{
"best_metric": 0.8633093520177468,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/bio/ner-seq/run-42/checkpoints/checkpoint-9936",
"epoch": 207.0,
"global_step": 9936,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"eval_loss": 1.1098062992095947,
"eval_micro_f1": 0.003890104334087921,
"eval_runtime": 6.0388,
"eval_samples_per_second": 166.093,
"step": 24
},
{
"epoch": 1.0,
"eval_loss": 0.5973769426345825,
"eval_micro_f1": 0.42558139486896246,
"eval_runtime": 6.0634,
"eval_samples_per_second": 165.418,
"step": 48
},
{
"epoch": 1.5,
"eval_loss": 0.40060245990753174,
"eval_micro_f1": 0.6111590446544916,
"eval_runtime": 5.8615,
"eval_samples_per_second": 171.115,
"step": 72
},
{
"epoch": 2.0,
"eval_loss": 0.3138572573661804,
"eval_micro_f1": 0.7027103727086026,
"eval_runtime": 6.3832,
"eval_samples_per_second": 157.132,
"step": 96
},
{
"epoch": 2.5,
"eval_loss": 0.27617648243904114,
"eval_micro_f1": 0.7279544502705333,
"eval_runtime": 6.2183,
"eval_samples_per_second": 161.298,
"step": 120
},
{
"epoch": 3.0,
"eval_loss": 0.24901142716407776,
"eval_micro_f1": 0.747047513918934,
"eval_runtime": 6.1522,
"eval_samples_per_second": 163.032,
"step": 144
},
{
"epoch": 3.5,
"eval_loss": 0.23769469559192657,
"eval_micro_f1": 0.7653271151218225,
"eval_runtime": 6.7106,
"eval_samples_per_second": 149.466,
"step": 168
},
{
"epoch": 4.0,
"eval_loss": 0.22372488677501678,
"eval_micro_f1": 0.7922799217436097,
"eval_runtime": 6.3584,
"eval_samples_per_second": 157.745,
"step": 192
},
{
"epoch": 4.5,
"eval_loss": 0.2169770449399948,
"eval_micro_f1": 0.7921279207790637,
"eval_runtime": 6.3182,
"eval_samples_per_second": 158.748,
"step": 216
},
{
"epoch": 5.0,
"eval_loss": 0.2114868462085724,
"eval_micro_f1": 0.8005517236377132,
"eval_runtime": 6.262,
"eval_samples_per_second": 160.172,
"step": 240
},
{
"epoch": 5.5,
"eval_loss": 0.21184641122817993,
"eval_micro_f1": 0.8090292198293713,
"eval_runtime": 6.1684,
"eval_samples_per_second": 162.603,
"step": 264
},
{
"epoch": 6.0,
"eval_loss": 0.21851345896720886,
"eval_micro_f1": 0.8180932493258202,
"eval_runtime": 6.2879,
"eval_samples_per_second": 159.514,
"step": 288
},
{
"epoch": 6.5,
"eval_loss": 0.21611660718917847,
"eval_micro_f1": 0.8163490743409797,
"eval_runtime": 6.2623,
"eval_samples_per_second": 160.165,
"step": 312
},
{
"epoch": 7.0,
"eval_loss": 0.21607881784439087,
"eval_micro_f1": 0.8197811326207053,
"eval_runtime": 6.4184,
"eval_samples_per_second": 156.269,
"step": 336
},
{
"epoch": 7.5,
"eval_loss": 0.22012177109718323,
"eval_micro_f1": 0.8179942215385827,
"eval_runtime": 6.3666,
"eval_samples_per_second": 157.542,
"step": 360
},
{
"epoch": 8.0,
"eval_loss": 0.22075983881950378,
"eval_micro_f1": 0.8221823694818424,
"eval_runtime": 5.8453,
"eval_samples_per_second": 171.591,
"step": 384
},
{
"epoch": 8.5,
"eval_loss": 0.22356319427490234,
"eval_micro_f1": 0.8212321227121105,
"eval_runtime": 6.0762,
"eval_samples_per_second": 165.07,
"step": 408
},
{
"epoch": 9.0,
"eval_loss": 0.22051317989826202,
"eval_micro_f1": 0.8247197151137284,
"eval_runtime": 6.0755,
"eval_samples_per_second": 165.089,
"step": 432
},
{
"epoch": 9.5,
"eval_loss": 0.22701342403888702,
"eval_micro_f1": 0.8305528741723245,
"eval_runtime": 6.0451,
"eval_samples_per_second": 165.919,
"step": 456
},
{
"epoch": 10.0,
"eval_loss": 0.23073448240756989,
"eval_micro_f1": 0.8254530584997449,
"eval_runtime": 6.4299,
"eval_samples_per_second": 155.991,
"step": 480
},
{
"epoch": 10.42,
"learning_rate": 9.652777777777779e-06,
"loss": 0.2766,
"step": 500
},
{
"epoch": 10.5,
"eval_loss": 0.23178032040596008,
"eval_micro_f1": 0.829160934850542,
"eval_runtime": 6.1793,
"eval_samples_per_second": 162.315,
"step": 504
},
{
"epoch": 11.0,
"eval_loss": 0.23805859684944153,
"eval_micro_f1": 0.831497796856609,
"eval_runtime": 5.8217,
"eval_samples_per_second": 172.285,
"step": 528
},
{
"epoch": 11.5,
"eval_loss": 0.2399190366268158,
"eval_micro_f1": 0.8264078726545693,
"eval_runtime": 5.8392,
"eval_samples_per_second": 171.772,
"step": 552
},
{
"epoch": 12.0,
"eval_loss": 0.2405175417661667,
"eval_micro_f1": 0.8350260769085273,
"eval_runtime": 5.9074,
"eval_samples_per_second": 169.788,
"step": 576
},
{
"epoch": 12.5,
"eval_loss": 0.2381366789340973,
"eval_micro_f1": 0.834723171065113,
"eval_runtime": 6.5302,
"eval_samples_per_second": 153.593,
"step": 600
},
{
"epoch": 13.0,
"eval_loss": 0.24490594863891602,
"eval_micro_f1": 0.8348041914468227,
"eval_runtime": 6.0728,
"eval_samples_per_second": 165.164,
"step": 624
},
{
"epoch": 13.5,
"eval_loss": 0.24209046363830566,
"eval_micro_f1": 0.8395095738213074,
"eval_runtime": 6.0983,
"eval_samples_per_second": 164.471,
"step": 648
},
{
"epoch": 14.0,
"eval_loss": 0.24820514023303986,
"eval_micro_f1": 0.8326227474024123,
"eval_runtime": 6.4127,
"eval_samples_per_second": 156.407,
"step": 672
},
{
"epoch": 14.5,
"eval_loss": 0.25653138756752014,
"eval_micro_f1": 0.8367683424511504,
"eval_runtime": 6.0646,
"eval_samples_per_second": 165.387,
"step": 696
},
{
"epoch": 15.0,
"eval_loss": 0.2563244700431824,
"eval_micro_f1": 0.8394010161229527,
"eval_runtime": 6.36,
"eval_samples_per_second": 157.705,
"step": 720
},
{
"epoch": 15.5,
"eval_loss": 0.26074159145355225,
"eval_micro_f1": 0.8418304241253202,
"eval_runtime": 5.8817,
"eval_samples_per_second": 170.528,
"step": 744
},
{
"epoch": 16.0,
"eval_loss": 0.26279860734939575,
"eval_micro_f1": 0.8372411896821719,
"eval_runtime": 6.3173,
"eval_samples_per_second": 158.771,
"step": 768
},
{
"epoch": 16.5,
"eval_loss": 0.2652227580547333,
"eval_micro_f1": 0.8411522628742865,
"eval_runtime": 5.8698,
"eval_samples_per_second": 170.875,
"step": 792
},
{
"epoch": 17.0,
"eval_loss": 0.2626892030239105,
"eval_micro_f1": 0.8468793337577448,
"eval_runtime": 6.0919,
"eval_samples_per_second": 164.644,
"step": 816
},
{
"epoch": 17.5,
"eval_loss": 0.2680288255214691,
"eval_micro_f1": 0.8349993148496747,
"eval_runtime": 6.3897,
"eval_samples_per_second": 156.972,
"step": 840
},
{
"epoch": 18.0,
"eval_loss": 0.26079022884368896,
"eval_micro_f1": 0.8468493145683045,
"eval_runtime": 6.5686,
"eval_samples_per_second": 152.695,
"step": 864
},
{
"epoch": 18.5,
"eval_loss": 0.26652792096138,
"eval_micro_f1": 0.846419207447885,
"eval_runtime": 5.9486,
"eval_samples_per_second": 168.612,
"step": 888
},
{
"epoch": 19.0,
"eval_loss": 0.2698013484477997,
"eval_micro_f1": 0.8414969725322518,
"eval_runtime": 6.031,
"eval_samples_per_second": 166.309,
"step": 912
},
{
"epoch": 19.5,
"eval_loss": 0.26716122031211853,
"eval_micro_f1": 0.8425414359638563,
"eval_runtime": 6.27,
"eval_samples_per_second": 159.967,
"step": 936
},
{
"epoch": 20.0,
"eval_loss": 0.27200189232826233,
"eval_micro_f1": 0.8454770410175185,
"eval_runtime": 6.1163,
"eval_samples_per_second": 163.987,
"step": 960
},
{
"epoch": 20.5,
"eval_loss": 0.27574917674064636,
"eval_micro_f1": 0.8431183825604193,
"eval_runtime": 8.494,
"eval_samples_per_second": 118.084,
"step": 984
},
{
"epoch": 20.83,
"learning_rate": 9.305555555555557e-06,
"loss": 0.0254,
"step": 1000
},
{
"epoch": 21.0,
"eval_loss": 0.2804272472858429,
"eval_micro_f1": 0.8444873735855977,
"eval_runtime": 6.2176,
"eval_samples_per_second": 161.317,
"step": 1008
},
{
"epoch": 21.5,
"eval_loss": 0.2772634029388428,
"eval_micro_f1": 0.8412938742416919,
"eval_runtime": 6.1722,
"eval_samples_per_second": 162.503,
"step": 1032
},
{
"epoch": 22.0,
"eval_loss": 0.2732590436935425,
"eval_micro_f1": 0.8384982930152101,
"eval_runtime": 9.0717,
"eval_samples_per_second": 110.564,
"step": 1056
},
{
"epoch": 22.5,
"eval_loss": 0.2768493592739105,
"eval_micro_f1": 0.8461115686121808,
"eval_runtime": 6.0219,
"eval_samples_per_second": 166.559,
"step": 1080
},
{
"epoch": 23.0,
"eval_loss": 0.2818585932254791,
"eval_micro_f1": 0.8440919032197414,
"eval_runtime": 6.1012,
"eval_samples_per_second": 164.395,
"step": 1104
},
{
"epoch": 23.5,
"eval_loss": 0.28745830059051514,
"eval_micro_f1": 0.841771278296846,
"eval_runtime": 9.9264,
"eval_samples_per_second": 101.044,
"step": 1128
},
{
"epoch": 24.0,
"eval_loss": 0.29081103205680847,
"eval_micro_f1": 0.8411651547622235,
"eval_runtime": 6.3347,
"eval_samples_per_second": 158.334,
"step": 1152
},
{
"epoch": 24.5,
"eval_loss": 0.2879377007484436,
"eval_micro_f1": 0.8457629441502503,
"eval_runtime": 6.2616,
"eval_samples_per_second": 160.183,
"step": 1176
},
{
"epoch": 25.0,
"eval_loss": 0.2839908003807068,
"eval_micro_f1": 0.8430777711489715,
"eval_runtime": 6.0974,
"eval_samples_per_second": 164.495,
"step": 1200
},
{
"epoch": 25.5,
"eval_loss": 0.2796134948730469,
"eval_micro_f1": 0.8425099541887948,
"eval_runtime": 6.3706,
"eval_samples_per_second": 157.443,
"step": 1224
},
{
"epoch": 26.0,
"eval_loss": 0.2904074192047119,
"eval_micro_f1": 0.8425696162629374,
"eval_runtime": 6.0586,
"eval_samples_per_second": 165.551,
"step": 1248
},
{
"epoch": 26.5,
"eval_loss": 0.2851482033729553,
"eval_micro_f1": 0.8490044242785261,
"eval_runtime": 6.3763,
"eval_samples_per_second": 157.302,
