| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998673212153376, | |
| "eval_steps": 500, | |
| "global_step": 3768, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.6525198938992043e-06, | |
| "loss": 1.3287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.305039787798409e-06, | |
| "loss": 1.2877, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.957559681697613e-06, | |
| "loss": 1.2194, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.0610079575596817e-05, | |
| "loss": 1.0738, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3262599469496024e-05, | |
| "loss": 0.9618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.5915119363395225e-05, | |
| "loss": 0.8582, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.856763925729443e-05, | |
| "loss": 0.7276, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.1220159151193635e-05, | |
| "loss": 0.5857, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.3872679045092838e-05, | |
| "loss": 0.4838, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.6525198938992047e-05, | |
| "loss": 0.3778, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9177718832891247e-05, | |
| "loss": 0.3352, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.183023872679045e-05, | |
| "loss": 0.3077, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 0.2823, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.713527851458886e-05, | |
| "loss": 0.2651, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.978779840848806e-05, | |
| "loss": 0.2411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.244031830238727e-05, | |
| "loss": 0.2261, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5092838196286476e-05, | |
| "loss": 0.214, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.7745358090185675e-05, | |
| "loss": 0.2055, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.039787798408488e-05, | |
| "loss": 0.2032, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.3050397877984095e-05, | |
| "loss": 0.1882, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.570291777188329e-05, | |
| "loss": 0.1831, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5.8355437665782494e-05, | |
| "loss": 0.1768, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.100795755968171e-05, | |
| "loss": 0.1634, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.36604774535809e-05, | |
| "loss": 0.1598, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.631299734748011e-05, | |
| "loss": 0.1546, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 0.1538, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 7.161803713527851e-05, | |
| "loss": 0.1575, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.427055702917773e-05, | |
| "loss": 0.1464, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.147, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.957559681697613e-05, | |
| "loss": 0.1446, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.222811671087534e-05, | |
| "loss": 0.1417, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.488063660477454e-05, | |
| "loss": 0.1413, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.753315649867374e-05, | |
| "loss": 0.1356, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.018567639257295e-05, | |
| "loss": 0.1352, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.283819628647215e-05, | |
| "loss": 0.1345, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.549071618037135e-05, | |
| "loss": 0.1357, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.814323607427056e-05, | |
| "loss": 0.1308, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00010079575596816976, | |
| "loss": 0.1327, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00010344827586206898, | |
| "loss": 0.1296, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00010610079575596819, | |
| "loss": 0.1233, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00010875331564986738, | |
| "loss": 0.1273, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00011140583554376658, | |
| "loss": 0.1247, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011405835543766579, | |
| "loss": 0.1235, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011671087533156499, | |
| "loss": 0.1228, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001193633952254642, | |
| "loss": 0.1221, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00012201591511936341, | |
| "loss": 0.1219, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001246684350132626, | |
| "loss": 0.1212, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001273209549071618, | |
| "loss": 0.1213, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00012997347480106101, | |
| "loss": 0.1198, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00013262599469496023, | |
| "loss": 0.1188, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00013527851458885944, | |
| "loss": 0.1199, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00013793103448275863, | |
| "loss": 0.1165, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001405835543766578, | |
| "loss": 0.1173, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014323607427055703, | |
| "loss": 0.1146, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014588859416445624, | |
| "loss": 0.1123, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00014854111405835545, | |
| "loss": 0.1113, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00015119363395225467, | |
| "loss": 0.1146, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.1134, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00015649867374005304, | |
| "loss": 0.1124, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015915119363395225, | |
| "loss": 0.1127, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00016180371352785146, | |
| "loss": 0.1125, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00016445623342175068, | |
| "loss": 0.1103, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001671087533156499, | |
| "loss": 0.1111, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00016976127320954908, | |
| "loss": 0.1096, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00017241379310344826, | |
| "loss": 0.1104, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00017506631299734748, | |
| "loss": 0.1112, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001777188328912467, | |
| "loss": 0.1076, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001803713527851459, | |
| "loss": 0.1093, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018302387267904512, | |
| "loss": 0.1086, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001856763925729443, | |
| "loss": 0.1068, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018832891246684351, | |
| "loss": 0.107, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001909814323607427, | |
| "loss": 0.1091, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019363395225464191, | |
| "loss": 0.1069, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019628647214854113, | |
| "loss": 0.1048, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019893899204244034, | |
| "loss": 0.1062, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019982306104393983, | |
| "loss": 0.1076, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019952816278383958, | |
| "loss": 0.1026, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001992332645237393, | |
| "loss": 0.1064, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019893836626363906, | |
| "loss": 0.1065, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019864346800353878, | |
| "loss": 0.1079, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001983485697434385, | |
| "loss": 0.1067, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019805367148333826, | |
| "loss": 0.1023, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000197758773223238, | |
| "loss": 0.1038, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001974638749631377, | |
| "loss": 0.1033, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019716897670303746, | |
| "loss": 0.1024, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001968740784429372, | |
| "loss": 0.1035, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00019657918018283694, | |
| "loss": 0.1025, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019628428192273667, | |
| "loss": 0.1003, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001959893836626364, | |
| "loss": 0.1009, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00019569448540253615, | |
| "loss": 0.0994, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00019539958714243587, | |
| "loss": 0.1026, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001951046888823356, | |
| "loss": 0.1008, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00019480979062223535, | |
| "loss": 0.1012, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00019451489236213507, | |
| "loss": 0.0977, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001942199941020348, | |
| "loss": 0.0995, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019392509584193455, | |
| "loss": 0.1003, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019363019758183428, | |
| "loss": 0.0985, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00019333529932173403, | |
| "loss": 0.0976, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00019304040106163375, | |
| "loss": 0.1009, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00019274550280153348, | |
| "loss": 0.0986, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00019245060454143323, | |
| "loss": 0.1004, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00019215570628133296, | |
| "loss": 0.1007, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00019186080802123268, | |
| "loss": 0.0976, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00019156590976113244, | |
| "loss": 0.0979, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00019127101150103216, | |
| "loss": 0.0984, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00019097611324093189, | |
| "loss": 0.0978, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001906812149808316, | |
| "loss": 0.1001, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00019038631672073136, | |
| "loss": 0.0989, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001900914184606311, | |
| "loss": 0.0999, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018979652020053081, | |
| "loss": 0.0967, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018950162194043054, | |
| "loss": 0.0944, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001892067236803303, | |
| "loss": 0.0971, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018891182542023002, | |
| "loss": 0.0974, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018861692716012977, | |
| "loss": 0.0968, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001883220289000295, | |
| "loss": 0.0946, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018802713063992922, | |
| "loss": 0.0965, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018773223237982897, | |
| "loss": 0.0946, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001874373341197287, | |
| "loss": 0.0941, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018714243585962842, | |
| "loss": 0.0947, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00018684753759952818, | |
| "loss": 0.0953, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001865526393394279, | |
| "loss": 0.095, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018625774107932763, | |
| "loss": 0.0938, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018596284281922738, | |
| "loss": 0.094, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001856679445591271, | |
| "loss": 0.0951, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018537304629902686, | |
| "loss": 0.0946, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00018507814803892658, | |
| "loss": 0.0937, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001847832497788263, | |
| "loss": 0.0931, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00018448835151872606, | |
| "loss": 0.0942, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00018419345325862579, | |
| "loss": 0.0925, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001838985549985255, | |
| "loss": 0.0938, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00018360365673842526, | |
| "loss": 0.093, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000183308758478325, | |
| "loss": 0.0919, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00018301386021822474, | |
| "loss": 0.0951, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00018271896195812447, | |
| "loss": 0.0943, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001824240636980242, | |
| "loss": 0.0946, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00018212916543792394, | |
| "loss": 0.094, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00018183426717782367, | |
| "loss": 0.0954, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001815393689177234, | |
| "loss": 0.0912, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00018124447065762315, | |
| "loss": 0.0925, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00018094957239752287, | |
| "loss": 0.0928, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001806546741374226, | |
| "loss": 0.0908, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00018035977587732232, | |
| "loss": 0.0926, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00018006487761722205, | |
| "loss": 0.0958, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001797699793571218, | |
| "loss": 0.0927, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017947508109702153, | |
| "loss": 0.0912, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017918018283692125, | |
| "loss": 0.0936, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.000178885284576821, | |
| "loss": 0.0931, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00017859038631672073, | |
| "loss": 0.0927, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00017829548805662048, | |
| "loss": 0.0913, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001780005897965202, | |
| "loss": 0.0908, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00017770569153641993, | |
| "loss": 0.0928, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00017741079327631968, | |
| "loss": 0.0911, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001771158950162194, | |
| "loss": 0.0898, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00017682099675611913, | |
| "loss": 0.0887, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001765260984960189, | |
| "loss": 0.0918, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0001762312002359186, | |
| "loss": 0.0911, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00017593630197581834, | |
| "loss": 0.0925, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001756414037157181, | |
| "loss": 0.0901, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00017534650545561782, | |
| "loss": 0.0931, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017505160719551757, | |
| "loss": 0.0889, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0001747567089354173, | |
| "loss": 0.0892, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017446181067531702, | |
| "loss": 0.0926, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00017416691241521677, | |
| "loss": 0.0898, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001738720141551165, | |
| "loss": 0.0899, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017357711589501622, | |
| "loss": 0.088, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017328221763491597, | |
| "loss": 0.0912, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001729873193748157, | |
| "loss": 0.0903, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017269242111471545, | |
| "loss": 0.091, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00017239752285461518, | |
| "loss": 0.0893, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001721026245945149, | |
| "loss": 0.0883, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00017180772633441465, | |
| "loss": 0.0884, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00017151282807431438, | |
| "loss": 0.0878, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001712179298142141, | |
| "loss": 0.0908, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00017092303155411383, | |
| "loss": 0.0895, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00017062813329401358, | |
| "loss": 0.088, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001703332350339133, | |
| "loss": 0.0883, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00017003833677381303, | |
| "loss": 0.0886, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016974343851371276, | |
| "loss": 0.09, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001694485402536125, | |
| "loss": 0.0912, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016915364199351224, | |
| "loss": 0.0879, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016885874373341196, | |
| "loss": 0.0903, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016856384547331171, | |
| "loss": 0.0896, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016826894721321144, | |
| "loss": 0.0876, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00016797404895311117, | |
| "loss": 0.0872, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00016767915069301092, | |
| "loss": 0.0921, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016738425243291064, | |
| "loss": 0.086, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001670893541728104, | |
| "loss": 0.0861, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00016679445591271012, | |
| "loss": 0.0882, | |
| "step": 3760 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 15072, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 1.9064002664523104e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |