8170749412665311
},
{
"epoch": 0.7856180672199032,
"grad_norm": 1.9609375,
"learning_rate": 2.315451924371702e-06,
"loss": 0.7338740348815918,
"step": 11810,
"token_acc": 0.8221260750601129
},
{
"epoch": 0.7862832815020538,
"grad_norm": 2.234375,
"learning_rate": 2.301683471746403e-06,
"loss": 0.7302828788757324,
"step": 11820,
"token_acc": 0.8217261802868979
},
{
"epoch": 0.7869484957842044,
"grad_norm": 1.84375,
"learning_rate": 2.2879507514360633e-06,
"loss": 0.7490485191345215,
"step": 11830,
"token_acc": 0.8166772795180133
},
{
"epoch": 0.7876137100663552,
"grad_norm": 2.21875,
"learning_rate": 2.274253827182138e-06,
"loss": 0.769069766998291,
"step": 11840,
"token_acc": 0.8169764114492077
},
{
"epoch": 0.7882789243485058,
"grad_norm": 2.21875,
"learning_rate": 2.2605927625599377e-06,
"loss": 0.749467134475708,
"step": 11850,
"token_acc": 0.8145708649570363
},
{
"epoch": 0.7889441386306564,
"grad_norm": 1.9765625,
"learning_rate": 2.246967620978313e-06,
"loss": 0.754631757736206,
"step": 11860,
"token_acc": 0.8188484593114135
},
{
"epoch": 0.789609352912807,
"grad_norm": 2.046875,
"learning_rate": 2.2333784656793867e-06,
"loss": 0.7520146846771241,
"step": 11870,
"token_acc": 0.8163362726248093
},
{
"epoch": 0.7902745671949577,
"grad_norm": 2.0625,
"learning_rate": 2.219825359738245e-06,
"loss": 0.8184666633605957,
"step": 11880,
"token_acc": 0.8016256830601093
},
{
"epoch": 0.7909397814771083,
"grad_norm": 2.015625,
"learning_rate": 2.206308366062645e-06,
"loss": 0.7541178703308106,
"step": 11890,
"token_acc": 0.8152556017710989
},
{
"epoch": 0.7916049957592589,
"grad_norm": 1.9765625,
"learning_rate": 2.192827547392733e-06,
"loss": 0.737539529800415,
"step": 11900,
"token_acc": 0.8185660700002758
},
{
"epoch": 0.7922702100414096,
"grad_norm": 2.4375,
"learning_rate": 2.1793829663007404e-06,
"loss": 0.7914046287536621,
"step": 11910,
"token_acc": 0.8103318334788416
},
{
"epoch": 0.7929354243235602,
"grad_norm": 2.453125,
"learning_rate": 2.1659746851907015e-06,
"loss": 0.716754150390625,
"step": 11920,
"token_acc": 0.825658600623572
},
{
"epoch": 0.7936006386057108,
"grad_norm": 2.203125,
"learning_rate": 2.152602766298162e-06,
"loss": 0.7402582168579102,
"step": 11930,
"token_acc": 0.8175593317559332
},
{
"epoch": 0.7942658528878616,
"grad_norm": 2.296875,
"learning_rate": 2.1392672716898875e-06,
"loss": 0.7885359287261963,
"step": 11940,
"token_acc": 0.8097111756371951
},
{
"epoch": 0.7949310671700122,
"grad_norm": 2.265625,
"learning_rate": 2.125968263263579e-06,
"loss": 0.74464111328125,
"step": 11950,
"token_acc": 0.8170758447033194
},
{
"epoch": 0.7955962814521628,
"grad_norm": 2.3125,
"learning_rate": 2.1127058027475877e-06,
"loss": 0.733258867263794,
"step": 11960,
"token_acc": 0.8242766407904023
},
{
"epoch": 0.7962614957343134,
"grad_norm": 2.125,
"learning_rate": 2.0994799517006146e-06,
"loss": 0.7569648265838623,
"step": 11970,
"token_acc": 0.8142647457792185
},
{
"epoch": 0.7969267100164641,
"grad_norm": 2.234375,
"learning_rate": 2.0862907715114435e-06,
"loss": 0.7476845741271972,
"step": 11980,
"token_acc": 0.8201262413058337
},
{
"epoch": 0.7975919242986147,
"grad_norm": 2.09375,
"learning_rate": 2.0731383233986526e-06,
"loss": 0.7600986957550049,
"step": 11990,
"token_acc": 0.817885262777175
},
{
"epoch": 0.7982571385807653,
"grad_norm": 1.9921875,
"learning_rate": 2.0600226684103098e-06,
"loss": 0.7477683067321778,
"step": 12000,
"token_acc": 0.8188194303038531
},
{
"epoch": 0.798922352862916,
"grad_norm": 2.34375,
"learning_rate": 2.0469438674237187e-06,
"loss": 0.7259119987487793,
"step": 12010,
"token_acc": 0.8261348005502063
},
{
"epoch": 0.7995875671450666,
"grad_norm": 2.265625,
"learning_rate": 2.0339019811451154e-06,
"loss": 0.8035065650939941,
"step": 12020,
"token_acc": 0.8065029434663243
},
{
"epoch": 0.8002527814272172,
"grad_norm": 2.25,
"learning_rate": 2.0208970701093966e-06,
"loss": 0.6975488662719727,
"step": 12030,
"token_acc": 0.8284871066514184
},
{
"epoch": 0.8009179957093678,
"grad_norm": 1.9375,
"learning_rate": 2.0079291946798343e-06,
"loss": 0.77200288772583,
"step": 12040,
"token_acc": 0.8162570539153672
},
{
"epoch": 0.8015832099915186,
"grad_norm": 1.8359375,
"learning_rate": 1.9949984150477975e-06,
"loss": 0.7325646877288818,
"step": 12050,
"token_acc": 0.8206230947291195
},
{
"epoch": 0.8022484242736692,
"grad_norm": 2.296875,
"learning_rate": 1.982104791232473e-06,
"loss": 0.7205623626708985,
"step": 12060,
"token_acc": 0.8245385707524846
},
{
"epoch": 0.8029136385558198,
"grad_norm": 2.515625,
"learning_rate": 1.9692483830805863e-06,
"loss": 0.6964698791503906,
"step": 12070,
"token_acc": 0.8283605174353206
},
{
"epoch": 0.8035788528379705,
"grad_norm": 2.328125,
"learning_rate": 1.956429250266114e-06,
"loss": 0.7393205642700196,
"step": 12080,
"token_acc": 0.8223958579761671
},
{
"epoch": 0.8042440671201211,
"grad_norm": 2.5,
"learning_rate": 1.943647452290035e-06,
"loss": 0.739701223373413,
"step": 12090,
"token_acc": 0.8188068245594343
},
{
"epoch": 0.8049092814022717,
"grad_norm": 2.234375,
"learning_rate": 1.930903048480024e-06,
"loss": 0.7362034797668457,
"step": 12100,
"token_acc": 0.8193545014343686
},
{
"epoch": 0.8055744956844223,
"grad_norm": 1.84375,
"learning_rate": 1.918196097990186e-06,
"loss": 0.7076382160186767,
"step": 12110,
"token_acc": 0.8275230239229197
},
{
"epoch": 0.806239709966573,
"grad_norm": 1.875,
"learning_rate": 1.9055266598007837e-06,
"loss": 0.7217838764190674,
"step": 12120,
"token_acc": 0.8229313185709118
},
{
"epoch": 0.8069049242487236,
"grad_norm": 2.53125,
"learning_rate": 1.8928947927179774e-06,
"loss": 0.7601078033447266,
"step": 12130,
"token_acc": 0.816590326569808
},
{
"epoch": 0.8075701385308742,
"grad_norm": 2.359375,
"learning_rate": 1.880300555373521e-06,
"loss": 0.7383596897125244,
"step": 12140,
"token_acc": 0.8207176063893193
},
{
"epoch": 0.8082353528130249,
"grad_norm": 2.359375,
"learning_rate": 1.8677440062245134e-06,
"loss": 0.7522371292114258,
"step": 12150,
"token_acc": 0.8152425116686555
},
{
"epoch": 0.8089005670951755,
"grad_norm": 2.078125,
"learning_rate": 1.8552252035531238e-06,
"loss": 0.7690191268920898,
"step": 12160,
"token_acc": 0.817273856703614
},
{
"epoch": 0.8095657813773262,
"grad_norm": 2.046875,
"learning_rate": 1.8427442054663159e-06,
"loss": 0.7667648792266846,
"step": 12170,
"token_acc": 0.814929986003534
},
{
"epoch": 0.8102309956594768,
"grad_norm": 1.953125,
"learning_rate": 1.8303010698955803e-06,
"loss": 0.7468802452087402,
"step": 12180,
"token_acc": 0.8176888756057469
},
{
"epoch": 0.8108962099416275,
"grad_norm": 2.21875,
"learning_rate": 1.8178958545966663e-06,
"loss": 0.7648351669311524,
"step": 12190,
"token_acc": 0.8128869218735375
},
{
"epoch": 0.8115614242237781,
"grad_norm": 2.046875,
"learning_rate": 1.8055286171493135e-06,
"loss": 0.7331006050109863,
"step": 12200,
"token_acc": 0.8220014994826166
},
{
"epoch": 0.8122266385059287,
"grad_norm": 2.59375,