"step": 1272
},
{
"epoch": 27.0,
"eval_loss": 0.2814634442329407,
"eval_micro_f1": 0.845024021462732,
"eval_runtime": 6.3013,
"eval_samples_per_second": 159.173,
"step": 1296
},
{
"epoch": 27.5,
"eval_loss": 0.2927158772945404,
"eval_micro_f1": 0.8454432643556927,
"eval_runtime": 6.4777,
"eval_samples_per_second": 154.838,
"step": 1320
},
{
"epoch": 28.0,
"eval_loss": 0.2913835048675537,
"eval_micro_f1": 0.8525179851112751,
"eval_runtime": 6.0062,
"eval_samples_per_second": 166.995,
"step": 1344
},
{
"epoch": 28.5,
"eval_loss": 0.289249449968338,
"eval_micro_f1": 0.8486017352760508,
"eval_runtime": 6.3904,
"eval_samples_per_second": 156.955,
"step": 1368
},
{
"epoch": 29.0,
"eval_loss": 0.2902076840400696,
"eval_micro_f1": 0.8464501921249857,
"eval_runtime": 6.7322,
"eval_samples_per_second": 148.985,
"step": 1392
},
{
"epoch": 29.5,
"eval_loss": 0.29000627994537354,
"eval_micro_f1": 0.8463227217830025,
"eval_runtime": 6.226,
"eval_samples_per_second": 161.099,
"step": 1416
},
{
"epoch": 30.0,
"eval_loss": 0.2924293577671051,
"eval_micro_f1": 0.8505652049036853,
"eval_runtime": 6.0131,
"eval_samples_per_second": 166.801,
"step": 1440
},
{
"epoch": 30.5,
"eval_loss": 0.29464036226272583,
"eval_micro_f1": 0.8510638292870268,
"eval_runtime": 6.2792,
"eval_samples_per_second": 159.735,
"step": 1464
},
{
"epoch": 31.0,
"eval_loss": 0.2963722348213196,
"eval_micro_f1": 0.8486257344923084,
"eval_runtime": 6.2548,
"eval_samples_per_second": 160.356,
"step": 1488
},
{
"epoch": 31.25,
"learning_rate": 8.958333333333334e-06,
"loss": 0.008,
"step": 1500
},
{
"epoch": 31.5,
"eval_loss": 0.2964193820953369,
"eval_micro_f1": 0.8495672477481732,
"eval_runtime": 5.907,
"eval_samples_per_second": 169.799,
"step": 1512
},
{
"epoch": 32.0,
"eval_loss": 0.2991025149822235,
"eval_micro_f1": 0.8481618144513184,
"eval_runtime": 5.988,
"eval_samples_per_second": 167.5,
"step": 1536
},
{
"epoch": 32.5,
"eval_loss": 0.30083808302879333,
"eval_micro_f1": 0.8532084820114783,
"eval_runtime": 6.059,
"eval_samples_per_second": 165.539,
"step": 1560
},
{
"epoch": 33.0,
"eval_loss": 0.29919904470443726,
"eval_micro_f1": 0.8511749342256337,
"eval_runtime": 6.0406,
"eval_samples_per_second": 166.044,
"step": 1584
},
{
"epoch": 33.5,
"eval_loss": 0.30297034978866577,
"eval_micro_f1": 0.8507298259938528,
"eval_runtime": 5.7666,
"eval_samples_per_second": 173.934,
"step": 1608
},
{
"epoch": 34.0,
"eval_loss": 0.31402286887168884,
"eval_micro_f1": 0.8461964033725182,
"eval_runtime": 5.8909,
"eval_samples_per_second": 170.263,
"step": 1632
},
{
"epoch": 34.5,
"eval_loss": 0.30535468459129333,
"eval_micro_f1": 0.8467897487419885,
"eval_runtime": 9.2324,
"eval_samples_per_second": 108.639,
"step": 1656
},
{
"epoch": 35.0,
"eval_loss": 0.3078806698322296,
"eval_micro_f1": 0.8474436498571246,
"eval_runtime": 6.0346,
"eval_samples_per_second": 166.209,
"step": 1680
},
{
"epoch": 35.5,
"eval_loss": 0.30856069922447205,
"eval_micro_f1": 0.848934707403564,
"eval_runtime": 6.221,
"eval_samples_per_second": 161.228,
"step": 1704
},
{
"epoch": 36.0,
"eval_loss": 0.310249000787735,
"eval_micro_f1": 0.8474343095836978,
"eval_runtime": 8.9601,
"eval_samples_per_second": 111.941,
"step": 1728
},
{
"epoch": 36.5,
"eval_loss": 0.3153418302536011,
"eval_micro_f1": 0.8441700955217479,
"eval_runtime": 6.2978,
"eval_samples_per_second": 159.262,
"step": 1752
},
{
"epoch": 37.0,
"eval_loss": 0.30738189816474915,
"eval_micro_f1": 0.8492096214929111,
"eval_runtime": 5.8592,
"eval_samples_per_second": 171.183,
"step": 1776
},
{
"epoch": 37.5,
"eval_loss": 0.31066763401031494,
"eval_micro_f1": 0.8501100105008814,
"eval_runtime": 8.982,
"eval_samples_per_second": 111.668,
"step": 1800
},
{
"epoch": 38.0,
"eval_loss": 0.3155709207057953,
"eval_micro_f1": 0.849417636770983,
"eval_runtime": 5.9468,
"eval_samples_per_second": 168.661,
"step": 1824
},
{
"epoch": 38.5,
"eval_loss": 0.30841168761253357,
"eval_micro_f1": 0.8464070208931094,
"eval_runtime": 6.2933,
"eval_samples_per_second": 159.375,
"step": 1848
},
{
"epoch": 39.0,
"eval_loss": 0.31119850277900696,
"eval_micro_f1": 0.8525174916111974,
"eval_runtime": 5.9779,
"eval_samples_per_second": 167.785,
"step": 1872
},
{
"epoch": 39.5,
"eval_loss": 0.32061535120010376,
"eval_micro_f1": 0.8513047074936912,
"eval_runtime": 5.8262,
"eval_samples_per_second": 172.153,
"step": 1896
},
{
"epoch": 40.0,
"eval_loss": 0.3138852119445801,
"eval_micro_f1": 0.8493752569486447,
"eval_runtime": 6.1285,
"eval_samples_per_second": 163.662,
"step": 1920
},
{
"epoch": 40.5,
"eval_loss": 0.31410863995552063,
"eval_micro_f1": 0.8491497526539425,
"eval_runtime": 6.1391,
"eval_samples_per_second": 163.38,
"step": 1944
},
{
"epoch": 41.0,
"eval_loss": 0.3184076249599457,
"eval_micro_f1": 0.8503391937403856,
"eval_runtime": 5.8782,
"eval_samples_per_second": 170.629,
"step": 1968
},
{
"epoch": 41.5,
"eval_loss": 0.3144913911819458,
"eval_micro_f1": 0.8504302685887637,
"eval_runtime": 6.3221,
"eval_samples_per_second": 158.65,
"step": 1992
},
{
"epoch": 41.67,
"learning_rate": 8.611111111111112e-06,
"loss": 0.0036,
"step": 2000
},
{
"epoch": 42.0,
"eval_loss": 0.3145175576210022,
"eval_micro_f1": 0.849594054818341,
"eval_runtime": 6.7679,
"eval_samples_per_second": 148.199,
"step": 2016
},
{
"epoch": 42.5,
"eval_loss": 0.3162612318992615,
"eval_micro_f1": 0.8481861733533427,
"eval_runtime": 5.8201,
"eval_samples_per_second": 172.332,
"step": 2040
},
{
"epoch": 43.0,
"eval_loss": 0.3216666579246521,
"eval_micro_f1": 0.8520204104775647,
"eval_runtime": 5.6573,
"eval_samples_per_second": 177.294,
"step": 2064
},
{
"epoch": 43.5,
"eval_loss": 0.32895880937576294,
"eval_micro_f1": 0.8503674936059948,
"eval_runtime": 5.8628,
"eval_samples_per_second": 171.078,
"step": 2088
},
{
"epoch": 44.0,
"eval_loss": 0.3290811777114868,
"eval_micro_f1": 0.8527345359372976,
"eval_runtime": 6.1149,
"eval_samples_per_second": 164.027,
"step": 2112
},
{
"epoch": 44.5,
"eval_loss": 0.3273111581802368,
"eval_micro_f1": 0.8544277642704653,
"eval_runtime": 5.8979,
"eval_samples_per_second": 170.06,
"step": 2136
},
{
"epoch": 45.0,
"eval_loss": 0.3250843286514282,
"eval_micro_f1": 0.8488516017553166,
"eval_runtime": 5.9627,
"eval_samples_per_second": 168.213,
"step": 2160
},
{
"epoch": 45.5,
"eval_loss": 0.32967016100883484,
"eval_micro_f1": 0.8456449829617348,
"eval_runtime": 8.9687,
"eval_samples_per_second": 111.834,
"step": 2184
},
{
"epoch": 46.0,
"eval_loss": 0.3291603624820709,
"eval_micro_f1": 0.8507236383695155,
"eval_runtime": 6.0794,
"eval_samples_per_second": 164.983,
"step": 2208
},
{
"epoch": 46.5,
"eval_loss": 0.3306710124015808,
"eval_micro_f1": 0.8527153039430255,
"eval_runtime": 5.8369,
"eval_samples_per_second": 171.838,
"step": 2232
},
{
"epoch": 47.0,
"eval_loss": 0.3293270766735077,
"eval_micro_f1": 0.8468148951484756,
"eval_runtime": 6.1375,
"eval_samples_per_second": 163.42,
"step": 2256
},
{
"epoch": 47.5,
"eval_loss": 0.34013232588768005,
"eval_micro_f1": 0.8484257448327537,
"eval_runtime": 6.2118,
"eval_samples_per_second": 161.467,
"step": 2280
},
{
"epoch": 48.0,
"eval_loss": 0.33161190152168274,
"eval_micro_f1": 0.8463024277558394,
"eval_runtime": 6.0255,
"eval_samples_per_second": 166.458,
"step": 2304
},
{
"epoch": 48.5,
"eval_loss": 0.32816997170448303,
"eval_micro_f1": 0.8515506542206523,
"eval_runtime": 5.8808,
"eval_samples_per_second": 170.554,
"step": 2328
},
{
"epoch": 49.0,
"eval_loss": 0.3282072842121124,
"eval_micro_f1": 0.8534732766714263,
"eval_runtime": 5.9773,
"eval_samples_per_second": 167.802,
"step": 2352
},
{
"epoch": 49.5,
"eval_loss": 0.33128488063812256,
"eval_micro_f1": 0.853270639798478,
"eval_runtime": 6.3934,
"eval_samples_per_second": 156.88,
"step": 2376
},
{
"epoch": 50.0,
"eval_loss": 0.3289351165294647,
"eval_micro_f1": 0.848958332833139,
"eval_runtime": 6.0749,
"eval_samples_per_second": 165.106,
"step": 2400
},
{
"epoch": 50.5,
"eval_loss": 0.3343229591846466,
"eval_micro_f1": 0.8525764668461479,
"eval_runtime": 6.0397,
"eval_samples_per_second": 166.068,
"step": 2424
},
{
"epoch": 51.0,
"eval_loss": 0.33142992854118347,
"eval_micro_f1": 0.8509291116814691,
"eval_runtime": 6.1654,
"eval_samples_per_second": 162.682,
"step": 2448
},
{
"epoch": 51.5,
"eval_loss": 0.3288741707801819,
"eval_micro_f1": 0.8547854780476348,
"eval_runtime": 6.0434,
"eval_samples_per_second": 165.966,
"step": 2472
},
{
"epoch": 52.0,
"eval_loss": 0.3286861181259155,
"eval_micro_f1": 0.8542437949200667,
"eval_runtime": 5.9527,
"eval_samples_per_second": 168.496,
"step": 2496
},
{
"epoch": 52.08,
"learning_rate": 8.263888888888888e-06,
"loss": 0.002,
"step": 2500
},
{
"epoch": 52.5,
"eval_loss": 0.32903286814689636,
"eval_micro_f1": 0.8551324498308923,
"eval_runtime": 5.7535,
"eval_samples_per_second": 174.329,
"step": 2520
},
{
"epoch": 53.0,
"eval_loss": 0.33099424839019775,
"eval_micro_f1": 0.850929977617989,
"eval_runtime": 6.7595,
"eval_samples_per_second": 148.384,
"step": 2544
},
{
"epoch": 53.5,
"eval_loss": 0.33220967650413513,
"eval_micro_f1": 0.8531970717273579,
"eval_runtime": 6.1864,
"eval_samples_per_second": 162.129,
"step": 2568
},
{
"epoch": 54.0,
"eval_loss": 0.33008280396461487,
"eval_micro_f1": 0.8516641550949353,
"eval_runtime": 5.9901,
"eval_samples_per_second": 167.443,
"step": 2592
},
{
"epoch": 54.5,
"eval_loss": 0.3372100591659546,
"eval_micro_f1": 0.8543769874682328,
"eval_runtime": 5.7489,
"eval_samples_per_second": 174.469,
"step": 2616
},
{
"epoch": 55.0,
"eval_loss": 0.3379433751106262,
"eval_micro_f1": 0.8535645467059416,
"eval_runtime": 6.0943,
"eval_samples_per_second": 164.58,
"step": 2640
},
{
"epoch": 55.5,
"eval_loss": 0.33973467350006104,
"eval_micro_f1": 0.8511986768213481,
"eval_runtime": 6.2932,
"eval_samples_per_second": 159.378,
"step": 2664
},
{
"epoch": 56.0,
"eval_loss": 0.33183470368385315,
"eval_micro_f1": 0.8446562282269136,
"eval_runtime": 6.1639,
"eval_samples_per_second": 162.72,
"step": 2688
},
{
"epoch": 56.5,
"eval_loss": 0.32909512519836426,
"eval_micro_f1": 0.8533663770297203,
"eval_runtime": 6.0981,
"eval_samples_per_second": 164.478,
"step": 2712
},
{
"epoch": 57.0,
"eval_loss": 0.333426833152771,
"eval_micro_f1": 0.8543956038953913,
"eval_runtime": 6.0494,
"eval_samples_per_second": 165.802,
"step": 2736
},
{
"epoch": 57.5,
"eval_loss": 0.33772042393684387,
"eval_micro_f1": 0.8485263874367477,
"eval_runtime": 5.8869,
"eval_samples_per_second": 170.378,
"step": 2760
},
{
"epoch": 58.0,
"eval_loss": 0.3450329303741455,
"eval_micro_f1": 0.8483764441888267,
"eval_runtime": 6.2394,
"eval_samples_per_second": 160.753,
"step": 2784
},
{
"epoch": 58.5,
"eval_loss": 0.340576708316803,
"eval_micro_f1": 0.8493563402283809,
"eval_runtime": 6.2854,
"eval_samples_per_second": 159.576,
"step": 2808
},
{
"epoch": 59.0,
"eval_loss": 0.34551429748535156,
"eval_micro_f1": 0.8554881407021946,
"eval_runtime": 5.9139,
"eval_samples_per_second": 169.601,
"step": 2832
},
{
"epoch": 59.5,
"eval_loss": 0.3404690623283386,
"eval_micro_f1": 0.8519637457233545,
"eval_runtime": 6.1053,
"eval_samples_per_second": 164.283,
"step": 2856
},
{
"epoch": 60.0,
"eval_loss": 0.3353828191757202,
"eval_micro_f1": 0.8525983815099478,
"eval_runtime": 6.0235,
"eval_samples_per_second": 166.515,
"step": 2880
},
{
"epoch": 60.5,
"eval_loss": 0.33774691820144653,
"eval_micro_f1": 0.8539171136399364,
"eval_runtime": 6.759,
"eval_samples_per_second": 148.394,
"step": 2904
},
{
"epoch": 61.0,
"eval_loss": 0.33614590764045715,
"eval_micro_f1": 0.8552613522230775,
"eval_runtime": 5.8257,
"eval_samples_per_second": 172.168,
"step": 2928
},
{
"epoch": 61.5,
"eval_loss": 0.34379926323890686,
"eval_micro_f1": 0.8556001656357184,
"eval_runtime": 5.7605,
"eval_samples_per_second": 174.118,
"step": 2952
},
{
"epoch": 62.0,
"eval_loss": 0.33785271644592285,
"eval_micro_f1": 0.8527430216364513,
"eval_runtime": 6.3493,
"eval_samples_per_second": 157.971,
"step": 2976
},
{
"epoch": 62.5,
"learning_rate": 7.916666666666667e-06,
"loss": 0.0015,
"step": 3000
},
{
"epoch": 62.5,
"eval_loss": 0.3425731062889099,
"eval_micro_f1": 0.853171872349646,
"eval_runtime": 8.598,
"eval_samples_per_second": 116.655,
"step": 3000
},
{
"epoch": 63.0,
"eval_loss": 0.3453591763973236,
"eval_micro_f1": 0.8541609442951749,
"eval_runtime": 6.4746,
"eval_samples_per_second": 154.913,
"step": 3024
},
{
"epoch": 63.5,
"eval_loss": 0.3501335084438324,
"eval_micro_f1": 0.8550504347629945,
"eval_runtime": 5.9983,
"eval_samples_per_second": 167.214,
"step": 3048
},
{
"epoch": 64.0,
"eval_loss": 0.3514552116394043,
"eval_micro_f1": 0.8477366250142022,
"eval_runtime": 6.3077,
"eval_samples_per_second": 159.012,
"step": 3072
},
{
"epoch": 64.5,
"eval_loss": 0.3520335555076599,
"eval_micro_f1": 0.8502681144454716,
"eval_runtime": 6.2592,
"eval_samples_per_second": 160.244,
"step": 3096
},
{
"epoch": 65.0,
"eval_loss": 0.3587789535522461,
"eval_micro_f1": 0.8504155119651399,
"eval_runtime": 5.9962,
"eval_samples_per_second": 167.273,
"step": 3120
},
{
"epoch": 65.5,
"eval_loss": 0.34796902537345886,
"eval_micro_f1": 0.8516574580633011,
"eval_runtime": 6.318,
"eval_samples_per_second": 158.754,
"step": 3144
},
{
"epoch": 66.0,
"eval_loss": 0.34063753485679626,
"eval_micro_f1": 0.8540689650170088,
"eval_runtime": 5.9339,
"eval_samples_per_second": 169.029,
"step": 3168
},
{
"epoch": 66.5,
"eval_loss": 0.341467022895813,
"eval_micro_f1": 0.8573788541253242,
"eval_runtime": 6.16,
"eval_samples_per_second": 162.826,
"step": 3192
},
{
"epoch": 67.0,
"eval_loss": 0.3511905074119568,
"eval_micro_f1": 0.8540885737049632,
"eval_runtime": 6.1041,
"eval_samples_per_second": 164.317,
"step": 3216
},
{
"epoch": 67.5,
"eval_loss": 0.3426903188228607,
"eval_micro_f1": 0.8565127493274739,
"eval_runtime": 6.6022,
"eval_samples_per_second": 151.919,
"step": 3240
},
{
"epoch": 68.0,
"eval_loss": 0.34657588601112366,
"eval_micro_f1": 0.8525720585261094,
"eval_runtime": 6.5244,
"eval_samples_per_second": 153.731,
"step": 3264
},
{
"epoch": 68.5,
"eval_loss": 0.34785816073417664,
"eval_micro_f1": 0.8562725001920929,
"eval_runtime": 6.2324,
"eval_samples_per_second": 160.932,
"step": 3288
},
{
"epoch": 69.0,
"eval_loss": 0.3417331576347351,
"eval_micro_f1": 0.853373642484531,
"eval_runtime": 6.2335,
"eval_samples_per_second": 160.904,
"step": 3312
},
{
"epoch": 69.5,
"eval_loss": 0.34264498949050903,
"eval_micro_f1": 0.8529048202661667,
"eval_runtime": 6.3502,
"eval_samples_per_second": 157.947,
"step": 3336
},
{
"epoch": 70.0,
"eval_loss": 0.3420845866203308,
"eval_micro_f1": 0.8584853505224274,
"eval_runtime": 5.7697,
"eval_samples_per_second": 173.839,
"step": 3360
},
{
"epoch": 70.5,
"eval_loss": 0.34508171677589417,
"eval_micro_f1": 0.852513501784767,
"eval_runtime": 8.8802,
"eval_samples_per_second": 112.948,
"step": 3384
},
{
"epoch": 71.0,
"eval_loss": 0.3419511914253235,
"eval_micro_f1": 0.8503699638736089,
"eval_runtime": 5.9241,
"eval_samples_per_second": 169.308,
"step": 3408
},
{
"epoch": 71.5,
"eval_loss": 0.34192588925361633,
"eval_micro_f1": 0.8539171136399364,
"eval_runtime": 5.924,
"eval_samples_per_second": 169.311,
"step": 3432
},
{
"epoch": 72.0,
"eval_loss": 0.3473137617111206,
"eval_micro_f1": 0.8556016592508007,
"eval_runtime": 5.9289,
"eval_samples_per_second": 169.172,
"step": 3456
},
{
"epoch": 72.5,
"eval_loss": 0.34460851550102234,
"eval_micro_f1": 0.8527472522470402,
"eval_runtime": 5.7178,
"eval_samples_per_second": 175.418,
"step": 3480
},
{
"epoch": 72.92,
"learning_rate": 7.569444444444445e-06,
"loss": 0.0011,
"step": 3500
},
{
"epoch": 73.0,
"eval_loss": 0.34844404458999634,
"eval_micro_f1": 0.8531642074137356,
"eval_runtime": 5.6024,
"eval_samples_per_second": 179.03,
"step": 3504
},
{
"epoch": 73.5,
"eval_loss": 0.3471376597881317,
"eval_micro_f1": 0.8531756937532877,
"eval_runtime": 5.5814,
"eval_samples_per_second": 179.705,
"step": 3528
},
{
"epoch": 74.0,
"eval_loss": 0.34734970331192017,
"eval_micro_f1": 0.8544303792466125,
"eval_runtime": 6.0314,
"eval_samples_per_second": 166.296,
"step": 3552
},
{
"epoch": 74.5,
"eval_loss": 0.3543611764907837,
"eval_micro_f1": 0.853628195767905,
"eval_runtime": 5.7411,
"eval_samples_per_second": 174.706,
"step": 3576
},
{
"epoch": 75.0,
"eval_loss": 0.35149452090263367,
"eval_micro_f1": 0.8507112272307422,
"eval_runtime": 8.9533,
"eval_samples_per_second": 112.025,
"step": 3600
},
{
"epoch": 75.5,
"eval_loss": 0.35118862986564636,
"eval_micro_f1": 0.8526619887692789,
"eval_runtime": 5.6822,
"eval_samples_per_second": 176.515,
"step": 3624
},
{
"epoch": 76.0,
"eval_loss": 0.3524828553199768,
"eval_micro_f1": 0.8578505568136601,
"eval_runtime": 5.6765,
"eval_samples_per_second": 176.693,
"step": 3648
},
{
"epoch": 76.5,
"eval_loss": 0.3460742235183716,
"eval_micro_f1": 0.8519934457041062,
"eval_runtime": 5.7029,
"eval_samples_per_second": 175.876,
"step": 3672
},
{
"epoch": 77.0,
"eval_loss": 0.34593841433525085,
"eval_micro_f1": 0.8539823003847196,
"eval_runtime": 5.5593,
"eval_samples_per_second": 180.419,
"step": 3696
},
{
"epoch": 77.5,
"eval_loss": 0.3435734808444977,
"eval_micro_f1": 0.8543502197640915,
"eval_runtime": 5.5691,
"eval_samples_per_second": 180.099,
"step": 3720
},
{
"epoch": 78.0,
"eval_loss": 0.34400710463523865,
"eval_micro_f1": 0.854465269621049,
"eval_runtime": 5.8316,
"eval_samples_per_second": 171.993,
"step": 3744
},
{
"epoch": 78.5,
"eval_loss": 0.33947327733039856,
"eval_micro_f1": 0.8509874321748107,
"eval_runtime": 6.2684,
"eval_samples_per_second": 160.009,
"step": 3768
},
{
"epoch": 79.0,
"eval_loss": 0.3416493535041809,
"eval_micro_f1": 0.8496479354379136,
"eval_runtime": 5.6672,
"eval_samples_per_second": 176.983,
"step": 3792
},
{
"epoch": 79.5,
"eval_loss": 0.348812460899353,
"eval_micro_f1": 0.8516984253489787,
"eval_runtime": 5.7239,
"eval_samples_per_second": 175.231,
"step": 3816
},
{
"epoch": 80.0,
"eval_loss": 0.34709683060646057,
"eval_micro_f1": 0.8521571855399067,
"eval_runtime": 5.8615,
"eval_samples_per_second": 171.116,
"step": 3840
},
{
"epoch": 80.5,
"eval_loss": 0.34579169750213623,
"eval_micro_f1": 0.8540807909260013,
"eval_runtime": 6.1261,
"eval_samples_per_second": 163.725,
"step": 3864
},
{
"epoch": 81.0,
"eval_loss": 0.3537646532058716,
"eval_micro_f1": 0.8519587623863811,
"eval_runtime": 5.8368,
"eval_samples_per_second": 171.84,
"step": 3888
},
{
"epoch": 81.5,
"eval_loss": 0.353626012802124,
"eval_micro_f1": 0.8530831833872001,
"eval_runtime": 5.872,
"eval_samples_per_second": 170.811,
"step": 3912
},
{
"epoch": 82.0,
"eval_loss": 0.3480609059333801,
"eval_micro_f1": 0.848767122787482,
"eval_runtime": 5.7421,
"eval_samples_per_second": 174.676,
"step": 3936
},
{
"epoch": 82.5,
"eval_loss": 0.3502531945705414,
"eval_micro_f1": 0.8530140374849123,
"eval_runtime": 5.8972,
"eval_samples_per_second": 170.081,
"step": 3960
},
{
"epoch": 83.0,
"eval_loss": 0.3507061004638672,
"eval_micro_f1": 0.8517089300400132,
"eval_runtime": 5.6921,
"eval_samples_per_second": 176.208,
"step": 3984
},
{
"epoch": 83.33,
"learning_rate": 7.222222222222223e-06,
"loss": 0.0008,
"step": 4000
},
{
"epoch": 83.5,
"eval_loss": 0.34787294268608093,
"eval_micro_f1": 0.8554865419428296,
"eval_runtime": 5.4924,
"eval_samples_per_second": 182.617,
"step": 4008
},
{
"epoch": 84.0,
"eval_loss": 0.3475159704685211,
"eval_micro_f1": 0.8558434394115667,
"eval_runtime": 5.9916,
"eval_samples_per_second": 167.4,
"step": 4032
},
{
"epoch": 84.5,
"eval_loss": 0.35441136360168457,
"eval_micro_f1": 0.8564692825395669,
"eval_runtime": 5.6875,
"eval_samples_per_second": 176.352,
"step": 4056
},
{
"epoch": 85.0,
"eval_loss": 0.34438231587409973,
"eval_micro_f1": 0.8563954283859084,
"eval_runtime": 5.6085,
"eval_samples_per_second": 178.837,
"step": 4080
},
{
"epoch": 85.5,
"eval_loss": 0.34063827991485596,
"eval_micro_f1": 0.8483769341662961,
"eval_runtime": 5.5764,
"eval_samples_per_second": 179.865,
"step": 4104
},
{
"epoch": 86.0,
"eval_loss": 0.3490903675556183,
"eval_micro_f1": 0.851181428268592,
"eval_runtime": 5.7933,
"eval_samples_per_second": 173.131,
"step": 4128
},
{
"epoch": 86.5,
"eval_loss": 0.3459572196006775,
"eval_micro_f1": 0.8517350152726698,
"eval_runtime": 5.9026,
"eval_samples_per_second": 169.924,
"step": 4152
},
{
"epoch": 87.0,
"eval_loss": 0.34485316276550293,
"eval_micro_f1": 0.8522696006001917,
"eval_runtime": 5.5017,
"eval_samples_per_second": 182.306,
"step": 4176
},
{
"epoch": 87.5,
"eval_loss": 0.3643297255039215,
"eval_micro_f1": 0.8547509413164622,
"eval_runtime": 5.6704,
"eval_samples_per_second": 176.884,
"step": 4200
},
{
"epoch": 88.0,
"eval_loss": 0.3472428321838379,
"eval_micro_f1": 0.8618357482920342,
"eval_runtime": 5.7938,
"eval_samples_per_second": 173.116,
"step": 4224
},
{
"epoch": 88.5,
"eval_loss": 0.3448476195335388,
"eval_micro_f1": 0.8558843766504973,
"eval_runtime": 5.435,
"eval_samples_per_second": 184.546,
"step": 4248
},
{
"epoch": 89.0,
"eval_loss": 0.36234745383262634,
"eval_micro_f1": 0.8582162232370842,
"eval_runtime": 5.7096,
"eval_samples_per_second": 175.67,
"step": 4272
},
{
"epoch": 89.5,
"eval_loss": 0.3701987862586975,
"eval_micro_f1": 0.8531042123600764,
"eval_runtime": 6.1332,
"eval_samples_per_second": 163.537,
"step": 4296
},
{
"epoch": 90.0,
"eval_loss": 0.3521389365196228,
"eval_micro_f1": 0.8508820281657026,
"eval_runtime": 5.5021,
"eval_samples_per_second": 182.294,
"step": 4320
},
{
"epoch": 90.5,
"eval_loss": 0.35653793811798096,
"eval_micro_f1": 0.860658003370373,
"eval_runtime": 5.5114,
"eval_samples_per_second": 181.985,
"step": 4344
},
{
"epoch": 91.0,
"eval_loss": 0.3529963195323944,
"eval_micro_f1": 0.8529210557318647,
"eval_runtime": 5.641,
"eval_samples_per_second": 177.806,
"step": 4368
},
{
"epoch": 91.5,
"eval_loss": 0.3580401837825775,
"eval_micro_f1": 0.8532526470035618,
"eval_runtime": 6.4058,
"eval_samples_per_second": 156.577,
"step": 4392
},
{
"epoch": 92.0,
"eval_loss": 0.3582540452480316,
"eval_micro_f1": 0.8562733429774225,
"eval_runtime": 6.0419,
"eval_samples_per_second": 166.009,
"step": 4416
},
{
"epoch": 92.5,
"eval_loss": 0.3542097210884094,
"eval_micro_f1": 0.8561170942249785,
"eval_runtime": 5.5594,
"eval_samples_per_second": 180.414,
"step": 4440
},
{
"epoch": 93.0,
"eval_loss": 0.3571048974990845,
"eval_micro_f1": 0.8574183766867111,
"eval_runtime": 5.3927,
"eval_samples_per_second": 185.993,
"step": 4464
},
{
"epoch": 93.5,
"eval_loss": 0.36213651299476624,
"eval_micro_f1": 0.8523323207804733,
"eval_runtime": 5.6708,
"eval_samples_per_second": 176.87,
"step": 4488
},
{
"epoch": 93.75,
"learning_rate": 6.875e-06,
"loss": 0.0007,
"step": 4500
},
{
"epoch": 94.0,
"eval_loss": 0.3665699064731598,
"eval_micro_f1": 0.8544574977720514,
"eval_runtime": 5.8227,
"eval_samples_per_second": 172.256,
"step": 4512
},
{
"epoch": 94.5,
"eval_loss": 0.36207252740859985,
"eval_micro_f1": 0.8555617039823312,
"eval_runtime": 5.6242,
"eval_samples_per_second": 178.335,
"step": 4536
},
{
"epoch": 95.0,
"eval_loss": 0.36637625098228455,
"eval_micro_f1": 0.8587975725830543,
"eval_runtime": 6.0728,
"eval_samples_per_second": 165.162,
"step": 4560
},
{
"epoch": 95.5,
"eval_loss": 0.3622714579105377,
"eval_micro_f1": 0.85792724726918,
"eval_runtime": 5.5578,
"eval_samples_per_second": 180.466,
"step": 4584
},
{
"epoch": 96.0,
"eval_loss": 0.3659743368625641,
"eval_micro_f1": 0.8548653101100087,
"eval_runtime": 5.6934,
"eval_samples_per_second": 176.168,
"step": 4608
},
{
"epoch": 96.5,
"eval_loss": 0.36642375588417053,
"eval_micro_f1": 0.8587927947699571,
"eval_runtime": 5.683,
"eval_samples_per_second": 176.491,
"step": 4632
},
{
"epoch": 97.0,
"eval_loss": 0.35858702659606934,
"eval_micro_f1": 0.8538493202079045,
"eval_runtime": 8.872,
"eval_samples_per_second": 113.052,
"step": 4656
},
{
"epoch": 97.5,
"eval_loss": 0.3688984811306,
"eval_micro_f1": 0.855199222045932,
"eval_runtime": 6.0184,
"eval_samples_per_second": 166.656,
"step": 4680
},
{
"epoch": 98.0,
"eval_loss": 0.3623090088367462,
"eval_micro_f1": 0.8535679907001111,
"eval_runtime": 5.6719,
"eval_samples_per_second": 176.837,
"step": 4704
},
{
"epoch": 98.5,
"eval_loss": 0.38087159395217896,
"eval_micro_f1": 0.8560732108142424,
"eval_runtime": 5.6312,
"eval_samples_per_second": 178.116,
"step": 4728
},
{
"epoch": 99.0,
"eval_loss": 0.3709181845188141,
"eval_micro_f1": 0.8554466376331349,
"eval_runtime": 5.5415,
"eval_samples_per_second": 180.999,
"step": 4752
},
{
"epoch": 99.5,
"eval_loss": 0.3728066384792328,
"eval_micro_f1": 0.8544251442474945,
"eval_runtime": 6.2188,
"eval_samples_per_second": 161.286,
"step": 4776
},
{
"epoch": 100.0,
"eval_loss": 0.37541478872299194,
"eval_micro_f1": 0.8525313831388901,
"eval_runtime": 5.861,
"eval_samples_per_second": 171.131,
"step": 4800
},
{
"epoch": 100.5,
"eval_loss": 0.3905048072338104,
"eval_micro_f1": 0.8469514719178496,
"eval_runtime": 5.8398,
"eval_samples_per_second": 171.751,
"step": 4824
},
{
"epoch": 101.0,
"eval_loss": 0.3774263262748718,
"eval_micro_f1": 0.8538429803879977,
"eval_runtime": 5.6702,
"eval_samples_per_second": 176.889,
"step": 4848
},
{
"epoch": 101.5,
"eval_loss": 0.3738786578178406,
"eval_micro_f1": 0.8543073737244422,
"eval_runtime": 5.5758,
"eval_samples_per_second": 179.884,
"step": 4872
},
{
"epoch": 102.0,
"eval_loss": 0.3875065743923187,
"eval_micro_f1": 0.8495648565242165,
"eval_runtime": 5.7307,
"eval_samples_per_second": 175.023,
"step": 4896
},
{
"epoch": 102.5,
"eval_loss": 0.39181411266326904,
"eval_micro_f1": 0.8462498262015571,
"eval_runtime": 6.1952,
"eval_samples_per_second": 161.899,
"step": 4920
},
{
"epoch": 103.0,
"eval_loss": 0.3727124333381653,
"eval_micro_f1": 0.8535242285746646,
"eval_runtime": 5.7922,
"eval_samples_per_second": 173.164,
"step": 4944
},
{
"epoch": 103.5,
"eval_loss": 0.36870327591896057,
"eval_micro_f1": 0.8481186482226688,
"eval_runtime": 5.9526,
"eval_samples_per_second": 168.499,
"step": 4968
},
{
"epoch": 104.0,
"eval_loss": 0.36689645051956177,
"eval_micro_f1": 0.8511871888978889,
"eval_runtime": 6.0549,
"eval_samples_per_second": 165.652,
"step": 4992
},
{
"epoch": 104.17,
"learning_rate": 6.5277777777777784e-06,
"loss": 0.0007,
"step": 5000
},
{
"epoch": 104.5,
"eval_loss": 0.3692272901535034,
"eval_micro_f1": 0.8514988253044343,
"eval_runtime": 6.1692,
"eval_samples_per_second": 162.583,
"step": 5016
},
{
"epoch": 105.0,
"eval_loss": 0.3660043478012085,
"eval_micro_f1": 0.8517099858199334,
"eval_runtime": 5.7015,
"eval_samples_per_second": 175.918,
"step": 5040
},
{
"epoch": 105.5,
"eval_loss": 0.372674822807312,
"eval_micro_f1": 0.8507647783340004,
"eval_runtime": 5.4465,
"eval_samples_per_second": 184.155,
"step": 5064
},
{
"epoch": 106.0,
"eval_loss": 0.380240797996521,
"eval_micro_f1": 0.8532818527816217,
"eval_runtime": 6.1483,
"eval_samples_per_second": 163.134,
"step": 5088
},
{
"epoch": 106.5,
"eval_loss": 0.3633327782154083,
"eval_micro_f1": 0.8493449776657929,
"eval_runtime": 5.9509,
"eval_samples_per_second": 168.547,
"step": 5112
},
{
"epoch": 107.0,
"eval_loss": 0.36895424127578735,
"eval_micro_f1": 0.851627136841192,
"eval_runtime": 5.7861,
"eval_samples_per_second": 173.347,
"step": 5136
},
{
"epoch": 107.5,
"eval_loss": 0.37197694182395935,
"eval_micro_f1": 0.8514332960819097,
"eval_runtime": 5.5635,
"eval_samples_per_second": 180.283,
"step": 5160
},
{
"epoch": 108.0,
"eval_loss": 0.3767761290073395,
"eval_micro_f1": 0.8492809729510925,
"eval_runtime": 6.0983,
"eval_samples_per_second": 164.471,
"step": 5184
},
{
"epoch": 108.5,
"eval_loss": 0.3700298070907593,
"eval_micro_f1": 0.8512101205118823,
"eval_runtime": 5.6367,
"eval_samples_per_second": 177.942,
"step": 5208
},
{
"epoch": 109.0,
"eval_loss": 0.36682432889938354,
"eval_micro_f1": 0.8519687194888215,
"eval_runtime": 5.6234,
"eval_samples_per_second": 178.363,
"step": 5232
},
{
"epoch": 109.5,
"eval_loss": 0.3719537854194641,
"eval_micro_f1": 0.8510403743102992,
"eval_runtime": 5.7217,
"eval_samples_per_second": 175.296,
"step": 5256
},
{
"epoch": 110.0,
"eval_loss": 0.3728875517845154,
"eval_micro_f1": 0.8538705666309933,
"eval_runtime": 5.4587,
"eval_samples_per_second": 183.742,
"step": 5280
},
{
"epoch": 110.5,
"eval_loss": 0.3713199198246002,
"eval_micro_f1": 0.8528198069275643,
"eval_runtime": 5.9244,
"eval_samples_per_second": 169.301,
"step": 5304
},
{
"epoch": 111.0,
"eval_loss": 0.37196192145347595,
"eval_micro_f1": 0.8544225191630753,
"eval_runtime": 5.9278,
"eval_samples_per_second": 169.201,
"step": 5328
},
{
"epoch": 111.5,
"eval_loss": 0.3665309548377991,
"eval_micro_f1": 0.8517350152726698,
"eval_runtime": 5.9205,
"eval_samples_per_second": 169.411,
"step": 5352
},
{
"epoch": 112.0,
"eval_loss": 0.36780908703804016,
"eval_micro_f1": 0.8532967027964905,
"eval_runtime": 5.8132,
"eval_samples_per_second": 172.539,
"step": 5376
},
{
"epoch": 112.5,
"eval_loss": 0.36912158131599426,
"eval_micro_f1": 0.8522649038092883,
"eval_runtime": 6.2147,
"eval_samples_per_second": 161.392,
"step": 5400
},
{
"epoch": 113.0,
"eval_loss": 0.36149299144744873,
"eval_micro_f1": 0.8558855880586357,
"eval_runtime": 5.7636,
"eval_samples_per_second": 174.023,
"step": 5424
},
{
"epoch": 113.5,
"eval_loss": 0.3701845109462738,
"eval_micro_f1": 0.8520513878130679,
"eval_runtime": 6.1708,
"eval_samples_per_second": 162.539,
"step": 5448
},
{
"epoch": 114.0,
"eval_loss": 0.3650461435317993,
"eval_micro_f1": 0.8499727218130091,
"eval_runtime": 5.6282,
"eval_samples_per_second": 178.21,
"step": 5472
},
{
"epoch": 114.5,
"eval_loss": 0.3701334297657013,
"eval_micro_f1": 0.856552862935897,
"eval_runtime": 5.8273,
"eval_samples_per_second": 172.12,
"step": 5496
},
{
"epoch": 114.58,
"learning_rate": 6.180555555555557e-06,
"loss": 0.0005,
"step": 5500
},
{
"epoch": 115.0,
"eval_loss": 0.372747540473938,
"eval_micro_f1": 0.8559591211680423,
"eval_runtime": 6.142,
"eval_samples_per_second": 163.303,
"step": 5520
},
{
"epoch": 115.5,
"eval_loss": 0.36282673478126526,
"eval_micro_f1": 0.8573004269091156,
"eval_runtime": 5.9641,
"eval_samples_per_second": 168.172,
"step": 5544
},
{
"epoch": 116.0,
"eval_loss": 0.3660167455673218,
"eval_micro_f1": 0.8576168090104072,
"eval_runtime": 5.7047,
"eval_samples_per_second": 175.82,
"step": 5568
},
{
"epoch": 116.5,
"eval_loss": 0.3644525408744812,
"eval_micro_f1": 0.8549555702448751,
"eval_runtime": 5.8433,
"eval_samples_per_second": 171.65,
"step": 5592
},
{
"epoch": 117.0,
"eval_loss": 0.39221301674842834,
"eval_micro_f1": 0.8509212725316333,
"eval_runtime": 6.2098,
"eval_samples_per_second": 161.519,
"step": 5616
},
{
"epoch": 117.5,
"eval_loss": 0.37303581833839417,
"eval_micro_f1": 0.8548987179784805,
"eval_runtime": 5.8319,
"eval_samples_per_second": 171.984,
"step": 5640
},
{
"epoch": 118.0,
"eval_loss": 0.37046360969543457,
"eval_micro_f1": 0.8536251704984554,
"eval_runtime": 5.7636,
"eval_samples_per_second": 174.022,
"step": 5664
},
{
"epoch": 118.5,
"eval_loss": 0.36990973353385925,
"eval_micro_f1": 0.8569069890429795,
"eval_runtime": 5.7379,
"eval_samples_per_second": 174.804,
"step": 5688
},
{
"epoch": 119.0,
"eval_loss": 0.3653363585472107,
"eval_micro_f1": 0.8573013446668724,
"eval_runtime": 5.8924,
"eval_samples_per_second": 170.22,
"step": 5712
},
{
"epoch": 119.5,
"eval_loss": 0.3810867667198181,
"eval_micro_f1": 0.8565477012078675,
"eval_runtime": 5.9608,
"eval_samples_per_second": 168.265,
"step": 5736
},
{
"epoch": 120.0,
"eval_loss": 0.3663919270038605,
"eval_micro_f1": 0.8575349981272968,
"eval_runtime": 5.4571,
"eval_samples_per_second": 183.797,
"step": 5760
},
{
"epoch": 120.5,
"eval_loss": 0.37352585792541504,
"eval_micro_f1": 0.855140186415671,
"eval_runtime": 5.6351,
"eval_samples_per_second": 177.99,
"step": 5784
},
{
"epoch": 121.0,
"eval_loss": 0.3712100386619568,
"eval_micro_f1": 0.858478888235853,
"eval_runtime": 5.6798,
"eval_samples_per_second": 176.592,
"step": 5808
},
{
"epoch": 121.5,
"eval_loss": 0.3769887685775757,
"eval_micro_f1": 0.8552957354007412,
"eval_runtime": 5.8072,
"eval_samples_per_second": 172.718,
"step": 5832
},
{
"epoch": 122.0,
"eval_loss": 0.37318331003189087,
"eval_micro_f1": 0.8567884212778529,
"eval_runtime": 5.6716,
"eval_samples_per_second": 176.845,
"step": 5856
},
{
"epoch": 122.5,
"eval_loss": 0.37376827001571655,
"eval_micro_f1": 0.8558011044721399,
"eval_runtime": 6.2446,
"eval_samples_per_second": 160.619,
"step": 5880
},
{
"epoch": 123.0,
"eval_loss": 0.37398213148117065,
"eval_micro_f1": 0.8557612595163431,
"eval_runtime": 5.6401,
"eval_samples_per_second": 177.835,
"step": 5904
},
{
"epoch": 123.5,
"eval_loss": 0.3746246099472046,
"eval_micro_f1": 0.8532743846890433,
"eval_runtime": 5.636,
"eval_samples_per_second": 177.963,
"step": 5928
},
{
"epoch": 124.0,
"eval_loss": 0.3776625692844391,
"eval_micro_f1": 0.8565907517426913,
"eval_runtime": 5.7377,
"eval_samples_per_second": 174.809,
"step": 5952
},
{
"epoch": 124.5,
"eval_loss": 0.3907985985279083,
"eval_micro_f1": 0.8550020808096065,
"eval_runtime": 5.936,
"eval_samples_per_second": 168.969,
"step": 5976
},
{
"epoch": 125.0,
"learning_rate": 5.833333333333334e-06,
"loss": 0.0005,
"step": 6000
},
{
"epoch": 125.0,
"eval_loss": 0.37965744733810425,
"eval_micro_f1": 0.8533479387028808,
"eval_runtime": 5.6237,
"eval_samples_per_second": 178.352,
"step": 6000
},
{
"epoch": 125.5,
"eval_loss": 0.37962594628334045,
"eval_micro_f1": 0.8523195163814845,
"eval_runtime": 5.6029,
"eval_samples_per_second": 179.015,
"step": 6024
},
{
"epoch": 126.0,
"eval_loss": 0.39396020770072937,
"eval_micro_f1": 0.8528428088643412,
"eval_runtime": 5.5906,
"eval_samples_per_second": 179.408,
"step": 6048
},
{
"epoch": 126.5,
"eval_loss": 0.3795776963233948,
"eval_micro_f1": 0.8543209871541182,
"eval_runtime": 5.8837,
"eval_samples_per_second": 170.47,
"step": 6072
},
{
"epoch": 127.0,
"eval_loss": 0.3853691816329956,
"eval_micro_f1": 0.8537560298236841,
"eval_runtime": 6.0649,
"eval_samples_per_second": 165.378,
"step": 6096
},
{
"epoch": 127.5,
"eval_loss": 0.39363810420036316,
"eval_micro_f1": 0.8536585360851318,
"eval_runtime": 5.8293,
"eval_samples_per_second": 172.062,
"step": 6120
},
{
"epoch": 128.0,
"eval_loss": 0.38859593868255615,
"eval_micro_f1": 0.855090481610553,
"eval_runtime": 6.0043,
"eval_samples_per_second": 167.047,
"step": 6144
},
{
"epoch": 128.5,
"eval_loss": 0.38463208079338074,
"eval_micro_f1": 0.8484597315069492,
"eval_runtime": 5.7281,
"eval_samples_per_second": 175.101,
"step": 6168
},
{
"epoch": 129.0,
"eval_loss": 0.38469961285591125,
"eval_micro_f1": 0.8541237815774666,
"eval_runtime": 5.7777,
"eval_samples_per_second": 173.597,
"step": 6192
},
{
"epoch": 129.5,
"eval_loss": 0.37942320108413696,
"eval_micro_f1": 0.8577710590023256,
"eval_runtime": 5.702,
"eval_samples_per_second": 175.904,
"step": 6216
},
{
"epoch": 130.0,
"eval_loss": 0.3804577887058258,
"eval_micro_f1": 0.8547455290733686,
"eval_runtime": 5.9726,
"eval_samples_per_second": 167.934,
"step": 6240
},
{
"epoch": 130.5,
"eval_loss": 0.3916989266872406,
"eval_micro_f1": 0.8516666661664399,
"eval_runtime": 5.9032,
"eval_samples_per_second": 169.907,
"step": 6264
},
{
"epoch": 131.0,
"eval_loss": 0.38645055890083313,
"eval_micro_f1": 0.851181428268592,
"eval_runtime": 5.5458,
"eval_samples_per_second": 180.858,
"step": 6288
},
{
"epoch": 131.5,
"eval_loss": 0.37874165177345276,
"eval_micro_f1": 0.8535842784922911,
"eval_runtime": 6.3049,
"eval_samples_per_second": 159.082,
"step": 6312
},
{
"epoch": 132.0,
"eval_loss": 0.38064897060394287,
"eval_micro_f1": 0.854500275590323,
"eval_runtime": 5.6982,
"eval_samples_per_second": 176.02,
"step": 6336
},
{
"epoch": 132.5,
"eval_loss": 0.3811017572879791,
"eval_micro_f1": 0.8520253508362279,
"eval_runtime": 5.8722,
"eval_samples_per_second": 170.805,
"step": 6360
},
{
"epoch": 133.0,
"eval_loss": 0.38710901141166687,
"eval_micro_f1": 0.8537494816154948,
"eval_runtime": 5.8989,
"eval_samples_per_second": 170.031,
"step": 6384
},
{
"epoch": 133.5,
"eval_loss": 0.39245015382766724,
"eval_micro_f1": 0.8535541747930717,
"eval_runtime": 5.6235,
"eval_samples_per_second": 178.358,
"step": 6408
},
{
"epoch": 134.0,
"eval_loss": 0.3756490647792816,
"eval_micro_f1": 0.8525085905650751,
"eval_runtime": 5.659,
"eval_samples_per_second": 177.238,
"step": 6432
},
{
"epoch": 134.5,
"eval_loss": 0.3782115578651428,
"eval_micro_f1": 0.8535102261443193,
"eval_runtime": 8.3175,
"eval_samples_per_second": 120.589,
"step": 6456
},
{
"epoch": 135.0,
"eval_loss": 0.3912818431854248,
"eval_micro_f1": 0.8539853565932857,
"eval_runtime": 6.2509,
"eval_samples_per_second": 160.457,
"step": 6480
},
{
"epoch": 135.42,
"learning_rate": 5.486111111111112e-06,
"loss": 0.0004,
"step": 6500
},
{
"epoch": 135.5,
"eval_loss": 0.38531988859176636,
"eval_micro_f1": 0.8534292030395869,
"eval_runtime": 5.908,
"eval_samples_per_second": 169.769,
"step": 6504
},
{
"epoch": 136.0,
"eval_loss": 0.3855549991130829,
"eval_micro_f1": 0.8551647738005119,
"eval_runtime": 5.6047,
"eval_samples_per_second": 178.957,
"step": 6528
},
{
"epoch": 136.5,
"eval_loss": 0.38542604446411133,
"eval_micro_f1": 0.8533517617665229,
"eval_runtime": 5.7414,
"eval_samples_per_second": 174.696,
"step": 6552
},
{
"epoch": 137.0,
"eval_loss": 0.38722705841064453,
"eval_micro_f1": 0.8554801158916177,
"eval_runtime": 5.5862,
"eval_samples_per_second": 179.55,
"step": 6576
},
{
"epoch": 137.5,
"eval_loss": 0.3835110366344452,
"eval_micro_f1": 0.8500068610340341,
"eval_runtime": 8.5511,
"eval_samples_per_second": 117.295,
"step": 6600
},
{
"epoch": 138.0,
"eval_loss": 0.3856574296951294,
"eval_micro_f1": 0.849800741563823,
"eval_runtime": 5.6908,
"eval_samples_per_second": 176.249,
"step": 6624
},
{
"epoch": 138.5,
"eval_loss": 0.3717750012874603,
"eval_micro_f1": 0.8491237672982827,
"eval_runtime": 6.1099,
"eval_samples_per_second": 164.161,
"step": 6648
},
{
"epoch": 139.0,
"eval_loss": 0.38148289918899536,
"eval_micro_f1": 0.8531932535777292,
"eval_runtime": 5.7548,
"eval_samples_per_second": 174.288,
"step": 6672
},
{
"epoch": 139.5,
"eval_loss": 0.38594627380371094,
"eval_micro_f1": 0.8534256050360963,
"eval_runtime": 5.572,
"eval_samples_per_second": 180.008,
"step": 6696
},
{
"epoch": 140.0,
"eval_loss": 0.3809627294540405,
"eval_micro_f1": 0.855609084152218,
"eval_runtime": 6.0836,
"eval_samples_per_second": 164.87,
"step": 6720
},
{
"epoch": 140.5,
"eval_loss": 0.38293471932411194,
"eval_micro_f1": 0.8566298337539076,
"eval_runtime": 6.2031,
"eval_samples_per_second": 161.694,
"step": 6744
},
{
"epoch": 141.0,
"eval_loss": 0.37818583846092224,
"eval_micro_f1": 0.8535084114817699,
"eval_runtime": 5.8175,
"eval_samples_per_second": 172.41,
"step": 6768
},
{
"epoch": 141.5,
"eval_loss": 0.38753288984298706,
"eval_micro_f1": 0.8528644039509473,
"eval_runtime": 5.9812,
"eval_samples_per_second": 167.693,
"step": 6792
},
{
"epoch": 142.0,
"eval_loss": 0.3880375623703003,
"eval_micro_f1": 0.8550865046900751,
"eval_runtime": 5.7101,
"eval_samples_per_second": 175.653,
"step": 6816
},
{
"epoch": 142.5,
"eval_loss": 0.38564714789390564,
"eval_micro_f1": 0.8569847851152539,
"eval_runtime": 5.6349,
"eval_samples_per_second": 177.999,
"step": 6840
},
{
"epoch": 143.0,
"eval_loss": 0.3862641155719757,
"eval_micro_f1": 0.8545028266960164,
"eval_runtime": 5.443,
"eval_samples_per_second": 184.272,
"step": 6864
},
{
"epoch": 143.5,
"eval_loss": 0.3768296539783478,
"eval_micro_f1": 0.8520401149002539,
"eval_runtime": 5.4694,
"eval_samples_per_second": 183.385,
"step": 6888
},
{
"epoch": 144.0,
"eval_loss": 0.3925332725048065,
"eval_micro_f1": 0.8559888574385065,
"eval_runtime": 5.6488,
"eval_samples_per_second": 177.561,
"step": 6912
},
{
"epoch": 144.5,
"eval_loss": 0.383102148771286,
"eval_micro_f1": 0.8543101069082006,
"eval_runtime": 6.1279,
"eval_samples_per_second": 163.678,
"step": 6936
},
{
"epoch": 145.0,
"eval_loss": 0.38753485679626465,
"eval_micro_f1": 0.8541781954045783,
"eval_runtime": 6.0038,
"eval_samples_per_second": 167.06,
"step": 6960
},
{
"epoch": 145.5,
"eval_loss": 0.38225728273391724,
"eval_micro_f1": 0.8515259824527658,
"eval_runtime": 5.9668,
"eval_samples_per_second": 168.096,
"step": 6984
},
{
"epoch": 145.83,
"learning_rate": 5.138888888888889e-06,
"loss": 0.0003,
"step": 7000
},
{
"epoch": 146.0,
"eval_loss": 0.38822275400161743,
"eval_micro_f1": 0.8542671992791703,
"eval_runtime": 6.0265,
"eval_samples_per_second": 166.432,
"step": 7008
},
{
"epoch": 146.5,
"eval_loss": 0.3835729658603668,
"eval_micro_f1": 0.8543956038953913,
"eval_runtime": 5.8949,
"eval_samples_per_second": 170.147,
"step": 7032
},
{
"epoch": 147.0,
"eval_loss": 0.3849795162677765,
"eval_micro_f1": 0.8587633139277608,
"eval_runtime": 5.8164,
"eval_samples_per_second": 172.444,
"step": 7056
},
{
"epoch": 147.5,
"eval_loss": 0.3917798697948456,
"eval_micro_f1": 0.8590808411387438,
"eval_runtime": 5.7209,
"eval_samples_per_second": 175.321,
"step": 7080
},
{
"epoch": 148.0,
"eval_loss": 0.39219409227371216,
"eval_micro_f1": 0.8584474880842375,
"eval_runtime": 5.5661,
"eval_samples_per_second": 180.199,
"step": 7104
},
{
"epoch": 148.5,
"eval_loss": 0.3943347632884979,
"eval_micro_f1": 0.8584474880842375,
"eval_runtime": 5.6779,
"eval_samples_per_second": 176.649,
"step": 7128
},
{
"epoch": 149.0,
"eval_loss": 0.3948417603969574,
"eval_micro_f1": 0.8584070791457803,
"eval_runtime": 5.7195,
"eval_samples_per_second": 175.364,
"step": 7152
},
{
"epoch": 149.5,
"eval_loss": 0.3897669315338135,
"eval_micro_f1": 0.8535450309807922,
"eval_runtime": 5.9135,
"eval_samples_per_second": 169.611,
"step": 7176
},
{
"epoch": 150.0,
"eval_loss": 0.39478468894958496,
"eval_micro_f1": 0.8583679109797072,
"eval_runtime": 8.3714,
"eval_samples_per_second": 119.813,
"step": 7200
},
{
"epoch": 150.5,
"eval_loss": 0.38256460428237915,
"eval_micro_f1": 0.8574173180122125,
"eval_runtime": 5.5847,
"eval_samples_per_second": 179.597,
"step": 7224
},
{
"epoch": 151.0,
"eval_loss": 0.38082531094551086,
"eval_micro_f1": 0.8563982987728741,
"eval_runtime": 5.6053,
"eval_samples_per_second": 178.937,
"step": 7248
},
{
"epoch": 151.5,
"eval_loss": 0.39371758699417114,
"eval_micro_f1": 0.8581727431570508,
"eval_runtime": 6.3519,
"eval_samples_per_second": 157.905,
"step": 7272
},
{
"epoch": 152.0,
"eval_loss": 0.3845665752887726,
"eval_micro_f1": 0.8565121407801193,
"eval_runtime": 5.8139,
"eval_samples_per_second": 172.518,
"step": 7296
},
{
"epoch": 152.5,
"eval_loss": 0.3823990821838379,
"eval_micro_f1": 0.8587927947699571,
"eval_runtime": 5.667,
"eval_samples_per_second": 176.99,
"step": 7320
},
{
"epoch": 153.0,
"eval_loss": 0.3907621502876282,
"eval_micro_f1": 0.8582861868876499,
"eval_runtime": 5.7157,
"eval_samples_per_second": 175.483,
"step": 7344
},
{
"epoch": 153.5,
"eval_loss": 0.38899049162864685,
"eval_micro_f1": 0.8571034857888699,
"eval_runtime": 6.1259,
"eval_samples_per_second": 163.73,
"step": 7368
},
{
"epoch": 154.0,
"eval_loss": 0.402112752199173,
"eval_micro_f1": 0.8543769874682328,
"eval_runtime": 5.6522,
"eval_samples_per_second": 177.452,
"step": 7392
},
{
"epoch": 154.5,
"eval_loss": 0.3932728171348572,
"eval_micro_f1": 0.8557958952291065,
"eval_runtime": 5.7058,
"eval_samples_per_second": 175.785,
"step": 7416
},
{
"epoch": 155.0,
"eval_loss": 0.38310226798057556,
"eval_micro_f1": 0.8550645067740174,
"eval_runtime": 5.8421,
"eval_samples_per_second": 171.684,
"step": 7440
},
{
"epoch": 155.5,
"eval_loss": 0.3877960741519928,
"eval_micro_f1": 0.8586851206070292,
"eval_runtime": 5.9703,
"eval_samples_per_second": 167.999,
"step": 7464
},
{
"epoch": 156.0,
"eval_loss": 0.39034387469291687,
"eval_micro_f1": 0.8552903843804399,
"eval_runtime": 5.6986,
"eval_samples_per_second": 176.008,
"step": 7488
},
{
"epoch": 156.25,
"learning_rate": 4.791666666666668e-06,
"loss": 0.0003,
"step": 7500
},
{
"epoch": 156.5,
"eval_loss": 0.39123356342315674,
"eval_micro_f1": 0.8557227663090982,
"eval_runtime": 5.8192,
"eval_samples_per_second": 172.361,
"step": 7512
},
{
"epoch": 157.0,
"eval_loss": 0.3877943754196167,
"eval_micro_f1": 0.8563528268189945,
"eval_runtime": 6.0841,
"eval_samples_per_second": 164.855,
"step": 7536
},
{
"epoch": 157.5,
"eval_loss": 0.39917612075805664,
"eval_micro_f1": 0.8549280172184792,
"eval_runtime": 5.6549,
"eval_samples_per_second": 177.368,
"step": 7560
},
{
"epoch": 158.0,
"eval_loss": 0.3977440297603607,
"eval_micro_f1": 0.8555232955041876,
"eval_runtime": 5.4972,
"eval_samples_per_second": 182.456,
"step": 7584
},
{
"epoch": 158.5,
"eval_loss": 0.40202879905700684,
"eval_micro_f1": 0.854304635261356,
"eval_runtime": 5.8271,
"eval_samples_per_second": 172.126,
"step": 7608
},
{
"epoch": 159.0,
"eval_loss": 0.39499518275260925,
"eval_micro_f1": 0.857379767327292,
"eval_runtime": 6.0158,
"eval_samples_per_second": 166.728,
"step": 7632
},
{
"epoch": 159.5,
"eval_loss": 0.39411211013793945,
"eval_micro_f1": 0.8547478351463419,
"eval_runtime": 6.0658,
"eval_samples_per_second": 165.353,
"step": 7656
},
{
"epoch": 160.0,
"eval_loss": 0.3973565399646759,
"eval_micro_f1": 0.8534697257922715,
"eval_runtime": 5.6179,
"eval_samples_per_second": 178.537,
"step": 7680
},
{
"epoch": 160.5,
"eval_loss": 0.38958290219306946,
"eval_micro_f1": 0.8566313175000474,
"eval_runtime": 6.1011,
"eval_samples_per_second": 164.396,
"step": 7704
},
{
"epoch": 161.0,
"eval_loss": 0.3927232623100281,
"eval_micro_f1": 0.855640137908068,
"eval_runtime": 8.4923,
"eval_samples_per_second": 118.107,
"step": 7728
},
{
"epoch": 161.5,
"eval_loss": 0.40015000104904175,
"eval_micro_f1": 0.8534803578733052,
"eval_runtime": 5.6185,
"eval_samples_per_second": 178.517,
"step": 7752
},
{
"epoch": 162.0,
"eval_loss": 0.4028796851634979,
"eval_micro_f1": 0.8533075001917099,
"eval_runtime": 6.2091,
"eval_samples_per_second": 161.536,
"step": 7776
},
{
"epoch": 162.5,
"eval_loss": 0.39666134119033813,
"eval_micro_f1": 0.8550423077255965,
"eval_runtime": 5.8041,
"eval_samples_per_second": 172.807,
"step": 7800
},
{
"epoch": 163.0,
"eval_loss": 0.38879114389419556,
"eval_micro_f1": 0.8524137926032161,
"eval_runtime": 6.0472,
"eval_samples_per_second": 165.861,
"step": 7824
},
{
"epoch": 163.5,
"eval_loss": 0.38980597257614136,
"eval_micro_f1": 0.853002069893141,
"eval_runtime": 5.9512,
"eval_samples_per_second": 168.537,
"step": 7848
},
{
"epoch": 164.0,
"eval_loss": 0.3938656449317932,
"eval_micro_f1": 0.8561974350436811,
"eval_runtime": 6.074,
"eval_samples_per_second": 165.13,
"step": 7872
},
{
"epoch": 164.5,
"eval_loss": 0.3952140212059021,
"eval_micro_f1": 0.8568673365985447,
"eval_runtime": 6.3602,
"eval_samples_per_second": 157.7,
"step": 7896
},
{
"epoch": 165.0,
"eval_loss": 0.40358638763427734,
"eval_micro_f1": 0.8536247919734773,
"eval_runtime": 5.5093,
"eval_samples_per_second": 182.057,
"step": 7920
},
{
"epoch": 165.5,
"eval_loss": 0.3869708478450775,
"eval_micro_f1": 0.8544225191630753,
"eval_runtime": 5.7983,
"eval_samples_per_second": 172.982,
"step": 7944
},
{
"epoch": 166.0,
"eval_loss": 0.3874531686306,
"eval_micro_f1": 0.8550524567057288,
"eval_runtime": 5.5447,
"eval_samples_per_second": 180.892,
"step": 7968
},
{
"epoch": 166.5,
"eval_loss": 0.3891386091709137,
"eval_micro_f1": 0.8550124270059786,
"eval_runtime": 5.8403,
"eval_samples_per_second": 171.739,
"step": 7992
},
{
"epoch": 166.67,
"learning_rate": 4.444444444444444e-06,
"loss": 0.0003,
"step": 8000
},
{
"epoch": 167.0,
"eval_loss": 0.3918393850326538,
"eval_micro_f1": 0.8555632337775797,
"eval_runtime": 5.7383,
"eval_samples_per_second": 174.791,
"step": 8016
},
{
"epoch": 167.5,
"eval_loss": 0.3910408318042755,
"eval_micro_f1": 0.8536652830405661,
"eval_runtime": 5.9314,
"eval_samples_per_second": 169.1,
"step": 8040
},
{
"epoch": 168.0,
"eval_loss": 0.39062175154685974,
"eval_micro_f1": 0.8530910087246123,
"eval_runtime": 6.1458,
"eval_samples_per_second": 163.2,
"step": 8064
},
{
"epoch": 168.5,
"eval_loss": 0.39219942688941956,
"eval_micro_f1": 0.8552067482205489,
"eval_runtime": 5.6698,
"eval_samples_per_second": 176.902,
"step": 8088
},
{
"epoch": 169.0,
"eval_loss": 0.3994564414024353,
"eval_micro_f1": 0.855354658748736,
"eval_runtime": 5.7264,
"eval_samples_per_second": 175.153,
"step": 8112
},
{
"epoch": 169.5,
"eval_loss": 0.39145705103874207,
"eval_micro_f1": 0.8595614760470895,
"eval_runtime": 5.716,
"eval_samples_per_second": 175.471,
"step": 8136
},
{
"epoch": 170.0,
"eval_loss": 0.39426934719085693,
"eval_micro_f1": 0.8576581571024312,
"eval_runtime": 5.8686,
"eval_samples_per_second": 170.91,
"step": 8160
},
{
"epoch": 170.5,
"eval_loss": 0.39562082290649414,
"eval_micro_f1": 0.857895466018551,
"eval_runtime": 8.614,
"eval_samples_per_second": 116.439,
"step": 8184
},
{
"epoch": 171.0,
"eval_loss": 0.3995242714881897,
"eval_micro_f1": 0.8583298707087372,
"eval_runtime": 5.8989,
"eval_samples_per_second": 170.032,
"step": 8208
},
{
"epoch": 171.5,
"eval_loss": 0.39817550778388977,
"eval_micro_f1": 0.8549660612811749,
"eval_runtime": 5.7135,
"eval_samples_per_second": 175.55,
"step": 8232
},
{
"epoch": 172.0,
"eval_loss": 0.3983123004436493,
"eval_micro_f1": 0.8547339317734334,
"eval_runtime": 5.921,
"eval_samples_per_second": 169.397,
"step": 8256
},
{
"epoch": 172.5,
"eval_loss": 0.3970920443534851,
"eval_micro_f1": 0.8546206891549398,
"eval_runtime": 5.7379,
"eval_samples_per_second": 174.803,
"step": 8280
},
{
"epoch": 173.0,
"eval_loss": 0.39891427755355835,
"eval_micro_f1": 0.8570247928882011,
"eval_runtime": 5.7045,
"eval_samples_per_second": 175.827,
"step": 8304
},
{
"epoch": 173.5,
"eval_loss": 0.39694347977638245,
"eval_micro_f1": 0.8556473824198819,
"eval_runtime": 6.1692,
"eval_samples_per_second": 162.581,
"step": 8328
},
{
"epoch": 174.0,
"eval_loss": 0.3953845202922821,
"eval_micro_f1": 0.8554768841311742,
"eval_runtime": 5.7391,
"eval_samples_per_second": 174.765,
"step": 8352
},
{
"epoch": 174.5,
"eval_loss": 0.39521798491477966,
"eval_micro_f1": 0.855674398721887,
"eval_runtime": 5.6073,
"eval_samples_per_second": 178.873,
"step": 8376
},
{
"epoch": 175.0,
"eval_loss": 0.39752158522605896,
"eval_micro_f1": 0.8563896207013778,
"eval_runtime": 5.731,
"eval_samples_per_second": 175.013,
"step": 8400
},
{
"epoch": 175.5,
"eval_loss": 0.39693886041641235,
"eval_micro_f1": 0.854374307362444,
"eval_runtime": 5.9297,
"eval_samples_per_second": 169.147,
"step": 8424
},
{
"epoch": 176.0,
"eval_loss": 0.39973294734954834,
"eval_micro_f1": 0.8566273416232946,
"eval_runtime": 5.7092,
"eval_samples_per_second": 175.682,
"step": 8448
},
{
"epoch": 176.5,
"eval_loss": 0.3962303400039673,
"eval_micro_f1": 0.8539480944749174,
"eval_runtime": 5.6499,
"eval_samples_per_second": 177.525,
"step": 8472
},
{
"epoch": 177.0,
"eval_loss": 0.39966246485710144,
"eval_micro_f1": 0.8558807283788374,
"eval_runtime": 5.6861,
"eval_samples_per_second": 176.396,
"step": 8496
},
{
"epoch": 177.08,
"learning_rate": 4.097222222222222e-06,
"loss": 0.0002,
"step": 8500
},
{
"epoch": 177.5,
"eval_loss": 0.4028112590312958,
"eval_micro_f1": 0.8552850022667805,
"eval_runtime": 5.6586,
"eval_samples_per_second": 177.252,
"step": 8520
},
{
"epoch": 178.0,
"eval_loss": 0.4031909108161926,
"eval_micro_f1": 0.8557599220554263,
"eval_runtime": 5.6041,
"eval_samples_per_second": 178.976,
"step": 8544
},
{
"epoch": 178.5,
"eval_loss": 0.40641722083091736,
"eval_micro_f1": 0.8574591747004272,
"eval_runtime": 5.7003,
"eval_samples_per_second": 175.957,
"step": 8568
},
{
"epoch": 179.0,
"eval_loss": 0.4027506709098816,
"eval_micro_f1": 0.8565923474216028,
"eval_runtime": 6.1105,
"eval_samples_per_second": 164.144,
"step": 8592
},
{
"epoch": 179.5,
"eval_loss": 0.4038204550743103,
"eval_micro_f1": 0.8558396677789618,
"eval_runtime": 5.7716,
"eval_samples_per_second": 173.783,
"step": 8616
},
{
"epoch": 180.0,
"eval_loss": 0.4131969213485718,
"eval_micro_f1": 0.8523816131645413,
"eval_runtime": 5.6353,
"eval_samples_per_second": 177.984,
"step": 8640
},
{
"epoch": 180.5,
"eval_loss": 0.40509098768234253,
"eval_micro_f1": 0.8555647606154785,
"eval_runtime": 5.6804,
"eval_samples_per_second": 176.572,
"step": 8664
},
{
"epoch": 181.0,
"eval_loss": 0.4057497978210449,
"eval_micro_f1": 0.8567474043440538,
"eval_runtime": 5.5763,
"eval_samples_per_second": 179.868,
"step": 8688
},
{
"epoch": 181.5,
"eval_loss": 0.40371522307395935,
"eval_micro_f1": 0.8576154371289898,
"eval_runtime": 5.7443,
"eval_samples_per_second": 174.607,
"step": 8712
},
{
"epoch": 182.0,
"eval_loss": 0.4053860902786255,
"eval_micro_f1": 0.8572610669387409,
"eval_runtime": 5.7325,
"eval_samples_per_second": 174.968,
"step": 8736
},
{
"epoch": 182.5,
"eval_loss": 0.40778404474258423,
"eval_micro_f1": 0.859156875795547,
"eval_runtime": 5.9697,
"eval_samples_per_second": 168.014,
"step": 8760
},
{
"epoch": 183.0,
"eval_loss": 0.40705546736717224,
"eval_micro_f1": 0.8597485140776264,
"eval_runtime": 5.6568,
"eval_samples_per_second": 177.309,
"step": 8784
},
{
"epoch": 183.5,
"eval_loss": 0.39787569642066956,
"eval_micro_f1": 0.8560804291926519,
"eval_runtime": 6.5717,
"eval_samples_per_second": 152.625,
"step": 8808
},
{
"epoch": 184.0,
"eval_loss": 0.40880951285362244,
"eval_micro_f1": 0.8575778541710434,
"eval_runtime": 5.7729,
"eval_samples_per_second": 173.744,
"step": 8832
},
{
"epoch": 184.5,
"eval_loss": 0.40336480736732483,
"eval_micro_f1": 0.8547409035791523,
"eval_runtime": 8.64,
"eval_samples_per_second": 116.088,
"step": 8856
},
{
"epoch": 185.0,
"eval_loss": 0.39812880754470825,
"eval_micro_f1": 0.8532160522760345,
"eval_runtime": 5.6351,
"eval_samples_per_second": 177.991,
"step": 8880
},
{
"epoch": 185.5,
"eval_loss": 0.3996230363845825,
"eval_micro_f1": 0.8536383677467382,
"eval_runtime": 5.5888,
"eval_samples_per_second": 179.465,
"step": 8904
},
{
"epoch": 186.0,
"eval_loss": 0.40416982769966125,
"eval_micro_f1": 0.856826056325822,
"eval_runtime": 5.5375,
"eval_samples_per_second": 181.129,
"step": 8928
},
{
"epoch": 186.5,
"eval_loss": 0.3977098762989044,
"eval_micro_f1": 0.8583252857461446,
"eval_runtime": 6.0174,
"eval_samples_per_second": 166.683,
"step": 8952
},
{
"epoch": 187.0,
"eval_loss": 0.4049621522426605,
"eval_micro_f1": 0.8563528268189945,
"eval_runtime": 5.7731,
"eval_samples_per_second": 173.737,
"step": 8976
},
{
"epoch": 187.5,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0002,
"step": 9000
},
{
"epoch": 187.5,
"eval_loss": 0.39555349946022034,
"eval_micro_f1": 0.8561577708416512,
"eval_runtime": 5.8513,
"eval_samples_per_second": 171.415,
"step": 9000
},
{
"epoch": 188.0,
"eval_loss": 0.3971739709377289,
"eval_micro_f1": 0.8559977883333734,
"eval_runtime": 5.7265,
"eval_samples_per_second": 175.152,
"step": 9024
},
{
"epoch": 188.5,
"eval_loss": 0.4019377827644348,
"eval_micro_f1": 0.8543339790068261,
"eval_runtime": 5.5606,
"eval_samples_per_second": 180.375,
"step": 9048
},
{
"epoch": 189.0,
"eval_loss": 0.4021461009979248,
"eval_micro_f1": 0.8545328714720821,
"eval_runtime": 5.899,
"eval_samples_per_second": 170.03,
"step": 9072
},
{
"epoch": 189.5,
"eval_loss": 0.40178442001342773,
"eval_micro_f1": 0.8555601712211325,
"eval_runtime": 5.4149,
"eval_samples_per_second": 185.23,
"step": 9096
},
{
"epoch": 190.0,
"eval_loss": 0.402057945728302,
"eval_micro_f1": 0.8560742480106384,
"eval_runtime": 5.91,
"eval_samples_per_second": 169.714,
"step": 9120
},
{
"epoch": 190.5,
"eval_loss": 0.40114665031433105,
"eval_micro_f1": 0.8559579757231529,
"eval_runtime": 5.7715,
"eval_samples_per_second": 173.785,
"step": 9144
},
{
"epoch": 191.0,
"eval_loss": 0.40176090598106384,
"eval_micro_f1": 0.8563543530253626,
"eval_runtime": 5.8027,
"eval_samples_per_second": 172.851,
"step": 9168
},
{
"epoch": 191.5,
"eval_loss": 0.40274718403816223,
"eval_micro_f1": 0.8564725360716672,
"eval_runtime": 5.802,
"eval_samples_per_second": 172.872,
"step": 9192
},
{
"epoch": 192.0,
"eval_loss": 0.40702563524246216,
"eval_micro_f1": 0.8559193253735035,
"eval_runtime": 5.6942,
"eval_samples_per_second": 176.145,
"step": 9216
},
{
"epoch": 192.5,
"eval_loss": 0.40590065717697144,
"eval_micro_f1": 0.8568670706525529,
"eval_runtime": 6.0125,
"eval_samples_per_second": 166.82,
"step": 9240
},
{
"epoch": 193.0,
"eval_loss": 0.4045752286911011,
"eval_micro_f1": 0.8570640932282318,
"eval_runtime": 5.4373,
"eval_samples_per_second": 184.466,
"step": 9264
},
{
"epoch": 193.5,
"eval_loss": 0.4057496190071106,
"eval_micro_f1": 0.8565912846624812,
"eval_runtime": 6.2198,
"eval_samples_per_second": 161.258,
"step": 9288
},
{
"epoch": 194.0,
"eval_loss": 0.40410348773002625,
"eval_micro_f1": 0.8571428566426279,
"eval_runtime": 5.6852,
"eval_samples_per_second": 176.424,
"step": 9312
},
{
"epoch": 194.5,
"eval_loss": 0.4102969765663147,
"eval_micro_f1": 0.8573806876240739,
"eval_runtime": 5.5912,
"eval_samples_per_second": 179.388,
"step": 9336
},
{
"epoch": 195.0,
"eval_loss": 0.3981609046459198,
"eval_micro_f1": 0.8586373016332908,
"eval_runtime": 5.6659,
"eval_samples_per_second": 177.023,
"step": 9360
},
{
"epoch": 195.5,
"eval_loss": 0.40271085500717163,
"eval_micro_f1": 0.8603522391336583,
"eval_runtime": 5.9572,
"eval_samples_per_second": 168.369,
"step": 9384
},
{
"epoch": 196.0,
"eval_loss": 0.4059590995311737,
"eval_micro_f1": 0.8580520194222863,
"eval_runtime": 5.756,
"eval_samples_per_second": 174.253,
"step": 9408
},
{
"epoch": 196.5,
"eval_loss": 0.40151461958885193,
"eval_micro_f1": 0.8567489309763983,
"eval_runtime": 5.6257,
"eval_samples_per_second": 178.288,
"step": 9432
},
{
"epoch": 197.0,
"eval_loss": 0.4040184020996094,
"eval_micro_f1": 0.8561568189365402,
"eval_runtime": 5.5723,
"eval_samples_per_second": 179.997,
"step": 9456
},
{
"epoch": 197.5,
"eval_loss": 0.3993892967700958,
"eval_micro_f1": 0.8594766712428058,
"eval_runtime": 5.6807,
"eval_samples_per_second": 176.561,
"step": 9480
},
{
"epoch": 197.92,
"learning_rate": 3.4027777777777783e-06,
"loss": 0.0001,
"step": 9500
},
{
"epoch": 198.0,
"eval_loss": 0.4072522819042206,
"eval_micro_f1": 0.8595497854409317,
"eval_runtime": 5.6766,
"eval_samples_per_second": 176.691,
"step": 9504
},
{
"epoch": 198.5,
"eval_loss": 0.4100194275379181,
"eval_micro_f1": 0.8594721564708834,
"eval_runtime": 8.317,
"eval_samples_per_second": 120.597,
"step": 9528
},
{
"epoch": 199.0,
"eval_loss": 0.4050011932849884,
"eval_micro_f1": 0.857656163126076,
"eval_runtime": 5.4136,
"eval_samples_per_second": 185.273,
"step": 9552
},
{
"epoch": 199.5,
"eval_loss": 0.40566879510879517,
"eval_micro_f1": 0.858130530473214,
"eval_runtime": 5.4929,
"eval_samples_per_second": 182.599,
"step": 9576
},
{
"epoch": 200.0,
"eval_loss": 0.40994182229042053,
"eval_micro_f1": 0.8548900257827903,
"eval_runtime": 5.4167,
"eval_samples_per_second": 185.168,
"step": 9600
},
{
"epoch": 200.5,
"eval_loss": 0.3946707844734192,
"eval_micro_f1": 0.8590677844578437,
"eval_runtime": 5.4529,
"eval_samples_per_second": 183.938,
"step": 9624
},
{
"epoch": 201.0,
"eval_loss": 0.394417941570282,
"eval_micro_f1": 0.8593792909032482,
"eval_runtime": 6.1316,
"eval_samples_per_second": 163.578,
"step": 9648
},
{
"epoch": 201.5,
"eval_loss": 0.3943053185939789,
"eval_micro_f1": 0.861602209444514,
"eval_runtime": 5.7586,
"eval_samples_per_second": 174.173,
"step": 9672
},
{
"epoch": 202.0,
"eval_loss": 0.3954358994960785,
"eval_micro_f1": 0.8612148881119107,
"eval_runtime": 5.6373,
"eval_samples_per_second": 177.921,
"step": 9696
},
{
"epoch": 202.5,
"eval_loss": 0.40347030758857727,
"eval_micro_f1": 0.8599221784881004,
"eval_runtime": 5.8309,
"eval_samples_per_second": 172.015,
"step": 9720
},
{
"epoch": 203.0,
"eval_loss": 0.40211471915245056,
"eval_micro_f1": 0.8600635441882556,
"eval_runtime": 5.7031,
"eval_samples_per_second": 175.869,
"step": 9744
},
{
"epoch": 203.5,
"eval_loss": 0.4008079469203949,
"eval_micro_f1": 0.8608467792542825,
"eval_runtime": 5.589,
"eval_samples_per_second": 179.459,
"step": 9768
},
{
"epoch": 204.0,
"eval_loss": 0.40170103311538696,
"eval_micro_f1": 0.8611686692055229,
"eval_runtime": 5.9822,
"eval_samples_per_second": 167.663,
"step": 9792
},
{
"epoch": 204.5,
"eval_loss": 0.40431681275367737,
"eval_micro_f1": 0.8593944416399532,
"eval_runtime": 5.5512,
"eval_samples_per_second": 180.682,
"step": 9816
},
{
"epoch": 205.0,
"eval_loss": 0.4069841802120209,
"eval_micro_f1": 0.8587633139277608,
"eval_runtime": 5.6951,
"eval_samples_per_second": 176.117,
"step": 9840
},
{
"epoch": 205.5,
"eval_loss": 0.40759971737861633,
"eval_micro_f1": 0.8589601764909128,
"eval_runtime": 5.7064,
"eval_samples_per_second": 175.769,
"step": 9864
},
{
"epoch": 206.0,
"eval_loss": 0.40662652254104614,
"eval_micro_f1": 0.858444965664658,
"eval_runtime": 5.8179,
"eval_samples_per_second": 172.4,
"step": 9888
},
{
"epoch": 206.5,
"eval_loss": 0.4064077138900757,
"eval_micro_f1": 0.8586791667409089,
"eval_runtime": 6.1843,
"eval_samples_per_second": 162.184,
"step": 9912
},
{
"epoch": 207.0,
"eval_loss": 0.41001489758491516,
"eval_micro_f1": 0.8633093520177468,
"eval_runtime": 5.8209,
"eval_samples_per_second": 172.311,
"step": 9936
}
],
"max_steps": 14400,
"num_train_epochs": 300,
"total_flos": 37620331380469854,
"trial_name": null,
"trial_params": null
}
{
"best_metric": 0.8633093520177468,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/bio/ner-seq/run-42/checkpoints/checkpoint-9936",
"epoch": 207.0,
"global_step": 9936,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"eval_loss": 1.1098062992095947,
"eval_micro_f1": 0.003890104334087921,
"eval_runtime": 6.0388,
"eval_samples_per_second": 166.093,
"step": 24
},
{
"epoch": 1.0,
"eval_loss": 0.5973769426345825,
"eval_micro_f1": 0.42558139486896246,
"eval_runtime": 6.0634,
"eval_samples_per_second": 165.418,
"step": 48
},
{
"epoch": 1.5,
"eval_loss": 0.40060245990753174,
"eval_micro_f1": 0.6111590446544916,
"eval_runtime": 5.8615,
"eval_samples_per_second": 171.115,
"step": 72
},
{
"epoch": 2.0,
"eval_loss": 0.3138572573661804,
"eval_micro_f1": 0.7027103727086026,
"eval_runtime": 6.3832,
"eval_samples_per_second": 157.132,
"step": 96
},
{
"epoch": 2.5,
"eval_loss": 0.27617648243904114,
"eval_micro_f1": 0.7279544502705333,
"eval_runtime": 6.2183,
"eval_samples_per_second": 161.298,
"step": 120
},
{
"epoch": 3.0,
"eval_loss": 0.24901142716407776,
"eval_micro_f1": 0.747047513918934,
"eval_runtime": 6.1522,
"eval_samples_per_second": 163.032,
"step": 144
},
{
"epoch": 3.5,
"eval_loss": 0.23769469559192657,
"eval_micro_f1": 0.7653271151218225,
"eval_runtime": 6.7106,
"eval_samples_per_second": 149.466,
"step": 168
},
{
"epoch": 4.0,
"eval_loss": 0.22372488677501678,
"eval_micro_f1": 0.7922799217436097,
"eval_runtime": 6.3584,
"eval_samples_per_second": 157.745,
"step": 192
},
{
"epoch": 4.5,
"eval_loss": 0.2169770449399948,
"eval_micro_f1": 0.7921279207790637,
"eval_runtime": 6.3182,
"eval_samples_per_second": 158.748,
"step": 216
},
{
"epoch": 5.0,
"eval_loss": 0.2114868462085724,
"eval_micro_f1": 0.8005517236377132,
"eval_runtime": 6.262,
"eval_samples_per_second": 160.172,
"step": 240
},
{
"epoch": 5.5,
"eval_loss": 0.21184641122817993,
"eval_micro_f1": 0.8090292198293713,
"eval_runtime": 6.1684,
"eval_samples_per_second": 162.603,
"step": 264
},
{
"epoch": 6.0,
"eval_loss": 0.21851345896720886,