HBERTv1_48_L12_H768_A12 / trainer_state.json
gokuls's picture
End of training
3d6e492
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.8303757230169264,
"eval_steps": 1000000,
"global_step": 223412,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 9.9307,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 1.0000000000000002e-06,
"loss": 9.1941,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 8.8037,
"step": 1500
},
{
"epoch": 0.02,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.3291,
"step": 2000
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 7.8277,
"step": 2500
},
{
"epoch": 0.02,
"learning_rate": 3e-06,
"loss": 7.4316,
"step": 3000
},
{
"epoch": 0.03,
"learning_rate": 3.5e-06,
"loss": 7.1798,
"step": 3500
},
{
"epoch": 0.03,
"learning_rate": 4.000000000000001e-06,
"loss": 7.0415,
"step": 4000
},
{
"epoch": 0.04,
"learning_rate": 4.5e-06,
"loss": 6.9606,
"step": 4500
},
{
"epoch": 0.04,
"learning_rate": 5e-06,
"loss": 6.8942,
"step": 5000
},
{
"epoch": 0.05,
"learning_rate": 5.500000000000001e-06,
"loss": 6.8412,
"step": 5500
},
{
"epoch": 0.05,
"learning_rate": 6e-06,
"loss": 6.7951,
"step": 6000
},
{
"epoch": 0.05,
"learning_rate": 6.5000000000000004e-06,
"loss": 6.7596,
"step": 6500
},
{
"epoch": 0.06,
"learning_rate": 7e-06,
"loss": 6.7325,
"step": 7000
},
{
"epoch": 0.06,
"learning_rate": 7.500000000000001e-06,
"loss": 6.7014,
"step": 7500
},
{
"epoch": 0.07,
"learning_rate": 8.000000000000001e-06,
"loss": 6.6684,
"step": 8000
},
{
"epoch": 0.07,
"learning_rate": 8.5e-06,
"loss": 6.6367,
"step": 8500
},
{
"epoch": 0.07,
"learning_rate": 9e-06,
"loss": 6.6156,
"step": 9000
},
{
"epoch": 0.08,
"learning_rate": 9.5e-06,
"loss": 6.5912,
"step": 9500
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 6.5759,
"step": 10000
},
{
"epoch": 0.09,
"learning_rate": 9.999590022794733e-06,
"loss": 6.5535,
"step": 10500
},
{
"epoch": 0.09,
"learning_rate": 9.999180045589466e-06,
"loss": 6.5264,
"step": 11000
},
{
"epoch": 0.09,
"learning_rate": 9.998770068384198e-06,
"loss": 6.5051,
"step": 11500
},
{
"epoch": 0.1,
"learning_rate": 9.99836009117893e-06,
"loss": 6.4966,
"step": 12000
},
{
"epoch": 0.1,
"learning_rate": 9.997950113973663e-06,
"loss": 6.4762,
"step": 12500
},
{
"epoch": 0.11,
"learning_rate": 9.997540136768397e-06,
"loss": 6.4693,
"step": 13000
},
{
"epoch": 0.11,
"learning_rate": 9.997130159563128e-06,
"loss": 6.4547,
"step": 13500
},
{
"epoch": 0.11,
"learning_rate": 9.996720182357862e-06,
"loss": 6.4464,
"step": 14000
},
{
"epoch": 0.12,
"learning_rate": 9.996310205152595e-06,
"loss": 6.4292,
"step": 14500
},
{
"epoch": 0.12,
"learning_rate": 9.995900227947327e-06,
"loss": 6.4215,
"step": 15000
},
{
"epoch": 0.13,
"learning_rate": 9.99549025074206e-06,
"loss": 6.4099,
"step": 15500
},
{
"epoch": 0.13,
"learning_rate": 9.995080273536792e-06,
"loss": 6.4088,
"step": 16000
},
{
"epoch": 0.14,
"learning_rate": 9.994670296331524e-06,
"loss": 6.3884,
"step": 16500
},
{
"epoch": 0.14,
"learning_rate": 9.994260319126257e-06,
"loss": 6.3826,
"step": 17000
},
{
"epoch": 0.14,
"learning_rate": 9.99385034192099e-06,
"loss": 6.3773,
"step": 17500
},
{
"epoch": 0.15,
"learning_rate": 9.993440364715724e-06,
"loss": 6.3609,
"step": 18000
},
{
"epoch": 0.15,
"learning_rate": 9.993030387510454e-06,
"loss": 6.3544,
"step": 18500
},
{
"epoch": 0.16,
"learning_rate": 9.992620410305188e-06,
"loss": 6.3456,
"step": 19000
},
{
"epoch": 0.16,
"learning_rate": 9.992210433099921e-06,
"loss": 6.3431,
"step": 19500
},
{
"epoch": 0.16,
"learning_rate": 9.991800455894653e-06,
"loss": 6.3307,
"step": 20000
},
{
"epoch": 0.17,
"learning_rate": 9.991390478689386e-06,
"loss": 6.3222,
"step": 20500
},
{
"epoch": 0.17,
"learning_rate": 9.990980501484118e-06,
"loss": 6.3223,
"step": 21000
},
{
"epoch": 0.18,
"learning_rate": 9.99057052427885e-06,
"loss": 6.3062,
"step": 21500
},
{
"epoch": 0.18,
"learning_rate": 9.990160547073583e-06,
"loss": 6.304,
"step": 22000
},
{
"epoch": 0.18,
"learning_rate": 9.989750569868316e-06,
"loss": 6.2998,
"step": 22500
},
{
"epoch": 0.19,
"learning_rate": 9.989340592663048e-06,
"loss": 6.2995,
"step": 23000
},
{
"epoch": 0.19,
"learning_rate": 9.98893061545778e-06,
"loss": 6.2923,
"step": 23500
},
{
"epoch": 0.2,
"learning_rate": 9.988520638252513e-06,
"loss": 6.2868,
"step": 24000
},
{
"epoch": 0.2,
"learning_rate": 9.988110661047247e-06,
"loss": 6.275,
"step": 24500
},
{
"epoch": 0.2,
"learning_rate": 9.987700683841978e-06,
"loss": 6.2762,
"step": 25000
},
{
"epoch": 0.21,
"learning_rate": 9.987290706636712e-06,
"loss": 6.2686,
"step": 25500
},
{
"epoch": 0.21,
"learning_rate": 9.986880729431445e-06,
"loss": 6.2723,
"step": 26000
},
{
"epoch": 0.22,
"learning_rate": 9.986470752226177e-06,
"loss": 6.2577,
"step": 26500
},
{
"epoch": 0.22,
"learning_rate": 9.98606077502091e-06,
"loss": 6.2484,
"step": 27000
},
{
"epoch": 0.23,
"learning_rate": 9.985650797815642e-06,
"loss": 6.2478,
"step": 27500
},
{
"epoch": 0.23,
"learning_rate": 9.985240820610374e-06,
"loss": 6.2531,
"step": 28000
},
{
"epoch": 0.23,
"learning_rate": 9.984830843405109e-06,
"loss": 6.25,
"step": 28500
},
{
"epoch": 0.24,
"learning_rate": 9.98442086619984e-06,
"loss": 6.2382,
"step": 29000
},
{
"epoch": 0.24,
"learning_rate": 9.984010888994574e-06,
"loss": 6.2365,
"step": 29500
},
{
"epoch": 0.25,
"learning_rate": 9.983600911789304e-06,
"loss": 6.2293,
"step": 30000
},
{
"epoch": 0.25,
"learning_rate": 9.983190934584038e-06,
"loss": 6.2299,
"step": 30500
},
{
"epoch": 0.25,
"learning_rate": 9.982780957378771e-06,
"loss": 6.2206,
"step": 31000
},
{
"epoch": 0.26,
"learning_rate": 9.982370980173503e-06,
"loss": 6.224,
"step": 31500
},
{
"epoch": 0.26,
"learning_rate": 9.981961002968236e-06,
"loss": 6.222,
"step": 32000
},
{
"epoch": 0.27,
"learning_rate": 9.981551025762968e-06,
"loss": 6.2179,
"step": 32500
},
{
"epoch": 0.27,
"learning_rate": 9.9811410485577e-06,
"loss": 6.209,
"step": 33000
},
{
"epoch": 0.27,
"learning_rate": 9.980731071352435e-06,
"loss": 6.2013,
"step": 33500
},
{
"epoch": 0.28,
"learning_rate": 9.980321094147166e-06,
"loss": 6.2027,
"step": 34000
},
{
"epoch": 0.28,
"learning_rate": 9.979911116941898e-06,
"loss": 6.2037,
"step": 34500
},
{
"epoch": 0.29,
"learning_rate": 9.979501139736632e-06,
"loss": 6.197,
"step": 35000
},
{
"epoch": 0.29,
"learning_rate": 9.979091162531363e-06,
"loss": 6.2052,
"step": 35500
},
{
"epoch": 0.29,
"learning_rate": 9.978681185326097e-06,
"loss": 6.1891,
"step": 36000
},
{
"epoch": 0.3,
"learning_rate": 9.97827120812083e-06,
"loss": 6.1859,
"step": 36500
},
{
"epoch": 0.3,
"learning_rate": 9.977861230915562e-06,
"loss": 6.1851,
"step": 37000
},
{
"epoch": 0.31,
"learning_rate": 9.977451253710295e-06,
"loss": 6.1883,
"step": 37500
},
{
"epoch": 0.31,
"learning_rate": 9.977041276505027e-06,
"loss": 6.1754,
"step": 38000
},
{
"epoch": 0.32,
"learning_rate": 9.97663129929976e-06,
"loss": 6.1844,
"step": 38500
},
{
"epoch": 0.32,
"learning_rate": 9.976221322094492e-06,
"loss": 6.1753,
"step": 39000
},
{
"epoch": 0.32,
"learning_rate": 9.975811344889224e-06,
"loss": 6.1705,
"step": 39500
},
{
"epoch": 0.33,
"learning_rate": 9.975401367683959e-06,
"loss": 6.1724,
"step": 40000
},
{
"epoch": 0.33,
"learning_rate": 9.97499139047869e-06,
"loss": 6.1694,
"step": 40500
},
{
"epoch": 0.34,
"learning_rate": 9.974581413273423e-06,
"loss": 6.1701,
"step": 41000
},
{
"epoch": 0.34,
"learning_rate": 9.974171436068156e-06,
"loss": 6.1676,
"step": 41500
},
{
"epoch": 0.34,
"learning_rate": 9.973761458862888e-06,
"loss": 6.1675,
"step": 42000
},
{
"epoch": 0.35,
"learning_rate": 9.973351481657621e-06,
"loss": 6.1654,
"step": 42500
},
{
"epoch": 0.35,
"learning_rate": 9.972941504452353e-06,
"loss": 6.1596,
"step": 43000
},
{
"epoch": 0.36,
"learning_rate": 9.972531527247086e-06,
"loss": 6.1586,
"step": 43500
},
{
"epoch": 0.36,
"learning_rate": 9.972121550041818e-06,
"loss": 6.1529,
"step": 44000
},
{
"epoch": 0.36,
"learning_rate": 9.97171157283655e-06,
"loss": 6.1528,
"step": 44500
},
{
"epoch": 0.37,
"learning_rate": 9.971301595631285e-06,
"loss": 6.1494,
"step": 45000
},
{
"epoch": 0.37,
"learning_rate": 9.970891618426016e-06,
"loss": 6.1403,
"step": 45500
},
{
"epoch": 0.38,
"learning_rate": 9.97048164122075e-06,
"loss": 6.1315,
"step": 46000
},
{
"epoch": 0.38,
"learning_rate": 9.970071664015482e-06,
"loss": 6.1282,
"step": 46500
},
{
"epoch": 0.39,
"learning_rate": 9.969661686810213e-06,
"loss": 6.1203,
"step": 47000
},
{
"epoch": 0.39,
"learning_rate": 9.969251709604947e-06,
"loss": 6.1231,
"step": 47500
},
{
"epoch": 0.39,
"learning_rate": 9.96884173239968e-06,
"loss": 6.1079,
"step": 48000
},
{
"epoch": 0.4,
"learning_rate": 9.968431755194412e-06,
"loss": 6.0863,
"step": 48500
},
{
"epoch": 0.4,
"learning_rate": 9.968021777989145e-06,
"loss": 6.0685,
"step": 49000
},
{
"epoch": 0.41,
"learning_rate": 9.967611800783877e-06,
"loss": 6.0634,
"step": 49500
},
{
"epoch": 0.41,
"learning_rate": 9.96720182357861e-06,
"loss": 6.0453,
"step": 50000
},
{
"epoch": 0.41,
"learning_rate": 9.966791846373342e-06,
"loss": 6.0361,
"step": 50500
},
{
"epoch": 0.42,
"learning_rate": 9.966381869168074e-06,
"loss": 6.0238,
"step": 51000
},
{
"epoch": 0.42,
"learning_rate": 9.965971891962809e-06,
"loss": 6.0042,
"step": 51500
},
{
"epoch": 0.43,
"learning_rate": 9.96556191475754e-06,
"loss": 5.9904,
"step": 52000
},
{
"epoch": 0.43,
"learning_rate": 9.965151937552273e-06,
"loss": 5.9857,
"step": 52500
},
{
"epoch": 0.43,
"learning_rate": 9.964741960347006e-06,
"loss": 5.977,
"step": 53000
},
{
"epoch": 0.44,
"learning_rate": 9.964331983141738e-06,
"loss": 5.9645,
"step": 53500
},
{
"epoch": 0.44,
"learning_rate": 9.96392200593647e-06,
"loss": 5.9649,
"step": 54000
},
{
"epoch": 0.45,
"learning_rate": 9.963512028731203e-06,
"loss": 5.9498,
"step": 54500
},
{
"epoch": 0.45,
"learning_rate": 9.963102051525936e-06,
"loss": 5.9466,
"step": 55000
},
{
"epoch": 0.45,
"learning_rate": 9.962692074320668e-06,
"loss": 5.9379,
"step": 55500
},
{
"epoch": 0.46,
"learning_rate": 9.9622820971154e-06,
"loss": 5.9348,
"step": 56000
},
{
"epoch": 0.46,
"learning_rate": 9.961872119910135e-06,
"loss": 5.9269,
"step": 56500
},
{
"epoch": 0.47,
"learning_rate": 9.961462142704866e-06,
"loss": 5.9166,
"step": 57000
},
{
"epoch": 0.47,
"learning_rate": 9.9610521654996e-06,
"loss": 5.9126,
"step": 57500
},
{
"epoch": 0.48,
"learning_rate": 9.960642188294332e-06,
"loss": 5.8988,
"step": 58000
},
{
"epoch": 0.48,
"learning_rate": 9.960232211089065e-06,
"loss": 5.9004,
"step": 58500
},
{
"epoch": 0.48,
"learning_rate": 9.959822233883797e-06,
"loss": 5.8911,
"step": 59000
},
{
"epoch": 0.49,
"learning_rate": 9.95941225667853e-06,
"loss": 5.8821,
"step": 59500
},
{
"epoch": 0.49,
"learning_rate": 9.959002279473262e-06,
"loss": 5.8793,
"step": 60000
},
{
"epoch": 0.5,
"learning_rate": 9.958592302267995e-06,
"loss": 5.8769,
"step": 60500
},
{
"epoch": 0.5,
"learning_rate": 9.958182325062727e-06,
"loss": 5.8678,
"step": 61000
},
{
"epoch": 0.5,
"learning_rate": 9.95777234785746e-06,
"loss": 5.8626,
"step": 61500
},
{
"epoch": 0.51,
"learning_rate": 9.957362370652192e-06,
"loss": 5.858,
"step": 62000
},
{
"epoch": 0.51,
"learning_rate": 9.956952393446924e-06,
"loss": 5.8423,
"step": 62500
},
{
"epoch": 0.52,
"learning_rate": 9.956542416241659e-06,
"loss": 5.8444,
"step": 63000
},
{
"epoch": 0.52,
"learning_rate": 9.95613243903639e-06,
"loss": 5.8345,
"step": 63500
},
{
"epoch": 0.52,
"learning_rate": 9.955722461831123e-06,
"loss": 5.8241,
"step": 64000
},
{
"epoch": 0.53,
"learning_rate": 9.955312484625856e-06,
"loss": 5.8212,
"step": 64500
},
{
"epoch": 0.53,
"learning_rate": 9.954902507420588e-06,
"loss": 5.8165,
"step": 65000
},
{
"epoch": 0.54,
"learning_rate": 9.95449253021532e-06,
"loss": 5.8117,
"step": 65500
},
{
"epoch": 0.54,
"learning_rate": 9.954082553010053e-06,
"loss": 5.8055,
"step": 66000
},
{
"epoch": 0.54,
"learning_rate": 9.953672575804786e-06,
"loss": 5.7916,
"step": 66500
},
{
"epoch": 0.55,
"learning_rate": 9.95326259859952e-06,
"loss": 5.7925,
"step": 67000
},
{
"epoch": 0.55,
"learning_rate": 9.95285262139425e-06,
"loss": 5.78,
"step": 67500
},
{
"epoch": 0.56,
"learning_rate": 9.952442644188985e-06,
"loss": 5.7672,
"step": 68000
},
{
"epoch": 0.56,
"learning_rate": 9.952032666983716e-06,
"loss": 5.7609,
"step": 68500
},
{
"epoch": 0.57,
"learning_rate": 9.95162268977845e-06,
"loss": 5.7548,
"step": 69000
},
{
"epoch": 0.57,
"learning_rate": 9.951212712573182e-06,
"loss": 5.744,
"step": 69500
},
{
"epoch": 0.57,
"learning_rate": 9.950802735367915e-06,
"loss": 5.7386,
"step": 70000
},
{
"epoch": 0.58,
"learning_rate": 9.950392758162647e-06,
"loss": 5.7395,
"step": 70500
},
{
"epoch": 0.58,
"learning_rate": 9.94998278095738e-06,
"loss": 5.7289,
"step": 71000
},
{
"epoch": 0.59,
"learning_rate": 9.949572803752112e-06,
"loss": 5.7175,
"step": 71500
},
{
"epoch": 0.59,
"learning_rate": 9.949162826546844e-06,
"loss": 5.7184,
"step": 72000
},
{
"epoch": 0.59,
"learning_rate": 9.948752849341577e-06,
"loss": 5.7033,
"step": 72500
},
{
"epoch": 0.6,
"learning_rate": 9.94834287213631e-06,
"loss": 5.7021,
"step": 73000
},
{
"epoch": 0.6,
"learning_rate": 9.947932894931044e-06,
"loss": 5.6901,
"step": 73500
},
{
"epoch": 0.61,
"learning_rate": 9.947522917725774e-06,
"loss": 5.6777,
"step": 74000
},
{
"epoch": 0.61,
"learning_rate": 9.947112940520508e-06,
"loss": 5.6673,
"step": 74500
},
{
"epoch": 0.61,
"learning_rate": 9.946702963315241e-06,
"loss": 5.6631,
"step": 75000
},
{
"epoch": 0.62,
"learning_rate": 9.946292986109973e-06,
"loss": 5.656,
"step": 75500
},
{
"epoch": 0.62,
"learning_rate": 9.945883008904706e-06,
"loss": 5.644,
"step": 76000
},
{
"epoch": 0.63,
"learning_rate": 9.945473031699438e-06,
"loss": 5.6291,
"step": 76500
},
{
"epoch": 0.63,
"learning_rate": 9.94506305449417e-06,
"loss": 5.607,
"step": 77000
},
{
"epoch": 0.63,
"learning_rate": 9.944653077288903e-06,
"loss": 5.5867,
"step": 77500
},
{
"epoch": 0.64,
"learning_rate": 9.944243100083636e-06,
"loss": 5.5579,
"step": 78000
},
{
"epoch": 0.64,
"learning_rate": 9.94383312287837e-06,
"loss": 5.5283,
"step": 78500
},
{
"epoch": 0.65,
"learning_rate": 9.9434231456731e-06,
"loss": 5.4993,
"step": 79000
},
{
"epoch": 0.65,
"learning_rate": 9.943013168467835e-06,
"loss": 5.4677,
"step": 79500
},
{
"epoch": 0.66,
"learning_rate": 9.942603191262567e-06,
"loss": 5.4399,
"step": 80000
},
{
"epoch": 0.66,
"learning_rate": 9.9421932140573e-06,
"loss": 5.4073,
"step": 80500
},
{
"epoch": 0.66,
"learning_rate": 9.941783236852032e-06,
"loss": 5.3745,
"step": 81000
},
{
"epoch": 0.67,
"learning_rate": 9.941373259646765e-06,
"loss": 5.3395,
"step": 81500
},
{
"epoch": 0.67,
"learning_rate": 9.940963282441497e-06,
"loss": 5.3141,
"step": 82000
},
{
"epoch": 0.68,
"learning_rate": 9.94055330523623e-06,
"loss": 5.2784,
"step": 82500
},
{
"epoch": 0.68,
"learning_rate": 9.940143328030962e-06,
"loss": 5.2393,
"step": 83000
},
{
"epoch": 0.68,
"learning_rate": 9.939733350825694e-06,
"loss": 5.214,
"step": 83500
},
{
"epoch": 0.69,
"learning_rate": 9.939323373620427e-06,
"loss": 5.1835,
"step": 84000
},
{
"epoch": 0.69,
"learning_rate": 9.93891339641516e-06,
"loss": 5.1434,
"step": 84500
},
{
"epoch": 0.7,
"learning_rate": 9.938503419209894e-06,
"loss": 5.1242,
"step": 85000
},
{
"epoch": 0.7,
"learning_rate": 9.938093442004624e-06,
"loss": 5.0995,
"step": 85500
},
{
"epoch": 0.7,
"learning_rate": 9.937683464799358e-06,
"loss": 5.0657,
"step": 86000
},
{
"epoch": 0.71,
"learning_rate": 9.937273487594091e-06,
"loss": 5.0337,
"step": 86500
},
{
"epoch": 0.71,
"learning_rate": 9.936863510388823e-06,
"loss": 5.0172,
"step": 87000
},
{
"epoch": 0.72,
"learning_rate": 9.936453533183556e-06,
"loss": 4.9943,
"step": 87500
},
{
"epoch": 0.72,
"learning_rate": 9.936043555978288e-06,
"loss": 4.9616,
"step": 88000
},
{
"epoch": 0.73,
"learning_rate": 9.93563357877302e-06,
"loss": 4.9441,
"step": 88500
},
{
"epoch": 0.73,
"learning_rate": 9.935223601567753e-06,
"loss": 4.9234,
"step": 89000
},
{
"epoch": 0.73,
"learning_rate": 9.934813624362486e-06,
"loss": 4.901,
"step": 89500
},
{
"epoch": 0.74,
"learning_rate": 9.93440364715722e-06,
"loss": 4.8758,
"step": 90000
},
{
"epoch": 0.74,
"learning_rate": 9.93399366995195e-06,
"loss": 4.8607,
"step": 90500
},
{
"epoch": 0.75,
"learning_rate": 9.933583692746685e-06,
"loss": 4.8342,
"step": 91000
},
{
"epoch": 0.75,
"learning_rate": 9.933173715541417e-06,
"loss": 4.8142,
"step": 91500
},
{
"epoch": 0.75,
"learning_rate": 9.93276373833615e-06,
"loss": 4.7955,
"step": 92000
},
{
"epoch": 0.76,
"learning_rate": 9.932353761130882e-06,
"loss": 4.7713,
"step": 92500
},
{
"epoch": 0.76,
"learning_rate": 9.931943783925615e-06,
"loss": 4.7573,
"step": 93000
},
{
"epoch": 0.77,
"learning_rate": 9.931533806720347e-06,
"loss": 4.7423,
"step": 93500
},
{
"epoch": 0.77,
"learning_rate": 9.93112382951508e-06,
"loss": 4.7205,
"step": 94000
},
{
"epoch": 0.77,
"learning_rate": 9.930713852309812e-06,
"loss": 4.6955,
"step": 94500
},
{
"epoch": 0.78,
"learning_rate": 9.930303875104546e-06,
"loss": 4.6763,
"step": 95000
},
{
"epoch": 0.78,
"learning_rate": 9.929893897899277e-06,
"loss": 4.6696,
"step": 95500
},
{
"epoch": 0.79,
"learning_rate": 9.92948392069401e-06,
"loss": 4.6482,
"step": 96000
},
{
"epoch": 0.79,
"learning_rate": 9.929073943488743e-06,
"loss": 4.625,
"step": 96500
},
{
"epoch": 0.79,
"learning_rate": 9.928663966283474e-06,
"loss": 4.613,
"step": 97000
},
{
"epoch": 0.8,
"learning_rate": 9.928253989078208e-06,
"loss": 4.5897,
"step": 97500
},
{
"epoch": 0.8,
"learning_rate": 9.927844011872941e-06,
"loss": 4.5762,
"step": 98000
},
{
"epoch": 0.81,
"learning_rate": 9.927434034667673e-06,
"loss": 4.5628,
"step": 98500
},
{
"epoch": 0.81,
"learning_rate": 9.927024057462406e-06,
"loss": 4.5434,
"step": 99000
},
{
"epoch": 0.82,
"learning_rate": 9.926614080257138e-06,
"loss": 4.5264,
"step": 99500
},
{
"epoch": 0.82,
"learning_rate": 9.92620410305187e-06,
"loss": 4.5068,
"step": 100000
},
{
"epoch": 0.82,
"learning_rate": 9.925794125846603e-06,
"loss": 4.4728,
"step": 100500
},
{
"epoch": 0.83,
"learning_rate": 9.925384148641336e-06,
"loss": 4.4319,
"step": 101000
},
{
"epoch": 0.83,
"learning_rate": 9.92497417143607e-06,
"loss": 4.3988,
"step": 101500
},
{
"epoch": 0.84,
"learning_rate": 9.9245641942308e-06,
"loss": 4.3711,
"step": 102000
},
{
"epoch": 0.84,
"learning_rate": 9.924154217025535e-06,
"loss": 4.3419,
"step": 102500
},
{
"epoch": 0.84,
"learning_rate": 9.923744239820267e-06,
"loss": 4.3145,
"step": 103000
},
{
"epoch": 0.85,
"learning_rate": 9.923334262615e-06,
"loss": 4.2825,
"step": 103500
},
{
"epoch": 0.85,
"learning_rate": 9.922924285409732e-06,
"loss": 4.2612,
"step": 104000
},
{
"epoch": 0.86,
"learning_rate": 9.922514308204465e-06,
"loss": 4.2297,
"step": 104500
},
{
"epoch": 0.86,
"learning_rate": 9.922104330999197e-06,
"loss": 4.2028,
"step": 105000
},
{
"epoch": 0.86,
"learning_rate": 9.921694353793931e-06,
"loss": 4.1805,
"step": 105500
},
{
"epoch": 0.87,
"learning_rate": 9.921284376588662e-06,
"loss": 4.168,
"step": 106000
},
{
"epoch": 0.87,
"learning_rate": 9.920874399383396e-06,
"loss": 4.1422,
"step": 106500
},
{
"epoch": 0.88,
"learning_rate": 9.920464422178127e-06,
"loss": 4.1278,
"step": 107000
},
{
"epoch": 0.88,
"learning_rate": 9.920054444972861e-06,
"loss": 4.1073,
"step": 107500
},
{
"epoch": 0.88,
"learning_rate": 9.919644467767593e-06,
"loss": 4.0733,
"step": 108000
},
{
"epoch": 0.89,
"learning_rate": 9.919234490562324e-06,
"loss": 4.0574,
"step": 108500
},
{
"epoch": 0.89,
"learning_rate": 9.918824513357058e-06,
"loss": 4.0422,
"step": 109000
},
{
"epoch": 0.9,
"learning_rate": 9.91841453615179e-06,
"loss": 4.0213,
"step": 109500
},
{
"epoch": 0.9,
"learning_rate": 9.918004558946523e-06,
"loss": 4.0033,
"step": 110000
},
{
"epoch": 0.91,
"learning_rate": 9.917594581741256e-06,
"loss": 3.9806,
"step": 110500
},
{
"epoch": 0.91,
"learning_rate": 9.917184604535988e-06,
"loss": 3.9571,
"step": 111000
},
{
"epoch": 0.91,
"learning_rate": 9.91677462733072e-06,
"loss": 3.9422,
"step": 111500
},
{
"epoch": 0.92,
"learning_rate": 9.916364650125455e-06,
"loss": 3.9273,
"step": 112000
},
{
"epoch": 0.92,
"learning_rate": 9.915954672920186e-06,
"loss": 3.8996,
"step": 112500
},
{
"epoch": 0.93,
"learning_rate": 9.91554469571492e-06,
"loss": 3.8779,
"step": 113000
},
{
"epoch": 0.93,
"learning_rate": 9.915134718509652e-06,
"loss": 3.866,
"step": 113500
},
{
"epoch": 0.93,
"learning_rate": 9.914724741304385e-06,
"loss": 3.8534,
"step": 114000
},
{
"epoch": 0.94,
"learning_rate": 9.914314764099117e-06,
"loss": 3.8263,
"step": 114500
},
{
"epoch": 0.94,
"learning_rate": 9.91390478689385e-06,
"loss": 3.8156,
"step": 115000
},
{
"epoch": 0.95,
"learning_rate": 9.913494809688582e-06,
"loss": 3.7987,
"step": 115500
},
{
"epoch": 0.95,
"learning_rate": 9.913084832483315e-06,
"loss": 3.7958,
"step": 116000
},
{
"epoch": 0.95,
"learning_rate": 9.912674855278047e-06,
"loss": 3.773,
"step": 116500
},
{
"epoch": 0.96,
"learning_rate": 9.912264878072781e-06,
"loss": 3.7562,
"step": 117000
},
{
"epoch": 0.96,
"learning_rate": 9.911854900867512e-06,
"loss": 3.7467,
"step": 117500
},
{
"epoch": 0.97,
"learning_rate": 9.911444923662246e-06,
"loss": 3.7314,
"step": 118000
},
{
"epoch": 0.97,
"learning_rate": 9.911034946456978e-06,
"loss": 3.716,
"step": 118500
},
{
"epoch": 0.97,
"learning_rate": 9.910624969251711e-06,
"loss": 3.7067,
"step": 119000
},
{
"epoch": 0.98,
"learning_rate": 9.910214992046443e-06,
"loss": 3.6922,
"step": 119500
},
{
"epoch": 0.98,
"learning_rate": 9.909805014841176e-06,
"loss": 3.6784,
"step": 120000
},
{
"epoch": 0.99,
"learning_rate": 9.909395037635908e-06,
"loss": 3.6657,
"step": 120500
},
{
"epoch": 0.99,
"learning_rate": 9.90898506043064e-06,
"loss": 3.6592,
"step": 121000
},
{
"epoch": 1.0,
"learning_rate": 9.908575083225373e-06,
"loss": 3.6396,
"step": 121500
},
{
"epoch": 1.0,
"learning_rate": 9.908165106020106e-06,
"loss": 3.6335,
"step": 122000
},
{
"epoch": 1.0,
"learning_rate": 9.907755128814838e-06,
"loss": 3.6178,
"step": 122500
},
{
"epoch": 1.01,
"learning_rate": 9.90734515160957e-06,
"loss": 3.6023,
"step": 123000
},
{
"epoch": 1.01,
"learning_rate": 9.906935174404305e-06,
"loss": 3.5968,
"step": 123500
},
{
"epoch": 1.02,
"learning_rate": 9.906525197199036e-06,
"loss": 3.5778,
"step": 124000
},
{
"epoch": 1.02,
"learning_rate": 9.90611521999377e-06,
"loss": 3.5817,
"step": 124500
},
{
"epoch": 1.02,
"learning_rate": 9.905705242788502e-06,
"loss": 3.5692,
"step": 125000
},
{
"epoch": 1.03,
"learning_rate": 9.905295265583235e-06,
"loss": 3.5516,
"step": 125500
},
{
"epoch": 1.03,
"learning_rate": 9.904885288377967e-06,
"loss": 3.5441,
"step": 126000
},
{
"epoch": 1.04,
"learning_rate": 9.9044753111727e-06,
"loss": 3.5337,
"step": 126500
},
{
"epoch": 1.04,
"learning_rate": 9.904065333967432e-06,
"loss": 3.5248,
"step": 127000
},
{
"epoch": 1.04,
"learning_rate": 9.903655356762164e-06,
"loss": 3.5127,
"step": 127500
},
{
"epoch": 1.05,
"learning_rate": 9.903245379556897e-06,
"loss": 3.5071,
"step": 128000
},
{
"epoch": 1.05,
"learning_rate": 9.902835402351631e-06,
"loss": 3.4899,
"step": 128500
},
{
"epoch": 1.06,
"learning_rate": 9.902425425146362e-06,
"loss": 3.4871,
"step": 129000
},
{
"epoch": 1.06,
"learning_rate": 9.902015447941096e-06,
"loss": 3.4784,
"step": 129500
},
{
"epoch": 1.07,
"learning_rate": 9.901605470735828e-06,
"loss": 3.4718,
"step": 130000
},
{
"epoch": 1.07,
"learning_rate": 9.901195493530561e-06,
"loss": 3.4594,
"step": 130500
},
{
"epoch": 1.07,
"learning_rate": 9.900785516325293e-06,
"loss": 3.4548,
"step": 131000
},
{
"epoch": 1.08,
"learning_rate": 9.900375539120026e-06,
"loss": 3.4507,
"step": 131500
},
{
"epoch": 1.08,
"learning_rate": 9.899965561914758e-06,
"loss": 3.4356,
"step": 132000
},
{
"epoch": 1.09,
"learning_rate": 9.89955558470949e-06,
"loss": 3.4366,
"step": 132500
},
{
"epoch": 1.09,
"learning_rate": 9.899145607504223e-06,
"loss": 3.4249,
"step": 133000
},
{
"epoch": 1.09,
"learning_rate": 9.898735630298956e-06,
"loss": 3.406,
"step": 133500
},
{
"epoch": 1.1,
"learning_rate": 9.898325653093688e-06,
"loss": 3.4147,
"step": 134000
},
{
"epoch": 1.1,
"learning_rate": 9.89791567588842e-06,
"loss": 3.3966,
"step": 134500
},
{
"epoch": 1.11,
"learning_rate": 9.897505698683155e-06,
"loss": 3.3916,
"step": 135000
},
{
"epoch": 1.11,
"learning_rate": 9.897095721477886e-06,
"loss": 3.3856,
"step": 135500
},
{
"epoch": 1.11,
"learning_rate": 9.89668574427262e-06,
"loss": 3.3783,
"step": 136000
},
{
"epoch": 1.12,
"learning_rate": 9.896275767067352e-06,
"loss": 3.3738,
"step": 136500
},
{
"epoch": 1.12,
"learning_rate": 9.895865789862085e-06,
"loss": 3.3661,
"step": 137000
},
{
"epoch": 1.13,
"learning_rate": 9.895455812656817e-06,
"loss": 3.3528,
"step": 137500
},
{
"epoch": 1.13,
"learning_rate": 9.89504583545155e-06,
"loss": 3.3494,
"step": 138000
},
{
"epoch": 1.13,
"learning_rate": 9.894635858246282e-06,
"loss": 3.3437,
"step": 138500
},
{
"epoch": 1.14,
"learning_rate": 9.894225881041014e-06,
"loss": 3.3416,
"step": 139000
},
{
"epoch": 1.14,
"learning_rate": 9.893815903835747e-06,
"loss": 3.3261,
"step": 139500
},
{
"epoch": 1.15,
"learning_rate": 9.893405926630481e-06,
"loss": 3.3271,
"step": 140000
},
{
"epoch": 1.15,
"learning_rate": 9.892995949425212e-06,
"loss": 3.3184,
"step": 140500
},
{
"epoch": 1.16,
"learning_rate": 9.892585972219946e-06,
"loss": 3.3131,
"step": 141000
},
{
"epoch": 1.16,
"learning_rate": 9.892175995014678e-06,
"loss": 3.2927,
"step": 141500
},
{
"epoch": 1.16,
"learning_rate": 9.891766017809411e-06,
"loss": 3.3,
"step": 142000
},
{
"epoch": 1.17,
"learning_rate": 9.891356040604143e-06,
"loss": 3.2922,
"step": 142500
},
{
"epoch": 1.17,
"learning_rate": 9.890946063398876e-06,
"loss": 3.2868,
"step": 143000
},
{
"epoch": 1.18,
"learning_rate": 9.890536086193608e-06,
"loss": 3.2848,
"step": 143500
},
{
"epoch": 1.18,
"learning_rate": 9.890126108988342e-06,
"loss": 3.2759,
"step": 144000
},
{
"epoch": 1.18,
"learning_rate": 9.889716131783073e-06,
"loss": 3.267,
"step": 144500
},
{
"epoch": 1.19,
"learning_rate": 9.889306154577806e-06,
"loss": 3.2611,
"step": 145000
},
{
"epoch": 1.19,
"learning_rate": 9.888896177372538e-06,
"loss": 3.2564,
"step": 145500
},
{
"epoch": 1.2,
"learning_rate": 9.88848620016727e-06,
"loss": 3.255,
"step": 146000
},
{
"epoch": 1.2,
"learning_rate": 9.888076222962005e-06,
"loss": 3.2413,
"step": 146500
},
{
"epoch": 1.2,
"learning_rate": 9.887666245756735e-06,
"loss": 3.239,
"step": 147000
},
{
"epoch": 1.21,
"learning_rate": 9.88725626855147e-06,
"loss": 3.2289,
"step": 147500
},
{
"epoch": 1.21,
"learning_rate": 9.886846291346202e-06,
"loss": 3.2311,
"step": 148000
},
{
"epoch": 1.22,
"learning_rate": 9.886436314140935e-06,
"loss": 3.2231,
"step": 148500
},
{
"epoch": 1.22,
"learning_rate": 9.886026336935667e-06,
"loss": 3.2168,
"step": 149000
},
{
"epoch": 1.22,
"learning_rate": 9.8856163597304e-06,
"loss": 3.2104,
"step": 149500
},
{
"epoch": 1.23,
"learning_rate": 9.885206382525132e-06,
"loss": 3.2044,
"step": 150000
},
{
"epoch": 1.23,
"learning_rate": 9.884796405319866e-06,
"loss": 3.1964,
"step": 150500
},
{
"epoch": 1.24,
"learning_rate": 9.884386428114597e-06,
"loss": 3.1875,
"step": 151000
},
{
"epoch": 1.24,
"learning_rate": 9.883976450909331e-06,
"loss": 3.1962,
"step": 151500
},
{
"epoch": 1.25,
"learning_rate": 9.883566473704063e-06,
"loss": 3.1807,
"step": 152000
},
{
"epoch": 1.25,
"learning_rate": 9.883156496498796e-06,
"loss": 3.1827,
"step": 152500
},
{
"epoch": 1.25,
"learning_rate": 9.882746519293528e-06,
"loss": 3.1828,
"step": 153000
},
{
"epoch": 1.26,
"learning_rate": 9.882336542088261e-06,
"loss": 3.166,
"step": 153500
},
{
"epoch": 1.26,
"learning_rate": 9.881926564882993e-06,
"loss": 3.1694,
"step": 154000
},
{
"epoch": 1.27,
"learning_rate": 9.881516587677726e-06,
"loss": 3.1611,
"step": 154500
},
{
"epoch": 1.27,
"learning_rate": 9.881106610472458e-06,
"loss": 3.1505,
"step": 155000
},
{
"epoch": 1.27,
"learning_rate": 9.880696633267192e-06,
"loss": 3.1515,
"step": 155500
},
{
"epoch": 1.28,
"learning_rate": 9.880286656061923e-06,
"loss": 3.1482,
"step": 156000
},
{
"epoch": 1.28,
"learning_rate": 9.879876678856657e-06,
"loss": 3.1499,
"step": 156500
},
{
"epoch": 1.29,
"learning_rate": 9.87946670165139e-06,
"loss": 3.139,
"step": 157000
},
{
"epoch": 1.29,
"learning_rate": 9.87905672444612e-06,
"loss": 3.1285,
"step": 157500
},
{
"epoch": 1.29,
"learning_rate": 9.878646747240855e-06,
"loss": 3.1264,
"step": 158000
},
{
"epoch": 1.3,
"learning_rate": 9.878236770035587e-06,
"loss": 3.1133,
"step": 158500
},
{
"epoch": 1.3,
"learning_rate": 9.87782679283032e-06,
"loss": 3.118,
"step": 159000
},
{
"epoch": 1.31,
"learning_rate": 9.877416815625052e-06,
"loss": 3.1162,
"step": 159500
},
{
"epoch": 1.31,
"learning_rate": 9.877006838419785e-06,
"loss": 3.1107,
"step": 160000
},
{
"epoch": 1.31,
"learning_rate": 9.876596861214517e-06,
"loss": 3.0997,
"step": 160500
},
{
"epoch": 1.32,
"learning_rate": 9.87618688400925e-06,
"loss": 3.096,
"step": 161000
},
{
"epoch": 1.32,
"learning_rate": 9.875776906803982e-06,
"loss": 3.087,
"step": 161500
},
{
"epoch": 1.33,
"learning_rate": 9.875366929598716e-06,
"loss": 3.0929,
"step": 162000
},
{
"epoch": 1.33,
"learning_rate": 9.874956952393447e-06,
"loss": 3.0958,
"step": 162500
},
{
"epoch": 1.34,
"learning_rate": 9.874546975188181e-06,
"loss": 3.0843,
"step": 163000
},
{
"epoch": 1.34,
"learning_rate": 9.874136997982913e-06,
"loss": 3.0751,
"step": 163500
},
{
"epoch": 1.34,
"learning_rate": 9.873727020777646e-06,
"loss": 3.0753,
"step": 164000
},
{
"epoch": 1.35,
"learning_rate": 9.873317043572378e-06,
"loss": 3.0662,
"step": 164500
},
{
"epoch": 1.35,
"learning_rate": 9.87290706636711e-06,
"loss": 3.0677,
"step": 165000
},
{
"epoch": 1.36,
"learning_rate": 9.872497089161843e-06,
"loss": 3.0606,
"step": 165500
},
{
"epoch": 1.36,
"learning_rate": 9.872087111956576e-06,
"loss": 3.0519,
"step": 166000
},
{
"epoch": 1.36,
"learning_rate": 9.871677134751308e-06,
"loss": 3.0493,
"step": 166500
},
{
"epoch": 1.37,
"learning_rate": 9.871267157546042e-06,
"loss": 3.053,
"step": 167000
},
{
"epoch": 1.37,
"learning_rate": 9.870857180340773e-06,
"loss": 3.0406,
"step": 167500
},
{
"epoch": 1.38,
"learning_rate": 9.870447203135507e-06,
"loss": 3.0446,
"step": 168000
},
{
"epoch": 1.38,
"learning_rate": 9.87003722593024e-06,
"loss": 3.0292,
"step": 168500
},
{
"epoch": 1.38,
"learning_rate": 9.869627248724972e-06,
"loss": 3.033,
"step": 169000
},
{
"epoch": 1.39,
"learning_rate": 9.869217271519705e-06,
"loss": 3.0346,
"step": 169500
},
{
"epoch": 1.39,
"learning_rate": 9.868807294314437e-06,
"loss": 3.033,
"step": 170000
},
{
"epoch": 1.4,
"learning_rate": 9.86839731710917e-06,
"loss": 3.0174,
"step": 170500
},
{
"epoch": 1.4,
"learning_rate": 9.867987339903902e-06,
"loss": 3.0139,
"step": 171000
},
{
"epoch": 1.41,
"learning_rate": 9.867577362698634e-06,
"loss": 3.0092,
"step": 171500
},
{
"epoch": 1.41,
"learning_rate": 9.867167385493367e-06,
"loss": 3.0096,
"step": 172000
},
{
"epoch": 1.41,
"learning_rate": 9.8667574082881e-06,
"loss": 3.0058,
"step": 172500
},
{
"epoch": 1.42,
"learning_rate": 9.866347431082832e-06,
"loss": 3.0043,
"step": 173000
},
{
"epoch": 1.42,
"learning_rate": 9.865937453877566e-06,
"loss": 2.9933,
"step": 173500
},
{
"epoch": 1.43,
"learning_rate": 9.865527476672297e-06,
"loss": 2.9923,
"step": 174000
},
{
"epoch": 1.43,
"learning_rate": 9.865117499467031e-06,
"loss": 2.9919,
"step": 174500
},
{
"epoch": 1.43,
"learning_rate": 9.864707522261763e-06,
"loss": 2.9822,
"step": 175000
},
{
"epoch": 1.44,
"learning_rate": 9.864297545056496e-06,
"loss": 2.9915,
"step": 175500
},
{
"epoch": 1.44,
"learning_rate": 9.863887567851228e-06,
"loss": 2.9816,
"step": 176000
},
{
"epoch": 1.45,
"learning_rate": 9.86347759064596e-06,
"loss": 2.9783,
"step": 176500
},
{
"epoch": 1.45,
"learning_rate": 9.863067613440693e-06,
"loss": 2.9771,
"step": 177000
},
{
"epoch": 1.45,
"learning_rate": 9.862657636235426e-06,
"loss": 2.9773,
"step": 177500
},
{
"epoch": 1.46,
"learning_rate": 9.862247659030158e-06,
"loss": 2.9683,
"step": 178000
},
{
"epoch": 1.46,
"learning_rate": 9.861837681824892e-06,
"loss": 2.9603,
"step": 178500
},
{
"epoch": 1.47,
"learning_rate": 9.861427704619623e-06,
"loss": 2.96,
"step": 179000
},
{
"epoch": 1.47,
"learning_rate": 9.861017727414357e-06,
"loss": 2.9553,
"step": 179500
},
{
"epoch": 1.47,
"learning_rate": 9.86060775020909e-06,
"loss": 2.9512,
"step": 180000
},
{
"epoch": 1.48,
"learning_rate": 9.860197773003822e-06,
"loss": 2.952,
"step": 180500
},
{
"epoch": 1.48,
"learning_rate": 9.859787795798555e-06,
"loss": 2.9487,
"step": 181000
},
{
"epoch": 1.49,
"learning_rate": 9.859377818593287e-06,
"loss": 2.9473,
"step": 181500
},
{
"epoch": 1.49,
"learning_rate": 9.85896784138802e-06,
"loss": 2.9399,
"step": 182000
},
{
"epoch": 1.5,
"learning_rate": 9.858557864182752e-06,
"loss": 2.932,
"step": 182500
},
{
"epoch": 1.5,
"learning_rate": 9.858147886977484e-06,
"loss": 2.9373,
"step": 183000
},
{
"epoch": 1.5,
"learning_rate": 9.857737909772217e-06,
"loss": 2.9362,
"step": 183500
},
{
"epoch": 1.51,
"learning_rate": 9.85732793256695e-06,
"loss": 2.9284,
"step": 184000
},
{
"epoch": 1.51,
"learning_rate": 9.856917955361682e-06,
"loss": 2.9266,
"step": 184500
},
{
"epoch": 1.52,
"learning_rate": 9.856507978156416e-06,
"loss": 2.9279,
"step": 185000
},
{
"epoch": 1.52,
"learning_rate": 9.856098000951147e-06,
"loss": 2.9205,
"step": 185500
},
{
"epoch": 1.52,
"learning_rate": 9.855688023745881e-06,
"loss": 2.9112,
"step": 186000
},
{
"epoch": 1.53,
"learning_rate": 9.855278046540613e-06,
"loss": 2.9139,
"step": 186500
},
{
"epoch": 1.53,
"learning_rate": 9.854868069335346e-06,
"loss": 2.9115,
"step": 187000
},
{
"epoch": 1.54,
"learning_rate": 9.854458092130078e-06,
"loss": 2.9099,
"step": 187500
},
{
"epoch": 1.54,
"learning_rate": 9.85404811492481e-06,
"loss": 2.9102,
"step": 188000
},
{
"epoch": 1.54,
"learning_rate": 9.853638137719543e-06,
"loss": 2.9063,
"step": 188500
},
{
"epoch": 1.55,
"learning_rate": 9.853228160514277e-06,
"loss": 2.9013,
"step": 189000
},
{
"epoch": 1.55,
"learning_rate": 9.852818183309008e-06,
"loss": 2.8969,
"step": 189500
},
{
"epoch": 1.56,
"learning_rate": 9.852408206103742e-06,
"loss": 2.9042,
"step": 190000
},
{
"epoch": 1.56,
"learning_rate": 9.851998228898475e-06,
"loss": 2.8986,
"step": 190500
},
{
"epoch": 1.56,
"learning_rate": 9.851588251693207e-06,
"loss": 2.8891,
"step": 191000
},
{
"epoch": 1.57,
"learning_rate": 9.85117827448794e-06,
"loss": 2.8867,
"step": 191500
},
{
"epoch": 1.57,
"learning_rate": 9.850768297282672e-06,
"loss": 2.889,
"step": 192000
},
{
"epoch": 1.58,
"learning_rate": 9.850358320077405e-06,
"loss": 2.8804,
"step": 192500
},
{
"epoch": 1.58,
"learning_rate": 9.849948342872137e-06,
"loss": 2.8795,
"step": 193000
},
{
"epoch": 1.59,
"learning_rate": 9.84953836566687e-06,
"loss": 2.8772,
"step": 193500
},
{
"epoch": 1.59,
"learning_rate": 9.849128388461602e-06,
"loss": 2.8751,
"step": 194000
},
{
"epoch": 1.59,
"learning_rate": 9.848718411256334e-06,
"loss": 2.8733,
"step": 194500
},
{
"epoch": 1.6,
"learning_rate": 9.848308434051067e-06,
"loss": 2.8742,
"step": 195000
},
{
"epoch": 1.6,
"learning_rate": 9.847898456845801e-06,
"loss": 2.8727,
"step": 195500
},
{
"epoch": 1.61,
"learning_rate": 9.847488479640532e-06,
"loss": 2.8608,
"step": 196000
},
{
"epoch": 1.61,
"learning_rate": 9.847078502435266e-06,
"loss": 2.8595,
"step": 196500
},
{
"epoch": 1.61,
"learning_rate": 9.846668525229998e-06,
"loss": 2.8664,
"step": 197000
},
{
"epoch": 1.62,
"learning_rate": 9.846258548024731e-06,
"loss": 2.8597,
"step": 197500
},
{
"epoch": 1.62,
"learning_rate": 9.845848570819463e-06,
"loss": 2.8557,
"step": 198000
},
{
"epoch": 1.63,
"learning_rate": 9.845438593614196e-06,
"loss": 2.8565,
"step": 198500
},
{
"epoch": 1.63,
"learning_rate": 9.845028616408928e-06,
"loss": 2.8489,
"step": 199000
},
{
"epoch": 1.63,
"learning_rate": 9.84461863920366e-06,
"loss": 2.8491,
"step": 199500
},
{
"epoch": 1.64,
"learning_rate": 9.844208661998393e-06,
"loss": 2.8472,
"step": 200000
},
{
"epoch": 1.64,
"learning_rate": 9.843798684793127e-06,
"loss": 2.8433,
"step": 200500
},
{
"epoch": 1.65,
"learning_rate": 9.843388707587858e-06,
"loss": 2.8373,
"step": 201000
},
{
"epoch": 1.65,
"learning_rate": 9.842978730382592e-06,
"loss": 2.8368,
"step": 201500
},
{
"epoch": 1.65,
"learning_rate": 9.842568753177325e-06,
"loss": 2.8287,
"step": 202000
},
{
"epoch": 1.66,
"learning_rate": 9.842158775972057e-06,
"loss": 2.8352,
"step": 202500
},
{
"epoch": 1.66,
"learning_rate": 9.84174879876679e-06,
"loss": 2.829,
"step": 203000
},
{
"epoch": 1.67,
"learning_rate": 9.841338821561522e-06,
"loss": 2.8262,
"step": 203500
},
{
"epoch": 1.67,
"learning_rate": 9.840928844356255e-06,
"loss": 2.8309,
"step": 204000
},
{
"epoch": 1.68,
"learning_rate": 9.840518867150987e-06,
"loss": 2.8271,
"step": 204500
},
{
"epoch": 1.68,
"learning_rate": 9.84010888994572e-06,
"loss": 2.8207,
"step": 205000
},
{
"epoch": 1.68,
"learning_rate": 9.839698912740454e-06,
"loss": 2.8221,
"step": 205500
},
{
"epoch": 1.69,
"learning_rate": 9.839288935535184e-06,
"loss": 2.8157,
"step": 206000
},
{
"epoch": 1.69,
"learning_rate": 9.838878958329917e-06,
"loss": 2.8092,
"step": 206500
},
{
"epoch": 1.7,
"learning_rate": 9.838468981124651e-06,
"loss": 2.8138,
"step": 207000
},
{
"epoch": 1.7,
"learning_rate": 9.838059003919382e-06,
"loss": 2.81,
"step": 207500
},
{
"epoch": 1.7,
"learning_rate": 9.837649026714116e-06,
"loss": 2.8085,
"step": 208000
},
{
"epoch": 1.71,
"learning_rate": 9.837239049508848e-06,
"loss": 2.8103,
"step": 208500
},
{
"epoch": 1.71,
"learning_rate": 9.83682907230358e-06,
"loss": 2.7985,
"step": 209000
},
{
"epoch": 1.72,
"learning_rate": 9.836419095098313e-06,
"loss": 2.7991,
"step": 209500
},
{
"epoch": 1.72,
"learning_rate": 9.836009117893046e-06,
"loss": 2.7987,
"step": 210000
},
{
"epoch": 1.72,
"learning_rate": 9.835599140687778e-06,
"loss": 2.8006,
"step": 210500
},
{
"epoch": 1.73,
"learning_rate": 9.83518916348251e-06,
"loss": 2.7949,
"step": 211000
},
{
"epoch": 1.73,
"learning_rate": 9.834779186277243e-06,
"loss": 2.7935,
"step": 211500
},
{
"epoch": 1.74,
"learning_rate": 9.834369209071977e-06,
"loss": 2.7939,
"step": 212000
},
{
"epoch": 1.74,
"learning_rate": 9.833959231866708e-06,
"loss": 2.7915,
"step": 212500
},
{
"epoch": 1.75,
"learning_rate": 9.833549254661442e-06,
"loss": 2.7805,
"step": 213000
},
{
"epoch": 1.75,
"learning_rate": 9.833139277456175e-06,
"loss": 2.789,
"step": 213500
},
{
"epoch": 1.75,
"learning_rate": 9.832729300250907e-06,
"loss": 2.7823,
"step": 214000
},
{
"epoch": 1.76,
"learning_rate": 9.83231932304564e-06,
"loss": 2.7811,
"step": 214500
},
{
"epoch": 1.76,
"learning_rate": 9.831909345840372e-06,
"loss": 2.7841,
"step": 215000
},
{
"epoch": 1.77,
"learning_rate": 9.831499368635105e-06,
"loss": 2.778,
"step": 215500
},
{
"epoch": 1.77,
"learning_rate": 9.831089391429837e-06,
"loss": 2.7668,
"step": 216000
},
{
"epoch": 1.77,
"learning_rate": 9.83067941422457e-06,
"loss": 2.7753,
"step": 216500
},
{
"epoch": 1.78,
"learning_rate": 9.830269437019304e-06,
"loss": 2.7702,
"step": 217000
},
{
"epoch": 1.78,
"learning_rate": 9.829859459814034e-06,
"loss": 2.7645,
"step": 217500
},
{
"epoch": 1.79,
"learning_rate": 9.829449482608769e-06,
"loss": 2.7674,
"step": 218000
},
{
"epoch": 1.79,
"learning_rate": 9.829039505403501e-06,
"loss": 2.7636,
"step": 218500
},
{
"epoch": 1.79,
"learning_rate": 9.828629528198232e-06,
"loss": 2.7643,
"step": 219000
},
{
"epoch": 1.8,
"learning_rate": 9.828219550992966e-06,
"loss": 2.7585,
"step": 219500
},
{
"epoch": 1.8,
"learning_rate": 9.827809573787698e-06,
"loss": 2.7534,
"step": 220000
},
{
"epoch": 1.81,
"learning_rate": 9.82739959658243e-06,
"loss": 2.7606,
"step": 220500
},
{
"epoch": 1.81,
"learning_rate": 9.826989619377163e-06,
"loss": 2.7563,
"step": 221000
},
{
"epoch": 1.81,
"learning_rate": 9.826579642171896e-06,
"loss": 2.7494,
"step": 221500
},
{
"epoch": 1.82,
"learning_rate": 9.826169664966628e-06,
"loss": 2.7555,
"step": 222000
},
{
"epoch": 1.82,
"learning_rate": 9.82575968776136e-06,
"loss": 2.7548,
"step": 222500
},
{
"epoch": 1.83,
"learning_rate": 9.825349710556093e-06,
"loss": 2.7482,
"step": 223000
},
{
"epoch": 1.83,
"step": 223412,
"total_flos": 3.1773110645597143e+18,
"train_loss": 4.445307940913256,
"train_runtime": 197999.0929,
"train_samples_per_second": 2958.982,
"train_steps_per_second": 61.646
}
],
"logging_steps": 500,
"max_steps": 12205800,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 3.1773110645597143e+18,
"trial_name": null,
"trial_params": null
}