sujr's picture
Upload folder using huggingface_hub
8a3746a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2349409384585264,
"eval_steps": 500,
"global_step": 3600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006526137179403511,
"grad_norm": 17.690582114691438,
"learning_rate": 1.948051948051948e-06,
"loss": 1.3559,
"step": 10
},
{
"epoch": 0.0013052274358807021,
"grad_norm": 7.768088366444893,
"learning_rate": 3.896103896103896e-06,
"loss": 1.2706,
"step": 20
},
{
"epoch": 0.001957841153821053,
"grad_norm": 7.705313536090087,
"learning_rate": 5.844155844155845e-06,
"loss": 1.3781,
"step": 30
},
{
"epoch": 0.0026104548717614043,
"grad_norm": 34.39078827766783,
"learning_rate": 7.792207792207792e-06,
"loss": 1.2749,
"step": 40
},
{
"epoch": 0.0032630685897017554,
"grad_norm": 68.28824334896528,
"learning_rate": 9.74025974025974e-06,
"loss": 1.2955,
"step": 50
},
{
"epoch": 0.003915682307642106,
"grad_norm": 14.220322607917241,
"learning_rate": 1.168831168831169e-05,
"loss": 1.2315,
"step": 60
},
{
"epoch": 0.0045682960255824575,
"grad_norm": 12.611848231734811,
"learning_rate": 1.3636363636363637e-05,
"loss": 1.0953,
"step": 70
},
{
"epoch": 0.0052209097435228086,
"grad_norm": 6.055664298727015,
"learning_rate": 1.5584415584415583e-05,
"loss": 1.105,
"step": 80
},
{
"epoch": 0.00587352346146316,
"grad_norm": 3.52269227801977,
"learning_rate": 1.753246753246753e-05,
"loss": 0.9563,
"step": 90
},
{
"epoch": 0.006526137179403511,
"grad_norm": 10.771884023354394,
"learning_rate": 1.948051948051948e-05,
"loss": 0.9523,
"step": 100
},
{
"epoch": 0.007178750897343862,
"grad_norm": 33.41476483216757,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.832,
"step": 110
},
{
"epoch": 0.007831364615284213,
"grad_norm": 31.120240364617406,
"learning_rate": 2.337662337662338e-05,
"loss": 0.8376,
"step": 120
},
{
"epoch": 0.008483978333224564,
"grad_norm": 5.517231564060886,
"learning_rate": 2.5324675324675325e-05,
"loss": 0.8293,
"step": 130
},
{
"epoch": 0.009136592051164915,
"grad_norm": 4.311605388342058,
"learning_rate": 2.7272727272727273e-05,
"loss": 0.8295,
"step": 140
},
{
"epoch": 0.009789205769105266,
"grad_norm": 6.997724163121519,
"learning_rate": 2.922077922077922e-05,
"loss": 0.7662,
"step": 150
},
{
"epoch": 0.010441819487045617,
"grad_norm": 6.517836234400708,
"learning_rate": 2.999998841890695e-05,
"loss": 0.8158,
"step": 160
},
{
"epoch": 0.011094433204985968,
"grad_norm": 4.186989141019666,
"learning_rate": 2.99999176456253e-05,
"loss": 0.8037,
"step": 170
},
{
"epoch": 0.01174704692292632,
"grad_norm": 5.181546943355458,
"learning_rate": 2.9999782533305785e-05,
"loss": 0.7274,
"step": 180
},
{
"epoch": 0.01239966064086667,
"grad_norm": 3.767076521211455,
"learning_rate": 2.9999583082527935e-05,
"loss": 0.7474,
"step": 190
},
{
"epoch": 0.013052274358807021,
"grad_norm": 18.84416377940188,
"learning_rate": 2.999931929414726e-05,
"loss": 0.7708,
"step": 200
},
{
"epoch": 0.013704888076747372,
"grad_norm": 3.169160630444992,
"learning_rate": 2.999899116929522e-05,
"loss": 0.8279,
"step": 210
},
{
"epoch": 0.014357501794687724,
"grad_norm": 1.912782077307437,
"learning_rate": 2.999859870937924e-05,
"loss": 0.7407,
"step": 220
},
{
"epoch": 0.015010115512628075,
"grad_norm": 3.3906505952914974,
"learning_rate": 2.9998141916082696e-05,
"loss": 0.7732,
"step": 230
},
{
"epoch": 0.015662729230568426,
"grad_norm": 2.7144492322383584,
"learning_rate": 2.999762079136491e-05,
"loss": 0.7272,
"step": 240
},
{
"epoch": 0.01631534294850878,
"grad_norm": 7.109330196029837,
"learning_rate": 2.9997035337461135e-05,
"loss": 0.7748,
"step": 250
},
{
"epoch": 0.016967956666449128,
"grad_norm": 1.6054280593801813,
"learning_rate": 2.9996385556882555e-05,
"loss": 0.7676,
"step": 260
},
{
"epoch": 0.01762057038438948,
"grad_norm": 10.883212441614672,
"learning_rate": 2.9995671452416274e-05,
"loss": 0.735,
"step": 270
},
{
"epoch": 0.01827318410232983,
"grad_norm": 3.511064886507805,
"learning_rate": 2.999489302712529e-05,
"loss": 0.7741,
"step": 280
},
{
"epoch": 0.018925797820270183,
"grad_norm": 3.618603818375307,
"learning_rate": 2.9994050284348497e-05,
"loss": 0.749,
"step": 290
},
{
"epoch": 0.019578411538210532,
"grad_norm": 6.012944880342178,
"learning_rate": 2.9993143227700668e-05,
"loss": 0.7411,
"step": 300
},
{
"epoch": 0.020231025256150885,
"grad_norm": 2.348670372295822,
"learning_rate": 2.9992171861072428e-05,
"loss": 0.7394,
"step": 310
},
{
"epoch": 0.020883638974091234,
"grad_norm": 4.728309497649916,
"learning_rate": 2.9991136188630263e-05,
"loss": 0.8077,
"step": 320
},
{
"epoch": 0.021536252692031587,
"grad_norm": 15.611917863290122,
"learning_rate": 2.9990036214816467e-05,
"loss": 0.7209,
"step": 330
},
{
"epoch": 0.022188866409971936,
"grad_norm": 3.7315277354070817,
"learning_rate": 2.998887194434916e-05,
"loss": 0.7101,
"step": 340
},
{
"epoch": 0.02284148012791229,
"grad_norm": 6.618759094750745,
"learning_rate": 2.998764338222222e-05,
"loss": 0.7759,
"step": 350
},
{
"epoch": 0.02349409384585264,
"grad_norm": 6.770044306239603,
"learning_rate": 2.998635053370533e-05,
"loss": 0.7398,
"step": 360
},
{
"epoch": 0.02414670756379299,
"grad_norm": 12.471224202357552,
"learning_rate": 2.998499340434389e-05,
"loss": 0.7046,
"step": 370
},
{
"epoch": 0.02479932128173334,
"grad_norm": 4.147359416986547,
"learning_rate": 2.9983571999959013e-05,
"loss": 0.761,
"step": 380
},
{
"epoch": 0.025451934999673693,
"grad_norm": 34.84722866603778,
"learning_rate": 2.9982086326647533e-05,
"loss": 0.757,
"step": 390
},
{
"epoch": 0.026104548717614043,
"grad_norm": 5.245498180313093,
"learning_rate": 2.998053639078193e-05,
"loss": 0.7536,
"step": 400
},
{
"epoch": 0.026757162435554396,
"grad_norm": 36.55990241841121,
"learning_rate": 2.997892219901034e-05,
"loss": 0.7395,
"step": 410
},
{
"epoch": 0.027409776153494745,
"grad_norm": 5.03198653806696,
"learning_rate": 2.9977243758256494e-05,
"loss": 0.7208,
"step": 420
},
{
"epoch": 0.028062389871435098,
"grad_norm": 11.376914733036081,
"learning_rate": 2.997550107571972e-05,
"loss": 0.719,
"step": 430
},
{
"epoch": 0.028715003589375447,
"grad_norm": 2.958119684662306,
"learning_rate": 2.9973694158874898e-05,
"loss": 0.7271,
"step": 440
},
{
"epoch": 0.0293676173073158,
"grad_norm": 6.037096737490817,
"learning_rate": 2.9971823015472418e-05,
"loss": 0.7356,
"step": 450
},
{
"epoch": 0.03002023102525615,
"grad_norm": 5.3042973640363575,
"learning_rate": 2.9969887653538164e-05,
"loss": 0.7207,
"step": 460
},
{
"epoch": 0.030672844743196502,
"grad_norm": 2.4985603001745624,
"learning_rate": 2.996788808137347e-05,
"loss": 0.7769,
"step": 470
},
{
"epoch": 0.03132545846113685,
"grad_norm": 7.607065841315647,
"learning_rate": 2.9965824307555084e-05,
"loss": 0.7091,
"step": 480
},
{
"epoch": 0.03197807217907721,
"grad_norm": 4.322533035107957,
"learning_rate": 2.9963696340935144e-05,
"loss": 0.7114,
"step": 490
},
{
"epoch": 0.03263068589701756,
"grad_norm": 5.878565903250334,
"learning_rate": 2.9961504190641108e-05,
"loss": 0.7284,
"step": 500
},
{
"epoch": 0.033283299614957906,
"grad_norm": 5.0026507027119855,
"learning_rate": 2.9959247866075764e-05,
"loss": 0.6992,
"step": 510
},
{
"epoch": 0.033935913332898256,
"grad_norm": 7.12632150273901,
"learning_rate": 2.9956927376917137e-05,
"loss": 0.7285,
"step": 520
},
{
"epoch": 0.03458852705083861,
"grad_norm": 5.211123255860348,
"learning_rate": 2.9954542733118496e-05,
"loss": 0.7511,
"step": 530
},
{
"epoch": 0.03524114076877896,
"grad_norm": 9.925273547498618,
"learning_rate": 2.995209394490827e-05,
"loss": 0.7699,
"step": 540
},
{
"epoch": 0.03589375448671931,
"grad_norm": 7.418381681996765,
"learning_rate": 2.9949581022790025e-05,
"loss": 0.759,
"step": 550
},
{
"epoch": 0.03654636820465966,
"grad_norm": 4.352380973507467,
"learning_rate": 2.9947003977542423e-05,
"loss": 0.7537,
"step": 560
},
{
"epoch": 0.037198981922600016,
"grad_norm": 9.712842120769198,
"learning_rate": 2.9944362820219167e-05,
"loss": 0.7063,
"step": 570
},
{
"epoch": 0.037851595640540366,
"grad_norm": 5.757600819230482,
"learning_rate": 2.994165756214895e-05,
"loss": 0.7893,
"step": 580
},
{
"epoch": 0.038504209358480715,
"grad_norm": 5.529209601152462,
"learning_rate": 2.9938888214935426e-05,
"loss": 0.6771,
"step": 590
},
{
"epoch": 0.039156823076421064,
"grad_norm": 10.550479346499758,
"learning_rate": 2.9936054790457127e-05,
"loss": 0.737,
"step": 600
},
{
"epoch": 0.03980943679436142,
"grad_norm": 8.284279553451016,
"learning_rate": 2.9933157300867437e-05,
"loss": 0.7182,
"step": 610
},
{
"epoch": 0.04046205051230177,
"grad_norm": 8.18511648646326,
"learning_rate": 2.9930195758594542e-05,
"loss": 0.6901,
"step": 620
},
{
"epoch": 0.04111466423024212,
"grad_norm": 14.569754827631956,
"learning_rate": 2.9927170176341365e-05,
"loss": 0.7008,
"step": 630
},
{
"epoch": 0.04176727794818247,
"grad_norm": 4.214581273685441,
"learning_rate": 2.992408056708551e-05,
"loss": 0.7489,
"step": 640
},
{
"epoch": 0.042419891666122825,
"grad_norm": 10.038596627079452,
"learning_rate": 2.9920926944079224e-05,
"loss": 0.7649,
"step": 650
},
{
"epoch": 0.043072505384063174,
"grad_norm": 2.386544029221306,
"learning_rate": 2.9917709320849305e-05,
"loss": 0.7223,
"step": 660
},
{
"epoch": 0.043725119102003523,
"grad_norm": 8.286359254511249,
"learning_rate": 2.9914427711197096e-05,
"loss": 0.7089,
"step": 670
},
{
"epoch": 0.04437773281994387,
"grad_norm": 4.235819327444911,
"learning_rate": 2.9911082129198372e-05,
"loss": 0.7138,
"step": 680
},
{
"epoch": 0.04503034653788423,
"grad_norm": 5.187338033698449,
"learning_rate": 2.9907672589203316e-05,
"loss": 0.7192,
"step": 690
},
{
"epoch": 0.04568296025582458,
"grad_norm": 6.360475337181379,
"learning_rate": 2.9904199105836443e-05,
"loss": 0.7094,
"step": 700
},
{
"epoch": 0.04633557397376493,
"grad_norm": 4.906400836156689,
"learning_rate": 2.990066169399654e-05,
"loss": 0.654,
"step": 710
},
{
"epoch": 0.04698818769170528,
"grad_norm": 17.600495314130633,
"learning_rate": 2.9897060368856603e-05,
"loss": 0.7299,
"step": 720
},
{
"epoch": 0.04764080140964563,
"grad_norm": 7.765935941492389,
"learning_rate": 2.989339514586377e-05,
"loss": 0.7486,
"step": 730
},
{
"epoch": 0.04829341512758598,
"grad_norm": 7.30026395137639,
"learning_rate": 2.9889666040739252e-05,
"loss": 0.6941,
"step": 740
},
{
"epoch": 0.04894602884552633,
"grad_norm": 4.676985481218465,
"learning_rate": 2.9885873069478275e-05,
"loss": 0.7701,
"step": 750
},
{
"epoch": 0.04959864256346668,
"grad_norm": 42.50656974727186,
"learning_rate": 2.9882016248350006e-05,
"loss": 0.7428,
"step": 760
},
{
"epoch": 0.05025125628140704,
"grad_norm": 3.9893667031114766,
"learning_rate": 2.9878095593897474e-05,
"loss": 0.7204,
"step": 770
},
{
"epoch": 0.05090386999934739,
"grad_norm": 8.909028486553332,
"learning_rate": 2.9874111122937518e-05,
"loss": 0.7336,
"step": 780
},
{
"epoch": 0.051556483717287736,
"grad_norm": 5.256925284136456,
"learning_rate": 2.9870062852560698e-05,
"loss": 0.7674,
"step": 790
},
{
"epoch": 0.052209097435228086,
"grad_norm": 5.835535487534073,
"learning_rate": 2.986595080013123e-05,
"loss": 0.7547,
"step": 800
},
{
"epoch": 0.05286171115316844,
"grad_norm": 4.7337998648314565,
"learning_rate": 2.9861774983286913e-05,
"loss": 0.7412,
"step": 810
},
{
"epoch": 0.05351432487110879,
"grad_norm": 4.020304406250962,
"learning_rate": 2.9857535419939053e-05,
"loss": 0.7351,
"step": 820
},
{
"epoch": 0.05416693858904914,
"grad_norm": 7.005748568175158,
"learning_rate": 2.9853232128272367e-05,
"loss": 0.7146,
"step": 830
},
{
"epoch": 0.05481955230698949,
"grad_norm": 12.598315147497464,
"learning_rate": 2.984886512674494e-05,
"loss": 0.7066,
"step": 840
},
{
"epoch": 0.055472166024929846,
"grad_norm": 5.636755294839953,
"learning_rate": 2.9844434434088114e-05,
"loss": 0.8033,
"step": 850
},
{
"epoch": 0.056124779742870196,
"grad_norm": 2.5964949457129305,
"learning_rate": 2.9839940069306436e-05,
"loss": 0.718,
"step": 860
},
{
"epoch": 0.056777393460810545,
"grad_norm": 5.496060434333994,
"learning_rate": 2.9835382051677548e-05,
"loss": 0.7382,
"step": 870
},
{
"epoch": 0.057430007178750894,
"grad_norm": 3.367511777906771,
"learning_rate": 2.9830760400752117e-05,
"loss": 0.7049,
"step": 880
},
{
"epoch": 0.05808262089669125,
"grad_norm": 12.228282751386294,
"learning_rate": 2.9826075136353762e-05,
"loss": 0.7135,
"step": 890
},
{
"epoch": 0.0587352346146316,
"grad_norm": 7.426066867205744,
"learning_rate": 2.9821326278578955e-05,
"loss": 0.6966,
"step": 900
},
{
"epoch": 0.05938784833257195,
"grad_norm": 5.720080945169142,
"learning_rate": 2.981651384779693e-05,
"loss": 0.7325,
"step": 910
},
{
"epoch": 0.0600404620505123,
"grad_norm": 3.3362738196336275,
"learning_rate": 2.9811637864649622e-05,
"loss": 0.7013,
"step": 920
},
{
"epoch": 0.060693075768452655,
"grad_norm": 5.5481143050516675,
"learning_rate": 2.980669835005154e-05,
"loss": 0.7107,
"step": 930
},
{
"epoch": 0.061345689486393004,
"grad_norm": 2.7247889305754533,
"learning_rate": 2.980169532518971e-05,
"loss": 0.6839,
"step": 940
},
{
"epoch": 0.06199830320433335,
"grad_norm": 12.705144630158374,
"learning_rate": 2.9796628811523576e-05,
"loss": 0.7061,
"step": 950
},
{
"epoch": 0.0626509169222737,
"grad_norm": 3.1174966376805777,
"learning_rate": 2.9791498830784896e-05,
"loss": 0.706,
"step": 960
},
{
"epoch": 0.06330353064021406,
"grad_norm": 6.454819870022971,
"learning_rate": 2.9786305404977657e-05,
"loss": 0.6901,
"step": 970
},
{
"epoch": 0.06395614435815442,
"grad_norm": 8.62099817289566,
"learning_rate": 2.9781048556377982e-05,
"loss": 0.6737,
"step": 980
},
{
"epoch": 0.06460875807609476,
"grad_norm": 12.649532843245389,
"learning_rate": 2.977572830753404e-05,
"loss": 0.6777,
"step": 990
},
{
"epoch": 0.06526137179403511,
"grad_norm": 5.019508830810828,
"learning_rate": 2.9770344681265925e-05,
"loss": 0.7125,
"step": 1000
},
{
"epoch": 0.06591398551197546,
"grad_norm": 5.417114630539967,
"learning_rate": 2.9764897700665595e-05,
"loss": 0.7558,
"step": 1010
},
{
"epoch": 0.06656659922991581,
"grad_norm": 13.487574757960102,
"learning_rate": 2.975938738909674e-05,
"loss": 0.7305,
"step": 1020
},
{
"epoch": 0.06721921294785617,
"grad_norm": 4.115297871929447,
"learning_rate": 2.97538137701947e-05,
"loss": 0.7382,
"step": 1030
},
{
"epoch": 0.06787182666579651,
"grad_norm": 4.218133725965425,
"learning_rate": 2.974817686786636e-05,
"loss": 0.7131,
"step": 1040
},
{
"epoch": 0.06852444038373687,
"grad_norm": 23.754945260227526,
"learning_rate": 2.9742476706290044e-05,
"loss": 0.6854,
"step": 1050
},
{
"epoch": 0.06917705410167722,
"grad_norm": 9.992382581534882,
"learning_rate": 2.973671330991541e-05,
"loss": 0.7224,
"step": 1060
},
{
"epoch": 0.06982966781961757,
"grad_norm": 9.022842665053004,
"learning_rate": 2.973088670346336e-05,
"loss": 0.69,
"step": 1070
},
{
"epoch": 0.07048228153755792,
"grad_norm": 7.180693480173149,
"learning_rate": 2.97249969119259e-05,
"loss": 0.6752,
"step": 1080
},
{
"epoch": 0.07113489525549826,
"grad_norm": 4.631581340679664,
"learning_rate": 2.9719043960566088e-05,
"loss": 0.7078,
"step": 1090
},
{
"epoch": 0.07178750897343862,
"grad_norm": 3.8365551360021497,
"learning_rate": 2.9713027874917867e-05,
"loss": 0.7455,
"step": 1100
},
{
"epoch": 0.07244012269137898,
"grad_norm": 20.612721990589407,
"learning_rate": 2.9706948680785984e-05,
"loss": 0.7123,
"step": 1110
},
{
"epoch": 0.07309273640931932,
"grad_norm": 8.515913036269723,
"learning_rate": 2.9700806404245893e-05,
"loss": 0.6755,
"step": 1120
},
{
"epoch": 0.07374535012725968,
"grad_norm": 8.702591994450561,
"learning_rate": 2.9694601071643607e-05,
"loss": 0.743,
"step": 1130
},
{
"epoch": 0.07439796384520003,
"grad_norm": 20.204623397644042,
"learning_rate": 2.968833270959562e-05,
"loss": 0.6995,
"step": 1140
},
{
"epoch": 0.07505057756314037,
"grad_norm": 3.4150625200259563,
"learning_rate": 2.9682001344988768e-05,
"loss": 0.7245,
"step": 1150
},
{
"epoch": 0.07570319128108073,
"grad_norm": 4.827412673105033,
"learning_rate": 2.967560700498013e-05,
"loss": 0.6764,
"step": 1160
},
{
"epoch": 0.07635580499902107,
"grad_norm": 5.9778449783108965,
"learning_rate": 2.9669149716996897e-05,
"loss": 0.7094,
"step": 1170
},
{
"epoch": 0.07700841871696143,
"grad_norm": 4.626419468156439,
"learning_rate": 2.9662629508736278e-05,
"loss": 0.7139,
"step": 1180
},
{
"epoch": 0.07766103243490179,
"grad_norm": 8.23953369228554,
"learning_rate": 2.9656046408165344e-05,
"loss": 0.7132,
"step": 1190
},
{
"epoch": 0.07831364615284213,
"grad_norm": 5.755275462407804,
"learning_rate": 2.964940044352095e-05,
"loss": 0.6923,
"step": 1200
},
{
"epoch": 0.07896625987078248,
"grad_norm": 3.8396649246253816,
"learning_rate": 2.9642691643309572e-05,
"loss": 0.7082,
"step": 1210
},
{
"epoch": 0.07961887358872284,
"grad_norm": 5.7429454484886415,
"learning_rate": 2.963592003630723e-05,
"loss": 0.7095,
"step": 1220
},
{
"epoch": 0.08027148730666318,
"grad_norm": 17.628494673763004,
"learning_rate": 2.962908565155932e-05,
"loss": 0.7309,
"step": 1230
},
{
"epoch": 0.08092410102460354,
"grad_norm": 4.83400055237192,
"learning_rate": 2.9622188518380528e-05,
"loss": 0.6925,
"step": 1240
},
{
"epoch": 0.08157671474254388,
"grad_norm": 3.1535973307593905,
"learning_rate": 2.9615228666354667e-05,
"loss": 0.7441,
"step": 1250
},
{
"epoch": 0.08222932846048424,
"grad_norm": 4.085385929026401,
"learning_rate": 2.9608206125334586e-05,
"loss": 0.7137,
"step": 1260
},
{
"epoch": 0.0828819421784246,
"grad_norm": 4.299591870123697,
"learning_rate": 2.9601120925442016e-05,
"loss": 0.7515,
"step": 1270
},
{
"epoch": 0.08353455589636494,
"grad_norm": 12.873434323415678,
"learning_rate": 2.959397309706746e-05,
"loss": 0.6852,
"step": 1280
},
{
"epoch": 0.0841871696143053,
"grad_norm": 6.427088345402557,
"learning_rate": 2.958676267087004e-05,
"loss": 0.6499,
"step": 1290
},
{
"epoch": 0.08483978333224565,
"grad_norm": 4.70723263638176,
"learning_rate": 2.9579489677777387e-05,
"loss": 0.6803,
"step": 1300
},
{
"epoch": 0.08549239705018599,
"grad_norm": 4.819218491318424,
"learning_rate": 2.9572154148985495e-05,
"loss": 0.6798,
"step": 1310
},
{
"epoch": 0.08614501076812635,
"grad_norm": 3.0652661968089827,
"learning_rate": 2.9564756115958592e-05,
"loss": 0.6935,
"step": 1320
},
{
"epoch": 0.08679762448606669,
"grad_norm": 5.997224165634556,
"learning_rate": 2.9557295610429017e-05,
"loss": 0.7133,
"step": 1330
},
{
"epoch": 0.08745023820400705,
"grad_norm": 3.3593003375605717,
"learning_rate": 2.954977266439706e-05,
"loss": 0.7335,
"step": 1340
},
{
"epoch": 0.0881028519219474,
"grad_norm": 4.161242018302672,
"learning_rate": 2.954218731013083e-05,
"loss": 0.7054,
"step": 1350
},
{
"epoch": 0.08875546563988775,
"grad_norm": 5.827431481546491,
"learning_rate": 2.953453958016614e-05,
"loss": 0.6321,
"step": 1360
},
{
"epoch": 0.0894080793578281,
"grad_norm": 7.1039105888444904,
"learning_rate": 2.952682950730634e-05,
"loss": 0.6941,
"step": 1370
},
{
"epoch": 0.09006069307576846,
"grad_norm": 2.7616336275225892,
"learning_rate": 2.951905712462219e-05,
"loss": 0.6928,
"step": 1380
},
{
"epoch": 0.0907133067937088,
"grad_norm": 4.261061690296871,
"learning_rate": 2.9511222465451716e-05,
"loss": 0.7176,
"step": 1390
},
{
"epoch": 0.09136592051164916,
"grad_norm": 5.4134818862551395,
"learning_rate": 2.950332556340006e-05,
"loss": 0.7048,
"step": 1400
},
{
"epoch": 0.0920185342295895,
"grad_norm": 6.3477656240577085,
"learning_rate": 2.949536645233935e-05,
"loss": 0.6842,
"step": 1410
},
{
"epoch": 0.09267114794752986,
"grad_norm": 63.477804314776044,
"learning_rate": 2.9487345166408545e-05,
"loss": 0.6876,
"step": 1420
},
{
"epoch": 0.09332376166547021,
"grad_norm": 4.368664541213622,
"learning_rate": 2.9479261740013286e-05,
"loss": 0.6913,
"step": 1430
},
{
"epoch": 0.09397637538341055,
"grad_norm": 9.476938465079238,
"learning_rate": 2.9471116207825754e-05,
"loss": 0.6891,
"step": 1440
},
{
"epoch": 0.09462898910135091,
"grad_norm": 8.434794578560851,
"learning_rate": 2.9462908604784523e-05,
"loss": 0.6585,
"step": 1450
},
{
"epoch": 0.09528160281929127,
"grad_norm": 4.798759761163433,
"learning_rate": 2.945463896609441e-05,
"loss": 0.6736,
"step": 1460
},
{
"epoch": 0.09593421653723161,
"grad_norm": 9.782724872581115,
"learning_rate": 2.9446307327226306e-05,
"loss": 0.6659,
"step": 1470
},
{
"epoch": 0.09658683025517197,
"grad_norm": 3.997516099278308,
"learning_rate": 2.9437913723917058e-05,
"loss": 0.6527,
"step": 1480
},
{
"epoch": 0.09723944397311232,
"grad_norm": 4.623015725563099,
"learning_rate": 2.942945819216928e-05,
"loss": 0.7274,
"step": 1490
},
{
"epoch": 0.09789205769105266,
"grad_norm": 3.2197835799755055,
"learning_rate": 2.942094076825123e-05,
"loss": 0.6966,
"step": 1500
},
{
"epoch": 0.09854467140899302,
"grad_norm": 3.5107988249516984,
"learning_rate": 2.9412361488696628e-05,
"loss": 0.7235,
"step": 1510
},
{
"epoch": 0.09919728512693336,
"grad_norm": 18.7865650951996,
"learning_rate": 2.9403720390304518e-05,
"loss": 0.7382,
"step": 1520
},
{
"epoch": 0.09984989884487372,
"grad_norm": 3.85598692653545,
"learning_rate": 2.93950175101391e-05,
"loss": 0.7475,
"step": 1530
},
{
"epoch": 0.10050251256281408,
"grad_norm": 20.459657003411998,
"learning_rate": 2.938625288552957e-05,
"loss": 0.6558,
"step": 1540
},
{
"epoch": 0.10115512628075442,
"grad_norm": 6.416583997846208,
"learning_rate": 2.9377426554069976e-05,
"loss": 0.7205,
"step": 1550
},
{
"epoch": 0.10180773999869477,
"grad_norm": 5.532087704430113,
"learning_rate": 2.936853855361904e-05,
"loss": 0.7189,
"step": 1560
},
{
"epoch": 0.10246035371663513,
"grad_norm": 4.756518458886862,
"learning_rate": 2.9359588922299986e-05,
"loss": 0.7088,
"step": 1570
},
{
"epoch": 0.10311296743457547,
"grad_norm": 5.775658785412931,
"learning_rate": 2.9350577698500408e-05,
"loss": 0.682,
"step": 1580
},
{
"epoch": 0.10376558115251583,
"grad_norm": 7.714313915746094,
"learning_rate": 2.9341504920872087e-05,
"loss": 0.7393,
"step": 1590
},
{
"epoch": 0.10441819487045617,
"grad_norm": 11.153510433173501,
"learning_rate": 2.933237062833082e-05,
"loss": 0.6616,
"step": 1600
},
{
"epoch": 0.10507080858839653,
"grad_norm": 4.575896778703132,
"learning_rate": 2.9323174860056258e-05,
"loss": 0.7168,
"step": 1610
},
{
"epoch": 0.10572342230633688,
"grad_norm": 46.2282201673799,
"learning_rate": 2.9313917655491744e-05,
"loss": 0.7016,
"step": 1620
},
{
"epoch": 0.10637603602427723,
"grad_norm": 51.80540559466864,
"learning_rate": 2.9304599054344148e-05,
"loss": 0.6709,
"step": 1630
},
{
"epoch": 0.10702864974221758,
"grad_norm": 4.607057564284905,
"learning_rate": 2.9295219096583663e-05,
"loss": 0.6894,
"step": 1640
},
{
"epoch": 0.10768126346015794,
"grad_norm": 4.158724628963882,
"learning_rate": 2.9285777822443686e-05,
"loss": 0.6847,
"step": 1650
},
{
"epoch": 0.10833387717809828,
"grad_norm": 6.634813921115065,
"learning_rate": 2.92762752724206e-05,
"loss": 0.7094,
"step": 1660
},
{
"epoch": 0.10898649089603864,
"grad_norm": 2.437577662086608,
"learning_rate": 2.926671148727362e-05,
"loss": 0.69,
"step": 1670
},
{
"epoch": 0.10963910461397898,
"grad_norm": 22.722071681603026,
"learning_rate": 2.925708650802463e-05,
"loss": 0.704,
"step": 1680
},
{
"epoch": 0.11029171833191934,
"grad_norm": 2.913996227830109,
"learning_rate": 2.9247400375957976e-05,
"loss": 0.7211,
"step": 1690
},
{
"epoch": 0.11094433204985969,
"grad_norm": 5.279852146043678,
"learning_rate": 2.923765313262032e-05,
"loss": 0.6693,
"step": 1700
},
{
"epoch": 0.11159694576780003,
"grad_norm": 4.47116557104752,
"learning_rate": 2.9227844819820434e-05,
"loss": 0.6958,
"step": 1710
},
{
"epoch": 0.11224955948574039,
"grad_norm": 6.9451125709413,
"learning_rate": 2.9217975479629047e-05,
"loss": 0.6549,
"step": 1720
},
{
"epoch": 0.11290217320368075,
"grad_norm": 8.218016152925602,
"learning_rate": 2.920804515437865e-05,
"loss": 0.7034,
"step": 1730
},
{
"epoch": 0.11355478692162109,
"grad_norm": 4.725968454405007,
"learning_rate": 2.9198053886663314e-05,
"loss": 0.7292,
"step": 1740
},
{
"epoch": 0.11420740063956145,
"grad_norm": 8.078717621365517,
"learning_rate": 2.9188001719338514e-05,
"loss": 0.6556,
"step": 1750
},
{
"epoch": 0.11486001435750179,
"grad_norm": 9.045448414751244,
"learning_rate": 2.9177888695520933e-05,
"loss": 0.7223,
"step": 1760
},
{
"epoch": 0.11551262807544214,
"grad_norm": 4.318313439658446,
"learning_rate": 2.916771485858829e-05,
"loss": 0.6762,
"step": 1770
},
{
"epoch": 0.1161652417933825,
"grad_norm": 13.078874026489483,
"learning_rate": 2.9157480252179156e-05,
"loss": 0.7189,
"step": 1780
},
{
"epoch": 0.11681785551132284,
"grad_norm": 8.585825980992096,
"learning_rate": 2.9147184920192745e-05,
"loss": 0.7142,
"step": 1790
},
{
"epoch": 0.1174704692292632,
"grad_norm": 138.05135197182966,
"learning_rate": 2.9136828906788765e-05,
"loss": 0.6514,
"step": 1800
},
{
"epoch": 0.11812308294720356,
"grad_norm": 2.9764498791953167,
"learning_rate": 2.9126412256387172e-05,
"loss": 0.6835,
"step": 1810
},
{
"epoch": 0.1187756966651439,
"grad_norm": 10.553495101154766,
"learning_rate": 2.9115935013668038e-05,
"loss": 0.7049,
"step": 1820
},
{
"epoch": 0.11942831038308425,
"grad_norm": 3.8520760029457755,
"learning_rate": 2.910539722357132e-05,
"loss": 0.6805,
"step": 1830
},
{
"epoch": 0.1200809241010246,
"grad_norm": 6.002281391018973,
"learning_rate": 2.9094798931296692e-05,
"loss": 0.7044,
"step": 1840
},
{
"epoch": 0.12073353781896495,
"grad_norm": 9.04002888227592,
"learning_rate": 2.9084140182303328e-05,
"loss": 0.7221,
"step": 1850
},
{
"epoch": 0.12138615153690531,
"grad_norm": 2.324509546376411,
"learning_rate": 2.907342102230972e-05,
"loss": 0.7,
"step": 1860
},
{
"epoch": 0.12203876525484565,
"grad_norm": 4.136482440945801,
"learning_rate": 2.9062641497293485e-05,
"loss": 0.7213,
"step": 1870
},
{
"epoch": 0.12269137897278601,
"grad_norm": 2.9193932096141673,
"learning_rate": 2.9051801653491158e-05,
"loss": 0.6656,
"step": 1880
},
{
"epoch": 0.12334399269072636,
"grad_norm": 6.319528726800553,
"learning_rate": 2.9040901537398008e-05,
"loss": 0.6701,
"step": 1890
},
{
"epoch": 0.1239966064086667,
"grad_norm": 3.5042010027049533,
"learning_rate": 2.9029941195767824e-05,
"loss": 0.6454,
"step": 1900
},
{
"epoch": 0.12464922012660706,
"grad_norm": 4.3096531856338895,
"learning_rate": 2.9018920675612712e-05,
"loss": 0.6818,
"step": 1910
},
{
"epoch": 0.1253018338445474,
"grad_norm": 6.849873350879978,
"learning_rate": 2.900784002420292e-05,
"loss": 0.7674,
"step": 1920
},
{
"epoch": 0.12595444756248778,
"grad_norm": 7.645127543651015,
"learning_rate": 2.89966992890666e-05,
"loss": 0.7,
"step": 1930
},
{
"epoch": 0.12660706128042812,
"grad_norm": 3.334578297503325,
"learning_rate": 2.8985498517989623e-05,
"loss": 0.6783,
"step": 1940
},
{
"epoch": 0.12725967499836846,
"grad_norm": 7.91381208921764,
"learning_rate": 2.897423775901538e-05,
"loss": 0.7327,
"step": 1950
},
{
"epoch": 0.12791228871630883,
"grad_norm": 7.74516810255062,
"learning_rate": 2.8962917060444562e-05,
"loss": 0.7145,
"step": 1960
},
{
"epoch": 0.12856490243424917,
"grad_norm": 5.468499401345368,
"learning_rate": 2.8951536470834957e-05,
"loss": 0.6807,
"step": 1970
},
{
"epoch": 0.12921751615218952,
"grad_norm": 3.7005534196349963,
"learning_rate": 2.894009603900125e-05,
"loss": 0.7004,
"step": 1980
},
{
"epoch": 0.12987012987012986,
"grad_norm": 3.6355286647446716,
"learning_rate": 2.89285958140148e-05,
"loss": 0.6804,
"step": 1990
},
{
"epoch": 0.13052274358807023,
"grad_norm": 4.199898882057381,
"learning_rate": 2.891703584520343e-05,
"loss": 0.7268,
"step": 2000
},
{
"epoch": 0.13117535730601057,
"grad_norm": 4.9058604480600385,
"learning_rate": 2.8905416182151244e-05,
"loss": 0.7168,
"step": 2010
},
{
"epoch": 0.1318279710239509,
"grad_norm": 4.2197732320304535,
"learning_rate": 2.8893736874698367e-05,
"loss": 0.701,
"step": 2020
},
{
"epoch": 0.13248058474189128,
"grad_norm": 4.66981547707892,
"learning_rate": 2.888199797294078e-05,
"loss": 0.6624,
"step": 2030
},
{
"epoch": 0.13313319845983163,
"grad_norm": 2.1811717459296274,
"learning_rate": 2.887019952723006e-05,
"loss": 0.7181,
"step": 2040
},
{
"epoch": 0.13378581217777197,
"grad_norm": 5.9404267175163135,
"learning_rate": 2.8858341588173194e-05,
"loss": 0.7231,
"step": 2050
},
{
"epoch": 0.13443842589571234,
"grad_norm": 3.279458419701383,
"learning_rate": 2.884642420663236e-05,
"loss": 0.6863,
"step": 2060
},
{
"epoch": 0.13509103961365268,
"grad_norm": 3.441960856231174,
"learning_rate": 2.8834447433724693e-05,
"loss": 0.6985,
"step": 2070
},
{
"epoch": 0.13574365333159302,
"grad_norm": 6.296333990212765,
"learning_rate": 2.8822411320822074e-05,
"loss": 0.7166,
"step": 2080
},
{
"epoch": 0.1363962670495334,
"grad_norm": 4.087401381303271,
"learning_rate": 2.881031591955092e-05,
"loss": 0.6765,
"step": 2090
},
{
"epoch": 0.13704888076747374,
"grad_norm": 6.6119114402937305,
"learning_rate": 2.879816128179195e-05,
"loss": 0.7228,
"step": 2100
},
{
"epoch": 0.13770149448541408,
"grad_norm": 4.897020539614396,
"learning_rate": 2.8785947459679953e-05,
"loss": 0.7173,
"step": 2110
},
{
"epoch": 0.13835410820335445,
"grad_norm": 3.482291928967508,
"learning_rate": 2.87736745056036e-05,
"loss": 0.685,
"step": 2120
},
{
"epoch": 0.1390067219212948,
"grad_norm": 12.111542144788995,
"learning_rate": 2.876134247220517e-05,
"loss": 0.7198,
"step": 2130
},
{
"epoch": 0.13965933563923513,
"grad_norm": 7.1442170238273786,
"learning_rate": 2.8748951412380384e-05,
"loss": 0.7549,
"step": 2140
},
{
"epoch": 0.14031194935717548,
"grad_norm": 4.841978475189581,
"learning_rate": 2.873650137927811e-05,
"loss": 0.6388,
"step": 2150
},
{
"epoch": 0.14096456307511585,
"grad_norm": 4.053407088369962,
"learning_rate": 2.872399242630018e-05,
"loss": 0.6837,
"step": 2160
},
{
"epoch": 0.1416171767930562,
"grad_norm": 2.537769446137546,
"learning_rate": 2.871142460710117e-05,
"loss": 0.678,
"step": 2170
},
{
"epoch": 0.14226979051099653,
"grad_norm": 6.452520531522298,
"learning_rate": 2.8698797975588133e-05,
"loss": 0.669,
"step": 2180
},
{
"epoch": 0.1429224042289369,
"grad_norm": 6.840893292905677,
"learning_rate": 2.868611258592038e-05,
"loss": 0.7022,
"step": 2190
},
{
"epoch": 0.14357501794687724,
"grad_norm": 4.634307774411798,
"learning_rate": 2.867336849250926e-05,
"loss": 0.6873,
"step": 2200
},
{
"epoch": 0.14422763166481758,
"grad_norm": 3.74851807876996,
"learning_rate": 2.866056575001793e-05,
"loss": 0.6946,
"step": 2210
},
{
"epoch": 0.14488024538275796,
"grad_norm": 2.0416537952666123,
"learning_rate": 2.8647704413361095e-05,
"loss": 0.6637,
"step": 2220
},
{
"epoch": 0.1455328591006983,
"grad_norm": 3.555607066840982,
"learning_rate": 2.863478453770479e-05,
"loss": 0.71,
"step": 2230
},
{
"epoch": 0.14618547281863864,
"grad_norm": 5.481578146356155,
"learning_rate": 2.862180617846615e-05,
"loss": 0.7335,
"step": 2240
},
{
"epoch": 0.146838086536579,
"grad_norm": 4.089959406196587,
"learning_rate": 2.8608769391313153e-05,
"loss": 0.6951,
"step": 2250
},
{
"epoch": 0.14749070025451935,
"grad_norm": 4.054901293812647,
"learning_rate": 2.8595674232164403e-05,
"loss": 0.6933,
"step": 2260
},
{
"epoch": 0.1481433139724597,
"grad_norm": 11.977393154495003,
"learning_rate": 2.8582520757188858e-05,
"loss": 0.6793,
"step": 2270
},
{
"epoch": 0.14879592769040006,
"grad_norm": 9.862463610911956,
"learning_rate": 2.856930902280563e-05,
"loss": 0.693,
"step": 2280
},
{
"epoch": 0.1494485414083404,
"grad_norm": 6.6933607998065305,
"learning_rate": 2.8556039085683717e-05,
"loss": 0.6512,
"step": 2290
},
{
"epoch": 0.15010115512628075,
"grad_norm": 13.33031435802581,
"learning_rate": 2.8542711002741765e-05,
"loss": 0.6818,
"step": 2300
},
{
"epoch": 0.1507537688442211,
"grad_norm": 3.55607266109624,
"learning_rate": 2.8529324831147817e-05,
"loss": 0.6969,
"step": 2310
},
{
"epoch": 0.15140638256216146,
"grad_norm": 2.76158562626684,
"learning_rate": 2.8515880628319084e-05,
"loss": 0.6469,
"step": 2320
},
{
"epoch": 0.1520589962801018,
"grad_norm": 14.835614032644079,
"learning_rate": 2.8502378451921686e-05,
"loss": 0.7095,
"step": 2330
},
{
"epoch": 0.15271160999804215,
"grad_norm": 3.837370004844092,
"learning_rate": 2.8488818359870418e-05,
"loss": 0.6549,
"step": 2340
},
{
"epoch": 0.15336422371598252,
"grad_norm": 8.077714625547088,
"learning_rate": 2.8475200410328477e-05,
"loss": 0.7036,
"step": 2350
},
{
"epoch": 0.15401683743392286,
"grad_norm": 4.208380267696714,
"learning_rate": 2.846152466170724e-05,
"loss": 0.7083,
"step": 2360
},
{
"epoch": 0.1546694511518632,
"grad_norm": 5.882366675192563,
"learning_rate": 2.8447791172665994e-05,
"loss": 0.6774,
"step": 2370
},
{
"epoch": 0.15532206486980357,
"grad_norm": 10.332970110344341,
"learning_rate": 2.8434000002111686e-05,
"loss": 0.6871,
"step": 2380
},
{
"epoch": 0.15597467858774391,
"grad_norm": 5.233682432902447,
"learning_rate": 2.84201512091987e-05,
"loss": 0.6685,
"step": 2390
},
{
"epoch": 0.15662729230568426,
"grad_norm": 4.051922217192083,
"learning_rate": 2.840624485332855e-05,
"loss": 0.6893,
"step": 2400
},
{
"epoch": 0.15727990602362463,
"grad_norm": 8.208037033800602,
"learning_rate": 2.8392280994149673e-05,
"loss": 0.7163,
"step": 2410
},
{
"epoch": 0.15793251974156497,
"grad_norm": 6.38338502443,
"learning_rate": 2.8378259691557143e-05,
"loss": 0.6738,
"step": 2420
},
{
"epoch": 0.1585851334595053,
"grad_norm": 5.91196516331796,
"learning_rate": 2.8364181005692437e-05,
"loss": 0.6777,
"step": 2430
},
{
"epoch": 0.15923774717744568,
"grad_norm": 4.255829123415314,
"learning_rate": 2.835004499694316e-05,
"loss": 0.7101,
"step": 2440
},
{
"epoch": 0.15989036089538602,
"grad_norm": 6.462145986397376,
"learning_rate": 2.833585172594279e-05,
"loss": 0.7031,
"step": 2450
},
{
"epoch": 0.16054297461332637,
"grad_norm": 4.701946326296281,
"learning_rate": 2.8321601253570425e-05,
"loss": 0.7195,
"step": 2460
},
{
"epoch": 0.16119558833126674,
"grad_norm": 2.7081882046671337,
"learning_rate": 2.830729364095051e-05,
"loss": 0.697,
"step": 2470
},
{
"epoch": 0.16184820204920708,
"grad_norm": 12.027371026479301,
"learning_rate": 2.8292928949452578e-05,
"loss": 0.6701,
"step": 2480
},
{
"epoch": 0.16250081576714742,
"grad_norm": 4.375553205119334,
"learning_rate": 2.8278507240691e-05,
"loss": 0.6698,
"step": 2490
},
{
"epoch": 0.16315342948508776,
"grad_norm": 2.3145460407904968,
"learning_rate": 2.8264028576524714e-05,
"loss": 0.6619,
"step": 2500
},
{
"epoch": 0.16380604320302813,
"grad_norm": 9.62186450170952,
"learning_rate": 2.824949301905694e-05,
"loss": 0.7049,
"step": 2510
},
{
"epoch": 0.16445865692096848,
"grad_norm": 3.242262212053335,
"learning_rate": 2.8234900630634945e-05,
"loss": 0.6684,
"step": 2520
},
{
"epoch": 0.16511127063890882,
"grad_norm": 5.874441891397036,
"learning_rate": 2.8220251473849747e-05,
"loss": 0.6841,
"step": 2530
},
{
"epoch": 0.1657638843568492,
"grad_norm": 5.5132935867506685,
"learning_rate": 2.8205545611535876e-05,
"loss": 0.7077,
"step": 2540
},
{
"epoch": 0.16641649807478953,
"grad_norm": 4.178673623014923,
"learning_rate": 2.8190783106771076e-05,
"loss": 0.6779,
"step": 2550
},
{
"epoch": 0.16706911179272987,
"grad_norm": 3.8308465742128974,
"learning_rate": 2.8175964022876057e-05,
"loss": 0.6638,
"step": 2560
},
{
"epoch": 0.16772172551067024,
"grad_norm": 3.122478077844367,
"learning_rate": 2.8161088423414197e-05,
"loss": 0.7063,
"step": 2570
},
{
"epoch": 0.1683743392286106,
"grad_norm": 4.633331835812846,
"learning_rate": 2.8146156372191306e-05,
"loss": 0.6555,
"step": 2580
},
{
"epoch": 0.16902695294655093,
"grad_norm": 17.541201672163616,
"learning_rate": 2.8131167933255323e-05,
"loss": 0.7001,
"step": 2590
},
{
"epoch": 0.1696795666644913,
"grad_norm": 6.134101489242109,
"learning_rate": 2.8116123170896046e-05,
"loss": 0.7173,
"step": 2600
},
{
"epoch": 0.17033218038243164,
"grad_norm": 8.073444833192916,
"learning_rate": 2.8101022149644868e-05,
"loss": 0.6771,
"step": 2610
},
{
"epoch": 0.17098479410037198,
"grad_norm": 6.780231733384814,
"learning_rate": 2.8085864934274488e-05,
"loss": 0.7313,
"step": 2620
},
{
"epoch": 0.17163740781831235,
"grad_norm": 3.857057315644847,
"learning_rate": 2.8070651589798638e-05,
"loss": 0.6844,
"step": 2630
},
{
"epoch": 0.1722900215362527,
"grad_norm": 2.6968793212573106,
"learning_rate": 2.805538218147181e-05,
"loss": 0.6806,
"step": 2640
},
{
"epoch": 0.17294263525419304,
"grad_norm": 3.347039146921558,
"learning_rate": 2.8040056774788968e-05,
"loss": 0.6993,
"step": 2650
},
{
"epoch": 0.17359524897213338,
"grad_norm": 3.3015836383740456,
"learning_rate": 2.8024675435485257e-05,
"loss": 0.7268,
"step": 2660
},
{
"epoch": 0.17424786269007375,
"grad_norm": 3.317639807807373,
"learning_rate": 2.8009238229535758e-05,
"loss": 0.6674,
"step": 2670
},
{
"epoch": 0.1749004764080141,
"grad_norm": 5.874714621247871,
"learning_rate": 2.7993745223155156e-05,
"loss": 0.6571,
"step": 2680
},
{
"epoch": 0.17555309012595444,
"grad_norm": 3.435629734690448,
"learning_rate": 2.7978196482797496e-05,
"loss": 0.6998,
"step": 2690
},
{
"epoch": 0.1762057038438948,
"grad_norm": 30.168294226928044,
"learning_rate": 2.7962592075155875e-05,
"loss": 0.6531,
"step": 2700
},
{
"epoch": 0.17685831756183515,
"grad_norm": 3.6088167890096865,
"learning_rate": 2.794693206716217e-05,
"loss": 0.644,
"step": 2710
},
{
"epoch": 0.1775109312797755,
"grad_norm": 5.471338847334227,
"learning_rate": 2.7931216525986733e-05,
"loss": 0.6864,
"step": 2720
},
{
"epoch": 0.17816354499771586,
"grad_norm": 3.5451837616331763,
"learning_rate": 2.7915445519038124e-05,
"loss": 0.6794,
"step": 2730
},
{
"epoch": 0.1788161587156562,
"grad_norm": 4.9951779955670705,
"learning_rate": 2.7899619113962806e-05,
"loss": 0.6702,
"step": 2740
},
{
"epoch": 0.17946877243359655,
"grad_norm": 6.849902588089016,
"learning_rate": 2.7883737378644866e-05,
"loss": 0.679,
"step": 2750
},
{
"epoch": 0.18012138615153692,
"grad_norm": 11.250488948793029,
"learning_rate": 2.786780038120572e-05,
"loss": 0.7153,
"step": 2760
},
{
"epoch": 0.18077399986947726,
"grad_norm": 13.184900398210909,
"learning_rate": 2.7851808190003803e-05,
"loss": 0.6734,
"step": 2770
},
{
"epoch": 0.1814266135874176,
"grad_norm": 7.234749638062084,
"learning_rate": 2.7835760873634318e-05,
"loss": 0.6677,
"step": 2780
},
{
"epoch": 0.18207922730535797,
"grad_norm": 13.085129406019094,
"learning_rate": 2.7819658500928897e-05,
"loss": 0.691,
"step": 2790
},
{
"epoch": 0.1827318410232983,
"grad_norm": 3.5248377823535,
"learning_rate": 2.780350114095533e-05,
"loss": 0.6397,
"step": 2800
},
{
"epoch": 0.18338445474123866,
"grad_norm": 26.796889805025064,
"learning_rate": 2.7787288863017263e-05,
"loss": 0.7222,
"step": 2810
},
{
"epoch": 0.184037068459179,
"grad_norm": 3.125330335323775,
"learning_rate": 2.77710217366539e-05,
"loss": 0.7082,
"step": 2820
},
{
"epoch": 0.18468968217711937,
"grad_norm": 5.07678317608623,
"learning_rate": 2.775469983163972e-05,
"loss": 0.642,
"step": 2830
},
{
"epoch": 0.1853422958950597,
"grad_norm": 3.8465548570361605,
"learning_rate": 2.773832321798414e-05,
"loss": 0.735,
"step": 2840
},
{
"epoch": 0.18599490961300005,
"grad_norm": 2.596039278811819,
"learning_rate": 2.7721891965931252e-05,
"loss": 0.6885,
"step": 2850
},
{
"epoch": 0.18664752333094042,
"grad_norm": 14.003078667143276,
"learning_rate": 2.7705406145959505e-05,
"loss": 0.7036,
"step": 2860
},
{
"epoch": 0.18730013704888077,
"grad_norm": 4.5877627845774365,
"learning_rate": 2.7688865828781413e-05,
"loss": 0.6995,
"step": 2870
},
{
"epoch": 0.1879527507668211,
"grad_norm": 7.044776485625493,
"learning_rate": 2.767227108534323e-05,
"loss": 0.7161,
"step": 2880
},
{
"epoch": 0.18860536448476148,
"grad_norm": 3.072683258675077,
"learning_rate": 2.765562198682468e-05,
"loss": 0.7406,
"step": 2890
},
{
"epoch": 0.18925797820270182,
"grad_norm": 8.84720999495458,
"learning_rate": 2.763891860463861e-05,
"loss": 0.6727,
"step": 2900
},
{
"epoch": 0.18991059192064216,
"grad_norm": 9.494450604703584,
"learning_rate": 2.7622161010430717e-05,
"loss": 0.6859,
"step": 2910
},
{
"epoch": 0.19056320563858253,
"grad_norm": 2.803990269441359,
"learning_rate": 2.7605349276079238e-05,
"loss": 0.7,
"step": 2920
},
{
"epoch": 0.19121581935652288,
"grad_norm": 6.501435928194476,
"learning_rate": 2.7588483473694613e-05,
"loss": 0.66,
"step": 2930
},
{
"epoch": 0.19186843307446322,
"grad_norm": 3.9434365221991667,
"learning_rate": 2.7571563675619202e-05,
"loss": 0.6575,
"step": 2940
},
{
"epoch": 0.1925210467924036,
"grad_norm": 6.473206095572867,
"learning_rate": 2.7554589954426986e-05,
"loss": 0.6509,
"step": 2950
},
{
"epoch": 0.19317366051034393,
"grad_norm": 6.359600241231479,
"learning_rate": 2.7537562382923217e-05,
"loss": 0.6554,
"step": 2960
},
{
"epoch": 0.19382627422828427,
"grad_norm": 9.209939347687689,
"learning_rate": 2.752048103414413e-05,
"loss": 0.723,
"step": 2970
},
{
"epoch": 0.19447888794622464,
"grad_norm": 23.703947692957573,
"learning_rate": 2.7503345981356633e-05,
"loss": 0.6927,
"step": 2980
},
{
"epoch": 0.19513150166416499,
"grad_norm": 8.212074266427711,
"learning_rate": 2.7486157298057986e-05,
"loss": 0.6999,
"step": 2990
},
{
"epoch": 0.19578411538210533,
"grad_norm": 5.189620722030213,
"learning_rate": 2.7468915057975487e-05,
"loss": 0.6722,
"step": 3000
},
{
"epoch": 0.19643672910004567,
"grad_norm": 4.021048004797352,
"learning_rate": 2.745161933506614e-05,
"loss": 0.66,
"step": 3010
},
{
"epoch": 0.19708934281798604,
"grad_norm": 4.156307822377388,
"learning_rate": 2.7434270203516373e-05,
"loss": 0.6987,
"step": 3020
},
{
"epoch": 0.19774195653592638,
"grad_norm": 4.75441596904026,
"learning_rate": 2.7416867737741683e-05,
"loss": 0.6963,
"step": 3030
},
{
"epoch": 0.19839457025386673,
"grad_norm": 5.880889862093012,
"learning_rate": 2.739941201238635e-05,
"loss": 0.6445,
"step": 3040
},
{
"epoch": 0.1990471839718071,
"grad_norm": 4.686264689115436,
"learning_rate": 2.738190310232308e-05,
"loss": 0.751,
"step": 3050
},
{
"epoch": 0.19969979768974744,
"grad_norm": 5.015165789251315,
"learning_rate": 2.7364341082652716e-05,
"loss": 0.6676,
"step": 3060
},
{
"epoch": 0.20035241140768778,
"grad_norm": 4.629542414090964,
"learning_rate": 2.734672602870391e-05,
"loss": 0.6625,
"step": 3070
},
{
"epoch": 0.20100502512562815,
"grad_norm": 3.582640218606122,
"learning_rate": 2.7329058016032773e-05,
"loss": 0.7243,
"step": 3080
},
{
"epoch": 0.2016576388435685,
"grad_norm": 35.16576433756719,
"learning_rate": 2.7311337120422588e-05,
"loss": 0.6734,
"step": 3090
},
{
"epoch": 0.20231025256150884,
"grad_norm": 8.429048501615004,
"learning_rate": 2.729356341788347e-05,
"loss": 0.6761,
"step": 3100
},
{
"epoch": 0.2029628662794492,
"grad_norm": 10.361847043143795,
"learning_rate": 2.727573698465202e-05,
"loss": 0.691,
"step": 3110
},
{
"epoch": 0.20361547999738955,
"grad_norm": 3.125915545815778,
"learning_rate": 2.7257857897191044e-05,
"loss": 0.6439,
"step": 3120
},
{
"epoch": 0.2042680937153299,
"grad_norm": 3.7497179561089937,
"learning_rate": 2.7239926232189167e-05,
"loss": 0.6707,
"step": 3130
},
{
"epoch": 0.20492070743327026,
"grad_norm": 3.56873592233637,
"learning_rate": 2.722194206656056e-05,
"loss": 0.6673,
"step": 3140
},
{
"epoch": 0.2055733211512106,
"grad_norm": 10.54660445254849,
"learning_rate": 2.7203905477444574e-05,
"loss": 0.6829,
"step": 3150
},
{
"epoch": 0.20622593486915095,
"grad_norm": 3.6820544103925608,
"learning_rate": 2.7185816542205407e-05,
"loss": 0.6568,
"step": 3160
},
{
"epoch": 0.2068785485870913,
"grad_norm": 8.593912019069307,
"learning_rate": 2.7167675338431813e-05,
"loss": 0.6375,
"step": 3170
},
{
"epoch": 0.20753116230503166,
"grad_norm": 4.561901523582492,
"learning_rate": 2.7149481943936718e-05,
"loss": 0.6929,
"step": 3180
},
{
"epoch": 0.208183776022972,
"grad_norm": 3.3662024382508022,
"learning_rate": 2.7131236436756917e-05,
"loss": 0.7155,
"step": 3190
},
{
"epoch": 0.20883638974091234,
"grad_norm": 3.4110738212405542,
"learning_rate": 2.7112938895152733e-05,
"loss": 0.7195,
"step": 3200
},
{
"epoch": 0.2094890034588527,
"grad_norm": 3.6699604643477413,
"learning_rate": 2.709458939760768e-05,
"loss": 0.6266,
"step": 3210
},
{
"epoch": 0.21014161717679306,
"grad_norm": 1.7543595371849152,
"learning_rate": 2.7076188022828125e-05,
"loss": 0.6956,
"step": 3220
},
{
"epoch": 0.2107942308947334,
"grad_norm": 3.9842297097437647,
"learning_rate": 2.7057734849742944e-05,
"loss": 0.6616,
"step": 3230
},
{
"epoch": 0.21144684461267377,
"grad_norm": 5.223697167736633,
"learning_rate": 2.7039229957503207e-05,
"loss": 0.6951,
"step": 3240
},
{
"epoch": 0.2120994583306141,
"grad_norm": 4.189342719626237,
"learning_rate": 2.7020673425481807e-05,
"loss": 0.6937,
"step": 3250
},
{
"epoch": 0.21275207204855445,
"grad_norm": 5.746674612678528,
"learning_rate": 2.700206533327315e-05,
"loss": 0.6897,
"step": 3260
},
{
"epoch": 0.21340468576649482,
"grad_norm": 7.965064539148002,
"learning_rate": 2.6983405760692782e-05,
"loss": 0.6999,
"step": 3270
},
{
"epoch": 0.21405729948443517,
"grad_norm": 3.6218679643616953,
"learning_rate": 2.696469478777708e-05,
"loss": 0.6702,
"step": 3280
},
{
"epoch": 0.2147099132023755,
"grad_norm": 4.021322876113058,
"learning_rate": 2.6945932494782878e-05,
"loss": 0.736,
"step": 3290
},
{
"epoch": 0.21536252692031588,
"grad_norm": 5.6555927379479245,
"learning_rate": 2.692711896218715e-05,
"loss": 0.6576,
"step": 3300
},
{
"epoch": 0.21601514063825622,
"grad_norm": 5.56743771282241,
"learning_rate": 2.6908254270686633e-05,
"loss": 0.6824,
"step": 3310
},
{
"epoch": 0.21666775435619656,
"grad_norm": 51.07644011063222,
"learning_rate": 2.688933850119753e-05,
"loss": 0.6517,
"step": 3320
},
{
"epoch": 0.2173203680741369,
"grad_norm": 6.112257177604341,
"learning_rate": 2.6870371734855092e-05,
"loss": 0.6619,
"step": 3330
},
{
"epoch": 0.21797298179207727,
"grad_norm": 2.531145729460449,
"learning_rate": 2.685135405301335e-05,
"loss": 0.7057,
"step": 3340
},
{
"epoch": 0.21862559551001762,
"grad_norm": 1.995398951056393,
"learning_rate": 2.6832285537244697e-05,
"loss": 0.687,
"step": 3350
},
{
"epoch": 0.21927820922795796,
"grad_norm": 2.3570011145840364,
"learning_rate": 2.6813166269339587e-05,
"loss": 0.6698,
"step": 3360
},
{
"epoch": 0.21993082294589833,
"grad_norm": 3.6679571799521327,
"learning_rate": 2.6793996331306157e-05,
"loss": 0.6715,
"step": 3370
},
{
"epoch": 0.22058343666383867,
"grad_norm": 28.476293508674676,
"learning_rate": 2.6774775805369875e-05,
"loss": 0.66,
"step": 3380
},
{
"epoch": 0.22123605038177901,
"grad_norm": 3.2467702810162637,
"learning_rate": 2.675550477397321e-05,
"loss": 0.6721,
"step": 3390
},
{
"epoch": 0.22188866409971938,
"grad_norm": 1.6459151219515613,
"learning_rate": 2.6736183319775253e-05,
"loss": 0.7111,
"step": 3400
},
{
"epoch": 0.22254127781765973,
"grad_norm": 3.964489549873003,
"learning_rate": 2.6716811525651386e-05,
"loss": 0.7202,
"step": 3410
},
{
"epoch": 0.22319389153560007,
"grad_norm": 2.1839922437285586,
"learning_rate": 2.6697389474692896e-05,
"loss": 0.6455,
"step": 3420
},
{
"epoch": 0.22384650525354044,
"grad_norm": 6.5190517278902,
"learning_rate": 2.6677917250206642e-05,
"loss": 0.6543,
"step": 3430
},
{
"epoch": 0.22449911897148078,
"grad_norm": 3.0950755352607677,
"learning_rate": 2.6658394935714707e-05,
"loss": 0.6567,
"step": 3440
},
{
"epoch": 0.22515173268942112,
"grad_norm": 22.06688372148941,
"learning_rate": 2.6638822614954007e-05,
"loss": 0.673,
"step": 3450
},
{
"epoch": 0.2258043464073615,
"grad_norm": 4.066518820487963,
"learning_rate": 2.6619200371875952e-05,
"loss": 0.6879,
"step": 3460
},
{
"epoch": 0.22645696012530184,
"grad_norm": 3.121077860957678,
"learning_rate": 2.659952829064609e-05,
"loss": 0.6874,
"step": 3470
},
{
"epoch": 0.22710957384324218,
"grad_norm": 2.6914813691439923,
"learning_rate": 2.6579806455643734e-05,
"loss": 0.6774,
"step": 3480
},
{
"epoch": 0.22776218756118255,
"grad_norm": 4.968423508767704,
"learning_rate": 2.656003495146162e-05,
"loss": 0.6941,
"step": 3490
},
{
"epoch": 0.2284148012791229,
"grad_norm": 3.7025765443419836,
"learning_rate": 2.6540213862905497e-05,
"loss": 0.697,
"step": 3500
},
{
"epoch": 0.22906741499706323,
"grad_norm": 3.5133821241789924,
"learning_rate": 2.652034327499383e-05,
"loss": 0.6825,
"step": 3510
},
{
"epoch": 0.22972002871500358,
"grad_norm": 3.204727293127362,
"learning_rate": 2.6500423272957385e-05,
"loss": 0.6552,
"step": 3520
},
{
"epoch": 0.23037264243294395,
"grad_norm": 10.477867050932252,
"learning_rate": 2.6480453942238878e-05,
"loss": 0.7001,
"step": 3530
},
{
"epoch": 0.2310252561508843,
"grad_norm": 4.290081854975228,
"learning_rate": 2.6460435368492618e-05,
"loss": 0.7023,
"step": 3540
},
{
"epoch": 0.23167786986882463,
"grad_norm": 2.1041454905838695,
"learning_rate": 2.6440367637584127e-05,
"loss": 0.6998,
"step": 3550
},
{
"epoch": 0.232330483586765,
"grad_norm": 10.10346106723381,
"learning_rate": 2.642025083558978e-05,
"loss": 0.7233,
"step": 3560
},
{
"epoch": 0.23298309730470534,
"grad_norm": 2.801890474132496,
"learning_rate": 2.6400085048796427e-05,
"loss": 0.6821,
"step": 3570
},
{
"epoch": 0.2336357110226457,
"grad_norm": 3.935419895594201,
"learning_rate": 2.6379870363701032e-05,
"loss": 0.7208,
"step": 3580
},
{
"epoch": 0.23428832474058606,
"grad_norm": 8.554570222512323,
"learning_rate": 2.6359606867010294e-05,
"loss": 0.6633,
"step": 3590
},
{
"epoch": 0.2349409384585264,
"grad_norm": 6.675371241157707,
"learning_rate": 2.6339294645640287e-05,
"loss": 0.6769,
"step": 3600
}
],
"logging_steps": 10,
"max_steps": 15323,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 400,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.84085412488151e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}