| { | |
| "best_metric": 0.14763057231903076, | |
| "best_model_checkpoint": "./vit-front-page-384-complete-v2/checkpoint-28000", | |
| "epoch": 63.99933554817276, | |
| "global_step": 30080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7e-08, | |
| "loss": 1.0485, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.4e-07, | |
| "loss": 0.9833, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.6194995827128573, | |
| "eval_f1": 0.2849637284042793, | |
| "eval_loss": 0.9414144158363342, | |
| "eval_matthews_correlation": -0.046627386105974944, | |
| "eval_precision": 0.28223649662424866, | |
| "eval_recall": 0.3194839105028776, | |
| "eval_runtime": 1120.0285, | |
| "eval_samples_per_second": 54.56, | |
| "eval_steps_per_second": 1.705, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.0999999999999997e-07, | |
| "loss": 0.9031, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.8e-07, | |
| "loss": 0.8378, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.6742542015087793, | |
| "eval_f1": 0.27318592449369794, | |
| "eval_loss": 0.8087042570114136, | |
| "eval_matthews_correlation": -0.008566496106974774, | |
| "eval_precision": 0.33248655167577795, | |
| "eval_recall": 0.3329403574518804, | |
| "eval_runtime": 1146.8267, | |
| "eval_samples_per_second": 53.285, | |
| "eval_steps_per_second": 1.665, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.5e-07, | |
| "loss": 0.7846, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.1999999999999995e-07, | |
| "loss": 0.725, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.7299906724050467, | |
| "eval_f1": 0.45416361692283386, | |
| "eval_loss": 0.6847068071365356, | |
| "eval_matthews_correlation": 0.3478679528690636, | |
| "eval_precision": 0.7356178375809365, | |
| "eval_recall": 0.4490403016153819, | |
| "eval_runtime": 1122.3931, | |
| "eval_samples_per_second": 54.445, | |
| "eval_steps_per_second": 1.702, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.9e-07, | |
| "loss": 0.6452, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.5769, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_accuracy": 0.7984093995974406, | |
| "eval_f1": 0.6063804641618133, | |
| "eval_loss": 0.5433278679847717, | |
| "eval_matthews_correlation": 0.554774970478316, | |
| "eval_precision": 0.782372439805869, | |
| "eval_recall": 0.6092247400862097, | |
| "eval_runtime": 1136.2592, | |
| "eval_samples_per_second": 53.781, | |
| "eval_steps_per_second": 1.681, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.3e-07, | |
| "loss": 0.5208, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 7e-07, | |
| "loss": 0.4706, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.8339688098316124, | |
| "eval_f1": 0.6871318497564141, | |
| "eval_loss": 0.4425855875015259, | |
| "eval_matthews_correlation": 0.6440133138789277, | |
| "eval_precision": 0.8172733311232007, | |
| "eval_recall": 0.6865053904162712, | |
| "eval_runtime": 1131.2502, | |
| "eval_samples_per_second": 54.019, | |
| "eval_steps_per_second": 1.688, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.975928473177441e-07, | |
| "loss": 0.4247, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 6.951856946354883e-07, | |
| "loss": 0.3902, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.8571732478031059, | |
| "eval_f1": 0.7517270150716192, | |
| "eval_loss": 0.3730458915233612, | |
| "eval_matthews_correlation": 0.6959063906454223, | |
| "eval_precision": 0.8447385961080253, | |
| "eval_recall": 0.7349271721409717, | |
| "eval_runtime": 1143.842, | |
| "eval_samples_per_second": 53.424, | |
| "eval_steps_per_second": 1.67, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.927785419532324e-07, | |
| "loss": 0.3604, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 6.903713892709766e-07, | |
| "loss": 0.3392, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.8786430803973229, | |
| "eval_f1": 0.8069413230330182, | |
| "eval_loss": 0.32644152641296387, | |
| "eval_matthews_correlation": 0.7428749706793645, | |
| "eval_precision": 0.8632726130534206, | |
| "eval_recall": 0.7855049543193654, | |
| "eval_runtime": 1136.2051, | |
| "eval_samples_per_second": 53.783, | |
| "eval_steps_per_second": 1.681, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 6.879642365887207e-07, | |
| "loss": 0.3188, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.855570839064649e-07, | |
| "loss": 0.3044, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.8894925461061383, | |
| "eval_f1": 0.8329212820595306, | |
| "eval_loss": 0.2972641587257385, | |
| "eval_matthews_correlation": 0.7664388748302527, | |
| "eval_precision": 0.8723203701164862, | |
| "eval_recall": 0.8120687720492296, | |
| "eval_runtime": 1138.2797, | |
| "eval_samples_per_second": 53.685, | |
| "eval_steps_per_second": 1.678, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 6.83149931224209e-07, | |
| "loss": 0.2943, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.807427785419532e-07, | |
| "loss": 0.2795, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.8961691403884862, | |
| "eval_f1": 0.8432760143718706, | |
| "eval_loss": 0.2766903340816498, | |
| "eval_matthews_correlation": 0.781173318686851, | |
| "eval_precision": 0.8834852690618357, | |
| "eval_recall": 0.8221927104856026, | |
| "eval_runtime": 1109.6741, | |
| "eval_samples_per_second": 55.069, | |
| "eval_steps_per_second": 1.721, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.783356258596973e-07, | |
| "loss": 0.2738, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 6.759284731774416e-07, | |
| "loss": 0.262, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_accuracy": 0.9019784319821957, | |
| "eval_f1": 0.8550525638971442, | |
| "eval_loss": 0.26178261637687683, | |
| "eval_matthews_correlation": 0.7937491549035616, | |
| "eval_precision": 0.8893566012052573, | |
| "eval_recall": 0.8349244764526037, | |
| "eval_runtime": 1138.053, | |
| "eval_samples_per_second": 53.696, | |
| "eval_steps_per_second": 1.678, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 6.735213204951857e-07, | |
| "loss": 0.2567, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 6.711141678129298e-07, | |
| "loss": 0.2497, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_accuracy": 0.9061185750053183, | |
| "eval_f1": 0.8647877107942263, | |
| "eval_loss": 0.25028473138809204, | |
| "eval_matthews_correlation": 0.8031001323768835, | |
| "eval_precision": 0.888845641786976, | |
| "eval_recall": 0.8490665078134735, | |
| "eval_runtime": 1128.8955, | |
| "eval_samples_per_second": 54.132, | |
| "eval_steps_per_second": 1.692, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 6.68707015130674e-07, | |
| "loss": 0.2444, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 6.662998624484181e-07, | |
| "loss": 0.2414, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.908589569457854, | |
| "eval_f1": 0.8705010060852946, | |
| "eval_loss": 0.24158228933811188, | |
| "eval_matthews_correlation": 0.808821805927799, | |
| "eval_precision": 0.888714743861985, | |
| "eval_recall": 0.8577216170630284, | |
| "eval_runtime": 1121.8959, | |
| "eval_samples_per_second": 54.469, | |
| "eval_steps_per_second": 1.702, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 6.638927097661623e-07, | |
| "loss": 0.2321, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 6.614855570839064e-07, | |
| "loss": 0.2356, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "eval_accuracy": 0.9110441997087172, | |
| "eval_f1": 0.8747151973222319, | |
| "eval_loss": 0.23398438096046448, | |
| "eval_matthews_correlation": 0.8139518481821442, | |
| "eval_precision": 0.8928668344520597, | |
| "eval_recall": 0.861416198724987, | |
| "eval_runtime": 1133.6213, | |
| "eval_samples_per_second": 53.906, | |
| "eval_steps_per_second": 1.685, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 6.590784044016506e-07, | |
| "loss": 0.226, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 6.566712517193947e-07, | |
| "loss": 0.2251, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.9136297435729598, | |
| "eval_f1": 0.8786518904171384, | |
| "eval_loss": 0.22776289284229279, | |
| "eval_matthews_correlation": 0.8196091308971525, | |
| "eval_precision": 0.8955149466291931, | |
| "eval_recall": 0.8663159550061658, | |
| "eval_runtime": 1128.8199, | |
| "eval_samples_per_second": 54.135, | |
| "eval_steps_per_second": 1.692, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 6.542640990371389e-07, | |
| "loss": 0.2216, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 6.51856946354883e-07, | |
| "loss": 0.217, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_accuracy": 0.915577083571978, | |
| "eval_f1": 0.8816198142871025, | |
| "eval_loss": 0.22265483438968658, | |
| "eval_matthews_correlation": 0.8236394377439027, | |
| "eval_precision": 0.8990606065527942, | |
| "eval_recall": 0.8686464677513945, | |
| "eval_runtime": 1127.8916, | |
| "eval_samples_per_second": 54.18, | |
| "eval_steps_per_second": 1.693, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 6.494497936726272e-07, | |
| "loss": 0.2175, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 6.470426409903714e-07, | |
| "loss": 0.2133, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_accuracy": 0.9171153185291856, | |
| "eval_f1": 0.8827723003585022, | |
| "eval_loss": 0.21786576509475708, | |
| "eval_matthews_correlation": 0.8266852106519758, | |
| "eval_precision": 0.9034666000752295, | |
| "eval_recall": 0.8679497941871164, | |
| "eval_runtime": 1129.6487, | |
| "eval_samples_per_second": 54.096, | |
| "eval_steps_per_second": 1.691, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 6.446354883081155e-07, | |
| "loss": 0.2117, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 6.422283356258597e-07, | |
| "loss": 0.2098, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "eval_accuracy": 0.9182935410495999, | |
| "eval_f1": 0.884903972857821, | |
| "eval_loss": 0.21342970430850983, | |
| "eval_matthews_correlation": 0.8292988605784972, | |
| "eval_precision": 0.9040958524512837, | |
| "eval_recall": 0.870991653583178, | |
| "eval_runtime": 1152.1924, | |
| "eval_samples_per_second": 53.037, | |
| "eval_steps_per_second": 1.658, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 6.398211829436038e-07, | |
| "loss": 0.2021, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 6.37414030261348e-07, | |
| "loss": 0.2062, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_accuracy": 0.9201754242419283, | |
| "eval_f1": 0.8875922877918782, | |
| "eval_loss": 0.20977966487407684, | |
| "eval_matthews_correlation": 0.833123364179002, | |
| "eval_precision": 0.9084794166339746, | |
| "eval_recall": 0.872252852044762, | |
| "eval_runtime": 1135.8312, | |
| "eval_samples_per_second": 53.801, | |
| "eval_steps_per_second": 1.682, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 6.350068775790921e-07, | |
| "loss": 0.2033, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 6.325997248968363e-07, | |
| "loss": 0.1982, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "eval_accuracy": 0.9213863751656876, | |
| "eval_f1": 0.88930772340783, | |
| "eval_loss": 0.20641230046749115, | |
| "eval_matthews_correlation": 0.8357746010338397, | |
| "eval_precision": 0.9095846117319936, | |
| "eval_recall": 0.8745329047658825, | |
| "eval_runtime": 1143.3313, | |
| "eval_samples_per_second": 53.448, | |
| "eval_steps_per_second": 1.671, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.301925722145805e-07, | |
| "loss": 0.196, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 6.277854195323246e-07, | |
| "loss": 0.1983, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "eval_accuracy": 0.9222700420559983, | |
| "eval_f1": 0.8900453287552592, | |
| "eval_loss": 0.20386044681072235, | |
| "eval_matthews_correlation": 0.837555384879415, | |
| "eval_precision": 0.9123527733555781, | |
| "eval_recall": 0.8740593137023058, | |
| "eval_runtime": 1129.2304, | |
| "eval_samples_per_second": 54.116, | |
| "eval_steps_per_second": 1.691, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 6.253782668500687e-07, | |
| "loss": 0.1965, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 6.229711141678129e-07, | |
| "loss": 0.1936, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.9233828077697229, | |
| "eval_f1": 0.8932485448536257, | |
| "eval_loss": 0.20058760046958923, | |
| "eval_matthews_correlation": 0.8401209500114148, | |
| "eval_precision": 0.9107366418558472, | |
| "eval_recall": 0.8798434624360084, | |
| "eval_runtime": 1120.0565, | |
| "eval_samples_per_second": 54.559, | |
| "eval_steps_per_second": 1.705, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 6.205880330123796e-07, | |
| "loss": 0.1922, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 6.181808803301237e-07, | |
| "loss": 0.1953, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_accuracy": 0.9238246412148783, | |
| "eval_f1": 0.8951433768565843, | |
| "eval_loss": 0.19883869588375092, | |
| "eval_matthews_correlation": 0.8415676876590389, | |
| "eval_precision": 0.9072146230906633, | |
| "eval_recall": 0.885557435823166, | |
| "eval_runtime": 1137.9471, | |
| "eval_samples_per_second": 53.701, | |
| "eval_steps_per_second": 1.678, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 6.15773727647868e-07, | |
| "loss": 0.1843, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 6.133665749656121e-07, | |
| "loss": 0.1852, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_accuracy": 0.9253792403737584, | |
| "eval_f1": 0.8946482066160663, | |
| "eval_loss": 0.19628000259399414, | |
| "eval_matthews_correlation": 0.8441339816426117, | |
| "eval_precision": 0.9173420280370865, | |
| "eval_recall": 0.8782309033246154, | |
| "eval_runtime": 1124.1932, | |
| "eval_samples_per_second": 54.358, | |
| "eval_steps_per_second": 1.699, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.109594222833563e-07, | |
| "loss": 0.1845, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 6.085522696011004e-07, | |
| "loss": 0.1839, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "eval_accuracy": 0.9258374380205862, | |
| "eval_f1": 0.8972498157769592, | |
| "eval_loss": 0.1933354139328003, | |
| "eval_matthews_correlation": 0.8454266170310101, | |
| "eval_precision": 0.9128401019975159, | |
| "eval_recall": 0.8849382250200719, | |
| "eval_runtime": 1122.9259, | |
| "eval_samples_per_second": 54.419, | |
| "eval_steps_per_second": 1.701, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 6.061451169188445e-07, | |
| "loss": 0.1845, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 6.037379642365887e-07, | |
| "loss": 0.1791, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_accuracy": 0.9267047407092245, | |
| "eval_f1": 0.8983700490176202, | |
| "eval_loss": 0.19171090424060822, | |
| "eval_matthews_correlation": 0.8472176589659597, | |
| "eval_precision": 0.9145474859208962, | |
| "eval_recall": 0.8856752741366947, | |
| "eval_runtime": 1134.0907, | |
| "eval_samples_per_second": 53.884, | |
| "eval_steps_per_second": 1.684, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 6.013308115543328e-07, | |
| "loss": 0.182, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 5.98923658872077e-07, | |
| "loss": 0.18, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "eval_accuracy": 0.9271138457510351, | |
| "eval_f1": 0.8995050329011628, | |
| "eval_loss": 0.1895856410264969, | |
| "eval_matthews_correlation": 0.848294574832317, | |
| "eval_precision": 0.9131718148389393, | |
| "eval_recall": 0.8885987433408609, | |
| "eval_runtime": 1126.9856, | |
| "eval_samples_per_second": 54.223, | |
| "eval_steps_per_second": 1.695, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 5.965165061898212e-07, | |
| "loss": 0.1763, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.941093535075653e-07, | |
| "loss": 0.1782, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "eval_accuracy": 0.9275556791961904, | |
| "eval_f1": 0.9002696190246419, | |
| "eval_loss": 0.18787473440170288, | |
| "eval_matthews_correlation": 0.84921482512736, | |
| "eval_precision": 0.9139059903894043, | |
| "eval_recall": 0.88930836639531, | |
| "eval_runtime": 1128.4943, | |
| "eval_samples_per_second": 54.151, | |
| "eval_steps_per_second": 1.693, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 5.917022008253094e-07, | |
| "loss": 0.1788, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 5.892950481430536e-07, | |
| "loss": 0.1712, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_accuracy": 0.9287175375149324, | |
| "eval_f1": 0.9011964058613507, | |
| "eval_loss": 0.1861330270767212, | |
| "eval_matthews_correlation": 0.8514678062818634, | |
| "eval_precision": 0.9173976756930257, | |
| "eval_recall": 0.8884787278098573, | |
| "eval_runtime": 1120.0822, | |
| "eval_samples_per_second": 54.558, | |
| "eval_steps_per_second": 1.705, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 5.868878954607978e-07, | |
| "loss": 0.172, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.84480742778542e-07, | |
| "loss": 0.1737, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "eval_accuracy": 0.9296993896152776, | |
| "eval_f1": 0.9010626619953944, | |
| "eval_loss": 0.18573108315467834, | |
| "eval_matthews_correlation": 0.8533347114503049, | |
| "eval_precision": 0.9231173958750271, | |
| "eval_recall": 0.8849159091550628, | |
| "eval_runtime": 1156.0243, | |
| "eval_samples_per_second": 52.861, | |
| "eval_steps_per_second": 1.652, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.820735900962861e-07, | |
| "loss": 0.1726, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 5.796664374140302e-07, | |
| "loss": 0.1696, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "eval_accuracy": 0.930026673648726, | |
| "eval_f1": 0.9031918377265686, | |
| "eval_loss": 0.1828816682100296, | |
| "eval_matthews_correlation": 0.8542309647721633, | |
| "eval_precision": 0.9192960205580971, | |
| "eval_recall": 0.8904958440603054, | |
| "eval_runtime": 1124.8361, | |
| "eval_samples_per_second": 54.327, | |
| "eval_steps_per_second": 1.698, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 5.772592847317744e-07, | |
| "loss": 0.1682, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 5.748521320495185e-07, | |
| "loss": 0.1698, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "eval_accuracy": 0.9302885008754848, | |
| "eval_f1": 0.9048186507788922, | |
| "eval_loss": 0.18205700814723969, | |
| "eval_matthews_correlation": 0.8551184049776112, | |
| "eval_precision": 0.9164794554225942, | |
| "eval_recall": 0.8951361110635792, | |
| "eval_runtime": 1130.5739, | |
| "eval_samples_per_second": 54.051, | |
| "eval_steps_per_second": 1.689, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 5.724449793672627e-07, | |
| "loss": 0.1682, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 5.700378266850069e-07, | |
| "loss": 0.1667, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "eval_accuracy": 0.9303048650771573, | |
| "eval_f1": 0.9056480109419961, | |
| "eval_loss": 0.18090908229351044, | |
| "eval_matthews_correlation": 0.855428359187355, | |
| "eval_precision": 0.9147426706946558, | |
| "eval_recall": 0.8978667208863417, | |
| "eval_runtime": 1113.9498, | |
| "eval_samples_per_second": 54.858, | |
| "eval_steps_per_second": 1.715, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 5.67630674002751e-07, | |
| "loss": 0.1673, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 5.652235213204951e-07, | |
| "loss": 0.1651, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "eval_accuracy": 0.9307794269256574, | |
| "eval_f1": 0.90568642496187, | |
| "eval_loss": 0.17903146147727966, | |
| "eval_matthews_correlation": 0.8562905390552094, | |
| "eval_precision": 0.9160847482436384, | |
| "eval_recall": 0.8970366589757913, | |
| "eval_runtime": 1123.7851, | |
| "eval_samples_per_second": 54.378, | |
| "eval_steps_per_second": 1.7, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 5.628163686382393e-07, | |
| "loss": 0.1638, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 5.604092159559834e-07, | |
| "loss": 0.1614, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "eval_accuracy": 0.9319412852443993, | |
| "eval_f1": 0.9062846542418327, | |
| "eval_loss": 0.17761486768722534, | |
| "eval_matthews_correlation": 0.8583632583058451, | |
| "eval_precision": 0.9210761772993599, | |
| "eval_recall": 0.8945216174285454, | |
| "eval_runtime": 1135.9567, | |
| "eval_samples_per_second": 53.795, | |
| "eval_steps_per_second": 1.681, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 5.580261348005502e-07, | |
| "loss": 0.1629, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 5.556189821182944e-07, | |
| "loss": 0.16, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_accuracy": 0.9323667544878823, | |
| "eval_f1": 0.9057483267194343, | |
| "eval_loss": 0.177241712808609, | |
| "eval_matthews_correlation": 0.8590673404186833, | |
| "eval_precision": 0.9249219537323391, | |
| "eval_recall": 0.8912560253961389, | |
| "eval_runtime": 1147.9689, | |
| "eval_samples_per_second": 53.232, | |
| "eval_steps_per_second": 1.664, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 5.532118294360385e-07, | |
| "loss": 0.1622, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 5.508046767537827e-07, | |
| "loss": 0.1591, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "eval_accuracy": 0.9334467917982622, | |
| "eval_f1": 0.90852409435722, | |
| "eval_loss": 0.17550112307071686, | |
| "eval_matthews_correlation": 0.8615051567396046, | |
| "eval_precision": 0.9232173166653612, | |
| "eval_recall": 0.8966351633696954, | |
| "eval_runtime": 1144.6322, | |
| "eval_samples_per_second": 53.387, | |
| "eval_steps_per_second": 1.669, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 5.483975240715268e-07, | |
| "loss": 0.16, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 5.45990371389271e-07, | |
| "loss": 0.1601, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "eval_accuracy": 0.9333322423865552, | |
| "eval_f1": 0.9088120224095171, | |
| "eval_loss": 0.17453713715076447, | |
| "eval_matthews_correlation": 0.8613787118816909, | |
| "eval_precision": 0.9218305477922321, | |
| "eval_recall": 0.8980828107442319, | |
| "eval_runtime": 1143.4792, | |
| "eval_samples_per_second": 53.441, | |
| "eval_steps_per_second": 1.67, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 5.435832187070151e-07, | |
| "loss": 0.1584, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 5.411760660247592e-07, | |
| "loss": 0.1558, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_accuracy": 0.9338395326384002, | |
| "eval_f1": 0.9096298761981343, | |
| "eval_loss": 0.17321471869945526, | |
| "eval_matthews_correlation": 0.8625748894777745, | |
| "eval_precision": 0.9213568402254939, | |
| "eval_recall": 0.8999913944640027, | |
| "eval_runtime": 1116.2047, | |
| "eval_samples_per_second": 54.747, | |
| "eval_steps_per_second": 1.711, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 5.387689133425034e-07, | |
| "loss": 0.1544, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 5.363617606602475e-07, | |
| "loss": 0.1552, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "eval_accuracy": 0.9334631559999346, | |
| "eval_f1": 0.9101663960284817, | |
| "eval_loss": 0.17314866185188293, | |
| "eval_matthews_correlation": 0.8621017254091837, | |
| "eval_precision": 0.9185625631174649, | |
| "eval_recall": 0.9029180840503908, | |
| "eval_runtime": 1134.8054, | |
| "eval_samples_per_second": 53.85, | |
| "eval_steps_per_second": 1.683, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 5.339546079779917e-07, | |
| "loss": 0.1571, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 5.315474552957359e-07, | |
| "loss": 0.1526, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.9340849956634866, | |
| "eval_f1": 0.9110344713781423, | |
| "eval_loss": 0.17203205823898315, | |
| "eval_matthews_correlation": 0.8634918058087261, | |
| "eval_precision": 0.9187082054219985, | |
| "eval_recall": 0.9044161914490357, | |
| "eval_runtime": 1153.6876, | |
| "eval_samples_per_second": 52.968, | |
| "eval_steps_per_second": 1.656, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 5.2914030261348e-07, | |
| "loss": 0.1485, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 5.267331499312242e-07, | |
| "loss": 0.1532, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "eval_accuracy": 0.9346741069236937, | |
| "eval_f1": 0.9117218687868994, | |
| "eval_loss": 0.17076529562473297, | |
| "eval_matthews_correlation": 0.8646272156128906, | |
| "eval_precision": 0.9201726149656478, | |
| "eval_recall": 0.9044721170341236, | |
| "eval_runtime": 1135.1604, | |
| "eval_samples_per_second": 53.833, | |
| "eval_steps_per_second": 1.683, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 5.243259972489684e-07, | |
| "loss": 0.1551, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 5.219188445667125e-07, | |
| "loss": 0.1539, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "eval_accuracy": 0.9351159403688492, | |
| "eval_f1": 0.911610683009681, | |
| "eval_loss": 0.1695307195186615, | |
| "eval_matthews_correlation": 0.865289074877206, | |
| "eval_precision": 0.9226978459827032, | |
| "eval_recall": 0.9023554489680277, | |
| "eval_runtime": 1122.959, | |
| "eval_samples_per_second": 54.418, | |
| "eval_steps_per_second": 1.701, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 5.195116918844567e-07, | |
| "loss": 0.1477, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 5.171045392022008e-07, | |
| "loss": 0.1483, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "eval_accuracy": 0.9356723232257115, | |
| "eval_f1": 0.9116987398295661, | |
| "eval_loss": 0.16896899044513702, | |
| "eval_matthews_correlation": 0.8662695435076357, | |
| "eval_precision": 0.9255532080817271, | |
| "eval_recall": 0.9005543243181938, | |
| "eval_runtime": 1135.8593, | |
| "eval_samples_per_second": 53.8, | |
| "eval_steps_per_second": 1.682, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 5.146973865199449e-07, | |
| "loss": 0.1489, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 5.122902338376891e-07, | |
| "loss": 0.1469, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "eval_accuracy": 0.9358032368390908, | |
| "eval_f1": 0.9135814294302561, | |
| "eval_loss": 0.16858318448066711, | |
| "eval_matthews_correlation": 0.8670812623876053, | |
| "eval_precision": 0.9210624088966272, | |
| "eval_recall": 0.907023142033475, | |
| "eval_runtime": 1122.9881, | |
| "eval_samples_per_second": 54.416, | |
| "eval_steps_per_second": 1.701, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 5.099071526822558e-07, | |
| "loss": 0.1507, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 5.075e-07, | |
| "loss": 0.1461, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "eval_accuracy": 0.9359177862507978, | |
| "eval_f1": 0.9125886359052826, | |
| "eval_loss": 0.16734813153743744, | |
| "eval_matthews_correlation": 0.8668498402291797, | |
| "eval_precision": 0.9249962574783411, | |
| "eval_recall": 0.9022824765643582, | |
| "eval_runtime": 1124.669, | |
| "eval_samples_per_second": 54.335, | |
| "eval_steps_per_second": 1.698, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 5.050928473177441e-07, | |
| "loss": 0.1453, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 5.026856946354882e-07, | |
| "loss": 0.1487, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_accuracy": 0.936588718519367, | |
| "eval_f1": 0.9144201514784519, | |
| "eval_loss": 0.16664335131645203, | |
| "eval_matthews_correlation": 0.8685701549851123, | |
| "eval_precision": 0.9231788402692221, | |
| "eval_recall": 0.9068124874405709, | |
| "eval_runtime": 1132.0219, | |
| "eval_samples_per_second": 53.982, | |
| "eval_steps_per_second": 1.687, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 5.00302613480055e-07, | |
| "loss": 0.1499, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.978954607977991e-07, | |
| "loss": 0.1433, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9369978235611776, | |
| "eval_f1": 0.91467275197079, | |
| "eval_loss": 0.16577279567718506, | |
| "eval_matthews_correlation": 0.8693728793586808, | |
| "eval_precision": 0.924099137774855, | |
| "eval_recall": 0.9066503727608389, | |
| "eval_runtime": 1144.9998, | |
| "eval_samples_per_second": 53.37, | |
| "eval_steps_per_second": 1.668, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 4.954883081155432e-07, | |
| "loss": 0.144, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 4.930811554332874e-07, | |
| "loss": 0.1437, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "eval_accuracy": 0.9370796445695396, | |
| "eval_f1": 0.9143506341308217, | |
| "eval_loss": 0.1650729477405548, | |
| "eval_matthews_correlation": 0.8693576464491103, | |
| "eval_precision": 0.9258633996979286, | |
| "eval_recall": 0.9047199267971502, | |
| "eval_runtime": 1124.1861, | |
| "eval_samples_per_second": 54.358, | |
| "eval_steps_per_second": 1.699, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 4.906740027510316e-07, | |
| "loss": 0.1419, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "learning_rate": 4.882668500687758e-07, | |
| "loss": 0.1434, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "eval_accuracy": 0.9370796445695396, | |
| "eval_f1": 0.9154200976052094, | |
| "eval_loss": 0.1648997962474823, | |
| "eval_matthews_correlation": 0.8697098635796452, | |
| "eval_precision": 0.9230816943100145, | |
| "eval_recall": 0.9086611768001123, | |
| "eval_runtime": 1148.703, | |
| "eval_samples_per_second": 53.198, | |
| "eval_steps_per_second": 1.663, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 4.8585969738652e-07, | |
| "loss": 0.1439, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 4.834525447042641e-07, | |
| "loss": 0.1421, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "eval_accuracy": 0.9374232928046605, | |
| "eval_f1": 0.9159962475642537, | |
| "eval_loss": 0.16433577239513397, | |
| "eval_matthews_correlation": 0.8705984477158324, | |
| "eval_precision": 0.9223208386659031, | |
| "eval_recall": 0.9104375438916276, | |
| "eval_runtime": 1138.7887, | |
| "eval_samples_per_second": 53.661, | |
| "eval_steps_per_second": 1.677, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 21.49, | |
| "learning_rate": 4.810453920220083e-07, | |
| "loss": 0.1386, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 4.786382393397524e-07, | |
| "loss": 0.1383, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "eval_accuracy": 0.9377669410397814, | |
| "eval_f1": 0.9154593212298457, | |
| "eval_loss": 0.16332927346229553, | |
| "eval_matthews_correlation": 0.8708321918919477, | |
| "eval_precision": 0.9264808218886014, | |
| "eval_recall": 0.9061723895970233, | |
| "eval_runtime": 1130.5862, | |
| "eval_samples_per_second": 54.051, | |
| "eval_steps_per_second": 1.689, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 4.7623108665749656e-07, | |
| "loss": 0.144, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 4.7382393397524066e-07, | |
| "loss": 0.137, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "eval_accuracy": 0.937325107594626, | |
| "eval_f1": 0.9155487613959368, | |
| "eval_loss": 0.1631198674440384, | |
| "eval_matthews_correlation": 0.8701584028013903, | |
| "eval_precision": 0.9238303074503852, | |
| "eval_recall": 0.9083409162157898, | |
| "eval_runtime": 1138.2164, | |
| "eval_samples_per_second": 53.688, | |
| "eval_steps_per_second": 1.678, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "learning_rate": 4.714167812929848e-07, | |
| "loss": 0.1446, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 4.69009628610729e-07, | |
| "loss": 0.1387, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "eval_accuracy": 0.9385851511234025, | |
| "eval_f1": 0.9166627207954582, | |
| "eval_loss": 0.1620563566684723, | |
| "eval_matthews_correlation": 0.8725817378443448, | |
| "eval_precision": 0.9271811452031979, | |
| "eval_recall": 0.9077409974100349, | |
| "eval_runtime": 1145.5718, | |
| "eval_samples_per_second": 53.344, | |
| "eval_steps_per_second": 1.667, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 22.77, | |
| "learning_rate": 4.6660247592847314e-07, | |
| "loss": 0.1367, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "learning_rate": 4.641953232462173e-07, | |
| "loss": 0.1369, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.9383396880983161, | |
| "eval_f1": 0.9172324787033365, | |
| "eval_loss": 0.1618376225233078, | |
| "eval_matthews_correlation": 0.8723936452197988, | |
| "eval_precision": 0.9243962275737605, | |
| "eval_recall": 0.9109134783912377, | |
| "eval_runtime": 1141.2693, | |
| "eval_samples_per_second": 53.545, | |
| "eval_steps_per_second": 1.674, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 4.617881705639615e-07, | |
| "loss": 0.1348, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 4.5938101788170567e-07, | |
| "loss": 0.1378, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "eval_accuracy": 0.9388797067535061, | |
| "eval_f1": 0.9170030704594044, | |
| "eval_loss": 0.16103394329547882, | |
| "eval_matthews_correlation": 0.8732414480101915, | |
| "eval_precision": 0.9272751714823327, | |
| "eval_recall": 0.908404227472793, | |
| "eval_runtime": 1131.6065, | |
| "eval_samples_per_second": 54.002, | |
| "eval_steps_per_second": 1.688, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 4.569738651994498e-07, | |
| "loss": 0.1375, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 4.5456671251719393e-07, | |
| "loss": 0.1366, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "eval_accuracy": 0.9389451635601958, | |
| "eval_f1": 0.9178736477228994, | |
| "eval_loss": 0.16072671115398407, | |
| "eval_matthews_correlation": 0.8736416443228668, | |
| "eval_precision": 0.9252270842575737, | |
| "eval_recall": 0.9114700960342543, | |
| "eval_runtime": 1137.3148, | |
| "eval_samples_per_second": 53.731, | |
| "eval_steps_per_second": 1.679, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 4.521595598349381e-07, | |
| "loss": 0.1356, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.4975240715268225e-07, | |
| "loss": 0.1348, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "eval_accuracy": 0.9389287993585232, | |
| "eval_f1": 0.9184615824628515, | |
| "eval_loss": 0.16080142557621002, | |
| "eval_matthews_correlation": 0.8739011778237431, | |
| "eval_precision": 0.9233816839860781, | |
| "eval_recall": 0.9140549878602235, | |
| "eval_runtime": 1135.8462, | |
| "eval_samples_per_second": 53.8, | |
| "eval_steps_per_second": 1.682, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 24.47, | |
| "learning_rate": 4.4734525447042636e-07, | |
| "loss": 0.1331, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 24.68, | |
| "learning_rate": 4.449381017881705e-07, | |
| "loss": 0.1318, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 24.68, | |
| "eval_accuracy": 0.9396324600304374, | |
| "eval_f1": 0.9179972413838614, | |
| "eval_loss": 0.1595466136932373, | |
| "eval_matthews_correlation": 0.874736229093411, | |
| "eval_precision": 0.9290778467923758, | |
| "eval_recall": 0.9086960867914774, | |
| "eval_runtime": 1138.0648, | |
| "eval_samples_per_second": 53.696, | |
| "eval_steps_per_second": 1.678, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 4.425309491059147e-07, | |
| "loss": 0.133, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 4.4012379642365883e-07, | |
| "loss": 0.133, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "eval_accuracy": 0.9398942872571961, | |
| "eval_f1": 0.9190977119048673, | |
| "eval_loss": 0.1590360403060913, | |
| "eval_matthews_correlation": 0.8755172814743742, | |
| "eval_precision": 0.9272724566504644, | |
| "eval_recall": 0.9119361728726462, | |
| "eval_runtime": 1134.5021, | |
| "eval_samples_per_second": 53.864, | |
| "eval_steps_per_second": 1.684, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 4.37716643741403e-07, | |
| "loss": 0.1335, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 4.353094910591472e-07, | |
| "loss": 0.1314, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "eval_accuracy": 0.9395015464170581, | |
| "eval_f1": 0.9190581177761091, | |
| "eval_loss": 0.1591825634241104, | |
| "eval_matthews_correlation": 0.8750075920131161, | |
| "eval_precision": 0.9245997125950819, | |
| "eval_recall": 0.9141288069140882, | |
| "eval_runtime": 1127.6358, | |
| "eval_samples_per_second": 54.192, | |
| "eval_steps_per_second": 1.694, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "learning_rate": 4.3290233837689136e-07, | |
| "loss": 0.1312, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 25.96, | |
| "learning_rate": 4.30519257221458e-07, | |
| "loss": 0.1321, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 25.96, | |
| "eval_accuracy": 0.9405324911224205, | |
| "eval_f1": 0.9189856286227304, | |
| "eval_loss": 0.1582149714231491, | |
| "eval_matthews_correlation": 0.8765464055444899, | |
| "eval_precision": 0.9312260325323165, | |
| "eval_recall": 0.9088528341675056, | |
| "eval_runtime": 1128.8638, | |
| "eval_samples_per_second": 54.133, | |
| "eval_steps_per_second": 1.692, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 26.17, | |
| "learning_rate": 4.2811210453920216e-07, | |
| "loss": 0.1296, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 4.257049518569464e-07, | |
| "loss": 0.129, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "eval_accuracy": 0.9404997627190758, | |
| "eval_f1": 0.9200009556213352, | |
| "eval_loss": 0.15780366957187653, | |
| "eval_matthews_correlation": 0.8768428582724813, | |
| "eval_precision": 0.9276058379537663, | |
| "eval_recall": 0.9133484566347269, | |
| "eval_runtime": 1119.4943, | |
| "eval_samples_per_second": 54.586, | |
| "eval_steps_per_second": 1.706, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 26.6, | |
| "learning_rate": 4.2329779917469053e-07, | |
| "loss": 0.1322, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "learning_rate": 4.2089064649243464e-07, | |
| "loss": 0.1274, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "eval_accuracy": 0.9409579603659035, | |
| "eval_f1": 0.9200809083075646, | |
| "eval_loss": 0.15745599567890167, | |
| "eval_matthews_correlation": 0.8775856097831178, | |
| "eval_precision": 0.9300727450861266, | |
| "eval_recall": 0.9115769049685479, | |
| "eval_runtime": 1129.8115, | |
| "eval_samples_per_second": 54.088, | |
| "eval_steps_per_second": 1.691, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.184834938101788e-07, | |
| "loss": 0.1298, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 4.1607634112792296e-07, | |
| "loss": 0.1229, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "eval_accuracy": 0.9406797689374724, | |
| "eval_f1": 0.9207006984009518, | |
| "eval_loss": 0.15740837156772614, | |
| "eval_matthews_correlation": 0.8774253242767724, | |
| "eval_precision": 0.9264401397553, | |
| "eval_recall": 0.915588980453698, | |
| "eval_runtime": 1120.579, | |
| "eval_samples_per_second": 54.533, | |
| "eval_steps_per_second": 1.704, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 4.136691884456671e-07, | |
| "loss": 0.1288, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "learning_rate": 4.112620357634113e-07, | |
| "loss": 0.1297, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 27.66, | |
| "eval_accuracy": 0.9410070529709208, | |
| "eval_f1": 0.9195664023927276, | |
| "eval_loss": 0.15692035853862762, | |
| "eval_matthews_correlation": 0.8774949999573018, | |
| "eval_precision": 0.9325444450940837, | |
| "eval_recall": 0.9088784383760194, | |
| "eval_runtime": 1122.3792, | |
| "eval_samples_per_second": 54.446, | |
| "eval_steps_per_second": 1.702, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 27.87, | |
| "learning_rate": 4.088548830811554e-07, | |
| "loss": 0.1294, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 4.0644773039889954e-07, | |
| "loss": 0.127, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "eval_accuracy": 0.9410725097776105, | |
| "eval_f1": 0.9215107403838404, | |
| "eval_loss": 0.15686339139938354, | |
| "eval_matthews_correlation": 0.8783377225875042, | |
| "eval_precision": 0.9264187923955762, | |
| "eval_recall": 0.9170523743755302, | |
| "eval_runtime": 1130.091, | |
| "eval_samples_per_second": 54.074, | |
| "eval_steps_per_second": 1.69, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 4.040405777166437e-07, | |
| "loss": 0.1283, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 4.0163342503438786e-07, | |
| "loss": 0.1277, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "eval_accuracy": 0.9413343370043692, | |
| "eval_f1": 0.9206744312110247, | |
| "eval_loss": 0.15601210296154022, | |
| "eval_matthews_correlation": 0.8783752668296679, | |
| "eval_precision": 0.9305381948772499, | |
| "eval_recall": 0.9122284555164281, | |
| "eval_runtime": 1130.3041, | |
| "eval_samples_per_second": 54.064, | |
| "eval_steps_per_second": 1.69, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 28.72, | |
| "learning_rate": 3.9922627235213207e-07, | |
| "loss": 0.1253, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "learning_rate": 3.9681911966987623e-07, | |
| "loss": 0.1207, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "eval_accuracy": 0.9411379665843002, | |
| "eval_f1": 0.9214834197039864, | |
| "eval_loss": 0.1558128446340561, | |
| "eval_matthews_correlation": 0.8783956105526514, | |
| "eval_precision": 0.926977605882486, | |
| "eval_recall": 0.9164881442500526, | |
| "eval_runtime": 1129.013, | |
| "eval_samples_per_second": 54.126, | |
| "eval_steps_per_second": 1.692, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 29.15, | |
| "learning_rate": 3.9441196698762033e-07, | |
| "loss": 0.126, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 3.920048143053645e-07, | |
| "loss": 0.1233, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "eval_accuracy": 0.9414652506177487, | |
| "eval_f1": 0.9214108705582076, | |
| "eval_loss": 0.155442476272583, | |
| "eval_matthews_correlation": 0.8788308394514168, | |
| "eval_precision": 0.9290811733963565, | |
| "eval_recall": 0.9146004475707356, | |
| "eval_runtime": 1139.9159, | |
| "eval_samples_per_second": 53.608, | |
| "eval_steps_per_second": 1.676, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 3.8959766162310865e-07, | |
| "loss": 0.1231, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "learning_rate": 3.871905089408528e-07, | |
| "loss": 0.1263, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "eval_accuracy": 0.9417598062478522, | |
| "eval_f1": 0.9216422791525614, | |
| "eval_loss": 0.15486527979373932, | |
| "eval_matthews_correlation": 0.8794389554648475, | |
| "eval_precision": 0.9295396447855918, | |
| "eval_recall": 0.9147710213831234, | |
| "eval_runtime": 1125.9339, | |
| "eval_samples_per_second": 54.274, | |
| "eval_steps_per_second": 1.696, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.8478335625859697e-07, | |
| "loss": 0.1245, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 3.823762035763411e-07, | |
| "loss": 0.1237, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "eval_accuracy": 0.9416288926344728, | |
| "eval_f1": 0.9223605864239737, | |
| "eval_loss": 0.15512850880622864, | |
| "eval_matthews_correlation": 0.8795357475488215, | |
| "eval_precision": 0.9269163530437144, | |
| "eval_recall": 0.9182071872279179, | |
| "eval_runtime": 1104.6568, | |
| "eval_samples_per_second": 55.319, | |
| "eval_steps_per_second": 1.729, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 3.7996905089408523e-07, | |
| "loss": 0.1227, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "learning_rate": 3.775618982118294e-07, | |
| "loss": 0.1223, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "eval_accuracy": 0.9419725408695937, | |
| "eval_f1": 0.9224586705089605, | |
| "eval_loss": 0.1544523686170578, | |
| "eval_matthews_correlation": 0.8800542555052714, | |
| "eval_precision": 0.9285558015982011, | |
| "eval_recall": 0.9169498289882058, | |
| "eval_runtime": 1103.5815, | |
| "eval_samples_per_second": 55.373, | |
| "eval_steps_per_second": 1.731, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "learning_rate": 3.7515474552957355e-07, | |
| "loss": 0.122, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "learning_rate": 3.7274759284731776e-07, | |
| "loss": 0.1223, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 31.06, | |
| "eval_accuracy": 0.9423980101130767, | |
| "eval_f1": 0.9223331133049456, | |
| "eval_loss": 0.15414074063301086, | |
| "eval_matthews_correlation": 0.8806243664613724, | |
| "eval_precision": 0.9317093562981557, | |
| "eval_recall": 0.9142028224825047, | |
| "eval_runtime": 1127.3394, | |
| "eval_samples_per_second": 54.206, | |
| "eval_steps_per_second": 1.694, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 3.703404401650619e-07, | |
| "loss": 0.1222, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "learning_rate": 3.6795735900962856e-07, | |
| "loss": 0.121, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 31.49, | |
| "eval_accuracy": 0.9424143743147491, | |
| "eval_f1": 0.9226743391675636, | |
| "eval_loss": 0.15365062654018402, | |
| "eval_matthews_correlation": 0.8807922676782367, | |
| "eval_precision": 0.9305864010842684, | |
| "eval_recall": 0.9157406855938447, | |
| "eval_runtime": 1096.9802, | |
| "eval_samples_per_second": 55.707, | |
| "eval_steps_per_second": 1.741, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 3.655502063273727e-07, | |
| "loss": 0.1198, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 3.6314305364511693e-07, | |
| "loss": 0.1198, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "eval_accuracy": 0.9423652817097318, | |
| "eval_f1": 0.9218109899084128, | |
| "eval_loss": 0.15379200875759125, | |
| "eval_matthews_correlation": 0.8804685582055614, | |
| "eval_precision": 0.9326720200447173, | |
| "eval_recall": 0.9126828528399417, | |
| "eval_runtime": 1105.4205, | |
| "eval_samples_per_second": 55.281, | |
| "eval_steps_per_second": 1.728, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 3.607359009628611e-07, | |
| "loss": 0.1193, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 3.5832874828060525e-07, | |
| "loss": 0.1193, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "eval_accuracy": 0.9424961953231111, | |
| "eval_f1": 0.9231857675285348, | |
| "eval_loss": 0.15343151986598969, | |
| "eval_matthews_correlation": 0.8811431437323947, | |
| "eval_precision": 0.9293213427686996, | |
| "eval_recall": 0.9176996310804476, | |
| "eval_runtime": 1124.2062, | |
| "eval_samples_per_second": 54.357, | |
| "eval_steps_per_second": 1.699, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 3.5592159559834936e-07, | |
| "loss": 0.1194, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "learning_rate": 3.535144429160935e-07, | |
| "loss": 0.1215, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "eval_accuracy": 0.9421198186846454, | |
| "eval_f1": 0.9235682615682063, | |
| "eval_loss": 0.15412107110023499, | |
| "eval_matthews_correlation": 0.8809311583014519, | |
| "eval_precision": 0.9255101036658555, | |
| "eval_recall": 0.9217672088255878, | |
| "eval_runtime": 1116.4465, | |
| "eval_samples_per_second": 54.735, | |
| "eval_steps_per_second": 1.711, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 3.511072902338377e-07, | |
| "loss": 0.1168, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.4870013755158183e-07, | |
| "loss": 0.1177, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "eval_accuracy": 0.9427252941465251, | |
| "eval_f1": 0.9240914268595931, | |
| "eval_loss": 0.15340538322925568, | |
| "eval_matthews_correlation": 0.8819306422216652, | |
| "eval_precision": 0.9276927357523115, | |
| "eval_recall": 0.9207421406121524, | |
| "eval_runtime": 1132.2669, | |
| "eval_samples_per_second": 53.97, | |
| "eval_steps_per_second": 1.687, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.46292984869326e-07, | |
| "loss": 0.1177, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 33.62, | |
| "learning_rate": 3.4388583218707015e-07, | |
| "loss": 0.1158, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 33.62, | |
| "eval_accuracy": 0.9428725719615768, | |
| "eval_f1": 0.9230758188747847, | |
| "eval_loss": 0.152634397149086, | |
| "eval_matthews_correlation": 0.8817097283454953, | |
| "eval_precision": 0.9314416673623378, | |
| "eval_recall": 0.9158101125474704, | |
| "eval_runtime": 1135.4508, | |
| "eval_samples_per_second": 53.819, | |
| "eval_steps_per_second": 1.682, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 3.414786795048143e-07, | |
| "loss": 0.1204, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "learning_rate": 3.3907152682255847e-07, | |
| "loss": 0.1162, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 34.04, | |
| "eval_accuracy": 0.9432980412050598, | |
| "eval_f1": 0.9240152122705202, | |
| "eval_loss": 0.1521940678358078, | |
| "eval_matthews_correlation": 0.8826973056971621, | |
| "eval_precision": 0.931184031044368, | |
| "eval_recall": 0.9176525879531132, | |
| "eval_runtime": 1108.668, | |
| "eval_samples_per_second": 55.119, | |
| "eval_steps_per_second": 1.723, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "learning_rate": 3.3666437414030257e-07, | |
| "loss": 0.1166, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "learning_rate": 3.3425722145804673e-07, | |
| "loss": 0.1147, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 34.47, | |
| "eval_accuracy": 0.9433962264150944, | |
| "eval_f1": 0.9241868328582813, | |
| "eval_loss": 0.15216147899627686, | |
| "eval_matthews_correlation": 0.8829792231347647, | |
| "eval_precision": 0.9306640302786223, | |
| "eval_recall": 0.9184527518121871, | |
| "eval_runtime": 1132.2249, | |
| "eval_samples_per_second": 53.972, | |
| "eval_steps_per_second": 1.687, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 34.68, | |
| "learning_rate": 3.3185006877579094e-07, | |
| "loss": 0.1144, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "learning_rate": 3.2944291609353505e-07, | |
| "loss": 0.1172, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "eval_accuracy": 0.943576232633491, | |
| "eval_f1": 0.9243561247442994, | |
| "eval_loss": 0.15176311135292053, | |
| "eval_matthews_correlation": 0.8833109156622424, | |
| "eval_precision": 0.9312279042987696, | |
| "eval_recall": 0.9182818529319778, | |
| "eval_runtime": 1127.5884, | |
| "eval_samples_per_second": 54.194, | |
| "eval_steps_per_second": 1.694, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 3.270357634112792e-07, | |
| "loss": 0.1184, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "learning_rate": 3.2462861072902337e-07, | |
| "loss": 0.1185, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "eval_accuracy": 0.9433471338100771, | |
| "eval_f1": 0.9235180133752681, | |
| "eval_loss": 0.1514737904071808, | |
| "eval_matthews_correlation": 0.8825807929321668, | |
| "eval_precision": 0.9332458708783546, | |
| "eval_recall": 0.9151356262949316, | |
| "eval_runtime": 1129.6017, | |
| "eval_samples_per_second": 54.098, | |
| "eval_steps_per_second": 1.691, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 3.222214580467675e-07, | |
| "loss": 0.1162, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "learning_rate": 3.198143053645117e-07, | |
| "loss": 0.1116, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "eval_accuracy": 0.943461683221784, | |
| "eval_f1": 0.9242074753818227, | |
| "eval_loss": 0.15152059495449066, | |
| "eval_matthews_correlation": 0.8830141159932162, | |
| "eval_precision": 0.9315726012507216, | |
| "eval_recall": 0.9176551581996923, | |
| "eval_runtime": 1106.75, | |
| "eval_samples_per_second": 55.215, | |
| "eval_steps_per_second": 1.726, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 35.96, | |
| "learning_rate": 3.1740715268225584e-07, | |
| "loss": 0.113, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "learning_rate": 3.1502407152682254e-07, | |
| "loss": 0.1132, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 36.17, | |
| "eval_accuracy": 0.9433307696084047, | |
| "eval_f1": 0.923392580714841, | |
| "eval_loss": 0.1517263650894165, | |
| "eval_matthews_correlation": 0.8825102281931411, | |
| "eval_precision": 0.933593905999869, | |
| "eval_recall": 0.9146349342370028, | |
| "eval_runtime": 1132.4177, | |
| "eval_samples_per_second": 53.963, | |
| "eval_steps_per_second": 1.687, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 3.126169188445667e-07, | |
| "loss": 0.1127, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "learning_rate": 3.1020976616231086e-07, | |
| "loss": 0.1155, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "eval_accuracy": 0.9438707882635946, | |
| "eval_f1": 0.9249328530871743, | |
| "eval_loss": 0.15113794803619385, | |
| "eval_matthews_correlation": 0.8839614616032178, | |
| "eval_precision": 0.9313619229067885, | |
| "eval_recall": 0.9191784464817534, | |
| "eval_runtime": 1121.0877, | |
| "eval_samples_per_second": 54.509, | |
| "eval_steps_per_second": 1.704, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 36.81, | |
| "learning_rate": 3.07802613480055e-07, | |
| "loss": 0.1144, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 3.053954607977992e-07, | |
| "loss": 0.1105, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.9439689734736291, | |
| "eval_f1": 0.9247302421488585, | |
| "eval_loss": 0.15101274847984314, | |
| "eval_matthews_correlation": 0.8840791715082791, | |
| "eval_precision": 0.9321543176187953, | |
| "eval_recall": 0.9182413488263638, | |
| "eval_runtime": 1117.9497, | |
| "eval_samples_per_second": 54.662, | |
| "eval_steps_per_second": 1.708, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 3.0298830811554333e-07, | |
| "loss": 0.1121, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 3.0058115543328744e-07, | |
| "loss": 0.1103, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "eval_accuracy": 0.9438544240619221, | |
| "eval_f1": 0.9248424621748557, | |
| "eval_loss": 0.15083517134189606, | |
| "eval_matthews_correlation": 0.8839318423708653, | |
| "eval_precision": 0.9312687941809888, | |
| "eval_recall": 0.9191185521215243, | |
| "eval_runtime": 1136.279, | |
| "eval_samples_per_second": 53.78, | |
| "eval_steps_per_second": 1.681, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 37.66, | |
| "learning_rate": 2.981740027510316e-07, | |
| "loss": 0.1168, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "learning_rate": 2.9576685006877576e-07, | |
| "loss": 0.1104, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "eval_accuracy": 0.944001701876974, | |
| "eval_f1": 0.9255109565953598, | |
| "eval_loss": 0.15076182782649994, | |
| "eval_matthews_correlation": 0.8844550049466842, | |
| "eval_precision": 0.9300012352177646, | |
| "eval_recall": 0.9214207921543845, | |
| "eval_runtime": 1114.2003, | |
| "eval_samples_per_second": 54.846, | |
| "eval_steps_per_second": 1.714, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 2.9335969738651997e-07, | |
| "loss": 0.1111, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 2.9095254470426407e-07, | |
| "loss": 0.1134, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "eval_accuracy": 0.9439362450702843, | |
| "eval_f1": 0.9253671889189082, | |
| "eval_loss": 0.1507214605808258, | |
| "eval_matthews_correlation": 0.8842287570521736, | |
| "eval_precision": 0.9305811742807507, | |
| "eval_recall": 0.9206107706340921, | |
| "eval_runtime": 1111.784, | |
| "eval_samples_per_second": 54.965, | |
| "eval_steps_per_second": 1.718, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 38.51, | |
| "learning_rate": 2.8856946354883077e-07, | |
| "loss": 0.1089, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "learning_rate": 2.8616231086657493e-07, | |
| "loss": 0.1106, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 38.72, | |
| "eval_accuracy": 0.9441162512886809, | |
| "eval_f1": 0.9251360377006875, | |
| "eval_loss": 0.15033245086669922, | |
| "eval_matthews_correlation": 0.8843929494825783, | |
| "eval_precision": 0.9323618927884416, | |
| "eval_recall": 0.9187285395157545, | |
| "eval_runtime": 1121.674, | |
| "eval_samples_per_second": 54.48, | |
| "eval_steps_per_second": 1.703, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 38.94, | |
| "learning_rate": 2.8375515818431914e-07, | |
| "loss": 0.1114, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "learning_rate": 2.8134800550206325e-07, | |
| "loss": 0.1095, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 39.15, | |
| "eval_accuracy": 0.943887152465267, | |
| "eval_f1": 0.9255818230394176, | |
| "eval_loss": 0.15064190328121185, | |
| "eval_matthews_correlation": 0.8842602118056405, | |
| "eval_precision": 0.9297138876991945, | |
| "eval_recall": 0.9217534806465043, | |
| "eval_runtime": 1127.018, | |
| "eval_samples_per_second": 54.222, | |
| "eval_steps_per_second": 1.695, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 39.36, | |
| "learning_rate": 2.789408528198074e-07, | |
| "loss": 0.11, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 2.7653370013755156e-07, | |
| "loss": 0.1122, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "eval_accuracy": 0.9441489796920257, | |
| "eval_f1": 0.9250135407540009, | |
| "eval_loss": 0.14996594190597534, | |
| "eval_matthews_correlation": 0.884420266208998, | |
| "eval_precision": 0.9326893583639841, | |
| "eval_recall": 0.9182519548805012, | |
| "eval_runtime": 1113.4663, | |
| "eval_samples_per_second": 54.882, | |
| "eval_steps_per_second": 1.715, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 39.79, | |
| "learning_rate": 2.741265474552957e-07, | |
| "loss": 0.1083, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.717193947730399e-07, | |
| "loss": 0.1104, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9440180660786464, | |
| "eval_f1": 0.9253930021308615, | |
| "eval_loss": 0.15009328722953796, | |
| "eval_matthews_correlation": 0.8844160433170132, | |
| "eval_precision": 0.9304927678821387, | |
| "eval_recall": 0.920780596053561, | |
| "eval_runtime": 1131.9242, | |
| "eval_samples_per_second": 53.987, | |
| "eval_steps_per_second": 1.687, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 40.21, | |
| "learning_rate": 2.6931224209078404e-07, | |
| "loss": 0.1095, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 2.669050894085282e-07, | |
| "loss": 0.1099, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "eval_accuracy": 0.9441817080953706, | |
| "eval_f1": 0.9259059644722075, | |
| "eval_loss": 0.15028244256973267, | |
| "eval_matthews_correlation": 0.8848699358673907, | |
| "eval_precision": 0.9300530378191784, | |
| "eval_recall": 0.9221055593932391, | |
| "eval_runtime": 1133.4466, | |
| "eval_samples_per_second": 53.914, | |
| "eval_steps_per_second": 1.685, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 40.64, | |
| "learning_rate": 2.6449793672627236e-07, | |
| "loss": 0.105, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 2.6209078404401646e-07, | |
| "loss": 0.1098, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "eval_accuracy": 0.944198072297043, | |
| "eval_f1": 0.9254187143519279, | |
| "eval_loss": 0.14963504672050476, | |
| "eval_matthews_correlation": 0.8846911439559728, | |
| "eval_precision": 0.9313966189199636, | |
| "eval_recall": 0.9200651823703107, | |
| "eval_runtime": 1146.6556, | |
| "eval_samples_per_second": 53.293, | |
| "eval_steps_per_second": 1.666, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 41.06, | |
| "learning_rate": 2.596836313617606e-07, | |
| "loss": 0.1087, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 2.5727647867950483e-07, | |
| "loss": 0.1105, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "eval_accuracy": 0.9444435353221293, | |
| "eval_f1": 0.9256968337682165, | |
| "eval_loss": 0.14939628541469574, | |
| "eval_matthews_correlation": 0.8851581931672046, | |
| "eval_precision": 0.9320685204142367, | |
| "eval_recall": 0.920004214549341, | |
| "eval_runtime": 1134.2905, | |
| "eval_samples_per_second": 53.874, | |
| "eval_steps_per_second": 1.684, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "learning_rate": 2.5486932599724894e-07, | |
| "loss": 0.1053, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "learning_rate": 2.524621733149931e-07, | |
| "loss": 0.1085, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "eval_accuracy": 0.9446726341455433, | |
| "eval_f1": 0.925738034839588, | |
| "eval_loss": 0.14932939410209656, | |
| "eval_matthews_correlation": 0.8854889075253487, | |
| "eval_precision": 0.9336149730127167, | |
| "eval_recall": 0.9187943227620606, | |
| "eval_runtime": 1117.9194, | |
| "eval_samples_per_second": 54.663, | |
| "eval_steps_per_second": 1.709, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 41.91, | |
| "learning_rate": 2.5005502063273726e-07, | |
| "loss": 0.1062, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 2.476478679504814e-07, | |
| "loss": 0.108, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "eval_accuracy": 0.9447217267505604, | |
| "eval_f1": 0.9262048825799548, | |
| "eval_loss": 0.1495121866464615, | |
| "eval_matthews_correlation": 0.8858026294978001, | |
| "eval_precision": 0.9319552420338207, | |
| "eval_recall": 0.9210483479495699, | |
| "eval_runtime": 1115.2527, | |
| "eval_samples_per_second": 54.794, | |
| "eval_steps_per_second": 1.713, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 42.34, | |
| "learning_rate": 2.4524071526822557e-07, | |
| "loss": 0.1076, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "learning_rate": 2.4283356258596973e-07, | |
| "loss": 0.1044, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "eval_accuracy": 0.944508992128819, | |
| "eval_f1": 0.9261252498145538, | |
| "eval_loss": 0.14950193464756012, | |
| "eval_matthews_correlation": 0.8854199049552949, | |
| "eval_precision": 0.9313193606961945, | |
| "eval_recall": 0.9214106094253447, | |
| "eval_runtime": 1130.1649, | |
| "eval_samples_per_second": 54.071, | |
| "eval_steps_per_second": 1.69, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 42.77, | |
| "learning_rate": 2.404264099037139e-07, | |
| "loss": 0.106, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "learning_rate": 2.3801925722145802e-07, | |
| "loss": 0.1076, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "eval_accuracy": 0.9446562699438708, | |
| "eval_f1": 0.9261296033746204, | |
| "eval_loss": 0.14920221269130707, | |
| "eval_matthews_correlation": 0.8855912047264707, | |
| "eval_precision": 0.9324907409462333, | |
| "eval_recall": 0.9203679728109541, | |
| "eval_runtime": 1137.936, | |
| "eval_samples_per_second": 53.702, | |
| "eval_steps_per_second": 1.678, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.3561210453920218e-07, | |
| "loss": 0.107, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 2.3320495185694637e-07, | |
| "loss": 0.1044, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "eval_accuracy": 0.9445417205321638, | |
| "eval_f1": 0.9266300766293115, | |
| "eval_loss": 0.1497085839509964, | |
| "eval_matthews_correlation": 0.8857559939442303, | |
| "eval_precision": 0.9296997536026302, | |
| "eval_recall": 0.9237603159106365, | |
| "eval_runtime": 1136.0812, | |
| "eval_samples_per_second": 53.789, | |
| "eval_steps_per_second": 1.681, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 43.62, | |
| "learning_rate": 2.307977991746905e-07, | |
| "loss": 0.105, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 43.83, | |
| "learning_rate": 2.2839064649243466e-07, | |
| "loss": 0.1055, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 43.83, | |
| "eval_accuracy": 0.9446889983472156, | |
| "eval_f1": 0.9266109603225074, | |
| "eval_loss": 0.14924582839012146, | |
| "eval_matthews_correlation": 0.8859684030602588, | |
| "eval_precision": 0.9303740597513821, | |
| "eval_recall": 0.9231584769939456, | |
| "eval_runtime": 1125.8192, | |
| "eval_samples_per_second": 54.28, | |
| "eval_steps_per_second": 1.697, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 44.04, | |
| "learning_rate": 2.2598349381017882e-07, | |
| "loss": 0.1065, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 2.2357634112792295e-07, | |
| "loss": 0.1043, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "eval_accuracy": 0.9446071773388536, | |
| "eval_f1": 0.9263262351610323, | |
| "eval_loss": 0.14892685413360596, | |
| "eval_matthews_correlation": 0.8856938722284602, | |
| "eval_precision": 0.9309299279423926, | |
| "eval_recall": 0.9221329854554128, | |
| "eval_runtime": 1129.4248, | |
| "eval_samples_per_second": 54.106, | |
| "eval_steps_per_second": 1.691, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 2.211691884456671e-07, | |
| "loss": 0.1029, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "learning_rate": 2.187620357634113e-07, | |
| "loss": 0.1042, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "eval_accuracy": 0.944705362548888, | |
| "eval_f1": 0.9260999899887844, | |
| "eval_loss": 0.1488848179578781, | |
| "eval_matthews_correlation": 0.8857253503507664, | |
| "eval_precision": 0.9322554110387342, | |
| "eval_recall": 0.9205995144443117, | |
| "eval_runtime": 1114.3176, | |
| "eval_samples_per_second": 54.84, | |
| "eval_steps_per_second": 1.714, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 2.1635488308115542e-07, | |
| "loss": 0.1076, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "learning_rate": 2.1394773039889958e-07, | |
| "loss": 0.1024, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 45.11, | |
| "eval_accuracy": 0.9449508255739744, | |
| "eval_f1": 0.9260476048473397, | |
| "eval_loss": 0.1487448662519455, | |
| "eval_matthews_correlation": 0.8860574300049961, | |
| "eval_precision": 0.9340386476068, | |
| "eval_recall": 0.9190087193195606, | |
| "eval_runtime": 1127.35, | |
| "eval_samples_per_second": 54.206, | |
| "eval_steps_per_second": 1.694, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 2.1154057771664372e-07, | |
| "loss": 0.1038, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "learning_rate": 2.0913342503438787e-07, | |
| "loss": 0.1053, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 45.53, | |
| "eval_accuracy": 0.9449671897756468, | |
| "eval_f1": 0.9266078787740653, | |
| "eval_loss": 0.14872543513774872, | |
| "eval_matthews_correlation": 0.8863451628405484, | |
| "eval_precision": 0.9320275040537918, | |
| "eval_recall": 0.9217133998659879, | |
| "eval_runtime": 1121.4402, | |
| "eval_samples_per_second": 54.492, | |
| "eval_steps_per_second": 1.703, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 45.74, | |
| "learning_rate": 2.0672627235213206e-07, | |
| "loss": 0.1037, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 45.96, | |
| "learning_rate": 2.0431911966987622e-07, | |
| "loss": 0.1023, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 45.96, | |
| "eval_accuracy": 0.9447871835572501, | |
| "eval_f1": 0.9262474411932805, | |
| "eval_loss": 0.1485784500837326, | |
| "eval_matthews_correlation": 0.8859042819526408, | |
| "eval_precision": 0.9322667829591439, | |
| "eval_recall": 0.9208211984164509, | |
| "eval_runtime": 1107.2279, | |
| "eval_samples_per_second": 55.191, | |
| "eval_steps_per_second": 1.725, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 46.17, | |
| "learning_rate": 2.0191196698762035e-07, | |
| "loss": 0.1039, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 1.995048143053645e-07, | |
| "loss": 0.1037, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "eval_accuracy": 0.9448362761622674, | |
| "eval_f1": 0.926612727616941, | |
| "eval_loss": 0.14873600006103516, | |
| "eval_matthews_correlation": 0.8861794892897553, | |
| "eval_precision": 0.9311237661981897, | |
| "eval_recall": 0.9225047795245841, | |
| "eval_runtime": 1134.6231, | |
| "eval_samples_per_second": 53.858, | |
| "eval_steps_per_second": 1.683, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "learning_rate": 1.9709766162310864e-07, | |
| "loss": 0.1029, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "learning_rate": 1.946905089408528e-07, | |
| "loss": 0.1046, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "eval_accuracy": 0.944819911960595, | |
| "eval_f1": 0.9266815604872392, | |
| "eval_loss": 0.14862757921218872, | |
| "eval_matthews_correlation": 0.8861793421063061, | |
| "eval_precision": 0.9309033406756093, | |
| "eval_recall": 0.922807895033049, | |
| "eval_runtime": 1129.167, | |
| "eval_samples_per_second": 54.119, | |
| "eval_steps_per_second": 1.692, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 1.9230742778541952e-07, | |
| "loss": 0.1012, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "learning_rate": 1.8990027510316368e-07, | |
| "loss": 0.1027, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 47.23, | |
| "eval_accuracy": 0.9451144675906986, | |
| "eval_f1": 0.9268280716567586, | |
| "eval_loss": 0.1484626680612564, | |
| "eval_matthews_correlation": 0.8866650411840761, | |
| "eval_precision": 0.9320985784552063, | |
| "eval_recall": 0.922045014897367, | |
| "eval_runtime": 1111.3061, | |
| "eval_samples_per_second": 54.988, | |
| "eval_steps_per_second": 1.719, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 1.8749312242090781e-07, | |
| "loss": 0.1015, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "learning_rate": 1.8508596973865197e-07, | |
| "loss": 0.1013, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "eval_accuracy": 0.9451144675906986, | |
| "eval_f1": 0.9269906309252122, | |
| "eval_loss": 0.14851711690425873, | |
| "eval_matthews_correlation": 0.8867653549869635, | |
| "eval_precision": 0.9314070719703338, | |
| "eval_recall": 0.9229525395691017, | |
| "eval_runtime": 1067.1147, | |
| "eval_samples_per_second": 57.266, | |
| "eval_steps_per_second": 1.79, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "learning_rate": 1.8267881705639616e-07, | |
| "loss": 0.1035, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 1.8027166437414032e-07, | |
| "loss": 0.1024, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "eval_accuracy": 0.9452944738090953, | |
| "eval_f1": 0.9269075563677092, | |
| "eval_loss": 0.14834338426589966, | |
| "eval_matthews_correlation": 0.8869764186987058, | |
| "eval_precision": 0.9327962247988729, | |
| "eval_recall": 0.92164075253014, | |
| "eval_runtime": 1041.7879, | |
| "eval_samples_per_second": 58.658, | |
| "eval_steps_per_second": 1.833, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 1.7786451169188445e-07, | |
| "loss": 0.1019, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "learning_rate": 1.754573590096286e-07, | |
| "loss": 0.1017, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 48.51, | |
| "eval_accuracy": 0.945016282380664, | |
| "eval_f1": 0.9267798368823591, | |
| "eval_loss": 0.1482786238193512, | |
| "eval_matthews_correlation": 0.8864825429378855, | |
| "eval_precision": 0.9318586242689054, | |
| "eval_recall": 0.9221523757100277, | |
| "eval_runtime": 1047.8174, | |
| "eval_samples_per_second": 58.32, | |
| "eval_steps_per_second": 1.823, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 1.7305020632737277e-07, | |
| "loss": 0.1023, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "learning_rate": 1.7066712517193946e-07, | |
| "loss": 0.1003, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 48.94, | |
| "eval_accuracy": 0.9450490107840089, | |
| "eval_f1": 0.927166667024839, | |
| "eval_loss": 0.1484668105840683, | |
| "eval_matthews_correlation": 0.8866843486297423, | |
| "eval_precision": 0.9311237652714297, | |
| "eval_recall": 0.9234908404182439, | |
| "eval_runtime": 1048.467, | |
| "eval_samples_per_second": 58.284, | |
| "eval_steps_per_second": 1.822, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 49.15, | |
| "learning_rate": 1.6825997248968362e-07, | |
| "loss": 0.1007, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 1.6585281980742778e-07, | |
| "loss": 0.1019, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "eval_accuracy": 0.9454908442291643, | |
| "eval_f1": 0.9270481922188618, | |
| "eval_loss": 0.14815160632133484, | |
| "eval_matthews_correlation": 0.887288083753074, | |
| "eval_precision": 0.9338332607657969, | |
| "eval_recall": 0.9209852332071188, | |
| "eval_runtime": 1043.8215, | |
| "eval_samples_per_second": 58.544, | |
| "eval_steps_per_second": 1.83, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 1.6344566712517194e-07, | |
| "loss": 0.1008, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 49.79, | |
| "learning_rate": 1.610385144429161e-07, | |
| "loss": 0.0984, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 49.79, | |
| "eval_accuracy": 0.9450490107840089, | |
| "eval_f1": 0.9272141389942649, | |
| "eval_loss": 0.1484888792037964, | |
| "eval_matthews_correlation": 0.8867470893089248, | |
| "eval_precision": 0.930697822539048, | |
| "eval_recall": 0.9239834966686141, | |
| "eval_runtime": 1046.2775, | |
| "eval_samples_per_second": 58.406, | |
| "eval_steps_per_second": 1.826, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 1.5863136176066023e-07, | |
| "loss": 0.1005, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "learning_rate": 1.5622420907840441e-07, | |
| "loss": 0.1007, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "eval_accuracy": 0.9451799243973883, | |
| "eval_f1": 0.9271281688970315, | |
| "eval_loss": 0.14829137921333313, | |
| "eval_matthews_correlation": 0.8868975027838668, | |
| "eval_precision": 0.9315634975546264, | |
| "eval_recall": 0.9230624706283415, | |
| "eval_runtime": 1042.8498, | |
| "eval_samples_per_second": 58.598, | |
| "eval_steps_per_second": 1.832, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 50.43, | |
| "learning_rate": 1.5381705639614855e-07, | |
| "loss": 0.1001, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "learning_rate": 1.514099037138927e-07, | |
| "loss": 0.0968, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "eval_accuracy": 0.9454090232208022, | |
| "eval_f1": 0.9272991700931191, | |
| "eval_loss": 0.14818619191646576, | |
| "eval_matthews_correlation": 0.8872938388879654, | |
| "eval_precision": 0.9323994024344309, | |
| "eval_recall": 0.9226563864074547, | |
| "eval_runtime": 1044.5886, | |
| "eval_samples_per_second": 58.501, | |
| "eval_steps_per_second": 1.828, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 1.4900275103163686e-07, | |
| "loss": 0.102, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "learning_rate": 1.46595598349381e-07, | |
| "loss": 0.102, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "eval_accuracy": 0.9451635601957159, | |
| "eval_f1": 0.9269136270508408, | |
| "eval_loss": 0.14807577431201935, | |
| "eval_matthews_correlation": 0.8867722689003014, | |
| "eval_precision": 0.9321366838249306, | |
| "eval_recall": 0.9221728394253835, | |
| "eval_runtime": 1040.229, | |
| "eval_samples_per_second": 58.746, | |
| "eval_steps_per_second": 1.836, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 1.4418844566712518e-07, | |
| "loss": 0.0996, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 51.49, | |
| "learning_rate": 1.417812929848693e-07, | |
| "loss": 0.0974, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 51.49, | |
| "eval_accuracy": 0.9452290170024056, | |
| "eval_f1": 0.9270979729816141, | |
| "eval_loss": 0.1479618400335312, | |
| "eval_matthews_correlation": 0.8869160040122801, | |
| "eval_precision": 0.9322256627524821, | |
| "eval_recall": 0.9224124168662996, | |
| "eval_runtime": 1046.5218, | |
| "eval_samples_per_second": 58.392, | |
| "eval_steps_per_second": 1.825, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 51.7, | |
| "learning_rate": 1.3937414030261347e-07, | |
| "loss": 0.1015, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 1.3696698762035763e-07, | |
| "loss": 0.0997, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "eval_accuracy": 0.945441751624147, | |
| "eval_f1": 0.927200876203088, | |
| "eval_loss": 0.14792127907276154, | |
| "eval_matthews_correlation": 0.8872321998942353, | |
| "eval_precision": 0.9334694817739616, | |
| "eval_recall": 0.9215315698638195, | |
| "eval_runtime": 1046.7981, | |
| "eval_samples_per_second": 58.377, | |
| "eval_steps_per_second": 1.825, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 52.13, | |
| "learning_rate": 1.345598349381018e-07, | |
| "loss": 0.0969, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 52.34, | |
| "learning_rate": 1.3215268225584592e-07, | |
| "loss": 0.0991, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 52.34, | |
| "eval_accuracy": 0.9454090232208022, | |
| "eval_f1": 0.9275124073961015, | |
| "eval_loss": 0.148192897439003, | |
| "eval_matthews_correlation": 0.8874202841376583, | |
| "eval_precision": 0.9315495664101637, | |
| "eval_recall": 0.9237972745662067, | |
| "eval_runtime": 1056.3168, | |
| "eval_samples_per_second": 57.851, | |
| "eval_steps_per_second": 1.808, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 52.55, | |
| "learning_rate": 1.297455295735901e-07, | |
| "loss": 0.0999, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 52.77, | |
| "learning_rate": 1.2733837689133424e-07, | |
| "loss": 0.0961, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 52.77, | |
| "eval_accuracy": 0.9454090232208022, | |
| "eval_f1": 0.9276125960433504, | |
| "eval_loss": 0.14825843274593353, | |
| "eval_matthews_correlation": 0.8874404098766001, | |
| "eval_precision": 0.931482950472307, | |
| "eval_recall": 0.9240306380532243, | |
| "eval_runtime": 1049.1068, | |
| "eval_samples_per_second": 58.249, | |
| "eval_steps_per_second": 1.821, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 52.98, | |
| "learning_rate": 1.249312242090784e-07, | |
| "loss": 0.1015, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 1.2252407152682256e-07, | |
| "loss": 0.1003, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "eval_accuracy": 0.9454908442291643, | |
| "eval_f1": 0.9269883425691566, | |
| "eval_loss": 0.14782409369945526, | |
| "eval_matthews_correlation": 0.8872681574002631, | |
| "eval_precision": 0.9339854248197991, | |
| "eval_recall": 0.9207518697201013, | |
| "eval_runtime": 1048.4394, | |
| "eval_samples_per_second": 58.286, | |
| "eval_steps_per_second": 1.822, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 53.4, | |
| "learning_rate": 1.2011691884456671e-07, | |
| "loss": 0.0969, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 53.62, | |
| "learning_rate": 1.1770976616231087e-07, | |
| "loss": 0.0988, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 53.62, | |
| "eval_accuracy": 0.9456053936408713, | |
| "eval_f1": 0.9274062041867052, | |
| "eval_loss": 0.1478436291217804, | |
| "eval_matthews_correlation": 0.8876168167324782, | |
| "eval_precision": 0.9332789328012385, | |
| "eval_recall": 0.9221045841897744, | |
| "eval_runtime": 1048.83, | |
| "eval_samples_per_second": 58.264, | |
| "eval_steps_per_second": 1.821, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 53.83, | |
| "learning_rate": 1.1530261348005502e-07, | |
| "loss": 0.098, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "learning_rate": 1.1289546079779916e-07, | |
| "loss": 0.0986, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "eval_accuracy": 0.9456708504475609, | |
| "eval_f1": 0.9274017208924298, | |
| "eval_loss": 0.1477716565132141, | |
| "eval_matthews_correlation": 0.8877505832830167, | |
| "eval_precision": 0.9333189939052119, | |
| "eval_recall": 0.9220848688673379, | |
| "eval_runtime": 1045.0852, | |
| "eval_samples_per_second": 58.473, | |
| "eval_steps_per_second": 1.828, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 54.26, | |
| "learning_rate": 1.1048830811554334e-07, | |
| "loss": 0.0963, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 54.47, | |
| "learning_rate": 1.0808115543328748e-07, | |
| "loss": 0.1003, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 54.47, | |
| "eval_accuracy": 0.945441751624147, | |
| "eval_f1": 0.9272576298526598, | |
| "eval_loss": 0.1478091925382614, | |
| "eval_matthews_correlation": 0.8873054994658675, | |
| "eval_precision": 0.9328576996809682, | |
| "eval_recall": 0.9221798017722014, | |
| "eval_runtime": 1047.8846, | |
| "eval_samples_per_second": 58.317, | |
| "eval_steps_per_second": 1.823, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 54.68, | |
| "learning_rate": 1.0567400275103163e-07, | |
| "loss": 0.0967, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "learning_rate": 1.0326685006877579e-07, | |
| "loss": 0.0974, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "eval_accuracy": 0.9454090232208022, | |
| "eval_f1": 0.9272324111514144, | |
| "eval_loss": 0.14785851538181305, | |
| "eval_matthews_correlation": 0.8872587311118877, | |
| "eval_precision": 0.9326477457141271, | |
| "eval_recall": 0.9223193058150961, | |
| "eval_runtime": 1042.5297, | |
| "eval_samples_per_second": 58.616, | |
| "eval_steps_per_second": 1.832, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 1.0085969738651993e-07, | |
| "loss": 0.0978, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 55.32, | |
| "learning_rate": 9.84525447042641e-08, | |
| "loss": 0.0985, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 55.32, | |
| "eval_accuracy": 0.9455890294391988, | |
| "eval_f1": 0.92763614192194, | |
| "eval_loss": 0.14787529408931732, | |
| "eval_matthews_correlation": 0.8877198200242857, | |
| "eval_precision": 0.9322731450973873, | |
| "eval_recall": 0.9233930121989798, | |
| "eval_runtime": 1052.7253, | |
| "eval_samples_per_second": 58.048, | |
| "eval_steps_per_second": 1.814, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 55.53, | |
| "learning_rate": 9.604539202200825e-08, | |
| "loss": 0.0974, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 55.74, | |
| "learning_rate": 9.36382393397524e-08, | |
| "loss": 0.0968, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 55.74, | |
| "eval_accuracy": 0.9453599306157849, | |
| "eval_f1": 0.9277711434618366, | |
| "eval_loss": 0.1481289565563202, | |
| "eval_matthews_correlation": 0.8874539900521103, | |
| "eval_precision": 0.930771508987792, | |
| "eval_recall": 0.9249659138549541, | |
| "eval_runtime": 1046.0675, | |
| "eval_samples_per_second": 58.418, | |
| "eval_steps_per_second": 1.826, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 55.96, | |
| "learning_rate": 9.123108665749657e-08, | |
| "loss": 0.0965, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 56.17, | |
| "learning_rate": 8.882393397524071e-08, | |
| "loss": 0.0994, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 56.17, | |
| "eval_accuracy": 0.9454581158258194, | |
| "eval_f1": 0.9273153737422503, | |
| "eval_loss": 0.14774879813194275, | |
| "eval_matthews_correlation": 0.8873663018017705, | |
| "eval_precision": 0.9326728846418783, | |
| "eval_recall": 0.9224471303431127, | |
| "eval_runtime": 1044.2012, | |
| "eval_samples_per_second": 58.522, | |
| "eval_steps_per_second": 1.829, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 56.38, | |
| "learning_rate": 8.641678129298487e-08, | |
| "loss": 0.0986, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "learning_rate": 8.400962861072902e-08, | |
| "loss": 0.0967, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "eval_accuracy": 0.9452617454057504, | |
| "eval_f1": 0.9275893994739569, | |
| "eval_loss": 0.14803829789161682, | |
| "eval_matthews_correlation": 0.8872133913846761, | |
| "eval_precision": 0.9308688570782452, | |
| "eval_recall": 0.9245287598645741, | |
| "eval_runtime": 1045.1221, | |
| "eval_samples_per_second": 58.471, | |
| "eval_steps_per_second": 1.828, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 56.81, | |
| "learning_rate": 8.160247592847317e-08, | |
| "loss": 0.0928, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 57.02, | |
| "learning_rate": 7.919532324621733e-08, | |
| "loss": 0.0981, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 57.02, | |
| "eval_accuracy": 0.9457035788509057, | |
| "eval_f1": 0.927635695095954, | |
| "eval_loss": 0.14773297309875488, | |
| "eval_matthews_correlation": 0.8878658482696629, | |
| "eval_precision": 0.9330727346915296, | |
| "eval_recall": 0.9226973138381661, | |
| "eval_runtime": 1044.5351, | |
| "eval_samples_per_second": 58.504, | |
| "eval_steps_per_second": 1.829, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 57.23, | |
| "learning_rate": 7.678817056396149e-08, | |
| "loss": 0.0974, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 57.45, | |
| "learning_rate": 7.438101788170564e-08, | |
| "loss": 0.0971, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 57.45, | |
| "eval_accuracy": 0.9454581158258194, | |
| "eval_f1": 0.9276437107725939, | |
| "eval_loss": 0.14780069887638092, | |
| "eval_matthews_correlation": 0.8875004428021673, | |
| "eval_precision": 0.931844513397709, | |
| "eval_recall": 0.9237695234362117, | |
| "eval_runtime": 1046.8891, | |
| "eval_samples_per_second": 58.372, | |
| "eval_steps_per_second": 1.824, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 57.66, | |
| "learning_rate": 7.197386519944978e-08, | |
| "loss": 0.0964, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "learning_rate": 6.956671251719394e-08, | |
| "loss": 0.096, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "eval_accuracy": 0.9454908442291643, | |
| "eval_f1": 0.9274937428896638, | |
| "eval_loss": 0.1477871984243393, | |
| "eval_matthews_correlation": 0.8875013471949721, | |
| "eval_precision": 0.9322600481554396, | |
| "eval_recall": 0.9231373631429468, | |
| "eval_runtime": 1045.0428, | |
| "eval_samples_per_second": 58.475, | |
| "eval_steps_per_second": 1.828, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 58.09, | |
| "learning_rate": 6.71595598349381e-08, | |
| "loss": 0.0983, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 58.3, | |
| "learning_rate": 6.475240715268225e-08, | |
| "loss": 0.0971, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 58.3, | |
| "eval_accuracy": 0.9455235726325091, | |
| "eval_f1": 0.927552029801575, | |
| "eval_loss": 0.14768995344638824, | |
| "eval_matthews_correlation": 0.8875535000143042, | |
| "eval_precision": 0.9324442829035213, | |
| "eval_recall": 0.9230756469290579, | |
| "eval_runtime": 1046.0553, | |
| "eval_samples_per_second": 58.419, | |
| "eval_steps_per_second": 1.826, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 58.51, | |
| "learning_rate": 6.23452544704264e-08, | |
| "loss": 0.0952, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 58.72, | |
| "learning_rate": 5.993810178817056e-08, | |
| "loss": 0.0961, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 58.72, | |
| "eval_accuracy": 0.945638122044216, | |
| "eval_f1": 0.9279565448439383, | |
| "eval_loss": 0.14801862835884094, | |
| "eval_matthews_correlation": 0.8879656940505886, | |
| "eval_precision": 0.9314274864696435, | |
| "eval_recall": 0.9247395127147543, | |
| "eval_runtime": 1043.4327, | |
| "eval_samples_per_second": 58.565, | |
| "eval_steps_per_second": 1.83, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 58.94, | |
| "learning_rate": 5.753094910591472e-08, | |
| "loss": 0.0959, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "learning_rate": 5.512379642365887e-08, | |
| "loss": 0.0966, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "eval_accuracy": 0.945638122044216, | |
| "eval_f1": 0.9278932427247907, | |
| "eval_loss": 0.14785251021385193, | |
| "eval_matthews_correlation": 0.8879297115031657, | |
| "eval_precision": 0.9316436960957745, | |
| "eval_recall": 0.9244283613987311, | |
| "eval_runtime": 1042.6, | |
| "eval_samples_per_second": 58.612, | |
| "eval_steps_per_second": 1.832, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 59.36, | |
| "learning_rate": 5.2716643741403025e-08, | |
| "loss": 0.0964, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 59.57, | |
| "learning_rate": 5.030949105914718e-08, | |
| "loss": 0.0951, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 59.57, | |
| "eval_accuracy": 0.9457035788509057, | |
| "eval_f1": 0.9276842027293449, | |
| "eval_loss": 0.14763057231903076, | |
| "eval_matthews_correlation": 0.8879028981021795, | |
| "eval_precision": 0.932791895372278, | |
| "eval_recall": 0.9230343944305247, | |
| "eval_runtime": 1042.025, | |
| "eval_samples_per_second": 58.644, | |
| "eval_steps_per_second": 1.833, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 59.79, | |
| "learning_rate": 4.7902338376891336e-08, | |
| "loss": 0.096, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.549518569463548e-08, | |
| "loss": 0.0967, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.9457199430525782, | |
| "eval_f1": 0.927955781482661, | |
| "eval_loss": 0.14779448509216309, | |
| "eval_matthews_correlation": 0.8880701174127367, | |
| "eval_precision": 0.9319335364980635, | |
| "eval_recall": 0.9242870355021765, | |
| "eval_runtime": 1047.0793, | |
| "eval_samples_per_second": 58.361, | |
| "eval_steps_per_second": 1.824, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 60.21, | |
| "learning_rate": 4.31121045392022e-08, | |
| "loss": 0.0969, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "learning_rate": 4.070495185694635e-08, | |
| "loss": 0.0956, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "eval_accuracy": 0.9456544862458885, | |
| "eval_f1": 0.9276116803982696, | |
| "eval_loss": 0.1476927101612091, | |
| "eval_matthews_correlation": 0.8877873982600887, | |
| "eval_precision": 0.9328403451345734, | |
| "eval_recall": 0.9228547113498378, | |
| "eval_runtime": 1046.2884, | |
| "eval_samples_per_second": 58.406, | |
| "eval_steps_per_second": 1.826, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 60.64, | |
| "learning_rate": 3.829779917469051e-08, | |
| "loss": 0.0945, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 60.85, | |
| "learning_rate": 3.589064649243466e-08, | |
| "loss": 0.0949, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 60.85, | |
| "eval_accuracy": 0.9455890294391988, | |
| "eval_f1": 0.9274468934394512, | |
| "eval_loss": 0.14764761924743652, | |
| "eval_matthews_correlation": 0.8876320376738418, | |
| "eval_precision": 0.9328648830470847, | |
| "eval_recall": 0.9225373460799157, | |
| "eval_runtime": 1045.5567, | |
| "eval_samples_per_second": 58.446, | |
| "eval_steps_per_second": 1.827, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 61.06, | |
| "learning_rate": 3.348349381017882e-08, | |
| "loss": 0.0977, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 61.28, | |
| "learning_rate": 3.107634112792297e-08, | |
| "loss": 0.0998, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 61.28, | |
| "eval_accuracy": 0.945638122044216, | |
| "eval_f1": 0.9279059418767672, | |
| "eval_loss": 0.14780724048614502, | |
| "eval_matthews_correlation": 0.8879171433551577, | |
| "eval_precision": 0.9317532607784281, | |
| "eval_recall": 0.9243505735697252, | |
| "eval_runtime": 1040.7835, | |
| "eval_samples_per_second": 58.714, | |
| "eval_steps_per_second": 1.835, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 61.49, | |
| "learning_rate": 2.8669188445667127e-08, | |
| "loss": 0.0954, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 61.7, | |
| "learning_rate": 2.626203576341128e-08, | |
| "loss": 0.093, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 61.7, | |
| "eval_accuracy": 0.9457199430525782, | |
| "eval_f1": 0.9277906571185546, | |
| "eval_loss": 0.14767155051231384, | |
| "eval_matthews_correlation": 0.8879751002445269, | |
| "eval_precision": 0.932561984753093, | |
| "eval_recall": 0.9234313693831124, | |
| "eval_runtime": 1040.5623, | |
| "eval_samples_per_second": 58.727, | |
| "eval_steps_per_second": 1.836, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 61.91, | |
| "learning_rate": 2.3854883081155434e-08, | |
| "loss": 0.0957, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 62.13, | |
| "learning_rate": 2.1447730398899586e-08, | |
| "loss": 0.0921, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 62.13, | |
| "eval_accuracy": 0.9455235726325091, | |
| "eval_f1": 0.9275365932517117, | |
| "eval_loss": 0.1477140486240387, | |
| "eval_matthews_correlation": 0.88756898594448, | |
| "eval_precision": 0.9323037964838674, | |
| "eval_recall": 0.9231793640343989, | |
| "eval_runtime": 1044.4243, | |
| "eval_samples_per_second": 58.51, | |
| "eval_steps_per_second": 1.829, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 62.34, | |
| "learning_rate": 1.9040577716643742e-08, | |
| "loss": 0.0945, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 62.55, | |
| "learning_rate": 1.6633425034387894e-08, | |
| "loss": 0.0966, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 62.55, | |
| "eval_accuracy": 0.9456872146492333, | |
| "eval_f1": 0.9276527270587683, | |
| "eval_loss": 0.14766238629817963, | |
| "eval_matthews_correlation": 0.8878653323382849, | |
| "eval_precision": 0.9327960139595405, | |
| "eval_recall": 0.9229745000702957, | |
| "eval_runtime": 1043.2921, | |
| "eval_samples_per_second": 58.573, | |
| "eval_steps_per_second": 1.831, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 62.77, | |
| "learning_rate": 1.422627235213205e-08, | |
| "loss": 0.0986, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 62.98, | |
| "learning_rate": 1.1819119669876203e-08, | |
| "loss": 0.0944, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 62.98, | |
| "eval_accuracy": 0.945752671455923, | |
| "eval_f1": 0.9279373294113554, | |
| "eval_loss": 0.14771275222301483, | |
| "eval_matthews_correlation": 0.8880956425811568, | |
| "eval_precision": 0.9322586813552154, | |
| "eval_recall": 0.9239660265249349, | |
| "eval_runtime": 1044.3434, | |
| "eval_samples_per_second": 58.514, | |
| "eval_steps_per_second": 1.829, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 9.411966987620358e-09, | |
| "loss": 0.0952, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "learning_rate": 7.004814305364511e-09, | |
| "loss": 0.0993, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "eval_accuracy": 0.9458017640609403, | |
| "eval_f1": 0.9279988626113386, | |
| "eval_loss": 0.1477140486240387, | |
| "eval_matthews_correlation": 0.8881956101974604, | |
| "eval_precision": 0.9323332938470736, | |
| "eval_recall": 0.9240160632239456, | |
| "eval_runtime": 1043.8337, | |
| "eval_samples_per_second": 58.543, | |
| "eval_steps_per_second": 1.83, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 63.62, | |
| "learning_rate": 4.597661623108666e-09, | |
| "loss": 0.0939, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "learning_rate": 2.19050894085282e-09, | |
| "loss": 0.0953, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "eval_accuracy": 0.9457690356575954, | |
| "eval_f1": 0.9279030967153313, | |
| "eval_loss": 0.14768283069133759, | |
| "eval_matthews_correlation": 0.888099839706084, | |
| "eval_precision": 0.9324741697161726, | |
| "eval_recall": 0.9237147695691407, | |
| "eval_runtime": 1048.3281, | |
| "eval_samples_per_second": 58.292, | |
| "eval_steps_per_second": 1.822, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "step": 30080, | |
| "total_flos": 3.5213331699056304e+21, | |
| "train_loss": 0.1566047928276214, | |
| "train_runtime": 597098.8722, | |
| "train_samples_per_second": 25.809, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "max_steps": 30080, | |
| "num_train_epochs": 64, | |
| "total_flos": 3.5213331699056304e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |