nodule-AI / checkpoint-86570 /trainer_state.json
lhui2010's picture
Upload folder using huggingface_hub
30076c7 verified
{
"best_metric": 0.883420247381804,
"best_model_checkpoint": "finetune/models/plant-dnamamba-BPE-NoduleExpDup/checkpoint-86570",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 86570,
"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
}
],
"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": 1.925875963248599e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}