"learning_rate": 1.7931994149569865e-06,
"loss": 0.7772156715393066,
"step": 12210,
"token_acc": 0.8127629733520336
},
{
"epoch": 0.8128918527880794,
"grad_norm": 2.109375,
"learning_rate": 1.780908305246597e-06,
"loss": 0.7343027591705322,
"step": 12220,
"token_acc": 0.8207935622980661
},
{
"epoch": 0.81355706707023,
"grad_norm": 2.109375,
"learning_rate": 1.768655345068262e-06,
"loss": 0.768639326095581,
"step": 12230,
"token_acc": 0.813776887186578
},
{
"epoch": 0.8142222813523806,
"grad_norm": 2.265625,
"learning_rate": 1.7564405912950178e-06,
"loss": 0.7219296455383301,
"step": 12240,
"token_acc": 0.8235673885278804
},
{
"epoch": 0.8148874956345312,
"grad_norm": 2.671875,
"learning_rate": 1.744264100622558e-06,
"loss": 0.7291380405426026,
"step": 12250,
"token_acc": 0.8228839549028116
},
{
"epoch": 0.8155527099166819,
"grad_norm": 2.25,
"learning_rate": 1.7321259295689785e-06,
"loss": 0.7431364059448242,
"step": 12260,
"token_acc": 0.8195356285028023
},
{
"epoch": 0.8162179241988325,
"grad_norm": 1.90625,
"learning_rate": 1.7200261344745205e-06,
"loss": 0.76451096534729,
"step": 12270,
"token_acc": 0.8156587620492104
},
{
"epoch": 0.8168831384809832,
"grad_norm": 1.984375,
"learning_rate": 1.707964771501286e-06,
"loss": 0.7611779689788818,
"step": 12280,
"token_acc": 0.8145329046898638
},
{
"epoch": 0.8175483527631339,
"grad_norm": 2.140625,
"learning_rate": 1.6959418966329999e-06,
"loss": 0.7500142574310302,
"step": 12290,
"token_acc": 0.8154514690047685
},
{
"epoch": 0.8182135670452845,
"grad_norm": 2.734375,
"learning_rate": 1.6839575656747386e-06,
"loss": 0.7421700477600097,
"step": 12300,
"token_acc": 0.816257124037002
},
{
"epoch": 0.8188787813274351,
"grad_norm": 2.421875,
"learning_rate": 1.6720118342526782e-06,
"loss": 0.7606112957000732,
"step": 12310,
"token_acc": 0.8181655271283634
},
{
"epoch": 0.8195439956095857,
"grad_norm": 2.015625,
"learning_rate": 1.6601047578138273e-06,
"loss": 0.7495483875274658,
"step": 12320,
"token_acc": 0.8195997507654582
},
{
"epoch": 0.8202092098917364,
"grad_norm": 2.4375,
"learning_rate": 1.648236391625776e-06,
"loss": 0.6780556678771973,
"step": 12330,
"token_acc": 0.8346865506766087
},
{
"epoch": 0.820874424173887,
"grad_norm": 1.9140625,
"learning_rate": 1.636406790776439e-06,
"loss": 0.7678157329559326,
"step": 12340,
"token_acc": 0.8124002569315224
},
{
"epoch": 0.8215396384560376,
"grad_norm": 2.078125,
"learning_rate": 1.6246160101738018e-06,
"loss": 0.7722493171691894,
"step": 12350,
"token_acc": 0.8122545117209345
},
{
"epoch": 0.8222048527381883,
"grad_norm": 2.25,
"learning_rate": 1.6128641045456494e-06,
"loss": 0.7382788181304931,
"step": 12360,
"token_acc": 0.8185960574024422
},
{
"epoch": 0.8228700670203389,
"grad_norm": 2.0625,
"learning_rate": 1.6011511284393433e-06,
"loss": 0.7551382064819336,
"step": 12370,
"token_acc": 0.8168432818175956
},
{
"epoch": 0.8235352813024895,
"grad_norm": 2.1875,
"learning_rate": 1.5894771362215432e-06,
"loss": 0.705793809890747,
"step": 12380,
"token_acc": 0.8273193211526816
},
{
"epoch": 0.8242004955846401,
"grad_norm": 2.0625,
"learning_rate": 1.5778421820779576e-06,
"loss": 0.7620275020599365,
"step": 12390,
"token_acc": 0.8180935231397459
},
{
"epoch": 0.8248657098667909,
"grad_norm": 2.734375,
"learning_rate": 1.5662463200131028e-06,
"loss": 0.7643431663513184,
"step": 12400,
"token_acc": 0.8124061356780694
},
{
"epoch": 0.8255309241489415,
"grad_norm": 2.03125,
"learning_rate": 1.5546896038500403e-06,
"loss": 0.7291480541229248,
"step": 12410,
"token_acc": 0.8193728589590236
},
{
"epoch": 0.8261961384310921,
"grad_norm": 2.53125,
"learning_rate": 1.543172087230147e-06,
"loss": 0.729656457901001,
"step": 12420,
"token_acc": 0.8244187221268059
},
{
"epoch": 0.8268613527132428,
"grad_norm": 2.59375,
"learning_rate": 1.5316938236128332e-06,
"loss": 0.7139503002166748,
"step": 12430,
"token_acc": 0.8234331294378017
},
{
"epoch": 0.8275265669953934,
"grad_norm": 2.546875,
"learning_rate": 1.5202548662753247e-06,
"loss": 0.7956299304962158,
"step": 12440,
"token_acc": 0.8066082152796669
},
{
"epoch": 0.828191781277544,
"grad_norm": 2.203125,
"learning_rate": 1.5088552683124036e-06,
"loss": 0.7592096328735352,
"step": 12450,
"token_acc": 0.8156857153042673
},
{
"epoch": 0.8288569955596947,
"grad_norm": 2.296875,
"learning_rate": 1.49749508263616e-06,
"loss": 0.6916064739227294,
"step": 12460,
"token_acc": 0.8311400277049132
},
{
"epoch": 0.8295222098418453,
"grad_norm": 2.046875,
"learning_rate": 1.4861743619757497e-06,
"loss": 0.7815629959106445,
"step": 12470,
"token_acc": 0.811484525266655
},
{
"epoch": 0.8301874241239959,
"grad_norm": 1.890625,
"learning_rate": 1.4748931588771486e-06,
"loss": 0.7507816314697265,
"step": 12480,
"token_acc": 0.817081788943854
},
{
"epoch": 0.8308526384061465,
"grad_norm": 2.390625,
"learning_rate": 1.4636515257029116e-06,
"loss": 0.7319404602050781,
"step": 12490,
"token_acc": 0.8256226342549934
},
{
"epoch": 0.8315178526882973,
"grad_norm": 2.75,
"learning_rate": 1.4524495146319184e-06,
"loss": 0.710325050354004,
"step": 12500,
"token_acc": 0.8248488121670368
},
{
"epoch": 0.8321830669704479,
"grad_norm": 2.328125,
"learning_rate": 1.441287177659151e-06,
"loss": 0.7421144008636474,
"step": 12510,
"token_acc": 0.8172642963289118
},
{
"epoch": 0.8328482812525985,
"grad_norm": 2.09375,
"learning_rate": 1.4301645665954357e-06,
"loss": 0.7401434421539307,
"step": 12520,
"token_acc": 0.8226652881746322
},
{
"epoch": 0.8335134955347492,
"grad_norm": 2.0,
"learning_rate": 1.4190817330672047e-06,
"loss": 0.7506049633026123,
"step": 12530,
"token_acc": 0.81846830581361
},
{
"epoch": 0.8341787098168998,
"grad_norm": 2.453125,
"learning_rate": 1.4080387285162645e-06,
"loss": 0.7490301609039307,
"step": 12540,
"token_acc": 0.8182030424418176
},
{
"epoch": 0.8348439240990504,
"grad_norm": 2.390625,
"learning_rate": 1.3970356041995492e-06,
"loss": 0.7642875671386719,
"step": 12550,
"token_acc": 0.8143642492175169
},
{
"epoch": 0.835509138381201,
"grad_norm": 2.109375,
"learning_rate": 1.3860724111888934e-06,
"loss": 0.68789701461792,
"step": 12560,
"token_acc": 0.8304143113997077
},
{
"epoch": 0.8361743526633517,
"grad_norm": 2.09375,
"learning_rate": 1.3751492003707757e-06,
"loss": 0.7259564876556397,
"step": 12570,
"token_acc": 0.8198569999629534
},
{
"epoch": 0.8368395669455023,
"grad_norm": 2.421875,
"learning_rate": 1.3642660224461034e-06,
"loss": 0.7669519424438477,
"step": 12580,
"token_acc": 0.8151452552690637
},
{
"epoch": 0.8375047812276529,
"grad_norm": 2.265625,
"learning_rate": 1.3534229279299637e-06,
"loss": 0.7269845485687256,
"step": 12590,
"token_acc": 0.8242235361386356
},
{
"epoch": 0.8381699955098036,
"grad_norm": 2.640625,
"learning_rate": 1.342619967151395e-06,
"loss": 0.7418327808380127,
"step": 12600,
"token_acc": 0.8111864259173247
},
{
"epoch": 0.8388352097919543,
"grad_norm": 2.421875,
"learning_rate": 1.331857190253154e-06,
"loss": 0.725627326965332,
"step": 12610,
