{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 1525800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.998361515270678e-05, "loss": 26.7008, "step": 500 }, { "epoch": 0.01, "learning_rate": 4.996723030541355e-05, "loss": 12.1024, "step": 1000 }, { "epoch": 0.01, "learning_rate": 4.995084545812033e-05, "loss": 9.7267, "step": 1500 }, { "epoch": 0.01, "learning_rate": 4.993446061082711e-05, "loss": 8.7644, "step": 2000 }, { "epoch": 0.02, "learning_rate": 4.991807576353389e-05, "loss": 8.2778, "step": 2500 }, { "epoch": 0.02, "learning_rate": 4.9901690916240665e-05, "loss": 7.7068, "step": 3000 }, { "epoch": 0.02, "learning_rate": 4.988530606894744e-05, "loss": 7.4776, "step": 3500 }, { "epoch": 0.03, "learning_rate": 4.986892122165422e-05, "loss": 7.0971, "step": 4000 }, { "epoch": 0.03, "learning_rate": 4.985253637436099e-05, "loss": 6.6969, "step": 4500 }, { "epoch": 0.03, "learning_rate": 4.983615152706777e-05, "loss": 6.5538, "step": 5000 }, { "epoch": 0.04, "learning_rate": 4.981976667977455e-05, "loss": 6.4983, "step": 5500 }, { "epoch": 0.04, "learning_rate": 4.980338183248132e-05, "loss": 6.2465, "step": 6000 }, { "epoch": 0.04, "learning_rate": 4.97869969851881e-05, "loss": 6.1376, "step": 6500 }, { "epoch": 0.05, "learning_rate": 4.977061213789488e-05, "loss": 5.9955, "step": 7000 }, { "epoch": 0.05, "learning_rate": 4.975422729060165e-05, "loss": 5.9828, "step": 7500 }, { "epoch": 0.05, "learning_rate": 4.973784244330843e-05, "loss": 5.8374, "step": 8000 }, { "epoch": 0.06, "learning_rate": 4.972145759601521e-05, "loss": 5.7759, "step": 8500 }, { "epoch": 0.06, "learning_rate": 4.970507274872199e-05, "loss": 5.6724, "step": 9000 }, { "epoch": 0.06, "learning_rate": 4.968868790142876e-05, "loss": 5.5031, "step": 9500 }, { "epoch": 0.07, "learning_rate": 4.967230305413554e-05, "loss": 5.3764, "step": 10000 }, { "epoch": 0.07, "learning_rate": 4.965591820684232e-05, "loss": 5.3401, "step": 10500 }, { "epoch": 0.07, "learning_rate": 4.963953335954909e-05, "loss": 5.3554, "step": 11000 }, { "epoch": 0.08, "learning_rate": 4.962314851225587e-05, "loss": 5.2632, "step": 11500 }, { "epoch": 0.08, "learning_rate": 4.9606763664962646e-05, "loss": 5.1542, "step": 12000 }, { "epoch": 0.08, "learning_rate": 4.959037881766942e-05, "loss": 5.1098, "step": 12500 }, { "epoch": 0.09, "learning_rate": 4.9573993970376195e-05, "loss": 5.0191, "step": 13000 }, { "epoch": 0.09, "learning_rate": 4.9557609123082973e-05, "loss": 5.0376, "step": 13500 }, { "epoch": 0.09, "learning_rate": 4.954122427578975e-05, "loss": 4.961, "step": 14000 }, { "epoch": 0.1, "learning_rate": 4.952483942849653e-05, "loss": 4.8311, "step": 14500 }, { "epoch": 0.1, "learning_rate": 4.950845458120331e-05, "loss": 4.8068, "step": 15000 }, { "epoch": 0.1, "learning_rate": 4.9492069733910086e-05, "loss": 4.8048, "step": 15500 }, { "epoch": 0.1, "learning_rate": 4.947568488661686e-05, "loss": 4.8182, "step": 16000 }, { "epoch": 0.11, "learning_rate": 4.9459300039323636e-05, "loss": 4.6918, "step": 16500 }, { "epoch": 0.11, "learning_rate": 4.9442915192030414e-05, "loss": 4.6742, "step": 17000 }, { "epoch": 0.11, "learning_rate": 4.9426530344737186e-05, "loss": 4.6285, "step": 17500 }, { "epoch": 0.12, "learning_rate": 4.9410145497443964e-05, "loss": 4.5101, "step": 18000 }, { "epoch": 0.12, "learning_rate": 4.939376065015074e-05, "loss": 4.5388, "step": 18500 }, { "epoch": 0.12, "learning_rate": 4.937737580285752e-05, "loss": 4.516, "step": 19000 }, { "epoch": 0.13, "learning_rate": 4.93609909555643e-05, "loss": 4.3618, "step": 19500 }, { "epoch": 0.13, "learning_rate": 4.934460610827108e-05, "loss": 4.4579, "step": 20000 }, { "epoch": 0.13, "learning_rate": 4.9328221260977855e-05, "loss": 4.3789, "step": 20500 }, { "epoch": 0.14, "learning_rate": 4.9311836413684626e-05, "loss": 4.3639, "step": 21000 }, { "epoch": 0.14, "learning_rate": 4.9295451566391405e-05, "loss": 4.3467, "step": 21500 }, { "epoch": 0.14, "learning_rate": 4.927906671909818e-05, "loss": 4.2428, "step": 22000 }, { "epoch": 0.15, "learning_rate": 4.9262681871804954e-05, "loss": 4.2753, "step": 22500 }, { "epoch": 0.15, "learning_rate": 4.924629702451173e-05, "loss": 4.1781, "step": 23000 }, { "epoch": 0.15, "learning_rate": 4.922991217721851e-05, "loss": 4.1592, "step": 23500 }, { "epoch": 0.16, "learning_rate": 4.921352732992528e-05, "loss": 4.1291, "step": 24000 }, { "epoch": 0.16, "learning_rate": 4.919714248263207e-05, "loss": 4.199, "step": 24500 }, { "epoch": 0.16, "learning_rate": 4.9180757635338845e-05, "loss": 4.13, "step": 25000 }, { "epoch": 0.17, "learning_rate": 4.916437278804562e-05, "loss": 4.1636, "step": 25500 }, { "epoch": 0.17, "learning_rate": 4.9147987940752395e-05, "loss": 4.0639, "step": 26000 }, { "epoch": 0.17, "learning_rate": 4.913160309345917e-05, "loss": 4.1097, "step": 26500 }, { "epoch": 0.18, "learning_rate": 4.911521824616595e-05, "loss": 4.0065, "step": 27000 }, { "epoch": 0.18, "learning_rate": 4.909883339887272e-05, "loss": 4.0029, "step": 27500 }, { "epoch": 0.18, "learning_rate": 4.90824485515795e-05, "loss": 4.0373, "step": 28000 }, { "epoch": 0.19, "learning_rate": 4.906606370428628e-05, "loss": 3.9018, "step": 28500 }, { "epoch": 0.19, "learning_rate": 4.904967885699305e-05, "loss": 3.9437, "step": 29000 }, { "epoch": 0.19, "learning_rate": 4.903329400969983e-05, "loss": 3.965, "step": 29500 }, { "epoch": 0.2, "learning_rate": 4.901690916240661e-05, "loss": 3.9407, "step": 30000 }, { "epoch": 0.2, "learning_rate": 4.9000524315113385e-05, "loss": 3.8537, "step": 30500 }, { "epoch": 0.2, "learning_rate": 4.8984139467820163e-05, "loss": 3.8636, "step": 31000 }, { "epoch": 0.21, "learning_rate": 4.896775462052694e-05, "loss": 3.7865, "step": 31500 }, { "epoch": 0.21, "learning_rate": 4.895136977323372e-05, "loss": 3.7925, "step": 32000 }, { "epoch": 0.21, "learning_rate": 4.893498492594049e-05, "loss": 3.8035, "step": 32500 }, { "epoch": 0.22, "learning_rate": 4.891860007864727e-05, "loss": 3.7473, "step": 33000 }, { "epoch": 0.22, "learning_rate": 4.890221523135405e-05, "loss": 3.7976, "step": 33500 }, { "epoch": 0.22, "learning_rate": 4.888583038406082e-05, "loss": 3.6947, "step": 34000 }, { "epoch": 0.23, "learning_rate": 4.88694455367676e-05, "loss": 3.6567, "step": 34500 }, { "epoch": 0.23, "learning_rate": 4.8853060689474376e-05, "loss": 3.7356, "step": 35000 }, { "epoch": 0.23, "learning_rate": 4.8836675842181154e-05, "loss": 3.7598, "step": 35500 }, { "epoch": 0.24, "learning_rate": 4.882029099488793e-05, "loss": 3.6322, "step": 36000 }, { "epoch": 0.24, "learning_rate": 4.880390614759471e-05, "loss": 3.6672, "step": 36500 }, { "epoch": 0.24, "learning_rate": 4.878752130030148e-05, "loss": 3.5795, "step": 37000 }, { "epoch": 0.25, "learning_rate": 4.877113645300826e-05, "loss": 3.663, "step": 37500 }, { "epoch": 0.25, "learning_rate": 4.875475160571504e-05, "loss": 3.6402, "step": 38000 }, { "epoch": 0.25, "learning_rate": 4.8738366758421816e-05, "loss": 3.6571, "step": 38500 }, { "epoch": 0.26, "learning_rate": 4.872198191112859e-05, "loss": 3.6119, "step": 39000 }, { "epoch": 0.26, "learning_rate": 4.8705597063835366e-05, "loss": 3.5809, "step": 39500 }, { "epoch": 0.26, "learning_rate": 4.8689212216542144e-05, "loss": 3.529, "step": 40000 }, { "epoch": 0.27, "learning_rate": 4.8672827369248916e-05, "loss": 3.5132, "step": 40500 }, { "epoch": 0.27, "learning_rate": 4.86564425219557e-05, "loss": 3.4923, "step": 41000 }, { "epoch": 0.27, "learning_rate": 4.864005767466248e-05, "loss": 3.5398, "step": 41500 }, { "epoch": 0.28, "learning_rate": 4.862367282736925e-05, "loss": 3.5133, "step": 42000 }, { "epoch": 0.28, "learning_rate": 4.860728798007603e-05, "loss": 3.4739, "step": 42500 }, { "epoch": 0.28, "learning_rate": 4.859090313278281e-05, "loss": 3.5044, "step": 43000 }, { "epoch": 0.29, "learning_rate": 4.8574518285489585e-05, "loss": 3.4162, "step": 43500 }, { "epoch": 0.29, "learning_rate": 4.8558133438196356e-05, "loss": 3.4744, "step": 44000 }, { "epoch": 0.29, "learning_rate": 4.8541748590903135e-05, "loss": 3.4126, "step": 44500 }, { "epoch": 0.29, "learning_rate": 4.852536374360991e-05, "loss": 3.4004, "step": 45000 }, { "epoch": 0.3, "learning_rate": 4.8508978896316684e-05, "loss": 3.4211, "step": 45500 }, { "epoch": 0.3, "learning_rate": 4.849259404902346e-05, "loss": 3.3834, "step": 46000 }, { "epoch": 0.3, "learning_rate": 4.847620920173024e-05, "loss": 3.4083, "step": 46500 }, { "epoch": 0.31, "learning_rate": 4.845982435443702e-05, "loss": 3.4154, "step": 47000 }, { "epoch": 0.31, "learning_rate": 4.84434395071438e-05, "loss": 3.3123, "step": 47500 }, { "epoch": 0.31, "learning_rate": 4.8427054659850575e-05, "loss": 3.3356, "step": 48000 }, { "epoch": 0.32, "learning_rate": 4.841066981255735e-05, "loss": 3.2703, "step": 48500 }, { "epoch": 0.32, "learning_rate": 4.8394284965264125e-05, "loss": 3.3063, "step": 49000 }, { "epoch": 0.32, "learning_rate": 4.83779001179709e-05, "loss": 3.3356, "step": 49500 }, { "epoch": 0.33, "learning_rate": 4.836151527067768e-05, "loss": 3.2987, "step": 50000 }, { "epoch": 0.33, "learning_rate": 4.834513042338445e-05, "loss": 3.3073, "step": 50500 }, { "epoch": 0.33, "learning_rate": 4.832874557609123e-05, "loss": 3.2602, "step": 51000 }, { "epoch": 0.34, "learning_rate": 4.831236072879801e-05, "loss": 3.3187, "step": 51500 }, { "epoch": 0.34, "learning_rate": 4.829597588150479e-05, "loss": 3.3079, "step": 52000 }, { "epoch": 0.34, "learning_rate": 4.8279591034211566e-05, "loss": 3.2281, "step": 52500 }, { "epoch": 0.35, "learning_rate": 4.8263206186918344e-05, "loss": 3.2663, "step": 53000 }, { "epoch": 0.35, "learning_rate": 4.8246821339625115e-05, "loss": 3.291, "step": 53500 }, { "epoch": 0.35, "learning_rate": 4.8230436492331893e-05, "loss": 3.2178, "step": 54000 }, { "epoch": 0.36, "learning_rate": 4.821405164503867e-05, "loss": 3.2457, "step": 54500 }, { "epoch": 0.36, "learning_rate": 4.819766679774545e-05, "loss": 3.2127, "step": 55000 }, { "epoch": 0.36, "learning_rate": 4.818128195045222e-05, "loss": 3.2209, "step": 55500 }, { "epoch": 0.37, "learning_rate": 4.8164897103159e-05, "loss": 3.0884, "step": 56000 }, { "epoch": 0.37, "learning_rate": 4.814851225586578e-05, "loss": 3.1298, "step": 56500 }, { "epoch": 0.37, "learning_rate": 4.8132127408572556e-05, "loss": 3.1428, "step": 57000 }, { "epoch": 0.38, "learning_rate": 4.8115742561279334e-05, "loss": 3.1735, "step": 57500 }, { "epoch": 0.38, "learning_rate": 4.809935771398611e-05, "loss": 3.2086, "step": 58000 }, { "epoch": 0.38, "learning_rate": 4.8082972866692884e-05, "loss": 3.1233, "step": 58500 }, { "epoch": 0.39, "learning_rate": 4.806658801939966e-05, "loss": 3.1382, "step": 59000 }, { "epoch": 0.39, "learning_rate": 4.805020317210644e-05, "loss": 3.1445, "step": 59500 }, { "epoch": 0.39, "learning_rate": 4.803381832481321e-05, "loss": 3.1688, "step": 60000 }, { "epoch": 0.4, "learning_rate": 4.801743347751999e-05, "loss": 3.1632, "step": 60500 }, { "epoch": 0.4, "learning_rate": 4.800104863022677e-05, "loss": 3.0848, "step": 61000 }, { "epoch": 0.4, "learning_rate": 4.7984663782933546e-05, "loss": 3.0829, "step": 61500 }, { "epoch": 0.41, "learning_rate": 4.796827893564032e-05, "loss": 3.1169, "step": 62000 }, { "epoch": 0.41, "learning_rate": 4.7951894088347096e-05, "loss": 2.9744, "step": 62500 }, { "epoch": 0.41, "learning_rate": 4.7935509241053874e-05, "loss": 3.075, "step": 63000 }, { "epoch": 0.42, "learning_rate": 4.791912439376065e-05, "loss": 3.0744, "step": 63500 }, { "epoch": 0.42, "learning_rate": 4.790273954646743e-05, "loss": 3.0584, "step": 64000 }, { "epoch": 0.42, "learning_rate": 4.788635469917421e-05, "loss": 3.0144, "step": 64500 }, { "epoch": 0.43, "learning_rate": 4.786996985188098e-05, "loss": 3.0897, "step": 65000 }, { "epoch": 0.43, "learning_rate": 4.785358500458776e-05, "loss": 3.0404, "step": 65500 }, { "epoch": 0.43, "learning_rate": 4.783720015729454e-05, "loss": 2.9925, "step": 66000 }, { "epoch": 0.44, "learning_rate": 4.7820815310001315e-05, "loss": 3.0085, "step": 66500 }, { "epoch": 0.44, "learning_rate": 4.7804430462708086e-05, "loss": 3.0263, "step": 67000 }, { "epoch": 0.44, "learning_rate": 4.7788045615414865e-05, "loss": 3.0198, "step": 67500 }, { "epoch": 0.45, "learning_rate": 4.777166076812164e-05, "loss": 2.985, "step": 68000 }, { "epoch": 0.45, "learning_rate": 4.775527592082842e-05, "loss": 3.004, "step": 68500 }, { "epoch": 0.45, "learning_rate": 4.77388910735352e-05, "loss": 2.999, "step": 69000 }, { "epoch": 0.46, "learning_rate": 4.772250622624198e-05, "loss": 2.9586, "step": 69500 }, { "epoch": 0.46, "learning_rate": 4.770612137894875e-05, "loss": 2.9499, "step": 70000 }, { "epoch": 0.46, "learning_rate": 4.768973653165553e-05, "loss": 2.9811, "step": 70500 }, { "epoch": 0.47, "learning_rate": 4.7673351684362305e-05, "loss": 2.8611, "step": 71000 }, { "epoch": 0.47, "learning_rate": 4.765696683706908e-05, "loss": 2.9202, "step": 71500 }, { "epoch": 0.47, "learning_rate": 4.7640581989775855e-05, "loss": 2.9699, "step": 72000 }, { "epoch": 0.48, "learning_rate": 4.762419714248263e-05, "loss": 2.9051, "step": 72500 }, { "epoch": 0.48, "learning_rate": 4.760781229518941e-05, "loss": 2.8648, "step": 73000 }, { "epoch": 0.48, "learning_rate": 4.759142744789619e-05, "loss": 2.9433, "step": 73500 }, { "epoch": 0.48, "learning_rate": 4.757504260060297e-05, "loss": 2.9131, "step": 74000 }, { "epoch": 0.49, "learning_rate": 4.7558657753309746e-05, "loss": 2.9073, "step": 74500 }, { "epoch": 0.49, "learning_rate": 4.754227290601652e-05, "loss": 2.87, "step": 75000 }, { "epoch": 0.49, "learning_rate": 4.7525888058723296e-05, "loss": 2.8766, "step": 75500 }, { "epoch": 0.5, "learning_rate": 4.7509503211430074e-05, "loss": 2.946, "step": 76000 }, { "epoch": 0.5, "learning_rate": 4.7493118364136845e-05, "loss": 2.9183, "step": 76500 }, { "epoch": 0.5, "learning_rate": 4.7476733516843623e-05, "loss": 2.8819, "step": 77000 }, { "epoch": 0.51, "learning_rate": 4.74603486695504e-05, "loss": 2.8142, "step": 77500 }, { "epoch": 0.51, "learning_rate": 4.744396382225718e-05, "loss": 2.7919, "step": 78000 }, { "epoch": 