{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.25, "eval_steps": 500, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "grad_norm": 1.5213489532470703, "learning_rate": 9e-07, "loss": 1.1459, "step": 10 }, { "grad_norm": 0.7880924344062805, "learning_rate": 1.9e-06, "loss": 1.1201, "step": 20 }, { "grad_norm": 0.8483393788337708, "learning_rate": 2.9e-06, "loss": 1.1381, "step": 30 }, { "grad_norm": 0.8726585507392883, "learning_rate": 3.9e-06, "loss": 1.0945, "step": 40 }, { "grad_norm": 0.7667792439460754, "learning_rate": 4.9000000000000005e-06, "loss": 1.1, "step": 50 }, { "grad_norm": 0.691442608833313, "learning_rate": 5.9e-06, "loss": 1.0843, "step": 60 }, { "grad_norm": 0.8902367353439331, "learning_rate": 6.900000000000001e-06, "loss": 1.0682, "step": 70 }, { "grad_norm": 0.5816682577133179, "learning_rate": 7.9e-06, "loss": 1.0896, "step": 80 }, { "grad_norm": 0.4389974772930145, "learning_rate": 8.9e-06, "loss": 1.0764, "step": 90 }, { "grad_norm": 0.6934444308280945, "learning_rate": 9.900000000000002e-06, "loss": 1.0513, "step": 100 }, { "grad_norm": 0.844937801361084, "learning_rate": 1.09e-05, "loss": 1.0595, "step": 110 }, { "grad_norm": 0.6664673089981079, "learning_rate": 1.19e-05, "loss": 1.0522, "step": 120 }, { "grad_norm": 0.7008771300315857, "learning_rate": 1.29e-05, "loss": 1.0809, "step": 130 }, { "grad_norm": 1.0379997491836548, "learning_rate": 1.3900000000000002e-05, "loss": 1.0278, "step": 140 }, { "grad_norm": 1.0058794021606445, "learning_rate": 1.49e-05, "loss": 1.0705, "step": 150 }, { "grad_norm": 1.245025634765625, "learning_rate": 1.59e-05, "loss": 1.082, "step": 160 }, { "grad_norm": 1.8022712469100952, "learning_rate": 1.69e-05, "loss": 1.0148, "step": 170 }, { "grad_norm": 3.2677149772644043, "learning_rate": 1.79e-05, "loss": 0.9426, "step": 180 }, { "grad_norm": 2.9350149631500244, "learning_rate": 1.8900000000000002e-05, "loss": 0.818, "step": 190 }, { "grad_norm": 4.3919172286987305, "learning_rate": 1.9900000000000003e-05, "loss": 0.7303, "step": 200 }, { "grad_norm": 3.412487268447876, "learning_rate": 2.09e-05, "loss": 0.5792, "step": 210 }, { "grad_norm": 3.6358072757720947, "learning_rate": 2.19e-05, "loss": 0.5074, "step": 220 }, { "grad_norm": 4.186373233795166, "learning_rate": 2.29e-05, "loss": 0.4103, "step": 230 }, { "grad_norm": 2.730592727661133, "learning_rate": 2.39e-05, "loss": 0.363, "step": 240 }, { "grad_norm": 2.7083208560943604, "learning_rate": 2.4900000000000002e-05, "loss": 0.2558, "step": 250 }, { "grad_norm": 3.008880376815796, "learning_rate": 2.5900000000000003e-05, "loss": 0.2241, "step": 260 }, { "grad_norm": 3.8729772567749023, "learning_rate": 2.6900000000000003e-05, "loss": 0.2268, "step": 270 }, { "grad_norm": 3.59509539604187, "learning_rate": 2.7900000000000004e-05, "loss": 0.2062, "step": 280 }, { "grad_norm": 3.5228497982025146, "learning_rate": 2.8899999999999998e-05, "loss": 0.218, "step": 290 }, { "grad_norm": 2.418987989425659, "learning_rate": 2.9900000000000002e-05, "loss": 0.2252, "step": 300 }, { "grad_norm": 2.568413496017456, "learning_rate": 3.09e-05, "loss": 0.2207, "step": 310 }, { "grad_norm": 1.346835732460022, "learning_rate": 3.19e-05, "loss": 0.1508, "step": 320 }, { "grad_norm": 3.3324496746063232, "learning_rate": 3.29e-05, "loss": 0.1955, "step": 330 }, { "grad_norm": 2.5590157508850098, "learning_rate": 3.3900000000000004e-05, "loss": 0.1797, "step": 340 }, { "grad_norm": 2.2951533794403076, "learning_rate": 3.49e-05, "loss": 0.1648, "step": 350 }, { "grad_norm": 1.9694273471832275, "learning_rate": 3.59e-05, "loss": 0.1551, "step": 360 }, { "grad_norm": 2.5252740383148193, "learning_rate": 3.69e-05, "loss": 0.1887, "step": 370 }, { "grad_norm": 2.0709311962127686, "learning_rate": 3.79e-05, "loss": 0.1808, "step": 380 }, { "grad_norm": 1.9920077323913574, "learning_rate": 3.8900000000000004e-05, "loss": 0.1931, "step": 390 }, { "grad_norm": 3.5981061458587646, "learning_rate": 3.99e-05, "loss": 0.1814, "step": 400 }, { "grad_norm": 1.6646324396133423, "learning_rate": 4.09e-05, "loss": 0.1729, "step": 410 }, { "grad_norm": 1.7769408226013184, "learning_rate": 4.19e-05, "loss": 0.1506, "step": 420 }, { "grad_norm": 1.3985650539398193, "learning_rate": 4.29e-05, "loss": 0.1729, "step": 430 }, { "grad_norm": 1.3861799240112305, "learning_rate": 4.39e-05, "loss": 0.1642, "step": 440 }, { "grad_norm": 1.3587490320205688, "learning_rate": 4.49e-05, "loss": 0.1422, "step": 450 }, { "grad_norm": 1.8183093070983887, "learning_rate": 4.5900000000000004e-05, "loss": 0.1542, "step": 460 }, { "grad_norm": 2.0516979694366455, "learning_rate": 4.69e-05, "loss": 0.1449, "step": 470 }, { "grad_norm": 1.7738460302352905, "learning_rate": 4.79e-05, "loss": 0.165, "step": 480 }, { "grad_norm": 1.4665640592575073, "learning_rate": 4.89e-05, "loss": 0.1576, "step": 490 }, { "grad_norm": 1.6009067296981812, "learning_rate": 4.99e-05, "loss": 0.1433, "step": 500 }, { "grad_norm": 1.5568578243255615, "learning_rate": 5.0900000000000004e-05, "loss": 0.1599, "step": 510 }, { "grad_norm": 1.6298129558563232, "learning_rate": 5.19e-05, "loss": 0.1761, "step": 520 }, { "grad_norm": 2.0153603553771973, "learning_rate": 5.2900000000000005e-05, "loss": 0.1619, "step": 530 }, { "grad_norm": 1.2626113891601562, "learning_rate": 5.390000000000001e-05, "loss": 0.1208, "step": 540 }, { "grad_norm": 1.262470006942749, "learning_rate": 5.4900000000000006e-05, "loss": 0.1716, "step": 550 }, { "grad_norm": 1.6254278421401978, "learning_rate": 5.590000000000001e-05, "loss": 0.1674, "step": 560 }, { "grad_norm": 1.2208607196807861, "learning_rate": 5.69e-05, "loss": 0.142, "step": 570 }, { "grad_norm": 1.2460236549377441, "learning_rate": 5.79e-05, "loss": 0.1279, "step": 580 }, { "grad_norm": 1.5343554019927979, "learning_rate": 5.89e-05, "loss": 0.1435, "step": 590 }, { "grad_norm": 0.8064042329788208, "learning_rate": 5.99e-05, "loss": 0.1488, "step": 600 }, { "grad_norm": 1.3626583814620972, "learning_rate": 6.09e-05, "loss": 0.1233, "step": 610 }, { "grad_norm": 1.5085315704345703, "learning_rate": 6.19e-05, "loss": 0.116, "step": 620 }, { "grad_norm": 1.538020372390747, "learning_rate": 6.29e-05, "loss": 0.1429, "step": 630 }, { "grad_norm": 1.0814495086669922, "learning_rate": 6.390000000000001e-05, "loss": 0.1375, "step": 640 }, { "grad_norm": 1.3111987113952637, "learning_rate": 6.49e-05, "loss": 0.1232, "step": 650 }, { "grad_norm": 1.068990707397461, "learning_rate": 6.59e-05, "loss": 0.14, "step": 660 }, { "grad_norm": 1.0841020345687866, "learning_rate": 6.690000000000001e-05, "loss": 0.112, "step": 670 }, { "grad_norm": 1.0056569576263428, "learning_rate": 6.790000000000001e-05, "loss": 0.134, "step": 680 }, { "grad_norm": 0.8805966973304749, "learning_rate": 6.89e-05, "loss": 0.1172, "step": 690 }, { "grad_norm": 1.1099011898040771, "learning_rate": 6.99e-05, "loss": 0.1284, "step": 700 }, { "grad_norm": 1.4355127811431885, "learning_rate": 7.09e-05, "loss": 0.1274, "step": 710 }, { "grad_norm": 1.0597474575042725, "learning_rate": 7.19e-05, "loss": 0.1301, "step": 720 }, { "grad_norm": 1.148871898651123, "learning_rate": 7.29e-05, "loss": 0.1312, "step": 730 }, { "grad_norm": 0.6751792430877686, "learning_rate": 7.390000000000001e-05, "loss": 0.1087, "step": 740 }, { "grad_norm": 1.030468463897705, "learning_rate": 7.49e-05, "loss": 0.1187, "step": 750 }, { "grad_norm": 0.7389861941337585, "learning_rate": 7.59e-05, "loss": 0.111, "step": 760 }, { "grad_norm": 1.027443528175354, "learning_rate": 7.69e-05, "loss": 0.1261, "step": 770 }, { "grad_norm": 1.2138018608093262, "learning_rate": 7.790000000000001e-05, "loss": 0.1536, "step": 780 }, { "grad_norm": 1.1600711345672607, "learning_rate": 7.890000000000001e-05, "loss": 0.1175, "step": 790 }, { "grad_norm": 0.986129879951477, "learning_rate": 7.99e-05, "loss": 0.1151, "step": 800 }, { "grad_norm": 1.1461236476898193, "learning_rate": 8.090000000000001e-05, "loss": 0.1184, "step": 810 }, { "grad_norm": 1.070863127708435, "learning_rate": 8.19e-05, "loss": 0.1295, "step": 820 }, { "grad_norm": 1.0324434041976929, "learning_rate": 8.29e-05, "loss": 0.1407, "step": 830 }, { "grad_norm": 0.5455268025398254, "learning_rate": 8.39e-05, "loss": 0.1217, "step": 840 }, { "grad_norm": 1.2856420278549194, "learning_rate": 8.49e-05, "loss": 0.1381, "step": 850 }, { "grad_norm": 0.6798171997070312, "learning_rate": 8.59e-05, "loss": 0.1094, "step": 860 }, { "grad_norm": 1.1037408113479614, "learning_rate": 8.69e-05, "loss": 0.1417, "step": 870 }, { "grad_norm": 1.1323193311691284, "learning_rate": 8.790000000000001e-05, "loss": 0.1239, "step": 880 }, { "grad_norm": 0.9463742971420288, "learning_rate": 8.89e-05, "loss": 0.1212, "step": 890 }, { "grad_norm": 1.0618247985839844, "learning_rate": 8.99e-05, "loss": 0.1288, "step": 900 }, { "grad_norm": 0.9557912349700928, "learning_rate": 9.090000000000001e-05, "loss": 0.1241, "step": 910 }, { "grad_norm": 0.9128029942512512, "learning_rate": 9.190000000000001e-05, "loss": 0.1078, "step": 920 }, { "grad_norm": 0.6887853145599365, "learning_rate": 9.290000000000001e-05, "loss": 0.1159, "step": 930 }, { "grad_norm": 0.9718108773231506, "learning_rate": 9.39e-05, "loss": 0.1216, "step": 940 }, { "grad_norm": 0.6114986538887024, "learning_rate": 9.49e-05, "loss": 0.1042, "step": 950 }, { "grad_norm": 0.8769384622573853, "learning_rate": 9.59e-05, "loss": 0.1189, "step": 960 }, { "grad_norm": 1.0832934379577637, "learning_rate": 9.69e-05, "loss": 0.1394, "step": 970 }, { "grad_norm": 0.6401132941246033, "learning_rate": 9.790000000000001e-05, "loss": 0.0969, "step": 980 }, { "grad_norm": 0.8633731007575989, "learning_rate": 9.89e-05, "loss": 0.1039, "step": 990 }, { "grad_norm": 0.9721170663833618, "learning_rate": 9.99e-05, "loss": 0.1029, "step": 1000 }, { "grad_norm": 0.7459349632263184, "learning_rate": 9.999994463727085e-05, "loss": 0.1008, "step": 1010 }, { "grad_norm": 0.7490088939666748, "learning_rate": 9.999975326009292e-05, "loss": 0.1187, "step": 1020 }, { "grad_norm": 0.8068322539329529, "learning_rate": 9.999942518549879e-05, "loss": 0.0971, "step": 1030 }, { "grad_norm": 0.9983232021331787, "learning_rate": 9.999896041438544e-05, "loss": 0.1065, "step": 1040 }, { "grad_norm": 0.8005691766738892, "learning_rate": 9.999835894802353e-05, "loss": 0.1278, "step": 1050 }, { "grad_norm": 0.9839821457862854, "learning_rate": 9.999762078805743e-05, "loss": 0.1226, "step": 1060 }, { "grad_norm": 0.8889091610908508, "learning_rate": 9.999674593650526e-05, "loss": 0.1277, "step": 1070 }, { "grad_norm": 0.8241409659385681, "learning_rate": 9.99957343957588e-05, "loss": 0.1399, "step": 1080 }, { "grad_norm": 0.7831732034683228, "learning_rate": 9.99945861685836e-05, "loss": 0.1167, "step": 1090 }, { "grad_norm": 0.6063086986541748, "learning_rate": 9.999330125811884e-05, "loss": 0.0849, "step": 1100 }, { "grad_norm": 0.7521977424621582, "learning_rate": 9.999187966787744e-05, "loss": 0.1203, "step": 1110 }, { "grad_norm": 0.6242801547050476, "learning_rate": 9.999032140174595e-05, "loss": 0.0836, "step": 1120 }, { "grad_norm": 0.9872605204582214, "learning_rate": 9.998862646398464e-05, "loss": 0.1022, "step": 1130 }, { "grad_norm": 1.1914061307907104, "learning_rate": 9.998679485922739e-05, "loss": 0.1431, "step": 1140 }, { "grad_norm": 0.8260459303855896, "learning_rate": 9.998482659248174e-05, "loss": 0.1207, "step": 1150 }, { "grad_norm": 0.5030370354652405, "learning_rate": 9.998272166912883e-05, "loss": 0.1001, "step": 1160 }, { "grad_norm": 0.7728376984596252, "learning_rate": 9.998048009492347e-05, "loss": 0.1029, "step": 1170 }, { "grad_norm": 0.5780965089797974, "learning_rate": 9.997810187599403e-05, "loss": 0.0945, "step": 1180 }, { "grad_norm": 0.7676225304603577, "learning_rate": 9.997558701884249e-05, "loss": 0.0998, "step": 1190 }, { "grad_norm": 0.8692914247512817, "learning_rate": 9.997293553034433e-05, "loss": 0.1052, "step": 1200 }, { "grad_norm": 1.1212290525436401, "learning_rate": 9.997014741774866e-05, "loss": 0.1287, "step": 1210 }, { "grad_norm": 0.8846785426139832, "learning_rate": 9.996722268867803e-05, "loss": 0.1089, "step": 1220 }, { "grad_norm": 0.4960787296295166, "learning_rate": 9.996416135112858e-05, "loss": 0.0943, "step": 1230 }, { "grad_norm": 0.7296782732009888, "learning_rate": 9.996096341346988e-05, "loss": 0.1037, "step": 1240 }, { "grad_norm": 0.7197479009628296, "learning_rate": 9.995762888444495e-05, "loss": 0.0973, "step": 1250 }, { "grad_norm": 0.6831506490707397, "learning_rate": 9.995415777317027e-05, "loss": 0.0958, "step": 1260 }, { "grad_norm": 0.829959511756897, "learning_rate": 9.995055008913574e-05, "loss": 0.0794, "step": 1270 }, { "grad_norm": 0.7984001040458679, "learning_rate": 9.994680584220463e-05, "loss": 0.0919, "step": 1280 }, { "grad_norm": 0.6205410957336426, "learning_rate": 9.994292504261355e-05, "loss": 0.0891, "step": 1290 }, { "grad_norm": 0.6056678891181946, "learning_rate": 9.993890770097247e-05, "loss": 0.1016, "step": 1300 }, { "grad_norm": 0.5512028932571411, "learning_rate": 9.993475382826467e-05, "loss": 0.0998, "step": 1310 }, { "grad_norm": 0.596242368221283, "learning_rate": 9.993046343584664e-05, "loss": 0.101, "step": 1320 }, { "grad_norm": 0.6782081127166748, "learning_rate": 9.992603653544816e-05, "loss": 0.0767, "step": 1330 }, { "grad_norm": 0.607600748538971, "learning_rate": 9.992147313917222e-05, "loss": 0.0787, "step": 1340 }, { "grad_norm": 0.8410352468490601, "learning_rate": 9.991677325949497e-05, "loss": 0.1085, "step": 1350 }, { "grad_norm": 0.84430330991745, "learning_rate": 9.991193690926568e-05, "loss": 0.0995, "step": 1360 }, { "grad_norm": 0.8323556780815125, "learning_rate": 9.990696410170678e-05, "loss": 0.0825, "step": 1370 }, { "grad_norm": 0.46820303797721863, "learning_rate": 9.990185485041371e-05, "loss": 0.0706, "step": 1380 }, { "grad_norm": 0.4801246225833893, "learning_rate": 9.989660916935498e-05, "loss": 0.0896, "step": 1390 }, { "grad_norm": 0.6230830550193787, "learning_rate": 9.989122707287208e-05, "loss": 0.0786, "step": 1400 }, { "grad_norm": 0.7002012133598328, "learning_rate": 9.988570857567945e-05, "loss": 0.0807, "step": 1410 }, { "grad_norm": 0.7535853385925293, "learning_rate": 9.988005369286446e-05, "loss": 0.0919, "step": 1420 }, { "grad_norm": 0.5004695057868958, "learning_rate": 9.987426243988734e-05, "loss": 0.0714, "step": 1430 }, { "grad_norm": 0.49135348200798035, "learning_rate": 9.986833483258114e-05, "loss": 0.0953, "step": 1440 }, { "grad_norm": 0.8958180546760559, "learning_rate": 9.986227088715173e-05, "loss": 0.1157, "step": 1450 }, { "grad_norm": 0.5880500078201294, "learning_rate": 9.98560706201777e-05, "loss": 0.0977, "step": 1460 }, { "grad_norm": 0.5234725475311279, "learning_rate": 9.984973404861036e-05, "loss": 0.0997, "step": 1470 }, { "grad_norm": 0.5263286232948303, "learning_rate": 9.984326118977361e-05, "loss": 0.085, "step": 1480 }, { "grad_norm": 0.7574364542961121, "learning_rate": 9.983665206136406e-05, "loss": 0.0825, "step": 1490 }, { "grad_norm": 0.6920371055603027, "learning_rate": 9.982990668145075e-05, "loss": 0.0884, "step": 1500 }, { "grad_norm": 0.49095913767814636, "learning_rate": 9.982302506847534e-05, "loss": 0.0766, "step": 1510 }, { "grad_norm": 0.7113752365112305, "learning_rate": 9.981600724125189e-05, "loss": 0.082, "step": 1520 }, { "grad_norm": 0.47767770290374756, "learning_rate": 9.980885321896685e-05, "loss": 0.0964, "step": 1530 }, { "grad_norm": 0.5407960414886475, "learning_rate": 9.980156302117905e-05, "loss": 0.0871, "step": 1540 }, { "grad_norm": 0.6543983817100525, "learning_rate": 9.979413666781963e-05, "loss": 0.0778, "step": 1550 }, { "grad_norm": 0.4955432116985321, "learning_rate": 9.978657417919193e-05, "loss": 0.1037, "step": 1560 }, { "grad_norm": 0.7188798189163208, "learning_rate": 9.977887557597153e-05, "loss": 0.0733, "step": 1570 }, { "grad_norm": 0.6545672416687012, "learning_rate": 9.97710408792061e-05, "loss": 0.079, "step": 1580 }, { "grad_norm": 0.517619788646698, "learning_rate": 9.976307011031542e-05, "loss": 0.0916, "step": 1590 }, { "grad_norm": 0.8744682669639587, "learning_rate": 9.975496329109126e-05, "loss": 0.0873, "step": 1600 }, { "grad_norm": 0.4774981141090393, "learning_rate": 9.974672044369732e-05, "loss": 0.0711, "step": 1610 }, { "grad_norm": 0.6011234521865845, "learning_rate": 9.97383415906693e-05, "loss": 0.0785, "step": 1620 }, { "grad_norm": 0.7292971014976501, "learning_rate": 9.97298267549146e-05, "loss": 0.1196, "step": 1630 }, { "grad_norm": 0.7374907732009888, "learning_rate": 9.972117595971249e-05, "loss": 0.0872, "step": 1640 }, { "grad_norm": 0.6834810376167297, "learning_rate": 9.971238922871391e-05, "loss": 0.088, "step": 1650 }, { "grad_norm": 0.37965625524520874, "learning_rate": 9.970346658594142e-05, "loss": 0.0985, "step": 1660 }, { "grad_norm": 0.5898900628089905, "learning_rate": 9.969440805578923e-05, "loss": 0.087, "step": 1670 }, { "grad_norm": 0.5589766502380371, "learning_rate": 9.968521366302298e-05, "loss": 0.0922, "step": 1680 }, { "grad_norm": 0.6373990178108215, "learning_rate": 9.967588343277981e-05, "loss": 0.0853, "step": 1690 }, { "grad_norm": 0.5831761360168457, "learning_rate": 9.966641739056818e-05, "loss": 0.0857, "step": 1700 }, { "grad_norm": 0.7833588123321533, "learning_rate": 9.965681556226793e-05, "loss": 0.1012, "step": 1710 }, { "grad_norm": 0.5402719378471375, "learning_rate": 9.964707797413006e-05, "loss": 0.0845, "step": 1720 }, { "grad_norm": 0.4201139807701111, "learning_rate": 9.963720465277679e-05, "loss": 0.0814, "step": 1730 }, { "grad_norm": 0.4511631727218628, "learning_rate": 9.96271956252014e-05, "loss": 0.0769, "step": 1740 }, { "grad_norm": 0.4034776985645294, "learning_rate": 9.961705091876816e-05, "loss": 0.0831, "step": 1750 }, { "grad_norm": 0.6233536005020142, "learning_rate": 9.960677056121235e-05, "loss": 0.0798, "step": 1760 }, { "grad_norm": 0.4914403259754181, "learning_rate": 9.959635458064005e-05, "loss": 0.0766, "step": 1770 }, { "grad_norm": 0.685519278049469, "learning_rate": 9.958580300552815e-05, "loss": 0.0973, "step": 1780 }, { "grad_norm": 0.8895546793937683, "learning_rate": 9.957511586472426e-05, "loss": 0.0864, "step": 1790 }, { "grad_norm": 0.6138387322425842, "learning_rate": 9.956429318744662e-05, "loss": 0.0864, "step": 1800 }, { "grad_norm": 0.4782199263572693, "learning_rate": 9.955333500328404e-05, "loss": 0.0801, "step": 1810 }, { "grad_norm": 0.6924141049385071, "learning_rate": 9.95422413421957e-05, "loss": 0.0938, "step": 1820 }, { "grad_norm": 0.8799044489860535, "learning_rate": 9.953101223451133e-05, "loss": 0.09, "step": 1830 }, { "grad_norm": 0.46470800042152405, "learning_rate": 9.951964771093085e-05, "loss": 0.0951, "step": 1840 }, { "grad_norm": 0.6810444593429565, "learning_rate": 9.950814780252442e-05, "loss": 0.1077, "step": 1850 }, { "grad_norm": 0.6262006163597107, "learning_rate": 9.949651254073236e-05, "loss": 0.1062, "step": 1860 }, { "grad_norm": 0.37647661566734314, "learning_rate": 9.948474195736504e-05, "loss": 0.0742, "step": 1870 }, { "grad_norm": 0.5315661430358887, "learning_rate": 9.947283608460277e-05, "loss": 0.0675, "step": 1880 }, { "grad_norm": 0.4759484827518463, "learning_rate": 9.946079495499577e-05, "loss": 0.0788, "step": 1890 }, { "grad_norm": 0.5022087693214417, "learning_rate": 9.944861860146401e-05, "loss": 0.0768, "step": 1900 }, { "grad_norm": 0.7018097043037415, "learning_rate": 9.943630705729719e-05, "loss": 0.1027, "step": 1910 }, { "grad_norm": 0.7303236722946167, "learning_rate": 9.942386035615459e-05, "loss": 0.0864, "step": 1920 }, { "grad_norm": 0.6607370972633362, "learning_rate": 9.941127853206503e-05, "loss": 0.0732, "step": 1930 }, { "grad_norm": 0.7114208340644836, "learning_rate": 9.939856161942673e-05, "loss": 0.0804, "step": 1940 }, { "grad_norm": 0.5491101741790771, "learning_rate": 9.938570965300724e-05, "loss": 0.0747, "step": 1950 }, { "grad_norm": 0.6218782663345337, "learning_rate": 9.937272266794335e-05, "loss": 0.0843, "step": 1960 }, { "grad_norm": 0.7050214409828186, "learning_rate": 9.935960069974096e-05, "loss": 0.0598, "step": 1970 }, { "grad_norm": 0.731332540512085, "learning_rate": 9.934634378427506e-05, "loss": 0.0775, "step": 1980 }, { "grad_norm": 0.5450892448425293, "learning_rate": 9.933295195778954e-05, "loss": 0.0719, "step": 1990 }, { "grad_norm": 0.4165823459625244, "learning_rate": 9.931942525689715e-05, "loss": 0.0841, "step": 2000 }, { "grad_norm": 0.8278062343597412, "learning_rate": 9.930576371857936e-05, "loss": 0.1109, "step": 2010 }, { "grad_norm": 0.5803648233413696, "learning_rate": 9.929196738018629e-05, "loss": 0.0809, "step": 2020 }, { "grad_norm": 0.42353275418281555, "learning_rate": 9.927803627943662e-05, "loss": 0.0645, "step": 2030 }, { "grad_norm": 0.4303644299507141, "learning_rate": 9.926397045441744e-05, "loss": 0.0818, "step": 2040 }, { "grad_norm": 0.5936858057975769, "learning_rate": 9.924976994358417e-05, "loss": 0.0762, "step": 2050 }, { "grad_norm": 0.70964115858078, "learning_rate": 9.923543478576048e-05, "loss": 0.0751, "step": 2060 }, { "grad_norm": 0.6013302803039551, "learning_rate": 9.922096502013813e-05, "loss": 0.0659, "step": 2070 }, { "grad_norm": 0.4162874221801758, "learning_rate": 9.92063606862769e-05, "loss": 0.0758, "step": 2080 }, { "grad_norm": 0.36834216117858887, "learning_rate": 9.919162182410453e-05, "loss": 0.0693, "step": 2090 }, { "grad_norm": 0.5240453481674194, "learning_rate": 9.917674847391645e-05, "loss": 0.0746, "step": 2100 }, { "grad_norm": 0.5158270597457886, "learning_rate": 9.916174067637584e-05, "loss": 0.0898, "step": 2110 }, { "grad_norm": 0.4343959093093872, "learning_rate": 9.914659847251348e-05, "loss": 0.0771, "step": 2120 }, { "grad_norm": 0.5657391548156738, "learning_rate": 9.913132190372753e-05, "loss": 0.0792, "step": 2130 }, { "grad_norm": 0.32675492763519287, "learning_rate": 9.911591101178359e-05, "loss": 0.06, "step": 2140 }, { "grad_norm": 0.3764674961566925, "learning_rate": 9.910036583881443e-05, "loss": 0.079, "step": 2150 }, { "grad_norm": 0.41884034872055054, "learning_rate": 9.908468642731995e-05, "loss": 0.0736, "step": 2160 }, { "grad_norm": 0.41224420070648193, "learning_rate": 9.906887282016707e-05, "loss": 0.0739, "step": 2170 }, { "grad_norm": 0.5577347874641418, "learning_rate": 9.90529250605896e-05, "loss": 0.0867, "step": 2180 }, { "grad_norm": 0.4412975609302521, "learning_rate": 9.903684319218809e-05, "loss": 0.0754, "step": 2190 }, { "grad_norm": 0.47419559955596924, "learning_rate": 9.902062725892976e-05, "loss": 0.079, "step": 2200 }, { "grad_norm": 0.47286808490753174, "learning_rate": 9.900427730514834e-05, "loss": 0.0698, "step": 2210 }, { "grad_norm": 0.9424721598625183, "learning_rate": 9.8987793375544e-05, "loss": 0.0784, "step": 2220 }, { "grad_norm": 0.6497565507888794, "learning_rate": 9.897117551518318e-05, "loss": 0.0673, "step": 2230 }, { "grad_norm": 0.5508472919464111, "learning_rate": 9.895442376949844e-05, "loss": 0.0682, "step": 2240 }, { "grad_norm": 0.5709905624389648, "learning_rate": 9.893753818428845e-05, "loss": 0.0768, "step": 2250 }, { "grad_norm": 0.41989320516586304, "learning_rate": 9.892051880571773e-05, "loss": 0.0608, "step": 2260 }, { "grad_norm": 0.4534190595149994, "learning_rate": 9.890336568031663e-05, "loss": 0.0697, "step": 2270 }, { "grad_norm": 0.4371137320995331, "learning_rate": 9.888607885498113e-05, "loss": 0.0684, "step": 2280 }, { "grad_norm": 0.461468905210495, "learning_rate": 9.886865837697275e-05, "loss": 0.0888, "step": 2290 }, { "grad_norm": 0.5334675908088684, "learning_rate": 9.88511042939184e-05, "loss": 0.0681, "step": 2300 }, { "grad_norm": 0.49628573656082153, "learning_rate": 9.883341665381028e-05, "loss": 0.0775, "step": 2310 }, { "grad_norm": 0.5461555123329163, "learning_rate": 9.881559550500575e-05, "loss": 0.0654, "step": 2320 }, { "grad_norm": 0.5235754251480103, "learning_rate": 9.879764089622712e-05, "loss": 0.0899, "step": 2330 }, { "grad_norm": 0.38445132970809937, "learning_rate": 9.87795528765616e-05, "loss": 0.0696, "step": 2340 }, { "grad_norm": 0.45889338850975037, "learning_rate": 9.876133149546118e-05, "loss": 0.0653, "step": 2350 }, { "grad_norm": 0.6385811567306519, "learning_rate": 9.874297680274238e-05, "loss": 0.077, "step": 2360 }, { "grad_norm": 0.5093027949333191, "learning_rate": 9.872448884858624e-05, "loss": 0.0712, "step": 2370 }, { "grad_norm": 0.41936078667640686, "learning_rate": 9.870586768353815e-05, "loss": 0.0866, "step": 2380 }, { "grad_norm": 0.4418678879737854, "learning_rate": 9.868711335850764e-05, "loss": 0.0808, "step": 2390 }, { "grad_norm": 0.4069119095802307, "learning_rate": 9.866822592476833e-05, "loss": 0.0762, "step": 2400 }, { "grad_norm": 0.5922132134437561, "learning_rate": 9.86492054339577e-05, "loss": 0.0694, "step": 2410 }, { "grad_norm": 0.548949658870697, "learning_rate": 9.863005193807711e-05, "loss": 0.1066, "step": 2420 }, { "grad_norm": 0.40248897671699524, "learning_rate": 9.861076548949143e-05, "loss": 0.0738, "step": 2430 }, { "grad_norm": 0.4671937823295593, "learning_rate": 9.859134614092912e-05, "loss": 0.0763, "step": 2440 }, { "grad_norm": 0.6811140775680542, "learning_rate": 9.857179394548191e-05, "loss": 0.0791, "step": 2450 }, { "grad_norm": 0.49203163385391235, "learning_rate": 9.855210895660477e-05, "loss": 0.0701, "step": 2460 }, { "grad_norm": 0.5631263256072998, "learning_rate": 9.853229122811568e-05, "loss": 0.0617, "step": 2470 }, { "grad_norm": 0.639837920665741, "learning_rate": 9.851234081419559e-05, "loss": 0.0863, "step": 2480 }, { "grad_norm": 0.4485801160335541, "learning_rate": 9.849225776938814e-05, "loss": 0.0695, "step": 2490 }, { "grad_norm": 0.464404433965683, "learning_rate": 9.847204214859964e-05, "loss": 0.067, "step": 2500 }, { "grad_norm": 0.563795268535614, "learning_rate": 9.845169400709879e-05, "loss": 0.0606, "step": 2510 }, { "grad_norm": 0.3246845006942749, "learning_rate": 9.843121340051664e-05, "loss": 0.067, "step": 2520 }, { "grad_norm": 0.38927990198135376, "learning_rate": 9.841060038484641e-05, "loss": 0.0572, "step": 2530 }, { "grad_norm": 0.5653524398803711, "learning_rate": 9.838985501644328e-05, "loss": 0.0658, "step": 2540 }, { "grad_norm": 0.4581703543663025, "learning_rate": 9.83689773520243e-05, "loss": 0.0703, "step": 2550 }, { "grad_norm": 0.4526871144771576, "learning_rate": 9.834796744866819e-05, "loss": 0.0709, "step": 2560 }, { "grad_norm": 0.6715877056121826, "learning_rate": 9.832682536381525e-05, "loss": 0.0673, "step": 2570 }, { "grad_norm": 0.5345441102981567, "learning_rate": 9.830555115526711e-05, "loss": 0.0727, "step": 2580 }, { "grad_norm": 0.6979884505271912, "learning_rate": 9.828414488118667e-05, "loss": 0.0709, "step": 2590 }, { "grad_norm": 0.406823992729187, "learning_rate": 9.826260660009785e-05, "loss": 0.0706, "step": 2600 }, { "grad_norm": 0.45266419649124146, "learning_rate": 9.824093637088547e-05, "loss": 0.0735, "step": 2610 }, { "grad_norm": 0.5179680585861206, "learning_rate": 9.821913425279514e-05, "loss": 0.0621, "step": 2620 }, { "grad_norm": 0.3936919867992401, "learning_rate": 9.8197200305433e-05, "loss": 0.0709, "step": 2630 }, { "grad_norm": 0.548202395439148, "learning_rate": 9.817513458876564e-05, "loss": 0.0787, "step": 2640 }, { "grad_norm": 0.3964272439479828, "learning_rate": 9.815293716311987e-05, "loss": 0.0731, "step": 2650 }, { "grad_norm": 0.4738668203353882, "learning_rate": 9.813060808918262e-05, "loss": 0.0765, "step": 2660 }, { "grad_norm": 0.7000216841697693, "learning_rate": 9.810814742800069e-05, "loss": 0.0861, "step": 2670 }, { "grad_norm": 0.4945289194583893, "learning_rate": 9.808555524098074e-05, "loss": 0.0836, "step": 2680 }, { "grad_norm": 0.3806956708431244, "learning_rate": 9.806283158988887e-05, "loss": 0.0741, "step": 2690 }, { "grad_norm": 0.5644925236701965, "learning_rate": 9.803997653685072e-05, "loss": 0.065, "step": 2700 }, { "grad_norm": 0.40524864196777344, "learning_rate": 9.801699014435112e-05, "loss": 0.0682, "step": 2710 }, { "grad_norm": 0.4175611734390259, "learning_rate": 9.799387247523398e-05, "loss": 0.0896, "step": 2720 }, { "grad_norm": 0.539764404296875, "learning_rate": 9.797062359270215e-05, "loss": 0.0625, "step": 2730 }, { "grad_norm": 0.5547727346420288, "learning_rate": 9.794724356031715e-05, "loss": 0.0613, "step": 2740 }, { "grad_norm": 0.5607513189315796, "learning_rate": 9.792373244199913e-05, "loss": 0.0744, "step": 2750 }, { "grad_norm": 0.7333391904830933, "learning_rate": 9.790009030202658e-05, "loss": 0.0672, "step": 2760 }, { "grad_norm": 0.45608630776405334, "learning_rate": 9.78763172050362e-05, "loss": 0.0752, "step": 2770 }, { "grad_norm": 0.5053641200065613, "learning_rate": 9.785241321602274e-05, "loss": 0.0845, "step": 2780 }, { "grad_norm": 0.5175443887710571, "learning_rate": 9.782837840033879e-05, "loss": 0.0742, "step": 2790 }, { "grad_norm": 0.4193556308746338, "learning_rate": 9.780421282369461e-05, "loss": 0.0615, "step": 2800 }, { "grad_norm": 0.4790283739566803, "learning_rate": 9.777991655215797e-05, "loss": 0.0867, "step": 2810 }, { "grad_norm": 0.6773892641067505, "learning_rate": 9.775548965215394e-05, "loss": 0.0773, "step": 2820 }, { "grad_norm": 0.363373339176178, "learning_rate": 9.773093219046474e-05, "loss": 0.0746, "step": 2830 }, { "grad_norm": 0.38518255949020386, "learning_rate": 9.770624423422954e-05, "loss": 0.0753, "step": 2840 }, { "grad_norm": 0.6493068337440491, "learning_rate": 9.768142585094426e-05, "loss": 0.0776, "step": 2850 }, { "grad_norm": 0.5536928176879883, "learning_rate": 9.765647710846142e-05, "loss": 0.0709, "step": 2860 }, { "grad_norm": 0.6037115454673767, "learning_rate": 9.763139807498991e-05, "loss": 0.0651, "step": 2870 }, { "grad_norm": 0.36817696690559387, "learning_rate": 9.760618881909487e-05, "loss": 0.0615, "step": 2880 }, { "grad_norm": 0.5279136896133423, "learning_rate": 9.758084940969744e-05, "loss": 0.0685, "step": 2890 }, { "grad_norm": 0.4277317523956299, "learning_rate": 9.755537991607459e-05, "loss": 0.0778, "step": 2900 }, { "grad_norm": 0.4091714322566986, "learning_rate": 9.752978040785895e-05, "loss": 0.0689, "step": 2910 }, { "grad_norm": 0.5397607684135437, "learning_rate": 9.750405095503859e-05, "loss": 0.0721, "step": 2920 }, { "grad_norm": 0.4959225058555603, "learning_rate": 9.747819162795686e-05, "loss": 0.052, "step": 2930 }, { "grad_norm": 0.3833876848220825, "learning_rate": 9.745220249731217e-05, "loss": 0.0586, "step": 2940 }, { "grad_norm": 0.4811829924583435, "learning_rate": 9.742608363415781e-05, "loss": 0.0576, "step": 2950 }, { "grad_norm": 0.3008730411529541, "learning_rate": 9.739983510990176e-05, "loss": 0.0709, "step": 2960 }, { "grad_norm": 0.3946513235569, "learning_rate": 9.737345699630647e-05, "loss": 0.0607, "step": 2970 }, { "grad_norm": 0.5362507700920105, "learning_rate": 9.734694936548869e-05, "loss": 0.0678, "step": 2980 }, { "grad_norm": 0.44529569149017334, "learning_rate": 9.732031228991932e-05, "loss": 0.0739, "step": 2990 }, { "grad_norm": 0.42165446281433105, "learning_rate": 9.729354584242302e-05, "loss": 0.0737, "step": 3000 }, { "grad_norm": 0.4531683921813965, "learning_rate": 9.726665009617832e-05, "loss": 0.0572, "step": 3010 }, { "grad_norm": 0.29048892855644226, "learning_rate": 9.723962512471714e-05, "loss": 0.0659, "step": 3020 }, { "grad_norm": 0.3302564322948456, "learning_rate": 9.72124710019247e-05, "loss": 0.0614, "step": 3030 }, { "grad_norm": 0.5023411512374878, "learning_rate": 9.718518780203934e-05, "loss": 0.0624, "step": 3040 }, { "grad_norm": 0.559954822063446, "learning_rate": 9.715777559965228e-05, "loss": 0.0621, "step": 3050 }, { "grad_norm": 0.4008285105228424, "learning_rate": 9.713023446970746e-05, "loss": 0.0658, "step": 3060 }, { "grad_norm": 0.3796211779117584, "learning_rate": 9.710256448750126e-05, "loss": 0.0464, "step": 3070 }, { "grad_norm": 0.41075679659843445, "learning_rate": 9.707476572868235e-05, "loss": 0.064, "step": 3080 }, { "grad_norm": 0.5989819169044495, "learning_rate": 9.704683826925149e-05, "loss": 0.0823, "step": 3090 }, { "grad_norm": 0.5700626969337463, "learning_rate": 9.701878218556129e-05, "loss": 0.0627, "step": 3100 }, { "grad_norm": 0.3708138167858124, "learning_rate": 9.699059755431598e-05, "loss": 0.0528, "step": 3110 }, { "grad_norm": 0.4388757050037384, "learning_rate": 9.696228445257132e-05, "loss": 0.055, "step": 3120 }, { "grad_norm": 0.4572599232196808, "learning_rate": 9.693384295773419e-05, "loss": 0.0627, "step": 3130 }, { "grad_norm": 0.42831283807754517, "learning_rate": 9.690527314756259e-05, "loss": 0.066, "step": 3140 }, { "grad_norm": 0.4210793375968933, "learning_rate": 9.687657510016527e-05, "loss": 0.0546, "step": 3150 }, { "grad_norm": 0.3184014856815338, "learning_rate": 9.684774889400161e-05, "loss": 0.0618, "step": 3160 }, { "grad_norm": 0.3647445738315582, "learning_rate": 9.681879460788135e-05, "loss": 0.0573, "step": 3170 }, { "grad_norm": 0.51015305519104, "learning_rate": 9.67897123209644e-05, "loss": 0.0796, "step": 3180 }, { "grad_norm": 0.5470426678657532, "learning_rate": 9.676050211276062e-05, "loss": 0.0744, "step": 3190 }, { "grad_norm": 0.5098283290863037, "learning_rate": 9.673116406312962e-05, "loss": 0.0724, "step": 3200 }, { "grad_norm": 0.6475949287414551, "learning_rate": 9.67016982522805e-05, "loss": 0.0656, "step": 3210 }, { "grad_norm": 0.39355769753456116, "learning_rate": 9.667210476077164e-05, "loss": 0.0845, "step": 3220 }, { "grad_norm": 0.6729139685630798, "learning_rate": 9.664238366951055e-05, "loss": 0.0769, "step": 3230 }, { "grad_norm": 0.4515778422355652, "learning_rate": 9.661253505975355e-05, "loss": 0.064, "step": 3240 }, { "grad_norm": 0.29692012071609497, "learning_rate": 9.658255901310557e-05, "loss": 0.08, "step": 3250 }, { "grad_norm": 0.6647087335586548, "learning_rate": 9.655245561152e-05, "loss": 0.0788, "step": 3260 }, { "grad_norm": 0.6858780384063721, "learning_rate": 9.65222249372984e-05, "loss": 0.0772, "step": 3270 }, { "grad_norm": 0.42347073554992676, "learning_rate": 9.649186707309026e-05, "loss": 0.0652, "step": 3280 }, { "grad_norm": 0.4052954912185669, "learning_rate": 9.646138210189283e-05, "loss": 0.0654, "step": 3290 }, { "grad_norm": 0.5611249804496765, "learning_rate": 9.643077010705087e-05, "loss": 0.0626, "step": 3300 }, { "grad_norm": 0.5174850225448608, "learning_rate": 9.640003117225637e-05, "loss": 0.0681, "step": 3310 }, { "grad_norm": 0.5723249912261963, "learning_rate": 9.636916538154846e-05, "loss": 0.0824, "step": 3320 }, { "grad_norm": 0.48169010877609253, "learning_rate": 9.633817281931296e-05, "loss": 0.0656, "step": 3330 }, { "grad_norm": 0.4672619104385376, "learning_rate": 9.630705357028242e-05, "loss": 0.0655, "step": 3340 }, { "grad_norm": 0.6956623196601868, "learning_rate": 9.627580771953563e-05, "loss": 0.0668, "step": 3350 }, { "grad_norm": 0.6034864783287048, "learning_rate": 9.624443535249759e-05, "loss": 0.0657, "step": 3360 }, { "grad_norm": 0.45017504692077637, "learning_rate": 9.621293655493913e-05, "loss": 0.0671, "step": 3370 }, { "grad_norm": 0.36460450291633606, "learning_rate": 9.618131141297675e-05, "loss": 0.1002, "step": 3380 }, { "grad_norm": 0.3848011791706085, "learning_rate": 9.614956001307242e-05, "loss": 0.0599, "step": 3390 }, { "grad_norm": 0.554142415523529, "learning_rate": 9.611768244203321e-05, "loss": 0.069, "step": 3400 }, { "grad_norm": 0.5206557512283325, "learning_rate": 9.60856787870112e-05, "loss": 0.0716, "step": 3410 }, { "grad_norm": 0.5587310194969177, "learning_rate": 9.605354913550318e-05, "loss": 0.0573, "step": 3420 }, { "grad_norm": 0.5434862971305847, "learning_rate": 9.602129357535037e-05, "loss": 0.0598, "step": 3430 }, { "grad_norm": 0.6129313707351685, "learning_rate": 9.598891219473825e-05, "loss": 0.0787, "step": 3440 }, { "grad_norm": 0.46743470430374146, "learning_rate": 9.595640508219625e-05, "loss": 0.0615, "step": 3450 }, { "grad_norm": 0.4357616901397705, "learning_rate": 9.592377232659761e-05, "loss": 0.0562, "step": 3460 }, { "grad_norm": 0.335782527923584, "learning_rate": 9.589101401715904e-05, "loss": 0.0709, "step": 3470 }, { "grad_norm": 0.35368964076042175, "learning_rate": 9.585813024344045e-05, "loss": 0.0664, "step": 3480 }, { "grad_norm": 0.6416192650794983, "learning_rate": 9.58251210953449e-05, "loss": 0.0692, "step": 3490 }, { "grad_norm": 0.4220646917819977, "learning_rate": 9.579198666311809e-05, "loss": 0.0503, "step": 3500 }, { "grad_norm": 0.371980220079422, "learning_rate": 9.575872703734832e-05, "loss": 0.0587, "step": 3510 }, { "grad_norm": 0.7096942067146301, "learning_rate": 9.572534230896611e-05, "loss": 0.0675, "step": 3520 }, { "grad_norm": 0.39120808243751526, "learning_rate": 9.569183256924403e-05, "loss": 0.0626, "step": 3530 }, { "grad_norm": 0.4355262219905853, "learning_rate": 9.565819790979646e-05, "loss": 0.0598, "step": 3540 }, { "grad_norm": 0.43314382433891296, "learning_rate": 9.562443842257925e-05, "loss": 0.0647, "step": 3550 }, { "grad_norm": 0.3631117641925812, "learning_rate": 9.559055419988956e-05, "loss": 0.0451, "step": 3560 }, { "grad_norm": 0.37445390224456787, "learning_rate": 9.555654533436557e-05, "loss": 0.0646, "step": 3570 }, { "grad_norm": 0.5261792540550232, "learning_rate": 9.552241191898621e-05, "loss": 0.0722, "step": 3580 }, { "grad_norm": 0.5027698874473572, "learning_rate": 9.548815404707092e-05, "loss": 0.0781, "step": 3590 }, { "grad_norm": 0.5249517560005188, "learning_rate": 9.545377181227942e-05, "loss": 0.0607, "step": 3600 }, { "grad_norm": 0.5215481519699097, "learning_rate": 9.541926530861145e-05, "loss": 0.0654, "step": 3610 }, { "grad_norm": 0.2896328270435333, "learning_rate": 9.538463463040645e-05, "loss": 0.0575, "step": 3620 }, { "grad_norm": 0.4600287675857544, "learning_rate": 9.534987987234337e-05, "loss": 0.0484, "step": 3630 }, { "grad_norm": 0.3302086591720581, "learning_rate": 9.53150011294404e-05, "loss": 0.0554, "step": 3640 }, { "grad_norm": 0.6352643966674805, "learning_rate": 9.527999849705471e-05, "loss": 0.0644, "step": 3650 }, { "grad_norm": 0.556961715221405, "learning_rate": 9.524487207088213e-05, "loss": 0.0632, "step": 3660 }, { "grad_norm": 0.3770855665206909, "learning_rate": 9.520962194695698e-05, "loss": 0.068, "step": 3670 }, { "grad_norm": 0.44415804743766785, "learning_rate": 9.517424822165175e-05, "loss": 0.0669, "step": 3680 }, { "grad_norm": 0.5286231637001038, "learning_rate": 9.513875099167685e-05, "loss": 0.0612, "step": 3690 }, { "grad_norm": 0.32096609473228455, "learning_rate": 9.510313035408035e-05, "loss": 0.0583, "step": 3700 }, { "grad_norm": 0.32460126280784607, "learning_rate": 9.506738640624775e-05, "loss": 0.0567, "step": 3710 }, { "grad_norm": 0.3958132565021515, "learning_rate": 9.50315192459016e-05, "loss": 0.0594, "step": 3720 }, { "grad_norm": 0.423059344291687, "learning_rate": 9.499552897110136e-05, "loss": 0.0501, "step": 3730 }, { "grad_norm": 0.37693944573402405, "learning_rate": 9.495941568024304e-05, "loss": 0.0572, "step": 3740 }, { "grad_norm": 0.349576860666275, "learning_rate": 9.492317947205904e-05, "loss": 0.0682, "step": 3750 }, { "grad_norm": 0.33538660407066345, "learning_rate": 9.488682044561775e-05, "loss": 0.0529, "step": 3760 }, { "grad_norm": 0.411823570728302, "learning_rate": 9.485033870032335e-05, "loss": 0.0704, "step": 3770 }, { "grad_norm": 0.5954554080963135, "learning_rate": 9.481373433591556e-05, "loss": 0.0659, "step": 3780 }, { "grad_norm": 0.43300774693489075, "learning_rate": 9.47770074524693e-05, "loss": 0.0619, "step": 3790 }, { "grad_norm": 0.35564863681793213, "learning_rate": 9.474015815039446e-05, "loss": 0.0852, "step": 3800 }, { "grad_norm": 0.5341017246246338, "learning_rate": 9.470318653043565e-05, "loss": 0.0644, "step": 3810 }, { "grad_norm": 0.4436597228050232, "learning_rate": 9.466609269367185e-05, "loss": 0.0636, "step": 3820 }, { "grad_norm": 0.3200393617153168, "learning_rate": 9.46288767415162e-05, "loss": 0.0545, "step": 3830 }, { "grad_norm": 0.4848664700984955, "learning_rate": 9.459153877571567e-05, "loss": 0.0524, "step": 3840 }, { "grad_norm": 0.5200585722923279, "learning_rate": 9.455407889835087e-05, "loss": 0.0772, "step": 3850 }, { "grad_norm": 0.4237646162509918, "learning_rate": 9.451649721183564e-05, "loss": 0.0555, "step": 3860 }, { "grad_norm": 0.4679590165615082, "learning_rate": 9.447879381891692e-05, "loss": 0.0589, "step": 3870 }, { "grad_norm": 0.5023428201675415, "learning_rate": 9.444096882267428e-05, "loss": 0.0525, "step": 3880 }, { "grad_norm": 0.3898168206214905, "learning_rate": 9.440302232651988e-05, "loss": 0.0649, "step": 3890 }, { "grad_norm": 0.40037524700164795, "learning_rate": 9.436495443419795e-05, "loss": 0.0635, "step": 3900 }, { "grad_norm": 0.40977975726127625, "learning_rate": 9.432676524978466e-05, "loss": 0.0595, "step": 3910 }, { "grad_norm": 0.5892367959022522, "learning_rate": 9.42884548776878e-05, "loss": 0.0676, "step": 3920 }, { "grad_norm": 0.4612579345703125, "learning_rate": 9.425002342264646e-05, "loss": 0.055, "step": 3930 }, { "grad_norm": 0.37688493728637695, "learning_rate": 9.421147098973077e-05, "loss": 0.0751, "step": 3940 }, { "grad_norm": 0.31961745023727417, "learning_rate": 9.41727976843416e-05, "loss": 0.0664, "step": 3950 }, { "grad_norm": 0.35288187861442566, "learning_rate": 9.413400361221029e-05, "loss": 0.0736, "step": 3960 }, { "grad_norm": 0.6691736578941345, "learning_rate": 9.409508887939835e-05, "loss": 0.0581, "step": 3970 }, { "grad_norm": 0.43810462951660156, "learning_rate": 9.40560535922972e-05, "loss": 0.0657, "step": 3980 }, { "grad_norm": 0.4077014923095703, "learning_rate": 9.40168978576278e-05, "loss": 0.0631, "step": 3990 }, { "grad_norm": 0.5063613653182983, "learning_rate": 9.397762178244043e-05, "loss": 0.0608, "step": 4000 }, { "grad_norm": 0.47698378562927246, "learning_rate": 9.393822547411439e-05, "loss": 0.0555, "step": 4010 }, { "grad_norm": 0.38870927691459656, "learning_rate": 9.389870904035769e-05, "loss": 0.0633, "step": 4020 }, { "grad_norm": 0.5973719954490662, "learning_rate": 9.385907258920672e-05, "loss": 0.0666, "step": 4030 }, { "grad_norm": 0.36002427339553833, "learning_rate": 9.381931622902607e-05, "loss": 0.0478, "step": 4040 }, { "grad_norm": 0.6954936385154724, "learning_rate": 9.377944006850807e-05, "loss": 0.0699, "step": 4050 }, { "grad_norm": 0.5508219003677368, "learning_rate": 9.373944421667265e-05, "loss": 0.0658, "step": 4060 }, { "grad_norm": 0.4282638430595398, "learning_rate": 9.369932878286691e-05, "loss": 0.0539, "step": 4070 }, { "grad_norm": 0.6118499636650085, "learning_rate": 9.365909387676494e-05, "loss": 0.0679, "step": 4080 }, { "grad_norm": 0.44618308544158936, "learning_rate": 9.361873960836744e-05, "loss": 0.0605, "step": 4090 }, { "grad_norm": 0.46227312088012695, "learning_rate": 9.357826608800142e-05, "loss": 0.0562, "step": 4100 }, { "grad_norm": 0.24338363111019135, "learning_rate": 9.353767342631994e-05, "loss": 0.0646, "step": 4110 }, { "grad_norm": 0.3737015426158905, "learning_rate": 9.34969617343018e-05, "loss": 0.0628, "step": 4120 }, { "grad_norm": 0.4608723223209381, "learning_rate": 9.345613112325122e-05, "loss": 0.0609, "step": 4130 }, { "grad_norm": 0.553767204284668, "learning_rate": 9.34151817047975e-05, "loss": 0.0579, "step": 4140 }, { "grad_norm": 0.384003609418869, "learning_rate": 9.33741135908948e-05, "loss": 0.0674, "step": 4150 }, { "grad_norm": 0.36163198947906494, "learning_rate": 9.33329268938218e-05, "loss": 0.0549, "step": 4160 }, { "grad_norm": 0.4170988202095032, "learning_rate": 9.329162172618132e-05, "loss": 0.054, "step": 4170 }, { "grad_norm": 0.3676707446575165, "learning_rate": 9.325019820090013e-05, "loss": 0.0516, "step": 4180 }, { "grad_norm": 0.3805757164955139, "learning_rate": 9.320865643122855e-05, "loss": 0.0563, "step": 4190 }, { "grad_norm": 0.2689366936683655, "learning_rate": 9.316699653074023e-05, "loss": 0.0507, "step": 4200 }, { "grad_norm": 0.3161689341068268, "learning_rate": 9.312521861333172e-05, "loss": 0.054, "step": 4210 }, { "grad_norm": 0.3564290404319763, "learning_rate": 9.308332279322224e-05, "loss": 0.0673, "step": 4220 }, { "grad_norm": 0.3406626582145691, "learning_rate": 9.304130918495338e-05, "loss": 0.0684, "step": 4230 }, { "grad_norm": 0.5409299731254578, "learning_rate": 9.299917790338874e-05, "loss": 0.0697, "step": 4240 }, { "grad_norm": 0.5530665516853333, "learning_rate": 9.295692906371363e-05, "loss": 0.067, "step": 4250 }, { "grad_norm": 0.40163499116897583, "learning_rate": 9.291456278143476e-05, "loss": 0.0676, "step": 4260 }, { "grad_norm": 0.3614158034324646, "learning_rate": 9.287207917237994e-05, "loss": 0.0567, "step": 4270 }, { "grad_norm": 0.468063086271286, "learning_rate": 9.282947835269773e-05, "loss": 0.0534, "step": 4280 }, { "grad_norm": 0.5936371684074402, "learning_rate": 9.278676043885715e-05, "loss": 0.0581, "step": 4290 }, { "grad_norm": 0.4098218083381653, "learning_rate": 9.274392554764733e-05, "loss": 0.054, "step": 4300 }, { "grad_norm": 0.4250509738922119, "learning_rate": 9.270097379617723e-05, "loss": 0.0616, "step": 4310 }, { "grad_norm": 0.3863816559314728, "learning_rate": 9.26579053018753e-05, "loss": 0.0852, "step": 4320 }, { "grad_norm": 0.4025675058364868, "learning_rate": 9.261472018248918e-05, "loss": 0.0551, "step": 4330 }, { "grad_norm": 0.43184420466423035, "learning_rate": 9.25714185560853e-05, "loss": 0.0482, "step": 4340 }, { "grad_norm": 0.34683769941329956, "learning_rate": 9.252800054104868e-05, "loss": 0.0446, "step": 4350 }, { "grad_norm": 0.4519708454608917, "learning_rate": 9.248446625608252e-05, "loss": 0.0484, "step": 4360 }, { "grad_norm": 0.37790781259536743, "learning_rate": 9.244081582020789e-05, "loss": 0.0614, "step": 4370 }, { "grad_norm": 0.5895617008209229, "learning_rate": 9.239704935276339e-05, "loss": 0.0693, "step": 4380 }, { "grad_norm": 0.37066084146499634, "learning_rate": 9.235316697340489e-05, "loss": 0.0539, "step": 4390 }, { "grad_norm": 0.47893595695495605, "learning_rate": 9.230916880210512e-05, "loss": 0.0625, "step": 4400 }, { "grad_norm": 0.41077014803886414, "learning_rate": 9.226505495915342e-05, "loss": 0.0599, "step": 4410 }, { "grad_norm": 0.4323832094669342, "learning_rate": 9.222082556515536e-05, "loss": 0.0737, "step": 4420 }, { "grad_norm": 0.42029616236686707, "learning_rate": 9.217648074103242e-05, "loss": 0.0638, "step": 4430 }, { "grad_norm": 0.44474565982818604, "learning_rate": 9.213202060802161e-05, "loss": 0.0664, "step": 4440 }, { "grad_norm": 0.41344979405403137, "learning_rate": 9.208744528767528e-05, "loss": 0.0677, "step": 4450 }, { "grad_norm": 0.3374527394771576, "learning_rate": 9.204275490186064e-05, "loss": 0.0555, "step": 4460 }, { "grad_norm": 0.380389004945755, "learning_rate": 9.199794957275949e-05, "loss": 0.0545, "step": 4470 }, { "grad_norm": 0.537401556968689, "learning_rate": 9.19530294228679e-05, "loss": 0.0609, "step": 4480 }, { "grad_norm": 0.43015357851982117, "learning_rate": 9.190799457499583e-05, "loss": 0.0645, "step": 4490 }, { "grad_norm": 0.47438549995422363, "learning_rate": 9.186284515226686e-05, "loss": 0.0554, "step": 4500 }, { "grad_norm": 0.3287853002548218, "learning_rate": 9.181758127811777e-05, "loss": 0.0753, "step": 4510 }, { "grad_norm": 0.4407401978969574, "learning_rate": 9.177220307629825e-05, "loss": 0.0642, "step": 4520 }, { "grad_norm": 0.38520941138267517, "learning_rate": 9.172671067087059e-05, "loss": 0.058, "step": 4530 }, { "grad_norm": 0.5340979099273682, "learning_rate": 9.16811041862093e-05, "loss": 0.0754, "step": 4540 }, { "grad_norm": 0.49036866426467896, "learning_rate": 9.163538374700076e-05, "loss": 0.0674, "step": 4550 }, { "grad_norm": 0.4153555929660797, "learning_rate": 9.158954947824287e-05, "loss": 0.0567, "step": 4560 }, { "grad_norm": 0.4453776776790619, "learning_rate": 9.154360150524482e-05, "loss": 0.0602, "step": 4570 }, { "grad_norm": 0.5705938935279846, "learning_rate": 9.14975399536266e-05, "loss": 0.0562, "step": 4580 }, { "grad_norm": 0.4510863125324249, "learning_rate": 9.14513649493187e-05, "loss": 0.0527, "step": 4590 }, { "grad_norm": 0.3248927891254425, "learning_rate": 9.140507661856187e-05, "loss": 0.059, "step": 4600 }, { "grad_norm": 0.4323951303958893, "learning_rate": 9.135867508790661e-05, "loss": 0.0669, "step": 4610 }, { "grad_norm": 0.4253670871257782, "learning_rate": 9.131216048421291e-05, "loss": 0.0599, "step": 4620 }, { "grad_norm": 0.4736694395542145, "learning_rate": 9.126553293464998e-05, "loss": 0.067, "step": 4630 }, { "grad_norm": 0.6026774048805237, "learning_rate": 9.121879256669572e-05, "loss": 0.067, "step": 4640 }, { "grad_norm": 0.41097766160964966, "learning_rate": 9.117193950813652e-05, "loss": 0.0518, "step": 4650 }, { "grad_norm": 0.5359702110290527, "learning_rate": 9.112497388706685e-05, "loss": 0.0636, "step": 4660 }, { "grad_norm": 0.5441976189613342, "learning_rate": 9.10778958318889e-05, "loss": 0.0553, "step": 4670 }, { "grad_norm": 0.4872678518295288, "learning_rate": 9.103070547131232e-05, "loss": 0.059, "step": 4680 }, { "grad_norm": 0.43204641342163086, "learning_rate": 9.098340293435375e-05, "loss": 0.0666, "step": 4690 }, { "grad_norm": 0.5552080869674683, "learning_rate": 9.093598835033649e-05, "loss": 0.0579, "step": 4700 }, { "grad_norm": 0.5426272749900818, "learning_rate": 9.088846184889021e-05, "loss": 0.0603, "step": 4710 }, { "grad_norm": 0.5322993397712708, "learning_rate": 9.084082355995057e-05, "loss": 0.0572, "step": 4720 }, { "grad_norm": 0.3568741977214813, "learning_rate": 9.079307361375882e-05, "loss": 0.0575, "step": 4730 }, { "grad_norm": 0.34751611948013306, "learning_rate": 9.074521214086149e-05, "loss": 0.0609, "step": 4740 }, { "grad_norm": 0.3707248568534851, "learning_rate": 9.069723927211001e-05, "loss": 0.0472, "step": 4750 }, { "grad_norm": 0.4899339973926544, "learning_rate": 9.064915513866037e-05, "loss": 0.0587, "step": 4760 }, { "grad_norm": 0.41481518745422363, "learning_rate": 9.060095987197279e-05, "loss": 0.0612, "step": 4770 }, { "grad_norm": 0.3718417286872864, "learning_rate": 9.055265360381126e-05, "loss": 0.0655, "step": 4780 }, { "grad_norm": 0.3920193016529083, "learning_rate": 9.050423646624326e-05, "loss": 0.054, "step": 4790 }, { "grad_norm": 0.3364790678024292, "learning_rate": 9.045570859163943e-05, "loss": 0.0609, "step": 4800 }, { "grad_norm": 0.5538080930709839, "learning_rate": 9.04070701126731e-05, "loss": 0.0589, "step": 4810 }, { "grad_norm": 0.4119049906730652, "learning_rate": 9.035832116232001e-05, "loss": 0.0591, "step": 4820 }, { "grad_norm": 0.33189713954925537, "learning_rate": 9.030946187385796e-05, "loss": 0.0545, "step": 4830 }, { "grad_norm": 0.4923993945121765, "learning_rate": 9.026049238086635e-05, "loss": 0.0604, "step": 4840 }, { "grad_norm": 0.4770161807537079, "learning_rate": 9.021141281722591e-05, "loss": 0.0614, "step": 4850 }, { "grad_norm": 0.3449961543083191, "learning_rate": 9.01622233171183e-05, "loss": 0.053, "step": 4860 }, { "grad_norm": 0.34431275725364685, "learning_rate": 9.011292401502574e-05, "loss": 0.0624, "step": 4870 }, { "grad_norm": 0.3619093894958496, "learning_rate": 9.006351504573063e-05, "loss": 0.0551, "step": 4880 }, { "grad_norm": 0.550771951675415, "learning_rate": 9.001399654431519e-05, "loss": 0.0766, "step": 4890 }, { "grad_norm": 0.5385379791259766, "learning_rate": 8.996436864616116e-05, "loss": 0.051, "step": 4900 }, { "grad_norm": 0.4363107681274414, "learning_rate": 8.991463148694925e-05, "loss": 0.0587, "step": 4910 }, { "grad_norm": 0.3706141412258148, "learning_rate": 8.986478520265902e-05, "loss": 0.0641, "step": 4920 }, { "grad_norm": 0.4135291278362274, "learning_rate": 8.981482992956827e-05, "loss": 0.054, "step": 4930 }, { "grad_norm": 0.40870434045791626, "learning_rate": 8.976476580425282e-05, "loss": 0.05, "step": 4940 }, { "grad_norm": 0.4539478123188019, "learning_rate": 8.971459296358606e-05, "loss": 0.0606, "step": 4950 }, { "grad_norm": 0.34760892391204834, "learning_rate": 8.966431154473864e-05, "loss": 0.0561, "step": 4960 }, { "grad_norm": 0.3292563855648041, "learning_rate": 8.961392168517803e-05, "loss": 0.0652, "step": 4970 }, { "grad_norm": 0.23807686567306519, "learning_rate": 8.956342352266821e-05, "loss": 0.0524, "step": 4980 }, { "grad_norm": 0.38372892141342163, "learning_rate": 8.95128171952692e-05, "loss": 0.0543, "step": 4990 }, { "grad_norm": 0.33882585167884827, "learning_rate": 8.946210284133676e-05, "loss": 0.0573, "step": 5000 } ], "logging_steps": 10, "max_steps": 20000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }