Harshkmr's picture
Model save
b435234 verified
raw
history blame contribute delete
No virus
33.2 kB
{
"best_metric": 0.019619259983301163,
"best_model_checkpoint": "./deberta-v3-base_finetuned_bluegennx_run2.19_5e/checkpoint-61284",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 76605,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"grad_norm": 3.245230197906494,
"learning_rate": 1.6317472749820508e-06,
"loss": 2.448,
"step": 500
},
{
"epoch": 0.07,
"grad_norm": 2.250610589981079,
"learning_rate": 3.2634945499641016e-06,
"loss": 0.6227,
"step": 1000
},
{
"epoch": 0.1,
"grad_norm": 1.1213871240615845,
"learning_rate": 4.895241824946153e-06,
"loss": 0.2667,
"step": 1500
},
{
"epoch": 0.13,
"grad_norm": 1.0988842248916626,
"learning_rate": 6.526989099928203e-06,
"loss": 0.1493,
"step": 2000
},
{
"epoch": 0.16,
"grad_norm": 0.4658643901348114,
"learning_rate": 8.158736374910254e-06,
"loss": 0.1199,
"step": 2500
},
{
"epoch": 0.2,
"grad_norm": 3.3459713459014893,
"learning_rate": 9.790483649892306e-06,
"loss": 0.0827,
"step": 3000
},
{
"epoch": 0.23,
"grad_norm": 0.9581575989723206,
"learning_rate": 1.1422230924874356e-05,
"loss": 0.0722,
"step": 3500
},
{
"epoch": 0.26,
"grad_norm": 0.7753175497055054,
"learning_rate": 1.3053978199856406e-05,
"loss": 0.0662,
"step": 4000
},
{
"epoch": 0.29,
"grad_norm": 1.246222972869873,
"learning_rate": 1.4685725474838458e-05,
"loss": 0.0581,
"step": 4500
},
{
"epoch": 0.33,
"grad_norm": 0.37093016505241394,
"learning_rate": 1.6317472749820508e-05,
"loss": 0.0613,
"step": 5000
},
{
"epoch": 0.36,
"grad_norm": 0.08493436872959137,
"learning_rate": 1.794922002480256e-05,
"loss": 0.0476,
"step": 5500
},
{
"epoch": 0.39,
"grad_norm": 2.2330055236816406,
"learning_rate": 1.9580967299784612e-05,
"loss": 0.0513,
"step": 6000
},
{
"epoch": 0.42,
"grad_norm": 0.4164097309112549,
"learning_rate": 2.1212714574766664e-05,
"loss": 0.0479,
"step": 6500
},
{
"epoch": 0.46,
"grad_norm": 3.0428450107574463,
"learning_rate": 2.2844461849748712e-05,
"loss": 0.0485,
"step": 7000
},
{
"epoch": 0.49,
"grad_norm": 0.09525569528341293,
"learning_rate": 2.447620912473076e-05,
"loss": 0.0453,
"step": 7500
},
{
"epoch": 0.52,
"grad_norm": 0.07735457271337509,
"learning_rate": 2.6107956399712813e-05,
"loss": 0.0498,
"step": 8000
},
{
"epoch": 0.55,
"grad_norm": 0.946909487247467,
"learning_rate": 2.7739703674694868e-05,
"loss": 0.0473,
"step": 8500
},
{
"epoch": 0.59,
"grad_norm": 0.9449179172515869,
"learning_rate": 2.9371450949676916e-05,
"loss": 0.0474,
"step": 9000
},
{
"epoch": 0.62,
"grad_norm": 0.2430952489376068,
"learning_rate": 3.1003198224658965e-05,
"loss": 0.049,
"step": 9500
},
{
"epoch": 0.65,
"grad_norm": 0.028986895456910133,
"learning_rate": 3.2634945499641017e-05,
"loss": 0.0463,
"step": 10000
},
{
"epoch": 0.69,
"grad_norm": 1.1573065519332886,
"learning_rate": 3.426669277462307e-05,
"loss": 0.0464,
"step": 10500
},
{
"epoch": 0.72,
"grad_norm": 0.5098071694374084,
"learning_rate": 3.589844004960512e-05,
"loss": 0.0328,
"step": 11000
},
{
"epoch": 0.75,
"grad_norm": 2.0675878524780273,
"learning_rate": 3.7530187324587165e-05,
"loss": 0.0475,
"step": 11500
},
{
"epoch": 0.78,
"grad_norm": 1.0651479959487915,
"learning_rate": 3.9161934599569224e-05,
"loss": 0.0401,
"step": 12000
},
{
"epoch": 0.82,
"grad_norm": 1.4569103717803955,
"learning_rate": 4.079368187455127e-05,
"loss": 0.041,
"step": 12500
},
{
"epoch": 0.85,
"grad_norm": 0.0765555128455162,
"learning_rate": 4.242542914953333e-05,
"loss": 0.0418,
"step": 13000
},
{
"epoch": 0.88,
"grad_norm": 0.020283367484807968,
"learning_rate": 4.405717642451537e-05,
"loss": 0.042,
"step": 13500
},
{
"epoch": 0.91,
"grad_norm": 1.3270998001098633,
"learning_rate": 4.5688923699497425e-05,
"loss": 0.0379,
"step": 14000
},
{
"epoch": 0.95,
"grad_norm": 0.03816336765885353,
"learning_rate": 4.7320670974479476e-05,
"loss": 0.0389,
"step": 14500
},
{
"epoch": 0.98,
"grad_norm": 0.19806864857673645,
"learning_rate": 4.895241824946152e-05,
"loss": 0.0356,
"step": 15000
},
{
"epoch": 1.0,
"eval_AADHAR_CARD_f1": 0.9541764859910972,
"eval_AGE_f1": 0.9221036963532623,
"eval_CITY_f1": 0.961690662625242,
"eval_COUNTRY_f1": 0.9815987933634993,
"eval_CREDITCARDCVV_f1": 0.9242819843342036,
"eval_CREDITCARDNUMBER_f1": 0.9194598504943332,
"eval_DATEOFBIRTH_f1": 0.8261840929401251,
"eval_DATE_f1": 0.9235115474256657,
"eval_EMAIL_f1": 0.9826121319897253,
"eval_EXPIRYDATE_f1": 0.9477218225419664,
"eval_ORGANIZATION_f1": 0.9882065880439204,
"eval_PAN_CARD_f1": 0.952861952861953,
"eval_PERSON_f1": 0.9784977775772208,
"eval_PHONENUMBER_f1": 0.9684334165320805,
"eval_PINCODE_f1": 0.9187232642316552,
"eval_SECONDARYADDRESS_f1": 0.9734371879368884,
"eval_STATE_f1": 0.9665119779254986,
"eval_TIME_f1": 0.9722814498933902,
"eval_URL_f1": 0.9888343010272443,
"eval_loss": 0.03825685754418373,
"eval_overall_accuracy": 0.9914659328103238,
"eval_overall_f1": 0.9604457982205258,
"eval_overall_precision": 0.953495189906404,
"eval_overall_recall": 0.9674984850988817,
"eval_runtime": 283.0168,
"eval_samples_per_second": 54.135,
"eval_steps_per_second": 13.536,
"step": 15321
},
{
"epoch": 1.01,
"grad_norm": 0.31435033679008484,
"learning_rate": 4.999894750857725e-05,
"loss": 0.0413,
"step": 15500
},
{
"epoch": 1.04,
"grad_norm": 0.7508180737495422,
"learning_rate": 4.998485702341302e-05,
"loss": 0.0385,
"step": 16000
},
{
"epoch": 1.08,
"grad_norm": 0.05294118449091911,
"learning_rate": 4.995435313505215e-05,
"loss": 0.0341,
"step": 16500
},
{
"epoch": 1.11,
"grad_norm": 1.2048356533050537,
"learning_rate": 4.990745588253741e-05,
"loss": 0.0348,
"step": 17000
},
{
"epoch": 1.14,
"grad_norm": 0.943110466003418,
"learning_rate": 4.9844196074270636e-05,
"loss": 0.0324,
"step": 17500
},
{
"epoch": 1.17,
"grad_norm": 0.6435505151748657,
"learning_rate": 4.976461526777355e-05,
"loss": 0.033,
"step": 18000
},
{
"epoch": 1.21,
"grad_norm": 1.040231466293335,
"learning_rate": 4.9668765742387324e-05,
"loss": 0.0311,
"step": 18500
},
{
"epoch": 1.24,
"grad_norm": 0.9562444686889648,
"learning_rate": 4.95567104649284e-05,
"loss": 0.0387,
"step": 19000
},
{
"epoch": 1.27,
"grad_norm": 0.04553946480154991,
"learning_rate": 4.942852304832349e-05,
"loss": 0.0344,
"step": 19500
},
{
"epoch": 1.31,
"grad_norm": 0.9238176941871643,
"learning_rate": 4.9284287703250774e-05,
"loss": 0.0317,
"step": 20000
},
{
"epoch": 1.34,
"grad_norm": 1.8379842042922974,
"learning_rate": 4.912409918281895e-05,
"loss": 0.0324,
"step": 20500
},
{
"epoch": 1.37,
"grad_norm": 0.031245272606611252,
"learning_rate": 4.8948062720320765e-05,
