{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.399203657277688, "eval_steps": 1000000, "global_step": 292842, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 5.000000000000001e-07, "loss": 9.9527, "step": 500 }, { "epoch": 0.01, "learning_rate": 1.0000000000000002e-06, "loss": 9.1966, "step": 1000 }, { "epoch": 0.01, "learning_rate": 1.5e-06, "loss": 8.7737, "step": 1500 }, { "epoch": 0.02, "learning_rate": 2.0000000000000003e-06, "loss": 8.3012, "step": 2000 }, { "epoch": 0.02, "learning_rate": 2.5e-06, "loss": 7.8046, "step": 2500 }, { "epoch": 0.02, "learning_rate": 3e-06, "loss": 7.4149, "step": 3000 }, { "epoch": 0.03, "learning_rate": 3.5e-06, "loss": 7.1666, "step": 3500 }, { "epoch": 0.03, "learning_rate": 4.000000000000001e-06, "loss": 7.0257, "step": 4000 }, { "epoch": 0.04, "learning_rate": 4.5e-06, "loss": 6.9423, "step": 4500 }, { "epoch": 0.04, "learning_rate": 5e-06, "loss": 6.8754, "step": 5000 }, { "epoch": 0.05, "learning_rate": 5.500000000000001e-06, "loss": 6.8221, "step": 5500 }, { "epoch": 0.05, "learning_rate": 6e-06, "loss": 6.775, "step": 6000 }, { "epoch": 0.05, "learning_rate": 6.5000000000000004e-06, "loss": 6.7376, "step": 6500 }, { "epoch": 0.06, "learning_rate": 7e-06, "loss": 6.7071, "step": 7000 }, { "epoch": 0.06, "learning_rate": 7.500000000000001e-06, "loss": 6.6743, "step": 7500 }, { "epoch": 0.07, "learning_rate": 8.000000000000001e-06, "loss": 6.639, "step": 8000 }, { "epoch": 0.07, "learning_rate": 8.5e-06, "loss": 6.6047, "step": 8500 }, { "epoch": 0.07, "learning_rate": 9e-06, "loss": 6.5799, "step": 9000 }, { "epoch": 0.08, "learning_rate": 9.5e-06, "loss": 6.5529, "step": 9500 }, { "epoch": 0.08, "learning_rate": 1e-05, "loss": 6.5341, "step": 10000 }, { "epoch": 0.09, "learning_rate": 9.999590022794733e-06, "loss": 6.5078, "step": 10500 }, { "epoch": 0.09, "learning_rate": 9.999180045589466e-06, "loss": 6.4779, "step": 11000 }, { "epoch": 0.09, "learning_rate": 9.998770068384198e-06, "loss": 6.4536, "step": 11500 }, { "epoch": 0.1, "learning_rate": 9.99836009117893e-06, "loss": 6.443, "step": 12000 }, { "epoch": 0.1, "learning_rate": 9.997950113973663e-06, "loss": 6.42, "step": 12500 }, { "epoch": 0.11, "learning_rate": 9.997540136768397e-06, "loss": 6.4115, "step": 13000 }, { "epoch": 0.11, "learning_rate": 9.997130159563128e-06, "loss": 6.3957, "step": 13500 }, { "epoch": 0.11, "learning_rate": 9.996720182357862e-06, "loss": 6.386, "step": 14000 }, { "epoch": 0.12, "learning_rate": 9.996310205152595e-06, "loss": 6.3674, "step": 14500 }, { "epoch": 0.12, "learning_rate": 9.995900227947327e-06, "loss": 6.3595, "step": 15000 }, { "epoch": 0.13, "learning_rate": 9.99549025074206e-06, "loss": 6.3477, "step": 15500 }, { "epoch": 0.13, "learning_rate": 9.995080273536792e-06, "loss": 6.3465, "step": 16000 }, { "epoch": 0.14, "learning_rate": 9.994670296331524e-06, "loss": 6.3256, "step": 16500 }, { "epoch": 0.14, "learning_rate": 9.994260319126257e-06, "loss": 6.3203, "step": 17000 }, { "epoch": 0.14, "learning_rate": 9.99385034192099e-06, "loss": 6.3142, "step": 17500 }, { "epoch": 0.15, "learning_rate": 9.993440364715724e-06, "loss": 6.2985, "step": 18000 }, { "epoch": 0.15, "learning_rate": 9.993030387510454e-06, "loss": 6.2923, "step": 18500 }, { "epoch": 0.16, "learning_rate": 9.992620410305188e-06, "loss": 6.2835, "step": 19000 }, { "epoch": 0.16, "learning_rate": 9.992210433099921e-06, "loss": 6.2804, "step": 19500 }, { "epoch": 0.16, "learning_rate": 9.991800455894653e-06, "loss": 6.2699, "step": 20000 }, { "epoch": 0.17, "learning_rate": 9.991390478689386e-06, "loss": 6.2609, "step": 20500 }, { "epoch": 0.17, "learning_rate": 9.990980501484118e-06, "loss": 6.2614, "step": 21000 }, { "epoch": 0.18, "learning_rate": 9.99057052427885e-06, "loss": 6.2472, "step": 21500 }, { "epoch": 0.18, "learning_rate": 9.990160547073583e-06, "loss": 6.2437, "step": 22000 }, { "epoch": 0.18, "learning_rate": 9.989750569868316e-06, "loss": 6.2405, "step": 22500 }, { "epoch": 0.19, "learning_rate": 9.989340592663048e-06, "loss": 6.2412, "step": 23000 }, { "epoch": 0.19, "learning_rate": 9.98893061545778e-06, "loss": 6.235, "step": 23500 }, { "epoch": 0.2, "learning_rate": 9.988520638252513e-06, "loss": 6.2297, "step": 24000 }, { "epoch": 0.2, "learning_rate": 9.988110661047247e-06, "loss": 6.2182, "step": 24500 }, { "epoch": 0.2, "learning_rate": 9.987700683841978e-06, "loss": 6.2185, "step": 25000 }, { "epoch": 0.21, "learning_rate": 9.987290706636712e-06, "loss": 6.2121, "step": 25500 }, { "epoch": 0.21, "learning_rate": 9.986880729431445e-06, "loss": 6.2154, "step": 26000 }, { "epoch": 0.22, "learning_rate": 9.986470752226177e-06, "loss": 6.2014, "step": 26500 }, { "epoch": 0.22, "learning_rate": 9.98606077502091e-06, "loss": 6.1937, "step": 27000 }, { "epoch": 0.23, "learning_rate": 9.985650797815642e-06, "loss": 6.1935, "step": 27500 }, { "epoch": 0.23, "learning_rate": 9.985240820610374e-06, "loss": 6.1982, "step": 28000 }, { "epoch": 0.23, "learning_rate": 9.984830843405109e-06, "loss": 6.1961, "step": 28500 }, { "epoch": 0.24, "learning_rate": 9.98442086619984e-06, "loss": 6.184, "step": 29000 }, { "epoch": 0.24, "learning_rate": 9.984010888994574e-06, "loss": 6.1825, "step": 29500 }, { "epoch": 0.25, "learning_rate": 9.983600911789304e-06, "loss": 6.176, "step": 30000 }, { "epoch": 0.25, "learning_rate": 9.983190934584038e-06, "loss": 6.1768, "step": 30500 }, { "epoch": 0.25, "learning_rate": 9.982780957378771e-06, "loss": 6.1692, "step": 31000 }, { "epoch": 0.26, "learning_rate": 9.982370980173503e-06, "loss": 6.1722, "step": 31500 }, { "epoch": 0.26, "learning_rate": 9.981961002968236e-06, "loss": 6.1705, "step": 32000 }, { "epoch": 0.27, "learning_rate": 9.981551025762968e-06, "loss": 6.1671, "step": 32500 }, { "epoch": 0.27, "learning_rate": 9.9811410485577e-06, "loss": 6.1591, "step": 33000 }, { "epoch": 0.27, "learning_rate": 9.980731071352435e-06, "loss": 6.1511, "step": 33500 }, { "epoch": 0.28, "learning_rate": 9.980321094147166e-06, "loss": 6.1535, "step": 34000 }, { "epoch": 0.28, "learning_rate": 9.979911116941898e-06, "loss": 6.154, "step": 34500 }, { "epoch": 0.29, "learning_rate": 9.979501139736632e-06, "loss": 6.1482, "step": 35000 }, { "epoch": 0.29, "learning_rate": 9.979091162531363e-06, "loss": 6.1563, "step": 35500 }, { "epoch": 0.29, "learning_rate": 9.978681185326097e-06, "loss": 6.1401, "step": 36000 }, { "epoch": 0.3, "learning_rate": 9.97827120812083e-06, "loss": 6.1381, "step": 36500 }, { "epoch": 0.3, "learning_rate": 9.977861230915562e-06, "loss": 6.1378, "step": 37000 }, { "epoch": 0.31, "learning_rate": 9.977451253710295e-06, "loss": 6.14, "step": 37500 }, { "epoch": 0.31, "learning_rate": 9.977041276505027e-06, "loss": 6.1273, "step": 38000 }, { "epoch": 0.32, "learning_rate": 9.97663129929976e-06, "loss": 6.1371, "step": 38500 }, { "epoch": 0.32, "learning_rate": 9.976221322094492e-06, "loss": 6.1282, "step": 39000 }, { "epoch": 0.32, "learning_rate": 9.975811344889224e-06, "loss": 6.1232, "step": 39500 }, { "epoch": 0.33, "learning_rate": 9.975401367683959e-06, "loss": 6.1257, "step": 40000 }, { "epoch": 0.33, "learning_rate": 9.97499139047869e-06, "loss": 6.1229, "step": 40500 }, { "epoch": 0.34, "learning_rate": 9.974581413273423e-06, "loss": 6.123, "step": 41000 }, { "epoch": 0.34, "learning_rate": 9.974171436068156e-06, "loss": 6.122, "step": 41500 }, { "epoch": 0.34, "learning_rate": 9.973761458862888e-06, "loss": 6.1213, "step": 42000 }, { "epoch": 0.35, "learning_rate": 9.973351481657621e-06, "loss": 6.1202, "step": 42500 }, { "epoch": 0.35, "learning_rate": 9.972941504452353e-06, "loss": 6.1141, "step": 43000 }, { "epoch": 0.36, "learning_rate": 9.972531527247086e-06, "loss": 6.1135, "step": 43500 }, { "epoch": 0.36, "learning_rate": 9.972121550041818e-06, "loss": 6.1085, "step": 44000 }, { "epoch": 0.36, "learning_rate": 9.97171157283655e-06, "loss": 6.1094, "step": 44500 }, { "epoch": 0.37, "learning_rate": 9.971301595631285e-06, "loss": 6.1085, "step": 45000 }, { "epoch": 0.37, "learning_rate": 9.970891618426016e-06, "loss": 6.102, "step": 45500 }, { "epoch": 0.38, "learning_rate": 9.97048164122075e-06, "loss": 6.0967, "step": 46000 }, { "epoch": 0.38, "learning_rate": 9.970071664015482e-06, "loss": 6.0975, "step": 46500 }, { "epoch": 0.39, "learning_rate": 9.969661686810213e-06, "loss": 6.0942, "step": 47000 }, { "epoch": 0.39, "learning_rate": 9.969251709604947e-06, "loss": 6.1022, "step": 47500 }, { "epoch": 0.39, "learning_rate": 9.96884173239968e-06, "loss": 6.0955, "step": 48000 }, { "epoch": 0.4, "learning_rate": 9.968431755194412e-06, "loss": 6.0882, "step": 48500 }, { "epoch": 0.4, "learning_rate": 9.968021777989145e-06, "loss": 6.0863, "step": 49000 }, { "epoch": 0.41, "learning_rate": 9.967611800783877e-06, "loss": 6.0955, "step": 49500 }, { "epoch": 0.41, "learning_rate": 9.96720182357861e-06, "loss": 6.0885, "step": 50000 }, { "epoch": 0.41, "learning_rate": 9.966791846373342e-06, "loss": 6.0898, "step": 50500 }, { "epoch": 0.42, "learning_rate": 9.966381869168074e-06, "loss": 6.0886, "step": 51000 }, { "epoch": 0.42, "learning_rate": 9.965971891962809e-06, "loss": 6.0811, "step": 51500 }, { "epoch": 0.43, "learning_rate": 9.96556191475754e-06, "loss": 6.0758, "step": 52000 }, { "epoch": 0.43, "learning_rate": 9.965151937552273e-06, "loss": 6.0782, "step": 52500 }, { "epoch": 0.43, "learning_rate": 9.964741960347006e-06, "loss": 6.0786, "step": 53000 }, { "epoch": 0.44, "learning_rate": 9.964331983141738e-06, "loss": 6.0729, "step": 53500 }, { "epoch": 0.44, "learning_rate": 9.96392200593647e-06, "loss": 6.0796, "step": 54000 }, { "epoch": 0.45, "learning_rate": 9.963512028731203e-06, "loss": 6.0707, "step": 54500 }, { "epoch": 0.45, "learning_rate": 9.963102051525936e-06, "loss": 6.0731, "step": 55000 }, { "epoch": 0.45, "learning_rate": 9.962692074320668e-06, "loss": 6.0702, "step": 55500 }, { "epoch": 0.46, "learning_rate": 9.9622820971154e-06, "loss": 6.073, "step": 56000 }, { "epoch": 0.46, "learning_rate": 9.961872119910135e-06, "loss": 6.0695, "step": 56500 }, { "epoch": 0.47, "learning_rate": 9.961462142704866e-06, "loss": 6.0657, "step": 57000 }, { "epoch": 0.47, "learning_rate": 9.9610521654996e-06, "loss": 6.0668, "step": 57500 }, { "epoch": 0.48, "learning_rate": 9.960642188294332e-06, "loss": 6.0575, "step": 58000 }, { "epoch": 0.48, "learning_rate": 9.960232211089065e-06, "loss": 6.0645, "step": 58500 }, { "epoch": 0.48, "learning_rate": 9.959822233883797e-06, "loss": 6.0605, "step": 59000 }, { "epoch": 0.49, "learning_rate": 9.95941225667853e-06, "loss": 6.0551, "step": 59500 }, { "epoch": 0.49, "learning_rate": 9.959002279473262e-06, "loss": 6.0569, "step": 60000 }, { "epoch": 0.5, "learning_rate": 9.958592302267995e-06, "loss": 6.0596, "step": 60500 }, { "epoch": 0.5, "learning_rate": 9.958182325062727e-06, "loss": 6.0578, "step": 61000 }, { "epoch": 0.5, "learning_rate": 9.95777234785746e-06, "loss": 6.0566, "step": 61500 }, { "epoch": 0.51, "learning_rate": 9.957362370652192e-06, "loss": 6.0571, "step": 62000 }, { "epoch": 0.51, "learning_rate": 9.956952393446924e-06, "loss": 6.0445, "step": 62500 }, { "epoch": 0.52, "learning_rate": 9.956542416241659e-06, "loss": 6.0514, "step": 63000 }, { "epoch": 0.52, "learning_rate": 9.95613243903639e-06, "loss": 6.0461, "step": 63500 }, { "epoch": 0.52, "learning_rate": 9.955722461831123e-06, "loss": 6.0412, "step": 64000 }, { "epoch": 0.53, "learning_rate": 9.955312484625856e-06, "loss": 6.0442, "step": 64500 }, { "epoch": 0.53, "learning_rate": 9.954902507420588e-06, "loss": 6.0488, "step": 65000 }, { "epoch": 0.54, "learning_rate": 9.95449253021532e-06, "loss": 6.0514, "step": 65500 }, { "epoch": 0.54, "learning_rate": 9.954082553010053e-06, "loss": 6.0514, "step": 66000 }, { "epoch": 0.54, "learning_rate": 9.953672575804786e-06, "loss": 6.0415, "step": 66500 }, { "epoch": 0.55, "learning_rate": 9.95326259859952e-06, "loss": 6.0467, "step": 67000 }, { "epoch": 0.55, "learning_rate": 9.95285262139425e-06, "loss": 6.0417, "step": 67500 }, { "epoch": 0.56, "learning_rate": 9.952442644188985e-06, "loss": 6.0354, "step": 68000 }, { "epoch": 0.56, "learning_rate": 9.952032666983716e-06, "loss": 6.0354, "step": 68500 }, { "epoch": 0.57, "learning_rate": 9.95162268977845e-06, "loss": 6.0355, "step": 69000 }, { "epoch": 0.57, "learning_rate": 9.951212712573182e-06, "loss": 6.0326, "step": 69500 }, { "epoch": 0.57, "learning_rate": 9.950802735367915e-06, "loss": 6.0346, "step": 70000 }, { "epoch": 0.58, "learning_rate": 9.950392758162647e-06, "loss": 6.0407, "step": 70500 }, { "epoch": 0.58, "learning_rate": 9.94998278095738e-06, "loss": 6.0378, "step": 71000 }, { "epoch": 0.59, "learning_rate": 9.949572803752112e-06, "loss": 6.0297, "step": 71500 }, { "epoch": 0.59, "learning_rate": 9.949162826546844e-06, "loss": 6.0389, "step": 72000 }, { "epoch": 0.59, "learning_rate": 9.948752849341577e-06, "loss": 6.0293, "step": 72500 }, { "epoch": 0.6, "learning_rate": 9.94834287213631e-06, "loss": 6.0345, "step": 73000 }, { "epoch": 0.6, "learning_rate": 9.947932894931044e-06, "loss": 6.0282, "step": 73500 }, { "epoch": 0.61, "learning_rate": 9.947522917725774e-06, "loss": 6.0257, "step": 74000 }, { "epoch": 0.61, "learning_rate": 9.947112940520508e-06, "loss": 6.0222, "step": 74500 }, { "epoch": 0.61, "learning_rate": 9.946702963315241e-06, "loss": 6.0267, "step": 75000 }, { "epoch": 0.62, "learning_rate": 9.946292986109973e-06, "loss": 6.027, "step": 75500 }, { "epoch": 0.62, "learning_rate": 9.945883008904706e-06, "loss": 6.0264, "step": 76000 }, { "epoch": 0.63, "learning_rate": 9.945473031699438e-06, "loss": 6.0267, "step": 76500 }, { "epoch": 0.63, "learning_rate": 9.94506305449417e-06, "loss": 6.0198, "step": 77000 }, { "epoch": 0.63, "learning_rate": 9.944653077288903e-06, "loss": 6.0228, "step": 77500 }, { "epoch": 0.64, "learning_rate": 9.944243100083636e-06, "loss": 6.0162, "step": 78000 }, { "epoch": 0.64, "learning_rate": 9.94383312287837e-06, "loss": 6.0182, "step": 78500 }, { "epoch": 0.65, "learning_rate": 9.9434231456731e-06, "loss": 6.0169, "step": 79000 }, { "epoch": 0.65, "learning_rate": 9.943013168467835e-06, "loss": 6.0175, "step": 79500 }, { "epoch": 0.66, "learning_rate": 9.942603191262567e-06, "loss": 6.0175, "step": 80000 }, { "epoch": 0.66, "learning_rate": 9.9421932140573e-06, "loss": 6.0165, "step": 80500 }, { "epoch": 0.66, "learning_rate": 9.941783236852032e-06, "loss": 6.0144, "step": 81000 }, { "epoch": 0.67, "learning_rate": 9.941373259646765e-06, "loss": 6.0107, "step": 81500 }, { "epoch": 0.67, "learning_rate": 9.940963282441497e-06, "loss": 6.0183, "step": 82000 }, { "epoch": 0.68, "learning_rate": 9.94055330523623e-06, "loss": 6.0146, "step": 82500 }, { "epoch": 0.68, "learning_rate": 9.940143328030962e-06, "loss": 6.0049, "step": 83000 }, { "epoch": 0.68, "learning_rate": 9.939733350825694e-06, "loss": 6.009, "step": 83500 }, { "epoch": 0.69, "learning_rate": 9.939323373620427e-06, "loss": 6.009, "step": 84000 }, { "epoch": 0.69, "learning_rate": 9.93891339641516e-06, "loss": 6.0006, "step": 84500 }, { "epoch": 0.7, "learning_rate": 9.938503419209894e-06, "loss": 6.0086, "step": 85000 }, { "epoch": 0.7, "learning_rate": 9.938093442004624e-06, "loss": 6.0052, "step": 85500 }, { "epoch": 0.7, "learning_rate": 9.937683464799358e-06, "loss": 6.0051, "step": 86000 }, { "epoch": 0.71, "learning_rate": 9.937273487594091e-06, "loss": 5.9998, "step": 86500 }, { "epoch": 0.71, "learning_rate": 9.936863510388823e-06, "loss": 6.0042, "step": 87000 }, { "epoch": 0.72, "learning_rate": 9.936453533183556e-06, "loss": 6.0022, "step": 87500 }, { "epoch": 0.72, "learning_rate": 9.936043555978288e-06, "loss": 5.9982, "step": 88000 }, { "epoch": 0.73, "learning_rate": 9.93563357877302e-06, "loss": 6.001, "step": 88500 }, { "epoch": 0.73, "learning_rate": 9.935223601567753e-06, "loss": 6.006, "step": 89000 }, { "epoch": 0.73, "learning_rate": 9.934813624362486e-06, "loss": 6.0025, "step": 89500 }, { "epoch": 0.74, "learning_rate": 9.93440364715722e-06, "loss": 6.0006, "step": 90000 }, { "epoch": 0.74, "learning_rate": 9.93399366995195e-06, "loss": 6.0028, "step": 90500 }, { "epoch": 0.75, "learning_rate": 9.933583692746685e-06, "loss": 5.9939, "step": 91000 }, { "epoch": 0.75, "learning_rate": 9.933173715541417e-06, "loss": 5.996, "step": 91500 }, { "epoch": 0.75, "learning_rate": 9.93276373833615e-06, "loss": 5.9939, "step": 92000 }, { "epoch": 0.76, "learning_rate": 9.932353761130882e-06, "loss": 5.9902, "step": 92500 }, { "epoch": 0.76, "learning_rate": 9.931943783925615e-06, "loss": 5.9998, "step": 93000 }, { "epoch": 0.77, "learning_rate": 9.931533806720347e-06, "loss": 5.9962, "step": 93500 }, { "epoch": 0.77, "learning_rate": 9.93112382951508e-06, "loss": 5.99, "step": 94000 }, { "epoch": 0.77, "learning_rate": 9.930713852309812e-06, "loss": 5.9908, "step": 94500 }, { "epoch": 0.78, "learning_rate": 9.930303875104546e-06, "loss": 5.9858, "step": 95000 }, { "epoch": 0.78, "learning_rate": 9.929893897899277e-06, "loss": 5.9929, "step": 95500 }, { "epoch": 0.79, "learning_rate": 9.92948392069401e-06, "loss": 5.9884, "step": 96000 }, { "epoch": 0.79, "learning_rate": 9.929073943488743e-06, "loss": 5.9867, "step": 96500 }, { "epoch": 0.79, "learning_rate": 9.928663966283474e-06, "loss": 5.9906, "step": 97000 }, { "epoch": 0.8, "learning_rate": 9.928253989078208e-06, "loss": 5.9853, "step": 97500 }, { "epoch": 0.8, "learning_rate": 9.927844011872941e-06, "loss": 5.9872, "step": 98000 }, { "epoch": 0.81, "learning_rate": 9.927434034667673e-06, "loss": 5.9921, "step": 98500 }, { "epoch": 0.81, "learning_rate": 9.927024057462406e-06, "loss": 5.9891, "step": 99000 }, { "epoch": 0.82, "learning_rate": 9.926614080257138e-06, "loss": 5.9891, "step": 99500 }, { "epoch": 0.82, "learning_rate": 9.92620410305187e-06, "loss": 5.9899, "step": 100000 }, { "epoch": 0.82, "learning_rate": 9.925794125846603e-06, "loss": 5.9839, "step": 100500 }, { "epoch": 0.83, "learning_rate": 9.925384148641336e-06, "loss": 5.9795, "step": 101000 }, { "epoch": 0.83, "learning_rate": 9.92497417143607e-06, "loss": 5.9819, "step": 101500 }, { "epoch": 0.84, "learning_rate": 9.9245641942308e-06, "loss": 5.9855, "step": 102000 }, { "epoch": 0.84, "learning_rate": 9.924154217025535e-06, "loss": 5.9844, "step": 102500 }, { "epoch": 0.84, "learning_rate": 9.923744239820267e-06, "loss": 5.9821, "step": 103000 }, { "epoch": 0.85, "learning_rate": 9.923334262615e-06, "loss": 5.9788, "step": 103500 }, { "epoch": 0.85, "learning_rate": 9.922924285409732e-06, "loss": 5.9848, "step": 104000 }, { "epoch": 0.86, "learning_rate": 9.922514308204465e-06, "loss": 5.9758, "step": 104500 }, { "epoch": 0.86, "learning_rate": 9.922104330999197e-06, "loss": 5.9741, "step": 105000 }, { "epoch": 0.86, "learning_rate": 9.921694353793931e-06, "loss": 5.9756, "step": 105500 }, { "epoch": 0.87, "learning_rate": 9.921284376588662e-06, "loss": 5.9779, "step": 106000 }, { "epoch": 0.87, "learning_rate": 9.920874399383396e-06, "loss": 5.9814, "step": 106500 }, { "epoch": 0.88, "learning_rate": 9.920464422178127e-06, "loss": 5.9843, "step": 107000 }, { "epoch": 0.88, "learning_rate": 9.920054444972861e-06, "loss": 5.9837, "step": 107500 }, { "epoch": 0.88, "learning_rate": 9.919644467767593e-06, "loss": 5.9723, "step": 108000 }, { "epoch": 0.89, "learning_rate": 9.919234490562324e-06, "loss": 5.9738, "step": 108500 }, { "epoch": 0.89, "learning_rate": 9.918824513357058e-06, "loss": 5.9826, "step": 109000 }, { "epoch": 0.9, "learning_rate": 9.91841453615179e-06, "loss": 5.9774, "step": 109500 }, { "epoch": 0.9, "learning_rate": 9.918004558946523e-06, "loss": 5.9758, "step": 110000 }, { "epoch": 0.91, "learning_rate": 9.917594581741256e-06, "loss": 5.9742, "step": 110500 }, { "epoch": 0.91, "learning_rate": 9.917184604535988e-06, "loss": 5.9738, "step": 111000 }, { "epoch": 0.91, "learning_rate": 9.91677462733072e-06, "loss": 5.975, "step": 111500 }, { "epoch": 0.92, "learning_rate": 9.916364650125455e-06, "loss": 5.9754, "step": 112000 }, { "epoch": 0.92, "learning_rate": 9.915954672920186e-06, "loss": 5.9696, "step": 112500 }, { "epoch": 0.93, "learning_rate": 9.91554469571492e-06, "loss": 5.9688, "step": 113000 }, { "epoch": 0.93, "learning_rate": 9.915134718509652e-06, "loss": 5.9689, "step": 113500 }, { "epoch": 0.93, "learning_rate": 9.914724741304385e-06, "loss": 5.974, "step": 114000 }, { "epoch": 0.94, "learning_rate": 9.914314764099117e-06, "loss": 5.9604, "step": 114500 }, { "epoch": 0.94, "learning_rate": 9.91390478689385e-06, "loss": 5.9666, "step": 115000 }, { "epoch": 0.95, "learning_rate": 9.913494809688582e-06, "loss": 5.9663, "step": 115500 }, { "epoch": 0.95, "learning_rate": 9.913084832483315e-06, "loss": 5.9696, "step": 116000 }, { "epoch": 0.95, "learning_rate": 9.912674855278047e-06, "loss": 5.9652, "step": 116500 }, { "epoch": 0.96, "learning_rate": 9.912264878072781e-06, "loss": 5.9625, "step": 117000 }, { "epoch": 0.96, "learning_rate": 9.911854900867512e-06, "loss": 5.9565, "step": 117500 }, { "epoch": 0.97, "learning_rate": 9.911444923662246e-06, "loss": 5.9561, "step": 118000 }, { "epoch": 0.97, "learning_rate": 9.911034946456978e-06, "loss": 5.95, "step": 118500 }, { "epoch": 0.97, "learning_rate": 9.910624969251711e-06, "loss": 5.9468, "step": 119000 }, { "epoch": 0.98, "learning_rate": 9.910214992046443e-06, "loss": 5.9412, "step": 119500 }, { "epoch": 0.98, "learning_rate": 9.909805014841176e-06, "loss": 5.9278, "step": 120000 }, { "epoch": 0.99, "learning_rate": 9.909395037635908e-06, "loss": 5.9177, "step": 120500 }, { "epoch": 0.99, "learning_rate": 9.90898506043064e-06, "loss": 5.9108, "step": 121000 }, { "epoch": 1.0, "learning_rate": 9.908575083225373e-06, "loss": 5.8951, "step": 121500 }, { "epoch": 1.0, "learning_rate": 9.908165106020106e-06, "loss": 5.8845, "step": 122000 }, { "epoch": 1.0, "learning_rate": 9.907755128814838e-06, "loss": 5.8666, "step": 122500 }, { "epoch": 1.01, "learning_rate": 9.90734515160957e-06, "loss": 5.8549, "step": 123000 }, { "epoch": 1.01, "learning_rate": 9.906935174404305e-06, "loss": 5.8484, "step": 123500 }, { "epoch": 1.02, "learning_rate": 9.906525197199036e-06, "loss": 5.8272, "step": 124000 }, { "epoch": 1.02, "learning_rate": 9.90611521999377e-06, "loss": 5.8294, "step": 124500 }, { "epoch": 1.02, "learning_rate": 9.905705242788502e-06, "loss": 5.8177, "step": 125000 }, { "epoch": 1.03, "learning_rate": 9.905295265583235e-06, "loss": 5.8042, "step": 125500 }, { "epoch": 1.03, "learning_rate": 9.904885288377967e-06, "loss": 5.7966, "step": 126000 }, { "epoch": 1.04, "learning_rate": 9.9044753111727e-06, "loss": 5.7856, "step": 126500 }, { "epoch": 1.04, "learning_rate": 9.904065333967432e-06, "loss": 5.7805, "step": 127000 }, { "epoch": 1.04, "learning_rate": 9.903655356762164e-06, "loss": 5.765, "step": 127500 }, { "epoch": 1.05, "learning_rate": 9.903245379556897e-06, "loss": 5.7572, "step": 128000 }, { "epoch": 1.05, "learning_rate": 9.902835402351631e-06, "loss": 5.7467, "step": 128500 }, { "epoch": 1.06, "learning_rate": 9.902425425146362e-06, "loss": 5.7438, "step": 129000 }, { "epoch": 1.06, "learning_rate": 9.902015447941096e-06, "loss": 5.7373, "step": 129500 }, { "epoch": 1.07, "learning_rate": 9.901605470735828e-06, "loss": 5.7314, "step": 130000 }, { "epoch": 1.07, "learning_rate": 9.901195493530561e-06, "loss": 5.7186, "step": 130500 }, { "epoch": 1.07, "learning_rate": 9.900785516325293e-06, "loss": 5.718, "step": 131000 }, { "epoch": 1.08, "learning_rate": 9.900375539120026e-06, "loss": 5.7112, "step": 131500 }, { "epoch": 1.08, "learning_rate": 9.899965561914758e-06, "loss": 5.6979, "step": 132000 }, { "epoch": 1.09, "learning_rate": 9.89955558470949e-06, "loss": 5.6973, "step": 132500 }, { "epoch": 1.09, "learning_rate": 9.899145607504223e-06, "loss": 5.685, "step": 133000 }, { "epoch": 1.09, "learning_rate": 9.898735630298956e-06, "loss": 5.6754, "step": 133500 }, { "epoch": 1.1, "learning_rate": 9.898325653093688e-06, "loss": 5.6818, "step": 134000 }, { "epoch": 1.1, "learning_rate": 9.89791567588842e-06, "loss": 5.6681, "step": 134500 }, { "epoch": 1.11, "learning_rate": 9.897505698683155e-06, "loss": 5.662, "step": 135000 }, { "epoch": 1.11, "learning_rate": 9.897095721477886e-06, "loss": 5.6553, "step": 135500 }, { "epoch": 1.11, "learning_rate": 9.89668574427262e-06, "loss": 5.6435, "step": 136000 }, { "epoch": 1.12, "learning_rate": 9.896275767067352e-06, "loss": 5.6417, "step": 136500 }, { "epoch": 1.12, "learning_rate": 9.895865789862085e-06, "loss": 5.6315, "step": 137000 }, { "epoch": 1.13, "learning_rate": 9.895455812656817e-06, "loss": 5.6243, "step": 137500 }, { "epoch": 1.13, "learning_rate": 9.89504583545155e-06, "loss": 5.6162, "step": 138000 }, { "epoch": 1.13, "learning_rate": 9.894635858246282e-06, "loss": 5.6064, "step": 138500 }, { "epoch": 1.14, "learning_rate": 9.894225881041014e-06, "loss": 5.6047, "step": 139000 }, { "epoch": 1.14, "learning_rate": 9.893815903835747e-06, "loss": 5.598, "step": 139500 }, { "epoch": 1.15, "learning_rate": 9.893405926630481e-06, "loss": 5.5944, "step": 140000 }, { "epoch": 1.15, "learning_rate": 9.892995949425212e-06, "loss": 5.5791, "step": 140500 }, { "epoch": 1.16, "learning_rate": 9.892585972219946e-06, "loss": 5.5754, "step": 141000 }, { "epoch": 1.16, "learning_rate": 9.892175995014678e-06, "loss": 5.5592, "step": 141500 }, { "epoch": 1.16, "learning_rate": 9.891766017809411e-06, "loss": 5.5599, "step": 142000 }, { "epoch": 1.17, "learning_rate": 9.891356040604143e-06, "loss": 5.5509, "step": 142500 }, { "epoch": 1.17, "learning_rate": 9.890946063398876e-06, "loss": 5.5441, "step": 143000 }, { "epoch": 1.18, "learning_rate": 9.890536086193608e-06, "loss": 5.5397, "step": 143500 }, { "epoch": 1.18, "learning_rate": 9.890126108988342e-06, "loss": 5.5273, "step": 144000 }, { "epoch": 1.18, "learning_rate": 9.889716131783073e-06, "loss": 5.5151, "step": 144500 }, { "epoch": 1.19, "learning_rate": 9.889306154577806e-06, "loss": 5.5035, "step": 145000 }, { "epoch": 1.19, "learning_rate": 9.888896177372538e-06, "loss": 5.4958, "step": 145500 }, { "epoch": 1.2, "learning_rate": 9.88848620016727e-06, "loss": 5.4898, "step": 146000 }, { "epoch": 1.2, "learning_rate": 9.888076222962005e-06, "loss": 5.4751, "step": 146500 }, { "epoch": 1.2, "learning_rate": 9.887666245756735e-06, "loss": 5.4626, "step": 147000 }, { "epoch": 1.21, "learning_rate": 9.88725626855147e-06, "loss": 5.4522, "step": 147500 }, { "epoch": 1.21, "learning_rate": 9.886846291346202e-06, "loss": 5.4701, "step": 148000 }, { "epoch": 1.22, "learning_rate": 9.886436314140935e-06, "loss": 5.4391, "step": 148500 }, { "epoch": 1.22, "learning_rate": 9.886026336935667e-06, "loss": 5.4279, "step": 149000 }, { "epoch": 1.22, "learning_rate": 9.8856163597304e-06, "loss": 5.4183, "step": 149500 }, { "epoch": 1.23, "learning_rate": 9.885206382525132e-06, "loss": 5.4053, "step": 150000 }, { "epoch": 1.23, "learning_rate": 9.884796405319866e-06, "loss": 5.4312, "step": 150500 }, { "epoch": 1.24, "learning_rate": 9.884386428114597e-06, "loss": 5.3896, "step": 151000 }, { "epoch": 1.24, "learning_rate": 9.883976450909331e-06, "loss": 5.3819, "step": 151500 }, { "epoch": 1.25, "learning_rate": 9.883566473704063e-06, "loss": 5.4848, "step": 152000 }, { "epoch": 1.25, "learning_rate": 9.883156496498796e-06, "loss": 5.4951, "step": 152500 }, { "epoch": 1.25, "learning_rate": 9.882746519293528e-06, "loss": 5.459, "step": 153000 }, { "epoch": 1.26, "learning_rate": 9.882336542088261e-06, "loss": 5.4116, "step": 153500 }, { "epoch": 1.26, "learning_rate": 9.881926564882993e-06, "loss": 5.3916, "step": 154000 }, { "epoch": 1.27, "learning_rate": 9.881516587677726e-06, "loss": 5.3717, "step": 154500 }, { "epoch": 1.27, "learning_rate": 9.881106610472458e-06, "loss": 5.3408, "step": 155000 }, { "epoch": 1.27, "learning_rate": 9.880696633267192e-06, "loss": 5.3338, "step": 155500 }, { "epoch": 1.28, "learning_rate": 9.880286656061923e-06, "loss": 5.3153, "step": 156000 }, { "epoch": 1.28, "learning_rate": 9.879876678856657e-06, "loss": 5.2978, "step": 156500 }, { "epoch": 1.29, "learning_rate": 9.87946670165139e-06, "loss": 5.2771, "step": 157000 }, { "epoch": 1.29, "learning_rate": 9.87905672444612e-06, "loss": 5.2582, "step": 157500 }, { "epoch": 1.29, "learning_rate": 9.878646747240855e-06, "loss": 5.2367, "step": 158000 }, { "epoch": 1.3, "learning_rate": 9.878236770035587e-06, "loss": 5.2109, "step": 158500 }, { "epoch": 1.3, "learning_rate": 9.87782679283032e-06, "loss": 5.2005, "step": 159000 }, { "epoch": 1.31, "learning_rate": 9.877416815625052e-06, "loss": 5.1799, "step": 159500 }, { "epoch": 1.31, "learning_rate": 9.877006838419785e-06, "loss": 5.1683, "step": 160000 }, { "epoch": 1.31, "learning_rate": 9.876596861214517e-06, "loss": 5.1326, "step": 160500 }, { "epoch": 1.32, "learning_rate": 9.87618688400925e-06, "loss": 5.1092, "step": 161000 }, { "epoch": 1.32, "learning_rate": 9.875776906803982e-06, "loss": 5.0876, "step": 161500 }, { "epoch": 1.33, "learning_rate": 9.875366929598716e-06, "loss": 5.0742, "step": 162000 }, { "epoch": 1.33, "learning_rate": 9.874956952393447e-06, "loss": 5.0547, "step": 162500 }, { "epoch": 1.34, "learning_rate": 9.874546975188181e-06, "loss": 5.0256, "step": 163000 }, { "epoch": 1.34, "learning_rate": 9.874136997982913e-06, "loss": 5.0043, "step": 163500 }, { "epoch": 1.34, "learning_rate": 9.873727020777646e-06, "loss": 4.9879, "step": 164000 }, { "epoch": 1.35, "learning_rate": 9.873317043572378e-06, "loss": 4.9613, "step": 164500 }, { "epoch": 1.35, "learning_rate": 9.87290706636711e-06, "loss": 4.9432, "step": 165000 }, { "epoch": 1.36, "learning_rate": 9.872497089161843e-06, "loss": 4.9568, "step": 165500 }, { "epoch": 1.36, "learning_rate": 9.872087111956576e-06, "loss": 4.9095, "step": 166000 }, { "epoch": 1.36, "learning_rate": 9.871677134751308e-06, "loss": 4.8854, "step": 166500 }, { "epoch": 1.37, "learning_rate": 9.871267157546042e-06, "loss": 4.8734, "step": 167000 }, { "epoch": 1.37, "learning_rate": 9.870857180340773e-06, "loss": 4.8439, "step": 167500 }, { "epoch": 1.38, "learning_rate": 9.870447203135507e-06, "loss": 4.8283, "step": 168000 }, { "epoch": 1.38, "learning_rate": 9.87003722593024e-06, "loss": 4.7974, "step": 168500 }, { "epoch": 1.38, "learning_rate": 9.869627248724972e-06, "loss": 4.7818, "step": 169000 }, { "epoch": 1.39, "learning_rate": 9.869217271519705e-06, "loss": 4.7894, "step": 169500 }, { "epoch": 1.39, "learning_rate": 9.868807294314437e-06, "loss": 4.7617, "step": 170000 }, { "epoch": 1.4, "learning_rate": 9.86839731710917e-06, "loss": 4.7221, "step": 170500 }, { "epoch": 1.4, "learning_rate": 9.867987339903902e-06, "loss": 4.7078, "step": 171000 }, { "epoch": 1.41, "learning_rate": 9.867577362698634e-06, "loss": 4.6952, "step": 171500 }, { "epoch": 1.41, "learning_rate": 9.867167385493367e-06, "loss": 4.6771, "step": 172000 }, { "epoch": 1.41, "learning_rate": 9.8667574082881e-06, "loss": 4.6439, "step": 172500 }, { "epoch": 1.42, "learning_rate": 9.866347431082832e-06, "loss": 4.6252, "step": 173000 }, { "epoch": 1.42, "learning_rate": 9.865937453877566e-06, "loss": 4.6202, "step": 173500 }, { "epoch": 1.43, "learning_rate": 9.865527476672297e-06, "loss": 4.5785, "step": 174000 }, { "epoch": 1.43, "learning_rate": 9.865117499467031e-06, "loss": 4.5526, "step": 174500 }, { "epoch": 1.43, "learning_rate": 9.864707522261763e-06, "loss": 4.5272, "step": 175000 }, { "epoch": 1.44, "learning_rate": 9.864297545056496e-06, "loss": 4.5108, "step": 175500 }, { "epoch": 1.44, "learning_rate": 9.863887567851228e-06, "loss": 4.4886, "step": 176000 }, { "epoch": 1.45, "learning_rate": 9.86347759064596e-06, "loss": 4.457, "step": 176500 }, { "epoch": 1.45, "learning_rate": 9.863067613440693e-06, "loss": 4.4399, "step": 177000 }, { "epoch": 1.45, "learning_rate": 9.862657636235426e-06, "loss": 4.4196, "step": 177500 }, { "epoch": 1.46, "learning_rate": 9.862247659030158e-06, "loss": 4.3904, "step": 178000 }, { "epoch": 1.46, "learning_rate": 9.861837681824892e-06, "loss": 4.3747, "step": 178500 }, { "epoch": 1.47, "learning_rate": 9.861427704619623e-06, "loss": 4.3499, "step": 179000 }, { "epoch": 1.47, "learning_rate": 9.861017727414357e-06, "loss": 4.3159, "step": 179500 }, { "epoch": 1.47, "learning_rate": 9.86060775020909e-06, "loss": 4.2988, "step": 180000 }, { "epoch": 1.48, "learning_rate": 9.860197773003822e-06, "loss": 4.2792, "step": 180500 }, { "epoch": 1.48, "learning_rate": 9.859787795798555e-06, "loss": 4.259, "step": 181000 }, { "epoch": 1.49, "learning_rate": 9.859377818593287e-06, "loss": 4.2489, "step": 181500 }, { "epoch": 1.49, "learning_rate": 9.85896784138802e-06, "loss": 4.2267, "step": 182000 }, { "epoch": 1.5, "learning_rate": 9.858557864182752e-06, "loss": 4.1976, "step": 182500 }, { "epoch": 1.5, "learning_rate": 9.858147886977484e-06, "loss": 4.1874, "step": 183000 }, { "epoch": 1.5, "learning_rate": 9.857737909772217e-06, "loss": 4.191, "step": 183500 }, { "epoch": 1.51, "learning_rate": 9.85732793256695e-06, "loss": 4.155, "step": 184000 }, { "epoch": 1.51, "learning_rate": 9.856917955361682e-06, "loss": 4.1255, "step": 184500 }, { "epoch": 1.52, "learning_rate": 9.856507978156416e-06, "loss": 4.1147, "step": 185000 }, { "epoch": 1.52, "learning_rate": 9.856098000951147e-06, "loss": 4.0869, "step": 185500 }, { "epoch": 1.52, "learning_rate": 9.855688023745881e-06, "loss": 4.0806, "step": 186000 }, { "epoch": 1.53, "learning_rate": 9.855278046540613e-06, "loss": 4.0635, "step": 186500 }, { "epoch": 1.53, "learning_rate": 9.854868069335346e-06, "loss": 4.0525, "step": 187000 }, { "epoch": 1.54, "learning_rate": 9.854458092130078e-06, "loss": 4.0286, "step": 187500 }, { "epoch": 1.54, "learning_rate": 9.85404811492481e-06, "loss": 4.0121, "step": 188000 }, { "epoch": 1.54, "learning_rate": 9.853638137719543e-06, "loss": 4.0062, "step": 188500 }, { "epoch": 1.55, "learning_rate": 9.853228160514277e-06, "loss": 3.9757, "step": 189000 }, { "epoch": 1.55, "learning_rate": 9.852818183309008e-06, "loss": 3.9754, "step": 189500 }, { "epoch": 1.56, "learning_rate": 9.852408206103742e-06, "loss": 3.9647, "step": 190000 }, { "epoch": 1.56, "learning_rate": 9.851998228898475e-06, "loss": 3.9375, "step": 190500 }, { "epoch": 1.56, "learning_rate": 9.851588251693207e-06, "loss": 4.0285, "step": 191000 }, { "epoch": 1.57, "learning_rate": 9.85117827448794e-06, "loss": 3.9618, "step": 191500 }, { "epoch": 1.57, "learning_rate": 9.850768297282672e-06, "loss": 3.9384, "step": 192000 }, { "epoch": 1.58, "learning_rate": 9.850358320077405e-06, "loss": 3.8983, "step": 192500 }, { "epoch": 1.58, "learning_rate": 9.849948342872137e-06, "loss": 3.8736, "step": 193000 }, { "epoch": 1.59, "learning_rate": 9.84953836566687e-06, "loss": 3.8536, "step": 193500 }, { "epoch": 1.59, "learning_rate": 9.849128388461602e-06, "loss": 3.8413, "step": 194000 }, { "epoch": 1.59, "learning_rate": 9.848718411256334e-06, "loss": 3.8269, "step": 194500 }, { "epoch": 1.6, "learning_rate": 9.848308434051067e-06, "loss": 3.8253, "step": 195000 }, { "epoch": 1.6, "learning_rate": 9.847898456845801e-06, "loss": 3.7981, "step": 195500 }, { "epoch": 1.61, "learning_rate": 9.847488479640532e-06, "loss": 3.7768, "step": 196000 }, { "epoch": 1.61, "learning_rate": 9.847078502435266e-06, "loss": 3.7624, "step": 196500 }, { "epoch": 1.61, "learning_rate": 9.846668525229998e-06, "loss": 3.7615, "step": 197000 }, { "epoch": 1.62, "learning_rate": 9.846258548024731e-06, "loss": 3.7521, "step": 197500 }, { "epoch": 1.62, "learning_rate": 9.845848570819463e-06, "loss": 3.7378, "step": 198000 }, { "epoch": 1.63, "learning_rate": 9.845438593614196e-06, "loss": 3.7196, "step": 198500 }, { "epoch": 1.63, "learning_rate": 9.845028616408928e-06, "loss": 3.6944, "step": 199000 }, { "epoch": 1.63, "learning_rate": 9.84461863920366e-06, "loss": 3.6922, "step": 199500 }, { "epoch": 1.64, "learning_rate": 9.844208661998393e-06, "loss": 3.682, "step": 200000 }, { "epoch": 1.64, "learning_rate": 9.843798684793127e-06, "loss": 3.6819, "step": 200500 }, { "epoch": 1.65, "learning_rate": 9.843388707587858e-06, "loss": 3.6617, "step": 201000 }, { "epoch": 1.65, "learning_rate": 9.842978730382592e-06, "loss": 3.6491, "step": 201500 }, { "epoch": 1.65, "learning_rate": 9.842568753177325e-06, "loss": 3.6424, "step": 202000 }, { "epoch": 1.66, "learning_rate": 9.842158775972057e-06, "loss": 3.6295, "step": 202500 }, { "epoch": 1.66, "learning_rate": 9.84174879876679e-06, "loss": 3.6155, "step": 203000 }, { "epoch": 1.67, "learning_rate": 9.841338821561522e-06, "loss": 3.6067, "step": 203500 }, { "epoch": 1.67, "learning_rate": 9.840928844356255e-06, "loss": 3.6006, "step": 204000 }, { "epoch": 1.68, "learning_rate": 9.840518867150987e-06, "loss": 3.583, "step": 204500 }, { "epoch": 1.68, "learning_rate": 9.84010888994572e-06, "loss": 3.5762, "step": 205000 }, { "epoch": 1.68, "learning_rate": 9.839698912740454e-06, "loss": 3.5693, "step": 205500 }, { "epoch": 1.69, "learning_rate": 9.839288935535184e-06, "loss": 3.5653, "step": 206000 }, { "epoch": 1.69, "learning_rate": 9.838878958329917e-06, "loss": 3.5646, "step": 206500 }, { "epoch": 1.7, "learning_rate": 9.838468981124651e-06, "loss": 3.554, "step": 207000 }, { "epoch": 1.7, "learning_rate": 9.838059003919382e-06, "loss": 3.5415, "step": 207500 }, { "epoch": 1.7, "learning_rate": 9.837649026714116e-06, "loss": 3.5334, "step": 208000 }, { "epoch": 1.71, "learning_rate": 9.837239049508848e-06, "loss": 3.5344, "step": 208500 }, { "epoch": 1.71, "learning_rate": 9.83682907230358e-06, "loss": 3.5127, "step": 209000 }, { "epoch": 1.72, "learning_rate": 9.836419095098313e-06, "loss": 3.5073, "step": 209500 }, { "epoch": 1.72, "learning_rate": 9.836009117893046e-06, "loss": 3.5022, "step": 210000 }, { "epoch": 1.72, "learning_rate": 9.835599140687778e-06, "loss": 3.4953, "step": 210500 }, { "epoch": 1.73, "learning_rate": 9.83518916348251e-06, "loss": 3.4879, "step": 211000 }, { "epoch": 1.73, "learning_rate": 9.834779186277243e-06, "loss": 3.4836, "step": 211500 }, { "epoch": 1.74, "learning_rate": 9.834369209071977e-06, "loss": 3.486, "step": 212000 }, { "epoch": 1.74, "learning_rate": 9.833959231866708e-06, "loss": 3.4859, "step": 212500 }, { "epoch": 1.75, "learning_rate": 9.833549254661442e-06, "loss": 3.4669, "step": 213000 }, { "epoch": 1.75, "learning_rate": 9.833139277456175e-06, "loss": 3.4699, "step": 213500 }, { "epoch": 1.75, "learning_rate": 9.832729300250907e-06, "loss": 3.4552, "step": 214000 }, { "epoch": 1.76, "learning_rate": 9.83231932304564e-06, "loss": 3.4458, "step": 214500 }, { "epoch": 1.76, "learning_rate": 9.831909345840372e-06, "loss": 3.4439, "step": 215000 }, { "epoch": 1.77, "learning_rate": 9.831499368635105e-06, "loss": 3.4365, "step": 215500 }, { "epoch": 1.77, "learning_rate": 9.831089391429837e-06, "loss": 3.421, "step": 216000 }, { "epoch": 1.77, "learning_rate": 9.83067941422457e-06, "loss": 3.4254, "step": 216500 }, { "epoch": 1.78, "learning_rate": 9.830269437019304e-06, "loss": 3.4283, "step": 217000 }, { "epoch": 1.78, "learning_rate": 9.829859459814034e-06, "loss": 3.4104, "step": 217500 }, { "epoch": 1.79, "learning_rate": 9.829449482608769e-06, "loss": 3.4117, "step": 218000 }, { "epoch": 1.79, "learning_rate": 9.829039505403501e-06, "loss": 3.4137, "step": 218500 }, { "epoch": 1.79, "learning_rate": 9.828629528198232e-06, "loss": 3.4104, "step": 219000 }, { "epoch": 1.8, "learning_rate": 9.828219550992966e-06, "loss": 3.4028, "step": 219500 }, { "epoch": 1.8, "learning_rate": 9.827809573787698e-06, "loss": 3.3965, "step": 220000 }, { "epoch": 1.81, "learning_rate": 9.82739959658243e-06, "loss": 3.398, "step": 220500 }, { "epoch": 1.81, "learning_rate": 9.826989619377163e-06, "loss": 3.3841, "step": 221000 }, { "epoch": 1.81, "learning_rate": 9.826579642171896e-06, "loss": 3.3684, "step": 221500 }, { "epoch": 1.82, "learning_rate": 9.826169664966628e-06, "loss": 3.3729, "step": 222000 }, { "epoch": 1.82, "learning_rate": 9.82575968776136e-06, "loss": 3.3701, "step": 222500 }, { "epoch": 1.83, "learning_rate": 9.825349710556093e-06, "loss": 3.3599, "step": 223000 }, { "epoch": 1.83, "learning_rate": 9.824939733350827e-06, "loss": 3.3518, "step": 223500 }, { "epoch": 1.84, "learning_rate": 9.824529756145558e-06, "loss": 3.3591, "step": 224000 }, { "epoch": 1.84, "learning_rate": 9.824119778940292e-06, "loss": 3.3534, "step": 224500 }, { "epoch": 1.84, "learning_rate": 9.823709801735025e-06, "loss": 3.3433, "step": 225000 }, { "epoch": 1.85, "learning_rate": 9.823299824529757e-06, "loss": 3.3323, "step": 225500 }, { "epoch": 1.85, "learning_rate": 9.82288984732449e-06, "loss": 3.3267, "step": 226000 }, { "epoch": 1.86, "learning_rate": 9.822479870119222e-06, "loss": 3.3217, "step": 226500 }, { "epoch": 1.86, "learning_rate": 9.822069892913954e-06, "loss": 3.3107, "step": 227000 }, { "epoch": 1.86, "learning_rate": 9.821659915708689e-06, "loss": 3.3058, "step": 227500 }, { "epoch": 1.87, "learning_rate": 9.82124993850342e-06, "loss": 3.3154, "step": 228000 }, { "epoch": 1.87, "learning_rate": 9.820839961298154e-06, "loss": 3.3026, "step": 228500 }, { "epoch": 1.88, "learning_rate": 9.820429984092886e-06, "loss": 3.301, "step": 229000 }, { "epoch": 1.88, "learning_rate": 9.820020006887618e-06, "loss": 3.2846, "step": 229500 }, { "epoch": 1.88, "learning_rate": 9.819610029682351e-06, "loss": 3.2885, "step": 230000 }, { "epoch": 1.89, "learning_rate": 9.819200052477082e-06, "loss": 3.2807, "step": 230500 }, { "epoch": 1.89, "learning_rate": 9.818790075271816e-06, "loss": 3.2787, "step": 231000 }, { "epoch": 1.9, "learning_rate": 9.818380098066548e-06, "loss": 3.2746, "step": 231500 }, { "epoch": 1.9, "learning_rate": 9.81797012086128e-06, "loss": 3.2654, "step": 232000 }, { "epoch": 1.9, "learning_rate": 9.817560143656013e-06, "loss": 3.2704, "step": 232500 }, { "epoch": 1.91, "learning_rate": 9.817150166450746e-06, "loss": 3.2666, "step": 233000 }, { "epoch": 1.91, "learning_rate": 9.816740189245478e-06, "loss": 3.2688, "step": 233500 }, { "epoch": 1.92, "learning_rate": 9.816330212040212e-06, "loss": 3.2705, "step": 234000 }, { "epoch": 1.92, "learning_rate": 9.815920234834943e-06, "loss": 3.2563, "step": 234500 }, { "epoch": 1.93, "learning_rate": 9.815510257629677e-06, "loss": 3.2619, "step": 235000 }, { "epoch": 1.93, "learning_rate": 9.81510028042441e-06, "loss": 3.2557, "step": 235500 }, { "epoch": 1.93, "learning_rate": 9.814690303219142e-06, "loss": 3.2419, "step": 236000 }, { "epoch": 1.94, "learning_rate": 9.814280326013875e-06, "loss": 3.2356, "step": 236500 }, { "epoch": 1.94, "learning_rate": 9.813870348808607e-06, "loss": 3.2401, "step": 237000 }, { "epoch": 1.95, "learning_rate": 9.81346037160334e-06, "loss": 3.2418, "step": 237500 }, { "epoch": 1.95, "learning_rate": 9.813050394398072e-06, "loss": 3.2315, "step": 238000 }, { "epoch": 1.95, "learning_rate": 9.812640417192804e-06, "loss": 3.233, "step": 238500 }, { "epoch": 1.96, "learning_rate": 9.812230439987539e-06, "loss": 3.2181, "step": 239000 }, { "epoch": 1.96, "learning_rate": 9.81182046278227e-06, "loss": 3.2364, "step": 239500 }, { "epoch": 1.97, "learning_rate": 9.811410485577004e-06, "loss": 3.2149, "step": 240000 }, { "epoch": 1.97, "learning_rate": 9.811000508371736e-06, "loss": 3.2026, "step": 240500 }, { "epoch": 1.97, "learning_rate": 9.810590531166468e-06, "loss": 3.2053, "step": 241000 }, { "epoch": 1.98, "learning_rate": 9.810180553961201e-06, "loss": 3.1994, "step": 241500 }, { "epoch": 1.98, "learning_rate": 9.809770576755933e-06, "loss": 3.1933, "step": 242000 }, { "epoch": 1.99, "learning_rate": 9.809360599550666e-06, "loss": 3.1945, "step": 242500 }, { "epoch": 1.99, "learning_rate": 9.808950622345398e-06, "loss": 3.1907, "step": 243000 }, { "epoch": 1.99, "learning_rate": 9.80854064514013e-06, "loss": 3.1865, "step": 243500 }, { "epoch": 2.0, "learning_rate": 9.808130667934863e-06, "loss": 3.1886, "step": 244000 }, { "epoch": 2.0, "learning_rate": 9.807720690729596e-06, "loss": 3.1766, "step": 244500 }, { "epoch": 2.01, "learning_rate": 9.807310713524328e-06, "loss": 3.1757, "step": 245000 }, { "epoch": 2.01, "learning_rate": 9.806900736319062e-06, "loss": 3.1759, "step": 245500 }, { "epoch": 2.02, "learning_rate": 9.806490759113793e-06, "loss": 3.1687, "step": 246000 }, { "epoch": 2.02, "learning_rate": 9.806080781908527e-06, "loss": 3.1521, "step": 246500 }, { "epoch": 2.02, "learning_rate": 9.80567080470326e-06, "loss": 3.1649, "step": 247000 }, { "epoch": 2.03, "learning_rate": 9.805260827497992e-06, "loss": 3.1577, "step": 247500 }, { "epoch": 2.03, "learning_rate": 9.804850850292725e-06, "loss": 3.1544, "step": 248000 }, { "epoch": 2.04, "learning_rate": 9.804440873087457e-06, "loss": 3.1526, "step": 248500 }, { "epoch": 2.04, "learning_rate": 9.80403089588219e-06, "loss": 3.1477, "step": 249000 }, { "epoch": 2.04, "learning_rate": 9.803620918676922e-06, "loss": 3.1447, "step": 249500 }, { "epoch": 2.05, "learning_rate": 9.803210941471654e-06, "loss": 3.1419, "step": 250000 }, { "epoch": 2.05, "learning_rate": 9.802800964266389e-06, "loss": 3.1377, "step": 250500 }, { "epoch": 2.06, "learning_rate": 9.80239098706112e-06, "loss": 3.1521, "step": 251000 }, { "epoch": 2.06, "learning_rate": 9.801981009855853e-06, "loss": 3.1341, "step": 251500 }, { "epoch": 2.06, "learning_rate": 9.801571032650586e-06, "loss": 3.1279, "step": 252000 }, { "epoch": 2.07, "learning_rate": 9.801161055445318e-06, "loss": 3.1296, "step": 252500 }, { "epoch": 2.07, "learning_rate": 9.800751078240051e-06, "loss": 3.1243, "step": 253000 }, { "epoch": 2.08, "learning_rate": 9.800341101034783e-06, "loss": 3.1164, "step": 253500 }, { "epoch": 2.08, "learning_rate": 9.799931123829516e-06, "loss": 3.1177, "step": 254000 }, { "epoch": 2.09, "learning_rate": 9.799521146624248e-06, "loss": 3.1196, "step": 254500 }, { "epoch": 2.09, "learning_rate": 9.79911116941898e-06, "loss": 3.1148, "step": 255000 }, { "epoch": 2.09, "learning_rate": 9.798701192213713e-06, "loss": 3.1061, "step": 255500 }, { "epoch": 2.1, "learning_rate": 9.798291215008446e-06, "loss": 3.1101, "step": 256000 }, { "epoch": 2.1, "learning_rate": 9.797881237803178e-06, "loss": 3.107, "step": 256500 }, { "epoch": 2.11, "learning_rate": 9.797471260597912e-06, "loss": 3.1068, "step": 257000 }, { "epoch": 2.11, "learning_rate": 9.797061283392643e-06, "loss": 3.108, "step": 257500 }, { "epoch": 2.11, "learning_rate": 9.796651306187377e-06, "loss": 3.0922, "step": 258000 }, { "epoch": 2.12, "learning_rate": 9.79624132898211e-06, "loss": 3.0889, "step": 258500 }, { "epoch": 2.12, "learning_rate": 9.795831351776842e-06, "loss": 3.0981, "step": 259000 }, { "epoch": 2.13, "learning_rate": 9.795421374571575e-06, "loss": 3.0861, "step": 259500 }, { "epoch": 2.13, "learning_rate": 9.795011397366307e-06, "loss": 3.0924, "step": 260000 }, { "epoch": 2.13, "learning_rate": 9.79460142016104e-06, "loss": 3.0889, "step": 260500 }, { "epoch": 2.14, "learning_rate": 9.794191442955772e-06, "loss": 3.0936, "step": 261000 }, { "epoch": 2.14, "learning_rate": 9.793781465750504e-06, "loss": 3.0831, "step": 261500 }, { "epoch": 2.15, "learning_rate": 9.793371488545239e-06, "loss": 3.0684, "step": 262000 }, { "epoch": 2.15, "learning_rate": 9.79296151133997e-06, "loss": 3.078, "step": 262500 }, { "epoch": 2.15, "learning_rate": 9.792551534134703e-06, "loss": 3.0753, "step": 263000 }, { "epoch": 2.16, "learning_rate": 9.792141556929436e-06, "loss": 3.0687, "step": 263500 }, { "epoch": 2.16, "learning_rate": 9.791731579724168e-06, "loss": 3.0662, "step": 264000 }, { "epoch": 2.17, "learning_rate": 9.7913216025189e-06, "loss": 3.0591, "step": 264500 }, { "epoch": 2.17, "learning_rate": 9.790911625313633e-06, "loss": 3.06, "step": 265000 }, { "epoch": 2.18, "learning_rate": 9.790501648108366e-06, "loss": 3.0507, "step": 265500 }, { "epoch": 2.18, "learning_rate": 9.7900916709031e-06, "loss": 3.0593, "step": 266000 }, { "epoch": 2.18, "learning_rate": 9.78968169369783e-06, "loss": 3.0589, "step": 266500 }, { "epoch": 2.19, "learning_rate": 9.789271716492565e-06, "loss": 3.0523, "step": 267000 }, { "epoch": 2.19, "learning_rate": 9.788861739287297e-06, "loss": 3.0443, "step": 267500 }, { "epoch": 2.2, "learning_rate": 9.788451762082028e-06, "loss": 3.0464, "step": 268000 }, { "epoch": 2.2, "learning_rate": 9.788041784876762e-06, "loss": 3.0398, "step": 268500 }, { "epoch": 2.2, "learning_rate": 9.787631807671493e-06, "loss": 3.0371, "step": 269000 }, { "epoch": 2.21, "learning_rate": 9.787221830466227e-06, "loss": 3.0287, "step": 269500 }, { "epoch": 2.21, "learning_rate": 9.78681185326096e-06, "loss": 3.0457, "step": 270000 }, { "epoch": 2.22, "learning_rate": 9.786401876055692e-06, "loss": 3.0355, "step": 270500 }, { "epoch": 2.22, "learning_rate": 9.785991898850424e-06, "loss": 3.0385, "step": 271000 }, { "epoch": 2.22, "learning_rate": 9.785581921645157e-06, "loss": 3.0242, "step": 271500 }, { "epoch": 2.23, "learning_rate": 9.78517194443989e-06, "loss": 3.0248, "step": 272000 }, { "epoch": 2.23, "learning_rate": 9.784761967234624e-06, "loss": 3.0148, "step": 272500 }, { "epoch": 2.24, "learning_rate": 9.784351990029354e-06, "loss": 3.0449, "step": 273000 }, { "epoch": 2.24, "learning_rate": 9.783942012824088e-06, "loss": 3.0311, "step": 273500 }, { "epoch": 2.24, "learning_rate": 9.783532035618821e-06, "loss": 3.0237, "step": 274000 }, { "epoch": 2.25, "learning_rate": 9.783122058413553e-06, "loss": 3.0253, "step": 274500 }, { "epoch": 2.25, "learning_rate": 9.782712081208286e-06, "loss": 3.0234, "step": 275000 }, { "epoch": 2.26, "learning_rate": 9.782302104003018e-06, "loss": 3.0212, "step": 275500 }, { "epoch": 2.26, "learning_rate": 9.78189212679775e-06, "loss": 3.0142, "step": 276000 }, { "epoch": 2.27, "learning_rate": 9.781482149592483e-06, "loss": 3.0159, "step": 276500 }, { "epoch": 2.27, "learning_rate": 9.781072172387216e-06, "loss": 3.0111, "step": 277000 }, { "epoch": 2.27, "learning_rate": 9.78066219518195e-06, "loss": 3.0126, "step": 277500 }, { "epoch": 2.28, "learning_rate": 9.78025221797668e-06, "loss": 3.0104, "step": 278000 }, { "epoch": 2.28, "learning_rate": 9.779842240771415e-06, "loss": 2.9987, "step": 278500 }, { "epoch": 2.29, "learning_rate": 9.779432263566147e-06, "loss": 2.994, "step": 279000 }, { "epoch": 2.29, "learning_rate": 9.779022286360878e-06, "loss": 2.9956, "step": 279500 }, { "epoch": 2.29, "learning_rate": 9.778612309155612e-06, "loss": 2.9843, "step": 280000 }, { "epoch": 2.3, "learning_rate": 9.778202331950345e-06, "loss": 2.9861, "step": 280500 }, { "epoch": 2.3, "learning_rate": 9.777792354745077e-06, "loss": 2.992, "step": 281000 }, { "epoch": 2.31, "learning_rate": 9.77738237753981e-06, "loss": 2.989, "step": 281500 }, { "epoch": 2.31, "learning_rate": 9.776972400334542e-06, "loss": 2.9962, "step": 282000 }, { "epoch": 2.31, "learning_rate": 9.776562423129274e-06, "loss": 2.9844, "step": 282500 }, { "epoch": 2.32, "learning_rate": 9.776152445924007e-06, "loss": 2.9777, "step": 283000 }, { "epoch": 2.32, "learning_rate": 9.77574246871874e-06, "loss": 2.9806, "step": 283500 }, { "epoch": 2.33, "learning_rate": 9.775332491513474e-06, "loss": 2.9783, "step": 284000 }, { "epoch": 2.33, "learning_rate": 9.774922514308204e-06, "loss": 2.9717, "step": 284500 }, { "epoch": 2.33, "learning_rate": 9.774512537102938e-06, "loss": 2.9753, "step": 285000 }, { "epoch": 2.34, "learning_rate": 9.774102559897671e-06, "loss": 3.0081, "step": 285500 }, { "epoch": 2.34, "learning_rate": 9.773692582692403e-06, "loss": 2.9719, "step": 286000 }, { "epoch": 2.35, "learning_rate": 9.773282605487136e-06, "loss": 2.9699, "step": 286500 }, { "epoch": 2.35, "learning_rate": 9.772872628281868e-06, "loss": 2.9652, "step": 287000 }, { "epoch": 2.36, "learning_rate": 9.7724626510766e-06, "loss": 2.9697, "step": 287500 }, { "epoch": 2.36, "learning_rate": 9.772052673871333e-06, "loss": 2.9538, "step": 288000 }, { "epoch": 2.36, "learning_rate": 9.771642696666066e-06, "loss": 2.9509, "step": 288500 }, { "epoch": 2.37, "learning_rate": 9.7712327194608e-06, "loss": 2.954, "step": 289000 }, { "epoch": 2.37, "learning_rate": 9.77082274225553e-06, "loss": 2.9578, "step": 289500 }, { "epoch": 2.38, "learning_rate": 9.770412765050265e-06, "loss": 2.9521, "step": 290000 }, { "epoch": 2.38, "learning_rate": 9.770002787844997e-06, "loss": 2.9494, "step": 290500 }, { "epoch": 2.38, "learning_rate": 9.76959281063973e-06, "loss": 2.9559, "step": 291000 }, { "epoch": 2.39, "learning_rate": 9.769182833434462e-06, "loss": 2.9464, "step": 291500 }, { "epoch": 2.39, "learning_rate": 9.768772856229195e-06, "loss": 2.9491, "step": 292000 }, { "epoch": 2.4, "learning_rate": 9.768362879023927e-06, "loss": 2.946, "step": 292500 }, { "epoch": 2.4, "step": 292842, "total_flos": 2.3285464173306184e+18, "train_loss": 4.907397945397096, "train_runtime": 197998.9762, "train_samples_per_second": 2958.984, "train_steps_per_second": 61.646 } ], "logging_steps": 500, "max_steps": 12205800, "num_train_epochs": 100, "save_steps": 1000000, "total_flos": 2.3285464173306184e+18, "trial_name": null, "trial_params": null }