nodule-AI / checkpoint-173140 /trainer_state.json
lhui2010's picture
Upload folder using huggingface_hub
30076c7 verified
{
"best_metric": 0.8962368802798873,
"best_model_checkpoint": "finetune/models/plant-dnamamba-BPE-NoduleExpDup/checkpoint-129855",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 173140,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.011551345731777752,
"grad_norm": 29.45172119140625,
"learning_rate": 4.620218074293107e-07,
"loss": 1.0687,
"step": 500
},
{
"epoch": 0.023102691463555505,
"grad_norm": 31.642974853515625,
"learning_rate": 9.240436148586214e-07,
"loss": 0.9807,
"step": 1000
},
{
"epoch": 0.034654037195333255,
"grad_norm": 12.195789337158203,
"learning_rate": 1.3860654222879322e-06,
"loss": 0.8373,
"step": 1500
},
{
"epoch": 0.04620538292711101,
"grad_norm": 13.536879539489746,
"learning_rate": 1.8480872297172428e-06,
"loss": 0.7818,
"step": 2000
},
{
"epoch": 0.05775672865888876,
"grad_norm": 13.85306453704834,
"learning_rate": 2.3101090371465534e-06,
"loss": 0.7234,
"step": 2500
},
{
"epoch": 0.06930807439066651,
"grad_norm": 11.797886848449707,
"learning_rate": 2.7721308445758644e-06,
"loss": 0.6925,
"step": 3000
},
{
"epoch": 0.08085942012244426,
"grad_norm": 6.770650386810303,
"learning_rate": 3.2341526520051746e-06,
"loss": 0.6751,
"step": 3500
},
{
"epoch": 0.09241076585422202,
"grad_norm": 10.289820671081543,
"learning_rate": 3.6961744594344856e-06,
"loss": 0.6636,
"step": 4000
},
{
"epoch": 0.10396211158599977,
"grad_norm": 15.198243141174316,
"learning_rate": 4.158196266863797e-06,
"loss": 0.6563,
"step": 4500
},
{
"epoch": 0.11551345731777753,
"grad_norm": 13.971009254455566,
"learning_rate": 4.620218074293107e-06,
"loss": 0.6481,
"step": 5000
},
{
"epoch": 0.12706480304955528,
"grad_norm": 8.441276550292969,
"learning_rate": 5.082239881722417e-06,
"loss": 0.6549,
"step": 5500
},
{
"epoch": 0.13861614878133302,
"grad_norm": 14.8948335647583,
"learning_rate": 5.544261689151729e-06,
"loss": 0.6507,
"step": 6000
},
{
"epoch": 0.1501674945131108,
"grad_norm": 7.725317478179932,
"learning_rate": 6.006283496581039e-06,
"loss": 0.6544,
"step": 6500
},
{
"epoch": 0.16171884024488853,
"grad_norm": 17.12333106994629,
"learning_rate": 6.468305304010349e-06,
"loss": 0.6476,
"step": 7000
},
{
"epoch": 0.17327018597666627,
"grad_norm": 7.033656120300293,
"learning_rate": 6.930327111439661e-06,
"loss": 0.6496,
"step": 7500
},
{
"epoch": 0.18482153170844404,
"grad_norm": 7.053399085998535,
"learning_rate": 7.392348918868971e-06,
"loss": 0.6523,
"step": 8000
},
{
"epoch": 0.19637287744022178,
"grad_norm": 6.655728340148926,
"learning_rate": 7.854370726298282e-06,
"loss": 0.6455,
"step": 8500
},
{
"epoch": 0.20792422317199954,
"grad_norm": 8.08369255065918,
"learning_rate": 8.316392533727593e-06,
"loss": 0.6415,
"step": 9000
},
{
"epoch": 0.21947556890377729,
"grad_norm": 3.947148084640503,
"learning_rate": 8.778414341156903e-06,
"loss": 0.6514,
"step": 9500
},
{
"epoch": 0.23102691463555505,
"grad_norm": 8.264023780822754,
"learning_rate": 9.240436148586214e-06,
"loss": 0.6431,
"step": 10000
},
{
"epoch": 0.2425782603673328,
"grad_norm": 4.74052095413208,
"learning_rate": 9.702457956015525e-06,
"loss": 0.6331,
"step": 10500
},
{
"epoch": 0.25412960609911056,
"grad_norm": 12.625064849853516,
"learning_rate": 9.991342538776186e-06,
"loss": 0.6449,
"step": 11000
},
{
"epoch": 0.2656809518308883,
"grad_norm": 17.814157485961914,
"learning_rate": 9.967023827473336e-06,
"loss": 0.6414,
"step": 11500
},
{
"epoch": 0.27723229756266604,
"grad_norm": 15.34868049621582,
"learning_rate": 9.942705116170485e-06,
"loss": 0.6287,
"step": 12000
},
{
"epoch": 0.2887836432944438,
"grad_norm": 5.785658836364746,
"learning_rate": 9.918386404867634e-06,
"loss": 0.6417,
"step": 12500
},
{
"epoch": 0.3003349890262216,
"grad_norm": 3.7156598567962646,
"learning_rate": 9.894067693564784e-06,
"loss": 0.6436,
"step": 13000
},
{
"epoch": 0.3118863347579993,
"grad_norm": 12.272802352905273,
"learning_rate": 9.869748982261933e-06,
"loss": 0.6505,
"step": 13500
},
{
"epoch": 0.32343768048977706,
"grad_norm": 15.592353820800781,
"learning_rate": 9.845430270959082e-06,
"loss": 0.6313,
"step": 14000
},
{
"epoch": 0.3349890262215548,
"grad_norm": 4.684946537017822,
"learning_rate": 9.821111559656232e-06,
"loss": 0.6457,
"step": 14500
},
{
"epoch": 0.34654037195333254,
"grad_norm": 6.0165300369262695,
"learning_rate": 9.79679284835338e-06,
"loss": 0.641,
"step": 15000
},
{
"epoch": 0.35809171768511033,
"grad_norm": 10.924590110778809,
"learning_rate": 9.772474137050531e-06,
"loss": 0.6293,
"step": 15500
},
{
"epoch": 0.3696430634168881,
"grad_norm": 7.296951770782471,
"learning_rate": 9.74815542574768e-06,
"loss": 0.627,
"step": 16000
},
{
"epoch": 0.3811944091486658,
"grad_norm": 14.750964164733887,
"learning_rate": 9.723836714444829e-06,
"loss": 0.6254,
"step": 16500
},
{
"epoch": 0.39274575488044355,
"grad_norm": 7.377384662628174,
"learning_rate": 9.699518003141977e-06,
"loss": 0.6287,
"step": 17000
},
{
"epoch": 0.40429710061222135,
"grad_norm": 6.540673732757568,
"learning_rate": 9.675199291839128e-06,
"loss": 0.6309,
"step": 17500
},
{
"epoch": 0.4158484463439991,
"grad_norm": 6.4445295333862305,
"learning_rate": 9.650880580536277e-06,
"loss": 0.6302,
"step": 18000
},
{
"epoch": 0.42739979207577683,
"grad_norm": 7.85426664352417,
"learning_rate": 9.626561869233427e-06,
"loss": 0.6201,
"step": 18500
},
{
"epoch": 0.43895113780755457,
"grad_norm": 5.960766792297363,
"learning_rate": 9.602243157930576e-06,
"loss": 0.626,
"step": 19000
},
{
"epoch": 0.4505024835393323,
"grad_norm": 9.376029968261719,
"learning_rate": 9.577924446627726e-06,
"loss": 0.6164,
"step": 19500
},
{
"epoch": 0.4620538292711101,
"grad_norm": 17.05916976928711,
"learning_rate": 9.553605735324875e-06,
"loss": 0.6232,
"step": 20000
},
{
"epoch": 0.47360517500288785,
"grad_norm": 7.523278713226318,
"learning_rate": 9.529287024022024e-06,
"loss": 0.601,
"step": 20500
},
{
"epoch": 0.4851565207346656,
"grad_norm": 6.75208044052124,
"learning_rate": 9.504968312719172e-06,
"loss": 0.6157,
"step": 21000
},
{
"epoch": 0.4967078664664433,
"grad_norm": 12.919069290161133,
"learning_rate": 9.480649601416323e-06,
"loss": 0.6098,
"step": 21500
},
{
"epoch": 0.5082592121982211,
"grad_norm": 19.89571189880371,
"learning_rate": 9.456330890113472e-06,
"loss": 0.6131,
"step": 22000
},
{
"epoch": 0.5198105579299989,
"grad_norm": 7.436350345611572,
"learning_rate": 9.432012178810622e-06,
"loss": 0.6121,
"step": 22500
},
{
"epoch": 0.5313619036617766,
"grad_norm": 10.576221466064453,
"learning_rate": 9.40769346750777e-06,
"loss": 0.6005,
"step": 23000
},
{
"epoch": 0.5429132493935543,
"grad_norm": 12.731452941894531,
"learning_rate": 9.383374756204921e-06,
"loss": 0.6217,
"step": 23500
},
{
"epoch": 0.5544645951253321,
"grad_norm": 9.219985961914062,
"learning_rate": 9.35905604490207e-06,
"loss": 0.5985,
"step": 24000
},
{
"epoch": 0.5660159408571098,
"grad_norm": 12.659988403320312,
"learning_rate": 9.334737333599219e-06,
"loss": 0.5951,
"step": 24500
},
{
"epoch": 0.5775672865888876,
"grad_norm": 32.879234313964844,
"learning_rate": 9.310418622296367e-06,
"loss": 0.5961,
"step": 25000
},
{
"epoch": 0.5891186323206653,
"grad_norm": 9.763121604919434,
"learning_rate": 9.286099910993518e-06,
"loss": 0.6081,
"step": 25500
},
{
"epoch": 0.6006699780524432,
"grad_norm": 9.057079315185547,
"learning_rate": 9.261781199690667e-06,
"loss": 0.5863,
"step": 26000
},
{
"epoch": 0.6122213237842209,
"grad_norm": 17.381582260131836,
"learning_rate": 9.237462488387817e-06,
"loss": 0.5857,
"step": 26500
},
{
"epoch": 0.6237726695159986,
"grad_norm": 18.3979549407959,
"learning_rate": 9.213143777084966e-06,
"loss": 0.5853,
"step": 27000
},
{
"epoch": 0.6353240152477764,
"grad_norm": 11.13846206665039,
"learning_rate": 9.188825065782114e-06,
"loss": 0.582,
"step": 27500
},
{
"epoch": 0.6468753609795541,
"grad_norm": 8.506060600280762,
"learning_rate": 9.164506354479265e-06,
"loss": 0.5773,
"step": 28000
},
{
"epoch": 0.6584267067113319,
"grad_norm": 9.814123153686523,
"learning_rate": 9.140187643176414e-06,
"loss": 0.5797,
"step": 28500
},
{
"epoch": 0.6699780524431096,
"grad_norm": 11.70206069946289,
"learning_rate": 9.115868931873562e-06,
"loss": 0.5587,
"step": 29000
},
{
"epoch": 0.6815293981748873,
"grad_norm": 11.949383735656738,
"learning_rate": 9.091550220570711e-06,
"loss": 0.5769,
"step": 29500
},
{
"epoch": 0.6930807439066651,
"grad_norm": 11.51278018951416,
"learning_rate": 9.067231509267862e-06,
"loss": 0.5798,
"step": 30000
},
{
"epoch": 0.7046320896384429,
"grad_norm": 13.705997467041016,
"learning_rate": 9.042912797965012e-06,
"loss": 0.5585,
"step": 30500
},
{
"epoch": 0.7161834353702207,
"grad_norm": 18.50054168701172,
"learning_rate": 9.01859408666216e-06,
"loss": 0.5656,
"step": 31000
},
{
"epoch": 0.7277347811019984,
"grad_norm": 23.920692443847656,
"learning_rate": 8.99427537535931e-06,
"loss": 0.5493,
"step": 31500
},
{
"epoch": 0.7392861268337761,
"grad_norm": 15.425186157226562,
"learning_rate": 8.96995666405646e-06,
"loss": 0.5538,
"step": 32000
},
{
"epoch": 0.7508374725655539,
"grad_norm": 11.077018737792969,
"learning_rate": 8.945637952753609e-06,
"loss": 0.5553,
"step": 32500
},
{
"epoch": 0.7623888182973316,
"grad_norm": 17.128128051757812,
"learning_rate": 8.921319241450757e-06,
"loss": 0.5657,
"step": 33000
},
{
"epoch": 0.7739401640291094,
"grad_norm": 37.22261428833008,
"learning_rate": 8.897000530147906e-06,
"loss": 0.5573,
"step": 33500
},
{
"epoch": 0.7854915097608871,
"grad_norm": 18.649255752563477,
"learning_rate": 8.872681818845056e-06,
"loss": 0.5337,
"step": 34000
},
{
"epoch": 0.7970428554926648,
"grad_norm": 11.49511432647705,
"learning_rate": 8.848363107542205e-06,
"loss": 0.5442,
"step": 34500
},
{
"epoch": 0.8085942012244427,
"grad_norm": 20.64067840576172,
"learning_rate": 8.824044396239356e-06,
"loss": 0.5632,
"step": 35000
},
{
"epoch": 0.8201455469562204,
"grad_norm": 18.51673126220703,
"learning_rate": 8.799725684936504e-06,
"loss": 0.5454,
"step": 35500
},
{
"epoch": 0.8316968926879982,
"grad_norm": 18.139997482299805,
"learning_rate": 8.775406973633655e-06,
"loss": 0.5371,
"step": 36000
},
{
"epoch": 0.8432482384197759,
"grad_norm": 21.852693557739258,
"learning_rate": 8.751088262330804e-06,
"loss": 0.539,
"step": 36500
},
{
"epoch": 0.8547995841515537,
"grad_norm": 31.914161682128906,
"learning_rate": 8.726769551027952e-06,
"loss": 0.5383,
"step": 37000
},
{
"epoch": 0.8663509298833314,
"grad_norm": 9.24451732635498,
"learning_rate": 8.702450839725101e-06,
"loss": 0.548,
"step": 37500
},
{
"epoch": 0.8779022756151091,
"grad_norm": 27.3262882232666,
"learning_rate": 8.678132128422251e-06,
"loss": 0.524,
"step": 38000
},
{
"epoch": 0.8894536213468869,
"grad_norm": 23.231952667236328,
"learning_rate": 8.6538134171194e-06,
"loss": 0.5121,
"step": 38500
},
{
"epoch": 0.9010049670786646,
"grad_norm": 28.35572052001953,
"learning_rate": 8.62949470581655e-06,
"loss": 0.5333,
"step": 39000
},
{
"epoch": 0.9125563128104425,
"grad_norm": 24.61405372619629,
"learning_rate": 8.6051759945137e-06,
"loss": 0.5015,
"step": 39500
},
{
"epoch": 0.9241076585422202,
"grad_norm": 30.62819480895996,
"learning_rate": 8.580857283210848e-06,
"loss": 0.5092,
"step": 40000
},
{
"epoch": 0.935659004273998,
"grad_norm": 19.295331954956055,
"learning_rate": 8.556538571907999e-06,
"loss": 0.5125,
"step": 40500
},
{
"epoch": 0.9472103500057757,
"grad_norm": 10.785584449768066,
"learning_rate": 8.532219860605147e-06,
"loss": 0.5161,
"step": 41000
},
{
"epoch": 0.9587616957375534,
"grad_norm": 24.81365394592285,
"learning_rate": 8.507901149302296e-06,
"loss": 0.498,
"step": 41500
},
{
"epoch": 0.9703130414693312,
"grad_norm": 48.026973724365234,
"learning_rate": 8.483582437999446e-06,
"loss": 0.4916,
"step": 42000
},
{
"epoch": 0.9818643872011089,
"grad_norm": 6.653892517089844,
"learning_rate": 8.459263726696595e-06,
"loss": 0.4944,
"step": 42500
},
{
"epoch": 0.9934157329328867,
"grad_norm": 39.814945220947266,
"learning_rate": 8.434945015393746e-06,
"loss": 0.4954,
"step": 43000
},
{
"epoch": 1.0,
"eval_accuracy": 0.7796003234376805,
"eval_f1": 0.7890500619140279,
"eval_loss": 0.4737609326839447,
"eval_matthews_correlation": 0.5599099791389662,
"eval_precision": 0.7656524910955671,
"eval_recall": 0.8139227225035354,
"eval_runtime": 550.4755,
"eval_samples_per_second": 78.632,
"eval_steps_per_second": 4.916,
"step": 43285
},
{
"epoch": 1.0049670786646645,
"grad_norm": 22.5259952545166,
"learning_rate": 8.410626304090894e-06,
"loss": 0.4339,
"step": 43500
},
{
"epoch": 1.0165184243964422,
"grad_norm": 25.5583438873291,
"learning_rate": 8.386307592788043e-06,
"loss": 0.3274,
"step": 44000
},
{
"epoch": 1.02806977012822,
"grad_norm": 9.524903297424316,
"learning_rate": 8.361988881485194e-06,
"loss": 0.3372,
"step": 44500
},
{
"epoch": 1.0396211158599977,
"grad_norm": 37.77333068847656,
"learning_rate": 8.337670170182342e-06,
"loss": 0.3471,
"step": 45000
},
{
"epoch": 1.0511724615917755,
"grad_norm": 47.2765007019043,
"learning_rate": 8.313351458879491e-06,
"loss": 0.3436,
"step": 45500
},
{
"epoch": 1.0627238073235532,
"grad_norm": 58.79914474487305,
"learning_rate": 8.289032747576641e-06,
"loss": 0.3524,
"step": 46000
},
{
"epoch": 1.074275153055331,
"grad_norm": 23.910385131835938,
"learning_rate": 8.26471403627379e-06,
"loss": 0.3283,
"step": 46500
},
{
"epoch": 1.0858264987871087,
"grad_norm": 65.18335723876953,
"learning_rate": 8.24039532497094e-06,
"loss": 0.3529,
"step": 47000
},
{
"epoch": 1.0973778445188864,
"grad_norm": 29.333236694335938,
"learning_rate": 8.21607661366809e-06,
"loss": 0.3471,
"step": 47500
},
{
"epoch": 1.1089291902506642,
"grad_norm": 41.33262252807617,
"learning_rate": 8.191757902365238e-06,
"loss": 0.3507,
"step": 48000
},
{
"epoch": 1.120480535982442,
"grad_norm": 91.7591781616211,
"learning_rate": 8.167439191062387e-06,
"loss": 0.3506,
"step": 48500
},
{
"epoch": 1.1320318817142196,
"grad_norm": 7.366957187652588,
"learning_rate": 8.143120479759537e-06,
"loss": 0.3526,
"step": 49000
},
{
"epoch": 1.1435832274459974,
"grad_norm": 31.159626007080078,
"learning_rate": 8.118801768456686e-06,
"loss": 0.3423,
"step": 49500
},
{
"epoch": 1.1551345731777751,
"grad_norm": 15.73024845123291,
"learning_rate": 8.094483057153836e-06,
"loss": 0.3516,
"step": 50000
},
{
"epoch": 1.1666859189095529,
"grad_norm": 66.58766174316406,
"learning_rate": 8.070164345850985e-06,
"loss": 0.3435,
"step": 50500
},
{
"epoch": 1.1782372646413308,
"grad_norm": 48.182308197021484,
"learning_rate": 8.045845634548136e-06,
"loss": 0.344,
"step": 51000
},
{
"epoch": 1.1897886103731086,
"grad_norm": 42.61834716796875,
"learning_rate": 8.021526923245284e-06,
"loss": 0.3739,
"step": 51500
},
{
"epoch": 1.2013399561048863,
"grad_norm": 59.38914489746094,
"learning_rate": 7.997208211942433e-06,
"loss": 0.3399,
"step": 52000
},
{
"epoch": 1.212891301836664,
"grad_norm": 5.7647857666015625,
"learning_rate": 7.972889500639582e-06,
"loss": 0.3518,
"step": 52500
},
{
"epoch": 1.2244426475684418,
"grad_norm": 73.71373748779297,
"learning_rate": 7.948570789336732e-06,
"loss": 0.3523,
"step": 53000
},
{
"epoch": 1.2359939933002195,
"grad_norm": 14.03942584991455,
"learning_rate": 7.924252078033881e-06,
"loss": 0.3512,
"step": 53500
},
{
"epoch": 1.2475453390319973,
"grad_norm": 53.254791259765625,
"learning_rate": 7.899933366731031e-06,
"loss": 0.3454,
"step": 54000
},
{
"epoch": 1.259096684763775,
"grad_norm": 4.009112358093262,
"learning_rate": 7.87561465542818e-06,
"loss": 0.3406,
"step": 54500
},
{
"epoch": 1.2706480304955527,
"grad_norm": 37.73891067504883,
"learning_rate": 7.85129594412533e-06,
"loss": 0.3474,
"step": 55000
},
{
"epoch": 1.2821993762273305,
"grad_norm": 84.36405181884766,
"learning_rate": 7.82697723282248e-06,
"loss": 0.3551,
"step": 55500
},
{
"epoch": 1.2937507219591082,
"grad_norm": 43.2830810546875,
"learning_rate": 7.802658521519628e-06,
"loss": 0.3521,
"step": 56000
},
{
"epoch": 1.305302067690886,
"grad_norm": 143.8572998046875,
"learning_rate": 7.778339810216777e-06,
"loss": 0.3544,
"step": 56500
},
{
"epoch": 1.3168534134226637,
"grad_norm": 19.368745803833008,
"learning_rate": 7.754021098913927e-06,
"loss": 0.332,
"step": 57000
},
{
"epoch": 1.3284047591544415,
"grad_norm": 37.57652282714844,
"learning_rate": 7.729702387611076e-06,
"loss": 0.3614,
"step": 57500
},
{
"epoch": 1.3399561048862192,
"grad_norm": 12.710687637329102,
"learning_rate": 7.705383676308226e-06,
"loss": 0.3397,
"step": 58000
},
{
"epoch": 1.351507450617997,
"grad_norm": 9.734477043151855,
"learning_rate": 7.681064965005375e-06,
"loss": 0.3337,
"step": 58500
},
{
"epoch": 1.3630587963497747,
"grad_norm": 50.98896408081055,
"learning_rate": 7.656746253702524e-06,
"loss": 0.3466,
"step": 59000
},
{
"epoch": 1.3746101420815524,
"grad_norm": 36.90542221069336,
"learning_rate": 7.632427542399674e-06,
"loss": 0.3345,
"step": 59500
},
{
"epoch": 1.3861614878133302,
"grad_norm": 87.90083312988281,
"learning_rate": 7.608108831096823e-06,
"loss": 0.3268,
"step": 60000
},
{
"epoch": 1.397712833545108,
"grad_norm": 33.43013000488281,
"learning_rate": 7.583790119793973e-06,
"loss": 0.3572,
"step": 60500
},
{
"epoch": 1.4092641792768856,
"grad_norm": 10.33069896697998,
"learning_rate": 7.559471408491121e-06,
"loss": 0.3565,
"step": 61000
},
{
"epoch": 1.4208155250086634,
"grad_norm": 1.686011791229248,
"learning_rate": 7.535152697188272e-06,
"loss": 0.3647,
"step": 61500
},
{
"epoch": 1.4323668707404413,
"grad_norm": 20.76148223876953,
"learning_rate": 7.5108339858854206e-06,
"loss": 0.3284,
"step": 62000
},
{
"epoch": 1.443918216472219,
"grad_norm": 9.261433601379395,
"learning_rate": 7.48651527458257e-06,
"loss": 0.3474,
"step": 62500
},
{
"epoch": 1.4554695622039968,
"grad_norm": 38.97019577026367,
"learning_rate": 7.462196563279719e-06,
"loss": 0.3433,
"step": 63000
},
{
"epoch": 1.4670209079357746,
"grad_norm": 43.138450622558594,
"learning_rate": 7.437877851976869e-06,
"loss": 0.3406,
"step": 63500
},
{
"epoch": 1.4785722536675523,
"grad_norm": 10.66066837310791,
"learning_rate": 7.413559140674018e-06,
"loss": 0.3533,
"step": 64000
},
{
"epoch": 1.49012359939933,
"grad_norm": 32.289588928222656,
"learning_rate": 7.389240429371168e-06,
"loss": 0.3377,
"step": 64500
},
{
"epoch": 1.5016749451311078,
"grad_norm": 85.28985595703125,
"learning_rate": 7.364921718068316e-06,
"loss": 0.3598,
"step": 65000
},
{
"epoch": 1.5132262908628855,
"grad_norm": 56.37942123413086,
"learning_rate": 7.340603006765467e-06,
"loss": 0.3354,
"step": 65500
},
{
"epoch": 1.5247776365946633,
"grad_norm": 91.6646499633789,
"learning_rate": 7.3162842954626156e-06,
"loss": 0.3557,
"step": 66000
},
{
"epoch": 1.536328982326441,
"grad_norm": 22.282794952392578,
"learning_rate": 7.291965584159765e-06,
"loss": 0.3375,
"step": 66500
},
{
"epoch": 1.5478803280582187,
"grad_norm": 23.59638214111328,
"learning_rate": 7.267646872856914e-06,
"loss": 0.3613,
"step": 67000
},
{
"epoch": 1.5594316737899967,
"grad_norm": 101.47071838378906,
"learning_rate": 7.243328161554064e-06,
"loss": 0.3625,
"step": 67500
},
{
"epoch": 1.5709830195217744,
"grad_norm": 10.680140495300293,
"learning_rate": 7.219009450251213e-06,
"loss": 0.3447,
"step": 68000
},
{
"epoch": 1.5825343652535522,
"grad_norm": 3.526810646057129,
"learning_rate": 7.194690738948363e-06,
"loss": 0.3752,
"step": 68500
},
{
"epoch": 1.59408571098533,
"grad_norm": 63.79883575439453,
"learning_rate": 7.170372027645511e-06,
"loss": 0.3556,
"step": 69000
},
{
"epoch": 1.6056370567171077,
"grad_norm": 57.77899169921875,
"learning_rate": 7.14605331634266e-06,
"loss": 0.3734,
"step": 69500
},
{
"epoch": 1.6171884024488854,
"grad_norm": 12.811071395874023,
"learning_rate": 7.1217346050398105e-06,
"loss": 0.3314,
"step": 70000
},
{
"epoch": 1.6287397481806631,
"grad_norm": 45.64273452758789,
"learning_rate": 7.09741589373696e-06,
"loss": 0.3603,
"step": 70500
},
{
"epoch": 1.6402910939124409,
"grad_norm": 0.7724096775054932,
"learning_rate": 7.073097182434109e-06,
"loss": 0.3531,
"step": 71000
},
{
"epoch": 1.6518424396442186,
"grad_norm": 111.21202850341797,
"learning_rate": 7.048778471131258e-06,
"loss": 0.3687,
"step": 71500
},
{
"epoch": 1.6633937853759964,
"grad_norm": 2.9768288135528564,
"learning_rate": 7.024459759828408e-06,
"loss": 0.362,
"step": 72000
},
{
"epoch": 1.674945131107774,
"grad_norm": 27.48809242248535,
"learning_rate": 7.000141048525558e-06,
"loss": 0.3616,
"step": 72500
},
{
"epoch": 1.6864964768395518,
"grad_norm": 48.34687805175781,
"learning_rate": 6.975822337222706e-06,
"loss": 0.3367,
"step": 73000
},
{
"epoch": 1.6980478225713296,
"grad_norm": 39.69007110595703,
"learning_rate": 6.951503625919855e-06,
"loss": 0.3621,
"step": 73500
},
{
"epoch": 1.7095991683031073,
"grad_norm": 110.33565521240234,
"learning_rate": 6.9271849146170055e-06,
"loss": 0.3539,
"step": 74000
},
{
"epoch": 1.721150514034885,
"grad_norm": 41.324222564697266,
"learning_rate": 6.902866203314154e-06,
"loss": 0.3433,
"step": 74500
},
{
"epoch": 1.7327018597666628,
"grad_norm": 73.07483673095703,
"learning_rate": 6.878547492011304e-06,
"loss": 0.3581,
"step": 75000
},
{
"epoch": 1.7442532054984405,
"grad_norm": 2.784154176712036,
"learning_rate": 6.854228780708453e-06,
"loss": 0.3506,
"step": 75500
},
{
"epoch": 1.7558045512302183,
"grad_norm": 46.016876220703125,
"learning_rate": 6.829910069405603e-06,
"loss": 0.3687,
"step": 76000
},
{
"epoch": 1.767355896961996,
"grad_norm": 10.431674003601074,
"learning_rate": 6.805591358102752e-06,
"loss": 0.3448,
"step": 76500
},
{
"epoch": 1.7789072426937738,
"grad_norm": 77.33363342285156,
"learning_rate": 6.781272646799901e-06,
"loss": 0.3688,
"step": 77000
},
{
"epoch": 1.7904585884255515,
"grad_norm": 36.162261962890625,
"learning_rate": 6.75695393549705e-06,
"loss": 0.3481,
"step": 77500
},
{
"epoch": 1.8020099341573292,
"grad_norm": 34.184844970703125,
"learning_rate": 6.7326352241942005e-06,
"loss": 0.3538,
"step": 78000
},
{
"epoch": 1.813561279889107,
"grad_norm": 89.07086944580078,
"learning_rate": 6.708316512891349e-06,
"loss": 0.3735,
"step": 78500
},
{
"epoch": 1.8251126256208847,
"grad_norm": 3.9982004165649414,
"learning_rate": 6.683997801588499e-06,
"loss": 0.3394,
"step": 79000
},
{
"epoch": 1.8366639713526625,
"grad_norm": 81.374267578125,
"learning_rate": 6.659679090285648e-06,
"loss": 0.3174,
"step": 79500
},
{
"epoch": 1.8482153170844402,
"grad_norm": 0.20297826826572418,
"learning_rate": 6.635360378982797e-06,
"loss": 0.3153,
"step": 80000
},
{
"epoch": 1.859766662816218,
"grad_norm": 59.6692008972168,
"learning_rate": 6.611041667679947e-06,
"loss": 0.3545,
"step": 80500
},
{
"epoch": 1.8713180085479957,
"grad_norm": 1.2928632497787476,
"learning_rate": 6.586722956377096e-06,
"loss": 0.3373,
"step": 81000
},
{
"epoch": 1.8828693542797736,
"grad_norm": 94.39313507080078,
"learning_rate": 6.562404245074245e-06,
"loss": 0.3222,
"step": 81500
},
{
"epoch": 1.8944207000115514,
"grad_norm": 29.352657318115234,
"learning_rate": 6.538085533771395e-06,
"loss": 0.3418,
"step": 82000
},
{
"epoch": 1.9059720457433291,
"grad_norm": 11.170536041259766,
"learning_rate": 6.513766822468544e-06,
"loss": 0.3423,
"step": 82500
},
{
"epoch": 1.9175233914751069,
"grad_norm": 90.75904846191406,
"learning_rate": 6.489448111165694e-06,
"loss": 0.3253,
"step": 83000
},
{
"epoch": 1.9290747372068846,
"grad_norm": 79.5523681640625,
"learning_rate": 6.4651293998628426e-06,
"loss": 0.3423,
"step": 83500
},
{
"epoch": 1.9406260829386623,
"grad_norm": 2.362600564956665,
"learning_rate": 6.440810688559992e-06,
"loss": 0.3233,
"step": 84000
},
{
"epoch": 1.95217742867044,
"grad_norm": 106.5050277709961,
"learning_rate": 6.416491977257142e-06,
"loss": 0.3291,
"step": 84500
},
{
"epoch": 1.9637287744022178,
"grad_norm": 44.49625015258789,
"learning_rate": 6.392173265954291e-06,
"loss": 0.3462,
"step": 85000
},
{
"epoch": 1.9752801201339956,
"grad_norm": 65.74842071533203,
"learning_rate": 6.36785455465144e-06,
"loss": 0.3356,
"step": 85500
},
{
"epoch": 1.9868314658657735,
"grad_norm": 25.529869079589844,
"learning_rate": 6.34353584334859e-06,
"loss": 0.3418,
"step": 86000
},
{
"epoch": 1.9983828115975513,
"grad_norm": 0.7819985151290894,
"learning_rate": 6.319217132045739e-06,
"loss": 0.3299,
"step": 86500
},
{
"epoch": 2.0,
"eval_accuracy": 0.8750144391821647,
"eval_f1": 0.883420247381804,
"eval_loss": 0.5118392705917358,
"eval_matthews_correlation": 0.7549403916374646,
"eval_precision": 0.8371656115989381,
"eval_recall": 0.9350850782354819,
"eval_runtime": 543.2127,
"eval_samples_per_second": 79.683,
"eval_steps_per_second": 4.981,
"step": 86570
},
{
"epoch": 2.009934157329329,
"grad_norm": 0.09307216852903366,
"learning_rate": 6.294898420742889e-06,
"loss": 0.2056,
"step": 87000
},
{
"epoch": 2.0214855030611067,
"grad_norm": 0.1265561431646347,
"learning_rate": 6.2705797094400376e-06,
"loss": 0.201,
"step": 87500
},
{
"epoch": 2.0330368487928845,
"grad_norm": 0.5366824865341187,
"learning_rate": 6.246260998137187e-06,
"loss": 0.1897,
"step": 88000
},
{
"epoch": 2.0445881945246622,
"grad_norm": 37.82719421386719,
"learning_rate": 6.221942286834337e-06,
"loss": 0.2095,
"step": 88500
},
{
"epoch": 2.05613954025644,
"grad_norm": 0.5017096996307373,
"learning_rate": 6.197623575531486e-06,
"loss": 0.1988,
"step": 89000
},
{
"epoch": 2.0676908859882177,
"grad_norm": 0.10803969949483871,
"learning_rate": 6.173304864228635e-06,
"loss": 0.1991,
"step": 89500
},
{
"epoch": 2.0792422317199954,
"grad_norm": 0.3513072431087494,
"learning_rate": 6.148986152925785e-06,
"loss": 0.2018,
"step": 90000
},
{
"epoch": 2.090793577451773,
"grad_norm": 1.3080644607543945,
"learning_rate": 6.124667441622933e-06,
"loss": 0.2095,
"step": 90500
},
{
"epoch": 2.102344923183551,
"grad_norm": 5.2385053634643555,
"learning_rate": 6.100348730320084e-06,
"loss": 0.1974,
"step": 91000
},
{
"epoch": 2.1138962689153287,
"grad_norm": 10.532730102539062,
"learning_rate": 6.0760300190172326e-06,
"loss": 0.2019,
"step": 91500
},
{
"epoch": 2.1254476146471064,
"grad_norm": 0.104009710252285,
"learning_rate": 6.051711307714382e-06,
"loss": 0.2091,
"step": 92000
},
{
"epoch": 2.136998960378884,
"grad_norm": 0.038262490183115005,
"learning_rate": 6.027392596411531e-06,
"loss": 0.2422,
"step": 92500
},
{
"epoch": 2.148550306110662,
"grad_norm": 0.30325543880462646,
"learning_rate": 6.003073885108681e-06,
"loss": 0.1971,
"step": 93000
},
{
"epoch": 2.1601016518424396,
"grad_norm": 0.2501794099807739,
"learning_rate": 5.97875517380583e-06,
"loss": 0.2123,
"step": 93500
},
{
"epoch": 2.1716529975742174,
"grad_norm": 0.9724676609039307,
"learning_rate": 5.95443646250298e-06,
"loss": 0.2222,
"step": 94000
},
{
"epoch": 2.183204343305995,
"grad_norm": 23.507680892944336,
"learning_rate": 5.930117751200128e-06,
"loss": 0.199,
"step": 94500
},
{
"epoch": 2.194755689037773,
"grad_norm": 23.95125389099121,
"learning_rate": 5.905799039897279e-06,
"loss": 0.2367,
"step": 95000
},
{
"epoch": 2.2063070347695506,
"grad_norm": 0.026822537183761597,
"learning_rate": 5.8814803285944275e-06,
"loss": 0.1918,
"step": 95500
},
{
"epoch": 2.2178583805013283,
"grad_norm": 0.11111404001712799,
"learning_rate": 5.857161617291577e-06,
"loss": 0.2047,
"step": 96000
},
{
"epoch": 2.229409726233106,
"grad_norm": 0.1919553279876709,
"learning_rate": 5.832842905988726e-06,
"loss": 0.225,
"step": 96500
},
{
"epoch": 2.240961071964884,
"grad_norm": 0.44445013999938965,
"learning_rate": 5.808524194685876e-06,
"loss": 0.2373,
"step": 97000
},
{
"epoch": 2.2525124176966616,
"grad_norm": 0.0314050130546093,
"learning_rate": 5.784205483383025e-06,
"loss": 0.2313,
"step": 97500
},
{
"epoch": 2.2640637634284393,
"grad_norm": 0.3491435945034027,
"learning_rate": 5.759886772080175e-06,
"loss": 0.2149,
"step": 98000
},
{
"epoch": 2.275615109160217,
"grad_norm": 0.41699114441871643,
"learning_rate": 5.735568060777323e-06,
"loss": 0.2012,
"step": 98500
},
{
"epoch": 2.2871664548919948,
"grad_norm": 0.05766846239566803,
"learning_rate": 5.711249349474474e-06,
"loss": 0.2247,
"step": 99000
},
{
"epoch": 2.2987178006237725,
"grad_norm": 10.02811336517334,
"learning_rate": 5.6869306381716225e-06,
"loss": 0.2081,
"step": 99500
},
{
"epoch": 2.3102691463555503,
"grad_norm": 0.1262376755475998,
"learning_rate": 5.662611926868772e-06,
"loss": 0.2471,
"step": 100000
},
{
"epoch": 2.321820492087328,
"grad_norm": 7.784575939178467,
"learning_rate": 5.638293215565921e-06,
"loss": 0.2188,
"step": 100500
},
{
"epoch": 2.3333718378191057,
"grad_norm": 0.4924183189868927,
"learning_rate": 5.61397450426307e-06,
"loss": 0.182,
"step": 101000
},
{
"epoch": 2.3449231835508835,
"grad_norm": 0.8090869188308716,
"learning_rate": 5.58965579296022e-06,
"loss": 0.2307,
"step": 101500
},
{
"epoch": 2.3564745292826617,
"grad_norm": 0.5244800448417664,
"learning_rate": 5.56533708165737e-06,
"loss": 0.2162,
"step": 102000
},
{
"epoch": 2.368025875014439,
"grad_norm": 0.12117698788642883,
"learning_rate": 5.541018370354518e-06,
"loss": 0.2339,
"step": 102500
},
{
"epoch": 2.379577220746217,
"grad_norm": 139.68356323242188,
"learning_rate": 5.516699659051667e-06,
"loss": 0.2306,
"step": 103000
},
{
"epoch": 2.391128566477995,
"grad_norm": 0.34436774253845215,
"learning_rate": 5.4923809477488175e-06,
"loss": 0.2289,
"step": 103500
},
{
"epoch": 2.4026799122097726,
"grad_norm": 0.06684353947639465,
"learning_rate": 5.468062236445967e-06,
"loss": 0.2388,
"step": 104000
},
{
"epoch": 2.4142312579415504,
"grad_norm": 38.31502914428711,
"learning_rate": 5.443743525143116e-06,
"loss": 0.2185,
"step": 104500
},
{
"epoch": 2.425782603673328,
"grad_norm": 0.47605860233306885,
"learning_rate": 5.419424813840265e-06,
"loss": 0.2536,
"step": 105000
},
{
"epoch": 2.437333949405106,
"grad_norm": 2.486711025238037,
"learning_rate": 5.395106102537415e-06,
"loss": 0.224,
"step": 105500
},
{
"epoch": 2.4488852951368836,
"grad_norm": 0.19100871682167053,
"learning_rate": 5.370787391234565e-06,
"loss": 0.2429,
"step": 106000
},
{
"epoch": 2.4604366408686613,
"grad_norm": 0.6943984627723694,
"learning_rate": 5.346468679931713e-06,
"loss": 0.2051,
"step": 106500
},
{
"epoch": 2.471987986600439,
"grad_norm": 100.54878234863281,
"learning_rate": 5.322149968628862e-06,
"loss": 0.2177,
"step": 107000
},
{
"epoch": 2.483539332332217,
"grad_norm": 1.6368072032928467,
"learning_rate": 5.2978312573260125e-06,
"loss": 0.2182,
"step": 107500
},
{
"epoch": 2.4950906780639945,
"grad_norm": 0.33522534370422363,
"learning_rate": 5.273512546023162e-06,
"loss": 0.2011,
"step": 108000
},
{
"epoch": 2.5066420237957723,
"grad_norm": 1.7450274229049683,
"learning_rate": 5.249193834720311e-06,
"loss": 0.2316,
"step": 108500
},
{
"epoch": 2.51819336952755,
"grad_norm": 0.29246997833251953,
"learning_rate": 5.2248751234174596e-06,
"loss": 0.2311,
"step": 109000
},
{
"epoch": 2.5297447152593278,
