HBERTv1_48_L8_H256_A4 / trainer_state.json
gokuls's picture
End of training
c809032
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.008307525930295,
"eval_steps": 1000000,
"global_step": 427710,
"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": 10.268,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 9.9962,
"step": 1000
},
{
"epoch": 0.02,
"learning_rate": 1.5e-06,
"loss": 9.792,
"step": 1500
},
{
"epoch": 0.03,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.5654,
"step": 2000
},
{
"epoch": 0.04,
"learning_rate": 2.5e-06,
"loss": 9.2879,
"step": 2500
},
{
"epoch": 0.05,
"learning_rate": 3e-06,
"loss": 8.9699,
"step": 3000
},
{
"epoch": 0.06,
"learning_rate": 3.5e-06,
"loss": 8.6244,
"step": 3500
},
{
"epoch": 0.07,
"learning_rate": 4.000000000000001e-06,
"loss": 8.275,
"step": 4000
},
{
"epoch": 0.07,
"learning_rate": 4.5e-06,
"loss": 7.9345,
"step": 4500
},
{
"epoch": 0.08,
"learning_rate": 5e-06,
"loss": 7.6419,
"step": 5000
},
{
"epoch": 0.09,
"learning_rate": 5.500000000000001e-06,
"loss": 7.4036,
"step": 5500
},
{
"epoch": 0.1,
"learning_rate": 6e-06,
"loss": 7.2361,
"step": 6000
},
{
"epoch": 0.11,
"learning_rate": 6.5000000000000004e-06,
"loss": 7.128,
"step": 6500
},
{
"epoch": 0.11,
"learning_rate": 7e-06,
"loss": 7.0524,
"step": 7000
},
{
"epoch": 0.12,
"learning_rate": 7.500000000000001e-06,
"loss": 6.9887,
"step": 7500
},
{
"epoch": 0.13,
"learning_rate": 8.000000000000001e-06,
"loss": 6.9382,
"step": 8000
},
{
"epoch": 0.14,
"learning_rate": 8.5e-06,
"loss": 6.8975,
"step": 8500
},
{
"epoch": 0.15,
"learning_rate": 9e-06,
"loss": 6.8609,
"step": 9000
},
{
"epoch": 0.16,
"learning_rate": 9.5e-06,
"loss": 6.822,
"step": 9500
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 6.7911,
"step": 10000
},
{
"epoch": 0.17,
"learning_rate": 9.999179372712501e-06,
"loss": 6.7655,
"step": 10500
},
{
"epoch": 0.18,
"learning_rate": 9.998358745425003e-06,
"loss": 6.731,
"step": 11000
},
{
"epoch": 0.19,
"learning_rate": 9.997538118137506e-06,
"loss": 6.7144,
"step": 11500
},
{
"epoch": 0.2,
"learning_rate": 9.996717490850006e-06,
"loss": 6.6944,
"step": 12000
},
{
"epoch": 0.2,
"learning_rate": 9.995896863562508e-06,
"loss": 6.6726,
"step": 12500
},
{
"epoch": 0.21,
"learning_rate": 9.99507623627501e-06,
"loss": 6.6593,
"step": 13000
},
{
"epoch": 0.22,
"learning_rate": 9.994255608987511e-06,
"loss": 6.6396,
"step": 13500
},
{
"epoch": 0.23,
"learning_rate": 9.993434981700011e-06,
"loss": 6.623,
"step": 14000
},
{
"epoch": 0.24,
"learning_rate": 9.992614354412514e-06,
"loss": 6.6121,
"step": 14500
},
{
"epoch": 0.25,
"learning_rate": 9.991793727125016e-06,
"loss": 6.5987,
"step": 15000
},
{
"epoch": 0.25,
"learning_rate": 9.990973099837516e-06,
"loss": 6.5833,
"step": 15500
},
{
"epoch": 0.26,
"learning_rate": 9.990152472550018e-06,
"loss": 6.5752,
"step": 16000
},
{
"epoch": 0.27,
"learning_rate": 9.98933184526252e-06,
"loss": 6.5612,
"step": 16500
},
{
"epoch": 0.28,
"learning_rate": 9.988511217975021e-06,
"loss": 6.5423,
"step": 17000
},
{
"epoch": 0.29,
"learning_rate": 9.987690590687521e-06,
"loss": 6.5387,
"step": 17500
},
{
"epoch": 0.29,
"learning_rate": 9.986869963400024e-06,
"loss": 6.5334,
"step": 18000
},
{
"epoch": 0.3,
"learning_rate": 9.986049336112526e-06,
"loss": 6.5136,
"step": 18500
},
{
"epoch": 0.31,
"learning_rate": 9.985228708825026e-06,
"loss": 6.5098,
"step": 19000
},
{
"epoch": 0.32,
"learning_rate": 9.984408081537528e-06,
"loss": 6.5016,
"step": 19500
},
{
"epoch": 0.33,
"learning_rate": 9.98358745425003e-06,
"loss": 6.4882,
"step": 20000
},
{
"epoch": 0.34,
"learning_rate": 9.982766826962531e-06,
"loss": 6.4841,
"step": 20500
},
{
"epoch": 0.34,
"learning_rate": 9.981946199675032e-06,
"loss": 6.4752,
"step": 21000
},
{
"epoch": 0.35,
"learning_rate": 9.981125572387534e-06,
"loss": 6.4651,
"step": 21500
},
{
"epoch": 0.36,
"learning_rate": 9.980304945100036e-06,
"loss": 6.4614,
"step": 22000
},
{
"epoch": 0.37,
"learning_rate": 9.979484317812536e-06,
"loss": 6.4544,
"step": 22500
},
{
"epoch": 0.38,
"learning_rate": 9.978663690525039e-06,
"loss": 6.442,
"step": 23000
},
{
"epoch": 0.39,
"learning_rate": 9.97784306323754e-06,
"loss": 6.4348,
"step": 23500
},
{
"epoch": 0.39,
"learning_rate": 9.977022435950041e-06,
"loss": 6.4353,
"step": 24000
},
{
"epoch": 0.4,
"learning_rate": 9.976201808662542e-06,
"loss": 6.4202,
"step": 24500
},
{
"epoch": 0.41,
"learning_rate": 9.975381181375044e-06,
"loss": 6.4225,
"step": 25000
},
{
"epoch": 0.42,
"learning_rate": 9.974560554087546e-06,
"loss": 6.414,
"step": 25500
},
{
"epoch": 0.43,
"learning_rate": 9.973739926800046e-06,
"loss": 6.4026,
"step": 26000
},
{
"epoch": 0.43,
"learning_rate": 9.972919299512549e-06,
"loss": 6.3962,
"step": 26500
},
{
"epoch": 0.44,
"learning_rate": 9.97209867222505e-06,
"loss": 6.3933,
"step": 27000
},
{
"epoch": 0.45,
"learning_rate": 9.971278044937551e-06,
"loss": 6.3853,
"step": 27500
},
{
"epoch": 0.46,
"learning_rate": 9.970457417650052e-06,
"loss": 6.3811,
"step": 28000
},
{
"epoch": 0.47,
"learning_rate": 9.969636790362554e-06,
"loss": 6.3739,
"step": 28500
},
{
"epoch": 0.48,
"learning_rate": 9.968816163075056e-06,
"loss": 6.3688,
"step": 29000
},
{
"epoch": 0.48,
"learning_rate": 9.967995535787557e-06,
"loss": 6.364,
"step": 29500
},
{
"epoch": 0.49,
"learning_rate": 9.967174908500059e-06,
"loss": 6.3587,
"step": 30000
},
{
"epoch": 0.5,
"learning_rate": 9.966354281212561e-06,
"loss": 6.3572,
"step": 30500
},
{
"epoch": 0.51,
"learning_rate": 9.965533653925061e-06,
"loss": 6.3522,
"step": 31000
},
{
"epoch": 0.52,
"learning_rate": 9.964713026637562e-06,
"loss": 6.3417,
"step": 31500
},
{
"epoch": 0.52,
"learning_rate": 9.963892399350064e-06,
"loss": 6.3379,
"step": 32000
},
{
"epoch": 0.53,
"learning_rate": 9.963071772062566e-06,
"loss": 6.3354,
"step": 32500
},
{
"epoch": 0.54,
"learning_rate": 9.962251144775067e-06,
"loss": 6.3403,
"step": 33000
},
{
"epoch": 0.55,
"learning_rate": 9.961430517487569e-06,
"loss": 6.3312,
"step": 33500
},
{
"epoch": 0.56,
"learning_rate": 9.960609890200071e-06,
"loss": 6.321,
"step": 34000
},
{
"epoch": 0.57,
"learning_rate": 9.959789262912571e-06,
"loss": 6.3209,
"step": 34500
},
{
"epoch": 0.57,
"learning_rate": 9.958968635625072e-06,
"loss": 6.3124,
"step": 35000
},
{
"epoch": 0.58,
"learning_rate": 9.958148008337574e-06,
"loss": 6.3152,
"step": 35500
},
{
"epoch": 0.59,
"learning_rate": 9.957327381050076e-06,
"loss": 6.3107,
"step": 36000
},
{
"epoch": 0.6,
"learning_rate": 9.956506753762577e-06,
"loss": 6.3034,
"step": 36500
},
{
"epoch": 0.61,
"learning_rate": 9.955686126475079e-06,
"loss": 6.2993,
"step": 37000
},
{
"epoch": 0.61,
"learning_rate": 9.95486549918758e-06,
"loss": 6.2987,
"step": 37500
},
{
"epoch": 0.62,
"learning_rate": 9.954044871900081e-06,
"loss": 6.2966,
"step": 38000
},
{
"epoch": 0.63,
"learning_rate": 9.953224244612582e-06,
"loss": 6.2926,
"step": 38500
},
{
"epoch": 0.64,
"learning_rate": 9.952403617325084e-06,
"loss": 6.287,
"step": 39000
},
{
"epoch": 0.65,
"learning_rate": 9.951582990037586e-06,
"loss": 6.2817,
"step": 39500
},
{
"epoch": 0.66,
"learning_rate": 9.950762362750087e-06,
"loss": 6.2827,
"step": 40000
},
{
"epoch": 0.66,
"learning_rate": 9.949941735462589e-06,
"loss": 6.2768,
"step": 40500
},
{
"epoch": 0.67,
"learning_rate": 9.94912110817509e-06,
"loss": 6.2728,
"step": 41000
},
{
"epoch": 0.68,
"learning_rate": 9.948300480887592e-06,
"loss": 6.2702,
"step": 41500
},
{
"epoch": 0.69,
"learning_rate": 9.947479853600092e-06,
"loss": 6.2667,
"step": 42000
},
{
"epoch": 0.7,
"learning_rate": 9.946659226312594e-06,
"loss": 6.2595,
"step": 42500
},
{
"epoch": 0.7,
"learning_rate": 9.945838599025096e-06,
"loss": 6.2602,
"step": 43000
},
{
"epoch": 0.71,
"learning_rate": 9.945017971737597e-06,
"loss": 6.2524,
"step": 43500
},
{
"epoch": 0.72,
"learning_rate": 9.944197344450099e-06,
"loss": 6.2538,
"step": 44000
},
{
"epoch": 0.73,
"learning_rate": 9.9433767171626e-06,
"loss": 6.2512,
"step": 44500
},
{
"epoch": 0.74,
"learning_rate": 9.942556089875102e-06,
"loss": 6.2496,
"step": 45000
},
{
"epoch": 0.75,
"learning_rate": 9.941735462587602e-06,
"loss": 6.2438,
"step": 45500
},
{
"epoch": 0.75,
"learning_rate": 9.940914835300104e-06,
"loss": 6.2417,
"step": 46000
},
{
"epoch": 0.76,
"learning_rate": 9.940094208012606e-06,
"loss": 6.2399,
"step": 46500
},
{
"epoch": 0.77,
"learning_rate": 9.939273580725107e-06,
"loss": 6.2391,
"step": 47000
},
{
"epoch": 0.78,
"learning_rate": 9.938452953437609e-06,
"loss": 6.2306,
"step": 47500
},
{
"epoch": 0.79,
"learning_rate": 9.93763232615011e-06,
"loss": 6.2358,
"step": 48000
},
{
"epoch": 0.79,
"learning_rate": 9.936811698862612e-06,
"loss": 6.2295,
"step": 48500
},
{
"epoch": 0.8,
"learning_rate": 9.935991071575112e-06,
"loss": 6.2259,
"step": 49000
},
{
"epoch": 0.81,
"learning_rate": 9.935170444287614e-06,
"loss": 6.2299,
"step": 49500
},
{
"epoch": 0.82,
"learning_rate": 9.934349817000117e-06,
"loss": 6.2287,
"step": 50000
},
{
"epoch": 0.83,
"learning_rate": 9.933529189712617e-06,
"loss": 6.219,
"step": 50500
},
{
"epoch": 0.84,
"learning_rate": 9.93270856242512e-06,
"loss": 6.2198,
"step": 51000
},
{
"epoch": 0.84,
"learning_rate": 9.93188793513762e-06,
"loss": 6.2203,
"step": 51500
},
{
"epoch": 0.85,
"learning_rate": 9.931067307850122e-06,
"loss": 6.2177,
"step": 52000
},
{
"epoch": 0.86,
"learning_rate": 9.930246680562622e-06,
"loss": 6.2067,
"step": 52500
},
{
"epoch": 0.87,
"learning_rate": 9.929426053275124e-06,
"loss": 6.21,
"step": 53000
},
{
"epoch": 0.88,
"learning_rate": 9.928605425987625e-06,
"loss": 6.2164,
"step": 53500
},
{
"epoch": 0.88,
"learning_rate": 9.927784798700127e-06,
"loss": 6.2073,
"step": 54000
},
{
"epoch": 0.89,
"learning_rate": 9.92696417141263e-06,
"loss": 6.2061,
"step": 54500
},
{
"epoch": 0.9,
"learning_rate": 9.92614354412513e-06,
"loss": 6.2032,
"step": 55000
},
{
"epoch": 0.91,
"learning_rate": 9.925322916837632e-06,
"loss": 6.2025,
"step": 55500
},
{
"epoch": 0.92,
"learning_rate": 9.924502289550132e-06,
"loss": 6.2048,
"step": 56000
},
{
"epoch": 0.93,
"learning_rate": 9.923681662262635e-06,
"loss": 6.1983,
"step": 56500
},
{
"epoch": 0.93,
"learning_rate": 9.922861034975135e-06,
"loss": 6.2018,
"step": 57000
},
{
"epoch": 0.94,
"learning_rate": 9.922040407687637e-06,
"loss": 6.1944,
"step": 57500
},
{
"epoch": 0.95,
"learning_rate": 9.92121978040014e-06,
"loss": 6.1971,
"step": 58000
},
{
"epoch": 0.96,
"learning_rate": 9.92039915311264e-06,
"loss": 6.1926,
"step": 58500
},
{
"epoch": 0.97,
"learning_rate": 9.919578525825142e-06,
"loss": 6.1847,
"step": 59000
},
{
"epoch": 0.97,
"learning_rate": 9.918757898537642e-06,
"loss": 6.1895,
"step": 59500
},
{
"epoch": 0.98,
"learning_rate": 9.917937271250145e-06,
"loss": 6.187,
"step": 60000
},
{
"epoch": 0.99,
"learning_rate": 9.917116643962645e-06,
"loss": 6.1833,
"step": 60500
},
{
"epoch": 1.0,
"learning_rate": 9.916296016675147e-06,
"loss": 6.1849,
"step": 61000
},
{
"epoch": 1.01,
"learning_rate": 9.91547538938765e-06,
"loss": 6.1763,
"step": 61500
},
{
"epoch": 1.02,
"learning_rate": 9.91465476210015e-06,
"loss": 6.1833,
"step": 62000
},
{
"epoch": 1.02,
"learning_rate": 9.913834134812652e-06,
"loss": 6.1786,
"step": 62500
},
{
"epoch": 1.03,
"learning_rate": 9.913013507525153e-06,
"loss": 6.1779,
"step": 63000
},
{
"epoch": 1.04,
"learning_rate": 9.912192880237655e-06,
"loss": 6.1759,
"step": 63500
},
{
"epoch": 1.05,
"learning_rate": 9.911372252950155e-06,
"loss": 6.1702,
"step": 64000
},
{
"epoch": 1.06,
"learning_rate": 9.910551625662657e-06,
"loss": 6.1672,
"step": 64500
},
{
"epoch": 1.07,
"learning_rate": 9.90973099837516e-06,
"loss": 6.172,
"step": 65000
},
{
"epoch": 1.07,
"learning_rate": 9.90891037108766e-06,
"loss": 6.1697,
"step": 65500
},
{
"epoch": 1.08,
"learning_rate": 9.908089743800162e-06,
"loss": 6.1684,
"step": 66000
},
{
"epoch": 1.09,
"learning_rate": 9.907269116512663e-06,
"loss": 6.1647,
"step": 66500
},
{
"epoch": 1.1,
"learning_rate": 9.906448489225165e-06,
"loss": 6.1639,
"step": 67000
},
{
"epoch": 1.11,
"learning_rate": 9.905627861937665e-06,
"loss": 6.1613,
"step": 67500
},
{
"epoch": 1.11,
"learning_rate": 9.904807234650167e-06,
"loss": 6.1595,
"step": 68000
},
{
"epoch": 1.12,
"learning_rate": 9.90398660736267e-06,
"loss": 6.16,
"step": 68500
},
{
"epoch": 1.13,
"learning_rate": 9.90316598007517e-06,
"loss": 6.1576,
"step": 69000
},
{
"epoch": 1.14,
"learning_rate": 9.90234535278767e-06,
"loss": 6.1587,
"step": 69500
},
{
"epoch": 1.15,
"learning_rate": 9.901524725500173e-06,
"loss": 6.158,
"step": 70000
},
{
"epoch": 1.16,
"learning_rate": 9.900704098212675e-06,
"loss": 6.1537,
"step": 70500
},
{
"epoch": 1.16,
"learning_rate": 9.899883470925175e-06,
"loss": 6.1484,
"step": 71000
},
{
"epoch": 1.17,
"learning_rate": 9.899062843637678e-06,
"loss": 6.152,
"step": 71500
},
{
"epoch": 1.18,
"learning_rate": 9.89824221635018e-06,
"loss": 6.1499,
"step": 72000
},
{
"epoch": 1.19,
"learning_rate": 9.89742158906268e-06,
"loss": 6.1443,
"step": 72500
},
{
"epoch": 1.2,
"learning_rate": 9.89660096177518e-06,
"loss": 6.1467,
"step": 73000
},
{
"epoch": 1.2,
"learning_rate": 9.895780334487683e-06,
"loss": 6.1425,
"step": 73500
},
{
"epoch": 1.21,
"learning_rate": 9.894959707200185e-06,
"loss": 6.141,
"step": 74000
},
{
"epoch": 1.22,
"learning_rate": 9.894139079912685e-06,
"loss": 6.1412,
"step": 74500
},
{
"epoch": 1.23,
"learning_rate": 9.893318452625188e-06,
"loss": 6.1369,
"step": 75000
},
{
"epoch": 1.24,
"learning_rate": 9.89249782533769e-06,
"loss": 6.1371,
"step": 75500
},
{
"epoch": 1.25,
"learning_rate": 9.89167719805019e-06,
"loss": 6.137,
"step": 76000
},
{
"epoch": 1.25,
"learning_rate": 9.89085657076269e-06,
"loss": 6.1382,
"step": 76500
},
{
"epoch": 1.26,
"learning_rate": 9.890035943475193e-06,
"loss": 6.1372,
"step": 77000
},
{
"epoch": 1.27,
"learning_rate": 9.889215316187695e-06,
"loss": 6.1335,
"step": 77500
},
{
"epoch": 1.28,
"learning_rate": 9.888394688900196e-06,
"loss": 6.1351,
"step": 78000
},
{
"epoch": 1.29,
"learning_rate": 9.887574061612698e-06,
"loss": 6.1331,
"step": 78500
},
{
"epoch": 1.29,
"learning_rate": 9.8867534343252e-06,
"loss": 6.1366,
"step": 79000
},
{
"epoch": 1.3,
"learning_rate": 9.8859328070377e-06,
"loss": 6.124,
"step": 79500
},
{
"epoch": 1.31,
"learning_rate": 9.8851121797502e-06,
"loss": 6.1309,
"step": 80000
},
{
"epoch": 1.32,
"learning_rate": 9.884291552462703e-06,
"loss": 6.1301,
"step": 80500
},
{
"epoch": 1.33,
"learning_rate": 9.883470925175205e-06,
"loss": 6.1261,
"step": 81000
},
{
"epoch": 1.34,
"learning_rate": 9.882650297887706e-06,
"loss": 6.1258,
"step": 81500
},
{
"epoch": 1.34,
"learning_rate": 9.881829670600208e-06,
"loss": 6.1199,
"step": 82000
},
{
"epoch": 1.35,
"learning_rate": 9.88100904331271e-06,
"loss": 6.123,
"step": 82500
},
{
"epoch": 1.36,
"learning_rate": 9.88018841602521e-06,
"loss": 6.1199,
"step": 83000
},
{
"epoch": 1.37,
"learning_rate": 9.879367788737711e-06,
"loss": 6.1219,
"step": 83500
},
{
"epoch": 1.38,
"learning_rate": 9.878547161450213e-06,
"loss": 6.1195,
"step": 84000
},
{
"epoch": 1.38,
"learning_rate": 9.877726534162715e-06,
"loss": 6.112,
"step": 84500
},
{
"epoch": 1.39,
"learning_rate": 9.876905906875216e-06,
"loss": 6.1239,
"step": 85000
},
{
"epoch": 1.4,
"learning_rate": 9.876085279587718e-06,
"loss": 6.1191,
"step": 85500
},
{
"epoch": 1.41,
"learning_rate": 9.87526465230022e-06,
"loss": 6.115,
"step": 86000
},
{
"epoch": 1.42,
"learning_rate": 9.87444402501272e-06,
"loss": 6.115,
"step": 86500
},
{
"epoch": 1.43,
"learning_rate": 9.873623397725221e-06,
"loss": 6.1112,
"step": 87000
},
{
"epoch": 1.43,
"learning_rate": 9.872802770437723e-06,
"loss": 6.1141,
"step": 87500
},
{
"epoch": 1.44,
"learning_rate": 9.871982143150225e-06,
"loss": 6.1179,
"step": 88000
},
{
"epoch": 1.45,
"learning_rate": 9.871161515862726e-06,
"loss": 6.1109,
"step": 88500
},
{
"epoch": 1.46,
"learning_rate": 9.870340888575228e-06,
"loss": 6.1109,
"step": 89000
},
{
"epoch": 1.47,
"learning_rate": 9.86952026128773e-06,
"loss": 6.1074,
"step": 89500
},
{
"epoch": 1.47,
"learning_rate": 9.86869963400023e-06,
"loss": 6.1079,
"step": 90000
},
{
"epoch": 1.48,
"learning_rate": 9.867879006712731e-06,
"loss": 6.1074,
"step": 90500
},
{
"epoch": 1.49,
"learning_rate": 9.867058379425233e-06,
"loss": 6.102,
"step": 91000
},
{
"epoch": 1.5,
"learning_rate": 9.866237752137735e-06,
"loss": 6.1018,
"step": 91500
},
{
"epoch": 1.51,
"learning_rate": 9.865417124850236e-06,
"loss": 6.1033,
"step": 92000
},
{
"epoch": 1.52,
"learning_rate": 9.864596497562738e-06,
"loss": 6.1009,
"step": 92500
},
{
"epoch": 1.52,
"learning_rate": 9.86377587027524e-06,
"loss": 6.0959,
"step": 93000
},
{
"epoch": 1.53,
"learning_rate": 9.86295524298774e-06,
"loss": 6.0982,
"step": 93500
},
{
"epoch": 1.54,
"learning_rate": 9.862134615700241e-06,
"loss": 6.1017,
"step": 94000
},
{
"epoch": 1.55,
"learning_rate": 9.861313988412743e-06,
"loss": 6.103,
"step": 94500
},
{
"epoch": 1.56,
"learning_rate": 9.860493361125245e-06,
"loss": 6.1043,
"step": 95000
},
{
"epoch": 1.56,
"learning_rate": 9.859672733837746e-06,
"loss": 6.0965,
"step": 95500
},
{
"epoch": 1.57,
"learning_rate": 9.858852106550248e-06,
"loss": 6.0955,
"step": 96000
},
{
"epoch": 1.58,
"learning_rate": 9.85803147926275e-06,
"loss": 6.0968,
"step": 96500
},
{
"epoch": 1.59,
"learning_rate": 9.85721085197525e-06,
"loss": 6.0964,
"step": 97000
},
{
"epoch": 1.6,
"learning_rate": 9.856390224687751e-06,
"loss": 6.096,
"step": 97500
},
{
"epoch": 1.61,
"learning_rate": 9.855569597400253e-06,
"loss": 6.0951,
"step": 98000
},
{
"epoch": 1.61,
"learning_rate": 9.854748970112756e-06,
"loss": 6.1004,
"step": 98500
},
{
"epoch": 1.62,
"learning_rate": 9.853928342825256e-06,
"loss": 6.0914,
"step": 99000
},
{
"epoch": 1.63,
"learning_rate": 9.853107715537758e-06,
"loss": 6.0879,
"step": 99500
},
{
"epoch": 1.64,
"learning_rate": 9.85228708825026e-06,
"loss": 6.0957,
"step": 100000
},
{
"epoch": 1.65,
"learning_rate": 9.851466460962761e-06,
"loss": 6.09,
"step": 100500
},
{
"epoch": 1.65,
"learning_rate": 9.850645833675261e-06,
"loss": 6.0914,
"step": 101000
},
{
"epoch": 1.66,
"learning_rate": 9.849825206387764e-06,
"loss": 6.0896,
"step": 101500
},
{
"epoch": 1.67,
"learning_rate": 9.849004579100266e-06,
"loss": 6.0842,
"step": 102000
},
{
"epoch": 1.68,
"learning_rate": 9.848183951812766e-06,
"loss": 6.0889,
"step": 102500
},
{
"epoch": 1.69,
"learning_rate": 9.847363324525268e-06,
"loss": 6.088,
"step": 103000
},
{
"epoch": 1.7,
"learning_rate": 9.84654269723777e-06,
"loss": 6.079,
"step": 103500
},
{
"epoch": 1.7,
"learning_rate": 9.845722069950271e-06,
"loss": 6.0831,
"step": 104000
},
{
"epoch": 1.71,
"learning_rate": 9.844901442662771e-06,
"loss": 6.0864,
"step": 104500
},
{
"epoch": 1.72,
"learning_rate": 9.844080815375274e-06,
"loss": 6.0831,
"step": 105000
},
{
"epoch": 1.73,
"learning_rate": 9.843260188087776e-06,
"loss": 6.083,
"step": 105500
},
{
"epoch": 1.74,
"learning_rate": 9.842439560800276e-06,
"loss": 6.0828,
"step": 106000
},
{
"epoch": 1.75,
"learning_rate": 9.841618933512778e-06,
"loss": 6.0824,
"step": 106500
},
{
"epoch": 1.75,
"learning_rate": 9.84079830622528e-06,
"loss": 6.0838,
"step": 107000
},
{
"epoch": 1.76,
"learning_rate": 9.839977678937781e-06,
"loss": 6.0819,
"step": 107500
},
{
"epoch": 1.77,
"learning_rate": 9.839157051650282e-06,
"loss": 6.0776,
"step": 108000
},
{
"epoch": 1.78,
"learning_rate": 9.838336424362784e-06,
"loss": 6.0779,
"step": 108500
},
{
"epoch": 1.79,
"learning_rate": 9.837515797075286e-06,
"loss": 6.0756,
"step": 109000
},
{
"epoch": 1.79,
"learning_rate": 9.836695169787786e-06,
"loss": 6.074,
"step": 109500
},
{
"epoch": 1.8,
"learning_rate": 9.835874542500288e-06,
"loss": 6.0729,
"step": 110000
},
{
"epoch": 1.81,
"learning_rate": 9.83505391521279e-06,
"loss": 6.0765,
"step": 110500
},
{
"epoch": 1.82,
"learning_rate": 9.834233287925291e-06,
"loss": 6.0733,
"step": 111000
},
{
"epoch": 1.83,
"learning_rate": 9.833412660637792e-06,
"loss": 6.0773,
"step": 111500
},
{
"epoch": 1.84,
"learning_rate": 9.832592033350294e-06,
"loss": 6.0763,
"step": 112000
},
{
"epoch": 1.84,
"learning_rate": 9.831771406062796e-06,
"loss": 6.0769,
"step": 112500
},
{
"epoch": 1.85,
"learning_rate": 9.830950778775296e-06,
"loss": 6.0743,
"step": 113000
},
{
"epoch": 1.86,
"learning_rate": 9.830130151487799e-06,
"loss": 6.0759,
"step": 113500
},
{
"epoch": 1.87,
"learning_rate": 9.8293095242003e-06,
"loss": 6.0737,
"step": 114000
},
{
"epoch": 1.88,
"learning_rate": 9.828488896912801e-06,
"loss": 6.068,
"step": 114500
},
{
"epoch": 1.88,
"learning_rate": 9.827668269625302e-06,
"loss": 6.0702,
"step": 115000
},
{
"epoch": 1.89,
"learning_rate": 9.826847642337804e-06,
"loss": 6.0664,
"step": 115500
},
{
"epoch": 1.9,
"learning_rate": 9.826027015050306e-06,
"loss": 6.0705,
"step": 116000
},
{
"epoch": 1.91,
"learning_rate": 9.825206387762806e-06,
"loss": 6.0654,
"step": 116500
},
{
"epoch": 1.92,
"learning_rate": 9.824385760475309e-06,
"loss": 6.0703,
"step": 117000
},
{
"epoch": 1.93,
"learning_rate": 9.823565133187809e-06,
"loss": 6.0618,
"step": 117500
},
{
"epoch": 1.93,
"learning_rate": 9.822744505900311e-06,
"loss": 6.0694,
"step": 118000
},
{
"epoch": 1.94,
"learning_rate": 9.821923878612812e-06,
"loss": 6.0637,
"step": 118500
},
{
"epoch": 1.95,
"learning_rate": 9.821103251325314e-06,
"loss": 6.0689,
"step": 119000
},
{
"epoch": 1.96,
"learning_rate": 9.820282624037816e-06,
"loss": 6.0652,
"step": 119500
},
{
"epoch": 1.97,
"learning_rate": 9.819461996750317e-06,
"loss": 6.0656,
"step": 120000
},
{
"epoch": 1.97,
"learning_rate": 9.818641369462819e-06,
"loss": 6.0608,
"step": 120500
},
{
"epoch": 1.98,
"learning_rate": 9.81782074217532e-06,
"loss": 6.0624,
"step": 121000
},
{
"epoch": 1.99,
"learning_rate": 9.817000114887821e-06,
"loss": 6.0609,
"step": 121500
},
{
"epoch": 2.0,
"learning_rate": 9.816179487600322e-06,
"loss": 6.0616,
"step": 122000
},
{
"epoch": 2.01,
"learning_rate": 9.815358860312824e-06,
"loss": 6.0602,
"step": 122500
},
{
"epoch": 2.02,
"learning_rate": 9.814538233025326e-06,
"loss": 6.0581,
"step": 123000
},
{
"epoch": 2.02,
"learning_rate": 9.813717605737827e-06,
"loss": 6.0584,
"step": 123500
},
{
"epoch": 2.03,
"learning_rate": 9.812896978450329e-06,
"loss": 6.0586,
"step": 124000
},
{
"epoch": 2.04,
"learning_rate": 9.81207635116283e-06,
"loss": 6.0598,
"step": 124500
},
{
"epoch": 2.05,
"learning_rate": 9.811255723875331e-06,
"loss": 6.0538,
"step": 125000
},
{
"epoch": 2.06,
"learning_rate": 9.810435096587832e-06,
"loss": 6.0549,
"step": 125500
},
{
"epoch": 2.06,
"learning_rate": 9.809614469300334e-06,
"loss": 6.0544,
"step": 126000
},
{
"epoch": 2.07,
"learning_rate": 9.808793842012836e-06,
"loss": 6.0574,
"step": 126500
},
{
"epoch": 2.08,
"learning_rate": 9.807973214725337e-06,
"loss": 6.0497,
"step": 127000
},
{
"epoch": 2.09,
"learning_rate": 9.807152587437839e-06,
"loss": 6.0581,
"step": 127500
},
{
"epoch": 2.1,
"learning_rate": 9.80633196015034e-06,
"loss": 6.0536,
"step": 128000
},
{
"epoch": 2.11,
"learning_rate": 9.805511332862842e-06,
"loss": 6.0557,
"step": 128500
},
{
"epoch": 2.11,
"learning_rate": 9.804690705575342e-06,
"loss": 6.0542,
"step": 129000
},
{
"epoch": 2.12,
"learning_rate": 9.803870078287844e-06,
"loss": 6.053,
"step": 129500
},
{
"epoch": 2.13,
"learning_rate": 9.803049451000346e-06,
"loss": 6.052,
"step": 130000
},
{
"epoch": 2.14,
"learning_rate": 9.802228823712847e-06,
"loss": 6.0513,
"step": 130500
},
{
"epoch": 2.15,
"learning_rate": 9.801408196425349e-06,
"loss": 6.0508,
"step": 131000
},
{
"epoch": 2.15,
"learning_rate": 9.80058756913785e-06,
"loss": 6.0524,
"step": 131500
},
{
"epoch": 2.16,
"learning_rate": 9.799766941850352e-06,
"loss": 6.0535,
"step": 132000
},
{
"epoch": 2.17,
"learning_rate": 9.798946314562852e-06,
"loss": 6.0538,
"step": 132500
},
{
"epoch": 2.18,
"learning_rate": 9.798125687275354e-06,
"loss": 6.0446,
"step": 133000
},
{
"epoch": 2.19,
"learning_rate": 9.797305059987855e-06,
"loss": 6.0518,
"step": 133500
},
{
"epoch": 2.2,
"learning_rate": 9.796484432700357e-06,
"loss": 6.0478,
"step": 134000
},
{
"epoch": 2.2,
"learning_rate": 9.795663805412859e-06,
"loss": 6.0468,
"step": 134500
},
{
"epoch": 2.21,
"learning_rate": 9.79484317812536e-06,
"loss": 6.0492,
"step": 135000
},
{
"epoch": 2.22,
"learning_rate": 9.794022550837862e-06,
"loss": 6.0492,
"step": 135500
},
{
"epoch": 2.23,
"learning_rate": 9.793201923550362e-06,
"loss": 6.0466,
"step": 136000
},
{
"epoch": 2.24,
"learning_rate": 9.792381296262864e-06,
"loss": 6.0437,
"step": 136500
},
{
"epoch": 2.24,
"learning_rate": 9.791560668975365e-06,
"loss": 6.0414,
"step": 137000
},
{
"epoch": 2.25,
"learning_rate": 9.790740041687867e-06,
"loss": 6.0425,
"step": 137500
},
{
"epoch": 2.26,
"learning_rate": 9.78991941440037e-06,
"loss": 6.0424,
"step": 138000
},
{
"epoch": 2.27,
"learning_rate": 9.78909878711287e-06,
"loss": 6.0392,
"step": 138500
},
{
"epoch": 2.28,
"learning_rate": 9.788278159825372e-06,
"loss": 6.0491,
"step": 139000
},
{
"epoch": 2.29,
"learning_rate": 9.787457532537872e-06,
"loss": 6.0431,
"step": 139500
},
{
"epoch": 2.29,
"learning_rate": 9.786636905250374e-06,
"loss": 6.0426,
"step": 140000
},
{
"epoch": 2.3,
"learning_rate": 9.785816277962875e-06,
"loss": 6.0423,
"step": 140500
},
{
"epoch": 2.31,
"learning_rate": 9.784995650675377e-06,
"loss": 6.0451,
"step": 141000
},
{
"epoch": 2.32,
"learning_rate": 9.78417502338788e-06,
"loss": 6.0384,
"step": 141500
},
{
"epoch": 2.33,
"learning_rate": 9.78335439610038e-06,
"loss": 6.0383,
"step": 142000
},
{
"epoch": 2.33,
"learning_rate": 9.782533768812882e-06,
"loss": 6.0411,
"step": 142500
},
{
"epoch": 2.34,
"learning_rate": 9.781713141525382e-06,
"loss": 6.045,
"step": 143000
},
{
"epoch": 2.35,
"learning_rate": 9.780892514237885e-06,
"loss": 6.0359,
"step": 143500
},
{
"epoch": 2.36,
"learning_rate": 9.780071886950385e-06,
"loss": 6.0368,
"step": 144000
},
{
"epoch": 2.37,
"learning_rate": 9.779251259662887e-06,
"loss": 6.0342,
"step": 144500
},
{
"epoch": 2.38,
"learning_rate": 9.77843063237539e-06,
"loss": 6.039,
"step": 145000
},
{
"epoch": 2.38,
"learning_rate": 9.77761000508789e-06,
"loss": 6.0401,
"step": 145500
},
{
"epoch": 2.39,
"learning_rate": 9.776789377800392e-06,
"loss": 6.0357,
"step": 146000
},
{
"epoch": 2.4,
"learning_rate": 9.775968750512892e-06,
"loss": 6.0402,
"step": 146500
},
{
"epoch": 2.41,
"learning_rate": 9.775148123225395e-06,
"loss": 6.0361,
"step": 147000
},
{
"epoch": 2.42,
"learning_rate": 9.774327495937895e-06,
"loss": 6.0367,
"step": 147500
},
{
"epoch": 2.43,
"learning_rate": 9.773506868650397e-06,
"loss": 6.0301,
"step": 148000
},
{
"epoch": 2.43,
"learning_rate": 9.7726862413629e-06,
"loss": 6.0378,
"step": 148500
},
{
"epoch": 2.44,
"learning_rate": 9.7718656140754e-06,
"loss": 6.0314,
"step": 149000
},
{
"epoch": 2.45,
"learning_rate": 9.7710449867879e-06,
"loss": 6.0296,
"step": 149500
},
{
"epoch": 2.46,
"learning_rate": 9.770224359500403e-06,
"loss": 6.0342,
"step": 150000
},
{
"epoch": 2.47,
"learning_rate": 9.769403732212905e-06,
"loss": 6.0295,
"step": 150500
},
{
"epoch": 2.47,
"learning_rate": 9.768583104925405e-06,
"loss": 6.0337,
"step": 151000
},
{
"epoch": 2.48,
"learning_rate": 9.767762477637907e-06,
"loss": 6.0355,
"step": 151500
},
{
"epoch": 2.49,
"learning_rate": 9.76694185035041e-06,
"loss": 6.0272,
"step": 152000
},
{
"epoch": 2.5,
"learning_rate": 9.76612122306291e-06,
"loss": 6.0313,
"step": 152500
},
{
"epoch": 2.51,
"learning_rate": 9.76530059577541e-06,
"loss": 6.0267,
"step": 153000
},
{
"epoch": 2.52,
"learning_rate": 9.764479968487913e-06,
"loss": 6.028,
"step": 153500
},
{
"epoch": 2.52,
"learning_rate": 9.763659341200415e-06,
"loss": 6.0238,
"step": 154000
},
{
"epoch": 2.53,
"learning_rate": 9.762838713912915e-06,
"loss": 6.0293,
"step": 154500
},
{
"epoch": 2.54,
"learning_rate": 9.762018086625417e-06,
"loss": 6.0291,
"step": 155000
},
{
"epoch": 2.55,
"learning_rate": 9.76119745933792e-06,
"loss": 6.0258,
"step": 155500
},
{
"epoch": 2.56,
"learning_rate": 9.76037683205042e-06,
"loss": 6.0246,
"step": 156000
},
{
"epoch": 2.56,
"learning_rate": 9.75955620476292e-06,
"loss": 6.0251,
"step": 156500
},
{
"epoch": 2.57,
"learning_rate": 9.758735577475423e-06,
"loss": 6.0315,
"step": 157000
},
{
"epoch": 2.58,
"learning_rate": 9.757914950187925e-06,
"loss": 6.029,
"step": 157500
},
{
"epoch": 2.59,
"learning_rate": 9.757094322900425e-06,
"loss": 6.0293,
"step": 158000
},
{
"epoch": 2.6,
"learning_rate": 9.756273695612928e-06,
"loss": 6.0257,
"step": 158500
},
{
"epoch": 2.61,
"learning_rate": 9.75545306832543e-06,
"loss": 6.0216,
"step": 159000
},
{
"epoch": 2.61,
"learning_rate": 9.75463244103793e-06,
"loss": 6.0269,
"step": 159500
},
{
"epoch": 2.62,
"learning_rate": 9.75381181375043e-06,
"loss": 6.0241,
"step": 160000
},
{
"epoch": 2.63,
"learning_rate": 9.752991186462933e-06,
"loss": 6.0261,
"step": 160500
},
{
"epoch": 2.64,
"learning_rate": 9.752170559175435e-06,
"loss": 6.0194,
"step": 161000
},
{
"epoch": 2.65,
"learning_rate": 9.751349931887935e-06,
"loss": 6.0225,
"step": 161500
},
{
"epoch": 2.65,
"learning_rate": 9.750529304600438e-06,
"loss": 6.0214,
"step": 162000
},
{
"epoch": 2.66,
"learning_rate": 9.74970867731294e-06,
"loss": 6.0182,
"step": 162500
},
{
"epoch": 2.67,
"learning_rate": 9.74888805002544e-06,
"loss": 6.0224,
"step": 163000
},
{
"epoch": 2.68,
"learning_rate": 9.74806742273794e-06,
"loss": 6.0245,
"step": 163500
},
{
"epoch": 2.69,
"learning_rate": 9.747246795450443e-06,
"loss": 6.0222,
"step": 164000
},
{
"epoch": 2.7,
"learning_rate": 9.746426168162945e-06,
"loss": 6.0206,
"step": 164500
},
{
"epoch": 2.7,
"learning_rate": 9.745605540875446e-06,
"loss": 6.0224,
"step": 165000
},
{
"epoch": 2.71,
"learning_rate": 9.744784913587948e-06,
"loss": 6.0208,
"step": 165500
},
{
"epoch": 2.72,
"learning_rate": 9.74396428630045e-06,
"loss": 6.018,
"step": 166000
},
{
"epoch": 2.73,
"learning_rate": 9.74314365901295e-06,
"loss": 6.0226,
"step": 166500
},
{
"epoch": 2.74,
"learning_rate": 9.74232303172545e-06,
"loss": 6.0173,
"step": 167000
},
{
"epoch": 2.74,
"learning_rate": 9.741502404437953e-06,
"loss": 6.0182,
"step": 167500
},
{
"epoch": 2.75,
"learning_rate": 9.740681777150455e-06,
"loss": 6.0187,
"step": 168000
},
{
"epoch": 2.76,
"learning_rate": 9.739861149862956e-06,
"loss": 6.012,
"step": 168500
},
{
"epoch": 2.77,
"learning_rate": 9.739040522575458e-06,
"loss": 6.0129,
"step": 169000
},
{
"epoch": 2.78,
"learning_rate": 9.73821989528796e-06,
"loss": 6.0207,
"step": 169500
},
{
"epoch": 2.79,
"learning_rate": 9.73739926800046e-06,
"loss": 6.0183,
"step": 170000
},
{
"epoch": 2.79,
"learning_rate": 9.736578640712961e-06,
"loss": 6.0149,
"step": 170500
},
{
"epoch": 2.8,
"learning_rate": 9.735758013425463e-06,
"loss": 6.0157,
"step": 171000
},
{
"epoch": 2.81,
"learning_rate": 9.734937386137965e-06,
"loss": 6.0195,
"step": 171500
},
{
"epoch": 2.82,
"learning_rate": 9.734116758850466e-06,
"loss": 6.0137,
"step": 172000
},
{
"epoch": 2.83,
"learning_rate": 9.733296131562968e-06,
"loss": 6.0161,
"step": 172500
},
{
"epoch": 2.83,
"learning_rate": 9.73247550427547e-06,
"loss": 6.0134,
"step": 173000
},
{
"epoch": 2.84,
"learning_rate": 9.73165487698797e-06,
"loss": 6.0139,
"step": 173500
},
{
"epoch": 2.85,
"learning_rate": 9.730834249700471e-06,
"loss": 6.0145,
"step": 174000
},
{
"epoch": 2.86,
"learning_rate": 9.730013622412973e-06,
"loss": 6.011,
"step": 174500
},
{
"epoch": 2.87,
"learning_rate": 9.729192995125475e-06,
"loss": 6.0145,
"step": 175000
},
{
"epoch": 2.88,
"learning_rate": 9.728372367837976e-06,
"loss": 6.0093,
"step": 175500
},
{
"epoch": 2.88,
"learning_rate": 9.727551740550478e-06,
"loss": 6.0074,
"step": 176000
},
{
"epoch": 2.89,
"learning_rate": 9.72673111326298e-06,
"loss": 6.0097,
"step": 176500
},
{
"epoch": 2.9,
"learning_rate": 9.72591048597548e-06,
"loss": 6.013,
"step": 177000
},
{
"epoch": 2.91,
"learning_rate": 9.725089858687981e-06,
"loss": 6.0085,
"step": 177500
},
{
"epoch": 2.92,
"learning_rate": 9.724269231400483e-06,
"loss": 6.008,
"step": 178000
},
{
"epoch": 2.92,
"learning_rate": 9.723448604112985e-06,
"loss": 6.0169,
"step": 178500
},
{
"epoch": 2.93,
"learning_rate": 9.722627976825486e-06,
"loss": 6.0097,
"step": 179000
},
{
"epoch": 2.94,
"learning_rate": 9.721807349537988e-06,
"loss": 6.0052,
"step": 179500
},
{
"epoch": 2.95,
"learning_rate": 9.72098672225049e-06,
"loss": 6.0113,
"step": 180000
},
{
"epoch": 2.96,
"learning_rate": 9.72016609496299e-06,
"loss": 6.0088,
"step": 180500
},
{
"epoch": 2.97,
"learning_rate": 9.719345467675491e-06,
"loss": 6.0117,
"step": 181000
},
{
"epoch": 2.97,
"learning_rate": 9.718524840387993e-06,
"loss": 6.0062,
"step": 181500
},
{
"epoch": 2.98,
"learning_rate": 9.717704213100495e-06,
"loss": 6.0086,
"step": 182000
},
{
"epoch": 2.99,
"learning_rate": 9.716883585812996e-06,
"loss": 6.0071,
"step": 182500
},
{
"epoch": 3.0,
"learning_rate": 9.716062958525498e-06,
"loss": 6.0028,
"step": 183000
},
{
"epoch": 3.01,
"learning_rate": 9.715242331238e-06,
"loss": 6.0089,
"step": 183500
},
{
"epoch": 3.01,
"learning_rate": 9.7144217039505e-06,
"loss": 6.0051,
"step": 184000
},
{
"epoch": 3.02,
"learning_rate": 9.713601076663001e-06,
"loss": 6.0033,
"step": 184500
},
{
"epoch": 3.03,
"learning_rate": 9.712780449375503e-06,
"loss": 6.0077,
"step": 185000
},
{
"epoch": 3.04,
"learning_rate": 9.711959822088006e-06,
"loss": 6.0043,
"step": 185500
},
{
"epoch": 3.05,
"learning_rate": 9.711139194800506e-06,
"loss": 6.0029,
"step": 186000
},
{
"epoch": 3.06,
"learning_rate": 9.710318567513008e-06,
"loss": 6.0042,
"step": 186500
},
{
"epoch": 3.06,
"learning_rate": 9.70949794022551e-06,
"loss": 6.0027,
"step": 187000
},
{
"epoch": 3.07,
"learning_rate": 9.70867731293801e-06,
"loss": 6.0067,
"step": 187500
},
{
"epoch": 3.08,
"learning_rate": 9.707856685650511e-06,
"loss": 6.0039,
"step": 188000
},
{
"epoch": 3.09,
"learning_rate": 9.707036058363013e-06,
"loss": 6.0011,
"step": 188500
},
{
"epoch": 3.1,
"learning_rate": 9.706215431075516e-06,
"loss": 6.0048,
"step": 189000
},
{
"epoch": 3.11,
"learning_rate": 9.705394803788016e-06,
"loss": 5.9993,
"step": 189500
},
{
"epoch": 3.11,
"learning_rate": 9.704574176500518e-06,
"loss": 6.0025,
"step": 190000
},
{
"epoch": 3.12,
"learning_rate": 9.70375354921302e-06,
"loss": 6.0051,
"step": 190500
},
{
"epoch": 3.13,
"learning_rate": 9.702932921925521e-06,
"loss": 5.9963,
"step": 191000
},
{
"epoch": 3.14,
"learning_rate": 9.702112294638021e-06,
"loss": 5.9946,
"step": 191500
},
{
"epoch": 3.15,
"learning_rate": 9.701291667350524e-06,
"loss": 5.999,
"step": 192000
},
{
"epoch": 3.15,
"learning_rate": 9.700471040063026e-06,
"loss": 5.9966,
"step": 192500
},
{
"epoch": 3.16,
"learning_rate": 9.699650412775526e-06,
"loss": 6.0022,
"step": 193000
},
{
"epoch": 3.17,
"learning_rate": 9.698829785488028e-06,
"loss": 6.0003,
"step": 193500
},
{
"epoch": 3.18,
"learning_rate": 9.69800915820053e-06,
"loss": 6.0,
"step": 194000
},
{
"epoch": 3.19,
"learning_rate": 9.697188530913031e-06,
"loss": 6.0025,
"step": 194500
},
{
"epoch": 3.2,
"learning_rate": 9.696367903625531e-06,
"loss": 5.9967,
"step": 195000
},
{
"epoch": 3.2,
"learning_rate": 9.695547276338034e-06,
"loss": 6.0,
"step": 195500
},
{
"epoch": 3.21,
"learning_rate": 9.694726649050536e-06,
"loss": 5.9983,
"step": 196000
},
{
"epoch": 3.22,
"learning_rate": 9.693906021763036e-06,
"loss": 5.9985,
"step": 196500
},
{
"epoch": 3.23,
"learning_rate": 9.693085394475538e-06,
"loss": 5.9922,
"step": 197000
},
{
"epoch": 3.24,
"learning_rate": 9.69226476718804e-06,
"loss": 5.9955,
"step": 197500
},
{
"epoch": 3.24,
"learning_rate": 9.691444139900541e-06,
"loss": 5.997,
"step": 198000
},
{
"epoch": 3.25,
"learning_rate": 9.690623512613042e-06,
"loss": 5.9986,
"step": 198500
},
{
"epoch": 3.26,
"learning_rate": 9.689802885325544e-06,
"loss": 6.0001,
"step": 199000
},
{
"epoch": 3.27,
"learning_rate": 9.688982258038046e-06,
"loss": 5.9945,
"step": 199500
},
{
"epoch": 3.28,
"learning_rate": 9.688161630750546e-06,
"loss": 5.9906,
"step": 200000
},
{
"epoch": 3.29,
"learning_rate": 9.687341003463049e-06,
"loss": 5.9948,
"step": 200500
},
{
"epoch": 3.29,
"learning_rate": 9.686520376175549e-06,
"loss": 5.9954,
"step": 201000
},
{
"epoch": 3.3,
"learning_rate": 9.685699748888051e-06,
"loss": 5.9916,
"step": 201500
},
{
"epoch": 3.31,
"learning_rate": 9.684879121600552e-06,
"loss": 5.9945,
"step": 202000
},
{
"epoch": 3.32,
"learning_rate": 9.684058494313054e-06,
"loss": 5.9961,
"step": 202500
},
{
"epoch": 3.33,
"learning_rate": 9.683237867025556e-06,
"loss": 5.994,
"step": 203000
},
{
"epoch": 3.33,
"learning_rate": 9.682417239738056e-06,
"loss": 5.9949,
"step": 203500
},
{
"epoch": 3.34,
"learning_rate": 9.681596612450559e-06,
"loss": 5.9875,
"step": 204000
},
{
"epoch": 3.35,
"learning_rate": 9.680775985163059e-06,
"loss": 5.9897,
"step": 204500
},
{
"epoch": 3.36,
"learning_rate": 9.679955357875561e-06,
"loss": 5.9948,
"step": 205000
},
{
"epoch": 3.37,
"learning_rate": 9.679134730588062e-06,
"loss": 5.9893,
"step": 205500
},
{
"epoch": 3.38,
"learning_rate": 9.678314103300564e-06,
"loss": 5.9901,
"step": 206000
},
{
"epoch": 3.38,
"learning_rate": 9.677493476013066e-06,
"loss": 5.985,
"step": 206500
},
{
"epoch": 3.39,
"learning_rate": 9.676672848725567e-06,
"loss": 5.992,
"step": 207000
},
{
"epoch": 3.4,
"learning_rate": 9.675852221438069e-06,
"loss": 5.9911,
"step": 207500
},
{
"epoch": 3.41,
"learning_rate": 9.67503159415057e-06,
"loss": 5.9914,
"step": 208000
},
{
"epoch": 3.42,
"learning_rate": 9.674210966863071e-06,
"loss": 5.9868,
"step": 208500
},
{
"epoch": 3.42,
"learning_rate": 9.673390339575572e-06,
"loss": 5.9901,
"step": 209000
},
{
"epoch": 3.43,
"learning_rate": 9.672569712288074e-06,
"loss": 5.984,
"step": 209500
},
{
"epoch": 3.44,
"learning_rate": 9.671749085000576e-06,
"loss": 5.99,
"step": 210000
},
{
"epoch": 3.45,
"learning_rate": 9.670928457713077e-06,
"loss": 5.9902,
"step": 210500
},
{
"epoch": 3.46,
"learning_rate": 9.670107830425579e-06,
"loss": 5.9858,
"step": 211000
},
{
"epoch": 3.47,
"learning_rate": 9.66928720313808e-06,
"loss": 5.9822,
"step": 211500
},
{
"epoch": 3.47,
"learning_rate": 9.668466575850581e-06,
"loss": 5.9871,
"step": 212000
},
{
"epoch": 3.48,
"learning_rate": 9.667645948563082e-06,
"loss": 5.9866,
"step": 212500
},
{
"epoch": 3.49,
"learning_rate": 9.666825321275584e-06,
"loss": 5.9862,
"step": 213000
},
{
"epoch": 3.5,
"learning_rate": 9.666004693988086e-06,
"loss": 5.9821,
"step": 213500
},
{
"epoch": 3.51,
"learning_rate": 9.665184066700587e-06,
"loss": 5.9813,
"step": 214000
},
{
"epoch": 3.51,
"learning_rate": 9.664363439413089e-06,
"loss": 5.9799,
"step": 214500
},
{
"epoch": 3.52,
"learning_rate": 9.66354281212559e-06,
"loss": 5.9841,
"step": 215000
},
{
"epoch": 3.53,
"learning_rate": 9.662722184838092e-06,
"loss": 5.9765,
"step": 215500
},
{
"epoch": 3.54,
"learning_rate": 9.661901557550592e-06,
"loss": 5.9729,
"step": 216000
},
{
"epoch": 3.55,
"learning_rate": 9.661080930263094e-06,
"loss": 5.9722,
"step": 216500
},
{
"epoch": 3.56,
"learning_rate": 9.660260302975595e-06,
"loss": 5.9711,
"step": 217000
},
{
"epoch": 3.56,
"learning_rate": 9.659439675688097e-06,
"loss": 5.9697,
"step": 217500
},
{
"epoch": 3.57,
"learning_rate": 9.658619048400599e-06,
"loss": 5.9561,
"step": 218000
},
{
"epoch": 3.58,
"learning_rate": 9.6577984211131e-06,
"loss": 5.9558,
"step": 218500
},
{
"epoch": 3.59,
"learning_rate": 9.656977793825602e-06,
"loss": 5.9524,
"step": 219000
},
{
"epoch": 3.6,
"learning_rate": 9.656157166538102e-06,
"loss": 5.9474,
"step": 219500
},
{
"epoch": 3.6,
"learning_rate": 9.655336539250604e-06,
"loss": 5.9422,
"step": 220000
},
{
"epoch": 3.61,
"learning_rate": 9.654515911963105e-06,
"loss": 5.9394,
"step": 220500
},
{
"epoch": 3.62,
"learning_rate": 9.653695284675607e-06,
"loss": 5.9274,
"step": 221000
},
{
"epoch": 3.63,
"learning_rate": 9.652874657388109e-06,
"loss": 5.9342,
"step": 221500
},
{
"epoch": 3.64,
"learning_rate": 9.65205403010061e-06,
"loss": 5.928,
"step": 222000
},
{
"epoch": 3.65,
"learning_rate": 9.651233402813112e-06,
"loss": 5.9243,
"step": 222500
},
{
"epoch": 3.65,
"learning_rate": 9.650412775525612e-06,
"loss": 5.9183,
"step": 223000
},
{
"epoch": 3.66,
"learning_rate": 9.649592148238114e-06,
"loss": 5.9142,
"step": 223500
},
{
"epoch": 3.67,
"learning_rate": 9.648771520950615e-06,
"loss": 5.9075,
"step": 224000
},
{
"epoch": 3.68,
"learning_rate": 9.647950893663117e-06,
"loss": 5.9022,
"step": 224500
},
{
"epoch": 3.69,
"learning_rate": 9.647130266375619e-06,
"loss": 5.8985,
"step": 225000
},
{
"epoch": 3.69,
"learning_rate": 9.64630963908812e-06,
"loss": 5.896,
"step": 225500
},
{
"epoch": 3.7,
"learning_rate": 9.645489011800622e-06,
"loss": 5.8948,
"step": 226000
},
{
"epoch": 3.71,
"learning_rate": 9.644668384513122e-06,
"loss": 5.8884,
"step": 226500
},
{
"epoch": 3.72,
"learning_rate": 9.643847757225624e-06,
"loss": 5.8867,
"step": 227000
},
{
"epoch": 3.73,
"learning_rate": 9.643027129938125e-06,
"loss": 5.887,
"step": 227500
},
{
"epoch": 3.74,
"learning_rate": 9.642206502650627e-06,
"loss": 5.8805,
"step": 228000
},
{
"epoch": 3.74,
"learning_rate": 9.64138587536313e-06,
"loss": 5.8769,
"step": 228500
},
{
"epoch": 3.75,
"learning_rate": 9.64056524807563e-06,
"loss": 5.8746,
"step": 229000
},
{
"epoch": 3.76,
"learning_rate": 9.639744620788132e-06,
"loss": 5.8716,
"step": 229500
},
{
"epoch": 3.77,
"learning_rate": 9.638923993500632e-06,
"loss": 5.8658,
"step": 230000
},
{
"epoch": 3.78,
"learning_rate": 9.638103366213134e-06,
"loss": 5.863,
"step": 230500
},
{
"epoch": 3.79,
"learning_rate": 9.637282738925635e-06,
"loss": 5.8618,
"step": 231000
},
{
"epoch": 3.79,
"learning_rate": 9.636462111638137e-06,
"loss": 5.8608,
"step": 231500
},
{
"epoch": 3.8,
"learning_rate": 9.63564148435064e-06,
"loss": 5.8547,
"step": 232000
},
{
"epoch": 3.81,
"learning_rate": 9.63482085706314e-06,
"loss": 5.8538,
"step": 232500
},
{
"epoch": 3.82,
"learning_rate": 9.63400022977564e-06,
"loss": 5.8533,
"step": 233000
},
{
"epoch": 3.83,
"learning_rate": 9.633179602488142e-06,
"loss": 5.8478,
"step": 233500
},
{
"epoch": 3.83,
"learning_rate": 9.632358975200645e-06,
"loss": 5.8468,
"step": 234000
},
{
"epoch": 3.84,
"learning_rate": 9.631538347913145e-06,
"loss": 5.8412,
"step": 234500
},
{
"epoch": 3.85,
"learning_rate": 9.630717720625647e-06,
"loss": 5.8408,
"step": 235000
},
{
"epoch": 3.86,
"learning_rate": 9.62989709333815e-06,
"loss": 5.8423,
"step": 235500
},
{
"epoch": 3.87,
"learning_rate": 9.62907646605065e-06,
"loss": 5.8384,
"step": 236000
},
{
"epoch": 3.88,
"learning_rate": 9.62825583876315e-06,
"loss": 5.8333,
"step": 236500
},
{
"epoch": 3.88,
"learning_rate": 9.627435211475652e-06,
"loss": 5.8339,
"step": 237000
},
{
"epoch": 3.89,
"learning_rate": 9.626614584188155e-06,
"loss": 5.8346,
"step": 237500
},
{
"epoch": 3.9,
"learning_rate": 9.625793956900655e-06,
"loss": 5.8269,
"step": 238000
},
{
"epoch": 3.91,
"learning_rate": 9.624973329613157e-06,
"loss": 5.8289,
"step": 238500
},
{
"epoch": 3.92,
"learning_rate": 9.62415270232566e-06,
"loss": 5.8224,
"step": 239000
},
{
"epoch": 3.92,
"learning_rate": 9.62333207503816e-06,
"loss": 5.821,
"step": 239500
},
{
"epoch": 3.93,
"learning_rate": 9.62251144775066e-06,
"loss": 5.824,
"step": 240000
},
{
"epoch": 3.94,
"learning_rate": 9.621690820463163e-06,
"loss": 5.8168,
"step": 240500
},
{
"epoch": 3.95,
"learning_rate": 9.620870193175665e-06,
"loss": 5.817,
"step": 241000
},
{
"epoch": 3.96,
"learning_rate": 9.620049565888165e-06,
"loss": 5.8177,
"step": 241500
},
{
"epoch": 3.97,
"learning_rate": 9.619228938600667e-06,
"loss": 5.8141,
"step": 242000
},
{
"epoch": 3.97,
"learning_rate": 9.61840831131317e-06,
"loss": 5.8145,
"step": 242500
},
{
"epoch": 3.98,
"learning_rate": 9.61758768402567e-06,
"loss": 5.8105,
"step": 243000
},
{
"epoch": 3.99,
"learning_rate": 9.61676705673817e-06,
"loss": 5.81,
"step": 243500
},
{
"epoch": 4.0,
"learning_rate": 9.615946429450673e-06,
"loss": 5.8058,
"step": 244000
},
{
"epoch": 4.01,
"learning_rate": 9.615125802163175e-06,
"loss": 5.8046,
"step": 244500
},
{
"epoch": 4.01,
"learning_rate": 9.614305174875675e-06,
"loss": 5.8036,
"step": 245000
},
{
"epoch": 4.02,
"learning_rate": 9.613484547588177e-06,
"loss": 5.8003,
"step": 245500
},
{
"epoch": 4.03,
"learning_rate": 9.61266392030068e-06,
"loss": 5.8,
"step": 246000
},
{
"epoch": 4.04,
"learning_rate": 9.61184329301318e-06,
"loss": 5.7994,
"step": 246500
},
{
"epoch": 4.05,
"learning_rate": 9.61102266572568e-06,
"loss": 5.7977,
"step": 247000
},
{
"epoch": 4.06,
"learning_rate": 9.610202038438183e-06,
"loss": 5.79,
"step": 247500
},
{
"epoch": 4.06,
"learning_rate": 9.609381411150685e-06,
"loss": 5.7912,
"step": 248000
},
{
"epoch": 4.07,
"learning_rate": 9.608560783863185e-06,
"loss": 5.7935,
"step": 248500
},
{
"epoch": 4.08,
"learning_rate": 9.607740156575688e-06,
"loss": 5.7851,
"step": 249000
},
{
"epoch": 4.09,
"learning_rate": 9.60691952928819e-06,
"loss": 5.7883,
"step": 249500
},
{
"epoch": 4.1,
"learning_rate": 9.60609890200069e-06,
"loss": 5.7903,
"step": 250000
},
{
"epoch": 4.1,
"learning_rate": 9.60527827471319e-06,
"loss": 5.7838,
"step": 250500
},
{
"epoch": 4.11,
"learning_rate": 9.604457647425693e-06,
"loss": 5.7784,
"step": 251000
},
{
"epoch": 4.12,
"learning_rate": 9.603637020138195e-06,
"loss": 5.7776,
"step": 251500
},
{
"epoch": 4.13,
"learning_rate": 9.602816392850695e-06,
"loss": 5.7738,
"step": 252000
},
{
"epoch": 4.14,
"learning_rate": 9.601995765563198e-06,
"loss": 5.7755,
"step": 252500
},
{
"epoch": 4.15,
"learning_rate": 9.6011751382757e-06,
"loss": 5.7719,
"step": 253000
},
{
"epoch": 4.15,
"learning_rate": 9.6003545109882e-06,
"loss": 5.7723,
"step": 253500
},
{
"epoch": 4.16,
"learning_rate": 9.5995338837007e-06,
"loss": 5.7686,
"step": 254000
},
{
"epoch": 4.17,
"learning_rate": 9.598713256413203e-06,
"loss": 5.7676,
"step": 254500
},
{
"epoch": 4.18,
"learning_rate": 9.597892629125705e-06,
"loss": 5.7672,
"step": 255000
},
{
"epoch": 4.19,
"learning_rate": 9.597072001838206e-06,
"loss": 5.7628,
"step": 255500
},
{
"epoch": 4.19,
"learning_rate": 9.596251374550708e-06,
"loss": 5.761,
"step": 256000
},
{
"epoch": 4.2,
"learning_rate": 9.59543074726321e-06,
"loss": 5.7633,
"step": 256500
},
{
"epoch": 4.21,
"learning_rate": 9.59461011997571e-06,
"loss": 5.7581,
"step": 257000
},
{
"epoch": 4.22,
"learning_rate": 9.59378949268821e-06,
"loss": 5.7619,
"step": 257500
},
{
"epoch": 4.23,
"learning_rate": 9.592968865400713e-06,
"loss": 5.758,
"step": 258000
},
{
"epoch": 4.24,
"learning_rate": 9.592148238113215e-06,
"loss": 5.7555,
"step": 258500
},
{
"epoch": 4.24,
"learning_rate": 9.591327610825716e-06,
"loss": 5.7507,
"step": 259000
},
{
"epoch": 4.25,
"learning_rate": 9.590506983538218e-06,
"loss": 5.7519,
"step": 259500
},
{
"epoch": 4.26,
"learning_rate": 9.58968635625072e-06,
"loss": 5.7492,
"step": 260000
},
{
"epoch": 4.27,
"learning_rate": 9.58886572896322e-06,
"loss": 5.7467,
"step": 260500
},
{
"epoch": 4.28,
"learning_rate": 9.588045101675721e-06,
"loss": 5.7457,
"step": 261000
},
{
"epoch": 4.28,
"learning_rate": 9.587224474388223e-06,
"loss": 5.746,
"step": 261500
},
{
"epoch": 4.29,
"learning_rate": 9.586403847100725e-06,
"loss": 5.741,
"step": 262000
},
{
"epoch": 4.3,
"learning_rate": 9.585583219813226e-06,
"loss": 5.7402,
"step": 262500
},
{
"epoch": 4.31,
"learning_rate": 9.584762592525728e-06,
"loss": 5.742,
"step": 263000
},
{
"epoch": 4.32,
"learning_rate": 9.58394196523823e-06,
"loss": 5.7371,
"step": 263500
},
{
"epoch": 4.33,
"learning_rate": 9.58312133795073e-06,
"loss": 5.7388,
"step": 264000
},
{
"epoch": 4.33,
"learning_rate": 9.582300710663231e-06,
"loss": 5.7349,
"step": 264500
},
{
"epoch": 4.34,
"learning_rate": 9.581480083375733e-06,
"loss": 5.7327,
"step": 265000
},
{
"epoch": 4.35,
"learning_rate": 9.580659456088235e-06,
"loss": 5.7296,
"step": 265500
},
{
"epoch": 4.36,
"learning_rate": 9.579838828800736e-06,
"loss": 5.7332,
"step": 266000
},
{
"epoch": 4.37,
"learning_rate": 9.579018201513238e-06,
"loss": 5.7286,
"step": 266500
},
{
"epoch": 4.37,
"learning_rate": 9.57819757422574e-06,
"loss": 5.7251,
"step": 267000
},
{
"epoch": 4.38,
"learning_rate": 9.57737694693824e-06,
"loss": 5.7235,
"step": 267500
},
{
"epoch": 4.39,
"learning_rate": 9.576556319650741e-06,
"loss": 5.7219,
"step": 268000
},
{
"epoch": 4.4,
"learning_rate": 9.575735692363243e-06,
"loss": 5.7223,
"step": 268500
},
{
"epoch": 4.41,
"learning_rate": 9.574915065075745e-06,
"loss": 5.7171,
"step": 269000
},
{
"epoch": 4.42,
"learning_rate": 9.574094437788246e-06,
"loss": 5.7221,
"step": 269500
},
{
"epoch": 4.42,
"learning_rate": 9.573273810500748e-06,
"loss": 5.7192,
"step": 270000
},
{
"epoch": 4.43,
"learning_rate": 9.57245318321325e-06,
"loss": 5.7122,
"step": 270500
},
{
"epoch": 4.44,
"learning_rate": 9.57163255592575e-06,
"loss": 5.7143,
"step": 271000
},
{
"epoch": 4.45,
"learning_rate": 9.570811928638251e-06,
"loss": 5.7114,
"step": 271500
},
{
"epoch": 4.46,
"learning_rate": 9.569991301350753e-06,
"loss": 5.7082,
"step": 272000
},
{
"epoch": 4.47,
"learning_rate": 9.569170674063256e-06,
"loss": 5.7093,
"step": 272500
},
{
"epoch": 4.47,
"learning_rate": 9.568350046775756e-06,
"loss": 5.7109,
"step": 273000
},
{
"epoch": 4.48,
"learning_rate": 9.567529419488258e-06,
"loss": 5.706,
"step": 273500
},
{
"epoch": 4.49,
"learning_rate": 9.56670879220076e-06,
"loss": 5.7005,
"step": 274000
},
{
"epoch": 4.5,
"learning_rate": 9.56588816491326e-06,
"loss": 5.7084,
"step": 274500
},
{
"epoch": 4.51,
"learning_rate": 9.565067537625761e-06,
"loss": 5.7035,
"step": 275000
},
{
"epoch": 4.51,
"learning_rate": 9.564246910338263e-06,
"loss": 5.6939,
"step": 275500
},
{
"epoch": 4.52,
"learning_rate": 9.563426283050766e-06,
"loss": 5.6962,
"step": 276000
},
{
"epoch": 4.53,
"learning_rate": 9.562605655763266e-06,
"loss": 5.6926,
"step": 276500
},
{
"epoch": 4.54,
"learning_rate": 9.561785028475768e-06,
"loss": 5.691,
"step": 277000
},
{
"epoch": 4.55,
"learning_rate": 9.56096440118827e-06,
"loss": 5.6909,
"step": 277500
},
{
"epoch": 4.56,
"learning_rate": 9.560143773900771e-06,
"loss": 5.6904,
"step": 278000
},
{
"epoch": 4.56,
"learning_rate": 9.559323146613271e-06,
"loss": 5.6827,
"step": 278500
},
{
"epoch": 4.57,
"learning_rate": 9.558502519325774e-06,
"loss": 5.6863,
"step": 279000
},
{
"epoch": 4.58,
"learning_rate": 9.557681892038276e-06,
"loss": 5.6846,
"step": 279500
},
{
"epoch": 4.59,
"learning_rate": 9.556861264750776e-06,
"loss": 5.6843,
"step": 280000
},
{
"epoch": 4.6,
"learning_rate": 9.556040637463278e-06,
"loss": 5.6849,
"step": 280500
},
{
"epoch": 4.6,
"learning_rate": 9.555220010175779e-06,
"loss": 5.6826,
"step": 281000
},
{
"epoch": 4.61,
"learning_rate": 9.554399382888281e-06,
"loss": 5.6775,
"step": 281500
},
{
"epoch": 4.62,
"learning_rate": 9.553578755600781e-06,
"loss": 5.6705,
"step": 282000
},
{
"epoch": 4.63,
"learning_rate": 9.552758128313284e-06,
"loss": 5.6714,
"step": 282500
},
{
"epoch": 4.64,
"learning_rate": 9.551937501025786e-06,
"loss": 5.67,
"step": 283000
},
{
"epoch": 4.65,
"learning_rate": 9.551116873738286e-06,
"loss": 5.6753,
"step": 283500
},
{
"epoch": 4.65,
"learning_rate": 9.550296246450788e-06,
"loss": 5.6696,
"step": 284000
},
{
"epoch": 4.66,
"learning_rate": 9.549475619163289e-06,
"loss": 5.667,
"step": 284500
},
{
"epoch": 4.67,
"learning_rate": 9.548654991875791e-06,
"loss": 5.6648,
"step": 285000
},
{
"epoch": 4.68,
"learning_rate": 9.547834364588292e-06,
"loss": 5.6573,
"step": 285500
},
{
"epoch": 4.69,
"learning_rate": 9.547013737300794e-06,
"loss": 5.6603,
"step": 286000
},
{
"epoch": 4.69,
"learning_rate": 9.546193110013296e-06,
"loss": 5.6536,
"step": 286500
},
{
"epoch": 4.7,
"learning_rate": 9.545372482725796e-06,
"loss": 5.6614,
"step": 287000
},
{
"epoch": 4.71,
"learning_rate": 9.544551855438298e-06,
"loss": 5.6569,
"step": 287500
},
{
"epoch": 4.72,
"learning_rate": 9.543731228150799e-06,
"loss": 5.6542,
"step": 288000
},
{
"epoch": 4.73,
"learning_rate": 9.542910600863301e-06,
"loss": 5.6534,
"step": 288500
},
{
"epoch": 4.74,
"learning_rate": 9.542089973575802e-06,
"loss": 5.6499,
"step": 289000
},
{
"epoch": 4.74,
"learning_rate": 9.541269346288304e-06,
"loss": 5.6505,
"step": 289500
},
{
"epoch": 4.75,
"learning_rate": 9.540448719000806e-06,
"loss": 5.6456,
"step": 290000
},
{
"epoch": 4.76,
"learning_rate": 9.539628091713306e-06,
"loss": 5.6456,
"step": 290500
},
{
"epoch": 4.77,
"learning_rate": 9.538807464425809e-06,
"loss": 5.6456,
"step": 291000
},
{
"epoch": 4.78,
"learning_rate": 9.537986837138309e-06,
"loss": 5.6461,
"step": 291500
},
{
"epoch": 4.78,
"learning_rate": 9.537166209850811e-06,
"loss": 5.6376,
"step": 292000
},
{
"epoch": 4.79,
"learning_rate": 9.536345582563312e-06,
"loss": 5.6388,
"step": 292500
},
{
"epoch": 4.8,
"learning_rate": 9.535524955275814e-06,
"loss": 5.6388,
"step": 293000
},
{
"epoch": 4.81,
"learning_rate": 9.534704327988316e-06,
"loss": 5.6354,
"step": 293500
},
{
"epoch": 4.82,
"learning_rate": 9.533883700700816e-06,
"loss": 5.632,
"step": 294000
},
{
"epoch": 4.83,
"learning_rate": 9.533063073413319e-06,
"loss": 5.6291,
"step": 294500
},
{
"epoch": 4.83,
"learning_rate": 9.532242446125819e-06,
"loss": 5.633,
"step": 295000
},
{
"epoch": 4.84,
"learning_rate": 9.531421818838321e-06,
"loss": 5.6283,
"step": 295500
},
{
"epoch": 4.85,
"learning_rate": 9.530601191550822e-06,
"loss": 5.6281,
"step": 296000
},
{
"epoch": 4.86,
"learning_rate": 9.529780564263324e-06,
"loss": 5.62,
"step": 296500
},
{
"epoch": 4.87,
"learning_rate": 9.528959936975824e-06,
"loss": 5.6193,
"step": 297000
},
{
"epoch": 4.87,
"learning_rate": 9.528139309688327e-06,
"loss": 5.6182,
"step": 297500
},
{
"epoch": 4.88,
"learning_rate": 9.527318682400829e-06,
"loss": 5.6156,
"step": 298000
},
{
"epoch": 4.89,
"learning_rate": 9.52649805511333e-06,
"loss": 5.6157,
"step": 298500
},
{
"epoch": 4.9,
"learning_rate": 9.525677427825831e-06,
"loss": 5.6158,
"step": 299000
},
{
"epoch": 4.91,
"learning_rate": 9.524856800538332e-06,
"loss": 5.6107,
"step": 299500
},
{
"epoch": 4.92,
"learning_rate": 9.524036173250834e-06,
"loss": 5.6105,
"step": 300000
},
{
"epoch": 4.92,
"learning_rate": 9.523215545963334e-06,
"loss": 5.6057,
"step": 300500
},
{
"epoch": 4.93,
"learning_rate": 9.522394918675837e-06,
"loss": 5.6065,
"step": 301000
},
{
"epoch": 4.94,
"learning_rate": 9.521574291388339e-06,
"loss": 5.6018,
"step": 301500
},
{
"epoch": 4.95,
"learning_rate": 9.52075366410084e-06,
"loss": 5.6046,
"step": 302000
},
{
"epoch": 4.96,
"learning_rate": 9.519933036813341e-06,
"loss": 5.6054,
"step": 302500
},
{
"epoch": 4.96,
"learning_rate": 9.519112409525842e-06,
"loss": 5.6006,
"step": 303000
},
{
"epoch": 4.97,
"learning_rate": 9.518291782238344e-06,
"loss": 5.5989,
"step": 303500
},
{
"epoch": 4.98,
"learning_rate": 9.517471154950845e-06,
"loss": 5.5969,
"step": 304000
},
{
"epoch": 4.99,
"learning_rate": 9.516650527663347e-06,
"loss": 5.5954,
"step": 304500
},
{
"epoch": 5.0,
"learning_rate": 9.515829900375849e-06,
"loss": 5.5939,
"step": 305000
},
{
"epoch": 5.01,
"learning_rate": 9.51500927308835e-06,
"loss": 5.5855,
"step": 305500
},
{
"epoch": 5.01,
"learning_rate": 9.514188645800852e-06,
"loss": 5.5864,
"step": 306000
},
{
"epoch": 5.02,
"learning_rate": 9.513368018513352e-06,
"loss": 5.5833,
"step": 306500
},
{
"epoch": 5.03,
"learning_rate": 9.512547391225854e-06,
"loss": 5.5852,
"step": 307000
},
{
"epoch": 5.04,
"learning_rate": 9.511726763938355e-06,
"loss": 5.5847,
"step": 307500
},
{
"epoch": 5.05,
"learning_rate": 9.510906136650857e-06,
"loss": 5.5805,
"step": 308000
},
{
"epoch": 5.05,
"learning_rate": 9.510085509363359e-06,
"loss": 5.577,
"step": 308500
},
{
"epoch": 5.06,
"learning_rate": 9.50926488207586e-06,
"loss": 5.5791,
"step": 309000
},
{
"epoch": 5.07,
"learning_rate": 9.508444254788362e-06,
"loss": 5.5706,
"step": 309500
},
{
"epoch": 5.08,
"learning_rate": 9.507623627500862e-06,
"loss": 5.5668,
"step": 310000
},
{
"epoch": 5.09,
"learning_rate": 9.506803000213364e-06,
"loss": 5.5647,
"step": 310500
},
{
"epoch": 5.1,
"learning_rate": 9.505982372925865e-06,
"loss": 5.5687,
"step": 311000
},
{
"epoch": 5.1,
"learning_rate": 9.505161745638367e-06,
"loss": 5.5634,
"step": 311500
},
{
"epoch": 5.11,
"learning_rate": 9.504341118350869e-06,
"loss": 5.5676,
"step": 312000
},
{
"epoch": 5.12,
"learning_rate": 9.50352049106337e-06,
"loss": 5.5577,
"step": 312500
},
{
"epoch": 5.13,
"learning_rate": 9.50269986377587e-06,
"loss": 5.5603,
"step": 313000
},
{
"epoch": 5.14,
"learning_rate": 9.501879236488372e-06,
"loss": 5.557,
"step": 313500
},
{
"epoch": 5.15,
"learning_rate": 9.501058609200874e-06,
"loss": 5.5534,
"step": 314000
},
{
"epoch": 5.15,
"learning_rate": 9.500237981913375e-06,
"loss": 5.5559,
"step": 314500
},
{
"epoch": 5.16,
"learning_rate": 9.499417354625877e-06,
"loss": 5.5509,
"step": 315000
},
{
"epoch": 5.17,
"learning_rate": 9.49859672733838e-06,
"loss": 5.5481,
"step": 315500
},
{
"epoch": 5.18,
"learning_rate": 9.49777610005088e-06,
"loss": 5.5471,
"step": 316000
},
{
"epoch": 5.19,
"learning_rate": 9.49695547276338e-06,
"loss": 5.5452,
"step": 316500
},
{
"epoch": 5.19,
"learning_rate": 9.496134845475882e-06,
"loss": 5.5477,
"step": 317000
},
{
"epoch": 5.2,
"learning_rate": 9.495314218188384e-06,
"loss": 5.5425,
"step": 317500
},
{
"epoch": 5.21,
"learning_rate": 9.494493590900885e-06,
"loss": 5.5439,
"step": 318000
},
{
"epoch": 5.22,
"learning_rate": 9.493672963613387e-06,
"loss": 5.5368,
"step": 318500
},
{
"epoch": 5.23,
"learning_rate": 9.49285233632589e-06,
"loss": 5.536,
"step": 319000
},
{
"epoch": 5.24,
"learning_rate": 9.49203170903839e-06,
"loss": 5.529,
"step": 319500
},
{
"epoch": 5.24,
"learning_rate": 9.49121108175089e-06,
"loss": 5.5298,
"step": 320000
},
{
"epoch": 5.25,
"learning_rate": 9.490390454463392e-06,
"loss": 5.528,
"step": 320500
},
{
"epoch": 5.26,
"learning_rate": 9.489569827175895e-06,
"loss": 5.5249,
"step": 321000
},
{
"epoch": 5.27,
"learning_rate": 9.488749199888395e-06,
"loss": 5.5277,
"step": 321500
},
{
"epoch": 5.28,
"learning_rate": 9.487928572600897e-06,
"loss": 5.525,
"step": 322000
},
{
"epoch": 5.28,
"learning_rate": 9.4871079453134e-06,
"loss": 5.5232,
"step": 322500
},
{
"epoch": 5.29,
"learning_rate": 9.4862873180259e-06,
"loss": 5.5178,
"step": 323000
},
{
"epoch": 5.3,
"learning_rate": 9.4854666907384e-06,
"loss": 5.5173,
"step": 323500
},
{
"epoch": 5.31,
"learning_rate": 9.484646063450902e-06,
"loss": 5.5152,
"step": 324000
},
{
"epoch": 5.32,
"learning_rate": 9.483825436163405e-06,
"loss": 5.5088,
"step": 324500
},
{
"epoch": 5.33,
"learning_rate": 9.483004808875905e-06,
"loss": 5.5116,
"step": 325000
},
{
"epoch": 5.33,
"learning_rate": 9.482184181588407e-06,
"loss": 5.509,
"step": 325500
},
{
"epoch": 5.34,
"learning_rate": 9.48136355430091e-06,
"loss": 5.5048,
"step": 326000
},
{
"epoch": 5.35,
"learning_rate": 9.48054292701341e-06,
"loss": 5.507,
"step": 326500
},
{
"epoch": 5.36,
"learning_rate": 9.47972229972591e-06,
"loss": 5.5074,
"step": 327000
},
{
"epoch": 5.37,
"learning_rate": 9.478901672438413e-06,
"loss": 5.4962,
"step": 327500
},
{
"epoch": 5.37,
"learning_rate": 9.478081045150915e-06,
"loss": 5.497,
"step": 328000
},
{
"epoch": 5.38,
"learning_rate": 9.477260417863415e-06,
"loss": 5.4944,
"step": 328500
},
{
"epoch": 5.39,
"learning_rate": 9.476439790575916e-06,
"loss": 5.4943,
"step": 329000
},
{
"epoch": 5.4,
"learning_rate": 9.47561916328842e-06,
"loss": 5.4882,
"step": 329500
},
{
"epoch": 5.41,
"learning_rate": 9.47479853600092e-06,
"loss": 5.4912,
"step": 330000
},
{
"epoch": 5.42,
"learning_rate": 9.47397790871342e-06,
"loss": 5.4862,
"step": 330500
},
{
"epoch": 5.42,
"learning_rate": 9.473157281425923e-06,
"loss": 5.481,
"step": 331000
},
{
"epoch": 5.43,
"learning_rate": 9.472336654138425e-06,
"loss": 5.4771,
"step": 331500
},
{
"epoch": 5.44,
"learning_rate": 9.471516026850925e-06,
"loss": 5.4779,
"step": 332000
},
{
"epoch": 5.45,
"learning_rate": 9.470695399563426e-06,
"loss": 5.4769,
"step": 332500
},
{
"epoch": 5.46,
"learning_rate": 9.46987477227593e-06,
"loss": 5.4699,
"step": 333000
},
{
"epoch": 5.46,
"learning_rate": 9.46905414498843e-06,
"loss": 5.4708,
"step": 333500
},
{
"epoch": 5.47,
"learning_rate": 9.46823351770093e-06,
"loss": 5.469,
"step": 334000
},
{
"epoch": 5.48,
"learning_rate": 9.467412890413433e-06,
"loss": 5.4692,
"step": 334500
},
{
"epoch": 5.49,
"learning_rate": 9.466592263125935e-06,
"loss": 5.4651,
"step": 335000
},
{
"epoch": 5.5,
"learning_rate": 9.465771635838435e-06,
"loss": 5.4621,
"step": 335500
},
{
"epoch": 5.51,
"learning_rate": 9.464951008550936e-06,
"loss": 5.4604,
"step": 336000
},
{
"epoch": 5.51,
"learning_rate": 9.46413038126344e-06,
"loss": 5.4542,
"step": 336500
},
{
"epoch": 5.52,
"learning_rate": 9.46330975397594e-06,
"loss": 5.4541,
"step": 337000
},
{
"epoch": 5.53,
"learning_rate": 9.46248912668844e-06,
"loss": 5.4507,
"step": 337500
},
{
"epoch": 5.54,
"learning_rate": 9.461668499400943e-06,
"loss": 5.4527,
"step": 338000
},
{
"epoch": 5.55,
"learning_rate": 9.460847872113445e-06,
"loss": 5.45,
"step": 338500
},
{
"epoch": 5.55,
"learning_rate": 9.460027244825945e-06,
"loss": 5.4424,
"step": 339000
},
{
"epoch": 5.56,
"learning_rate": 9.459206617538446e-06,
"loss": 5.4408,
"step": 339500
},
{
"epoch": 5.57,
"learning_rate": 9.45838599025095e-06,
"loss": 5.4404,
"step": 340000
},
{
"epoch": 5.58,
"learning_rate": 9.45756536296345e-06,
"loss": 5.4357,
"step": 340500
},
{
"epoch": 5.59,
"learning_rate": 9.45674473567595e-06,
"loss": 5.435,
"step": 341000
},
{
"epoch": 5.6,
"learning_rate": 9.455924108388453e-06,
"loss": 5.4365,
"step": 341500
},
{
"epoch": 5.6,
"learning_rate": 9.455103481100955e-06,
"loss": 5.4292,
"step": 342000
},
{
"epoch": 5.61,
"learning_rate": 9.454282853813456e-06,
"loss": 5.4237,
"step": 342500
},
{
"epoch": 5.62,
"learning_rate": 9.453462226525956e-06,
"loss": 5.4218,
"step": 343000
},
{
"epoch": 5.63,
"learning_rate": 9.45264159923846e-06,
"loss": 5.4103,
"step": 343500
},
{
"epoch": 5.64,
"learning_rate": 9.45182097195096e-06,
"loss": 5.409,
"step": 344000
},
{
"epoch": 5.64,
"learning_rate": 9.45100034466346e-06,
"loss": 5.407,
"step": 344500
},
{
"epoch": 5.65,
"learning_rate": 9.450179717375963e-06,
"loss": 5.4045,
"step": 345000
},
{
"epoch": 5.66,
"learning_rate": 9.449359090088465e-06,
"loss": 5.4028,
"step": 345500
},
{
"epoch": 5.67,
"learning_rate": 9.448538462800966e-06,
"loss": 5.3995,
"step": 346000
},
{
"epoch": 5.68,
"learning_rate": 9.447717835513466e-06,
"loss": 5.3945,
"step": 346500
},
{
"epoch": 5.69,
"learning_rate": 9.44689720822597e-06,
"loss": 5.3895,
"step": 347000
},
{
"epoch": 5.69,
"learning_rate": 9.44607658093847e-06,
"loss": 5.3865,
"step": 347500
},
{
"epoch": 5.7,
"learning_rate": 9.445255953650971e-06,
"loss": 5.3889,
"step": 348000
},
{
"epoch": 5.71,
"learning_rate": 9.444435326363473e-06,
"loss": 5.3868,
"step": 348500
},
{
"epoch": 5.72,
"learning_rate": 9.443614699075975e-06,
"loss": 5.3828,
"step": 349000
},
{
"epoch": 5.73,
"learning_rate": 9.442794071788476e-06,
"loss": 5.3801,
"step": 349500
},
{
"epoch": 5.73,
"learning_rate": 9.441973444500976e-06,
"loss": 5.3706,
"step": 350000
},
{
"epoch": 5.74,
"learning_rate": 9.44115281721348e-06,
"loss": 5.3708,
"step": 350500
},
{
"epoch": 5.75,
"learning_rate": 9.44033218992598e-06,
"loss": 5.3649,
"step": 351000
},
{
"epoch": 5.76,
"learning_rate": 9.439511562638481e-06,
"loss": 5.3665,
"step": 351500
},
{
"epoch": 5.77,
"learning_rate": 9.438690935350983e-06,
"loss": 5.3636,
"step": 352000
},
{
"epoch": 5.78,
"learning_rate": 9.437870308063485e-06,
"loss": 5.3594,
"step": 352500
},
{
"epoch": 5.78,
"learning_rate": 9.437049680775986e-06,
"loss": 5.3471,
"step": 353000
},
{
"epoch": 5.79,
"learning_rate": 9.436229053488486e-06,
"loss": 5.3477,
"step": 353500
},
{
"epoch": 5.8,
"learning_rate": 9.43540842620099e-06,
"loss": 5.3454,
"step": 354000
},
{
"epoch": 5.81,
"learning_rate": 9.43458779891349e-06,
"loss": 5.3418,
"step": 354500
},
{
"epoch": 5.82,
"learning_rate": 9.433767171625991e-06,
"loss": 5.3411,
"step": 355000
},
{
"epoch": 5.83,
"learning_rate": 9.432946544338493e-06,
"loss": 5.3341,
"step": 355500
},
{
"epoch": 5.83,
"learning_rate": 9.432125917050995e-06,
"loss": 5.3366,
"step": 356000
},
{
"epoch": 5.84,
"learning_rate": 9.431305289763496e-06,
"loss": 5.3289,
"step": 356500
},
{
"epoch": 5.85,
"learning_rate": 9.430484662475996e-06,
"loss": 5.3263,
"step": 357000
},
{
"epoch": 5.86,
"learning_rate": 9.4296640351885e-06,
"loss": 5.3227,
"step": 357500
},
{
"epoch": 5.87,
"learning_rate": 9.428843407901e-06,
"loss": 5.3193,
"step": 358000
},
{
"epoch": 5.87,
"learning_rate": 9.428022780613501e-06,
"loss": 5.3186,
"step": 358500
},
{
"epoch": 5.88,
"learning_rate": 9.427202153326003e-06,
"loss": 5.3095,
"step": 359000
},
{
"epoch": 5.89,
"learning_rate": 9.426381526038505e-06,
"loss": 5.3073,
"step": 359500
},
{
"epoch": 5.9,
"learning_rate": 9.425560898751006e-06,
"loss": 5.3022,
"step": 360000
},
{
"epoch": 5.91,
"learning_rate": 9.424740271463506e-06,
"loss": 5.3026,
"step": 360500
},
{
"epoch": 5.92,
"learning_rate": 9.42391964417601e-06,
"loss": 5.2975,
"step": 361000
},
{
"epoch": 5.92,
"learning_rate": 9.42309901688851e-06,
"loss": 5.2978,
"step": 361500
},
{
"epoch": 5.93,
"learning_rate": 9.422278389601011e-06,
"loss": 5.2901,
"step": 362000
},
{
"epoch": 5.94,
"learning_rate": 9.421457762313513e-06,
"loss": 5.2846,
"step": 362500
},
{
"epoch": 5.95,
"learning_rate": 9.420637135026016e-06,
"loss": 5.2836,
"step": 363000
},
{
"epoch": 5.96,
"learning_rate": 9.419816507738516e-06,
"loss": 5.2786,
"step": 363500
},
{
"epoch": 5.96,
"learning_rate": 9.418995880451016e-06,
"loss": 5.2775,
"step": 364000
},
{
"epoch": 5.97,
"learning_rate": 9.418175253163519e-06,
"loss": 5.2732,
"step": 364500
},
{
"epoch": 5.98,
"learning_rate": 9.41735462587602e-06,
"loss": 5.2713,
"step": 365000
},
{
"epoch": 5.99,
"learning_rate": 9.416533998588521e-06,
"loss": 5.2656,
"step": 365500
},
{
"epoch": 6.0,
"learning_rate": 9.415713371301023e-06,
"loss": 5.2652,
"step": 366000
},
{
"epoch": 6.01,
"learning_rate": 9.414892744013526e-06,
"loss": 5.2599,
"step": 366500
},
{
"epoch": 6.01,
"learning_rate": 9.414072116726026e-06,
"loss": 5.2556,
"step": 367000
},
{
"epoch": 6.02,
"learning_rate": 9.413251489438527e-06,
"loss": 5.2473,
"step": 367500
},
{
"epoch": 6.03,
"learning_rate": 9.412430862151029e-06,
"loss": 5.2492,
"step": 368000
},
{
"epoch": 6.04,
"learning_rate": 9.411610234863531e-06,
"loss": 5.2405,
"step": 368500
},
{
"epoch": 6.05,
"learning_rate": 9.410789607576031e-06,
"loss": 5.2383,
"step": 369000
},
{
"epoch": 6.05,
"learning_rate": 9.409968980288534e-06,
"loss": 5.2364,
"step": 369500
},
{
"epoch": 6.06,
"learning_rate": 9.409148353001036e-06,
"loss": 5.2352,
"step": 370000
},
{
"epoch": 6.07,
"learning_rate": 9.408327725713536e-06,
"loss": 5.2266,
"step": 370500
},
{
"epoch": 6.08,
"learning_rate": 9.407507098426037e-06,
"loss": 5.2264,
"step": 371000
},
{
"epoch": 6.09,
"learning_rate": 9.406686471138539e-06,
"loss": 5.2184,
"step": 371500
},
{
"epoch": 6.1,
"learning_rate": 9.405865843851041e-06,
"loss": 5.2155,
"step": 372000
},
{
"epoch": 6.1,
"learning_rate": 9.405045216563541e-06,
"loss": 5.2131,
"step": 372500
},
{
"epoch": 6.11,
"learning_rate": 9.404224589276044e-06,
"loss": 5.2096,
"step": 373000
},
{
"epoch": 6.12,
"learning_rate": 9.403403961988546e-06,
"loss": 5.2035,
"step": 373500
},
{
"epoch": 6.13,
"learning_rate": 9.402583334701046e-06,
"loss": 5.2047,
"step": 374000
},
{
"epoch": 6.14,
"learning_rate": 9.401762707413547e-06,
"loss": 5.2002,
"step": 374500
},
{
"epoch": 6.14,
"learning_rate": 9.400942080126049e-06,
"loss": 5.1904,
"step": 375000
},
{
"epoch": 6.15,
"learning_rate": 9.400121452838551e-06,
"loss": 5.1894,
"step": 375500
},
{
"epoch": 6.16,
"learning_rate": 9.399300825551052e-06,
"loss": 5.1849,
"step": 376000
},
{
"epoch": 6.17,
"learning_rate": 9.398480198263554e-06,
"loss": 5.1828,
"step": 376500
},
{
"epoch": 6.18,
"learning_rate": 9.397659570976056e-06,
"loss": 5.1776,
"step": 377000
},
{
"epoch": 6.19,
"learning_rate": 9.396838943688556e-06,
"loss": 5.1773,
"step": 377500
},
{
"epoch": 6.19,
"learning_rate": 9.396018316401057e-06,
"loss": 5.1721,
"step": 378000
},
{
"epoch": 6.2,
"learning_rate": 9.395197689113559e-06,
"loss": 5.1672,
"step": 378500
},
{
"epoch": 6.21,
"learning_rate": 9.394377061826061e-06,
"loss": 5.1591,
"step": 379000
},
{
"epoch": 6.22,
"learning_rate": 9.393556434538562e-06,
"loss": 5.1612,
"step": 379500
},
{
"epoch": 6.23,
"learning_rate": 9.392735807251064e-06,
"loss": 5.1554,
"step": 380000
},
{
"epoch": 6.23,
"learning_rate": 9.391915179963564e-06,
"loss": 5.1496,
"step": 380500
},
{
"epoch": 6.24,
"learning_rate": 9.391094552676066e-06,
"loss": 5.1476,
"step": 381000
},
{
"epoch": 6.25,
"learning_rate": 9.390273925388567e-06,
"loss": 5.1402,
"step": 381500
},
{
"epoch": 6.26,
"learning_rate": 9.389453298101069e-06,
"loss": 5.1381,
"step": 382000
},
{
"epoch": 6.27,
"learning_rate": 9.388632670813571e-06,
"loss": 5.1359,
"step": 382500
},
{
"epoch": 6.28,
"learning_rate": 9.387812043526072e-06,
"loss": 5.1306,
"step": 383000
},
{
"epoch": 6.28,
"learning_rate": 9.386991416238574e-06,
"loss": 5.1276,
"step": 383500
},
{
"epoch": 6.29,
"learning_rate": 9.386170788951074e-06,
"loss": 5.1212,
"step": 384000
},
{
"epoch": 6.3,
"learning_rate": 9.385350161663577e-06,
"loss": 5.1183,
"step": 384500
},
{
"epoch": 6.31,
"learning_rate": 9.384529534376077e-06,
"loss": 5.1137,
"step": 385000
},
{
"epoch": 6.32,
"learning_rate": 9.38370890708858e-06,
"loss": 5.1119,
"step": 385500
},
{
"epoch": 6.32,
"learning_rate": 9.382888279801081e-06,
"loss": 5.1031,
"step": 386000
},
{
"epoch": 6.33,
"learning_rate": 9.382067652513582e-06,
"loss": 5.1016,
"step": 386500
},
{
"epoch": 6.34,
"learning_rate": 9.381247025226084e-06,
"loss": 5.0969,
"step": 387000
},
{
"epoch": 6.35,
"learning_rate": 9.380426397938584e-06,
"loss": 5.0968,
"step": 387500
},
{
"epoch": 6.36,
"learning_rate": 9.379605770651087e-06,
"loss": 5.0927,
"step": 388000
},
{
"epoch": 6.37,
"learning_rate": 9.378785143363587e-06,
"loss": 5.0864,
"step": 388500
},
{
"epoch": 6.37,
"learning_rate": 9.37796451607609e-06,
"loss": 5.08,
"step": 389000
},
{
"epoch": 6.38,
"learning_rate": 9.377143888788591e-06,
"loss": 5.0728,
"step": 389500
},
{
"epoch": 6.39,
"learning_rate": 9.376323261501092e-06,
"loss": 5.0716,
"step": 390000
},
{
"epoch": 6.4,
"learning_rate": 9.375502634213594e-06,
"loss": 5.0647,
"step": 390500
},
{
"epoch": 6.41,
"learning_rate": 9.374682006926095e-06,
"loss": 5.067,
"step": 391000
},
{
"epoch": 6.41,
"learning_rate": 9.373861379638597e-06,
"loss": 5.0602,
"step": 391500
},
{
"epoch": 6.42,
"learning_rate": 9.373040752351097e-06,
"loss": 5.0557,
"step": 392000
},
{
"epoch": 6.43,
"learning_rate": 9.3722201250636e-06,
"loss": 5.0514,
"step": 392500
},
{
"epoch": 6.44,
"learning_rate": 9.371399497776102e-06,
"loss": 5.048,
"step": 393000
},
{
"epoch": 6.45,
"learning_rate": 9.370578870488602e-06,
"loss": 5.0444,
"step": 393500
},
{
"epoch": 6.46,
"learning_rate": 9.369758243201104e-06,
"loss": 5.0343,
"step": 394000
},
{
"epoch": 6.46,
"learning_rate": 9.368937615913605e-06,
"loss": 5.0339,
"step": 394500
},
{
"epoch": 6.47,
"learning_rate": 9.368116988626107e-06,
"loss": 5.0303,
"step": 395000
},
{
"epoch": 6.48,
"learning_rate": 9.367296361338607e-06,
"loss": 5.0254,
"step": 395500
},
{
"epoch": 6.49,
"learning_rate": 9.36647573405111e-06,
"loss": 5.0209,
"step": 396000
},
{
"epoch": 6.5,
"learning_rate": 9.36565510676361e-06,
"loss": 5.0211,
"step": 396500
},
{
"epoch": 6.51,
"learning_rate": 9.364834479476112e-06,
"loss": 5.0154,
"step": 397000
},
{
"epoch": 6.51,
"learning_rate": 9.364013852188614e-06,
"loss": 5.0147,
"step": 397500
},
{
"epoch": 6.52,
"learning_rate": 9.363193224901115e-06,
"loss": 5.0049,
"step": 398000
},
{
"epoch": 6.53,
"learning_rate": 9.362372597613617e-06,
"loss": 5.0002,
"step": 398500
},
{
"epoch": 6.54,
"learning_rate": 9.361551970326117e-06,
"loss": 4.999,
"step": 399000
},
{
"epoch": 6.55,
"learning_rate": 9.36073134303862e-06,
"loss": 4.9883,
"step": 399500
},
{
"epoch": 6.55,
"learning_rate": 9.35991071575112e-06,
"loss": 4.9908,
"step": 400000
},
{
"epoch": 6.56,
"learning_rate": 9.359090088463622e-06,
"loss": 4.9853,
"step": 400500
},
{
"epoch": 6.57,
"learning_rate": 9.358269461176124e-06,
"loss": 4.9815,
"step": 401000
},
{
"epoch": 6.58,
"learning_rate": 9.357448833888625e-06,
"loss": 4.9804,
"step": 401500
},
{
"epoch": 6.59,
"learning_rate": 9.356628206601127e-06,
"loss": 4.9727,
"step": 402000
},
{
"epoch": 6.6,
"learning_rate": 9.355807579313627e-06,
"loss": 4.9718,
"step": 402500
},
{
"epoch": 6.6,
"learning_rate": 9.35498695202613e-06,
"loss": 4.9677,
"step": 403000
},
{
"epoch": 6.61,
"learning_rate": 9.35416632473863e-06,
"loss": 4.9595,
"step": 403500
},
{
"epoch": 6.62,
"learning_rate": 9.353345697451132e-06,
"loss": 4.9556,
"step": 404000
},
{
"epoch": 6.63,
"learning_rate": 9.352525070163634e-06,
"loss": 4.9558,
"step": 404500
},
{
"epoch": 6.64,
"learning_rate": 9.351704442876135e-06,
"loss": 4.9516,
"step": 405000
},
{
"epoch": 6.64,
"learning_rate": 9.350883815588637e-06,
"loss": 4.9423,
"step": 405500
},
{
"epoch": 6.65,
"learning_rate": 9.350063188301138e-06,
"loss": 4.9376,
"step": 406000
},
{
"epoch": 6.66,
"learning_rate": 9.34924256101364e-06,
"loss": 4.9398,
"step": 406500
},
{
"epoch": 6.67,
"learning_rate": 9.34842193372614e-06,
"loss": 4.9264,
"step": 407000
},
{
"epoch": 6.68,
"learning_rate": 9.347601306438642e-06,
"loss": 4.9316,
"step": 407500
},
{
"epoch": 6.69,
"learning_rate": 9.346780679151144e-06,
"loss": 4.9235,
"step": 408000
},
{
"epoch": 6.69,
"learning_rate": 9.345960051863645e-06,
"loss": 4.9214,
"step": 408500
},
{
"epoch": 6.7,
"learning_rate": 9.345139424576147e-06,
"loss": 4.9168,
"step": 409000
},
{
"epoch": 6.71,
"learning_rate": 9.344318797288648e-06,
"loss": 4.9084,
"step": 409500
},
{
"epoch": 6.72,
"learning_rate": 9.34349817000115e-06,
"loss": 4.909,
"step": 410000
},
{
"epoch": 6.73,
"learning_rate": 9.34267754271365e-06,
"loss": 4.9032,
"step": 410500
},
{
"epoch": 6.73,
"learning_rate": 9.341856915426152e-06,
"loss": 4.9021,
"step": 411000
},
{
"epoch": 6.74,
"learning_rate": 9.341036288138655e-06,
"loss": 4.8946,
"step": 411500
},
{
"epoch": 6.75,
"learning_rate": 9.340215660851155e-06,
"loss": 4.8937,
"step": 412000
},
{
"epoch": 6.76,
"learning_rate": 9.339395033563656e-06,
"loss": 4.8856,
"step": 412500
},
{
"epoch": 6.77,
"learning_rate": 9.338574406276158e-06,
"loss": 4.8824,
"step": 413000
},
{
"epoch": 6.78,
"learning_rate": 9.33775377898866e-06,
"loss": 4.8847,
"step": 413500
},
{
"epoch": 6.78,
"learning_rate": 9.33693315170116e-06,
"loss": 4.8774,
"step": 414000
},
{
"epoch": 6.79,
"learning_rate": 9.336112524413662e-06,
"loss": 4.8746,
"step": 414500
},
{
"epoch": 6.8,
"learning_rate": 9.335291897126165e-06,
"loss": 4.8664,
"step": 415000
},
{
"epoch": 6.81,
"learning_rate": 9.334471269838665e-06,
"loss": 4.8648,
"step": 415500
},
{
"epoch": 6.82,
"learning_rate": 9.333650642551166e-06,
"loss": 4.8583,
"step": 416000
},
{
"epoch": 6.82,
"learning_rate": 9.332830015263668e-06,
"loss": 4.853,
"step": 416500
},
{
"epoch": 6.83,
"learning_rate": 9.33200938797617e-06,
"loss": 4.852,
"step": 417000
},
{
"epoch": 6.84,
"learning_rate": 9.33118876068867e-06,
"loss": 4.8504,
"step": 417500
},
{
"epoch": 6.85,
"learning_rate": 9.330368133401173e-06,
"loss": 4.8426,
"step": 418000
},
{
"epoch": 6.86,
"learning_rate": 9.329547506113675e-06,
"loss": 4.8404,
"step": 418500
},
{
"epoch": 6.87,
"learning_rate": 9.328726878826175e-06,
"loss": 4.8363,
"step": 419000
},
{
"epoch": 6.87,
"learning_rate": 9.327906251538676e-06,
"loss": 4.8351,
"step": 419500
},
{
"epoch": 6.88,
"learning_rate": 9.327085624251178e-06,
"loss": 4.8237,
"step": 420000
},
{
"epoch": 6.89,
"learning_rate": 9.32626499696368e-06,
"loss": 4.8172,
"step": 420500
},
{
"epoch": 6.9,
"learning_rate": 9.32544436967618e-06,
"loss": 4.8131,
"step": 421000
},
{
"epoch": 6.91,
"learning_rate": 9.324623742388683e-06,
"loss": 4.8163,
"step": 421500
},
{
"epoch": 6.91,
"learning_rate": 9.323803115101185e-06,
"loss": 4.8096,
"step": 422000
},
{
"epoch": 6.92,
"learning_rate": 9.322982487813685e-06,
"loss": 4.8061,
"step": 422500
},
{
"epoch": 6.93,
"learning_rate": 9.322161860526186e-06,
"loss": 4.8019,
"step": 423000
},
{
"epoch": 6.94,
"learning_rate": 9.321341233238688e-06,
"loss": 4.7993,
"step": 423500
},
{
"epoch": 6.95,
"learning_rate": 9.32052060595119e-06,
"loss": 4.7997,
"step": 424000
},
{
"epoch": 6.96,
"learning_rate": 9.31969997866369e-06,
"loss": 4.7884,
"step": 424500
},
{
"epoch": 6.96,
"learning_rate": 9.318879351376193e-06,
"loss": 4.7868,
"step": 425000
},
{
"epoch": 6.97,
"learning_rate": 9.318058724088695e-06,
"loss": 4.7849,
"step": 425500
},
{
"epoch": 6.98,
"learning_rate": 9.317238096801195e-06,
"loss": 4.7762,
"step": 426000
},
{
"epoch": 6.99,
"learning_rate": 9.316417469513696e-06,
"loss": 4.7754,
"step": 426500
},
{
"epoch": 7.0,
"learning_rate": 9.315596842226198e-06,
"loss": 4.7671,
"step": 427000
},
{
"epoch": 7.0,
"learning_rate": 9.3147762149387e-06,
"loss": 4.7614,
"step": 427500
},
{
"epoch": 7.01,
"step": 427710,
"total_flos": 9.106141994895278e+17,
"train_loss": 5.837019857484345,
"train_runtime": 197999.0531,
"train_samples_per_second": 2958.983,
"train_steps_per_second": 30.823
}
],
"logging_steps": 500,
"max_steps": 6102900,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 9.106141994895278e+17,
"trial_name": null,
"trial_params": null
}