"token_acc": 0.8239855072463768
},
{
"epoch": 0.8395004240741049,
"grad_norm": 2.453125,
"learning_rate": 1.3211346471914766e-06,
"loss": 0.6911958694458008,
"step": 12620,
"token_acc": 0.8333344906844806
},
{
"epoch": 0.8401656383562555,
"grad_norm": 2.15625,
"learning_rate": 1.3104523877358554e-06,
"loss": 0.7832218647003174,
"step": 12630,
"token_acc": 0.8087223102737534
},
{
"epoch": 0.8408308526384062,
"grad_norm": 2.140625,
"learning_rate": 1.2998104614687946e-06,
"loss": 0.739612627029419,
"step": 12640,
"token_acc": 0.819972264538915
},
{
"epoch": 0.8414960669205568,
"grad_norm": 2.3125,
"learning_rate": 1.2892089177856003e-06,
"loss": 0.7351601123809814,
"step": 12650,
"token_acc": 0.8226423204043218
},
{
"epoch": 0.8421612812027074,
"grad_norm": 2.203125,
"learning_rate": 1.2786478058941354e-06,
"loss": 0.7449721336364746,
"step": 12660,
"token_acc": 0.81940742621032
},
{
"epoch": 0.8428264954848581,
"grad_norm": 2.078125,
"learning_rate": 1.268127174814594e-06,
"loss": 0.746445894241333,
"step": 12670,
"token_acc": 0.8168626936385046
},
{
"epoch": 0.8434917097670087,
"grad_norm": 2.234375,
"learning_rate": 1.2576470733792734e-06,
"loss": 0.7860873222351075,
"step": 12680,
"token_acc": 0.805779400654747
},
{
"epoch": 0.8441569240491593,
"grad_norm": 2.09375,
"learning_rate": 1.2472075502323521e-06,
"loss": 0.7526457786560059,
"step": 12690,
"token_acc": 0.8191349659825932
},
{
"epoch": 0.8448221383313099,
"grad_norm": 2.078125,
"learning_rate": 1.2368086538296676e-06,
"loss": 0.7363354682922363,
"step": 12700,
"token_acc": 0.8211748065012922
},
{
"epoch": 0.8454873526134606,
"grad_norm": 1.984375,
"learning_rate": 1.226450432438474e-06,
"loss": 0.7500771045684814,
"step": 12710,
"token_acc": 0.8186567164179105
},
{
"epoch": 0.8461525668956112,
"grad_norm": 2.46875,
"learning_rate": 1.2161329341372364e-06,
"loss": 0.7871901035308838,
"step": 12720,
"token_acc": 0.8112322902864132
},
{
"epoch": 0.8468177811777619,
"grad_norm": 1.7890625,
"learning_rate": 1.2058562068153979e-06,
"loss": 0.7285461902618409,
"step": 12730,
"token_acc": 0.8226884136200507
},
{
"epoch": 0.8474829954599126,
"grad_norm": 2.265625,
"learning_rate": 1.1956202981731623e-06,
"loss": 0.7703880786895752,
"step": 12740,
"token_acc": 0.8149514402559325
},
{
"epoch": 0.8481482097420632,
"grad_norm": 2.09375,
"learning_rate": 1.1854252557212686e-06,
"loss": 0.7086236476898193,
"step": 12750,
"token_acc": 0.8280805899149977
},
{
"epoch": 0.8488134240242138,
"grad_norm": 2.765625,
"learning_rate": 1.1752711267807726e-06,
"loss": 0.7329237937927247,
"step": 12760,
"token_acc": 0.8225149067854177
},
{
"epoch": 0.8494786383063644,
"grad_norm": 2.546875,
"learning_rate": 1.1651579584828298e-06,
"loss": 0.7215950012207031,
"step": 12770,
"token_acc": 0.8203919835164444
},
{
"epoch": 0.8501438525885151,
"grad_norm": 2.359375,
"learning_rate": 1.155085797768465e-06,
"loss": 0.7757081508636474,
"step": 12780,
"token_acc": 0.8136971738531787
},
{
"epoch": 0.8508090668706657,
"grad_norm": 2.265625,
"learning_rate": 1.1450546913883743e-06,
"loss": 0.7807986736297607,
"step": 12790,
"token_acc": 0.8108581436077058
},
{
"epoch": 0.8514742811528163,
"grad_norm": 2.15625,
"learning_rate": 1.1350646859026926e-06,
"loss": 0.7674762725830078,
"step": 12800,
"token_acc": 0.8154182735093444
},
{
"epoch": 0.852139495434967,
"grad_norm": 2.484375,
"learning_rate": 1.1251158276807817e-06,
"loss": 0.800546932220459,
"step": 12810,
"token_acc": 0.8074464009722461
},
{
"epoch": 0.8528047097171176,
"grad_norm": 2.34375,
"learning_rate": 1.1152081629010102e-06,
"loss": 0.7580554008483886,
"step": 12820,
"token_acc": 0.8151567812618058
},
{
"epoch": 0.8534699239992682,
"grad_norm": 1.9765625,
"learning_rate": 1.1053417375505514e-06,
"loss": 0.7284594058990479,
"step": 12830,
"token_acc": 0.8234221641496248
},
{
"epoch": 0.8541351382814188,
"grad_norm": 2.75,
"learning_rate": 1.0955165974251657e-06,
"loss": 0.7424296379089356,
"step": 12840,
"token_acc": 0.8168002419476789
},
{
"epoch": 0.8548003525635696,
"grad_norm": 2.375,
"learning_rate": 1.0857327881289726e-06,
"loss": 0.7666614055633545,
"step": 12850,
"token_acc": 0.8153631382403239
},
{
"epoch": 0.8554655668457202,
"grad_norm": 2.4375,
"learning_rate": 1.0759903550742613e-06,
"loss": 0.7432961940765381,
"step": 12860,
"token_acc": 0.8213769658725228
},
{
"epoch": 0.8561307811278708,
"grad_norm": 2.09375,
"learning_rate": 1.066289343481267e-06,
"loss": 0.7240518093109131,
"step": 12870,
"token_acc": 0.8237197867025239
},
{
"epoch": 0.8567959954100215,
"grad_norm": 2.359375,
"learning_rate": 1.056629798377965e-06,
"loss": 0.7952365398406982,
"step": 12880,
"token_acc": 0.8105818414322251
},
{
"epoch": 0.8574612096921721,
"grad_norm": 2.03125,
"learning_rate": 1.047011764599859e-06,
"loss": 0.7083343029022217,
"step": 12890,
"token_acc": 0.8284742135085817
},
{
"epoch": 0.8581264239743227,
"grad_norm": 1.7734375,
"learning_rate": 1.0374352867897774e-06,
"loss": 0.6590012550354004,
"step": 12900,
"token_acc": 0.8368652564437173
},
{
"epoch": 0.8587916382564734,
"grad_norm": 2.125,
"learning_rate": 1.0279004093976608e-06,
"loss": 0.7335064888000489,
"step": 12910,
"token_acc": 0.8238477200366215
},
{
"epoch": 0.859456852538624,
"grad_norm": 2.203125,
"learning_rate": 1.0184071766803604e-06,
"loss": 0.728295087814331,
"step": 12920,
"token_acc": 0.8247248599467599
},
{
"epoch": 0.8601220668207746,
"grad_norm": 2.15625,
"learning_rate": 1.0089556327014282e-06,
"loss": 0.7359903812408447,
"step": 12930,
"token_acc": 0.8194429933881584
},
{
"epoch": 0.8607872811029252,
"grad_norm": 1.9140625,
"learning_rate": 9.995458213309184e-07,
"loss": 0.7680520057678223,
"step": 12940,
"token_acc": 0.810745918258457
},
{
"epoch": 0.861452495385076,
"grad_norm": 2.0625,
"learning_rate": 9.901777862451779e-07,
"loss": 0.7582465648651123,
"step": 12950,
"token_acc": 0.8159220807907889
},
{
"epoch": 0.8621177096672266,
"grad_norm": 2.078125,
"learning_rate": 9.80851570926642e-07,
"loss": 0.7138647556304931,
"step": 12960,
"token_acc": 0.8266051910084578
},
{
"epoch": 0.8627829239493772,
"grad_norm": 2.1875,
"learning_rate": 9.715672186636417e-07,
"loss": 0.7412016868591309,
"step": 12970,
"token_acc": 0.8185737193949449
},
{
"epoch": 0.8634481382315279,
"grad_norm": 2.125,
"learning_rate": 9.623247725502006e-07,
"loss": 0.7839868068695068,
"step": 12980,
"token_acc": 0.8117788941635556
},
{
"epoch": 0.8641133525136785,
"grad_norm": 2.1875,
"learning_rate": 9.531242754858227e-07,
"loss": 0.7455582618713379,
"step": 12990,
"token_acc": 0.8201620427862767
},
{
"epoch": 0.8647785667958291,
"grad_norm": 1.890625,
"learning_rate": 9.43965770175308e-07,
"loss": 0.7250793933868408,
"step": 13000,
"token_acc": 0.822643199031361
},
{
"epoch": 0.8654437810779797,
"grad_norm": 2.390625,
"learning_rate": 9.348492991285463e-07,
"loss": 0.7411177635192872,
"step": 13010,
"token_acc": 0.8192769424680933
},
{
"epoch": 0.8661089953601304,
"grad_norm": 2.0625,
