{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.5526315789473686, "eval_steps": 500, "global_step": 5400, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006578947368421052, "grad_norm": 19.201007081270827, "learning_rate": 8.458646616541353e-07, "loss": 8.2522, "step": 10 }, { "epoch": 0.013157894736842105, "grad_norm": 18.114759300569585, "learning_rate": 1.7857142857142857e-06, "loss": 8.1346, "step": 20 }, { "epoch": 0.019736842105263157, "grad_norm": 9.479492840003324, "learning_rate": 2.725563909774436e-06, "loss": 7.5119, "step": 30 }, { "epoch": 0.02631578947368421, "grad_norm": 4.976331973381574, "learning_rate": 3.6654135338345866e-06, "loss": 6.7788, "step": 40 }, { "epoch": 0.03289473684210526, "grad_norm": 3.2804593438080754, "learning_rate": 4.605263157894737e-06, "loss": 6.2892, "step": 50 }, { "epoch": 0.039473684210526314, "grad_norm": 2.8583967169035027, "learning_rate": 5.5451127819548875e-06, "loss": 5.9528, "step": 60 }, { "epoch": 0.046052631578947366, "grad_norm": 3.5512069733934597, "learning_rate": 6.484962406015038e-06, "loss": 5.5755, "step": 70 }, { "epoch": 0.05263157894736842, "grad_norm": 3.731444843289522, "learning_rate": 7.424812030075189e-06, "loss": 4.9914, "step": 80 }, { "epoch": 0.05921052631578947, "grad_norm": 5.60127901105382, "learning_rate": 8.364661654135339e-06, "loss": 4.3233, "step": 90 }, { "epoch": 0.06578947368421052, "grad_norm": 3.7839180004348996, "learning_rate": 9.30451127819549e-06, "loss": 3.7305, "step": 100 }, { "epoch": 0.07236842105263158, "grad_norm": 5.421177691842472, "learning_rate": 1.024436090225564e-05, "loss": 3.3248, "step": 110 }, { "epoch": 0.07894736842105263, "grad_norm": 3.7158079343320694, "learning_rate": 1.118421052631579e-05, "loss": 3.092, "step": 120 }, { "epoch": 0.08552631578947369, "grad_norm": 5.042680618782553, "learning_rate": 1.212406015037594e-05, "loss": 2.9383, "step": 130 }, { "epoch": 0.09210526315789473, "grad_norm": 5.8029975922287615, "learning_rate": 1.3063909774436093e-05, "loss": 2.8108, "step": 140 }, { "epoch": 0.09868421052631579, "grad_norm": 7.443887556478386, "learning_rate": 1.4003759398496241e-05, "loss": 2.7256, "step": 150 }, { "epoch": 0.10526315789473684, "grad_norm": 6.942055828457074, "learning_rate": 1.4943609022556393e-05, "loss": 2.6465, "step": 160 }, { "epoch": 0.1118421052631579, "grad_norm": 20.211444588304172, "learning_rate": 1.5883458646616542e-05, "loss": 2.5756, "step": 170 }, { "epoch": 0.11842105263157894, "grad_norm": 23.482614308148037, "learning_rate": 1.6823308270676694e-05, "loss": 2.5262, "step": 180 }, { "epoch": 0.125, "grad_norm": 13.648396628618737, "learning_rate": 1.7763157894736842e-05, "loss": 2.4699, "step": 190 }, { "epoch": 0.13157894736842105, "grad_norm": 15.205800265082752, "learning_rate": 1.8703007518796993e-05, "loss": 2.4115, "step": 200 }, { "epoch": 0.13815789473684212, "grad_norm": 16.093588917694532, "learning_rate": 1.9642857142857145e-05, "loss": 2.3548, "step": 210 }, { "epoch": 0.14473684210526316, "grad_norm": 19.61654573509106, "learning_rate": 2.0582706766917297e-05, "loss": 2.3042, "step": 220 }, { "epoch": 0.1513157894736842, "grad_norm": 12.268305710278183, "learning_rate": 2.1522556390977445e-05, "loss": 2.2494, "step": 230 }, { "epoch": 0.15789473684210525, "grad_norm": 12.399788763360808, "learning_rate": 2.2462406015037596e-05, "loss": 2.1853, "step": 240 }, { "epoch": 0.16447368421052633, "grad_norm": 7.463420275410263, "learning_rate": 2.3402255639097744e-05, "loss": 2.0998, "step": 250 }, { "epoch": 0.17105263157894737, "grad_norm": 12.087535187997679, "learning_rate": 2.4342105263157896e-05, "loss": 2.0075, "step": 260 }, { "epoch": 0.17763157894736842, "grad_norm": 6.62910919540051, "learning_rate": 2.5281954887218044e-05, "loss": 1.8974, "step": 270 }, { "epoch": 0.18421052631578946, "grad_norm": 8.989470792407845, "learning_rate": 2.62218045112782e-05, "loss": 1.7928, "step": 280 }, { "epoch": 0.19078947368421054, "grad_norm": 6.928524369383665, "learning_rate": 2.716165413533835e-05, "loss": 1.7057, "step": 290 }, { "epoch": 0.19736842105263158, "grad_norm": 10.311746680652767, "learning_rate": 2.8101503759398495e-05, "loss": 1.6251, "step": 300 }, { "epoch": 0.20394736842105263, "grad_norm": 7.107313244759928, "learning_rate": 2.9041353383458647e-05, "loss": 1.5522, "step": 310 }, { "epoch": 0.21052631578947367, "grad_norm": 5.8857302431981156, "learning_rate": 2.9981203007518798e-05, "loss": 1.4974, "step": 320 }, { "epoch": 0.21710526315789475, "grad_norm": 6.775917238582609, "learning_rate": 3.092105263157895e-05, "loss": 1.4355, "step": 330 }, { "epoch": 0.2236842105263158, "grad_norm": 9.938119729849578, "learning_rate": 3.1860902255639094e-05, "loss": 1.3895, "step": 340 }, { "epoch": 0.23026315789473684, "grad_norm": 4.870796794495703, "learning_rate": 3.2800751879699246e-05, "loss": 1.3432, "step": 350 }, { "epoch": 0.23684210526315788, "grad_norm": 5.353011232164181, "learning_rate": 3.37406015037594e-05, "loss": 1.3002, "step": 360 }, { "epoch": 0.24342105263157895, "grad_norm": 7.078794515741611, "learning_rate": 3.468045112781955e-05, "loss": 1.2641, "step": 370 }, { "epoch": 0.25, "grad_norm": 5.419600483372193, "learning_rate": 3.56203007518797e-05, "loss": 1.209, "step": 380 }, { "epoch": 0.2565789473684211, "grad_norm": 3.5327527407457926, "learning_rate": 3.656015037593985e-05, "loss": 1.1644, "step": 390 }, { "epoch": 0.2631578947368421, "grad_norm": 5.894523313050658, "learning_rate": 3.7500000000000003e-05, "loss": 1.1319, "step": 400 }, { "epoch": 0.26973684210526316, "grad_norm": 3.9863193805342316, "learning_rate": 3.8439849624060155e-05, "loss": 1.094, "step": 410 }, { "epoch": 0.27631578947368424, "grad_norm": 4.225678742387179, "learning_rate": 3.9379699248120307e-05, "loss": 1.0651, "step": 420 }, { "epoch": 0.28289473684210525, "grad_norm": 5.586389531542015, "learning_rate": 4.031954887218045e-05, "loss": 1.0247, "step": 430 }, { "epoch": 0.2894736842105263, "grad_norm": 7.0928476432315675, "learning_rate": 4.12593984962406e-05, "loss": 0.9973, "step": 440 }, { "epoch": 0.29605263157894735, "grad_norm": 5.797737179453841, "learning_rate": 4.2199248120300754e-05, "loss": 0.9738, "step": 450 }, { "epoch": 0.3026315789473684, "grad_norm": 5.436160406452568, "learning_rate": 4.3139097744360906e-05, "loss": 0.9539, "step": 460 }, { "epoch": 0.3092105263157895, "grad_norm": 4.940473111611711, "learning_rate": 4.407894736842105e-05, "loss": 0.9197, "step": 470 }, { "epoch": 0.3157894736842105, "grad_norm": 5.844247327503255, "learning_rate": 4.50187969924812e-05, "loss": 0.8862, "step": 480 }, { "epoch": 0.3223684210526316, "grad_norm": 4.744124381908569, "learning_rate": 4.5958646616541354e-05, "loss": 0.8668, "step": 490 }, { "epoch": 0.32894736842105265, "grad_norm": 4.689028836800058, "learning_rate": 4.6898496240601505e-05, "loss": 0.8476, "step": 500 }, { "epoch": 0.3355263157894737, "grad_norm": 4.398308995209079, "learning_rate": 4.783834586466166e-05, "loss": 0.82, "step": 510 }, { "epoch": 0.34210526315789475, "grad_norm": 5.554811082819198, "learning_rate": 4.877819548872181e-05, "loss": 0.7974, "step": 520 }, { "epoch": 0.34868421052631576, "grad_norm": 3.7243976034524584, "learning_rate": 4.971804511278196e-05, "loss": 0.7715, "step": 530 }, { "epoch": 0.35526315789473684, "grad_norm": 4.879577435611285, "learning_rate": 5.0657894736842104e-05, "loss": 0.7514, "step": 540 }, { "epoch": 0.3618421052631579, "grad_norm": 5.516075231521318, "learning_rate": 5.1597744360902256e-05, "loss": 0.7291, "step": 550 }, { "epoch": 0.3684210526315789, "grad_norm": 5.494655015332771, "learning_rate": 5.253759398496241e-05, "loss": 0.6974, "step": 560 }, { "epoch": 0.375, "grad_norm": 5.0610034411984826, "learning_rate": 5.347744360902256e-05, "loss": 0.6779, "step": 570 }, { "epoch": 0.3815789473684211, "grad_norm": 6.241132985448258, "learning_rate": 5.441729323308271e-05, "loss": 0.6723, "step": 580 }, { "epoch": 0.3881578947368421, "grad_norm": 4.582816961569543, "learning_rate": 5.535714285714286e-05, "loss": 0.652, "step": 590 }, { "epoch": 0.39473684210526316, "grad_norm": 3.5845708789821042, "learning_rate": 5.6296992481203013e-05, "loss": 0.6154, "step": 600 }, { "epoch": 0.40131578947368424, "grad_norm": 4.328768044098044, "learning_rate": 5.723684210526316e-05, "loss": 0.6042, "step": 610 }, { "epoch": 0.40789473684210525, "grad_norm": 3.5473602851751793, "learning_rate": 5.817669172932331e-05, "loss": 0.5803, "step": 620 }, { "epoch": 0.4144736842105263, "grad_norm": 4.233181045605189, "learning_rate": 5.911654135338346e-05, "loss": 0.5688, "step": 630 }, { "epoch": 0.42105263157894735, "grad_norm": 4.0831509210740835, "learning_rate": 6.005639097744361e-05, "loss": 0.5385, "step": 640 }, { "epoch": 0.4276315789473684, "grad_norm": 3.8705204303765814, "learning_rate": 6.0996240601503764e-05, "loss": 0.5201, "step": 650 }, { "epoch": 0.4342105263157895, "grad_norm": 3.8269827275761337, "learning_rate": 6.193609022556392e-05, "loss": 0.504, "step": 660 }, { "epoch": 0.4407894736842105, "grad_norm": 3.7042333223437476, "learning_rate": 6.287593984962407e-05, "loss": 0.485, "step": 670 }, { "epoch": 0.4473684210526316, "grad_norm": 3.1454584376141725, "learning_rate": 6.381578947368422e-05, "loss": 0.4692, "step": 680 }, { "epoch": 0.45394736842105265, "grad_norm": 3.6715281367823698, "learning_rate": 6.475563909774437e-05, "loss": 0.4474, "step": 690 }, { "epoch": 0.4605263157894737, "grad_norm": 3.3520165299765203, "learning_rate": 6.569548872180451e-05, "loss": 0.4335, "step": 700 }, { "epoch": 0.46710526315789475, "grad_norm": 3.4830856151143554, "learning_rate": 6.663533834586466e-05, "loss": 0.4156, "step": 710 }, { "epoch": 0.47368421052631576, "grad_norm": 3.4130338264227835, "learning_rate": 6.757518796992481e-05, "loss": 0.3984, "step": 720 }, { "epoch": 0.48026315789473684, "grad_norm": 3.6699720598135834, "learning_rate": 6.851503759398496e-05, "loss": 0.3884, "step": 730 }, { "epoch": 0.4868421052631579, "grad_norm": 3.2598730307422192, "learning_rate": 6.945488721804511e-05, "loss": 0.3727, "step": 740 }, { "epoch": 0.4934210526315789, "grad_norm": 3.0065146921519097, "learning_rate": 7.039473684210527e-05, "loss": 0.3521, "step": 750 }, { "epoch": 0.5, "grad_norm": 2.3801132893266956, "learning_rate": 7.133458646616542e-05, "loss": 0.3415, "step": 760 }, { "epoch": 0.506578947368421, "grad_norm": 2.5040976105308466, "learning_rate": 7.227443609022557e-05, "loss": 0.3303, "step": 770 }, { "epoch": 0.5131578947368421, "grad_norm": 2.3095873713136004, "learning_rate": 7.321428571428571e-05, "loss": 0.3155, "step": 780 }, { "epoch": 0.5197368421052632, "grad_norm": 2.221909098699267, "learning_rate": 7.415413533834586e-05, "loss": 0.3, "step": 790 }, { "epoch": 0.5263157894736842, "grad_norm": 2.3650008130107008, "learning_rate": 7.509398496240601e-05, "loss": 0.2881, "step": 800 }, { "epoch": 0.5328947368421053, "grad_norm": 2.92228181953594, "learning_rate": 7.603383458646618e-05, "loss": 0.2759, "step": 810 }, { "epoch": 0.5394736842105263, "grad_norm": 2.39576316770683, "learning_rate": 7.697368421052633e-05, "loss": 0.2611, "step": 820 }, { "epoch": 0.5460526315789473, "grad_norm": 1.9345517046210943, "learning_rate": 7.791353383458648e-05, "loss": 0.2472, "step": 830 }, { "epoch": 0.5526315789473685, "grad_norm": 2.321485582474392, "learning_rate": 7.885338345864663e-05, "loss": 0.2409, "step": 840 }, { "epoch": 0.5592105263157895, "grad_norm": 1.8690657258212422, "learning_rate": 7.979323308270678e-05, "loss": 0.2308, "step": 850 }, { "epoch": 0.5657894736842105, "grad_norm": 1.901049780468097, "learning_rate": 8.073308270676692e-05, "loss": 0.2171, "step": 860 }, { "epoch": 0.5723684210526315, "grad_norm": 2.2229311039801596, "learning_rate": 8.167293233082707e-05, "loss": 0.2072, "step": 870 }, { "epoch": 0.5789473684210527, "grad_norm": 2.213221418124993, "learning_rate": 8.261278195488722e-05, "loss": 0.1965, "step": 880 }, { "epoch": 0.5855263157894737, "grad_norm": 1.870540842703205, "learning_rate": 8.355263157894737e-05, "loss": 0.1877, "step": 890 }, { "epoch": 0.5921052631578947, "grad_norm": 1.311680351399902, "learning_rate": 8.449248120300753e-05, "loss": 0.1792, "step": 900 }, { "epoch": 0.5986842105263158, "grad_norm": 1.5798663811679752, "learning_rate": 8.543233082706768e-05, "loss": 0.1716, "step": 910 }, { "epoch": 0.6052631578947368, "grad_norm": 7.169134004434136, "learning_rate": 8.637218045112783e-05, "loss": 0.1721, "step": 920 }, { "epoch": 0.6118421052631579, "grad_norm": 1.5044155665130965, "learning_rate": 8.731203007518798e-05, "loss": 0.193, "step": 930 }, { "epoch": 0.618421052631579, "grad_norm": 1.305309283144098, "learning_rate": 8.825187969924813e-05, "loss": 0.1566, "step": 940 }, { "epoch": 0.625, "grad_norm": 1.23686939558907, "learning_rate": 8.919172932330827e-05, "loss": 0.1445, "step": 950 }, { "epoch": 0.631578947368421, "grad_norm": 1.0445490067006857, "learning_rate": 9.013157894736842e-05, "loss": 0.1356, "step": 960 }, { "epoch": 0.6381578947368421, "grad_norm": 1.3136634908844078, "learning_rate": 9.107142857142857e-05, "loss": 0.1308, "step": 970 }, { "epoch": 0.6447368421052632, "grad_norm": 1.7716809252302665, "learning_rate": 9.201127819548872e-05, "loss": 0.124, "step": 980 }, { "epoch": 0.6513157894736842, "grad_norm": 1.0772175167269311, "learning_rate": 9.295112781954888e-05, "loss": 0.1202, "step": 990 }, { "epoch": 0.6578947368421053, "grad_norm": 1.1878390185089365, "learning_rate": 9.389097744360903e-05, "loss": 0.114, "step": 1000 }, { "epoch": 0.6644736842105263, "grad_norm": 0.8915150933559234, "learning_rate": 9.483082706766918e-05, "loss": 0.1054, "step": 1010 }, { "epoch": 0.6710526315789473, "grad_norm": 0.7818448157917527, "learning_rate": 9.577067669172933e-05, "loss": 0.0996, "step": 1020 }, { "epoch": 0.6776315789473685, "grad_norm": 0.990430969229284, "learning_rate": 9.671052631578947e-05, "loss": 0.0974, "step": 1030 }, { "epoch": 0.6842105263157895, "grad_norm": 0.9276518666370865, "learning_rate": 9.765037593984962e-05, "loss": 0.0933, "step": 1040 }, { "epoch": 0.6907894736842105, "grad_norm": 0.6846215892309722, "learning_rate": 9.859022556390977e-05, "loss": 0.0874, "step": 1050 }, { "epoch": 0.6973684210526315, "grad_norm": 0.714553023496577, "learning_rate": 9.953007518796992e-05, "loss": 0.0814, "step": 1060 }, { "epoch": 0.7039473684210527, "grad_norm": 0.7546346945965402, "learning_rate": 9.999993273155467e-05, "loss": 0.0774, "step": 1070 }, { "epoch": 0.7105263157894737, "grad_norm": 0.571192300635228, "learning_rate": 9.999939458507816e-05, "loss": 0.0762, "step": 1080 }, { "epoch": 0.7171052631578947, "grad_norm": 0.8584193322720889, "learning_rate": 9.999831829791713e-05, "loss": 0.0756, "step": 1090 }, { "epoch": 0.7236842105263158, "grad_norm": 1.3952479453359226, "learning_rate": 9.999670388165563e-05, "loss": 0.075, "step": 1100 }, { "epoch": 0.7302631578947368, "grad_norm": 0.751465926189691, "learning_rate": 9.999455135366951e-05, "loss": 0.069, "step": 1110 }, { "epoch": 0.7368421052631579, "grad_norm": 0.4873110858150168, "learning_rate": 9.999186073712635e-05, "loss": 0.064, "step": 1120 }, { "epoch": 0.743421052631579, "grad_norm": 0.4495642582063532, "learning_rate": 9.998863206098507e-05, "loss": 0.0623, "step": 1130 }, { "epoch": 0.75, "grad_norm": 0.45684969056385805, "learning_rate": 9.998486535999573e-05, "loss": 0.059, "step": 1140 }, { "epoch": 0.756578947368421, "grad_norm": 0.4304228051311271, "learning_rate": 9.998056067469915e-05, "loss": 0.0574, "step": 1150 }, { "epoch": 0.7631578947368421, "grad_norm": 0.38692754350368835, "learning_rate": 9.997571805142639e-05, "loss": 0.0568, "step": 1160 }, { "epoch": 0.7697368421052632, "grad_norm": 0.44697102978905795, "learning_rate": 9.997033754229835e-05, "loss": 0.054, "step": 1170 }, { "epoch": 0.7763157894736842, "grad_norm": 0.3475319362475707, "learning_rate": 9.996441920522512e-05, "loss": 0.0512, "step": 1180 }, { "epoch": 0.7828947368421053, "grad_norm": 0.3776964171490181, "learning_rate": 9.995796310390547e-05, "loss": 0.0496, "step": 1190 }, { "epoch": 0.7894736842105263, "grad_norm": 0.3599383764053137, "learning_rate": 9.995096930782604e-05, "loss": 0.049, "step": 1200 }, { "epoch": 0.7960526315789473, "grad_norm": 0.4004701605242826, "learning_rate": 9.994343789226066e-05, "loss": 0.0468, "step": 1210 }, { "epoch": 0.8026315789473685, "grad_norm": 0.3822329385724864, "learning_rate": 9.993536893826954e-05, "loss": 0.0457, "step": 1220 }, { "epoch": 0.8092105263157895, "grad_norm": 0.3620248875103048, "learning_rate": 9.992676253269837e-05, "loss": 0.0446, "step": 1230 }, { "epoch": 0.8157894736842105, "grad_norm": 0.28358957764617276, "learning_rate": 9.991761876817743e-05, "loss": 0.0429, "step": 1240 }, { "epoch": 0.8223684210526315, "grad_norm": 0.32929903528232773, "learning_rate": 9.990793774312053e-05, "loss": 0.0421, "step": 1250 }, { "epoch": 0.8289473684210527, "grad_norm": 0.34141322063560897, "learning_rate": 9.9897719561724e-05, "loss": 0.0418, "step": 1260 }, { "epoch": 0.8355263157894737, "grad_norm": 0.28296527941759625, "learning_rate": 9.988696433396557e-05, "loss": 0.0403, "step": 1270 }, { "epoch": 0.8421052631578947, "grad_norm": 0.3686897659419288, "learning_rate": 9.987567217560314e-05, "loss": 0.0395, "step": 1280 }, { "epoch": 0.8486842105263158, "grad_norm": 0.3066999773216274, "learning_rate": 9.986384320817359e-05, "loss": 0.0395, "step": 1290 }, { "epoch": 0.8552631578947368, "grad_norm": 0.33225917789321974, "learning_rate": 9.985147755899142e-05, "loss": 0.0385, "step": 1300 }, { "epoch": 0.8618421052631579, "grad_norm": 0.3004075266809671, "learning_rate": 9.983857536114743e-05, "loss": 0.0377, "step": 1310 }, { "epoch": 0.868421052631579, "grad_norm": 0.2698302147467991, "learning_rate": 9.982513675350724e-05, "loss": 0.0367, "step": 1320 }, { "epoch": 0.875, "grad_norm": 0.26807280624783797, "learning_rate": 9.981116188070984e-05, "loss": 0.0356, "step": 1330 }, { "epoch": 0.881578947368421, "grad_norm": 0.3127969801843736, "learning_rate": 9.979665089316602e-05, "loss": 0.035, "step": 1340 }, { "epoch": 0.8881578947368421, "grad_norm": 0.28653732054861003, "learning_rate": 9.978160394705668e-05, "loss": 0.0343, "step": 1350 }, { "epoch": 0.8947368421052632, "grad_norm": 0.2504478087548026, "learning_rate": 9.976602120433133e-05, "loss": 0.0341, "step": 1360 }, { "epoch": 0.9013157894736842, "grad_norm": 0.24532062538161709, "learning_rate": 9.97499028327061e-05, "loss": 0.0331, "step": 1370 }, { "epoch": 0.9078947368421053, "grad_norm": 0.5595503828448865, "learning_rate": 9.973324900566213e-05, "loss": 0.041, "step": 1380 }, { "epoch": 0.9144736842105263, "grad_norm": 0.32103277633584737, "learning_rate": 9.971605990244365e-05, "loss": 0.0396, "step": 1390 }, { "epoch": 0.9210526315789473, "grad_norm": 0.39243105455264066, "learning_rate": 9.969833570805599e-05, "loss": 0.0345, "step": 1400 }, { "epoch": 0.9276315789473685, "grad_norm": 0.24537350120004972, "learning_rate": 9.968007661326369e-05, "loss": 0.0323, "step": 1410 }, { "epoch": 0.9342105263157895, "grad_norm": 0.21282115870790244, "learning_rate": 9.966128281458832e-05, "loss": 0.0309, "step": 1420 }, { "epoch": 0.9407894736842105, "grad_norm": 0.22792100873990018, "learning_rate": 9.964195451430653e-05, "loss": 0.0302, "step": 1430 }, { "epoch": 0.9473684210526315, "grad_norm": 0.2513211642537743, "learning_rate": 9.962209192044772e-05, "loss": 0.0298, "step": 1440 }, { "epoch": 0.9539473684210527, "grad_norm": 0.25009559541845094, "learning_rate": 9.960169524679187e-05, "loss": 0.0293, "step": 1450 }, { "epoch": 0.9605263157894737, "grad_norm": 0.23293995789061867, "learning_rate": 9.958076471286724e-05, "loss": 0.0289, "step": 1460 }, { "epoch": 0.9671052631578947, "grad_norm": 0.22361624312785255, "learning_rate": 9.955930054394798e-05, "loss": 0.0282, "step": 1470 }, { "epoch": 0.9736842105263158, "grad_norm": 0.23906361425178743, "learning_rate": 9.953730297105175e-05, "loss": 0.0281, "step": 1480 }, { "epoch": 0.9802631578947368, "grad_norm": 0.23143391534241473, "learning_rate": 9.951477223093722e-05, "loss": 0.0275, "step": 1490 }, { "epoch": 0.9868421052631579, "grad_norm": 0.2147052689574608, "learning_rate": 9.949170856610144e-05, "loss": 0.0271, "step": 1500 }, { "epoch": 0.993421052631579, "grad_norm": 0.20377711124649098, "learning_rate": 9.946811222477737e-05, "loss": 0.0263, "step": 1510 }, { "epoch": 1.0, "grad_norm": 0.2135903768894096, "learning_rate": 9.944398346093109e-05, "loss": 0.0262, "step": 1520 }, { "epoch": 1.006578947368421, "grad_norm": 0.20254766138767108, "learning_rate": 9.941932253425917e-05, "loss": 0.0248, "step": 1530 }, { "epoch": 1.013157894736842, "grad_norm": 0.2197030932035537, "learning_rate": 9.939412971018574e-05, "loss": 0.0246, "step": 1540 }, { "epoch": 1.019736842105263, "grad_norm": 0.1933628837351623, "learning_rate": 9.936840525985978e-05, "loss": 0.0242, "step": 1550 }, { "epoch": 1.0263157894736843, "grad_norm": 0.19721213696918533, "learning_rate": 9.934214946015213e-05, "loss": 0.0238, "step": 1560 }, { "epoch": 1.0328947368421053, "grad_norm": 0.20774618691091581, "learning_rate": 9.931536259365244e-05, "loss": 0.0234, "step": 1570 }, { "epoch": 1.0394736842105263, "grad_norm": 0.19785742831408606, "learning_rate": 9.928804494866629e-05, "loss": 0.0228, "step": 1580 }, { "epoch": 1.0460526315789473, "grad_norm": 0.2035358859489929, "learning_rate": 9.926019681921196e-05, "loss": 0.0227, "step": 1590 }, { "epoch": 1.0526315789473684, "grad_norm": 0.20629560858059492, "learning_rate": 9.92318185050173e-05, "loss": 0.0227, "step": 1600 }, { "epoch": 1.0592105263157894, "grad_norm": 0.17943582514083126, "learning_rate": 9.920291031151652e-05, "loss": 0.0223, "step": 1610 }, { "epoch": 1.0657894736842106, "grad_norm": 0.2069047937737935, "learning_rate": 9.917347254984688e-05, "loss": 0.0219, "step": 1620 }, { "epoch": 1.0723684210526316, "grad_norm": 0.18149990279040348, "learning_rate": 9.91435055368454e-05, "loss": 0.0215, "step": 1630 }, { "epoch": 1.0789473684210527, "grad_norm": 0.21588259501861692, "learning_rate": 9.91130095950453e-05, "loss": 0.0216, "step": 1640 }, { "epoch": 1.0855263157894737, "grad_norm": 0.19248955273518795, "learning_rate": 9.908198505267273e-05, "loss": 0.0211, "step": 1650 }, { "epoch": 1.0921052631578947, "grad_norm": 0.21323425974286558, "learning_rate": 9.90504322436431e-05, "loss": 0.0212, "step": 1660 }, { "epoch": 1.0986842105263157, "grad_norm": 0.19659430552879165, "learning_rate": 9.901835150755754e-05, "loss": 0.0204, "step": 1670 }, { "epoch": 1.1052631578947367, "grad_norm": 0.18723287056746327, "learning_rate": 9.898574318969918e-05, "loss": 0.0202, "step": 1680 }, { "epoch": 1.111842105263158, "grad_norm": 0.18512625335755417, "learning_rate": 9.895260764102956e-05, "loss": 0.0198, "step": 1690 }, { "epoch": 1.118421052631579, "grad_norm": 0.19124114649058113, "learning_rate": 9.89189452181847e-05, "loss": 0.0201, "step": 1700 }, { "epoch": 1.125, "grad_norm": 0.18895302686535878, "learning_rate": 9.888475628347142e-05, "loss": 0.0195, "step": 1710 }, { "epoch": 1.131578947368421, "grad_norm": 0.1772267382799342, "learning_rate": 9.885004120486326e-05, "loss": 0.0191, "step": 1720 }, { "epoch": 1.138157894736842, "grad_norm": 0.17908235775562148, "learning_rate": 9.881480035599667e-05, "loss": 0.0189, "step": 1730 }, { "epoch": 1.1447368421052633, "grad_norm": 0.17580586627136524, "learning_rate": 9.877903411616697e-05, "loss": 0.0189, "step": 1740 }, { "epoch": 1.1513157894736843, "grad_norm": 0.18518601084678493, "learning_rate": 9.874274287032417e-05, "loss": 0.0186, "step": 1750 }, { "epoch": 1.1578947368421053, "grad_norm": 0.18048608002452143, "learning_rate": 9.870592700906892e-05, "loss": 0.0183, "step": 1760 }, { "epoch": 1.1644736842105263, "grad_norm": 0.15777383982627308, "learning_rate": 9.866858692864829e-05, "loss": 0.018, "step": 1770 }, { "epoch": 1.1710526315789473, "grad_norm": 0.20607208990685497, "learning_rate": 9.863072303095144e-05, "loss": 0.0175, "step": 1780 }, { "epoch": 1.1776315789473684, "grad_norm": 0.1611318675087161, "learning_rate": 9.859233572350541e-05, "loss": 0.0171, "step": 1790 }, { "epoch": 1.1842105263157894, "grad_norm": 0.17589801094486104, "learning_rate": 9.855342541947065e-05, "loss": 0.0171, "step": 1800 }, { "epoch": 1.1907894736842106, "grad_norm": 0.17121384019730954, "learning_rate": 9.851399253763656e-05, "loss": 0.017, "step": 1810 }, { "epoch": 1.1973684210526316, "grad_norm": 0.16253563174923477, "learning_rate": 9.847403750241704e-05, "loss": 0.0166, "step": 1820 }, { "epoch": 1.2039473684210527, "grad_norm": 0.17851024747091337, "learning_rate": 9.84335607438459e-05, "loss": 0.0166, "step": 1830 }, { "epoch": 1.2105263157894737, "grad_norm": 0.16919035493728743, "learning_rate": 9.839256269757223e-05, "loss": 0.0161, "step": 1840 }, { "epoch": 1.2171052631578947, "grad_norm": 0.1939807706315173, "learning_rate": 9.835104380485572e-05, "loss": 0.0163, "step": 1850 }, { "epoch": 1.2236842105263157, "grad_norm": 0.17147592181772123, "learning_rate": 9.830900451256187e-05, "loss": 0.0157, "step": 1860 }, { "epoch": 1.2302631578947367, "grad_norm": 0.17218945397214414, "learning_rate": 9.826644527315722e-05, "loss": 0.0156, "step": 1870 }, { "epoch": 1.236842105263158, "grad_norm": 0.16873620481355664, "learning_rate": 9.82233665447045e-05, "loss": 0.0151, "step": 1880 }, { "epoch": 1.243421052631579, "grad_norm": 0.16469742855514352, "learning_rate": 9.817976879085764e-05, "loss": 0.0153, "step": 1890 }, { "epoch": 1.25, "grad_norm": 0.1692877712959756, "learning_rate": 9.813565248085686e-05, "loss": 0.0148, "step": 1900 }, { "epoch": 1.256578947368421, "grad_norm": 0.16625631046909073, "learning_rate": 9.809101808952348e-05, "loss": 0.0148, "step": 1910 }, { "epoch": 1.263157894736842, "grad_norm": 0.18262802890291954, "learning_rate": 9.804586609725499e-05, "loss": 0.0147, "step": 1920 }, { "epoch": 1.2697368421052633, "grad_norm": 0.18607861180613644, "learning_rate": 9.800019699001974e-05, "loss": 0.0144, "step": 1930 }, { "epoch": 1.2763157894736843, "grad_norm": 0.16285676137508193, "learning_rate": 9.795401125935177e-05, "loss": 0.0143, "step": 1940 }, { "epoch": 1.2828947368421053, "grad_norm": 0.1707670608457863, "learning_rate": 9.790730940234552e-05, "loss": 0.0143, "step": 1950 }, { "epoch": 1.2894736842105263, "grad_norm": 0.15525731103278195, "learning_rate": 9.786009192165048e-05, "loss": 0.0137, "step": 1960 }, { "epoch": 1.2960526315789473, "grad_norm": 0.16347793214903164, "learning_rate": 9.781235932546574e-05, "loss": 0.0133, "step": 1970 }, { "epoch": 1.3026315789473684, "grad_norm": 0.15933544137667022, "learning_rate": 9.776411212753453e-05, "loss": 0.0134, "step": 1980 }, { "epoch": 1.3092105263157894, "grad_norm": 0.13814532510818728, "learning_rate": 9.771535084713879e-05, "loss": 0.0129, "step": 1990 }, { "epoch": 1.3157894736842106, "grad_norm": 0.16523793061268452, "learning_rate": 9.766607600909341e-05, "loss": 0.0128, "step": 2000 }, { "epoch": 1.3223684210526316, "grad_norm": 0.14022908820622706, "learning_rate": 9.761628814374073e-05, "loss": 0.0126, "step": 2010 }, { "epoch": 1.3289473684210527, "grad_norm": 0.2069333200433914, "learning_rate": 9.756598778694477e-05, "loss": 0.0125, "step": 2020 }, { "epoch": 1.3355263157894737, "grad_norm": 0.17334974425963282, "learning_rate": 9.751517548008542e-05, "loss": 0.0123, "step": 2030 }, { "epoch": 1.3421052631578947, "grad_norm": 0.1505657722626437, "learning_rate": 9.746385177005272e-05, "loss": 0.0121, "step": 2040 }, { "epoch": 1.3486842105263157, "grad_norm": 0.168192073561971, "learning_rate": 9.741201720924089e-05, "loss": 0.0117, "step": 2050 }, { "epoch": 1.3552631578947367, "grad_norm": 0.15074266703733896, "learning_rate": 9.73596723555424e-05, "loss": 0.0119, "step": 2060 }, { "epoch": 1.361842105263158, "grad_norm": 0.17348324277964447, "learning_rate": 9.730681777234196e-05, "loss": 0.0115, "step": 2070 }, { "epoch": 1.368421052631579, "grad_norm": 0.14638399471630661, "learning_rate": 9.725345402851053e-05, "loss": 0.0118, "step": 2080 }, { "epoch": 1.375, "grad_norm": 0.15352208983536622, "learning_rate": 9.719958169839906e-05, "loss": 0.0113, "step": 2090 }, { "epoch": 1.381578947368421, "grad_norm": 0.16084962439952788, "learning_rate": 9.714520136183243e-05, "loss": 0.0115, "step": 2100 }, { "epoch": 1.388157894736842, "grad_norm": 0.1344941180659645, "learning_rate": 9.709031360410318e-05, "loss": 0.011, "step": 2110 }, { "epoch": 1.3947368421052633, "grad_norm": 0.1452614934065403, "learning_rate": 9.703491901596516e-05, "loss": 0.0109, "step": 2120 }, { "epoch": 1.4013157894736843, "grad_norm": 0.13843890039006693, "learning_rate": 9.697901819362721e-05, "loss": 0.0107, "step": 2130 }, { "epoch": 1.4078947368421053, "grad_norm": 0.13684375615554292, "learning_rate": 9.692261173874675e-05, "loss": 0.0105, "step": 2140 }, { "epoch": 1.4144736842105263, "grad_norm": 0.14083447160331208, "learning_rate": 9.68657002584233e-05, "loss": 0.0102, "step": 2150 }, { "epoch": 1.4210526315789473, "grad_norm": 0.13789659384952696, "learning_rate": 9.680828436519196e-05, "loss": 0.0104, "step": 2160 }, { "epoch": 1.4276315789473684, "grad_norm": 0.14516526202810717, "learning_rate": 9.675036467701674e-05, "loss": 0.0101, "step": 2170 }, { "epoch": 1.4342105263157894, "grad_norm": 0.12293537720506266, "learning_rate": 9.669194181728403e-05, "loss": 0.0099, "step": 2180 }, { "epoch": 1.4407894736842106, "grad_norm": 0.1259249188196858, "learning_rate": 9.663301641479579e-05, "loss": 0.0097, "step": 2190 }, { "epoch": 1.4473684210526316, "grad_norm": 0.12557298712724865, "learning_rate": 9.65735891037628e-05, "loss": 0.0097, "step": 2200 }, { "epoch": 1.4539473684210527, "grad_norm": 0.143039377177587, "learning_rate": 9.65136605237979e-05, "loss": 0.0094, "step": 2210 }, { "epoch": 1.4605263157894737, "grad_norm": 0.13504613441385002, "learning_rate": 9.645323131990908e-05, "loss": 0.0096, "step": 2220 }, { "epoch": 1.4671052631578947, "grad_norm": 0.13228183618353204, "learning_rate": 9.639230214249242e-05, "loss": 0.0093, "step": 2230 }, { "epoch": 1.4736842105263157, "grad_norm": 0.1480027541710592, "learning_rate": 9.633087364732527e-05, "loss": 0.0093, "step": 2240 }, { "epoch": 1.4802631578947367, "grad_norm": 0.1293455699844313, "learning_rate": 9.626894649555909e-05, "loss": 0.0094, "step": 2250 }, { "epoch": 1.486842105263158, "grad_norm": 0.1393940674869785, "learning_rate": 9.620652135371232e-05, "loss": 0.0091, "step": 2260 }, { "epoch": 1.493421052631579, "grad_norm": 0.15121559409028545, "learning_rate": 9.61435988936633e-05, "loss": 0.0091, "step": 2270 }, { "epoch": 1.5, "grad_norm": 0.1301327368552193, "learning_rate": 9.608017979264292e-05, "loss": 0.0091, "step": 2280 }, { "epoch": 1.506578947368421, "grad_norm": 0.1421460799492161, "learning_rate": 9.601626473322744e-05, "loss": 0.0089, "step": 2290 }, { "epoch": 1.513157894736842, "grad_norm": 0.17041691269286594, "learning_rate": 9.595185440333103e-05, "loss": 0.0092, "step": 2300 }, { "epoch": 1.5197368421052633, "grad_norm": 0.14376606305315906, "learning_rate": 9.588694949619851e-05, "loss": 0.0086, "step": 2310 }, { "epoch": 1.526315789473684, "grad_norm": 0.13694156071766578, "learning_rate": 9.582155071039771e-05, "loss": 0.0087, "step": 2320 }, { "epoch": 1.5328947368421053, "grad_norm": 0.12727756352863123, "learning_rate": 9.575565874981214e-05, "loss": 0.0087, "step": 2330 }, { "epoch": 1.5394736842105263, "grad_norm": 0.12785472470651071, "learning_rate": 9.568927432363327e-05, "loss": 0.0082, "step": 2340 }, { "epoch": 1.5460526315789473, "grad_norm": 0.12091981259643964, "learning_rate": 9.562239814635294e-05, "loss": 0.0083, "step": 2350 }, { "epoch": 1.5526315789473686, "grad_norm": 0.12758853427180586, "learning_rate": 9.555503093775575e-05, "loss": 0.008, "step": 2360 }, { "epoch": 1.5592105263157894, "grad_norm": 0.12354223372657464, "learning_rate": 9.548717342291115e-05, "loss": 0.0081, "step": 2370 }, { "epoch": 1.5657894736842106, "grad_norm": 0.12076843350000686, "learning_rate": 9.541882633216579e-05, "loss": 0.0079, "step": 2380 }, { "epoch": 1.5723684210526314, "grad_norm": 0.1197614697335571, "learning_rate": 9.534999040113559e-05, "loss": 0.008, "step": 2390 }, { "epoch": 1.5789473684210527, "grad_norm": 0.12153418093253635, "learning_rate": 9.52806663706978e-05, "loss": 0.0077, "step": 2400 }, { "epoch": 1.5855263157894737, "grad_norm": 0.13543828010220124, "learning_rate": 9.521085498698309e-05, "loss": 0.0079, "step": 2410 }, { "epoch": 1.5921052631578947, "grad_norm": 0.10948806505136653, "learning_rate": 9.514055700136747e-05, "loss": 0.0077, "step": 2420 }, { "epoch": 1.598684210526316, "grad_norm": 0.10980266602887555, "learning_rate": 9.506977317046424e-05, "loss": 0.0074, "step": 2430 }, { "epoch": 1.6052631578947367, "grad_norm": 0.12485717268206407, "learning_rate": 9.49985042561158e-05, "loss": 0.0075, "step": 2440 }, { "epoch": 1.611842105263158, "grad_norm": 0.11541304858534408, "learning_rate": 9.492675102538547e-05, "loss": 0.0072, "step": 2450 }, { "epoch": 1.618421052631579, "grad_norm": 0.12122451397522918, "learning_rate": 9.485451425054926e-05, "loss": 0.0072, "step": 2460 }, { "epoch": 1.625, "grad_norm": 0.4210179348904546, "learning_rate": 9.478179470908756e-05, "loss": 0.0075, "step": 2470 }, { "epoch": 1.631578947368421, "grad_norm": 0.5896074678764591, "learning_rate": 9.470859318367669e-05, "loss": 0.0086, "step": 2480 }, { "epoch": 1.638157894736842, "grad_norm": 3.7823641198616387, "learning_rate": 9.463491046218058e-05, "loss": 0.0186, "step": 2490 }, { "epoch": 1.6447368421052633, "grad_norm": 5.014692495425624, "learning_rate": 9.456074733764224e-05, "loss": 0.0827, "step": 2500 }, { "epoch": 1.651315789473684, "grad_norm": 0.30328471004984053, "learning_rate": 9.448610460827522e-05, "loss": 0.0328, "step": 2510 }, { "epoch": 1.6578947368421053, "grad_norm": 0.17555996108962088, "learning_rate": 9.441098307745507e-05, "loss": 0.0119, "step": 2520 }, { "epoch": 1.6644736842105263, "grad_norm": 0.12830924181654307, "learning_rate": 9.433538355371057e-05, "loss": 0.0096, "step": 2530 }, { "epoch": 1.6710526315789473, "grad_norm": 0.1306978986667964, "learning_rate": 9.425930685071517e-05, "loss": 0.0083, "step": 2540 }, { "epoch": 1.6776315789473686, "grad_norm": 0.1507331325454933, "learning_rate": 9.418275378727819e-05, "loss": 0.0083, "step": 2550 }, { "epoch": 1.6842105263157894, "grad_norm": 0.11592835345613971, "learning_rate": 9.410572518733596e-05, "loss": 0.0079, "step": 2560 }, { "epoch": 1.6907894736842106, "grad_norm": 0.10808538914723062, "learning_rate": 9.402822187994298e-05, "loss": 0.0073, "step": 2570 }, { "epoch": 1.6973684210526314, "grad_norm": 0.11722096305528684, "learning_rate": 9.395024469926302e-05, "loss": 0.0073, "step": 2580 }, { "epoch": 1.7039473684210527, "grad_norm": 0.10458331688166168, "learning_rate": 9.387179448456009e-05, "loss": 0.0072, "step": 2590 }, { "epoch": 1.7105263157894737, "grad_norm": 0.11291592102103867, "learning_rate": 9.379287208018945e-05, "loss": 0.0067, "step": 2600 }, { "epoch": 1.7171052631578947, "grad_norm": 0.08646582566807197, "learning_rate": 9.371347833558856e-05, "loss": 0.0065, "step": 2610 }, { "epoch": 1.723684210526316, "grad_norm": 0.10553066382224695, "learning_rate": 9.363361410526783e-05, "loss": 0.0067, "step": 2620 }, { "epoch": 1.7302631578947367, "grad_norm": 0.09811144117737546, "learning_rate": 9.35532802488015e-05, "loss": 0.0065, "step": 2630 }, { "epoch": 1.736842105263158, "grad_norm": 0.09975550040113049, "learning_rate": 9.347247763081835e-05, "loss": 0.0064, "step": 2640 }, { "epoch": 1.743421052631579, "grad_norm": 0.11209372785035113, "learning_rate": 9.339120712099245e-05, "loss": 0.0065, "step": 2650 }, { "epoch": 1.75, "grad_norm": 0.09335458400468914, "learning_rate": 9.330946959403375e-05, "loss": 0.0061, "step": 2660 }, { "epoch": 1.756578947368421, "grad_norm": 0.0975073527993663, "learning_rate": 9.322726592967868e-05, "loss": 0.006, "step": 2670 }, { "epoch": 1.763157894736842, "grad_norm": 0.09366196020997528, "learning_rate": 9.314459701268065e-05, "loss": 0.006, "step": 2680 }, { "epoch": 1.7697368421052633, "grad_norm": 0.09562732934182246, "learning_rate": 9.306146373280061e-05, "loss": 0.0059, "step": 2690 }, { "epoch": 1.776315789473684, "grad_norm": 0.09966326146415878, "learning_rate": 9.297786698479739e-05, "loss": 0.006, "step": 2700 }, { "epoch": 1.7828947368421053, "grad_norm": 0.10122383105599052, "learning_rate": 9.289380766841811e-05, "loss": 0.0059, "step": 2710 }, { "epoch": 1.7894736842105263, "grad_norm": 0.10095110671102905, "learning_rate": 9.280928668838848e-05, "loss": 0.0057, "step": 2720 }, { "epoch": 1.7960526315789473, "grad_norm": 0.091482492267746, "learning_rate": 9.27243049544031e-05, "loss": 0.0057, "step": 2730 }, { "epoch": 1.8026315789473686, "grad_norm": 0.08891652643763134, "learning_rate": 9.263886338111559e-05, "loss": 0.0055, "step": 2740 }, { "epoch": 1.8092105263157894, "grad_norm": 0.09263144069565209, "learning_rate": 9.25529628881288e-05, "loss": 0.0055, "step": 2750 }, { "epoch": 1.8157894736842106, "grad_norm": 0.11137233685500829, "learning_rate": 9.246660439998497e-05, "loss": 0.0055, "step": 2760 }, { "epoch": 1.8223684210526314, "grad_norm": 0.11114880917458508, "learning_rate": 9.237978884615565e-05, "loss": 0.0054, "step": 2770 }, { "epoch": 1.8289473684210527, "grad_norm": 0.09841409593938921, "learning_rate": 9.229251716103179e-05, "loss": 0.0055, "step": 2780 }, { "epoch": 1.8355263157894737, "grad_norm": 0.11223577944844708, "learning_rate": 9.220479028391364e-05, "loss": 0.0054, "step": 2790 }, { "epoch": 1.8421052631578947, "grad_norm": 0.09110216546608073, "learning_rate": 9.211660915900069e-05, "loss": 0.0053, "step": 2800 }, { "epoch": 1.848684210526316, "grad_norm": 0.09506804998323148, "learning_rate": 9.202797473538143e-05, "loss": 0.0053, "step": 2810 }, { "epoch": 1.8552631578947367, "grad_norm": 0.09167591406498078, "learning_rate": 9.193888796702321e-05, "loss": 0.0052, "step": 2820 }, { "epoch": 1.861842105263158, "grad_norm": 0.0910480942341495, "learning_rate": 9.184934981276192e-05, "loss": 0.0053, "step": 2830 }, { "epoch": 1.868421052631579, "grad_norm": 0.08389589500624173, "learning_rate": 9.175936123629171e-05, "loss": 0.0053, "step": 2840 }, { "epoch": 1.875, "grad_norm": 0.08751212493753141, "learning_rate": 9.16689232061546e-05, "loss": 0.0052, "step": 2850 }, { "epoch": 1.881578947368421, "grad_norm": 0.08925947798147087, "learning_rate": 9.157803669573e-05, "loss": 0.005, "step": 2860 }, { "epoch": 1.888157894736842, "grad_norm": 0.0896619316816315, "learning_rate": 9.148670268322438e-05, "loss": 0.005, "step": 2870 }, { "epoch": 1.8947368421052633, "grad_norm": 0.09175226088849178, "learning_rate": 9.139492215166059e-05, "loss": 0.0048, "step": 2880 }, { "epoch": 1.901315789473684, "grad_norm": 0.08885389457486895, "learning_rate": 9.130269608886735e-05, "loss": 0.005, "step": 2890 }, { "epoch": 1.9078947368421053, "grad_norm": 0.09883908696946943, "learning_rate": 9.12100254874686e-05, "loss": 0.0051, "step": 2900 }, { "epoch": 1.9144736842105263, "grad_norm": 0.09233528269274262, "learning_rate": 9.111691134487286e-05, "loss": 0.005, "step": 2910 }, { "epoch": 1.9210526315789473, "grad_norm": 0.08544980345629175, "learning_rate": 9.102335466326241e-05, "loss": 0.0049, "step": 2920 }, { "epoch": 1.9276315789473686, "grad_norm": 0.10003966542752647, "learning_rate": 9.092935644958257e-05, "loss": 0.0048, "step": 2930 }, { "epoch": 1.9342105263157894, "grad_norm": 0.08168055005388938, "learning_rate": 9.083491771553089e-05, "loss": 0.0047, "step": 2940 }, { "epoch": 1.9407894736842106, "grad_norm": 0.0992409697866901, "learning_rate": 9.074003947754615e-05, "loss": 0.0047, "step": 2950 }, { "epoch": 1.9473684210526314, "grad_norm": 0.08492119209203541, "learning_rate": 9.06447227567975e-05, "loss": 0.0048, "step": 2960 }, { "epoch": 1.9539473684210527, "grad_norm": 0.08129120975425032, "learning_rate": 9.054896857917349e-05, "loss": 0.0048, "step": 2970 }, { "epoch": 1.9605263157894737, "grad_norm": 0.08471582707226462, "learning_rate": 9.045277797527096e-05, "loss": 0.0047, "step": 2980 }, { "epoch": 1.9671052631578947, "grad_norm": 0.08915074149762475, "learning_rate": 9.035615198038401e-05, "loss": 0.0047, "step": 2990 }, { "epoch": 1.973684210526316, "grad_norm": 0.08922804724560857, "learning_rate": 9.02590916344928e-05, "loss": 0.0046, "step": 3000 }, { "epoch": 1.9802631578947367, "grad_norm": 0.08357488105287375, "learning_rate": 9.016159798225239e-05, "loss": 0.0045, "step": 3010 }, { "epoch": 1.986842105263158, "grad_norm": 0.09089197660267276, "learning_rate": 9.006367207298152e-05, "loss": 0.0045, "step": 3020 }, { "epoch": 1.993421052631579, "grad_norm": 0.07872067497811534, "learning_rate": 8.996531496065128e-05, "loss": 0.0046, "step": 3030 }, { "epoch": 2.0, "grad_norm": 0.08439906072392114, "learning_rate": 8.986652770387372e-05, "loss": 0.0044, "step": 3040 }, { "epoch": 2.0065789473684212, "grad_norm": 0.06961910527253773, "learning_rate": 8.976731136589059e-05, "loss": 0.0033, "step": 3050 }, { "epoch": 2.013157894736842, "grad_norm": 0.07154791151160267, "learning_rate": 8.966766701456177e-05, "loss": 0.0033, "step": 3060 }, { "epoch": 2.0197368421052633, "grad_norm": 0.07772175093467776, "learning_rate": 8.956759572235383e-05, "loss": 0.0031, "step": 3070 }, { "epoch": 2.026315789473684, "grad_norm": 0.0733292062504736, "learning_rate": 8.946709856632848e-05, "loss": 0.0031, "step": 3080 }, { "epoch": 2.0328947368421053, "grad_norm": 0.07783736387463817, "learning_rate": 8.9366176628131e-05, "loss": 0.003, "step": 3090 }, { "epoch": 2.039473684210526, "grad_norm": 0.06633555943399455, "learning_rate": 8.926483099397855e-05, "loss": 0.003, "step": 3100 }, { "epoch": 2.0460526315789473, "grad_norm": 0.07782294604433761, "learning_rate": 8.916306275464852e-05, "loss": 0.0029, "step": 3110 }, { "epoch": 2.0526315789473686, "grad_norm": 0.07670901138238165, "learning_rate": 8.906087300546675e-05, "loss": 0.0031, "step": 3120 }, { "epoch": 2.0592105263157894, "grad_norm": 0.07524758423152544, "learning_rate": 8.895826284629582e-05, "loss": 0.0029, "step": 3130 }, { "epoch": 2.0657894736842106, "grad_norm": 0.07695970302800449, "learning_rate": 8.885523338152313e-05, "loss": 0.0031, "step": 3140 }, { "epoch": 2.0723684210526314, "grad_norm": 0.0745426942514364, "learning_rate": 8.875178572004903e-05, "loss": 0.0032, "step": 3150 }, { "epoch": 2.0789473684210527, "grad_norm": 0.0723930470222858, "learning_rate": 8.864792097527489e-05, "loss": 0.0031, "step": 3160 }, { "epoch": 2.085526315789474, "grad_norm": 0.08361406797403782, "learning_rate": 8.854364026509117e-05, "loss": 0.0031, "step": 3170 }, { "epoch": 2.0921052631578947, "grad_norm": 0.06955666676258866, "learning_rate": 8.843894471186529e-05, "loss": 0.0031, "step": 3180 }, { "epoch": 2.098684210526316, "grad_norm": 0.07227264207927699, "learning_rate": 8.833383544242966e-05, "loss": 0.0031, "step": 3190 }, { "epoch": 2.1052631578947367, "grad_norm": 0.06914653302815033, "learning_rate": 8.822831358806942e-05, "loss": 0.0029, "step": 3200 }, { "epoch": 2.111842105263158, "grad_norm": 0.07323401762292578, "learning_rate": 8.812238028451043e-05, "loss": 0.003, "step": 3210 }, { "epoch": 2.1184210526315788, "grad_norm": 0.07393279181869614, "learning_rate": 8.801603667190686e-05, "loss": 0.003, "step": 3220 }, { "epoch": 2.125, "grad_norm": 0.07096487949532827, "learning_rate": 8.790928389482909e-05, "loss": 0.003, "step": 3230 }, { "epoch": 2.1315789473684212, "grad_norm": 0.0728089853059884, "learning_rate": 8.780212310225126e-05, "loss": 0.0031, "step": 3240 }, { "epoch": 2.138157894736842, "grad_norm": 0.0695501122917682, "learning_rate": 8.7694555447539e-05, "loss": 0.0031, "step": 3250 }, { "epoch": 2.1447368421052633, "grad_norm": 0.07705485434544583, "learning_rate": 8.758658208843694e-05, "loss": 0.0031, "step": 3260 }, { "epoch": 2.151315789473684, "grad_norm": 0.0845273469079357, "learning_rate": 8.74782041870563e-05, "loss": 0.0031, "step": 3270 }, { "epoch": 2.1578947368421053, "grad_norm": 0.08068281928940782, "learning_rate": 8.736942290986239e-05, "loss": 0.0031, "step": 3280 }, { "epoch": 2.1644736842105265, "grad_norm": 0.07961859812048024, "learning_rate": 8.726023942766196e-05, "loss": 0.003, "step": 3290 }, { "epoch": 2.1710526315789473, "grad_norm": 0.08758099933665693, "learning_rate": 8.715065491559076e-05, "loss": 0.0029, "step": 3300 }, { "epoch": 2.1776315789473686, "grad_norm": 0.07188296495338724, "learning_rate": 8.704067055310072e-05, "loss": 0.0031, "step": 3310 }, { "epoch": 2.1842105263157894, "grad_norm": 0.07663306624675915, "learning_rate": 8.693028752394741e-05, "loss": 0.003, "step": 3320 }, { "epoch": 2.1907894736842106, "grad_norm": 0.07462874387461102, "learning_rate": 8.681950701617715e-05, "loss": 0.003, "step": 3330 }, { "epoch": 2.1973684210526314, "grad_norm": 0.07336225552850846, "learning_rate": 8.67083302221144e-05, "loss": 0.003, "step": 3340 }, { "epoch": 2.2039473684210527, "grad_norm": 0.0752519347418371, "learning_rate": 8.659675833834872e-05, "loss": 0.0029, "step": 3350 }, { "epoch": 2.2105263157894735, "grad_norm": 0.0727931975094885, "learning_rate": 8.648479256572208e-05, "loss": 0.003, "step": 3360 }, { "epoch": 2.2171052631578947, "grad_norm": 0.07511952648108541, "learning_rate": 8.637243410931582e-05, "loss": 0.0029, "step": 3370 }, { "epoch": 2.223684210526316, "grad_norm": 0.07882019908319284, "learning_rate": 8.625968417843769e-05, "loss": 0.0029, "step": 3380 }, { "epoch": 2.2302631578947367, "grad_norm": 0.08265112815093757, "learning_rate": 8.614654398660889e-05, "loss": 0.0029, "step": 3390 }, { "epoch": 2.236842105263158, "grad_norm": 0.0797172772654838, "learning_rate": 8.603301475155098e-05, "loss": 0.003, "step": 3400 }, { "epoch": 2.2434210526315788, "grad_norm": 0.07058513328217333, "learning_rate": 8.591909769517277e-05, "loss": 0.0031, "step": 3410 }, { "epoch": 2.25, "grad_norm": 0.0806856826321758, "learning_rate": 8.580479404355714e-05, "loss": 0.003, "step": 3420 }, { "epoch": 2.2565789473684212, "grad_norm": 0.08816650076302643, "learning_rate": 8.56901050269479e-05, "loss": 0.003, "step": 3430 }, { "epoch": 2.263157894736842, "grad_norm": 0.08576523991244484, "learning_rate": 8.557503187973651e-05, "loss": 0.0031, "step": 3440 }, { "epoch": 2.2697368421052633, "grad_norm": 0.07817935240746017, "learning_rate": 8.545957584044882e-05, "loss": 0.003, "step": 3450 }, { "epoch": 2.276315789473684, "grad_norm": 0.07132102691438429, "learning_rate": 8.534373815173173e-05, "loss": 0.0028, "step": 3460 }, { "epoch": 2.2828947368421053, "grad_norm": 0.06907666862127639, "learning_rate": 8.522752006033977e-05, "loss": 0.0029, "step": 3470 }, { "epoch": 2.2894736842105265, "grad_norm": 0.07888763534903219, "learning_rate": 8.511092281712174e-05, "loss": 0.0028, "step": 3480 }, { "epoch": 2.2960526315789473, "grad_norm": 0.07104911749539242, "learning_rate": 8.499394767700728e-05, "loss": 0.0028, "step": 3490 }, { "epoch": 2.3026315789473686, "grad_norm": 0.07161589717548758, "learning_rate": 8.487659589899325e-05, "loss": 0.003, "step": 3500 }, { "epoch": 2.3092105263157894, "grad_norm": 0.07545738438626039, "learning_rate": 8.475886874613027e-05, "loss": 0.003, "step": 3510 }, { "epoch": 2.3157894736842106, "grad_norm": 0.06960029822263444, "learning_rate": 8.464076748550911e-05, "loss": 0.0028, "step": 3520 }, { "epoch": 2.3223684210526314, "grad_norm": 0.09053565638501836, "learning_rate": 8.4522293388247e-05, "loss": 0.003, "step": 3530 }, { "epoch": 2.3289473684210527, "grad_norm": 0.08111502757412685, "learning_rate": 8.440344772947403e-05, "loss": 0.0029, "step": 3540 }, { "epoch": 2.3355263157894735, "grad_norm": 0.07907419444465598, "learning_rate": 8.428423178831937e-05, "loss": 0.0029, "step": 3550 }, { "epoch": 2.3421052631578947, "grad_norm": 0.07530055852137314, "learning_rate": 8.416464684789751e-05, "loss": 0.0033, "step": 3560 }, { "epoch": 2.348684210526316, "grad_norm": 0.08578659904895668, "learning_rate": 8.404469419529448e-05, "loss": 0.0032, "step": 3570 }, { "epoch": 2.3552631578947367, "grad_norm": 0.07749694254198063, "learning_rate": 8.392437512155397e-05, "loss": 0.003, "step": 3580 }, { "epoch": 2.361842105263158, "grad_norm": 0.09613810033382267, "learning_rate": 8.380369092166343e-05, "loss": 0.0031, "step": 3590 }, { "epoch": 2.3684210526315788, "grad_norm": 0.10312166758776871, "learning_rate": 8.368264289454012e-05, "loss": 0.003, "step": 3600 }, { "epoch": 2.375, "grad_norm": 0.06867498813233379, "learning_rate": 8.35612323430172e-05, "loss": 0.003, "step": 3610 }, { "epoch": 2.3815789473684212, "grad_norm": 0.07705859736599766, "learning_rate": 8.343946057382967e-05, "loss": 0.0031, "step": 3620 }, { "epoch": 2.388157894736842, "grad_norm": 0.07041390906154826, "learning_rate": 8.33173288976002e-05, "loss": 0.0029, "step": 3630 }, { "epoch": 2.3947368421052633, "grad_norm": 0.08776967253298393, "learning_rate": 8.319483862882523e-05, "loss": 0.003, "step": 3640 }, { "epoch": 2.401315789473684, "grad_norm": 0.07556100987543657, "learning_rate": 8.307199108586064e-05, "loss": 0.0028, "step": 3650 }, { "epoch": 2.4078947368421053, "grad_norm": 0.07071854707231168, "learning_rate": 8.294878759090769e-05, "loss": 0.003, "step": 3660 }, { "epoch": 2.4144736842105265, "grad_norm": 0.06851373158159291, "learning_rate": 8.282522946999865e-05, "loss": 0.0028, "step": 3670 }, { "epoch": 2.4210526315789473, "grad_norm": 0.07586987705553193, "learning_rate": 8.270131805298269e-05, "loss": 0.003, "step": 3680 }, { "epoch": 2.4276315789473686, "grad_norm": 0.0711029870103729, "learning_rate": 8.257705467351145e-05, "loss": 0.0028, "step": 3690 }, { "epoch": 2.4342105263157894, "grad_norm": 0.07353488997496402, "learning_rate": 8.245244066902472e-05, "loss": 0.0027, "step": 3700 }, { "epoch": 2.4407894736842106, "grad_norm": 0.08069559598721139, "learning_rate": 8.232747738073606e-05, "loss": 0.0027, "step": 3710 }, { "epoch": 2.4473684210526314, "grad_norm": 0.08032004169661551, "learning_rate": 8.220216615361833e-05, "loss": 0.0028, "step": 3720 }, { "epoch": 2.4539473684210527, "grad_norm": 0.06368051417844219, "learning_rate": 8.207650833638926e-05, "loss": 0.0026, "step": 3730 }, { "epoch": 2.4605263157894735, "grad_norm": 0.0674086770746194, "learning_rate": 8.195050528149693e-05, "loss": 0.0029, "step": 3740 }, { "epoch": 2.4671052631578947, "grad_norm": 0.07830285476547033, "learning_rate": 8.18241583451051e-05, "loss": 0.0027, "step": 3750 }, { "epoch": 2.473684210526316, "grad_norm": 0.0866857145186936, "learning_rate": 8.169746888707884e-05, "loss": 0.0027, "step": 3760 }, { "epoch": 2.4802631578947367, "grad_norm": 0.06911558660644061, "learning_rate": 8.157043827096964e-05, "loss": 0.0028, "step": 3770 }, { "epoch": 2.486842105263158, "grad_norm": 0.07259825247456937, "learning_rate": 8.144306786400096e-05, "loss": 0.0028, "step": 3780 }, { "epoch": 2.4934210526315788, "grad_norm": 0.06844850269700717, "learning_rate": 8.131535903705332e-05, "loss": 0.0029, "step": 3790 }, { "epoch": 2.5, "grad_norm": 0.08278983177211563, "learning_rate": 8.118731316464967e-05, "loss": 0.0027, "step": 3800 }, { "epoch": 2.5065789473684212, "grad_norm": 0.06219877650762257, "learning_rate": 8.10589316249406e-05, "loss": 0.0027, "step": 3810 }, { "epoch": 2.513157894736842, "grad_norm": 0.06824657148655913, "learning_rate": 8.093021579968941e-05, "loss": 0.0028, "step": 3820 }, { "epoch": 2.5197368421052633, "grad_norm": 0.07996281509026834, "learning_rate": 8.080116707425732e-05, "loss": 0.003, "step": 3830 }, { "epoch": 2.526315789473684, "grad_norm": 0.06422551748134994, "learning_rate": 8.067178683758855e-05, "loss": 0.0027, "step": 3840 }, { "epoch": 2.5328947368421053, "grad_norm": 0.09323022007000262, "learning_rate": 8.054207648219534e-05, "loss": 0.0029, "step": 3850 }, { "epoch": 2.5394736842105265, "grad_norm": 0.07497257348678213, "learning_rate": 8.041203740414298e-05, "loss": 0.0028, "step": 3860 }, { "epoch": 2.5460526315789473, "grad_norm": 0.08301851491054957, "learning_rate": 8.028167100303476e-05, "loss": 0.0028, "step": 3870 }, { "epoch": 2.5526315789473686, "grad_norm": 0.06474154045528839, "learning_rate": 8.015097868199699e-05, "loss": 0.0028, "step": 3880 }, { "epoch": 2.5592105263157894, "grad_norm": 0.06874706823653907, "learning_rate": 8.001996184766381e-05, "loss": 0.0027, "step": 3890 }, { "epoch": 2.5657894736842106, "grad_norm": 0.08107437503239583, "learning_rate": 7.988862191016205e-05, "loss": 0.0026, "step": 3900 }, { "epoch": 2.5723684210526314, "grad_norm": 0.07597780656490642, "learning_rate": 7.975696028309611e-05, "loss": 0.0026, "step": 3910 }, { "epoch": 2.5789473684210527, "grad_norm": 0.07357713377704023, "learning_rate": 7.96249783835327e-05, "loss": 0.0026, "step": 3920 }, { "epoch": 2.5855263157894735, "grad_norm": 0.06225901705415947, "learning_rate": 7.949267763198563e-05, "loss": 0.0027, "step": 3930 }, { "epoch": 2.5921052631578947, "grad_norm": 0.0703385334924199, "learning_rate": 7.936005945240051e-05, "loss": 0.0026, "step": 3940 }, { "epoch": 2.598684210526316, "grad_norm": 0.0736999092196569, "learning_rate": 7.92271252721393e-05, "loss": 0.0026, "step": 3950 }, { "epoch": 2.6052631578947367, "grad_norm": 0.07729069940862861, "learning_rate": 7.909387652196522e-05, "loss": 0.0026, "step": 3960 }, { "epoch": 2.611842105263158, "grad_norm": 0.07481211359608593, "learning_rate": 7.896031463602706e-05, "loss": 0.0024, "step": 3970 }, { "epoch": 2.6184210526315788, "grad_norm": 0.06814464123536673, "learning_rate": 7.882644105184395e-05, "loss": 0.0025, "step": 3980 }, { "epoch": 2.625, "grad_norm": 0.07129054851729393, "learning_rate": 7.869225721028978e-05, "loss": 0.0026, "step": 3990 }, { "epoch": 2.6315789473684212, "grad_norm": 0.08376454356231268, "learning_rate": 7.855776455557769e-05, "loss": 0.0026, "step": 4000 }, { "epoch": 2.638157894736842, "grad_norm": 0.06662673919070906, "learning_rate": 7.842296453524463e-05, "loss": 0.0025, "step": 4010 }, { "epoch": 2.6447368421052633, "grad_norm": 0.06020388907136684, "learning_rate": 7.828785860013564e-05, "loss": 0.0025, "step": 4020 }, { "epoch": 2.651315789473684, "grad_norm": 0.06444105223285773, "learning_rate": 7.815244820438836e-05, "loss": 0.0023, "step": 4030 }, { "epoch": 2.6578947368421053, "grad_norm": 0.06050467090500708, "learning_rate": 7.801673480541728e-05, "loss": 0.0024, "step": 4040 }, { "epoch": 2.6644736842105265, "grad_norm": 0.06527207049067266, "learning_rate": 7.788071986389814e-05, "loss": 0.0024, "step": 4050 }, { "epoch": 2.6710526315789473, "grad_norm": 0.06979889616926872, "learning_rate": 7.774440484375212e-05, "loss": 0.0023, "step": 4060 }, { "epoch": 2.6776315789473686, "grad_norm": 0.06743094271741353, "learning_rate": 7.760779121213013e-05, "loss": 0.0023, "step": 4070 }, { "epoch": 2.6842105263157894, "grad_norm": 0.07204637868870485, "learning_rate": 7.747088043939709e-05, "loss": 0.0024, "step": 4080 }, { "epoch": 2.6907894736842106, "grad_norm": 0.06415928404465751, "learning_rate": 7.733367399911593e-05, "loss": 0.0023, "step": 4090 }, { "epoch": 2.6973684210526314, "grad_norm": 0.07280188098779707, "learning_rate": 7.719617336803194e-05, "loss": 0.0026, "step": 4100 }, { "epoch": 2.7039473684210527, "grad_norm": 0.05998059047850096, "learning_rate": 7.705838002605665e-05, "loss": 0.0024, "step": 4110 }, { "epoch": 2.7105263157894735, "grad_norm": 0.06400082013104166, "learning_rate": 7.692029545625213e-05, "loss": 0.0024, "step": 4120 }, { "epoch": 2.7171052631578947, "grad_norm": 0.07352802986302866, "learning_rate": 7.678192114481487e-05, "loss": 0.0024, "step": 4130 }, { "epoch": 2.723684210526316, "grad_norm": 0.0702258918716786, "learning_rate": 7.664325858105981e-05, "loss": 0.0024, "step": 4140 }, { "epoch": 2.7302631578947367, "grad_norm": 0.06641871081534573, "learning_rate": 7.650430925740438e-05, "loss": 0.0023, "step": 4150 }, { "epoch": 2.736842105263158, "grad_norm": 0.06546274261192724, "learning_rate": 7.636507466935237e-05, "loss": 0.0023, "step": 4160 }, { "epoch": 2.7434210526315788, "grad_norm": 0.06644783924036698, "learning_rate": 7.622555631547784e-05, "loss": 0.0023, "step": 4170 }, { "epoch": 2.75, "grad_norm": 0.05362886039562456, "learning_rate": 7.608575569740906e-05, "loss": 0.0022, "step": 4180 }, { "epoch": 2.7565789473684212, "grad_norm": 0.06903071092819318, "learning_rate": 7.59456743198122e-05, "loss": 0.0023, "step": 4190 }, { "epoch": 2.763157894736842, "grad_norm": 0.05789722056728834, "learning_rate": 7.580531369037533e-05, "loss": 0.0021, "step": 4200 }, { "epoch": 2.7697368421052633, "grad_norm": 0.0643558212306574, "learning_rate": 7.566467531979202e-05, "loss": 0.0023, "step": 4210 }, { "epoch": 2.776315789473684, "grad_norm": 0.07052044594959722, "learning_rate": 7.55237607217452e-05, "loss": 0.0023, "step": 4220 }, { "epoch": 2.7828947368421053, "grad_norm": 0.064534269417758, "learning_rate": 7.538257141289079e-05, "loss": 0.0022, "step": 4230 }, { "epoch": 2.7894736842105265, "grad_norm": 0.060914750483076874, "learning_rate": 7.52411089128414e-05, "loss": 0.0021, "step": 4240 }, { "epoch": 2.7960526315789473, "grad_norm": 0.06975178617845787, "learning_rate": 7.509937474415001e-05, "loss": 0.0021, "step": 4250 }, { "epoch": 2.8026315789473686, "grad_norm": 0.05801976261020139, "learning_rate": 7.495737043229356e-05, "loss": 0.0022, "step": 4260 }, { "epoch": 2.8092105263157894, "grad_norm": 0.07312109565555201, "learning_rate": 7.481509750565647e-05, "loss": 0.0022, "step": 4270 }, { "epoch": 2.8157894736842106, "grad_norm": 0.06731904434882949, "learning_rate": 7.467255749551432e-05, "loss": 0.0023, "step": 4280 }, { "epoch": 2.8223684210526314, "grad_norm": 0.06865526567597074, "learning_rate": 7.452975193601723e-05, "loss": 0.0023, "step": 4290 }, { "epoch": 2.8289473684210527, "grad_norm": 0.08582709819548066, "learning_rate": 7.438668236417346e-05, "loss": 0.0024, "step": 4300 }, { "epoch": 2.8355263157894735, "grad_norm": 0.0739094089893243, "learning_rate": 7.424335031983278e-05, "loss": 0.0023, "step": 4310 }, { "epoch": 2.8421052631578947, "grad_norm": 0.05891595007709077, "learning_rate": 7.409975734566998e-05, "loss": 0.0022, "step": 4320 }, { "epoch": 2.848684210526316, "grad_norm": 0.0721809677663778, "learning_rate": 7.39559049871682e-05, "loss": 0.0023, "step": 4330 }, { "epoch": 2.8552631578947367, "grad_norm": 0.055924960105078504, "learning_rate": 7.381179479260233e-05, "loss": 0.0023, "step": 4340 }, { "epoch": 2.861842105263158, "grad_norm": 0.07924382043010371, "learning_rate": 7.36674283130223e-05, "loss": 0.0022, "step": 4350 }, { "epoch": 2.8684210526315788, "grad_norm": 0.07736302121317264, "learning_rate": 7.352280710223645e-05, "loss": 0.0025, "step": 4360 }, { "epoch": 2.875, "grad_norm": 0.07607651273281507, "learning_rate": 7.337793271679478e-05, "loss": 0.0024, "step": 4370 }, { "epoch": 2.8815789473684212, "grad_norm": 0.06346291574478992, "learning_rate": 7.323280671597219e-05, "loss": 0.0023, "step": 4380 }, { "epoch": 2.888157894736842, "grad_norm": 0.061302508622908966, "learning_rate": 7.308743066175172e-05, "loss": 0.0022, "step": 4390 }, { "epoch": 2.8947368421052633, "grad_norm": 0.0609505149341482, "learning_rate": 7.294180611880766e-05, "loss": 0.0022, "step": 4400 }, { "epoch": 2.901315789473684, "grad_norm": 0.06332339525555587, "learning_rate": 7.279593465448884e-05, "loss": 0.0023, "step": 4410 }, { "epoch": 2.9078947368421053, "grad_norm": 0.06389140242733114, "learning_rate": 7.264981783880166e-05, "loss": 0.0022, "step": 4420 }, { "epoch": 2.9144736842105265, "grad_norm": 0.05995795028450876, "learning_rate": 7.250345724439323e-05, "loss": 0.0022, "step": 4430 }, { "epoch": 2.9210526315789473, "grad_norm": 0.07002238446710278, "learning_rate": 7.235685444653444e-05, "loss": 0.0022, "step": 4440 }, { "epoch": 2.9276315789473686, "grad_norm": 0.06460285769189916, "learning_rate": 7.221001102310298e-05, "loss": 0.0023, "step": 4450 }, { "epoch": 2.9342105263157894, "grad_norm": 0.06995475688793039, "learning_rate": 7.206292855456638e-05, "loss": 0.002, "step": 4460 }, { "epoch": 2.9407894736842106, "grad_norm": 0.07124928971946126, "learning_rate": 7.191560862396505e-05, "loss": 0.0023, "step": 4470 }, { "epoch": 2.9473684210526314, "grad_norm": 0.07629357364809666, "learning_rate": 7.176805281689514e-05, "loss": 0.0022, "step": 4480 }, { "epoch": 2.9539473684210527, "grad_norm": 0.08193349418976627, "learning_rate": 7.162026272149152e-05, "loss": 0.0021, "step": 4490 }, { "epoch": 2.9605263157894735, "grad_norm": 0.07303326416003306, "learning_rate": 7.147223992841074e-05, "loss": 0.0022, "step": 4500 }, { "epoch": 2.9671052631578947, "grad_norm": 0.08529692109248832, "learning_rate": 7.132398603081382e-05, "loss": 0.0022, "step": 4510 }, { "epoch": 2.973684210526316, "grad_norm": 0.061074529913310756, "learning_rate": 7.117550262434917e-05, "loss": 0.0021, "step": 4520 }, { "epoch": 2.9802631578947367, "grad_norm": 0.0652049352287244, "learning_rate": 7.102679130713537e-05, "loss": 0.0021, "step": 4530 }, { "epoch": 2.986842105263158, "grad_norm": 0.05954432016331547, "learning_rate": 7.087785367974402e-05, "loss": 0.002, "step": 4540 }, { "epoch": 2.9934210526315788, "grad_norm": 0.061906863190638615, "learning_rate": 7.072869134518243e-05, "loss": 0.002, "step": 4550 }, { "epoch": 3.0, "grad_norm": 0.06269104180471789, "learning_rate": 7.057930590887648e-05, "loss": 0.0021, "step": 4560 }, { "epoch": 3.0065789473684212, "grad_norm": 0.044136760952164476, "learning_rate": 7.042969897865325e-05, "loss": 0.0013, "step": 4570 }, { "epoch": 3.013157894736842, "grad_norm": 0.04755011035898616, "learning_rate": 7.027987216472377e-05, "loss": 0.0014, "step": 4580 }, { "epoch": 3.0197368421052633, "grad_norm": 0.04504389965591228, "learning_rate": 7.012982707966561e-05, "loss": 0.0012, "step": 4590 }, { "epoch": 3.026315789473684, "grad_norm": 0.039326385477169795, "learning_rate": 6.997956533840565e-05, "loss": 0.0012, "step": 4600 }, { "epoch": 3.0328947368421053, "grad_norm": 0.050717328095234285, "learning_rate": 6.98290885582026e-05, "loss": 0.001, "step": 4610 }, { "epoch": 3.039473684210526, "grad_norm": 0.07042333565934958, "learning_rate": 6.967839835862962e-05, "loss": 0.0011, "step": 4620 }, { "epoch": 3.0460526315789473, "grad_norm": 0.041419088284560174, "learning_rate": 6.952749636155686e-05, "loss": 0.001, "step": 4630 }, { "epoch": 3.0526315789473686, "grad_norm": 0.047502535032076625, "learning_rate": 6.93763841911341e-05, "loss": 0.001, "step": 4640 }, { "epoch": 3.0592105263157894, "grad_norm": 0.04278077403078802, "learning_rate": 6.922506347377317e-05, "loss": 0.001, "step": 4650 }, { "epoch": 3.0657894736842106, "grad_norm": 0.038900292014083175, "learning_rate": 6.907353583813045e-05, "loss": 0.0009, "step": 4660 }, { "epoch": 3.0723684210526314, "grad_norm": 0.055076300918611376, "learning_rate": 6.892180291508944e-05, "loss": 0.001, "step": 4670 }, { "epoch": 3.0789473684210527, "grad_norm": 0.04627844007982353, "learning_rate": 6.876986633774304e-05, "loss": 0.001, "step": 4680 }, { "epoch": 3.085526315789474, "grad_norm": 0.04320535511746515, "learning_rate": 6.861772774137618e-05, "loss": 0.0011, "step": 4690 }, { "epoch": 3.0921052631578947, "grad_norm": 0.05504211999563014, "learning_rate": 6.846538876344802e-05, "loss": 0.001, "step": 4700 }, { "epoch": 3.098684210526316, "grad_norm": 0.05448192261747016, "learning_rate": 6.831285104357447e-05, "loss": 0.001, "step": 4710 }, { "epoch": 3.1052631578947367, "grad_norm": 0.04552769740470275, "learning_rate": 6.816011622351046e-05, "loss": 0.001, "step": 4720 }, { "epoch": 3.111842105263158, "grad_norm": 0.04380094534401855, "learning_rate": 6.80071859471323e-05, "loss": 0.0011, "step": 4730 }, { "epoch": 3.1184210526315788, "grad_norm": 0.05316132876867928, "learning_rate": 6.785406186041999e-05, "loss": 0.001, "step": 4740 }, { "epoch": 3.125, "grad_norm": 0.06748335057222496, "learning_rate": 6.770074561143953e-05, "loss": 0.001, "step": 4750 }, { "epoch": 3.1315789473684212, "grad_norm": 0.05077013593653331, "learning_rate": 6.754723885032509e-05, "loss": 0.001, "step": 4760 }, { "epoch": 3.138157894736842, "grad_norm": 0.04785887103202659, "learning_rate": 6.739354322926136e-05, "loss": 0.001, "step": 4770 }, { "epoch": 3.1447368421052633, "grad_norm": 0.04683825413816567, "learning_rate": 6.723966040246572e-05, "loss": 0.001, "step": 4780 }, { "epoch": 3.151315789473684, "grad_norm": 0.04117391629226033, "learning_rate": 6.708559202617038e-05, "loss": 0.001, "step": 4790 }, { "epoch": 3.1578947368421053, "grad_norm": 0.04553304662726201, "learning_rate": 6.693133975860469e-05, "loss": 0.0009, "step": 4800 }, { "epoch": 3.1644736842105265, "grad_norm": 0.049513375189675204, "learning_rate": 6.677690525997714e-05, "loss": 0.001, "step": 4810 }, { "epoch": 3.1710526315789473, "grad_norm": 0.04391216195471761, "learning_rate": 6.66222901924576e-05, "loss": 0.001, "step": 4820 }, { "epoch": 3.1776315789473686, "grad_norm": 0.044387416555585354, "learning_rate": 6.64674962201594e-05, "loss": 0.001, "step": 4830 }, { "epoch": 3.1842105263157894, "grad_norm": 0.04438285777547525, "learning_rate": 6.631252500912138e-05, "loss": 0.0011, "step": 4840 }, { "epoch": 3.1907894736842106, "grad_norm": 0.047101474036633194, "learning_rate": 6.615737822729e-05, "loss": 0.001, "step": 4850 }, { "epoch": 3.1973684210526314, "grad_norm": 0.040121280292295405, "learning_rate": 6.60020575445014e-05, "loss": 0.001, "step": 4860 }, { "epoch": 3.2039473684210527, "grad_norm": 0.044535989576363004, "learning_rate": 6.584656463246342e-05, "loss": 0.001, "step": 4870 }, { "epoch": 3.2105263157894735, "grad_norm": 0.07776632409312663, "learning_rate": 6.569090116473751e-05, "loss": 0.0011, "step": 4880 }, { "epoch": 3.2171052631578947, "grad_norm": 0.04682875202534155, "learning_rate": 6.553506881672088e-05, "loss": 0.0011, "step": 4890 }, { "epoch": 3.223684210526316, "grad_norm": 0.05497866325358715, "learning_rate": 6.537906926562837e-05, "loss": 0.001, "step": 4900 }, { "epoch": 3.2302631578947367, "grad_norm": 0.06474765645613281, "learning_rate": 6.522290419047444e-05, "loss": 0.001, "step": 4910 }, { "epoch": 3.236842105263158, "grad_norm": 0.04305292992711723, "learning_rate": 6.506657527205501e-05, "loss": 0.001, "step": 4920 }, { "epoch": 3.2434210526315788, "grad_norm": 0.045387566372484936, "learning_rate": 6.49100841929295e-05, "loss": 0.001, "step": 4930 }, { "epoch": 3.25, "grad_norm": 0.1120983923723266, "learning_rate": 6.475343263740261e-05, "loss": 0.0035, "step": 4940 }, { "epoch": 3.2565789473684212, "grad_norm": 0.07941930777156028, "learning_rate": 6.459662229150629e-05, "loss": 0.0024, "step": 4950 }, { "epoch": 3.263157894736842, "grad_norm": 0.07966562157041894, "learning_rate": 6.44396548429815e-05, "loss": 0.0016, "step": 4960 }, { "epoch": 3.2697368421052633, "grad_norm": 0.07346284814536075, "learning_rate": 6.428253198126009e-05, "loss": 0.0015, "step": 4970 }, { "epoch": 3.276315789473684, "grad_norm": 0.12406992455137089, "learning_rate": 6.412525539744664e-05, "loss": 0.0028, "step": 4980 }, { "epoch": 3.2828947368421053, "grad_norm": 0.12753701081458718, "learning_rate": 6.396782678430021e-05, "loss": 0.002, "step": 4990 }, { "epoch": 3.2894736842105265, "grad_norm": 0.06701592063617125, "learning_rate": 6.381024783621614e-05, "loss": 0.0016, "step": 5000 }, { "epoch": 3.2960526315789473, "grad_norm": 0.05171422173018302, "learning_rate": 6.365252024920784e-05, "loss": 0.0013, "step": 5010 }, { "epoch": 3.3026315789473686, "grad_norm": 0.05818564557929872, "learning_rate": 6.349464572088849e-05, "loss": 0.0013, "step": 5020 }, { "epoch": 3.3092105263157894, "grad_norm": 0.073006934280184, "learning_rate": 6.333662595045281e-05, "loss": 0.0014, "step": 5030 }, { "epoch": 3.3157894736842106, "grad_norm": 0.054778073601371255, "learning_rate": 6.317846263865872e-05, "loss": 0.0014, "step": 5040 }, { "epoch": 3.3223684210526314, "grad_norm": 0.05659243950533705, "learning_rate": 6.302015748780909e-05, "loss": 0.0012, "step": 5050 }, { "epoch": 3.3289473684210527, "grad_norm": 0.04770376014919815, "learning_rate": 6.286171220173343e-05, "loss": 0.0012, "step": 5060 }, { "epoch": 3.3355263157894735, "grad_norm": 0.06283432984369176, "learning_rate": 6.270312848576944e-05, "loss": 0.0013, "step": 5070 }, { "epoch": 3.3421052631578947, "grad_norm": 0.0570672191700207, "learning_rate": 6.25444080467448e-05, "loss": 0.0012, "step": 5080 }, { "epoch": 3.348684210526316, "grad_norm": 0.05506455230381448, "learning_rate": 6.238555259295872e-05, "loss": 0.0012, "step": 5090 }, { "epoch": 3.3552631578947367, "grad_norm": 0.04071882369132935, "learning_rate": 6.222656383416352e-05, "loss": 0.0011, "step": 5100 }, { "epoch": 3.361842105263158, "grad_norm": 0.04561858668173625, "learning_rate": 6.206744348154635e-05, "loss": 0.0012, "step": 5110 }, { "epoch": 3.3684210526315788, "grad_norm": 0.04919438581324567, "learning_rate": 6.190819324771062e-05, "loss": 0.0011, "step": 5120 }, { "epoch": 3.375, "grad_norm": 0.05418076160498796, "learning_rate": 6.174881484665768e-05, "loss": 0.0011, "step": 5130 }, { "epoch": 3.3815789473684212, "grad_norm": 0.056960371113187074, "learning_rate": 6.158930999376838e-05, "loss": 0.0011, "step": 5140 }, { "epoch": 3.388157894736842, "grad_norm": 0.04255944372616425, "learning_rate": 6.142968040578449e-05, "loss": 0.0011, "step": 5150 }, { "epoch": 3.3947368421052633, "grad_norm": 0.048340947040949475, "learning_rate": 6.126992780079031e-05, "loss": 0.0011, "step": 5160 }, { "epoch": 3.401315789473684, "grad_norm": 0.0442107482386399, "learning_rate": 6.111005389819422e-05, "loss": 0.0011, "step": 5170 }, { "epoch": 3.4078947368421053, "grad_norm": 0.04136846778037803, "learning_rate": 6.0950060418710065e-05, "loss": 0.0011, "step": 5180 }, { "epoch": 3.4144736842105265, "grad_norm": 0.04323795038841515, "learning_rate": 6.078994908433872e-05, "loss": 0.0011, "step": 5190 }, { "epoch": 3.4210526315789473, "grad_norm": 0.05416639442819582, "learning_rate": 6.062972161834948e-05, "loss": 0.001, "step": 5200 }, { "epoch": 3.4276315789473686, "grad_norm": 0.04010090748408715, "learning_rate": 6.0469379745261624e-05, "loss": 0.0011, "step": 5210 }, { "epoch": 3.4342105263157894, "grad_norm": 0.05141200227401958, "learning_rate": 6.0308925190825725e-05, "loss": 0.0011, "step": 5220 }, { "epoch": 3.4407894736842106, "grad_norm": 0.05960335396630123, "learning_rate": 6.014835968200521e-05, "loss": 0.0011, "step": 5230 }, { "epoch": 3.4473684210526314, "grad_norm": 0.03996319019239445, "learning_rate": 5.9987684946957625e-05, "loss": 0.0009, "step": 5240 }, { "epoch": 3.4539473684210527, "grad_norm": 0.03754917546922171, "learning_rate": 5.9826902715016154e-05, "loss": 0.001, "step": 5250 }, { "epoch": 3.4605263157894735, "grad_norm": 0.044709261031248435, "learning_rate": 5.966601471667096e-05, "loss": 0.001, "step": 5260 }, { "epoch": 3.4671052631578947, "grad_norm": 0.05394706576681355, "learning_rate": 5.950502268355057e-05, "loss": 0.001, "step": 5270 }, { "epoch": 3.473684210526316, "grad_norm": 0.04640630644633933, "learning_rate": 5.934392834840321e-05, "loss": 0.001, "step": 5280 }, { "epoch": 3.4802631578947367, "grad_norm": 0.03996275338024238, "learning_rate": 5.91827334450782e-05, "loss": 0.001, "step": 5290 }, { "epoch": 3.486842105263158, "grad_norm": 0.04513935016051976, "learning_rate": 5.902143970850725e-05, "loss": 0.0009, "step": 5300 }, { "epoch": 3.4934210526315788, "grad_norm": 0.04727412105314611, "learning_rate": 5.8860048874685836e-05, "loss": 0.001, "step": 5310 }, { "epoch": 3.5, "grad_norm": 0.041740001551287126, "learning_rate": 5.8698562680654436e-05, "loss": 0.0009, "step": 5320 }, { "epoch": 3.5065789473684212, "grad_norm": 0.04711270749810497, "learning_rate": 5.8536982864479925e-05, "loss": 0.001, "step": 5330 }, { "epoch": 3.513157894736842, "grad_norm": 0.04576375416018754, "learning_rate": 5.837531116523682e-05, "loss": 0.0009, "step": 5340 }, { "epoch": 3.5197368421052633, "grad_norm": 0.038452015974273716, "learning_rate": 5.821354932298858e-05, "loss": 0.0009, "step": 5350 }, { "epoch": 3.526315789473684, "grad_norm": 0.03906108461777927, "learning_rate": 5.805169907876884e-05, "loss": 0.0009, "step": 5360 }, { "epoch": 3.5328947368421053, "grad_norm": 0.05168966022643398, "learning_rate": 5.788976217456274e-05, "loss": 0.001, "step": 5370 }, { "epoch": 3.5394736842105265, "grad_norm": 0.0445000606377978, "learning_rate": 5.772774035328809e-05, "loss": 0.0009, "step": 5380 }, { "epoch": 3.5460526315789473, "grad_norm": 0.03328912347538213, "learning_rate": 5.756563535877668e-05, "loss": 0.001, "step": 5390 }, { "epoch": 3.5526315789473686, "grad_norm": 0.044808425570984904, "learning_rate": 5.74034489357555e-05, "loss": 0.001, "step": 5400 } ], "logging_steps": 10, "max_steps": 10640, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 1800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 430016523927552.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }