MattyB95's picture
End of training
8902e6e verified
{
"best_metric": 0.9663852453231812,
"best_model_checkpoint": "../res/Transformers/VIT-ASVspoof5-Mel_Spectrogram-Synthetic-Voice-Detection\\checkpoint-22795",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 68385,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.021934634788330774,
"grad_norm": 0.34741124510765076,
"learning_rate": 4.963442275352782e-05,
"loss": 0.1315,
"step": 500
},
{
"epoch": 0.04386926957666155,
"grad_norm": 0.0708213597536087,
"learning_rate": 4.926884550705564e-05,
"loss": 0.074,
"step": 1000
},
{
"epoch": 0.06580390436499232,
"grad_norm": 0.017688876017928123,
"learning_rate": 4.890326826058346e-05,
"loss": 0.0627,
"step": 1500
},
{
"epoch": 0.0877385391533231,
"grad_norm": 0.009881118312478065,
"learning_rate": 4.853769101411129e-05,
"loss": 0.054,
"step": 2000
},
{
"epoch": 0.10967317394165386,
"grad_norm": 0.017528673633933067,
"learning_rate": 4.817211376763911e-05,
"loss": 0.0529,
"step": 2500
},
{
"epoch": 0.13160780872998465,
"grad_norm": 0.05024711415171623,
"learning_rate": 4.780653652116692e-05,
"loss": 0.0436,
"step": 3000
},
{
"epoch": 0.15354244351831542,
"grad_norm": 0.0056371367536485195,
"learning_rate": 4.7440959274694746e-05,
"loss": 0.0478,
"step": 3500
},
{
"epoch": 0.1754770783066462,
"grad_norm": 0.0035752628464251757,
"learning_rate": 4.7075382028222566e-05,
"loss": 0.0304,
"step": 4000
},
{
"epoch": 0.19741171309497696,
"grad_norm": 0.006441359408199787,
"learning_rate": 4.6709804781750386e-05,
"loss": 0.0379,
"step": 4500
},
{
"epoch": 0.21934634788330773,
"grad_norm": 0.0028403999749571085,
"learning_rate": 4.6344227535278205e-05,
"loss": 0.0359,
"step": 5000
},
{
"epoch": 0.24128098267163853,
"grad_norm": 0.003119397209957242,
"learning_rate": 4.5978650288806025e-05,
"loss": 0.0242,
"step": 5500
},
{
"epoch": 0.2632156174599693,
"grad_norm": 0.006989920046180487,
"learning_rate": 4.561307304233385e-05,
"loss": 0.0352,
"step": 6000
},
{
"epoch": 0.28515025224830004,
"grad_norm": 0.054010841995477676,
"learning_rate": 4.5247495795861664e-05,
"loss": 0.029,
"step": 6500
},
{
"epoch": 0.30708488703663084,
"grad_norm": 0.002598833991214633,
"learning_rate": 4.488191854938949e-05,
"loss": 0.0292,
"step": 7000
},
{
"epoch": 0.32901952182496164,
"grad_norm": 0.0669151097536087,
"learning_rate": 4.451634130291731e-05,
"loss": 0.0316,
"step": 7500
},
{
"epoch": 0.3509541566132924,
"grad_norm": 0.03422193601727486,
"learning_rate": 4.415076405644513e-05,
"loss": 0.0219,
"step": 8000
},
{
"epoch": 0.3728887914016232,
"grad_norm": 0.0012628569966182113,
"learning_rate": 4.378518680997295e-05,
"loss": 0.0266,
"step": 8500
},
{
"epoch": 0.3948234261899539,
"grad_norm": 0.04995453730225563,
"learning_rate": 4.341960956350077e-05,
"loss": 0.0255,
"step": 9000
},
{
"epoch": 0.4167580609782847,
"grad_norm": 0.0008714247378520668,
"learning_rate": 4.3054032317028595e-05,
"loss": 0.0259,
"step": 9500
},
{
"epoch": 0.43869269576661546,
"grad_norm": 0.002895859070122242,
"learning_rate": 4.268845507055641e-05,
"loss": 0.0279,
"step": 10000
},
{
"epoch": 0.46062733055494626,
"grad_norm": 0.002743455581367016,
"learning_rate": 4.232287782408423e-05,
"loss": 0.0176,
"step": 10500
},
{
"epoch": 0.48256196534327706,
"grad_norm": 0.0018967551877722144,
"learning_rate": 4.1957300577612054e-05,
"loss": 0.0167,
"step": 11000
},
{
"epoch": 0.5044966001316078,
"grad_norm": 0.08448649197816849,
"learning_rate": 4.159172333113987e-05,
"loss": 0.0178,
"step": 11500
},
{
"epoch": 0.5264312349199386,
"grad_norm": 0.001365090487524867,
"learning_rate": 4.122614608466769e-05,
"loss": 0.0169,
"step": 12000
},
{
"epoch": 0.5483658697082694,
"grad_norm": 0.0005711843841709197,
"learning_rate": 4.086056883819551e-05,
"loss": 0.018,
"step": 12500
},
{
"epoch": 0.5703005044966001,
"grad_norm": 0.0006833109073340893,
"learning_rate": 4.049499159172334e-05,
"loss": 0.0173,
"step": 13000
},
{
"epoch": 0.5922351392849309,
"grad_norm": 0.0005675885477103293,
"learning_rate": 4.012941434525115e-05,
"loss": 0.0222,
"step": 13500
},
{
"epoch": 0.6141697740732617,
"grad_norm": 0.02867540344595909,
"learning_rate": 3.976383709877897e-05,
"loss": 0.0221,
"step": 14000
},
{
"epoch": 0.6361044088615925,
"grad_norm": 0.0008733811555430293,
"learning_rate": 3.93982598523068e-05,
"loss": 0.0128,
"step": 14500
},
{
"epoch": 0.6580390436499233,
"grad_norm": 0.0015775271458551288,
"learning_rate": 3.903268260583462e-05,
"loss": 0.0209,
"step": 15000
},
{
"epoch": 0.679973678438254,
"grad_norm": 0.0007889546104706824,
"learning_rate": 3.866710535936244e-05,
"loss": 0.0143,
"step": 15500
},
{
"epoch": 0.7019083132265848,
"grad_norm": 0.005065426230430603,
"learning_rate": 3.8301528112890256e-05,
"loss": 0.0142,
"step": 16000
},
{
"epoch": 0.7238429480149156,
"grad_norm": 0.0019233387429267168,
"learning_rate": 3.7935950866418076e-05,
"loss": 0.0167,
"step": 16500
},
{
"epoch": 0.7457775828032464,
"grad_norm": 0.004881173837929964,
"learning_rate": 3.7570373619945896e-05,
"loss": 0.0182,
"step": 17000
},
{
"epoch": 0.7677122175915772,
"grad_norm": 0.004554756451398134,
"learning_rate": 3.7204796373473715e-05,
"loss": 0.0164,
"step": 17500
},
{
"epoch": 0.7896468523799078,
"grad_norm": 0.0010554809123277664,
"learning_rate": 3.683921912700154e-05,
"loss": 0.015,
"step": 18000
},
{
"epoch": 0.8115814871682386,
"grad_norm": 0.0011578754056245089,
"learning_rate": 3.6473641880529354e-05,
"loss": 0.0137,
"step": 18500
},
{
"epoch": 0.8335161219565694,
"grad_norm": 0.0028496412560343742,
"learning_rate": 3.6108064634057174e-05,
"loss": 0.0128,
"step": 19000
},
{
"epoch": 0.8554507567449002,
"grad_norm": 0.0005675283609889448,
"learning_rate": 3.5742487387585e-05,
"loss": 0.0079,
"step": 19500
},
{
"epoch": 0.8773853915332309,
"grad_norm": 0.000873275741469115,
"learning_rate": 3.537691014111282e-05,
"loss": 0.0133,
"step": 20000
},
{
"epoch": 0.8993200263215617,
"grad_norm": 0.002682998776435852,
"learning_rate": 3.501133289464064e-05,
"loss": 0.0176,
"step": 20500
},
{
"epoch": 0.9212546611098925,
"grad_norm": 0.00047966442070901394,
"learning_rate": 3.464575564816846e-05,
"loss": 0.0034,
"step": 21000
},
{
"epoch": 0.9431892958982233,
"grad_norm": 0.00044119294034317136,
"learning_rate": 3.428017840169628e-05,
"loss": 0.0081,
"step": 21500
},
{
"epoch": 0.9651239306865541,
"grad_norm": 0.0005569157656282187,
"learning_rate": 3.39146011552241e-05,
"loss": 0.0164,
"step": 22000
},
{
"epoch": 0.9870585654748848,
"grad_norm": 0.0005497235688380897,
"learning_rate": 3.354902390875192e-05,
"loss": 0.0047,
"step": 22500
},
{
"epoch": 1.0,
"eval_accuracy": 0.8372543455125931,
"eval_f1": 0.8919393816628117,
"eval_loss": 0.9663852453231812,
"eval_precision": 0.9221433233005075,
"eval_recall": 0.8636512917822216,
"eval_runtime": 782.1941,
"eval_samples_per_second": 180.198,
"eval_steps_per_second": 22.525,
"step": 22795
},
{
"epoch": 1.0089932002632156,
"grad_norm": 0.0004964213585481048,
"learning_rate": 3.3183446662279744e-05,
"loss": 0.017,
"step": 23000
},
{
"epoch": 1.0309278350515463,
"grad_norm": 0.0005278219468891621,
"learning_rate": 3.2817869415807564e-05,
"loss": 0.0042,
"step": 23500
},
{
"epoch": 1.0528624698398772,
"grad_norm": 0.0016331393271684647,
"learning_rate": 3.245229216933538e-05,
"loss": 0.007,
"step": 24000
},
{
"epoch": 1.0747971046282079,
"grad_norm": 0.00023824520758353174,
"learning_rate": 3.20867149228632e-05,
"loss": 0.0027,
"step": 24500
},
{
"epoch": 1.0967317394165388,
"grad_norm": 0.00027841408154927194,
"learning_rate": 3.172113767639102e-05,
"loss": 0.0166,
"step": 25000
},
{
"epoch": 1.1186663742048695,
"grad_norm": 0.00036192481638863683,
"learning_rate": 3.135556042991884e-05,
"loss": 0.0075,
"step": 25500
},
{
"epoch": 1.1406010089932002,
"grad_norm": 0.0002430744789307937,
"learning_rate": 3.098998318344666e-05,
"loss": 0.0119,
"step": 26000
},
{
"epoch": 1.162535643781531,
"grad_norm": 0.0004526956763584167,
"learning_rate": 3.062440593697448e-05,
"loss": 0.0137,
"step": 26500
},
{
"epoch": 1.1844702785698618,
"grad_norm": 0.10140929371118546,
"learning_rate": 3.0258828690502304e-05,
"loss": 0.0093,
"step": 27000
},
{
"epoch": 1.2064049133581927,
"grad_norm": 0.00041032847366295755,
"learning_rate": 2.9893251444030124e-05,
"loss": 0.0053,
"step": 27500
},
{
"epoch": 1.2283395481465234,
"grad_norm": 0.0003452656092122197,
"learning_rate": 2.9527674197557947e-05,
"loss": 0.0076,
"step": 28000
},
{
"epoch": 1.250274182934854,
"grad_norm": 0.0002765257377177477,
"learning_rate": 2.9162096951085767e-05,
"loss": 0.0049,
"step": 28500
},
{
"epoch": 1.272208817723185,
"grad_norm": 0.00047475536121055484,
"learning_rate": 2.8796519704613583e-05,
"loss": 0.0114,
"step": 29000
},
{
"epoch": 1.2941434525115156,
"grad_norm": 0.0001869210391305387,
"learning_rate": 2.8430942458141406e-05,
"loss": 0.0053,
"step": 29500
},
{
"epoch": 1.3160780872998465,
"grad_norm": 0.0001772296818671748,
"learning_rate": 2.8065365211669225e-05,
"loss": 0.0026,
"step": 30000
},
{
"epoch": 1.3380127220881772,
"grad_norm": 0.0003674278559628874,
"learning_rate": 2.769978796519705e-05,
"loss": 0.003,
"step": 30500
},
{
"epoch": 1.359947356876508,
"grad_norm": 0.0005148735363036394,
"learning_rate": 2.7334210718724868e-05,
"loss": 0.0089,
"step": 31000
},
{
"epoch": 1.3818819916648388,
"grad_norm": 0.00596097856760025,
"learning_rate": 2.6968633472252684e-05,
"loss": 0.0074,
"step": 31500
},
{
"epoch": 1.4038166264531695,
"grad_norm": 0.009417912922799587,
"learning_rate": 2.660305622578051e-05,
"loss": 0.0065,
"step": 32000
},
{
"epoch": 1.4257512612415004,
"grad_norm": 0.0004612387565430254,
"learning_rate": 2.6237478979308327e-05,
"loss": 0.0054,
"step": 32500
},
{
"epoch": 1.447685896029831,
"grad_norm": 0.000312151329126209,
"learning_rate": 2.587190173283615e-05,
"loss": 0.0013,
"step": 33000
},
{
"epoch": 1.4696205308181618,
"grad_norm": 0.00043960358016192913,
"learning_rate": 2.550632448636397e-05,
"loss": 0.0081,
"step": 33500
},
{
"epoch": 1.4915551656064927,
"grad_norm": 0.00014296828885562718,
"learning_rate": 2.514074723989179e-05,
"loss": 0.0012,
"step": 34000
},
{
"epoch": 1.5134898003948234,
"grad_norm": 0.00014170966460369527,
"learning_rate": 2.4775169993419612e-05,
"loss": 0.0067,
"step": 34500
},
{
"epoch": 1.5354244351831543,
"grad_norm": 0.00012841432180721313,
"learning_rate": 2.440959274694743e-05,
"loss": 0.0021,
"step": 35000
},
{
"epoch": 1.557359069971485,
"grad_norm": 0.00016817337018437684,
"learning_rate": 2.404401550047525e-05,
"loss": 0.0103,
"step": 35500
},
{
"epoch": 1.5792937047598157,
"grad_norm": 0.00028819849831052125,
"learning_rate": 2.367843825400307e-05,
"loss": 0.0055,
"step": 36000
},
{
"epoch": 1.6012283395481464,
"grad_norm": 0.00032831408316269517,
"learning_rate": 2.3312861007530894e-05,
"loss": 0.0049,
"step": 36500
},
{
"epoch": 1.6231629743364773,
"grad_norm": 0.0003929148952011019,
"learning_rate": 2.2947283761058713e-05,
"loss": 0.011,
"step": 37000
},
{
"epoch": 1.6450976091248082,
"grad_norm": 0.015144962817430496,
"learning_rate": 2.2581706514586533e-05,
"loss": 0.0009,
"step": 37500
},
{
"epoch": 1.6670322439131389,
"grad_norm": 0.0004016929306089878,
"learning_rate": 2.2216129268114352e-05,
"loss": 0.0039,
"step": 38000
},
{
"epoch": 1.6889668787014696,
"grad_norm": 0.0003622666699811816,
"learning_rate": 2.1850552021642172e-05,
"loss": 0.011,
"step": 38500
},
{
"epoch": 1.7109015134898002,
"grad_norm": 0.00015891093062236905,
"learning_rate": 2.1484974775169995e-05,
"loss": 0.0039,
"step": 39000
},
{
"epoch": 1.7328361482781311,
"grad_norm": 2.2137434482574463,
"learning_rate": 2.1119397528697815e-05,
"loss": 0.0064,
"step": 39500
},
{
"epoch": 1.754770783066462,
"grad_norm": 0.01450470369309187,
"learning_rate": 2.0753820282225638e-05,
"loss": 0.0019,
"step": 40000
},
{
"epoch": 1.7767054178547927,
"grad_norm": 0.0001268786145374179,
"learning_rate": 2.0388243035753457e-05,
"loss": 0.006,
"step": 40500
},
{
"epoch": 1.7986400526431234,
"grad_norm": 0.00022799715225119144,
"learning_rate": 2.0022665789281277e-05,
"loss": 0.0,
"step": 41000
},
{
"epoch": 1.8205746874314541,
"grad_norm": 0.0007139018853195012,
"learning_rate": 1.9657088542809096e-05,
"loss": 0.0105,
"step": 41500
},
{
"epoch": 1.842509322219785,
"grad_norm": 0.000262285815551877,
"learning_rate": 1.9291511296336916e-05,
"loss": 0.0002,
"step": 42000
},
{
"epoch": 1.864443957008116,
"grad_norm": 9.916254930431023e-05,
"learning_rate": 1.892593404986474e-05,
"loss": 0.0034,
"step": 42500
},
{
"epoch": 1.8863785917964466,
"grad_norm": 0.00010086688416777179,
"learning_rate": 1.856035680339256e-05,
"loss": 0.0103,
"step": 43000
},
{
"epoch": 1.9083132265847773,
"grad_norm": 0.0003273077018093318,
"learning_rate": 1.8194779556920378e-05,
"loss": 0.0043,
"step": 43500
},
{
"epoch": 1.930247861373108,
"grad_norm": 0.0004520936054177582,
"learning_rate": 1.7829202310448198e-05,
"loss": 0.0012,
"step": 44000
},
{
"epoch": 1.952182496161439,
"grad_norm": 0.00017915925127454102,
"learning_rate": 1.7463625063976017e-05,
"loss": 0.0027,
"step": 44500
},
{
"epoch": 1.9741171309497698,
"grad_norm": 8.093972428468987e-05,
"learning_rate": 1.709804781750384e-05,
"loss": 0.0,
"step": 45000
},
{
"epoch": 1.9960517657381005,
"grad_norm": 0.00023188079649116844,
"learning_rate": 1.673247057103166e-05,
"loss": 0.0064,
"step": 45500
},
{
"epoch": 2.0,
"eval_accuracy": 0.7830365377793543,
"eval_f1": 0.8420981974585766,
"eval_loss": 1.6013481616973877,
"eval_precision": 0.9701385997263696,
"eval_recall": 0.7439151218800175,
"eval_runtime": 713.4707,
"eval_samples_per_second": 197.555,
"eval_steps_per_second": 24.695,
"step": 45590
},
{
"epoch": 2.017986400526431,
"grad_norm": 0.00013298647536430508,
"learning_rate": 1.636689332455948e-05,
"loss": 0.0,
"step": 46000
},
{
"epoch": 2.039921035314762,
"grad_norm": 0.002622125670313835,
"learning_rate": 1.60013160780873e-05,
"loss": 0.0049,
"step": 46500
},
{
"epoch": 2.0618556701030926,
"grad_norm": 0.0016739132115617394,
"learning_rate": 1.5635738831615122e-05,
"loss": 0.0033,
"step": 47000
},
{
"epoch": 2.0837903048914237,
"grad_norm": 7.326369086513296e-05,
"learning_rate": 1.5270161585142942e-05,
"loss": 0.0,
"step": 47500
},
{
"epoch": 2.1057249396797544,
"grad_norm": 7.18442679499276e-05,
"learning_rate": 1.4904584338670763e-05,
"loss": 0.0016,
"step": 48000
},
{
"epoch": 2.127659574468085,
"grad_norm": 0.00014385154645424336,
"learning_rate": 1.4539007092198581e-05,
"loss": 0.0,
"step": 48500
},
{
"epoch": 2.1495942092564158,
"grad_norm": 0.00024707347620278597,
"learning_rate": 1.4173429845726402e-05,
"loss": 0.0,
"step": 49000
},
{
"epoch": 2.1715288440447464,
"grad_norm": 0.00010678445687517524,
"learning_rate": 1.3807852599254223e-05,
"loss": 0.0,
"step": 49500
},
{
"epoch": 2.1934634788330776,
"grad_norm": 5.570024222834036e-05,
"learning_rate": 1.3442275352782043e-05,
"loss": 0.0,
"step": 50000
},
{
"epoch": 2.2153981136214083,
"grad_norm": 0.03718312457203865,
"learning_rate": 1.3076698106309864e-05,
"loss": 0.0106,
"step": 50500
},
{
"epoch": 2.237332748409739,
"grad_norm": 5.917974704061635e-05,
"learning_rate": 1.2711120859837682e-05,
"loss": 0.0001,
"step": 51000
},
{
"epoch": 2.2592673831980696,
"grad_norm": 8.80313673405908e-05,
"learning_rate": 1.2345543613365505e-05,
"loss": 0.0,
"step": 51500
},
{
"epoch": 2.2812020179864003,
"grad_norm": 8.454511407762766e-05,
"learning_rate": 1.1979966366893325e-05,
"loss": 0.0,
"step": 52000
},
{
"epoch": 2.3031366527747315,
"grad_norm": 4.547155913314782e-05,
"learning_rate": 1.1614389120421146e-05,
"loss": 0.0013,
"step": 52500
},
{
"epoch": 2.325071287563062,
"grad_norm": 9.757141378941014e-05,
"learning_rate": 1.1248811873948966e-05,
"loss": 0.0,
"step": 53000
},
{
"epoch": 2.347005922351393,
"grad_norm": 6.546088116010651e-05,
"learning_rate": 1.0883234627476787e-05,
"loss": 0.0026,
"step": 53500
},
{
"epoch": 2.3689405571397235,
"grad_norm": 3.695198756759055e-05,
"learning_rate": 1.0517657381004607e-05,
"loss": 0.0012,
"step": 54000
},
{
"epoch": 2.390875191928054,
"grad_norm": 3.3266915124841034e-05,
"learning_rate": 1.0152080134532426e-05,
"loss": 0.0,
"step": 54500
},
{
"epoch": 2.4128098267163853,
"grad_norm": 3.605923484428786e-05,
"learning_rate": 9.786502888060247e-06,
"loss": 0.0048,
"step": 55000
},
{
"epoch": 2.434744461504716,
"grad_norm": 8.535337110515684e-05,
"learning_rate": 9.420925641588069e-06,
"loss": 0.0028,
"step": 55500
},
{
"epoch": 2.4566790962930467,
"grad_norm": 7.798920705681667e-05,
"learning_rate": 9.055348395115888e-06,
"loss": 0.0011,
"step": 56000
},
{
"epoch": 2.4786137310813774,
"grad_norm": 3.1817657145438716e-05,
"learning_rate": 8.68977114864371e-06,
"loss": 0.0016,
"step": 56500
},
{
"epoch": 2.500548365869708,
"grad_norm": 3.148000905639492e-05,
"learning_rate": 8.32419390217153e-06,
"loss": 0.0,
"step": 57000
},
{
"epoch": 2.522483000658039,
"grad_norm": 0.21145348250865936,
"learning_rate": 7.95861665569935e-06,
"loss": 0.0035,
"step": 57500
},
{
"epoch": 2.54441763544637,
"grad_norm": 4.887134491582401e-05,
"learning_rate": 7.593039409227171e-06,
"loss": 0.0006,
"step": 58000
},
{
"epoch": 2.5663522702347006,
"grad_norm": 2.885399771912489e-05,
"learning_rate": 7.2274621627549905e-06,
"loss": 0.0025,
"step": 58500
},
{
"epoch": 2.5882869050230313,
"grad_norm": 2.8404225304257125e-05,
"learning_rate": 6.861884916282811e-06,
"loss": 0.001,
"step": 59000
},
{
"epoch": 2.610221539811362,
"grad_norm": 6.570501864189282e-05,
"learning_rate": 6.496307669810631e-06,
"loss": 0.0,
"step": 59500
},
{
"epoch": 2.632156174599693,
"grad_norm": 4.453480869415216e-05,
"learning_rate": 6.130730423338452e-06,
"loss": 0.0,
"step": 60000
},
{
"epoch": 2.6540908093880238,
"grad_norm": 4.257899854565039e-05,
"learning_rate": 5.7651531768662715e-06,
"loss": 0.0,
"step": 60500
},
{
"epoch": 2.6760254441763545,
"grad_norm": 4.08503801736515e-05,
"learning_rate": 5.399575930394093e-06,
"loss": 0.0012,
"step": 61000
},
{
"epoch": 2.697960078964685,
"grad_norm": 2.521094575058669e-05,
"learning_rate": 5.033998683921913e-06,
"loss": 0.0001,
"step": 61500
},
{
"epoch": 2.719894713753016,
"grad_norm": 5.6092027080012485e-05,
"learning_rate": 4.668421437449734e-06,
"loss": 0.0011,
"step": 62000
},
{
"epoch": 2.741829348541347,
"grad_norm": 3.7315894587663934e-05,
"learning_rate": 4.302844190977553e-06,
"loss": 0.0,
"step": 62500
},
{
"epoch": 2.7637639833296777,
"grad_norm": 3.713283149409108e-05,
"learning_rate": 3.9372669445053745e-06,
"loss": 0.0,
"step": 63000
},
{
"epoch": 2.7856986181180083,
"grad_norm": 3.7352405342971906e-05,
"learning_rate": 3.5716896980331945e-06,
"loss": 0.0028,
"step": 63500
},
{
"epoch": 2.807633252906339,
"grad_norm": 2.116698851750698e-05,
"learning_rate": 3.206112451561015e-06,
"loss": 0.0,
"step": 64000
},
{
"epoch": 2.8295678876946697,
"grad_norm": 2.0813607989111915e-05,
"learning_rate": 2.8405352050888354e-06,
"loss": 0.0,
"step": 64500
},
{
"epoch": 2.851502522483001,
"grad_norm": 2.0640662114601582e-05,
"learning_rate": 2.474957958616656e-06,
"loss": 0.0018,
"step": 65000
},
{
"epoch": 2.8734371572713315,
"grad_norm": 4.867030293098651e-05,
"learning_rate": 2.109380712144476e-06,
"loss": 0.0,
"step": 65500
},
{
"epoch": 2.895371792059662,
"grad_norm": 3.334460052428767e-05,
"learning_rate": 1.7438034656722967e-06,
"loss": 0.0,
"step": 66000
},
{
"epoch": 2.917306426847993,
"grad_norm": 4.7563084081048146e-05,
"learning_rate": 1.3782262192001172e-06,
"loss": 0.0,
"step": 66500
},
{
"epoch": 2.9392410616363236,
"grad_norm": 1.908742342493497e-05,
"learning_rate": 1.0126489727279376e-06,
"loss": 0.0,
"step": 67000
},
{
"epoch": 2.9611756964246547,
"grad_norm": 3.217206904082559e-05,
"learning_rate": 6.470717262557578e-07,
"loss": 0.0,
"step": 67500
},
{
"epoch": 2.9831103312129854,
"grad_norm": 4.605944195645861e-05,
"learning_rate": 2.814944797835783e-07,
"loss": 0.0,
"step": 68000
},
{
"epoch": 3.0,
"eval_accuracy": 0.7633416105001773,
"eval_f1": 0.8263822744093812,
"eval_loss": 2.0727663040161133,
"eval_precision": 0.9621029413546957,
"eval_recall": 0.7242190921033426,
"eval_runtime": 717.116,
"eval_samples_per_second": 196.551,
"eval_steps_per_second": 24.569,
"step": 68385
},
{
"epoch": 3.0,
"step": 68385,
"total_flos": 4.2393620250444464e+19,
"train_loss": 0.011377156182601716,
"train_runtime": 7007.9208,
"train_samples_per_second": 78.065,
"train_steps_per_second": 9.758
}
],
"logging_steps": 500,
"max_steps": 68385,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 4.2393620250444464e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}