"grad_norm": 0.0980878472328186,
"learning_rate": 5.20055641211461e-06,
"loss": 0.2224,
"step": 109500
},
{
"epoch": 2.5412960609911055,
"grad_norm": 19.347719192504883,
"learning_rate": 5.17623770081176e-06,
"loss": 0.2156,
"step": 110000
},
{
"epoch": 2.5528474067228832,
"grad_norm": 0.4555191099643707,
"learning_rate": 5.151918989508908e-06,
"loss": 0.2192,
"step": 110500
},
{
"epoch": 2.564398752454661,
"grad_norm": 8.327524185180664,
"learning_rate": 5.127600278206057e-06,
"loss": 0.2331,
"step": 111000
},
{
"epoch": 2.5759500981864387,
"grad_norm": 0.23247091472148895,
"learning_rate": 5.103281566903207e-06,
"loss": 0.2068,
"step": 111500
},
{
"epoch": 2.5875014439182165,
"grad_norm": 0.5253803730010986,
"learning_rate": 5.078962855600357e-06,
"loss": 0.2199,
"step": 112000
},
{
"epoch": 2.599052789649994,
"grad_norm": 0.16480697691440582,
"learning_rate": 5.054644144297506e-06,
"loss": 0.2303,
"step": 112500
},
{
"epoch": 2.610604135381772,
"grad_norm": 13.176816940307617,
"learning_rate": 5.0303254329946546e-06,
"loss": 0.2463,
"step": 113000
},
{
"epoch": 2.6221554811135497,
"grad_norm": 0.30696120858192444,
"learning_rate": 5.006006721691804e-06,
"loss": 0.229,
"step": 113500
},
{
"epoch": 2.6337068268453274,
"grad_norm": 10.747370719909668,
"learning_rate": 4.981688010388954e-06,
"loss": 0.239,
"step": 114000
},
{
"epoch": 2.645258172577105,
"grad_norm": 10.800712585449219,
"learning_rate": 4.957369299086103e-06,
"loss": 0.2464,
"step": 114500
},
{
"epoch": 2.656809518308883,
"grad_norm": 137.77926635742188,
"learning_rate": 4.933050587783252e-06,
"loss": 0.2082,
"step": 115000
},
{
"epoch": 2.6683608640406606,
"grad_norm": 47.672916412353516,
"learning_rate": 4.908731876480402e-06,
"loss": 0.2169,
"step": 115500
},
{
"epoch": 2.6799122097724384,
"grad_norm": 13.38288402557373,
"learning_rate": 4.884413165177551e-06,
"loss": 0.2316,
"step": 116000
},
{
"epoch": 2.691463555504216,
"grad_norm": 1.015547275543213,
"learning_rate": 4.860094453874701e-06,
"loss": 0.2129,
"step": 116500
},
{
"epoch": 2.703014901235994,
"grad_norm": 0.6633150577545166,
"learning_rate": 4.8357757425718495e-06,
"loss": 0.2346,
"step": 117000
},
{
"epoch": 2.7145662469677716,
"grad_norm": 0.4231832027435303,
"learning_rate": 4.811457031268999e-06,
"loss": 0.2465,
"step": 117500
},
{
"epoch": 2.7261175926995493,
"grad_norm": 0.1299211084842682,
"learning_rate": 4.787138319966149e-06,
"loss": 0.2395,
"step": 118000
},
{
"epoch": 2.7376689384313275,
"grad_norm": 0.05142102763056755,
"learning_rate": 4.762819608663298e-06,
"loss": 0.2327,
"step": 118500
},
{
"epoch": 2.749220284163105,
"grad_norm": 0.11573930829763412,
"learning_rate": 4.738500897360447e-06,
"loss": 0.2035,
"step": 119000
},
{
"epoch": 2.760771629894883,
"grad_norm": 0.5103738307952881,
"learning_rate": 4.714182186057597e-06,
"loss": 0.2195,
"step": 119500
},
{
"epoch": 2.7723229756266603,
"grad_norm": 0.45950281620025635,
"learning_rate": 4.689863474754746e-06,
"loss": 0.2523,
"step": 120000
},
{
"epoch": 2.7838743213584385,
"grad_norm": 0.3899378180503845,
"learning_rate": 4.665544763451896e-06,
"loss": 0.2071,
"step": 120500
},
{
"epoch": 2.795425667090216,
"grad_norm": 6.975862503051758,
"learning_rate": 4.6412260521490445e-06,
"loss": 0.2541,
"step": 121000
},
{
"epoch": 2.806977012821994,
"grad_norm": 34.19971466064453,
"learning_rate": 4.616907340846194e-06,
"loss": 0.2136,
"step": 121500
},
{
"epoch": 2.8185283585537713,
"grad_norm": 0.10601510852575302,
"learning_rate": 4.592588629543344e-06,
"loss": 0.2143,
"step": 122000
},
{
"epoch": 2.8300797042855494,
"grad_norm": 7.919482231140137,
"learning_rate": 4.5682699182404924e-06,
"loss": 0.2346,
"step": 122500
},
{
"epoch": 2.8416310500173267,
"grad_norm": 0.47603341937065125,
"learning_rate": 4.543951206937642e-06,
"loss": 0.2185,
"step": 123000
},
{
"epoch": 2.853182395749105,
"grad_norm": 26.099021911621094,
"learning_rate": 4.519632495634792e-06,
"loss": 0.2307,
"step": 123500
},
{
"epoch": 2.8647337414808827,
"grad_norm": 0.5455193519592285,
"learning_rate": 4.495313784331941e-06,
"loss": 0.2057,
"step": 124000
},
{
"epoch": 2.8762850872126604,
"grad_norm": 2.6065433025360107,
"learning_rate": 4.47099507302909e-06,
"loss": 0.2273,
"step": 124500
},
{
"epoch": 2.887836432944438,
"grad_norm": 0.44194814562797546,
"learning_rate": 4.4466763617262395e-06,
"loss": 0.2237,
"step": 125000
},
{
"epoch": 2.899387778676216,
"grad_norm": 2.659928321838379,
"learning_rate": 4.422357650423389e-06,
"loss": 0.2162,
"step": 125500
},
{
"epoch": 2.9109391244079936,
"grad_norm": 1.6970124244689941,
"learning_rate": 4.398038939120539e-06,
"loss": 0.2316,
"step": 126000
},
{
"epoch": 2.9224904701397714,
"grad_norm": 103.99176025390625,
"learning_rate": 4.3737202278176874e-06,
"loss": 0.2209,
"step": 126500
},
{
"epoch": 2.934041815871549,
"grad_norm": 0.775031328201294,
"learning_rate": 4.349401516514837e-06,
"loss": 0.2073,
"step": 127000
},
{
"epoch": 2.945593161603327,
"grad_norm": 0.6462440490722656,
"learning_rate": 4.325082805211987e-06,
"loss": 0.2185,
"step": 127500
},
{
"epoch": 2.9571445073351046,
"grad_norm": 2.127567768096924,
"learning_rate": 4.300764093909136e-06,
"loss": 0.2188,
"step": 128000
},
{
"epoch": 2.9686958530668823,
"grad_norm": 0.3134165406227112,
"learning_rate": 4.276445382606285e-06,
"loss": 0.2495,
"step": 128500
},
{
"epoch": 2.98024719879866,
"grad_norm": 0.4288942515850067,
"learning_rate": 4.2521266713034345e-06,
"loss": 0.2171,
"step": 129000
},
{
"epoch": 2.991798544530438,
"grad_norm": 51.89253234863281,
"learning_rate": 4.227807960000584e-06,
"loss": 0.1999,
"step": 129500
},
{
"epoch": 3.0,
"eval_accuracy": 0.887628508721266,
"eval_f1": 0.8962368802798873,
"eval_loss": 0.683422863483429,
"eval_matthews_correlation": 0.7825720644338475,
"eval_precision": 0.8417551592867161,
"eval_recall": 0.9582592035034898,
"eval_runtime": 541.3245,
"eval_samples_per_second": 79.961,
"eval_steps_per_second": 4.999,
"step": 129855
},
{
"epoch": 3.0033498902622155,
"grad_norm": 8.645707130432129,
"learning_rate": 4.203489248697734e-06,
"loss": 0.2205,
"step": 130000
},
{
"epoch": 3.0149012359939933,
"grad_norm": 0.025636987760663033,
"learning_rate": 4.179170537394882e-06,
"loss": 0.1589,
"step": 130500
},
{
"epoch": 3.026452581725771,
"grad_norm": 9.634745597839355,
"learning_rate": 4.154851826092032e-06,
"loss": 0.1591,
"step": 131000
},
{
"epoch": 3.0380039274575488,
"grad_norm": 0.9399522542953491,
"learning_rate": 4.130533114789182e-06,
"loss": 0.1473,
"step": 131500
},
{
"epoch": 3.0495552731893265,
"grad_norm": 0.17956668138504028,
"learning_rate": 4.106214403486331e-06,
"loss": 0.1727,
"step": 132000
},
{
"epoch": 3.0611066189211042,
"grad_norm": 36.57072067260742,
"learning_rate": 4.08189569218348e-06,
"loss": 0.1547,
"step": 132500
},
{
"epoch": 3.072657964652882,
"grad_norm": 0.30588293075561523,
"learning_rate": 4.0575769808806295e-06,
"loss": 0.1727,
"step": 133000
},
{
"epoch": 3.0842093103846597,
"grad_norm": 2.21580171585083,
"learning_rate": 4.033258269577779e-06,
"loss": 0.1519,
"step": 133500
},
{
"epoch": 3.0957606561164375,
"grad_norm": 35.42125701904297,
"learning_rate": 4.008939558274928e-06,
"loss": 0.162,
"step": 134000
},
{
"epoch": 3.107312001848215,
"grad_norm": 19.89476776123047,
"learning_rate": 3.984620846972077e-06,
"loss": 0.1489,
"step": 134500
},
{
"epoch": 3.118863347579993,
"grad_norm": 0.5846690535545349,
"learning_rate": 3.960302135669227e-06,
"loss": 0.1838,
"step": 135000
},
{
"epoch": 3.1304146933117707,
"grad_norm": 33.746910095214844,
"learning_rate": 3.935983424366377e-06,
"loss": 0.1657,
"step": 135500
},
{
"epoch": 3.1419660390435484,
"grad_norm": 0.1903204321861267,
"learning_rate": 3.911664713063525e-06,
"loss": 0.1431,
"step": 136000
},
{
"epoch": 3.153517384775326,
"grad_norm": 1.768623948097229,
"learning_rate": 3.887346001760675e-06,
"loss": 0.157,
"step": 136500
},
{
"epoch": 3.165068730507104,
"grad_norm": 9.588990211486816,
"learning_rate": 3.8630272904578245e-06,
"loss": 0.1508,
"step": 137000
},
{
"epoch": 3.1766200762388817,
"grad_norm": 0.5915334820747375,
"learning_rate": 3.838708579154974e-06,
"loss": 0.1769,
"step": 137500
},
{
"epoch": 3.1881714219706594,
"grad_norm": 8.681124687194824,
"learning_rate": 3.814389867852123e-06,
"loss": 0.1802,
"step": 138000
},
{
"epoch": 3.199722767702437,
"grad_norm": 9.283745765686035,
"learning_rate": 3.7900711565492724e-06,
"loss": 0.1584,
"step": 138500
},
{
"epoch": 3.2112741134342153,
"grad_norm": 0.6678259968757629,
"learning_rate": 3.7657524452464216e-06,
"loss": 0.1554,
"step": 139000
},
{
"epoch": 3.2228254591659926,
"grad_norm": 0.31929489970207214,
"learning_rate": 3.741433733943571e-06,
"loss": 0.1702,
"step": 139500
},
{
"epoch": 3.234376804897771,
"grad_norm": 2.6308133602142334,
"learning_rate": 3.7171150226407203e-06,
"loss": 0.1597,
"step": 140000
},
{
"epoch": 3.2459281506295485,
"grad_norm": 0.37557047605514526,
"learning_rate": 3.69279631133787e-06,
"loss": 0.1542,
"step": 140500
},
{
"epoch": 3.2574794963613263,
"grad_norm": 0.47243937849998474,
"learning_rate": 3.668477600035019e-06,
"loss": 0.1595,
"step": 141000
},
{
"epoch": 3.269030842093104,
"grad_norm": 0.026057422161102295,
"learning_rate": 3.6441588887321686e-06,
"loss": 0.1917,
"step": 141500
},
{
"epoch": 3.2805821878248818,
"grad_norm": 0.18791376054286957,
"learning_rate": 3.619840177429318e-06,
"loss": 0.1325,
"step": 142000
},
{
"epoch": 3.2921335335566595,
"grad_norm": 0.5374308824539185,
"learning_rate": 3.5955214661264674e-06,
"loss": 0.1703,
"step": 142500
},
{
"epoch": 3.3036848792884372,
"grad_norm": 0.0012748383451253176,
"learning_rate": 3.5712027548236165e-06,
"loss": 0.1509,
"step": 143000
},
{
"epoch": 3.315236225020215,
"grad_norm": 0.19805267453193665,
"learning_rate": 3.5468840435207657e-06,
"loss": 0.1437,
"step": 143500
},
{
"epoch": 3.3267875707519927,
"grad_norm": 15.450338363647461,
"learning_rate": 3.5225653322179153e-06,
"loss": 0.1741,
"step": 144000
},
{
"epoch": 3.3383389164837705,
"grad_norm": 0.3308798670768738,
"learning_rate": 3.4982466209150645e-06,
"loss": 0.1392,
"step": 144500
},
{
"epoch": 3.349890262215548,
"grad_norm": 21.04158592224121,
"learning_rate": 3.473927909612214e-06,
"loss": 0.1704,
"step": 145000
},
{
"epoch": 3.361441607947326,
"grad_norm": 8.919427871704102,
"learning_rate": 3.449609198309363e-06,
"loss": 0.158,
"step": 145500
},
{
"epoch": 3.3729929536791037,
"grad_norm": 0.04234965518116951,
"learning_rate": 3.425290487006513e-06,
"loss": 0.1676,
"step": 146000
},
{
"epoch": 3.3845442994108814,
"grad_norm": 0.7735577821731567,
"learning_rate": 3.400971775703662e-06,
"loss": 0.1717,
"step": 146500
},
{
"epoch": 3.396095645142659,
"grad_norm": 0.0031218251679092646,
"learning_rate": 3.3766530644008115e-06,
"loss": 0.1852,
"step": 147000
},
{
"epoch": 3.407646990874437,
"grad_norm": 0.2701342701911926,
"learning_rate": 3.3523343530979607e-06,
"loss": 0.178,
"step": 147500
},
{
"epoch": 3.4191983366062146,
"grad_norm": 14.016953468322754,
"learning_rate": 3.3280156417951103e-06,
"loss": 0.1832,
"step": 148000
},
{
"epoch": 3.4307496823379924,
"grad_norm": 0.002833212958648801,
"learning_rate": 3.3036969304922594e-06,
"loss": 0.1431,
"step": 148500
},
{
"epoch": 3.44230102806977,
"grad_norm": 0.38238525390625,
"learning_rate": 3.279378219189409e-06,
"loss": 0.1736,
"step": 149000
},
{
"epoch": 3.453852373801548,
"grad_norm": 0.019360702484846115,
"learning_rate": 3.255059507886558e-06,
"loss": 0.1589,
"step": 149500
},
{
"epoch": 3.4654037195333256,
"grad_norm": 316.6242370605469,
"learning_rate": 3.2307407965837078e-06,
"loss": 0.1813,
"step": 150000
},
{
"epoch": 3.4769550652651033,
"grad_norm": 0.6166911125183105,
"learning_rate": 3.206422085280857e-06,
"loss": 0.1562,
"step": 150500
},
{
"epoch": 3.488506410996881,
"grad_norm": 0.12754186987876892,
"learning_rate": 3.1821033739780065e-06,
"loss": 0.1826,
"step": 151000
},
{
"epoch": 3.500057756728659,
"grad_norm": 1.4088376760482788,
"learning_rate": 3.1577846626751557e-06,
"loss": 0.1751,
"step": 151500
},
{
"epoch": 3.5116091024604366,
"grad_norm": 0.6573951840400696,
"learning_rate": 3.1334659513723053e-06,
"loss": 0.1612,
"step": 152000
},
{
"epoch": 3.5231604481922143,
"grad_norm": 0.6012342572212219,
"learning_rate": 3.1091472400694544e-06,
"loss": 0.1734,
"step": 152500
},
{
"epoch": 3.534711793923992,
"grad_norm": 0.6947406530380249,
"learning_rate": 3.084828528766604e-06,
"loss": 0.1574,
"step": 153000
},
{
"epoch": 3.54626313965577,
"grad_norm": 0.49752572178840637,
"learning_rate": 3.060509817463753e-06,
"loss": 0.142,
"step": 153500
},
{
"epoch": 3.5578144853875475,
"grad_norm": 0.6474779844284058,
"learning_rate": 3.0361911061609028e-06,
"loss": 0.1511,
"step": 154000
},
{
"epoch": 3.5693658311193253,
"grad_norm": 1.3100844621658325,
"learning_rate": 3.011872394858052e-06,
"loss": 0.1652,
"step": 154500
},
{
"epoch": 3.580917176851103,
"grad_norm": 0.9856226444244385,
"learning_rate": 2.987553683555201e-06,
"loss": 0.1884,
"step": 155000
},
{
"epoch": 3.5924685225828807,
"grad_norm": 73.24075317382812,
"learning_rate": 2.9632349722523507e-06,
"loss": 0.1629,
"step": 155500
},
{
"epoch": 3.6040198683146585,
"grad_norm": 8.039386749267578,
"learning_rate": 2.9389162609495e-06,
"loss": 0.1628,
"step": 156000
},
{
"epoch": 3.6155712140464367,
"grad_norm": 0.0022829582449048758,
"learning_rate": 2.9145975496466494e-06,
"loss": 0.1532,
"step": 156500
},
{
"epoch": 3.627122559778214,
"grad_norm": 0.43138188123703003,
"learning_rate": 2.8902788383437986e-06,
"loss": 0.1711,
"step": 157000
},
{
"epoch": 3.638673905509992,
"grad_norm": 7.881419658660889,
"learning_rate": 2.865960127040948e-06,
"loss": 0.155,
"step": 157500
},
{
"epoch": 3.6502252512417694,
"grad_norm": 117.18584442138672,
"learning_rate": 2.8416414157380973e-06,
"loss": 0.155,
"step": 158000
},
{
"epoch": 3.6617765969735476,
"grad_norm": 0.0010274089872837067,
"learning_rate": 2.817322704435247e-06,
"loss": 0.1717,
"step": 158500
},
{
"epoch": 3.673327942705325,
"grad_norm": 109.89828491210938,
"learning_rate": 2.793003993132396e-06,
"loss": 0.1608,
"step": 159000
},
{
"epoch": 3.684879288437103,
"grad_norm": 0.7722026109695435,
"learning_rate": 2.7686852818295457e-06,
"loss": 0.1789,
"step": 159500
},
{
"epoch": 3.6964306341688804,
"grad_norm": 0.0013100790092721581,
"learning_rate": 2.744366570526695e-06,
"loss": 0.1601,
"step": 160000
},
{
"epoch": 3.7079819799006586,
"grad_norm": 0.25156673789024353,
"learning_rate": 2.7200478592238444e-06,
"loss": 0.1588,
"step": 160500
},
{
"epoch": 3.7195333256324363,
"grad_norm": 0.18242871761322021,
"learning_rate": 2.6957291479209936e-06,
"loss": 0.1626,
"step": 161000
},
{
"epoch": 3.731084671364214,
"grad_norm": 0.008753698319196701,
"learning_rate": 2.671410436618143e-06,
"loss": 0.1654,
"step": 161500
},
{
"epoch": 3.742636017095992,
"grad_norm": 0.6226741671562195,
"learning_rate": 2.6470917253152923e-06,
"loss": 0.174,
"step": 162000
},
{
"epoch": 3.7541873628277695,
"grad_norm": 12.760992050170898,
"learning_rate": 2.622773014012442e-06,
"loss": 0.1656,
"step": 162500
},
{
"epoch": 3.7657387085595473,
"grad_norm": 16.012075424194336,
"learning_rate": 2.598454302709591e-06,
"loss": 0.15,
"step": 163000
},
{
"epoch": 3.777290054291325,
"grad_norm": 7.900235652923584,
"learning_rate": 2.5741355914067407e-06,
"loss": 0.1705,
"step": 163500
},
{
"epoch": 3.7888414000231028,
"grad_norm": 2.0820932388305664,
"learning_rate": 2.54981688010389e-06,
"loss": 0.1752,
"step": 164000
},
{
"epoch": 3.8003927457548805,
"grad_norm": 1.189961552619934,
"learning_rate": 2.5254981688010394e-06,
"loss": 0.1578,
"step": 164500
},
{
"epoch": 3.8119440914866582,
"grad_norm": 0.005685470532625914,
"learning_rate": 2.5011794574981886e-06,
"loss": 0.147,
"step": 165000
},
{
"epoch": 3.823495437218436,
"grad_norm": 0.33695000410079956,
"learning_rate": 2.4768607461953377e-06,
"loss": 0.1835,
"step": 165500
},
{
"epoch": 3.8350467829502137,
"grad_norm": 18.306541442871094,
"learning_rate": 2.4525420348924873e-06,
"loss": 0.1963,
"step": 166000
},
{
"epoch": 3.8465981286819915,
"grad_norm": 0.6380665302276611,
"learning_rate": 2.4282233235896365e-06,
"loss": 0.1696,
"step": 166500
},
{
"epoch": 3.858149474413769,
"grad_norm": 0.31257039308547974,
"learning_rate": 2.403904612286786e-06,
"loss": 0.166,
"step": 167000
},
{
"epoch": 3.869700820145547,
"grad_norm": 0.09384506940841675,
"learning_rate": 2.3795859009839352e-06,
"loss": 0.1734,
"step": 167500
},
{
"epoch": 3.8812521658773247,
"grad_norm": 0.12250012159347534,
"learning_rate": 2.355267189681085e-06,
"loss": 0.1705,
"step": 168000
},
{
"epoch": 3.8928035116091024,
"grad_norm": 0.3609682619571686,
"learning_rate": 2.330948478378234e-06,
"loss": 0.1548,
"step": 168500
},
{
"epoch": 3.90435485734088,
"grad_norm": 9.560044288635254,
"learning_rate": 2.3066297670753836e-06,
"loss": 0.1468,
"step": 169000
},
{
"epoch": 3.915906203072658,
"grad_norm": 1.053947925567627,
"learning_rate": 2.2823110557725327e-06,
"loss": 0.1686,
"step": 169500
},
{
"epoch": 3.9274575488044356,
"grad_norm": 0.032445378601551056,
"learning_rate": 2.2579923444696823e-06,
"loss": 0.1487,
"step": 170000
},
{
"epoch": 3.9390088945362134,
"grad_norm": 8.668307304382324,
"learning_rate": 2.2336736331668315e-06,
"loss": 0.1791,
"step": 170500
},
{
"epoch": 3.950560240267991,
"grad_norm": 9.52789306640625,
"learning_rate": 2.2093549218639806e-06,
"loss": 0.1841,
"step": 171000
},
{
"epoch": 3.962111585999769,
"grad_norm": 0.011110074818134308,
"learning_rate": 2.18503621056113e-06,
"loss": 0.1625,
"step": 171500
},
{
"epoch": 3.9736629317315466,
"grad_norm": 82.39501190185547,
"learning_rate": 2.1607174992582794e-06,
"loss": 0.1714,
"step": 172000
},
{
"epoch": 3.9852142774633244,
"grad_norm": 1.0335499048233032,
"learning_rate": 2.136398787955429e-06,
"loss": 0.15,
"step": 172500
},
{
"epoch": 3.996765623195102,
"grad_norm": 2.844334363937378,
"learning_rate": 2.112080076652578e-06,
"loss": 0.1628,
"step": 173000
},
{
"epoch": 4.0,
"eval_accuracy": 0.8855723691810096,
"eval_f1": 0.895216738242823,
"eval_loss": 0.9363193511962891,
"eval_matthews_correlation": 0.7805306223945409,
"eval_precision": 0.8347009626005997,
"eval_recall": 0.9651931937411614,
"eval_runtime": 550.7934,
"eval_samples_per_second": 78.587,
"eval_steps_per_second": 4.913,
"step": 173140
}
],
"logging_steps": 500,
"max_steps": 216425,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.851751926497198e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}