HBERTv1_48_L2_H256_A4 / trainer_state.json
gokuls's picture
End of training
5a17777
raw
history blame contribute delete
No virus
118 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 11.992000797428293,
"eval_steps": 1000000,
"global_step": 481227,
"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": 10.3263,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 10.1175,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 1.5e-06,
"loss": 9.8544,
"step": 1500
},
{
"epoch": 0.05,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.5843,
"step": 2000
},
{
"epoch": 0.06,
"learning_rate": 2.5e-06,
"loss": 9.2832,
"step": 2500
},
{
"epoch": 0.07,
"learning_rate": 3e-06,
"loss": 8.9468,
"step": 3000
},
{
"epoch": 0.09,
"learning_rate": 3.5e-06,
"loss": 8.5905,
"step": 3500
},
{
"epoch": 0.1,
"learning_rate": 4.000000000000001e-06,
"loss": 8.2279,
"step": 4000
},
{
"epoch": 0.11,
"learning_rate": 4.5e-06,
"loss": 7.894,
"step": 4500
},
{
"epoch": 0.12,
"learning_rate": 5e-06,
"loss": 7.6046,
"step": 5000
},
{
"epoch": 0.14,
"learning_rate": 5.500000000000001e-06,
"loss": 7.3752,
"step": 5500
},
{
"epoch": 0.15,
"learning_rate": 6e-06,
"loss": 7.2116,
"step": 6000
},
{
"epoch": 0.16,
"learning_rate": 6.5000000000000004e-06,
"loss": 7.0989,
"step": 6500
},
{
"epoch": 0.17,
"learning_rate": 7e-06,
"loss": 7.0198,
"step": 7000
},
{
"epoch": 0.19,
"learning_rate": 7.500000000000001e-06,
"loss": 6.9562,
"step": 7500
},
{
"epoch": 0.2,
"learning_rate": 8.000000000000001e-06,
"loss": 6.9055,
"step": 8000
},
{
"epoch": 0.21,
"learning_rate": 8.5e-06,
"loss": 6.8697,
"step": 8500
},
{
"epoch": 0.22,
"learning_rate": 9e-06,
"loss": 6.8281,
"step": 9000
},
{
"epoch": 0.24,
"learning_rate": 9.5e-06,
"loss": 6.7968,
"step": 9500
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 6.7643,
"step": 10000
},
{
"epoch": 0.26,
"learning_rate": 9.998750905593446e-06,
"loss": 6.735,
"step": 10500
},
{
"epoch": 0.27,
"learning_rate": 9.99750181118689e-06,
"loss": 6.7055,
"step": 11000
},
{
"epoch": 0.29,
"learning_rate": 9.996252716780335e-06,
"loss": 6.683,
"step": 11500
},
{
"epoch": 0.3,
"learning_rate": 9.99500362237378e-06,
"loss": 6.6671,
"step": 12000
},
{
"epoch": 0.31,
"learning_rate": 9.993754527967225e-06,
"loss": 6.6462,
"step": 12500
},
{
"epoch": 0.32,
"learning_rate": 9.99250543356067e-06,
"loss": 6.6288,
"step": 13000
},
{
"epoch": 0.34,
"learning_rate": 9.991256339154115e-06,
"loss": 6.6121,
"step": 13500
},
{
"epoch": 0.35,
"learning_rate": 9.99000724474756e-06,
"loss": 6.5972,
"step": 14000
},
{
"epoch": 0.36,
"learning_rate": 9.988758150341003e-06,
"loss": 6.5807,
"step": 14500
},
{
"epoch": 0.37,
"learning_rate": 9.987509055934448e-06,
"loss": 6.5674,
"step": 15000
},
{
"epoch": 0.39,
"learning_rate": 9.986259961527892e-06,
"loss": 6.5534,
"step": 15500
},
{
"epoch": 0.4,
"learning_rate": 9.985010867121337e-06,
"loss": 6.5435,
"step": 16000
},
{
"epoch": 0.41,
"learning_rate": 9.983761772714782e-06,
"loss": 6.5359,
"step": 16500
},
{
"epoch": 0.42,
"learning_rate": 9.982512678308227e-06,
"loss": 6.5232,
"step": 17000
},
{
"epoch": 0.44,
"learning_rate": 9.981263583901672e-06,
"loss": 6.5075,
"step": 17500
},
{
"epoch": 0.45,
"learning_rate": 9.980014489495117e-06,
"loss": 6.4984,
"step": 18000
},
{
"epoch": 0.46,
"learning_rate": 9.978765395088562e-06,
"loss": 6.4935,
"step": 18500
},
{
"epoch": 0.47,
"learning_rate": 9.977516300682006e-06,
"loss": 6.4813,
"step": 19000
},
{
"epoch": 0.49,
"learning_rate": 9.976267206275451e-06,
"loss": 6.4716,
"step": 19500
},
{
"epoch": 0.5,
"learning_rate": 9.975018111868896e-06,
"loss": 6.4678,
"step": 20000
},
{
"epoch": 0.51,
"learning_rate": 9.973769017462341e-06,
"loss": 6.4554,
"step": 20500
},
{
"epoch": 0.52,
"learning_rate": 9.972519923055786e-06,
"loss": 6.4445,
"step": 21000
},
{
"epoch": 0.54,
"learning_rate": 9.97127082864923e-06,
"loss": 6.443,
"step": 21500
},
{
"epoch": 0.55,
"learning_rate": 9.970021734242675e-06,
"loss": 6.4372,
"step": 22000
},
{
"epoch": 0.56,
"learning_rate": 9.96877263983612e-06,
"loss": 6.4238,
"step": 22500
},
{
"epoch": 0.57,
"learning_rate": 9.967523545429565e-06,
"loss": 6.4178,
"step": 23000
},
{
"epoch": 0.59,
"learning_rate": 9.966274451023008e-06,
"loss": 6.4157,
"step": 23500
},
{
"epoch": 0.6,
"learning_rate": 9.965025356616453e-06,
"loss": 6.4078,
"step": 24000
},
{
"epoch": 0.61,
"learning_rate": 9.963776262209898e-06,
"loss": 6.4002,
"step": 24500
},
{
"epoch": 0.62,
"learning_rate": 9.962527167803343e-06,
"loss": 6.3949,
"step": 25000
},
{
"epoch": 0.64,
"learning_rate": 9.961278073396788e-06,
"loss": 6.3927,
"step": 25500
},
{
"epoch": 0.65,
"learning_rate": 9.960028978990233e-06,
"loss": 6.3866,
"step": 26000
},
{
"epoch": 0.66,
"learning_rate": 9.958779884583677e-06,
"loss": 6.3812,
"step": 26500
},
{
"epoch": 0.67,
"learning_rate": 9.957530790177122e-06,
"loss": 6.3707,
"step": 27000
},
{
"epoch": 0.69,
"learning_rate": 9.956281695770567e-06,
"loss": 6.3663,
"step": 27500
},
{
"epoch": 0.7,
"learning_rate": 9.955032601364012e-06,
"loss": 6.3625,
"step": 28000
},
{
"epoch": 0.71,
"learning_rate": 9.953783506957457e-06,
"loss": 6.3559,
"step": 28500
},
{
"epoch": 0.72,
"learning_rate": 9.952534412550902e-06,
"loss": 6.3508,
"step": 29000
},
{
"epoch": 0.74,
"learning_rate": 9.951285318144347e-06,
"loss": 6.346,
"step": 29500
},
{
"epoch": 0.75,
"learning_rate": 9.950036223737791e-06,
"loss": 6.3436,
"step": 30000
},
{
"epoch": 0.76,
"learning_rate": 9.948787129331236e-06,
"loss": 6.3354,
"step": 30500
},
{
"epoch": 0.77,
"learning_rate": 9.947538034924681e-06,
"loss": 6.3354,
"step": 31000
},
{
"epoch": 0.78,
"learning_rate": 9.946288940518126e-06,
"loss": 6.3286,
"step": 31500
},
{
"epoch": 0.8,
"learning_rate": 9.94503984611157e-06,
"loss": 6.3242,
"step": 32000
},
{
"epoch": 0.81,
"learning_rate": 9.943790751705014e-06,
"loss": 6.3245,
"step": 32500
},
{
"epoch": 0.82,
"learning_rate": 9.942541657298459e-06,
"loss": 6.3166,
"step": 33000
},
{
"epoch": 0.83,
"learning_rate": 9.941292562891904e-06,
"loss": 6.3127,
"step": 33500
},
{
"epoch": 0.85,
"learning_rate": 9.940043468485348e-06,
"loss": 6.3121,
"step": 34000
},
{
"epoch": 0.86,
"learning_rate": 9.938794374078793e-06,
"loss": 6.3052,
"step": 34500
},
{
"epoch": 0.87,
"learning_rate": 9.937545279672238e-06,
"loss": 6.303,
"step": 35000
},
{
"epoch": 0.88,
"learning_rate": 9.936296185265683e-06,
"loss": 6.3003,
"step": 35500
},
{
"epoch": 0.9,
"learning_rate": 9.935047090859128e-06,
"loss": 6.2982,
"step": 36000
},
{
"epoch": 0.91,
"learning_rate": 9.933797996452573e-06,
"loss": 6.2937,
"step": 36500
},
{
"epoch": 0.92,
"learning_rate": 9.932548902046018e-06,
"loss": 6.2929,
"step": 37000
},
{
"epoch": 0.93,
"learning_rate": 9.931299807639462e-06,
"loss": 6.2917,
"step": 37500
},
{
"epoch": 0.95,
"learning_rate": 9.930050713232907e-06,
"loss": 6.2882,
"step": 38000
},
{
"epoch": 0.96,
"learning_rate": 9.928801618826352e-06,
"loss": 6.2821,
"step": 38500
},
{
"epoch": 0.97,
"learning_rate": 9.927552524419797e-06,
"loss": 6.278,
"step": 39000
},
{
"epoch": 0.98,
"learning_rate": 9.926303430013242e-06,
"loss": 6.2773,
"step": 39500
},
{
"epoch": 1.0,
"learning_rate": 9.925054335606687e-06,
"loss": 6.2737,
"step": 40000
},
{
"epoch": 1.01,
"learning_rate": 9.923805241200131e-06,
"loss": 6.269,
"step": 40500
},
{
"epoch": 1.02,
"learning_rate": 9.922556146793575e-06,
"loss": 6.267,
"step": 41000
},
{
"epoch": 1.03,
"learning_rate": 9.92130705238702e-06,
"loss": 6.2694,
"step": 41500
},
{
"epoch": 1.05,
"learning_rate": 9.920057957980464e-06,
"loss": 6.2624,
"step": 42000
},
{
"epoch": 1.06,
"learning_rate": 9.91880886357391e-06,
"loss": 6.2591,
"step": 42500
},
{
"epoch": 1.07,
"learning_rate": 9.917559769167354e-06,
"loss": 6.2567,
"step": 43000
},
{
"epoch": 1.08,
"learning_rate": 9.916310674760799e-06,
"loss": 6.2552,
"step": 43500
},
{
"epoch": 1.1,
"learning_rate": 9.915061580354244e-06,
"loss": 6.2533,
"step": 44000
},
{
"epoch": 1.11,
"learning_rate": 9.913812485947689e-06,
"loss": 6.2502,
"step": 44500
},
{
"epoch": 1.12,
"learning_rate": 9.912563391541133e-06,
"loss": 6.2485,
"step": 45000
},
{
"epoch": 1.13,
"learning_rate": 9.911314297134578e-06,
"loss": 6.2429,
"step": 45500
},
{
"epoch": 1.15,
"learning_rate": 9.910065202728023e-06,
"loss": 6.247,
"step": 46000
},
{
"epoch": 1.16,
"learning_rate": 9.908816108321468e-06,
"loss": 6.2382,
"step": 46500
},
{
"epoch": 1.17,
"learning_rate": 9.907567013914913e-06,
"loss": 6.2412,
"step": 47000
},
{
"epoch": 1.18,
"learning_rate": 9.906317919508358e-06,
"loss": 6.2356,
"step": 47500
},
{
"epoch": 1.2,
"learning_rate": 9.905068825101802e-06,
"loss": 6.233,
"step": 48000
},
{
"epoch": 1.21,
"learning_rate": 9.903819730695247e-06,
"loss": 6.2273,
"step": 48500
},
{
"epoch": 1.22,
"learning_rate": 9.902570636288692e-06,
"loss": 6.2313,
"step": 49000
},
{
"epoch": 1.23,
"learning_rate": 9.901321541882137e-06,
"loss": 6.2233,
"step": 49500
},
{
"epoch": 1.25,
"learning_rate": 9.90007244747558e-06,
"loss": 6.2243,
"step": 50000
},
{
"epoch": 1.26,
"learning_rate": 9.898823353069025e-06,
"loss": 6.2243,
"step": 50500
},
{
"epoch": 1.27,
"learning_rate": 9.89757425866247e-06,
"loss": 6.2208,
"step": 51000
},
{
"epoch": 1.28,
"learning_rate": 9.896325164255915e-06,
"loss": 6.2226,
"step": 51500
},
{
"epoch": 1.3,
"learning_rate": 9.89507606984936e-06,
"loss": 6.2185,
"step": 52000
},
{
"epoch": 1.31,
"learning_rate": 9.893826975442804e-06,
"loss": 6.2171,
"step": 52500
},
{
"epoch": 1.32,
"learning_rate": 9.89257788103625e-06,
"loss": 6.2161,
"step": 53000
},
{
"epoch": 1.33,
"learning_rate": 9.891328786629694e-06,
"loss": 6.2146,
"step": 53500
},
{
"epoch": 1.35,
"learning_rate": 9.890079692223139e-06,
"loss": 6.2114,
"step": 54000
},
{
"epoch": 1.36,
"learning_rate": 9.888830597816584e-06,
"loss": 6.2094,
"step": 54500
},
{
"epoch": 1.37,
"learning_rate": 9.887581503410029e-06,
"loss": 6.2078,
"step": 55000
},
{
"epoch": 1.38,
"learning_rate": 9.886332409003474e-06,
"loss": 6.2032,
"step": 55500
},
{
"epoch": 1.4,
"learning_rate": 9.885083314596918e-06,
"loss": 6.2091,
"step": 56000
},
{
"epoch": 1.41,
"learning_rate": 9.883834220190363e-06,
"loss": 6.2023,
"step": 56500
},
{
"epoch": 1.42,
"learning_rate": 9.882585125783808e-06,
"loss": 6.2031,
"step": 57000
},
{
"epoch": 1.43,
"learning_rate": 9.881336031377253e-06,
"loss": 6.1977,
"step": 57500
},
{
"epoch": 1.45,
"learning_rate": 9.880086936970698e-06,
"loss": 6.1997,
"step": 58000
},
{
"epoch": 1.46,
"learning_rate": 9.878837842564143e-06,
"loss": 6.193,
"step": 58500
},
{
"epoch": 1.47,
"learning_rate": 9.877588748157586e-06,
"loss": 6.191,
"step": 59000
},
{
"epoch": 1.48,
"learning_rate": 9.87633965375103e-06,
"loss": 6.1945,
"step": 59500
},
{
"epoch": 1.5,
"learning_rate": 9.875090559344475e-06,
"loss": 6.184,
"step": 60000
},
{
"epoch": 1.51,
"learning_rate": 9.87384146493792e-06,
"loss": 6.1872,
"step": 60500
},
{
"epoch": 1.52,
"learning_rate": 9.872592370531365e-06,
"loss": 6.1853,
"step": 61000
},
{
"epoch": 1.53,
"learning_rate": 9.87134327612481e-06,
"loss": 6.1842,
"step": 61500
},
{
"epoch": 1.55,
"learning_rate": 9.870094181718255e-06,
"loss": 6.188,
"step": 62000
},
{
"epoch": 1.56,
"learning_rate": 9.8688450873117e-06,
"loss": 6.1893,
"step": 62500
},
{
"epoch": 1.57,
"learning_rate": 9.867595992905145e-06,
"loss": 6.1822,
"step": 63000
},
{
"epoch": 1.58,
"learning_rate": 9.86634689849859e-06,
"loss": 6.1833,
"step": 63500
},
{
"epoch": 1.59,
"learning_rate": 9.865097804092034e-06,
"loss": 6.1865,
"step": 64000
},
{
"epoch": 1.61,
"learning_rate": 9.863848709685479e-06,
"loss": 6.178,
"step": 64500
},
{
"epoch": 1.62,
"learning_rate": 9.862599615278924e-06,
"loss": 6.1796,
"step": 65000
},
{
"epoch": 1.63,
"learning_rate": 9.861350520872369e-06,
"loss": 6.1723,
"step": 65500
},
{
"epoch": 1.64,
"learning_rate": 9.860101426465814e-06,
"loss": 6.1749,
"step": 66000
},
{
"epoch": 1.66,
"learning_rate": 9.858852332059258e-06,
"loss": 6.1761,
"step": 66500
},
{
"epoch": 1.67,
"learning_rate": 9.857603237652703e-06,
"loss": 6.1716,
"step": 67000
},
{
"epoch": 1.68,
"learning_rate": 9.856354143246148e-06,
"loss": 6.1711,
"step": 67500
},
{
"epoch": 1.69,
"learning_rate": 9.855105048839591e-06,
"loss": 6.1667,
"step": 68000
},
{
"epoch": 1.71,
"learning_rate": 9.853855954433036e-06,
"loss": 6.1673,
"step": 68500
},
{
"epoch": 1.72,
"learning_rate": 9.852606860026481e-06,
"loss": 6.168,
"step": 69000
},
{
"epoch": 1.73,
"learning_rate": 9.851357765619926e-06,
"loss": 6.1644,
"step": 69500
},
{
"epoch": 1.74,
"learning_rate": 9.85010867121337e-06,
"loss": 6.165,
"step": 70000
},
{
"epoch": 1.76,
"learning_rate": 9.848859576806816e-06,
"loss": 6.1588,
"step": 70500
},
{
"epoch": 1.77,
"learning_rate": 9.84761048240026e-06,
"loss": 6.1636,
"step": 71000
},
{
"epoch": 1.78,
"learning_rate": 9.846361387993705e-06,
"loss": 6.1573,
"step": 71500
},
{
"epoch": 1.79,
"learning_rate": 9.84511229358715e-06,
"loss": 6.1557,
"step": 72000
},
{
"epoch": 1.81,
"learning_rate": 9.843863199180595e-06,
"loss": 6.1572,
"step": 72500
},
{
"epoch": 1.82,
"learning_rate": 9.84261410477404e-06,
"loss": 6.158,
"step": 73000
},
{
"epoch": 1.83,
"learning_rate": 9.841365010367485e-06,
"loss": 6.1569,
"step": 73500
},
{
"epoch": 1.84,
"learning_rate": 9.84011591596093e-06,
"loss": 6.1563,
"step": 74000
},
{
"epoch": 1.86,
"learning_rate": 9.838866821554374e-06,
"loss": 6.1542,
"step": 74500
},
{
"epoch": 1.87,
"learning_rate": 9.83761772714782e-06,
"loss": 6.157,
"step": 75000
},
{
"epoch": 1.88,
"learning_rate": 9.836368632741264e-06,
"loss": 6.1547,
"step": 75500
},
{
"epoch": 1.89,
"learning_rate": 9.835119538334709e-06,
"loss": 6.1478,
"step": 76000
},
{
"epoch": 1.91,
"learning_rate": 9.833870443928154e-06,
"loss": 6.152,
"step": 76500
},
{
"epoch": 1.92,
"learning_rate": 9.832621349521597e-06,
"loss": 6.1462,
"step": 77000
},
{
"epoch": 1.93,
"learning_rate": 9.831372255115042e-06,
"loss": 6.1484,
"step": 77500
},
{
"epoch": 1.94,
"learning_rate": 9.830123160708487e-06,
"loss": 6.1458,
"step": 78000
},
{
"epoch": 1.96,
"learning_rate": 9.828874066301931e-06,
"loss": 6.146,
"step": 78500
},
{
"epoch": 1.97,
"learning_rate": 9.827624971895376e-06,
"loss": 6.1413,
"step": 79000
},
{
"epoch": 1.98,
"learning_rate": 9.826375877488821e-06,
"loss": 6.1402,
"step": 79500
},
{
"epoch": 1.99,
"learning_rate": 9.825126783082266e-06,
"loss": 6.1406,
"step": 80000
},
{
"epoch": 2.01,
"learning_rate": 9.82387768867571e-06,
"loss": 6.1417,
"step": 80500
},
{
"epoch": 2.02,
"learning_rate": 9.822628594269156e-06,
"loss": 6.138,
"step": 81000
},
{
"epoch": 2.03,
"learning_rate": 9.8213794998626e-06,
"loss": 6.1369,
"step": 81500
},
{
"epoch": 2.04,
"learning_rate": 9.820130405456045e-06,
"loss": 6.1383,
"step": 82000
},
{
"epoch": 2.06,
"learning_rate": 9.81888131104949e-06,
"loss": 6.1316,
"step": 82500
},
{
"epoch": 2.07,
"learning_rate": 9.817632216642935e-06,
"loss": 6.133,
"step": 83000
},
{
"epoch": 2.08,
"learning_rate": 9.81638312223638e-06,
"loss": 6.1371,
"step": 83500
},
{
"epoch": 2.09,
"learning_rate": 9.815134027829825e-06,
"loss": 6.1306,
"step": 84000
},
{
"epoch": 2.11,
"learning_rate": 9.81388493342327e-06,
"loss": 6.1313,
"step": 84500
},
{
"epoch": 2.12,
"learning_rate": 9.812635839016714e-06,
"loss": 6.1313,
"step": 85000
},
{
"epoch": 2.13,
"learning_rate": 9.81138674461016e-06,
"loss": 6.1303,
"step": 85500
},
{
"epoch": 2.14,
"learning_rate": 9.810137650203602e-06,
"loss": 6.1305,
"step": 86000
},
{
"epoch": 2.16,
"learning_rate": 9.808888555797047e-06,
"loss": 6.1298,
"step": 86500
},
{
"epoch": 2.17,
"learning_rate": 9.807639461390492e-06,
"loss": 6.1281,
"step": 87000
},
{
"epoch": 2.18,
"learning_rate": 9.806390366983937e-06,
"loss": 6.1267,
"step": 87500
},
{
"epoch": 2.19,
"learning_rate": 9.805141272577382e-06,
"loss": 6.1256,
"step": 88000
},
{
"epoch": 2.21,
"learning_rate": 9.803892178170827e-06,
"loss": 6.1238,
"step": 88500
},
{
"epoch": 2.22,
"learning_rate": 9.802643083764272e-06,
"loss": 6.125,
"step": 89000
},
{
"epoch": 2.23,
"learning_rate": 9.801393989357716e-06,
"loss": 6.1253,
"step": 89500
},
{
"epoch": 2.24,
"learning_rate": 9.800144894951161e-06,
"loss": 6.1188,
"step": 90000
},
{
"epoch": 2.26,
"learning_rate": 9.798895800544606e-06,
"loss": 6.1216,
"step": 90500
},
{
"epoch": 2.27,
"learning_rate": 9.797646706138051e-06,
"loss": 6.1185,
"step": 91000
},
{
"epoch": 2.28,
"learning_rate": 9.796397611731496e-06,
"loss": 6.1204,
"step": 91500
},
{
"epoch": 2.29,
"learning_rate": 9.79514851732494e-06,
"loss": 6.1182,
"step": 92000
},
{
"epoch": 2.31,
"learning_rate": 9.793899422918385e-06,
"loss": 6.1201,
"step": 92500
},
{
"epoch": 2.32,
"learning_rate": 9.79265032851183e-06,
"loss": 6.1169,
"step": 93000
},
{
"epoch": 2.33,
"learning_rate": 9.791401234105275e-06,
"loss": 6.119,
"step": 93500
},
{
"epoch": 2.34,
"learning_rate": 9.790152139698718e-06,
"loss": 6.1204,
"step": 94000
},
{
"epoch": 2.35,
"learning_rate": 9.788903045292165e-06,
"loss": 6.1148,
"step": 94500
},
{
"epoch": 2.37,
"learning_rate": 9.787653950885608e-06,
"loss": 6.1089,
"step": 95000
},
{
"epoch": 2.38,
"learning_rate": 9.786404856479053e-06,
"loss": 6.1177,
"step": 95500
},
{
"epoch": 2.39,
"learning_rate": 9.785155762072498e-06,
"loss": 6.113,
"step": 96000
},
{
"epoch": 2.4,
"learning_rate": 9.783906667665943e-06,
"loss": 6.1125,
"step": 96500
},
{
"epoch": 2.42,
"learning_rate": 9.782657573259387e-06,
"loss": 6.1135,
"step": 97000
},
{
"epoch": 2.43,
"learning_rate": 9.781408478852832e-06,
"loss": 6.1079,
"step": 97500
},
{
"epoch": 2.44,
"learning_rate": 9.780159384446277e-06,
"loss": 6.1111,
"step": 98000
},
{
"epoch": 2.45,
"learning_rate": 9.778910290039722e-06,
"loss": 6.1064,
"step": 98500
},
{
"epoch": 2.47,
"learning_rate": 9.777661195633167e-06,
"loss": 6.109,
"step": 99000
},
{
"epoch": 2.48,
"learning_rate": 9.776412101226612e-06,
"loss": 6.1076,
"step": 99500
},
{
"epoch": 2.49,
"learning_rate": 9.775163006820057e-06,
"loss": 6.1031,
"step": 100000
},
{
"epoch": 2.5,
"learning_rate": 9.773913912413501e-06,
"loss": 6.1049,
"step": 100500
},
{
"epoch": 2.52,
"learning_rate": 9.772664818006946e-06,
"loss": 6.1027,
"step": 101000
},
{
"epoch": 2.53,
"learning_rate": 9.771415723600391e-06,
"loss": 6.1014,
"step": 101500
},
{
"epoch": 2.54,
"learning_rate": 9.770166629193836e-06,
"loss": 6.107,
"step": 102000
},
{
"epoch": 2.55,
"learning_rate": 9.76891753478728e-06,
"loss": 6.1043,
"step": 102500
},
{
"epoch": 2.57,
"learning_rate": 9.767668440380724e-06,
"loss": 6.1015,
"step": 103000
},
{
"epoch": 2.58,
"learning_rate": 9.76641934597417e-06,
"loss": 6.1026,
"step": 103500
},
{
"epoch": 2.59,
"learning_rate": 9.765170251567614e-06,
"loss": 6.1013,
"step": 104000
},
{
"epoch": 2.6,
"learning_rate": 9.763921157161058e-06,
"loss": 6.0995,
"step": 104500
},
{
"epoch": 2.62,
"learning_rate": 9.762672062754503e-06,
"loss": 6.0971,
"step": 105000
},
{
"epoch": 2.63,
"learning_rate": 9.761422968347948e-06,
"loss": 6.0993,
"step": 105500
},
{
"epoch": 2.64,
"learning_rate": 9.760173873941393e-06,
"loss": 6.0941,
"step": 106000
},
{
"epoch": 2.65,
"learning_rate": 9.758924779534838e-06,
"loss": 6.096,
"step": 106500
},
{
"epoch": 2.67,
"learning_rate": 9.757675685128283e-06,
"loss": 6.0942,
"step": 107000
},
{
"epoch": 2.68,
"learning_rate": 9.756426590721728e-06,
"loss": 6.0944,
"step": 107500
},
{
"epoch": 2.69,
"learning_rate": 9.755177496315172e-06,
"loss": 6.0928,
"step": 108000
},
{
"epoch": 2.7,
"learning_rate": 9.753928401908617e-06,
"loss": 6.0948,
"step": 108500
},
{
"epoch": 2.72,
"learning_rate": 9.752679307502062e-06,
"loss": 6.0903,
"step": 109000
},
{
"epoch": 2.73,
"learning_rate": 9.751430213095507e-06,
"loss": 6.0976,
"step": 109500
},
{
"epoch": 2.74,
"learning_rate": 9.750181118688952e-06,
"loss": 6.0881,
"step": 110000
},
{
"epoch": 2.75,
"learning_rate": 9.748932024282397e-06,
"loss": 6.0956,
"step": 110500
},
{
"epoch": 2.77,
"learning_rate": 9.747682929875841e-06,
"loss": 6.0872,
"step": 111000
},
{
"epoch": 2.78,
"learning_rate": 9.746433835469286e-06,
"loss": 6.089,
"step": 111500
},
{
"epoch": 2.79,
"learning_rate": 9.74518474106273e-06,
"loss": 6.09,
"step": 112000
},
{
"epoch": 2.8,
"learning_rate": 9.743935646656176e-06,
"loss": 6.0898,
"step": 112500
},
{
"epoch": 2.82,
"learning_rate": 9.74268655224962e-06,
"loss": 6.0868,
"step": 113000
},
{
"epoch": 2.83,
"learning_rate": 9.741437457843064e-06,
"loss": 6.0894,
"step": 113500
},
{
"epoch": 2.84,
"learning_rate": 9.740188363436509e-06,
"loss": 6.088,
"step": 114000
},
{
"epoch": 2.85,
"learning_rate": 9.738939269029954e-06,
"loss": 6.0829,
"step": 114500
},
{
"epoch": 2.87,
"learning_rate": 9.737690174623399e-06,
"loss": 6.0854,
"step": 115000
},
{
"epoch": 2.88,
"learning_rate": 9.736441080216843e-06,
"loss": 6.0796,
"step": 115500
},
{
"epoch": 2.89,
"learning_rate": 9.735191985810288e-06,
"loss": 6.0832,
"step": 116000
},
{
"epoch": 2.9,
"learning_rate": 9.733942891403733e-06,
"loss": 6.0822,
"step": 116500
},
{
"epoch": 2.92,
"learning_rate": 9.732693796997178e-06,
"loss": 6.0795,
"step": 117000
},
{
"epoch": 2.93,
"learning_rate": 9.731444702590623e-06,
"loss": 6.0833,
"step": 117500
},
{
"epoch": 2.94,
"learning_rate": 9.730195608184068e-06,
"loss": 6.0804,
"step": 118000
},
{
"epoch": 2.95,
"learning_rate": 9.728946513777512e-06,
"loss": 6.0809,
"step": 118500
},
{
"epoch": 2.97,
"learning_rate": 9.727697419370957e-06,
"loss": 6.0794,
"step": 119000
},
{
"epoch": 2.98,
"learning_rate": 9.726448324964402e-06,
"loss": 6.0749,
"step": 119500
},
{
"epoch": 2.99,
"learning_rate": 9.725199230557847e-06,
"loss": 6.077,
"step": 120000
},
{
"epoch": 3.0,
"learning_rate": 9.723950136151292e-06,
"loss": 6.0752,
"step": 120500
},
{
"epoch": 3.02,
"learning_rate": 9.722701041744735e-06,
"loss": 6.078,
"step": 121000
},
{
"epoch": 3.03,
"learning_rate": 9.721451947338182e-06,
"loss": 6.075,
"step": 121500
},
{
"epoch": 3.04,
"learning_rate": 9.720202852931625e-06,
"loss": 6.0786,
"step": 122000
},
{
"epoch": 3.05,
"learning_rate": 9.71895375852507e-06,
"loss": 6.0738,
"step": 122500
},
{
"epoch": 3.07,
"learning_rate": 9.717704664118514e-06,
"loss": 6.076,
"step": 123000
},
{
"epoch": 3.08,
"learning_rate": 9.71645556971196e-06,
"loss": 6.0789,
"step": 123500
},
{
"epoch": 3.09,
"learning_rate": 9.715206475305404e-06,
"loss": 6.0714,
"step": 124000
},
{
"epoch": 3.1,
"learning_rate": 9.713957380898849e-06,
"loss": 6.0732,
"step": 124500
},
{
"epoch": 3.11,
"learning_rate": 9.712708286492294e-06,
"loss": 6.0741,
"step": 125000
},
{
"epoch": 3.13,
"learning_rate": 9.711459192085739e-06,
"loss": 6.0739,
"step": 125500
},
{
"epoch": 3.14,
"learning_rate": 9.710210097679184e-06,
"loss": 6.0651,
"step": 126000
},
{
"epoch": 3.15,
"learning_rate": 9.708961003272628e-06,
"loss": 6.0687,
"step": 126500
},
{
"epoch": 3.16,
"learning_rate": 9.707711908866073e-06,
"loss": 6.0694,
"step": 127000
},
{
"epoch": 3.18,
"learning_rate": 9.706462814459518e-06,
"loss": 6.0694,
"step": 127500
},
{
"epoch": 3.19,
"learning_rate": 9.705213720052963e-06,
"loss": 6.0694,
"step": 128000
},
{
"epoch": 3.2,
"learning_rate": 9.703964625646408e-06,
"loss": 6.0666,
"step": 128500
},
{
"epoch": 3.21,
"learning_rate": 9.702715531239853e-06,
"loss": 6.0722,
"step": 129000
},
{
"epoch": 3.23,
"learning_rate": 9.701466436833297e-06,
"loss": 6.0669,
"step": 129500
},
{
"epoch": 3.24,
"learning_rate": 9.70021734242674e-06,
"loss": 6.0658,
"step": 130000
},
{
"epoch": 3.25,
"learning_rate": 9.698968248020187e-06,
"loss": 6.0709,
"step": 130500
},
{
"epoch": 3.26,
"learning_rate": 9.69771915361363e-06,
"loss": 6.0678,
"step": 131000
},
{
"epoch": 3.28,
"learning_rate": 9.696470059207075e-06,
"loss": 6.0652,
"step": 131500
},
{
"epoch": 3.29,
"learning_rate": 9.69522096480052e-06,
"loss": 6.0616,
"step": 132000
},
{
"epoch": 3.3,
"learning_rate": 9.693971870393965e-06,
"loss": 6.0678,
"step": 132500
},
{
"epoch": 3.31,
"learning_rate": 9.69272277598741e-06,
"loss": 6.0641,
"step": 133000
},
{
"epoch": 3.33,
"learning_rate": 9.691473681580855e-06,
"loss": 6.0657,
"step": 133500
},
{
"epoch": 3.34,
"learning_rate": 9.6902245871743e-06,
"loss": 6.0652,
"step": 134000
},
{
"epoch": 3.35,
"learning_rate": 9.688975492767744e-06,
"loss": 6.0599,
"step": 134500
},
{
"epoch": 3.36,
"learning_rate": 9.687726398361189e-06,
"loss": 6.0604,
"step": 135000
},
{
"epoch": 3.38,
"learning_rate": 9.686477303954634e-06,
"loss": 6.0623,
"step": 135500
},
{
"epoch": 3.39,
"learning_rate": 9.685228209548079e-06,
"loss": 6.0585,
"step": 136000
},
{
"epoch": 3.4,
"learning_rate": 9.683979115141524e-06,
"loss": 6.0612,
"step": 136500
},
{
"epoch": 3.41,
"learning_rate": 9.682730020734968e-06,
"loss": 6.0629,
"step": 137000
},
{
"epoch": 3.43,
"learning_rate": 9.681480926328413e-06,
"loss": 6.0595,
"step": 137500
},
{
"epoch": 3.44,
"learning_rate": 9.680231831921856e-06,
"loss": 6.057,
"step": 138000
},
{
"epoch": 3.45,
"learning_rate": 9.678982737515303e-06,
"loss": 6.0643,
"step": 138500
},
{
"epoch": 3.46,
"learning_rate": 9.677733643108746e-06,
"loss": 6.0567,
"step": 139000
},
{
"epoch": 3.48,
"learning_rate": 9.676484548702193e-06,
"loss": 6.0585,
"step": 139500
},
{
"epoch": 3.49,
"learning_rate": 9.675235454295636e-06,
"loss": 6.0585,
"step": 140000
},
{
"epoch": 3.5,
"learning_rate": 9.67398635988908e-06,
"loss": 6.0542,
"step": 140500
},
{
"epoch": 3.51,
"learning_rate": 9.672737265482526e-06,
"loss": 6.0544,
"step": 141000
},
{
"epoch": 3.53,
"learning_rate": 9.67148817107597e-06,
"loss": 6.0551,
"step": 141500
},
{
"epoch": 3.54,
"learning_rate": 9.670239076669415e-06,
"loss": 6.0565,
"step": 142000
},
{
"epoch": 3.55,
"learning_rate": 9.66898998226286e-06,
"loss": 6.0558,
"step": 142500
},
{
"epoch": 3.56,
"learning_rate": 9.667740887856305e-06,
"loss": 6.054,
"step": 143000
},
{
"epoch": 3.58,
"learning_rate": 9.66649179344975e-06,
"loss": 6.0524,
"step": 143500
},
{
"epoch": 3.59,
"learning_rate": 9.665242699043195e-06,
"loss": 6.0545,
"step": 144000
},
{
"epoch": 3.6,
"learning_rate": 9.66399360463664e-06,
"loss": 6.0498,
"step": 144500
},
{
"epoch": 3.61,
"learning_rate": 9.662744510230084e-06,
"loss": 6.0524,
"step": 145000
},
{
"epoch": 3.63,
"learning_rate": 9.66149541582353e-06,
"loss": 6.0503,
"step": 145500
},
{
"epoch": 3.64,
"learning_rate": 9.660246321416974e-06,
"loss": 6.0526,
"step": 146000
},
{
"epoch": 3.65,
"learning_rate": 9.658997227010419e-06,
"loss": 6.052,
"step": 146500
},
{
"epoch": 3.66,
"learning_rate": 9.657748132603862e-06,
"loss": 6.0499,
"step": 147000
},
{
"epoch": 3.68,
"learning_rate": 9.656499038197309e-06,
"loss": 6.049,
"step": 147500
},
{
"epoch": 3.69,
"learning_rate": 9.655249943790752e-06,
"loss": 6.0468,
"step": 148000
},
{
"epoch": 3.7,
"learning_rate": 9.654000849384198e-06,
"loss": 6.0464,
"step": 148500
},
{
"epoch": 3.71,
"learning_rate": 9.652751754977641e-06,
"loss": 6.0497,
"step": 149000
},
{
"epoch": 3.73,
"learning_rate": 9.651502660571086e-06,
"loss": 6.0488,
"step": 149500
},
{
"epoch": 3.74,
"learning_rate": 9.650253566164531e-06,
"loss": 6.0488,
"step": 150000
},
{
"epoch": 3.75,
"learning_rate": 9.649004471757976e-06,
"loss": 6.048,
"step": 150500
},
{
"epoch": 3.76,
"learning_rate": 9.64775537735142e-06,
"loss": 6.0477,
"step": 151000
},
{
"epoch": 3.78,
"learning_rate": 9.646506282944866e-06,
"loss": 6.0453,
"step": 151500
},
{
"epoch": 3.79,
"learning_rate": 9.64525718853831e-06,
"loss": 6.0498,
"step": 152000
},
{
"epoch": 3.8,
"learning_rate": 9.644008094131755e-06,
"loss": 6.0415,
"step": 152500
},
{
"epoch": 3.81,
"learning_rate": 9.6427589997252e-06,
"loss": 6.0485,
"step": 153000
},
{
"epoch": 3.83,
"learning_rate": 9.641509905318645e-06,
"loss": 6.045,
"step": 153500
},
{
"epoch": 3.84,
"learning_rate": 9.64026081091209e-06,
"loss": 6.0411,
"step": 154000
},
{
"epoch": 3.85,
"learning_rate": 9.639011716505535e-06,
"loss": 6.0454,
"step": 154500
},
{
"epoch": 3.86,
"learning_rate": 9.63776262209898e-06,
"loss": 6.0465,
"step": 155000
},
{
"epoch": 3.88,
"learning_rate": 9.636513527692424e-06,
"loss": 6.0447,
"step": 155500
},
{
"epoch": 3.89,
"learning_rate": 9.635264433285868e-06,
"loss": 6.0448,
"step": 156000
},
{
"epoch": 3.9,
"learning_rate": 9.634015338879314e-06,
"loss": 6.0393,
"step": 156500
},
{
"epoch": 3.91,
"learning_rate": 9.632766244472757e-06,
"loss": 6.0371,
"step": 157000
},
{
"epoch": 3.92,
"learning_rate": 9.631517150066204e-06,
"loss": 6.0396,
"step": 157500
},
{
"epoch": 3.94,
"learning_rate": 9.630268055659647e-06,
"loss": 6.0449,
"step": 158000
},
{
"epoch": 3.95,
"learning_rate": 9.629018961253092e-06,
"loss": 6.0435,
"step": 158500
},
{
"epoch": 3.96,
"learning_rate": 9.627769866846537e-06,
"loss": 6.0418,
"step": 159000
},
{
"epoch": 3.97,
"learning_rate": 9.626520772439982e-06,
"loss": 6.0434,
"step": 159500
},
{
"epoch": 3.99,
"learning_rate": 9.625271678033426e-06,
"loss": 6.0391,
"step": 160000
},
{
"epoch": 4.0,
"learning_rate": 9.624022583626871e-06,
"loss": 6.0398,
"step": 160500
},
{
"epoch": 4.01,
"learning_rate": 9.622773489220316e-06,
"loss": 6.0357,
"step": 161000
},
{
"epoch": 4.02,
"learning_rate": 9.621524394813761e-06,
"loss": 6.0388,
"step": 161500
},
{
"epoch": 4.04,
"learning_rate": 9.620275300407206e-06,
"loss": 6.0386,
"step": 162000
},
{
"epoch": 4.05,
"learning_rate": 9.61902620600065e-06,
"loss": 6.0385,
"step": 162500
},
{
"epoch": 4.06,
"learning_rate": 9.617777111594095e-06,
"loss": 6.0352,
"step": 163000
},
{
"epoch": 4.07,
"learning_rate": 9.61652801718754e-06,
"loss": 6.0352,
"step": 163500
},
{
"epoch": 4.09,
"learning_rate": 9.615278922780985e-06,
"loss": 6.0356,
"step": 164000
},
{
"epoch": 4.1,
"learning_rate": 9.61402982837443e-06,
"loss": 6.0375,
"step": 164500
},
{
"epoch": 4.11,
"learning_rate": 9.612780733967873e-06,
"loss": 6.0354,
"step": 165000
},
{
"epoch": 4.12,
"learning_rate": 9.61153163956132e-06,
"loss": 6.0326,
"step": 165500
},
{
"epoch": 4.14,
"learning_rate": 9.610282545154763e-06,
"loss": 6.0334,
"step": 166000
},
{
"epoch": 4.15,
"learning_rate": 9.60903345074821e-06,
"loss": 6.0363,
"step": 166500
},
{
"epoch": 4.16,
"learning_rate": 9.607784356341653e-06,
"loss": 6.033,
"step": 167000
},
{
"epoch": 4.17,
"learning_rate": 9.606535261935097e-06,
"loss": 6.0339,
"step": 167500
},
{
"epoch": 4.19,
"learning_rate": 9.605286167528542e-06,
"loss": 6.0353,
"step": 168000
},
{
"epoch": 4.2,
"learning_rate": 9.604037073121987e-06,
"loss": 6.0288,
"step": 168500
},
{
"epoch": 4.21,
"learning_rate": 9.602787978715432e-06,
"loss": 6.0299,
"step": 169000
},
{
"epoch": 4.22,
"learning_rate": 9.601538884308877e-06,
"loss": 6.032,
"step": 169500
},
{
"epoch": 4.24,
"learning_rate": 9.600289789902322e-06,
"loss": 6.0333,
"step": 170000
},
{
"epoch": 4.25,
"learning_rate": 9.599040695495767e-06,
"loss": 6.032,
"step": 170500
},
{
"epoch": 4.26,
"learning_rate": 9.597791601089211e-06,
"loss": 6.0298,
"step": 171000
},
{
"epoch": 4.27,
"learning_rate": 9.596542506682656e-06,
"loss": 6.0287,
"step": 171500
},
{
"epoch": 4.29,
"learning_rate": 9.595293412276101e-06,
"loss": 6.0291,
"step": 172000
},
{
"epoch": 4.3,
"learning_rate": 9.594044317869546e-06,
"loss": 6.0299,
"step": 172500
},
{
"epoch": 4.31,
"learning_rate": 9.59279522346299e-06,
"loss": 6.0281,
"step": 173000
},
{
"epoch": 4.32,
"learning_rate": 9.591546129056436e-06,
"loss": 6.0342,
"step": 173500
},
{
"epoch": 4.34,
"learning_rate": 9.590297034649879e-06,
"loss": 6.0276,
"step": 174000
},
{
"epoch": 4.35,
"learning_rate": 9.589047940243325e-06,
"loss": 6.0294,
"step": 174500
},
{
"epoch": 4.36,
"learning_rate": 9.587798845836768e-06,
"loss": 6.0289,
"step": 175000
},
{
"epoch": 4.37,
"learning_rate": 9.586549751430215e-06,
"loss": 6.0294,
"step": 175500
},
{
"epoch": 4.39,
"learning_rate": 9.585300657023658e-06,
"loss": 6.0238,
"step": 176000
},
{
"epoch": 4.4,
"learning_rate": 9.584051562617103e-06,
"loss": 6.0275,
"step": 176500
},
{
"epoch": 4.41,
"learning_rate": 9.582802468210548e-06,
"loss": 6.0265,
"step": 177000
},
{
"epoch": 4.42,
"learning_rate": 9.581553373803993e-06,
"loss": 6.031,
"step": 177500
},
{
"epoch": 4.44,
"learning_rate": 9.580304279397438e-06,
"loss": 6.0223,
"step": 178000
},
{
"epoch": 4.45,
"learning_rate": 9.579055184990882e-06,
"loss": 6.0269,
"step": 178500
},
{
"epoch": 4.46,
"learning_rate": 9.577806090584327e-06,
"loss": 6.0224,
"step": 179000
},
{
"epoch": 4.47,
"learning_rate": 9.576556996177772e-06,
"loss": 6.0271,
"step": 179500
},
{
"epoch": 4.49,
"learning_rate": 9.575307901771217e-06,
"loss": 6.0279,
"step": 180000
},
{
"epoch": 4.5,
"learning_rate": 9.574058807364662e-06,
"loss": 6.0238,
"step": 180500
},
{
"epoch": 4.51,
"learning_rate": 9.572809712958107e-06,
"loss": 6.0242,
"step": 181000
},
{
"epoch": 4.52,
"learning_rate": 9.571560618551551e-06,
"loss": 6.0225,
"step": 181500
},
{
"epoch": 4.54,
"learning_rate": 9.570311524144996e-06,
"loss": 6.0234,
"step": 182000
},
{
"epoch": 4.55,
"learning_rate": 9.569062429738441e-06,
"loss": 6.0261,
"step": 182500
},
{
"epoch": 4.56,
"learning_rate": 9.567813335331884e-06,
"loss": 6.0189,
"step": 183000
},
{
"epoch": 4.57,
"learning_rate": 9.566564240925331e-06,
"loss": 6.0232,
"step": 183500
},
{
"epoch": 4.59,
"learning_rate": 9.565315146518774e-06,
"loss": 6.0206,
"step": 184000
},
{
"epoch": 4.6,
"learning_rate": 9.564066052112219e-06,
"loss": 6.0262,
"step": 184500
},
{
"epoch": 4.61,
"learning_rate": 9.562816957705664e-06,
"loss": 6.0263,
"step": 185000
},
{
"epoch": 4.62,
"learning_rate": 9.561567863299109e-06,
"loss": 6.018,
"step": 185500
},
{
"epoch": 4.64,
"learning_rate": 9.560318768892553e-06,
"loss": 6.0234,
"step": 186000
},
{
"epoch": 4.65,
"learning_rate": 9.559069674485998e-06,
"loss": 6.0215,
"step": 186500
},
{
"epoch": 4.66,
"learning_rate": 9.557820580079443e-06,
"loss": 6.0209,
"step": 187000
},
{
"epoch": 4.67,
"learning_rate": 9.556571485672888e-06,
"loss": 6.0214,
"step": 187500
},
{
"epoch": 4.68,
"learning_rate": 9.555322391266333e-06,
"loss": 6.0206,
"step": 188000
},
{
"epoch": 4.7,
"learning_rate": 9.554073296859778e-06,
"loss": 6.0139,
"step": 188500
},
{
"epoch": 4.71,
"learning_rate": 9.552824202453223e-06,
"loss": 6.0214,
"step": 189000
},
{
"epoch": 4.72,
"learning_rate": 9.551575108046667e-06,
"loss": 6.0184,
"step": 189500
},
{
"epoch": 4.73,
"learning_rate": 9.550326013640112e-06,
"loss": 6.0165,
"step": 190000
},
{
"epoch": 4.75,
"learning_rate": 9.549076919233557e-06,
"loss": 6.0177,
"step": 190500
},
{
"epoch": 4.76,
"learning_rate": 9.547827824827e-06,
"loss": 6.0187,
"step": 191000
},
{
"epoch": 4.77,
"learning_rate": 9.546578730420447e-06,
"loss": 6.0173,
"step": 191500
},
{
"epoch": 4.78,
"learning_rate": 9.54532963601389e-06,
"loss": 6.02,
"step": 192000
},
{
"epoch": 4.8,
"learning_rate": 9.544080541607336e-06,
"loss": 6.0216,
"step": 192500
},
{
"epoch": 4.81,
"learning_rate": 9.54283144720078e-06,
"loss": 6.0193,
"step": 193000
},
{
"epoch": 4.82,
"learning_rate": 9.541582352794224e-06,
"loss": 6.0145,
"step": 193500
},
{
"epoch": 4.83,
"learning_rate": 9.54033325838767e-06,
"loss": 6.0186,
"step": 194000
},
{
"epoch": 4.85,
"learning_rate": 9.539084163981114e-06,
"loss": 6.0182,
"step": 194500
},
{
"epoch": 4.86,
"learning_rate": 9.537835069574559e-06,
"loss": 6.0138,
"step": 195000
},
{
"epoch": 4.87,
"learning_rate": 9.536585975168004e-06,
"loss": 6.0153,
"step": 195500
},
{
"epoch": 4.88,
"learning_rate": 9.535336880761449e-06,
"loss": 6.0122,
"step": 196000
},
{
"epoch": 4.9,
"learning_rate": 9.534087786354894e-06,
"loss": 6.0161,
"step": 196500
},
{
"epoch": 4.91,
"learning_rate": 9.532838691948338e-06,
"loss": 6.0163,
"step": 197000
},
{
"epoch": 4.92,
"learning_rate": 9.531589597541783e-06,
"loss": 6.0121,
"step": 197500
},
{
"epoch": 4.93,
"learning_rate": 9.530340503135228e-06,
"loss": 6.0146,
"step": 198000
},
{
"epoch": 4.95,
"learning_rate": 9.529091408728673e-06,
"loss": 6.0142,
"step": 198500
},
{
"epoch": 4.96,
"learning_rate": 9.527842314322118e-06,
"loss": 6.0156,
"step": 199000
},
{
"epoch": 4.97,
"learning_rate": 9.526593219915563e-06,
"loss": 6.0134,
"step": 199500
},
{
"epoch": 4.98,
"learning_rate": 9.525344125509006e-06,
"loss": 6.0138,
"step": 200000
},
{
"epoch": 5.0,
"learning_rate": 9.524095031102452e-06,
"loss": 6.0177,
"step": 200500
},
{
"epoch": 5.01,
"learning_rate": 9.522845936695895e-06,
"loss": 6.0087,
"step": 201000
},
{
"epoch": 5.02,
"learning_rate": 9.521596842289342e-06,
"loss": 6.0101,
"step": 201500
},
{
"epoch": 5.03,
"learning_rate": 9.520347747882785e-06,
"loss": 6.0142,
"step": 202000
},
{
"epoch": 5.05,
"learning_rate": 9.51909865347623e-06,
"loss": 6.0101,
"step": 202500
},
{
"epoch": 5.06,
"learning_rate": 9.517849559069675e-06,
"loss": 6.0113,
"step": 203000
},
{
"epoch": 5.07,
"learning_rate": 9.51660046466312e-06,
"loss": 6.0075,
"step": 203500
},
{
"epoch": 5.08,
"learning_rate": 9.515351370256565e-06,
"loss": 6.0078,
"step": 204000
},
{
"epoch": 5.1,
"learning_rate": 9.51410227585001e-06,
"loss": 6.0128,
"step": 204500
},
{
"epoch": 5.11,
"learning_rate": 9.512853181443454e-06,
"loss": 6.0083,
"step": 205000
},
{
"epoch": 5.12,
"learning_rate": 9.511604087036899e-06,
"loss": 6.0133,
"step": 205500
},
{
"epoch": 5.13,
"learning_rate": 9.510354992630344e-06,
"loss": 6.0098,
"step": 206000
},
{
"epoch": 5.15,
"learning_rate": 9.509105898223789e-06,
"loss": 6.0083,
"step": 206500
},
{
"epoch": 5.16,
"learning_rate": 9.507856803817234e-06,
"loss": 6.0122,
"step": 207000
},
{
"epoch": 5.17,
"learning_rate": 9.506607709410678e-06,
"loss": 6.0088,
"step": 207500
},
{
"epoch": 5.18,
"learning_rate": 9.505358615004123e-06,
"loss": 6.0073,
"step": 208000
},
{
"epoch": 5.2,
"learning_rate": 9.504109520597568e-06,
"loss": 6.0085,
"step": 208500
},
{
"epoch": 5.21,
"learning_rate": 9.502860426191011e-06,
"loss": 6.0131,
"step": 209000
},
{
"epoch": 5.22,
"learning_rate": 9.501611331784458e-06,
"loss": 6.0072,
"step": 209500
},
{
"epoch": 5.23,
"learning_rate": 9.500362237377901e-06,
"loss": 6.0067,
"step": 210000
},
{
"epoch": 5.25,
"learning_rate": 9.499113142971348e-06,
"loss": 6.0031,
"step": 210500
},
{
"epoch": 5.26,
"learning_rate": 9.49786404856479e-06,
"loss": 6.003,
"step": 211000
},
{
"epoch": 5.27,
"learning_rate": 9.496614954158236e-06,
"loss": 6.007,
"step": 211500
},
{
"epoch": 5.28,
"learning_rate": 9.49536585975168e-06,
"loss": 6.0082,
"step": 212000
},
{
"epoch": 5.3,
"learning_rate": 9.494116765345125e-06,
"loss": 6.0088,
"step": 212500
},
{
"epoch": 5.31,
"learning_rate": 9.49286767093857e-06,
"loss": 6.0056,
"step": 213000
},
{
"epoch": 5.32,
"learning_rate": 9.491618576532015e-06,
"loss": 6.001,
"step": 213500
},
{
"epoch": 5.33,
"learning_rate": 9.49036948212546e-06,
"loss": 6.0087,
"step": 214000
},
{
"epoch": 5.35,
"learning_rate": 9.489120387718905e-06,
"loss": 6.0057,
"step": 214500
},
{
"epoch": 5.36,
"learning_rate": 9.48787129331235e-06,
"loss": 6.007,
"step": 215000
},
{
"epoch": 5.37,
"learning_rate": 9.486622198905794e-06,
"loss": 6.005,
"step": 215500
},
{
"epoch": 5.38,
"learning_rate": 9.48537310449924e-06,
"loss": 6.0037,
"step": 216000
},
{
"epoch": 5.4,
"learning_rate": 9.484124010092684e-06,
"loss": 6.0051,
"step": 216500
},
{
"epoch": 5.41,
"learning_rate": 9.482874915686129e-06,
"loss": 6.0065,
"step": 217000
},
{
"epoch": 5.42,
"learning_rate": 9.481625821279574e-06,
"loss": 6.0025,
"step": 217500
},
{
"epoch": 5.43,
"learning_rate": 9.480376726873017e-06,
"loss": 6.0007,
"step": 218000
},
{
"epoch": 5.44,
"learning_rate": 9.479127632466463e-06,
"loss": 6.0004,
"step": 218500
},
{
"epoch": 5.46,
"learning_rate": 9.477878538059907e-06,
"loss": 5.9987,
"step": 219000
},
{
"epoch": 5.47,
"learning_rate": 9.476629443653353e-06,
"loss": 6.0011,
"step": 219500
},
{
"epoch": 5.48,
"learning_rate": 9.475380349246796e-06,
"loss": 6.0018,
"step": 220000
},
{
"epoch": 5.49,
"learning_rate": 9.474131254840241e-06,
"loss": 6.0012,
"step": 220500
},
{
"epoch": 5.51,
"learning_rate": 9.472882160433686e-06,
"loss": 6.0023,
"step": 221000
},
{
"epoch": 5.52,
"learning_rate": 9.471633066027131e-06,
"loss": 5.9965,
"step": 221500
},
{
"epoch": 5.53,
"learning_rate": 9.470383971620576e-06,
"loss": 6.0052,
"step": 222000
},
{
"epoch": 5.54,
"learning_rate": 9.46913487721402e-06,
"loss": 6.0041,
"step": 222500
},
{
"epoch": 5.56,
"learning_rate": 9.467885782807465e-06,
"loss": 5.9988,
"step": 223000
},
{
"epoch": 5.57,
"learning_rate": 9.46663668840091e-06,
"loss": 6.0003,
"step": 223500
},
{
"epoch": 5.58,
"learning_rate": 9.465387593994355e-06,
"loss": 5.997,
"step": 224000
},
{
"epoch": 5.59,
"learning_rate": 9.4641384995878e-06,
"loss": 6.005,
"step": 224500
},
{
"epoch": 5.61,
"learning_rate": 9.462889405181245e-06,
"loss": 6.0023,
"step": 225000
},
{
"epoch": 5.62,
"learning_rate": 9.46164031077469e-06,
"loss": 6.0026,
"step": 225500
},
{
"epoch": 5.63,
"learning_rate": 9.460391216368134e-06,
"loss": 5.9982,
"step": 226000
},
{
"epoch": 5.64,
"learning_rate": 9.45914212196158e-06,
"loss": 6.0,
"step": 226500
},
{
"epoch": 5.66,
"learning_rate": 9.457893027555022e-06,
"loss": 5.999,
"step": 227000
},
{
"epoch": 5.67,
"learning_rate": 9.456643933148469e-06,
"loss": 5.9982,
"step": 227500
},
{
"epoch": 5.68,
"learning_rate": 9.455394838741912e-06,
"loss": 5.9971,
"step": 228000
},
{
"epoch": 5.69,
"learning_rate": 9.454145744335359e-06,
"loss": 5.9912,
"step": 228500
},
{
"epoch": 5.71,
"learning_rate": 9.452896649928802e-06,
"loss": 5.9952,
"step": 229000
},
{
"epoch": 5.72,
"learning_rate": 9.451647555522247e-06,
"loss": 6.0016,
"step": 229500
},
{
"epoch": 5.73,
"learning_rate": 9.450398461115692e-06,
"loss": 5.9937,
"step": 230000
},
{
"epoch": 5.74,
"learning_rate": 9.449149366709136e-06,
"loss": 5.9954,
"step": 230500
},
{
"epoch": 5.76,
"learning_rate": 9.447900272302581e-06,
"loss": 5.9948,
"step": 231000
},
{
"epoch": 5.77,
"learning_rate": 9.446651177896026e-06,
"loss": 6.0018,
"step": 231500
},
{
"epoch": 5.78,
"learning_rate": 9.445402083489471e-06,
"loss": 5.9968,
"step": 232000
},
{
"epoch": 5.79,
"learning_rate": 9.444152989082916e-06,
"loss": 5.9948,
"step": 232500
},
{
"epoch": 5.81,
"learning_rate": 9.44290389467636e-06,
"loss": 5.9927,
"step": 233000
},
{
"epoch": 5.82,
"learning_rate": 9.441654800269806e-06,
"loss": 5.9954,
"step": 233500
},
{
"epoch": 5.83,
"learning_rate": 9.44040570586325e-06,
"loss": 5.9971,
"step": 234000
},
{
"epoch": 5.84,
"learning_rate": 9.439156611456695e-06,
"loss": 5.9972,
"step": 234500
},
{
"epoch": 5.86,
"learning_rate": 9.43790751705014e-06,
"loss": 5.9937,
"step": 235000
},
{
"epoch": 5.87,
"learning_rate": 9.436658422643585e-06,
"loss": 5.9954,
"step": 235500
},
{
"epoch": 5.88,
"learning_rate": 9.435409328237028e-06,
"loss": 5.9952,
"step": 236000
},
{
"epoch": 5.89,
"learning_rate": 9.434160233830475e-06,
"loss": 5.9954,
"step": 236500
},
{
"epoch": 5.91,
"learning_rate": 9.432911139423918e-06,
"loss": 5.9961,
"step": 237000
},
{
"epoch": 5.92,
"learning_rate": 9.431662045017364e-06,
"loss": 5.992,
"step": 237500
},
{
"epoch": 5.93,
"learning_rate": 9.430412950610807e-06,
"loss": 5.9949,
"step": 238000
},
{
"epoch": 5.94,
"learning_rate": 9.429163856204252e-06,
"loss": 5.9919,
"step": 238500
},
{
"epoch": 5.96,
"learning_rate": 9.427914761797697e-06,
"loss": 5.9904,
"step": 239000
},
{
"epoch": 5.97,
"learning_rate": 9.426665667391142e-06,
"loss": 5.9917,
"step": 239500
},
{
"epoch": 5.98,
"learning_rate": 9.425416572984587e-06,
"loss": 5.9961,
"step": 240000
},
{
"epoch": 5.99,
"learning_rate": 9.424167478578032e-06,
"loss": 5.9929,
"step": 240500
},
{
"epoch": 6.01,
"learning_rate": 9.422918384171477e-06,
"loss": 5.9923,
"step": 241000
},
{
"epoch": 6.02,
"learning_rate": 9.421669289764921e-06,
"loss": 5.991,
"step": 241500
},
{
"epoch": 6.03,
"learning_rate": 9.420420195358366e-06,
"loss": 5.992,
"step": 242000
},
{
"epoch": 6.04,
"learning_rate": 9.419171100951811e-06,
"loss": 5.9916,
"step": 242500
},
{
"epoch": 6.06,
"learning_rate": 9.417922006545256e-06,
"loss": 5.992,
"step": 243000
},
{
"epoch": 6.07,
"learning_rate": 9.4166729121387e-06,
"loss": 5.9911,
"step": 243500
},
{
"epoch": 6.08,
"learning_rate": 9.415423817732144e-06,
"loss": 5.99,
"step": 244000
},
{
"epoch": 6.09,
"learning_rate": 9.41417472332559e-06,
"loss": 5.9864,
"step": 244500
},
{
"epoch": 6.11,
"learning_rate": 9.412925628919034e-06,
"loss": 5.9897,
"step": 245000
},
{
"epoch": 6.12,
"learning_rate": 9.41167653451248e-06,
"loss": 5.9899,
"step": 245500
},
{
"epoch": 6.13,
"learning_rate": 9.410427440105923e-06,
"loss": 5.9905,
"step": 246000
},
{
"epoch": 6.14,
"learning_rate": 9.40917834569937e-06,
"loss": 5.9901,
"step": 246500
},
{
"epoch": 6.16,
"learning_rate": 9.407929251292813e-06,
"loss": 5.9859,
"step": 247000
},
{
"epoch": 6.17,
"learning_rate": 9.406680156886258e-06,
"loss": 5.9881,
"step": 247500
},
{
"epoch": 6.18,
"learning_rate": 9.405431062479703e-06,
"loss": 5.9898,
"step": 248000
},
{
"epoch": 6.19,
"learning_rate": 9.404181968073148e-06,
"loss": 5.9884,
"step": 248500
},
{
"epoch": 6.2,
"learning_rate": 9.402932873666592e-06,
"loss": 5.9894,
"step": 249000
},
{
"epoch": 6.22,
"learning_rate": 9.401683779260037e-06,
"loss": 5.988,
"step": 249500
},
{
"epoch": 6.23,
"learning_rate": 9.400434684853482e-06,
"loss": 5.9869,
"step": 250000
},
{
"epoch": 6.24,
"learning_rate": 9.399185590446927e-06,
"loss": 5.9883,
"step": 250500
},
{
"epoch": 6.25,
"learning_rate": 9.397936496040372e-06,
"loss": 5.9891,
"step": 251000
},
{
"epoch": 6.27,
"learning_rate": 9.396687401633817e-06,
"loss": 5.9912,
"step": 251500
},
{
"epoch": 6.28,
"learning_rate": 9.395438307227261e-06,
"loss": 5.9847,
"step": 252000
},
{
"epoch": 6.29,
"learning_rate": 9.394189212820706e-06,
"loss": 5.9904,
"step": 252500
},
{
"epoch": 6.3,
"learning_rate": 9.39294011841415e-06,
"loss": 5.9865,
"step": 253000
},
{
"epoch": 6.32,
"learning_rate": 9.391691024007596e-06,
"loss": 5.9874,
"step": 253500
},
{
"epoch": 6.33,
"learning_rate": 9.39044192960104e-06,
"loss": 5.9853,
"step": 254000
},
{
"epoch": 6.34,
"learning_rate": 9.389192835194486e-06,
"loss": 5.9822,
"step": 254500
},
{
"epoch": 6.35,
"learning_rate": 9.387943740787929e-06,
"loss": 5.986,
"step": 255000
},
{
"epoch": 6.37,
"learning_rate": 9.386694646381375e-06,
"loss": 5.9893,
"step": 255500
},
{
"epoch": 6.38,
"learning_rate": 9.385445551974819e-06,
"loss": 5.9846,
"step": 256000
},
{
"epoch": 6.39,
"learning_rate": 9.384196457568263e-06,
"loss": 5.9854,
"step": 256500
},
{
"epoch": 6.4,
"learning_rate": 9.382947363161708e-06,
"loss": 5.9866,
"step": 257000
},
{
"epoch": 6.42,
"learning_rate": 9.381698268755153e-06,
"loss": 5.9839,
"step": 257500
},
{
"epoch": 6.43,
"learning_rate": 9.380449174348598e-06,
"loss": 5.9839,
"step": 258000
},
{
"epoch": 6.44,
"learning_rate": 9.379200079942043e-06,
"loss": 5.9843,
"step": 258500
},
{
"epoch": 6.45,
"learning_rate": 9.377950985535488e-06,
"loss": 5.9824,
"step": 259000
},
{
"epoch": 6.47,
"learning_rate": 9.376701891128933e-06,
"loss": 5.9847,
"step": 259500
},
{
"epoch": 6.48,
"learning_rate": 9.375452796722377e-06,
"loss": 5.9819,
"step": 260000
},
{
"epoch": 6.49,
"learning_rate": 9.374203702315822e-06,
"loss": 5.9829,
"step": 260500
},
{
"epoch": 6.5,
"learning_rate": 9.372954607909267e-06,
"loss": 5.9872,
"step": 261000
},
{
"epoch": 6.52,
"learning_rate": 9.371705513502712e-06,
"loss": 5.9882,
"step": 261500
},
{
"epoch": 6.53,
"learning_rate": 9.370456419096155e-06,
"loss": 5.9803,
"step": 262000
},
{
"epoch": 6.54,
"learning_rate": 9.369207324689602e-06,
"loss": 5.9845,
"step": 262500
},
{
"epoch": 6.55,
"learning_rate": 9.367958230283045e-06,
"loss": 5.9785,
"step": 263000
},
{
"epoch": 6.57,
"learning_rate": 9.366709135876491e-06,
"loss": 5.9843,
"step": 263500
},
{
"epoch": 6.58,
"learning_rate": 9.365460041469934e-06,
"loss": 5.9825,
"step": 264000
},
{
"epoch": 6.59,
"learning_rate": 9.364210947063381e-06,
"loss": 5.9841,
"step": 264500
},
{
"epoch": 6.6,
"learning_rate": 9.362961852656824e-06,
"loss": 5.9839,
"step": 265000
},
{
"epoch": 6.62,
"learning_rate": 9.361712758250269e-06,
"loss": 5.9824,
"step": 265500
},
{
"epoch": 6.63,
"learning_rate": 9.360463663843714e-06,
"loss": 5.9819,
"step": 266000
},
{
"epoch": 6.64,
"learning_rate": 9.359214569437159e-06,
"loss": 5.9824,
"step": 266500
},
{
"epoch": 6.65,
"learning_rate": 9.357965475030604e-06,
"loss": 5.9831,
"step": 267000
},
{
"epoch": 6.67,
"learning_rate": 9.356716380624048e-06,
"loss": 5.9821,
"step": 267500
},
{
"epoch": 6.68,
"learning_rate": 9.355467286217493e-06,
"loss": 5.9822,
"step": 268000
},
{
"epoch": 6.69,
"learning_rate": 9.354218191810938e-06,
"loss": 5.9814,
"step": 268500
},
{
"epoch": 6.7,
"learning_rate": 9.352969097404383e-06,
"loss": 5.982,
"step": 269000
},
{
"epoch": 6.72,
"learning_rate": 9.351720002997828e-06,
"loss": 5.9787,
"step": 269500
},
{
"epoch": 6.73,
"learning_rate": 9.350470908591273e-06,
"loss": 5.9797,
"step": 270000
},
{
"epoch": 6.74,
"learning_rate": 9.349221814184717e-06,
"loss": 5.9803,
"step": 270500
},
{
"epoch": 6.75,
"learning_rate": 9.34797271977816e-06,
"loss": 5.9809,
"step": 271000
},
{
"epoch": 6.77,
"learning_rate": 9.346723625371607e-06,
"loss": 5.9756,
"step": 271500
},
{
"epoch": 6.78,
"learning_rate": 9.34547453096505e-06,
"loss": 5.9837,
"step": 272000
},
{
"epoch": 6.79,
"learning_rate": 9.344225436558497e-06,
"loss": 5.9786,
"step": 272500
},
{
"epoch": 6.8,
"learning_rate": 9.34297634215194e-06,
"loss": 5.9807,
"step": 273000
},
{
"epoch": 6.82,
"learning_rate": 9.341727247745387e-06,
"loss": 5.9813,
"step": 273500
},
{
"epoch": 6.83,
"learning_rate": 9.34047815333883e-06,
"loss": 5.978,
"step": 274000
},
{
"epoch": 6.84,
"learning_rate": 9.339229058932275e-06,
"loss": 5.9818,
"step": 274500
},
{
"epoch": 6.85,
"learning_rate": 9.33797996452572e-06,
"loss": 5.9766,
"step": 275000
},
{
"epoch": 6.87,
"learning_rate": 9.336730870119164e-06,
"loss": 5.9797,
"step": 275500
},
{
"epoch": 6.88,
"learning_rate": 9.335481775712609e-06,
"loss": 5.9789,
"step": 276000
},
{
"epoch": 6.89,
"learning_rate": 9.334232681306054e-06,
"loss": 5.9738,
"step": 276500
},
{
"epoch": 6.9,
"learning_rate": 9.332983586899499e-06,
"loss": 5.9776,
"step": 277000
},
{
"epoch": 6.92,
"learning_rate": 9.331734492492944e-06,
"loss": 5.9788,
"step": 277500
},
{
"epoch": 6.93,
"learning_rate": 9.330485398086389e-06,
"loss": 5.9773,
"step": 278000
},
{
"epoch": 6.94,
"learning_rate": 9.329236303679833e-06,
"loss": 5.9767,
"step": 278500
},
{
"epoch": 6.95,
"learning_rate": 9.327987209273278e-06,
"loss": 5.9786,
"step": 279000
},
{
"epoch": 6.97,
"learning_rate": 9.326738114866723e-06,
"loss": 5.9771,
"step": 279500
},
{
"epoch": 6.98,
"learning_rate": 9.325489020460166e-06,
"loss": 5.9764,
"step": 280000
},
{
"epoch": 6.99,
"learning_rate": 9.324239926053613e-06,
"loss": 5.9777,
"step": 280500
},
{
"epoch": 7.0,
"learning_rate": 9.322990831647056e-06,
"loss": 5.9731,
"step": 281000
},
{
"epoch": 7.01,
"learning_rate": 9.321741737240502e-06,
"loss": 5.9761,
"step": 281500
},
{
"epoch": 7.03,
"learning_rate": 9.320492642833946e-06,
"loss": 5.9802,
"step": 282000
},
{
"epoch": 7.04,
"learning_rate": 9.319243548427392e-06,
"loss": 5.9716,
"step": 282500
},
{
"epoch": 7.05,
"learning_rate": 9.317994454020835e-06,
"loss": 5.9801,
"step": 283000
},
{
"epoch": 7.06,
"learning_rate": 9.31674535961428e-06,
"loss": 5.9767,
"step": 283500
},
{
"epoch": 7.08,
"learning_rate": 9.315496265207725e-06,
"loss": 5.9766,
"step": 284000
},
{
"epoch": 7.09,
"learning_rate": 9.31424717080117e-06,
"loss": 5.9766,
"step": 284500
},
{
"epoch": 7.1,
"learning_rate": 9.312998076394615e-06,
"loss": 5.9746,
"step": 285000
},
{
"epoch": 7.11,
"learning_rate": 9.31174898198806e-06,
"loss": 5.9745,
"step": 285500
},
{
"epoch": 7.13,
"learning_rate": 9.310499887581504e-06,
"loss": 5.9721,
"step": 286000
},
{
"epoch": 7.14,
"learning_rate": 9.30925079317495e-06,
"loss": 5.9705,
"step": 286500
},
{
"epoch": 7.15,
"learning_rate": 9.308001698768394e-06,
"loss": 5.9726,
"step": 287000
},
{
"epoch": 7.16,
"learning_rate": 9.306752604361839e-06,
"loss": 5.9748,
"step": 287500
},
{
"epoch": 7.18,
"learning_rate": 9.305503509955284e-06,
"loss": 5.9721,
"step": 288000
},
{
"epoch": 7.19,
"learning_rate": 9.304254415548729e-06,
"loss": 5.9771,
"step": 288500
},
{
"epoch": 7.2,
"learning_rate": 9.303005321142172e-06,
"loss": 5.9726,
"step": 289000
},
{
"epoch": 7.21,
"learning_rate": 9.301756226735618e-06,
"loss": 5.974,
"step": 289500
},
{
"epoch": 7.23,
"learning_rate": 9.300507132329061e-06,
"loss": 5.9742,
"step": 290000
},
{
"epoch": 7.24,
"learning_rate": 9.299258037922508e-06,
"loss": 5.9694,
"step": 290500
},
{
"epoch": 7.25,
"learning_rate": 9.298008943515951e-06,
"loss": 5.9692,
"step": 291000
},
{
"epoch": 7.26,
"learning_rate": 9.296759849109398e-06,
"loss": 5.9736,
"step": 291500
},
{
"epoch": 7.28,
"learning_rate": 9.295510754702841e-06,
"loss": 5.9716,
"step": 292000
},
{
"epoch": 7.29,
"learning_rate": 9.294261660296286e-06,
"loss": 5.9719,
"step": 292500
},
{
"epoch": 7.3,
"learning_rate": 9.29301256588973e-06,
"loss": 5.9717,
"step": 293000
},
{
"epoch": 7.31,
"learning_rate": 9.291763471483175e-06,
"loss": 5.9718,
"step": 293500
},
{
"epoch": 7.33,
"learning_rate": 9.29051437707662e-06,
"loss": 5.9717,
"step": 294000
},
{
"epoch": 7.34,
"learning_rate": 9.289265282670065e-06,
"loss": 5.9752,
"step": 294500
},
{
"epoch": 7.35,
"learning_rate": 9.28801618826351e-06,
"loss": 5.9712,
"step": 295000
},
{
"epoch": 7.36,
"learning_rate": 9.286767093856955e-06,
"loss": 5.9715,
"step": 295500
},
{
"epoch": 7.38,
"learning_rate": 9.2855179994504e-06,
"loss": 5.9738,
"step": 296000
},
{
"epoch": 7.39,
"learning_rate": 9.284268905043844e-06,
"loss": 5.9719,
"step": 296500
},
{
"epoch": 7.4,
"learning_rate": 9.283019810637288e-06,
"loss": 5.9699,
"step": 297000
},
{
"epoch": 7.41,
"learning_rate": 9.281770716230734e-06,
"loss": 5.9696,
"step": 297500
},
{
"epoch": 7.43,
"learning_rate": 9.280521621824177e-06,
"loss": 5.9707,
"step": 298000
},
{
"epoch": 7.44,
"learning_rate": 9.279272527417624e-06,
"loss": 5.9695,
"step": 298500
},
{
"epoch": 7.45,
"learning_rate": 9.278023433011067e-06,
"loss": 5.9725,
"step": 299000
},
{
"epoch": 7.46,
"learning_rate": 9.276774338604514e-06,
"loss": 5.9706,
"step": 299500
},
{
"epoch": 7.48,
"learning_rate": 9.275525244197957e-06,
"loss": 5.9702,
"step": 300000
},
{
"epoch": 7.49,
"learning_rate": 9.274276149791403e-06,
"loss": 5.9716,
"step": 300500
},
{
"epoch": 7.5,
"learning_rate": 9.273027055384846e-06,
"loss": 5.9724,
"step": 301000
},
{
"epoch": 7.51,
"learning_rate": 9.271777960978291e-06,
"loss": 5.968,
"step": 301500
},
{
"epoch": 7.53,
"learning_rate": 9.270528866571736e-06,
"loss": 5.9718,
"step": 302000
},
{
"epoch": 7.54,
"learning_rate": 9.269279772165181e-06,
"loss": 5.969,
"step": 302500
},
{
"epoch": 7.55,
"learning_rate": 9.268030677758626e-06,
"loss": 5.9712,
"step": 303000
},
{
"epoch": 7.56,
"learning_rate": 9.26678158335207e-06,
"loss": 5.9714,
"step": 303500
},
{
"epoch": 7.58,
"learning_rate": 9.265532488945516e-06,
"loss": 5.9688,
"step": 304000
},
{
"epoch": 7.59,
"learning_rate": 9.26428339453896e-06,
"loss": 5.9711,
"step": 304500
},
{
"epoch": 7.6,
"learning_rate": 9.263034300132405e-06,
"loss": 5.9697,
"step": 305000
},
{
"epoch": 7.61,
"learning_rate": 9.26178520572585e-06,
"loss": 5.9704,
"step": 305500
},
{
"epoch": 7.63,
"learning_rate": 9.260536111319293e-06,
"loss": 5.9695,
"step": 306000
},
{
"epoch": 7.64,
"learning_rate": 9.25928701691274e-06,
"loss": 5.967,
"step": 306500
},
{
"epoch": 7.65,
"learning_rate": 9.258037922506183e-06,
"loss": 5.9685,
"step": 307000
},
{
"epoch": 7.66,
"learning_rate": 9.25678882809963e-06,
"loss": 5.9641,
"step": 307500
},
{
"epoch": 7.68,
"learning_rate": 9.255539733693073e-06,
"loss": 5.9678,
"step": 308000
},
{
"epoch": 7.69,
"learning_rate": 9.254290639286519e-06,
"loss": 5.9666,
"step": 308500
},
{
"epoch": 7.7,
"learning_rate": 9.253041544879962e-06,
"loss": 5.967,
"step": 309000
},
{
"epoch": 7.71,
"learning_rate": 9.251792450473409e-06,
"loss": 5.969,
"step": 309500
},
{
"epoch": 7.73,
"learning_rate": 9.250543356066852e-06,
"loss": 5.9645,
"step": 310000
},
{
"epoch": 7.74,
"learning_rate": 9.249294261660297e-06,
"loss": 5.969,
"step": 310500
},
{
"epoch": 7.75,
"learning_rate": 9.248045167253742e-06,
"loss": 5.9673,
"step": 311000
},
{
"epoch": 7.76,
"learning_rate": 9.246796072847187e-06,
"loss": 5.9662,
"step": 311500
},
{
"epoch": 7.77,
"learning_rate": 9.245546978440631e-06,
"loss": 5.9681,
"step": 312000
},
{
"epoch": 7.79,
"learning_rate": 9.244297884034076e-06,
"loss": 5.9653,
"step": 312500
},
{
"epoch": 7.8,
"learning_rate": 9.243048789627521e-06,
"loss": 5.9635,
"step": 313000
},
{
"epoch": 7.81,
"learning_rate": 9.241799695220966e-06,
"loss": 5.9661,
"step": 313500
},
{
"epoch": 7.82,
"learning_rate": 9.24055060081441e-06,
"loss": 5.9632,
"step": 314000
},
{
"epoch": 7.84,
"learning_rate": 9.239301506407856e-06,
"loss": 5.9636,
"step": 314500
},
{
"epoch": 7.85,
"learning_rate": 9.238052412001299e-06,
"loss": 5.965,
"step": 315000
},
{
"epoch": 7.86,
"learning_rate": 9.236803317594745e-06,
"loss": 5.9662,
"step": 315500
},
{
"epoch": 7.87,
"learning_rate": 9.235554223188188e-06,
"loss": 5.9649,
"step": 316000
},
{
"epoch": 7.89,
"learning_rate": 9.234305128781635e-06,
"loss": 5.9638,
"step": 316500
},
{
"epoch": 7.9,
"learning_rate": 9.233056034375078e-06,
"loss": 5.9685,
"step": 317000
},
{
"epoch": 7.91,
"learning_rate": 9.231806939968525e-06,
"loss": 5.9605,
"step": 317500
},
{
"epoch": 7.92,
"learning_rate": 9.230557845561968e-06,
"loss": 5.9654,
"step": 318000
},
{
"epoch": 7.94,
"learning_rate": 9.229308751155414e-06,
"loss": 5.9675,
"step": 318500
},
{
"epoch": 7.95,
"learning_rate": 9.228059656748858e-06,
"loss": 5.9659,
"step": 319000
},
{
"epoch": 7.96,
"learning_rate": 9.226810562342302e-06,
"loss": 5.964,
"step": 319500
},
{
"epoch": 7.97,
"learning_rate": 9.225561467935747e-06,
"loss": 5.9661,
"step": 320000
},
{
"epoch": 7.99,
"learning_rate": 9.224312373529192e-06,
"loss": 5.9619,
"step": 320500
},
{
"epoch": 8.0,
"learning_rate": 9.223063279122637e-06,
"loss": 5.966,
"step": 321000
},
{
"epoch": 8.01,
"learning_rate": 9.221814184716082e-06,
"loss": 5.9658,
"step": 321500
},
{
"epoch": 8.02,
"learning_rate": 9.220565090309527e-06,
"loss": 5.9637,
"step": 322000
},
{
"epoch": 8.04,
"learning_rate": 9.219315995902972e-06,
"loss": 5.9578,
"step": 322500
},
{
"epoch": 8.05,
"learning_rate": 9.218066901496416e-06,
"loss": 5.9627,
"step": 323000
},
{
"epoch": 8.06,
"learning_rate": 9.216817807089861e-06,
"loss": 5.9623,
"step": 323500
},
{
"epoch": 8.07,
"learning_rate": 9.215568712683304e-06,
"loss": 5.9575,
"step": 324000
},
{
"epoch": 8.09,
"learning_rate": 9.214319618276751e-06,
"loss": 5.964,
"step": 324500
},
{
"epoch": 8.1,
"learning_rate": 9.213070523870194e-06,
"loss": 5.9613,
"step": 325000
},
{
"epoch": 8.11,
"learning_rate": 9.21182142946364e-06,
"loss": 5.9616,
"step": 325500
},
{
"epoch": 8.12,
"learning_rate": 9.210572335057084e-06,
"loss": 5.9594,
"step": 326000
},
{
"epoch": 8.14,
"learning_rate": 9.20932324065053e-06,
"loss": 5.9594,
"step": 326500
},
{
"epoch": 8.15,
"learning_rate": 9.208074146243973e-06,
"loss": 5.9619,
"step": 327000
},
{
"epoch": 8.16,
"learning_rate": 9.20682505183742e-06,
"loss": 5.9608,
"step": 327500
},
{
"epoch": 8.17,
"learning_rate": 9.205575957430863e-06,
"loss": 5.9636,
"step": 328000
},
{
"epoch": 8.19,
"learning_rate": 9.204326863024308e-06,
"loss": 5.9609,
"step": 328500
},
{
"epoch": 8.2,
"learning_rate": 9.203077768617753e-06,
"loss": 5.9592,
"step": 329000
},
{
"epoch": 8.21,
"learning_rate": 9.201828674211198e-06,
"loss": 5.9632,
"step": 329500
},
{
"epoch": 8.22,
"learning_rate": 9.200579579804643e-06,
"loss": 5.9629,
"step": 330000
},
{
"epoch": 8.24,
"learning_rate": 9.199330485398087e-06,
"loss": 5.9594,
"step": 330500
},
{
"epoch": 8.25,
"learning_rate": 9.198081390991532e-06,
"loss": 5.9602,
"step": 331000
},
{
"epoch": 8.26,
"learning_rate": 9.196832296584977e-06,
"loss": 5.9624,
"step": 331500
},
{
"epoch": 8.27,
"learning_rate": 9.195583202178422e-06,
"loss": 5.9589,
"step": 332000
},
{
"epoch": 8.29,
"learning_rate": 9.194334107771867e-06,
"loss": 5.9607,
"step": 332500
},
{
"epoch": 8.3,
"learning_rate": 9.19308501336531e-06,
"loss": 5.9629,
"step": 333000
},
{
"epoch": 8.31,
"learning_rate": 9.191835918958756e-06,
"loss": 5.9629,
"step": 333500
},
{
"epoch": 8.32,
"learning_rate": 9.1905868245522e-06,
"loss": 5.9582,
"step": 334000
},
{
"epoch": 8.34,
"learning_rate": 9.189337730145646e-06,
"loss": 5.9603,
"step": 334500
},
{
"epoch": 8.35,
"learning_rate": 9.18808863573909e-06,
"loss": 5.9598,
"step": 335000
},
{
"epoch": 8.36,
"learning_rate": 9.186839541332536e-06,
"loss": 5.962,
"step": 335500
},
{
"epoch": 8.37,
"learning_rate": 9.185590446925979e-06,
"loss": 5.9592,
"step": 336000
},
{
"epoch": 8.39,
"learning_rate": 9.184341352519426e-06,
"loss": 5.9542,
"step": 336500
},
{
"epoch": 8.4,
"learning_rate": 9.183092258112869e-06,
"loss": 5.9615,
"step": 337000
},
{
"epoch": 8.41,
"learning_rate": 9.181843163706314e-06,
"loss": 5.9591,
"step": 337500
},
{
"epoch": 8.42,
"learning_rate": 9.180594069299758e-06,
"loss": 5.9599,
"step": 338000
},
{
"epoch": 8.44,
"learning_rate": 9.179344974893203e-06,
"loss": 5.9563,
"step": 338500
},
{
"epoch": 8.45,
"learning_rate": 9.178095880486648e-06,
"loss": 5.9564,
"step": 339000
},
{
"epoch": 8.46,
"learning_rate": 9.176846786080093e-06,
"loss": 5.9638,
"step": 339500
},
{
"epoch": 8.47,
"learning_rate": 9.175597691673538e-06,
"loss": 5.9582,
"step": 340000
},
{
"epoch": 8.49,
"learning_rate": 9.174348597266983e-06,
"loss": 5.9629,
"step": 340500
},
{
"epoch": 8.5,
"learning_rate": 9.173099502860427e-06,
"loss": 5.961,
"step": 341000
},
{
"epoch": 8.51,
"learning_rate": 9.171850408453872e-06,
"loss": 5.9533,
"step": 341500
},
{
"epoch": 8.52,
"learning_rate": 9.170601314047315e-06,
"loss": 5.955,
"step": 342000
},
{
"epoch": 8.53,
"learning_rate": 9.169352219640762e-06,
"loss": 5.9528,
"step": 342500
},
{
"epoch": 8.55,
"learning_rate": 9.168103125234205e-06,
"loss": 5.9597,
"step": 343000
},
{
"epoch": 8.56,
"learning_rate": 9.166854030827652e-06,
"loss": 5.9597,
"step": 343500
},
{
"epoch": 8.57,
"learning_rate": 9.165604936421095e-06,
"loss": 5.9568,
"step": 344000
},
{
"epoch": 8.58,
"learning_rate": 9.164355842014541e-06,
"loss": 5.9591,
"step": 344500
},
{
"epoch": 8.6,
"learning_rate": 9.163106747607985e-06,
"loss": 5.9573,
"step": 345000
},
{
"epoch": 8.61,
"learning_rate": 9.16185765320143e-06,
"loss": 5.956,
"step": 345500
},
{
"epoch": 8.62,
"learning_rate": 9.160608558794874e-06,
"loss": 5.9567,
"step": 346000
},
{
"epoch": 8.63,
"learning_rate": 9.159359464388319e-06,
"loss": 5.9564,
"step": 346500
},
{
"epoch": 8.65,
"learning_rate": 9.158110369981764e-06,
"loss": 5.959,
"step": 347000
},
{
"epoch": 8.66,
"learning_rate": 9.156861275575209e-06,
"loss": 5.958,
"step": 347500
},
{
"epoch": 8.67,
"learning_rate": 9.155612181168654e-06,
"loss": 5.9584,
"step": 348000
},
{
"epoch": 8.68,
"learning_rate": 9.154363086762099e-06,
"loss": 5.9588,
"step": 348500
},
{
"epoch": 8.7,
"learning_rate": 9.153113992355543e-06,
"loss": 5.9555,
"step": 349000
},
{
"epoch": 8.71,
"learning_rate": 9.151864897948988e-06,
"loss": 5.9545,
"step": 349500
},
{
"epoch": 8.72,
"learning_rate": 9.150615803542431e-06,
"loss": 5.9531,
"step": 350000
},
{
"epoch": 8.73,
"learning_rate": 9.149366709135878e-06,
"loss": 5.958,
"step": 350500
},
{
"epoch": 8.75,
"learning_rate": 9.148117614729321e-06,
"loss": 5.9592,
"step": 351000
},
{
"epoch": 8.76,
"learning_rate": 9.146868520322768e-06,
"loss": 5.961,
"step": 351500
},
{
"epoch": 8.77,
"learning_rate": 9.14561942591621e-06,
"loss": 5.955,
"step": 352000
},
{
"epoch": 8.78,
"learning_rate": 9.144370331509657e-06,
"loss": 5.958,
"step": 352500
},
{
"epoch": 8.8,
"learning_rate": 9.1431212371031e-06,
"loss": 5.9543,
"step": 353000
},
{
"epoch": 8.81,
"learning_rate": 9.141872142696547e-06,
"loss": 5.9569,
"step": 353500
},
{
"epoch": 8.82,
"learning_rate": 9.14062304828999e-06,
"loss": 5.9571,
"step": 354000
},
{
"epoch": 8.83,
"learning_rate": 9.139373953883435e-06,
"loss": 5.9536,
"step": 354500
},
{
"epoch": 8.85,
"learning_rate": 9.13812485947688e-06,
"loss": 5.9554,
"step": 355000
},
{
"epoch": 8.86,
"learning_rate": 9.136875765070325e-06,
"loss": 5.9551,
"step": 355500
},
{
"epoch": 8.87,
"learning_rate": 9.13562667066377e-06,
"loss": 5.9524,
"step": 356000
},
{
"epoch": 8.88,
"learning_rate": 9.134377576257214e-06,
"loss": 5.9522,
"step": 356500
},
{
"epoch": 8.9,
"learning_rate": 9.13312848185066e-06,
"loss": 5.9536,
"step": 357000
},
{
"epoch": 8.91,
"learning_rate": 9.131879387444104e-06,
"loss": 5.9569,
"step": 357500
},
{
"epoch": 8.92,
"learning_rate": 9.130630293037549e-06,
"loss": 5.9552,
"step": 358000
},
{
"epoch": 8.93,
"learning_rate": 9.129381198630994e-06,
"loss": 5.9552,
"step": 358500
},
{
"epoch": 8.95,
"learning_rate": 9.128132104224437e-06,
"loss": 5.9514,
"step": 359000
},
{
"epoch": 8.96,
"learning_rate": 9.126883009817883e-06,
"loss": 5.9543,
"step": 359500
},
{
"epoch": 8.97,
"learning_rate": 9.125633915411327e-06,
"loss": 5.9535,
"step": 360000
},
{
"epoch": 8.98,
"learning_rate": 9.124384821004773e-06,
"loss": 5.9525,
"step": 360500
},
{
"epoch": 9.0,
"learning_rate": 9.123135726598216e-06,
"loss": 5.9524,
"step": 361000
},
{
"epoch": 9.01,
"learning_rate": 9.121886632191663e-06,
"loss": 5.9534,
"step": 361500
},
{
"epoch": 9.02,
"learning_rate": 9.120637537785106e-06,
"loss": 5.9499,
"step": 362000
},
{
"epoch": 9.03,
"learning_rate": 9.119388443378553e-06,
"loss": 5.9489,
"step": 362500
},
{
"epoch": 9.05,
"learning_rate": 9.118139348971996e-06,
"loss": 5.9537,
"step": 363000
},
{
"epoch": 9.06,
"learning_rate": 9.11689025456544e-06,
"loss": 5.9553,
"step": 363500
},
{
"epoch": 9.07,
"learning_rate": 9.115641160158885e-06,
"loss": 5.9546,
"step": 364000
},
{
"epoch": 9.08,
"learning_rate": 9.11439206575233e-06,
"loss": 5.9475,
"step": 364500
},
{
"epoch": 9.1,
"learning_rate": 9.113142971345775e-06,
"loss": 5.952,
"step": 365000
},
{
"epoch": 9.11,
"learning_rate": 9.11189387693922e-06,
"loss": 5.9484,
"step": 365500
},
{
"epoch": 9.12,
"learning_rate": 9.110644782532665e-06,
"loss": 5.9485,
"step": 366000
},
{
"epoch": 9.13,
"learning_rate": 9.10939568812611e-06,
"loss": 5.9501,
"step": 366500
},
{
"epoch": 9.15,
"learning_rate": 9.108146593719555e-06,
"loss": 5.9512,
"step": 367000
},
{
"epoch": 9.16,
"learning_rate": 9.106897499313e-06,
"loss": 5.9544,
"step": 367500
},
{
"epoch": 9.17,
"learning_rate": 9.105648404906443e-06,
"loss": 5.9507,
"step": 368000
},
{
"epoch": 9.18,
"learning_rate": 9.104399310499889e-06,
"loss": 5.9521,
"step": 368500
},
{
"epoch": 9.2,
"learning_rate": 9.103150216093332e-06,
"loss": 5.952,
"step": 369000
},
{
"epoch": 9.21,
"learning_rate": 9.101901121686779e-06,
"loss": 5.9519,
"step": 369500
},
{
"epoch": 9.22,
"learning_rate": 9.100652027280222e-06,
"loss": 5.9468,
"step": 370000
},
{
"epoch": 9.23,
"learning_rate": 9.099402932873668e-06,
"loss": 5.9556,
"step": 370500
},
{
"epoch": 9.25,
"learning_rate": 9.098153838467112e-06,
"loss": 5.9499,
"step": 371000
},
{
"epoch": 9.26,
"learning_rate": 9.096904744060558e-06,
"loss": 5.9479,
"step": 371500
},
{
"epoch": 9.27,
"learning_rate": 9.095655649654001e-06,
"loss": 5.9502,
"step": 372000
},
{
"epoch": 9.28,
"learning_rate": 9.094406555247446e-06,
"loss": 5.9487,
"step": 372500
},
{
"epoch": 9.3,
"learning_rate": 9.093157460840891e-06,
"loss": 5.9507,
"step": 373000
},
{
"epoch": 9.31,
"learning_rate": 9.091908366434336e-06,
"loss": 5.9488,
"step": 373500
},
{
"epoch": 9.32,
"learning_rate": 9.09065927202778e-06,
"loss": 5.9474,
"step": 374000
},
{
"epoch": 9.33,
"learning_rate": 9.089410177621226e-06,
"loss": 5.9513,
"step": 374500
},
{
"epoch": 9.34,
"learning_rate": 9.08816108321467e-06,
"loss": 5.9486,
"step": 375000
},
{
"epoch": 9.36,
"learning_rate": 9.086911988808115e-06,
"loss": 5.9501,
"step": 375500
},
{
"epoch": 9.37,
"learning_rate": 9.08566289440156e-06,
"loss": 5.9465,
"step": 376000
},
{
"epoch": 9.38,
"learning_rate": 9.084413799995005e-06,
"loss": 5.9491,
"step": 376500
},
{
"epoch": 9.39,
"learning_rate": 9.083164705588448e-06,
"loss": 5.9495,
"step": 377000
},
{
"epoch": 9.41,
"learning_rate": 9.081915611181895e-06,
"loss": 5.9474,
"step": 377500
},
{
"epoch": 9.42,
"learning_rate": 9.080666516775338e-06,
"loss": 5.9497,
"step": 378000
},
{
"epoch": 9.43,
"learning_rate": 9.079417422368784e-06,
"loss": 5.9493,
"step": 378500
},
{
"epoch": 9.44,
"learning_rate": 9.078168327962227e-06,
"loss": 5.9521,
"step": 379000
},
{
"epoch": 9.46,
"learning_rate": 9.076919233555674e-06,
"loss": 5.9505,
"step": 379500
},
{
"epoch": 9.47,
"learning_rate": 9.075670139149117e-06,
"loss": 5.9474,
"step": 380000
},
{
"epoch": 9.48,
"learning_rate": 9.074421044742564e-06,
"loss": 5.9444,
"step": 380500
},
{
"epoch": 9.49,
"learning_rate": 9.073171950336007e-06,
"loss": 5.9532,
"step": 381000
},
{
"epoch": 9.51,
"learning_rate": 9.071922855929452e-06,
"loss": 5.9492,
"step": 381500
},
{
"epoch": 9.52,
"learning_rate": 9.070673761522897e-06,
"loss": 5.9454,
"step": 382000
},
{
"epoch": 9.53,
"learning_rate": 9.069424667116341e-06,
"loss": 5.9483,
"step": 382500
},
{
"epoch": 9.54,
"learning_rate": 9.068175572709786e-06,
"loss": 5.9487,
"step": 383000
},
{
"epoch": 9.56,
"learning_rate": 9.066926478303231e-06,
"loss": 5.9482,
"step": 383500
},
{
"epoch": 9.57,
"learning_rate": 9.065677383896676e-06,
"loss": 5.95,
"step": 384000
},
{
"epoch": 9.58,
"learning_rate": 9.06442828949012e-06,
"loss": 5.9438,
"step": 384500
},
{
"epoch": 9.59,
"learning_rate": 9.063179195083566e-06,
"loss": 5.9471,
"step": 385000
},
{
"epoch": 9.61,
"learning_rate": 9.06193010067701e-06,
"loss": 5.9505,
"step": 385500
},
{
"epoch": 9.62,
"learning_rate": 9.060681006270454e-06,
"loss": 5.9498,
"step": 386000
},
{
"epoch": 9.63,
"learning_rate": 9.0594319118639e-06,
"loss": 5.9463,
"step": 386500
},
{
"epoch": 9.64,
"learning_rate": 9.058182817457343e-06,
"loss": 5.9459,
"step": 387000
},
{
"epoch": 9.66,
"learning_rate": 9.05693372305079e-06,
"loss": 5.9487,
"step": 387500
},
{
"epoch": 9.67,
"learning_rate": 9.055684628644233e-06,
"loss": 5.9418,
"step": 388000
},
{
"epoch": 9.68,
"learning_rate": 9.05443553423768e-06,
"loss": 5.9455,
"step": 388500
},
{
"epoch": 9.69,
"learning_rate": 9.053186439831123e-06,
"loss": 5.9476,
"step": 389000
},
{
"epoch": 9.71,
"learning_rate": 9.05193734542457e-06,
"loss": 5.9475,
"step": 389500
},
{
"epoch": 9.72,
"learning_rate": 9.050688251018012e-06,
"loss": 5.9486,
"step": 390000
},
{
"epoch": 9.73,
"learning_rate": 9.049439156611457e-06,
"loss": 5.9483,
"step": 390500
},
{
"epoch": 9.74,
"learning_rate": 9.048190062204902e-06,
"loss": 5.9463,
"step": 391000
},
{
"epoch": 9.76,
"learning_rate": 9.046940967798347e-06,
"loss": 5.9456,
"step": 391500
},
{
"epoch": 9.77,
"learning_rate": 9.045691873391792e-06,
"loss": 5.9463,
"step": 392000
},
{
"epoch": 9.78,
"learning_rate": 9.044442778985237e-06,
"loss": 5.9408,
"step": 392500
},
{
"epoch": 9.79,
"learning_rate": 9.043193684578682e-06,
"loss": 5.9456,
"step": 393000
},
{
"epoch": 9.81,
"learning_rate": 9.041944590172126e-06,
"loss": 5.9445,
"step": 393500
},
{
"epoch": 9.82,
"learning_rate": 9.04069549576557e-06,
"loss": 5.9457,
"step": 394000
},
{
"epoch": 9.83,
"learning_rate": 9.039446401359016e-06,
"loss": 5.9453,
"step": 394500
},
{
"epoch": 9.84,
"learning_rate": 9.03819730695246e-06,
"loss": 5.9392,
"step": 395000
},
{
"epoch": 9.86,
"learning_rate": 9.036948212545906e-06,
"loss": 5.9475,
"step": 395500
},
{
"epoch": 9.87,
"learning_rate": 9.035699118139349e-06,
"loss": 5.9471,
"step": 396000
},
{
"epoch": 9.88,
"learning_rate": 9.034450023732795e-06,
"loss": 5.9424,
"step": 396500
},
{
"epoch": 9.89,
"learning_rate": 9.033200929326239e-06,
"loss": 5.9437,
"step": 397000
},
{
"epoch": 9.91,
"learning_rate": 9.031951834919685e-06,
"loss": 5.9438,
"step": 397500
},
{
"epoch": 9.92,
"learning_rate": 9.030702740513128e-06,
"loss": 5.9424,
"step": 398000
},
{
"epoch": 9.93,
"learning_rate": 9.029453646106573e-06,
"loss": 5.9417,
"step": 398500
},
{
"epoch": 9.94,
"learning_rate": 9.028204551700018e-06,
"loss": 5.9429,
"step": 399000
},
{
"epoch": 9.96,
"learning_rate": 9.026955457293463e-06,
"loss": 5.9411,
"step": 399500
},
{
"epoch": 9.97,
"learning_rate": 9.025706362886908e-06,
"loss": 5.9464,
"step": 400000
},
{
"epoch": 9.98,
"learning_rate": 9.024457268480353e-06,
"loss": 5.9431,
"step": 400500
},
{
"epoch": 9.99,
"learning_rate": 9.023208174073797e-06,
"loss": 5.9412,
"step": 401000
},
{
"epoch": 10.01,
"learning_rate": 9.021959079667242e-06,
"loss": 5.9417,
"step": 401500
},
{
"epoch": 10.02,
"learning_rate": 9.020709985260687e-06,
"loss": 5.9427,
"step": 402000
},
{
"epoch": 10.03,
"learning_rate": 9.019460890854132e-06,
"loss": 5.9417,
"step": 402500
},
{
"epoch": 10.04,
"learning_rate": 9.018211796447575e-06,
"loss": 5.9407,
"step": 403000
},
{
"epoch": 10.06,
"learning_rate": 9.016962702041022e-06,
"loss": 5.9425,
"step": 403500
},
{
"epoch": 10.07,
"learning_rate": 9.015713607634465e-06,
"loss": 5.9429,
"step": 404000
},
{
"epoch": 10.08,
"learning_rate": 9.014464513227911e-06,
"loss": 5.9407,
"step": 404500
},
{
"epoch": 10.09,
"learning_rate": 9.013215418821354e-06,
"loss": 5.9421,
"step": 405000
},
{
"epoch": 10.1,
"learning_rate": 9.011966324414801e-06,
"loss": 5.942,
"step": 405500
},
{
"epoch": 10.12,
"learning_rate": 9.010717230008244e-06,
"loss": 5.9422,
"step": 406000
},
{
"epoch": 10.13,
"learning_rate": 9.00946813560169e-06,
"loss": 5.9403,
"step": 406500
},
{
"epoch": 10.14,
"learning_rate": 9.008219041195134e-06,
"loss": 5.9438,
"step": 407000
},
{
"epoch": 10.15,
"learning_rate": 9.006969946788579e-06,
"loss": 5.9439,
"step": 407500
},
{
"epoch": 10.17,
"learning_rate": 9.005720852382024e-06,
"loss": 5.9384,
"step": 408000
},
{
"epoch": 10.18,
"learning_rate": 9.004471757975468e-06,
"loss": 5.9443,
"step": 408500
},
{
"epoch": 10.19,
"learning_rate": 9.003222663568913e-06,
"loss": 5.9414,
"step": 409000
},
{
"epoch": 10.2,
"learning_rate": 9.001973569162358e-06,
"loss": 5.9408,
"step": 409500
},
{
"epoch": 10.22,
"learning_rate": 9.000724474755803e-06,
"loss": 5.9384,
"step": 410000
},
{
"epoch": 10.23,
"learning_rate": 8.999475380349248e-06,
"loss": 5.9399,
"step": 410500
},
{
"epoch": 10.24,
"learning_rate": 8.998226285942693e-06,
"loss": 5.9392,
"step": 411000
},
{
"epoch": 10.25,
"learning_rate": 8.996977191536138e-06,
"loss": 5.9436,
"step": 411500
},
{
"epoch": 10.27,
"learning_rate": 8.99572809712958e-06,
"loss": 5.9379,
"step": 412000
},
{
"epoch": 10.28,
"learning_rate": 8.994479002723027e-06,
"loss": 5.9434,
"step": 412500
},
{
"epoch": 10.29,
"learning_rate": 8.99322990831647e-06,
"loss": 5.9418,
"step": 413000
},
{
"epoch": 10.3,
"learning_rate": 8.991980813909917e-06,
"loss": 5.9373,
"step": 413500
},
{
"epoch": 10.32,
"learning_rate": 8.99073171950336e-06,
"loss": 5.9395,
"step": 414000
},
{
"epoch": 10.33,
"learning_rate": 8.989482625096807e-06,
"loss": 5.94,
"step": 414500
},
{
"epoch": 10.34,
"learning_rate": 8.98823353069025e-06,
"loss": 5.9416,
"step": 415000
},
{
"epoch": 10.35,
"learning_rate": 8.986984436283696e-06,
"loss": 5.9416,
"step": 415500
},
{
"epoch": 10.37,
"learning_rate": 8.98573534187714e-06,
"loss": 5.9415,
"step": 416000
},
{
"epoch": 10.38,
"learning_rate": 8.984486247470584e-06,
"loss": 5.9412,
"step": 416500
},
{
"epoch": 10.39,
"learning_rate": 8.983237153064029e-06,
"loss": 5.9352,
"step": 417000
},
{
"epoch": 10.4,
"learning_rate": 8.981988058657474e-06,
"loss": 5.9421,
"step": 417500
},
{
"epoch": 10.42,
"learning_rate": 8.980738964250919e-06,
"loss": 5.9397,
"step": 418000
},
{
"epoch": 10.43,
"learning_rate": 8.979489869844364e-06,
"loss": 5.9396,
"step": 418500
},
{
"epoch": 10.44,
"learning_rate": 8.978240775437809e-06,
"loss": 5.9366,
"step": 419000
},
{
"epoch": 10.45,
"learning_rate": 8.976991681031253e-06,
"loss": 5.9427,
"step": 419500
},
{
"epoch": 10.47,
"learning_rate": 8.975742586624698e-06,
"loss": 5.9415,
"step": 420000
},
{
"epoch": 10.48,
"learning_rate": 8.974493492218143e-06,
"loss": 5.9377,
"step": 420500
},
{
"epoch": 10.49,
"learning_rate": 8.973244397811586e-06,
"loss": 5.9375,
"step": 421000
},
{
"epoch": 10.5,
"learning_rate": 8.971995303405033e-06,
"loss": 5.9331,
"step": 421500
},
{
"epoch": 10.52,
"learning_rate": 8.970746208998476e-06,
"loss": 5.9397,
"step": 422000
},
{
"epoch": 10.53,
"learning_rate": 8.969497114591922e-06,
"loss": 5.9404,
"step": 422500
},
{
"epoch": 10.54,
"learning_rate": 8.968248020185366e-06,
"loss": 5.9409,
"step": 423000
},
{
"epoch": 10.55,
"learning_rate": 8.966998925778812e-06,
"loss": 5.9382,
"step": 423500
},
{
"epoch": 10.57,
"learning_rate": 8.965749831372255e-06,
"loss": 5.9393,
"step": 424000
},
{
"epoch": 10.58,
"learning_rate": 8.964500736965702e-06,
"loss": 5.9368,
"step": 424500
},
{
"epoch": 10.59,
"learning_rate": 8.963251642559145e-06,
"loss": 5.9325,
"step": 425000
},
{
"epoch": 10.6,
"learning_rate": 8.96200254815259e-06,
"loss": 5.9414,
"step": 425500
},
{
"epoch": 10.62,
"learning_rate": 8.960753453746035e-06,
"loss": 5.9398,
"step": 426000
},
{
"epoch": 10.63,
"learning_rate": 8.95950435933948e-06,
"loss": 5.9366,
"step": 426500
},
{
"epoch": 10.64,
"learning_rate": 8.958255264932924e-06,
"loss": 5.94,
"step": 427000
},
{
"epoch": 10.65,
"learning_rate": 8.95700617052637e-06,
"loss": 5.9394,
"step": 427500
},
{
"epoch": 10.67,
"learning_rate": 8.955757076119814e-06,
"loss": 5.9401,
"step": 428000
},
{
"epoch": 10.68,
"learning_rate": 8.954507981713259e-06,
"loss": 5.9381,
"step": 428500
},
{
"epoch": 10.69,
"learning_rate": 8.953258887306704e-06,
"loss": 5.9352,
"step": 429000
},
{
"epoch": 10.7,
"learning_rate": 8.952009792900149e-06,
"loss": 5.9389,
"step": 429500
},
{
"epoch": 10.72,
"learning_rate": 8.950760698493592e-06,
"loss": 5.9343,
"step": 430000
},
{
"epoch": 10.73,
"learning_rate": 8.949511604087038e-06,
"loss": 5.9363,
"step": 430500
},
{
"epoch": 10.74,
"learning_rate": 8.948262509680481e-06,
"loss": 5.9353,
"step": 431000
},
{
"epoch": 10.75,
"learning_rate": 8.947013415273928e-06,
"loss": 5.9339,
"step": 431500
},
{
"epoch": 10.77,
"learning_rate": 8.945764320867371e-06,
"loss": 5.9331,
"step": 432000
},
{
"epoch": 10.78,
"learning_rate": 8.944515226460818e-06,
"loss": 5.9352,
"step": 432500
},
{
"epoch": 10.79,
"learning_rate": 8.943266132054261e-06,
"loss": 5.9379,
"step": 433000
},
{
"epoch": 10.8,
"learning_rate": 8.942017037647707e-06,
"loss": 5.9377,
"step": 433500
},
{
"epoch": 10.82,
"learning_rate": 8.94076794324115e-06,
"loss": 5.9323,
"step": 434000
},
{
"epoch": 10.83,
"learning_rate": 8.939518848834595e-06,
"loss": 5.9349,
"step": 434500
},
{
"epoch": 10.84,
"learning_rate": 8.93826975442804e-06,
"loss": 5.9354,
"step": 435000
},
{
"epoch": 10.85,
"learning_rate": 8.937020660021485e-06,
"loss": 5.9328,
"step": 435500
},
{
"epoch": 10.86,
"learning_rate": 8.93577156561493e-06,
"loss": 5.9318,
"step": 436000
},
{
"epoch": 10.88,
"learning_rate": 8.934522471208375e-06,
"loss": 5.9341,
"step": 436500
},
{
"epoch": 10.89,
"learning_rate": 8.93327337680182e-06,
"loss": 5.9359,
"step": 437000
},
{
"epoch": 10.9,
"learning_rate": 8.932024282395265e-06,
"loss": 5.9333,
"step": 437500
},
{
"epoch": 10.91,
"learning_rate": 8.93077518798871e-06,
"loss": 5.9312,
"step": 438000
},
{
"epoch": 10.93,
"learning_rate": 8.929526093582154e-06,
"loss": 5.9339,
"step": 438500
},
{
"epoch": 10.94,
"learning_rate": 8.928276999175597e-06,
"loss": 5.9311,
"step": 439000
},
{
"epoch": 10.95,
"learning_rate": 8.927027904769044e-06,
"loss": 5.9352,
"step": 439500
},
{
"epoch": 10.96,
"learning_rate": 8.925778810362487e-06,
"loss": 5.9329,
"step": 440000
},
{
"epoch": 10.98,
"learning_rate": 8.924529715955934e-06,
"loss": 5.9335,
"step": 440500
},
{
"epoch": 10.99,
"learning_rate": 8.923280621549377e-06,
"loss": 5.9331,
"step": 441000
},
{
"epoch": 11.0,
"learning_rate": 8.922031527142823e-06,
"loss": 5.9349,
"step": 441500
},
{
"epoch": 11.01,
"learning_rate": 8.920782432736266e-06,
"loss": 5.9338,
"step": 442000
},
{
"epoch": 11.03,
"learning_rate": 8.919533338329713e-06,
"loss": 5.9337,
"step": 442500
},
{
"epoch": 11.04,
"learning_rate": 8.918284243923156e-06,
"loss": 5.9319,
"step": 443000
},
{
"epoch": 11.05,
"learning_rate": 8.917035149516601e-06,
"loss": 5.928,
"step": 443500
},
{
"epoch": 11.06,
"learning_rate": 8.915786055110046e-06,
"loss": 5.9241,
"step": 444000
},
{
"epoch": 11.08,
"learning_rate": 8.91453696070349e-06,
"loss": 5.9345,
"step": 444500
},
{
"epoch": 11.09,
"learning_rate": 8.913287866296936e-06,
"loss": 5.9327,
"step": 445000
},
{
"epoch": 11.1,
"learning_rate": 8.91203877189038e-06,
"loss": 5.9352,
"step": 445500
},
{
"epoch": 11.11,
"learning_rate": 8.910789677483825e-06,
"loss": 5.9296,
"step": 446000
},
{
"epoch": 11.13,
"learning_rate": 8.90954058307727e-06,
"loss": 5.9295,
"step": 446500
},
{
"epoch": 11.14,
"learning_rate": 8.908291488670713e-06,
"loss": 5.932,
"step": 447000
},
{
"epoch": 11.15,
"learning_rate": 8.90704239426416e-06,
"loss": 5.9281,
"step": 447500
},
{
"epoch": 11.16,
"learning_rate": 8.905793299857603e-06,
"loss": 5.9331,
"step": 448000
},
{
"epoch": 11.18,
"learning_rate": 8.90454420545105e-06,
"loss": 5.9326,
"step": 448500
},
{
"epoch": 11.19,
"learning_rate": 8.903295111044493e-06,
"loss": 5.9315,
"step": 449000
},
{
"epoch": 11.2,
"learning_rate": 8.90204601663794e-06,
"loss": 5.9267,
"step": 449500
},
{
"epoch": 11.21,
"learning_rate": 8.900796922231382e-06,
"loss": 5.9292,
"step": 450000
},
{
"epoch": 11.23,
"learning_rate": 8.899547827824829e-06,
"loss": 5.9251,
"step": 450500
},
{
"epoch": 11.24,
"learning_rate": 8.898298733418272e-06,
"loss": 5.9281,
"step": 451000
},
{
"epoch": 11.25,
"learning_rate": 8.897049639011717e-06,
"loss": 5.9251,
"step": 451500
},
{
"epoch": 11.26,
"learning_rate": 8.895800544605162e-06,
"loss": 5.9293,
"step": 452000
},
{
"epoch": 11.28,
"learning_rate": 8.894551450198607e-06,
"loss": 5.9329,
"step": 452500
},
{
"epoch": 11.29,
"learning_rate": 8.893302355792051e-06,
"loss": 5.9308,
"step": 453000
},
{
"epoch": 11.3,
"learning_rate": 8.892053261385496e-06,
"loss": 5.9251,
"step": 453500
},
{
"epoch": 11.31,
"learning_rate": 8.890804166978941e-06,
"loss": 5.9283,
"step": 454000
},
{
"epoch": 11.33,
"learning_rate": 8.889555072572386e-06,
"loss": 5.9285,
"step": 454500
},
{
"epoch": 11.34,
"learning_rate": 8.88830597816583e-06,
"loss": 5.9265,
"step": 455000
},
{
"epoch": 11.35,
"learning_rate": 8.887056883759276e-06,
"loss": 5.929,
"step": 455500
},
{
"epoch": 11.36,
"learning_rate": 8.885807789352719e-06,
"loss": 5.9292,
"step": 456000
},
{
"epoch": 11.38,
"learning_rate": 8.884558694946165e-06,
"loss": 5.9241,
"step": 456500
},
{
"epoch": 11.39,
"learning_rate": 8.883309600539609e-06,
"loss": 5.9218,
"step": 457000
},
{
"epoch": 11.4,
"learning_rate": 8.882060506133055e-06,
"loss": 5.9265,
"step": 457500
},
{
"epoch": 11.41,
"learning_rate": 8.880811411726498e-06,
"loss": 5.9262,
"step": 458000
},
{
"epoch": 11.43,
"learning_rate": 8.879562317319945e-06,
"loss": 5.9295,
"step": 458500
},
{
"epoch": 11.44,
"learning_rate": 8.878313222913388e-06,
"loss": 5.9218,
"step": 459000
},
{
"epoch": 11.45,
"learning_rate": 8.877064128506834e-06,
"loss": 5.9228,
"step": 459500
},
{
"epoch": 11.46,
"learning_rate": 8.875815034100278e-06,
"loss": 5.9285,
"step": 460000
},
{
"epoch": 11.48,
"learning_rate": 8.874565939693722e-06,
"loss": 5.9233,
"step": 460500
},
{
"epoch": 11.49,
"learning_rate": 8.873316845287167e-06,
"loss": 5.9255,
"step": 461000
},
{
"epoch": 11.5,
"learning_rate": 8.872067750880612e-06,
"loss": 5.9244,
"step": 461500
},
{
"epoch": 11.51,
"learning_rate": 8.870818656474057e-06,
"loss": 5.9215,
"step": 462000
},
{
"epoch": 11.53,
"learning_rate": 8.869569562067502e-06,
"loss": 5.9268,
"step": 462500
},
{
"epoch": 11.54,
"learning_rate": 8.868320467660947e-06,
"loss": 5.9251,
"step": 463000
},
{
"epoch": 11.55,
"learning_rate": 8.867071373254392e-06,
"loss": 5.9214,
"step": 463500
},
{
"epoch": 11.56,
"learning_rate": 8.865822278847836e-06,
"loss": 5.9231,
"step": 464000
},
{
"epoch": 11.58,
"learning_rate": 8.864573184441281e-06,
"loss": 5.9271,
"step": 464500
},
{
"epoch": 11.59,
"learning_rate": 8.863324090034724e-06,
"loss": 5.9193,
"step": 465000
},
{
"epoch": 11.6,
"learning_rate": 8.862074995628171e-06,
"loss": 5.9232,
"step": 465500
},
{
"epoch": 11.61,
"learning_rate": 8.860825901221614e-06,
"loss": 5.9249,
"step": 466000
},
{
"epoch": 11.63,
"learning_rate": 8.85957680681506e-06,
"loss": 5.9214,
"step": 466500
},
{
"epoch": 11.64,
"learning_rate": 8.858327712408504e-06,
"loss": 5.9212,
"step": 467000
},
{
"epoch": 11.65,
"learning_rate": 8.85707861800195e-06,
"loss": 5.9185,
"step": 467500
},
{
"epoch": 11.66,
"learning_rate": 8.855829523595393e-06,
"loss": 5.9207,
"step": 468000
},
{
"epoch": 11.67,
"learning_rate": 8.85458042918884e-06,
"loss": 5.9219,
"step": 468500
},
{
"epoch": 11.69,
"learning_rate": 8.853331334782283e-06,
"loss": 5.9192,
"step": 469000
},
{
"epoch": 11.7,
"learning_rate": 8.852082240375728e-06,
"loss": 5.9218,
"step": 469500
},
{
"epoch": 11.71,
"learning_rate": 8.850833145969173e-06,
"loss": 5.9224,
"step": 470000
},
{
"epoch": 11.72,
"learning_rate": 8.849584051562618e-06,
"loss": 5.9193,
"step": 470500
},
{
"epoch": 11.74,
"learning_rate": 8.848334957156063e-06,
"loss": 5.9217,
"step": 471000
},
{
"epoch": 11.75,
"learning_rate": 8.847085862749507e-06,
"loss": 5.9205,
"step": 471500
},
{
"epoch": 11.76,
"learning_rate": 8.845836768342952e-06,
"loss": 5.9228,
"step": 472000
},
{
"epoch": 11.77,
"learning_rate": 8.844587673936397e-06,
"loss": 5.9232,
"step": 472500
},
{
"epoch": 11.79,
"learning_rate": 8.843338579529842e-06,
"loss": 5.9204,
"step": 473000
},
{
"epoch": 11.8,
"learning_rate": 8.842089485123287e-06,
"loss": 5.9226,
"step": 473500
},
{
"epoch": 11.81,
"learning_rate": 8.84084039071673e-06,
"loss": 5.9184,
"step": 474000
},
{
"epoch": 11.82,
"learning_rate": 8.839591296310176e-06,
"loss": 5.9189,
"step": 474500
},
{
"epoch": 11.84,
"learning_rate": 8.83834220190362e-06,
"loss": 5.9205,
"step": 475000
},
{
"epoch": 11.85,
"learning_rate": 8.837093107497066e-06,
"loss": 5.9192,
"step": 475500
},
{
"epoch": 11.86,
"learning_rate": 8.83584401309051e-06,
"loss": 5.9195,
"step": 476000
},
{
"epoch": 11.87,
"learning_rate": 8.834594918683956e-06,
"loss": 5.917,
"step": 476500
},
{
"epoch": 11.89,
"learning_rate": 8.833345824277399e-06,
"loss": 5.9202,
"step": 477000
},
{
"epoch": 11.9,
"learning_rate": 8.832096729870846e-06,
"loss": 5.9165,
"step": 477500
},
{
"epoch": 11.91,
"learning_rate": 8.830847635464289e-06,
"loss": 5.9172,
"step": 478000
},
{
"epoch": 11.92,
"learning_rate": 8.829598541057734e-06,
"loss": 5.9176,
"step": 478500
},
{
"epoch": 11.94,
"learning_rate": 8.828349446651178e-06,
"loss": 5.9162,
"step": 479000
},
{
"epoch": 11.95,
"learning_rate": 8.827100352244623e-06,
"loss": 5.9183,
"step": 479500
},
{
"epoch": 11.96,
"learning_rate": 8.825851257838068e-06,
"loss": 5.9158,
"step": 480000
},
{
"epoch": 11.97,
"learning_rate": 8.824602163431513e-06,
"loss": 5.9147,
"step": 480500
},
{
"epoch": 11.99,
"learning_rate": 8.823353069024958e-06,
"loss": 5.9183,
"step": 481000
},
{
"epoch": 11.99,
"step": 481227,
"total_flos": 4.052977989053317e+17,
"train_loss": 6.077395075454175,
"train_runtime": 197999.1974,
"train_samples_per_second": 2958.981,
"train_steps_per_second": 20.267
}
],
"logging_steps": 500,
"max_steps": 4012900,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 4.052977989053317e+17,
"trial_name": null,
"trial_params": null
}