0.51, "learning_rate": 4.742757897496395e-05, "loss": 2.8545, "step": 78500 }, { "epoch": 0.52, "learning_rate": 4.741119412767073e-05, "loss": 2.8462, "step": 79000 }, { "epoch": 0.52, "learning_rate": 4.7394809280377515e-05, "loss": 2.8303, "step": 79500 }, { "epoch": 0.52, "learning_rate": 4.7378424433084286e-05, "loss": 2.8243, "step": 80000 }, { "epoch": 0.53, "learning_rate": 4.7362039585791064e-05, "loss": 2.8277, "step": 80500 }, { "epoch": 0.53, "learning_rate": 4.734565473849784e-05, "loss": 2.7444, "step": 81000 }, { "epoch": 0.53, "learning_rate": 4.7329269891204614e-05, "loss": 2.8309, "step": 81500 }, { "epoch": 0.54, "learning_rate": 4.731288504391139e-05, "loss": 2.7444, "step": 82000 }, { "epoch": 0.54, "learning_rate": 4.729650019661817e-05, "loss": 2.8073, "step": 82500 }, { "epoch": 0.54, "learning_rate": 4.728011534932494e-05, "loss": 2.8496, "step": 83000 }, { "epoch": 0.55, "learning_rate": 4.726373050203172e-05, "loss": 2.7844, "step": 83500 }, { "epoch": 0.55, "learning_rate": 4.72473456547385e-05, "loss": 2.7896, "step": 84000 }, { "epoch": 0.55, "learning_rate": 4.7230960807445276e-05, "loss": 2.7618, "step": 84500 }, { "epoch": 0.56, "learning_rate": 4.7214575960152055e-05, "loss": 2.7714, "step": 85000 }, { "epoch": 0.56, "learning_rate": 4.719819111285883e-05, "loss": 2.8077, "step": 85500 }, { "epoch": 0.56, "learning_rate": 4.718180626556561e-05, "loss": 2.7313, "step": 86000 }, { "epoch": 0.57, "learning_rate": 4.716542141827238e-05, "loss": 2.7721, "step": 86500 }, { "epoch": 0.57, "learning_rate": 4.714903657097916e-05, "loss": 2.8006, "step": 87000 }, { "epoch": 0.57, "learning_rate": 4.713265172368594e-05, "loss": 2.8372, "step": 87500 }, { "epoch": 0.58, "learning_rate": 4.711626687639271e-05, "loss": 2.816, "step": 88000 }, { "epoch": 0.58, "learning_rate": 4.709988202909949e-05, "loss": 2.7658, "step": 88500 }, { "epoch": 0.58, "learning_rate": 4.708349718180627e-05, "loss": 2.7556, "step": 89000 }, { "epoch": 0.59, "learning_rate": 4.7067112334513045e-05, "loss": 2.742, "step": 89500 }, { "epoch": 0.59, "learning_rate": 4.705072748721982e-05, "loss": 2.7525, "step": 90000 }, { "epoch": 0.59, "learning_rate": 4.70343426399266e-05, "loss": 2.7154, "step": 90500 }, { "epoch": 0.6, "learning_rate": 4.701795779263338e-05, "loss": 2.6879, "step": 91000 }, { "epoch": 0.6, "learning_rate": 4.700157294534015e-05, "loss": 2.7266, "step": 91500 }, { "epoch": 0.6, "learning_rate": 4.698518809804693e-05, "loss": 2.6836, "step": 92000 }, { "epoch": 0.61, "learning_rate": 4.696880325075371e-05, "loss": 2.705, "step": 92500 }, { "epoch": 0.61, "learning_rate": 4.695241840346048e-05, "loss": 2.7869, "step": 93000 }, { "epoch": 0.61, "learning_rate": 4.693603355616726e-05, "loss": 2.7363, "step": 93500 }, { "epoch": 0.62, "learning_rate": 4.6919648708874035e-05, "loss": 2.6664, "step": 94000 }, { "epoch": 0.62, "learning_rate": 4.690326386158081e-05, "loss": 2.7212, "step": 94500 }, { "epoch": 0.62, "learning_rate": 4.6886879014287585e-05, "loss": 2.667, "step": 95000 }, { "epoch": 0.63, "learning_rate": 4.687049416699436e-05, "loss": 2.6901, "step": 95500 }, { "epoch": 0.63, "learning_rate": 4.685410931970115e-05, "loss": 2.7002, "step": 96000 }, { "epoch": 0.63, "learning_rate": 4.683772447240792e-05, "loss": 2.7001, "step": 96500 }, { "epoch": 0.64, "learning_rate": 4.68213396251147e-05, "loss": 2.6707, "step": 97000 }, { "epoch": 0.64, "learning_rate": 4.6804954777821476e-05, "loss": 2.6699, "step": 97500 }, { "epoch": 0.64, "learning_rate": 4.678856993052825e-05, "loss": 2.6852, "step": 98000 }, { "epoch": 0.65, "learning_rate": 4.6772185083235026e-05, "loss": 2.6334, "step": 98500 }, { "epoch": 0.65, "learning_rate": 4.6755800235941804e-05, "loss": 2.6272, "step": 99000 }, { "epoch": 0.65, "learning_rate": 4.6739415388648575e-05, "loss": 2.6776, "step": 99500 }, { "epoch": 0.66, "learning_rate": 4.6723030541355353e-05, "loss": 2.6632, "step": 100000 }, { "epoch": 0.66, "learning_rate": 4.670664569406213e-05, "loss": 2.6457, "step": 100500 }, { "epoch": 0.66, "learning_rate": 4.669026084676891e-05, "loss": 2.6083, "step": 101000 }, { "epoch": 0.67, "learning_rate": 4.667387599947569e-05, "loss": 2.6384, "step": 101500 }, { "epoch": 0.67, "learning_rate": 4.6657491152182466e-05, "loss": 2.6713, "step": 102000 }, { "epoch": 0.67, "learning_rate": 4.6641106304889245e-05, "loss": 2.6494, "step": 102500 }, { "epoch": 0.68, "learning_rate": 4.6624721457596016e-05, "loss": 2.6576, "step": 103000 }, { "epoch": 0.68, "learning_rate": 4.6608336610302794e-05, "loss": 2.6585, "step": 103500 }, { "epoch": 0.68, "learning_rate": 4.659195176300957e-05, "loss": 2.6395, "step": 104000 }, { "epoch": 0.68, "learning_rate": 4.6575566915716344e-05, "loss": 2.6244, "step": 104500 }, { "epoch": 0.69, "learning_rate": 4.655918206842312e-05, "loss": 2.6149, "step": 105000 }, { "epoch": 0.69, "learning_rate": 4.65427972211299e-05, "loss": 2.6049, "step": 105500 }, { "epoch": 0.69, "learning_rate": 4.652641237383668e-05, "loss": 2.6265, "step": 106000 }, { "epoch": 0.7, "learning_rate": 4.651002752654346e-05, "loss": 2.5734, "step": 106500 }, { "epoch": 0.7, "learning_rate": 4.6493642679250235e-05, "loss": 2.6167, "step": 107000 }, { "epoch": 0.7, "learning_rate": 4.647725783195701e-05, "loss": 2.5793, "step": 107500 }, { "epoch": 0.71, "learning_rate": 4.6460872984663785e-05, "loss": 2.6338, "step": 108000 }, { "epoch": 0.71, "learning_rate": 4.644448813737056e-05, "loss": 2.5765, "step": 108500 }, { "epoch": 0.71, "learning_rate": 4.642810329007734e-05, "loss": 2.6133, "step": 109000 }, { "epoch": 0.72, "learning_rate": 4.641171844278411e-05, "loss": 2.5643, "step": 109500 }, { "epoch": 0.72, "learning_rate": 4.639533359549089e-05, "loss": 2.5827, "step": 110000 }, { "epoch": 0.72, "learning_rate": 4.637894874819767e-05, "loss": 2.52, "step": 110500 }, { "epoch": 0.73, "learning_rate": 4.636256390090444e-05, "loss": 2.5995, "step": 111000 }, { "epoch": 0.73, "learning_rate": 4.634617905361122e-05, "loss": 2.573, "step": 111500 }, { "epoch": 0.73, "learning_rate": 4.6329794206318003e-05, "loss": 2.5656, "step": 112000 }, { "epoch": 0.74, "learning_rate": 4.631340935902478e-05, "loss": 2.5778, "step": 112500 }, { "epoch": 0.74, "learning_rate": 4.629702451173155e-05, "loss": 2.5484, "step": 113000 }, { "epoch": 0.74, "learning_rate": 4.628063966443833e-05, "loss": 2.5886, "step": 113500 }, { "epoch": 0.75, "learning_rate": 4.626425481714511e-05, "loss": 2.5282, "step": 114000 }, { "epoch": 0.75, "learning_rate": 4.624786996985188e-05, "loss": 2.5704, "step": 114500 }, { "epoch": 0.75, "learning_rate": 4.623148512255866e-05, "loss": 2.5307, "step": 115000 }, { "epoch": 0.76, "learning_rate": 4.621510027526544e-05, "loss": 2.5512, "step": 115500 }, { "epoch": 0.76, "learning_rate": 4.619871542797221e-05, "loss": 2.5606, "step": 116000 }, { "epoch": 0.76, "learning_rate": 4.618233058067899e-05, "loss": 2.5786, "step": 116500 }, { "epoch": 0.77, "learning_rate": 4.6165945733385765e-05, "loss": 2.5294, "step": 117000 }, { "epoch": 0.77, "learning_rate": 4.6149560886092543e-05, "loss": 2.4891, "step": 117500 }, { "epoch": 0.77, "learning_rate": 4.613317603879932e-05, "loss": 2.5024, "step": 118000 }, { "epoch": 0.78, "learning_rate": 4.61167911915061e-05, "loss": 2.521, "step": 118500 }, { "epoch": 0.78, "learning_rate": 4.610040634421288e-05, "loss": 2.4772, "step": 119000 }, { "epoch": 0.78, "learning_rate": 4.608402149691965e-05, "loss": 2.4857, "step": 119500 }, { "epoch": 0.79, "learning_rate": 4.606763664962643e-05, "loss": 2.515, "step": 120000 }, { "epoch": 0.79, "learning_rate": 4.6051251802333206e-05, "loss": 2.4954, "step": 120500 }, { "epoch": 0.79, "learning_rate": 4.603486695503998e-05, "loss": 2.4621, "step": 121000 }, { "epoch": 0.8, "learning_rate": 4.6018482107746756e-05, "loss": 2.4862, "step": 121500 }, { "epoch": 0.8, "learning_rate": 4.6002097260453534e-05, "loss": 2.4842, "step": 122000 }, { "epoch": 0.8, "learning_rate": 4.598571241316031e-05, "loss": 2.5454, "step": 122500 }, { "epoch": 0.81, "learning_rate": 4.596932756586709e-05, "loss": 2.4898, "step": 123000 }, { "epoch": 0.81, "learning_rate": 4.595294271857387e-05, "loss": 2.5025, "step": 123500 }, { "epoch": 0.81, "learning_rate": 4.593655787128065e-05, "loss": 2.5156, "step": 124000 }, { "epoch": 0.82, "learning_rate": 4.592017302398742e-05, "loss": 2.4829, "step": 124500 }, { "epoch": 0.82, "learning_rate": 4.5903788176694196e-05, "loss": 2.5104, "step": 125000 }, { "epoch": 0.82, "learning_rate": 4.5887403329400975e-05, "loss": 2.5355, "step": 125500 }, { "epoch": 0.83, "learning_rate": 4.5871018482107746e-05, "loss": 2.4824, "step": 126000 }, { "epoch": 0.83, "learning_rate": 4.5854633634814524e-05, "loss": 2.4133, "step": 126500 }, { "epoch": 0.83, "learning_rate": 4.58382487875213e-05, "loss": 2.4726, "step": 127000 }, { "epoch": 0.84, "learning_rate": 4.5821863940228074e-05, "loss": 2.479, "step": 127500 }, { "epoch": 0.84, "learning_rate": 4.580547909293485e-05, "loss": 2.4205, "step": 128000 }, { "epoch": 0.84, "learning_rate": 4.578909424564164e-05, "loss": 2.4007, "step": 128500 }, { "epoch": 0.85, "learning_rate": 4.5772709398348415e-05, "loss": 2.458, "step": 129000 }, { "epoch": 0.85, "learning_rate": 4.575632455105519e-05, "loss": 2.4048, "step": 129500 }, { "epoch": 0.85, "learning_rate": 4.5739939703761965e-05, "loss": 2.4582, "step": 130000 }, { "epoch": 0.86, "learning_rate": 4.572355485646874e-05, "loss": 2.4572, "step": 130500 }, { "epoch": 0.86, "learning_rate": 4.5707170009175515e-05, "loss": 2.4689, "step": 131000 }, { "epoch": 0.86, "learning_rate": 4.569078516188229e-05, "loss": 2.403, "step": 131500 }, { "epoch": 0.87, "learning_rate": 4.567440031458907e-05, "loss": 2.4276, "step": 132000 }, { "epoch": 0.87, "learning_rate": 4.565801546729584e-05, "loss": 2.4424, "step": 132500 }, { "epoch": 0.87, "learning_rate": 4.564163062000262e-05, "loss": 2.4385, "step": 133000 }, { "epoch": 0.87, "learning_rate": 4.56252457727094e-05, "loss": 2.4916, "step": 133500 }, { "epoch": 0.88, "learning_rate": 4.560886092541618e-05, "loss": 2.428, "step": 134000 }, { "epoch": 0.88, "learning_rate": 4.5592476078122955e-05, "loss": 2.4297, "step": 134500 }, { "epoch": 0.88, "learning_rate": 4.5576091230829733e-05, "loss": 2.3688, "step": 135000 }, { "epoch": 0.89, "learning_rate": 4.555970638353651e-05, "loss": 2.4306, "step": 135500 }, { "epoch": 0.89, "learning_rate": 4.554332153624328e-05, "loss": 2.4257, "step": 136000 }, { "epoch": 0.89, "learning_rate": 4.552693668895006e-05, "loss": 2.384, "step": 136500 }, { "epoch": 0.9, "learning_rate": 4.551055184165684e-05, "loss": 2.4469, "step": 137000 }, { "epoch": 0.9, "learning_rate": 4.549416699436361e-05, "loss": 2.3958, "step": 137500 }, { "epoch": 0.9, "learning_rate": 4.547778214707039e-05, "loss": 2.3964, "step": 138000 }, { "epoch": 0.91, "learning_rate": 4.546139729977717e-05, "loss": 2.3973, "step": 138500 }, { "epoch": 0.91, "learning_rate": 4.5445012452483946e-05, "loss": 2.4224, "step": 139000 }, { "epoch": 0.91, "learning_rate": 4.5428627605190724e-05, "loss": 2.3722, "step": 139500 }, { "epoch": 0.92, "learning_rate": 4.54122427578975e-05, "loss": 2.3841, "step": 140000 }, { "epoch": 0.92, "learning_rate": 4.539585791060428e-05, "loss": 2.3356, "step": 140500 }, { "epoch": 0.92, "learning_rate": 4.537947306331105e-05, "loss": 2.3698, "step": 141000 }, { "epoch": 0.93, "learning_rate": 4.536308821601783e-05, "loss": 2.4221, "step": 141500 }, { "epoch": 0.93, "learning_rate": 4.534670336872461e-05, "loss": 2.343, "step": 142000 }, { "epoch": 0.93, "learning_rate": 4.533031852143138e-05, "loss": 2.3866, "step": 142500 }, { "epoch": 0.94, "learning_rate": 4.531393367413816e-05, "loss": 2.3304, "step": 143000 }, { "epoch": 0.94, "learning_rate": 4.5297548826844936e-05, "loss": 2.3629, "step": 143500 }, { "epoch": 0.94, "learning_rate": 4.528116397955171e-05, "loss": 2.3904, "step": 144000 }, { "epoch": 0.95, "learning_rate": 4.526477913225849e-05, "loss": 2.4121, "step": 144500 }, { "epoch": 0.95, "learning_rate": 4.524839428496527e-05, "loss": 2.3569, "step": 145000 }, { "epoch": 0.95, "learning_rate": 4.523200943767204e-05, "loss": 2.3259, "step": 145500 }, { "epoch": 0.96, "learning_rate": 4.521562459037882e-05, "loss": 2.3297, "step": 146000 }, { "epoch": 0.96, "learning_rate": 4.51992397430856e-05, "loss": 2.3536, "step": 146500 }, { "epoch": 0.96, "learning_rate": 4.518285489579238e-05, "loss": 2.3706, "step": 147000 }, { "epoch": 0.97, "learning_rate": 4.516647004849915e-05, "loss": 2.3845, "step": 147500 }, { "epoch": 0.97, "learning_rate": 4.5150085201205926e-05, "loss": 2.3699, "step": 148000 }, { "epoch": 0.97, "learning_rate": 4.5133700353912705e-05, "loss": 2.3856, "step": 148500 }, { "epoch": 0.98, "learning_rate": 4.5117315506619476e-05, "loss": 2.3529, "step": 149000 }, { "epoch": 0.98, "learning_rate": 4.5100930659326254e-05, "loss": 2.3667, "step": 149500 }, { "epoch": 0.98, "learning_rate": 4.508454581203303e-05, "loss": 2.3064, "step": 150000 }, { "epoch": 0.99, "learning_rate": 4.506816096473981e-05, "loss": 2.3734, "step": 150500 }, { "epoch": 0.99, "learning_rate": 4.505177611744659e-05, "loss": 2.3264, "step": 151000 }, { "epoch": 0.99, "learning_rate": 4.503539127015337e-05, "loss": 2.3296, "step": 151500 }, { "epoch": 1.0, "learning_rate": 4.5019006422860145e-05, "loss": 2.3026, "step": 152000 }, { "epoch": 1.0, "learning_rate": 4.500262157556692e-05, "loss": 2.3402, "step": 152500 }, { "epoch": 1.0, "learning_rate": 4.4986236728273695e-05, "loss": 2.3119, "step": 153000 }, { "epoch": 1.01, "learning_rate": 4.496985188098047e-05, "loss": 2.2831, "step": 153500 }, { "epoch": 1.01, "learning_rate": 4.4953467033687245e-05, "loss": 2.2935, "step": 154000 }, { "epoch": 1.01, "learning_rate": 4.493708218639402e-05, "loss": 2.2845, "step": 154500 }, { "epoch": 1.02, "learning_rate": 4.49206973391008e-05, "loss": 2.3412, "step": 155000 }, { "epoch": 1.02, "learning_rate": 4.490431249180758e-05, "loss": 2.3238, "step": 155500 }, { "epoch": 1.02, "learning_rate": 4.488792764451436e-05, "loss": 2.3132, "step": 156000 }, { "epoch": 1.03, "learning_rate": 4.4871542797221136e-05, "loss": 2.3288, "step": 156500 }, { "epoch": 1.03, "learning_rate": 4.485515794992791e-05, "loss": 2.2781, "step": 157000 }, { "epoch": 1.03, "learning_rate": 4.4838773102634685e-05, "loss": 2.3217, "step": 157500 }, { "epoch": 1.04, "learning_rate": 4.4822388255341463e-05, "loss": 2.3274, "step": 158000 }, { "epoch": 1.04, "learning_rate": 4.480600340804824e-05, "loss": 2.2894, "step": 158500 }, { "epoch": 1.04, "learning_rate": 4.478961856075501e-05, "loss": 2.2941, "step": 159000 }, { "epoch": 1.05, "learning_rate": 4.477323371346179e-05, "loss": 2.2349, "step": 159500 }, { "epoch": 1.05, "learning_rate": 4.475684886616857e-05, "loss": 2.261, "step": 160000 }, { "epoch": 1.05, "learning_rate": 4.474046401887534e-05, "loss": 2.2789, "step": 160500 }, { "epoch": 1.06, "learning_rate": 4.4724079171582126e-05, "loss": 2.2513, "step": 161000 }, { "epoch": 1.06, "learning_rate": 4.4707694324288904e-05, "loss": 2.2614, "step": 161500 }, { "epoch": 1.06, "learning_rate": 4.4691309476995676e-05, "loss": 2.2618, "step": 162000 }, { "epoch": 1.07, "learning_rate": 4.4674924629702454e-05, "loss": 2.3238, "step": 162500 }, { "epoch": 1.07, "learning_rate": 4.465853978240923e-05, "loss": 2.2985, "step": 163000 }, { "epoch": 1.07, "learning_rate": 4.464215493511601e-05, "loss": 2.3029, "step": 163500 }, { "epoch": 1.07, "learning_rate": 4.462577008782278e-05, "loss": 2.2998, "step": 164000 }, { "epoch": 1.08, "learning_rate": 4.460938524052956e-05, "loss": 2.2667, "step": 164500 }, { "epoch": 1.08, "learning_rate": 4.459300039323634e-05, "loss": 2.2302, "step": 165000 }, { "epoch": 1.08, "learning_rate": 4.457661554594311e-05, "loss": 2.2646, "step": 165500 }, { "epoch": 1.09, "learning_rate": 4.456023069864989e-05, "loss": 2.268, "step": 166000 }, { "epoch": 1.09, "learning_rate": 4.4543845851356666e-05, "loss": 2.2148, "step": 166500 }, { "epoch": 1.09, "learning_rate": 4.4527461004063444e-05, "loss": 2.2423, "step": 167000 }, { "epoch": 1.1, "learning_rate": 4.451107615677022e-05, "loss": 2.2485, "step": 167500 }, { "epoch": 1.1, "learning_rate": 4.4494691309477e-05, "loss": 2.1954, "step": 168000 }, { "epoch": 1.1, "learning_rate": 4.447830646218377e-05, "loss": 2.2261, "step": 168500 }, { "epoch": 1.11, "learning_rate": 4.446192161489055e-05, "loss": 2.2999, "step": 169000 }, { "epoch": 1.11, "learning_rate": 4.444553676759733e-05, "loss": 2.2329, "step": 169500 }, { "epoch": 1.11, "learning_rate": 4.442915192030411e-05, "loss": 2.2624, "step": 170000 }, { "epoch": 1.12, "learning_rate": 4.441276707301088e-05, "loss": 2.2543, "step": 170500 }, { "epoch": 1.12, "learning_rate": 4.4396382225717656e-05, "loss": 2.2592, "step": 171000 }, { "epoch": 1.12, "learning_rate": 4.4379997378424435e-05, "loss": 2.2337, "step": 171500 }, { "epoch": 1.13, "learning_rate": 4.436361253113121e-05, "loss": 2.2104, "step": 172000 }, { "epoch": 1.13, "learning_rate": 4.434722768383799e-05, "loss": 2.2157, "step": 172500 }, { "epoch": 1.13, "learning_rate": 4.433084283654477e-05, "loss": 2.192, "step": 173000 }, { "epoch": 1.14, "learning_rate": 4.431445798925154e-05, "loss": 2.2079, "step": 173500 }, { "epoch": 1.14, "learning_rate": 4.429807314195832e-05, "loss": 2.2211, "step": 174000 }, { "epoch": 1.14, "learning_rate": 4.42816882946651e-05, "loss": 2.1626, "step": 174500 }, { "epoch": 1.15, "learning_rate": 4.4265303447371875e-05, "loss": 2.2117, "step": 175000 }, { "epoch": 1.15, "learning_rate": 4.424891860007865e-05, "loss": 2.2466, "step": 175500 }, { "epoch": 1.15, "learning_rate": 4.4232533752785425e-05, "loss": 2.2639, "step": 176000 }, { "epoch": 1.16, "learning_rate": 4.42161489054922e-05, "loss": 2.2069, "step": 176500 }, { "epoch": 1.16, "learning_rate": 4.419976405819898e-05, "loss": 2.1893, "step": 177000 }, { "epoch": 1.16, "learning_rate": 4.418337921090576e-05, "loss": 2.244, "step": 177500 }, { "epoch": 1.17, "learning_rate": 4.416699436361254e-05, "loss": 2.1944, "step": 178000 }, { "epoch": 1.17, "learning_rate": 4.415060951631931e-05, "loss": 2.2529, "step": 178500 }, { "epoch": 1.17, "learning_rate": 4.413422466902609e-05, "loss": 2.213, "step": 179000 }, { "epoch": 1.18, "learning_rate": 4.4117839821732866e-05, "loss": 2.21, "step": 179500 }, { "epoch": 1.18, "learning_rate": 4.410145497443964e-05, "loss": 2.2308, "step": 180000 }, { "epoch": 1.18, "learning_rate": 4.4085070127146415e-05, "loss": 2.2126, "step": 180500 }, { "epoch": 1.19, "learning_rate": 4.4068685279853193e-05, "loss": 2.2153, "step": 181000 }, { "epoch": 1.19, "learning_rate": 4.405230043255997e-05, "loss": 2.1841, "step": 181500 }, { "epoch": 1.19, "learning_rate": 4.403591558526674e-05, "loss": 2.241, "step": 182000 }, { "epoch": 1.2, "learning_rate": 4.401953073797352e-05, "loss": 2.1668, "step": 182500 }, { "epoch": 1.2, "learning_rate": 4.40031458906803e-05, "loss": 2.2255, "step": 183000 }, { "epoch": 1.2, "learning_rate": 4.398676104338708e-05, "loss": 2.1768, "step": 183500 }, { "epoch": 1.21, "learning_rate": 4.3970376196093856e-05, "loss": 2.1898, "step": 184000 }, { "epoch": 1.21, "learning_rate": 4.3953991348800634e-05, "loss": 2.2137, "step": 184500 }, { "epoch": 1.21, "learning_rate": 4.3937606501507406e-05, "loss": 2.2134, "step": 185000 }, { "epoch": 1.22, "learning_rate": 4.3921221654214184e-05, "loss": 2.1856, "step": 185500 }, { "epoch": 1.22, "learning_rate": 4.390483680692096e-05, "loss": 2.2435, "step": 186000 }, { "epoch": 1.22, "learning_rate": 4.388845195962774e-05, "loss": 2.1958, "step": 186500 }, { "epoch": 1.23, "learning_rate": 4.387206711233451e-05, "loss": 2.2051, "step": 187000 }, { "epoch": 1.23, "learning_rate": 4.385568226504129e-05, "loss": 2.2278, "step": 187500 }, { "epoch": 1.23, "learning_rate": 4.383929741774807e-05, "loss": 2.2004, "step": 188000 }, { "epoch": 1.24, "learning_rate": 4.3822912570454846e-05, "loss": 2.2042, "step": 188500 }, { "epoch": 1.24, "learning_rate": 4.3806527723161625e-05, "loss": 2.1624, "step": 189000 }, { "epoch": 1.24, "learning_rate": 4.37901428758684e-05, "loss": 2.1779, "step": 189500 }, { "epoch": 1.25, "learning_rate": 4.3773758028575174e-05, "loss": 2.1528, "step": 190000 }, { "epoch": 1.25, "learning_rate": 4.375737318128195e-05, "loss": 2.1773, "step": 190500 }, { "epoch": 1.25, "learning_rate": 4.374098833398873e-05, "loss": 2.1656, "step": 191000 }, { "epoch": 1.26, "learning_rate": 4.37246034866955e-05, "loss": 2.1532, "step": 191500 }, { "epoch": 1.26, "learning_rate": 4.370821863940228e-05, "loss": 2.1574, "step": 192000 }, { "epoch": 1.26, "learning_rate": 4.369183379210906e-05, "loss": 2.1625, "step": 192500 }, { "epoch": 1.26, "learning_rate": 4.367544894481584e-05, "loss": 2.1484, "step": 193000 }, { "epoch": 1.27, "learning_rate": 4.3659064097522615e-05, "loss": 2.1732, "step": 193500 }, { "epoch": 1.27, "learning_rate": 4.364267925022939e-05, "loss": 2.1294, "step": 194000 }, { "epoch": 1.27, "learning_rate": 4.362629440293617e-05, "loss": 2.1445, "step": 194500 }, { "epoch": 1.28, "learning_rate": 4.360990955564294e-05, "loss": 2.1555, "step": 195000 }, { "epoch": 1.28, "learning_rate": 4.359352470834972e-05, "loss": 2.1583, "step": 195500 }, { "epoch": 1.28, "learning_rate": 4.35771398610565e-05, "loss": 2.145, "step": 196000 }, { "epoch": 1.29, "learning_rate": 4.356075501376327e-05, "loss": 2.1277, "step": 196500 }, { "epoch": 1.29, "learning_rate": 4.354437016647005e-05, "loss": 2.1547, "step": 197000 }, { "epoch": 1.29, "learning_rate": 4.352798531917683e-05, "loss": 2.1766, "step": 197500 }, { "epoch": 1.3, "learning_rate": 4.3511600471883605e-05, "loss": 2.1429, "step": 198000 }, { "epoch": 1.3, "learning_rate": 4.349521562459038e-05, "loss": 2.1714, "step": 198500 }, { "epoch": 1.3, "learning_rate": 4.3478830777297155e-05, "loss": 2.135, "step": 199000 }, { "epoch": 1.31, "learning_rate": 4.346244593000394e-05, "loss": 2.1185, "step": 199500 }, { "epoch": 1.31, "learning_rate": 4.344606108271071e-05, "loss": 2.1559, "step": 200000 }, { "epoch": 1.31, "learning_rate": 4.342967623541749e-05, "loss": 2.1687, "step": 200500 }, { "epoch": 1.32, "learning_rate": 4.341329138812427e-05, "loss": 2.139, "step": 201000 }, { "epoch": 1.32, "learning_rate": 4.339690654083104e-05, "loss": 2.1995, "step": 201500 }, { "epoch": 1.32, "learning_rate": 4.338052169353782e-05, "loss": 2.1449, "step": 202000 }, { "epoch": 1.33, "learning_rate": 4.3364136846244596e-05, "loss": 2.1296, "step": 202500 }, { "epoch": 1.33, "learning_rate": 4.334775199895137e-05, "loss": 2.13, "step": 203000 }, { "epoch": 1.33, "learning_rate": 4.3331367151658145e-05, "loss": 2.139, "step": 203500 }, { "epoch": 1.34, "learning_rate": 4.3314982304364923e-05, "loss": 2.1115, "step": 204000 }, { "epoch": 1.34, "learning_rate": 4.32985974570717e-05, "loss": 2.1276, "step": 204500 }, { "epoch": 1.34, "learning_rate": 4.328221260977848e-05, "loss": 2.1194, "step": 205000 }, { "epoch": 1.35, "learning_rate": 4.326582776248526e-05, "loss": 2.1173, "step": 205500 }, { "epoch": 1.35, "learning_rate": 4.3249442915192036e-05, "loss": 2.0946, "step": 206000 }, { "epoch": 1.35, "learning_rate": 4.323305806789881e-05, "loss": 2.1313, "step": 206500 }, { "epoch": 1.36, "learning_rate": 4.3216673220605586e-05, "loss": 2.1395, "step": 207000 }, { "epoch": 1.36, "learning_rate": 4.3200288373312364e-05, "loss": 2.1386, "step": 207500 }, { "epoch": 1.36, "learning_rate": 4.3183903526019136e-05, "loss": 2.1101, "step": 208000 }, { "epoch": 1.37, "learning_rate": 4.3167518678725914e-05, "loss": 2.1277, "step": 208500 }, { "epoch": 1.37, "learning_rate": 4.315113383143269e-05, "loss": 2.0737, "step": 209000 }, { "epoch": 1.37, "learning_rate": 4.313474898413947e-05, "loss": 2.0535, "step": 209500 }, { "epoch": 1.38, "learning_rate": 4.311836413684625e-05, "loss": 2.0983, "step": 210000 }, { "epoch": 1.38, "learning_rate": 4.310197928955303e-05, "loss": 2.13, "step": 210500 }, { "epoch": 1.38, "learning_rate": 4.3085594442259805e-05, "loss": 2.1315, "step": 211000 }, { "epoch": 1.39, "learning_rate": 4.3069209594966576e-05, "loss": 2.1632, "step": 211500 }, { "epoch": 1.39, "learning_rate": 4.3052824747673355e-05, "loss": 2.0939, "step": 212000 }, { "epoch": 1.39, "learning_rate": 4.303643990038013e-05, "loss": 2.074, "step": 212500 }, { "epoch": 1.4, "learning_rate": 4.3020055053086904e-05, "loss": 2.1109, "step": 213000 }, { "epoch": 1.4, "learning_rate": 4.300367020579368e-05, "loss": 2.1588, "step": 213500 }, { "epoch": 1.4, "learning_rate": 4.298728535850046e-05, "loss": 2.1276, "step": 214000 }, { "epoch": 1.41, "learning_rate": 4.297090051120723e-05, "loss": 2.1125, "step": 214500 }, { "epoch": 1.41, "learning_rate": 4.295451566391401e-05, "loss": 2.0941, "step": 215000 }, { "epoch": 1.41, "learning_rate": 4.293813081662079e-05, "loss": 2.1186, "step": 215500 }, { "epoch": 1.42, "learning_rate": 4.2921745969327573e-05, "loss": 2.1093, "step": 216000 }, { "epoch": 1.42, "learning_rate": 4.2905361122034345e-05, "loss": 2.1239, "step": 216500 }, { "epoch": 1.42, "learning_rate": 4.288897627474112e-05, "loss": 2.0665, "step": 217000 }, { "epoch": 1.43, "learning_rate": 4.28725914274479e-05, "loss": 2.1046, "step": 217500 }, { "epoch": 1.43, "learning_rate": 4.285620658015467e-05, "loss": 2.0596, "step": 218000 }, { "epoch": 1.43, "learning_rate": 4.283982173286145e-05, "loss": 2.0987, "step": 218500 }, { "epoch": 1.44, "learning_rate": 4.282343688556823e-05, "loss": 2.0734, "step": 219000 }, { "epoch": 1.44, "learning_rate": 4.2807052038275e-05, "loss": 2.1092, "step": 219500 }, { "epoch": 1.44, "learning_rate": 4.279066719098178e-05, "loss": 2.0912, "step": 220000 }, { "epoch": 1.45, "learning_rate": 4.277428234368856e-05, "loss": 2.0993, "step": 220500 }, { "epoch": 1.45, "learning_rate": 4.2757897496395335e-05, "loss": 2.0974, "step": 221000 }, { "epoch": 1.45, "learning_rate": 4.2741512649102113e-05, "loss": 2.1064, "step": 221500 }, { "epoch": 1.45, "learning_rate": 4.272512780180889e-05, "loss": 2.0406, "step": 222000 }, { "epoch": 1.46, "learning_rate": 4.270874295451567e-05, "loss": 2.0477, "step": 222500 }, { "epoch": 1.46, "learning_rate": 4.269235810722244e-05, "loss": 2.0389, "step": 223000 }, { "epoch": 1.46, "learning_rate": 4.267597325992922e-05, "loss": 2.1165, "step": 223500 }, { "epoch": 1.47, "learning_rate": 4.2659588412636e-05, "loss": 2.1055, "step": 224000 }, { "epoch": 1.47, "learning_rate": 4.264320356534277e-05, "loss": 2.1165, "step": 224500 }, { "epoch": 1.47, "learning_rate": 4.262681871804955e-05, "loss": 2.0781, "step": 225000 }, { "epoch": 1.48, "learning_rate": 4.2610433870756326e-05, "loss": 2.0948, "step": 225500 }, { "epoch": 1.48, "learning_rate": 4.2594049023463104e-05, "loss": 2.0862, "step": 226000 }, { "epoch": 1.48, "learning_rate": 4.257766417616988e-05, "loss": 2.1054, "step": 226500 }, { "epoch": 1.49, "learning_rate": 4.256127932887666e-05, "loss": 2.0423, "step": 227000 }, { "epoch": 1.49, "learning_rate": 4.254489448158344e-05, "loss": 2.129, "step": 227500 }, { "epoch": 1.49, "learning_rate": 4.252850963429021e-05, "loss": 2.0653, "step": 228000 }, { "epoch": 1.5, "learning_rate": 4.251212478699699e-05, "loss": 2.1091, "step": 228500 }, { "epoch": 1.5, "learning_rate": 4.2495739939703766e-05, "loss": 2.0577, "step": 229000 }, { "epoch": 1.5, "learning_rate": 4.247935509241054e-05, "loss": 2.0462, "step": 229500 }, { "epoch": 1.51, "learning_rate": 4.2462970245117316e-05, "loss": 2.0531, "step": 230000 }, { "epoch": 1.51, "learning_rate": 4.2446585397824094e-05, "loss": 2.1126, "step": 230500 }, { "epoch": 1.51, "learning_rate": 4.2430200550530866e-05, "loss": 2.0423, "step": 231000 }, { "epoch": 1.52, "learning_rate": 4.2413815703237644e-05, "loss": 2.1091, "step": 231500 }, { "epoch": 1.52, "learning_rate": 4.239743085594443e-05, "loss": 2.0658, "step": 232000 }, { "epoch": 1.52, "learning_rate": 4.238104600865121e-05, "loss": 2.0164, "step": 232500 }, { "epoch": 1.53, "learning_rate": 4.236466116135798e-05, "loss": 2.0613, "step": 233000 }, { "epoch": 1.53, "learning_rate": 4.234827631406476e-05, "loss": 2.078, "step": 233500 }, { "epoch": 1.53, "learning_rate": 4.2331891466771535e-05, "loss": 2.0308, "step": 234000 }, { "epoch": 1.54, "learning_rate": 4.2315506619478306e-05, "loss": 2.0768, "step": 234500 }, { "epoch": 1.54, "learning_rate": 4.2299121772185085e-05, "loss": 2.0302, "step": 235000 }, { "epoch": 1.54, "learning_rate": 4.228273692489186e-05, "loss": 2.0392, "step": 235500 }, { "epoch": 1.55, "learning_rate": 4.2266352077598634e-05, "loss": 2.0345, "step": 236000 }, { "epoch": 1.55, "learning_rate": 4.224996723030541e-05, "loss": 2.0522, "step": 236500 }, { "epoch": 1.55, "learning_rate": 4.223358238301219e-05, "loss": 2.0818, "step": 237000 }, { "epoch": 1.56, "learning_rate": 4.221719753571897e-05, "loss": 2.057, "step": 237500 }, { "epoch": 1.56, "learning_rate": 4.220081268842575e-05, "loss": 2.0406, "step": 238000 }, { "epoch": 1.56, "learning_rate": 4.2184427841132525e-05, "loss": 2.0753, "step": 238500 }, { "epoch": 1.57, "learning_rate": 4.2168042993839303e-05, "loss": 2.0674, "step": 239000 }, { "epoch": 1.57, "learning_rate": 4.2151658146546075e-05, "loss": 2.0373, "step": 239500 }, { "epoch": 1.57, "learning_rate": 4.213527329925285e-05, "loss": 2.0403, "step": 240000 }, { "epoch": 1.58, "learning_rate": 4.211888845195963e-05, "loss": 2.084, "step": 240500 }, { "epoch": 1.58, "learning_rate": 4.21025036046664e-05, "loss": 2.0569, "step": 241000 }, { "epoch": 1.58, "learning_rate": 4.208611875737318e-05, "loss": 2.024, "step": 241500 }, { "epoch": 1.59, "learning_rate": 4.206973391007996e-05, "loss": 2.0109, "step": 242000 }, { "epoch": 1.59, "learning_rate": 4.205334906278674e-05, "loss": 2.0377, "step": 242500 }, { "epoch": 1.59, "learning_rate": 4.2036964215493516e-05, "loss": 2.0437, "step": 243000 }, { "epoch": 1.6, "learning_rate": 4.2020579368200294e-05, "loss": 2.0634, "step": 243500 }, { "epoch": 1.6, "learning_rate": 4.200419452090707e-05, "loss": 2.044, "step": 244000 }, { "epoch": 1.6, "learning_rate": 4.1987809673613843e-05, "loss": 2.0403, "step": 244500 }, { "epoch": 1.61, "learning_rate": 4.197142482632062e-05, "loss": 2.0625, "step": 245000 }, { "epoch": 1.61, "learning_rate": 4.19550399790274e-05, "loss": 2.0114, "step": 245500 }, { "epoch": 1.61, "learning_rate": 4.193865513173417e-05, "loss": 2.0536, "step": 246000 }, { "epoch": 1.62, "learning_rate": 4.192227028444095e-05, "loss": 2.0452, "step": 246500 }, { "epoch": 1.62, "learning_rate": 4.190588543714773e-05, "loss": 2.0121, "step": 247000 }, { "epoch": 1.62, "learning_rate": 4.18895005898545e-05, "loss": 2.0588, "step": 247500 }, { "epoch": 1.63, "learning_rate": 4.187311574256128e-05, "loss": 2.0754, "step": 248000 }, { "epoch": 1.63, "learning_rate": 4.185673089526806e-05, "loss": 2.0012, "step": 248500 }, { "epoch": 1.63, "learning_rate": 4.1840346047974834e-05, "loss": 2.0249, "step": 249000 }, { "epoch": 1.64, "learning_rate": 4.182396120068161e-05, "loss": 2.0051, "step": 249500 }, { "epoch": 1.64, "learning_rate": 4.180757635338839e-05, "loss": 2.0572, "step": 250000 }, { "epoch": 1.64, "learning_rate": 4.179119150609517e-05, "loss": 2.0218, "step": 250500 }, { "epoch": 1.65, "learning_rate": 4.177480665880194e-05, "loss": 2.0441, "step": 251000 }, { "epoch": 1.65, "learning_rate": 4.175842181150872e-05, "loss": 2.0569, "step": 251500 }, { "epoch": 1.65, "learning_rate": 4.1742036964215496e-05, "loss": 2.0066, "step": 252000 }, { "epoch": 1.65, "learning_rate": 4.172565211692227e-05, "loss": 2.0733, "step": 252500 }, { "epoch": 1.66, "learning_rate": 4.1709267269629046e-05, "loss": 2.0561, "step": 253000 }, { "epoch": 1.66, "learning_rate": 4.1692882422335824e-05, "loss": 1.9634, "step": 253500 }, { "epoch": 1.66, "learning_rate": 4.16764975750426e-05, "loss": 2.0124, "step": 254000 }, { "epoch": 1.67, "learning_rate": 4.166011272774938e-05, "loss": 2.0046, "step": 254500 }, { "epoch": 1.67, "learning_rate": 4.164372788045616e-05, "loss": 1.9938, "step": 255000 }, { "epoch": 1.67, "learning_rate": 4.162734303316294e-05, "loss": 2.0606, "step": 255500 }, { "epoch": 1.68, "learning_rate": 4.161095818586971e-05, "loss": 1.9944, "step": 256000 }, { "epoch": 1.68, "learning_rate": 4.159457333857649e-05, "loss": 2.0212, "step": 256500 }, { "epoch": 1.68, "learning_rate": 4.1578188491283265e-05, "loss": 2.0189, "step": 257000 }, { "epoch": 1.69, "learning_rate": 4.1561803643990036e-05, "loss": 2.0322, "step": 257500 }, { "epoch": 1.69, "learning_rate": 4.1545418796696815e-05, "loss": 1.9998, "step": 258000 }, { "epoch": 1.69, "learning_rate": 4.152903394940359e-05, "loss": 2.0088, "step": 258500 }, { "epoch": 1.7, "learning_rate": 4.151264910211037e-05, "loss": 1.965, "step": 259000 }, { "epoch": 1.7, "learning_rate": 4.149626425481715e-05, "loss": 2.0404, "step": 259500 }, { "epoch": 1.7, "learning_rate": 4.147987940752393e-05, "loss": 2.0035, "step": 260000 }, { "epoch": 1.71, "learning_rate": 4.14634945602307e-05, "loss": 2.0247, "step": 260500 }, { "epoch": 1.71, "learning_rate": 4.144710971293748e-05, "loss": 2.0115, "step": 261000 }, { "epoch": 1.71, "learning_rate": 4.1430724865644255e-05, "loss": 1.9907, "step": 261500 }, { "epoch": 1.72, "learning_rate": 4.1414340018351033e-05, "loss": 1.9963, "step": 262000 }, { "epoch": 1.72, "learning_rate": 4.1397955171057805e-05, "loss": 1.9923, "step": 262500 }, { "epoch": 1.72, "learning_rate": 4.138157032376458e-05, "loss": 2.0169, "step": 263000 }, { "epoch": 1.73, "learning_rate": 4.136518547647136e-05, "loss": 1.9834, "step": 263500 }, { "epoch": 1.73, "learning_rate": 4.134880062917813e-05, "loss": 1.9915, "step": 264000 }, { "epoch": 1.73, "learning_rate": 4.133241578188492e-05, "loss": 1.9908, "step": 264500 }, { "epoch": 1.74, "learning_rate": 4.1316030934591696e-05, "loss": 1.9743, "step": 265000 }, { "epoch": 1.74, "learning_rate": 4.129964608729847e-05, "loss": 2.0256, "step": 265500 }, { "epoch": 1.74, "learning_rate": 4.1283261240005246e-05, "loss": 1.9608, "step": 266000 }, { "epoch": 1.75, "learning_rate": 4.1266876392712024e-05, "loss": 1.9813, "step": 266500 }, { "epoch": 1.75, "learning_rate": 4.12504915454188e-05, "loss": 1.9929, "step": 267000 }, { "epoch": 1.75, "learning_rate": 4.1234106698125573e-05, "loss": 2.0109, "step": 267500 }, { "epoch": 1.76, "learning_rate": 4.121772185083235e-05, "loss": 1.9545, "step": 268000 }, { "epoch": 1.76, "learning_rate": 4.120133700353913e-05, "loss": 1.9616, "step": 268500 }, { "epoch": 1.76, "learning_rate": 4.11849521562459e-05, "loss": 1.9704, "step": 269000 }, { "epoch": 1.77, "learning_rate": 4.116856730895268e-05, "loss": 1.9551, "step": 269500 }, { "epoch": 1.77, "learning_rate": 4.115218246165946e-05, "loss": 1.9826, "step": 270000 }, { "epoch": 1.77, "learning_rate": 4.1135797614366236e-05, "loss": 1.9818, "step": 270500 }, { "epoch": 1.78, "learning_rate": 4.1119412767073014e-05, "loss": 1.9889, "step": 271000 }, { "epoch": 1.78, "learning_rate": 4.110302791977979e-05, "loss": 1.9646, "step": 271500 }, { "epoch": 1.78, "learning_rate": 4.1086643072486564e-05, "loss": 2.0047, "step": 272000 }, { "epoch": 1.79, "learning_rate": 4.107025822519334e-05, "loss": 1.9924, "step": 272500 }, { "epoch": 1.79, "learning_rate": 4.105387337790012e-05, "loss": 1.9922, "step": 273000 }, { "epoch": 1.79, "learning_rate": 4.10374885306069e-05, "loss": 2.0368, "step": 273500 }, { "epoch": 1.8, "learning_rate": 4.102110368331367e-05, "loss": 1.98, "step": 274000 }, { "epoch": 1.8, "learning_rate": 4.100471883602045e-05, "loss": 1.9428, "step": 274500 }, { "epoch": 1.8, "learning_rate": 4.0988333988727226e-05, "loss": 1.9916, "step": 275000 }, { "epoch": 1.81, "learning_rate": 4.0971949141434005e-05, "loss": 1.9686, "step": 275500 }, { "epoch": 1.81, "learning_rate": 4.095556429414078e-05, "loss": 1.9679, "step": 276000 }, { "epoch": 1.81, "learning_rate": 4.093917944684756e-05, "loss": 1.9917, "step": 276500 }, { "epoch": 1.82, "learning_rate": 4.092279459955433e-05, "loss": 1.9367, "step": 277000 }, { "epoch": 1.82, "learning_rate": 4.090640975226111e-05, "loss": 1.9666, "step": 277500 }, { "epoch": 1.82, "learning_rate": 4.089002490496789e-05, "loss": 1.9729, "step": 278000 }, { "epoch": 1.83, "learning_rate": 4.087364005767467e-05, "loss": 1.9763, "step": 278500 }, { "epoch": 1.83, "learning_rate": 4.085725521038144e-05, "loss": 1.9897, "step": 279000 }, { "epoch": 1.83, "learning_rate": 4.084087036308822e-05, "loss": 1.9343, "step": 279500 }, { "epoch": 1.84, "learning_rate": 4.0824485515794995e-05, "loss": 1.9318, "step": 280000 }, { "epoch": 1.84, "learning_rate": 4.0808100668501766e-05, "loss": 1.9718, "step": 280500 }, { "epoch": 1.84, "learning_rate": 4.079171582120855e-05, "loss": 1.9612, "step": 281000 }, { "epoch": 1.84, "learning_rate": 4.077533097391533e-05, "loss": 1.9785, "step": 281500 }, { "epoch": 1.85, "learning_rate": 4.07589461266221e-05, "loss": 1.9467, "step": 282000 }, { "epoch": 1.85, "learning_rate": 4.074256127932888e-05, "loss": 1.9881, "step": 282500 }, { "epoch": 1.85, "learning_rate": 4.072617643203566e-05, "loss": 1.9968, "step": 283000 }, { "epoch": 1.86, "learning_rate": 4.070979158474243e-05, "loss": 1.9951, "step": 283500 }, { "epoch": 1.86, "learning_rate": 4.069340673744921e-05, "loss": 1.9506, "step": 284000 }, { "epoch": 1.86, "learning_rate": 4.0677021890155985e-05, "loss": 1.9881, "step": 284500 }, { "epoch": 1.87, "learning_rate": 4.0660637042862763e-05, "loss": 2.0045, "step": 285000 }, { "epoch": 1.87, "learning_rate": 4.0644252195569535e-05, "loss": 2.0164, "step": 285500 }, { "epoch": 1.87, "learning_rate": 4.062786734827631e-05, "loss": 1.9656, "step": 286000 }, { "epoch": 1.88, "learning_rate": 4.061148250098309e-05, "loss": 2.0256, "step": 286500 }, { "epoch": 1.88, "learning_rate": 4.059509765368987e-05, "loss": 1.9628, "step": 287000 }, { "epoch": 1.88, "learning_rate": 4.057871280639665e-05, "loss": 1.9357, "step": 287500 }, { "epoch": 1.89, "learning_rate": 4.0562327959103426e-05, "loss": 1.9275, "step": 288000 }, { "epoch": 1.89, "learning_rate": 4.05459431118102e-05, "loss": 1.9508, "step": 288500 }, { "epoch": 1.89, "learning_rate": 4.0529558264516976e-05, "loss": 1.979, "step": 289000 }, { "epoch": 1.9, "learning_rate": 4.0513173417223754e-05, "loss": 1.964, "step": 289500 }, { "epoch": 1.9, "learning_rate": 4.049678856993053e-05, "loss": 1.9323, "step": 290000 }, { "epoch": 1.9, "learning_rate": 4.0480403722637303e-05, "loss": 1.912, "step": 290500 }, { "epoch": 1.91, "learning_rate": 4.046401887534408e-05, "loss": 1.9392, "step": 291000 }, { "epoch": 1.91, "learning_rate": 4.044763402805086e-05, "loss": 1.9446, "step": 291500 }, { "epoch": 1.91, "learning_rate": 4.043124918075764e-05, "loss": 2.0005, "step": 292000 }, { "epoch": 1.92, "learning_rate": 4.0414864333464416e-05, "loss": 1.96, "step": 292500 }, { "epoch": 1.92, "learning_rate": 4.0398479486171195e-05, "loss": 1.9529, "step": 293000 }, { "epoch": 1.92, "learning_rate": 4.0382094638877966e-05, "loss": 1.9194, "step": 293500 }, { "epoch": 1.93, "learning_rate": 4.0365709791584744e-05, "loss": 1.9078, "step": 294000 }, { "epoch": 1.93, "learning_rate": 4.034932494429152e-05, "loss": 1.9361, "step": 294500 }, { "epoch": 1.93, "learning_rate": 4.03329400969983e-05, "loss": 1.9663, "step": 295000 }, { "epoch": 1.94, "learning_rate": 4.031655524970507e-05, "loss": 1.9434, "step": 295500 }, { "epoch": 1.94, "learning_rate": 4.030017040241185e-05, "loss": 1.9645, "step": 296000 }, { "epoch": 1.94, "learning_rate": 4.028378555511863e-05, "loss": 1.9599, "step": 296500 }, { "epoch": 1.95, "learning_rate": 4.026740070782541e-05, "loss": 1.9384, "step": 297000 }, { "epoch": 1.95, "learning_rate": 4.0251015860532185e-05, "loss": 1.9535, "step": 297500 }, { "epoch": 1.95, "learning_rate": 4.023463101323896e-05, "loss": 1.9368, "step": 298000 }, { "epoch": 1.96, "learning_rate": 4.0218246165945735e-05, "loss": 1.9437, "step": 298500 }, { "epoch": 1.96, "learning_rate": 4.020186131865251e-05, "loss": 1.926, "step": 299000 }, { "epoch": 1.96, "learning_rate": 4.018547647135929e-05, "loss": 1.9856, "step": 299500 }, { "epoch": 1.97, "learning_rate": 4.016909162406606e-05, "loss": 1.9596, "step": 300000 }, { "epoch": 1.97, "learning_rate": 4.015270677677284e-05, "loss": 1.9545, "step": 300500 }, { "epoch": 1.97, "learning_rate": 4.013632192947962e-05, "loss": 1.9025, "step": 301000 }, { "epoch": 1.98, "learning_rate": 4.01199370821864e-05, "loss": 1.9473, "step": 301500 }, { "epoch": 1.98, "learning_rate": 4.010355223489317e-05, "loss": 1.9402, "step": 302000 }, { "epoch": 1.98, "learning_rate": 4.008716738759995e-05, "loss": 1.921, "step": 302500 }, { "epoch": 1.99, "learning_rate": 4.0070782540306725e-05, "loss": 1.9377, "step": 303000 }, { "epoch": 1.99, "learning_rate": 4.00543976930135e-05, "loss": 1.9043, "step": 303500 }, { "epoch": 1.99, "learning_rate": 4.003801284572028e-05, "loss": 1.9234, "step": 304000 }, { "epoch": 2.0, "learning_rate": 4.002162799842706e-05, "loss": 1.9196, "step": 304500 }, { "epoch": 2.0, "learning_rate": 4.000524315113383e-05, "loss": 1.8987, "step": 305000 }, { "epoch": 2.0, "learning_rate": 3.998885830384061e-05, "loss": 1.8504, "step": 305500 }, { "epoch": 2.01, "learning_rate": 3.997247345654739e-05, "loss": 1.9076, "step": 306000 }, { "epoch": 2.01, "learning_rate": 3.9956088609254166e-05, "loss": 1.9002, "step": 306500 }, { "epoch": 2.01, "learning_rate": 3.993970376196094e-05, "loss": 1.8584, "step": 307000 }, { "epoch": 2.02, "learning_rate": 3.9923318914667715e-05, "loss": 1.8941, "step": 307500 }, { "epoch": 2.02, "learning_rate": 3.9906934067374493e-05, "loss": 1.8996, "step": 308000 }, { "epoch": 2.02, "learning_rate": 3.989054922008127e-05, "loss": 1.89, "step": 308500 }, { "epoch": 2.03, "learning_rate": 3.987416437278805e-05, "loss": 1.8675, "step": 309000 }, { "epoch": 2.03, "learning_rate": 3.985777952549483e-05, "loss": 1.8991, "step": 309500 }, { "epoch": 2.03, "learning_rate": 3.98413946782016e-05, "loss": 1.9079, "step": 310000 }, { "epoch": 2.03, "learning_rate": 3.982500983090838e-05, "loss": 1.8204, "step": 310500 }, { "epoch": 2.04, "learning_rate": 3.9808624983615156e-05, "loss": 1.9255, "step": 311000 }, { "epoch": 2.04, "learning_rate": 3.979224013632193e-05, "loss": 1.9214, "step": 311500 }, { "epoch": 2.04, "learning_rate": 3.9775855289028706e-05, "loss": 1.9228, "step": 312000 }, { "epoch": 2.05, "learning_rate": 3.9759470441735484e-05, "loss": 1.9066, "step": 312500 }, { "epoch": 2.05, "learning_rate": 3.974308559444226e-05, "loss": 1.8935, "step": 313000 }, { "epoch": 2.05, "learning_rate": 3.972670074714904e-05, "loss": 1.9053, "step": 313500 }, { "epoch": 2.06, "learning_rate": 3.971031589985582e-05, "loss": 1.8803, "step": 314000 }, { "epoch": 2.06, "learning_rate": 3.96939310525626e-05, "loss": 1.8632, "step": 314500 }, { "epoch": 2.06, "learning_rate": 3.967754620526937e-05, "loss": 1.8739, "step": 315000 }, { "epoch": 2.07, "learning_rate": 3.9661161357976146e-05, "loss": 1.8866, "step": 315500 }, { "epoch": 2.07, "learning_rate": 3.9644776510682925e-05, "loss": 1.8859, "step": 316000 }, { "epoch": 2.07, "learning_rate": 3.9628391663389696e-05, "loss": 1.8466, "step": 316500 }, { "epoch": 2.08, "learning_rate": 3.9612006816096474e-05, "loss": 1.8983, "step": 317000 }, { "epoch": 2.08, "learning_rate": 3.959562196880325e-05, "loss": 1.9166, "step": 317500 }, { "epoch": 2.08, "learning_rate": 3.957923712151003e-05, "loss": 1.913, "step": 318000 }, { "epoch": 2.09, "learning_rate": 3.95628522742168e-05, "loss": 1.8765, "step": 318500 }, { "epoch": 2.09, "learning_rate": 3.954646742692358e-05, "loss": 1.8587, "step": 319000 }, { "epoch": 2.09, "learning_rate": 3.9530082579630365e-05, "loss": 1.8585, "step": 319500 }, { "epoch": 2.1, "learning_rate": 3.951369773233714e-05, "loss": 1.8476, "step": 320000 }, { "epoch": 2.1, "learning_rate": 3.9497312885043915e-05, "loss": 1.8661, "step": 320500 }, { "epoch": 2.1, "learning_rate": 3.948092803775069e-05, "loss": 1.911, "step": 321000 }, { "epoch": 2.11, "learning_rate": 3.9464543190457465e-05, "loss": 1.8387, "step": 321500 }, { "epoch": 2.11, "learning_rate": 3.944815834316424e-05, "loss": 1.8547, "step": 322000 }, { "epoch": 2.11, "learning_rate": 3.943177349587102e-05, "loss": 1.8678, "step": 322500 }, { "epoch": 2.12, "learning_rate": 3.941538864857779e-05, "loss": 1.8557, "step": 323000 }, { "epoch": 2.12, "learning_rate": 3.939900380128457e-05, "loss": 1.8851, "step": 323500 }, { "epoch": 2.12, "learning_rate": 3.938261895399135e-05, "loss": 1.8645, "step": 324000 }, { "epoch": 2.13, "learning_rate": 3.936623410669813e-05, "loss": 1.8711, "step": 324500 }, { "epoch": 2.13, "learning_rate": 3.9349849259404905e-05, "loss": 1.8375, "step": 325000 }, { "epoch": 2.13, "learning_rate": 3.9333464412111683e-05, "loss": 1.8725, "step": 325500 }, { "epoch": 2.14, "learning_rate": 3.931707956481846e-05, "loss": 1.8568, "step": 326000 }, { "epoch": 2.14, "learning_rate": 3.930069471752523e-05, "loss": 1.8997, "step": 326500 }, { "epoch": 2.14, "learning_rate": 3.928430987023201e-05, "loss": 1.9208, "step": 327000 }, { "epoch": 2.15, "learning_rate": 3.926792502293879e-05, "loss": 1.8545, "step": 327500 }, { "epoch": 2.15, "learning_rate": 3.925154017564556e-05, "loss": 1.8741, "step": 328000 }, { "epoch": 2.15, "learning_rate": 3.923515532835234e-05, "loss": 1.9132, "step": 328500 }, { "epoch": 2.16, "learning_rate": 3.921877048105912e-05, "loss": 1.8845, "step": 329000 }, { "epoch": 2.16, "learning_rate": 3.9202385633765896e-05, "loss": 1.9004, "step": 329500 }, { "epoch": 2.16, "learning_rate": 3.9186000786472674e-05, "loss": 1.8238, "step": 330000 }, { "epoch": 2.17, "learning_rate": 3.916961593917945e-05, "loss": 1.8421, "step": 330500 }, { "epoch": 2.17, "learning_rate": 3.915323109188623e-05, "loss": 1.9118, "step": 331000 }, { "epoch": 2.17, "learning_rate": 3.9136846244593e-05, "loss": 1.856, "step": 331500 }, { "epoch": 2.18, "learning_rate": 3.912046139729978e-05, "loss": 1.9245, "step": 332000 }, { "epoch": 2.18, "learning_rate": 3.910407655000656e-05, "loss": 1.8702, "step": 332500 }, { "epoch": 2.18, "learning_rate": 3.908769170271333e-05, "loss": 1.8833, "step": 333000 }, { "epoch": 2.19, "learning_rate": 3.907130685542011e-05, "loss": 1.881, "step": 333500 }, { "epoch": 2.19, "learning_rate": 3.9054922008126886e-05, "loss": 1.8948, "step": 334000 }, { "epoch": 2.19, "learning_rate": 3.903853716083366e-05, "loss": 1.835, "step": 334500 }, { "epoch": 2.2, "learning_rate": 3.9022152313540436e-05, "loss": 1.8931, "step": 335000 }, { "epoch": 2.2, "learning_rate": 3.9005767466247214e-05, "loss": 1.8698, "step": 335500 }, { "epoch": 2.2, "learning_rate": 3.8989382618954e-05, "loss": 1.8422, "step": 336000 }, { "epoch": 2.21, "learning_rate": 3.897299777166077e-05, "loss": 1.8407, "step": 336500 }, { "epoch": 2.21, "learning_rate": 3.895661292436755e-05, "loss": 1.8456, "step": 337000 }, { "epoch": 2.21, "learning_rate": 3.894022807707433e-05, "loss": 1.878, "step": 337500 }, { "epoch": 2.22, "learning_rate": 3.89238432297811e-05, "loss": 1.886, "step": 338000 }, { "epoch": 2.22, "learning_rate": 3.8907458382487876e-05, "loss": 1.8397, "step": 338500 }, { "epoch": 2.22, "learning_rate": 3.8891073535194655e-05, "loss": 1.8759, "step": 339000 }, { "epoch": 2.23, "learning_rate": 3.8874688687901426e-05, "loss": 1.9162, "step": 339500 }, { "epoch": 2.23, "learning_rate": 3.8858303840608204e-05, "loss": 1.889, "step": 340000 }, { "epoch": 2.23, "learning_rate": 3.884191899331498e-05, "loss": 1.8071, "step": 340500 }, { "epoch": 2.23, "learning_rate": 3.882553414602176e-05, "loss": 1.8631, "step": 341000 }, { "epoch": 2.24, "learning_rate": 3.880914929872854e-05, "loss": 1.8273, "step": 341500 }, { "epoch": 2.24, "learning_rate": 3.879276445143532e-05, "loss": 1.862, "step": 342000 }, { "epoch": 2.24, "learning_rate": 3.8776379604142095e-05, "loss": 1.8594, "step": 342500 }, { "epoch": 2.25, "learning_rate": 3.875999475684887e-05, "loss": 1.8605, "step": 343000 }, { "epoch": 2.25, "learning_rate": 3.8743609909555645e-05, "loss": 1.8635, "step": 343500 }, { "epoch": 2.25, "learning_rate": 3.872722506226242e-05, "loss": 1.8418, "step": 344000 }, { "epoch": 2.26, "learning_rate": 3.8710840214969195e-05, "loss": 1.8935, "step": 344500 }, { "epoch": 2.26, "learning_rate": 3.869445536767597e-05, "loss": 1.8546, "step": 345000 }, { "epoch": 2.26, "learning_rate": 3.867807052038275e-05, "loss": 1.8234, "step": 345500 }, { "epoch": 2.27, "learning_rate": 3.866168567308953e-05, "loss": 1.8606, "step": 346000 }, { "epoch": 2.27, "learning_rate": 3.864530082579631e-05, "loss": 1.8159, "step": 346500 }, { "epoch": 2.27, "learning_rate": 3.8628915978503086e-05, "loss": 1.8247, "step": 347000 }, { "epoch": 2.28, "learning_rate": 3.8612531131209864e-05, "loss": 1.8247, "step": 347500 }, { "epoch": 2.28, "learning_rate": 3.8596146283916635e-05, "loss": 1.8176, "step": 348000 }, { "epoch": 2.28, "learning_rate": 3.8579761436623413e-05, "loss": 1.8634, "step": 348500 }, { "epoch": 2.29, "learning_rate": 3.856337658933019e-05, "loss": 1.8248, "step": 349000 }, { "epoch": 2.29, "learning_rate": 3.854699174203696e-05, "loss": 1.8861, "step": 349500 }, { "epoch": 2.29, "learning_rate": 3.853060689474374e-05, "loss": 1.8569, "step": 350000 }, { "epoch": 2.3, "learning_rate": 3.851422204745052e-05, "loss": 1.8773, "step": 350500 }, { "epoch": 2.3, "learning_rate": 3.849783720015729e-05, "loss": 1.8388, "step": 351000 }, { "epoch": 2.3, "learning_rate": 3.848145235286407e-05, "loss": 1.851, "step": 351500 }, { "epoch": 2.31, "learning_rate": 3.8465067505570854e-05, "loss": 1.8733, "step": 352000 }, { "epoch": 2.31, "learning_rate": 3.844868265827763e-05, "loss": 1.8752, "step": 352500 }, { "epoch": 2.31, "learning_rate": 3.8432297810984404e-05, "loss": 1.7966, "step": 353000 }, { "epoch": 2.32, "learning_rate": 3.841591296369118e-05, "loss": 1.8572, "step": 353500 }, { "epoch": 2.32, "learning_rate": 3.839952811639796e-05, "loss": 1.8528, "step": 354000 }, { "epoch": 2.32, "learning_rate": 3.838314326910473e-05, "loss": 1.8467, "step": 354500 }, { "epoch": 2.33, "learning_rate": 3.836675842181151e-05, "loss": 1.8455, "step": 355000 }, { "epoch": 2.33, "learning_rate": 3.835037357451829e-05, "loss": 1.8371, "step": 355500 }, { "epoch": 2.33, "learning_rate": 3.833398872722506e-05, "loss": 1.8466, "step": 356000 }, { "epoch": 2.34, "learning_rate": 3.831760387993184e-05, "loss": 1.8512, "step": 356500 }, { "epoch": 2.34, "learning_rate": 3.8301219032638616e-05, "loss": 1.8518, "step": 357000 }, { "epoch": 2.34, "learning_rate": 3.8284834185345394e-05, "loss": 1.867, "step": 357500 }, { "epoch": 2.35, "learning_rate": 3.826844933805217e-05, "loss": 1.8346, "step": 358000 }, { "epoch": 2.35, "learning_rate": 3.825206449075895e-05, "loss": 1.8393, "step": 358500 }, { "epoch": 2.35, "learning_rate": 3.823567964346573e-05, "loss": 1.8926, "step": 359000 }, { "epoch": 2.36, "learning_rate": 3.82192947961725e-05, "loss": 1.8717, "step": 359500 }, { "epoch": 2.36, "learning_rate": 3.820290994887928e-05, "loss": 1.8577, "step": 360000 }, { "epoch": 2.36, "learning_rate": 3.818652510158606e-05, "loss": 1.8611, "step": 360500 }, { "epoch": 2.37, "learning_rate": 3.817014025429283e-05, "loss": 1.8146, "step": 361000 }, { "epoch": 2.37, "learning_rate": 3.8153755406999606e-05, "loss": 1.8534, "step": 361500 }, { "epoch": 2.37, "learning_rate": 3.8137370559706385e-05, "loss": 1.8584, "step": 362000 }, { "epoch": 2.38, "learning_rate": 3.812098571241316e-05, "loss": 1.8384, "step": 362500 }, { "epoch": 2.38, "learning_rate": 3.810460086511994e-05, "loss": 1.8103, "step": 363000 }, { "epoch": 2.38, "learning_rate": 3.808821601782672e-05, "loss": 1.8542, "step": 363500 }, { "epoch": 2.39, "learning_rate": 3.80718311705335e-05, "loss": 1.8473, "step": 364000 }, { "epoch": 2.39, "learning_rate": 3.805544632324027e-05, "loss": 1.8523, "step": 364500 }, { "epoch": 2.39, "learning_rate": 3.803906147594705e-05, "loss": 1.8552, "step": 365000 }, { "epoch": 2.4, "learning_rate": 3.8022676628653825e-05, "loss": 1.8207, "step": 365500 }, { "epoch": 2.4, "learning_rate": 3.80062917813606e-05, "loss": 1.8496, "step": 366000 }, { "epoch": 2.4, "learning_rate": 3.7989906934067375e-05, "loss": 1.8246, "step": 366500 }, { "epoch": 2.41, "learning_rate": 3.797352208677415e-05, "loss": 1.8192, "step": 367000 }, { "epoch": 2.41, "learning_rate": 3.7957137239480925e-05, "loss": 1.848, "step": 367500 }, { "epoch": 2.41, "learning_rate": 3.79407523921877e-05, "loss": 1.8221, "step": 368000 }, { "epoch": 2.42, "learning_rate": 3.792436754489449e-05, "loss": 1.8342, "step": 368500 }, { "epoch": 2.42, "learning_rate": 3.790798269760126e-05, "loss": 1.85, "step": 369000 }, { "epoch": 2.42, "learning_rate": 3.789159785030804e-05, "loss": 1.8297, "step": 369500 }, { "epoch": 2.42, "learning_rate": 3.7875213003014816e-05, "loss": 1.8322, "step": 370000 }, { "epoch": 2.43, "learning_rate": 3.7858828155721594e-05, "loss": 1.7929, "step": 370500 }, { "epoch": 2.43, "learning_rate": 3.7842443308428365e-05, "loss": 1.8386, "step": 371000 }, { "epoch": 2.43, "learning_rate": 3.7826058461135143e-05, "loss": 1.8239, "step": 371500 }, { "epoch": 2.44, "learning_rate": 3.780967361384192e-05, "loss": 1.8269, "step": 372000 }, { "epoch": 2.44, "learning_rate": 3.779328876654869e-05, "loss": 1.8243, "step": 372500 }, { "epoch": 2.44, "learning_rate": 3.777690391925547e-05, "loss": 1.8025, "step": 373000 }, { "epoch": 2.45, "learning_rate": 3.776051907196225e-05, "loss": 1.8223, "step": 373500 }, { "epoch": 2.45, "learning_rate": 3.774413422466903e-05, "loss": 1.7803, "step": 374000 }, { "epoch": 2.45, "learning_rate": 3.7727749377375806e-05, "loss": 1.8362, "step": 374500 }, { "epoch": 2.46, "learning_rate": 3.7711364530082584e-05, "loss": 1.7842, "step": 375000 }, { "epoch": 2.46, "learning_rate": 3.769497968278936e-05, "loss": 1.8182, "step": 375500 }, { "epoch": 2.46, "learning_rate": 3.7678594835496134e-05, "loss": 1.7648, "step": 376000 }, { "epoch": 2.47, "learning_rate": 3.766220998820291e-05, "loss": 1.7973, "step": 376500 }, { "epoch": 2.47, "learning_rate": 3.764582514090969e-05, "loss": 1.8127, "step": 377000 }, { "epoch": 2.47, "learning_rate": 3.762944029361646e-05, "loss": 1.8066, "step": 377500 }, { "epoch": 2.48, "learning_rate": 3.761305544632324e-05, "loss": 1.8281, "step": 378000 }, { "epoch": 2.48, "learning_rate": 3.759667059903002e-05, "loss": 1.8037, "step": 378500 }, { "epoch": 2.48, "learning_rate": 3.7580285751736796e-05, "loss": 1.8348, "step": 379000 }, { "epoch": 2.49, "learning_rate": 3.7563900904443575e-05, "loss": 1.8217, "step": 379500 }, { "epoch": 2.49, "learning_rate": 3.754751605715035e-05, "loss": 1.7834, "step": 380000 }, { "epoch": 2.49, "learning_rate": 3.7531131209857124e-05, "loss": 1.8194, "step": 380500 }, { "epoch": 2.5, "learning_rate": 3.75147463625639e-05, "loss": 1.7992, "step": 381000 }, { "epoch": 2.5, "learning_rate": 3.749836151527068e-05, "loss": 1.8152, "step": 381500 }, { "epoch": 2.5, "learning_rate": 3.748197666797746e-05, "loss": 1.7908, "step": 382000 }, { "epoch": 2.51, "learning_rate": 3.746559182068423e-05, "loss": 1.7822, "step": 382500 }, { "epoch": 2.51, "learning_rate": 3.744920697339101e-05, "loss": 1.8028, "step": 383000 }, { "epoch": 2.51, "learning_rate": 3.743282212609779e-05, "loss": 1.8158, "step": 383500 }, { "epoch": 2.52, "learning_rate": 3.741643727880456e-05, "loss": 1.7704, "step": 384000 }, { "epoch": 2.52, "learning_rate": 3.740005243151134e-05, "loss": 1.7716, "step": 384500 }, { "epoch": 2.52, "learning_rate": 3.738366758421812e-05, "loss": 1.8556, "step": 385000 }, { "epoch": 2.53, "learning_rate": 3.736728273692489e-05, "loss": 1.8143, "step": 385500 }, { "epoch": 2.53, "learning_rate": 3.735089788963167e-05, "loss": 1.8055, "step": 386000 }, { "epoch": 2.53, "learning_rate": 3.733451304233845e-05, "loss": 1.7999, "step": 386500 }, { "epoch": 2.54, "learning_rate": 3.731812819504523e-05, "loss": 1.7878, "step": 387000 }, { "epoch": 2.54, "learning_rate": 3.7301743347752e-05, "loss": 1.7837, "step": 387500 }, { "epoch": 2.54, "learning_rate": 3.728535850045878e-05, "loss": 1.748, "step": 388000 }, { "epoch": 2.55, "learning_rate": 3.7268973653165555e-05, "loss": 1.7912, "step": 388500 }, { "epoch": 2.55, "learning_rate": 3.725258880587233e-05, "loss": 1.8096, "step": 389000 }, { "epoch": 2.55, "learning_rate": 3.7236203958579105e-05, "loss": 1.8591, "step": 389500 }, { "epoch": 2.56, "learning_rate": 3.721981911128588e-05, "loss": 1.7965, "step": 390000 }, { "epoch": 2.56, "learning_rate": 3.720343426399266e-05, "loss": 1.8203, "step": 390500 }, { "epoch": 2.56, "learning_rate": 3.718704941669944e-05, "loss": 1.8123, "step": 391000 }, { "epoch": 2.57, "learning_rate": 3.717066456940622e-05, "loss": 1.8197, "step": 391500 }, { "epoch": 2.57, "learning_rate": 3.715427972211299e-05, "loss": 1.7981, "step": 392000 }, { "epoch": 2.57, "learning_rate": 3.713789487481977e-05, "loss": 1.8235, "step": 392500 }, { "epoch": 2.58, "learning_rate": 3.7121510027526546e-05, "loss": 1.8286, "step": 393000 }, { "epoch": 2.58, "learning_rate": 3.7105125180233324e-05, "loss": 1.8121, "step": 393500 }, { "epoch": 2.58, "learning_rate": 3.7088740332940095e-05, "loss": 1.8203, "step": 394000 }, { "epoch": 2.59, "learning_rate": 3.7072355485646873e-05, "loss": 1.8078, "step": 394500 }, { "epoch": 2.59, "learning_rate": 3.705597063835365e-05, "loss": 1.8131, "step": 395000 }, { "epoch": 2.59, "learning_rate": 3.703958579106043e-05, "loss": 1.817, "step": 395500 }, { "epoch": 2.6, "learning_rate": 3.702320094376721e-05, "loss": 1.8051, "step": 396000 }, { "epoch": 2.6, "learning_rate": 3.7006816096473986e-05, "loss": 1.7823, "step": 396500 }, { "epoch": 2.6, "learning_rate": 3.699043124918076e-05, "loss": 1.7812, "step": 397000 }, { "epoch": 2.61, "learning_rate": 3.6974046401887536e-05, "loss": 1.796, "step": 397500 }, { "epoch": 2.61, "learning_rate": 3.6957661554594314e-05, "loss": 1.809, "step": 398000 }, { "epoch": 2.61, "learning_rate": 3.694127670730109e-05, "loss": 1.8312, "step": 398500 }, { "epoch": 2.62, "learning_rate": 3.6924891860007864e-05, "loss": 1.8046, "step": 399000 }, { "epoch": 2.62, "learning_rate": 3.690850701271464e-05, "loss": 1.8215, "step": 399500 }, { "epoch": 2.62, "learning_rate": 3.689212216542142e-05, "loss": 1.7835, "step": 400000 }, { "epoch": 2.62, "learning_rate": 3.687573731812819e-05, "loss": 1.7571, "step": 400500 }, { "epoch": 2.63, "learning_rate": 3.685935247083498e-05, "loss": 1.8263, "step": 401000 }, { "epoch": 2.63, "learning_rate": 3.6842967623541755e-05, "loss": 1.7631, "step": 401500 }, { "epoch": 2.63, "learning_rate": 3.6826582776248526e-05, "loss": 1.7853, "step": 402000 }, { "epoch": 2.64, "learning_rate": 3.6810197928955305e-05, "loss": 1.7796, "step": 402500 }, { "epoch": 2.64, "learning_rate": 3.679381308166208e-05, "loss": 1.7648, "step": 403000 }, { "epoch": 2.64, "learning_rate": 3.6777428234368854e-05, "loss": 1.7654, "step": 403500 }, { "epoch": 2.65, "learning_rate": 3.676104338707563e-05, "loss": 1.7841, "step": 404000 }, { "epoch": 2.65, "learning_rate": 3.674465853978241e-05, "loss": 1.7791, "step": 404500 }, { "epoch": 2.65, "learning_rate": 3.672827369248919e-05, "loss": 1.8306, "step": 405000 }, { "epoch": 2.66, "learning_rate": 3.671188884519596e-05, "loss": 1.7657, "step": 405500 }, { "epoch": 2.66, "learning_rate": 3.669550399790274e-05, "loss": 1.758, "step": 406000 }, { "epoch": 2.66, "learning_rate": 3.667911915060952e-05, "loss": 1.8041, "step": 406500 }, { "epoch": 2.67, "learning_rate": 3.6662734303316295e-05, "loss": 1.7977, "step": 407000 }, { "epoch": 2.67, "learning_rate": 3.664634945602307e-05, "loss": 1.7616, "step": 407500 }, { "epoch": 2.67, "learning_rate": 3.662996460872985e-05, "loss": 1.808, "step": 408000 }, { "epoch": 2.68, "learning_rate": 3.661357976143662e-05, "loss": 1.7864, "step": 408500 }, { "epoch": 2.68, "learning_rate": 3.65971949141434e-05, "loss": 1.7767, "step": 409000 }, { "epoch": 2.68, "learning_rate": 3.658081006685018e-05, "loss": 1.745, "step": 409500 }, { "epoch": 2.69, "learning_rate": 3.656442521955696e-05, "loss": 1.778, "step": 410000 }, { "epoch": 2.69, "learning_rate": 3.654804037226373e-05, "loss": 1.7937, "step": 410500 }, { "epoch": 2.69, "learning_rate": 3.653165552497051e-05, "loss": 1.769, "step": 411000 }, { "epoch": 2.7, "learning_rate": 3.6515270677677285e-05, "loss": 1.7995, "step": 411500 }, { "epoch": 2.7, "learning_rate": 3.6498885830384063e-05, "loss": 1.8033, "step": 412000 }, { "epoch": 2.7, "learning_rate": 3.648250098309084e-05, "loss": 1.7775, "step": 412500 }, { "epoch": 2.71, "learning_rate": 3.646611613579762e-05, "loss": 1.7735, "step": 413000 }, { "epoch": 2.71, "learning_rate": 3.644973128850439e-05, "loss": 1.7786, "step": 413500 }, { "epoch": 2.71, "learning_rate": 3.643334644121117e-05, "loss": 1.8041, "step": 414000 }, { "epoch": 2.72, "learning_rate": 3.641696159391795e-05, "loss": 1.8076, "step": 414500 }, { "epoch": 2.72, "learning_rate": 3.640057674662472e-05, "loss": 1.8171, "step": 415000 }, { "epoch": 2.72, "learning_rate": 3.63841918993315e-05, "loss": 1.7865, "step": 415500 }, { "epoch": 2.73, "learning_rate": 3.6367807052038276e-05, "loss": 1.7789, "step": 416000 }, { "epoch": 2.73, "learning_rate": 3.6351422204745054e-05, "loss": 1.827, "step": 416500 }, { "epoch": 2.73, "learning_rate": 3.633503735745183e-05, "loss": 1.7638, "step": 417000 }, { "epoch": 2.74, "learning_rate": 3.631865251015861e-05, "loss": 1.7942, "step": 417500 }, { "epoch": 2.74, "learning_rate": 3.630226766286539e-05, "loss": 1.7953, "step": 418000 }, { "epoch": 2.74, "learning_rate": 3.628588281557216e-05, "loss": 1.7785, "step": 418500 }, { "epoch": 2.75, "learning_rate": 3.626949796827894e-05, "loss": 1.7424, "step": 419000 }, { "epoch": 2.75, "learning_rate": 3.6253113120985716e-05, "loss": 1.7789, "step": 419500 }, { "epoch": 2.75, "learning_rate": 3.623672827369249e-05, "loss": 1.7597, "step": 420000 }, { "epoch": 2.76, "learning_rate": 3.6220343426399266e-05, "loss": 1.7853, "step": 420500 }, { "epoch": 2.76, "learning_rate": 3.6203958579106044e-05, "loss": 1.7693, "step": 421000 }, { "epoch": 2.76, "learning_rate": 3.618757373181282e-05, "loss": 1.7755, "step": 421500 }, { "epoch": 2.77, "learning_rate": 3.6171188884519594e-05, "loss": 1.762, "step": 422000 }, { "epoch": 2.77, "learning_rate": 3.615480403722637e-05, "loss": 1.7901, "step": 422500 }, { "epoch": 2.77, "learning_rate": 3.613841918993316e-05, "loss": 1.786, "step": 423000 }, { "epoch": 2.78, "learning_rate": 3.612203434263993e-05, "loss": 1.7941, "step": 423500 }, { "epoch": 2.78, "learning_rate": 3.610564949534671e-05, "loss": 1.7901, "step": 424000 }, { "epoch": 2.78, "learning_rate": 3.6089264648053485e-05, "loss": 1.7875, "step": 424500 }, { "epoch": 2.79, "learning_rate": 3.6072879800760256e-05, "loss": 1.7921, "step": 425000 }, { "epoch": 2.79, "learning_rate": 3.6056494953467035e-05, "loss": 1.748, "step": 425500 }, { "epoch": 2.79, "learning_rate": 3.604011010617381e-05, "loss": 1.7249, "step": 426000 }, { "epoch": 2.8, "learning_rate": 3.6023725258880584e-05, "loss": 1.7784, "step": 426500 }, { "epoch": 2.8, "learning_rate": 3.600734041158736e-05, "loss": 1.7795, "step": 427000 }, { "epoch": 2.8, "learning_rate": 3.599095556429414e-05, "loss": 1.7445, "step": 427500 }, { "epoch": 2.81, "learning_rate": 3.597457071700092e-05, "loss": 1.7704, "step": 428000 }, { "epoch": 2.81, "learning_rate": 3.59581858697077e-05, "loss": 1.8064, "step": 428500 }, { "epoch": 2.81, "learning_rate": 3.5941801022414475e-05, "loss": 1.7393, "step": 429000 }, { "epoch": 2.81, "learning_rate": 3.5925416175121253e-05, "loss": 1.7755, "step": 429500 }, { "epoch": 2.82, "learning_rate": 3.5909031327828025e-05, "loss": 1.7486, "step": 430000 }, { "epoch": 2.82, "learning_rate": 3.58926464805348e-05, "loss": 1.7799, "step": 430500 }, { "epoch": 2.82, "learning_rate": 3.587626163324158e-05, "loss": 1.7419, "step": 431000 }, { "epoch": 2.83, "learning_rate": 3.585987678594835e-05, "loss": 1.7835, "step": 431500 }, { "epoch": 2.83, "learning_rate": 3.584349193865513e-05, "loss": 1.7511, "step": 432000 }, { "epoch": 2.83, "learning_rate": 3.582710709136191e-05, "loss": 1.7887, "step": 432500 }, { "epoch": 2.84, "learning_rate": 3.581072224406869e-05, "loss": 1.7529, "step": 433000 }, { "epoch": 2.84, "learning_rate": 3.5794337396775466e-05, "loss": 1.8058, "step": 433500 }, { "epoch": 2.84, "learning_rate": 3.5777952549482244e-05, "loss": 1.762, "step": 434000 }, { "epoch": 2.85, "learning_rate": 3.576156770218902e-05, "loss": 1.7514, "step": 434500 }, { "epoch": 2.85, "learning_rate": 3.5745182854895793e-05, "loss": 1.7905, "step": 435000 }, { "epoch": 2.85, "learning_rate": 3.572879800760257e-05, "loss": 1.7452, "step": 435500 }, { "epoch": 2.86, "learning_rate": 3.571241316030935e-05, "loss": 1.7609, "step": 436000 }, { "epoch": 2.86, "learning_rate": 3.569602831301612e-05, "loss": 1.7428, "step": 436500 }, { "epoch": 2.86, "learning_rate": 3.56796434657229e-05, "loss": 1.7659, "step": 437000 }, { "epoch": 2.87, "learning_rate": 3.566325861842968e-05, "loss": 1.7108, "step": 437500 }, { "epoch": 2.87, "learning_rate": 3.564687377113645e-05, "loss": 1.7589, "step": 438000 }, { "epoch": 2.87, "learning_rate": 3.563048892384323e-05, "loss": 1.7366, "step": 438500 }, { "epoch": 2.88, "learning_rate": 3.5614104076550006e-05, "loss": 1.7468, "step": 439000 }, { "epoch": 2.88, "learning_rate": 3.559771922925679e-05, "loss": 1.7424, "step": 439500 }, { "epoch": 2.88, "learning_rate": 3.558133438196356e-05, "loss": 1.7494, "step": 440000 }, { "epoch": 2.89, "learning_rate": 3.556494953467034e-05, "loss": 1.7681, "step": 440500 }, { "epoch": 2.89, "learning_rate": 3.554856468737712e-05, "loss": 1.796, "step": 441000 }, { "epoch": 2.89, "learning_rate": 3.553217984008389e-05, "loss": 1.7367, "step": 441500 }, { "epoch": 2.9, "learning_rate": 3.551579499279067e-05, "loss": 1.7811, "step": 442000 }, { "epoch": 2.9, "learning_rate": 3.5499410145497446e-05, "loss": 1.7693, "step": 442500 }, { "epoch": 2.9, "learning_rate": 3.548302529820422e-05, "loss": 1.7743, "step": 443000 }, { "epoch": 2.91, "learning_rate": 3.5466640450910996e-05, "loss": 1.7457, "step": 443500 }, { "epoch": 2.91, "learning_rate": 3.5450255603617774e-05, "loss": 1.7371, "step": 444000 }, { "epoch": 2.91, "learning_rate": 3.543387075632455e-05, "loss": 1.7546, "step": 444500 }, { "epoch": 2.92, "learning_rate": 3.541748590903133e-05, "loss": 1.7865, "step": 445000 }, { "epoch": 2.92, "learning_rate": 3.540110106173811e-05, "loss": 1.7303, "step": 445500 }, { "epoch": 2.92, "learning_rate": 3.538471621444489e-05, "loss": 1.7348, "step": 446000 }, { "epoch": 2.93, "learning_rate": 3.536833136715166e-05, "loss": 1.7748, "step": 446500 }, { "epoch": 2.93, "learning_rate": 3.535194651985844e-05, "loss": 1.7374, "step": 447000 }, { "epoch": 2.93, "learning_rate": 3.5335561672565215e-05, "loss": 1.7599, "step": 447500 }, { "epoch": 2.94, "learning_rate": 3.5319176825271986e-05, "loss": 1.7388, "step": 448000 }, { "epoch": 2.94, "learning_rate": 3.5302791977978765e-05, "loss": 1.7739, "step": 448500 }, { "epoch": 2.94, "learning_rate": 3.528640713068554e-05, "loss": 1.8031, "step": 449000 }, { "epoch": 2.95, "learning_rate": 3.527002228339232e-05, "loss": 1.7347, "step": 449500 }, { "epoch": 2.95, "learning_rate": 3.52536374360991e-05, "loss": 1.752, "step": 450000 }, { "epoch": 2.95, "learning_rate": 3.523725258880588e-05, "loss": 1.7375, "step": 450500 }, { "epoch": 2.96, "learning_rate": 3.5220867741512656e-05, "loss": 1.7758, "step": 451000 }, { "epoch": 2.96, "learning_rate": 3.520448289421943e-05, "loss": 1.7387, "step": 451500 }, { "epoch": 2.96, "learning_rate": 3.5188098046926205e-05, "loss": 1.741, "step": 452000 }, { "epoch": 2.97, "learning_rate": 3.5171713199632983e-05, "loss": 1.7451, "step": 452500 }, { "epoch": 2.97, "learning_rate": 3.5155328352339755e-05, "loss": 1.7449, "step": 453000 }, { "epoch": 2.97, "learning_rate": 3.513894350504653e-05, "loss": 1.7559, "step": 453500 }, { "epoch": 2.98, "learning_rate": 3.512255865775331e-05, "loss": 1.7489, "step": 454000 }, { "epoch": 2.98, "learning_rate": 3.510617381046008e-05, "loss": 1.7499, "step": 454500 }, { "epoch": 2.98, "learning_rate": 3.508978896316686e-05, "loss": 1.7459, "step": 455000 }, { "epoch": 2.99, "learning_rate": 3.5073404115873646e-05, "loss": 1.7484, "step": 455500 }, { "epoch": 2.99, "learning_rate": 3.5057019268580424e-05, "loss": 1.7517, "step": 456000 }, { "epoch": 2.99, "learning_rate": 3.5040634421287196e-05, "loss": 1.7493, "step": 456500 }, { "epoch": 3.0, "learning_rate": 3.5024249573993974e-05, "loss": 1.7694, "step": 457000 }, { "epoch": 3.0, "learning_rate": 3.500786472670075e-05, "loss": 1.7367, "step": 457500 }, { "epoch": 3.0, "learning_rate": 3.4991479879407524e-05, "loss": 1.7385, "step": 458000 }, { "epoch": 3.0, "learning_rate": 3.49750950321143e-05, "loss": 1.7105, "step": 458500 }, { "epoch": 3.01, "learning_rate": 3.495871018482108e-05, "loss": 1.7496, "step": 459000 }, { "epoch": 3.01, "learning_rate": 3.494232533752785e-05, "loss": 1.7593, "step": 459500 }, { "epoch": 3.01, "learning_rate": 3.492594049023463e-05, "loss": 1.7289, "step": 460000 }, { "epoch": 3.02, "learning_rate": 3.490955564294141e-05, "loss": 1.7128, "step": 460500 }, { "epoch": 3.02, "learning_rate": 3.4893170795648186e-05, "loss": 1.7193, "step": 461000 }, { "epoch": 3.02, "learning_rate": 3.4876785948354964e-05, "loss": 1.709, "step": 461500 }, { "epoch": 3.03, "learning_rate": 3.486040110106174e-05, "loss": 1.7432, "step": 462000 }, { "epoch": 3.03, "learning_rate": 3.484401625376852e-05, "loss": 1.7497, "step": 462500 }, { "epoch": 3.03, "learning_rate": 3.482763140647529e-05, "loss": 1.6956, "step": 463000 }, { "epoch": 3.04, "learning_rate": 3.481124655918207e-05, "loss": 1.6699, "step": 463500 }, { "epoch": 3.04, "learning_rate": 3.479486171188885e-05, "loss": 1.7603, "step": 464000 }, { "epoch": 3.04, "learning_rate": 3.477847686459562e-05, "loss": 1.7567, "step": 464500 }, { "epoch": 3.05, "learning_rate": 3.47620920173024e-05, "loss": 1.7129, "step": 465000 }, { "epoch": 3.05, "learning_rate": 3.4745707170009176e-05, "loss": 1.7119, "step": 465500 }, { "epoch": 3.05, "learning_rate": 3.4729322322715955e-05, "loss": 1.7604, "step": 466000 }, { "epoch": 3.06, "learning_rate": 3.471293747542273e-05, "loss": 1.7388, "step": 466500 }, { "epoch": 3.06, "learning_rate": 3.469655262812951e-05, "loss": 1.7333, "step": 467000 }, { "epoch": 3.06, "learning_rate": 3.468016778083629e-05, "loss": 1.7099, "step": 467500 }, { "epoch": 3.07, "learning_rate": 3.466378293354306e-05, "loss": 1.7239, "step": 468000 }, { "epoch": 3.07, "learning_rate": 3.464739808624984e-05, "loss": 1.6958, "step": 468500 }, { "epoch": 3.07, "learning_rate": 3.463101323895662e-05, "loss": 1.7056, "step": 469000 }, { "epoch": 3.08, "learning_rate": 3.461462839166339e-05, "loss": 1.7156, "step": 469500 }, { "epoch": 3.08, "learning_rate": 3.459824354437017e-05, "loss": 1.6879, "step": 470000 }, { "epoch": 3.08, "learning_rate": 3.4581858697076945e-05, "loss": 1.7337, "step": 470500 }, { "epoch": 3.09, "learning_rate": 3.4565473849783716e-05, "loss": 1.7446, "step": 471000 }, { "epoch": 3.09, "learning_rate": 3.4549089002490495e-05, "loss": 1.7016, "step": 471500 }, { "epoch": 3.09, "learning_rate": 3.453270415519728e-05, "loss": 1.7137, "step": 472000 }, { "epoch": 3.1, "learning_rate": 3.451631930790405e-05, "loss": 1.7226, "step": 472500 }, { "epoch": 3.1, "learning_rate": 3.449993446061083e-05, "loss": 1.7148, "step": 473000 }, { "epoch": 3.1, "learning_rate": 3.448354961331761e-05, "loss": 1.7083, "step": 473500 }, { "epoch": 3.11, "learning_rate": 3.4467164766024386e-05, "loss": 1.7156, "step": 474000 }, { "epoch": 3.11, "learning_rate": 3.445077991873116e-05, "loss": 1.7119, "step": 474500 }, { "epoch": 3.11, "learning_rate": 3.4434395071437935e-05, "loss": 1.7337, "step": 475000 }, { "epoch": 3.12, "learning_rate": 3.4418010224144713e-05, "loss": 1.7217, "step": 475500 }, { "epoch": 3.12, "learning_rate": 3.4401625376851485e-05, "loss": 1.7038, "step": 476000 }, { "epoch": 3.12, "learning_rate": 3.438524052955826e-05, "loss": 1.7461, "step": 476500 }, { "epoch": 3.13, "learning_rate": 3.436885568226504e-05, "loss": 1.7043, "step": 477000 }, { "epoch": 3.13, "learning_rate": 3.435247083497182e-05, "loss": 1.725, "step": 477500 }, { "epoch": 3.13, "learning_rate": 3.43360859876786e-05, "loss": 1.7366, "step": 478000 }, { "epoch": 3.14, "learning_rate": 3.4319701140385376e-05, "loss": 1.7166, "step": 478500 }, { "epoch": 3.14, "learning_rate": 3.4303316293092154e-05, "loss": 1.7275, "step": 479000 }, { "epoch": 3.14, "learning_rate": 3.4286931445798926e-05, "loss": 1.7352, "step": 479500 }, { "epoch": 3.15, "learning_rate": 3.4270546598505704e-05, "loss": 1.7241, "step": 480000 }, { "epoch": 3.15, "learning_rate": 3.425416175121248e-05, "loss": 1.6828, "step": 480500 }, { "epoch": 3.15, "learning_rate": 3.4237776903919254e-05, "loss": 1.7276, "step": 481000 }, { "epoch": 3.16, "learning_rate": 3.422139205662603e-05, "loss": 1.6836, "step": 481500 }, { "epoch": 3.16, "learning_rate": 3.420500720933281e-05, "loss": 1.684, "step": 482000 }, { "epoch": 3.16, "learning_rate": 3.418862236203959e-05, "loss": 1.6933, "step": 482500 }, { "epoch": 3.17, "learning_rate": 3.4172237514746366e-05, "loss": 1.7195, "step": 483000 }, { "epoch": 3.17, "learning_rate": 3.4155852667453145e-05, "loss": 1.6831, "step": 483500 }, { "epoch": 3.17, "learning_rate": 3.413946782015992e-05, "loss": 1.7012, "step": 484000 }, { "epoch": 3.18, "learning_rate": 3.4123082972866694e-05, "loss": 1.7071, "step": 484500 }, { "epoch": 3.18, "learning_rate": 3.410669812557347e-05, "loss": 1.7151, "step": 485000 }, { "epoch": 3.18, "learning_rate": 3.409031327828025e-05, "loss": 1.6851, "step": 485500 }, { "epoch": 3.19, "learning_rate": 3.407392843098702e-05, "loss": 1.7126, "step": 486000 }, { "epoch": 3.19, "learning_rate": 3.40575435836938e-05, "loss": 1.7147, "step": 486500 }, { "epoch": 3.19, "learning_rate": 3.404115873640058e-05, "loss": 1.7061, "step": 487000 }, { "epoch": 3.2, "learning_rate": 3.402477388910735e-05, "loss": 1.6821, "step": 487500 }, { "epoch": 3.2, "learning_rate": 3.4008389041814135e-05, "loss": 1.6861, "step": 488000 }, { "epoch": 3.2, "learning_rate": 3.399200419452091e-05, "loss": 1.7535, "step": 488500 }, { "epoch": 3.2, "learning_rate": 3.3975619347227685e-05, "loss": 1.6879, "step": 489000 }, { "epoch": 3.21, "learning_rate": 3.395923449993446e-05, "loss": 1.7032, "step": 489500 }, { "epoch": 3.21, "learning_rate": 3.394284965264124e-05, "loss": 1.6739, "step": 490000 }, { "epoch": 3.21, "learning_rate": 3.392646480534802e-05, "loss": 1.6799, "step": 490500 }, { "epoch": 3.22, "learning_rate": 3.391007995805479e-05, "loss": 1.6946, "step": 491000 }, { "epoch": 3.22, "learning_rate": 3.389369511076157e-05, "loss": 1.6893, "step": 491500 }, { "epoch": 3.22, "learning_rate": 3.387731026346835e-05, "loss": 1.7095, "step": 492000 }, { "epoch": 3.23, "learning_rate": 3.386092541617512e-05, "loss": 1.6993, "step": 492500 }, { "epoch": 3.23, "learning_rate": 3.38445405688819e-05, "loss": 1.7053, "step": 493000 }, { "epoch": 3.23, "learning_rate": 3.3828155721588675e-05, "loss": 1.6555, "step": 493500 }, { "epoch": 3.24, "learning_rate": 3.381177087429545e-05, "loss": 1.7148, "step": 494000 }, { "epoch": 3.24, "learning_rate": 3.379538602700223e-05, "loss": 1.7247, "step": 494500 }, { "epoch": 3.24, "learning_rate": 3.377900117970901e-05, "loss": 1.6898, "step": 495000 }, { "epoch": 3.25, "learning_rate": 3.376261633241579e-05, "loss": 1.7192, "step": 495500 }, { "epoch": 3.25, "learning_rate": 3.374623148512256e-05, "loss": 1.7257, "step": 496000 }, { "epoch": 3.25, "learning_rate": 3.372984663782934e-05, "loss": 1.7248, "step": 496500 }, { "epoch": 3.26, "learning_rate": 3.3713461790536116e-05, "loss": 1.6814, "step": 497000 }, { "epoch": 3.26, "learning_rate": 3.369707694324289e-05, "loss": 1.6853, "step": 497500 }, { "epoch": 3.26, "learning_rate": 3.3680692095949665e-05, "loss": 1.7132, "step": 498000 }, { "epoch": 3.27, "learning_rate": 3.3664307248656444e-05, "loss": 1.6927, "step": 498500 }, { "epoch": 3.27, "learning_rate": 3.364792240136322e-05, "loss": 1.6775, "step": 499000 }, { "epoch": 3.27, "learning_rate": 3.363153755407e-05, "loss": 1.6894, "step": 499500 }, { "epoch": 3.28, "learning_rate": 3.361515270677678e-05, "loss": 1.6964, "step": 500000 }, { "epoch": 3.28, "learning_rate": 3.359876785948355e-05, "loss": 1.6801, "step": 500500 }, { "epoch": 3.28, "learning_rate": 3.358238301219033e-05, "loss": 1.7075, "step": 501000 }, { "epoch": 3.29, "learning_rate": 3.3565998164897106e-05, "loss": 1.6885, "step": 501500 }, { "epoch": 3.29, "learning_rate": 3.3549613317603884e-05, "loss": 1.701, "step": 502000 }, { "epoch": 3.29, "learning_rate": 3.3533228470310656e-05, "loss": 1.7093, "step": 502500 }, { "epoch": 3.3, "learning_rate": 3.3516843623017434e-05, "loss": 1.6962, "step": 503000 }, { "epoch": 3.3, "learning_rate": 3.350045877572421e-05, "loss": 1.7065, "step": 503500 }, { "epoch": 3.3, "learning_rate": 3.3484073928430984e-05, "loss": 1.6895, "step": 504000 }, { "epoch": 3.31, "learning_rate": 3.346768908113777e-05, "loss": 1.6696, "step": 504500 }, { "epoch": 3.31, "learning_rate": 3.345130423384455e-05, "loss": 1.7053, "step": 505000 }, { "epoch": 3.31, "learning_rate": 3.343491938655132e-05, "loss": 1.6895, "step": 505500 }, { "epoch": 3.32, "learning_rate": 3.3418534539258096e-05, "loss": 1.7054, "step": 506000 }, { "epoch": 3.32, "learning_rate": 3.3402149691964875e-05, "loss": 1.6367, "step": 506500 }, { "epoch": 3.32, "learning_rate": 3.338576484467165e-05, "loss": 1.7154, "step": 507000 }, { "epoch": 3.33, "learning_rate": 3.3369379997378424e-05, "loss": 1.7124, "step": 507500 }, { "epoch": 3.33, "learning_rate": 3.33529951500852e-05, "loss": 1.7233, "step": 508000 }, { "epoch": 3.33, "learning_rate": 3.333661030279198e-05, "loss": 1.7145, "step": 508500 }, { "epoch": 3.34, "learning_rate": 3.332022545549875e-05, "loss": 1.7272, "step": 509000 }, { "epoch": 3.34, "learning_rate": 3.330384060820553e-05, "loss": 1.6912, "step": 509500 }, { "epoch": 3.34, "learning_rate": 3.328745576091231e-05, "loss": 1.6985, "step": 510000 }, { "epoch": 3.35, "learning_rate": 3.327107091361909e-05, "loss": 1.7099, "step": 510500 }, { "epoch": 3.35, "learning_rate": 3.3254686066325865e-05, "loss": 1.6546, "step": 511000 }, { "epoch": 3.35, "learning_rate": 3.323830121903264e-05, "loss": 1.7075, "step": 511500 }, { "epoch": 3.36, "learning_rate": 3.3221916371739415e-05, "loss": 1.7114, "step": 512000 }, { "epoch": 3.36, "learning_rate": 3.320553152444619e-05, "loss": 1.6993, "step": 512500 }, { "epoch": 3.36, "learning_rate": 3.318914667715297e-05, "loss": 1.6812, "step": 513000 }, { "epoch": 3.37, "learning_rate": 3.317276182985975e-05, "loss": 1.6552, "step": 513500 }, { "epoch": 3.37, "learning_rate": 3.315637698256652e-05, "loss": 1.6522, "step": 514000 }, { "epoch": 3.37, "learning_rate": 3.31399921352733e-05, "loss": 1.6596, "step": 514500 }, { "epoch": 3.38, "learning_rate": 3.312360728798008e-05, "loss": 1.7068, "step": 515000 }, { "epoch": 3.38, "learning_rate": 3.3107222440686855e-05, "loss": 1.6845, "step": 515500 }, { "epoch": 3.38, "learning_rate": 3.3090837593393633e-05, "loss": 1.6684, "step": 516000 }, { "epoch": 3.39, "learning_rate": 3.307445274610041e-05, "loss": 1.6874, "step": 516500 }, { "epoch": 3.39, "learning_rate": 3.305806789880718e-05, "loss": 1.6643, "step": 517000 }, { "epoch": 3.39, "learning_rate": 3.304168305151396e-05, "loss": 1.7178, "step": 517500 }, { "epoch": 3.39, "learning_rate": 3.302529820422074e-05, "loss": 1.679, "step": 518000 }, { "epoch": 3.4, "learning_rate": 3.300891335692752e-05, "loss": 1.6668, "step": 518500 }, { "epoch": 3.4, "learning_rate": 3.299252850963429e-05, "loss": 1.6784, "step": 519000 }, { "epoch": 3.4, "learning_rate": 3.297614366234107e-05, "loss": 1.6928, "step": 519500 }, { "epoch": 3.41, "learning_rate": 3.2959758815047846e-05, "loss": 1.6563, "step": 520000 }, { "epoch": 3.41, "learning_rate": 3.2943373967754624e-05, "loss": 1.7028, "step": 520500 }, { "epoch": 3.41, "learning_rate": 3.29269891204614e-05, "loss": 1.6833, "step": 521000 }, { "epoch": 3.42, "learning_rate": 3.291060427316818e-05, "loss": 1.6829, "step": 521500 }, { "epoch": 3.42, "learning_rate": 3.289421942587495e-05, "loss": 1.6721, "step": 522000 }, { "epoch": 3.42, "learning_rate": 3.287783457858173e-05, "loss": 1.6827, "step": 522500 }, { "epoch": 3.43, "learning_rate": 3.286144973128851e-05, "loss": 1.6826, "step": 523000 }, { "epoch": 3.43, "learning_rate": 3.284506488399528e-05, "loss": 1.6407, "step": 523500 }, { "epoch": 3.43, "learning_rate": 3.282868003670206e-05, "loss": 1.7075, "step": 524000 }, { "epoch": 3.44, "learning_rate": 3.2812295189408836e-05, "loss": 1.6864, "step": 524500 }, { "epoch": 3.44, "learning_rate": 3.2795910342115614e-05, "loss": 1.6367, "step": 525000 }, { "epoch": 3.44, "learning_rate": 3.2779525494822386e-05, "loss": 1.6613, "step": 525500 }, { "epoch": 3.45, "learning_rate": 3.2763140647529164e-05, "loss": 1.6708, "step": 526000 }, { "epoch": 3.45, "learning_rate": 3.274675580023594e-05, "loss": 1.6339, "step": 526500 }, { "epoch": 3.45, "learning_rate": 3.273037095294272e-05, "loss": 1.6611, "step": 527000 }, { "epoch": 3.46, "learning_rate": 3.27139861056495e-05, "loss": 1.6813, "step": 527500 }, { "epoch": 3.46, "learning_rate": 3.269760125835628e-05, "loss": 1.6607, "step": 528000 }, { "epoch": 3.46, "learning_rate": 3.268121641106305e-05, "loss": 1.6709, "step": 528500 }, { "epoch": 3.47, "learning_rate": 3.2664831563769826e-05, "loss": 1.6842, "step": 529000 }, { "epoch": 3.47, "learning_rate": 3.2648446716476605e-05, "loss": 1.6691, "step": 529500 }, { "epoch": 3.47, "learning_rate": 3.263206186918338e-05, "loss": 1.6516, "step": 530000 }, { "epoch": 3.48, "learning_rate": 3.2615677021890154e-05, "loss": 1.668, "step": 530500 }, { "epoch": 3.48, "learning_rate": 3.259929217459693e-05, "loss": 1.6658, "step": 531000 }, { "epoch": 3.48, "learning_rate": 3.258290732730371e-05, "loss": 1.7045, "step": 531500 }, { "epoch": 3.49, "learning_rate": 3.256652248001049e-05, "loss": 1.6973, "step": 532000 }, { "epoch": 3.49, "learning_rate": 3.255013763271727e-05, "loss": 1.6833, "step": 532500 }, { "epoch": 3.49, "learning_rate": 3.2533752785424045e-05, "loss": 1.6538, "step": 533000 }, { "epoch": 3.5, "learning_rate": 3.251736793813082e-05, "loss": 1.6834, "step": 533500 }, { "epoch": 3.5, "learning_rate": 3.2500983090837595e-05, "loss": 1.6824, "step": 534000 }, { "epoch": 3.5, "learning_rate": 3.248459824354437e-05, "loss": 1.7013, "step": 534500 }, { "epoch": 3.51, "learning_rate": 3.2468213396251145e-05, "loss": 1.6814, "step": 535000 }, { "epoch": 3.51, "learning_rate": 3.245182854895792e-05, "loss": 1.6732, "step": 535500 }, { "epoch": 3.51, "learning_rate": 3.24354437016647e-05, "loss": 1.6899, "step": 536000 }, { "epoch": 3.52, "learning_rate": 3.241905885437148e-05, "loss": 1.7101, "step": 536500 }, { "epoch": 3.52, "learning_rate": 3.240267400707826e-05, "loss": 1.6874, "step": 537000 }, { "epoch": 3.52, "learning_rate": 3.2386289159785036e-05, "loss": 1.6796, "step": 537500 }, { "epoch": 3.53, "learning_rate": 3.2369904312491814e-05, "loss": 1.676, "step": 538000 }, { "epoch": 3.53, "learning_rate": 3.2353519465198585e-05, "loss": 1.6853, "step": 538500 }, { "epoch": 3.53, "learning_rate": 3.2337134617905364e-05, "loss": 1.6956, "step": 539000 }, { "epoch": 3.54, "learning_rate": 3.232074977061214e-05, "loss": 1.66, "step": 539500 }, { "epoch": 3.54, "learning_rate": 3.230436492331891e-05, "loss": 1.6773, "step": 540000 }, { "epoch": 3.54, "learning_rate": 3.228798007602569e-05, "loss": 1.6621, "step": 540500 }, { "epoch": 3.55, "learning_rate": 3.227159522873247e-05, "loss": 1.6384, "step": 541000 }, { "epoch": 3.55, "learning_rate": 3.225521038143925e-05, "loss": 1.6842, "step": 541500 }, { "epoch": 3.55, "learning_rate": 3.223882553414602e-05, "loss": 1.6741, "step": 542000 }, { "epoch": 3.56, "learning_rate": 3.22224406868528e-05, "loss": 1.6683, "step": 542500 }, { "epoch": 3.56, "learning_rate": 3.220605583955958e-05, "loss": 1.7014, "step": 543000 }, { "epoch": 3.56, "learning_rate": 3.2189670992266354e-05, "loss": 1.6593, "step": 543500 }, { "epoch": 