"loss": 0.0297,
"step": 21000
},
{
"epoch": 1.4,
"grad_norm": 1.3249530792236328,
"learning_rate": 4.875629396010166e-05,
"loss": 0.0326,
"step": 21500
},
{
"epoch": 1.44,
"grad_norm": 0.7412520051002502,
"learning_rate": 4.8548918881589053e-05,
"loss": 0.0255,
"step": 22000
},
{
"epoch": 1.47,
"grad_norm": 0.0375283844769001,
"learning_rate": 4.832607371653218e-05,
"loss": 0.0298,
"step": 22500
},
{
"epoch": 1.5,
"grad_norm": 4.709392547607422,
"learning_rate": 4.80879048595068e-05,
"loss": 0.0289,
"step": 23000
},
{
"epoch": 1.53,
"grad_norm": 0.03978699445724487,
"learning_rate": 4.783456877174363e-05,
"loss": 0.0292,
"step": 23500
},
{
"epoch": 1.57,
"grad_norm": 1.0908358097076416,
"learning_rate": 4.756623187834363e-05,
"loss": 0.0282,
"step": 24000
},
{
"epoch": 1.6,
"grad_norm": 0.3756016492843628,
"learning_rate": 4.728307045894771e-05,
"loss": 0.029,
"step": 24500
},
{
"epoch": 1.63,
"grad_norm": 0.9585224390029907,
"learning_rate": 4.69852705319326e-05,
"loss": 0.0338,
"step": 25000
},
{
"epoch": 1.66,
"grad_norm": 0.8365939855575562,
"learning_rate": 4.667302773220904e-05,
"loss": 0.0263,
"step": 25500
},
{
"epoch": 1.7,
"grad_norm": 0.04708540067076683,
"learning_rate": 4.634654718270259e-05,
"loss": 0.0251,
"step": 26000
},
{
"epoch": 1.73,
"grad_norm": 7.851020812988281,
"learning_rate": 4.600604335960137e-05,
"loss": 0.0275,
"step": 26500
},
{
"epoch": 1.76,
"grad_norm": 0.26771125197410583,
"learning_rate": 4.5651739951459325e-05,
"loss": 0.0249,
"step": 27000
},
{
"epoch": 1.79,
"grad_norm": 0.9391166567802429,
"learning_rate": 4.5283869712247654e-05,
"loss": 0.0258,
"step": 27500
},
{
"epoch": 1.83,
"grad_norm": 0.2116001844406128,
"learning_rate": 4.490267430845077e-05,
"loss": 0.0283,
"step": 28000
},
{
"epoch": 1.86,
"grad_norm": 1.2127752304077148,
"learning_rate": 4.4508404160307335e-05,
"loss": 0.0241,
"step": 28500
},
{
"epoch": 1.89,
"grad_norm": 0.6359685659408569,
"learning_rate": 4.410131827730075e-05,
"loss": 0.0256,
"step": 29000
},
{
"epoch": 1.93,
"grad_norm": 0.8148425817489624,
"learning_rate": 4.368168408800692e-05,
"loss": 0.027,
"step": 29500
},
{
"epoch": 1.96,
"grad_norm": 0.36649465560913086,
"learning_rate": 4.324977726441138e-05,
"loss": 0.027,
"step": 30000
},
{
"epoch": 1.99,
"grad_norm": 0.3655473291873932,
"learning_rate": 4.2805881540810985e-05,
"loss": 0.0231,
"step": 30500
},
{
"epoch": 2.0,
"eval_AADHAR_CARD_f1": 0.9585547290116896,
"eval_AGE_f1": 0.9436792916871618,
"eval_CITY_f1": 0.9808301383563929,
"eval_COUNTRY_f1": 0.9821049438883834,
"eval_CREDITCARDCVV_f1": 0.9798747763864043,
"eval_CREDITCARDNUMBER_f1": 0.9006162464985994,
"eval_DATEOFBIRTH_f1": 0.8788368336025848,
"eval_DATE_f1": 0.9488200589970501,
"eval_EMAIL_f1": 0.9863582443653618,
"eval_EXPIRYDATE_f1": 0.97678916827853,
"eval_ORGANIZATION_f1": 0.9842724080012216,
"eval_PAN_CARD_f1": 0.9836812144212523,
"eval_PERSON_f1": 0.9824277196535044,
"eval_PHONENUMBER_f1": 0.9809048178613397,
"eval_PINCODE_f1": 0.9840319361277445,
"eval_SECONDARYADDRESS_f1": 0.9819501865483513,
"eval_STATE_f1": 0.9906398256186691,
"eval_TIME_f1": 0.9748799408939787,
"eval_URL_f1": 0.9783627035467322,
"eval_loss": 0.026541395112872124,
"eval_overall_accuracy": 0.9937106918238994,
"eval_overall_f1": 0.9709243706638617,
"eval_overall_precision": 0.9606781562088824,
"eval_overall_recall": 0.981391505536275,
"eval_runtime": 250.4032,
"eval_samples_per_second": 61.185,
"eval_steps_per_second": 15.299,
"step": 30642
},
{
"epoch": 2.02,
"grad_norm": 2.719433307647705,
"learning_rate": 4.235028852741913e-05,
"loss": 0.0246,
"step": 31000
},
{
"epoch": 2.06,
"grad_norm": 0.7214369177818298,
"learning_rate": 4.188329751879714e-05,
"loss": 0.0169,
"step": 31500
},
{
"epoch": 2.09,
"grad_norm": 0.23133157193660736,
"learning_rate": 4.140521529723744e-05,
"loss": 0.0203,
"step": 32000
},
{
"epoch": 2.12,
"grad_norm": 0.07947224378585815,
"learning_rate": 4.091635593122785e-05,
"loss": 0.0228,
"step": 32500
},
{
"epoch": 2.15,
"grad_norm": 0.12643003463745117,
"learning_rate": 4.041704056912928e-05,
"loss": 0.0207,
"step": 33000
},
{
"epoch": 2.19,
"grad_norm": 0.0956706777215004,
"learning_rate": 3.990759722820246e-05,
"loss": 0.0169,
"step": 33500
},
{
"epoch": 2.22,
"grad_norm": 1.9679731130599976,
"learning_rate": 3.938836057912222e-05,
"loss": 0.0182,
"step": 34000
},
{
"epoch": 2.25,
"grad_norm": 0.5308653712272644,
"learning_rate": 3.8859671726120916e-05,
"loss": 0.0226,
"step": 34500
},
{
"epoch": 2.28,
"grad_norm": 0.40330055356025696,
"learning_rate": 3.832187798290548e-05,
"loss": 0.0202,
"step": 35000
},
{
"epoch": 2.32,
"grad_norm": 0.1867927610874176,
"learning_rate": 3.777533264449522e-05,
"loss": 0.0218,
"step": 35500
},
{
"epoch": 2.35,
"grad_norm": 0.533061683177948,
"learning_rate": 3.722039475513024e-05,
"loss": 0.015,
"step": 36000
},
{
"epoch": 2.38,
"grad_norm": 0.012933309189975262,
"learning_rate": 3.665742887240311e-05,
"loss": 0.0196,
"step": 36500
},
{
"epoch": 2.41,
"grad_norm": 0.02278105542063713,
"learning_rate": 3.6086804827768564e-05,
"loss": 0.0178,
"step": 37000
},
{
"epoch": 2.45,
"grad_norm": 0.017285320907831192,
"learning_rate": 3.5508897483588626e-05,
"loss": 0.02,
"step": 37500
},
{
"epoch": 2.48,
"grad_norm": 0.5036013126373291,
"learning_rate": 3.4924086486872724e-05,
"loss": 0.0212,
"step": 38000
},
{
"epoch": 2.51,
"grad_norm": 0.2554037570953369,
"learning_rate": 3.433275601987469e-05,
"loss": 0.0247,
"step": 38500
},
{
"epoch": 2.55,
"grad_norm": 1.2537500858306885,
"learning_rate": 3.3735294547710354e-05,
"loss": 0.0192,
"step": 39000
},
{
"epoch": 2.58,
"grad_norm": 0.11956170201301575,
"learning_rate": 3.313209456316154e-05,
"loss": 0.0169,
"step": 39500
},
{
"epoch": 2.61,
"grad_norm": 0.7699991464614868,
"learning_rate": 3.2523552328834274e-05,
"loss": 0.0208,
"step": 40000
},
{
"epoch": 2.64,
"grad_norm": 0.00504554295912385,
"learning_rate": 3.1910067616840286e-05,
"loss": 0.0179,
"step": 40500
},
{
"epoch": 2.68,
"grad_norm": 0.020942695438861847,
"learning_rate": 3.1292043446173205e-05,
"loss": 0.0175,
"step": 41000
},
{
"epoch": 2.71,
"grad_norm": 0.04590239003300667,
"learning_rate": 3.066988581795156e-05,
"loss": 0.0183,
"step": 41500
},
{
"epoch": 2.74,
"grad_norm": 0.05620180070400238,
"learning_rate": 3.0044003448702918e-05,
"loss": 0.0185,
"step": 42000
},
{
"epoch": 2.77,
"grad_norm": 0.01712827943265438,
"learning_rate": 2.9414807501864007e-05,
"loss": 0.0156,
"step": 42500
},
{
"epoch": 2.81,
"grad_norm": 0.07057254761457443,
"learning_rate": 2.87827113176735e-05,
"loss": 0.0173,
"step": 43000
},
{
"epoch": 2.84,
"grad_norm": 0.02034137025475502,
"learning_rate": 2.814813014163472e-05,
"loss": 0.0164,
"step": 43500
},
{
"epoch": 2.87,
"grad_norm": 0.12140174210071564,
"learning_rate": 2.7511480851726734e-05,
"loss": 0.0176,
"step": 44000
},
{
"epoch": 2.9,
"grad_norm": 0.3486383259296417,
"learning_rate": 2.6873181684543036e-05,
"loss": 0.0151,
"step": 44500
},
{
"epoch": 2.94,
"grad_norm": 0.015888692811131477,
"learning_rate": 2.6233651960537648e-05,
"loss": 0.0151,
"step": 45000
},
{
"epoch": 2.97,
"grad_norm": 0.348768413066864,
"learning_rate": 2.559331180855928e-05,
"loss": 0.0182,
"step": 45500
},
{
"epoch": 3.0,
"eval_AADHAR_CARD_f1": 0.9842354177614293,
"eval_AGE_f1": 0.9630551063565119,
"eval_CITY_f1": 0.985635543677969,
"eval_COUNTRY_f1": 0.9843467790487658,
"eval_CREDITCARDCVV_f1": 0.9854488471009626,
"eval_CREDITCARDNUMBER_f1": 0.9423696456270134,
"eval_DATEOFBIRTH_f1": 0.8962226640159046,
"eval_DATE_f1": 0.9552639427378468,
"eval_EMAIL_f1": 0.989039202132912,
"eval_EXPIRYDATE_f1": 0.9878463782207098,
"eval_ORGANIZATION_f1": 0.9921492659053834,
"eval_PAN_CARD_f1": 0.9869194312796208,
"eval_PERSON_f1": 0.9858850543661781,
"eval_PHONENUMBER_f1": 0.9814869233029679,
"eval_PINCODE_f1": 0.986728599867286,
"eval_SECONDARYADDRESS_f1": 0.9883943889393481,
"eval_STATE_f1": 0.9916826615483045,
"eval_TIME_f1": 0.9767226189372159,
"eval_URL_f1": 0.9961994187346301,
"eval_loss": 0.021940715610980988,
"eval_overall_accuracy": 0.9950686247786047,
"eval_overall_f1": 0.9789248441664341,
"eval_overall_precision": 0.9725538809508275,
"eval_overall_recall": 0.9853798270258359,
"eval_runtime": 250.1917,
"eval_samples_per_second": 61.237,
"eval_steps_per_second": 15.312,
"step": 45963
},
{
"epoch": 3.0,
"grad_norm": 0.023316623643040657,
"learning_rate": 2.495258188985437e-05,
"loss": 0.0157,
"step": 46000
},
{
"epoch": 3.04,
"grad_norm": 0.5379074811935425,
"learning_rate": 2.431188312172038e-05,
"loss": 0.0122,
"step": 46500
},
{
"epoch": 3.07,
"grad_norm": 0.021363502368330956,
"learning_rate": 2.367163640099091e-05,
"loss": 0.0093,
"step": 47000
},
{
"epoch": 3.1,
"grad_norm": 0.006295538041740656,
"learning_rate": 2.3032262327534213e-05,
"loss": 0.0116,
"step": 47500
},
{
"epoch": 3.13,
"grad_norm": 0.04374461993575096,
"learning_rate": 2.2394180927946856e-05,
"loss": 0.0118,
"step": 48000
},
{
"epoch": 3.17,
"grad_norm": 0.06676093488931656,
"learning_rate": 2.1757811379623928e-05,
"loss": 0.0116,
"step": 48500
},
{
"epoch": 3.2,
"grad_norm": 0.009012291207909584,
"learning_rate": 2.1123571735387153e-05,
"loss": 0.0089,
"step": 49000
},
{
"epoch": 3.23,
"grad_norm": 7.529526710510254,
"learning_rate": 2.049187864885171e-05,
"loss": 0.0138,
"step": 49500
},
{
"epoch": 3.26,
"grad_norm": 0.0050605605356395245,
"learning_rate": 1.9863147100712365e-05,
"loss": 0.0115,
"step": 50000
},
{
"epoch": 3.3,
"grad_norm": 0.40215590596199036,
"learning_rate": 1.9237790126128464e-05,
"loss": 0.0132,
"step": 50500
},
{
"epoch": 3.33,
"grad_norm": 0.006608816795051098,
"learning_rate": 1.8616218543387105e-05,
"loss": 0.0123,
"step": 51000
},
{
"epoch": 3.36,
"grad_norm": 0.02073794975876808,
"learning_rate": 1.7998840684022602e-05,
"loss": 0.0149,
"step": 51500
},
{
"epoch": 3.39,
"grad_norm": 0.21203799545764923,
"learning_rate": 1.7386062124569624e-05,
"loss": 0.0128,
"step": 52000
},
{
"epoch": 3.43,
"grad_norm": 0.0049758171662688255,
"learning_rate": 1.6778285420126123e-05,
"loss": 0.0105,
"step": 52500
},
{
"epoch": 3.46,
"grad_norm": 0.012410460039973259,
"learning_rate": 1.6175909839901208e-05,
"loss": 0.0137,
"step": 53000
},
{
"epoch": 3.49,
"grad_norm": 0.00482690054923296,
"learning_rate": 1.557933110492161e-05,
"loss": 0.0094,
"step": 53500
},
{
"epoch": 3.52,
"grad_norm": 0.02019447833299637,
"learning_rate": 1.4988941128069068e-05,
"loss": 0.0129,
"step": 54000
},
{
"epoch": 3.56,
"grad_norm": 0.001453628996387124,
"learning_rate": 1.4405127756619403e-05,
"loss": 0.0092,
"step": 54500
},
{
"epoch": 3.59,
"grad_norm": 0.003288328880444169,
"learning_rate": 1.382827451745244e-05,
"loss": 0.0119,
"step": 55000
},
{
"epoch": 3.62,
"grad_norm": 0.02008083090186119,
"learning_rate": 1.3258760365100162e-05,
"loss": 0.0072,
"step": 55500
},
{
"epoch": 3.66,
"grad_norm": 0.818644106388092,
"learning_rate": 1.2696959432798547e-05,
"loss": 0.0093,
"step": 56000
},
{
"epoch": 3.69,
"grad_norm": 0.06376053392887115,
"learning_rate": 1.214324078670674e-05,
"loss": 0.0111,
"step": 56500
},
{
"epoch": 3.72,
"grad_norm": 0.08838366717100143,
"learning_rate": 1.1597968183454874e-05,
"loss": 0.0123,
"step": 57000
},
{
"epoch": 3.75,
"grad_norm": 0.3981121778488159,
"learning_rate": 1.106149983118004e-05,
"loss": 0.009,
"step": 57500
},
{
"epoch": 3.79,
"grad_norm": 0.22205697000026703,
"learning_rate": 1.0534188154207075e-05,
"loss": 0.0091,
"step": 58000
},
{
"epoch": 3.82,
"grad_norm": 0.47372546792030334,
"learning_rate": 1.0016379561529099e-05,
"loss": 0.0134,
"step": 58500
},
{
"epoch": 3.85,
"grad_norm": 1.0051251649856567,
"learning_rate": 9.508414219239608e-06,
"loss": 0.0118,
"step": 59000
},
{
"epoch": 3.88,
"grad_norm": 0.03393113985657692,
"learning_rate": 9.010625827065807e-06,
"loss": 0.0137,
"step": 59500
},
{
"epoch": 3.92,
"grad_norm": 0.08359457552433014,
"learning_rate": 8.523341399149901e-06,
"loss": 0.0118,
"step": 60000
},
{
"epoch": 3.95,
"grad_norm": 0.2319985330104828,
"learning_rate": 8.046881049222332e-06,
"loss": 0.0079,
"step": 60500
},
{
"epoch": 3.98,
"grad_norm": 0.02699044905602932,
"learning_rate": 7.581557780308232e-06,
"loss": 0.0106,
"step": 61000
},
{
"epoch": 4.0,
"eval_AADHAR_CARD_f1": 0.9907578558225508,
"eval_AGE_f1": 0.9708328161846841,
"eval_CITY_f1": 0.9878752404047161,
"eval_COUNTRY_f1": 0.9825406381697773,
"eval_CREDITCARDCVV_f1": 0.9914874551971327,
"eval_CREDITCARDNUMBER_f1": 0.9427984036763817,
"eval_DATEOFBIRTH_f1": 0.905574984571076,
"eval_DATE_f1": 0.9626126791783657,
"eval_EMAIL_f1": 0.9927686973749381,
"eval_EXPIRYDATE_f1": 0.9897909577053962,
"eval_ORGANIZATION_f1": 0.9925087907047851,
"eval_PAN_CARD_f1": 0.986565752128666,
"eval_PERSON_f1": 0.988700182691657,
"eval_PHONENUMBER_f1": 0.9879518072289156,
"eval_PINCODE_f1": 0.9896975739448322,
"eval_SECONDARYADDRESS_f1": 0.9890931125025247,
"eval_STATE_f1": 0.9911617778916357,
"eval_TIME_f1": 0.9831231454005935,
"eval_URL_f1": 0.9955277280858676,
"eval_loss": 0.019619259983301163,
"eval_overall_accuracy": 0.9957009162002273,
"eval_overall_f1": 0.9821630214328783,
"eval_overall_precision": 0.9773414062073856,
"eval_overall_recall": 0.9870324464275877,
"eval_runtime": 250.3524,
"eval_samples_per_second": 61.198,
"eval_steps_per_second": 15.302,
"step": 61284
},
{
"epoch": 4.01,
"grad_norm": 0.21583209931850433,
"learning_rate": 7.127677279105039e-06,
"loss": 0.01,
"step": 61500
},
{
"epoch": 4.05,
"grad_norm": 0.03639248013496399,
"learning_rate": 6.685537715166509e-06,
"loss": 0.0069,
"step": 62000
},
{
"epoch": 4.08,
"grad_norm": 0.022935694083571434,
"learning_rate": 6.255429545024985e-06,
"loss": 0.008,
"step": 62500
},
{
"epoch": 4.11,
"grad_norm": 0.2646021246910095,
"learning_rate": 5.837635321380621e-06,
"loss": 0.0054,
"step": 63000
},
{
"epoch": 4.14,
"grad_norm": 0.042872123420238495,
"learning_rate": 5.432429507482867e-06,
"loss": 0.0059,
"step": 63500
},
{
"epoch": 4.18,
"grad_norm": 0.3728538155555725,
"learning_rate": 5.040078296826237e-06,
"loss": 0.01,
"step": 64000
},
{
"epoch": 4.21,
"grad_norm": 0.0075051430612802505,
"learning_rate": 4.660839438278744e-06,
"loss": 0.0098,
"step": 64500
},
{
"epoch": 4.24,
"grad_norm": 1.2772583961486816,
"learning_rate": 4.294962066757888e-06,
"loss": 0.0064,
"step": 65000
},
{
"epoch": 4.28,
"grad_norm": 0.9278016686439514,
"learning_rate": 3.94268653956544e-06,
"loss": 0.0039,
"step": 65500
},
{
"epoch": 4.31,
"grad_norm": 0.8312927484512329,
"learning_rate": 3.6042442784885526e-06,
"loss": 0.006,
"step": 66000
},
{
"epoch": 4.34,
"grad_norm": 0.02065468765795231,
"learning_rate": 3.2798576177709097e-06,
"loss": 0.0061,
"step": 66500
},
{
"epoch": 4.37,
"grad_norm": 0.958082377910614,
"learning_rate": 2.9697396580537965e-06,
"loss": 0.0049,
"step": 67000
},
{
"epoch": 4.41,
"grad_norm": 0.0006930904928594828,
"learning_rate": 2.674094126383009e-06,
"loss": 0.0056,
"step": 67500
},
{
"epoch": 4.44,
"grad_norm": 0.016762958839535713,
"learning_rate": 2.393115242373664e-06,
"loss": 0.0058,
"step": 68000
},
{
"epoch": 4.47,
"grad_norm": 0.02655264548957348,
"learning_rate": 2.1269875906206852e-06,
"loss": 0.0062,
"step": 68500
},
{
"epoch": 4.5,
"grad_norm": 0.2882128059864044,
"learning_rate": 1.8758859994389228e-06,
"loss": 0.0069,
"step": 69000
},
{
"epoch": 4.54,
"grad_norm": 0.15941615402698517,
"learning_rate": 1.6399754260124522e-06,
"loss": 0.0056,
"step": 69500
},
{
"epoch": 4.57,
"grad_norm": 0.023537589237093925,
"learning_rate": 1.4194108480286211e-06,
"loss": 0.0069,
"step": 70000
},
{
"epoch": 4.6,
"grad_norm": 0.008936550468206406,
"learning_rate": 1.214337161867901e-06,
"loss": 0.0046,
"step": 70500
},
{
"epoch": 4.63,
"grad_norm": 0.006893637590110302,
"learning_rate": 1.0248890874165306e-06,
"loss": 0.0056,
"step": 71000
},
{
"epoch": 4.67,
"grad_norm": 0.010946184396743774,
"learning_rate": 8.511910795644451e-07,
"loss": 0.0048,
"step": 71500
},
{
"epoch": 4.7,
"grad_norm": 0.034461166709661484,
"learning_rate": 6.933572464466104e-07,
"loss": 0.0054,
"step": 72000
},
{
"epoch": 4.73,
"grad_norm": 0.27507975697517395,
"learning_rate": 5.514912744815053e-07,
"loss": 0.0072,
"step": 72500
},
{
"epoch": 4.76,
"grad_norm": 0.02132672443985939,
"learning_rate": 4.256863602559946e-07,
"loss": 0.0062,
"step": 73000
},
{
"epoch": 4.8,
"grad_norm": 0.785845160484314,
"learning_rate": 3.160251493012967e-07,
"loss": 0.0074,
"step": 73500
},
{
"epoch": 4.83,
"grad_norm": 0.004894765559583902,
"learning_rate": 2.2257968180034728e-07,
"loss": 0.0052,
"step": 74000
},
{
"epoch": 4.86,
"grad_norm": 0.7538247108459473,
"learning_rate": 1.4541134526212807e-07,
"loss": 0.0053,
"step": 74500
},
{
"epoch": 4.9,
"grad_norm": 1.4640376567840576,
"learning_rate": 8.45708341941337e-08,
"loss": 0.0056,
"step": 75000
},
{
"epoch": 4.93,
"grad_norm": 0.056750182062387466,
"learning_rate": 4.009811679941966e-08,
"loss": 0.0066,
"step": 75500
},
{
"epoch": 4.96,
"grad_norm": 0.013171417638659477,
"learning_rate": 1.2022408720130384e-08,
"loss": 0.007,
"step": 76000
},
{
"epoch": 4.99,
"grad_norm": 0.001819392666220665,
"learning_rate": 3.6215384475180027e-10,
"loss": 0.0044,
"step": 76500
},
{
"epoch": 5.0,
"eval_AADHAR_CARD_f1": 0.993405433922448,
"eval_AGE_f1": 0.9710379117464264,
"eval_CITY_f1": 0.9885153826808618,
"eval_COUNTRY_f1": 0.9846153846153847,
"eval_CREDITCARDCVV_f1": 0.9914874551971327,
"eval_CREDITCARDNUMBER_f1": 0.9452593917710196,
"eval_DATEOFBIRTH_f1": 0.9125102207686018,
"eval_DATE_f1": 0.9646096654275093,
"eval_EMAIL_f1": 0.9930651872399444,
"eval_EXPIRYDATE_f1": 0.9898107714701602,
"eval_ORGANIZATION_f1": 0.9936721779955092,
"eval_PAN_CARD_f1": 0.9874999999999999,
"eval_PERSON_f1": 0.988620456084895,
"eval_PHONENUMBER_f1": 0.9892568064753495,
"eval_PINCODE_f1": 0.9907161803713527,
"eval_SECONDARYADDRESS_f1": 0.9903128153380424,
"eval_STATE_f1": 0.9924407431133888,
"eval_TIME_f1": 0.9837375708577271,
"eval_URL_f1": 0.9957522915269394,
"eval_loss": 0.021437210962176323,
"eval_overall_accuracy": 0.9958975737683697,
"eval_overall_f1": 0.983098622444503,
"eval_overall_precision": 0.9786869315514211,
"eval_overall_recall": 0.9875502671734699,
"eval_runtime": 250.4213,
"eval_samples_per_second": 61.181,
"eval_steps_per_second": 15.298,
"step": 76605
},
{
"epoch": 5.0,
"step": 76605,
"total_flos": 2.977427926260837e+16,
"train_loss": 0.04493269212492903,
"train_runtime": 13569.8925,
"train_samples_per_second": 22.58,
"train_steps_per_second": 5.645
},
{
"epoch": 5.0,
"eval_AADHAR_CARD_f1": 0.9907578558225508,
"eval_AGE_f1": 0.9708328161846841,
"eval_CITY_f1": 0.9878752404047161,
"eval_COUNTRY_f1": 0.9825406381697773,
"eval_CREDITCARDCVV_f1": 0.9914874551971327,
"eval_CREDITCARDNUMBER_f1": 0.9427984036763817,
"eval_DATEOFBIRTH_f1": 0.905574984571076,
"eval_DATE_f1": 0.9626126791783657,
"eval_EMAIL_f1": 0.9927686973749381,
"eval_EXPIRYDATE_f1": 0.9897909577053962,
"eval_ORGANIZATION_f1": 0.9925087907047851,
"eval_PAN_CARD_f1": 0.986565752128666,
"eval_PERSON_f1": 0.988700182691657,
"eval_PHONENUMBER_f1": 0.9879518072289156,
"eval_PINCODE_f1": 0.9896975739448322,
"eval_SECONDARYADDRESS_f1": 0.9890931125025247,
"eval_STATE_f1": 0.9911617778916357,
"eval_TIME_f1": 0.9831231454005935,
"eval_URL_f1": 0.9955277280858676,
"eval_loss": 0.019619259983301163,
"eval_overall_accuracy": 0.9957009162002273,
"eval_overall_f1": 0.9821630214328783,
"eval_overall_precision": 0.9773414062073856,
"eval_overall_recall": 0.9870324464275877,
"eval_runtime": 250.2495,
"eval_samples_per_second": 61.223,
"eval_steps_per_second": 15.309,
"step": 76605
}
],
"logging_steps": 500,
"max_steps": 76605,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 2.977427926260837e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}