GolemPII-v1 / checkpoint-7615 /trainer_state.json
CordwainerSmith's picture
Upload folder using huggingface_hub
9882178 verified
raw
history blame
29.2 kB
{
"best_metric": 0.998085740410612,
"best_model_checkpoint": "/content/drive/MyDrive/GolemPII/GolemPII-xlm-roberta-v1/checkpoint-7615",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 7615,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03282994090610637,
"grad_norm": 10.239672660827637,
"learning_rate": 6.036745406824147e-06,
"loss": 3.0294,
"step": 50
},
{
"epoch": 0.06565988181221274,
"grad_norm": 1.969146966934204,
"learning_rate": 1.2598425196850394e-05,
"loss": 1.5238,
"step": 100
},
{
"epoch": 0.0984898227183191,
"grad_norm": 0.7575042843818665,
"learning_rate": 1.916010498687664e-05,
"loss": 0.2974,
"step": 150
},
{
"epoch": 0.1313197636244255,
"grad_norm": 0.6243991851806641,
"learning_rate": 2.572178477690289e-05,
"loss": 0.0568,
"step": 200
},
{
"epoch": 0.16414970453053185,
"grad_norm": 0.35771840810775757,
"learning_rate": 3.228346456692913e-05,
"loss": 0.031,
"step": 250
},
{
"epoch": 0.1969796454366382,
"grad_norm": 0.7596266865730286,
"learning_rate": 3.8845144356955383e-05,
"loss": 0.0205,
"step": 300
},
{
"epoch": 0.2298095863427446,
"grad_norm": 0.4744904339313507,
"learning_rate": 4.540682414698163e-05,
"loss": 0.0189,
"step": 350
},
{
"epoch": 0.262639527248851,
"grad_norm": 1.39719557762146,
"learning_rate": 4.989632291954659e-05,
"loss": 0.0138,
"step": 400
},
{
"epoch": 0.29546946815495734,
"grad_norm": 0.29437175393104553,
"learning_rate": 4.955073265136854e-05,
"loss": 0.0125,
"step": 450
},
{
"epoch": 0.3282994090610637,
"grad_norm": 0.19857335090637207,
"learning_rate": 4.920514238319049e-05,
"loss": 0.0107,
"step": 500
},
{
"epoch": 0.36112934996717005,
"grad_norm": 0.34563446044921875,
"learning_rate": 4.885955211501244e-05,
"loss": 0.0106,
"step": 550
},
{
"epoch": 0.3939592908732764,
"grad_norm": 0.3963533639907837,
"learning_rate": 4.851396184683439e-05,
"loss": 0.0122,
"step": 600
},
{
"epoch": 0.42678923177938277,
"grad_norm": 0.37360525131225586,
"learning_rate": 4.816837157865634e-05,
"loss": 0.009,
"step": 650
},
{
"epoch": 0.4596191726854892,
"grad_norm": 0.2154053896665573,
"learning_rate": 4.78227813104783e-05,
"loss": 0.0083,
"step": 700
},
{
"epoch": 0.49244911359159554,
"grad_norm": 0.33652621507644653,
"learning_rate": 4.747719104230025e-05,
"loss": 0.0078,
"step": 750
},
{
"epoch": 0.525279054497702,
"grad_norm": 0.5589196085929871,
"learning_rate": 4.71316007741222e-05,
"loss": 0.0088,
"step": 800
},
{
"epoch": 0.5581089954038083,
"grad_norm": 0.33235111832618713,
"learning_rate": 4.678601050594415e-05,
"loss": 0.0064,
"step": 850
},
{
"epoch": 0.5909389363099147,
"grad_norm": 0.36602529883384705,
"learning_rate": 4.644042023776611e-05,
"loss": 0.0068,
"step": 900
},
{
"epoch": 0.623768877216021,
