{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "global_step": 881659, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.997175778844202e-05, "loss": 1.3304, "step": 500 }, { "epoch": 0.0, "learning_rate": 4.994345886561585e-05, "loss": 1.3122, "step": 1000 }, { "epoch": 0.0, "learning_rate": 4.991510323152149e-05, "loss": 1.2993, "step": 1500 }, { "epoch": 0.0, "learning_rate": 4.988680430869531e-05, "loss": 1.2774, "step": 2000 }, { "epoch": 0.0, "learning_rate": 4.9858448674600954e-05, "loss": 1.2626, "step": 2500 }, { "epoch": 0.0, "learning_rate": 4.983009304050659e-05, "loss": 1.2627, "step": 3000 }, { "epoch": 0.0, "learning_rate": 4.980173740641223e-05, "loss": 1.254, "step": 3500 }, { "epoch": 0.0, "learning_rate": 4.9773381772317873e-05, "loss": 1.2599, "step": 4000 }, { "epoch": 0.01, "learning_rate": 4.974502613822351e-05, "loss": 1.2455, "step": 4500 }, { "epoch": 0.01, "learning_rate": 4.971667050412915e-05, "loss": 1.2563, "step": 5000 }, { "epoch": 0.01, "learning_rate": 4.968831487003479e-05, "loss": 1.2451, "step": 5500 }, { "epoch": 0.01, "learning_rate": 4.966001594720862e-05, "loss": 1.2504, "step": 6000 }, { "epoch": 0.01, "learning_rate": 4.963166031311426e-05, "loss": 1.2343, "step": 6500 }, { "epoch": 0.01, "learning_rate": 4.9603304679019894e-05, "loss": 1.2249, "step": 7000 }, { "epoch": 0.01, "learning_rate": 4.9574949044925536e-05, "loss": 1.2318, "step": 7500 }, { "epoch": 0.01, "learning_rate": 4.954659341083117e-05, "loss": 1.2294, "step": 8000 }, { "epoch": 0.01, "learning_rate": 4.951823777673681e-05, "loss": 1.2279, "step": 8500 }, { "epoch": 0.01, "learning_rate": 4.9489882142642455e-05, "loss": 1.2212, "step": 9000 }, { "epoch": 0.01, "learning_rate": 4.946158321981628e-05, "loss": 1.2309, "step": 9500 }, { "epoch": 0.01, "learning_rate": 4.943322758572192e-05, "loss": 1.2208, "step": 10000 }, { "epoch": 0.01, "learning_rate": 4.9404871951627556e-05, "loss": 1.228, "step": 10500 }, { "epoch": 0.01, "learning_rate": 4.937657302880139e-05, "loss": 1.2176, "step": 11000 }, { "epoch": 0.01, "learning_rate": 4.934821739470702e-05, "loss": 1.2161, "step": 11500 }, { "epoch": 0.01, "learning_rate": 4.931986176061267e-05, "loss": 1.2172, "step": 12000 }, { "epoch": 0.01, "learning_rate": 4.9291506126518306e-05, "loss": 1.2119, "step": 12500 }, { "epoch": 0.01, "learning_rate": 4.926315049242394e-05, "loss": 1.2083, "step": 13000 }, { "epoch": 0.02, "learning_rate": 4.9234794858329584e-05, "loss": 1.2215, "step": 13500 }, { "epoch": 0.02, "learning_rate": 4.9206439224235226e-05, "loss": 1.2043, "step": 14000 }, { "epoch": 0.02, "learning_rate": 4.917808359014086e-05, "loss": 1.2027, "step": 14500 }, { "epoch": 0.02, "learning_rate": 4.914978466731469e-05, "loss": 1.21, "step": 15000 }, { "epoch": 0.02, "learning_rate": 4.912142903322033e-05, "loss": 1.2094, "step": 15500 }, { "epoch": 0.02, "learning_rate": 4.909307339912597e-05, "loss": 1.2119, "step": 16000 }, { "epoch": 0.02, "learning_rate": 4.906471776503161e-05, "loss": 1.193, "step": 16500 }, { "epoch": 0.02, "learning_rate": 4.9036362130937246e-05, "loss": 1.2033, "step": 17000 }, { "epoch": 0.02, "learning_rate": 4.900806320811108e-05, "loss": 1.206, "step": 17500 }, { "epoch": 0.02, "learning_rate": 4.897970757401671e-05, "loss": 1.2061, "step": 18000 }, { "epoch": 0.02, "learning_rate": 4.8951351939922354e-05, "loss": 1.193, "step": 18500 }, { "epoch": 0.02, "learning_rate": 4.8922996305827996e-05, "loss": 1.1924, "step": 19000 }, { "epoch": 0.02, "learning_rate": 4.889464067173363e-05, "loss": 1.1871, "step": 19500 }, { "epoch": 0.02, "learning_rate": 4.8866285037639273e-05, "loss": 1.1883, "step": 20000 }, { "epoch": 0.02, "learning_rate": 4.883792940354491e-05, "loss": 1.1917, "step": 20500 }, { "epoch": 0.02, "learning_rate": 4.880957376945055e-05, "loss": 1.1936, "step": 21000 }, { "epoch": 0.02, "learning_rate": 4.8781218135356186e-05, "loss": 1.1904, "step": 21500 }, { "epoch": 0.02, "learning_rate": 4.875291921253002e-05, "loss": 1.1855, "step": 22000 }, { "epoch": 0.03, "learning_rate": 4.872456357843566e-05, "loss": 1.1826, "step": 22500 }, { "epoch": 0.03, "learning_rate": 4.8696207944341294e-05, "loss": 1.1903, "step": 23000 }, { "epoch": 0.03, "learning_rate": 4.8667852310246936e-05, "loss": 1.1751, "step": 23500 }, { "epoch": 0.03, "learning_rate": 4.863955338742076e-05, "loss": 1.1854, "step": 24000 }, { "epoch": 0.03, "learning_rate": 4.861125446459459e-05, "loss": 1.1777, "step": 24500 }, { "epoch": 0.03, "learning_rate": 4.8582898830500226e-05, "loss": 1.1808, "step": 25000 }, { "epoch": 0.03, "learning_rate": 4.8554543196405875e-05, "loss": 1.1903, "step": 25500 }, { "epoch": 0.03, "learning_rate": 4.852618756231151e-05, "loss": 1.1777, "step": 26000 }, { "epoch": 0.03, "learning_rate": 4.8497831928217145e-05, "loss": 1.1816, "step": 26500 }, { "epoch": 0.03, "learning_rate": 4.846947629412279e-05, "loss": 1.1829, "step": 27000 }, { "epoch": 0.03, "learning_rate": 4.844117737129661e-05, "loss": 1.1851, "step": 27500 }, { "epoch": 0.03, "learning_rate": 4.841282173720225e-05, "loss": 1.1809, "step": 28000 }, { "epoch": 0.03, "learning_rate": 4.8384466103107895e-05, "loss": 1.1794, "step": 28500 }, { "epoch": 0.03, "learning_rate": 4.835616718028172e-05, "loss": 1.1758, "step": 29000 }, { "epoch": 0.03, "learning_rate": 4.832781154618736e-05, "loss": 1.1778, "step": 29500 }, { "epoch": 0.03, "learning_rate": 4.8299455912093e-05, "loss": 1.165, "step": 30000 }, { "epoch": 0.03, "learning_rate": 4.827110027799864e-05, "loss": 1.1737, "step": 30500 }, { "epoch": 0.04, "learning_rate": 4.824274464390428e-05, "loss": 1.1753, "step": 31000 }, { "epoch": 0.04, "learning_rate": 4.8214389009809916e-05, "loss": 1.1745, "step": 31500 }, { "epoch": 0.04, "learning_rate": 4.818603337571556e-05, "loss": 1.1764, "step": 32000 }, { "epoch": 0.04, "learning_rate": 4.815767774162119e-05, "loss": 1.1638, "step": 32500 }, { "epoch": 0.04, "learning_rate": 4.8129322107526835e-05, "loss": 1.1753, "step": 33000 }, { "epoch": 0.04, "learning_rate": 4.810102318470066e-05, "loss": 1.1726, "step": 33500 }, { "epoch": 0.04, "learning_rate": 4.80726675506063e-05, "loss": 1.1659, "step": 34000 }, { "epoch": 0.04, "learning_rate": 4.804442533904832e-05, "loss": 1.1625, "step": 34500 }, { "epoch": 0.04, "learning_rate": 4.8016069704953956e-05, "loss": 1.1626, "step": 35000 }, { "epoch": 0.04, "learning_rate": 4.79877140708596e-05, "loss": 1.1735, "step": 35500 }, { "epoch": 0.04, "learning_rate": 4.795935843676524e-05, "loss": 1.1706, "step": 36000 }, { "epoch": 0.04, "learning_rate": 4.7931002802670875e-05, "loss": 1.1638, "step": 36500 }, { "epoch": 0.04, "learning_rate": 4.790264716857652e-05, "loss": 1.1604, "step": 37000 }, { "epoch": 0.04, "learning_rate": 4.787429153448216e-05, "loss": 1.1753, "step": 37500 }, { "epoch": 0.04, "learning_rate": 4.7845935900387794e-05, "loss": 1.1571, "step": 38000 }, { "epoch": 0.04, "learning_rate": 4.781758026629343e-05, "loss": 1.1588, "step": 38500 }, { "epoch": 0.04, "learning_rate": 4.778922463219907e-05, "loss": 1.1719, "step": 39000 }, { "epoch": 0.04, "learning_rate": 4.7760868998104714e-05, "loss": 1.1604, "step": 39500 }, { "epoch": 0.05, "learning_rate": 4.773251336401035e-05, "loss": 1.1631, "step": 40000 }, { "epoch": 0.05, "learning_rate": 4.770415772991599e-05, "loss": 1.148, "step": 40500 }, { "epoch": 0.05, "learning_rate": 4.767580209582163e-05, "loss": 1.1462, "step": 41000 }, { "epoch": 0.05, "learning_rate": 4.764750317299546e-05, "loss": 1.1637, "step": 41500 }, { "epoch": 0.05, "learning_rate": 4.76191475389011e-05, "loss": 1.1625, "step": 42000 }, { "epoch": 0.05, "learning_rate": 4.7590791904806734e-05, "loss": 1.1514, "step": 42500 }, { "epoch": 0.05, "learning_rate": 4.7562436270712376e-05, "loss": 1.1566, "step": 43000 }, { "epoch": 0.05, "learning_rate": 4.753408063661802e-05, "loss": 1.1626, "step": 43500 }, { "epoch": 0.05, "learning_rate": 4.750578171379184e-05, "loss": 1.1559, "step": 44000 }, { "epoch": 0.05, "learning_rate": 4.747742607969748e-05, "loss": 1.1504, "step": 44500 }, { "epoch": 0.05, "learning_rate": 4.744907044560312e-05, "loss": 1.1485, "step": 45000 }, { "epoch": 0.05, "learning_rate": 4.742071481150876e-05, "loss": 1.1574, "step": 45500 }, { "epoch": 0.05, "learning_rate": 4.7392359177414397e-05, "loss": 1.1498, "step": 46000 }, { "epoch": 0.05, "learning_rate": 4.736400354332004e-05, "loss": 1.1593, "step": 46500 }, { "epoch": 0.05, "learning_rate": 4.733564790922568e-05, "loss": 1.149, "step": 47000 }, { "epoch": 0.05, "learning_rate": 4.7307348986399505e-05, "loss": 1.1522, "step": 47500 }, { "epoch": 0.05, "learning_rate": 4.7278993352305147e-05, "loss": 1.1449, "step": 48000 }, { "epoch": 0.06, "learning_rate": 4.725063771821078e-05, "loss": 1.1574, "step": 48500 }, { "epoch": 0.06, "learning_rate": 4.7222282084116424e-05, "loss": 1.1529, "step": 49000 }, { "epoch": 0.06, "learning_rate": 4.7193926450022066e-05, "loss": 1.1524, "step": 49500 }, { "epoch": 0.06, "learning_rate": 4.71655708159277e-05, "loss": 1.1406, "step": 50000 }, { "epoch": 0.06, "learning_rate": 4.713721518183334e-05, "loss": 1.1452, "step": 50500 }, { "epoch": 0.06, "learning_rate": 4.710891625900717e-05, "loss": 1.1443, "step": 51000 }, { "epoch": 0.06, "learning_rate": 4.708056062491281e-05, "loss": 1.1378, "step": 51500 }, { "epoch": 0.06, "learning_rate": 4.705220499081845e-05, "loss": 1.1504, "step": 52000 }, { "epoch": 0.06, "learning_rate": 4.7023849356724086e-05, "loss": 1.1519, "step": 52500 }, { "epoch": 0.06, "learning_rate": 4.699549372262972e-05, "loss": 1.14, "step": 53000 }, { "epoch": 0.06, "learning_rate": 4.696719479980355e-05, "loss": 1.1465, "step": 53500 }, { "epoch": 0.06, "learning_rate": 4.6938839165709194e-05, "loss": 1.1483, "step": 54000 }, { "epoch": 0.06, "learning_rate": 4.6910483531614836e-05, "loss": 1.1561, "step": 54500 }, { "epoch": 0.06, "learning_rate": 4.688212789752047e-05, "loss": 1.1454, "step": 55000 }, { "epoch": 0.06, "learning_rate": 4.685377226342611e-05, "loss": 1.1399, "step": 55500 }, { "epoch": 0.06, "learning_rate": 4.6825416629331756e-05, "loss": 1.1418, "step": 56000 }, { "epoch": 0.06, "learning_rate": 4.679711770650558e-05, "loss": 1.1524, "step": 56500 }, { "epoch": 0.06, "learning_rate": 4.6768762072411215e-05, "loss": 1.1433, "step": 57000 }, { "epoch": 0.07, "learning_rate": 4.674040643831686e-05, "loss": 1.1457, "step": 57500 }, { "epoch": 0.07, "learning_rate": 4.67120508042225e-05, "loss": 1.1497, "step": 58000 }, { "epoch": 0.07, "learning_rate": 4.668375188139632e-05, "loss": 1.1427, "step": 58500 }, { "epoch": 0.07, "learning_rate": 4.6655396247301965e-05, "loss": 1.14, "step": 59000 }, { "epoch": 0.07, "learning_rate": 4.66270406132076e-05, "loss": 1.1461, "step": 59500 }, { "epoch": 0.07, "learning_rate": 4.659868497911324e-05, "loss": 1.1371, "step": 60000 }, { "epoch": 0.07, "learning_rate": 4.6570386056287066e-05, "loss": 1.137, "step": 60500 }, { "epoch": 0.07, "learning_rate": 4.6542030422192715e-05, "loss": 1.141, "step": 61000 }, { "epoch": 0.07, "learning_rate": 4.651367478809835e-05, "loss": 1.1325, "step": 61500 }, { "epoch": 0.07, "learning_rate": 4.648537586527218e-05, "loss": 1.1385, "step": 62000 }, { "epoch": 0.07, "learning_rate": 4.6457020231177816e-05, "loss": 1.1444, "step": 62500 }, { "epoch": 0.07, "learning_rate": 4.642866459708345e-05, "loss": 1.141, "step": 63000 }, { "epoch": 0.07, "learning_rate": 4.6400308962989093e-05, "loss": 1.1354, "step": 63500 }, { "epoch": 0.07, "learning_rate": 4.6371953328894735e-05, "loss": 1.1478, "step": 64000 }, { "epoch": 0.07, "learning_rate": 4.634359769480037e-05, "loss": 1.1372, "step": 64500 }, { "epoch": 0.07, "learning_rate": 4.631524206070601e-05, "loss": 1.1286, "step": 65000 }, { "epoch": 0.07, "learning_rate": 4.6286943137879843e-05, "loss": 1.1348, "step": 65500 }, { "epoch": 0.07, "learning_rate": 4.625858750378548e-05, "loss": 1.1296, "step": 66000 }, { "epoch": 0.08, "learning_rate": 4.623028858095931e-05, "loss": 1.1325, "step": 66500 }, { "epoch": 0.08, "learning_rate": 4.6201932946864945e-05, "loss": 1.1338, "step": 67000 }, { "epoch": 0.08, "learning_rate": 4.617357731277059e-05, "loss": 1.132, "step": 67500 }, { "epoch": 0.08, "learning_rate": 4.614522167867623e-05, "loss": 1.1414, "step": 68000 }, { "epoch": 0.08, "learning_rate": 4.6116866044581864e-05, "loss": 1.1266, "step": 68500 }, { "epoch": 0.08, "learning_rate": 4.60885104104875e-05, "loss": 1.1294, "step": 69000 }, { "epoch": 0.08, "learning_rate": 4.606015477639314e-05, "loss": 1.1278, "step": 69500 }, { "epoch": 0.08, "learning_rate": 4.6031855853566965e-05, "loss": 1.1262, "step": 70000 }, { "epoch": 0.08, "learning_rate": 4.6003500219472614e-05, "loss": 1.1395, "step": 70500 }, { "epoch": 0.08, "learning_rate": 4.597514458537825e-05, "loss": 1.1315, "step": 71000 }, { "epoch": 0.08, "learning_rate": 4.5946788951283884e-05, "loss": 1.1319, "step": 71500 }, { "epoch": 0.08, "learning_rate": 4.5918433317189526e-05, "loss": 1.1272, "step": 72000 }, { "epoch": 0.08, "learning_rate": 4.589007768309517e-05, "loss": 1.1259, "step": 72500 }, { "epoch": 0.08, "learning_rate": 4.5861722049000804e-05, "loss": 1.1353, "step": 73000 }, { "epoch": 0.08, "learning_rate": 4.5833366414906446e-05, "loss": 1.1257, "step": 73500 }, { "epoch": 0.08, "learning_rate": 4.580501078081209e-05, "loss": 1.128, "step": 74000 }, { "epoch": 0.08, "learning_rate": 4.577665514671772e-05, "loss": 1.1318, "step": 74500 }, { "epoch": 0.09, "learning_rate": 4.5748356223891554e-05, "loss": 1.1273, "step": 75000 }, { "epoch": 0.09, "learning_rate": 4.572000058979719e-05, "loss": 1.1279, "step": 75500 }, { "epoch": 0.09, "learning_rate": 4.569170166697102e-05, "loss": 1.1378, "step": 76000 }, { "epoch": 0.09, "learning_rate": 4.5663346032876655e-05, "loss": 1.1314, "step": 76500 }, { "epoch": 0.09, "learning_rate": 4.56349903987823e-05, "loss": 1.1322, "step": 77000 }, { "epoch": 0.09, "learning_rate": 4.560663476468794e-05, "loss": 1.1253, "step": 77500 }, { "epoch": 0.09, "learning_rate": 4.5578279130593574e-05, "loss": 1.1267, "step": 78000 }, { "epoch": 0.09, "learning_rate": 4.5549923496499216e-05, "loss": 1.1214, "step": 78500 }, { "epoch": 0.09, "learning_rate": 4.552156786240486e-05, "loss": 1.1325, "step": 79000 }, { "epoch": 0.09, "learning_rate": 4.5493212228310493e-05, "loss": 1.1245, "step": 79500 }, { "epoch": 0.09, "learning_rate": 4.546485659421613e-05, "loss": 1.1287, "step": 80000 }, { "epoch": 0.09, "learning_rate": 4.543650096012178e-05, "loss": 1.1274, "step": 80500 }, { "epoch": 0.09, "learning_rate": 4.540814532602741e-05, "loss": 1.1321, "step": 81000 }, { "epoch": 0.09, "learning_rate": 4.537978969193305e-05, "loss": 1.1246, "step": 81500 }, { "epoch": 0.09, "learning_rate": 4.535143405783869e-05, "loss": 1.1176, "step": 82000 }, { "epoch": 0.09, "learning_rate": 4.532313513501252e-05, "loss": 1.1291, "step": 82500 }, { "epoch": 0.09, "learning_rate": 4.5294779500918156e-05, "loss": 1.1186, "step": 83000 }, { "epoch": 0.09, "learning_rate": 4.52664238668238e-05, "loss": 1.1247, "step": 83500 }, { "epoch": 0.1, "learning_rate": 4.523812494399762e-05, "loss": 1.1236, "step": 84000 }, { "epoch": 0.1, "learning_rate": 4.5209769309903264e-05, "loss": 1.1217, "step": 84500 }, { "epoch": 0.1, "learning_rate": 4.5181413675808906e-05, "loss": 1.1094, "step": 85000 }, { "epoch": 0.1, "learning_rate": 4.515305804171454e-05, "loss": 1.1224, "step": 85500 }, { "epoch": 0.1, "learning_rate": 4.512470240762018e-05, "loss": 1.1217, "step": 86000 }, { "epoch": 0.1, "learning_rate": 4.509634677352582e-05, "loss": 1.1242, "step": 86500 }, { "epoch": 0.1, "learning_rate": 4.506799113943146e-05, "loss": 1.119, "step": 87000 }, { "epoch": 0.1, "learning_rate": 4.50396355053371e-05, "loss": 1.1181, "step": 87500 }, { "epoch": 0.1, "learning_rate": 4.501127987124274e-05, "loss": 1.1154, "step": 88000 }, { "epoch": 0.1, "learning_rate": 4.498292423714838e-05, "loss": 1.1226, "step": 88500 }, { "epoch": 0.1, "learning_rate": 4.4954568603054015e-05, "loss": 1.1146, "step": 89000 }, { "epoch": 0.1, "learning_rate": 4.492621296895966e-05, "loss": 1.1202, "step": 89500 }, { "epoch": 0.1, "learning_rate": 4.489785733486529e-05, "loss": 1.0994, "step": 90000 }, { "epoch": 0.1, "learning_rate": 4.486955841203912e-05, "loss": 1.1205, "step": 90500 }, { "epoch": 0.1, "learning_rate": 4.4841202777944765e-05, "loss": 1.121, "step": 91000 }, { "epoch": 0.1, "learning_rate": 4.48128471438504e-05, "loss": 1.1109, "step": 91500 }, { "epoch": 0.1, "learning_rate": 4.478449150975604e-05, "loss": 1.1127, "step": 92000 }, { "epoch": 0.1, "learning_rate": 4.4756135875661684e-05, "loss": 1.1177, "step": 92500 }, { "epoch": 0.11, "learning_rate": 4.472778024156732e-05, "loss": 1.1124, "step": 93000 }, { "epoch": 0.11, "learning_rate": 4.469948131874115e-05, "loss": 1.1209, "step": 93500 }, { "epoch": 0.11, "learning_rate": 4.4671125684646785e-05, "loss": 1.1206, "step": 94000 }, { "epoch": 0.11, "learning_rate": 4.464277005055243e-05, "loss": 1.1107, "step": 94500 }, { "epoch": 0.11, "learning_rate": 4.461441441645807e-05, "loss": 1.1137, "step": 95000 }, { "epoch": 0.11, "learning_rate": 4.4586058782363705e-05, "loss": 1.1213, "step": 95500 }, { "epoch": 0.11, "learning_rate": 4.4557759859537535e-05, "loss": 1.1106, "step": 96000 }, { "epoch": 0.11, "learning_rate": 4.452940422544317e-05, "loss": 1.1123, "step": 96500 }, { "epoch": 0.11, "learning_rate": 4.450104859134881e-05, "loss": 1.1174, "step": 97000 }, { "epoch": 0.11, "learning_rate": 4.447274966852264e-05, "loss": 1.1023, "step": 97500 }, { "epoch": 0.11, "learning_rate": 4.444445074569647e-05, "loss": 1.1074, "step": 98000 }, { "epoch": 0.11, "learning_rate": 4.441609511160211e-05, "loss": 1.1233, "step": 98500 }, { "epoch": 0.11, "learning_rate": 4.4387739477507745e-05, "loss": 1.119, "step": 99000 }, { "epoch": 0.11, "learning_rate": 4.435938384341339e-05, "loss": 1.1247, "step": 99500 }, { "epoch": 0.11, "learning_rate": 4.433108492058721e-05, "loss": 1.1054, "step": 100000 }, { "epoch": 0.11, "learning_rate": 4.430272928649285e-05, "loss": 1.1037, "step": 100500 }, { "epoch": 0.11, "learning_rate": 4.4274373652398495e-05, "loss": 1.1209, "step": 101000 }, { "epoch": 0.12, "learning_rate": 4.424601801830413e-05, "loss": 1.1118, "step": 101500 }, { "epoch": 0.12, "learning_rate": 4.4217662384209765e-05, "loss": 1.1099, "step": 102000 }, { "epoch": 0.12, "learning_rate": 4.4189306750115414e-05, "loss": 1.1069, "step": 102500 }, { "epoch": 0.12, "learning_rate": 4.416095111602105e-05, "loss": 1.1166, "step": 103000 }, { "epoch": 0.12, "learning_rate": 4.4132595481926684e-05, "loss": 1.1263, "step": 103500 }, { "epoch": 0.12, "learning_rate": 4.4104239847832326e-05, "loss": 1.1107, "step": 104000 }, { "epoch": 0.12, "learning_rate": 4.407588421373797e-05, "loss": 1.1145, "step": 104500 }, { "epoch": 0.12, "learning_rate": 4.40475852909118e-05, "loss": 1.1109, "step": 105000 }, { "epoch": 0.12, "learning_rate": 4.4019229656817435e-05, "loss": 1.1037, "step": 105500 }, { "epoch": 0.12, "learning_rate": 4.399087402272307e-05, "loss": 1.1023, "step": 106000 }, { "epoch": 0.12, "learning_rate": 4.396251838862871e-05, "loss": 1.1152, "step": 106500 }, { "epoch": 0.12, "learning_rate": 4.3934162754534354e-05, "loss": 1.1259, "step": 107000 }, { "epoch": 0.12, "learning_rate": 4.390580712043999e-05, "loss": 1.1106, "step": 107500 }, { "epoch": 0.12, "learning_rate": 4.387745148634563e-05, "loss": 1.1024, "step": 108000 }, { "epoch": 0.12, "learning_rate": 4.3849152563519455e-05, "loss": 1.1107, "step": 108500 }, { "epoch": 0.12, "learning_rate": 4.38207969294251e-05, "loss": 1.1101, "step": 109000 }, { "epoch": 0.12, "learning_rate": 4.379244129533074e-05, "loss": 1.1149, "step": 109500 }, { "epoch": 0.12, "learning_rate": 4.3764085661236374e-05, "loss": 1.1109, "step": 110000 }, { "epoch": 0.13, "learning_rate": 4.3735786738410205e-05, "loss": 1.1148, "step": 110500 }, { "epoch": 0.13, "learning_rate": 4.370748781558403e-05, "loss": 1.1078, "step": 111000 }, { "epoch": 0.13, "learning_rate": 4.367913218148967e-05, "loss": 1.1108, "step": 111500 }, { "epoch": 0.13, "learning_rate": 4.365077654739531e-05, "loss": 1.1025, "step": 112000 }, { "epoch": 0.13, "learning_rate": 4.362247762456914e-05, "loss": 1.1018, "step": 112500 }, { "epoch": 0.13, "learning_rate": 4.359412199047478e-05, "loss": 1.1211, "step": 113000 }, { "epoch": 0.13, "learning_rate": 4.3565766356380414e-05, "loss": 1.1098, "step": 113500 }, { "epoch": 0.13, "learning_rate": 4.3537410722286056e-05, "loss": 1.1044, "step": 114000 }, { "epoch": 0.13, "learning_rate": 4.35090550881917e-05, "loss": 1.103, "step": 114500 }, { "epoch": 0.13, "learning_rate": 4.3480699454097334e-05, "loss": 1.1096, "step": 115000 }, { "epoch": 0.13, "learning_rate": 4.345234382000297e-05, "loss": 1.103, "step": 115500 }, { "epoch": 0.13, "learning_rate": 4.342398818590862e-05, "loss": 1.1027, "step": 116000 }, { "epoch": 0.13, "learning_rate": 4.339563255181425e-05, "loss": 1.1022, "step": 116500 }, { "epoch": 0.13, "learning_rate": 4.336727691771989e-05, "loss": 1.1095, "step": 117000 }, { "epoch": 0.13, "learning_rate": 4.333892128362553e-05, "loss": 1.0986, "step": 117500 }, { "epoch": 0.13, "learning_rate": 4.331056564953117e-05, "loss": 1.0942, "step": 118000 }, { "epoch": 0.13, "learning_rate": 4.328221001543681e-05, "loss": 1.1055, "step": 118500 }, { "epoch": 0.13, "learning_rate": 4.325385438134245e-05, "loss": 1.1031, "step": 119000 }, { "epoch": 0.14, "learning_rate": 4.322555545851627e-05, "loss": 1.1006, "step": 119500 }, { "epoch": 0.14, "learning_rate": 4.3197199824421915e-05, "loss": 1.1081, "step": 120000 }, { "epoch": 0.14, "learning_rate": 4.316884419032756e-05, "loss": 1.0948, "step": 120500 }, { "epoch": 0.14, "learning_rate": 4.314048855623319e-05, "loss": 1.0963, "step": 121000 }, { "epoch": 0.14, "learning_rate": 4.311218963340702e-05, "loss": 1.1024, "step": 121500 }, { "epoch": 0.14, "learning_rate": 4.308383399931266e-05, "loss": 1.1126, "step": 122000 }, { "epoch": 0.14, "learning_rate": 4.30554783652183e-05, "loss": 1.0998, "step": 122500 }, { "epoch": 0.14, "learning_rate": 4.302712273112394e-05, "loss": 1.0975, "step": 123000 }, { "epoch": 0.14, "learning_rate": 4.299876709702958e-05, "loss": 1.098, "step": 123500 }, { "epoch": 0.14, "learning_rate": 4.297041146293522e-05, "loss": 1.0997, "step": 124000 }, { "epoch": 0.14, "learning_rate": 4.294205582884086e-05, "loss": 1.1036, "step": 124500 }, { "epoch": 0.14, "learning_rate": 4.2913756906014686e-05, "loss": 1.1071, "step": 125000 }, { "epoch": 0.14, "learning_rate": 4.288545798318852e-05, "loss": 1.0956, "step": 125500 }, { "epoch": 0.14, "learning_rate": 4.285710234909415e-05, "loss": 1.0978, "step": 126000 }, { "epoch": 0.14, "learning_rate": 4.282880342626798e-05, "loss": 1.1087, "step": 126500 }, { "epoch": 0.14, "learning_rate": 4.280044779217362e-05, "loss": 1.094, "step": 127000 }, { "epoch": 0.14, "learning_rate": 4.277209215807926e-05, "loss": 1.0898, "step": 127500 }, { "epoch": 0.15, "learning_rate": 4.27437365239849e-05, "loss": 1.0999, "step": 128000 }, { "epoch": 0.15, "learning_rate": 4.271538088989054e-05, "loss": 1.1047, "step": 128500 }, { "epoch": 0.15, "learning_rate": 4.268702525579618e-05, "loss": 1.0952, "step": 129000 }, { "epoch": 0.15, "learning_rate": 4.265866962170182e-05, "loss": 1.0901, "step": 129500 }, { "epoch": 0.15, "learning_rate": 4.2630313987607456e-05, "loss": 1.1066, "step": 130000 }, { "epoch": 0.15, "learning_rate": 4.260201506478128e-05, "loss": 1.1087, "step": 130500 }, { "epoch": 0.15, "learning_rate": 4.257371614195511e-05, "loss": 1.097, "step": 131000 }, { "epoch": 0.15, "learning_rate": 4.2545360507860747e-05, "loss": 1.1003, "step": 131500 }, { "epoch": 0.15, "learning_rate": 4.251700487376639e-05, "loss": 1.0966, "step": 132000 }, { "epoch": 0.15, "learning_rate": 4.248864923967203e-05, "loss": 1.0973, "step": 132500 }, { "epoch": 0.15, "learning_rate": 4.2460293605577666e-05, "loss": 1.0905, "step": 133000 }, { "epoch": 0.15, "learning_rate": 4.243193797148331e-05, "loss": 1.1033, "step": 133500 }, { "epoch": 0.15, "learning_rate": 4.240358233738895e-05, "loss": 1.0993, "step": 134000 }, { "epoch": 0.15, "learning_rate": 4.2375226703294585e-05, "loss": 1.1042, "step": 134500 }, { "epoch": 0.15, "learning_rate": 4.234687106920023e-05, "loss": 1.1049, "step": 135000 }, { "epoch": 0.15, "learning_rate": 4.231851543510586e-05, "loss": 1.1044, "step": 135500 }, { "epoch": 0.15, "learning_rate": 4.229021651227969e-05, "loss": 1.1066, "step": 136000 }, { "epoch": 0.15, "learning_rate": 4.2261860878185335e-05, "loss": 1.0993, "step": 136500 }, { "epoch": 0.16, "learning_rate": 4.223350524409097e-05, "loss": 1.0956, "step": 137000 }, { "epoch": 0.16, "learning_rate": 4.2205149609996605e-05, "loss": 1.0968, "step": 137500 }, { "epoch": 0.16, "learning_rate": 4.2176793975902254e-05, "loss": 1.0987, "step": 138000 }, { "epoch": 0.16, "learning_rate": 4.214849505307608e-05, "loss": 1.0942, "step": 138500 }, { "epoch": 0.16, "learning_rate": 4.212013941898172e-05, "loss": 1.0911, "step": 139000 }, { "epoch": 0.16, "learning_rate": 4.2091783784887355e-05, "loss": 1.0987, "step": 139500 }, { "epoch": 0.16, "learning_rate": 4.206342815079299e-05, "loss": 1.0996, "step": 140000 }, { "epoch": 0.16, "learning_rate": 4.203507251669864e-05, "loss": 1.0917, "step": 140500 }, { "epoch": 0.16, "learning_rate": 4.2006716882604275e-05, "loss": 1.0973, "step": 141000 }, { "epoch": 0.16, "learning_rate": 4.197836124850991e-05, "loss": 1.1076, "step": 141500 }, { "epoch": 0.16, "learning_rate": 4.195000561441555e-05, "loss": 1.0885, "step": 142000 }, { "epoch": 0.16, "learning_rate": 4.1921649980321194e-05, "loss": 1.0938, "step": 142500 }, { "epoch": 0.16, "learning_rate": 4.189329434622683e-05, "loss": 1.0964, "step": 143000 }, { "epoch": 0.16, "learning_rate": 4.186493871213247e-05, "loss": 1.0999, "step": 143500 }, { "epoch": 0.16, "learning_rate": 4.183658307803811e-05, "loss": 1.0868, "step": 144000 }, { "epoch": 0.16, "learning_rate": 4.180822744394375e-05, "loss": 1.0868, "step": 144500 }, { "epoch": 0.16, "learning_rate": 4.1779871809849384e-05, "loss": 1.0857, "step": 145000 }, { "epoch": 0.17, "learning_rate": 4.1751572887023214e-05, "loss": 1.0877, "step": 145500 }, { "epoch": 0.17, "learning_rate": 4.1723217252928856e-05, "loss": 1.096, "step": 146000 }, { "epoch": 0.17, "learning_rate": 4.169491833010268e-05, "loss": 1.0915, "step": 146500 }, { "epoch": 0.17, "learning_rate": 4.166656269600832e-05, "loss": 1.0894, "step": 147000 }, { "epoch": 0.17, "learning_rate": 4.1638207061913964e-05, "loss": 1.0959, "step": 147500 }, { "epoch": 0.17, "learning_rate": 4.16098514278196e-05, "loss": 1.0915, "step": 148000 }, { "epoch": 0.17, "learning_rate": 4.158155250499343e-05, "loss": 1.0851, "step": 148500 }, { "epoch": 0.17, "learning_rate": 4.155319687089907e-05, "loss": 1.0984, "step": 149000 }, { "epoch": 0.17, "learning_rate": 4.152484123680471e-05, "loss": 1.0902, "step": 149500 }, { "epoch": 0.17, "learning_rate": 4.149654231397854e-05, "loss": 1.0895, "step": 150000 }, { "epoch": 0.17, "learning_rate": 4.1468186679884174e-05, "loss": 1.0867, "step": 150500 }, { "epoch": 0.17, "learning_rate": 4.143983104578981e-05, "loss": 1.0924, "step": 151000 }, { "epoch": 0.17, "learning_rate": 4.141147541169546e-05, "loss": 1.0795, "step": 151500 }, { "epoch": 0.17, "learning_rate": 4.138311977760109e-05, "loss": 1.0907, "step": 152000 }, { "epoch": 0.17, "learning_rate": 4.135476414350673e-05, "loss": 1.0914, "step": 152500 }, { "epoch": 0.17, "learning_rate": 4.132646522068056e-05, "loss": 1.0896, "step": 153000 }, { "epoch": 0.17, "learning_rate": 4.12981095865862e-05, "loss": 1.0801, "step": 153500 }, { "epoch": 0.17, "learning_rate": 4.126975395249184e-05, "loss": 1.0953, "step": 154000 }, { "epoch": 0.18, "learning_rate": 4.124139831839748e-05, "loss": 1.0908, "step": 154500 }, { "epoch": 0.18, "learning_rate": 4.12130993955713e-05, "loss": 1.0882, "step": 155000 }, { "epoch": 0.18, "learning_rate": 4.1184743761476944e-05, "loss": 1.0917, "step": 155500 }, { "epoch": 0.18, "learning_rate": 4.1156388127382586e-05, "loss": 1.0837, "step": 156000 }, { "epoch": 0.18, "learning_rate": 4.112803249328822e-05, "loss": 1.0893, "step": 156500 }, { "epoch": 0.18, "learning_rate": 4.1099676859193864e-05, "loss": 1.099, "step": 157000 }, { "epoch": 0.18, "learning_rate": 4.10713212250995e-05, "loss": 1.0879, "step": 157500 }, { "epoch": 0.18, "learning_rate": 4.104296559100514e-05, "loss": 1.0878, "step": 158000 }, { "epoch": 0.18, "learning_rate": 4.101460995691078e-05, "loss": 1.0789, "step": 158500 }, { "epoch": 0.18, "learning_rate": 4.098625432281642e-05, "loss": 1.0858, "step": 159000 }, { "epoch": 0.18, "learning_rate": 4.095789868872206e-05, "loss": 1.0892, "step": 159500 }, { "epoch": 0.18, "learning_rate": 4.09295430546277e-05, "loss": 1.0869, "step": 160000 }, { "epoch": 0.18, "learning_rate": 4.0901244131801526e-05, "loss": 1.0855, "step": 160500 }, { "epoch": 0.18, "learning_rate": 4.087288849770717e-05, "loss": 1.0937, "step": 161000 }, { "epoch": 0.18, "learning_rate": 4.084458957488099e-05, "loss": 1.0903, "step": 161500 }, { "epoch": 0.18, "learning_rate": 4.081623394078663e-05, "loss": 1.0806, "step": 162000 }, { "epoch": 0.18, "learning_rate": 4.0787878306692276e-05, "loss": 1.0861, "step": 162500 }, { "epoch": 0.18, "learning_rate": 4.075952267259791e-05, "loss": 1.0807, "step": 163000 }, { "epoch": 0.19, "learning_rate": 4.0731167038503547e-05, "loss": 1.0914, "step": 163500 }, { "epoch": 0.19, "learning_rate": 4.070281140440919e-05, "loss": 1.0872, "step": 164000 }, { "epoch": 0.19, "learning_rate": 4.067451248158301e-05, "loss": 1.0803, "step": 164500 }, { "epoch": 0.19, "learning_rate": 4.064615684748866e-05, "loss": 1.0973, "step": 165000 }, { "epoch": 0.19, "learning_rate": 4.0617801213394297e-05, "loss": 1.0788, "step": 165500 }, { "epoch": 0.19, "learning_rate": 4.058944557929993e-05, "loss": 1.0794, "step": 166000 }, { "epoch": 0.19, "learning_rate": 4.0561089945205574e-05, "loss": 1.0794, "step": 166500 }, { "epoch": 0.19, "learning_rate": 4.0532734311111216e-05, "loss": 1.0831, "step": 167000 }, { "epoch": 0.19, "learning_rate": 4.050437867701685e-05, "loss": 1.0809, "step": 167500 }, { "epoch": 0.19, "learning_rate": 4.047602304292249e-05, "loss": 1.0758, "step": 168000 }, { "epoch": 0.19, "learning_rate": 4.0447667408828135e-05, "loss": 1.094, "step": 168500 }, { "epoch": 0.19, "learning_rate": 4.041931177473377e-05, "loss": 1.0886, "step": 169000 }, { "epoch": 0.19, "learning_rate": 4.0390956140639405e-05, "loss": 1.0821, "step": 169500 }, { "epoch": 0.19, "learning_rate": 4.036260050654505e-05, "loss": 1.0738, "step": 170000 }, { "epoch": 0.19, "learning_rate": 4.033424487245069e-05, "loss": 1.0809, "step": 170500 }, { "epoch": 0.19, "learning_rate": 4.030594594962452e-05, "loss": 1.0909, "step": 171000 }, { "epoch": 0.19, "learning_rate": 4.0277590315530155e-05, "loss": 1.086, "step": 171500 }, { "epoch": 0.2, "learning_rate": 4.024923468143579e-05, "loss": 1.0798, "step": 172000 }, { "epoch": 0.2, "learning_rate": 4.022087904734144e-05, "loss": 1.0911, "step": 172500 }, { "epoch": 0.2, "learning_rate": 4.0192580124515264e-05, "loss": 1.0834, "step": 173000 }, { "epoch": 0.2, "learning_rate": 4.0164224490420906e-05, "loss": 1.0834, "step": 173500 }, { "epoch": 0.2, "learning_rate": 4.013592556759473e-05, "loss": 1.0755, "step": 174000 }, { "epoch": 0.2, "learning_rate": 4.0107569933500365e-05, "loss": 1.0855, "step": 174500 }, { "epoch": 0.2, "learning_rate": 4.0079271010674196e-05, "loss": 1.077, "step": 175000 }, { "epoch": 0.2, "learning_rate": 4.005091537657983e-05, "loss": 1.0917, "step": 175500 }, { "epoch": 0.2, "learning_rate": 4.002255974248548e-05, "loss": 1.0744, "step": 176000 }, { "epoch": 0.2, "learning_rate": 3.9994204108391115e-05, "loss": 1.0882, "step": 176500 }, { "epoch": 0.2, "learning_rate": 3.996584847429675e-05, "loss": 1.081, "step": 177000 }, { "epoch": 0.2, "learning_rate": 3.993749284020239e-05, "loss": 1.0818, "step": 177500 }, { "epoch": 0.2, "learning_rate": 3.9909137206108034e-05, "loss": 1.0766, "step": 178000 }, { "epoch": 0.2, "learning_rate": 3.988078157201367e-05, "loss": 1.0843, "step": 178500 }, { "epoch": 0.2, "learning_rate": 3.985242593791931e-05, "loss": 1.0836, "step": 179000 }, { "epoch": 0.2, "learning_rate": 3.982407030382495e-05, "loss": 1.0837, "step": 179500 }, { "epoch": 0.2, "learning_rate": 3.979571466973059e-05, "loss": 1.0808, "step": 180000 }, { "epoch": 0.2, "learning_rate": 3.976735903563623e-05, "loss": 1.0773, "step": 180500 }, { "epoch": 0.21, "learning_rate": 3.9739003401541866e-05, "loss": 1.0918, "step": 181000 }, { "epoch": 0.21, "learning_rate": 3.971064776744751e-05, "loss": 1.085, "step": 181500 }, { "epoch": 0.21, "learning_rate": 3.968229213335314e-05, "loss": 1.081, "step": 182000 }, { "epoch": 0.21, "learning_rate": 3.9653936499258785e-05, "loss": 1.0789, "step": 182500 }, { "epoch": 0.21, "learning_rate": 3.962563757643261e-05, "loss": 1.0768, "step": 183000 }, { "epoch": 0.21, "learning_rate": 3.959728194233826e-05, "loss": 1.0727, "step": 183500 }, { "epoch": 0.21, "learning_rate": 3.956892630824389e-05, "loss": 1.0834, "step": 184000 }, { "epoch": 0.21, "learning_rate": 3.954057067414953e-05, "loss": 1.0872, "step": 184500 }, { "epoch": 0.21, "learning_rate": 3.951227175132336e-05, "loss": 1.0829, "step": 185000 }, { "epoch": 0.21, "learning_rate": 3.9483916117228994e-05, "loss": 1.083, "step": 185500 }, { "epoch": 0.21, "learning_rate": 3.945556048313464e-05, "loss": 1.0741, "step": 186000 }, { "epoch": 0.21, "learning_rate": 3.942720484904028e-05, "loss": 1.0697, "step": 186500 }, { "epoch": 0.21, "learning_rate": 3.93989059262141e-05, "loss": 1.0813, "step": 187000 }, { "epoch": 0.21, "learning_rate": 3.9370550292119744e-05, "loss": 1.0761, "step": 187500 }, { "epoch": 0.21, "learning_rate": 3.9342194658025386e-05, "loss": 1.0703, "step": 188000 }, { "epoch": 0.21, "learning_rate": 3.931383902393102e-05, "loss": 1.0769, "step": 188500 }, { "epoch": 0.21, "learning_rate": 3.928554010110485e-05, "loss": 1.0751, "step": 189000 }, { "epoch": 0.21, "learning_rate": 3.925718446701049e-05, "loss": 1.0826, "step": 189500 }, { "epoch": 0.22, "learning_rate": 3.922882883291613e-05, "loss": 1.0833, "step": 190000 }, { "epoch": 0.22, "learning_rate": 3.920047319882177e-05, "loss": 1.0772, "step": 190500 }, { "epoch": 0.22, "learning_rate": 3.9172174275995596e-05, "loss": 1.086, "step": 191000 }, { "epoch": 0.22, "learning_rate": 3.914381864190124e-05, "loss": 1.0773, "step": 191500 }, { "epoch": 0.22, "learning_rate": 3.911551971907506e-05, "loss": 1.0649, "step": 192000 }, { "epoch": 0.22, "learning_rate": 3.9087164084980704e-05, "loss": 1.0756, "step": 192500 }, { "epoch": 0.22, "learning_rate": 3.905880845088634e-05, "loss": 1.0754, "step": 193000 }, { "epoch": 0.22, "learning_rate": 3.903045281679198e-05, "loss": 1.0733, "step": 193500 }, { "epoch": 0.22, "learning_rate": 3.900209718269762e-05, "loss": 1.0722, "step": 194000 }, { "epoch": 0.22, "learning_rate": 3.897379825987145e-05, "loss": 1.0726, "step": 194500 }, { "epoch": 0.22, "learning_rate": 3.894549933704528e-05, "loss": 1.0719, "step": 195000 }, { "epoch": 0.22, "learning_rate": 3.891714370295091e-05, "loss": 1.0746, "step": 195500 }, { "epoch": 0.22, "learning_rate": 3.8888788068856555e-05, "loss": 1.0777, "step": 196000 }, { "epoch": 0.22, "learning_rate": 3.88604324347622e-05, "loss": 1.0766, "step": 196500 }, { "epoch": 0.22, "learning_rate": 3.883207680066783e-05, "loss": 1.0698, "step": 197000 }, { "epoch": 0.22, "learning_rate": 3.8803721166573474e-05, "loss": 1.0802, "step": 197500 }, { "epoch": 0.22, "learning_rate": 3.8775365532479116e-05, "loss": 1.0729, "step": 198000 }, { "epoch": 0.23, "learning_rate": 3.874700989838475e-05, "loss": 1.0793, "step": 198500 }, { "epoch": 0.23, "learning_rate": 3.871865426429039e-05, "loss": 1.0716, "step": 199000 }, { "epoch": 0.23, "learning_rate": 3.869029863019603e-05, "loss": 1.0747, "step": 199500 }, { "epoch": 0.23, "learning_rate": 3.866194299610167e-05, "loss": 1.0826, "step": 200000 }, { "epoch": 0.23, "learning_rate": 3.86336440732755e-05, "loss": 1.0724, "step": 200500 }, { "epoch": 0.23, "learning_rate": 3.8605345150449326e-05, "loss": 1.067, "step": 201000 }, { "epoch": 0.23, "learning_rate": 3.857698951635497e-05, "loss": 1.0701, "step": 201500 }, { "epoch": 0.23, "learning_rate": 3.85486338822606e-05, "loss": 1.0726, "step": 202000 }, { "epoch": 0.23, "learning_rate": 3.8520278248166245e-05, "loss": 1.073, "step": 202500 }, { "epoch": 0.23, "learning_rate": 3.849192261407189e-05, "loss": 1.0718, "step": 203000 }, { "epoch": 0.23, "learning_rate": 3.846356697997752e-05, "loss": 1.0829, "step": 203500 }, { "epoch": 0.23, "learning_rate": 3.843521134588316e-05, "loss": 1.0724, "step": 204000 }, { "epoch": 0.23, "learning_rate": 3.840691242305699e-05, "loss": 1.0734, "step": 204500 }, { "epoch": 0.23, "learning_rate": 3.837855678896263e-05, "loss": 1.0741, "step": 205000 }, { "epoch": 0.23, "learning_rate": 3.8350201154868265e-05, "loss": 1.0681, "step": 205500 }, { "epoch": 0.23, "learning_rate": 3.832184552077391e-05, "loss": 1.0762, "step": 206000 }, { "epoch": 0.23, "learning_rate": 3.829348988667954e-05, "loss": 1.0755, "step": 206500 }, { "epoch": 0.23, "learning_rate": 3.8265134252585185e-05, "loss": 1.0728, "step": 207000 }, { "epoch": 0.24, "learning_rate": 3.8236778618490826e-05, "loss": 1.0674, "step": 207500 }, { "epoch": 0.24, "learning_rate": 3.820842298439646e-05, "loss": 1.0653, "step": 208000 }, { "epoch": 0.24, "learning_rate": 3.8180067350302104e-05, "loss": 1.0694, "step": 208500 }, { "epoch": 0.24, "learning_rate": 3.8151768427475935e-05, "loss": 1.0635, "step": 209000 }, { "epoch": 0.24, "learning_rate": 3.812341279338157e-05, "loss": 1.0777, "step": 209500 }, { "epoch": 0.24, "learning_rate": 3.809505715928721e-05, "loss": 1.0659, "step": 210000 }, { "epoch": 0.24, "learning_rate": 3.806670152519285e-05, "loss": 1.0675, "step": 210500 }, { "epoch": 0.24, "learning_rate": 3.803834589109849e-05, "loss": 1.0763, "step": 211000 }, { "epoch": 0.24, "learning_rate": 3.8009990257004124e-05, "loss": 1.0518, "step": 211500 }, { "epoch": 0.24, "learning_rate": 3.7981634622909766e-05, "loss": 1.0768, "step": 212000 }, { "epoch": 0.24, "learning_rate": 3.795327898881541e-05, "loss": 1.0753, "step": 212500 }, { "epoch": 0.24, "learning_rate": 3.7924923354721043e-05, "loss": 1.067, "step": 213000 }, { "epoch": 0.24, "learning_rate": 3.7896624431894874e-05, "loss": 1.0686, "step": 213500 }, { "epoch": 0.24, "learning_rate": 3.786826879780051e-05, "loss": 1.0754, "step": 214000 }, { "epoch": 0.24, "learning_rate": 3.783991316370615e-05, "loss": 1.0623, "step": 214500 }, { "epoch": 0.24, "learning_rate": 3.7811557529611793e-05, "loss": 1.0638, "step": 215000 }, { "epoch": 0.24, "learning_rate": 3.778320189551743e-05, "loss": 1.0659, "step": 215500 }, { "epoch": 0.24, "learning_rate": 3.775484626142307e-05, "loss": 1.0634, "step": 216000 }, { "epoch": 0.25, "learning_rate": 3.7726490627328706e-05, "loss": 1.0814, "step": 216500 }, { "epoch": 0.25, "learning_rate": 3.769813499323435e-05, "loss": 1.0723, "step": 217000 }, { "epoch": 0.25, "learning_rate": 3.766983607040818e-05, "loss": 1.0724, "step": 217500 }, { "epoch": 0.25, "learning_rate": 3.7641480436313814e-05, "loss": 1.0654, "step": 218000 }, { "epoch": 0.25, "learning_rate": 3.761312480221945e-05, "loss": 1.0594, "step": 218500 }, { "epoch": 0.25, "learning_rate": 3.75847691681251e-05, "loss": 1.0684, "step": 219000 }, { "epoch": 0.25, "learning_rate": 3.755641353403073e-05, "loss": 1.0603, "step": 219500 }, { "epoch": 0.25, "learning_rate": 3.7528114611204564e-05, "loss": 1.0627, "step": 220000 }, { "epoch": 0.25, "learning_rate": 3.749981568837839e-05, "loss": 1.0682, "step": 220500 }, { "epoch": 0.25, "learning_rate": 3.747146005428403e-05, "loss": 1.0624, "step": 221000 }, { "epoch": 0.25, "learning_rate": 3.7443104420189665e-05, "loss": 1.0663, "step": 221500 }, { "epoch": 0.25, "learning_rate": 3.741474878609531e-05, "loss": 1.0591, "step": 222000 }, { "epoch": 0.25, "learning_rate": 3.738639315200095e-05, "loss": 1.0656, "step": 222500 }, { "epoch": 0.25, "learning_rate": 3.7358037517906585e-05, "loss": 1.0611, "step": 223000 }, { "epoch": 0.25, "learning_rate": 3.732968188381222e-05, "loss": 1.0673, "step": 223500 }, { "epoch": 0.25, "learning_rate": 3.730132624971786e-05, "loss": 1.0745, "step": 224000 }, { "epoch": 0.25, "learning_rate": 3.727302732689169e-05, "loss": 1.0636, "step": 224500 }, { "epoch": 0.26, "learning_rate": 3.724467169279733e-05, "loss": 1.0634, "step": 225000 }, { "epoch": 0.26, "learning_rate": 3.721631605870297e-05, "loss": 1.069, "step": 225500 }, { "epoch": 0.26, "learning_rate": 3.718796042460861e-05, "loss": 1.0601, "step": 226000 }, { "epoch": 0.26, "learning_rate": 3.715960479051425e-05, "loss": 1.0631, "step": 226500 }, { "epoch": 0.26, "learning_rate": 3.713124915641989e-05, "loss": 1.07, "step": 227000 }, { "epoch": 0.26, "learning_rate": 3.7102893522325524e-05, "loss": 1.0714, "step": 227500 }, { "epoch": 0.26, "learning_rate": 3.7074537888231166e-05, "loss": 1.0717, "step": 228000 }, { "epoch": 0.26, "learning_rate": 3.704618225413681e-05, "loss": 1.0608, "step": 228500 }, { "epoch": 0.26, "learning_rate": 3.7017826620042443e-05, "loss": 1.0585, "step": 229000 }, { "epoch": 0.26, "learning_rate": 3.6989527697216274e-05, "loss": 1.0588, "step": 229500 }, { "epoch": 0.26, "learning_rate": 3.69612287743901e-05, "loss": 1.0633, "step": 230000 }, { "epoch": 0.26, "learning_rate": 3.693287314029574e-05, "loss": 1.0741, "step": 230500 }, { "epoch": 0.26, "learning_rate": 3.690451750620138e-05, "loss": 1.0622, "step": 231000 }, { "epoch": 0.26, "learning_rate": 3.687616187210702e-05, "loss": 1.0739, "step": 231500 }, { "epoch": 0.26, "learning_rate": 3.684780623801265e-05, "loss": 1.0569, "step": 232000 }, { "epoch": 0.26, "learning_rate": 3.6819507315186484e-05, "loss": 1.064, "step": 232500 }, { "epoch": 0.26, "learning_rate": 3.6791151681092126e-05, "loss": 1.0649, "step": 233000 }, { "epoch": 0.26, "learning_rate": 3.6762852758265956e-05, "loss": 1.067, "step": 233500 }, { "epoch": 0.27, "learning_rate": 3.673449712417159e-05, "loss": 1.0709, "step": 234000 }, { "epoch": 0.27, "learning_rate": 3.6706141490077234e-05, "loss": 1.0565, "step": 234500 }, { "epoch": 0.27, "learning_rate": 3.667778585598287e-05, "loss": 1.0694, "step": 235000 }, { "epoch": 0.27, "learning_rate": 3.664943022188851e-05, "loss": 1.0597, "step": 235500 }, { "epoch": 0.27, "learning_rate": 3.6621074587794146e-05, "loss": 1.0597, "step": 236000 }, { "epoch": 0.27, "learning_rate": 3.659271895369979e-05, "loss": 1.0481, "step": 236500 }, { "epoch": 0.27, "learning_rate": 3.656436331960543e-05, "loss": 1.066, "step": 237000 }, { "epoch": 0.27, "learning_rate": 3.6536007685511065e-05, "loss": 1.0637, "step": 237500 }, { "epoch": 0.27, "learning_rate": 3.650765205141671e-05, "loss": 1.0579, "step": 238000 }, { "epoch": 0.27, "learning_rate": 3.647935312859053e-05, "loss": 1.0722, "step": 238500 }, { "epoch": 0.27, "learning_rate": 3.645105420576436e-05, "loss": 1.0723, "step": 239000 }, { "epoch": 0.27, "learning_rate": 3.642269857167e-05, "loss": 1.0714, "step": 239500 }, { "epoch": 0.27, "learning_rate": 3.6394342937575646e-05, "loss": 1.0566, "step": 240000 }, { "epoch": 0.27, "learning_rate": 3.636598730348128e-05, "loss": 1.062, "step": 240500 }, { "epoch": 0.27, "learning_rate": 3.633763166938692e-05, "loss": 1.0604, "step": 241000 }, { "epoch": 0.27, "learning_rate": 3.630927603529256e-05, "loss": 1.0525, "step": 241500 }, { "epoch": 0.27, "learning_rate": 3.62809204011982e-05, "loss": 1.0616, "step": 242000 }, { "epoch": 0.28, "learning_rate": 3.6252621478372025e-05, "loss": 1.061, "step": 242500 }, { "epoch": 0.28, "learning_rate": 3.622426584427767e-05, "loss": 1.0648, "step": 243000 }, { "epoch": 0.28, "learning_rate": 3.61959102101833e-05, "loss": 1.05, "step": 243500 }, { "epoch": 0.28, "learning_rate": 3.6167554576088944e-05, "loss": 1.0543, "step": 244000 }, { "epoch": 0.28, "learning_rate": 3.6139198941994586e-05, "loss": 1.0648, "step": 244500 }, { "epoch": 0.28, "learning_rate": 3.611084330790022e-05, "loss": 1.0633, "step": 245000 }, { "epoch": 0.28, "learning_rate": 3.608254438507405e-05, "loss": 1.0491, "step": 245500 }, { "epoch": 0.28, "learning_rate": 3.605418875097969e-05, "loss": 1.056, "step": 246000 }, { "epoch": 0.28, "learning_rate": 3.602583311688533e-05, "loss": 1.0641, "step": 246500 }, { "epoch": 0.28, "learning_rate": 3.599747748279097e-05, "loss": 1.0672, "step": 247000 }, { "epoch": 0.28, "learning_rate": 3.5969121848696606e-05, "loss": 1.0645, "step": 247500 }, { "epoch": 0.28, "learning_rate": 3.594082292587043e-05, "loss": 1.0632, "step": 248000 }, { "epoch": 0.28, "learning_rate": 3.591246729177607e-05, "loss": 1.0574, "step": 248500 }, { "epoch": 0.28, "learning_rate": 3.5884111657681714e-05, "loss": 1.0641, "step": 249000 }, { "epoch": 0.28, "learning_rate": 3.585575602358735e-05, "loss": 1.0603, "step": 249500 }, { "epoch": 0.28, "learning_rate": 3.582740038949299e-05, "loss": 1.0642, "step": 250000 }, { "epoch": 0.28, "learning_rate": 3.5799101466666816e-05, "loss": 1.0594, "step": 250500 }, { "epoch": 0.28, "learning_rate": 3.577074583257246e-05, "loss": 1.0665, "step": 251000 }, { "epoch": 0.29, "learning_rate": 3.57423901984781e-05, "loss": 1.0579, "step": 251500 }, { "epoch": 0.29, "learning_rate": 3.5714034564383735e-05, "loss": 1.063, "step": 252000 }, { "epoch": 0.29, "learning_rate": 3.568567893028938e-05, "loss": 1.0591, "step": 252500 }, { "epoch": 0.29, "learning_rate": 3.565732329619502e-05, "loss": 1.0643, "step": 253000 }, { "epoch": 0.29, "learning_rate": 3.5628967662100654e-05, "loss": 1.0502, "step": 253500 }, { "epoch": 0.29, "learning_rate": 3.5600725450542674e-05, "loss": 1.0512, "step": 254000 }, { "epoch": 0.29, "learning_rate": 3.557236981644831e-05, "loss": 1.0624, "step": 254500 }, { "epoch": 0.29, "learning_rate": 3.554401418235395e-05, "loss": 1.0603, "step": 255000 }, { "epoch": 0.29, "learning_rate": 3.5515658548259586e-05, "loss": 1.0609, "step": 255500 }, { "epoch": 0.29, "learning_rate": 3.548730291416523e-05, "loss": 1.0542, "step": 256000 }, { "epoch": 0.29, "learning_rate": 3.545894728007087e-05, "loss": 1.0546, "step": 256500 }, { "epoch": 0.29, "learning_rate": 3.5430591645976505e-05, "loss": 1.0575, "step": 257000 }, { "epoch": 0.29, "learning_rate": 3.540223601188215e-05, "loss": 1.0603, "step": 257500 }, { "epoch": 0.29, "learning_rate": 3.537388037778779e-05, "loss": 1.0464, "step": 258000 }, { "epoch": 0.29, "learning_rate": 3.5345581454961614e-05, "loss": 1.0492, "step": 258500 }, { "epoch": 0.29, "learning_rate": 3.5317225820867256e-05, "loss": 1.0553, "step": 259000 }, { "epoch": 0.29, "learning_rate": 3.528887018677289e-05, "loss": 1.0577, "step": 259500 }, { "epoch": 0.29, "learning_rate": 3.526051455267853e-05, "loss": 1.0579, "step": 260000 }, { "epoch": 0.3, "learning_rate": 3.523215891858417e-05, "loss": 1.0637, "step": 260500 }, { "epoch": 0.3, "learning_rate": 3.520380328448981e-05, "loss": 1.0554, "step": 261000 }, { "epoch": 0.3, "learning_rate": 3.517544765039545e-05, "loss": 1.0501, "step": 261500 }, { "epoch": 0.3, "learning_rate": 3.514709201630109e-05, "loss": 1.0576, "step": 262000 }, { "epoch": 0.3, "learning_rate": 3.511873638220673e-05, "loss": 1.0535, "step": 262500 }, { "epoch": 0.3, "learning_rate": 3.5090380748112364e-05, "loss": 1.057, "step": 263000 }, { "epoch": 0.3, "learning_rate": 3.5062025114018006e-05, "loss": 1.0506, "step": 263500 }, { "epoch": 0.3, "learning_rate": 3.503366947992365e-05, "loss": 1.0555, "step": 264000 }, { "epoch": 0.3, "learning_rate": 3.500537055709747e-05, "loss": 1.0588, "step": 264500 }, { "epoch": 0.3, "learning_rate": 3.4977014923003114e-05, "loss": 1.0632, "step": 265000 }, { "epoch": 0.3, "learning_rate": 3.494865928890875e-05, "loss": 1.0404, "step": 265500 }, { "epoch": 0.3, "learning_rate": 3.492030365481439e-05, "loss": 1.0532, "step": 266000 }, { "epoch": 0.3, "learning_rate": 3.4891948020720034e-05, "loss": 1.0585, "step": 266500 }, { "epoch": 0.3, "learning_rate": 3.486359238662567e-05, "loss": 1.0621, "step": 267000 }, { "epoch": 0.3, "learning_rate": 3.483523675253131e-05, "loss": 1.0614, "step": 267500 }, { "epoch": 0.3, "learning_rate": 3.4806881118436946e-05, "loss": 1.0562, "step": 268000 }, { "epoch": 0.3, "learning_rate": 3.477858219561078e-05, "loss": 1.0502, "step": 268500 }, { "epoch": 0.31, "learning_rate": 3.475028327278461e-05, "loss": 1.054, "step": 269000 }, { "epoch": 0.31, "learning_rate": 3.472192763869024e-05, "loss": 1.0581, "step": 269500 }, { "epoch": 0.31, "learning_rate": 3.469357200459588e-05, "loss": 1.0417, "step": 270000 }, { "epoch": 0.31, "learning_rate": 3.466521637050153e-05, "loss": 1.0417, "step": 270500 }, { "epoch": 0.31, "learning_rate": 3.463686073640716e-05, "loss": 1.0432, "step": 271000 }, { "epoch": 0.31, "learning_rate": 3.46085051023128e-05, "loss": 1.0455, "step": 271500 }, { "epoch": 0.31, "learning_rate": 3.458020617948663e-05, "loss": 1.0507, "step": 272000 }, { "epoch": 0.31, "learning_rate": 3.455185054539227e-05, "loss": 1.0543, "step": 272500 }, { "epoch": 0.31, "learning_rate": 3.4523494911297905e-05, "loss": 1.055, "step": 273000 }, { "epoch": 0.31, "learning_rate": 3.449513927720355e-05, "loss": 1.0433, "step": 273500 }, { "epoch": 0.31, "learning_rate": 3.446678364310918e-05, "loss": 1.0495, "step": 274000 }, { "epoch": 0.31, "learning_rate": 3.4438428009014825e-05, "loss": 1.0601, "step": 274500 }, { "epoch": 0.31, "learning_rate": 3.4410129086188656e-05, "loss": 1.0542, "step": 275000 }, { "epoch": 0.31, "learning_rate": 3.438177345209429e-05, "loss": 1.0472, "step": 275500 }, { "epoch": 0.31, "learning_rate": 3.435341781799993e-05, "loss": 1.0475, "step": 276000 }, { "epoch": 0.31, "learning_rate": 3.432506218390557e-05, "loss": 1.0495, "step": 276500 }, { "epoch": 0.31, "learning_rate": 3.429670654981121e-05, "loss": 1.0514, "step": 277000 }, { "epoch": 0.31, "learning_rate": 3.426835091571685e-05, "loss": 1.0404, "step": 277500 }, { "epoch": 0.32, "learning_rate": 3.423999528162249e-05, "loss": 1.0464, "step": 278000 }, { "epoch": 0.32, "learning_rate": 3.421169635879632e-05, "loss": 1.0518, "step": 278500 }, { "epoch": 0.32, "learning_rate": 3.418334072470195e-05, "loss": 1.0479, "step": 279000 }, { "epoch": 0.32, "learning_rate": 3.4154985090607595e-05, "loss": 1.0589, "step": 279500 }, { "epoch": 0.32, "learning_rate": 3.412662945651323e-05, "loss": 1.0594, "step": 280000 }, { "epoch": 0.32, "learning_rate": 3.409833053368706e-05, "loss": 1.0479, "step": 280500 }, { "epoch": 0.32, "learning_rate": 3.4069974899592696e-05, "loss": 1.0449, "step": 281000 }, { "epoch": 0.32, "learning_rate": 3.4041619265498345e-05, "loss": 1.0561, "step": 281500 }, { "epoch": 0.32, "learning_rate": 3.401326363140398e-05, "loss": 1.0455, "step": 282000 }, { "epoch": 0.32, "learning_rate": 3.3984907997309616e-05, "loss": 1.051, "step": 282500 }, { "epoch": 0.32, "learning_rate": 3.395655236321526e-05, "loss": 1.0445, "step": 283000 }, { "epoch": 0.32, "learning_rate": 3.39281967291209e-05, "loss": 1.0516, "step": 283500 }, { "epoch": 0.32, "learning_rate": 3.3899841095026535e-05, "loss": 1.0578, "step": 284000 }, { "epoch": 0.32, "learning_rate": 3.3871542172200366e-05, "loss": 1.0471, "step": 284500 }, { "epoch": 0.32, "learning_rate": 3.3843186538106e-05, "loss": 1.0518, "step": 285000 }, { "epoch": 0.32, "learning_rate": 3.381488761527983e-05, "loss": 1.0426, "step": 285500 }, { "epoch": 0.32, "learning_rate": 3.3786531981185474e-05, "loss": 1.0514, "step": 286000 }, { "epoch": 0.32, "learning_rate": 3.375817634709111e-05, "loss": 1.0381, "step": 286500 }, { "epoch": 0.33, "learning_rate": 3.372982071299675e-05, "loss": 1.0435, "step": 287000 }, { "epoch": 0.33, "learning_rate": 3.3701465078902386e-05, "loss": 1.0402, "step": 287500 }, { "epoch": 0.33, "learning_rate": 3.367310944480803e-05, "loss": 1.0431, "step": 288000 }, { "epoch": 0.33, "learning_rate": 3.364475381071367e-05, "loss": 1.0354, "step": 288500 }, { "epoch": 0.33, "learning_rate": 3.3616398176619305e-05, "loss": 1.0472, "step": 289000 }, { "epoch": 0.33, "learning_rate": 3.3588099253793136e-05, "loss": 1.0379, "step": 289500 }, { "epoch": 0.33, "learning_rate": 3.355974361969877e-05, "loss": 1.0459, "step": 290000 }, { "epoch": 0.33, "learning_rate": 3.3531387985604414e-05, "loss": 1.0439, "step": 290500 }, { "epoch": 0.33, "learning_rate": 3.3503032351510056e-05, "loss": 1.0515, "step": 291000 }, { "epoch": 0.33, "learning_rate": 3.347467671741569e-05, "loss": 1.0502, "step": 291500 }, { "epoch": 0.33, "learning_rate": 3.344632108332133e-05, "loss": 1.0481, "step": 292000 }, { "epoch": 0.33, "learning_rate": 3.341796544922697e-05, "loss": 1.0388, "step": 292500 }, { "epoch": 0.33, "learning_rate": 3.338960981513261e-05, "loss": 1.0446, "step": 293000 }, { "epoch": 0.33, "learning_rate": 3.3361310892306434e-05, "loss": 1.0507, "step": 293500 }, { "epoch": 0.33, "learning_rate": 3.3332955258212076e-05, "loss": 1.0462, "step": 294000 }, { "epoch": 0.33, "learning_rate": 3.330459962411772e-05, "loss": 1.0454, "step": 294500 }, { "epoch": 0.33, "learning_rate": 3.327624399002335e-05, "loss": 1.0449, "step": 295000 }, { "epoch": 0.34, "learning_rate": 3.3247888355928995e-05, "loss": 1.0383, "step": 295500 }, { "epoch": 0.34, "learning_rate": 3.321953272183464e-05, "loss": 1.055, "step": 296000 }, { "epoch": 0.34, "learning_rate": 3.319117708774027e-05, "loss": 1.0455, "step": 296500 }, { "epoch": 0.34, "learning_rate": 3.3162821453645914e-05, "loss": 1.0551, "step": 297000 }, { "epoch": 0.34, "learning_rate": 3.313446581955155e-05, "loss": 1.0504, "step": 297500 }, { "epoch": 0.34, "learning_rate": 3.3106166896725374e-05, "loss": 1.0321, "step": 298000 }, { "epoch": 0.34, "learning_rate": 3.307781126263102e-05, "loss": 1.0465, "step": 298500 }, { "epoch": 0.34, "learning_rate": 3.304945562853666e-05, "loss": 1.0394, "step": 299000 }, { "epoch": 0.34, "learning_rate": 3.302109999444229e-05, "loss": 1.0492, "step": 299500 }, { "epoch": 0.34, "learning_rate": 3.2992801071616124e-05, "loss": 1.047, "step": 300000 }, { "epoch": 0.34, "learning_rate": 3.2964445437521766e-05, "loss": 1.0467, "step": 300500 }, { "epoch": 0.34, "learning_rate": 3.293614651469559e-05, "loss": 1.0346, "step": 301000 }, { "epoch": 0.34, "learning_rate": 3.290779088060123e-05, "loss": 1.0463, "step": 301500 }, { "epoch": 0.34, "learning_rate": 3.2879435246506874e-05, "loss": 1.0604, "step": 302000 }, { "epoch": 0.34, "learning_rate": 3.285107961241251e-05, "loss": 1.0509, "step": 302500 }, { "epoch": 0.34, "learning_rate": 3.282272397831815e-05, "loss": 1.0409, "step": 303000 }, { "epoch": 0.34, "learning_rate": 3.279442505549198e-05, "loss": 1.046, "step": 303500 }, { "epoch": 0.34, "learning_rate": 3.276606942139762e-05, "loss": 1.0413, "step": 304000 }, { "epoch": 0.35, "learning_rate": 3.273777049857145e-05, "loss": 1.0476, "step": 304500 }, { "epoch": 0.35, "learning_rate": 3.270941486447708e-05, "loss": 1.0441, "step": 305000 }, { "epoch": 0.35, "learning_rate": 3.268105923038272e-05, "loss": 1.041, "step": 305500 }, { "epoch": 0.35, "learning_rate": 3.265270359628837e-05, "loss": 1.0403, "step": 306000 }, { "epoch": 0.35, "learning_rate": 3.2624347962194e-05, "loss": 1.0397, "step": 306500 }, { "epoch": 0.35, "learning_rate": 3.259599232809964e-05, "loss": 1.0371, "step": 307000 }, { "epoch": 0.35, "learning_rate": 3.256769340527347e-05, "loss": 1.0354, "step": 307500 }, { "epoch": 0.35, "learning_rate": 3.2539337771179104e-05, "loss": 1.0436, "step": 308000 }, { "epoch": 0.35, "learning_rate": 3.251098213708475e-05, "loss": 1.0415, "step": 308500 }, { "epoch": 0.35, "learning_rate": 3.248262650299039e-05, "loss": 1.0357, "step": 309000 }, { "epoch": 0.35, "learning_rate": 3.245427086889602e-05, "loss": 1.0567, "step": 309500 }, { "epoch": 0.35, "learning_rate": 3.2425915234801665e-05, "loss": 1.0387, "step": 310000 }, { "epoch": 0.35, "learning_rate": 3.239755960070731e-05, "loss": 1.0362, "step": 310500 }, { "epoch": 0.35, "learning_rate": 3.236920396661294e-05, "loss": 1.0497, "step": 311000 }, { "epoch": 0.35, "learning_rate": 3.2340848332518584e-05, "loss": 1.0333, "step": 311500 }, { "epoch": 0.35, "learning_rate": 3.231254940969241e-05, "loss": 1.0323, "step": 312000 }, { "epoch": 0.35, "learning_rate": 3.228419377559805e-05, "loss": 1.0385, "step": 312500 }, { "epoch": 0.36, "learning_rate": 3.225583814150369e-05, "loss": 1.0244, "step": 313000 }, { "epoch": 0.36, "learning_rate": 3.222748250740933e-05, "loss": 1.0379, "step": 313500 }, { "epoch": 0.36, "learning_rate": 3.219912687331497e-05, "loss": 1.0411, "step": 314000 }, { "epoch": 0.36, "learning_rate": 3.217077123922061e-05, "loss": 1.0482, "step": 314500 }, { "epoch": 0.36, "learning_rate": 3.2142472316394435e-05, "loss": 1.0341, "step": 315000 }, { "epoch": 0.36, "learning_rate": 3.211411668230008e-05, "loss": 1.0411, "step": 315500 }, { "epoch": 0.36, "learning_rate": 3.208576104820571e-05, "loss": 1.0341, "step": 316000 }, { "epoch": 0.36, "learning_rate": 3.2057405414111355e-05, "loss": 1.0346, "step": 316500 }, { "epoch": 0.36, "learning_rate": 3.202904978001699e-05, "loss": 1.0438, "step": 317000 }, { "epoch": 0.36, "learning_rate": 3.200069414592263e-05, "loss": 1.0415, "step": 317500 }, { "epoch": 0.36, "learning_rate": 3.197233851182827e-05, "loss": 1.0418, "step": 318000 }, { "epoch": 0.36, "learning_rate": 3.194398287773391e-05, "loss": 1.0355, "step": 318500 }, { "epoch": 0.36, "learning_rate": 3.191562724363955e-05, "loss": 1.0396, "step": 319000 }, { "epoch": 0.36, "learning_rate": 3.1887271609545186e-05, "loss": 1.0383, "step": 319500 }, { "epoch": 0.36, "learning_rate": 3.185897268671902e-05, "loss": 1.0381, "step": 320000 }, { "epoch": 0.36, "learning_rate": 3.183061705262466e-05, "loss": 1.0418, "step": 320500 }, { "epoch": 0.36, "learning_rate": 3.180231812979848e-05, "loss": 1.0422, "step": 321000 }, { "epoch": 0.36, "learning_rate": 3.1773962495704125e-05, "loss": 1.0352, "step": 321500 }, { "epoch": 0.37, "learning_rate": 3.174560686160976e-05, "loss": 1.0425, "step": 322000 }, { "epoch": 0.37, "learning_rate": 3.1717251227515396e-05, "loss": 1.0394, "step": 322500 }, { "epoch": 0.37, "learning_rate": 3.1688952304689226e-05, "loss": 1.034, "step": 323000 }, { "epoch": 0.37, "learning_rate": 3.166059667059487e-05, "loss": 1.0391, "step": 323500 }, { "epoch": 0.37, "learning_rate": 3.163224103650051e-05, "loss": 1.0363, "step": 324000 }, { "epoch": 0.37, "learning_rate": 3.1603885402406146e-05, "loss": 1.0363, "step": 324500 }, { "epoch": 0.37, "learning_rate": 3.157552976831179e-05, "loss": 1.0355, "step": 325000 }, { "epoch": 0.37, "learning_rate": 3.154717413421743e-05, "loss": 1.0344, "step": 325500 }, { "epoch": 0.37, "learning_rate": 3.1518818500123065e-05, "loss": 1.0348, "step": 326000 }, { "epoch": 0.37, "learning_rate": 3.1490519577296896e-05, "loss": 1.0304, "step": 326500 }, { "epoch": 0.37, "learning_rate": 3.146216394320253e-05, "loss": 1.0398, "step": 327000 }, { "epoch": 0.37, "learning_rate": 3.143386502037636e-05, "loss": 1.0305, "step": 327500 }, { "epoch": 0.37, "learning_rate": 3.1405509386282004e-05, "loss": 1.0399, "step": 328000 }, { "epoch": 0.37, "learning_rate": 3.137715375218764e-05, "loss": 1.0438, "step": 328500 }, { "epoch": 0.37, "learning_rate": 3.1348798118093274e-05, "loss": 1.0422, "step": 329000 }, { "epoch": 0.37, "learning_rate": 3.1320442483998916e-05, "loss": 1.0397, "step": 329500 }, { "epoch": 0.37, "learning_rate": 3.129208684990456e-05, "loss": 1.034, "step": 330000 }, { "epoch": 0.37, "learning_rate": 3.1263731215810193e-05, "loss": 1.0411, "step": 330500 }, { "epoch": 0.38, "learning_rate": 3.1235375581715835e-05, "loss": 1.0361, "step": 331000 }, { "epoch": 0.38, "learning_rate": 3.120707665888966e-05, "loss": 1.0304, "step": 331500 }, { "epoch": 0.38, "learning_rate": 3.11787210247953e-05, "loss": 1.0402, "step": 332000 }, { "epoch": 0.38, "learning_rate": 3.1150365390700943e-05, "loss": 1.0353, "step": 332500 }, { "epoch": 0.38, "learning_rate": 3.112200975660658e-05, "loss": 1.0403, "step": 333000 }, { "epoch": 0.38, "learning_rate": 3.109365412251222e-05, "loss": 1.0377, "step": 333500 }, { "epoch": 0.38, "learning_rate": 3.106529848841786e-05, "loss": 1.0377, "step": 334000 }, { "epoch": 0.38, "learning_rate": 3.10369428543235e-05, "loss": 1.0374, "step": 334500 }, { "epoch": 0.38, "learning_rate": 3.100858722022913e-05, "loss": 1.0323, "step": 335000 }, { "epoch": 0.38, "learning_rate": 3.0980288297402964e-05, "loss": 1.0321, "step": 335500 }, { "epoch": 0.38, "learning_rate": 3.0951932663308606e-05, "loss": 1.0294, "step": 336000 }, { "epoch": 0.38, "learning_rate": 3.092357702921425e-05, "loss": 1.0446, "step": 336500 }, { "epoch": 0.38, "learning_rate": 3.089522139511988e-05, "loss": 1.0369, "step": 337000 }, { "epoch": 0.38, "learning_rate": 3.0866922472293714e-05, "loss": 1.0385, "step": 337500 }, { "epoch": 0.38, "learning_rate": 3.083856683819935e-05, "loss": 1.0312, "step": 338000 }, { "epoch": 0.38, "learning_rate": 3.081021120410499e-05, "loss": 1.0368, "step": 338500 }, { "epoch": 0.38, "learning_rate": 3.078185557001063e-05, "loss": 1.0346, "step": 339000 }, { "epoch": 0.39, "learning_rate": 3.075349993591627e-05, "loss": 1.0374, "step": 339500 }, { "epoch": 0.39, "learning_rate": 3.0725144301821904e-05, "loss": 1.0403, "step": 340000 }, { "epoch": 0.39, "learning_rate": 3.069678866772755e-05, "loss": 1.0405, "step": 340500 }, { "epoch": 0.39, "learning_rate": 3.066843303363319e-05, "loss": 1.0413, "step": 341000 }, { "epoch": 0.39, "learning_rate": 3.064013411080701e-05, "loss": 1.0441, "step": 341500 }, { "epoch": 0.39, "learning_rate": 3.0611778476712654e-05, "loss": 1.0337, "step": 342000 }, { "epoch": 0.39, "learning_rate": 3.058342284261829e-05, "loss": 1.0377, "step": 342500 }, { "epoch": 0.39, "learning_rate": 3.055506720852393e-05, "loss": 1.0303, "step": 343000 }, { "epoch": 0.39, "learning_rate": 3.052671157442957e-05, "loss": 1.0263, "step": 343500 }, { "epoch": 0.39, "learning_rate": 3.049835594033521e-05, "loss": 1.027, "step": 344000 }, { "epoch": 0.39, "learning_rate": 3.047005701750904e-05, "loss": 1.0238, "step": 344500 }, { "epoch": 0.39, "learning_rate": 3.0441701383414678e-05, "loss": 1.0358, "step": 345000 }, { "epoch": 0.39, "learning_rate": 3.0413345749320316e-05, "loss": 1.0365, "step": 345500 }, { "epoch": 0.39, "learning_rate": 3.0384990115225958e-05, "loss": 1.031, "step": 346000 }, { "epoch": 0.39, "learning_rate": 3.0356634481131597e-05, "loss": 1.0359, "step": 346500 }, { "epoch": 0.39, "learning_rate": 3.0328278847037232e-05, "loss": 1.0326, "step": 347000 }, { "epoch": 0.39, "learning_rate": 3.029992321294287e-05, "loss": 1.0333, "step": 347500 }, { "epoch": 0.39, "learning_rate": 3.0271567578848513e-05, "loss": 1.0333, "step": 348000 }, { "epoch": 0.4, "learning_rate": 3.024321194475415e-05, "loss": 1.0384, "step": 348500 }, { "epoch": 0.4, "learning_rate": 3.0214913021927982e-05, "loss": 1.0247, "step": 349000 }, { "epoch": 0.4, "learning_rate": 3.018655738783362e-05, "loss": 1.0285, "step": 349500 }, { "epoch": 0.4, "learning_rate": 3.0158201753739256e-05, "loss": 1.0348, "step": 350000 }, { "epoch": 0.4, "learning_rate": 3.0129902830913087e-05, "loss": 1.0334, "step": 350500 }, { "epoch": 0.4, "learning_rate": 3.0101547196818725e-05, "loss": 1.0232, "step": 351000 }, { "epoch": 0.4, "learning_rate": 3.0073191562724367e-05, "loss": 1.0332, "step": 351500 }, { "epoch": 0.4, "learning_rate": 3.0044835928630006e-05, "loss": 1.0291, "step": 352000 }, { "epoch": 0.4, "learning_rate": 3.001648029453564e-05, "loss": 1.0249, "step": 352500 }, { "epoch": 0.4, "learning_rate": 2.9988181371709472e-05, "loss": 1.0328, "step": 353000 }, { "epoch": 0.4, "learning_rate": 2.995982573761511e-05, "loss": 1.0321, "step": 353500 }, { "epoch": 0.4, "learning_rate": 2.993147010352075e-05, "loss": 1.0271, "step": 354000 }, { "epoch": 0.4, "learning_rate": 2.9903171180694577e-05, "loss": 1.0408, "step": 354500 }, { "epoch": 0.4, "learning_rate": 2.9874872257868407e-05, "loss": 1.0263, "step": 355000 }, { "epoch": 0.4, "learning_rate": 2.9846516623774046e-05, "loss": 1.0365, "step": 355500 }, { "epoch": 0.4, "learning_rate": 2.9818160989679685e-05, "loss": 1.0225, "step": 356000 }, { "epoch": 0.4, "learning_rate": 2.9789805355585327e-05, "loss": 1.0367, "step": 356500 }, { "epoch": 0.4, "learning_rate": 2.9761449721490965e-05, "loss": 1.0261, "step": 357000 }, { "epoch": 0.41, "learning_rate": 2.97330940873966e-05, "loss": 1.0369, "step": 357500 }, { "epoch": 0.41, "learning_rate": 2.970479516457043e-05, "loss": 1.0264, "step": 358000 }, { "epoch": 0.41, "learning_rate": 2.967643953047607e-05, "loss": 1.0348, "step": 358500 }, { "epoch": 0.41, "learning_rate": 2.9648083896381705e-05, "loss": 1.0281, "step": 359000 }, { "epoch": 0.41, "learning_rate": 2.961972826228735e-05, "loss": 1.0275, "step": 359500 }, { "epoch": 0.41, "learning_rate": 2.9591372628192986e-05, "loss": 1.0419, "step": 360000 }, { "epoch": 0.41, "learning_rate": 2.9563016994098624e-05, "loss": 1.0338, "step": 360500 }, { "epoch": 0.41, "learning_rate": 2.9534661360004266e-05, "loss": 1.0356, "step": 361000 }, { "epoch": 0.41, "learning_rate": 2.9506305725909905e-05, "loss": 1.0257, "step": 361500 }, { "epoch": 0.41, "learning_rate": 2.9478006803083736e-05, "loss": 1.0314, "step": 362000 }, { "epoch": 0.41, "learning_rate": 2.9449651168989374e-05, "loss": 1.0287, "step": 362500 }, { "epoch": 0.41, "learning_rate": 2.942129553489501e-05, "loss": 1.0174, "step": 363000 }, { "epoch": 0.41, "learning_rate": 2.9392939900800655e-05, "loss": 1.0214, "step": 363500 }, { "epoch": 0.41, "learning_rate": 2.936458426670629e-05, "loss": 1.0258, "step": 364000 }, { "epoch": 0.41, "learning_rate": 2.933622863261193e-05, "loss": 1.021, "step": 364500 }, { "epoch": 0.41, "learning_rate": 2.930787299851757e-05, "loss": 1.0231, "step": 365000 }, { "epoch": 0.41, "learning_rate": 2.9279574075691395e-05, "loss": 1.0261, "step": 365500 }, { "epoch": 0.42, "learning_rate": 2.9251218441597034e-05, "loss": 1.0275, "step": 366000 }, { "epoch": 0.42, "learning_rate": 2.9222862807502676e-05, "loss": 1.0323, "step": 366500 }, { "epoch": 0.42, "learning_rate": 2.9194507173408314e-05, "loss": 1.0314, "step": 367000 }, { "epoch": 0.42, "learning_rate": 2.9166151539313953e-05, "loss": 1.026, "step": 367500 }, { "epoch": 0.42, "learning_rate": 2.913785261648778e-05, "loss": 1.0383, "step": 368000 }, { "epoch": 0.42, "learning_rate": 2.910949698239342e-05, "loss": 1.0296, "step": 368500 }, { "epoch": 0.42, "learning_rate": 2.908114134829906e-05, "loss": 1.0215, "step": 369000 }, { "epoch": 0.42, "learning_rate": 2.90527857142047e-05, "loss": 1.0247, "step": 369500 }, { "epoch": 0.42, "learning_rate": 2.9024430080110338e-05, "loss": 1.0266, "step": 370000 }, { "epoch": 0.42, "learning_rate": 2.899607444601598e-05, "loss": 1.0238, "step": 370500 }, { "epoch": 0.42, "learning_rate": 2.896771881192162e-05, "loss": 1.0221, "step": 371000 }, { "epoch": 0.42, "learning_rate": 2.8939363177827257e-05, "loss": 1.0131, "step": 371500 }, { "epoch": 0.42, "learning_rate": 2.8911007543732892e-05, "loss": 1.0217, "step": 372000 }, { "epoch": 0.42, "learning_rate": 2.8882708620906723e-05, "loss": 1.0158, "step": 372500 }, { "epoch": 0.42, "learning_rate": 2.8854352986812362e-05, "loss": 1.0243, "step": 373000 }, { "epoch": 0.42, "learning_rate": 2.882605406398619e-05, "loss": 1.0365, "step": 373500 }, { "epoch": 0.42, "learning_rate": 2.8797698429891828e-05, "loss": 1.0321, "step": 374000 }, { "epoch": 0.42, "learning_rate": 2.876934279579747e-05, "loss": 1.0244, "step": 374500 }, { "epoch": 0.43, "learning_rate": 2.874098716170311e-05, "loss": 1.0297, "step": 375000 }, { "epoch": 0.43, "learning_rate": 2.8712631527608747e-05, "loss": 1.0203, "step": 375500 }, { "epoch": 0.43, "learning_rate": 2.8684332604782578e-05, "loss": 1.0329, "step": 376000 }, { "epoch": 0.43, "learning_rate": 2.8655976970688213e-05, "loss": 1.0226, "step": 376500 }, { "epoch": 0.43, "learning_rate": 2.862762133659386e-05, "loss": 1.0218, "step": 377000 }, { "epoch": 0.43, "learning_rate": 2.8599265702499494e-05, "loss": 1.035, "step": 377500 }, { "epoch": 0.43, "learning_rate": 2.8570910068405132e-05, "loss": 1.0228, "step": 378000 }, { "epoch": 0.43, "learning_rate": 2.854255443431077e-05, "loss": 1.0219, "step": 378500 }, { "epoch": 0.43, "learning_rate": 2.85142555114846e-05, "loss": 1.0242, "step": 379000 }, { "epoch": 0.43, "learning_rate": 2.8485899877390237e-05, "loss": 1.0232, "step": 379500 }, { "epoch": 0.43, "learning_rate": 2.845754424329588e-05, "loss": 1.026, "step": 380000 }, { "epoch": 0.43, "learning_rate": 2.8429188609201518e-05, "loss": 1.0204, "step": 380500 }, { "epoch": 0.43, "learning_rate": 2.8400832975107156e-05, "loss": 1.0309, "step": 381000 }, { "epoch": 0.43, "learning_rate": 2.83724773410128e-05, "loss": 1.0229, "step": 381500 }, { "epoch": 0.43, "learning_rate": 2.8344121706918437e-05, "loss": 1.0236, "step": 382000 }, { "epoch": 0.43, "learning_rate": 2.8315766072824072e-05, "loss": 1.0157, "step": 382500 }, { "epoch": 0.43, "learning_rate": 2.8287410438729718e-05, "loss": 1.0271, "step": 383000 }, { "epoch": 0.43, "learning_rate": 2.8259054804635353e-05, "loss": 1.0162, "step": 383500 }, { "epoch": 0.44, "learning_rate": 2.823075588180918e-05, "loss": 1.0247, "step": 384000 }, { "epoch": 0.44, "learning_rate": 2.8202400247714822e-05, "loss": 1.0214, "step": 384500 }, { "epoch": 0.44, "learning_rate": 2.817404461362046e-05, "loss": 1.0247, "step": 385000 }, { "epoch": 0.44, "learning_rate": 2.8145688979526096e-05, "loss": 1.0257, "step": 385500 }, { "epoch": 0.44, "learning_rate": 2.811733334543174e-05, "loss": 1.0177, "step": 386000 }, { "epoch": 0.44, "learning_rate": 2.8088977711337377e-05, "loss": 1.0214, "step": 386500 }, { "epoch": 0.44, "learning_rate": 2.8060622077243015e-05, "loss": 1.0279, "step": 387000 }, { "epoch": 0.44, "learning_rate": 2.8032323154416846e-05, "loss": 1.0213, "step": 387500 }, { "epoch": 0.44, "learning_rate": 2.800396752032248e-05, "loss": 1.0162, "step": 388000 }, { "epoch": 0.44, "learning_rate": 2.7975611886228127e-05, "loss": 1.028, "step": 388500 }, { "epoch": 0.44, "learning_rate": 2.7947256252133762e-05, "loss": 1.0257, "step": 389000 }, { "epoch": 0.44, "learning_rate": 2.79189006180394e-05, "loss": 1.0182, "step": 389500 }, { "epoch": 0.44, "learning_rate": 2.789060169521323e-05, "loss": 1.0284, "step": 390000 }, { "epoch": 0.44, "learning_rate": 2.786224606111887e-05, "loss": 1.0254, "step": 390500 }, { "epoch": 0.44, "learning_rate": 2.7833890427024505e-05, "loss": 1.0226, "step": 391000 }, { "epoch": 0.44, "learning_rate": 2.780553479293015e-05, "loss": 1.0333, "step": 391500 }, { "epoch": 0.44, "learning_rate": 2.7777179158835786e-05, "loss": 1.0234, "step": 392000 }, { "epoch": 0.45, "learning_rate": 2.7748823524741424e-05, "loss": 1.0208, "step": 392500 }, { "epoch": 0.45, "learning_rate": 2.7720467890647066e-05, "loss": 1.0113, "step": 393000 }, { "epoch": 0.45, "learning_rate": 2.7692112256552705e-05, "loss": 1.0204, "step": 393500 }, { "epoch": 0.45, "learning_rate": 2.7663813333726536e-05, "loss": 1.0221, "step": 394000 }, { "epoch": 0.45, "learning_rate": 2.763545769963217e-05, "loss": 1.0142, "step": 394500 }, { "epoch": 0.45, "learning_rate": 2.760710206553781e-05, "loss": 1.0206, "step": 395000 }, { "epoch": 0.45, "learning_rate": 2.7578746431443452e-05, "loss": 1.0245, "step": 395500 }, { "epoch": 0.45, "learning_rate": 2.755039079734909e-05, "loss": 1.0211, "step": 396000 }, { "epoch": 0.45, "learning_rate": 2.7522091874522914e-05, "loss": 1.0229, "step": 396500 }, { "epoch": 0.45, "learning_rate": 2.749373624042856e-05, "loss": 1.0236, "step": 397000 }, { "epoch": 0.45, "learning_rate": 2.7465380606334195e-05, "loss": 1.0234, "step": 397500 }, { "epoch": 0.45, "learning_rate": 2.7437081683508026e-05, "loss": 1.0249, "step": 398000 }, { "epoch": 0.45, "learning_rate": 2.7408726049413664e-05, "loss": 1.0188, "step": 398500 }, { "epoch": 0.45, "learning_rate": 2.7380427126587492e-05, "loss": 1.02, "step": 399000 }, { "epoch": 0.45, "learning_rate": 2.735207149249313e-05, "loss": 1.0236, "step": 399500 }, { "epoch": 0.45, "learning_rate": 2.732371585839877e-05, "loss": 1.0245, "step": 400000 }, { "epoch": 0.45, "learning_rate": 2.729536022430441e-05, "loss": 1.0333, "step": 400500 }, { "epoch": 0.45, "learning_rate": 2.726700459021005e-05, "loss": 1.0197, "step": 401000 }, { "epoch": 0.46, "learning_rate": 2.7238648956115685e-05, "loss": 1.0254, "step": 401500 }, { "epoch": 0.46, "learning_rate": 2.721029332202133e-05, "loss": 1.0158, "step": 402000 }, { "epoch": 0.46, "learning_rate": 2.7181937687926966e-05, "loss": 1.0247, "step": 402500 }, { "epoch": 0.46, "learning_rate": 2.7153582053832604e-05, "loss": 1.0168, "step": 403000 }, { "epoch": 0.46, "learning_rate": 2.7125226419738243e-05, "loss": 1.0238, "step": 403500 }, { "epoch": 0.46, "learning_rate": 2.7096870785643885e-05, "loss": 1.0162, "step": 404000 }, { "epoch": 0.46, "learning_rate": 2.7068515151549523e-05, "loss": 1.0162, "step": 404500 }, { "epoch": 0.46, "learning_rate": 2.7040216228723354e-05, "loss": 1.0237, "step": 405000 }, { "epoch": 0.46, "learning_rate": 2.701186059462899e-05, "loss": 1.0313, "step": 405500 }, { "epoch": 0.46, "learning_rate": 2.6983504960534628e-05, "loss": 1.0143, "step": 406000 }, { "epoch": 0.46, "learning_rate": 2.695514932644027e-05, "loss": 1.024, "step": 406500 }, { "epoch": 0.46, "learning_rate": 2.692679369234591e-05, "loss": 1.0265, "step": 407000 }, { "epoch": 0.46, "learning_rate": 2.6898438058251547e-05, "loss": 1.0232, "step": 407500 }, { "epoch": 0.46, "learning_rate": 2.6870139135425375e-05, "loss": 1.0174, "step": 408000 }, { "epoch": 0.46, "learning_rate": 2.6841840212599202e-05, "loss": 1.0099, "step": 408500 }, { "epoch": 0.46, "learning_rate": 2.6813484578504844e-05, "loss": 1.0173, "step": 409000 }, { "epoch": 0.46, "learning_rate": 2.6785128944410483e-05, "loss": 1.0189, "step": 409500 }, { "epoch": 0.47, "learning_rate": 2.6756773310316118e-05, "loss": 1.0187, "step": 410000 }, { "epoch": 0.47, "learning_rate": 2.672847438748995e-05, "loss": 1.0174, "step": 410500 }, { "epoch": 0.47, "learning_rate": 2.6700118753395587e-05, "loss": 1.018, "step": 411000 }, { "epoch": 0.47, "learning_rate": 2.667176311930123e-05, "loss": 1.0273, "step": 411500 }, { "epoch": 0.47, "learning_rate": 2.6643407485206868e-05, "loss": 1.0175, "step": 412000 }, { "epoch": 0.47, "learning_rate": 2.6615051851112503e-05, "loss": 1.0088, "step": 412500 }, { "epoch": 0.47, "learning_rate": 2.658669621701815e-05, "loss": 1.0083, "step": 413000 }, { "epoch": 0.47, "learning_rate": 2.6558340582923784e-05, "loss": 1.0152, "step": 413500 }, { "epoch": 0.47, "learning_rate": 2.6529984948829422e-05, "loss": 1.0096, "step": 414000 }, { "epoch": 0.47, "learning_rate": 2.6501629314735064e-05, "loss": 1.0183, "step": 414500 }, { "epoch": 0.47, "learning_rate": 2.6473273680640703e-05, "loss": 1.0206, "step": 415000 }, { "epoch": 0.47, "learning_rate": 2.644491804654634e-05, "loss": 1.0195, "step": 415500 }, { "epoch": 0.47, "learning_rate": 2.6416562412451977e-05, "loss": 1.015, "step": 416000 }, { "epoch": 0.47, "learning_rate": 2.6388263489625808e-05, "loss": 1.0138, "step": 416500 }, { "epoch": 0.47, "learning_rate": 2.6359907855531446e-05, "loss": 1.0162, "step": 417000 }, { "epoch": 0.47, "learning_rate": 2.6331552221437088e-05, "loss": 1.0137, "step": 417500 }, { "epoch": 0.47, "learning_rate": 2.6303196587342727e-05, "loss": 1.0178, "step": 418000 }, { "epoch": 0.47, "learning_rate": 2.6274897664516558e-05, "loss": 1.0175, "step": 418500 }, { "epoch": 0.48, "learning_rate": 2.6246598741690382e-05, "loss": 1.0197, "step": 419000 }, { "epoch": 0.48, "learning_rate": 2.6218243107596024e-05, "loss": 1.0193, "step": 419500 }, { "epoch": 0.48, "learning_rate": 2.6189887473501662e-05, "loss": 1.0139, "step": 420000 }, { "epoch": 0.48, "learning_rate": 2.61615318394073e-05, "loss": 1.0128, "step": 420500 }, { "epoch": 0.48, "learning_rate": 2.613323291658113e-05, "loss": 1.0197, "step": 421000 }, { "epoch": 0.48, "learning_rate": 2.6104877282486767e-05, "loss": 1.0199, "step": 421500 }, { "epoch": 0.48, "learning_rate": 2.6076521648392406e-05, "loss": 1.0163, "step": 422000 }, { "epoch": 0.48, "learning_rate": 2.6048166014298048e-05, "loss": 1.0169, "step": 422500 }, { "epoch": 0.48, "learning_rate": 2.6019810380203686e-05, "loss": 1.0141, "step": 423000 }, { "epoch": 0.48, "learning_rate": 2.5991511457377514e-05, "loss": 1.0149, "step": 423500 }, { "epoch": 0.48, "learning_rate": 2.5963155823283152e-05, "loss": 1.0175, "step": 424000 }, { "epoch": 0.48, "learning_rate": 2.593480018918879e-05, "loss": 1.0233, "step": 424500 }, { "epoch": 0.48, "learning_rate": 2.5906444555094433e-05, "loss": 1.016, "step": 425000 }, { "epoch": 0.48, "learning_rate": 2.5878145632268257e-05, "loss": 1.0118, "step": 425500 }, { "epoch": 0.48, "learning_rate": 2.5849789998173902e-05, "loss": 1.0155, "step": 426000 }, { "epoch": 0.48, "learning_rate": 2.5821434364079538e-05, "loss": 1.0154, "step": 426500 }, { "epoch": 0.48, "learning_rate": 2.5793078729985176e-05, "loss": 1.012, "step": 427000 }, { "epoch": 0.48, "learning_rate": 2.5764723095890815e-05, "loss": 1.0192, "step": 427500 }, { "epoch": 0.49, "learning_rate": 2.5736367461796457e-05, "loss": 1.0156, "step": 428000 }, { "epoch": 0.49, "learning_rate": 2.570806853897028e-05, "loss": 1.0168, "step": 428500 }, { "epoch": 0.49, "learning_rate": 2.5679712904875923e-05, "loss": 1.0094, "step": 429000 }, { "epoch": 0.49, "learning_rate": 2.565135727078156e-05, "loss": 1.0231, "step": 429500 }, { "epoch": 0.49, "learning_rate": 2.56230016366872e-05, "loss": 1.0187, "step": 430000 }, { "epoch": 0.49, "learning_rate": 2.559470271386103e-05, "loss": 1.0081, "step": 430500 }, { "epoch": 0.49, "learning_rate": 2.5566347079766666e-05, "loss": 1.0148, "step": 431000 }, { "epoch": 0.49, "learning_rate": 2.553799144567231e-05, "loss": 1.0189, "step": 431500 }, { "epoch": 0.49, "learning_rate": 2.5509692522846136e-05, "loss": 1.0128, "step": 432000 }, { "epoch": 0.49, "learning_rate": 2.548133688875177e-05, "loss": 1.0281, "step": 432500 }, { "epoch": 0.49, "learning_rate": 2.5452981254657416e-05, "loss": 1.0068, "step": 433000 }, { "epoch": 0.49, "learning_rate": 2.542462562056305e-05, "loss": 1.0117, "step": 433500 }, { "epoch": 0.49, "learning_rate": 2.539626998646869e-05, "loss": 1.0162, "step": 434000 }, { "epoch": 0.49, "learning_rate": 2.536797106364252e-05, "loss": 1.012, "step": 434500 }, { "epoch": 0.49, "learning_rate": 2.533961542954816e-05, "loss": 1.0134, "step": 435000 }, { "epoch": 0.49, "learning_rate": 2.53112597954538e-05, "loss": 1.0131, "step": 435500 }, { "epoch": 0.49, "learning_rate": 2.528290416135944e-05, "loss": 1.0112, "step": 436000 }, { "epoch": 0.5, "learning_rate": 2.5254548527265075e-05, "loss": 1.0098, "step": 436500 }, { "epoch": 0.5, "learning_rate": 2.522619289317072e-05, "loss": 1.0226, "step": 437000 }, { "epoch": 0.5, "learning_rate": 2.5197837259076356e-05, "loss": 1.0001, "step": 437500 }, { "epoch": 0.5, "learning_rate": 2.5169481624981995e-05, "loss": 1.0252, "step": 438000 }, { "epoch": 0.5, "learning_rate": 2.5141125990887637e-05, "loss": 1.0117, "step": 438500 }, { "epoch": 0.5, "learning_rate": 2.5112770356793275e-05, "loss": 1.0151, "step": 439000 }, { "epoch": 0.5, "learning_rate": 2.50844714339671e-05, "loss": 1.023, "step": 439500 }, { "epoch": 0.5, "learning_rate": 2.505617251114093e-05, "loss": 1.0151, "step": 440000 }, { "epoch": 0.5, "learning_rate": 2.502781687704657e-05, "loss": 1.009, "step": 440500 }, { "epoch": 0.5, "learning_rate": 2.4999461242952207e-05, "loss": 1.0079, "step": 441000 }, { "epoch": 0.5, "learning_rate": 2.497110560885785e-05, "loss": 1.0206, "step": 441500 }, { "epoch": 0.5, "learning_rate": 2.4942749974763488e-05, "loss": 1.0178, "step": 442000 }, { "epoch": 0.5, "learning_rate": 2.4914394340669126e-05, "loss": 1.0174, "step": 442500 }, { "epoch": 0.5, "learning_rate": 2.4886038706574765e-05, "loss": 1.0103, "step": 443000 }, { "epoch": 0.5, "learning_rate": 2.4857683072480404e-05, "loss": 1.0227, "step": 443500 }, { "epoch": 0.5, "learning_rate": 2.4829327438386042e-05, "loss": 1.0151, "step": 444000 }, { "epoch": 0.5, "learning_rate": 2.4800971804291684e-05, "loss": 1.0095, "step": 444500 }, { "epoch": 0.5, "learning_rate": 2.4772616170197323e-05, "loss": 1.0053, "step": 445000 }, { "epoch": 0.51, "learning_rate": 2.474426053610296e-05, "loss": 1.013, "step": 445500 }, { "epoch": 0.51, "learning_rate": 2.471596161327679e-05, "loss": 1.0146, "step": 446000 }, { "epoch": 0.51, "learning_rate": 2.468760597918243e-05, "loss": 1.0074, "step": 446500 }, { "epoch": 0.51, "learning_rate": 2.4659250345088066e-05, "loss": 1.0054, "step": 447000 }, { "epoch": 0.51, "learning_rate": 2.4630894710993708e-05, "loss": 1.008, "step": 447500 }, { "epoch": 0.51, "learning_rate": 2.4602595788167536e-05, "loss": 1.0061, "step": 448000 }, { "epoch": 0.51, "learning_rate": 2.4574240154073174e-05, "loss": 1.0053, "step": 448500 }, { "epoch": 0.51, "learning_rate": 2.4545884519978816e-05, "loss": 1.0048, "step": 449000 }, { "epoch": 0.51, "learning_rate": 2.451752888588445e-05, "loss": 1.0169, "step": 449500 }, { "epoch": 0.51, "learning_rate": 2.4489173251790093e-05, "loss": 1.0218, "step": 450000 }, { "epoch": 0.51, "learning_rate": 2.4460817617695732e-05, "loss": 0.9961, "step": 450500 }, { "epoch": 0.51, "learning_rate": 2.443246198360137e-05, "loss": 1.0112, "step": 451000 }, { "epoch": 0.51, "learning_rate": 2.4404163060775198e-05, "loss": 1.0223, "step": 451500 }, { "epoch": 0.51, "learning_rate": 2.4375864137949026e-05, "loss": 1.0085, "step": 452000 }, { "epoch": 0.51, "learning_rate": 2.4347508503854664e-05, "loss": 1.0154, "step": 452500 }, { "epoch": 0.51, "learning_rate": 2.4319152869760306e-05, "loss": 1.0067, "step": 453000 }, { "epoch": 0.51, "learning_rate": 2.4290797235665945e-05, "loss": 1.0142, "step": 453500 }, { "epoch": 0.51, "learning_rate": 2.4262441601571583e-05, "loss": 1.0057, "step": 454000 }, { "epoch": 0.52, "learning_rate": 2.4234085967477225e-05, "loss": 1.0126, "step": 454500 }, { "epoch": 0.52, "learning_rate": 2.420573033338286e-05, "loss": 1.0095, "step": 455000 }, { "epoch": 0.52, "learning_rate": 2.4177374699288503e-05, "loss": 1.0021, "step": 455500 }, { "epoch": 0.52, "learning_rate": 2.4149019065194138e-05, "loss": 1.0106, "step": 456000 }, { "epoch": 0.52, "learning_rate": 2.412066343109978e-05, "loss": 1.015, "step": 456500 }, { "epoch": 0.52, "learning_rate": 2.409230779700542e-05, "loss": 1.0096, "step": 457000 }, { "epoch": 0.52, "learning_rate": 2.4063952162911057e-05, "loss": 1.0056, "step": 457500 }, { "epoch": 0.52, "learning_rate": 2.4035653240084888e-05, "loss": 1.0073, "step": 458000 }, { "epoch": 0.52, "learning_rate": 2.4007297605990526e-05, "loss": 1.0066, "step": 458500 }, { "epoch": 0.52, "learning_rate": 2.3978998683164354e-05, "loss": 1.0048, "step": 459000 }, { "epoch": 0.52, "learning_rate": 2.3950643049069993e-05, "loss": 1.0074, "step": 459500 }, { "epoch": 0.52, "learning_rate": 2.3922287414975635e-05, "loss": 1.001, "step": 460000 }, { "epoch": 0.52, "learning_rate": 2.389393178088127e-05, "loss": 1.0088, "step": 460500 }, { "epoch": 0.52, "learning_rate": 2.3865576146786912e-05, "loss": 1.0063, "step": 461000 }, { "epoch": 0.52, "learning_rate": 2.383722051269255e-05, "loss": 1.0125, "step": 461500 }, { "epoch": 0.52, "learning_rate": 2.380886487859819e-05, "loss": 1.0034, "step": 462000 }, { "epoch": 0.52, "learning_rate": 2.3780509244503828e-05, "loss": 1.0051, "step": 462500 }, { "epoch": 0.53, "learning_rate": 2.3752210321677655e-05, "loss": 1.0107, "step": 463000 }, { "epoch": 0.53, "learning_rate": 2.3723854687583297e-05, "loss": 1.0042, "step": 463500 }, { "epoch": 0.53, "learning_rate": 2.3695499053488936e-05, "loss": 1.0103, "step": 464000 }, { "epoch": 0.53, "learning_rate": 2.3667143419394574e-05, "loss": 1.0007, "step": 464500 }, { "epoch": 0.53, "learning_rate": 2.3638787785300216e-05, "loss": 1.0033, "step": 465000 }, { "epoch": 0.53, "learning_rate": 2.3610488862474044e-05, "loss": 1.0069, "step": 465500 }, { "epoch": 0.53, "learning_rate": 2.358213322837968e-05, "loss": 1.0048, "step": 466000 }, { "epoch": 0.53, "learning_rate": 2.355383430555351e-05, "loss": 0.9998, "step": 466500 }, { "epoch": 0.53, "learning_rate": 2.352547867145915e-05, "loss": 0.9987, "step": 467000 }, { "epoch": 0.53, "learning_rate": 2.3497123037364787e-05, "loss": 0.9919, "step": 467500 }, { "epoch": 0.53, "learning_rate": 2.3468767403270426e-05, "loss": 1.0182, "step": 468000 }, { "epoch": 0.53, "learning_rate": 2.3440468480444256e-05, "loss": 0.9936, "step": 468500 }, { "epoch": 0.53, "learning_rate": 2.341211284634989e-05, "loss": 1.007, "step": 469000 }, { "epoch": 0.53, "learning_rate": 2.3383757212255534e-05, "loss": 1.0146, "step": 469500 }, { "epoch": 0.53, "learning_rate": 2.3355401578161172e-05, "loss": 1.0052, "step": 470000 }, { "epoch": 0.53, "learning_rate": 2.332704594406681e-05, "loss": 1.0066, "step": 470500 }, { "epoch": 0.53, "learning_rate": 2.3298690309972453e-05, "loss": 0.995, "step": 471000 }, { "epoch": 0.53, "learning_rate": 2.3270334675878088e-05, "loss": 1.018, "step": 471500 }, { "epoch": 0.54, "learning_rate": 2.324203575305192e-05, "loss": 1.0077, "step": 472000 }, { "epoch": 0.54, "learning_rate": 2.3213680118957557e-05, "loss": 1.0112, "step": 472500 }, { "epoch": 0.54, "learning_rate": 2.3185324484863196e-05, "loss": 1.0096, "step": 473000 }, { "epoch": 0.54, "learning_rate": 2.3157025562037024e-05, "loss": 1.0105, "step": 473500 }, { "epoch": 0.54, "learning_rate": 2.3128669927942666e-05, "loss": 0.9991, "step": 474000 }, { "epoch": 0.54, "learning_rate": 2.31003142938483e-05, "loss": 0.9982, "step": 474500 }, { "epoch": 0.54, "learning_rate": 2.3071958659753943e-05, "loss": 1.0006, "step": 475000 }, { "epoch": 0.54, "learning_rate": 2.304360302565958e-05, "loss": 1.0105, "step": 475500 }, { "epoch": 0.54, "learning_rate": 2.301524739156522e-05, "loss": 1.0055, "step": 476000 }, { "epoch": 0.54, "learning_rate": 2.2986891757470862e-05, "loss": 0.9948, "step": 476500 }, { "epoch": 0.54, "learning_rate": 2.29585361233765e-05, "loss": 1.0058, "step": 477000 }, { "epoch": 0.54, "learning_rate": 2.293018048928214e-05, "loss": 1.0053, "step": 477500 }, { "epoch": 0.54, "learning_rate": 2.2901824855187778e-05, "loss": 0.9997, "step": 478000 }, { "epoch": 0.54, "learning_rate": 2.2873525932361605e-05, "loss": 1.001, "step": 478500 }, { "epoch": 0.54, "learning_rate": 2.2845170298267247e-05, "loss": 1.0083, "step": 479000 }, { "epoch": 0.54, "learning_rate": 2.2816814664172882e-05, "loss": 0.9881, "step": 479500 }, { "epoch": 0.54, "learning_rate": 2.2788459030078524e-05, "loss": 1.009, "step": 480000 }, { "epoch": 0.54, "learning_rate": 2.2760103395984163e-05, "loss": 1.0054, "step": 480500 }, { "epoch": 0.55, "learning_rate": 2.27317477618898e-05, "loss": 0.9985, "step": 481000 }, { "epoch": 0.55, "learning_rate": 2.2703392127795444e-05, "loss": 0.9986, "step": 481500 }, { "epoch": 0.55, "learning_rate": 2.267503649370108e-05, "loss": 0.9972, "step": 482000 }, { "epoch": 0.55, "learning_rate": 2.264668085960672e-05, "loss": 1.0016, "step": 482500 }, { "epoch": 0.55, "learning_rate": 2.261838193678055e-05, "loss": 1.0047, "step": 483000 }, { "epoch": 0.55, "learning_rate": 2.2590026302686187e-05, "loss": 0.9989, "step": 483500 }, { "epoch": 0.55, "learning_rate": 2.2561784091128203e-05, "loss": 1.0026, "step": 484000 }, { "epoch": 0.55, "learning_rate": 2.2533428457033842e-05, "loss": 0.9959, "step": 484500 }, { "epoch": 0.55, "learning_rate": 2.2505072822939484e-05, "loss": 0.9968, "step": 485000 }, { "epoch": 0.55, "learning_rate": 2.2476717188845122e-05, "loss": 1.0093, "step": 485500 }, { "epoch": 0.55, "learning_rate": 2.244836155475076e-05, "loss": 1.0019, "step": 486000 }, { "epoch": 0.55, "learning_rate": 2.24200059206564e-05, "loss": 1.0069, "step": 486500 }, { "epoch": 0.55, "learning_rate": 2.2391650286562038e-05, "loss": 1.0065, "step": 487000 }, { "epoch": 0.55, "learning_rate": 2.236335136373587e-05, "loss": 0.9968, "step": 487500 }, { "epoch": 0.55, "learning_rate": 2.2334995729641504e-05, "loss": 0.9999, "step": 488000 }, { "epoch": 0.55, "learning_rate": 2.2306640095547146e-05, "loss": 1.0083, "step": 488500 }, { "epoch": 0.55, "learning_rate": 2.2278284461452785e-05, "loss": 1.0068, "step": 489000 }, { "epoch": 0.56, "learning_rate": 2.2249928827358424e-05, "loss": 0.9943, "step": 489500 }, { "epoch": 0.56, "learning_rate": 2.2221573193264066e-05, "loss": 1.0, "step": 490000 }, { "epoch": 0.56, "learning_rate": 2.2193274270437893e-05, "loss": 1.0014, "step": 490500 }, { "epoch": 0.56, "learning_rate": 2.216491863634353e-05, "loss": 1.0007, "step": 491000 }, { "epoch": 0.56, "learning_rate": 2.213656300224917e-05, "loss": 1.0129, "step": 491500 }, { "epoch": 0.56, "learning_rate": 2.210820736815481e-05, "loss": 1.0107, "step": 492000 }, { "epoch": 0.56, "learning_rate": 2.2079851734060447e-05, "loss": 0.9897, "step": 492500 }, { "epoch": 0.56, "learning_rate": 2.2051496099966086e-05, "loss": 1.0077, "step": 493000 }, { "epoch": 0.56, "learning_rate": 2.2023140465871728e-05, "loss": 0.9976, "step": 493500 }, { "epoch": 0.56, "learning_rate": 2.1994784831777367e-05, "loss": 1.0056, "step": 494000 }, { "epoch": 0.56, "learning_rate": 2.1966429197683005e-05, "loss": 1.0041, "step": 494500 }, { "epoch": 0.56, "learning_rate": 2.1938130274856833e-05, "loss": 1.0069, "step": 495000 }, { "epoch": 0.56, "learning_rate": 2.190983135203066e-05, "loss": 1.0037, "step": 495500 }, { "epoch": 0.56, "learning_rate": 2.1881475717936302e-05, "loss": 0.9918, "step": 496000 }, { "epoch": 0.56, "learning_rate": 2.185312008384194e-05, "loss": 1.0019, "step": 496500 }, { "epoch": 0.56, "learning_rate": 2.182476444974758e-05, "loss": 0.9973, "step": 497000 }, { "epoch": 0.56, "learning_rate": 2.1796408815653218e-05, "loss": 0.9979, "step": 497500 }, { "epoch": 0.56, "learning_rate": 2.176805318155886e-05, "loss": 1.01, "step": 498000 }, { "epoch": 0.57, "learning_rate": 2.1739697547464495e-05, "loss": 1.0116, "step": 498500 }, { "epoch": 0.57, "learning_rate": 2.1711341913370137e-05, "loss": 0.9946, "step": 499000 }, { "epoch": 0.57, "learning_rate": 2.1683042990543965e-05, "loss": 0.9969, "step": 499500 }, { "epoch": 0.57, "learning_rate": 2.1654744067717792e-05, "loss": 0.9998, "step": 500000 }, { "epoch": 0.57, "learning_rate": 2.162638843362343e-05, "loss": 1.0017, "step": 500500 }, { "epoch": 0.57, "learning_rate": 2.1598089510797258e-05, "loss": 0.9965, "step": 501000 }, { "epoch": 0.57, "learning_rate": 2.15697338767029e-05, "loss": 0.9956, "step": 501500 }, { "epoch": 0.57, "learning_rate": 2.1541378242608535e-05, "loss": 1.0097, "step": 502000 }, { "epoch": 0.57, "learning_rate": 2.1513022608514177e-05, "loss": 1.0106, "step": 502500 }, { "epoch": 0.57, "learning_rate": 2.1484666974419816e-05, "loss": 0.9964, "step": 503000 }, { "epoch": 0.57, "learning_rate": 2.1456311340325455e-05, "loss": 1.0046, "step": 503500 }, { "epoch": 0.57, "learning_rate": 2.1427955706231097e-05, "loss": 0.9957, "step": 504000 }, { "epoch": 0.57, "learning_rate": 2.1399600072136732e-05, "loss": 1.0013, "step": 504500 }, { "epoch": 0.57, "learning_rate": 2.1371244438042374e-05, "loss": 0.9992, "step": 505000 }, { "epoch": 0.57, "learning_rate": 2.1342888803948012e-05, "loss": 1.0072, "step": 505500 }, { "epoch": 0.57, "learning_rate": 2.131453316985365e-05, "loss": 1.0009, "step": 506000 }, { "epoch": 0.57, "learning_rate": 2.1286177535759293e-05, "loss": 0.9977, "step": 506500 }, { "epoch": 0.58, "learning_rate": 2.125782190166493e-05, "loss": 0.9949, "step": 507000 }, { "epoch": 0.58, "learning_rate": 2.122946626757057e-05, "loss": 0.9974, "step": 507500 }, { "epoch": 0.58, "learning_rate": 2.1201167344744398e-05, "loss": 1.0007, "step": 508000 }, { "epoch": 0.58, "learning_rate": 2.1172811710650036e-05, "loss": 0.9942, "step": 508500 }, { "epoch": 0.58, "learning_rate": 2.1144456076555678e-05, "loss": 1.005, "step": 509000 }, { "epoch": 0.58, "learning_rate": 2.1116100442461313e-05, "loss": 0.9941, "step": 509500 }, { "epoch": 0.58, "learning_rate": 2.1087801519635144e-05, "loss": 1.0026, "step": 510000 }, { "epoch": 0.58, "learning_rate": 2.1059445885540783e-05, "loss": 0.9952, "step": 510500 }, { "epoch": 0.58, "learning_rate": 2.103109025144642e-05, "loss": 0.9996, "step": 511000 }, { "epoch": 0.58, "learning_rate": 2.100273461735206e-05, "loss": 1.0008, "step": 511500 }, { "epoch": 0.58, "learning_rate": 2.09743789832577e-05, "loss": 0.9932, "step": 512000 }, { "epoch": 0.58, "learning_rate": 2.094602334916334e-05, "loss": 0.9992, "step": 512500 }, { "epoch": 0.58, "learning_rate": 2.0917724426337168e-05, "loss": 1.0031, "step": 513000 }, { "epoch": 0.58, "learning_rate": 2.0889368792242807e-05, "loss": 1.0025, "step": 513500 }, { "epoch": 0.58, "learning_rate": 2.0861013158148445e-05, "loss": 1.0033, "step": 514000 }, { "epoch": 0.58, "learning_rate": 2.0832657524054087e-05, "loss": 0.9991, "step": 514500 }, { "epoch": 0.58, "learning_rate": 2.0804301889959723e-05, "loss": 0.9925, "step": 515000 }, { "epoch": 0.58, "learning_rate": 2.0775946255865365e-05, "loss": 0.992, "step": 515500 }, { "epoch": 0.59, "learning_rate": 2.074770404430738e-05, "loss": 0.9922, "step": 516000 }, { "epoch": 0.59, "learning_rate": 2.071934841021302e-05, "loss": 1.0043, "step": 516500 }, { "epoch": 0.59, "learning_rate": 2.0690992776118658e-05, "loss": 0.9967, "step": 517000 }, { "epoch": 0.59, "learning_rate": 2.06626371420243e-05, "loss": 0.9938, "step": 517500 }, { "epoch": 0.59, "learning_rate": 2.0634281507929935e-05, "loss": 1.0054, "step": 518000 }, { "epoch": 0.59, "learning_rate": 2.0605925873835577e-05, "loss": 0.9903, "step": 518500 }, { "epoch": 0.59, "learning_rate": 2.0577570239741216e-05, "loss": 1.0006, "step": 519000 }, { "epoch": 0.59, "learning_rate": 2.0549214605646855e-05, "loss": 0.991, "step": 519500 }, { "epoch": 0.59, "learning_rate": 2.0520858971552497e-05, "loss": 0.9868, "step": 520000 }, { "epoch": 0.59, "learning_rate": 2.0492503337458132e-05, "loss": 0.9972, "step": 520500 }, { "epoch": 0.59, "learning_rate": 2.0464147703363774e-05, "loss": 0.9961, "step": 521000 }, { "epoch": 0.59, "learning_rate": 2.0435792069269412e-05, "loss": 0.9924, "step": 521500 }, { "epoch": 0.59, "learning_rate": 2.040743643517505e-05, "loss": 1.0049, "step": 522000 }, { "epoch": 0.59, "learning_rate": 2.037908080108069e-05, "loss": 0.994, "step": 522500 }, { "epoch": 0.59, "learning_rate": 2.035072516698633e-05, "loss": 0.9881, "step": 523000 }, { "epoch": 0.59, "learning_rate": 2.032242624416016e-05, "loss": 0.9917, "step": 523500 }, { "epoch": 0.59, "learning_rate": 2.0294070610065798e-05, "loss": 0.9919, "step": 524000 }, { "epoch": 0.59, "learning_rate": 2.0265828398507814e-05, "loss": 0.9902, "step": 524500 }, { "epoch": 0.6, "learning_rate": 2.0237472764413453e-05, "loss": 0.9817, "step": 525000 }, { "epoch": 0.6, "learning_rate": 2.020911713031909e-05, "loss": 0.9926, "step": 525500 }, { "epoch": 0.6, "learning_rate": 2.0180761496224733e-05, "loss": 0.9852, "step": 526000 }, { "epoch": 0.6, "learning_rate": 2.0152405862130372e-05, "loss": 1.001, "step": 526500 }, { "epoch": 0.6, "learning_rate": 2.012405022803601e-05, "loss": 1.0008, "step": 527000 }, { "epoch": 0.6, "learning_rate": 2.009569459394165e-05, "loss": 0.9931, "step": 527500 }, { "epoch": 0.6, "learning_rate": 2.006733895984729e-05, "loss": 0.991, "step": 528000 }, { "epoch": 0.6, "learning_rate": 2.0038983325752926e-05, "loss": 0.989, "step": 528500 }, { "epoch": 0.6, "learning_rate": 2.0010627691658568e-05, "loss": 0.9918, "step": 529000 }, { "epoch": 0.6, "learning_rate": 1.9982272057564207e-05, "loss": 0.9946, "step": 529500 }, { "epoch": 0.6, "learning_rate": 1.9953973134738034e-05, "loss": 0.9953, "step": 530000 }, { "epoch": 0.6, "learning_rate": 1.9925617500643673e-05, "loss": 0.9923, "step": 530500 }, { "epoch": 0.6, "learning_rate": 1.9897318577817504e-05, "loss": 0.995, "step": 531000 }, { "epoch": 0.6, "learning_rate": 1.986896294372314e-05, "loss": 0.9963, "step": 531500 }, { "epoch": 0.6, "learning_rate": 1.9840664020896966e-05, "loss": 0.9852, "step": 532000 }, { "epoch": 0.6, "learning_rate": 1.981230838680261e-05, "loss": 0.9863, "step": 532500 }, { "epoch": 0.6, "learning_rate": 1.9783952752708247e-05, "loss": 1.0024, "step": 533000 }, { "epoch": 0.61, "learning_rate": 1.9755597118613886e-05, "loss": 0.9835, "step": 533500 }, { "epoch": 0.61, "learning_rate": 1.9727241484519528e-05, "loss": 0.9939, "step": 534000 }, { "epoch": 0.61, "learning_rate": 1.9698885850425166e-05, "loss": 0.9932, "step": 534500 }, { "epoch": 0.61, "learning_rate": 1.9670530216330805e-05, "loss": 0.9922, "step": 535000 }, { "epoch": 0.61, "learning_rate": 1.9642174582236443e-05, "loss": 0.9876, "step": 535500 }, { "epoch": 0.61, "learning_rate": 1.9613818948142082e-05, "loss": 0.9955, "step": 536000 }, { "epoch": 0.61, "learning_rate": 1.958546331404772e-05, "loss": 0.9902, "step": 536500 }, { "epoch": 0.61, "learning_rate": 1.9557107679953363e-05, "loss": 0.9865, "step": 537000 }, { "epoch": 0.61, "learning_rate": 1.9528752045859e-05, "loss": 0.9973, "step": 537500 }, { "epoch": 0.61, "learning_rate": 1.950045312303283e-05, "loss": 0.9892, "step": 538000 }, { "epoch": 0.61, "learning_rate": 1.9472097488938467e-05, "loss": 0.9803, "step": 538500 }, { "epoch": 0.61, "learning_rate": 1.944374185484411e-05, "loss": 1.0036, "step": 539000 }, { "epoch": 0.61, "learning_rate": 1.9415386220749744e-05, "loss": 0.9909, "step": 539500 }, { "epoch": 0.61, "learning_rate": 1.9387030586655386e-05, "loss": 0.9942, "step": 540000 }, { "epoch": 0.61, "learning_rate": 1.9358674952561025e-05, "loss": 0.9936, "step": 540500 }, { "epoch": 0.61, "learning_rate": 1.9330376029734853e-05, "loss": 0.9986, "step": 541000 }, { "epoch": 0.61, "learning_rate": 1.930202039564049e-05, "loss": 0.9943, "step": 541500 }, { "epoch": 0.61, "learning_rate": 1.927366476154613e-05, "loss": 0.9922, "step": 542000 }, { "epoch": 0.62, "learning_rate": 1.9245309127451772e-05, "loss": 0.9821, "step": 542500 }, { "epoch": 0.62, "learning_rate": 1.921695349335741e-05, "loss": 0.9926, "step": 543000 }, { "epoch": 0.62, "learning_rate": 1.918859785926305e-05, "loss": 0.998, "step": 543500 }, { "epoch": 0.62, "learning_rate": 1.9160298936436876e-05, "loss": 0.9919, "step": 544000 }, { "epoch": 0.62, "learning_rate": 1.913194330234252e-05, "loss": 0.9886, "step": 544500 }, { "epoch": 0.62, "learning_rate": 1.9103587668248154e-05, "loss": 0.9965, "step": 545000 }, { "epoch": 0.62, "learning_rate": 1.9075345456690173e-05, "loss": 0.9941, "step": 545500 }, { "epoch": 0.62, "learning_rate": 1.9046989822595812e-05, "loss": 0.9832, "step": 546000 }, { "epoch": 0.62, "learning_rate": 1.9018634188501454e-05, "loss": 0.9805, "step": 546500 }, { "epoch": 0.62, "learning_rate": 1.899027855440709e-05, "loss": 0.9913, "step": 547000 }, { "epoch": 0.62, "learning_rate": 1.896192292031273e-05, "loss": 0.9906, "step": 547500 }, { "epoch": 0.62, "learning_rate": 1.8933567286218366e-05, "loss": 0.9859, "step": 548000 }, { "epoch": 0.62, "learning_rate": 1.890521165212401e-05, "loss": 0.9951, "step": 548500 }, { "epoch": 0.62, "learning_rate": 1.8876856018029647e-05, "loss": 0.9988, "step": 549000 }, { "epoch": 0.62, "learning_rate": 1.8848500383935286e-05, "loss": 0.9934, "step": 549500 }, { "epoch": 0.62, "learning_rate": 1.8820144749840928e-05, "loss": 1.0011, "step": 550000 }, { "epoch": 0.62, "learning_rate": 1.8791845827014755e-05, "loss": 0.9946, "step": 550500 }, { "epoch": 0.62, "learning_rate": 1.8763490192920394e-05, "loss": 0.9864, "step": 551000 }, { "epoch": 0.63, "learning_rate": 1.8735134558826032e-05, "loss": 0.9965, "step": 551500 }, { "epoch": 0.63, "learning_rate": 1.8706835635999863e-05, "loss": 0.9811, "step": 552000 }, { "epoch": 0.63, "learning_rate": 1.8678480001905498e-05, "loss": 0.9851, "step": 552500 }, { "epoch": 0.63, "learning_rate": 1.865012436781114e-05, "loss": 0.9932, "step": 553000 }, { "epoch": 0.63, "learning_rate": 1.8621768733716776e-05, "loss": 0.9888, "step": 553500 }, { "epoch": 0.63, "learning_rate": 1.8593413099622418e-05, "loss": 0.9839, "step": 554000 }, { "epoch": 0.63, "learning_rate": 1.8565114176796245e-05, "loss": 0.9882, "step": 554500 }, { "epoch": 0.63, "learning_rate": 1.8536758542701884e-05, "loss": 0.9815, "step": 555000 }, { "epoch": 0.63, "learning_rate": 1.8508402908607526e-05, "loss": 0.9839, "step": 555500 }, { "epoch": 0.63, "learning_rate": 1.8480047274513164e-05, "loss": 0.9842, "step": 556000 }, { "epoch": 0.63, "learning_rate": 1.8451691640418803e-05, "loss": 0.9871, "step": 556500 }, { "epoch": 0.63, "learning_rate": 1.842333600632444e-05, "loss": 0.9908, "step": 557000 }, { "epoch": 0.63, "learning_rate": 1.839498037223008e-05, "loss": 0.9846, "step": 557500 }, { "epoch": 0.63, "learning_rate": 1.8366624738135722e-05, "loss": 0.9952, "step": 558000 }, { "epoch": 0.63, "learning_rate": 1.8338269104041357e-05, "loss": 0.997, "step": 558500 }, { "epoch": 0.63, "learning_rate": 1.8309913469947e-05, "loss": 0.9956, "step": 559000 }, { "epoch": 0.63, "learning_rate": 1.8281557835852638e-05, "loss": 0.9836, "step": 559500 }, { "epoch": 0.64, "learning_rate": 1.8253202201758276e-05, "loss": 0.9878, "step": 560000 }, { "epoch": 0.64, "learning_rate": 1.822484656766392e-05, "loss": 0.9938, "step": 560500 }, { "epoch": 0.64, "learning_rate": 1.8196547644837746e-05, "loss": 0.983, "step": 561000 }, { "epoch": 0.64, "learning_rate": 1.8168192010743384e-05, "loss": 0.9908, "step": 561500 }, { "epoch": 0.64, "learning_rate": 1.8139836376649023e-05, "loss": 0.9919, "step": 562000 }, { "epoch": 0.64, "learning_rate": 1.8111480742554662e-05, "loss": 0.9829, "step": 562500 }, { "epoch": 0.64, "learning_rate": 1.8083125108460304e-05, "loss": 0.9736, "step": 563000 }, { "epoch": 0.64, "learning_rate": 1.805476947436594e-05, "loss": 0.981, "step": 563500 }, { "epoch": 0.64, "learning_rate": 1.802641384027158e-05, "loss": 0.9936, "step": 564000 }, { "epoch": 0.64, "learning_rate": 1.799805820617722e-05, "loss": 0.99, "step": 564500 }, { "epoch": 0.64, "learning_rate": 1.7969702572082858e-05, "loss": 0.9939, "step": 565000 }, { "epoch": 0.64, "learning_rate": 1.7941403649256686e-05, "loss": 0.9803, "step": 565500 }, { "epoch": 0.64, "learning_rate": 1.7913048015162328e-05, "loss": 0.9912, "step": 566000 }, { "epoch": 0.64, "learning_rate": 1.788474909233615e-05, "loss": 0.992, "step": 566500 }, { "epoch": 0.64, "learning_rate": 1.7856393458241794e-05, "loss": 0.9903, "step": 567000 }, { "epoch": 0.64, "learning_rate": 1.7828037824147432e-05, "loss": 0.976, "step": 567500 }, { "epoch": 0.64, "learning_rate": 1.779968219005307e-05, "loss": 0.9914, "step": 568000 }, { "epoch": 0.64, "learning_rate": 1.7771326555958713e-05, "loss": 0.9889, "step": 568500 }, { "epoch": 0.65, "learning_rate": 1.7742970921864348e-05, "loss": 0.9841, "step": 569000 }, { "epoch": 0.65, "learning_rate": 1.7714671999038176e-05, "loss": 0.9846, "step": 569500 }, { "epoch": 0.65, "learning_rate": 1.7686316364943818e-05, "loss": 0.9827, "step": 570000 }, { "epoch": 0.65, "learning_rate": 1.7657960730849456e-05, "loss": 0.9951, "step": 570500 }, { "epoch": 0.65, "learning_rate": 1.7629605096755095e-05, "loss": 0.983, "step": 571000 }, { "epoch": 0.65, "learning_rate": 1.7601249462660733e-05, "loss": 0.981, "step": 571500 }, { "epoch": 0.65, "learning_rate": 1.757295053983456e-05, "loss": 0.9897, "step": 572000 }, { "epoch": 0.65, "learning_rate": 1.7544594905740203e-05, "loss": 0.977, "step": 572500 }, { "epoch": 0.65, "learning_rate": 1.751629598291403e-05, "loss": 0.9825, "step": 573000 }, { "epoch": 0.65, "learning_rate": 1.748794034881967e-05, "loss": 0.9795, "step": 573500 }, { "epoch": 0.65, "learning_rate": 1.7459584714725307e-05, "loss": 0.9859, "step": 574000 }, { "epoch": 0.65, "learning_rate": 1.7431285791899135e-05, "loss": 0.9837, "step": 574500 }, { "epoch": 0.65, "learning_rate": 1.7402930157804777e-05, "loss": 0.9859, "step": 575000 }, { "epoch": 0.65, "learning_rate": 1.7374574523710415e-05, "loss": 0.9728, "step": 575500 }, { "epoch": 0.65, "learning_rate": 1.7346218889616054e-05, "loss": 0.9748, "step": 576000 }, { "epoch": 0.65, "learning_rate": 1.7317863255521693e-05, "loss": 0.9908, "step": 576500 }, { "epoch": 0.65, "learning_rate": 1.7289507621427335e-05, "loss": 0.9836, "step": 577000 }, { "epoch": 0.66, "learning_rate": 1.726115198733297e-05, "loss": 0.9849, "step": 577500 }, { "epoch": 0.66, "learning_rate": 1.7232796353238612e-05, "loss": 0.981, "step": 578000 }, { "epoch": 0.66, "learning_rate": 1.720444071914425e-05, "loss": 0.9864, "step": 578500 }, { "epoch": 0.66, "learning_rate": 1.7176141796318078e-05, "loss": 0.9832, "step": 579000 }, { "epoch": 0.66, "learning_rate": 1.7147786162223717e-05, "loss": 0.9839, "step": 579500 }, { "epoch": 0.66, "learning_rate": 1.711943052812936e-05, "loss": 0.9855, "step": 580000 }, { "epoch": 0.66, "learning_rate": 1.7091074894034997e-05, "loss": 0.9783, "step": 580500 }, { "epoch": 0.66, "learning_rate": 1.7062719259940636e-05, "loss": 0.9795, "step": 581000 }, { "epoch": 0.66, "learning_rate": 1.7034363625846274e-05, "loss": 0.9807, "step": 581500 }, { "epoch": 0.66, "learning_rate": 1.7006007991751913e-05, "loss": 0.9904, "step": 582000 }, { "epoch": 0.66, "learning_rate": 1.697765235765755e-05, "loss": 0.9851, "step": 582500 }, { "epoch": 0.66, "learning_rate": 1.6949296723563194e-05, "loss": 0.9822, "step": 583000 }, { "epoch": 0.66, "learning_rate": 1.6920941089468832e-05, "loss": 0.9958, "step": 583500 }, { "epoch": 0.66, "learning_rate": 1.689258545537447e-05, "loss": 0.9844, "step": 584000 }, { "epoch": 0.66, "learning_rate": 1.6864229821280113e-05, "loss": 0.9854, "step": 584500 }, { "epoch": 0.66, "learning_rate": 1.6835874187185748e-05, "loss": 0.9834, "step": 585000 }, { "epoch": 0.66, "learning_rate": 1.6807575264359576e-05, "loss": 0.9897, "step": 585500 }, { "epoch": 0.66, "learning_rate": 1.6779219630265218e-05, "loss": 0.9865, "step": 586000 }, { "epoch": 0.67, "learning_rate": 1.6750863996170856e-05, "loss": 0.9856, "step": 586500 }, { "epoch": 0.67, "learning_rate": 1.6722508362076495e-05, "loss": 0.9778, "step": 587000 }, { "epoch": 0.67, "learning_rate": 1.6694209439250326e-05, "loss": 0.9848, "step": 587500 }, { "epoch": 0.67, "learning_rate": 1.666585380515596e-05, "loss": 0.984, "step": 588000 }, { "epoch": 0.67, "learning_rate": 1.6637554882329788e-05, "loss": 0.9857, "step": 588500 }, { "epoch": 0.67, "learning_rate": 1.660919924823543e-05, "loss": 0.9821, "step": 589000 }, { "epoch": 0.67, "learning_rate": 1.658084361414107e-05, "loss": 0.9858, "step": 589500 }, { "epoch": 0.67, "learning_rate": 1.6552487980046707e-05, "loss": 0.9867, "step": 590000 }, { "epoch": 0.67, "learning_rate": 1.652413234595235e-05, "loss": 0.9771, "step": 590500 }, { "epoch": 0.67, "learning_rate": 1.6495776711857985e-05, "loss": 0.9785, "step": 591000 }, { "epoch": 0.67, "learning_rate": 1.6467421077763627e-05, "loss": 0.9895, "step": 591500 }, { "epoch": 0.67, "learning_rate": 1.6439065443669265e-05, "loss": 0.9833, "step": 592000 }, { "epoch": 0.67, "learning_rate": 1.6410709809574904e-05, "loss": 0.993, "step": 592500 }, { "epoch": 0.67, "learning_rate": 1.6382410886748735e-05, "loss": 0.9815, "step": 593000 }, { "epoch": 0.67, "learning_rate": 1.635405525265437e-05, "loss": 0.9872, "step": 593500 }, { "epoch": 0.67, "learning_rate": 1.6325699618560012e-05, "loss": 0.979, "step": 594000 }, { "epoch": 0.67, "learning_rate": 1.629740069573384e-05, "loss": 0.9726, "step": 594500 }, { "epoch": 0.67, "learning_rate": 1.6269045061639478e-05, "loss": 0.9865, "step": 595000 }, { "epoch": 0.68, "learning_rate": 1.6240689427545117e-05, "loss": 0.972, "step": 595500 }, { "epoch": 0.68, "learning_rate": 1.6212333793450755e-05, "loss": 0.991, "step": 596000 }, { "epoch": 0.68, "learning_rate": 1.6183978159356397e-05, "loss": 0.9768, "step": 596500 }, { "epoch": 0.68, "learning_rate": 1.6155679236530225e-05, "loss": 0.982, "step": 597000 }, { "epoch": 0.68, "learning_rate": 1.6127323602435863e-05, "loss": 0.9815, "step": 597500 }, { "epoch": 0.68, "learning_rate": 1.6098967968341502e-05, "loss": 0.9774, "step": 598000 }, { "epoch": 0.68, "learning_rate": 1.6070612334247144e-05, "loss": 0.9892, "step": 598500 }, { "epoch": 0.68, "learning_rate": 1.604225670015278e-05, "loss": 0.9855, "step": 599000 }, { "epoch": 0.68, "learning_rate": 1.6013957777326607e-05, "loss": 0.9809, "step": 599500 }, { "epoch": 0.68, "learning_rate": 1.598560214323225e-05, "loss": 0.982, "step": 600000 }, { "epoch": 0.68, "learning_rate": 1.5957246509137887e-05, "loss": 0.9747, "step": 600500 }, { "epoch": 0.68, "learning_rate": 1.5928890875043526e-05, "loss": 0.9738, "step": 601000 }, { "epoch": 0.68, "learning_rate": 1.5900535240949164e-05, "loss": 0.9766, "step": 601500 }, { "epoch": 0.68, "learning_rate": 1.5872179606854806e-05, "loss": 0.973, "step": 602000 }, { "epoch": 0.68, "learning_rate": 1.5843823972760445e-05, "loss": 0.9879, "step": 602500 }, { "epoch": 0.68, "learning_rate": 1.5815468338666084e-05, "loss": 0.986, "step": 603000 }, { "epoch": 0.68, "learning_rate": 1.5787112704571726e-05, "loss": 0.9771, "step": 603500 }, { "epoch": 0.69, "learning_rate": 1.575875707047736e-05, "loss": 0.9872, "step": 604000 }, { "epoch": 0.69, "learning_rate": 1.5730458147651188e-05, "loss": 0.99, "step": 604500 }, { "epoch": 0.69, "learning_rate": 1.570210251355683e-05, "loss": 0.973, "step": 605000 }, { "epoch": 0.69, "learning_rate": 1.567374687946247e-05, "loss": 0.9817, "step": 605500 }, { "epoch": 0.69, "learning_rate": 1.5645391245368107e-05, "loss": 0.9812, "step": 606000 }, { "epoch": 0.69, "learning_rate": 1.5617035611273746e-05, "loss": 0.9915, "step": 606500 }, { "epoch": 0.69, "learning_rate": 1.5588679977179385e-05, "loss": 0.9732, "step": 607000 }, { "epoch": 0.69, "learning_rate": 1.5560324343085027e-05, "loss": 0.9905, "step": 607500 }, { "epoch": 0.69, "learning_rate": 1.5531968708990665e-05, "loss": 0.9749, "step": 608000 }, { "epoch": 0.69, "learning_rate": 1.5503613074896304e-05, "loss": 0.9836, "step": 608500 }, { "epoch": 0.69, "learning_rate": 1.5475314152070135e-05, "loss": 0.9862, "step": 609000 }, { "epoch": 0.69, "learning_rate": 1.544695851797577e-05, "loss": 0.9842, "step": 609500 }, { "epoch": 0.69, "learning_rate": 1.5418659595149597e-05, "loss": 0.9814, "step": 610000 }, { "epoch": 0.69, "learning_rate": 1.539030396105524e-05, "loss": 0.9939, "step": 610500 }, { "epoch": 0.69, "learning_rate": 1.5361948326960878e-05, "loss": 0.9725, "step": 611000 }, { "epoch": 0.69, "learning_rate": 1.5333592692866517e-05, "loss": 0.9773, "step": 611500 }, { "epoch": 0.69, "learning_rate": 1.5305237058772155e-05, "loss": 0.9796, "step": 612000 }, { "epoch": 0.69, "learning_rate": 1.5276881424677797e-05, "loss": 0.9804, "step": 612500 }, { "epoch": 0.7, "learning_rate": 1.5248525790583434e-05, "loss": 0.9725, "step": 613000 }, { "epoch": 0.7, "learning_rate": 1.5220170156489074e-05, "loss": 0.972, "step": 613500 }, { "epoch": 0.7, "learning_rate": 1.5191871233662902e-05, "loss": 0.9727, "step": 614000 }, { "epoch": 0.7, "learning_rate": 1.5163515599568542e-05, "loss": 0.9777, "step": 614500 }, { "epoch": 0.7, "learning_rate": 1.5135159965474179e-05, "loss": 0.9731, "step": 615000 }, { "epoch": 0.7, "learning_rate": 1.510680433137982e-05, "loss": 0.9727, "step": 615500 }, { "epoch": 0.7, "learning_rate": 1.507844869728546e-05, "loss": 0.9839, "step": 616000 }, { "epoch": 0.7, "learning_rate": 1.5050093063191098e-05, "loss": 0.9794, "step": 616500 }, { "epoch": 0.7, "learning_rate": 1.5021737429096739e-05, "loss": 0.973, "step": 617000 }, { "epoch": 0.7, "learning_rate": 1.4993381795002376e-05, "loss": 0.9803, "step": 617500 }, { "epoch": 0.7, "learning_rate": 1.4965026160908016e-05, "loss": 0.9746, "step": 618000 }, { "epoch": 0.7, "learning_rate": 1.4936670526813656e-05, "loss": 0.972, "step": 618500 }, { "epoch": 0.7, "learning_rate": 1.490842831525567e-05, "loss": 0.9896, "step": 619000 }, { "epoch": 0.7, "learning_rate": 1.4880072681161311e-05, "loss": 0.9666, "step": 619500 }, { "epoch": 0.7, "learning_rate": 1.4851717047066951e-05, "loss": 0.9798, "step": 620000 }, { "epoch": 0.7, "learning_rate": 1.4823361412972588e-05, "loss": 0.9755, "step": 620500 }, { "epoch": 0.7, "learning_rate": 1.4795005778878229e-05, "loss": 0.976, "step": 621000 }, { "epoch": 0.7, "learning_rate": 1.4766650144783869e-05, "loss": 0.9763, "step": 621500 }, { "epoch": 0.71, "learning_rate": 1.4738294510689507e-05, "loss": 0.9684, "step": 622000 }, { "epoch": 0.71, "learning_rate": 1.4709938876595148e-05, "loss": 0.9886, "step": 622500 }, { "epoch": 0.71, "learning_rate": 1.4681583242500785e-05, "loss": 0.971, "step": 623000 }, { "epoch": 0.71, "learning_rate": 1.4653284319674616e-05, "loss": 0.9841, "step": 623500 }, { "epoch": 0.71, "learning_rate": 1.4624928685580252e-05, "loss": 0.9822, "step": 624000 }, { "epoch": 0.71, "learning_rate": 1.4596573051485893e-05, "loss": 0.9764, "step": 624500 }, { "epoch": 0.71, "learning_rate": 1.456827412865972e-05, "loss": 0.9775, "step": 625000 }, { "epoch": 0.71, "learning_rate": 1.453991849456536e-05, "loss": 0.9756, "step": 625500 }, { "epoch": 0.71, "learning_rate": 1.4511562860470997e-05, "loss": 0.9922, "step": 626000 }, { "epoch": 0.71, "learning_rate": 1.4483207226376638e-05, "loss": 0.9789, "step": 626500 }, { "epoch": 0.71, "learning_rate": 1.4454851592282278e-05, "loss": 0.9804, "step": 627000 }, { "epoch": 0.71, "learning_rate": 1.4426495958187917e-05, "loss": 0.9702, "step": 627500 }, { "epoch": 0.71, "learning_rate": 1.4398140324093557e-05, "loss": 0.9721, "step": 628000 }, { "epoch": 0.71, "learning_rate": 1.4369784689999197e-05, "loss": 0.9782, "step": 628500 }, { "epoch": 0.71, "learning_rate": 1.4341485767173025e-05, "loss": 0.9725, "step": 629000 }, { "epoch": 0.71, "learning_rate": 1.4313130133078662e-05, "loss": 0.9715, "step": 629500 }, { "epoch": 0.71, "learning_rate": 1.4284831210252492e-05, "loss": 0.9695, "step": 630000 }, { "epoch": 0.72, "learning_rate": 1.425647557615813e-05, "loss": 0.9712, "step": 630500 }, { "epoch": 0.72, "learning_rate": 1.422811994206377e-05, "loss": 0.9682, "step": 631000 }, { "epoch": 0.72, "learning_rate": 1.4199764307969407e-05, "loss": 0.9719, "step": 631500 }, { "epoch": 0.72, "learning_rate": 1.4171408673875047e-05, "loss": 0.9745, "step": 632000 }, { "epoch": 0.72, "learning_rate": 1.4143053039780687e-05, "loss": 0.9769, "step": 632500 }, { "epoch": 0.72, "learning_rate": 1.4114697405686326e-05, "loss": 0.97, "step": 633000 }, { "epoch": 0.72, "learning_rate": 1.4086341771591966e-05, "loss": 0.9707, "step": 633500 }, { "epoch": 0.72, "learning_rate": 1.4058042848765794e-05, "loss": 0.9803, "step": 634000 }, { "epoch": 0.72, "learning_rate": 1.4029687214671434e-05, "loss": 0.9779, "step": 634500 }, { "epoch": 0.72, "learning_rate": 1.400133158057707e-05, "loss": 0.9755, "step": 635000 }, { "epoch": 0.72, "learning_rate": 1.3973032657750902e-05, "loss": 0.9712, "step": 635500 }, { "epoch": 0.72, "learning_rate": 1.3944677023656538e-05, "loss": 0.9684, "step": 636000 }, { "epoch": 0.72, "learning_rate": 1.3916321389562179e-05, "loss": 0.9793, "step": 636500 }, { "epoch": 0.72, "learning_rate": 1.3888022466736006e-05, "loss": 0.9718, "step": 637000 }, { "epoch": 0.72, "learning_rate": 1.3859723543909834e-05, "loss": 0.9717, "step": 637500 }, { "epoch": 0.72, "learning_rate": 1.3831367909815474e-05, "loss": 0.9764, "step": 638000 }, { "epoch": 0.72, "learning_rate": 1.3803012275721114e-05, "loss": 0.9641, "step": 638500 }, { "epoch": 0.72, "learning_rate": 1.3774656641626751e-05, "loss": 0.9771, "step": 639000 }, { "epoch": 0.73, "learning_rate": 1.3746301007532391e-05, "loss": 0.9691, "step": 639500 }, { "epoch": 0.73, "learning_rate": 1.3717945373438028e-05, "loss": 0.971, "step": 640000 }, { "epoch": 0.73, "learning_rate": 1.3689589739343669e-05, "loss": 0.9731, "step": 640500 }, { "epoch": 0.73, "learning_rate": 1.3661234105249309e-05, "loss": 0.9767, "step": 641000 }, { "epoch": 0.73, "learning_rate": 1.3632878471154948e-05, "loss": 0.9653, "step": 641500 }, { "epoch": 0.73, "learning_rate": 1.3604522837060588e-05, "loss": 0.9729, "step": 642000 }, { "epoch": 0.73, "learning_rate": 1.3576167202966228e-05, "loss": 0.9628, "step": 642500 }, { "epoch": 0.73, "learning_rate": 1.3547811568871865e-05, "loss": 0.9756, "step": 643000 }, { "epoch": 0.73, "learning_rate": 1.3519512646045693e-05, "loss": 0.9818, "step": 643500 }, { "epoch": 0.73, "learning_rate": 1.3491157011951333e-05, "loss": 0.9808, "step": 644000 }, { "epoch": 0.73, "learning_rate": 1.346285808912516e-05, "loss": 0.9755, "step": 644500 }, { "epoch": 0.73, "learning_rate": 1.34345024550308e-05, "loss": 0.9725, "step": 645000 }, { "epoch": 0.73, "learning_rate": 1.3406146820936441e-05, "loss": 0.9754, "step": 645500 }, { "epoch": 0.73, "learning_rate": 1.3377791186842078e-05, "loss": 0.9796, "step": 646000 }, { "epoch": 0.73, "learning_rate": 1.3349435552747718e-05, "loss": 0.9779, "step": 646500 }, { "epoch": 0.73, "learning_rate": 1.3321079918653357e-05, "loss": 0.9741, "step": 647000 }, { "epoch": 0.73, "learning_rate": 1.3292780995827186e-05, "loss": 0.9711, "step": 647500 }, { "epoch": 0.73, "learning_rate": 1.3264425361732825e-05, "loss": 0.9764, "step": 648000 }, { "epoch": 0.74, "learning_rate": 1.3236069727638465e-05, "loss": 0.9716, "step": 648500 }, { "epoch": 0.74, "learning_rate": 1.3207714093544105e-05, "loss": 0.9703, "step": 649000 }, { "epoch": 0.74, "learning_rate": 1.3179358459449742e-05, "loss": 0.9741, "step": 649500 }, { "epoch": 0.74, "learning_rate": 1.3151002825355382e-05, "loss": 0.962, "step": 650000 }, { "epoch": 0.74, "learning_rate": 1.312264719126102e-05, "loss": 0.9723, "step": 650500 }, { "epoch": 0.74, "learning_rate": 1.309429155716666e-05, "loss": 0.971, "step": 651000 }, { "epoch": 0.74, "learning_rate": 1.30659359230723e-05, "loss": 0.9659, "step": 651500 }, { "epoch": 0.74, "learning_rate": 1.3037580288977938e-05, "loss": 0.973, "step": 652000 }, { "epoch": 0.74, "learning_rate": 1.3009224654883579e-05, "loss": 0.9649, "step": 652500 }, { "epoch": 0.74, "learning_rate": 1.2980925732057406e-05, "loss": 0.9739, "step": 653000 }, { "epoch": 0.74, "learning_rate": 1.2952626809231234e-05, "loss": 0.9721, "step": 653500 }, { "epoch": 0.74, "learning_rate": 1.2924271175136874e-05, "loss": 0.9722, "step": 654000 }, { "epoch": 0.74, "learning_rate": 1.2895915541042514e-05, "loss": 0.9699, "step": 654500 }, { "epoch": 0.74, "learning_rate": 1.2867559906948151e-05, "loss": 0.9611, "step": 655000 }, { "epoch": 0.74, "learning_rate": 1.2839204272853791e-05, "loss": 0.9761, "step": 655500 }, { "epoch": 0.74, "learning_rate": 1.2810848638759428e-05, "loss": 0.9618, "step": 656000 }, { "epoch": 0.74, "learning_rate": 1.2782493004665069e-05, "loss": 0.9714, "step": 656500 }, { "epoch": 0.75, "learning_rate": 1.2754137370570709e-05, "loss": 0.9764, "step": 657000 }, { "epoch": 0.75, "learning_rate": 1.2725781736476348e-05, "loss": 0.9708, "step": 657500 }, { "epoch": 0.75, "learning_rate": 1.2697426102381988e-05, "loss": 0.9673, "step": 658000 }, { "epoch": 0.75, "learning_rate": 1.2669127179555815e-05, "loss": 0.9642, "step": 658500 }, { "epoch": 0.75, "learning_rate": 1.2640771545461456e-05, "loss": 0.9664, "step": 659000 }, { "epoch": 0.75, "learning_rate": 1.2612415911367093e-05, "loss": 0.9681, "step": 659500 }, { "epoch": 0.75, "learning_rate": 1.2584116988540923e-05, "loss": 0.9707, "step": 660000 }, { "epoch": 0.75, "learning_rate": 1.255576135444656e-05, "loss": 0.961, "step": 660500 }, { "epoch": 0.75, "learning_rate": 1.25274057203522e-05, "loss": 0.9649, "step": 661000 }, { "epoch": 0.75, "learning_rate": 1.249905008625784e-05, "loss": 0.9611, "step": 661500 }, { "epoch": 0.75, "learning_rate": 1.2470694452163478e-05, "loss": 0.9685, "step": 662000 }, { "epoch": 0.75, "learning_rate": 1.2442338818069118e-05, "loss": 0.9748, "step": 662500 }, { "epoch": 0.75, "learning_rate": 1.2413983183974757e-05, "loss": 0.9633, "step": 663000 }, { "epoch": 0.75, "learning_rate": 1.2385627549880397e-05, "loss": 0.9667, "step": 663500 }, { "epoch": 0.75, "learning_rate": 1.2357271915786036e-05, "loss": 0.9796, "step": 664000 }, { "epoch": 0.75, "learning_rate": 1.2328972992959865e-05, "loss": 0.9569, "step": 664500 }, { "epoch": 0.75, "learning_rate": 1.2300617358865503e-05, "loss": 0.9757, "step": 665000 }, { "epoch": 0.75, "learning_rate": 1.2272261724771142e-05, "loss": 0.97, "step": 665500 }, { "epoch": 0.76, "learning_rate": 1.2243906090676782e-05, "loss": 0.9733, "step": 666000 }, { "epoch": 0.76, "learning_rate": 1.2215550456582421e-05, "loss": 0.9563, "step": 666500 }, { "epoch": 0.76, "learning_rate": 1.218719482248806e-05, "loss": 0.9745, "step": 667000 }, { "epoch": 0.76, "learning_rate": 1.2158839188393698e-05, "loss": 0.9661, "step": 667500 }, { "epoch": 0.76, "learning_rate": 1.2130540265567527e-05, "loss": 0.9667, "step": 668000 }, { "epoch": 0.76, "learning_rate": 1.2102184631473166e-05, "loss": 0.9658, "step": 668500 }, { "epoch": 0.76, "learning_rate": 1.2073885708646993e-05, "loss": 0.9702, "step": 669000 }, { "epoch": 0.76, "learning_rate": 1.2045530074552634e-05, "loss": 0.9644, "step": 669500 }, { "epoch": 0.76, "learning_rate": 1.2017174440458272e-05, "loss": 0.9734, "step": 670000 }, { "epoch": 0.76, "learning_rate": 1.1988818806363913e-05, "loss": 0.9704, "step": 670500 }, { "epoch": 0.76, "learning_rate": 1.1960463172269551e-05, "loss": 0.9614, "step": 671000 }, { "epoch": 0.76, "learning_rate": 1.1932107538175192e-05, "loss": 0.9628, "step": 671500 }, { "epoch": 0.76, "learning_rate": 1.190375190408083e-05, "loss": 0.9607, "step": 672000 }, { "epoch": 0.76, "learning_rate": 1.1875396269986469e-05, "loss": 0.9652, "step": 672500 }, { "epoch": 0.76, "learning_rate": 1.1847097347160298e-05, "loss": 0.962, "step": 673000 }, { "epoch": 0.76, "learning_rate": 1.1818741713065936e-05, "loss": 0.9572, "step": 673500 }, { "epoch": 0.76, "learning_rate": 1.1790386078971575e-05, "loss": 0.9683, "step": 674000 }, { "epoch": 0.77, "learning_rate": 1.1762030444877214e-05, "loss": 0.9622, "step": 674500 }, { "epoch": 0.77, "learning_rate": 1.1733674810782854e-05, "loss": 0.9601, "step": 675000 }, { "epoch": 0.77, "learning_rate": 1.1705375887956681e-05, "loss": 0.9681, "step": 675500 }, { "epoch": 0.77, "learning_rate": 1.1677020253862322e-05, "loss": 0.9731, "step": 676000 }, { "epoch": 0.77, "learning_rate": 1.1648664619767962e-05, "loss": 0.9673, "step": 676500 }, { "epoch": 0.77, "learning_rate": 1.16203089856736e-05, "loss": 0.9699, "step": 677000 }, { "epoch": 0.77, "learning_rate": 1.159195335157924e-05, "loss": 0.969, "step": 677500 }, { "epoch": 0.77, "learning_rate": 1.1563597717484878e-05, "loss": 0.9682, "step": 678000 }, { "epoch": 0.77, "learning_rate": 1.1535242083390518e-05, "loss": 0.9603, "step": 678500 }, { "epoch": 0.77, "learning_rate": 1.1506886449296157e-05, "loss": 0.9669, "step": 679000 }, { "epoch": 0.77, "learning_rate": 1.1478587526469984e-05, "loss": 0.9622, "step": 679500 }, { "epoch": 0.77, "learning_rate": 1.1450288603643813e-05, "loss": 0.9674, "step": 680000 }, { "epoch": 0.77, "learning_rate": 1.142198968081764e-05, "loss": 0.9608, "step": 680500 }, { "epoch": 0.77, "learning_rate": 1.139363404672328e-05, "loss": 0.9697, "step": 681000 }, { "epoch": 0.77, "learning_rate": 1.136527841262892e-05, "loss": 0.9684, "step": 681500 }, { "epoch": 0.77, "learning_rate": 1.1336922778534558e-05, "loss": 0.9669, "step": 682000 }, { "epoch": 0.77, "learning_rate": 1.1308567144440197e-05, "loss": 0.9762, "step": 682500 }, { "epoch": 0.77, "learning_rate": 1.1280211510345837e-05, "loss": 0.9691, "step": 683000 }, { "epoch": 0.78, "learning_rate": 1.1251855876251478e-05, "loss": 0.9578, "step": 683500 }, { "epoch": 0.78, "learning_rate": 1.1223500242157116e-05, "loss": 0.9582, "step": 684000 }, { "epoch": 0.78, "learning_rate": 1.1195144608062755e-05, "loss": 0.9628, "step": 684500 }, { "epoch": 0.78, "learning_rate": 1.1166788973968393e-05, "loss": 0.9667, "step": 685000 }, { "epoch": 0.78, "learning_rate": 1.1138490051142223e-05, "loss": 0.9689, "step": 685500 }, { "epoch": 0.78, "learning_rate": 1.1110134417047861e-05, "loss": 0.9671, "step": 686000 }, { "epoch": 0.78, "learning_rate": 1.108183549422169e-05, "loss": 0.9569, "step": 686500 }, { "epoch": 0.78, "learning_rate": 1.1053479860127329e-05, "loss": 0.9745, "step": 687000 }, { "epoch": 0.78, "learning_rate": 1.1025180937301156e-05, "loss": 0.9617, "step": 687500 }, { "epoch": 0.78, "learning_rate": 1.0996825303206795e-05, "loss": 0.963, "step": 688000 }, { "epoch": 0.78, "learning_rate": 1.0968469669112435e-05, "loss": 0.9718, "step": 688500 }, { "epoch": 0.78, "learning_rate": 1.0940114035018074e-05, "loss": 0.9576, "step": 689000 }, { "epoch": 0.78, "learning_rate": 1.0911758400923714e-05, "loss": 0.9648, "step": 689500 }, { "epoch": 0.78, "learning_rate": 1.0883402766829353e-05, "loss": 0.9619, "step": 690000 }, { "epoch": 0.78, "learning_rate": 1.0855047132734993e-05, "loss": 0.9674, "step": 690500 }, { "epoch": 0.78, "learning_rate": 1.0826691498640632e-05, "loss": 0.9683, "step": 691000 }, { "epoch": 0.78, "learning_rate": 1.079833586454627e-05, "loss": 0.9679, "step": 691500 }, { "epoch": 0.78, "learning_rate": 1.0769980230451909e-05, "loss": 0.9587, "step": 692000 }, { "epoch": 0.79, "learning_rate": 1.074162459635755e-05, "loss": 0.9625, "step": 692500 }, { "epoch": 0.79, "learning_rate": 1.0713325673531377e-05, "loss": 0.9681, "step": 693000 }, { "epoch": 0.79, "learning_rate": 1.0684970039437015e-05, "loss": 0.9708, "step": 693500 }, { "epoch": 0.79, "learning_rate": 1.0656614405342656e-05, "loss": 0.9635, "step": 694000 }, { "epoch": 0.79, "learning_rate": 1.0628315482516483e-05, "loss": 0.9583, "step": 694500 }, { "epoch": 0.79, "learning_rate": 1.0599959848422122e-05, "loss": 0.9659, "step": 695000 }, { "epoch": 0.79, "learning_rate": 1.0571604214327762e-05, "loss": 0.9611, "step": 695500 }, { "epoch": 0.79, "learning_rate": 1.0543248580233402e-05, "loss": 0.965, "step": 696000 }, { "epoch": 0.79, "learning_rate": 1.051489294613904e-05, "loss": 0.958, "step": 696500 }, { "epoch": 0.79, "learning_rate": 1.048653731204468e-05, "loss": 0.9603, "step": 697000 }, { "epoch": 0.79, "learning_rate": 1.045818167795032e-05, "loss": 0.9658, "step": 697500 }, { "epoch": 0.79, "learning_rate": 1.0429882755124147e-05, "loss": 0.9618, "step": 698000 }, { "epoch": 0.79, "learning_rate": 1.0401527121029786e-05, "loss": 0.9724, "step": 698500 }, { "epoch": 0.79, "learning_rate": 1.0373171486935426e-05, "loss": 0.959, "step": 699000 }, { "epoch": 0.79, "learning_rate": 1.0344872564109254e-05, "loss": 0.964, "step": 699500 }, { "epoch": 0.79, "learning_rate": 1.0316516930014892e-05, "loss": 0.9665, "step": 700000 }, { "epoch": 0.79, "learning_rate": 1.028816129592053e-05, "loss": 0.9659, "step": 700500 }, { "epoch": 0.8, "learning_rate": 1.0259805661826171e-05, "loss": 0.9496, "step": 701000 }, { "epoch": 0.8, "learning_rate": 1.0231450027731811e-05, "loss": 0.9658, "step": 701500 }, { "epoch": 0.8, "learning_rate": 1.020309439363745e-05, "loss": 0.9705, "step": 702000 }, { "epoch": 0.8, "learning_rate": 1.0174738759543089e-05, "loss": 0.9643, "step": 702500 }, { "epoch": 0.8, "learning_rate": 1.0146383125448729e-05, "loss": 0.9706, "step": 703000 }, { "epoch": 0.8, "learning_rate": 1.0118027491354367e-05, "loss": 0.9624, "step": 703500 }, { "epoch": 0.8, "learning_rate": 1.0089671857260006e-05, "loss": 0.9669, "step": 704000 }, { "epoch": 0.8, "learning_rate": 1.0061316223165645e-05, "loss": 0.968, "step": 704500 }, { "epoch": 0.8, "learning_rate": 1.0032960589071285e-05, "loss": 0.9671, "step": 705000 }, { "epoch": 0.8, "learning_rate": 1.0004604954976925e-05, "loss": 0.9484, "step": 705500 }, { "epoch": 0.8, "learning_rate": 9.976249320882564e-06, "loss": 0.9545, "step": 706000 }, { "epoch": 0.8, "learning_rate": 9.947893686788203e-06, "loss": 0.9583, "step": 706500 }, { "epoch": 0.8, "learning_rate": 9.919538052693843e-06, "loss": 0.9651, "step": 707000 }, { "epoch": 0.8, "learning_rate": 9.891182418599481e-06, "loss": 0.9668, "step": 707500 }, { "epoch": 0.8, "learning_rate": 9.86282678450512e-06, "loss": 0.9645, "step": 708000 }, { "epoch": 0.8, "learning_rate": 9.834471150410759e-06, "loss": 0.9703, "step": 708500 }, { "epoch": 0.8, "learning_rate": 9.806115516316399e-06, "loss": 0.9585, "step": 709000 }, { "epoch": 0.8, "learning_rate": 9.777873304758415e-06, "loss": 0.9683, "step": 709500 }, { "epoch": 0.81, "learning_rate": 9.749517670664056e-06, "loss": 0.9618, "step": 710000 }, { "epoch": 0.81, "learning_rate": 9.721162036569694e-06, "loss": 0.9621, "step": 710500 }, { "epoch": 0.81, "learning_rate": 9.692806402475334e-06, "loss": 0.9609, "step": 711000 }, { "epoch": 0.81, "learning_rate": 9.664450768380973e-06, "loss": 0.9654, "step": 711500 }, { "epoch": 0.81, "learning_rate": 9.636095134286613e-06, "loss": 0.9624, "step": 712000 }, { "epoch": 0.81, "learning_rate": 9.607739500192252e-06, "loss": 0.9577, "step": 712500 }, { "epoch": 0.81, "learning_rate": 9.57938386609789e-06, "loss": 0.9502, "step": 713000 }, { "epoch": 0.81, "learning_rate": 9.55102823200353e-06, "loss": 0.9596, "step": 713500 }, { "epoch": 0.81, "learning_rate": 9.52267259790917e-06, "loss": 0.9628, "step": 714000 }, { "epoch": 0.81, "learning_rate": 9.494316963814808e-06, "loss": 0.9621, "step": 714500 }, { "epoch": 0.81, "learning_rate": 9.465961329720448e-06, "loss": 0.9479, "step": 715000 }, { "epoch": 0.81, "learning_rate": 9.437605695626087e-06, "loss": 0.9521, "step": 715500 }, { "epoch": 0.81, "learning_rate": 9.409306772799916e-06, "loss": 0.9632, "step": 716000 }, { "epoch": 0.81, "learning_rate": 9.380951138705555e-06, "loss": 0.9517, "step": 716500 }, { "epoch": 0.81, "learning_rate": 9.352595504611193e-06, "loss": 0.9538, "step": 717000 }, { "epoch": 0.81, "learning_rate": 9.324239870516834e-06, "loss": 0.9554, "step": 717500 }, { "epoch": 0.81, "learning_rate": 9.295884236422472e-06, "loss": 0.9552, "step": 718000 }, { "epoch": 0.81, "learning_rate": 9.2675853135963e-06, "loss": 0.952, "step": 718500 }, { "epoch": 0.82, "learning_rate": 9.23922967950194e-06, "loss": 0.9689, "step": 719000 }, { "epoch": 0.82, "learning_rate": 9.210930756675767e-06, "loss": 0.9554, "step": 719500 }, { "epoch": 0.82, "learning_rate": 9.182575122581406e-06, "loss": 0.9591, "step": 720000 }, { "epoch": 0.82, "learning_rate": 9.154219488487045e-06, "loss": 0.9599, "step": 720500 }, { "epoch": 0.82, "learning_rate": 9.125863854392685e-06, "loss": 0.951, "step": 721000 }, { "epoch": 0.82, "learning_rate": 9.097508220298324e-06, "loss": 0.9536, "step": 721500 }, { "epoch": 0.82, "learning_rate": 9.069152586203964e-06, "loss": 0.951, "step": 722000 }, { "epoch": 0.82, "learning_rate": 9.040796952109603e-06, "loss": 0.9584, "step": 722500 }, { "epoch": 0.82, "learning_rate": 9.012498029283432e-06, "loss": 0.9532, "step": 723000 }, { "epoch": 0.82, "learning_rate": 8.98414239518907e-06, "loss": 0.966, "step": 723500 }, { "epoch": 0.82, "learning_rate": 8.955786761094709e-06, "loss": 0.9611, "step": 724000 }, { "epoch": 0.82, "learning_rate": 8.92743112700035e-06, "loss": 0.9633, "step": 724500 }, { "epoch": 0.82, "learning_rate": 8.899075492905988e-06, "loss": 0.9666, "step": 725000 }, { "epoch": 0.82, "learning_rate": 8.870776570079815e-06, "loss": 0.9713, "step": 725500 }, { "epoch": 0.82, "learning_rate": 8.842420935985456e-06, "loss": 0.9557, "step": 726000 }, { "epoch": 0.82, "learning_rate": 8.814065301891094e-06, "loss": 0.9483, "step": 726500 }, { "epoch": 0.82, "learning_rate": 8.785709667796733e-06, "loss": 0.9602, "step": 727000 }, { "epoch": 0.83, "learning_rate": 8.757354033702373e-06, "loss": 0.9436, "step": 727500 }, { "epoch": 0.83, "learning_rate": 8.7290551108762e-06, "loss": 0.9613, "step": 728000 }, { "epoch": 0.83, "learning_rate": 8.700756188050028e-06, "loss": 0.9605, "step": 728500 }, { "epoch": 0.83, "learning_rate": 8.672400553955667e-06, "loss": 0.964, "step": 729000 }, { "epoch": 0.83, "learning_rate": 8.644044919861307e-06, "loss": 0.9644, "step": 729500 }, { "epoch": 0.83, "learning_rate": 8.615689285766947e-06, "loss": 0.9516, "step": 730000 }, { "epoch": 0.83, "learning_rate": 8.587333651672586e-06, "loss": 0.9565, "step": 730500 }, { "epoch": 0.83, "learning_rate": 8.558978017578224e-06, "loss": 0.9563, "step": 731000 }, { "epoch": 0.83, "learning_rate": 8.530679094752054e-06, "loss": 0.958, "step": 731500 }, { "epoch": 0.83, "learning_rate": 8.502323460657692e-06, "loss": 0.9594, "step": 732000 }, { "epoch": 0.83, "learning_rate": 8.47396782656333e-06, "loss": 0.9577, "step": 732500 }, { "epoch": 0.83, "learning_rate": 8.445612192468971e-06, "loss": 0.9671, "step": 733000 }, { "epoch": 0.83, "learning_rate": 8.41725655837461e-06, "loss": 0.9539, "step": 733500 }, { "epoch": 0.83, "learning_rate": 8.388900924280248e-06, "loss": 0.9599, "step": 734000 }, { "epoch": 0.83, "learning_rate": 8.360602001454077e-06, "loss": 0.953, "step": 734500 }, { "epoch": 0.83, "learning_rate": 8.332246367359716e-06, "loss": 0.9513, "step": 735000 }, { "epoch": 0.83, "learning_rate": 8.303890733265356e-06, "loss": 0.9582, "step": 735500 }, { "epoch": 0.83, "learning_rate": 8.275535099170995e-06, "loss": 0.958, "step": 736000 }, { "epoch": 0.84, "learning_rate": 8.247179465076635e-06, "loss": 0.9549, "step": 736500 }, { "epoch": 0.84, "learning_rate": 8.218823830982274e-06, "loss": 0.9657, "step": 737000 }, { "epoch": 0.84, "learning_rate": 8.190468196887912e-06, "loss": 0.9493, "step": 737500 }, { "epoch": 0.84, "learning_rate": 8.162112562793551e-06, "loss": 0.9625, "step": 738000 }, { "epoch": 0.84, "learning_rate": 8.133756928699191e-06, "loss": 0.9549, "step": 738500 }, { "epoch": 0.84, "learning_rate": 8.10540129460483e-06, "loss": 0.9567, "step": 739000 }, { "epoch": 0.84, "learning_rate": 8.07704566051047e-06, "loss": 0.9513, "step": 739500 }, { "epoch": 0.84, "learning_rate": 8.048746737684298e-06, "loss": 0.9591, "step": 740000 }, { "epoch": 0.84, "learning_rate": 8.020447814858125e-06, "loss": 0.9548, "step": 740500 }, { "epoch": 0.84, "learning_rate": 7.992148892031953e-06, "loss": 0.9655, "step": 741000 }, { "epoch": 0.84, "learning_rate": 7.963793257937593e-06, "loss": 0.959, "step": 741500 }, { "epoch": 0.84, "learning_rate": 7.935437623843232e-06, "loss": 0.9559, "step": 742000 }, { "epoch": 0.84, "learning_rate": 7.907081989748872e-06, "loss": 0.9588, "step": 742500 }, { "epoch": 0.84, "learning_rate": 7.87872635565451e-06, "loss": 0.9559, "step": 743000 }, { "epoch": 0.84, "learning_rate": 7.85037072156015e-06, "loss": 0.9518, "step": 743500 }, { "epoch": 0.84, "learning_rate": 7.82201508746579e-06, "loss": 0.9653, "step": 744000 }, { "epoch": 0.84, "learning_rate": 7.793659453371428e-06, "loss": 0.9477, "step": 744500 }, { "epoch": 0.84, "learning_rate": 7.765303819277067e-06, "loss": 0.9602, "step": 745000 }, { "epoch": 0.85, "learning_rate": 7.736948185182707e-06, "loss": 0.959, "step": 745500 }, { "epoch": 0.85, "learning_rate": 7.708592551088347e-06, "loss": 0.9573, "step": 746000 }, { "epoch": 0.85, "learning_rate": 7.680236916993986e-06, "loss": 0.9506, "step": 746500 }, { "epoch": 0.85, "learning_rate": 7.651881282899624e-06, "loss": 0.96, "step": 747000 }, { "epoch": 0.85, "learning_rate": 7.623525648805265e-06, "loss": 0.9595, "step": 747500 }, { "epoch": 0.85, "learning_rate": 7.595170014710903e-06, "loss": 0.9584, "step": 748000 }, { "epoch": 0.85, "learning_rate": 7.566814380616542e-06, "loss": 0.9563, "step": 748500 }, { "epoch": 0.85, "learning_rate": 7.538458746522181e-06, "loss": 0.9485, "step": 749000 }, { "epoch": 0.85, "learning_rate": 7.51015982369601e-06, "loss": 0.9565, "step": 749500 }, { "epoch": 0.85, "learning_rate": 7.481804189601649e-06, "loss": 0.9652, "step": 750000 }, { "epoch": 0.85, "learning_rate": 7.453448555507288e-06, "loss": 0.9545, "step": 750500 }, { "epoch": 0.85, "learning_rate": 7.425092921412928e-06, "loss": 0.9546, "step": 751000 }, { "epoch": 0.85, "learning_rate": 7.396737287318567e-06, "loss": 0.9476, "step": 751500 }, { "epoch": 0.85, "learning_rate": 7.368438364492394e-06, "loss": 0.9592, "step": 752000 }, { "epoch": 0.85, "learning_rate": 7.340139441666223e-06, "loss": 0.9634, "step": 752500 }, { "epoch": 0.85, "learning_rate": 7.311783807571862e-06, "loss": 0.9472, "step": 753000 }, { "epoch": 0.85, "learning_rate": 7.283428173477501e-06, "loss": 0.9532, "step": 753500 }, { "epoch": 0.86, "learning_rate": 7.255072539383142e-06, "loss": 0.9553, "step": 754000 }, { "epoch": 0.86, "learning_rate": 7.22671690528878e-06, "loss": 0.949, "step": 754500 }, { "epoch": 0.86, "learning_rate": 7.198417982462608e-06, "loss": 0.9444, "step": 755000 }, { "epoch": 0.86, "learning_rate": 7.170062348368246e-06, "loss": 0.9637, "step": 755500 }, { "epoch": 0.86, "learning_rate": 7.141706714273887e-06, "loss": 0.9631, "step": 756000 }, { "epoch": 0.86, "learning_rate": 7.113351080179525e-06, "loss": 0.9647, "step": 756500 }, { "epoch": 0.86, "learning_rate": 7.084995446085165e-06, "loss": 0.9642, "step": 757000 }, { "epoch": 0.86, "learning_rate": 7.056639811990803e-06, "loss": 0.9535, "step": 757500 }, { "epoch": 0.86, "learning_rate": 7.0282841778964436e-06, "loss": 0.9574, "step": 758000 }, { "epoch": 0.86, "learning_rate": 6.999928543802082e-06, "loss": 0.9631, "step": 758500 }, { "epoch": 0.86, "learning_rate": 6.97162962097591e-06, "loss": 0.9613, "step": 759000 }, { "epoch": 0.86, "learning_rate": 6.94327398688155e-06, "loss": 0.9502, "step": 759500 }, { "epoch": 0.86, "learning_rate": 6.914918352787189e-06, "loss": 0.9564, "step": 760000 }, { "epoch": 0.86, "learning_rate": 6.886562718692828e-06, "loss": 0.9522, "step": 760500 }, { "epoch": 0.86, "learning_rate": 6.858263795866657e-06, "loss": 0.9613, "step": 761000 }, { "epoch": 0.86, "learning_rate": 6.829908161772296e-06, "loss": 0.9506, "step": 761500 }, { "epoch": 0.86, "learning_rate": 6.801609238946123e-06, "loss": 0.9601, "step": 762000 }, { "epoch": 0.86, "learning_rate": 6.7732536048517635e-06, "loss": 0.9619, "step": 762500 }, { "epoch": 0.87, "learning_rate": 6.744897970757402e-06, "loss": 0.951, "step": 763000 }, { "epoch": 0.87, "learning_rate": 6.7165423366630415e-06, "loss": 0.954, "step": 763500 }, { "epoch": 0.87, "learning_rate": 6.68818670256868e-06, "loss": 0.9555, "step": 764000 }, { "epoch": 0.87, "learning_rate": 6.6598877797425084e-06, "loss": 0.9579, "step": 764500 }, { "epoch": 0.87, "learning_rate": 6.631532145648148e-06, "loss": 0.9552, "step": 765000 }, { "epoch": 0.87, "learning_rate": 6.6031765115537865e-06, "loss": 0.9435, "step": 765500 }, { "epoch": 0.87, "learning_rate": 6.574820877459427e-06, "loss": 0.9568, "step": 766000 }, { "epoch": 0.87, "learning_rate": 6.546465243365065e-06, "loss": 0.9482, "step": 766500 }, { "epoch": 0.87, "learning_rate": 6.518109609270705e-06, "loss": 0.9496, "step": 767000 }, { "epoch": 0.87, "learning_rate": 6.4897539751763435e-06, "loss": 0.9513, "step": 767500 }, { "epoch": 0.87, "learning_rate": 6.461398341081984e-06, "loss": 0.9501, "step": 768000 }, { "epoch": 0.87, "learning_rate": 6.433042706987623e-06, "loss": 0.9417, "step": 768500 }, { "epoch": 0.87, "learning_rate": 6.404687072893262e-06, "loss": 0.9488, "step": 769000 }, { "epoch": 0.87, "learning_rate": 6.3763314387989005e-06, "loss": 0.9518, "step": 769500 }, { "epoch": 0.87, "learning_rate": 6.34803251597273e-06, "loss": 0.9483, "step": 770000 }, { "epoch": 0.87, "learning_rate": 6.319676881878368e-06, "loss": 0.9482, "step": 770500 }, { "epoch": 0.87, "learning_rate": 6.291321247784007e-06, "loss": 0.9463, "step": 771000 }, { "epoch": 0.88, "learning_rate": 6.262965613689646e-06, "loss": 0.9576, "step": 771500 }, { "epoch": 0.88, "learning_rate": 6.234609979595286e-06, "loss": 0.9539, "step": 772000 }, { "epoch": 0.88, "learning_rate": 6.206311056769114e-06, "loss": 0.9542, "step": 772500 }, { "epoch": 0.88, "learning_rate": 6.1779554226747535e-06, "loss": 0.9523, "step": 773000 }, { "epoch": 0.88, "learning_rate": 6.149599788580392e-06, "loss": 0.9535, "step": 773500 }, { "epoch": 0.88, "learning_rate": 6.1212441544860315e-06, "loss": 0.9559, "step": 774000 }, { "epoch": 0.88, "learning_rate": 6.092888520391671e-06, "loss": 0.9533, "step": 774500 }, { "epoch": 0.88, "learning_rate": 6.0645328862973105e-06, "loss": 0.9501, "step": 775000 }, { "epoch": 0.88, "learning_rate": 6.036177252202949e-06, "loss": 0.9479, "step": 775500 }, { "epoch": 0.88, "learning_rate": 6.0078216181085885e-06, "loss": 0.9554, "step": 776000 }, { "epoch": 0.88, "learning_rate": 5.979522695282417e-06, "loss": 0.9515, "step": 776500 }, { "epoch": 0.88, "learning_rate": 5.951223772456245e-06, "loss": 0.9556, "step": 777000 }, { "epoch": 0.88, "learning_rate": 5.922868138361884e-06, "loss": 0.9558, "step": 777500 }, { "epoch": 0.88, "learning_rate": 5.894512504267523e-06, "loss": 0.943, "step": 778000 }, { "epoch": 0.88, "learning_rate": 5.866156870173163e-06, "loss": 0.9576, "step": 778500 }, { "epoch": 0.88, "learning_rate": 5.837801236078802e-06, "loss": 0.9565, "step": 779000 }, { "epoch": 0.88, "learning_rate": 5.8095023132526295e-06, "loss": 0.953, "step": 779500 }, { "epoch": 0.88, "learning_rate": 5.781146679158269e-06, "loss": 0.9467, "step": 780000 }, { "epoch": 0.89, "learning_rate": 5.752791045063908e-06, "loss": 0.9592, "step": 780500 }, { "epoch": 0.89, "learning_rate": 5.724492122237736e-06, "loss": 0.9514, "step": 781000 }, { "epoch": 0.89, "learning_rate": 5.696136488143375e-06, "loss": 0.943, "step": 781500 }, { "epoch": 0.89, "learning_rate": 5.667780854049015e-06, "loss": 0.9479, "step": 782000 }, { "epoch": 0.89, "learning_rate": 5.639425219954654e-06, "loss": 0.9525, "step": 782500 }, { "epoch": 0.89, "learning_rate": 5.611069585860293e-06, "loss": 0.9518, "step": 783000 }, { "epoch": 0.89, "learning_rate": 5.582713951765932e-06, "loss": 0.949, "step": 783500 }, { "epoch": 0.89, "learning_rate": 5.554358317671572e-06, "loss": 0.9504, "step": 784000 }, { "epoch": 0.89, "learning_rate": 5.526002683577211e-06, "loss": 0.9545, "step": 784500 }, { "epoch": 0.89, "learning_rate": 5.4977037607510395e-06, "loss": 0.9445, "step": 785000 }, { "epoch": 0.89, "learning_rate": 5.469348126656678e-06, "loss": 0.9439, "step": 785500 }, { "epoch": 0.89, "learning_rate": 5.440992492562318e-06, "loss": 0.9426, "step": 786000 }, { "epoch": 0.89, "learning_rate": 5.412636858467956e-06, "loss": 0.9525, "step": 786500 }, { "epoch": 0.89, "learning_rate": 5.3842812243735965e-06, "loss": 0.9472, "step": 787000 }, { "epoch": 0.89, "learning_rate": 5.355925590279235e-06, "loss": 0.954, "step": 787500 }, { "epoch": 0.89, "learning_rate": 5.3275699561848746e-06, "loss": 0.9461, "step": 788000 }, { "epoch": 0.89, "learning_rate": 5.299214322090513e-06, "loss": 0.9437, "step": 788500 }, { "epoch": 0.89, "learning_rate": 5.2709153992643415e-06, "loss": 0.9481, "step": 789000 }, { "epoch": 0.9, "learning_rate": 5.242559765169981e-06, "loss": 0.9347, "step": 789500 }, { "epoch": 0.9, "learning_rate": 5.21420413107562e-06, "loss": 0.9457, "step": 790000 }, { "epoch": 0.9, "learning_rate": 5.18584849698126e-06, "loss": 0.9579, "step": 790500 }, { "epoch": 0.9, "learning_rate": 5.157549574155087e-06, "loss": 0.9443, "step": 791000 }, { "epoch": 0.9, "learning_rate": 5.129193940060727e-06, "loss": 0.9477, "step": 791500 }, { "epoch": 0.9, "learning_rate": 5.100838305966365e-06, "loss": 0.9481, "step": 792000 }, { "epoch": 0.9, "learning_rate": 5.072539383140194e-06, "loss": 0.9479, "step": 792500 }, { "epoch": 0.9, "learning_rate": 5.044183749045833e-06, "loss": 0.9608, "step": 793000 }, { "epoch": 0.9, "learning_rate": 5.015884826219661e-06, "loss": 0.9541, "step": 793500 }, { "epoch": 0.9, "learning_rate": 4.9875291921253e-06, "loss": 0.9438, "step": 794000 }, { "epoch": 0.9, "learning_rate": 4.9591735580309395e-06, "loss": 0.9448, "step": 794500 }, { "epoch": 0.9, "learning_rate": 4.930817923936579e-06, "loss": 0.9434, "step": 795000 }, { "epoch": 0.9, "learning_rate": 4.902462289842218e-06, "loss": 0.9566, "step": 795500 }, { "epoch": 0.9, "learning_rate": 4.874163367016047e-06, "loss": 0.9526, "step": 796000 }, { "epoch": 0.9, "learning_rate": 4.845807732921685e-06, "loss": 0.9459, "step": 796500 }, { "epoch": 0.9, "learning_rate": 4.817452098827325e-06, "loss": 0.947, "step": 797000 }, { "epoch": 0.9, "learning_rate": 4.789096464732964e-06, "loss": 0.9571, "step": 797500 }, { "epoch": 0.91, "learning_rate": 4.760740830638604e-06, "loss": 0.9537, "step": 798000 }, { "epoch": 0.91, "learning_rate": 4.732385196544242e-06, "loss": 0.9508, "step": 798500 }, { "epoch": 0.91, "learning_rate": 4.704029562449882e-06, "loss": 0.9405, "step": 799000 }, { "epoch": 0.91, "learning_rate": 4.675673928355521e-06, "loss": 0.9498, "step": 799500 }, { "epoch": 0.91, "learning_rate": 4.647318294261161e-06, "loss": 0.9484, "step": 800000 }, { "epoch": 0.91, "learning_rate": 4.618962660166799e-06, "loss": 0.9463, "step": 800500 }, { "epoch": 0.91, "learning_rate": 4.5906637373406275e-06, "loss": 0.9462, "step": 801000 }, { "epoch": 0.91, "learning_rate": 4.562308103246267e-06, "loss": 0.9494, "step": 801500 }, { "epoch": 0.91, "learning_rate": 4.533952469151906e-06, "loss": 0.9441, "step": 802000 }, { "epoch": 0.91, "learning_rate": 4.505596835057545e-06, "loss": 0.9441, "step": 802500 }, { "epoch": 0.91, "learning_rate": 4.4772412009631845e-06, "loss": 0.9421, "step": 803000 }, { "epoch": 0.91, "learning_rate": 4.448885566868824e-06, "loss": 0.9421, "step": 803500 }, { "epoch": 0.91, "learning_rate": 4.420586644042651e-06, "loss": 0.9506, "step": 804000 }, { "epoch": 0.91, "learning_rate": 4.392231009948291e-06, "loss": 0.9457, "step": 804500 }, { "epoch": 0.91, "learning_rate": 4.363932087122119e-06, "loss": 0.9373, "step": 805000 }, { "epoch": 0.91, "learning_rate": 4.335576453027758e-06, "loss": 0.955, "step": 805500 }, { "epoch": 0.91, "learning_rate": 4.307220818933397e-06, "loss": 0.9482, "step": 806000 }, { "epoch": 0.91, "learning_rate": 4.278865184839037e-06, "loss": 0.943, "step": 806500 }, { "epoch": 0.92, "learning_rate": 4.250509550744676e-06, "loss": 0.9444, "step": 807000 }, { "epoch": 0.92, "learning_rate": 4.222153916650315e-06, "loss": 0.9517, "step": 807500 }, { "epoch": 0.92, "learning_rate": 4.193798282555954e-06, "loss": 0.9513, "step": 808000 }, { "epoch": 0.92, "learning_rate": 4.165442648461594e-06, "loss": 0.9419, "step": 808500 }, { "epoch": 0.92, "learning_rate": 4.137087014367233e-06, "loss": 0.9427, "step": 809000 }, { "epoch": 0.92, "learning_rate": 4.108731380272872e-06, "loss": 0.9536, "step": 809500 }, { "epoch": 0.92, "learning_rate": 4.080375746178511e-06, "loss": 0.9402, "step": 810000 }, { "epoch": 0.92, "learning_rate": 4.0520768233523395e-06, "loss": 0.9479, "step": 810500 }, { "epoch": 0.92, "learning_rate": 4.023721189257978e-06, "loss": 0.9383, "step": 811000 }, { "epoch": 0.92, "learning_rate": 3.995365555163618e-06, "loss": 0.9398, "step": 811500 }, { "epoch": 0.92, "learning_rate": 3.967009921069257e-06, "loss": 0.9452, "step": 812000 }, { "epoch": 0.92, "learning_rate": 3.9386542869748964e-06, "loss": 0.946, "step": 812500 }, { "epoch": 0.92, "learning_rate": 3.910298652880536e-06, "loss": 0.9398, "step": 813000 }, { "epoch": 0.92, "learning_rate": 3.881999730054363e-06, "loss": 0.9459, "step": 813500 }, { "epoch": 0.92, "learning_rate": 3.853644095960003e-06, "loss": 0.9498, "step": 814000 }, { "epoch": 0.92, "learning_rate": 3.825288461865642e-06, "loss": 0.9454, "step": 814500 }, { "epoch": 0.92, "learning_rate": 3.7969328277712817e-06, "loss": 0.9592, "step": 815000 }, { "epoch": 0.92, "learning_rate": 3.7685771936769207e-06, "loss": 0.9392, "step": 815500 }, { "epoch": 0.93, "learning_rate": 3.74022155958256e-06, "loss": 0.942, "step": 816000 }, { "epoch": 0.93, "learning_rate": 3.7118659254881992e-06, "loss": 0.9476, "step": 816500 }, { "epoch": 0.93, "learning_rate": 3.6835102913938387e-06, "loss": 0.9465, "step": 817000 }, { "epoch": 0.93, "learning_rate": 3.6551546572994777e-06, "loss": 0.9465, "step": 817500 }, { "epoch": 0.93, "learning_rate": 3.626799023205117e-06, "loss": 0.952, "step": 818000 }, { "epoch": 0.93, "learning_rate": 3.5984433891107562e-06, "loss": 0.9371, "step": 818500 }, { "epoch": 0.93, "learning_rate": 3.570144466284584e-06, "loss": 0.9422, "step": 819000 }, { "epoch": 0.93, "learning_rate": 3.541788832190223e-06, "loss": 0.9438, "step": 819500 }, { "epoch": 0.93, "learning_rate": 3.5134331980958626e-06, "loss": 0.937, "step": 820000 }, { "epoch": 0.93, "learning_rate": 3.4850775640015016e-06, "loss": 0.9507, "step": 820500 }, { "epoch": 0.93, "learning_rate": 3.4567786411753295e-06, "loss": 0.9434, "step": 821000 }, { "epoch": 0.93, "learning_rate": 3.4284230070809694e-06, "loss": 0.9368, "step": 821500 }, { "epoch": 0.93, "learning_rate": 3.400067372986608e-06, "loss": 0.9519, "step": 822000 }, { "epoch": 0.93, "learning_rate": 3.371711738892248e-06, "loss": 0.9402, "step": 822500 }, { "epoch": 0.93, "learning_rate": 3.3433561047978865e-06, "loss": 0.9381, "step": 823000 }, { "epoch": 0.93, "learning_rate": 3.3150571819717147e-06, "loss": 0.9404, "step": 823500 }, { "epoch": 0.93, "learning_rate": 3.2867582591455426e-06, "loss": 0.9551, "step": 824000 }, { "epoch": 0.94, "learning_rate": 3.2584026250511825e-06, "loss": 0.9476, "step": 824500 }, { "epoch": 0.94, "learning_rate": 3.230046990956821e-06, "loss": 0.941, "step": 825000 }, { "epoch": 0.94, "learning_rate": 3.201691356862461e-06, "loss": 0.9441, "step": 825500 }, { "epoch": 0.94, "learning_rate": 3.1733357227680996e-06, "loss": 0.9496, "step": 826000 }, { "epoch": 0.94, "learning_rate": 3.1449800886737395e-06, "loss": 0.9427, "step": 826500 }, { "epoch": 0.94, "learning_rate": 3.116624454579378e-06, "loss": 0.9489, "step": 827000 }, { "epoch": 0.94, "learning_rate": 3.0882688204850175e-06, "loss": 0.9433, "step": 827500 }, { "epoch": 0.94, "learning_rate": 3.0599698976588454e-06, "loss": 0.9487, "step": 828000 }, { "epoch": 0.94, "learning_rate": 3.031614263564485e-06, "loss": 0.9404, "step": 828500 }, { "epoch": 0.94, "learning_rate": 3.003258629470124e-06, "loss": 0.9361, "step": 829000 }, { "epoch": 0.94, "learning_rate": 2.975016417912141e-06, "loss": 0.9489, "step": 829500 }, { "epoch": 0.94, "learning_rate": 2.94666078381778e-06, "loss": 0.9455, "step": 830000 }, { "epoch": 0.94, "learning_rate": 2.9183051497234195e-06, "loss": 0.9409, "step": 830500 }, { "epoch": 0.94, "learning_rate": 2.8899495156290585e-06, "loss": 0.9396, "step": 831000 }, { "epoch": 0.94, "learning_rate": 2.861593881534698e-06, "loss": 0.9349, "step": 831500 }, { "epoch": 0.94, "learning_rate": 2.833238247440337e-06, "loss": 0.9412, "step": 832000 }, { "epoch": 0.94, "learning_rate": 2.804939324614165e-06, "loss": 0.9498, "step": 832500 }, { "epoch": 0.94, "learning_rate": 2.776583690519804e-06, "loss": 0.94, "step": 833000 }, { "epoch": 0.95, "learning_rate": 2.7482280564254434e-06, "loss": 0.9424, "step": 833500 }, { "epoch": 0.95, "learning_rate": 2.719872422331083e-06, "loss": 0.9448, "step": 834000 }, { "epoch": 0.95, "learning_rate": 2.691516788236722e-06, "loss": 0.9464, "step": 834500 }, { "epoch": 0.95, "learning_rate": 2.6631611541423613e-06, "loss": 0.9364, "step": 835000 }, { "epoch": 0.95, "learning_rate": 2.6348055200480004e-06, "loss": 0.942, "step": 835500 }, { "epoch": 0.95, "learning_rate": 2.60644988595364e-06, "loss": 0.9414, "step": 836000 }, { "epoch": 0.95, "learning_rate": 2.578094251859279e-06, "loss": 0.9394, "step": 836500 }, { "epoch": 0.95, "learning_rate": 2.5497386177649183e-06, "loss": 0.9384, "step": 837000 }, { "epoch": 0.95, "learning_rate": 2.5213829836705573e-06, "loss": 0.9438, "step": 837500 }, { "epoch": 0.95, "learning_rate": 2.493027349576197e-06, "loss": 0.9328, "step": 838000 }, { "epoch": 0.95, "learning_rate": 2.464671715481836e-06, "loss": 0.9497, "step": 838500 }, { "epoch": 0.95, "learning_rate": 2.436372792655664e-06, "loss": 0.9486, "step": 839000 }, { "epoch": 0.95, "learning_rate": 2.408017158561303e-06, "loss": 0.9407, "step": 839500 }, { "epoch": 0.95, "learning_rate": 2.3796615244669426e-06, "loss": 0.9438, "step": 840000 }, { "epoch": 0.95, "learning_rate": 2.3513058903725817e-06, "loss": 0.9432, "step": 840500 }, { "epoch": 0.95, "learning_rate": 2.322950256278221e-06, "loss": 0.9379, "step": 841000 }, { "epoch": 0.95, "learning_rate": 2.29459462218386e-06, "loss": 0.9375, "step": 841500 }, { "epoch": 0.96, "learning_rate": 2.2662389880894996e-06, "loss": 0.9429, "step": 842000 }, { "epoch": 0.96, "learning_rate": 2.2378833539951386e-06, "loss": 0.9416, "step": 842500 }, { "epoch": 0.96, "learning_rate": 2.209527719900778e-06, "loss": 0.9437, "step": 843000 }, { "epoch": 0.96, "learning_rate": 2.181228797074606e-06, "loss": 0.9402, "step": 843500 }, { "epoch": 0.96, "learning_rate": 2.1528731629802454e-06, "loss": 0.9447, "step": 844000 }, { "epoch": 0.96, "learning_rate": 2.1245175288858844e-06, "loss": 0.9389, "step": 844500 }, { "epoch": 0.96, "learning_rate": 2.0962186060597127e-06, "loss": 0.9361, "step": 845000 }, { "epoch": 0.96, "learning_rate": 2.0678629719653518e-06, "loss": 0.9518, "step": 845500 }, { "epoch": 0.96, "learning_rate": 2.0395073378709912e-06, "loss": 0.9421, "step": 846000 }, { "epoch": 0.96, "learning_rate": 2.0111517037766303e-06, "loss": 0.943, "step": 846500 }, { "epoch": 0.96, "learning_rate": 1.9827960696822697e-06, "loss": 0.9367, "step": 847000 }, { "epoch": 0.96, "learning_rate": 1.9544404355879087e-06, "loss": 0.9387, "step": 847500 }, { "epoch": 0.96, "learning_rate": 1.926084801493548e-06, "loss": 0.941, "step": 848000 }, { "epoch": 0.96, "learning_rate": 1.8977291673991874e-06, "loss": 0.9456, "step": 848500 }, { "epoch": 0.96, "learning_rate": 1.869486955841204e-06, "loss": 0.951, "step": 849000 }, { "epoch": 0.96, "learning_rate": 1.8411313217468432e-06, "loss": 0.9447, "step": 849500 }, { "epoch": 0.96, "learning_rate": 1.8127756876524824e-06, "loss": 0.9369, "step": 850000 }, { "epoch": 0.96, "learning_rate": 1.7844200535581217e-06, "loss": 0.9509, "step": 850500 }, { "epoch": 0.97, "learning_rate": 1.756064419463761e-06, "loss": 0.9332, "step": 851000 }, { "epoch": 0.97, "learning_rate": 1.7277087853694002e-06, "loss": 0.9406, "step": 851500 }, { "epoch": 0.97, "learning_rate": 1.6993531512750394e-06, "loss": 0.9376, "step": 852000 }, { "epoch": 0.97, "learning_rate": 1.6710542284488675e-06, "loss": 0.9314, "step": 852500 }, { "epoch": 0.97, "learning_rate": 1.6426985943545067e-06, "loss": 0.9424, "step": 853000 }, { "epoch": 0.97, "learning_rate": 1.614342960260146e-06, "loss": 0.9371, "step": 853500 }, { "epoch": 0.97, "learning_rate": 1.5859873261657852e-06, "loss": 0.9481, "step": 854000 }, { "epoch": 0.97, "learning_rate": 1.5576316920714245e-06, "loss": 0.9351, "step": 854500 }, { "epoch": 0.97, "learning_rate": 1.5292760579770637e-06, "loss": 0.9399, "step": 855000 }, { "epoch": 0.97, "learning_rate": 1.500920423882703e-06, "loss": 0.9474, "step": 855500 }, { "epoch": 0.97, "learning_rate": 1.472621501056531e-06, "loss": 0.9376, "step": 856000 }, { "epoch": 0.97, "learning_rate": 1.4442658669621703e-06, "loss": 0.9332, "step": 856500 }, { "epoch": 0.97, "learning_rate": 1.4159102328678095e-06, "loss": 0.9468, "step": 857000 }, { "epoch": 0.97, "learning_rate": 1.3875545987734488e-06, "loss": 0.9452, "step": 857500 }, { "epoch": 0.97, "learning_rate": 1.3592556759472766e-06, "loss": 0.9416, "step": 858000 }, { "epoch": 0.97, "learning_rate": 1.3309000418529159e-06, "loss": 0.9406, "step": 858500 }, { "epoch": 0.97, "learning_rate": 1.3025444077585551e-06, "loss": 0.9367, "step": 859000 }, { "epoch": 0.97, "learning_rate": 1.2741887736641944e-06, "loss": 0.9474, "step": 859500 }, { "epoch": 0.98, "learning_rate": 1.2458331395698336e-06, "loss": 0.9392, "step": 860000 }, { "epoch": 0.98, "learning_rate": 1.2174775054754729e-06, "loss": 0.9337, "step": 860500 }, { "epoch": 0.98, "learning_rate": 1.1891218713811123e-06, "loss": 0.9317, "step": 861000 }, { "epoch": 0.98, "learning_rate": 1.1608229485549402e-06, "loss": 0.9367, "step": 861500 }, { "epoch": 0.98, "learning_rate": 1.1324673144605794e-06, "loss": 0.9523, "step": 862000 }, { "epoch": 0.98, "learning_rate": 1.1041116803662187e-06, "loss": 0.9487, "step": 862500 }, { "epoch": 0.98, "learning_rate": 1.0757560462718581e-06, "loss": 0.942, "step": 863000 }, { "epoch": 0.98, "learning_rate": 1.0474004121774974e-06, "loss": 0.9439, "step": 863500 }, { "epoch": 0.98, "learning_rate": 1.0190447780831366e-06, "loss": 0.9339, "step": 864000 }, { "epoch": 0.98, "learning_rate": 9.907458552569645e-07, "loss": 0.9431, "step": 864500 }, { "epoch": 0.98, "learning_rate": 9.623902211626037e-07, "loss": 0.9384, "step": 865000 }, { "epoch": 0.98, "learning_rate": 9.34034587068243e-07, "loss": 0.9471, "step": 865500 }, { "epoch": 0.98, "learning_rate": 9.056789529738822e-07, "loss": 0.9422, "step": 866000 }, { "epoch": 0.98, "learning_rate": 8.773233188795215e-07, "loss": 0.9384, "step": 866500 }, { "epoch": 0.98, "learning_rate": 8.489676847851607e-07, "loss": 0.9454, "step": 867000 }, { "epoch": 0.98, "learning_rate": 8.206120506908e-07, "loss": 0.9442, "step": 867500 }, { "epoch": 0.98, "learning_rate": 7.922564165964392e-07, "loss": 0.9336, "step": 868000 }, { "epoch": 0.99, "learning_rate": 7.639007825020786e-07, "loss": 0.9368, "step": 868500 }, { "epoch": 0.99, "learning_rate": 7.356018596759065e-07, "loss": 0.9461, "step": 869000 }, { "epoch": 0.99, "learning_rate": 7.072462255815458e-07, "loss": 0.9402, "step": 869500 }, { "epoch": 0.99, "learning_rate": 6.78890591487185e-07, "loss": 0.9414, "step": 870000 }, { "epoch": 0.99, "learning_rate": 6.505349573928243e-07, "loss": 0.9404, "step": 870500 }, { "epoch": 0.99, "learning_rate": 6.221793232984635e-07, "loss": 0.9533, "step": 871000 }, { "epoch": 0.99, "learning_rate": 5.938236892041027e-07, "loss": 0.9579, "step": 871500 }, { "epoch": 0.99, "learning_rate": 5.655247663779307e-07, "loss": 0.948, "step": 872000 }, { "epoch": 0.99, "learning_rate": 5.3716913228357e-07, "loss": 0.9422, "step": 872500 }, { "epoch": 0.99, "learning_rate": 5.088134981892092e-07, "loss": 0.9362, "step": 873000 }, { "epoch": 0.99, "learning_rate": 4.804578640948485e-07, "loss": 0.9432, "step": 873500 }, { "epoch": 0.99, "learning_rate": 4.5210223000048775e-07, "loss": 0.9325, "step": 874000 }, { "epoch": 0.99, "learning_rate": 4.23746595906127e-07, "loss": 0.9241, "step": 874500 }, { "epoch": 0.99, "learning_rate": 3.9539096181176624e-07, "loss": 0.9395, "step": 875000 }, { "epoch": 0.99, "learning_rate": 3.670353277174055e-07, "loss": 0.9564, "step": 875500 }, { "epoch": 0.99, "learning_rate": 3.386796936230448e-07, "loss": 0.9423, "step": 876000 }, { "epoch": 0.99, "learning_rate": 3.103807707968727e-07, "loss": 0.9459, "step": 876500 }, { "epoch": 0.99, "learning_rate": 2.82025136702512e-07, "loss": 0.9397, "step": 877000 }, { "epoch": 1.0, "learning_rate": 2.5366950260815125e-07, "loss": 0.9326, "step": 877500 }, { "epoch": 1.0, "learning_rate": 2.253138685137905e-07, "loss": 0.951, "step": 878000 }, { "epoch": 1.0, "learning_rate": 1.9695823441942974e-07, "loss": 0.9426, "step": 878500 }, { "epoch": 1.0, "learning_rate": 1.686593115932577e-07, "loss": 0.9356, "step": 879000 }, { "epoch": 1.0, "learning_rate": 1.4030367749889696e-07, "loss": 0.935, "step": 879500 }, { "epoch": 1.0, "learning_rate": 1.1194804340453621e-07, "loss": 0.9338, "step": 880000 }, { "epoch": 1.0, "learning_rate": 8.36491205783642e-08, "loss": 0.9346, "step": 880500 }, { "epoch": 1.0, "learning_rate": 5.5293486484003454e-08, "loss": 0.9402, "step": 881000 }, { "epoch": 1.0, "learning_rate": 2.6937852389642708e-08, "loss": 0.937, "step": 881500 } ], "max_steps": 881659, "num_train_epochs": 1, "total_flos": 3.713762155948923e+18, "trial_name": null, "trial_params": null }