{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.7377881560726602, "global_step": 16000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 0.0006992397089171283, "loss": 0.9904, "step": 100 }, { "epoch": 0.02, "learning_rate": 0.0006984794178342565, "loss": 1.0331, "step": 200 }, { "epoch": 0.03, "learning_rate": 0.0006977191267513849, "loss": 1.0506, "step": 300 }, { "epoch": 0.04, "learning_rate": 0.0006969588356685131, "loss": 1.0698, "step": 400 }, { "epoch": 0.05, "learning_rate": 0.0006961985445856413, "loss": 1.0191, "step": 500 }, { "epoch": 0.07, "learning_rate": 0.0006954382535027696, "loss": 1.0418, "step": 600 }, { "epoch": 0.08, "learning_rate": 0.0006946779624198979, "loss": 1.1059, "step": 700 }, { "epoch": 0.09, "learning_rate": 0.0006939176713370262, "loss": 1.0536, "step": 800 }, { "epoch": 0.1, "learning_rate": 0.0006931573802541545, "loss": 1.0631, "step": 900 }, { "epoch": 0.11, "learning_rate": 0.0006923970891712827, "loss": 1.0861, "step": 1000 }, { "epoch": 0.12, "learning_rate": 0.0006916367980884109, "loss": 1.1102, "step": 1100 }, { "epoch": 0.13, "learning_rate": 0.0006908765070055393, "loss": 1.0543, "step": 1200 }, { "epoch": 0.14, "learning_rate": 0.0006901162159226675, "loss": 1.0827, "step": 1300 }, { "epoch": 0.15, "learning_rate": 0.0006893559248397958, "loss": 1.0794, "step": 1400 }, { "epoch": 0.16, "learning_rate": 0.0006885956337569241, "loss": 1.0768, "step": 1500 }, { "epoch": 0.17, "learning_rate": 0.0006878353426740524, "loss": 1.1544, "step": 1600 }, { "epoch": 0.18, "learning_rate": 0.0006870750515911806, "loss": 1.1412, "step": 1700 }, { "epoch": 0.2, "learning_rate": 0.0006863147605083089, "loss": 1.0918, "step": 1800 }, { "epoch": 0.21, "learning_rate": 0.0006855544694254371, "loss": 1.0784, "step": 1900 }, { "epoch": 0.22, "learning_rate": 0.0006847941783425654, "loss": 1.085, "step": 2000 }, { "epoch": 0.23, "learning_rate": 0.0006840338872596937, "loss": 1.1224, "step": 2100 }, { "epoch": 0.24, "learning_rate": 0.000683273596176822, "loss": 1.1052, "step": 2200 }, { "epoch": 0.25, "learning_rate": 0.0006825133050939503, "loss": 1.0949, "step": 2300 }, { "epoch": 0.26, "learning_rate": 0.0006817530140110785, "loss": 1.0888, "step": 2400 }, { "epoch": 0.27, "learning_rate": 0.0006809927229282067, "loss": 1.0424, "step": 2500 }, { "epoch": 0.28, "learning_rate": 0.0006802324318453351, "loss": 1.0191, "step": 2600 }, { "epoch": 0.29, "learning_rate": 0.0006794721407624634, "loss": 1.1374, "step": 2700 }, { "epoch": 0.3, "learning_rate": 0.0006787118496795916, "loss": 1.0963, "step": 2800 }, { "epoch": 0.31, "learning_rate": 0.0006779515585967199, "loss": 1.1217, "step": 2900 }, { "epoch": 0.33, "learning_rate": 0.0006771912675138482, "loss": 1.1168, "step": 3000 }, { "epoch": 0.34, "learning_rate": 0.0006764309764309764, "loss": 1.0919, "step": 3100 }, { "epoch": 0.35, "learning_rate": 0.0006756706853481047, "loss": 1.0552, "step": 3200 }, { "epoch": 0.36, "learning_rate": 0.000674910394265233, "loss": 1.1408, "step": 3300 }, { "epoch": 0.37, "learning_rate": 0.0006741501031823612, "loss": 1.1443, "step": 3400 }, { "epoch": 0.38, "learning_rate": 0.0006733898120994895, "loss": 1.137, "step": 3500 }, { "epoch": 0.39, "learning_rate": 0.0006726295210166178, "loss": 1.1577, "step": 3600 }, { "epoch": 0.4, "learning_rate": 0.000671869229933746, "loss": 1.1505, "step": 3700 }, { "epoch": 0.41, "learning_rate": 0.0006711089388508743, "loss": 1.1479, "step": 3800 }, { "epoch": 0.42, "learning_rate": 0.0006703486477680026, "loss": 1.0887, "step": 3900 }, { "epoch": 0.43, "learning_rate": 0.0006695883566851309, "loss": 1.1219, "step": 4000 }, { "epoch": 0.45, "learning_rate": 0.0006688280656022592, "loss": 1.1188, "step": 4100 }, { "epoch": 0.46, "learning_rate": 0.0006680677745193874, "loss": 1.0956, "step": 4200 }, { "epoch": 0.47, "learning_rate": 0.0006673074834365157, "loss": 1.1544, "step": 4300 }, { "epoch": 0.48, "learning_rate": 0.0006665471923536439, "loss": 1.1014, "step": 4400 }, { "epoch": 0.49, "learning_rate": 0.0006657869012707722, "loss": 1.0761, "step": 4500 }, { "epoch": 0.5, "learning_rate": 0.0006650266101879005, "loss": 1.1168, "step": 4600 }, { "epoch": 0.51, "learning_rate": 0.0006642663191050288, "loss": 1.0792, "step": 4700 }, { "epoch": 0.52, "learning_rate": 0.000663506028022157, "loss": 1.085, "step": 4800 }, { "epoch": 0.53, "learning_rate": 0.0006627457369392853, "loss": 1.1649, "step": 4900 }, { "epoch": 0.54, "learning_rate": 0.0006619854458564137, "loss": 1.1575, "step": 5000 }, { "epoch": 0.55, "learning_rate": 0.0006612251547735418, "loss": 1.098, "step": 5100 }, { "epoch": 0.56, "learning_rate": 0.0006604648636906701, "loss": 1.1442, "step": 5200 }, { "epoch": 0.58, "learning_rate": 0.0006597045726077984, "loss": 1.1135, "step": 5300 }, { "epoch": 0.59, "learning_rate": 0.0006589442815249267, "loss": 1.1428, "step": 5400 }, { "epoch": 0.6, "learning_rate": 0.000658183990442055, "loss": 1.0998, "step": 5500 }, { "epoch": 0.61, "learning_rate": 0.0006574236993591833, "loss": 1.0847, "step": 5600 }, { "epoch": 0.62, "learning_rate": 0.0006566634082763115, "loss": 1.0957, "step": 5700 }, { "epoch": 0.63, "learning_rate": 0.0006559031171934397, "loss": 1.0979, "step": 5800 }, { "epoch": 0.64, "learning_rate": 0.000655142826110568, "loss": 1.1163, "step": 5900 }, { "epoch": 0.65, "learning_rate": 0.0006543825350276963, "loss": 1.1216, "step": 6000 }, { "epoch": 0.66, "learning_rate": 0.0006536222439448246, "loss": 1.0892, "step": 6100 }, { "epoch": 0.67, "learning_rate": 0.0006528619528619529, "loss": 1.1051, "step": 6200 }, { "epoch": 0.68, "learning_rate": 0.0006521016617790811, "loss": 1.1076, "step": 6300 }, { "epoch": 0.7, "learning_rate": 0.0006513413706962095, "loss": 1.1235, "step": 6400 }, { "epoch": 0.71, "learning_rate": 0.0006505810796133376, "loss": 1.0842, "step": 6500 }, { "epoch": 0.72, "learning_rate": 0.0006498207885304659, "loss": 1.1257, "step": 6600 }, { "epoch": 0.73, "learning_rate": 0.0006490604974475942, "loss": 1.1014, "step": 6700 }, { "epoch": 0.74, "learning_rate": 0.0006483002063647225, "loss": 1.0675, "step": 6800 }, { "epoch": 0.75, "learning_rate": 0.0006475399152818508, "loss": 1.0937, "step": 6900 }, { "epoch": 0.76, "learning_rate": 0.0006467796241989791, "loss": 1.1009, "step": 7000 }, { "epoch": 0.77, "learning_rate": 0.0006460193331161072, "loss": 1.0831, "step": 7100 }, { "epoch": 0.78, "learning_rate": 0.0006452590420332355, "loss": 1.0571, "step": 7200 }, { "epoch": 0.79, "learning_rate": 0.0006444987509503639, "loss": 1.046, "step": 7300 }, { "epoch": 0.8, "learning_rate": 0.0006437384598674921, "loss": 1.1214, "step": 7400 }, { "epoch": 0.81, "learning_rate": 0.0006429781687846204, "loss": 1.0686, "step": 7500 }, { "epoch": 0.83, "learning_rate": 0.0006422178777017487, "loss": 1.1346, "step": 7600 }, { "epoch": 0.84, "learning_rate": 0.0006414575866188769, "loss": 1.16, "step": 7700 }, { "epoch": 0.85, "learning_rate": 0.0006406972955360052, "loss": 1.1717, "step": 7800 }, { "epoch": 0.86, "learning_rate": 0.0006399370044531335, "loss": 1.1601, "step": 7900 }, { "epoch": 0.87, "learning_rate": 0.0006391767133702617, "loss": 1.1241, "step": 8000 }, { "epoch": 0.88, "learning_rate": 0.00063841642228739, "loss": 1.0692, "step": 8100 }, { "epoch": 0.89, "learning_rate": 0.0006376561312045183, "loss": 1.0775, "step": 8200 }, { "epoch": 0.9, "learning_rate": 0.0006368958401216466, "loss": 1.126, "step": 8300 }, { "epoch": 0.91, "learning_rate": 0.0006361355490387749, "loss": 1.0801, "step": 8400 }, { "epoch": 0.92, "learning_rate": 0.0006353752579559031, "loss": 1.1176, "step": 8500 }, { "epoch": 0.93, "learning_rate": 0.0006346149668730313, "loss": 1.1101, "step": 8600 }, { "epoch": 0.94, "learning_rate": 0.0006338546757901597, "loss": 1.0881, "step": 8700 }, { "epoch": 0.96, "learning_rate": 0.0006330943847072879, "loss": 1.1009, "step": 8800 }, { "epoch": 0.97, "learning_rate": 0.0006323340936244162, "loss": 1.1158, "step": 8900 }, { "epoch": 0.98, "learning_rate": 0.0006315738025415445, "loss": 1.0991, "step": 9000 }, { "epoch": 0.99, "learning_rate": 0.0006308135114586728, "loss": 1.1478, "step": 9100 }, { "epoch": 1.0, "learning_rate": 0.000630053220375801, "loss": 1.1408, "step": 9200 }, { "epoch": 1.01, "learning_rate": 0.0006292929292929293, "loss": 1.0484, "step": 9300 }, { "epoch": 1.02, "learning_rate": 0.0006285326382100575, "loss": 1.103, "step": 9400 }, { "epoch": 1.03, "learning_rate": 0.0006277723471271858, "loss": 0.9948, "step": 9500 }, { "epoch": 1.04, "learning_rate": 0.0006270120560443141, "loss": 1.0212, "step": 9600 }, { "epoch": 1.05, "learning_rate": 0.0006262517649614424, "loss": 1.1029, "step": 9700 }, { "epoch": 1.06, "learning_rate": 0.0006254914738785707, "loss": 1.064, "step": 9800 }, { "epoch": 1.08, "learning_rate": 0.0006247311827956989, "loss": 1.0066, "step": 9900 }, { "epoch": 1.09, "learning_rate": 0.0006239708917128271, "loss": 1.0117, "step": 10000 }, { "epoch": 1.1, "learning_rate": 0.0006232106006299555, "loss": 1.0196, "step": 10100 }, { "epoch": 1.11, "learning_rate": 0.0006224503095470838, "loss": 1.0576, "step": 10200 }, { "epoch": 1.12, "learning_rate": 0.000621690018464212, "loss": 1.0636, "step": 10300 }, { "epoch": 1.13, "learning_rate": 0.0006209297273813403, "loss": 1.0454, "step": 10400 }, { "epoch": 1.14, "learning_rate": 0.0006201694362984685, "loss": 1.0798, "step": 10500 }, { "epoch": 1.15, "learning_rate": 0.0006194091452155968, "loss": 1.007, "step": 10600 }, { "epoch": 1.16, "learning_rate": 0.0006186488541327251, "loss": 1.0612, "step": 10700 }, { "epoch": 1.17, "learning_rate": 0.0006178885630498534, "loss": 1.0791, "step": 10800 }, { "epoch": 1.18, "learning_rate": 0.0006171282719669816, "loss": 1.0961, "step": 10900 }, { "epoch": 1.19, "learning_rate": 0.0006163679808841099, "loss": 1.0745, "step": 11000 }, { "epoch": 1.21, "learning_rate": 0.0006156076898012382, "loss": 0.9832, "step": 11100 }, { "epoch": 1.22, "learning_rate": 0.0006148473987183664, "loss": 1.0083, "step": 11200 }, { "epoch": 1.23, "learning_rate": 0.0006140871076354947, "loss": 1.0772, "step": 11300 }, { "epoch": 1.24, "learning_rate": 0.000613326816552623, "loss": 1.0673, "step": 11400 }, { "epoch": 1.25, "learning_rate": 0.0006125665254697513, "loss": 1.1005, "step": 11500 }, { "epoch": 1.26, "learning_rate": 0.0006118062343868796, "loss": 1.0219, "step": 11600 }, { "epoch": 1.27, "learning_rate": 0.0006110459433040078, "loss": 1.0878, "step": 11700 }, { "epoch": 1.28, "learning_rate": 0.0006102856522211361, "loss": 1.047, "step": 11800 }, { "epoch": 1.29, "learning_rate": 0.0006095253611382643, "loss": 1.0663, "step": 11900 }, { "epoch": 1.3, "learning_rate": 0.0006087650700553926, "loss": 1.0473, "step": 12000 }, { "epoch": 1.31, "learning_rate": 0.0006080047789725209, "loss": 1.0146, "step": 12100 }, { "epoch": 1.33, "learning_rate": 0.0006072444878896492, "loss": 1.0381, "step": 12200 }, { "epoch": 1.34, "learning_rate": 0.0006064841968067774, "loss": 1.0991, "step": 12300 }, { "epoch": 1.35, "learning_rate": 0.0006057239057239057, "loss": 1.0377, "step": 12400 }, { "epoch": 1.36, "learning_rate": 0.0006049636146410341, "loss": 1.0478, "step": 12500 }, { "epoch": 1.37, "learning_rate": 0.0006042033235581622, "loss": 1.0773, "step": 12600 }, { "epoch": 1.38, "learning_rate": 0.0006034430324752905, "loss": 1.0496, "step": 12700 }, { "epoch": 1.39, "learning_rate": 0.0006026827413924188, "loss": 1.0943, "step": 12800 }, { "epoch": 1.4, "learning_rate": 0.0006019224503095471, "loss": 1.0303, "step": 12900 }, { "epoch": 1.41, "learning_rate": 0.0006011621592266754, "loss": 0.9987, "step": 13000 }, { "epoch": 1.42, "learning_rate": 0.0006004018681438037, "loss": 1.0489, "step": 13100 }, { "epoch": 1.43, "learning_rate": 0.0005996415770609318, "loss": 1.111, "step": 13200 }, { "epoch": 1.44, "learning_rate": 0.0005988812859780601, "loss": 1.0514, "step": 13300 }, { "epoch": 1.46, "learning_rate": 0.0005981209948951884, "loss": 1.0931, "step": 13400 }, { "epoch": 1.47, "learning_rate": 0.0005973607038123167, "loss": 1.0225, "step": 13500 }, { "epoch": 1.48, "learning_rate": 0.000596600412729445, "loss": 1.0295, "step": 13600 }, { "epoch": 1.49, "learning_rate": 0.0005958401216465733, "loss": 1.1068, "step": 13700 }, { "epoch": 1.5, "learning_rate": 0.0005950798305637015, "loss": 1.0739, "step": 13800 }, { "epoch": 1.51, "learning_rate": 0.0005943195394808299, "loss": 1.0453, "step": 13900 }, { "epoch": 1.52, "learning_rate": 0.000593559248397958, "loss": 1.0392, "step": 14000 }, { "epoch": 1.53, "learning_rate": 0.0005927989573150863, "loss": 1.0482, "step": 14100 }, { "epoch": 1.54, "learning_rate": 0.0005920386662322146, "loss": 1.0337, "step": 14200 }, { "epoch": 1.55, "learning_rate": 0.0005912783751493429, "loss": 1.0415, "step": 14300 }, { "epoch": 1.56, "learning_rate": 0.0005905180840664712, "loss": 1.0534, "step": 14400 }, { "epoch": 1.57, "learning_rate": 0.0005897577929835995, "loss": 1.028, "step": 14500 }, { "epoch": 1.59, "learning_rate": 0.0005889975019007276, "loss": 0.9978, "step": 14600 }, { "epoch": 1.6, "learning_rate": 0.0005882372108178559, "loss": 1.047, "step": 14700 }, { "epoch": 1.61, "learning_rate": 0.0005874769197349843, "loss": 1.0501, "step": 14800 }, { "epoch": 1.62, "learning_rate": 0.0005867166286521125, "loss": 1.0165, "step": 14900 }, { "epoch": 1.63, "learning_rate": 0.0005859563375692408, "loss": 1.0867, "step": 15000 }, { "epoch": 1.64, "learning_rate": 0.0005851960464863691, "loss": 1.0614, "step": 15100 }, { "epoch": 1.65, "learning_rate": 0.0005844357554034973, "loss": 1.0512, "step": 15200 }, { "epoch": 1.66, "learning_rate": 0.0005836754643206256, "loss": 0.9962, "step": 15300 }, { "epoch": 1.67, "learning_rate": 0.0005829151732377539, "loss": 1.0325, "step": 15400 }, { "epoch": 1.68, "learning_rate": 0.0005821548821548821, "loss": 1.0313, "step": 15500 }, { "epoch": 1.69, "learning_rate": 0.0005813945910720104, "loss": 1.0441, "step": 15600 }, { "epoch": 1.71, "learning_rate": 0.0005806342999891387, "loss": 1.0705, "step": 15700 }, { "epoch": 1.72, "learning_rate": 0.000579874008906267, "loss": 1.0209, "step": 15800 }, { "epoch": 1.73, "learning_rate": 0.0005791137178233953, "loss": 1.0627, "step": 15900 }, { "epoch": 1.74, "learning_rate": 0.0005783534267405235, "loss": 1.076, "step": 16000 } ], "max_steps": 92070, "num_train_epochs": 10, "total_flos": 3.281082781355213e+16, "trial_name": null, "trial_params": null }