"grad_norm": 1.011355996131897,
"learning_rate": 4.609482996958806e-05,
"loss": 0.0059,
"step": 950
},
{
"epoch": 0.6565988181221274,
"grad_norm": 0.5964003205299377,
"learning_rate": 4.574923970141001e-05,
"loss": 0.0051,
"step": 1000
},
{
"epoch": 0.6894287590282338,
"grad_norm": 0.21312755346298218,
"learning_rate": 4.540364943323196e-05,
"loss": 0.0058,
"step": 1050
},
{
"epoch": 0.7222586999343401,
"grad_norm": 0.19403104484081268,
"learning_rate": 4.5058059165053913e-05,
"loss": 0.0058,
"step": 1100
},
{
"epoch": 0.7550886408404465,
"grad_norm": 0.15370243787765503,
"learning_rate": 4.4712468896875864e-05,
"loss": 0.0051,
"step": 1150
},
{
"epoch": 0.7879185817465528,
"grad_norm": 0.3946862518787384,
"learning_rate": 4.4366878628697815e-05,
"loss": 0.0054,
"step": 1200
},
{
"epoch": 0.8207485226526592,
"grad_norm": 0.23363596200942993,
"learning_rate": 4.402128836051977e-05,
"loss": 0.0048,
"step": 1250
},
{
"epoch": 0.8535784635587655,
"grad_norm": 0.25897666811943054,
"learning_rate": 4.367569809234172e-05,
"loss": 0.007,
"step": 1300
},
{
"epoch": 0.886408404464872,
"grad_norm": 0.15858227014541626,
"learning_rate": 4.3330107824163674e-05,
"loss": 0.0042,
"step": 1350
},
{
"epoch": 0.9192383453709784,
"grad_norm": 0.13322387635707855,
"learning_rate": 4.2984517555985625e-05,
"loss": 0.005,
"step": 1400
},
{
"epoch": 0.9520682862770847,
"grad_norm": 0.16873428225517273,
"learning_rate": 4.2638927287807575e-05,
"loss": 0.0046,
"step": 1450
},
{
"epoch": 0.9848982271831911,
"grad_norm": 0.18423955142498016,
"learning_rate": 4.229333701962953e-05,
"loss": 0.0058,
"step": 1500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9993276594535457,
"eval_f1": 0.9933933815429036,
"eval_loss": 0.0024869011249393225,
"eval_precision": 0.9931092525380043,
"eval_recall": 0.9936776731732028,
"eval_runtime": 76.0097,
"eval_samples_per_second": 236.812,
"eval_steps_per_second": 3.71,
"step": 1523
},
{
"epoch": 1.0177281680892973,
"grad_norm": 0.29311779141426086,
"learning_rate": 4.1947746751451484e-05,
"loss": 0.0041,
"step": 1550
},
{
"epoch": 1.050558108995404,
"grad_norm": 0.10629381239414215,
"learning_rate": 4.1602156483273434e-05,
"loss": 0.0037,
"step": 1600
},
{
"epoch": 1.0833880499015103,
"grad_norm": 0.18275995552539825,
"learning_rate": 4.1256566215095385e-05,
"loss": 0.0043,
"step": 1650
},
{
"epoch": 1.1162179908076166,
"grad_norm": 0.06012125313282013,
"learning_rate": 4.0910975946917336e-05,
"loss": 0.0062,
"step": 1700
},
{
"epoch": 1.149047931713723,
"grad_norm": 7.185174942016602,
"learning_rate": 4.0565385678739286e-05,
"loss": 0.0085,
"step": 1750
},
{
"epoch": 1.1818778726198294,
"grad_norm": 0.07045840471982956,
"learning_rate": 4.021979541056124e-05,
"loss": 0.0031,
"step": 1800
},
{
"epoch": 1.2147078135259357,
"grad_norm": 0.23435795307159424,
"learning_rate": 3.9874205142383195e-05,
"loss": 0.0026,
"step": 1850
},
{
"epoch": 1.247537754432042,
"grad_norm": 0.046855829656124115,
"learning_rate": 3.9528614874205145e-05,
"loss": 0.0031,
"step": 1900
},
{
"epoch": 1.2803676953381484,
"grad_norm": 0.3116040527820587,
"learning_rate": 3.9183024606027096e-05,
"loss": 0.0032,
"step": 1950
},
{
"epoch": 1.3131976362442548,
"grad_norm": 0.10148299485445023,
"learning_rate": 3.883743433784905e-05,
"loss": 0.0026,
"step": 2000
},
{
"epoch": 1.3460275771503611,
"grad_norm": 0.06928931921720505,
"learning_rate": 3.8491844069671004e-05,
"loss": 0.0028,
"step": 2050
},
{
"epoch": 1.3788575180564675,
"grad_norm": 0.09313840419054031,
"learning_rate": 3.8146253801492955e-05,
"loss": 0.0027,
"step": 2100
},
{
"epoch": 1.4116874589625739,
"grad_norm": 0.28150513768196106,
"learning_rate": 3.7800663533314906e-05,
"loss": 0.0032,
"step": 2150
},
{
"epoch": 1.4445173998686802,
"grad_norm": 0.4722907841205597,
"learning_rate": 3.745507326513685e-05,
"loss": 0.0037,
"step": 2200
},
{
"epoch": 1.4773473407747866,
"grad_norm": 0.5664809346199036,
"learning_rate": 3.710948299695881e-05,
"loss": 0.0026,
"step": 2250
},
{
"epoch": 1.510177281680893,
"grad_norm": 0.03828972578048706,
"learning_rate": 3.676389272878076e-05,
"loss": 0.0022,
"step": 2300
},
{
"epoch": 1.5430072225869993,
"grad_norm": 0.5701923370361328,
"learning_rate": 3.641830246060271e-05,
"loss": 0.0022,
"step": 2350
},
{
"epoch": 1.5758371634931057,
"grad_norm": 0.15145182609558105,
"learning_rate": 3.607271219242466e-05,
"loss": 0.0029,
"step": 2400
},
{
"epoch": 1.608667104399212,
"grad_norm": 0.055488649755716324,
"learning_rate": 3.572712192424662e-05,
"loss": 0.002,
"step": 2450
},
{
"epoch": 1.6414970453053184,
"grad_norm": 0.2535063624382019,
"learning_rate": 3.538153165606857e-05,
"loss": 0.0024,
"step": 2500
},
{
"epoch": 1.6743269862114247,
"grad_norm": 0.09548994898796082,
"learning_rate": 3.503594138789052e-05,
"loss": 0.0024,
"step": 2550
},
{
"epoch": 1.707156927117531,
"grad_norm": 0.04930610582232475,
"learning_rate": 3.469035111971247e-05,
"loss": 0.0021,
"step": 2600
},
{
"epoch": 1.7399868680236374,
"grad_norm": 0.12071087211370468,
"learning_rate": 3.434476085153443e-05,
"loss": 0.0023,
"step": 2650
},
{
"epoch": 1.7728168089297438,
"grad_norm": 0.038167692720890045,
"learning_rate": 3.399917058335638e-05,
"loss": 0.0027,
"step": 2700
},
{
"epoch": 1.8056467498358502,
"grad_norm": 0.016604498028755188,
"learning_rate": 3.365358031517832e-05,
"loss": 0.0025,
"step": 2750
},
{
"epoch": 1.8384766907419565,
"grad_norm": 0.10711315274238586,
"learning_rate": 3.330799004700028e-05,
"loss": 0.0021,
"step": 2800
},
{
"epoch": 1.8713066316480629,
"grad_norm": 0.10547716170549393,
"learning_rate": 3.296239977882223e-05,
"loss": 0.0029,
"step": 2850
},
{
"epoch": 1.9041365725541692,
"grad_norm": 0.12901557981967926,
"learning_rate": 3.261680951064418e-05,
"loss": 0.0026,
"step": 2900
},
{
"epoch": 1.9369665134602758,
"grad_norm": 0.16034963726997375,
"learning_rate": 3.227121924246613e-05,
"loss": 0.0031,
"step": 2950
},
{
"epoch": 1.9697964543663822,
"grad_norm": 0.060961514711380005,
"learning_rate": 3.192562897428809e-05,
"loss": 0.0017,
"step": 3000
},
{
"epoch": 2.0,
"eval_accuracy": 0.9995754536025347,
"eval_f1": 0.995708295650744,
"eval_loss": 0.0013849161332473159,
"eval_precision": 0.9954693109933322,
"eval_recall": 0.9959473950829271,
"eval_runtime": 75.6987,
"eval_samples_per_second": 237.785,
"eval_steps_per_second": 3.725,
"step": 3046
},
{
"epoch": 2.0026263952724883,
"grad_norm": 0.08297313749790192,
"learning_rate": 3.158003870611004e-05,
"loss": 0.0026,
"step": 3050
},
{
"epoch": 2.0354563361785947,
"grad_norm": 0.19145315885543823,
"learning_rate": 3.123444843793199e-05,
"loss": 0.0014,
"step": 3100
},
{
"epoch": 2.0682862770847015,
"grad_norm": 0.08754308521747589,
"learning_rate": 3.088885816975394e-05,
"loss": 0.0014,
"step": 3150
},
{
"epoch": 2.101116217990808,
"grad_norm": 0.1580217033624649,
"learning_rate": 3.054326790157589e-05,
"loss": 0.0016,
"step": 3200
},
{
"epoch": 2.133946158896914,
"grad_norm": 0.022689586505293846,
"learning_rate": 3.0197677633397846e-05,
"loss": 0.0016,
"step": 3250
},
{
"epoch": 2.1667760998030205,
"grad_norm": 0.10402818024158478,
"learning_rate": 2.9852087365219793e-05,
"loss": 0.0015,
"step": 3300
},
{
"epoch": 2.199606040709127,
"grad_norm": 0.11667637526988983,
"learning_rate": 2.9506497097041747e-05,
"loss": 0.002,
"step": 3350
},
{
"epoch": 2.2324359816152333,
"grad_norm": 0.24381309747695923,
"learning_rate": 2.9160906828863698e-05,
"loss": 0.0039,
"step": 3400
},
{
"epoch": 2.2652659225213396,
"grad_norm": 0.03473767638206482,
"learning_rate": 2.8815316560685652e-05,
"loss": 0.0016,
"step": 3450
},
{
"epoch": 2.298095863427446,
"grad_norm": 1.3230725526809692,
"learning_rate": 2.8469726292507603e-05,
"loss": 0.0016,
"step": 3500
},
{
"epoch": 2.3309258043335523,
"grad_norm": 0.1341700553894043,
"learning_rate": 2.8124136024329557e-05,
"loss": 0.0047,
"step": 3550
},
{
"epoch": 2.3637557452396587,
"grad_norm": 0.13513527810573578,
"learning_rate": 2.7778545756151508e-05,
"loss": 0.0018,
"step": 3600
},
{
"epoch": 2.396585686145765,
"grad_norm": 0.0577649362385273,
"learning_rate": 2.743295548797346e-05,
"loss": 0.0014,
"step": 3650
},
{
"epoch": 2.4294156270518714,
"grad_norm": 0.1941065490245819,
"learning_rate": 2.7087365219795412e-05,
"loss": 0.0011,
"step": 3700
},
{
"epoch": 2.4622455679579778,
"grad_norm": 0.15985670685768127,
"learning_rate": 2.6741774951617367e-05,
"loss": 0.0016,
"step": 3750
},
{
"epoch": 2.495075508864084,
"grad_norm": 0.08614476025104523,
"learning_rate": 2.6396184683439317e-05,
"loss": 0.0016,
"step": 3800
},
{
"epoch": 2.5279054497701905,
"grad_norm": 0.15596601366996765,
"learning_rate": 2.605059441526127e-05,
"loss": 0.0016,
"step": 3850
},
{
"epoch": 2.560735390676297,
"grad_norm": 0.12409207224845886,
"learning_rate": 2.5705004147083215e-05,
"loss": 0.0015,
"step": 3900
},
{
"epoch": 2.593565331582403,
"grad_norm": 0.189951092004776,
"learning_rate": 2.535941387890517e-05,
"loss": 0.0015,
"step": 3950
},
{
"epoch": 2.6263952724885096,
"grad_norm": 0.059304554015398026,
"learning_rate": 2.501382361072712e-05,
"loss": 0.0014,
"step": 4000
},
{
"epoch": 2.659225213394616,
"grad_norm": 0.24233925342559814,
"learning_rate": 2.4668233342549074e-05,
"loss": 0.0013,
"step": 4050
},
{
"epoch": 2.6920551543007223,
"grad_norm": 0.2739645838737488,
"learning_rate": 2.4322643074371025e-05,
"loss": 0.0012,
"step": 4100
},
{
"epoch": 2.7248850952068286,
"grad_norm": 0.11855873465538025,
"learning_rate": 2.397705280619298e-05,
"loss": 0.0019,
"step": 4150
},
{
"epoch": 2.757715036112935,
"grad_norm": 0.05818852037191391,
"learning_rate": 2.363146253801493e-05,
"loss": 0.0027,
"step": 4200
},
{
"epoch": 2.7905449770190414,
"grad_norm": 0.06046278029680252,
"learning_rate": 2.3285872269836884e-05,
"loss": 0.0014,
"step": 4250
},
{
"epoch": 2.8233749179251477,
"grad_norm": 0.04216454550623894,
"learning_rate": 2.2940282001658835e-05,
"loss": 0.0011,
"step": 4300
},
{
"epoch": 2.856204858831254,
"grad_norm": 0.0564955435693264,
"learning_rate": 2.2594691733480785e-05,
"loss": 0.0015,
"step": 4350
},
{
"epoch": 2.8890347997373604,
"grad_norm": 0.10374019294977188,
"learning_rate": 2.224910146530274e-05,
"loss": 0.0013,
"step": 4400
},
{
"epoch": 2.921864740643467,
"grad_norm": 0.2742884159088135,
"learning_rate": 2.190351119712469e-05,
"loss": 0.0014,
"step": 4450
},
{
"epoch": 2.954694681549573,
"grad_norm": 0.02845386229455471,
"learning_rate": 2.155792092894664e-05,
"loss": 0.0013,
"step": 4500
},
{
"epoch": 2.9875246224556795,
"grad_norm": 0.10036207735538483,
"learning_rate": 2.1212330660768595e-05,
"loss": 0.0012,
"step": 4550
},
{
"epoch": 3.0,
"eval_accuracy": 0.9997391341413165,
"eval_f1": 0.9973228263586491,
"eval_loss": 0.0009462219895794988,
"eval_precision": 0.9971588480180992,
"eval_recall": 0.9974868586390879,
"eval_runtime": 75.644,
"eval_samples_per_second": 237.957,
"eval_steps_per_second": 3.728,
"step": 4569
},
{
"epoch": 3.020354563361786,
"grad_norm": 0.08079813420772552,
"learning_rate": 2.0866740392590546e-05,
"loss": 0.0011,
"step": 4600
},
{
"epoch": 3.0531845042678922,
"grad_norm": 0.09932583570480347,
"learning_rate": 2.0521150124412497e-05,
"loss": 0.0023,
"step": 4650
},
{
"epoch": 3.0860144451739986,
"grad_norm": 0.05140871927142143,
"learning_rate": 2.017555985623445e-05,
"loss": 0.001,
"step": 4700
},
{
"epoch": 3.118844386080105,
"grad_norm": 0.19095173478126526,
"learning_rate": 1.98299695880564e-05,
"loss": 0.001,
"step": 4750
},
{
"epoch": 3.1516743269862113,
"grad_norm": 0.041814982891082764,
"learning_rate": 1.9484379319878356e-05,
"loss": 0.0018,
"step": 4800
},
{
"epoch": 3.1845042678923177,
"grad_norm": 0.025649981573224068,
"learning_rate": 1.9138789051700303e-05,
"loss": 0.0008,
"step": 4850
},
{
"epoch": 3.217334208798424,
"grad_norm": 0.12662899494171143,
"learning_rate": 1.8793198783522257e-05,
"loss": 0.0009,
"step": 4900
},
{
"epoch": 3.2501641497045304,
"grad_norm": 0.10787362605333328,
"learning_rate": 1.8447608515344208e-05,
"loss": 0.0008,
"step": 4950
},
{
"epoch": 3.2829940906106367,
"grad_norm": 0.03877755254507065,
"learning_rate": 1.8102018247166162e-05,
"loss": 0.0008,
"step": 5000
},
{
"epoch": 3.315824031516743,
"grad_norm": 0.11100368201732635,
"learning_rate": 1.7756427978988113e-05,
"loss": 0.0007,
"step": 5050
},
{
"epoch": 3.3486539724228495,
"grad_norm": 0.027431080117821693,
"learning_rate": 1.7410837710810067e-05,
"loss": 0.0008,
"step": 5100
},
{
"epoch": 3.381483913328956,
"grad_norm": 0.013812090270221233,
"learning_rate": 1.7065247442632014e-05,
"loss": 0.0008,
"step": 5150
},
{
"epoch": 3.414313854235062,
"grad_norm": 0.1110658347606659,
"learning_rate": 1.6719657174453968e-05,
"loss": 0.0022,
"step": 5200
},
{
"epoch": 3.4471437951411685,
"grad_norm": 0.11397113651037216,
"learning_rate": 1.637406690627592e-05,
"loss": 0.0009,
"step": 5250
},
{
"epoch": 3.479973736047275,
"grad_norm": 0.2407987117767334,
"learning_rate": 1.6028476638097873e-05,
"loss": 0.0008,
"step": 5300
},
{
"epoch": 3.5128036769533812,
"grad_norm": 0.06540926545858383,
"learning_rate": 1.5682886369919824e-05,
"loss": 0.001,
"step": 5350
},
{
"epoch": 3.5456336178594876,
"grad_norm": 0.08520480245351791,
"learning_rate": 1.5337296101741775e-05,
"loss": 0.0007,
"step": 5400
},
{
"epoch": 3.578463558765594,
"grad_norm": 0.091216079890728,
"learning_rate": 1.4991705833563727e-05,
"loss": 0.0011,
"step": 5450
},
{
"epoch": 3.6112934996717003,
"grad_norm": 0.1052037924528122,
"learning_rate": 1.464611556538568e-05,
"loss": 0.0008,
"step": 5500
},
{
"epoch": 3.6441234405778067,
"grad_norm": 0.30819040536880493,
"learning_rate": 1.4300525297207632e-05,
"loss": 0.0007,
"step": 5550
},
{
"epoch": 3.6769533814839135,
"grad_norm": 0.06232546642422676,
"learning_rate": 1.3954935029029584e-05,
"loss": 0.0005,
"step": 5600
},
{
"epoch": 3.70978332239002,
"grad_norm": 0.08547823131084442,
"learning_rate": 1.3609344760851537e-05,
"loss": 0.0006,
"step": 5650
},
{
"epoch": 3.742613263296126,
"grad_norm": 0.12835901975631714,
"learning_rate": 1.3263754492673486e-05,
"loss": 0.0028,
"step": 5700
},
{
"epoch": 3.7754432042022326,
"grad_norm": 0.07907555252313614,
"learning_rate": 1.2918164224495438e-05,
"loss": 0.001,
"step": 5750
},
{
"epoch": 3.808273145108339,
"grad_norm": 0.03760789334774017,
"learning_rate": 1.257257395631739e-05,
"loss": 0.0008,
"step": 5800
},
{
"epoch": 3.8411030860144453,
"grad_norm": 0.008074942976236343,
"learning_rate": 1.2226983688139343e-05,
"loss": 0.0007,
"step": 5850
},
{
"epoch": 3.8739330269205516,
"grad_norm": 0.039751049131155014,
"learning_rate": 1.1881393419961294e-05,
"loss": 0.0008,
"step": 5900
},
{
"epoch": 3.906762967826658,
"grad_norm": 0.1129092127084732,
"learning_rate": 1.1535803151783246e-05,
"loss": 0.0009,
"step": 5950
},
{
"epoch": 3.9395929087327644,
"grad_norm": 0.030842676758766174,
"learning_rate": 1.1190212883605199e-05,
"loss": 0.0006,
"step": 6000
},
{
"epoch": 3.9724228496388707,
"grad_norm": 0.24821631610393524,
"learning_rate": 1.084462261542715e-05,
"loss": 0.0009,
"step": 6050
},
{
"epoch": 4.0,
"eval_accuracy": 0.9997499325101945,
"eval_f1": 0.9977469995625562,
"eval_loss": 0.0008962151478044689,
"eval_precision": 0.9976255936015996,
"eval_recall": 0.997868435076085,
"eval_runtime": 75.9398,
"eval_samples_per_second": 237.03,
"eval_steps_per_second": 3.713,
"step": 6092
},
{
"epoch": 4.005252790544977,
"grad_norm": 0.13012520968914032,
"learning_rate": 1.0499032347249102e-05,
"loss": 0.0007,
"step": 6100
},
{
"epoch": 4.038082731451083,
"grad_norm": 0.008424765430390835,
"learning_rate": 1.0153442079071054e-05,
"loss": 0.0005,
"step": 6150
},
{
"epoch": 4.070912672357189,
"grad_norm": 0.08021287620067596,
"learning_rate": 9.807851810893005e-06,
"loss": 0.0005,
"step": 6200
},
{
"epoch": 4.103742613263296,
"grad_norm": 0.015998413786292076,
"learning_rate": 9.462261542714957e-06,
"loss": 0.0003,
"step": 6250
},
{
"epoch": 4.136572554169403,
"grad_norm": 0.09457238763570786,
"learning_rate": 9.11667127453691e-06,
"loss": 0.0004,
"step": 6300
},
{
"epoch": 4.169402495075509,
"grad_norm": 0.04868745431303978,
"learning_rate": 8.77108100635886e-06,
"loss": 0.0008,
"step": 6350
},
{
"epoch": 4.202232435981616,
"grad_norm": 0.033117685467004776,
"learning_rate": 8.425490738180813e-06,
"loss": 0.0004,
"step": 6400
},
{
"epoch": 4.235062376887722,
"grad_norm": 0.03128530830144882,
"learning_rate": 8.079900470002765e-06,
"loss": 0.0003,
"step": 6450
},
{
"epoch": 4.267892317793828,
"grad_norm": 0.017696760594844818,
"learning_rate": 7.734310201824716e-06,
"loss": 0.0004,
"step": 6500
},
{
"epoch": 4.300722258699935,
"grad_norm": 0.051392361521720886,
"learning_rate": 7.388719933646669e-06,
"loss": 0.0004,
"step": 6550
},
{
"epoch": 4.333552199606041,
"grad_norm": 0.023702796548604965,
"learning_rate": 7.04312966546862e-06,
"loss": 0.0005,
"step": 6600
},
{
"epoch": 4.3663821405121475,
"grad_norm": 0.12985366582870483,
"learning_rate": 6.6975393972905724e-06,
"loss": 0.0007,
"step": 6650
},
{
"epoch": 4.399212081418254,
"grad_norm": 0.005154111888259649,
"learning_rate": 6.351949129112525e-06,
"loss": 0.0004,
"step": 6700
},
{
"epoch": 4.43204202232436,
"grad_norm": 0.060625988990068436,
"learning_rate": 6.0063588609344764e-06,
"loss": 0.0004,
"step": 6750
},
{
"epoch": 4.4648719632304665,
"grad_norm": 0.014278898015618324,
"learning_rate": 5.660768592756428e-06,
"loss": 0.0005,
"step": 6800
},
{
"epoch": 4.497701904136573,
"grad_norm": 0.03604033589363098,
"learning_rate": 5.31517832457838e-06,
"loss": 0.0003,
"step": 6850
},
{
"epoch": 4.530531845042679,
"grad_norm": 0.11452529579401016,
"learning_rate": 4.969588056400332e-06,
"loss": 0.0006,
"step": 6900
},
{
"epoch": 4.563361785948786,
"grad_norm": 0.030383341014385223,
"learning_rate": 4.623997788222284e-06,
"loss": 0.0016,
"step": 6950
},
{
"epoch": 4.596191726854892,
"grad_norm": 0.054634325206279755,
"learning_rate": 4.278407520044236e-06,
"loss": 0.0004,
"step": 7000
},
{
"epoch": 4.629021667760998,
"grad_norm": 0.05445707589387894,
"learning_rate": 3.932817251866188e-06,
"loss": 0.0018,
"step": 7050
},
{
"epoch": 4.661851608667105,
"grad_norm": 0.10374827682971954,
"learning_rate": 3.5872269836881396e-06,
"loss": 0.0007,
"step": 7100
},
{
"epoch": 4.694681549573211,
"grad_norm": 0.07730349153280258,
"learning_rate": 3.2416367155100916e-06,
"loss": 0.0005,
"step": 7150
},
{
"epoch": 4.727511490479317,
"grad_norm": 0.06179986149072647,
"learning_rate": 2.896046447332043e-06,
"loss": 0.0004,
"step": 7200
},
{
"epoch": 4.760341431385424,
"grad_norm": 0.015075119212269783,
"learning_rate": 2.550456179153995e-06,
"loss": 0.0011,
"step": 7250
},
{
"epoch": 4.79317137229153,
"grad_norm": 0.0656493604183197,
"learning_rate": 2.204865910975947e-06,
"loss": 0.0004,
"step": 7300
},
{
"epoch": 4.8260013131976365,
"grad_norm": 0.017132466658949852,
"learning_rate": 1.8592756427978988e-06,
"loss": 0.0004,
"step": 7350
},
{
"epoch": 4.858831254103743,
"grad_norm": 0.02434193529188633,
"learning_rate": 1.5136853746198508e-06,
"loss": 0.0005,
"step": 7400
},
{
"epoch": 4.891661195009849,
"grad_norm": 0.0716409906744957,
"learning_rate": 1.1680951064418028e-06,
"loss": 0.0004,
"step": 7450
},
{
"epoch": 4.9244911359159556,
"grad_norm": 0.017711373046040535,
"learning_rate": 8.225048382637546e-07,
"loss": 0.0004,
"step": 7500
},
{
"epoch": 4.957321076822062,
"grad_norm": 0.0037664847914129496,
"learning_rate": 4.769145700857065e-07,
"loss": 0.0004,
"step": 7550
},
{
"epoch": 4.990151017728168,
"grad_norm": 0.001125144655816257,
"learning_rate": 1.3132430190765827e-07,
"loss": 0.0006,
"step": 7600
},
{
"epoch": 5.0,
"eval_accuracy": 0.9997948309913187,
"eval_f1": 0.998085740410612,
"eval_loss": 0.0007292991504073143,
"eval_precision": 0.9979807015582144,
"eval_recall": 0.9981908013763068,
"eval_runtime": 76.3485,
"eval_samples_per_second": 235.761,
"eval_steps_per_second": 3.694,
"step": 7615
}
],
"logging_steps": 50,
"max_steps": 7615,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.27347239453568e+17,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}