ast_celeb_spoof / trainer_state.json
Kabatubare's picture
Upload
49d81d5 verified
{
"best_metric": 89136693248.0,
"best_model_checkpoint": "W:/res/Transformers/AST-VoxCelebSpoof-Synthetic-Voice-Detection/checkpoint-88581",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 88581,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.97177724342692e-05,
"loss": 981229121797357.6,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 4.94355448685384e-05,
"loss": 293114647320461.3,
"step": 1000
},
{
"epoch": 0.05,
"learning_rate": 4.91533173028076e-05,
"loss": 93657499965587.45,
"step": 1500
},
{
"epoch": 0.07,
"learning_rate": 4.8871089737076805e-05,
"loss": 0.0,
"step": 2000
},
{
"epoch": 0.08,
"learning_rate": 4.8588862171346e-05,
"loss": 5643194574307.328,
"step": 2500
},
{
"epoch": 0.1,
"learning_rate": 4.8306634605615204e-05,
"loss": 73667803047002.11,
"step": 3000
},
{
"epoch": 0.12,
"learning_rate": 4.80244070398844e-05,
"loss": 64841546469474.305,
"step": 3500
},
{
"epoch": 0.14,
"learning_rate": 4.77421794741536e-05,
"loss": 9083863347232.768,
"step": 4000
},
{
"epoch": 0.15,
"learning_rate": 4.74599519084228e-05,
"loss": 13152772555800.576,
"step": 4500
},
{
"epoch": 0.17,
"learning_rate": 4.717772434269201e-05,
"loss": 20340400325656.574,
"step": 5000
},
{
"epoch": 0.19,
"learning_rate": 4.68954967769612e-05,
"loss": 26080007788953.6,
"step": 5500
},
{
"epoch": 0.2,
"learning_rate": 4.6613269211230405e-05,
"loss": 7317327729131.52,
"step": 6000
},
{
"epoch": 0.22,
"learning_rate": 4.6331041645499604e-05,
"loss": 12972364602015.744,
"step": 6500
},
{
"epoch": 0.24,
"learning_rate": 4.60488140797688e-05,
"loss": 11636490186522.623,
"step": 7000
},
{
"epoch": 0.25,
"learning_rate": 4.5766586514038e-05,
"loss": 27702524026814.465,
"step": 7500
},
{
"epoch": 0.27,
"learning_rate": 4.54843589483072e-05,
"loss": 25504280307826.688,
"step": 8000
},
{
"epoch": 0.29,
"learning_rate": 4.52021313825764e-05,
"loss": 11533152199639.04,
"step": 8500
},
{
"epoch": 0.3,
"learning_rate": 4.49199038168456e-05,
"loss": 6039433761521.664,
"step": 9000
},
{
"epoch": 0.32,
"learning_rate": 4.4637676251114805e-05,
"loss": 0.0,
"step": 9500
},
{
"epoch": 0.34,
"learning_rate": 4.4355448685384e-05,
"loss": 13410034654380.031,
"step": 10000
},
{
"epoch": 0.36,
"learning_rate": 4.40732211196532e-05,
"loss": 8384607774834.688,
"step": 10500
},
{
"epoch": 0.37,
"learning_rate": 4.37909935539224e-05,
"loss": 9342839137763.328,
"step": 11000
},
{
"epoch": 0.39,
"learning_rate": 4.35087659881916e-05,
"loss": 13016159309791.232,
"step": 11500
},
{
"epoch": 0.41,
"learning_rate": 4.32265384224608e-05,
"loss": 5719609021825.024,
"step": 12000
},
{
"epoch": 0.42,
"learning_rate": 4.294431085673e-05,
"loss": 9965717843607.553,
"step": 12500
},
{
"epoch": 0.44,
"learning_rate": 4.26620832909992e-05,
"loss": 1556572920610.816,
"step": 13000
},
{
"epoch": 0.46,
"learning_rate": 4.2379855725268404e-05,
"loss": 8649103672082.432,
"step": 13500
},
{
"epoch": 0.47,
"learning_rate": 4.20976281595376e-05,
"loss": 11390139452358.656,
"step": 14000
},
{
"epoch": 0.49,
"learning_rate": 4.18154005938068e-05,
"loss": 4287775373262.848,
"step": 14500
},
{
"epoch": 0.51,
"learning_rate": 4.1533173028076e-05,
"loss": 11550081886978.049,
"step": 15000
},
{
"epoch": 0.52,
"learning_rate": 4.12509454623452e-05,
"loss": 4851886578466.816,
"step": 15500
},
{
"epoch": 0.54,
"learning_rate": 4.09687178966144e-05,
"loss": 3983609279021.056,
"step": 16000
},
{
"epoch": 0.56,
"learning_rate": 4.06864903308836e-05,
"loss": 1347694299709.44,
"step": 16500
},
{
"epoch": 0.58,
"learning_rate": 4.04042627651528e-05,
"loss": 5110744257396.736,
"step": 17000
},
{
"epoch": 0.59,
"learning_rate": 4.0122035199422e-05,
"loss": 5899718475382.784,
"step": 17500
},
{
"epoch": 0.61,
"learning_rate": 3.98398076336912e-05,
"loss": 0.0,
"step": 18000
},
{
"epoch": 0.63,
"learning_rate": 3.9557580067960395e-05,
"loss": 5675016523874.304,
"step": 18500
},
{
"epoch": 0.64,
"learning_rate": 3.92753525022296e-05,
"loss": 4547420104949.76,
"step": 19000
},
{
"epoch": 0.66,
"learning_rate": 3.89931249364988e-05,
"loss": 4149328444653.568,
"step": 19500
},
{
"epoch": 0.68,
"learning_rate": 3.8710897370768e-05,
"loss": 3490896267968.512,
"step": 20000
},
{
"epoch": 0.69,
"learning_rate": 3.84286698050372e-05,
"loss": 4580182115483.648,
"step": 20500
},
{
"epoch": 0.71,
"learning_rate": 3.8146442239306404e-05,
"loss": 4821170046107.648,
"step": 21000
},
{
"epoch": 0.73,
"learning_rate": 3.7864214673575596e-05,
"loss": 1243646301044.736,
"step": 21500
},
{
"epoch": 0.75,
"learning_rate": 3.75819871078448e-05,
"loss": 0.0,
"step": 22000
},
{
"epoch": 0.76,
"learning_rate": 3.7299759542114e-05,
"loss": 6636355832512.512,
"step": 22500
},
{
"epoch": 0.78,
"learning_rate": 3.70175319763832e-05,
"loss": 2408073540927.488,
"step": 23000
},
{
"epoch": 0.8,
"learning_rate": 3.67353044106524e-05,
"loss": 2302174948229.12,
"step": 23500
},
{
"epoch": 0.81,
"learning_rate": 3.64530768449216e-05,
"loss": 1779972423286.784,
"step": 24000
},
{
"epoch": 0.83,
"learning_rate": 3.61708492791908e-05,
"loss": 4300719062515.712,
"step": 24500
},
{
"epoch": 0.85,
"learning_rate": 3.5888621713459997e-05,
"loss": 1038094467858.432,
"step": 25000
},
{
"epoch": 0.86,
"learning_rate": 3.56063941477292e-05,
"loss": 0.0,
"step": 25500
},
{
"epoch": 0.88,
"learning_rate": 3.5324166581998395e-05,
"loss": 927895002284.032,
"step": 26000
},
{
"epoch": 0.9,
"learning_rate": 3.50419390162676e-05,
"loss": 0.0,
"step": 26500
},
{
"epoch": 0.91,
"learning_rate": 3.47597114505368e-05,
"loss": 5167577412141.056,
"step": 27000
},
{
"epoch": 0.93,
"learning_rate": 3.4477483884806e-05,
"loss": 1088813065568.256,
"step": 27500
},
{
"epoch": 0.95,
"learning_rate": 3.41952563190752e-05,
"loss": 2567835050049.536,
"step": 28000
},
{
"epoch": 0.97,
"learning_rate": 3.3913028753344404e-05,
"loss": 2749761006338.048,
"step": 28500
},
{
"epoch": 0.98,
"learning_rate": 3.3630801187613596e-05,
"loss": 930680087248.896,
"step": 29000
},
{
"epoch": 1.0,
"learning_rate": 3.33485736218828e-05,
"loss": 2218896740319.232,
"step": 29500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9997713908327724,
"eval_f1": 0.9998122809944936,
"eval_loss": 611463921664.0,
"eval_precision": 0.9999374191664233,
"eval_recall": 0.9996871741397289,
"eval_runtime": 5137.6511,
"eval_samples_per_second": 15.325,
"eval_steps_per_second": 1.916,
"step": 29527
},
{
"epoch": 1.02,
"learning_rate": 3.3066346056152e-05,
"loss": 0.0,
"step": 30000
},
{
"epoch": 1.03,
"learning_rate": 3.27841184904212e-05,
"loss": 3861603485220.864,
"step": 30500
},
{
"epoch": 1.05,
"learning_rate": 3.25018909246904e-05,
"loss": 3710917241995.264,
"step": 31000
},
{
"epoch": 1.07,
"learning_rate": 3.22196633589596e-05,
"loss": 455580871294.976,
"step": 31500
},
{
"epoch": 1.08,
"learning_rate": 3.19374357932288e-05,
"loss": 4421536224116.736,
"step": 32000
},
{
"epoch": 1.1,
"learning_rate": 3.1655208227497996e-05,
"loss": 0.0,
"step": 32500
},
{
"epoch": 1.12,
"learning_rate": 3.1372980661767195e-05,
"loss": 751868921774.08,
"step": 33000
},
{
"epoch": 1.13,
"learning_rate": 3.1090753096036394e-05,
"loss": 5901689865371.648,
"step": 33500
},
{
"epoch": 1.15,
"learning_rate": 3.08085255303056e-05,
"loss": 1815885194985.472,
"step": 34000
},
{
"epoch": 1.17,
"learning_rate": 3.05262979645748e-05,
"loss": 1309930531323.904,
"step": 34500
},
{
"epoch": 1.19,
"learning_rate": 3.0244070398843998e-05,
"loss": 433426691784.704,
"step": 35000
},
{
"epoch": 1.2,
"learning_rate": 2.9961842833113197e-05,
"loss": 1553386189094.912,
"step": 35500
},
{
"epoch": 1.22,
"learning_rate": 2.96796152673824e-05,
"loss": 2184752152969.216,
"step": 36000
},
{
"epoch": 1.24,
"learning_rate": 2.9397387701651595e-05,
"loss": 3375935831146.496,
"step": 36500
},
{
"epoch": 1.25,
"learning_rate": 2.9115160135920798e-05,
"loss": 1693437019553.792,
"step": 37000
},
{
"epoch": 1.27,
"learning_rate": 2.8832932570189997e-05,
"loss": 0.0,
"step": 37500
},
{
"epoch": 1.29,
"learning_rate": 2.85507050044592e-05,
"loss": 0.0,
"step": 38000
},
{
"epoch": 1.3,
"learning_rate": 2.8268477438728395e-05,
"loss": 0.0,
"step": 38500
},
{
"epoch": 1.32,
"learning_rate": 2.7986249872997594e-05,
"loss": 1764714954620.928,
"step": 39000
},
{
"epoch": 1.34,
"learning_rate": 2.7704022307266797e-05,
"loss": 0.0,
"step": 39500
},
{
"epoch": 1.35,
"learning_rate": 2.7421794741535996e-05,
"loss": 0.0,
"step": 40000
},
{
"epoch": 1.37,
"learning_rate": 2.7139567175805198e-05,
"loss": 0.0,
"step": 40500
},
{
"epoch": 1.39,
"learning_rate": 2.6857339610074394e-05,
"loss": 0.0,
"step": 41000
},
{
"epoch": 1.41,
"learning_rate": 2.6575112044343596e-05,
"loss": 1287525700206.592,
"step": 41500
},
{
"epoch": 1.42,
"learning_rate": 2.6292884478612795e-05,
"loss": 947075990683.648,
"step": 42000
},
{
"epoch": 1.44,
"learning_rate": 2.6010656912881998e-05,
"loss": 0.0,
"step": 42500
},
{
"epoch": 1.46,
"learning_rate": 2.5728429347151194e-05,
"loss": 0.0,
"step": 43000
},
{
"epoch": 1.47,
"learning_rate": 2.54462017814204e-05,
"loss": 1175255120871.424,
"step": 43500
},
{
"epoch": 1.49,
"learning_rate": 2.5163974215689595e-05,
"loss": 1263805132701.696,
"step": 44000
},
{
"epoch": 1.51,
"learning_rate": 2.4881746649958794e-05,
"loss": 2792309099855.872,
"step": 44500
},
{
"epoch": 1.52,
"learning_rate": 2.4599519084227997e-05,
"loss": 113429733965.824,
"step": 45000
},
{
"epoch": 1.54,
"learning_rate": 2.4317291518497196e-05,
"loss": 1864144655482.88,
"step": 45500
},
{
"epoch": 1.56,
"learning_rate": 2.4035063952766395e-05,
"loss": 677714231033.856,
"step": 46000
},
{
"epoch": 1.57,
"learning_rate": 2.3752836387035597e-05,
"loss": 0.0,
"step": 46500
},
{
"epoch": 1.59,
"learning_rate": 2.3470608821304796e-05,
"loss": 1446208904101.888,
"step": 47000
},
{
"epoch": 1.61,
"learning_rate": 2.3188381255573995e-05,
"loss": 0.0,
"step": 47500
},
{
"epoch": 1.63,
"learning_rate": 2.2906153689843194e-05,
"loss": 2399757678936.064,
"step": 48000
},
{
"epoch": 1.64,
"learning_rate": 2.2623926124112397e-05,
"loss": 0.0,
"step": 48500
},
{
"epoch": 1.66,
"learning_rate": 2.2341698558381596e-05,
"loss": 0.0,
"step": 49000
},
{
"epoch": 1.68,
"learning_rate": 2.2059470992650795e-05,
"loss": 1886529622376.448,
"step": 49500
},
{
"epoch": 1.69,
"learning_rate": 2.1777243426919997e-05,
"loss": 0.0,
"step": 50000
},
{
"epoch": 1.71,
"learning_rate": 2.1495015861189193e-05,
"loss": 317279199821.824,
"step": 50500
},
{
"epoch": 1.73,
"learning_rate": 2.1212788295458396e-05,
"loss": 0.0,
"step": 51000
},
{
"epoch": 1.74,
"learning_rate": 2.0930560729727595e-05,
"loss": 1996925045833.728,
"step": 51500
},
{
"epoch": 1.76,
"learning_rate": 2.0648333163996794e-05,
"loss": 0.0,
"step": 52000
},
{
"epoch": 1.78,
"learning_rate": 2.0366105598265993e-05,
"loss": 0.0,
"step": 52500
},
{
"epoch": 1.79,
"learning_rate": 2.0083878032535195e-05,
"loss": 341458523521.024,
"step": 53000
},
{
"epoch": 1.81,
"learning_rate": 1.9801650466804394e-05,
"loss": 0.0,
"step": 53500
},
{
"epoch": 1.83,
"learning_rate": 1.9519422901073593e-05,
"loss": 1089140623933.44,
"step": 54000
},
{
"epoch": 1.85,
"learning_rate": 1.9237195335342796e-05,
"loss": 1722647092133.888,
"step": 54500
},
{
"epoch": 1.86,
"learning_rate": 1.8954967769611995e-05,
"loss": 1563876512497.664,
"step": 55000
},
{
"epoch": 1.88,
"learning_rate": 1.8672740203881194e-05,
"loss": 288611937288.192,
"step": 55500
},
{
"epoch": 1.9,
"learning_rate": 1.8390512638150396e-05,
"loss": 0.0,
"step": 56000
},
{
"epoch": 1.91,
"learning_rate": 1.8108285072419596e-05,
"loss": 0.0,
"step": 56500
},
{
"epoch": 1.93,
"learning_rate": 1.7826057506688795e-05,
"loss": 0.0,
"step": 57000
},
{
"epoch": 1.95,
"learning_rate": 1.7543829940957997e-05,
"loss": 0.0,
"step": 57500
},
{
"epoch": 1.96,
"learning_rate": 1.7261602375227193e-05,
"loss": 0.0,
"step": 58000
},
{
"epoch": 1.98,
"learning_rate": 1.6979374809496392e-05,
"loss": 0.0,
"step": 58500
},
{
"epoch": 2.0,
"learning_rate": 1.6697147243765594e-05,
"loss": 522149441830.912,
"step": 59000
},
{
"epoch": 2.0,
"eval_accuracy": 0.9996951877770298,
"eval_f1": 0.9997497027720419,
"eval_loss": 284563668992.0,
"eval_precision": 0.999895694259012,
"eval_recall": 0.9996037539103233,
"eval_runtime": 5225.6012,
"eval_samples_per_second": 15.068,
"eval_steps_per_second": 1.884,
"step": 59054
},
{
"epoch": 2.02,
"learning_rate": 1.6414919678034793e-05,
"loss": 0.0,
"step": 59500
},
{
"epoch": 2.03,
"learning_rate": 1.6132692112303992e-05,
"loss": 0.0,
"step": 60000
},
{
"epoch": 2.05,
"learning_rate": 1.5850464546573195e-05,
"loss": 191304554250.24,
"step": 60500
},
{
"epoch": 2.07,
"learning_rate": 1.5568236980842394e-05,
"loss": 0.0,
"step": 61000
},
{
"epoch": 2.08,
"learning_rate": 1.5286009415111593e-05,
"loss": 491350298460.16,
"step": 61500
},
{
"epoch": 2.1,
"learning_rate": 1.5003781849380794e-05,
"loss": 0.0,
"step": 62000
},
{
"epoch": 2.12,
"learning_rate": 1.4721554283649993e-05,
"loss": 0.0,
"step": 62500
},
{
"epoch": 2.13,
"learning_rate": 1.4439326717919194e-05,
"loss": 1899711548096.512,
"step": 63000
},
{
"epoch": 2.15,
"learning_rate": 1.4157099152188394e-05,
"loss": 681978059816.96,
"step": 63500
},
{
"epoch": 2.17,
"learning_rate": 1.3874871586457593e-05,
"loss": 0.0,
"step": 64000
},
{
"epoch": 2.18,
"learning_rate": 1.3592644020726794e-05,
"loss": 0.0,
"step": 64500
},
{
"epoch": 2.2,
"learning_rate": 1.3310416454995995e-05,
"loss": 0.0,
"step": 65000
},
{
"epoch": 2.22,
"learning_rate": 1.3028188889265194e-05,
"loss": 0.0,
"step": 65500
},
{
"epoch": 2.24,
"learning_rate": 1.2745961323534391e-05,
"loss": 301877312880.64,
"step": 66000
},
{
"epoch": 2.25,
"learning_rate": 1.2463733757803594e-05,
"loss": 593167598485.504,
"step": 66500
},
{
"epoch": 2.27,
"learning_rate": 1.2181506192072793e-05,
"loss": 251006361272.32,
"step": 67000
},
{
"epoch": 2.29,
"learning_rate": 1.1899278626341992e-05,
"loss": 19797129560.064,
"step": 67500
},
{
"epoch": 2.3,
"learning_rate": 1.1617051060611193e-05,
"loss": 181410543435.776,
"step": 68000
},
{
"epoch": 2.32,
"learning_rate": 1.1334823494880392e-05,
"loss": 215261328179.2,
"step": 68500
},
{
"epoch": 2.34,
"learning_rate": 1.1052595929149593e-05,
"loss": 30928501997.568,
"step": 69000
},
{
"epoch": 2.35,
"learning_rate": 1.0770368363418792e-05,
"loss": 257392692428.8,
"step": 69500
},
{
"epoch": 2.37,
"learning_rate": 1.0488140797687992e-05,
"loss": 0.0,
"step": 70000
},
{
"epoch": 2.39,
"learning_rate": 1.0205913231957193e-05,
"loss": 257848730714.112,
"step": 70500
},
{
"epoch": 2.4,
"learning_rate": 9.923685666226392e-06,
"loss": 307711254200.32,
"step": 71000
},
{
"epoch": 2.42,
"learning_rate": 9.641458100495591e-06,
"loss": 0.0,
"step": 71500
},
{
"epoch": 2.44,
"learning_rate": 9.359230534764792e-06,
"loss": 158387253805.056,
"step": 72000
},
{
"epoch": 2.46,
"learning_rate": 9.077002969033991e-06,
"loss": 0.0,
"step": 72500
},
{
"epoch": 2.47,
"learning_rate": 8.794775403303192e-06,
"loss": 0.0,
"step": 73000
},
{
"epoch": 2.49,
"learning_rate": 8.512547837572393e-06,
"loss": 0.0,
"step": 73500
},
{
"epoch": 2.51,
"learning_rate": 8.230320271841592e-06,
"loss": 1090791367770.112,
"step": 74000
},
{
"epoch": 2.52,
"learning_rate": 7.948092706110793e-06,
"loss": 0.0,
"step": 74500
},
{
"epoch": 2.54,
"learning_rate": 7.665865140379992e-06,
"loss": 569641780903.936,
"step": 75000
},
{
"epoch": 2.56,
"learning_rate": 7.383637574649191e-06,
"loss": 0.0,
"step": 75500
},
{
"epoch": 2.57,
"learning_rate": 7.1014100089183914e-06,
"loss": 0.0,
"step": 76000
},
{
"epoch": 2.59,
"learning_rate": 6.819182443187591e-06,
"loss": 0.0,
"step": 76500
},
{
"epoch": 2.61,
"learning_rate": 6.536954877456791e-06,
"loss": 426132293812.224,
"step": 77000
},
{
"epoch": 2.62,
"learning_rate": 6.254727311725991e-06,
"loss": 0.0,
"step": 77500
},
{
"epoch": 2.64,
"learning_rate": 5.972499745995191e-06,
"loss": 0.0,
"step": 78000
},
{
"epoch": 2.66,
"learning_rate": 5.690272180264391e-06,
"loss": 39255350968.32,
"step": 78500
},
{
"epoch": 2.68,
"learning_rate": 5.408044614533591e-06,
"loss": 5119055233.024,
"step": 79000
},
{
"epoch": 2.69,
"learning_rate": 5.125817048802791e-06,
"loss": 57651782221.824,
"step": 79500
},
{
"epoch": 2.71,
"learning_rate": 4.843589483071991e-06,
"loss": 211899325087.744,
"step": 80000
},
{
"epoch": 2.73,
"learning_rate": 4.561361917341191e-06,
"loss": 0.0,
"step": 80500
},
{
"epoch": 2.74,
"learning_rate": 4.279134351610391e-06,
"loss": 0.0,
"step": 81000
},
{
"epoch": 2.76,
"learning_rate": 3.9969067858795905e-06,
"loss": 92870765707.264,
"step": 81500
},
{
"epoch": 2.78,
"learning_rate": 3.7146792201487904e-06,
"loss": 0.0,
"step": 82000
},
{
"epoch": 2.79,
"learning_rate": 3.4324516544179904e-06,
"loss": 0.0,
"step": 82500
},
{
"epoch": 2.81,
"learning_rate": 3.1502240886871903e-06,
"loss": 2615742038.016,
"step": 83000
},
{
"epoch": 2.83,
"learning_rate": 2.86799652295639e-06,
"loss": 0.0,
"step": 83500
},
{
"epoch": 2.84,
"learning_rate": 2.5857689572255905e-06,
"loss": 0.0,
"step": 84000
},
{
"epoch": 2.86,
"learning_rate": 2.30354139149479e-06,
"loss": 9586501222.4,
"step": 84500
},
{
"epoch": 2.88,
"learning_rate": 2.0213138257639904e-06,
"loss": 0.0,
"step": 85000
},
{
"epoch": 2.9,
"learning_rate": 1.73908626003319e-06,
"loss": 0.0,
"step": 85500
},
{
"epoch": 2.91,
"learning_rate": 1.45685869430239e-06,
"loss": 86379425955.84,
"step": 86000
},
{
"epoch": 2.93,
"learning_rate": 1.17463112857159e-06,
"loss": 0.0,
"step": 86500
},
{
"epoch": 2.95,
"learning_rate": 8.924035628407898e-07,
"loss": 0.0,
"step": 87000
},
{
"epoch": 2.96,
"learning_rate": 6.101759971099898e-07,
"loss": 0.0,
"step": 87500
},
{
"epoch": 2.98,
"learning_rate": 3.279484313791897e-07,
"loss": 0.0,
"step": 88000
},
{
"epoch": 3.0,
"learning_rate": 4.572086564838961e-08,
"loss": 0.0,
"step": 88500
},
{
"epoch": 3.0,
"eval_accuracy": 0.9998856954163862,
"eval_f1": 0.9999061434336903,
"eval_loss": 89136693248.0,
"eval_precision": 1.0,
"eval_recall": 0.9998123044838373,
"eval_runtime": 5135.9845,
"eval_samples_per_second": 15.33,
"eval_steps_per_second": 1.916,
"step": 88581
},
{
"epoch": 3.0,
"step": 88581,
"total_flos": 4.803336053113592e+19,
"train_loss": 10893808030881.182,
"train_runtime": 445813.7666,
"train_samples_per_second": 1.59,
"train_steps_per_second": 0.199
}
],
"logging_steps": 500,
"max_steps": 88581,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 4.803336053113592e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}