{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.7905919557268505, "global_step": 4000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 9.998023324767742e-06, "loss": 0.101, "step": 10 }, { "epoch": 0.0, "learning_rate": 9.996046649535482e-06, "loss": 0.0803, "step": 20 }, { "epoch": 0.01, "learning_rate": 9.994069974303224e-06, "loss": 0.0877, "step": 30 }, { "epoch": 0.01, "learning_rate": 9.992093299070964e-06, "loss": 0.0749, "step": 40 }, { "epoch": 0.01, "learning_rate": 9.990116623838703e-06, "loss": 0.0682, "step": 50 }, { "epoch": 0.01, "learning_rate": 9.988139948606445e-06, "loss": 0.0606, "step": 60 }, { "epoch": 0.01, "learning_rate": 9.986163273374185e-06, "loss": 0.0546, "step": 70 }, { "epoch": 0.02, "learning_rate": 9.984186598141926e-06, "loss": 0.0534, "step": 80 }, { "epoch": 0.02, "learning_rate": 9.982209922909668e-06, "loss": 0.0682, "step": 90 }, { "epoch": 0.02, "learning_rate": 9.980233247677408e-06, "loss": 0.0521, "step": 100 }, { "epoch": 0.02, "learning_rate": 9.978256572445149e-06, "loss": 0.0556, "step": 110 }, { "epoch": 0.02, "learning_rate": 9.976279897212889e-06, "loss": 0.0432, "step": 120 }, { "epoch": 0.03, "learning_rate": 9.974303221980629e-06, "loss": 0.0506, "step": 130 }, { "epoch": 0.03, "learning_rate": 9.97232654674837e-06, "loss": 0.0491, "step": 140 }, { "epoch": 0.03, "learning_rate": 9.97034987151611e-06, "loss": 0.0402, "step": 150 }, { "epoch": 0.03, "learning_rate": 9.968373196283852e-06, "loss": 0.0453, "step": 160 }, { "epoch": 0.03, "learning_rate": 9.966396521051591e-06, "loss": 0.0435, "step": 170 }, { "epoch": 0.04, "learning_rate": 9.964419845819333e-06, "loss": 0.0402, "step": 180 }, { "epoch": 0.04, "learning_rate": 9.962443170587075e-06, "loss": 0.0434, "step": 190 }, { "epoch": 0.04, "learning_rate": 9.960466495354814e-06, "loss": 0.0385, "step": 200 }, { "epoch": 0.04, "learning_rate": 9.958489820122554e-06, "loss": 0.0413, "step": 210 }, { "epoch": 0.04, "learning_rate": 9.956513144890296e-06, "loss": 0.0426, "step": 220 }, { "epoch": 0.05, "learning_rate": 9.954536469658036e-06, "loss": 0.0384, "step": 230 }, { "epoch": 0.05, "learning_rate": 9.952559794425777e-06, "loss": 0.0371, "step": 240 }, { "epoch": 0.05, "learning_rate": 9.950583119193517e-06, "loss": 0.0366, "step": 250 }, { "epoch": 0.05, "learning_rate": 9.948606443961258e-06, "loss": 0.0359, "step": 260 }, { "epoch": 0.05, "learning_rate": 9.946629768728998e-06, "loss": 0.0436, "step": 270 }, { "epoch": 0.06, "learning_rate": 9.944653093496738e-06, "loss": 0.0331, "step": 280 }, { "epoch": 0.06, "learning_rate": 9.94267641826448e-06, "loss": 0.0339, "step": 290 }, { "epoch": 0.06, "learning_rate": 9.940699743032221e-06, "loss": 0.0329, "step": 300 }, { "epoch": 0.06, "learning_rate": 9.938723067799961e-06, "loss": 0.0345, "step": 310 }, { "epoch": 0.06, "learning_rate": 9.936746392567702e-06, "loss": 0.0367, "step": 320 }, { "epoch": 0.07, "learning_rate": 9.934769717335442e-06, "loss": 0.0354, "step": 330 }, { "epoch": 0.07, "learning_rate": 9.932793042103184e-06, "loss": 0.0283, "step": 340 }, { "epoch": 0.07, "learning_rate": 9.930816366870924e-06, "loss": 0.0293, "step": 350 }, { "epoch": 0.07, "learning_rate": 9.928839691638663e-06, "loss": 0.0317, "step": 360 }, { "epoch": 0.07, "learning_rate": 9.926863016406405e-06, "loss": 0.0264, "step": 370 }, { "epoch": 0.08, "learning_rate": 9.924886341174147e-06, "loss": 0.0362, "step": 380 }, { "epoch": 0.08, "learning_rate": 9.922909665941886e-06, "loss": 0.0296, "step": 390 }, { "epoch": 0.08, "learning_rate": 9.920932990709628e-06, "loss": 0.0274, "step": 400 }, { "epoch": 0.08, "learning_rate": 9.918956315477368e-06, "loss": 0.0282, "step": 410 }, { "epoch": 0.08, "learning_rate": 9.91697964024511e-06, "loss": 0.033, "step": 420 }, { "epoch": 0.08, "learning_rate": 9.915002965012849e-06, "loss": 0.0259, "step": 430 }, { "epoch": 0.09, "learning_rate": 9.913026289780589e-06, "loss": 0.0351, "step": 440 }, { "epoch": 0.09, "learning_rate": 9.91104961454833e-06, "loss": 0.0309, "step": 450 }, { "epoch": 0.09, "learning_rate": 9.909072939316072e-06, "loss": 0.0321, "step": 460 }, { "epoch": 0.09, "learning_rate": 9.907096264083812e-06, "loss": 0.0277, "step": 470 }, { "epoch": 0.09, "learning_rate": 9.905119588851553e-06, "loss": 0.0273, "step": 480 }, { "epoch": 0.1, "learning_rate": 9.903142913619293e-06, "loss": 0.0248, "step": 490 }, { "epoch": 0.1, "learning_rate": 9.901166238387033e-06, "loss": 0.0338, "step": 500 }, { "epoch": 0.1, "learning_rate": 9.899189563154774e-06, "loss": 0.0278, "step": 510 }, { "epoch": 0.1, "learning_rate": 9.897212887922514e-06, "loss": 0.0315, "step": 520 }, { "epoch": 0.1, "learning_rate": 9.895236212690256e-06, "loss": 0.0299, "step": 530 }, { "epoch": 0.11, "learning_rate": 9.893259537457996e-06, "loss": 0.0228, "step": 540 }, { "epoch": 0.11, "learning_rate": 9.891282862225737e-06, "loss": 0.0271, "step": 550 }, { "epoch": 0.11, "learning_rate": 9.889306186993479e-06, "loss": 0.023, "step": 560 }, { "epoch": 0.11, "learning_rate": 9.887329511761219e-06, "loss": 0.024, "step": 570 }, { "epoch": 0.11, "learning_rate": 9.885352836528958e-06, "loss": 0.0334, "step": 580 }, { "epoch": 0.12, "learning_rate": 9.8833761612967e-06, "loss": 0.026, "step": 590 }, { "epoch": 0.12, "learning_rate": 9.88139948606444e-06, "loss": 0.0263, "step": 600 }, { "epoch": 0.12, "learning_rate": 9.879422810832181e-06, "loss": 0.0285, "step": 610 }, { "epoch": 0.12, "learning_rate": 9.877446135599921e-06, "loss": 0.0296, "step": 620 }, { "epoch": 0.12, "learning_rate": 9.875469460367663e-06, "loss": 0.0253, "step": 630 }, { "epoch": 0.13, "learning_rate": 9.873492785135404e-06, "loss": 0.0299, "step": 640 }, { "epoch": 0.13, "learning_rate": 9.871516109903144e-06, "loss": 0.0179, "step": 650 }, { "epoch": 0.13, "learning_rate": 9.869539434670884e-06, "loss": 0.0234, "step": 660 }, { "epoch": 0.13, "learning_rate": 9.867562759438625e-06, "loss": 0.0256, "step": 670 }, { "epoch": 0.13, "learning_rate": 9.865586084206365e-06, "loss": 0.0215, "step": 680 }, { "epoch": 0.14, "learning_rate": 9.863609408974107e-06, "loss": 0.0285, "step": 690 }, { "epoch": 0.14, "learning_rate": 9.861632733741846e-06, "loss": 0.0247, "step": 700 }, { "epoch": 0.14, "learning_rate": 9.859656058509588e-06, "loss": 0.0257, "step": 710 }, { "epoch": 0.14, "learning_rate": 9.85767938327733e-06, "loss": 0.0277, "step": 720 }, { "epoch": 0.14, "learning_rate": 9.855702708045068e-06, "loss": 0.0211, "step": 730 }, { "epoch": 0.15, "learning_rate": 9.85372603281281e-06, "loss": 0.0231, "step": 740 }, { "epoch": 0.15, "learning_rate": 9.85174935758055e-06, "loss": 0.0231, "step": 750 }, { "epoch": 0.15, "learning_rate": 9.84977268234829e-06, "loss": 0.0244, "step": 760 }, { "epoch": 0.15, "learning_rate": 9.847796007116032e-06, "loss": 0.0227, "step": 770 }, { "epoch": 0.15, "learning_rate": 9.845819331883772e-06, "loss": 0.0256, "step": 780 }, { "epoch": 0.16, "learning_rate": 9.843842656651513e-06, "loss": 0.0244, "step": 790 }, { "epoch": 0.16, "learning_rate": 9.841865981419253e-06, "loss": 0.0242, "step": 800 }, { "epoch": 0.16, "learning_rate": 9.839889306186993e-06, "loss": 0.0241, "step": 810 }, { "epoch": 0.16, "learning_rate": 9.837912630954735e-06, "loss": 0.0186, "step": 820 }, { "epoch": 0.16, "learning_rate": 9.835935955722476e-06, "loss": 0.0262, "step": 830 }, { "epoch": 0.17, "learning_rate": 9.833959280490216e-06, "loss": 0.0216, "step": 840 }, { "epoch": 0.17, "learning_rate": 9.831982605257957e-06, "loss": 0.0192, "step": 850 }, { "epoch": 0.17, "learning_rate": 9.830005930025697e-06, "loss": 0.0284, "step": 860 }, { "epoch": 0.17, "learning_rate": 9.828029254793439e-06, "loss": 0.0258, "step": 870 }, { "epoch": 0.17, "learning_rate": 9.826052579561179e-06, "loss": 0.0205, "step": 880 }, { "epoch": 0.18, "learning_rate": 9.824075904328918e-06, "loss": 0.0246, "step": 890 }, { "epoch": 0.18, "learning_rate": 9.82209922909666e-06, "loss": 0.0214, "step": 900 }, { "epoch": 0.18, "learning_rate": 9.820122553864402e-06, "loss": 0.0222, "step": 910 }, { "epoch": 0.18, "learning_rate": 9.818145878632141e-06, "loss": 0.0179, "step": 920 }, { "epoch": 0.18, "learning_rate": 9.816169203399883e-06, "loss": 0.0201, "step": 930 }, { "epoch": 0.19, "learning_rate": 9.814192528167623e-06, "loss": 0.0199, "step": 940 }, { "epoch": 0.19, "learning_rate": 9.812215852935364e-06, "loss": 0.0238, "step": 950 }, { "epoch": 0.19, "learning_rate": 9.810239177703104e-06, "loss": 0.0136, "step": 960 }, { "epoch": 0.19, "learning_rate": 9.808262502470844e-06, "loss": 0.0196, "step": 970 }, { "epoch": 0.19, "learning_rate": 9.806285827238585e-06, "loss": 0.0228, "step": 980 }, { "epoch": 0.2, "learning_rate": 9.804309152006325e-06, "loss": 0.02, "step": 990 }, { "epoch": 0.2, "learning_rate": 9.802332476774067e-06, "loss": 0.0212, "step": 1000 }, { "batch_size": 128, "epoch": 0.2, "step": 1000, "valid_mrr": 0.713063593146979, "valid_mrr_wo_pooler": 0.7165689455071271, "valid_pr1": 0.6296875, "valid_pr1_wo_pooler": 0.6328125, "valid_runtime": 19.0638, "valid_samples_per_second": 60.376, "valid_steps_per_second": 0.21 }, { "epoch": 0.2, "learning_rate": 9.800355801541808e-06, "loss": 0.017, "step": 1010 }, { "epoch": 0.2, "learning_rate": 9.798379126309548e-06, "loss": 0.0231, "step": 1020 }, { "epoch": 0.2, "learning_rate": 9.79640245107729e-06, "loss": 0.0206, "step": 1030 }, { "epoch": 0.21, "learning_rate": 9.79442577584503e-06, "loss": 0.0228, "step": 1040 }, { "epoch": 0.21, "learning_rate": 9.79244910061277e-06, "loss": 0.0122, "step": 1050 }, { "epoch": 0.21, "learning_rate": 9.79047242538051e-06, "loss": 0.016, "step": 1060 }, { "epoch": 0.21, "learning_rate": 9.78849575014825e-06, "loss": 0.0199, "step": 1070 }, { "epoch": 0.21, "learning_rate": 9.786519074915992e-06, "loss": 0.0144, "step": 1080 }, { "epoch": 0.22, "learning_rate": 9.784542399683734e-06, "loss": 0.0179, "step": 1090 }, { "epoch": 0.22, "learning_rate": 9.782565724451474e-06, "loss": 0.0159, "step": 1100 }, { "epoch": 0.22, "learning_rate": 9.780589049219215e-06, "loss": 0.0216, "step": 1110 }, { "epoch": 0.22, "learning_rate": 9.778612373986955e-06, "loss": 0.0176, "step": 1120 }, { "epoch": 0.22, "learning_rate": 9.776635698754695e-06, "loss": 0.0198, "step": 1130 }, { "epoch": 0.23, "learning_rate": 9.774659023522436e-06, "loss": 0.0176, "step": 1140 }, { "epoch": 0.23, "learning_rate": 9.772682348290176e-06, "loss": 0.0224, "step": 1150 }, { "epoch": 0.23, "learning_rate": 9.770705673057918e-06, "loss": 0.0172, "step": 1160 }, { "epoch": 0.23, "learning_rate": 9.768728997825659e-06, "loss": 0.0147, "step": 1170 }, { "epoch": 0.23, "learning_rate": 9.766752322593399e-06, "loss": 0.023, "step": 1180 }, { "epoch": 0.24, "learning_rate": 9.764775647361139e-06, "loss": 0.0247, "step": 1190 }, { "epoch": 0.24, "learning_rate": 9.76279897212888e-06, "loss": 0.0203, "step": 1200 }, { "epoch": 0.24, "learning_rate": 9.76082229689662e-06, "loss": 0.016, "step": 1210 }, { "epoch": 0.24, "learning_rate": 9.758845621664362e-06, "loss": 0.0179, "step": 1220 }, { "epoch": 0.24, "learning_rate": 9.756868946432102e-06, "loss": 0.0179, "step": 1230 }, { "epoch": 0.25, "learning_rate": 9.754892271199843e-06, "loss": 0.0207, "step": 1240 }, { "epoch": 0.25, "learning_rate": 9.752915595967583e-06, "loss": 0.0204, "step": 1250 }, { "epoch": 0.25, "learning_rate": 9.750938920735324e-06, "loss": 0.0208, "step": 1260 }, { "epoch": 0.25, "learning_rate": 9.748962245503064e-06, "loss": 0.0161, "step": 1270 }, { "epoch": 0.25, "learning_rate": 9.746985570270806e-06, "loss": 0.0188, "step": 1280 }, { "epoch": 0.25, "learning_rate": 9.745008895038546e-06, "loss": 0.0179, "step": 1290 }, { "epoch": 0.26, "learning_rate": 9.743032219806287e-06, "loss": 0.0164, "step": 1300 }, { "epoch": 0.26, "learning_rate": 9.741055544574027e-06, "loss": 0.013, "step": 1310 }, { "epoch": 0.26, "learning_rate": 9.739078869341768e-06, "loss": 0.0174, "step": 1320 }, { "epoch": 0.26, "learning_rate": 9.737102194109508e-06, "loss": 0.0197, "step": 1330 }, { "epoch": 0.26, "learning_rate": 9.73512551887725e-06, "loss": 0.02, "step": 1340 }, { "epoch": 0.27, "learning_rate": 9.73314884364499e-06, "loss": 0.0218, "step": 1350 }, { "epoch": 0.27, "learning_rate": 9.73117216841273e-06, "loss": 0.0137, "step": 1360 }, { "epoch": 0.27, "learning_rate": 9.729195493180471e-06, "loss": 0.0199, "step": 1370 }, { "epoch": 0.27, "learning_rate": 9.727218817948212e-06, "loss": 0.0143, "step": 1380 }, { "epoch": 0.27, "learning_rate": 9.725242142715952e-06, "loss": 0.017, "step": 1390 }, { "epoch": 0.28, "learning_rate": 9.723265467483694e-06, "loss": 0.0169, "step": 1400 }, { "epoch": 0.28, "learning_rate": 9.721288792251434e-06, "loss": 0.0175, "step": 1410 }, { "epoch": 0.28, "learning_rate": 9.719312117019175e-06, "loss": 0.0162, "step": 1420 }, { "epoch": 0.28, "learning_rate": 9.717335441786915e-06, "loss": 0.018, "step": 1430 }, { "epoch": 0.28, "learning_rate": 9.715358766554655e-06, "loss": 0.0226, "step": 1440 }, { "epoch": 0.29, "learning_rate": 9.713382091322396e-06, "loss": 0.0153, "step": 1450 }, { "epoch": 0.29, "learning_rate": 9.711405416090138e-06, "loss": 0.0146, "step": 1460 }, { "epoch": 0.29, "learning_rate": 9.709428740857878e-06, "loss": 0.0171, "step": 1470 }, { "epoch": 0.29, "learning_rate": 9.70745206562562e-06, "loss": 0.0195, "step": 1480 }, { "epoch": 0.29, "learning_rate": 9.705475390393359e-06, "loss": 0.0185, "step": 1490 }, { "epoch": 0.3, "learning_rate": 9.703498715161099e-06, "loss": 0.0171, "step": 1500 }, { "epoch": 0.3, "learning_rate": 9.70152203992884e-06, "loss": 0.017, "step": 1510 }, { "epoch": 0.3, "learning_rate": 9.69954536469658e-06, "loss": 0.0127, "step": 1520 }, { "epoch": 0.3, "learning_rate": 9.697568689464322e-06, "loss": 0.0178, "step": 1530 }, { "epoch": 0.3, "learning_rate": 9.695592014232063e-06, "loss": 0.016, "step": 1540 }, { "epoch": 0.31, "learning_rate": 9.693615338999803e-06, "loss": 0.0171, "step": 1550 }, { "epoch": 0.31, "learning_rate": 9.691638663767545e-06, "loss": 0.0141, "step": 1560 }, { "epoch": 0.31, "learning_rate": 9.689661988535285e-06, "loss": 0.0173, "step": 1570 }, { "epoch": 0.31, "learning_rate": 9.687685313303024e-06, "loss": 0.0148, "step": 1580 }, { "epoch": 0.31, "learning_rate": 9.685708638070766e-06, "loss": 0.0139, "step": 1590 }, { "epoch": 0.32, "learning_rate": 9.683731962838506e-06, "loss": 0.0186, "step": 1600 }, { "epoch": 0.32, "learning_rate": 9.681755287606247e-06, "loss": 0.0206, "step": 1610 }, { "epoch": 0.32, "learning_rate": 9.679778612373987e-06, "loss": 0.0201, "step": 1620 }, { "epoch": 0.32, "learning_rate": 9.677801937141729e-06, "loss": 0.0121, "step": 1630 }, { "epoch": 0.32, "learning_rate": 9.67582526190947e-06, "loss": 0.0195, "step": 1640 }, { "epoch": 0.33, "learning_rate": 9.67384858667721e-06, "loss": 0.0212, "step": 1650 }, { "epoch": 0.33, "learning_rate": 9.67187191144495e-06, "loss": 0.0164, "step": 1660 }, { "epoch": 0.33, "learning_rate": 9.669895236212691e-06, "loss": 0.0196, "step": 1670 }, { "epoch": 0.33, "learning_rate": 9.667918560980431e-06, "loss": 0.0187, "step": 1680 }, { "epoch": 0.33, "learning_rate": 9.665941885748173e-06, "loss": 0.0169, "step": 1690 }, { "epoch": 0.34, "learning_rate": 9.663965210515912e-06, "loss": 0.0181, "step": 1700 }, { "epoch": 0.34, "learning_rate": 9.661988535283654e-06, "loss": 0.0184, "step": 1710 }, { "epoch": 0.34, "learning_rate": 9.660011860051396e-06, "loss": 0.0196, "step": 1720 }, { "epoch": 0.34, "learning_rate": 9.658035184819135e-06, "loss": 0.0158, "step": 1730 }, { "epoch": 0.34, "learning_rate": 9.656058509586875e-06, "loss": 0.0147, "step": 1740 }, { "epoch": 0.35, "learning_rate": 9.654081834354617e-06, "loss": 0.0102, "step": 1750 }, { "epoch": 0.35, "learning_rate": 9.652105159122357e-06, "loss": 0.0212, "step": 1760 }, { "epoch": 0.35, "learning_rate": 9.650128483890098e-06, "loss": 0.0144, "step": 1770 }, { "epoch": 0.35, "learning_rate": 9.648151808657838e-06, "loss": 0.0168, "step": 1780 }, { "epoch": 0.35, "learning_rate": 9.64617513342558e-06, "loss": 0.0133, "step": 1790 }, { "epoch": 0.36, "learning_rate": 9.644198458193321e-06, "loss": 0.0178, "step": 1800 }, { "epoch": 0.36, "learning_rate": 9.642221782961059e-06, "loss": 0.0135, "step": 1810 }, { "epoch": 0.36, "learning_rate": 9.6402451077288e-06, "loss": 0.0177, "step": 1820 }, { "epoch": 0.36, "learning_rate": 9.638268432496542e-06, "loss": 0.0173, "step": 1830 }, { "epoch": 0.36, "learning_rate": 9.636291757264282e-06, "loss": 0.0176, "step": 1840 }, { "epoch": 0.37, "learning_rate": 9.634315082032023e-06, "loss": 0.0164, "step": 1850 }, { "epoch": 0.37, "learning_rate": 9.632338406799763e-06, "loss": 0.0196, "step": 1860 }, { "epoch": 0.37, "learning_rate": 9.630361731567505e-06, "loss": 0.0215, "step": 1870 }, { "epoch": 0.37, "learning_rate": 9.628385056335245e-06, "loss": 0.0183, "step": 1880 }, { "epoch": 0.37, "learning_rate": 9.626408381102984e-06, "loss": 0.0107, "step": 1890 }, { "epoch": 0.38, "learning_rate": 9.624431705870726e-06, "loss": 0.019, "step": 1900 }, { "epoch": 0.38, "learning_rate": 9.622455030638468e-06, "loss": 0.0157, "step": 1910 }, { "epoch": 0.38, "learning_rate": 9.620478355406207e-06, "loss": 0.0171, "step": 1920 }, { "epoch": 0.38, "learning_rate": 9.618501680173949e-06, "loss": 0.0153, "step": 1930 }, { "epoch": 0.38, "learning_rate": 9.616525004941689e-06, "loss": 0.0164, "step": 1940 }, { "epoch": 0.39, "learning_rate": 9.61454832970943e-06, "loss": 0.0161, "step": 1950 }, { "epoch": 0.39, "learning_rate": 9.61257165447717e-06, "loss": 0.0178, "step": 1960 }, { "epoch": 0.39, "learning_rate": 9.61059497924491e-06, "loss": 0.0111, "step": 1970 }, { "epoch": 0.39, "learning_rate": 9.608618304012651e-06, "loss": 0.0175, "step": 1980 }, { "epoch": 0.39, "learning_rate": 9.606641628780393e-06, "loss": 0.0122, "step": 1990 }, { "epoch": 0.4, "learning_rate": 9.604664953548133e-06, "loss": 0.0132, "step": 2000 }, { "batch_size": 128, "epoch": 0.4, "step": 2000, "valid_mrr": 0.7407695795617386, "valid_mrr_wo_pooler": 0.7474766604446019, "valid_pr1": 0.6546875, "valid_pr1_wo_pooler": 0.66875, "valid_runtime": 17.8534, "valid_samples_per_second": 64.47, "valid_steps_per_second": 0.224 }, { "epoch": 0.4, "learning_rate": 9.602688278315874e-06, "loss": 0.0163, "step": 2010 }, { "epoch": 0.4, "learning_rate": 9.600711603083614e-06, "loss": 0.0128, "step": 2020 }, { "epoch": 0.4, "learning_rate": 9.598734927851356e-06, "loss": 0.0171, "step": 2030 }, { "epoch": 0.4, "learning_rate": 9.596758252619095e-06, "loss": 0.0118, "step": 2040 }, { "epoch": 0.41, "learning_rate": 9.594781577386835e-06, "loss": 0.0199, "step": 2050 }, { "epoch": 0.41, "learning_rate": 9.592804902154577e-06, "loss": 0.0107, "step": 2060 }, { "epoch": 0.41, "learning_rate": 9.590828226922317e-06, "loss": 0.0151, "step": 2070 }, { "epoch": 0.41, "learning_rate": 9.588851551690058e-06, "loss": 0.0154, "step": 2080 }, { "epoch": 0.41, "learning_rate": 9.5868748764578e-06, "loss": 0.0187, "step": 2090 }, { "epoch": 0.42, "learning_rate": 9.58489820122554e-06, "loss": 0.0147, "step": 2100 }, { "epoch": 0.42, "learning_rate": 9.582921525993281e-06, "loss": 0.0166, "step": 2110 }, { "epoch": 0.42, "learning_rate": 9.580944850761021e-06, "loss": 0.0166, "step": 2120 }, { "epoch": 0.42, "learning_rate": 9.57896817552876e-06, "loss": 0.0129, "step": 2130 }, { "epoch": 0.42, "learning_rate": 9.576991500296502e-06, "loss": 0.0122, "step": 2140 }, { "epoch": 0.42, "learning_rate": 9.575014825064242e-06, "loss": 0.012, "step": 2150 }, { "epoch": 0.43, "learning_rate": 9.573038149831984e-06, "loss": 0.0152, "step": 2160 }, { "epoch": 0.43, "learning_rate": 9.571061474599725e-06, "loss": 0.0121, "step": 2170 }, { "epoch": 0.43, "learning_rate": 9.569084799367465e-06, "loss": 0.0126, "step": 2180 }, { "epoch": 0.43, "learning_rate": 9.567108124135205e-06, "loss": 0.0161, "step": 2190 }, { "epoch": 0.43, "learning_rate": 9.565131448902946e-06, "loss": 0.0208, "step": 2200 }, { "epoch": 0.44, "learning_rate": 9.563154773670686e-06, "loss": 0.0127, "step": 2210 }, { "epoch": 0.44, "learning_rate": 9.561178098438428e-06, "loss": 0.0192, "step": 2220 }, { "epoch": 0.44, "learning_rate": 9.559201423206167e-06, "loss": 0.0156, "step": 2230 }, { "epoch": 0.44, "learning_rate": 9.557224747973909e-06, "loss": 0.0091, "step": 2240 }, { "epoch": 0.44, "learning_rate": 9.55524807274165e-06, "loss": 0.0136, "step": 2250 }, { "epoch": 0.45, "learning_rate": 9.55327139750939e-06, "loss": 0.0183, "step": 2260 }, { "epoch": 0.45, "learning_rate": 9.55129472227713e-06, "loss": 0.0164, "step": 2270 }, { "epoch": 0.45, "learning_rate": 9.549318047044872e-06, "loss": 0.0194, "step": 2280 }, { "epoch": 0.45, "learning_rate": 9.547341371812612e-06, "loss": 0.0156, "step": 2290 }, { "epoch": 0.45, "learning_rate": 9.545364696580353e-06, "loss": 0.0158, "step": 2300 }, { "epoch": 0.46, "learning_rate": 9.543388021348093e-06, "loss": 0.0095, "step": 2310 }, { "epoch": 0.46, "learning_rate": 9.541411346115834e-06, "loss": 0.0158, "step": 2320 }, { "epoch": 0.46, "learning_rate": 9.539434670883574e-06, "loss": 0.013, "step": 2330 }, { "epoch": 0.46, "learning_rate": 9.537457995651316e-06, "loss": 0.0134, "step": 2340 }, { "epoch": 0.46, "learning_rate": 9.535481320419056e-06, "loss": 0.0175, "step": 2350 }, { "epoch": 0.47, "learning_rate": 9.533504645186797e-06, "loss": 0.0122, "step": 2360 }, { "epoch": 0.47, "learning_rate": 9.531527969954537e-06, "loss": 0.0161, "step": 2370 }, { "epoch": 0.47, "learning_rate": 9.529551294722278e-06, "loss": 0.0125, "step": 2380 }, { "epoch": 0.47, "learning_rate": 9.527574619490018e-06, "loss": 0.0157, "step": 2390 }, { "epoch": 0.47, "learning_rate": 9.52559794425776e-06, "loss": 0.0142, "step": 2400 }, { "epoch": 0.48, "learning_rate": 9.5236212690255e-06, "loss": 0.0143, "step": 2410 }, { "epoch": 0.48, "learning_rate": 9.52164459379324e-06, "loss": 0.0161, "step": 2420 }, { "epoch": 0.48, "learning_rate": 9.519667918560981e-06, "loss": 0.0188, "step": 2430 }, { "epoch": 0.48, "learning_rate": 9.51769124332872e-06, "loss": 0.0111, "step": 2440 }, { "epoch": 0.48, "learning_rate": 9.515714568096462e-06, "loss": 0.0137, "step": 2450 }, { "epoch": 0.49, "learning_rate": 9.513737892864204e-06, "loss": 0.0138, "step": 2460 }, { "epoch": 0.49, "learning_rate": 9.511761217631944e-06, "loss": 0.0134, "step": 2470 }, { "epoch": 0.49, "learning_rate": 9.509784542399685e-06, "loss": 0.0139, "step": 2480 }, { "epoch": 0.49, "learning_rate": 9.507807867167425e-06, "loss": 0.0098, "step": 2490 }, { "epoch": 0.49, "learning_rate": 9.505831191935165e-06, "loss": 0.0116, "step": 2500 }, { "epoch": 0.5, "learning_rate": 9.503854516702906e-06, "loss": 0.0177, "step": 2510 }, { "epoch": 0.5, "learning_rate": 9.501877841470646e-06, "loss": 0.0125, "step": 2520 }, { "epoch": 0.5, "learning_rate": 9.499901166238388e-06, "loss": 0.01, "step": 2530 }, { "epoch": 0.5, "learning_rate": 9.49792449100613e-06, "loss": 0.0116, "step": 2540 }, { "epoch": 0.5, "learning_rate": 9.495947815773869e-06, "loss": 0.0099, "step": 2550 }, { "epoch": 0.51, "learning_rate": 9.49397114054161e-06, "loss": 0.0137, "step": 2560 }, { "epoch": 0.51, "learning_rate": 9.49199446530935e-06, "loss": 0.0133, "step": 2570 }, { "epoch": 0.51, "learning_rate": 9.49001779007709e-06, "loss": 0.0153, "step": 2580 }, { "epoch": 0.51, "learning_rate": 9.488041114844832e-06, "loss": 0.0142, "step": 2590 }, { "epoch": 0.51, "learning_rate": 9.486064439612572e-06, "loss": 0.0118, "step": 2600 }, { "epoch": 0.52, "learning_rate": 9.484087764380313e-06, "loss": 0.0138, "step": 2610 }, { "epoch": 0.52, "learning_rate": 9.482111089148055e-06, "loss": 0.0098, "step": 2620 }, { "epoch": 0.52, "learning_rate": 9.480134413915795e-06, "loss": 0.0172, "step": 2630 }, { "epoch": 0.52, "learning_rate": 9.478157738683536e-06, "loss": 0.015, "step": 2640 }, { "epoch": 0.52, "learning_rate": 9.476181063451276e-06, "loss": 0.0147, "step": 2650 }, { "epoch": 0.53, "learning_rate": 9.474204388219016e-06, "loss": 0.0126, "step": 2660 }, { "epoch": 0.53, "learning_rate": 9.472227712986757e-06, "loss": 0.0115, "step": 2670 }, { "epoch": 0.53, "learning_rate": 9.470251037754497e-06, "loss": 0.0137, "step": 2680 }, { "epoch": 0.53, "learning_rate": 9.468274362522239e-06, "loss": 0.0145, "step": 2690 }, { "epoch": 0.53, "learning_rate": 9.466297687289978e-06, "loss": 0.012, "step": 2700 }, { "epoch": 0.54, "learning_rate": 9.46432101205772e-06, "loss": 0.0154, "step": 2710 }, { "epoch": 0.54, "learning_rate": 9.462344336825461e-06, "loss": 0.0133, "step": 2720 }, { "epoch": 0.54, "learning_rate": 9.460367661593201e-06, "loss": 0.0108, "step": 2730 }, { "epoch": 0.54, "learning_rate": 9.458390986360941e-06, "loss": 0.0137, "step": 2740 }, { "epoch": 0.54, "learning_rate": 9.456414311128683e-06, "loss": 0.0146, "step": 2750 }, { "epoch": 0.55, "learning_rate": 9.454437635896422e-06, "loss": 0.0122, "step": 2760 }, { "epoch": 0.55, "learning_rate": 9.452460960664164e-06, "loss": 0.0135, "step": 2770 }, { "epoch": 0.55, "learning_rate": 9.450484285431904e-06, "loss": 0.0121, "step": 2780 }, { "epoch": 0.55, "learning_rate": 9.448507610199645e-06, "loss": 0.0167, "step": 2790 }, { "epoch": 0.55, "learning_rate": 9.446530934967387e-06, "loss": 0.0143, "step": 2800 }, { "epoch": 0.56, "learning_rate": 9.444554259735125e-06, "loss": 0.0081, "step": 2810 }, { "epoch": 0.56, "learning_rate": 9.442577584502867e-06, "loss": 0.0107, "step": 2820 }, { "epoch": 0.56, "learning_rate": 9.440600909270608e-06, "loss": 0.0177, "step": 2830 }, { "epoch": 0.56, "learning_rate": 9.438624234038348e-06, "loss": 0.0114, "step": 2840 }, { "epoch": 0.56, "learning_rate": 9.43664755880609e-06, "loss": 0.0146, "step": 2850 }, { "epoch": 0.57, "learning_rate": 9.43467088357383e-06, "loss": 0.0088, "step": 2860 }, { "epoch": 0.57, "learning_rate": 9.43269420834157e-06, "loss": 0.0123, "step": 2870 }, { "epoch": 0.57, "learning_rate": 9.43071753310931e-06, "loss": 0.0122, "step": 2880 }, { "epoch": 0.57, "learning_rate": 9.42874085787705e-06, "loss": 0.013, "step": 2890 }, { "epoch": 0.57, "learning_rate": 9.426764182644792e-06, "loss": 0.0181, "step": 2900 }, { "epoch": 0.58, "learning_rate": 9.424787507412533e-06, "loss": 0.0122, "step": 2910 }, { "epoch": 0.58, "learning_rate": 9.422810832180273e-06, "loss": 0.0157, "step": 2920 }, { "epoch": 0.58, "learning_rate": 9.420834156948015e-06, "loss": 0.0127, "step": 2930 }, { "epoch": 0.58, "learning_rate": 9.418857481715755e-06, "loss": 0.0121, "step": 2940 }, { "epoch": 0.58, "learning_rate": 9.416880806483496e-06, "loss": 0.0126, "step": 2950 }, { "epoch": 0.59, "learning_rate": 9.414904131251236e-06, "loss": 0.0171, "step": 2960 }, { "epoch": 0.59, "learning_rate": 9.412927456018976e-06, "loss": 0.0099, "step": 2970 }, { "epoch": 0.59, "learning_rate": 9.410950780786717e-06, "loss": 0.0183, "step": 2980 }, { "epoch": 0.59, "learning_rate": 9.408974105554459e-06, "loss": 0.0073, "step": 2990 }, { "epoch": 0.59, "learning_rate": 9.406997430322199e-06, "loss": 0.0121, "step": 3000 }, { "batch_size": 128, "epoch": 0.59, "step": 3000, "valid_mrr": 0.7545951753143683, "valid_mrr_wo_pooler": 0.7653977925713823, "valid_pr1": 0.6734375, "valid_pr1_wo_pooler": 0.6921875, "valid_runtime": 17.9025, "valid_samples_per_second": 64.293, "valid_steps_per_second": 0.223 }, { "epoch": 0.59, "learning_rate": 9.40502075508994e-06, "loss": 0.0185, "step": 3010 }, { "epoch": 0.6, "learning_rate": 9.40304407985768e-06, "loss": 0.0102, "step": 3020 }, { "epoch": 0.6, "learning_rate": 9.401067404625422e-06, "loss": 0.0105, "step": 3030 }, { "epoch": 0.6, "learning_rate": 9.399090729393161e-06, "loss": 0.0119, "step": 3040 }, { "epoch": 0.6, "learning_rate": 9.397114054160901e-06, "loss": 0.0096, "step": 3050 }, { "epoch": 0.6, "learning_rate": 9.395137378928643e-06, "loss": 0.0131, "step": 3060 }, { "epoch": 0.61, "learning_rate": 9.393160703696383e-06, "loss": 0.0183, "step": 3070 }, { "epoch": 0.61, "learning_rate": 9.391184028464124e-06, "loss": 0.01, "step": 3080 }, { "epoch": 0.61, "learning_rate": 9.389207353231866e-06, "loss": 0.0135, "step": 3090 }, { "epoch": 0.61, "learning_rate": 9.387230677999605e-06, "loss": 0.0141, "step": 3100 }, { "epoch": 0.61, "learning_rate": 9.385254002767345e-06, "loss": 0.0132, "step": 3110 }, { "epoch": 0.62, "learning_rate": 9.383277327535087e-06, "loss": 0.0108, "step": 3120 }, { "epoch": 0.62, "learning_rate": 9.381300652302827e-06, "loss": 0.0127, "step": 3130 }, { "epoch": 0.62, "learning_rate": 9.379323977070568e-06, "loss": 0.0121, "step": 3140 }, { "epoch": 0.62, "learning_rate": 9.377347301838308e-06, "loss": 0.0145, "step": 3150 }, { "epoch": 0.62, "learning_rate": 9.37537062660605e-06, "loss": 0.0116, "step": 3160 }, { "epoch": 0.63, "learning_rate": 9.373393951373791e-06, "loss": 0.0142, "step": 3170 }, { "epoch": 0.63, "learning_rate": 9.371417276141531e-06, "loss": 0.0109, "step": 3180 }, { "epoch": 0.63, "learning_rate": 9.36944060090927e-06, "loss": 0.0175, "step": 3190 }, { "epoch": 0.63, "learning_rate": 9.367463925677012e-06, "loss": 0.0134, "step": 3200 }, { "epoch": 0.63, "learning_rate": 9.365487250444752e-06, "loss": 0.0123, "step": 3210 }, { "epoch": 0.64, "learning_rate": 9.363510575212494e-06, "loss": 0.0112, "step": 3220 }, { "epoch": 0.64, "learning_rate": 9.361533899980233e-06, "loss": 0.009, "step": 3230 }, { "epoch": 0.64, "learning_rate": 9.359557224747975e-06, "loss": 0.0131, "step": 3240 }, { "epoch": 0.64, "learning_rate": 9.357580549515716e-06, "loss": 0.0116, "step": 3250 }, { "epoch": 0.64, "learning_rate": 9.355603874283456e-06, "loss": 0.0115, "step": 3260 }, { "epoch": 0.65, "learning_rate": 9.353627199051196e-06, "loss": 0.0138, "step": 3270 }, { "epoch": 0.65, "learning_rate": 9.351650523818938e-06, "loss": 0.0089, "step": 3280 }, { "epoch": 0.65, "learning_rate": 9.349673848586677e-06, "loss": 0.0102, "step": 3290 }, { "epoch": 0.65, "learning_rate": 9.347697173354419e-06, "loss": 0.0157, "step": 3300 }, { "epoch": 0.65, "learning_rate": 9.345720498122159e-06, "loss": 0.0101, "step": 3310 }, { "epoch": 0.66, "learning_rate": 9.3437438228899e-06, "loss": 0.0091, "step": 3320 }, { "epoch": 0.66, "learning_rate": 9.34176714765764e-06, "loss": 0.01, "step": 3330 }, { "epoch": 0.66, "learning_rate": 9.33979047242538e-06, "loss": 0.0081, "step": 3340 }, { "epoch": 0.66, "learning_rate": 9.337813797193122e-06, "loss": 0.0098, "step": 3350 }, { "epoch": 0.66, "learning_rate": 9.335837121960863e-06, "loss": 0.0153, "step": 3360 }, { "epoch": 0.67, "learning_rate": 9.333860446728603e-06, "loss": 0.012, "step": 3370 }, { "epoch": 0.67, "learning_rate": 9.331883771496344e-06, "loss": 0.0159, "step": 3380 }, { "epoch": 0.67, "learning_rate": 9.329907096264084e-06, "loss": 0.0129, "step": 3390 }, { "epoch": 0.67, "learning_rate": 9.327930421031826e-06, "loss": 0.0122, "step": 3400 }, { "epoch": 0.67, "learning_rate": 9.325953745799566e-06, "loss": 0.0132, "step": 3410 }, { "epoch": 0.68, "learning_rate": 9.323977070567305e-06, "loss": 0.0137, "step": 3420 }, { "epoch": 0.68, "learning_rate": 9.322000395335047e-06, "loss": 0.0113, "step": 3430 }, { "epoch": 0.68, "learning_rate": 9.320023720102788e-06, "loss": 0.0144, "step": 3440 }, { "epoch": 0.68, "learning_rate": 9.318047044870528e-06, "loss": 0.01, "step": 3450 }, { "epoch": 0.68, "learning_rate": 9.31607036963827e-06, "loss": 0.0118, "step": 3460 }, { "epoch": 0.69, "learning_rate": 9.31409369440601e-06, "loss": 0.0112, "step": 3470 }, { "epoch": 0.69, "learning_rate": 9.312117019173751e-06, "loss": 0.0115, "step": 3480 }, { "epoch": 0.69, "learning_rate": 9.310140343941491e-06, "loss": 0.0147, "step": 3490 }, { "epoch": 0.69, "learning_rate": 9.308163668709231e-06, "loss": 0.0179, "step": 3500 }, { "epoch": 0.69, "learning_rate": 9.306186993476972e-06, "loss": 0.0149, "step": 3510 }, { "epoch": 0.7, "learning_rate": 9.304210318244712e-06, "loss": 0.0098, "step": 3520 }, { "epoch": 0.7, "learning_rate": 9.302233643012454e-06, "loss": 0.0099, "step": 3530 }, { "epoch": 0.7, "learning_rate": 9.300256967780195e-06, "loss": 0.0132, "step": 3540 }, { "epoch": 0.7, "learning_rate": 9.298280292547935e-06, "loss": 0.0088, "step": 3550 }, { "epoch": 0.7, "learning_rate": 9.296303617315677e-06, "loss": 0.0102, "step": 3560 }, { "epoch": 0.71, "learning_rate": 9.294326942083416e-06, "loss": 0.0135, "step": 3570 }, { "epoch": 0.71, "learning_rate": 9.292350266851156e-06, "loss": 0.0126, "step": 3580 }, { "epoch": 0.71, "learning_rate": 9.290373591618898e-06, "loss": 0.0088, "step": 3590 }, { "epoch": 0.71, "learning_rate": 9.288396916386638e-06, "loss": 0.0089, "step": 3600 }, { "epoch": 0.71, "learning_rate": 9.286420241154379e-06, "loss": 0.0149, "step": 3610 }, { "epoch": 0.72, "learning_rate": 9.28444356592212e-06, "loss": 0.0115, "step": 3620 }, { "epoch": 0.72, "learning_rate": 9.28246689068986e-06, "loss": 0.0105, "step": 3630 }, { "epoch": 0.72, "learning_rate": 9.280490215457602e-06, "loss": 0.0133, "step": 3640 }, { "epoch": 0.72, "learning_rate": 9.278513540225342e-06, "loss": 0.0145, "step": 3650 }, { "epoch": 0.72, "learning_rate": 9.276536864993082e-06, "loss": 0.014, "step": 3660 }, { "epoch": 0.73, "learning_rate": 9.274560189760823e-06, "loss": 0.01, "step": 3670 }, { "epoch": 0.73, "learning_rate": 9.272583514528563e-06, "loss": 0.0131, "step": 3680 }, { "epoch": 0.73, "learning_rate": 9.270606839296305e-06, "loss": 0.0133, "step": 3690 }, { "epoch": 0.73, "learning_rate": 9.268630164064046e-06, "loss": 0.0123, "step": 3700 }, { "epoch": 0.73, "learning_rate": 9.266653488831786e-06, "loss": 0.0113, "step": 3710 }, { "epoch": 0.74, "learning_rate": 9.264676813599527e-06, "loss": 0.01, "step": 3720 }, { "epoch": 0.74, "learning_rate": 9.262700138367267e-06, "loss": 0.0124, "step": 3730 }, { "epoch": 0.74, "learning_rate": 9.260723463135007e-06, "loss": 0.0147, "step": 3740 }, { "epoch": 0.74, "learning_rate": 9.258746787902749e-06, "loss": 0.0096, "step": 3750 }, { "epoch": 0.74, "learning_rate": 9.256770112670488e-06, "loss": 0.0101, "step": 3760 }, { "epoch": 0.75, "learning_rate": 9.25479343743823e-06, "loss": 0.0124, "step": 3770 }, { "epoch": 0.75, "learning_rate": 9.25281676220597e-06, "loss": 0.0132, "step": 3780 }, { "epoch": 0.75, "learning_rate": 9.250840086973711e-06, "loss": 0.0112, "step": 3790 }, { "epoch": 0.75, "learning_rate": 9.248863411741453e-06, "loss": 0.0119, "step": 3800 }, { "epoch": 0.75, "learning_rate": 9.246886736509193e-06, "loss": 0.0141, "step": 3810 }, { "epoch": 0.76, "learning_rate": 9.244910061276933e-06, "loss": 0.0102, "step": 3820 }, { "epoch": 0.76, "learning_rate": 9.242933386044674e-06, "loss": 0.0123, "step": 3830 }, { "epoch": 0.76, "learning_rate": 9.240956710812414e-06, "loss": 0.0146, "step": 3840 }, { "epoch": 0.76, "learning_rate": 9.238980035580155e-06, "loss": 0.0052, "step": 3850 }, { "epoch": 0.76, "learning_rate": 9.237003360347895e-06, "loss": 0.0113, "step": 3860 }, { "epoch": 0.76, "learning_rate": 9.235026685115637e-06, "loss": 0.0126, "step": 3870 }, { "epoch": 0.77, "learning_rate": 9.233050009883377e-06, "loss": 0.0103, "step": 3880 }, { "epoch": 0.77, "learning_rate": 9.231073334651116e-06, "loss": 0.0117, "step": 3890 }, { "epoch": 0.77, "learning_rate": 9.229096659418858e-06, "loss": 0.0144, "step": 3900 }, { "epoch": 0.77, "learning_rate": 9.2271199841866e-06, "loss": 0.0149, "step": 3910 }, { "epoch": 0.77, "learning_rate": 9.22514330895434e-06, "loss": 0.0112, "step": 3920 }, { "epoch": 0.78, "learning_rate": 9.22316663372208e-06, "loss": 0.0111, "step": 3930 }, { "epoch": 0.78, "learning_rate": 9.22118995848982e-06, "loss": 0.0091, "step": 3940 }, { "epoch": 0.78, "learning_rate": 9.219213283257562e-06, "loss": 0.0142, "step": 3950 }, { "epoch": 0.78, "learning_rate": 9.217236608025302e-06, "loss": 0.0099, "step": 3960 }, { "epoch": 0.78, "learning_rate": 9.215259932793042e-06, "loss": 0.0108, "step": 3970 }, { "epoch": 0.79, "learning_rate": 9.213283257560783e-06, "loss": 0.0128, "step": 3980 }, { "epoch": 0.79, "learning_rate": 9.211306582328525e-06, "loss": 0.0134, "step": 3990 }, { "epoch": 0.79, "learning_rate": 9.209329907096265e-06, "loss": 0.0151, "step": 4000 }, { "batch_size": 128, "epoch": 0.79, "step": 4000, "valid_mrr": 0.7539704627359516, "valid_mrr_wo_pooler": 0.7610087812537554, "valid_pr1": 0.671875, "valid_pr1_wo_pooler": 0.6859375, "valid_runtime": 17.9577, "valid_samples_per_second": 64.095, "valid_steps_per_second": 0.223 } ], "max_steps": 50590, "num_train_epochs": 10, "total_flos": 2.02065661919232e+17, "trial_name": null, "trial_params": null }