"learning_rate": 9.257749046603259e-07,
"loss": 0.7831026077270508,
"step": 13020,
"token_acc": 0.8101883171994736
},
{
"epoch": 0.866774209642281,
"grad_norm": 2.296875,
"learning_rate": 9.167426288901293e-07,
"loss": 0.7803151130676269,
"step": 13030,
"token_acc": 0.8123504774669124
},
{
"epoch": 0.8674394239244316,
"grad_norm": 2.234375,
"learning_rate": 9.07752513741944e-07,
"loss": 0.7455216407775879,
"step": 13040,
"token_acc": 0.8166975358350781
},
{
"epoch": 0.8681046382065823,
"grad_norm": 1.9765625,
"learning_rate": 8.988046009440665e-07,
"loss": 0.7800196170806885,
"step": 13050,
"token_acc": 0.8122681583318561
},
{
"epoch": 0.868769852488733,
"grad_norm": 2.078125,
"learning_rate": 8.898989320289042e-07,
"loss": 0.7537990570068359,
"step": 13060,
"token_acc": 0.8186883958644726
},
{
"epoch": 0.8694350667708836,
"grad_norm": 2.25,
"learning_rate": 8.810355483327915e-07,
"loss": 0.7591912746429443,
"step": 13070,
"token_acc": 0.8177129937637038
},
{
"epoch": 0.8701002810530342,
"grad_norm": 2.203125,
"learning_rate": 8.722144909957874e-07,
"loss": 0.7606600284576416,
"step": 13080,
"token_acc": 0.8152078518561858
},
{
"epoch": 0.8707654953351849,
"grad_norm": 1.9765625,
"learning_rate": 8.634358009614985e-07,
"loss": 0.7688061237335205,
"step": 13090,
"token_acc": 0.8100127848692088
},
{
"epoch": 0.8714307096173355,
"grad_norm": 2.21875,
"learning_rate": 8.54699518976867e-07,
"loss": 0.7757150173187256,
"step": 13100,
"token_acc": 0.8124304450110583
},
{
"epoch": 0.8720959238994861,
"grad_norm": 2.078125,
"learning_rate": 8.460056855920051e-07,
"loss": 0.775514030456543,
"step": 13110,
"token_acc": 0.8147016963025857
},
{
"epoch": 0.8727611381816368,
"grad_norm": 2.4375,
"learning_rate": 8.373543411599993e-07,
"loss": 0.7836643695831299,
"step": 13120,
"token_acc": 0.8066403877046857
},
{
"epoch": 0.8734263524637874,
"grad_norm": 2.6875,
"learning_rate": 8.287455258367083e-07,
"loss": 0.7556148052215577,
"step": 13130,
"token_acc": 0.8172252317155959
},
{
"epoch": 0.874091566745938,
"grad_norm": 2.59375,
"learning_rate": 8.201792795805985e-07,
"loss": 0.7418502807617188,
"step": 13140,
"token_acc": 0.8174628347629423
},
{
"epoch": 0.8747567810280886,
"grad_norm": 2.171875,
"learning_rate": 8.116556421525467e-07,
"loss": 0.7138179302215576,
"step": 13150,
"token_acc": 0.8282519739496282
},
{
"epoch": 0.8754219953102393,
"grad_norm": 2.265625,
"learning_rate": 8.031746531156559e-07,
"loss": 0.7524651050567627,
"step": 13160,
"token_acc": 0.8180933509156683
},
{
"epoch": 0.87608720959239,
"grad_norm": 1.90625,
"learning_rate": 7.947363518350748e-07,
"loss": 0.7429336547851563,
"step": 13170,
"token_acc": 0.8234292657885673
},
{
"epoch": 0.8767524238745406,
"grad_norm": 1.7265625,
"learning_rate": 7.86340777477812e-07,
"loss": 0.7226759910583496,
"step": 13180,
"token_acc": 0.8244128253222435
},
{
"epoch": 0.8774176381566913,
"grad_norm": 2.4375,
"learning_rate": 7.779879690125592e-07,
"loss": 0.7520774364471435,
"step": 13190,
"token_acc": 0.817699127812606
},
{
"epoch": 0.8780828524388419,
"grad_norm": 1.9921875,
"learning_rate": 7.696779652095043e-07,
"loss": 0.805053424835205,
"step": 13200,
"token_acc": 0.8062535295841703
},
{
"epoch": 0.8787480667209925,
"grad_norm": 2.046875,
"learning_rate": 7.614108046401513e-07,
"loss": 0.8226052284240722,
"step": 13210,
"token_acc": 0.7965224016477592
},
{
"epoch": 0.8794132810031431,
"grad_norm": 2.03125,
"learning_rate": 7.53186525677152e-07,
"loss": 0.8116080284118652,
"step": 13220,
"token_acc": 0.8094030344505491
},
{
"epoch": 0.8800784952852938,
"grad_norm": 2.140625,
"learning_rate": 7.45005166494116e-07,
"loss": 0.7549985408782959,
"step": 13230,
"token_acc": 0.8144020132290049
},
{
"epoch": 0.8807437095674444,
"grad_norm": 2.21875,
"learning_rate": 7.368667650654337e-07,
"loss": 0.8589279174804687,
"step": 13240,
"token_acc": 0.7950872656755009
},
{
"epoch": 0.881408923849595,
"grad_norm": 2.21875,
"learning_rate": 7.287713591661061e-07,
"loss": 0.760920524597168,
"step": 13250,
"token_acc": 0.8157280952217139
},
{
"epoch": 0.8820741381317457,
"grad_norm": 2.234375,
"learning_rate": 7.207189863715747e-07,
"loss": 0.7139156818389892,
"step": 13260,
"token_acc": 0.827196529470048
},
{
"epoch": 0.8827393524138963,
"grad_norm": 2.53125,
"learning_rate": 7.127096840575276e-07,
"loss": 0.7730007648468018,
"step": 13270,
"token_acc": 0.813000487930886
},
{
"epoch": 0.883404566696047,
"grad_norm": 2.421875,
"learning_rate": 7.047434893997451e-07,
"loss": 0.7661628723144531,
"step": 13280,
"token_acc": 0.8150740969984135
},
{
"epoch": 0.8840697809781976,
"grad_norm": 2.296875,
"learning_rate": 6.968204393739197e-07,
"loss": 0.7571478843688965,
"step": 13290,
"token_acc": 0.8160553962509861
},
{
"epoch": 0.8847349952603483,
"grad_norm": 2.546875,
"learning_rate": 6.889405707554819e-07,
"loss": 0.7427309036254883,
"step": 13300,
"token_acc": 0.8197933233117651
},
{
"epoch": 0.8854002095424989,
"grad_norm": 2.46875,
"learning_rate": 6.811039201194369e-07,
"loss": 0.779467248916626,
"step": 13310,
"token_acc": 0.812604294498445
},
{
"epoch": 0.8860654238246495,
"grad_norm": 2.1875,
"learning_rate": 6.733105238401849e-07,
"loss": 0.7616754055023194,
"step": 13320,
"token_acc": 0.8161051985134442
},
{
"epoch": 0.8867306381068002,
"grad_norm": 2.1875,
"learning_rate": 6.655604180913633e-07,
"loss": 0.7989961624145507,
"step": 13330,
"token_acc": 0.8055249517527968
},
{
"epoch": 0.8873958523889508,
"grad_norm": 2.21875,
"learning_rate": 6.578536388456713e-07,
"loss": 0.7707967758178711,
"step": 13340,
"token_acc": 0.8103733045424321
},
{
"epoch": 0.8880610666711014,
"grad_norm": 2.21875,
"learning_rate": 6.50190221874698e-07,
"loss": 0.7407102584838867,
"step": 13350,
"token_acc": 0.8193373292692074
},
{
"epoch": 0.888726280953252,
"grad_norm": 2.21875,
"learning_rate": 6.425702027487768e-07,
"loss": 0.7559770107269287,
"step": 13360,
"token_acc": 0.8151810648720413
},
{
"epoch": 0.8893914952354027,
"grad_norm": 2.3125,
"learning_rate": 6.349936168367965e-07,
"loss": 0.7173273086547851,
"step": 13370,
"token_acc": 0.8251174342638087
},
{
"epoch": 0.8900567095175533,
"grad_norm": 2.140625,
"learning_rate": 6.274604993060496e-07,
"loss": 0.7484136581420898,
"step": 13380,
"token_acc": 0.8187664551771764
},
{
"epoch": 0.8907219237997039,
"grad_norm": 2.15625,
"learning_rate": 6.199708851220665e-07,
"loss": 0.7472971439361572,
"step": 13390,
"token_acc": 0.8170596467140179
},
{
"epoch": 0.8913871380818547,
"grad_norm": 2.015625,
"learning_rate": 6.125248090484581e-07,
"loss": 0.7495847702026367,
"step": 13400,
"token_acc": 0.8190375353467533
},
{
"epoch": 0.8920523523640053,
"grad_norm": 2.21875,
"learning_rate": 6.051223056467448e-07,
"loss": 0.737662935256958,
"step": 13410,
"token_acc": 0.8236756001617588
},
{
"epoch": 0.8927175666461559,
"grad_norm": 2.203125,
"learning_rate": 5.977634092762019e-07,
"loss": 0.7727813243865966,
"step": 13420,
"token_acc": 0.8146888944694497
},
{
"epoch": 0.8933827809283066,
"grad_norm": 2.15625,
"learning_rate": 5.904481540937001e-07,
"loss": 0.7136052131652832,
"step": 13430,
"token_acc": 0.8289308629514816
},
{
"epoch": 0.8940479952104572,
"grad_norm": 2.484375,
"learning_rate": 5.831765740535467e-07,
"loss": 0.7773768901824951,
"step": 13440,
"token_acc": 0.8123344191096634
},
{
"epoch": 0.8947132094926078,
"grad_norm": 2.546875,
"learning_rate": 5.759487029073274e-07,
"loss": 0.7534355163574219,
"step": 13450,
"token_acc": 0.8203983516483516
},
{
"epoch": 0.8953784237747584,
"grad_norm": 2.015625,
"learning_rate": 5.687645742037485e-07,
"loss": 0.7715285778045654,
"step": 13460,
"token_acc": 0.8132360165625658
},
{
"epoch": 0.8960436380569091,
"grad_norm": 2.421875,
"learning_rate": 5.616242212884848e-07,
"loss": 0.7049496650695801,
"step": 13470,
"token_acc": 0.8300445326681729
},
{
"epoch": 0.8967088523390597,
"grad_norm": 2.53125,
"learning_rate": 5.545276773040232e-07,
"loss": 0.7721897602081299,
"step": 13480,
"token_acc": 0.812478217936803
},
{
"epoch": 0.8973740666212103,
"grad_norm": 2.171875,
"learning_rate": 5.474749751895003e-07,
"loss": 0.7733312129974366,
"step": 13490,
"token_acc": 0.8136938724882163
},
{
"epoch": 0.898039280903361,
"grad_norm": 1.984375,
"learning_rate": 5.404661476805672e-07,
"loss": 0.7222862243652344,
"step": 13500,
"token_acc": 0.8246481926761008
},
{
"epoch": 0.8987044951855117,
"grad_norm": 2.15625,
"learning_rate": 5.335012273092255e-07,
"loss": 0.7655940055847168,
"step": 13510,
"token_acc": 0.8143879144423866
},
{
"epoch": 0.8993697094676623,
"grad_norm": 2.015625,
"learning_rate": 5.265802464036729e-07,
"loss": 0.7593111991882324,
"step": 13520,
"token_acc": 0.8167902449309484
},
{
"epoch": 0.9000349237498129,
"grad_norm": 2.203125,
"learning_rate": 5.19703237088165e-07,
"loss": 0.7332557201385498,
"step": 13530,
"token_acc": 0.8237590976509951
},
{
"epoch": 0.9007001380319636,
"grad_norm": 1.7890625,
"learning_rate": 5.128702312828548e-07,
"loss": 0.7696627140045166,
"step": 13540,
"token_acc": 0.8126790553619821
},
{
"epoch": 0.9013653523141142,
"grad_norm": 1.9140625,
"learning_rate": 5.06081260703657e-07,
"loss": 0.7411143779754639,
"step": 13550,
"token_acc": 0.8146489915277056
},
{
"epoch": 0.9020305665962648,
"grad_norm": 2.109375,
"learning_rate": 4.993363568620846e-07,
"loss": 0.777694845199585,
"step": 13560,
"token_acc": 0.8094625500285878
},
{
"epoch": 0.9026957808784155,
"grad_norm": 2.15625,
"learning_rate": 4.926355510651193e-07,
"loss": 0.7542600631713867,
"step": 13570,
"token_acc": 0.8190626423163995
},
{
"epoch": 0.9033609951605661,
"grad_norm": 1.734375,
"learning_rate": 4.859788744150518e-07,
"loss": 0.7475131511688232,
"step": 13580,
"token_acc": 0.8155408629268626
},
{
"epoch": 0.9040262094427167,
"grad_norm": 2.125,
"learning_rate": 4.793663578093499e-07,
"loss": 0.7440214633941651,
"step": 13590,
"token_acc": 0.8193256386219827
},
{
"epoch": 0.9046914237248673,
"grad_norm": 2.078125,
"learning_rate": 4.727980319405057e-07,
"loss": 0.7644705772399902,
"step": 13600,
"token_acc": 0.8145106398893003
},
{
"epoch": 0.905356638007018,
"grad_norm": 2.078125,
"learning_rate": 4.6627392729589604e-07,
"loss": 0.7428989887237549,
"step": 13610,
"token_acc": 0.8167339675586887
},
{
"epoch": 0.9060218522891686,
"grad_norm": 2.34375,
"learning_rate": 4.597940741576479e-07,
"loss": 0.7543402194976807,
"step": 13620,
"token_acc": 0.8177948925820835
},
{
"epoch": 0.9066870665713193,
"grad_norm": 2.484375,
"learning_rate": 4.533585026024789e-07,
"loss": 0.7029013633728027,
"step": 13630,
"token_acc": 0.8265018763149043
},
{
"epoch": 0.90735228085347,
"grad_norm": 2.171875,
"learning_rate": 4.4696724250158585e-07,
"loss": 0.7716415882110595,
"step": 13640,
"token_acc": 0.8157385522888727
},
{
"epoch": 0.9080174951356206,
"grad_norm": 3.359375,
"learning_rate": 4.4062032352047866e-07,
"loss": 0.7716058731079102,
"step": 13650,
"token_acc": 0.8150425566422915
},
{
"epoch": 0.9086827094177712,
"grad_norm": 2.390625,
"learning_rate": 4.343177751188621e-07,
"loss": 0.8403903007507324,
"step": 13660,
"token_acc": 0.8027468657557403
},
{
"epoch": 0.9093479236999218,
"grad_norm": 2.03125,
"learning_rate": 4.280596265504855e-07,
"loss": 0.7076282024383544,
"step": 13670,
"token_acc": 0.8273977058080334
},
{
"epoch": 0.9100131379820725,
"grad_norm": 2.8125,
"learning_rate": 4.218459068630154e-07,
"loss": 0.7397566318511963,
"step": 13680,
"token_acc": 0.8224340337835351
},
{
"epoch": 0.9106783522642231,
"grad_norm": 2.4375,
"learning_rate": 4.156766448979044e-07,
"loss": 0.7387542724609375,
"step": 13690,
"token_acc": 0.8207437115430071
},
{
"epoch": 0.9113435665463737,
"grad_norm": 2.046875,
"learning_rate": 4.095518692902389e-07,
"loss": 0.742147970199585,
"step": 13700,
"token_acc": 0.8184483253905703
},
{
"epoch": 0.9120087808285244,
"grad_norm": 1.96875,
"learning_rate": 4.0347160846862967e-07,
"loss": 0.7561039924621582,
"step": 13710,
"token_acc": 0.8179737007233335
},
{
"epoch": 0.912673995110675,
"grad_norm": 1.6953125,
"learning_rate": 3.9743589065506236e-07,
"loss": 0.7782150745391846,
"step": 13720,
"token_acc": 0.8120687265342036
},
{
"epoch": 0.9133392093928256,
"grad_norm": 1.96875,
"learning_rate": 3.9144474386477724e-07,
"loss": 0.7652214527130127,
"step": 13730,
"token_acc": 0.8140341398595272
},
{
"epoch": 0.9140044236749763,
"grad_norm": 2.375,
"learning_rate": 3.8549819590612993e-07,
"loss": 0.713405704498291,
"step": 13740,
"token_acc": 0.8210895742996644
},
{
"epoch": 0.914669637957127,
"grad_norm": 2.296875,
"learning_rate": 3.7959627438047155e-07,
"loss": 0.7273184776306152,
"step": 13750,
"token_acc": 0.8225057024583932
},
{
"epoch": 0.9153348522392776,
"grad_norm": 2.65625,
"learning_rate": 3.737390066820157e-07,
"loss": 0.7514214038848877,
"step": 13760,
"token_acc": 0.8171638501102131
},
{
"epoch": 0.9160000665214282,
"grad_norm": 3.5625,
"learning_rate": 3.6792641999770615e-07,
"loss": 0.7540398597717285,
"step": 13770,
"token_acc": 0.8175094437743318
},
{
"epoch": 0.9166652808035789,
"grad_norm": 2.03125,
"learning_rate": 3.6215854130710605e-07,
"loss": 0.7616157054901123,
"step": 13780,
"token_acc": 0.8156927698326477
},
{
"epoch": 0.9173304950857295,
"grad_norm": 2.1875,
"learning_rate": 3.564353973822554e-07,
"loss": 0.7588217735290528,
"step": 13790,
"token_acc": 0.815572437421845
},
{
"epoch": 0.9179957093678801,
"grad_norm": 3.84375,
"learning_rate": 3.507570147875594e-07,
"loss": 0.7755050659179688,
"step": 13800,
"token_acc": 0.813603691218731
},
{
"epoch": 0.9186609236500307,
"grad_norm": 2.328125,
"learning_rate": 3.451234198796549e-07,
"loss": 0.7810738563537598,
"step": 13810,
"token_acc": 0.8108613289815167
},
{
"epoch": 0.9193261379321814,
"grad_norm": 2.5,
"learning_rate": 3.395346388072962e-07,
"loss": 0.7490992546081543,
"step": 13820,
"token_acc": 0.8152158627478554
},
{
"epoch": 0.919991352214332,
"grad_norm": 2.015625,
"learning_rate": 3.339906975112339e-07,
"loss": 0.7504191875457764,
"step": 13830,
"token_acc": 0.8188295098374905
},
{
"epoch": 0.9206565664964826,
"grad_norm": 2.296875,
"learning_rate": 3.2849162172408633e-07,
"loss": 0.7356757164001465,
"step": 13840,
"token_acc": 0.8221375375053579
},
{
"epoch": 0.9213217807786334,
"grad_norm": 2.03125,
"learning_rate": 3.2303743697022714e-07,
"loss": 0.6856590270996094,
"step": 13850,
"token_acc": 0.8318885280650027
},
{
"epoch": 0.921986995060784,
"grad_norm": 2.296875,
"learning_rate": 3.176281685656646e-07,
"loss": 0.786972951889038,
"step": 13860,
"token_acc": 0.8091591122225695
},
{
"epoch": 0.9226522093429346,
"grad_norm": 1.9921875,
"learning_rate": 3.1226384161792576e-07,
"loss": 0.7341162204742432,
"step": 13870,
"token_acc": 0.8197383517654806
},
{
"epoch": 0.9233174236250852,
"grad_norm": 1.890625,
"learning_rate": 3.069444810259359e-07,
"loss": 0.7607975006103516,
"step": 13880,
"token_acc": 0.8155827520217297
},
{
"epoch": 0.9239826379072359,
"grad_norm": 2.171875,
"learning_rate": 3.0167011147990923e-07,
"loss": 0.7848525524139405,
"step": 13890,
"token_acc": 0.8128864443395992
},
{
"epoch": 0.9246478521893865,
"grad_norm": 2.5625,
"learning_rate": 2.9644075746122714e-07,
"loss": 0.7113450527191162,
"step": 13900,
"token_acc": 0.828387881875168
},
{
"epoch": 0.9253130664715371,
"grad_norm": 2.3125,
"learning_rate": 2.912564432423304e-07,
"loss": 0.7673250675201416,
"step": 13910,
"token_acc": 0.8165538157709127
},
{
"epoch": 0.9259782807536878,
"grad_norm": 1.8671875,
"learning_rate": 2.8611719288660246e-07,
"loss": 0.7288234233856201,
"step": 13920,
"token_acc": 0.8237181834523992
},
{
"epoch": 0.9266434950358384,
"grad_norm": 2.328125,
"learning_rate": 2.8102303024826085e-07,
"loss": 0.7494546413421631,
"step": 13930,
"token_acc": 0.8173972704097076
},
{
"epoch": 0.927308709317989,
"grad_norm": 2.296875,
"learning_rate": 2.759739789722449e-07,
"loss": 0.6988474369049072,
"step": 13940,
"token_acc": 0.8314223626460034
},
{
"epoch": 0.9279739236001397,
"grad_norm": 2.59375,
"learning_rate": 2.709700624941036e-07,
"loss": 0.7844988822937011,
"step": 13950,
"token_acc": 0.8100103754875823
},
{
"epoch": 0.9286391378822904,
"grad_norm": 1.9765625,
"learning_rate": 2.660113040398915e-07,
"loss": 0.7000997066497803,
"step": 13960,
"token_acc": 0.8293918695749825
},
{
"epoch": 0.929304352164441,
"grad_norm": 2.125,
"learning_rate": 2.610977266260628e-07,
"loss": 0.7194863319396972,
"step": 13970,
"token_acc": 0.8239941409293483
},
{
"epoch": 0.9299695664465916,
"grad_norm": 1.8125,
"learning_rate": 2.562293530593529e-07,
"loss": 0.786644458770752,
"step": 13980,
"token_acc": 0.8122439964661473
},
{
"epoch": 0.9306347807287423,
"grad_norm": 2.109375,
"learning_rate": 2.514062059366851e-07,
"loss": 0.6964083671569824,
"step": 13990,
"token_acc": 0.8290147514114005
},
{
"epoch": 0.9312999950108929,
"grad_norm": 2.609375,
"learning_rate": 2.466283076450582e-07,
"loss": 0.734468936920166,
"step": 14000,
"token_acc": 0.8214124723808961
},
{
"epoch": 0.9319652092930435,
"grad_norm": 2.546875,
"learning_rate": 2.4189568036144697e-07,
"loss": 0.7554211616516113,
"step": 14010,
"token_acc": 0.8150565368255303
},
{
"epoch": 0.9326304235751942,
"grad_norm": 2.671875,
"learning_rate": 2.3720834605269638e-07,
"loss": 0.7122709274291992,
"step": 14020,
"token_acc": 0.8256758344680762
},
{
"epoch": 0.9332956378573448,
"grad_norm": 2.296875,
"learning_rate": 2.3256632647542298e-07,
"loss": 0.7087862968444825,
"step": 14030,
"token_acc": 0.8257711472744517
},
{
"epoch": 0.9339608521394954,
"grad_norm": 2.234375,
"learning_rate": 2.279696431759071e-07,
"loss": 0.8106839179992675,
"step": 14040,
"token_acc": 0.8022435008850313
},
{
"epoch": 0.934626066421646,
"grad_norm": 2.296875,
"learning_rate": 2.2341831749000176e-07,
"loss": 0.7724443435668945,
"step": 14050,
"token_acc": 0.8113166809366043
},
{
"epoch": 0.9352912807037967,
"grad_norm": 1.96875,
"learning_rate": 2.1891237054302627e-07,
"loss": 0.7082020282745362,
"step": 14060,
"token_acc": 0.8263985137565981
},
{
"epoch": 0.9359564949859474,
"grad_norm": 2.046875,
"learning_rate": 2.1445182324967174e-07,
"loss": 0.7266581535339356,
"step": 14070,
"token_acc": 0.8243995956638432
},
{
"epoch": 0.936621709268098,
"grad_norm": 2.09375,
"learning_rate": 2.1003669631390665e-07,
"loss": 0.7394362449645996,
"step": 14080,
"token_acc": 0.8214288059574076
},
{
"epoch": 0.9372869235502487,
"grad_norm": 2.1875,
"learning_rate": 2.0566701022887047e-07,
"loss": 0.7446671962738037,
"step": 14090,
"token_acc": 0.8192597839560829
},
{
"epoch": 0.9379521378323993,
"grad_norm": 2.140625,
"learning_rate": 2.0134278527679241e-07,
"loss": 0.7418570995330811,
"step": 14100,
"token_acc": 0.8184572327134758
},
{
"epoch": 0.9386173521145499,
"grad_norm": 2.34375,
"learning_rate": 1.9706404152888715e-07,
"loss": 0.7619320392608643,
"step": 14110,
"token_acc": 0.81469913446213
},
{
"epoch": 0.9392825663967005,
"grad_norm": 2.328125,
"learning_rate": 1.928307988452649e-07,
"loss": 0.7874303817749023,
"step": 14120,
"token_acc": 0.8113426833702914
},
{
"epoch": 0.9399477806788512,
"grad_norm": 1.9609375,
"learning_rate": 1.886430768748404e-07,
"loss": 0.7038110733032227,
"step": 14130,
"token_acc": 0.8292715550680827
},
{
"epoch": 0.9406129949610018,
"grad_norm": 1.9375,
"learning_rate": 1.8450089505524072e-07,
"loss": 0.7631545543670655,
"step": 14140,
"token_acc": 0.8139588468171567
},
{
"epoch": 0.9412782092431524,
"grad_norm": 2.234375,
"learning_rate": 1.80404272612712e-07,
"loss": 0.7759827136993408,
"step": 14150,
"token_acc": 0.8139268798893087
},
{
"epoch": 0.9419434235253031,
"grad_norm": 2.421875,
"learning_rate": 1.763532285620373e-07,
"loss": 0.7280136585235596,
"step": 14160,
"token_acc": 0.8232582120333563
},
{
"epoch": 0.9426086378074537,
"grad_norm": 2.28125,
"learning_rate": 1.723477817064423e-07,
"loss": 0.7059343338012696,
"step": 14170,
"token_acc": 0.8278663025820054
},
{
"epoch": 0.9432738520896043,
"grad_norm": 2.671875,
"learning_rate": 1.6838795063750745e-07,
"loss": 0.7408757209777832,
"step": 14180,
"token_acc": 0.8198780612418679
},
{
"epoch": 0.943939066371755,
"grad_norm": 1.9140625,
"learning_rate": 1.6447375373508934e-07,
"loss": 0.7194037914276123,
"step": 14190,
"token_acc": 0.8218612239230796
},
{
"epoch": 0.9446042806539057,
"grad_norm": 2.140625,
"learning_rate": 1.60605209167225e-07,
"loss": 0.7611899375915527,
"step": 14200,
"token_acc": 0.81756805966236
},
{
"epoch": 0.9452694949360563,
"grad_norm": 2.46875,
"learning_rate": 1.5678233489005656e-07,
"loss": 0.7344184398651123,
"step": 14210,
"token_acc": 0.8218463356656505
},
{
"epoch": 0.9459347092182069,
"grad_norm": 2.03125,
"learning_rate": 1.530051486477413e-07,
"loss": 0.7702674388885498,
"step": 14220,
"token_acc": 0.8139843339422909
},
{
"epoch": 0.9465999235003576,
"grad_norm": 2.5625,
"learning_rate": 1.4927366797237275e-07,
"loss": 0.7842254638671875,
"step": 14230,
"token_acc": 0.8108765774432687
},
{
"epoch": 0.9472651377825082,
"grad_norm": 2.359375,
"learning_rate": 1.4558791018389973e-07,
"loss": 0.750076150894165,
"step": 14240,
"token_acc": 0.8166648953129982
},
{
"epoch": 0.9479303520646588,
"grad_norm": 2.0625,
"learning_rate": 1.4194789239004525e-07,
"loss": 0.696656322479248,
"step": 14250,
"token_acc": 0.8288718720684164
},
{
"epoch": 0.9485955663468094,
"grad_norm": 2.171875,
"learning_rate": 1.3835363148622328e-07,
"loss": 0.7265699863433838,
"step": 14260,
"token_acc": 0.8220749826858681
},
{
"epoch": 0.9492607806289601,
"grad_norm": 2.15625,
"learning_rate": 1.3480514415546653e-07,
"loss": 0.6979762077331543,
"step": 14270,
"token_acc": 0.8281662619383067
},
{
"epoch": 0.9499259949111107,
"grad_norm": 2.84375,
"learning_rate": 1.313024468683466e-07,
"loss": 0.7361047267913818,
"step": 14280,
"token_acc": 0.8238497410113469
},
{
"epoch": 0.9505912091932613,
"grad_norm": 2.0,
"learning_rate": 1.2784555588289727e-07,
"loss": 0.7442665100097656,
"step": 14290,
"token_acc": 0.8171304770087034
},
{
"epoch": 0.9512564234754121,
"grad_norm": 2.28125,
"learning_rate": 1.2443448724453577e-07,
"loss": 0.7662309169769287,
"step": 14300,
"token_acc": 0.8103347189375424
},
{
"epoch": 0.9519216377575627,
"grad_norm": 2.09375,
"learning_rate": 1.210692567859939e-07,
"loss": 0.7399674892425537,
"step": 14310,
"token_acc": 0.8194661074501668
},
{
"epoch": 0.9525868520397133,
"grad_norm": 2.1875,
"learning_rate": 1.1774988012724364e-07,
"loss": 0.7393740653991699,
"step": 14320,
"token_acc": 0.8167055755995513
},
{
"epoch": 0.9532520663218639,
"grad_norm": 2.078125,
"learning_rate": 1.1447637267542055e-07,
"loss": 0.7390237331390381,
"step": 14330,
"token_acc": 0.8215276184915654
},
{
"epoch": 0.9539172806040146,
"grad_norm": 2.40625,
"learning_rate": 1.1124874962475386e-07,
"loss": 0.7526998519897461,
"step": 14340,
"token_acc": 0.8161221992711197
},
{
"epoch": 0.9545824948861652,
"grad_norm": 2.859375,
"learning_rate": 1.0806702595649976e-07,
"loss": 0.7406785011291503,
"step": 14350,
"token_acc": 0.8194025979208652
},
{
"epoch": 0.9552477091683158,
"grad_norm": 2.28125,
"learning_rate": 1.049312164388705e-07,
"loss": 0.7631886005401611,
"step": 14360,
"token_acc": 0.8130285959876591
},
{
"epoch": 0.9559129234504665,
"grad_norm": 2.25,
"learning_rate": 1.0184133562695764e-07,
"loss": 0.7189030647277832,
"step": 14370,
"token_acc": 0.8247792393709874
},
{
"epoch": 0.9565781377326171,
"grad_norm": 2.0625,
"learning_rate": 9.879739786267662e-08,
"loss": 0.7435270309448242,
"step": 14380,
"token_acc": 0.8203526317940892
},
{
"epoch": 0.9572433520147677,
"grad_norm": 3.125,
"learning_rate": 9.579941727469345e-08,
"loss": 0.7749327659606934,
"step": 14390,
"token_acc": 0.8150095437600348
},
{
"epoch": 0.9579085662969183,
"grad_norm": 2.296875,
"learning_rate": 9.284740777836254e-08,
"loss": 0.8207275390625,
"step": 14400,
"token_acc": 0.8004539675566295
},
{
"epoch": 0.9585737805790691,
"grad_norm": 2.09375,
"learning_rate": 8.99413830756557e-08,
"loss": 0.7519605159759521,
"step": 14410,
"token_acc": 0.8163308379777726
},
{
"epoch": 0.9592389948612197,
"grad_norm": 2.265625,
"learning_rate": 8.708135665510542e-08,
"loss": 0.727213716506958,
"step": 14420,
"token_acc": 0.8225189413243638
},
{
"epoch": 0.9599042091433703,
"grad_norm": 2.109375,
"learning_rate": 8.426734179173835e-08,
"loss": 0.7629182815551758,
"step": 14430,
"token_acc": 0.8148590734194638
},
{
"epoch": 0.960569423425521,
"grad_norm": 3.265625,
"learning_rate": 8.14993515470186e-08,
"loss": 0.7504594326019287,
"step": 14440,
"token_acc": 0.8176561907061787
},
{
"epoch": 0.9612346377076716,
"grad_norm": 2.21875,
"learning_rate": 7.8777398768779e-08,
"loss": 0.7245527267456054,
"step": 14450,
"token_acc": 0.8193795296800304
},
{
"epoch": 0.9618998519898222,
"grad_norm": 2.328125,
"learning_rate": 7.610149609116768e-08,
"loss": 0.7858740806579589,
"step": 14460,
"token_acc": 0.8107981786931219
},
{
"epoch": 0.9625650662719729,
"grad_norm": 1.9296875,
"learning_rate": 7.34716559345905e-08,
"loss": 0.7440548419952393,
"step": 14470,
"token_acc": 0.825651475855255
},
{
"epoch": 0.9632302805541235,
"grad_norm": 3.4375,
"learning_rate": 7.088789050564649e-08,
"loss": 0.7402670383453369,
"step": 14480,
"token_acc": 0.818523153942428
},
{
"epoch": 0.9638954948362741,
"grad_norm": 2.09375,
"learning_rate": 6.83502117970769e-08,
"loss": 0.7622016906738281,
"step": 14490,
"token_acc": 0.815806891707528
},
{
"epoch": 0.9645607091184247,
"grad_norm": 2.21875,
"learning_rate": 6.585863158770966e-08,
"loss": 0.7262953758239746,
"step": 14500,
"token_acc": 0.8237071039869692
},
{
"epoch": 0.9652259234005754,
"grad_norm": 2.40625,
"learning_rate": 6.34131614423994e-08,
"loss": 0.7897384643554688,
"step": 14510,
"token_acc": 0.8111690947307386
},
{
"epoch": 0.965891137682726,
"grad_norm": 2.015625,
"learning_rate": 6.101381271198192e-08,
"loss": 0.692768907546997,
"step": 14520,
"token_acc": 0.8316185503685504
},
{
"epoch": 0.9665563519648767,
"grad_norm": 2.421875,
"learning_rate": 5.866059653321321e-08,
"loss": 0.7919711112976074,
"step": 14530,
"token_acc": 0.8071255148346781
},
{
"epoch": 0.9672215662470274,
"grad_norm": 1.8984375,
"learning_rate": 5.6353523828724945e-08,
"loss": 0.7098623752593994,
"step": 14540,
"token_acc": 0.825793991416309
},
{
"epoch": 0.967886780529178,
"grad_norm": 2.046875,
"learning_rate": 5.409260530696681e-08,
"loss": 0.7971955299377441,
"step": 14550,
"token_acc": 0.8080693510491777
},
{
"epoch": 0.9685519948113286,
"grad_norm": 2.640625,
"learning_rate": 5.1877851462162066e-08,
"loss": 0.7517688274383545,
"step": 14560,
"token_acc": 0.8189874637052938
},
{
"epoch": 0.9692172090934792,
"grad_norm": 2.359375,
"learning_rate": 4.9709272574258724e-08,
"loss": 0.7258453845977784,
"step": 14570,
"token_acc": 0.8197123447128379
},
{
"epoch": 0.9698824233756299,
"grad_norm": 2.0625,
"learning_rate": 4.758687870887735e-08,
"loss": 0.7247337818145752,
"step": 14580,
"token_acc": 0.822083833049023
},
{
"epoch": 0.9705476376577805,
"grad_norm": 2.328125,
"learning_rate": 4.551067971726886e-08,
"loss": 0.7177899837493896,
"step": 14590,
"token_acc": 0.8263159460826613
},
{
"epoch": 0.9712128519399311,
"grad_norm": 2.40625,
"learning_rate": 4.3480685236266804e-08,
"loss": 0.728609848022461,
"step": 14600,
"token_acc": 0.8268548057259714
},
{
"epoch": 0.9718780662220818,
"grad_norm": 2.328125,
"learning_rate": 4.1496904688244075e-08,
"loss": 0.737406587600708,
"step": 14610,
"token_acc": 0.8240858413725377
},
{
"epoch": 0.9725432805042324,
"grad_norm": 2.140625,
"learning_rate": 3.955934728106736e-08,
"loss": 0.750378942489624,
"step": 14620,
"token_acc": 0.8189726403183479
},
{
"epoch": 0.973208494786383,
"grad_norm": 2.109375,
"learning_rate": 3.7668022008053864e-08,
"loss": 0.7055788993835449,
"step": 14630,
"token_acc": 0.828800997158634
},
{
"epoch": 0.9738737090685337,
"grad_norm": 2.34375,
"learning_rate": 3.582293764793243e-08,
"loss": 0.7405320167541504,
"step": 14640,
"token_acc": 0.8188520901172796
},
{
"epoch": 0.9745389233506844,
"grad_norm": 1.984375,
"learning_rate": 3.4024102764801394e-08,
"loss": 0.695186710357666,
"step": 14650,
"token_acc": 0.825788807706437
},
{
"epoch": 0.975204137632835,
"grad_norm": 2.015625,
"learning_rate": 3.2271525708087446e-08,
"loss": 0.7714601516723633,
"step": 14660,
"token_acc": 0.8132829387301066
},
{
"epoch": 0.9758693519149856,
"grad_norm": 2.03125,
"learning_rate": 3.0565214612507945e-08,
"loss": 0.7594583034515381,
"step": 14670,
"token_acc": 0.8162704056588338
},
{
"epoch": 0.9765345661971363,
"grad_norm": 2.609375,
"learning_rate": 2.8905177398036442e-08,
"loss": 0.7722745895385742,
"step": 14680,
"token_acc": 0.8135479543930249
},
{
"epoch": 0.9771997804792869,
"grad_norm": 2.0625,
"learning_rate": 2.729142176985944e-08,
"loss": 0.701285457611084,
"step": 14690,
"token_acc": 0.8285558503387791
},
{
"epoch": 0.9778649947614375,
"grad_norm": 1.703125,
"learning_rate": 2.5723955218345253e-08,
"loss": 0.7192367553710938,
"step": 14700,
"token_acc": 0.8254006544073531
},
{
"epoch": 0.9785302090435881,
"grad_norm": 2.375,
"learning_rate": 2.4202785019006304e-08,
"loss": 0.7201934814453125,
"step": 14710,
"token_acc": 0.8256292097411115
},
{
"epoch": 0.9791954233257388,
"grad_norm": 2.1875,
"learning_rate": 2.2727918232469116e-08,
"loss": 0.7375096321105957,
"step": 14720,
"token_acc": 0.8221115158963554
},
{
"epoch": 0.9798606376078894,
"grad_norm": 2.484375,
"learning_rate": 2.1299361704439914e-08,
"loss": 0.7198950290679932,
"step": 14730,
"token_acc": 0.8237636953779428
},
{
"epoch": 0.98052585189004,
"grad_norm": 2.125,
"learning_rate": 1.99171220656702e-08,
"loss": 0.7269183158874511,
"step": 14740,
"token_acc": 0.8211163766972824
},
{
"epoch": 0.9811910661721908,
"grad_norm": 2.03125,
"learning_rate": 1.858120573193012e-08,
"loss": 0.7573102951049805,
"step": 14750,
"token_acc": 0.8142256379499124
},
{
"epoch": 0.9818562804543414,
"grad_norm": 2.3125,
"learning_rate": 1.7291618903974017e-08,
"loss": 0.7612798690795899,
"step": 14760,
"token_acc": 0.8172984819018316
},
{
"epoch": 0.982521494736492,
"grad_norm": 2.578125,
"learning_rate": 1.6048367567517154e-08,
"loss": 0.7440046787261962,
"step": 14770,
"token_acc": 0.816972136733348
},
{
"epoch": 0.9831867090186426,
"grad_norm": 1.9140625,
"learning_rate": 1.4851457493204602e-08,
"loss": 0.7592097759246826,
"step": 14780,
"token_acc": 0.8195963156405177
},
{
"epoch": 0.9838519233007933,
"grad_norm": 2.078125,
"learning_rate": 1.3700894236583494e-08,
"loss": 0.7579694747924804,
"step": 14790,
"token_acc": 0.8146830338611161
},
{
"epoch": 0.9845171375829439,
"grad_norm": 2.390625,
"learning_rate": 1.2596683138080823e-08,
"loss": 0.7055313110351562,
"step": 14800,
"token_acc": 0.8279424946798684
},
{
"epoch": 0.9851823518650945,
"grad_norm": 2.4375,
"learning_rate": 1.1538829322973454e-08,
"loss": 0.7781519889831543,
"step": 14810,
"token_acc": 0.8105063869285283
},
{
"epoch": 0.9858475661472452,
"grad_norm": 2.5625,
"learning_rate": 1.0527337701371488e-08,
"loss": 0.7698148727416992,
"step": 14820,
"token_acc": 0.8139117665394446
},
{
"epoch": 0.9865127804293958,
"grad_norm": 2.71875,
"learning_rate": 9.562212968189377e-09,
"loss": 0.7526976585388183,
"step": 14830,
"token_acc": 0.8159537745760168
},
{
"epoch": 0.9871779947115464,
"grad_norm": 2.125,
"learning_rate": 8.643459603123738e-09,
"loss": 0.7493107795715332,
"step": 14840,
"token_acc": 0.8172869843724115
},
{
"epoch": 0.987843208993697,
"grad_norm": 2.203125,
"learning_rate": 7.771081870640018e-09,
"loss": 0.7449126720428467,
"step": 14850,
"token_acc": 0.8177694752152423
},
{
"epoch": 0.9885084232758478,
"grad_norm": 1.9140625,
"learning_rate": 6.945083819943632e-09,
"loss": 0.748995590209961,
"step": 14860,
"token_acc": 0.8155847857957322
},
{
"epoch": 0.9891736375579984,
"grad_norm": 2.0625,
"learning_rate": 6.165469284966641e-09,
"loss": 0.7190714359283448,
"step": 14870,
"token_acc": 0.824219120858255
},
{
"epoch": 0.989838851840149,
"grad_norm": 2.046875,
"learning_rate": 5.432241884348876e-09,
"loss": 0.7476667881011962,
"step": 14880,
"token_acc": 0.8190495202684999
},
{
"epoch": 0.9905040661222997,
"grad_norm": 1.9296875,
"learning_rate": 4.74540502142129e-09,
"loss": 0.7817049026489258,
"step": 14890,
"token_acc": 0.8110313277445674
},
{
"epoch": 0.9911692804044503,
"grad_norm": 2.171875,
"learning_rate": 4.104961884187076e-09,
"loss": 0.7320561408996582,
"step": 14900,
"token_acc": 0.8224264705882353
},
{
"epoch": 0.9918344946866009,
"grad_norm": 2.03125,
"learning_rate": 3.5109154453127905e-09,
"loss": 0.7880257606506348,
"step": 14910,
"token_acc": 0.8125349326467172
},
{
"epoch": 0.9924997089687515,
"grad_norm": 2.3125,
"learning_rate": 2.963268462108371e-09,
"loss": 0.7342030525207519,
"step": 14920,
"token_acc": 0.8220167541450867
},
{
"epoch": 0.9931649232509022,
"grad_norm": 2.328125,
"learning_rate": 2.4620234765193596e-09,
"loss": 0.6835910320281983,
"step": 14930,
"token_acc": 0.8349575772307085
},
{
"epoch": 0.9938301375330528,
"grad_norm": 2.15625,
"learning_rate": 2.0071828151113637e-09,
"loss": 0.7411874771118164,
"step": 14940,
"token_acc": 0.8171307428153426
},
{
"epoch": 0.9944953518152034,
"grad_norm": 1.8671875,
"learning_rate": 1.598748589061172e-09,
"loss": 0.718656063079834,
"step": 14950,
"token_acc": 0.8250063907745618
},
{
"epoch": 0.9951605660973541,
"grad_norm": 2.765625,
"learning_rate": 1.2367226941489841e-09,
"loss": 0.72723388671875,
"step": 14960,
"token_acc": 0.8235817165809424
},
{
"epoch": 0.9958257803795048,
"grad_norm": 2.0625,
"learning_rate": 9.211068107439769e-10,
"loss": 0.699773120880127,
"step": 14970,
"token_acc": 0.8330696147866644
},
{
"epoch": 0.9964909946616554,
"grad_norm": 2.171875,
"learning_rate": 6.519024037998645e-10,
"loss": 0.7491122722625733,
"step": 14980,
"token_acc": 0.8169519932958219
},
{
"epoch": 0.9971562089438061,
"grad_norm": 1.765625,
"learning_rate": 4.291107228504565e-10,
"loss": 0.7657447814941406,
"step": 14990,
"token_acc": 0.8136682406191501
},
{
"epoch": 0.9978214232259567,
"grad_norm": 1.9609375,
"learning_rate": 2.5273280199966666e-10,
"loss": 0.7516185283660889,
"step": 15000,
"token_acc": 0.8202439253077917
},
{
"epoch": 0.9984866375081073,
"grad_norm": 1.7578125,
"learning_rate": 1.227694599192919e-10,
"loss": 0.767716932296753,
"step": 15010,
"token_acc": 0.8109107720758206
},
{
"epoch": 0.9991518517902579,
"grad_norm": 2.015625,
"learning_rate": 3.922129984457179e-11,
"loss": 0.7612566947937012,
"step": 15020,
"token_acc": 0.8179623848860008
},
{
"epoch": 0.9998170660724086,
"grad_norm": 2.34375,
"learning_rate": 2.0887095686372706e-12,
"loss": 0.7338242053985595,
"step": 15030,
"token_acc": 0.823374922649628
}
],
"logging_steps": 10,
"max_steps": 15033,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.0049987244507791e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}