gokuls's picture
End of training
41dded3
raw
history blame contribute delete
No virus
112 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.379411343014564,
"eval_steps": 1000000,
"global_step": 457931,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 5.000000000000001e-07,
"loss": 3.2841,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.2801,
"step": 1000
},
{
"epoch": 0.03,
"learning_rate": 1.5e-06,
"loss": 3.2782,
"step": 1500
},
{
"epoch": 0.04,
"learning_rate": 2.0000000000000003e-06,
"loss": 3.2833,
"step": 2000
},
{
"epoch": 0.05,
"learning_rate": 2.5e-06,
"loss": 3.2791,
"step": 2500
},
{
"epoch": 0.06,
"learning_rate": 3e-06,
"loss": 3.2766,
"step": 3000
},
{
"epoch": 0.07,
"learning_rate": 3.5e-06,
"loss": 3.2768,
"step": 3500
},
{
"epoch": 0.08,
"learning_rate": 4.000000000000001e-06,
"loss": 3.2692,
"step": 4000
},
{
"epoch": 0.09,
"learning_rate": 4.5e-06,
"loss": 3.2767,
"step": 4500
},
{
"epoch": 0.1,
"learning_rate": 5e-06,
"loss": 3.2702,
"step": 5000
},
{
"epoch": 0.11,
"learning_rate": 5.500000000000001e-06,
"loss": 3.2669,
"step": 5500
},
{
"epoch": 0.12,
"learning_rate": 6e-06,
"loss": 3.2657,
"step": 6000
},
{
"epoch": 0.13,
"learning_rate": 6.5000000000000004e-06,
"loss": 3.273,
"step": 6500
},
{
"epoch": 0.14,
"learning_rate": 7e-06,
"loss": 3.2647,
"step": 7000
},
{
"epoch": 0.15,
"learning_rate": 7.500000000000001e-06,
"loss": 3.2674,
"step": 7500
},
{
"epoch": 0.16,
"learning_rate": 8.000000000000001e-06,
"loss": 3.2639,
"step": 8000
},
{
"epoch": 0.17,
"learning_rate": 8.5e-06,
"loss": 3.2601,
"step": 8500
},
{
"epoch": 0.18,
"learning_rate": 9e-06,
"loss": 3.2567,
"step": 9000
},
{
"epoch": 0.19,
"learning_rate": 9.5e-06,
"loss": 3.2571,
"step": 9500
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 3.2509,
"step": 10000
},
{
"epoch": 0.22,
"learning_rate": 9.998973790612238e-06,
"loss": 3.2506,
"step": 10500
},
{
"epoch": 0.23,
"learning_rate": 9.997947581224474e-06,
"loss": 3.2509,
"step": 11000
},
{
"epoch": 0.24,
"learning_rate": 9.996921371836712e-06,
"loss": 3.2403,
"step": 11500
},
{
"epoch": 0.25,
"learning_rate": 9.995895162448946e-06,
"loss": 3.2432,
"step": 12000
},
{
"epoch": 0.26,
"learning_rate": 9.994868953061183e-06,
"loss": 3.2417,
"step": 12500
},
{
"epoch": 0.27,
"learning_rate": 9.99384274367342e-06,
"loss": 3.2408,
"step": 13000
},
{
"epoch": 0.28,
"learning_rate": 9.992816534285656e-06,
"loss": 3.2267,
"step": 13500
},
{
"epoch": 0.29,
"learning_rate": 9.991790324897894e-06,
"loss": 3.2272,
"step": 14000
},
{
"epoch": 0.3,
"learning_rate": 9.99076411551013e-06,
"loss": 3.2246,
"step": 14500
},
{
"epoch": 0.31,
"learning_rate": 9.989737906122367e-06,
"loss": 3.2248,
"step": 15000
},
{
"epoch": 0.32,
"learning_rate": 9.988711696734603e-06,
"loss": 3.2226,
"step": 15500
},
{
"epoch": 0.33,
"learning_rate": 9.987685487346838e-06,
"loss": 3.2167,
"step": 16000
},
{
"epoch": 0.34,
"learning_rate": 9.986659277959076e-06,
"loss": 3.2162,
"step": 16500
},
{
"epoch": 0.35,
"learning_rate": 9.985633068571312e-06,
"loss": 3.2155,
"step": 17000
},
{
"epoch": 0.36,
"learning_rate": 9.98460685918355e-06,
"loss": 3.2094,
"step": 17500
},
{
"epoch": 0.37,
"learning_rate": 9.983580649795785e-06,
"loss": 3.2079,
"step": 18000
},
{
"epoch": 0.38,
"learning_rate": 9.982554440408022e-06,
"loss": 3.2027,
"step": 18500
},
{
"epoch": 0.39,
"learning_rate": 9.981528231020258e-06,
"loss": 3.1984,
"step": 19000
},
{
"epoch": 0.4,
"learning_rate": 9.980502021632494e-06,
"loss": 3.1998,
"step": 19500
},
{
"epoch": 0.41,
"learning_rate": 9.979475812244731e-06,
"loss": 3.1986,
"step": 20000
},
{
"epoch": 0.42,
"learning_rate": 9.978449602856967e-06,
"loss": 3.1939,
"step": 20500
},
{
"epoch": 0.43,
"learning_rate": 9.977423393469205e-06,
"loss": 3.1881,
"step": 21000
},
{
"epoch": 0.44,
"learning_rate": 9.97639718408144e-06,
"loss": 3.1888,
"step": 21500
},
{
"epoch": 0.45,
"learning_rate": 9.975370974693678e-06,
"loss": 3.1824,
"step": 22000
},
{
"epoch": 0.46,
"learning_rate": 9.974344765305914e-06,
"loss": 3.1843,
"step": 22500
},
{
"epoch": 0.47,
"learning_rate": 9.97331855591815e-06,
"loss": 3.1819,
"step": 23000
},
{
"epoch": 0.48,
"learning_rate": 9.972292346530387e-06,
"loss": 3.1786,
"step": 23500
},
{
"epoch": 0.49,
"learning_rate": 9.971266137142623e-06,
"loss": 3.1739,
"step": 24000
},
{
"epoch": 0.5,
"learning_rate": 9.97023992775486e-06,
"loss": 3.1689,
"step": 24500
},
{
"epoch": 0.51,
"learning_rate": 9.969213718367097e-06,
"loss": 3.17,
"step": 25000
},
{
"epoch": 0.52,
"learning_rate": 9.968187508979333e-06,
"loss": 3.1653,
"step": 25500
},
{
"epoch": 0.53,
"learning_rate": 9.967161299591569e-06,
"loss": 3.168,
"step": 26000
},
{
"epoch": 0.54,
"learning_rate": 9.966135090203806e-06,
"loss": 3.1662,
"step": 26500
},
{
"epoch": 0.55,
"learning_rate": 9.965108880816042e-06,
"loss": 3.1605,
"step": 27000
},
{
"epoch": 0.56,
"learning_rate": 9.96408267142828e-06,
"loss": 3.1582,
"step": 27500
},
{
"epoch": 0.57,
"learning_rate": 9.963056462040515e-06,
"loss": 3.1582,
"step": 28000
},
{
"epoch": 0.58,
"learning_rate": 9.962030252652753e-06,
"loss": 3.1554,
"step": 28500
},
{
"epoch": 0.59,
"learning_rate": 9.961004043264989e-06,
"loss": 3.1546,
"step": 29000
},
{
"epoch": 0.6,
"learning_rate": 9.959977833877224e-06,
"loss": 3.1493,
"step": 29500
},
{
"epoch": 0.61,
"learning_rate": 9.958951624489462e-06,
"loss": 3.1514,
"step": 30000
},
{
"epoch": 0.62,
"learning_rate": 9.957925415101698e-06,
"loss": 3.1422,
"step": 30500
},
{
"epoch": 0.63,
"learning_rate": 9.956899205713935e-06,
"loss": 3.1437,
"step": 31000
},
{
"epoch": 0.65,
"learning_rate": 9.955872996326171e-06,
"loss": 3.136,
"step": 31500
},
{
"epoch": 0.66,
"learning_rate": 9.954846786938408e-06,
"loss": 3.1404,
"step": 32000
},
{
"epoch": 0.67,
"learning_rate": 9.953820577550644e-06,
"loss": 3.1361,
"step": 32500
},
{
"epoch": 0.68,
"learning_rate": 9.95279436816288e-06,
"loss": 3.1394,
"step": 33000
},
{
"epoch": 0.69,
"learning_rate": 9.951768158775117e-06,
"loss": 3.1301,
"step": 33500
},
{
"epoch": 0.7,
"learning_rate": 9.950741949387353e-06,
"loss": 3.1325,
"step": 34000
},
{
"epoch": 0.71,
"learning_rate": 9.94971573999959e-06,
"loss": 3.1325,
"step": 34500
},
{
"epoch": 0.72,
"learning_rate": 9.948689530611826e-06,
"loss": 3.1279,
"step": 35000
},
{
"epoch": 0.73,
"learning_rate": 9.947663321224064e-06,
"loss": 3.131,
"step": 35500
},
{
"epoch": 0.74,
"learning_rate": 9.9466371118363e-06,
"loss": 3.1235,
"step": 36000
},
{
"epoch": 0.75,
"learning_rate": 9.945610902448535e-06,
"loss": 3.1235,
"step": 36500
},
{
"epoch": 0.76,
"learning_rate": 9.944584693060773e-06,
"loss": 3.1232,
"step": 37000
},
{
"epoch": 0.77,
"learning_rate": 9.943558483673009e-06,
"loss": 3.1173,
"step": 37500
},
{
"epoch": 0.78,
"learning_rate": 9.942532274285246e-06,
"loss": 3.1155,
"step": 38000
},
{
"epoch": 0.79,
"learning_rate": 9.941506064897482e-06,
"loss": 3.1132,
"step": 38500
},
{
"epoch": 0.8,
"learning_rate": 9.94047985550972e-06,
"loss": 3.1128,
"step": 39000
},
{
"epoch": 0.81,
"learning_rate": 9.939453646121957e-06,
"loss": 3.1146,
"step": 39500
},
{
"epoch": 0.82,
"learning_rate": 9.93842743673419e-06,
"loss": 3.1095,
"step": 40000
},
{
"epoch": 0.83,
"learning_rate": 9.937401227346428e-06,
"loss": 3.1091,
"step": 40500
},
{
"epoch": 0.84,
"learning_rate": 9.936375017958666e-06,
"loss": 3.1057,
"step": 41000
},
{
"epoch": 0.85,
"learning_rate": 9.935348808570901e-06,
"loss": 3.1025,
"step": 41500
},
{
"epoch": 0.86,
"learning_rate": 9.934322599183139e-06,
"loss": 3.1013,
"step": 42000
},
{
"epoch": 0.87,
"learning_rate": 9.933296389795375e-06,
"loss": 3.102,
"step": 42500
},
{
"epoch": 0.88,
"learning_rate": 9.932270180407612e-06,
"loss": 3.1002,
"step": 43000
},
{
"epoch": 0.89,
"learning_rate": 9.931243971019848e-06,
"loss": 3.095,
"step": 43500
},
{
"epoch": 0.9,
"learning_rate": 9.930217761632084e-06,
"loss": 3.094,
"step": 44000
},
{
"epoch": 0.91,
"learning_rate": 9.929191552244321e-06,
"loss": 3.0921,
"step": 44500
},
{
"epoch": 0.92,
"learning_rate": 9.928165342856557e-06,
"loss": 3.0942,
"step": 45000
},
{
"epoch": 0.93,
"learning_rate": 9.927139133468794e-06,
"loss": 3.0909,
"step": 45500
},
{
"epoch": 0.94,
"learning_rate": 9.92611292408103e-06,
"loss": 3.0878,
"step": 46000
},
{
"epoch": 0.95,
"learning_rate": 9.925086714693268e-06,
"loss": 3.0875,
"step": 46500
},
{
"epoch": 0.96,
"learning_rate": 9.924060505305503e-06,
"loss": 3.0822,
"step": 47000
},
{
"epoch": 0.97,
"learning_rate": 9.923034295917739e-06,
"loss": 3.0825,
"step": 47500
},
{
"epoch": 0.98,
"learning_rate": 9.922008086529977e-06,
"loss": 3.0825,
"step": 48000
},
{
"epoch": 0.99,
"learning_rate": 9.920981877142212e-06,
"loss": 3.0791,
"step": 48500
},
{
"epoch": 1.0,
"learning_rate": 9.91995566775445e-06,
"loss": 3.0792,
"step": 49000
},
{
"epoch": 1.01,
"learning_rate": 9.918929458366686e-06,
"loss": 3.083,
"step": 49500
},
{
"epoch": 1.02,
"learning_rate": 9.917903248978923e-06,
"loss": 3.0756,
"step": 50000
},
{
"epoch": 1.03,
"learning_rate": 9.916877039591159e-06,
"loss": 3.0731,
"step": 50500
},
{
"epoch": 1.04,
"learning_rate": 9.915850830203395e-06,
"loss": 3.0728,
"step": 51000
},
{
"epoch": 1.05,
"learning_rate": 9.914824620815632e-06,
"loss": 3.0712,
"step": 51500
},
{
"epoch": 1.07,
"learning_rate": 9.913798411427868e-06,
"loss": 3.0659,
"step": 52000
},
{
"epoch": 1.08,
"learning_rate": 9.912772202040105e-06,
"loss": 3.0664,
"step": 52500
},
{
"epoch": 1.09,
"learning_rate": 9.911745992652341e-06,
"loss": 3.0664,
"step": 53000
},
{
"epoch": 1.1,
"learning_rate": 9.910719783264578e-06,
"loss": 3.0669,
"step": 53500
},
{
"epoch": 1.11,
"learning_rate": 9.909693573876816e-06,
"loss": 3.0662,
"step": 54000
},
{
"epoch": 1.12,
"learning_rate": 9.90866736448905e-06,
"loss": 3.0629,
"step": 54500
},
{
"epoch": 1.13,
"learning_rate": 9.907641155101287e-06,
"loss": 3.0614,
"step": 55000
},
{
"epoch": 1.14,
"learning_rate": 9.906614945713525e-06,
"loss": 3.0579,
"step": 55500
},
{
"epoch": 1.15,
"learning_rate": 9.90558873632576e-06,
"loss": 3.0541,
"step": 56000
},
{
"epoch": 1.16,
"learning_rate": 9.904562526937998e-06,
"loss": 3.052,
"step": 56500
},
{
"epoch": 1.17,
"learning_rate": 9.903536317550234e-06,
"loss": 3.05,
"step": 57000
},
{
"epoch": 1.18,
"learning_rate": 9.902510108162471e-06,
"loss": 3.0525,
"step": 57500
},
{
"epoch": 1.19,
"learning_rate": 9.901483898774707e-06,
"loss": 3.0511,
"step": 58000
},
{
"epoch": 1.2,
"learning_rate": 9.900457689386943e-06,
"loss": 3.051,
"step": 58500
},
{
"epoch": 1.21,
"learning_rate": 9.89943147999918e-06,
"loss": 3.0495,
"step": 59000
},
{
"epoch": 1.22,
"learning_rate": 9.898405270611416e-06,
"loss": 3.0467,
"step": 59500
},
{
"epoch": 1.23,
"learning_rate": 9.897379061223654e-06,
"loss": 3.0462,
"step": 60000
},
{
"epoch": 1.24,
"learning_rate": 9.89635285183589e-06,
"loss": 3.0438,
"step": 60500
},
{
"epoch": 1.25,
"learning_rate": 9.895326642448127e-06,
"loss": 3.0462,
"step": 61000
},
{
"epoch": 1.26,
"learning_rate": 9.894300433060363e-06,
"loss": 3.0411,
"step": 61500
},
{
"epoch": 1.27,
"learning_rate": 9.893274223672598e-06,
"loss": 3.0413,
"step": 62000
},
{
"epoch": 1.28,
"learning_rate": 9.892248014284836e-06,
"loss": 3.0415,
"step": 62500
},
{
"epoch": 1.29,
"learning_rate": 9.891221804897072e-06,
"loss": 3.0397,
"step": 63000
},
{
"epoch": 1.3,
"learning_rate": 9.890195595509309e-06,
"loss": 3.0369,
"step": 63500
},
{
"epoch": 1.31,
"learning_rate": 9.889169386121545e-06,
"loss": 3.039,
"step": 64000
},
{
"epoch": 1.32,
"learning_rate": 9.888143176733782e-06,
"loss": 3.0424,
"step": 64500
},
{
"epoch": 1.33,
"learning_rate": 9.887116967346018e-06,
"loss": 3.0291,
"step": 65000
},
{
"epoch": 1.34,
"learning_rate": 9.886090757958254e-06,
"loss": 3.0329,
"step": 65500
},
{
"epoch": 1.35,
"learning_rate": 9.885064548570491e-06,
"loss": 3.0348,
"step": 66000
},
{
"epoch": 1.36,
"learning_rate": 9.884038339182727e-06,
"loss": 3.029,
"step": 66500
},
{
"epoch": 1.37,
"learning_rate": 9.883012129794964e-06,
"loss": 3.0352,
"step": 67000
},
{
"epoch": 1.38,
"learning_rate": 9.8819859204072e-06,
"loss": 3.029,
"step": 67500
},
{
"epoch": 1.39,
"learning_rate": 9.880959711019438e-06,
"loss": 3.0301,
"step": 68000
},
{
"epoch": 1.4,
"learning_rate": 9.879933501631673e-06,
"loss": 3.0271,
"step": 68500
},
{
"epoch": 1.41,
"learning_rate": 9.87890729224391e-06,
"loss": 3.0248,
"step": 69000
},
{
"epoch": 1.42,
"learning_rate": 9.877881082856147e-06,
"loss": 3.0213,
"step": 69500
},
{
"epoch": 1.43,
"learning_rate": 9.876854873468384e-06,
"loss": 3.0236,
"step": 70000
},
{
"epoch": 1.44,
"learning_rate": 9.87582866408062e-06,
"loss": 3.0196,
"step": 70500
},
{
"epoch": 1.45,
"learning_rate": 9.874802454692857e-06,
"loss": 3.0204,
"step": 71000
},
{
"epoch": 1.46,
"learning_rate": 9.873776245305093e-06,
"loss": 3.0181,
"step": 71500
},
{
"epoch": 1.47,
"learning_rate": 9.872750035917329e-06,
"loss": 3.0185,
"step": 72000
},
{
"epoch": 1.48,
"learning_rate": 9.871723826529566e-06,
"loss": 3.0151,
"step": 72500
},
{
"epoch": 1.5,
"learning_rate": 9.870697617141802e-06,
"loss": 3.0156,
"step": 73000
},
{
"epoch": 1.51,
"learning_rate": 9.86967140775404e-06,
"loss": 3.0133,
"step": 73500
},
{
"epoch": 1.52,
"learning_rate": 9.868645198366275e-06,
"loss": 3.0147,
"step": 74000
},
{
"epoch": 1.53,
"learning_rate": 9.867618988978513e-06,
"loss": 3.0124,
"step": 74500
},
{
"epoch": 1.54,
"learning_rate": 9.866592779590749e-06,
"loss": 3.0095,
"step": 75000
},
{
"epoch": 1.55,
"learning_rate": 9.865566570202984e-06,
"loss": 3.0112,
"step": 75500
},
{
"epoch": 1.56,
"learning_rate": 9.864540360815222e-06,
"loss": 3.0098,
"step": 76000
},
{
"epoch": 1.57,
"learning_rate": 9.863514151427458e-06,
"loss": 3.0085,
"step": 76500
},
{
"epoch": 1.58,
"learning_rate": 9.862487942039695e-06,
"loss": 3.0091,
"step": 77000
},
{
"epoch": 1.59,
"learning_rate": 9.86146173265193e-06,
"loss": 3.0061,
"step": 77500
},
{
"epoch": 1.6,
"learning_rate": 9.860435523264168e-06,
"loss": 3.0042,
"step": 78000
},
{
"epoch": 1.61,
"learning_rate": 9.859409313876404e-06,
"loss": 3.0043,
"step": 78500
},
{
"epoch": 1.62,
"learning_rate": 9.85838310448864e-06,
"loss": 3.005,
"step": 79000
},
{
"epoch": 1.63,
"learning_rate": 9.857356895100877e-06,
"loss": 3.0039,
"step": 79500
},
{
"epoch": 1.64,
"learning_rate": 9.856330685713113e-06,
"loss": 3.001,
"step": 80000
},
{
"epoch": 1.65,
"learning_rate": 9.85530447632535e-06,
"loss": 2.9973,
"step": 80500
},
{
"epoch": 1.66,
"learning_rate": 9.854278266937586e-06,
"loss": 2.9965,
"step": 81000
},
{
"epoch": 1.67,
"learning_rate": 9.853252057549824e-06,
"loss": 2.9957,
"step": 81500
},
{
"epoch": 1.68,
"learning_rate": 9.85222584816206e-06,
"loss": 2.9965,
"step": 82000
},
{
"epoch": 1.69,
"learning_rate": 9.851199638774295e-06,
"loss": 2.9993,
"step": 82500
},
{
"epoch": 1.7,
"learning_rate": 9.850173429386533e-06,
"loss": 2.9948,
"step": 83000
},
{
"epoch": 1.71,
"learning_rate": 9.849147219998768e-06,
"loss": 2.9925,
"step": 83500
},
{
"epoch": 1.72,
"learning_rate": 9.848121010611006e-06,
"loss": 2.9912,
"step": 84000
},
{
"epoch": 1.73,
"learning_rate": 9.847094801223243e-06,
"loss": 2.9879,
"step": 84500
},
{
"epoch": 1.74,
"learning_rate": 9.846068591835479e-06,
"loss": 2.9869,
"step": 85000
},
{
"epoch": 1.75,
"learning_rate": 9.845042382447717e-06,
"loss": 2.991,
"step": 85500
},
{
"epoch": 1.76,
"learning_rate": 9.84401617305995e-06,
"loss": 2.9891,
"step": 86000
},
{
"epoch": 1.77,
"learning_rate": 9.842989963672188e-06,
"loss": 2.9853,
"step": 86500
},
{
"epoch": 1.78,
"learning_rate": 9.841963754284426e-06,
"loss": 2.9877,
"step": 87000
},
{
"epoch": 1.79,
"learning_rate": 9.840937544896661e-06,
"loss": 2.9877,
"step": 87500
},
{
"epoch": 1.8,
"learning_rate": 9.839911335508899e-06,
"loss": 2.9768,
"step": 88000
},
{
"epoch": 1.81,
"learning_rate": 9.838885126121135e-06,
"loss": 2.9825,
"step": 88500
},
{
"epoch": 1.82,
"learning_rate": 9.837858916733372e-06,
"loss": 2.9788,
"step": 89000
},
{
"epoch": 1.83,
"learning_rate": 9.836832707345608e-06,
"loss": 2.9821,
"step": 89500
},
{
"epoch": 1.84,
"learning_rate": 9.835806497957844e-06,
"loss": 2.9782,
"step": 90000
},
{
"epoch": 1.85,
"learning_rate": 9.834780288570081e-06,
"loss": 2.9765,
"step": 90500
},
{
"epoch": 1.86,
"learning_rate": 9.833754079182317e-06,
"loss": 2.9753,
"step": 91000
},
{
"epoch": 1.87,
"learning_rate": 9.832727869794554e-06,
"loss": 2.9805,
"step": 91500
},
{
"epoch": 1.88,
"learning_rate": 9.83170166040679e-06,
"loss": 2.9785,
"step": 92000
},
{
"epoch": 1.89,
"learning_rate": 9.830675451019027e-06,
"loss": 2.9742,
"step": 92500
},
{
"epoch": 1.9,
"learning_rate": 9.829649241631263e-06,
"loss": 2.9711,
"step": 93000
},
{
"epoch": 1.92,
"learning_rate": 9.828623032243499e-06,
"loss": 2.9752,
"step": 93500
},
{
"epoch": 1.93,
"learning_rate": 9.827596822855736e-06,
"loss": 2.9738,
"step": 94000
},
{
"epoch": 1.94,
"learning_rate": 9.826570613467972e-06,
"loss": 2.9723,
"step": 94500
},
{
"epoch": 1.95,
"learning_rate": 9.82554440408021e-06,
"loss": 2.9693,
"step": 95000
},
{
"epoch": 1.96,
"learning_rate": 9.824518194692445e-06,
"loss": 2.9664,
"step": 95500
},
{
"epoch": 1.97,
"learning_rate": 9.823491985304683e-06,
"loss": 2.9677,
"step": 96000
},
{
"epoch": 1.98,
"learning_rate": 9.822465775916919e-06,
"loss": 2.9665,
"step": 96500
},
{
"epoch": 1.99,
"learning_rate": 9.821439566529154e-06,
"loss": 2.9678,
"step": 97000
},
{
"epoch": 2.0,
"learning_rate": 9.820413357141392e-06,
"loss": 2.9651,
"step": 97500
},
{
"epoch": 2.01,
"learning_rate": 9.819387147753628e-06,
"loss": 2.9647,
"step": 98000
},
{
"epoch": 2.02,
"learning_rate": 9.818360938365865e-06,
"loss": 2.9639,
"step": 98500
},
{
"epoch": 2.03,
"learning_rate": 9.817334728978103e-06,
"loss": 2.9649,
"step": 99000
},
{
"epoch": 2.04,
"learning_rate": 9.816308519590338e-06,
"loss": 2.9578,
"step": 99500
},
{
"epoch": 2.05,
"learning_rate": 9.815282310202574e-06,
"loss": 2.9581,
"step": 100000
},
{
"epoch": 2.06,
"learning_rate": 9.81425610081481e-06,
"loss": 2.9617,
"step": 100500
},
{
"epoch": 2.07,
"learning_rate": 9.813229891427047e-06,
"loss": 2.9522,
"step": 101000
},
{
"epoch": 2.08,
"learning_rate": 9.812203682039285e-06,
"loss": 2.9578,
"step": 101500
},
{
"epoch": 2.09,
"learning_rate": 9.81117747265152e-06,
"loss": 2.9565,
"step": 102000
},
{
"epoch": 2.1,
"learning_rate": 9.810151263263758e-06,
"loss": 2.9578,
"step": 102500
},
{
"epoch": 2.11,
"learning_rate": 9.809125053875994e-06,
"loss": 2.9583,
"step": 103000
},
{
"epoch": 2.12,
"learning_rate": 9.80809884448823e-06,
"loss": 2.9579,
"step": 103500
},
{
"epoch": 2.13,
"learning_rate": 9.807072635100467e-06,
"loss": 2.9554,
"step": 104000
},
{
"epoch": 2.14,
"learning_rate": 9.806046425712703e-06,
"loss": 2.9537,
"step": 104500
},
{
"epoch": 2.15,
"learning_rate": 9.80502021632494e-06,
"loss": 2.95,
"step": 105000
},
{
"epoch": 2.16,
"learning_rate": 9.803994006937176e-06,
"loss": 2.9563,
"step": 105500
},
{
"epoch": 2.17,
"learning_rate": 9.802967797549413e-06,
"loss": 2.9546,
"step": 106000
},
{
"epoch": 2.18,
"learning_rate": 9.80194158816165e-06,
"loss": 2.9505,
"step": 106500
},
{
"epoch": 2.19,
"learning_rate": 9.800915378773885e-06,
"loss": 2.9509,
"step": 107000
},
{
"epoch": 2.2,
"learning_rate": 9.799889169386122e-06,
"loss": 2.9504,
"step": 107500
},
{
"epoch": 2.21,
"learning_rate": 9.798862959998358e-06,
"loss": 2.9483,
"step": 108000
},
{
"epoch": 2.22,
"learning_rate": 9.797836750610596e-06,
"loss": 2.9484,
"step": 108500
},
{
"epoch": 2.23,
"learning_rate": 9.796810541222831e-06,
"loss": 2.9439,
"step": 109000
},
{
"epoch": 2.24,
"learning_rate": 9.795784331835069e-06,
"loss": 2.9414,
"step": 109500
},
{
"epoch": 2.25,
"learning_rate": 9.794758122447305e-06,
"loss": 2.9392,
"step": 110000
},
{
"epoch": 2.26,
"learning_rate": 9.79373191305954e-06,
"loss": 2.9424,
"step": 110500
},
{
"epoch": 2.27,
"learning_rate": 9.792705703671778e-06,
"loss": 2.9442,
"step": 111000
},
{
"epoch": 2.28,
"learning_rate": 9.791679494284014e-06,
"loss": 2.9416,
"step": 111500
},
{
"epoch": 2.29,
"learning_rate": 9.790653284896251e-06,
"loss": 2.9381,
"step": 112000
},
{
"epoch": 2.3,
"learning_rate": 9.789627075508487e-06,
"loss": 2.943,
"step": 112500
},
{
"epoch": 2.31,
"learning_rate": 9.788600866120724e-06,
"loss": 2.9418,
"step": 113000
},
{
"epoch": 2.32,
"learning_rate": 9.787574656732962e-06,
"loss": 2.9406,
"step": 113500
},
{
"epoch": 2.33,
"learning_rate": 9.786548447345196e-06,
"loss": 2.9394,
"step": 114000
},
{
"epoch": 2.35,
"learning_rate": 9.785522237957433e-06,
"loss": 2.9382,
"step": 114500
},
{
"epoch": 2.36,
"learning_rate": 9.784496028569669e-06,
"loss": 2.9323,
"step": 115000
},
{
"epoch": 2.37,
"learning_rate": 9.783469819181907e-06,
"loss": 2.9279,
"step": 115500
},
{
"epoch": 2.38,
"learning_rate": 9.782443609794144e-06,
"loss": 2.9383,
"step": 116000
},
{
"epoch": 2.39,
"learning_rate": 9.78141740040638e-06,
"loss": 2.9396,
"step": 116500
},
{
"epoch": 2.4,
"learning_rate": 9.780391191018617e-06,
"loss": 2.9342,
"step": 117000
},
{
"epoch": 2.41,
"learning_rate": 9.779364981630853e-06,
"loss": 2.9338,
"step": 117500
},
{
"epoch": 2.42,
"learning_rate": 9.778338772243089e-06,
"loss": 2.9317,
"step": 118000
},
{
"epoch": 2.43,
"learning_rate": 9.777312562855326e-06,
"loss": 2.9334,
"step": 118500
},
{
"epoch": 2.44,
"learning_rate": 9.776286353467562e-06,
"loss": 2.9319,
"step": 119000
},
{
"epoch": 2.45,
"learning_rate": 9.7752601440798e-06,
"loss": 2.9317,
"step": 119500
},
{
"epoch": 2.46,
"learning_rate": 9.774233934692035e-06,
"loss": 2.9297,
"step": 120000
},
{
"epoch": 2.47,
"learning_rate": 9.773207725304273e-06,
"loss": 2.9241,
"step": 120500
},
{
"epoch": 2.48,
"learning_rate": 9.772181515916508e-06,
"loss": 2.9236,
"step": 121000
},
{
"epoch": 2.49,
"learning_rate": 9.771155306528744e-06,
"loss": 2.9274,
"step": 121500
},
{
"epoch": 2.5,
"learning_rate": 9.770129097140982e-06,
"loss": 2.927,
"step": 122000
},
{
"epoch": 2.51,
"learning_rate": 9.769102887753217e-06,
"loss": 2.9251,
"step": 122500
},
{
"epoch": 2.52,
"learning_rate": 9.768076678365455e-06,
"loss": 2.9237,
"step": 123000
},
{
"epoch": 2.53,
"learning_rate": 9.76705046897769e-06,
"loss": 2.9215,
"step": 123500
},
{
"epoch": 2.54,
"learning_rate": 9.766024259589928e-06,
"loss": 2.9307,
"step": 124000
},
{
"epoch": 2.55,
"learning_rate": 9.764998050202164e-06,
"loss": 2.9135,
"step": 124500
},
{
"epoch": 2.56,
"learning_rate": 9.7639718408144e-06,
"loss": 2.9238,
"step": 125000
},
{
"epoch": 2.57,
"learning_rate": 9.762945631426637e-06,
"loss": 2.919,
"step": 125500
},
{
"epoch": 2.58,
"learning_rate": 9.761919422038873e-06,
"loss": 2.9167,
"step": 126000
},
{
"epoch": 2.59,
"learning_rate": 9.76089321265111e-06,
"loss": 2.9182,
"step": 126500
},
{
"epoch": 2.6,
"learning_rate": 9.759867003263346e-06,
"loss": 2.92,
"step": 127000
},
{
"epoch": 2.61,
"learning_rate": 9.758840793875584e-06,
"loss": 2.9198,
"step": 127500
},
{
"epoch": 2.62,
"learning_rate": 9.75781458448782e-06,
"loss": 2.9202,
"step": 128000
},
{
"epoch": 2.63,
"learning_rate": 9.756788375100055e-06,
"loss": 2.919,
"step": 128500
},
{
"epoch": 2.64,
"learning_rate": 9.755762165712293e-06,
"loss": 2.9169,
"step": 129000
},
{
"epoch": 2.65,
"learning_rate": 9.754735956324528e-06,
"loss": 2.9131,
"step": 129500
},
{
"epoch": 2.66,
"learning_rate": 9.753709746936766e-06,
"loss": 2.9164,
"step": 130000
},
{
"epoch": 2.67,
"learning_rate": 9.752683537549003e-06,
"loss": 2.9131,
"step": 130500
},
{
"epoch": 2.68,
"learning_rate": 9.751657328161239e-06,
"loss": 2.9111,
"step": 131000
},
{
"epoch": 2.69,
"learning_rate": 9.750631118773475e-06,
"loss": 2.911,
"step": 131500
},
{
"epoch": 2.7,
"learning_rate": 9.749604909385712e-06,
"loss": 2.9106,
"step": 132000
},
{
"epoch": 2.71,
"learning_rate": 9.748578699997948e-06,
"loss": 2.9155,
"step": 132500
},
{
"epoch": 2.72,
"learning_rate": 9.747552490610185e-06,
"loss": 2.9095,
"step": 133000
},
{
"epoch": 2.73,
"learning_rate": 9.746526281222421e-06,
"loss": 2.9127,
"step": 133500
},
{
"epoch": 2.74,
"learning_rate": 9.745500071834659e-06,
"loss": 2.9085,
"step": 134000
},
{
"epoch": 2.75,
"learning_rate": 9.744473862446894e-06,
"loss": 2.9106,
"step": 134500
},
{
"epoch": 2.77,
"learning_rate": 9.74344765305913e-06,
"loss": 2.9084,
"step": 135000
},
{
"epoch": 2.78,
"learning_rate": 9.742421443671368e-06,
"loss": 2.9066,
"step": 135500
},
{
"epoch": 2.79,
"learning_rate": 9.741395234283603e-06,
"loss": 2.9089,
"step": 136000
},
{
"epoch": 2.8,
"learning_rate": 9.740369024895841e-06,
"loss": 2.9084,
"step": 136500
},
{
"epoch": 2.81,
"learning_rate": 9.739342815508077e-06,
"loss": 2.9023,
"step": 137000
},
{
"epoch": 2.82,
"learning_rate": 9.738316606120314e-06,
"loss": 2.9036,
"step": 137500
},
{
"epoch": 2.83,
"learning_rate": 9.73729039673255e-06,
"loss": 2.9039,
"step": 138000
},
{
"epoch": 2.84,
"learning_rate": 9.736264187344787e-06,
"loss": 2.9016,
"step": 138500
},
{
"epoch": 2.85,
"learning_rate": 9.735237977957023e-06,
"loss": 2.902,
"step": 139000
},
{
"epoch": 2.86,
"learning_rate": 9.734211768569259e-06,
"loss": 2.9007,
"step": 139500
},
{
"epoch": 2.87,
"learning_rate": 9.733185559181496e-06,
"loss": 2.9021,
"step": 140000
},
{
"epoch": 2.88,
"learning_rate": 9.732159349793732e-06,
"loss": 2.9033,
"step": 140500
},
{
"epoch": 2.89,
"learning_rate": 9.73113314040597e-06,
"loss": 2.899,
"step": 141000
},
{
"epoch": 2.9,
"learning_rate": 9.730106931018205e-06,
"loss": 2.9017,
"step": 141500
},
{
"epoch": 2.91,
"learning_rate": 9.729080721630443e-06,
"loss": 2.9009,
"step": 142000
},
{
"epoch": 2.92,
"learning_rate": 9.728054512242679e-06,
"loss": 2.8961,
"step": 142500
},
{
"epoch": 2.93,
"learning_rate": 9.727028302854914e-06,
"loss": 2.9006,
"step": 143000
},
{
"epoch": 2.94,
"learning_rate": 9.726002093467152e-06,
"loss": 2.8959,
"step": 143500
},
{
"epoch": 2.95,
"learning_rate": 9.72497588407939e-06,
"loss": 2.9008,
"step": 144000
},
{
"epoch": 2.96,
"learning_rate": 9.723949674691625e-06,
"loss": 2.8935,
"step": 144500
},
{
"epoch": 2.97,
"learning_rate": 9.722923465303862e-06,
"loss": 2.8979,
"step": 145000
},
{
"epoch": 2.98,
"learning_rate": 9.721897255916098e-06,
"loss": 2.8968,
"step": 145500
},
{
"epoch": 2.99,
"learning_rate": 9.720871046528334e-06,
"loss": 2.8965,
"step": 146000
},
{
"epoch": 3.0,
"learning_rate": 9.719844837140571e-06,
"loss": 2.89,
"step": 146500
},
{
"epoch": 3.01,
"learning_rate": 9.718818627752807e-06,
"loss": 2.8946,
"step": 147000
},
{
"epoch": 3.02,
"learning_rate": 9.717792418365045e-06,
"loss": 2.8923,
"step": 147500
},
{
"epoch": 3.03,
"learning_rate": 9.71676620897728e-06,
"loss": 2.8918,
"step": 148000
},
{
"epoch": 3.04,
"learning_rate": 9.715739999589518e-06,
"loss": 2.8936,
"step": 148500
},
{
"epoch": 3.05,
"learning_rate": 9.714713790201754e-06,
"loss": 2.8901,
"step": 149000
},
{
"epoch": 3.06,
"learning_rate": 9.71368758081399e-06,
"loss": 2.8895,
"step": 149500
},
{
"epoch": 3.07,
"learning_rate": 9.712661371426227e-06,
"loss": 2.8864,
"step": 150000
},
{
"epoch": 3.08,
"learning_rate": 9.711635162038463e-06,
"loss": 2.886,
"step": 150500
},
{
"epoch": 3.09,
"learning_rate": 9.7106089526507e-06,
"loss": 2.8879,
"step": 151000
},
{
"epoch": 3.1,
"learning_rate": 9.709582743262936e-06,
"loss": 2.8869,
"step": 151500
},
{
"epoch": 3.11,
"learning_rate": 9.708556533875173e-06,
"loss": 2.8836,
"step": 152000
},
{
"epoch": 3.12,
"learning_rate": 9.707530324487409e-06,
"loss": 2.8888,
"step": 152500
},
{
"epoch": 3.13,
"learning_rate": 9.706504115099645e-06,
"loss": 2.8865,
"step": 153000
},
{
"epoch": 3.14,
"learning_rate": 9.705477905711882e-06,
"loss": 2.8821,
"step": 153500
},
{
"epoch": 3.15,
"learning_rate": 9.704451696324118e-06,
"loss": 2.8867,
"step": 154000
},
{
"epoch": 3.16,
"learning_rate": 9.703425486936356e-06,
"loss": 2.8809,
"step": 154500
},
{
"epoch": 3.17,
"learning_rate": 9.702399277548591e-06,
"loss": 2.8785,
"step": 155000
},
{
"epoch": 3.18,
"learning_rate": 9.701373068160829e-06,
"loss": 2.8792,
"step": 155500
},
{
"epoch": 3.2,
"learning_rate": 9.700346858773065e-06,
"loss": 2.883,
"step": 156000
},
{
"epoch": 3.21,
"learning_rate": 9.6993206493853e-06,
"loss": 2.8764,
"step": 156500
},
{
"epoch": 3.22,
"learning_rate": 9.698294439997538e-06,
"loss": 2.8762,
"step": 157000
},
{
"epoch": 3.23,
"learning_rate": 9.697268230609774e-06,
"loss": 2.8753,
"step": 157500
},
{
"epoch": 3.24,
"learning_rate": 9.696242021222011e-06,
"loss": 2.8781,
"step": 158000
},
{
"epoch": 3.25,
"learning_rate": 9.695215811834248e-06,
"loss": 2.8818,
"step": 158500
},
{
"epoch": 3.26,
"learning_rate": 9.694189602446484e-06,
"loss": 2.8792,
"step": 159000
},
{
"epoch": 3.27,
"learning_rate": 9.693163393058722e-06,
"loss": 2.8757,
"step": 159500
},
{
"epoch": 3.28,
"learning_rate": 9.692137183670956e-06,
"loss": 2.8756,
"step": 160000
},
{
"epoch": 3.29,
"learning_rate": 9.691110974283193e-06,
"loss": 2.8794,
"step": 160500
},
{
"epoch": 3.3,
"learning_rate": 9.69008476489543e-06,
"loss": 2.8735,
"step": 161000
},
{
"epoch": 3.31,
"learning_rate": 9.689058555507666e-06,
"loss": 2.8756,
"step": 161500
},
{
"epoch": 3.32,
"learning_rate": 9.688032346119904e-06,
"loss": 2.8744,
"step": 162000
},
{
"epoch": 3.33,
"learning_rate": 9.68700613673214e-06,
"loss": 2.8739,
"step": 162500
},
{
"epoch": 3.34,
"learning_rate": 9.685979927344377e-06,
"loss": 2.8748,
"step": 163000
},
{
"epoch": 3.35,
"learning_rate": 9.684953717956613e-06,
"loss": 2.8747,
"step": 163500
},
{
"epoch": 3.36,
"learning_rate": 9.683927508568849e-06,
"loss": 2.877,
"step": 164000
},
{
"epoch": 3.37,
"learning_rate": 9.682901299181086e-06,
"loss": 2.8761,
"step": 164500
},
{
"epoch": 3.38,
"learning_rate": 9.681875089793322e-06,
"loss": 2.8686,
"step": 165000
},
{
"epoch": 3.39,
"learning_rate": 9.68084888040556e-06,
"loss": 2.8702,
"step": 165500
},
{
"epoch": 3.4,
"learning_rate": 9.679822671017795e-06,
"loss": 2.869,
"step": 166000
},
{
"epoch": 3.41,
"learning_rate": 9.678796461630033e-06,
"loss": 2.871,
"step": 166500
},
{
"epoch": 3.42,
"learning_rate": 9.677770252242268e-06,
"loss": 2.8716,
"step": 167000
},
{
"epoch": 3.43,
"learning_rate": 9.676744042854504e-06,
"loss": 2.8672,
"step": 167500
},
{
"epoch": 3.44,
"learning_rate": 9.675717833466742e-06,
"loss": 2.8672,
"step": 168000
},
{
"epoch": 3.45,
"learning_rate": 9.674691624078977e-06,
"loss": 2.8679,
"step": 168500
},
{
"epoch": 3.46,
"learning_rate": 9.673665414691215e-06,
"loss": 2.8665,
"step": 169000
},
{
"epoch": 3.47,
"learning_rate": 9.67263920530345e-06,
"loss": 2.8669,
"step": 169500
},
{
"epoch": 3.48,
"learning_rate": 9.671612995915688e-06,
"loss": 2.8629,
"step": 170000
},
{
"epoch": 3.49,
"learning_rate": 9.670586786527924e-06,
"loss": 2.8659,
"step": 170500
},
{
"epoch": 3.5,
"learning_rate": 9.66956057714016e-06,
"loss": 2.862,
"step": 171000
},
{
"epoch": 3.51,
"learning_rate": 9.668534367752397e-06,
"loss": 2.8679,
"step": 171500
},
{
"epoch": 3.52,
"learning_rate": 9.667508158364633e-06,
"loss": 2.8619,
"step": 172000
},
{
"epoch": 3.53,
"learning_rate": 9.66648194897687e-06,
"loss": 2.8622,
"step": 172500
},
{
"epoch": 3.54,
"learning_rate": 9.665455739589108e-06,
"loss": 2.8636,
"step": 173000
},
{
"epoch": 3.55,
"learning_rate": 9.664429530201343e-06,
"loss": 2.8598,
"step": 173500
},
{
"epoch": 3.56,
"learning_rate": 9.66340332081358e-06,
"loss": 2.861,
"step": 174000
},
{
"epoch": 3.57,
"learning_rate": 9.662377111425815e-06,
"loss": 2.8607,
"step": 174500
},
{
"epoch": 3.58,
"learning_rate": 9.661350902038052e-06,
"loss": 2.8605,
"step": 175000
},
{
"epoch": 3.59,
"learning_rate": 9.66032469265029e-06,
"loss": 2.8583,
"step": 175500
},
{
"epoch": 3.6,
"learning_rate": 9.659298483262526e-06,
"loss": 2.8589,
"step": 176000
},
{
"epoch": 3.62,
"learning_rate": 9.658272273874763e-06,
"loss": 2.8552,
"step": 176500
},
{
"epoch": 3.63,
"learning_rate": 9.657246064486999e-06,
"loss": 2.8547,
"step": 177000
},
{
"epoch": 3.64,
"learning_rate": 9.656219855099235e-06,
"loss": 2.8579,
"step": 177500
},
{
"epoch": 3.65,
"learning_rate": 9.655193645711472e-06,
"loss": 2.8559,
"step": 178000
},
{
"epoch": 3.66,
"learning_rate": 9.654167436323708e-06,
"loss": 2.855,
"step": 178500
},
{
"epoch": 3.67,
"learning_rate": 9.653141226935945e-06,
"loss": 2.8571,
"step": 179000
},
{
"epoch": 3.68,
"learning_rate": 9.652115017548181e-06,
"loss": 2.8577,
"step": 179500
},
{
"epoch": 3.69,
"learning_rate": 9.651088808160419e-06,
"loss": 2.8546,
"step": 180000
},
{
"epoch": 3.7,
"learning_rate": 9.650062598772654e-06,
"loss": 2.8543,
"step": 180500
},
{
"epoch": 3.71,
"learning_rate": 9.64903638938489e-06,
"loss": 2.8549,
"step": 181000
},
{
"epoch": 3.72,
"learning_rate": 9.648010179997128e-06,
"loss": 2.8516,
"step": 181500
},
{
"epoch": 3.73,
"learning_rate": 9.646983970609363e-06,
"loss": 2.855,
"step": 182000
},
{
"epoch": 3.74,
"learning_rate": 9.6459577612216e-06,
"loss": 2.8546,
"step": 182500
},
{
"epoch": 3.75,
"learning_rate": 9.644931551833837e-06,
"loss": 2.8564,
"step": 183000
},
{
"epoch": 3.76,
"learning_rate": 9.643905342446074e-06,
"loss": 2.8527,
"step": 183500
},
{
"epoch": 3.77,
"learning_rate": 9.64287913305831e-06,
"loss": 2.8521,
"step": 184000
},
{
"epoch": 3.78,
"learning_rate": 9.641852923670546e-06,
"loss": 2.8472,
"step": 184500
},
{
"epoch": 3.79,
"learning_rate": 9.640826714282783e-06,
"loss": 2.8496,
"step": 185000
},
{
"epoch": 3.8,
"learning_rate": 9.639800504895019e-06,
"loss": 2.8479,
"step": 185500
},
{
"epoch": 3.81,
"learning_rate": 9.638774295507256e-06,
"loss": 2.848,
"step": 186000
},
{
"epoch": 3.82,
"learning_rate": 9.637748086119492e-06,
"loss": 2.8499,
"step": 186500
},
{
"epoch": 3.83,
"learning_rate": 9.63672187673173e-06,
"loss": 2.8544,
"step": 187000
},
{
"epoch": 3.84,
"learning_rate": 9.635695667343967e-06,
"loss": 2.8515,
"step": 187500
},
{
"epoch": 3.85,
"learning_rate": 9.634669457956201e-06,
"loss": 2.8466,
"step": 188000
},
{
"epoch": 3.86,
"learning_rate": 9.633643248568438e-06,
"loss": 2.8472,
"step": 188500
},
{
"epoch": 3.87,
"learning_rate": 9.632617039180674e-06,
"loss": 2.8458,
"step": 189000
},
{
"epoch": 3.88,
"learning_rate": 9.631590829792912e-06,
"loss": 2.849,
"step": 189500
},
{
"epoch": 3.89,
"learning_rate": 9.630564620405149e-06,
"loss": 2.8484,
"step": 190000
},
{
"epoch": 3.9,
"learning_rate": 9.629538411017385e-06,
"loss": 2.8432,
"step": 190500
},
{
"epoch": 3.91,
"learning_rate": 9.628512201629622e-06,
"loss": 2.8415,
"step": 191000
},
{
"epoch": 3.92,
"learning_rate": 9.627485992241858e-06,
"loss": 2.8396,
"step": 191500
},
{
"epoch": 3.93,
"learning_rate": 9.626459782854094e-06,
"loss": 2.8422,
"step": 192000
},
{
"epoch": 3.94,
"learning_rate": 9.625433573466331e-06,
"loss": 2.845,
"step": 192500
},
{
"epoch": 3.95,
"learning_rate": 9.624407364078567e-06,
"loss": 2.8414,
"step": 193000
},
{
"epoch": 3.96,
"learning_rate": 9.623381154690805e-06,
"loss": 2.8446,
"step": 193500
},
{
"epoch": 3.97,
"learning_rate": 9.62235494530304e-06,
"loss": 2.8469,
"step": 194000
},
{
"epoch": 3.98,
"learning_rate": 9.621328735915278e-06,
"loss": 2.8414,
"step": 194500
},
{
"epoch": 3.99,
"learning_rate": 9.620302526527514e-06,
"loss": 2.8386,
"step": 195000
},
{
"epoch": 4.0,
"learning_rate": 9.61927631713975e-06,
"loss": 2.8357,
"step": 195500
},
{
"epoch": 4.01,
"learning_rate": 9.618250107751987e-06,
"loss": 2.8368,
"step": 196000
},
{
"epoch": 4.02,
"learning_rate": 9.617223898364223e-06,
"loss": 2.8349,
"step": 196500
},
{
"epoch": 4.03,
"learning_rate": 9.61619768897646e-06,
"loss": 2.842,
"step": 197000
},
{
"epoch": 4.05,
"learning_rate": 9.615171479588696e-06,
"loss": 2.8418,
"step": 197500
},
{
"epoch": 4.06,
"learning_rate": 9.614145270200933e-06,
"loss": 2.8408,
"step": 198000
},
{
"epoch": 4.07,
"learning_rate": 9.613119060813169e-06,
"loss": 2.8365,
"step": 198500
},
{
"epoch": 4.08,
"learning_rate": 9.612092851425405e-06,
"loss": 2.8387,
"step": 199000
},
{
"epoch": 4.09,
"learning_rate": 9.611066642037642e-06,
"loss": 2.8418,
"step": 199500
},
{
"epoch": 4.1,
"learning_rate": 9.610040432649878e-06,
"loss": 2.8321,
"step": 200000
},
{
"epoch": 4.11,
"learning_rate": 9.609014223262115e-06,
"loss": 2.8336,
"step": 200500
},
{
"epoch": 4.12,
"learning_rate": 9.607988013874351e-06,
"loss": 2.8354,
"step": 201000
},
{
"epoch": 4.13,
"learning_rate": 9.606961804486589e-06,
"loss": 2.8329,
"step": 201500
},
{
"epoch": 4.14,
"learning_rate": 9.605935595098824e-06,
"loss": 2.8294,
"step": 202000
},
{
"epoch": 4.15,
"learning_rate": 9.60490938571106e-06,
"loss": 2.8349,
"step": 202500
},
{
"epoch": 4.16,
"learning_rate": 9.603883176323298e-06,
"loss": 2.8309,
"step": 203000
},
{
"epoch": 4.17,
"learning_rate": 9.602856966935533e-06,
"loss": 2.8346,
"step": 203500
},
{
"epoch": 4.18,
"learning_rate": 9.601830757547771e-06,
"loss": 2.8331,
"step": 204000
},
{
"epoch": 4.19,
"learning_rate": 9.600804548160008e-06,
"loss": 2.8313,
"step": 204500
},
{
"epoch": 4.2,
"learning_rate": 9.599778338772244e-06,
"loss": 2.8314,
"step": 205000
},
{
"epoch": 4.21,
"learning_rate": 9.59875212938448e-06,
"loss": 2.8297,
"step": 205500
},
{
"epoch": 4.22,
"learning_rate": 9.597725919996717e-06,
"loss": 2.8261,
"step": 206000
},
{
"epoch": 4.23,
"learning_rate": 9.596699710608953e-06,
"loss": 2.832,
"step": 206500
},
{
"epoch": 4.24,
"learning_rate": 9.59567350122119e-06,
"loss": 2.8299,
"step": 207000
},
{
"epoch": 4.25,
"learning_rate": 9.594647291833426e-06,
"loss": 2.8291,
"step": 207500
},
{
"epoch": 4.26,
"learning_rate": 9.593621082445664e-06,
"loss": 2.8295,
"step": 208000
},
{
"epoch": 4.27,
"learning_rate": 9.5925948730579e-06,
"loss": 2.8302,
"step": 208500
},
{
"epoch": 4.28,
"learning_rate": 9.591568663670135e-06,
"loss": 2.8283,
"step": 209000
},
{
"epoch": 4.29,
"learning_rate": 9.590542454282373e-06,
"loss": 2.8278,
"step": 209500
},
{
"epoch": 4.3,
"learning_rate": 9.589516244894609e-06,
"loss": 2.8233,
"step": 210000
},
{
"epoch": 4.31,
"learning_rate": 9.588490035506846e-06,
"loss": 2.8281,
"step": 210500
},
{
"epoch": 4.32,
"learning_rate": 9.587463826119082e-06,
"loss": 2.8227,
"step": 211000
},
{
"epoch": 4.33,
"learning_rate": 9.58643761673132e-06,
"loss": 2.8232,
"step": 211500
},
{
"epoch": 4.34,
"learning_rate": 9.585411407343555e-06,
"loss": 2.824,
"step": 212000
},
{
"epoch": 4.35,
"learning_rate": 9.58438519795579e-06,
"loss": 2.8263,
"step": 212500
},
{
"epoch": 4.36,
"learning_rate": 9.583358988568028e-06,
"loss": 2.8205,
"step": 213000
},
{
"epoch": 4.37,
"learning_rate": 9.582332779180264e-06,
"loss": 2.8263,
"step": 213500
},
{
"epoch": 4.38,
"learning_rate": 9.581306569792501e-06,
"loss": 2.8231,
"step": 214000
},
{
"epoch": 4.39,
"learning_rate": 9.580280360404737e-06,
"loss": 2.822,
"step": 214500
},
{
"epoch": 4.4,
"learning_rate": 9.579254151016975e-06,
"loss": 2.8233,
"step": 215000
},
{
"epoch": 4.41,
"learning_rate": 9.57822794162921e-06,
"loss": 2.8263,
"step": 215500
},
{
"epoch": 4.42,
"learning_rate": 9.577201732241446e-06,
"loss": 2.8217,
"step": 216000
},
{
"epoch": 4.43,
"learning_rate": 9.576175522853684e-06,
"loss": 2.8211,
"step": 216500
},
{
"epoch": 4.44,
"learning_rate": 9.57514931346592e-06,
"loss": 2.8195,
"step": 217000
},
{
"epoch": 4.45,
"learning_rate": 9.574123104078157e-06,
"loss": 2.8204,
"step": 217500
},
{
"epoch": 4.47,
"learning_rate": 9.573096894690393e-06,
"loss": 2.821,
"step": 218000
},
{
"epoch": 4.48,
"learning_rate": 9.57207068530263e-06,
"loss": 2.8192,
"step": 218500
},
{
"epoch": 4.49,
"learning_rate": 9.571044475914868e-06,
"loss": 2.8166,
"step": 219000
},
{
"epoch": 4.5,
"learning_rate": 9.570018266527102e-06,
"loss": 2.8207,
"step": 219500
},
{
"epoch": 4.51,
"learning_rate": 9.568992057139339e-06,
"loss": 2.8162,
"step": 220000
},
{
"epoch": 4.52,
"learning_rate": 9.567965847751577e-06,
"loss": 2.8182,
"step": 220500
},
{
"epoch": 4.53,
"learning_rate": 9.566939638363812e-06,
"loss": 2.8196,
"step": 221000
},
{
"epoch": 4.54,
"learning_rate": 9.56591342897605e-06,
"loss": 2.8158,
"step": 221500
},
{
"epoch": 4.55,
"learning_rate": 9.564887219588286e-06,
"loss": 2.8158,
"step": 222000
},
{
"epoch": 4.56,
"learning_rate": 9.563861010200523e-06,
"loss": 2.8188,
"step": 222500
},
{
"epoch": 4.57,
"learning_rate": 9.562834800812759e-06,
"loss": 2.8135,
"step": 223000
},
{
"epoch": 4.58,
"learning_rate": 9.561808591424995e-06,
"loss": 2.8135,
"step": 223500
},
{
"epoch": 4.59,
"learning_rate": 9.560782382037232e-06,
"loss": 2.8191,
"step": 224000
},
{
"epoch": 4.6,
"learning_rate": 9.559756172649468e-06,
"loss": 2.8139,
"step": 224500
},
{
"epoch": 4.61,
"learning_rate": 9.558729963261705e-06,
"loss": 2.8114,
"step": 225000
},
{
"epoch": 4.62,
"learning_rate": 9.557703753873941e-06,
"loss": 2.8131,
"step": 225500
},
{
"epoch": 4.63,
"learning_rate": 9.556677544486178e-06,
"loss": 2.8145,
"step": 226000
},
{
"epoch": 4.64,
"learning_rate": 9.555651335098414e-06,
"loss": 2.8163,
"step": 226500
},
{
"epoch": 4.65,
"learning_rate": 9.55462512571065e-06,
"loss": 2.8148,
"step": 227000
},
{
"epoch": 4.66,
"learning_rate": 9.553598916322887e-06,
"loss": 2.8137,
"step": 227500
},
{
"epoch": 4.67,
"learning_rate": 9.552572706935123e-06,
"loss": 2.8112,
"step": 228000
},
{
"epoch": 4.68,
"learning_rate": 9.55154649754736e-06,
"loss": 2.8099,
"step": 228500
},
{
"epoch": 4.69,
"learning_rate": 9.550520288159596e-06,
"loss": 2.8158,
"step": 229000
},
{
"epoch": 4.7,
"learning_rate": 9.549494078771834e-06,
"loss": 2.8108,
"step": 229500
},
{
"epoch": 4.71,
"learning_rate": 9.54846786938407e-06,
"loss": 2.8081,
"step": 230000
},
{
"epoch": 4.72,
"learning_rate": 9.547441659996305e-06,
"loss": 2.8135,
"step": 230500
},
{
"epoch": 4.73,
"learning_rate": 9.546415450608543e-06,
"loss": 2.807,
"step": 231000
},
{
"epoch": 4.74,
"learning_rate": 9.545389241220779e-06,
"loss": 2.8116,
"step": 231500
},
{
"epoch": 4.75,
"learning_rate": 9.544363031833016e-06,
"loss": 2.8131,
"step": 232000
},
{
"epoch": 4.76,
"learning_rate": 9.543336822445252e-06,
"loss": 2.812,
"step": 232500
},
{
"epoch": 4.77,
"learning_rate": 9.54231061305749e-06,
"loss": 2.8071,
"step": 233000
},
{
"epoch": 4.78,
"learning_rate": 9.541284403669727e-06,
"loss": 2.8086,
"step": 233500
},
{
"epoch": 4.79,
"learning_rate": 9.540258194281961e-06,
"loss": 2.8071,
"step": 234000
},
{
"epoch": 4.8,
"learning_rate": 9.539231984894198e-06,
"loss": 2.8103,
"step": 234500
},
{
"epoch": 4.81,
"learning_rate": 9.538205775506436e-06,
"loss": 2.8102,
"step": 235000
},
{
"epoch": 4.82,
"learning_rate": 9.537179566118672e-06,
"loss": 2.8066,
"step": 235500
},
{
"epoch": 4.83,
"learning_rate": 9.536153356730909e-06,
"loss": 2.8031,
"step": 236000
},
{
"epoch": 4.84,
"learning_rate": 9.535127147343145e-06,
"loss": 2.8044,
"step": 236500
},
{
"epoch": 4.85,
"learning_rate": 9.534100937955382e-06,
"loss": 2.807,
"step": 237000
},
{
"epoch": 4.86,
"learning_rate": 9.533074728567618e-06,
"loss": 2.8078,
"step": 237500
},
{
"epoch": 4.87,
"learning_rate": 9.532048519179854e-06,
"loss": 2.8071,
"step": 238000
},
{
"epoch": 4.88,
"learning_rate": 9.531022309792091e-06,
"loss": 2.8022,
"step": 238500
},
{
"epoch": 4.9,
"learning_rate": 9.529996100404327e-06,
"loss": 2.8018,
"step": 239000
},
{
"epoch": 4.91,
"learning_rate": 9.528969891016564e-06,
"loss": 2.802,
"step": 239500
},
{
"epoch": 4.92,
"learning_rate": 9.5279436816288e-06,
"loss": 2.8051,
"step": 240000
},
{
"epoch": 4.93,
"learning_rate": 9.526917472241038e-06,
"loss": 2.8018,
"step": 240500
},
{
"epoch": 4.94,
"learning_rate": 9.525891262853273e-06,
"loss": 2.8027,
"step": 241000
},
{
"epoch": 4.95,
"learning_rate": 9.52486505346551e-06,
"loss": 2.8044,
"step": 241500
},
{
"epoch": 4.96,
"learning_rate": 9.523838844077747e-06,
"loss": 2.798,
"step": 242000
},
{
"epoch": 4.97,
"learning_rate": 9.522812634689982e-06,
"loss": 2.8011,
"step": 242500
},
{
"epoch": 4.98,
"learning_rate": 9.52178642530222e-06,
"loss": 2.7999,
"step": 243000
},
{
"epoch": 4.99,
"learning_rate": 9.520760215914456e-06,
"loss": 2.7978,
"step": 243500
},
{
"epoch": 5.0,
"learning_rate": 9.519734006526693e-06,
"loss": 2.8006,
"step": 244000
},
{
"epoch": 5.01,
"learning_rate": 9.518707797138929e-06,
"loss": 2.8,
"step": 244500
},
{
"epoch": 5.02,
"learning_rate": 9.517681587751165e-06,
"loss": 2.8012,
"step": 245000
},
{
"epoch": 5.03,
"learning_rate": 9.516655378363402e-06,
"loss": 2.8032,
"step": 245500
},
{
"epoch": 5.04,
"learning_rate": 9.515629168975638e-06,
"loss": 2.7936,
"step": 246000
},
{
"epoch": 5.05,
"learning_rate": 9.514602959587875e-06,
"loss": 2.7988,
"step": 246500
},
{
"epoch": 5.06,
"learning_rate": 9.513576750200111e-06,
"loss": 2.7989,
"step": 247000
},
{
"epoch": 5.07,
"learning_rate": 9.512550540812349e-06,
"loss": 2.7979,
"step": 247500
},
{
"epoch": 5.08,
"learning_rate": 9.511524331424584e-06,
"loss": 2.7971,
"step": 248000
},
{
"epoch": 5.09,
"learning_rate": 9.51049812203682e-06,
"loss": 2.7919,
"step": 248500
},
{
"epoch": 5.1,
"learning_rate": 9.509471912649058e-06,
"loss": 2.7917,
"step": 249000
},
{
"epoch": 5.11,
"learning_rate": 9.508445703261295e-06,
"loss": 2.7963,
"step": 249500
},
{
"epoch": 5.12,
"learning_rate": 9.50741949387353e-06,
"loss": 2.7963,
"step": 250000
},
{
"epoch": 5.13,
"learning_rate": 9.506393284485768e-06,
"loss": 2.7977,
"step": 250500
},
{
"epoch": 5.14,
"learning_rate": 9.505367075098004e-06,
"loss": 2.8002,
"step": 251000
},
{
"epoch": 5.15,
"learning_rate": 9.50434086571024e-06,
"loss": 2.7953,
"step": 251500
},
{
"epoch": 5.16,
"learning_rate": 9.503314656322477e-06,
"loss": 2.7935,
"step": 252000
},
{
"epoch": 5.17,
"learning_rate": 9.502288446934713e-06,
"loss": 2.7907,
"step": 252500
},
{
"epoch": 5.18,
"learning_rate": 9.50126223754695e-06,
"loss": 2.7983,
"step": 253000
},
{
"epoch": 5.19,
"learning_rate": 9.500236028159186e-06,
"loss": 2.7909,
"step": 253500
},
{
"epoch": 5.2,
"learning_rate": 9.499209818771424e-06,
"loss": 2.7891,
"step": 254000
},
{
"epoch": 5.21,
"learning_rate": 9.49818360938366e-06,
"loss": 2.7948,
"step": 254500
},
{
"epoch": 5.22,
"learning_rate": 9.497157399995895e-06,
"loss": 2.7907,
"step": 255000
},
{
"epoch": 5.23,
"learning_rate": 9.496131190608133e-06,
"loss": 2.7913,
"step": 255500
},
{
"epoch": 5.24,
"learning_rate": 9.495104981220368e-06,
"loss": 2.7893,
"step": 256000
},
{
"epoch": 5.25,
"learning_rate": 9.494078771832606e-06,
"loss": 2.7911,
"step": 256500
},
{
"epoch": 5.26,
"learning_rate": 9.493052562444842e-06,
"loss": 2.7892,
"step": 257000
},
{
"epoch": 5.27,
"learning_rate": 9.492026353057079e-06,
"loss": 2.7898,
"step": 257500
},
{
"epoch": 5.28,
"learning_rate": 9.491000143669315e-06,
"loss": 2.7915,
"step": 258000
},
{
"epoch": 5.29,
"learning_rate": 9.48997393428155e-06,
"loss": 2.7872,
"step": 258500
},
{
"epoch": 5.3,
"learning_rate": 9.488947724893788e-06,
"loss": 2.7873,
"step": 259000
},
{
"epoch": 5.32,
"learning_rate": 9.487921515506024e-06,
"loss": 2.7873,
"step": 259500
},
{
"epoch": 5.33,
"learning_rate": 9.486895306118261e-06,
"loss": 2.7881,
"step": 260000
},
{
"epoch": 5.34,
"learning_rate": 9.485869096730497e-06,
"loss": 2.7869,
"step": 260500
},
{
"epoch": 5.35,
"learning_rate": 9.484842887342735e-06,
"loss": 2.7879,
"step": 261000
},
{
"epoch": 5.36,
"learning_rate": 9.483816677954972e-06,
"loss": 2.7893,
"step": 261500
},
{
"epoch": 5.37,
"learning_rate": 9.482790468567206e-06,
"loss": 2.7902,
"step": 262000
},
{
"epoch": 5.38,
"learning_rate": 9.481764259179444e-06,
"loss": 2.7896,
"step": 262500
},
{
"epoch": 5.39,
"learning_rate": 9.48073804979168e-06,
"loss": 2.788,
"step": 263000
},
{
"epoch": 5.4,
"learning_rate": 9.479711840403917e-06,
"loss": 2.7854,
"step": 263500
},
{
"epoch": 5.41,
"learning_rate": 9.478685631016154e-06,
"loss": 2.7837,
"step": 264000
},
{
"epoch": 5.42,
"learning_rate": 9.47765942162839e-06,
"loss": 2.7901,
"step": 264500
},
{
"epoch": 5.43,
"learning_rate": 9.476633212240627e-06,
"loss": 2.7873,
"step": 265000
},
{
"epoch": 5.44,
"learning_rate": 9.475607002852863e-06,
"loss": 2.784,
"step": 265500
},
{
"epoch": 5.45,
"learning_rate": 9.474580793465099e-06,
"loss": 2.7852,
"step": 266000
},
{
"epoch": 5.46,
"learning_rate": 9.473554584077336e-06,
"loss": 2.7831,
"step": 266500
},
{
"epoch": 5.47,
"learning_rate": 9.472528374689572e-06,
"loss": 2.7852,
"step": 267000
},
{
"epoch": 5.48,
"learning_rate": 9.47150216530181e-06,
"loss": 2.7835,
"step": 267500
},
{
"epoch": 5.49,
"learning_rate": 9.470475955914045e-06,
"loss": 2.7816,
"step": 268000
},
{
"epoch": 5.5,
"learning_rate": 9.469449746526283e-06,
"loss": 2.7851,
"step": 268500
},
{
"epoch": 5.51,
"learning_rate": 9.468423537138519e-06,
"loss": 2.7827,
"step": 269000
},
{
"epoch": 5.52,
"learning_rate": 9.467397327750754e-06,
"loss": 2.7839,
"step": 269500
},
{
"epoch": 5.53,
"learning_rate": 9.466371118362992e-06,
"loss": 2.7864,
"step": 270000
},
{
"epoch": 5.54,
"learning_rate": 9.465344908975228e-06,
"loss": 2.7817,
"step": 270500
},
{
"epoch": 5.55,
"learning_rate": 9.464318699587465e-06,
"loss": 2.7788,
"step": 271000
},
{
"epoch": 5.56,
"learning_rate": 9.463292490199701e-06,
"loss": 2.7834,
"step": 271500
},
{
"epoch": 5.57,
"learning_rate": 9.462266280811938e-06,
"loss": 2.7801,
"step": 272000
},
{
"epoch": 5.58,
"learning_rate": 9.461240071424174e-06,
"loss": 2.7796,
"step": 272500
},
{
"epoch": 5.59,
"learning_rate": 9.46021386203641e-06,
"loss": 2.7804,
"step": 273000
},
{
"epoch": 5.6,
"learning_rate": 9.459187652648647e-06,
"loss": 2.7774,
"step": 273500
},
{
"epoch": 5.61,
"learning_rate": 9.458161443260883e-06,
"loss": 2.7787,
"step": 274000
},
{
"epoch": 5.62,
"learning_rate": 9.45713523387312e-06,
"loss": 2.7761,
"step": 274500
},
{
"epoch": 5.63,
"learning_rate": 9.456109024485356e-06,
"loss": 2.777,
"step": 275000
},
{
"epoch": 5.64,
"learning_rate": 9.455082815097594e-06,
"loss": 2.7749,
"step": 275500
},
{
"epoch": 5.65,
"learning_rate": 9.45405660570983e-06,
"loss": 2.7753,
"step": 276000
},
{
"epoch": 5.66,
"learning_rate": 9.453030396322065e-06,
"loss": 2.783,
"step": 276500
},
{
"epoch": 5.67,
"learning_rate": 9.452004186934303e-06,
"loss": 2.7779,
"step": 277000
},
{
"epoch": 5.68,
"learning_rate": 9.450977977546539e-06,
"loss": 2.775,
"step": 277500
},
{
"epoch": 5.69,
"learning_rate": 9.449951768158776e-06,
"loss": 2.7764,
"step": 278000
},
{
"epoch": 5.7,
"learning_rate": 9.448925558771013e-06,
"loss": 2.778,
"step": 278500
},
{
"epoch": 5.71,
"learning_rate": 9.44789934938325e-06,
"loss": 2.773,
"step": 279000
},
{
"epoch": 5.72,
"learning_rate": 9.446873139995485e-06,
"loss": 2.768,
"step": 279500
},
{
"epoch": 5.74,
"learning_rate": 9.445846930607722e-06,
"loss": 2.7751,
"step": 280000
},
{
"epoch": 5.75,
"learning_rate": 9.444820721219958e-06,
"loss": 2.7716,
"step": 280500
},
{
"epoch": 5.76,
"learning_rate": 9.443794511832196e-06,
"loss": 2.7748,
"step": 281000
},
{
"epoch": 5.77,
"learning_rate": 9.442768302444431e-06,
"loss": 2.7738,
"step": 281500
},
{
"epoch": 5.78,
"learning_rate": 9.441742093056669e-06,
"loss": 2.7752,
"step": 282000
},
{
"epoch": 5.79,
"learning_rate": 9.440715883668905e-06,
"loss": 2.7768,
"step": 282500
},
{
"epoch": 5.8,
"learning_rate": 9.43968967428114e-06,
"loss": 2.7739,
"step": 283000
},
{
"epoch": 5.81,
"learning_rate": 9.438663464893378e-06,
"loss": 2.7728,
"step": 283500
},
{
"epoch": 5.82,
"learning_rate": 9.437637255505614e-06,
"loss": 2.7727,
"step": 284000
},
{
"epoch": 5.83,
"learning_rate": 9.436611046117851e-06,
"loss": 2.7743,
"step": 284500
},
{
"epoch": 5.84,
"learning_rate": 9.435584836730087e-06,
"loss": 2.7726,
"step": 285000
},
{
"epoch": 5.85,
"learning_rate": 9.434558627342324e-06,
"loss": 2.7719,
"step": 285500
},
{
"epoch": 5.86,
"learning_rate": 9.43353241795456e-06,
"loss": 2.7698,
"step": 286000
},
{
"epoch": 5.87,
"learning_rate": 9.432506208566796e-06,
"loss": 2.7705,
"step": 286500
},
{
"epoch": 5.88,
"learning_rate": 9.431479999179033e-06,
"loss": 2.7705,
"step": 287000
},
{
"epoch": 5.89,
"learning_rate": 9.430453789791269e-06,
"loss": 2.7706,
"step": 287500
},
{
"epoch": 5.9,
"learning_rate": 9.429427580403507e-06,
"loss": 2.7702,
"step": 288000
},
{
"epoch": 5.91,
"learning_rate": 9.428401371015742e-06,
"loss": 2.7664,
"step": 288500
},
{
"epoch": 5.92,
"learning_rate": 9.42737516162798e-06,
"loss": 2.7691,
"step": 289000
},
{
"epoch": 5.93,
"learning_rate": 9.426348952240216e-06,
"loss": 2.771,
"step": 289500
},
{
"epoch": 5.94,
"learning_rate": 9.425322742852451e-06,
"loss": 2.7675,
"step": 290000
},
{
"epoch": 5.95,
"learning_rate": 9.424296533464689e-06,
"loss": 2.7711,
"step": 290500
},
{
"epoch": 5.96,
"learning_rate": 9.423270324076925e-06,
"loss": 2.768,
"step": 291000
},
{
"epoch": 5.97,
"learning_rate": 9.422244114689162e-06,
"loss": 2.7704,
"step": 291500
},
{
"epoch": 5.98,
"learning_rate": 9.421217905301398e-06,
"loss": 2.7654,
"step": 292000
},
{
"epoch": 5.99,
"learning_rate": 9.420191695913635e-06,
"loss": 2.7697,
"step": 292500
},
{
"epoch": 6.0,
"learning_rate": 9.419165486525873e-06,
"loss": 2.7659,
"step": 293000
},
{
"epoch": 6.01,
"learning_rate": 9.418139277138107e-06,
"loss": 2.7637,
"step": 293500
},
{
"epoch": 6.02,
"learning_rate": 9.417113067750344e-06,
"loss": 2.7625,
"step": 294000
},
{
"epoch": 6.03,
"learning_rate": 9.416086858362582e-06,
"loss": 2.7656,
"step": 294500
},
{
"epoch": 6.04,
"learning_rate": 9.415060648974817e-06,
"loss": 2.7637,
"step": 295000
},
{
"epoch": 6.05,
"learning_rate": 9.414034439587055e-06,
"loss": 2.7661,
"step": 295500
},
{
"epoch": 6.06,
"learning_rate": 9.41300823019929e-06,
"loss": 2.7691,
"step": 296000
},
{
"epoch": 6.07,
"learning_rate": 9.411982020811528e-06,
"loss": 2.7639,
"step": 296500
},
{
"epoch": 6.08,
"learning_rate": 9.410955811423764e-06,
"loss": 2.7621,
"step": 297000
},
{
"epoch": 6.09,
"learning_rate": 9.409929602036e-06,
"loss": 2.7663,
"step": 297500
},
{
"epoch": 6.1,
"learning_rate": 9.408903392648237e-06,
"loss": 2.7646,
"step": 298000
},
{
"epoch": 6.11,
"learning_rate": 9.407877183260473e-06,
"loss": 2.7601,
"step": 298500
},
{
"epoch": 6.12,
"learning_rate": 9.40685097387271e-06,
"loss": 2.762,
"step": 299000
},
{
"epoch": 6.13,
"learning_rate": 9.405824764484946e-06,
"loss": 2.7572,
"step": 299500
},
{
"epoch": 6.14,
"learning_rate": 9.404798555097184e-06,
"loss": 2.7649,
"step": 300000
},
{
"epoch": 6.15,
"learning_rate": 9.40377234570942e-06,
"loss": 2.7647,
"step": 300500
},
{
"epoch": 6.17,
"learning_rate": 9.402746136321655e-06,
"loss": 2.7621,
"step": 301000
},
{
"epoch": 6.18,
"learning_rate": 9.401719926933893e-06,
"loss": 2.7649,
"step": 301500
},
{
"epoch": 6.19,
"learning_rate": 9.400693717546128e-06,
"loss": 2.7633,
"step": 302000
},
{
"epoch": 6.2,
"learning_rate": 9.399667508158366e-06,
"loss": 2.7582,
"step": 302500
},
{
"epoch": 6.21,
"learning_rate": 9.398641298770602e-06,
"loss": 2.7581,
"step": 303000
},
{
"epoch": 6.22,
"learning_rate": 9.397615089382839e-06,
"loss": 2.7591,
"step": 303500
},
{
"epoch": 6.23,
"learning_rate": 9.396588879995075e-06,
"loss": 2.7594,
"step": 304000
},
{
"epoch": 6.24,
"learning_rate": 9.39556267060731e-06,
"loss": 2.7604,
"step": 304500
},
{
"epoch": 6.25,
"learning_rate": 9.394536461219548e-06,
"loss": 2.7571,
"step": 305000
},
{
"epoch": 6.26,
"learning_rate": 9.393510251831784e-06,
"loss": 2.7599,
"step": 305500
},
{
"epoch": 6.27,
"learning_rate": 9.392484042444021e-06,
"loss": 2.7591,
"step": 306000
},
{
"epoch": 6.28,
"learning_rate": 9.391457833056257e-06,
"loss": 2.7616,
"step": 306500
},
{
"epoch": 6.29,
"learning_rate": 9.390431623668494e-06,
"loss": 2.7599,
"step": 307000
},
{
"epoch": 6.3,
"learning_rate": 9.389405414280732e-06,
"loss": 2.7579,
"step": 307500
},
{
"epoch": 6.31,
"learning_rate": 9.388379204892966e-06,
"loss": 2.7595,
"step": 308000
},
{
"epoch": 6.32,
"learning_rate": 9.387352995505203e-06,
"loss": 2.7563,
"step": 308500
},
{
"epoch": 6.33,
"learning_rate": 9.386326786117441e-06,
"loss": 2.7563,
"step": 309000
},
{
"epoch": 6.34,
"learning_rate": 9.385300576729677e-06,
"loss": 2.7562,
"step": 309500
},
{
"epoch": 6.35,
"learning_rate": 9.384274367341914e-06,
"loss": 2.7558,
"step": 310000
},
{
"epoch": 6.36,
"learning_rate": 9.38324815795415e-06,
"loss": 2.76,
"step": 310500
},
{
"epoch": 6.37,
"learning_rate": 9.382221948566387e-06,
"loss": 2.7617,
"step": 311000
},
{
"epoch": 6.38,
"learning_rate": 9.381195739178623e-06,
"loss": 2.7582,
"step": 311500
},
{
"epoch": 6.39,
"learning_rate": 9.380169529790859e-06,
"loss": 2.7576,
"step": 312000
},
{
"epoch": 6.4,
"learning_rate": 9.379143320403096e-06,
"loss": 2.7561,
"step": 312500
},
{
"epoch": 6.41,
"learning_rate": 9.378117111015332e-06,
"loss": 2.7577,
"step": 313000
},
{
"epoch": 6.42,
"learning_rate": 9.37709090162757e-06,
"loss": 2.7545,
"step": 313500
},
{
"epoch": 6.43,
"learning_rate": 9.376064692239805e-06,
"loss": 2.7554,
"step": 314000
},
{
"epoch": 6.44,
"learning_rate": 9.375038482852043e-06,
"loss": 2.7469,
"step": 314500
},
{
"epoch": 6.45,
"learning_rate": 9.374012273464279e-06,
"loss": 2.7508,
"step": 315000
},
{
"epoch": 6.46,
"learning_rate": 9.372986064076514e-06,
"loss": 2.7541,
"step": 315500
},
{
"epoch": 6.47,
"learning_rate": 9.371959854688752e-06,
"loss": 2.7533,
"step": 316000
},
{
"epoch": 6.48,
"learning_rate": 9.370933645300988e-06,
"loss": 2.7537,
"step": 316500
},
{
"epoch": 6.49,
"learning_rate": 9.369907435913225e-06,
"loss": 2.7524,
"step": 317000
},
{
"epoch": 6.5,
"learning_rate": 9.36888122652546e-06,
"loss": 2.7518,
"step": 317500
},
{
"epoch": 6.51,
"learning_rate": 9.367855017137698e-06,
"loss": 2.7522,
"step": 318000
},
{
"epoch": 6.52,
"learning_rate": 9.366828807749934e-06,
"loss": 2.754,
"step": 318500
},
{
"epoch": 6.53,
"learning_rate": 9.36580259836217e-06,
"loss": 2.7518,
"step": 319000
},
{
"epoch": 6.54,
"learning_rate": 9.364776388974407e-06,
"loss": 2.7521,
"step": 319500
},
{
"epoch": 6.55,
"learning_rate": 9.363750179586643e-06,
"loss": 2.7543,
"step": 320000
},
{
"epoch": 6.56,
"learning_rate": 9.36272397019888e-06,
"loss": 2.7528,
"step": 320500
},
{
"epoch": 6.57,
"learning_rate": 9.361697760811116e-06,
"loss": 2.7513,
"step": 321000
},
{
"epoch": 6.59,
"learning_rate": 9.360671551423354e-06,
"loss": 2.7519,
"step": 321500
},
{
"epoch": 6.6,
"learning_rate": 9.35964534203559e-06,
"loss": 2.7542,
"step": 322000
},
{
"epoch": 6.61,
"learning_rate": 9.358619132647825e-06,
"loss": 2.748,
"step": 322500
},
{
"epoch": 6.62,
"learning_rate": 9.357592923260063e-06,
"loss": 2.7514,
"step": 323000
},
{
"epoch": 6.63,
"learning_rate": 9.3565667138723e-06,
"loss": 2.7496,
"step": 323500
},
{
"epoch": 6.64,
"learning_rate": 9.355540504484536e-06,
"loss": 2.7503,
"step": 324000
},
{
"epoch": 6.65,
"learning_rate": 9.354514295096773e-06,
"loss": 2.7449,
"step": 324500
},
{
"epoch": 6.66,
"learning_rate": 9.353488085709009e-06,
"loss": 2.7532,
"step": 325000
},
{
"epoch": 6.67,
"learning_rate": 9.352461876321245e-06,
"loss": 2.7502,
"step": 325500
},
{
"epoch": 6.68,
"learning_rate": 9.351435666933482e-06,
"loss": 2.7529,
"step": 326000
},
{
"epoch": 6.69,
"learning_rate": 9.350409457545718e-06,
"loss": 2.7507,
"step": 326500
},
{
"epoch": 6.7,
"learning_rate": 9.349383248157956e-06,
"loss": 2.7461,
"step": 327000
},
{
"epoch": 6.71,
"learning_rate": 9.348357038770191e-06,
"loss": 2.7428,
"step": 327500
},
{
"epoch": 6.72,
"learning_rate": 9.347330829382429e-06,
"loss": 2.7509,
"step": 328000
},
{
"epoch": 6.73,
"learning_rate": 9.346304619994665e-06,
"loss": 2.7483,
"step": 328500
},
{
"epoch": 6.74,
"learning_rate": 9.3452784106069e-06,
"loss": 2.7466,
"step": 329000
},
{
"epoch": 6.75,
"learning_rate": 9.344252201219138e-06,
"loss": 2.749,
"step": 329500
},
{
"epoch": 6.76,
"learning_rate": 9.343225991831374e-06,
"loss": 2.7503,
"step": 330000
},
{
"epoch": 6.77,
"learning_rate": 9.342199782443611e-06,
"loss": 2.7483,
"step": 330500
},
{
"epoch": 6.78,
"learning_rate": 9.341173573055847e-06,
"loss": 2.7511,
"step": 331000
},
{
"epoch": 6.79,
"learning_rate": 9.340147363668084e-06,
"loss": 2.7464,
"step": 331500
},
{
"epoch": 6.8,
"learning_rate": 9.33912115428032e-06,
"loss": 2.7473,
"step": 332000
},
{
"epoch": 6.81,
"learning_rate": 9.338094944892556e-06,
"loss": 2.744,
"step": 332500
},
{
"epoch": 6.82,
"learning_rate": 9.337068735504793e-06,
"loss": 2.7431,
"step": 333000
},
{
"epoch": 6.83,
"learning_rate": 9.336042526117029e-06,
"loss": 2.7398,
"step": 333500
},
{
"epoch": 6.84,
"learning_rate": 9.335016316729266e-06,
"loss": 2.7453,
"step": 334000
},
{
"epoch": 6.85,
"learning_rate": 9.333990107341502e-06,
"loss": 2.7448,
"step": 334500
},
{
"epoch": 6.86,
"learning_rate": 9.33296389795374e-06,
"loss": 2.746,
"step": 335000
},
{
"epoch": 6.87,
"learning_rate": 9.331937688565975e-06,
"loss": 2.7451,
"step": 335500
},
{
"epoch": 6.88,
"learning_rate": 9.330911479178211e-06,
"loss": 2.7449,
"step": 336000
},
{
"epoch": 6.89,
"learning_rate": 9.329885269790449e-06,
"loss": 2.7457,
"step": 336500
},
{
"epoch": 6.9,
"learning_rate": 9.328859060402684e-06,
"loss": 2.7447,
"step": 337000
},
{
"epoch": 6.91,
"learning_rate": 9.327832851014922e-06,
"loss": 2.7452,
"step": 337500
},
{
"epoch": 6.92,
"learning_rate": 9.32680664162716e-06,
"loss": 2.741,
"step": 338000
},
{
"epoch": 6.93,
"learning_rate": 9.325780432239395e-06,
"loss": 2.7419,
"step": 338500
},
{
"epoch": 6.94,
"learning_rate": 9.324754222851633e-06,
"loss": 2.7441,
"step": 339000
},
{
"epoch": 6.95,
"learning_rate": 9.323728013463867e-06,
"loss": 2.7414,
"step": 339500
},
{
"epoch": 6.96,
"learning_rate": 9.322701804076104e-06,
"loss": 2.7388,
"step": 340000
},
{
"epoch": 6.97,
"learning_rate": 9.321675594688342e-06,
"loss": 2.7431,
"step": 340500
},
{
"epoch": 6.98,
"learning_rate": 9.320649385300577e-06,
"loss": 2.7414,
"step": 341000
},
{
"epoch": 6.99,
"learning_rate": 9.319623175912815e-06,
"loss": 2.7384,
"step": 341500
},
{
"epoch": 7.0,
"learning_rate": 9.31859696652505e-06,
"loss": 2.7422,
"step": 342000
},
{
"epoch": 7.02,
"learning_rate": 9.317570757137288e-06,
"loss": 2.7393,
"step": 342500
},
{
"epoch": 7.03,
"learning_rate": 9.316544547749524e-06,
"loss": 2.7384,
"step": 343000
},
{
"epoch": 7.04,
"learning_rate": 9.31551833836176e-06,
"loss": 2.7398,
"step": 343500
},
{
"epoch": 7.05,
"learning_rate": 9.314492128973997e-06,
"loss": 2.7365,
"step": 344000
},
{
"epoch": 7.06,
"learning_rate": 9.313465919586233e-06,
"loss": 2.7367,
"step": 344500
},
{
"epoch": 7.07,
"learning_rate": 9.31243971019847e-06,
"loss": 2.7378,
"step": 345000
},
{
"epoch": 7.08,
"learning_rate": 9.311413500810706e-06,
"loss": 2.7366,
"step": 345500
},
{
"epoch": 7.09,
"learning_rate": 9.310387291422943e-06,
"loss": 2.7401,
"step": 346000
},
{
"epoch": 7.1,
"learning_rate": 9.30936108203518e-06,
"loss": 2.7368,
"step": 346500
},
{
"epoch": 7.11,
"learning_rate": 9.308334872647415e-06,
"loss": 2.7368,
"step": 347000
},
{
"epoch": 7.12,
"learning_rate": 9.307308663259652e-06,
"loss": 2.7406,
"step": 347500
},
{
"epoch": 7.13,
"learning_rate": 9.306282453871888e-06,
"loss": 2.7331,
"step": 348000
},
{
"epoch": 7.14,
"learning_rate": 9.305256244484126e-06,
"loss": 2.7437,
"step": 348500
},
{
"epoch": 7.15,
"learning_rate": 9.304230035096361e-06,
"loss": 2.7348,
"step": 349000
},
{
"epoch": 7.16,
"learning_rate": 9.303203825708599e-06,
"loss": 2.7307,
"step": 349500
},
{
"epoch": 7.17,
"learning_rate": 9.302177616320835e-06,
"loss": 2.7397,
"step": 350000
},
{
"epoch": 7.18,
"learning_rate": 9.30115140693307e-06,
"loss": 2.734,
"step": 350500
},
{
"epoch": 7.19,
"learning_rate": 9.300125197545308e-06,
"loss": 2.7328,
"step": 351000
},
{
"epoch": 7.2,
"learning_rate": 9.299098988157544e-06,
"loss": 2.7355,
"step": 351500
},
{
"epoch": 7.21,
"learning_rate": 9.298072778769781e-06,
"loss": 2.7332,
"step": 352000
},
{
"epoch": 7.22,
"learning_rate": 9.297046569382019e-06,
"loss": 2.7342,
"step": 352500
},
{
"epoch": 7.23,
"learning_rate": 9.296020359994254e-06,
"loss": 2.7344,
"step": 353000
},
{
"epoch": 7.24,
"learning_rate": 9.29499415060649e-06,
"loss": 2.7309,
"step": 353500
},
{
"epoch": 7.25,
"learning_rate": 9.293967941218726e-06,
"loss": 2.7359,
"step": 354000
},
{
"epoch": 7.26,
"learning_rate": 9.292941731830963e-06,
"loss": 2.7325,
"step": 354500
},
{
"epoch": 7.27,
"learning_rate": 9.2919155224432e-06,
"loss": 2.7292,
"step": 355000
},
{
"epoch": 7.28,
"learning_rate": 9.290889313055437e-06,
"loss": 2.7334,
"step": 355500
},
{
"epoch": 7.29,
"learning_rate": 9.289863103667674e-06,
"loss": 2.7337,
"step": 356000
},
{
"epoch": 7.3,
"learning_rate": 9.28883689427991e-06,
"loss": 2.7334,
"step": 356500
},
{
"epoch": 7.31,
"learning_rate": 9.287810684892146e-06,
"loss": 2.73,
"step": 357000
},
{
"epoch": 7.32,
"learning_rate": 9.286784475504383e-06,
"loss": 2.7316,
"step": 357500
},
{
"epoch": 7.33,
"learning_rate": 9.285758266116619e-06,
"loss": 2.7342,
"step": 358000
},
{
"epoch": 7.34,
"learning_rate": 9.284732056728856e-06,
"loss": 2.7342,
"step": 358500
},
{
"epoch": 7.35,
"learning_rate": 9.283705847341092e-06,
"loss": 2.7292,
"step": 359000
},
{
"epoch": 7.36,
"learning_rate": 9.28267963795333e-06,
"loss": 2.7327,
"step": 359500
},
{
"epoch": 7.37,
"learning_rate": 9.281653428565565e-06,
"loss": 2.7305,
"step": 360000
},
{
"epoch": 7.38,
"learning_rate": 9.280627219177801e-06,
"loss": 2.735,
"step": 360500
},
{
"epoch": 7.39,
"learning_rate": 9.279601009790038e-06,
"loss": 2.7269,
"step": 361000
},
{
"epoch": 7.4,
"learning_rate": 9.278574800402274e-06,
"loss": 2.7294,
"step": 361500
},
{
"epoch": 7.41,
"learning_rate": 9.277548591014512e-06,
"loss": 2.7309,
"step": 362000
},
{
"epoch": 7.42,
"learning_rate": 9.276522381626747e-06,
"loss": 2.7276,
"step": 362500
},
{
"epoch": 7.44,
"learning_rate": 9.275496172238985e-06,
"loss": 2.732,
"step": 363000
},
{
"epoch": 7.45,
"learning_rate": 9.27446996285122e-06,
"loss": 2.7325,
"step": 363500
},
{
"epoch": 7.46,
"learning_rate": 9.273443753463456e-06,
"loss": 2.7303,
"step": 364000
},
{
"epoch": 7.47,
"learning_rate": 9.272417544075694e-06,
"loss": 2.7283,
"step": 364500
},
{
"epoch": 7.48,
"learning_rate": 9.27139133468793e-06,
"loss": 2.7279,
"step": 365000
},
{
"epoch": 7.49,
"learning_rate": 9.270365125300167e-06,
"loss": 2.7259,
"step": 365500
},
{
"epoch": 7.5,
"learning_rate": 9.269338915912403e-06,
"loss": 2.7293,
"step": 366000
},
{
"epoch": 7.51,
"learning_rate": 9.26831270652464e-06,
"loss": 2.7284,
"step": 366500
},
{
"epoch": 7.52,
"learning_rate": 9.267286497136878e-06,
"loss": 2.7278,
"step": 367000
},
{
"epoch": 7.53,
"learning_rate": 9.266260287749112e-06,
"loss": 2.7282,
"step": 367500
},
{
"epoch": 7.54,
"learning_rate": 9.26523407836135e-06,
"loss": 2.7259,
"step": 368000
},
{
"epoch": 7.55,
"learning_rate": 9.264207868973585e-06,
"loss": 2.7256,
"step": 368500
},
{
"epoch": 7.56,
"learning_rate": 9.263181659585823e-06,
"loss": 2.7286,
"step": 369000
},
{
"epoch": 7.57,
"learning_rate": 9.26215545019806e-06,
"loss": 2.7267,
"step": 369500
},
{
"epoch": 7.58,
"learning_rate": 9.261129240810296e-06,
"loss": 2.7229,
"step": 370000
},
{
"epoch": 7.59,
"learning_rate": 9.260103031422533e-06,
"loss": 2.7297,
"step": 370500
},
{
"epoch": 7.6,
"learning_rate": 9.259076822034769e-06,
"loss": 2.7232,
"step": 371000
},
{
"epoch": 7.61,
"learning_rate": 9.258050612647005e-06,
"loss": 2.7262,
"step": 371500
},
{
"epoch": 7.62,
"learning_rate": 9.257024403259242e-06,
"loss": 2.7236,
"step": 372000
},
{
"epoch": 7.63,
"learning_rate": 9.255998193871478e-06,
"loss": 2.7243,
"step": 372500
},
{
"epoch": 7.64,
"learning_rate": 9.254971984483715e-06,
"loss": 2.7237,
"step": 373000
},
{
"epoch": 7.65,
"learning_rate": 9.253945775095951e-06,
"loss": 2.7213,
"step": 373500
},
{
"epoch": 7.66,
"learning_rate": 9.252919565708189e-06,
"loss": 2.7223,
"step": 374000
},
{
"epoch": 7.67,
"learning_rate": 9.251893356320424e-06,
"loss": 2.7217,
"step": 374500
},
{
"epoch": 7.68,
"learning_rate": 9.25086714693266e-06,
"loss": 2.721,
"step": 375000
},
{
"epoch": 7.69,
"learning_rate": 9.249840937544898e-06,
"loss": 2.7216,
"step": 375500
},
{
"epoch": 7.7,
"learning_rate": 9.248814728157133e-06,
"loss": 2.7181,
"step": 376000
},
{
"epoch": 7.71,
"learning_rate": 9.247788518769371e-06,
"loss": 2.7255,
"step": 376500
},
{
"epoch": 7.72,
"learning_rate": 9.246762309381607e-06,
"loss": 2.7259,
"step": 377000
},
{
"epoch": 7.73,
"learning_rate": 9.245736099993844e-06,
"loss": 2.7233,
"step": 377500
},
{
"epoch": 7.74,
"learning_rate": 9.24470989060608e-06,
"loss": 2.7251,
"step": 378000
},
{
"epoch": 7.75,
"learning_rate": 9.243683681218316e-06,
"loss": 2.723,
"step": 378500
},
{
"epoch": 7.76,
"learning_rate": 9.242657471830553e-06,
"loss": 2.7234,
"step": 379000
},
{
"epoch": 7.77,
"learning_rate": 9.241631262442789e-06,
"loss": 2.724,
"step": 379500
},
{
"epoch": 7.78,
"learning_rate": 9.240605053055026e-06,
"loss": 2.7248,
"step": 380000
},
{
"epoch": 7.79,
"learning_rate": 9.239578843667262e-06,
"loss": 2.7201,
"step": 380500
},
{
"epoch": 7.8,
"learning_rate": 9.2385526342795e-06,
"loss": 2.7204,
"step": 381000
},
{
"epoch": 7.81,
"learning_rate": 9.237526424891735e-06,
"loss": 2.7198,
"step": 381500
},
{
"epoch": 7.82,
"learning_rate": 9.236500215503971e-06,
"loss": 2.7179,
"step": 382000
},
{
"epoch": 7.83,
"learning_rate": 9.235474006116209e-06,
"loss": 2.7219,
"step": 382500
},
{
"epoch": 7.84,
"learning_rate": 9.234447796728444e-06,
"loss": 2.719,
"step": 383000
},
{
"epoch": 7.85,
"learning_rate": 9.233421587340682e-06,
"loss": 2.7202,
"step": 383500
},
{
"epoch": 7.87,
"learning_rate": 9.23239537795292e-06,
"loss": 2.723,
"step": 384000
},
{
"epoch": 7.88,
"learning_rate": 9.231369168565155e-06,
"loss": 2.7223,
"step": 384500
},
{
"epoch": 7.89,
"learning_rate": 9.23034295917739e-06,
"loss": 2.7224,
"step": 385000
},
{
"epoch": 7.9,
"learning_rate": 9.229316749789628e-06,
"loss": 2.7204,
"step": 385500
},
{
"epoch": 7.91,
"learning_rate": 9.228290540401864e-06,
"loss": 2.723,
"step": 386000
},
{
"epoch": 7.92,
"learning_rate": 9.227264331014101e-06,
"loss": 2.7148,
"step": 386500
},
{
"epoch": 7.93,
"learning_rate": 9.226238121626337e-06,
"loss": 2.7189,
"step": 387000
},
{
"epoch": 7.94,
"learning_rate": 9.225211912238575e-06,
"loss": 2.7143,
"step": 387500
},
{
"epoch": 7.95,
"learning_rate": 9.22418570285081e-06,
"loss": 2.7208,
"step": 388000
},
{
"epoch": 7.96,
"learning_rate": 9.223159493463048e-06,
"loss": 2.717,
"step": 388500
},
{
"epoch": 7.97,
"learning_rate": 9.222133284075284e-06,
"loss": 2.7197,
"step": 389000
},
{
"epoch": 7.98,
"learning_rate": 9.22110707468752e-06,
"loss": 2.7161,
"step": 389500
},
{
"epoch": 7.99,
"learning_rate": 9.220080865299757e-06,
"loss": 2.7209,
"step": 390000
},
{
"epoch": 8.0,
"learning_rate": 9.219054655911993e-06,
"loss": 2.7159,
"step": 390500
},
{
"epoch": 8.01,
"learning_rate": 9.21802844652423e-06,
"loss": 2.7175,
"step": 391000
},
{
"epoch": 8.02,
"learning_rate": 9.217002237136466e-06,
"loss": 2.7194,
"step": 391500
},
{
"epoch": 8.03,
"learning_rate": 9.215976027748703e-06,
"loss": 2.7159,
"step": 392000
},
{
"epoch": 8.04,
"learning_rate": 9.214949818360939e-06,
"loss": 2.7138,
"step": 392500
},
{
"epoch": 8.05,
"learning_rate": 9.213923608973175e-06,
"loss": 2.7105,
"step": 393000
},
{
"epoch": 8.06,
"learning_rate": 9.212897399585412e-06,
"loss": 2.7177,
"step": 393500
},
{
"epoch": 8.07,
"learning_rate": 9.211871190197648e-06,
"loss": 2.7133,
"step": 394000
},
{
"epoch": 8.08,
"learning_rate": 9.210844980809886e-06,
"loss": 2.716,
"step": 394500
},
{
"epoch": 8.09,
"learning_rate": 9.209818771422121e-06,
"loss": 2.715,
"step": 395000
},
{
"epoch": 8.1,
"learning_rate": 9.208792562034359e-06,
"loss": 2.7122,
"step": 395500
},
{
"epoch": 8.11,
"learning_rate": 9.207766352646595e-06,
"loss": 2.7116,
"step": 396000
},
{
"epoch": 8.12,
"learning_rate": 9.20674014325883e-06,
"loss": 2.7174,
"step": 396500
},
{
"epoch": 8.13,
"learning_rate": 9.205713933871068e-06,
"loss": 2.7131,
"step": 397000
},
{
"epoch": 8.14,
"learning_rate": 9.204687724483305e-06,
"loss": 2.7089,
"step": 397500
},
{
"epoch": 8.15,
"learning_rate": 9.203661515095541e-06,
"loss": 2.7132,
"step": 398000
},
{
"epoch": 8.16,
"learning_rate": 9.202635305707778e-06,
"loss": 2.7138,
"step": 398500
},
{
"epoch": 8.17,
"learning_rate": 9.201609096320014e-06,
"loss": 2.7161,
"step": 399000
},
{
"epoch": 8.18,
"learning_rate": 9.20058288693225e-06,
"loss": 2.7129,
"step": 399500
},
{
"epoch": 8.19,
"learning_rate": 9.199556677544487e-06,
"loss": 2.7117,
"step": 400000
},
{
"epoch": 8.2,
"learning_rate": 9.198530468156723e-06,
"loss": 2.7087,
"step": 400500
},
{
"epoch": 8.21,
"learning_rate": 9.19750425876896e-06,
"loss": 2.7109,
"step": 401000
},
{
"epoch": 8.22,
"learning_rate": 9.196478049381196e-06,
"loss": 2.7114,
"step": 401500
},
{
"epoch": 8.23,
"learning_rate": 9.195451839993434e-06,
"loss": 2.7146,
"step": 402000
},
{
"epoch": 8.24,
"learning_rate": 9.19442563060567e-06,
"loss": 2.717,
"step": 402500
},
{
"epoch": 8.25,
"learning_rate": 9.193399421217905e-06,
"loss": 2.7106,
"step": 403000
},
{
"epoch": 8.26,
"learning_rate": 9.192373211830143e-06,
"loss": 2.7112,
"step": 403500
},
{
"epoch": 8.27,
"learning_rate": 9.191347002442379e-06,
"loss": 2.7075,
"step": 404000
},
{
"epoch": 8.29,
"learning_rate": 9.190320793054616e-06,
"loss": 2.7094,
"step": 404500
},
{
"epoch": 8.3,
"learning_rate": 9.189294583666852e-06,
"loss": 2.7139,
"step": 405000
},
{
"epoch": 8.31,
"learning_rate": 9.18826837427909e-06,
"loss": 2.7113,
"step": 405500
},
{
"epoch": 8.32,
"learning_rate": 9.187242164891325e-06,
"loss": 2.7114,
"step": 406000
},
{
"epoch": 8.33,
"learning_rate": 9.186215955503561e-06,
"loss": 2.7104,
"step": 406500
},
{
"epoch": 8.34,
"learning_rate": 9.185189746115798e-06,
"loss": 2.7128,
"step": 407000
},
{
"epoch": 8.35,
"learning_rate": 9.184163536728034e-06,
"loss": 2.709,
"step": 407500
},
{
"epoch": 8.36,
"learning_rate": 9.183137327340272e-06,
"loss": 2.708,
"step": 408000
},
{
"epoch": 8.37,
"learning_rate": 9.182111117952507e-06,
"loss": 2.7097,
"step": 408500
},
{
"epoch": 8.38,
"learning_rate": 9.181084908564745e-06,
"loss": 2.7083,
"step": 409000
},
{
"epoch": 8.39,
"learning_rate": 9.18005869917698e-06,
"loss": 2.7126,
"step": 409500
},
{
"epoch": 8.4,
"learning_rate": 9.179032489789216e-06,
"loss": 2.7098,
"step": 410000
},
{
"epoch": 8.41,
"learning_rate": 9.178006280401454e-06,
"loss": 2.7093,
"step": 410500
},
{
"epoch": 8.42,
"learning_rate": 9.17698007101369e-06,
"loss": 2.7075,
"step": 411000
},
{
"epoch": 8.43,
"learning_rate": 9.175953861625927e-06,
"loss": 2.7093,
"step": 411500
},
{
"epoch": 8.44,
"learning_rate": 9.174927652238164e-06,
"loss": 2.709,
"step": 412000
},
{
"epoch": 8.45,
"learning_rate": 9.1739014428504e-06,
"loss": 2.707,
"step": 412500
},
{
"epoch": 8.46,
"learning_rate": 9.172875233462638e-06,
"loss": 2.7031,
"step": 413000
},
{
"epoch": 8.47,
"learning_rate": 9.171849024074872e-06,
"loss": 2.7068,
"step": 413500
},
{
"epoch": 8.48,
"learning_rate": 9.17082281468711e-06,
"loss": 2.7071,
"step": 414000
},
{
"epoch": 8.49,
"learning_rate": 9.169796605299347e-06,
"loss": 2.7021,
"step": 414500
},
{
"epoch": 8.5,
"learning_rate": 9.168770395911582e-06,
"loss": 2.7087,
"step": 415000
},
{
"epoch": 8.51,
"learning_rate": 9.16774418652382e-06,
"loss": 2.7067,
"step": 415500
},
{
"epoch": 8.52,
"learning_rate": 9.166717977136056e-06,
"loss": 2.7069,
"step": 416000
},
{
"epoch": 8.53,
"learning_rate": 9.165691767748293e-06,
"loss": 2.7122,
"step": 416500
},
{
"epoch": 8.54,
"learning_rate": 9.164665558360529e-06,
"loss": 2.7021,
"step": 417000
},
{
"epoch": 8.55,
"learning_rate": 9.163639348972765e-06,
"loss": 2.7031,
"step": 417500
},
{
"epoch": 8.56,
"learning_rate": 9.162613139585002e-06,
"loss": 2.7067,
"step": 418000
},
{
"epoch": 8.57,
"learning_rate": 9.161586930197238e-06,
"loss": 2.6997,
"step": 418500
},
{
"epoch": 8.58,
"learning_rate": 9.160560720809475e-06,
"loss": 2.7047,
"step": 419000
},
{
"epoch": 8.59,
"learning_rate": 9.159534511421711e-06,
"loss": 2.706,
"step": 419500
},
{
"epoch": 8.6,
"learning_rate": 9.158508302033949e-06,
"loss": 2.7051,
"step": 420000
},
{
"epoch": 8.61,
"learning_rate": 9.157482092646184e-06,
"loss": 2.7036,
"step": 420500
},
{
"epoch": 8.62,
"learning_rate": 9.15645588325842e-06,
"loss": 2.7074,
"step": 421000
},
{
"epoch": 8.63,
"learning_rate": 9.155429673870658e-06,
"loss": 2.7063,
"step": 421500
},
{
"epoch": 8.64,
"learning_rate": 9.154403464482893e-06,
"loss": 2.7014,
"step": 422000
},
{
"epoch": 8.65,
"learning_rate": 9.15337725509513e-06,
"loss": 2.7042,
"step": 422500
},
{
"epoch": 8.66,
"learning_rate": 9.152351045707367e-06,
"loss": 2.7033,
"step": 423000
},
{
"epoch": 8.67,
"learning_rate": 9.151324836319604e-06,
"loss": 2.7045,
"step": 423500
},
{
"epoch": 8.68,
"learning_rate": 9.15029862693184e-06,
"loss": 2.6972,
"step": 424000
},
{
"epoch": 8.69,
"learning_rate": 9.149272417544076e-06,
"loss": 2.7037,
"step": 424500
},
{
"epoch": 8.7,
"learning_rate": 9.148246208156313e-06,
"loss": 2.7037,
"step": 425000
},
{
"epoch": 8.72,
"learning_rate": 9.147219998768549e-06,
"loss": 2.7046,
"step": 425500
},
{
"epoch": 8.73,
"learning_rate": 9.146193789380786e-06,
"loss": 2.7001,
"step": 426000
},
{
"epoch": 8.74,
"learning_rate": 9.145167579993024e-06,
"loss": 2.7016,
"step": 426500
},
{
"epoch": 8.75,
"learning_rate": 9.14414137060526e-06,
"loss": 2.7019,
"step": 427000
},
{
"epoch": 8.76,
"learning_rate": 9.143115161217495e-06,
"loss": 2.7028,
"step": 427500
},
{
"epoch": 8.77,
"learning_rate": 9.142088951829731e-06,
"loss": 2.6963,
"step": 428000
},
{
"epoch": 8.78,
"learning_rate": 9.141062742441968e-06,
"loss": 2.7003,
"step": 428500
},
{
"epoch": 8.79,
"learning_rate": 9.140036533054206e-06,
"loss": 2.6998,
"step": 429000
},
{
"epoch": 8.8,
"learning_rate": 9.139010323666442e-06,
"loss": 2.7017,
"step": 429500
},
{
"epoch": 8.81,
"learning_rate": 9.137984114278679e-06,
"loss": 2.6985,
"step": 430000
},
{
"epoch": 8.82,
"learning_rate": 9.136957904890915e-06,
"loss": 2.6999,
"step": 430500
},
{
"epoch": 8.83,
"learning_rate": 9.13593169550315e-06,
"loss": 2.7007,
"step": 431000
},
{
"epoch": 8.84,
"learning_rate": 9.134905486115388e-06,
"loss": 2.6958,
"step": 431500
},
{
"epoch": 8.85,
"learning_rate": 9.133879276727624e-06,
"loss": 2.6986,
"step": 432000
},
{
"epoch": 8.86,
"learning_rate": 9.132853067339861e-06,
"loss": 2.7012,
"step": 432500
},
{
"epoch": 8.87,
"learning_rate": 9.131826857952097e-06,
"loss": 2.6996,
"step": 433000
},
{
"epoch": 8.88,
"learning_rate": 9.130800648564335e-06,
"loss": 2.7007,
"step": 433500
},
{
"epoch": 8.89,
"learning_rate": 9.12977443917657e-06,
"loss": 2.6989,
"step": 434000
},
{
"epoch": 8.9,
"learning_rate": 9.128748229788806e-06,
"loss": 2.6993,
"step": 434500
},
{
"epoch": 8.91,
"learning_rate": 9.127722020401044e-06,
"loss": 2.6963,
"step": 435000
},
{
"epoch": 8.92,
"learning_rate": 9.12669581101328e-06,
"loss": 2.6996,
"step": 435500
},
{
"epoch": 8.93,
"learning_rate": 9.125669601625517e-06,
"loss": 2.6982,
"step": 436000
},
{
"epoch": 8.94,
"learning_rate": 9.124643392237753e-06,
"loss": 2.6993,
"step": 436500
},
{
"epoch": 8.95,
"learning_rate": 9.12361718284999e-06,
"loss": 2.7,
"step": 437000
},
{
"epoch": 8.96,
"learning_rate": 9.122590973462226e-06,
"loss": 2.6976,
"step": 437500
},
{
"epoch": 8.97,
"learning_rate": 9.121564764074462e-06,
"loss": 2.6943,
"step": 438000
},
{
"epoch": 8.98,
"learning_rate": 9.120538554686699e-06,
"loss": 2.6946,
"step": 438500
},
{
"epoch": 8.99,
"learning_rate": 9.119512345298935e-06,
"loss": 2.6979,
"step": 439000
},
{
"epoch": 9.0,
"learning_rate": 9.118486135911172e-06,
"loss": 2.699,
"step": 439500
},
{
"epoch": 9.01,
"learning_rate": 9.117459926523408e-06,
"loss": 2.6898,
"step": 440000
},
{
"epoch": 9.02,
"learning_rate": 9.116433717135645e-06,
"loss": 2.6934,
"step": 440500
},
{
"epoch": 9.03,
"learning_rate": 9.115407507747883e-06,
"loss": 2.696,
"step": 441000
},
{
"epoch": 9.04,
"learning_rate": 9.114381298360117e-06,
"loss": 2.6947,
"step": 441500
},
{
"epoch": 9.05,
"learning_rate": 9.113355088972354e-06,
"loss": 2.6921,
"step": 442000
},
{
"epoch": 9.06,
"learning_rate": 9.11232887958459e-06,
"loss": 2.696,
"step": 442500
},
{
"epoch": 9.07,
"learning_rate": 9.111302670196828e-06,
"loss": 2.6965,
"step": 443000
},
{
"epoch": 9.08,
"learning_rate": 9.110276460809065e-06,
"loss": 2.6922,
"step": 443500
},
{
"epoch": 9.09,
"learning_rate": 9.109250251421301e-06,
"loss": 2.6925,
"step": 444000
},
{
"epoch": 9.1,
"learning_rate": 9.108224042033538e-06,
"loss": 2.6988,
"step": 444500
},
{
"epoch": 9.11,
"learning_rate": 9.107197832645774e-06,
"loss": 2.6901,
"step": 445000
},
{
"epoch": 9.12,
"learning_rate": 9.10617162325801e-06,
"loss": 2.6958,
"step": 445500
},
{
"epoch": 9.14,
"learning_rate": 9.105145413870247e-06,
"loss": 2.6968,
"step": 446000
},
{
"epoch": 9.15,
"learning_rate": 9.104119204482483e-06,
"loss": 2.695,
"step": 446500
},
{
"epoch": 9.16,
"learning_rate": 9.10309299509472e-06,
"loss": 2.6935,
"step": 447000
},
{
"epoch": 9.17,
"learning_rate": 9.102066785706956e-06,
"loss": 2.6943,
"step": 447500
},
{
"epoch": 9.18,
"learning_rate": 9.101040576319194e-06,
"loss": 2.695,
"step": 448000
},
{
"epoch": 9.19,
"learning_rate": 9.10001436693143e-06,
"loss": 2.692,
"step": 448500
},
{
"epoch": 9.2,
"learning_rate": 9.098988157543665e-06,
"loss": 2.6946,
"step": 449000
},
{
"epoch": 9.21,
"learning_rate": 9.097961948155903e-06,
"loss": 2.6885,
"step": 449500
},
{
"epoch": 9.22,
"learning_rate": 9.096935738768139e-06,
"loss": 2.6943,
"step": 450000
},
{
"epoch": 9.23,
"learning_rate": 9.095909529380376e-06,
"loss": 2.6915,
"step": 450500
},
{
"epoch": 9.24,
"learning_rate": 9.094883319992612e-06,
"loss": 2.6902,
"step": 451000
},
{
"epoch": 9.25,
"learning_rate": 9.09385711060485e-06,
"loss": 2.6909,
"step": 451500
},
{
"epoch": 9.26,
"learning_rate": 9.092830901217085e-06,
"loss": 2.6874,
"step": 452000
},
{
"epoch": 9.27,
"learning_rate": 9.09180469182932e-06,
"loss": 2.6916,
"step": 452500
},
{
"epoch": 9.28,
"learning_rate": 9.090778482441558e-06,
"loss": 2.6897,
"step": 453000
},
{
"epoch": 9.29,
"learning_rate": 9.089752273053794e-06,
"loss": 2.6917,
"step": 453500
},
{
"epoch": 9.3,
"learning_rate": 9.088726063666031e-06,
"loss": 2.6946,
"step": 454000
},
{
"epoch": 9.31,
"learning_rate": 9.087699854278267e-06,
"loss": 2.6885,
"step": 454500
},
{
"epoch": 9.32,
"learning_rate": 9.086673644890505e-06,
"loss": 2.691,
"step": 455000
},
{
"epoch": 9.33,
"learning_rate": 9.08564743550274e-06,
"loss": 2.6899,
"step": 455500
},
{
"epoch": 9.34,
"learning_rate": 9.084621226114976e-06,
"loss": 2.695,
"step": 456000
},
{
"epoch": 9.35,
"learning_rate": 9.083595016727214e-06,
"loss": 2.6905,
"step": 456500
},
{
"epoch": 9.36,
"learning_rate": 9.08256880733945e-06,
"loss": 2.6915,
"step": 457000
},
{
"epoch": 9.37,
"learning_rate": 9.081542597951687e-06,
"loss": 2.6951,
"step": 457500
},
{
"epoch": 9.38,
"step": 457931,
"total_flos": 2.801390081280049e+18,
"train_loss": 2.8571379766411313,
"train_runtime": 179999.8715,
"train_samples_per_second": 3254.868,
"train_steps_per_second": 27.124
}
],
"logging_steps": 500,
"max_steps": 4882300,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 2.801390081280049e+18,
"trial_name": null,
"trial_params": null
}