3.57, "learning_rate": 3.217328614497313e-05, "loss": 1.6833, "step": 544000 }, { "epoch": 3.57, "learning_rate": 3.215690129767991e-05, "loss": 1.644, "step": 544500 }, { "epoch": 3.57, "learning_rate": 3.214051645038668e-05, "loss": 1.6769, "step": 545000 }, { "epoch": 3.58, "learning_rate": 3.212413160309346e-05, "loss": 1.6782, "step": 545500 }, { "epoch": 3.58, "learning_rate": 3.210774675580024e-05, "loss": 1.6538, "step": 546000 }, { "epoch": 3.58, "learning_rate": 3.209136190850701e-05, "loss": 1.6736, "step": 546500 }, { "epoch": 3.59, "learning_rate": 3.207497706121379e-05, "loss": 1.7024, "step": 547000 }, { "epoch": 3.59, "learning_rate": 3.2058592213920566e-05, "loss": 1.6669, "step": 547500 }, { "epoch": 3.59, "learning_rate": 3.2042207366627344e-05, "loss": 1.6476, "step": 548000 }, { "epoch": 3.59, "learning_rate": 3.202582251933412e-05, "loss": 1.6506, "step": 548500 }, { "epoch": 3.6, "learning_rate": 3.20094376720409e-05, "loss": 1.6818, "step": 549000 }, { "epoch": 3.6, "learning_rate": 3.199305282474768e-05, "loss": 1.6644, "step": 549500 }, { "epoch": 3.6, "learning_rate": 3.197666797745445e-05, "loss": 1.6469, "step": 550000 }, { "epoch": 3.61, "learning_rate": 3.196028313016123e-05, "loss": 1.6518, "step": 550500 }, { "epoch": 3.61, "learning_rate": 3.194389828286801e-05, "loss": 1.6466, "step": 551000 }, { "epoch": 3.61, "learning_rate": 3.192751343557478e-05, "loss": 1.6952, "step": 551500 }, { "epoch": 3.62, "learning_rate": 3.1911128588281556e-05, "loss": 1.6251, "step": 552000 }, { "epoch": 3.62, "learning_rate": 3.1894743740988335e-05, "loss": 1.6289, "step": 552500 }, { "epoch": 3.62, "learning_rate": 3.187835889369511e-05, "loss": 1.6941, "step": 553000 }, { "epoch": 3.63, "learning_rate": 3.186197404640189e-05, "loss": 1.6338, "step": 553500 }, { "epoch": 3.63, "learning_rate": 3.184558919910867e-05, "loss": 1.6788, "step": 554000 }, { "epoch": 3.63, "learning_rate": 3.182920435181545e-05, "loss": 1.6527, "step": 554500 }, { "epoch": 3.64, "learning_rate": 3.181281950452222e-05, "loss": 1.6584, "step": 555000 }, { "epoch": 3.64, "learning_rate": 3.1796434657229e-05, "loss": 1.6734, "step": 555500 }, { "epoch": 3.64, "learning_rate": 3.1780049809935775e-05, "loss": 1.6827, "step": 556000 }, { "epoch": 3.65, "learning_rate": 3.176366496264255e-05, "loss": 1.6649, "step": 556500 }, { "epoch": 3.65, "learning_rate": 3.1747280115349325e-05, "loss": 1.622, "step": 557000 }, { "epoch": 3.65, "learning_rate": 3.17308952680561e-05, "loss": 1.6376, "step": 557500 }, { "epoch": 3.66, "learning_rate": 3.1714510420762875e-05, "loss": 1.6668, "step": 558000 }, { "epoch": 3.66, "learning_rate": 3.169812557346965e-05, "loss": 1.6374, "step": 558500 }, { "epoch": 3.66, "learning_rate": 3.168174072617643e-05, "loss": 1.5976, "step": 559000 }, { "epoch": 3.67, "learning_rate": 3.1665355878883216e-05, "loss": 1.6802, "step": 559500 }, { "epoch": 3.67, "learning_rate": 3.164897103158999e-05, "loss": 1.6521, "step": 560000 }, { "epoch": 3.67, "learning_rate": 3.1632586184296766e-05, "loss": 1.6681, "step": 560500 }, { "epoch": 3.68, "learning_rate": 3.1616201337003544e-05, "loss": 1.679, "step": 561000 }, { "epoch": 3.68, "learning_rate": 3.1599816489710315e-05, "loss": 1.6325, "step": 561500 }, { "epoch": 3.68, "learning_rate": 3.1583431642417094e-05, "loss": 1.6355, "step": 562000 }, { "epoch": 3.69, "learning_rate": 3.156704679512387e-05, "loss": 1.6667, "step": 562500 }, { "epoch": 3.69, "learning_rate": 3.155066194783064e-05, "loss": 1.6495, "step": 563000 }, { "epoch": 3.69, "learning_rate": 3.153427710053742e-05, "loss": 1.6472, "step": 563500 }, { "epoch": 3.7, "learning_rate": 3.15178922532442e-05, "loss": 1.6648, "step": 564000 }, { "epoch": 3.7, "learning_rate": 3.150150740595098e-05, "loss": 1.6815, "step": 564500 }, { "epoch": 3.7, "learning_rate": 3.1485122558657756e-05, "loss": 1.6751, "step": 565000 }, { "epoch": 3.71, "learning_rate": 3.1468737711364534e-05, "loss": 1.7051, "step": 565500 }, { "epoch": 3.71, "learning_rate": 3.145235286407131e-05, "loss": 1.6596, "step": 566000 }, { "epoch": 3.71, "learning_rate": 3.1435968016778084e-05, "loss": 1.6655, "step": 566500 }, { "epoch": 3.72, "learning_rate": 3.141958316948486e-05, "loss": 1.6551, "step": 567000 }, { "epoch": 3.72, "learning_rate": 3.140319832219164e-05, "loss": 1.6184, "step": 567500 }, { "epoch": 3.72, "learning_rate": 3.138681347489841e-05, "loss": 1.632, "step": 568000 }, { "epoch": 3.73, "learning_rate": 3.137042862760519e-05, "loss": 1.644, "step": 568500 }, { "epoch": 3.73, "learning_rate": 3.135404378031197e-05, "loss": 1.6448, "step": 569000 }, { "epoch": 3.73, "learning_rate": 3.1337658933018746e-05, "loss": 1.663, "step": 569500 }, { "epoch": 3.74, "learning_rate": 3.1321274085725525e-05, "loss": 1.6415, "step": 570000 }, { "epoch": 3.74, "learning_rate": 3.13048892384323e-05, "loss": 1.6652, "step": 570500 }, { "epoch": 3.74, "learning_rate": 3.128850439113908e-05, "loss": 1.662, "step": 571000 }, { "epoch": 3.75, "learning_rate": 3.127211954384585e-05, "loss": 1.6398, "step": 571500 }, { "epoch": 3.75, "learning_rate": 3.125573469655263e-05, "loss": 1.6725, "step": 572000 }, { "epoch": 3.75, "learning_rate": 3.123934984925941e-05, "loss": 1.6996, "step": 572500 }, { "epoch": 3.76, "learning_rate": 3.122296500196618e-05, "loss": 1.6523, "step": 573000 }, { "epoch": 3.76, "learning_rate": 3.120658015467296e-05, "loss": 1.6852, "step": 573500 }, { "epoch": 3.76, "learning_rate": 3.119019530737974e-05, "loss": 1.655, "step": 574000 }, { "epoch": 3.77, "learning_rate": 3.117381046008651e-05, "loss": 1.6917, "step": 574500 }, { "epoch": 3.77, "learning_rate": 3.1157425612793286e-05, "loss": 1.6817, "step": 575000 }, { "epoch": 3.77, "learning_rate": 3.114104076550007e-05, "loss": 1.6599, "step": 575500 }, { "epoch": 3.78, "learning_rate": 3.112465591820685e-05, "loss": 1.6684, "step": 576000 }, { "epoch": 3.78, "learning_rate": 3.110827107091362e-05, "loss": 1.6492, "step": 576500 }, { "epoch": 3.78, "learning_rate": 3.10918862236204e-05, "loss": 1.6478, "step": 577000 }, { "epoch": 3.78, "learning_rate": 3.107550137632718e-05, "loss": 1.6659, "step": 577500 }, { "epoch": 3.79, "learning_rate": 3.105911652903395e-05, "loss": 1.6487, "step": 578000 }, { "epoch": 3.79, "learning_rate": 3.104273168174073e-05, "loss": 1.6637, "step": 578500 }, { "epoch": 3.79, "learning_rate": 3.1026346834447505e-05, "loss": 1.6682, "step": 579000 }, { "epoch": 3.8, "learning_rate": 3.100996198715428e-05, "loss": 1.6654, "step": 579500 }, { "epoch": 3.8, "learning_rate": 3.0993577139861055e-05, "loss": 1.6754, "step": 580000 }, { "epoch": 3.8, "learning_rate": 3.097719229256783e-05, "loss": 1.6518, "step": 580500 }, { "epoch": 3.81, "learning_rate": 3.096080744527461e-05, "loss": 1.6459, "step": 581000 }, { "epoch": 3.81, "learning_rate": 3.094442259798139e-05, "loss": 1.6474, "step": 581500 }, { "epoch": 3.81, "learning_rate": 3.092803775068817e-05, "loss": 1.6638, "step": 582000 }, { "epoch": 3.82, "learning_rate": 3.0911652903394946e-05, "loss": 1.6844, "step": 582500 }, { "epoch": 3.82, "learning_rate": 3.089526805610172e-05, "loss": 1.6288, "step": 583000 }, { "epoch": 3.82, "learning_rate": 3.0878883208808496e-05, "loss": 1.6177, "step": 583500 }, { "epoch": 3.83, "learning_rate": 3.0862498361515274e-05, "loss": 1.6511, "step": 584000 }, { "epoch": 3.83, "learning_rate": 3.0846113514222045e-05, "loss": 1.662, "step": 584500 }, { "epoch": 3.83, "learning_rate": 3.0829728666928824e-05, "loss": 1.6489, "step": 585000 }, { "epoch": 3.84, "learning_rate": 3.08133438196356e-05, "loss": 1.6209, "step": 585500 }, { "epoch": 3.84, "learning_rate": 3.079695897234238e-05, "loss": 1.6674, "step": 586000 }, { "epoch": 3.84, "learning_rate": 3.078057412504916e-05, "loss": 1.638, "step": 586500 }, { "epoch": 3.85, "learning_rate": 3.0764189277755936e-05, "loss": 1.628, "step": 587000 }, { "epoch": 3.85, "learning_rate": 3.0747804430462715e-05, "loss": 1.6359, "step": 587500 }, { "epoch": 3.85, "learning_rate": 3.0731419583169486e-05, "loss": 1.6, "step": 588000 }, { "epoch": 3.86, "learning_rate": 3.0715034735876264e-05, "loss": 1.6313, "step": 588500 }, { "epoch": 3.86, "learning_rate": 3.069864988858304e-05, "loss": 1.6414, "step": 589000 }, { "epoch": 3.86, "learning_rate": 3.0682265041289814e-05, "loss": 1.6432, "step": 589500 }, { "epoch": 3.87, "learning_rate": 3.066588019399659e-05, "loss": 1.6124, "step": 590000 }, { "epoch": 3.87, "learning_rate": 3.064949534670337e-05, "loss": 1.6527, "step": 590500 }, { "epoch": 3.87, "learning_rate": 3.063311049941014e-05, "loss": 1.6335, "step": 591000 }, { "epoch": 3.88, "learning_rate": 3.061672565211692e-05, "loss": 1.6819, "step": 591500 }, { "epoch": 3.88, "learning_rate": 3.0600340804823705e-05, "loss": 1.6002, "step": 592000 }, { "epoch": 3.88, "learning_rate": 3.0583955957530476e-05, "loss": 1.6634, "step": 592500 }, { "epoch": 3.89, "learning_rate": 3.0567571110237255e-05, "loss": 1.6271, "step": 593000 }, { "epoch": 3.89, "learning_rate": 3.055118626294403e-05, "loss": 1.6432, "step": 593500 }, { "epoch": 3.89, "learning_rate": 3.053480141565081e-05, "loss": 1.6598, "step": 594000 }, { "epoch": 3.9, "learning_rate": 3.051841656835758e-05, "loss": 1.6347, "step": 594500 }, { "epoch": 3.9, "learning_rate": 3.050203172106436e-05, "loss": 1.6215, "step": 595000 }, { "epoch": 3.9, "learning_rate": 3.048564687377114e-05, "loss": 1.626, "step": 595500 }, { "epoch": 3.91, "learning_rate": 3.0469262026477914e-05, "loss": 1.6111, "step": 596000 }, { "epoch": 3.91, "learning_rate": 3.0452877179184692e-05, "loss": 1.6378, "step": 596500 }, { "epoch": 3.91, "learning_rate": 3.043649233189147e-05, "loss": 1.6389, "step": 597000 }, { "epoch": 3.92, "learning_rate": 3.042010748459824e-05, "loss": 1.6451, "step": 597500 }, { "epoch": 3.92, "learning_rate": 3.040372263730502e-05, "loss": 1.6539, "step": 598000 }, { "epoch": 3.92, "learning_rate": 3.0387337790011798e-05, "loss": 1.6397, "step": 598500 }, { "epoch": 3.93, "learning_rate": 3.037095294271858e-05, "loss": 1.6477, "step": 599000 }, { "epoch": 3.93, "learning_rate": 3.035456809542535e-05, "loss": 1.6683, "step": 599500 }, { "epoch": 3.93, "learning_rate": 3.033818324813213e-05, "loss": 1.6573, "step": 600000 }, { "epoch": 3.94, "learning_rate": 3.0321798400838907e-05, "loss": 1.6221, "step": 600500 }, { "epoch": 3.94, "learning_rate": 3.0305413553545682e-05, "loss": 1.6319, "step": 601000 }, { "epoch": 3.94, "learning_rate": 3.028902870625246e-05, "loss": 1.6417, "step": 601500 }, { "epoch": 3.95, "learning_rate": 3.027264385895924e-05, "loss": 1.6525, "step": 602000 }, { "epoch": 3.95, "learning_rate": 3.025625901166601e-05, "loss": 1.6513, "step": 602500 }, { "epoch": 3.95, "learning_rate": 3.023987416437279e-05, "loss": 1.6524, "step": 603000 }, { "epoch": 3.96, "learning_rate": 3.0223489317079567e-05, "loss": 1.6137, "step": 603500 }, { "epoch": 3.96, "learning_rate": 3.020710446978634e-05, "loss": 1.6487, "step": 604000 }, { "epoch": 3.96, "learning_rate": 3.019071962249312e-05, "loss": 1.6207, "step": 604500 }, { "epoch": 3.97, "learning_rate": 3.0174334775199898e-05, "loss": 1.6519, "step": 605000 }, { "epoch": 3.97, "learning_rate": 3.0157949927906676e-05, "loss": 1.6464, "step": 605500 }, { "epoch": 3.97, "learning_rate": 3.0141565080613447e-05, "loss": 1.6461, "step": 606000 }, { "epoch": 3.97, "learning_rate": 3.0125180233320226e-05, "loss": 1.6519, "step": 606500 }, { "epoch": 3.98, "learning_rate": 3.0108795386027004e-05, "loss": 1.6451, "step": 607000 }, { "epoch": 3.98, "learning_rate": 3.009241053873378e-05, "loss": 1.6346, "step": 607500 }, { "epoch": 3.98, "learning_rate": 3.0076025691440557e-05, "loss": 1.616, "step": 608000 }, { "epoch": 3.99, "learning_rate": 3.0059640844147335e-05, "loss": 1.6521, "step": 608500 }, { "epoch": 3.99, "learning_rate": 3.004325599685411e-05, "loss": 1.6587, "step": 609000 }, { "epoch": 3.99, "learning_rate": 3.0026871149560888e-05, "loss": 1.661, "step": 609500 }, { "epoch": 4.0, "learning_rate": 3.0010486302267666e-05, "loss": 1.6484, "step": 610000 }, { "epoch": 4.0, "learning_rate": 2.9994101454974445e-05, "loss": 1.6421, "step": 610500 }, { "epoch": 4.0, "learning_rate": 2.9977716607681216e-05, "loss": 1.6069, "step": 611000 }, { "epoch": 4.01, "learning_rate": 2.9961331760387994e-05, "loss": 1.6015, "step": 611500 }, { "epoch": 4.01, "learning_rate": 2.9944946913094772e-05, "loss": 1.6337, "step": 612000 }, { "epoch": 4.01, "learning_rate": 2.9928562065801547e-05, "loss": 1.5906, "step": 612500 }, { "epoch": 4.02, "learning_rate": 2.9912177218508325e-05, "loss": 1.6301, "step": 613000 }, { "epoch": 4.02, "learning_rate": 2.9895792371215104e-05, "loss": 1.5727, "step": 613500 }, { "epoch": 4.02, "learning_rate": 2.9879407523921875e-05, "loss": 1.5994, "step": 614000 }, { "epoch": 4.03, "learning_rate": 2.9863022676628653e-05, "loss": 1.6106, "step": 614500 }, { "epoch": 4.03, "learning_rate": 2.984663782933543e-05, "loss": 1.59, "step": 615000 }, { "epoch": 4.03, "learning_rate": 2.9830252982042206e-05, "loss": 1.626, "step": 615500 }, { "epoch": 4.04, "learning_rate": 2.9813868134748985e-05, "loss": 1.5846, "step": 616000 }, { "epoch": 4.04, "learning_rate": 2.9797483287455763e-05, "loss": 1.6175, "step": 616500 }, { "epoch": 4.04, "learning_rate": 2.978109844016254e-05, "loss": 1.6276, "step": 617000 }, { "epoch": 4.05, "learning_rate": 2.9764713592869316e-05, "loss": 1.6436, "step": 617500 }, { "epoch": 4.05, "learning_rate": 2.9748328745576094e-05, "loss": 1.608, "step": 618000 }, { "epoch": 4.05, "learning_rate": 2.9731943898282872e-05, "loss": 1.6021, "step": 618500 }, { "epoch": 4.06, "learning_rate": 2.9715559050989644e-05, "loss": 1.5836, "step": 619000 }, { "epoch": 4.06, "learning_rate": 2.9699174203696422e-05, "loss": 1.5883, "step": 619500 }, { "epoch": 4.06, "learning_rate": 2.96827893564032e-05, "loss": 1.6205, "step": 620000 }, { "epoch": 4.07, "learning_rate": 2.9666404509109975e-05, "loss": 1.5798, "step": 620500 }, { "epoch": 4.07, "learning_rate": 2.9650019661816753e-05, "loss": 1.6262, "step": 621000 }, { "epoch": 4.07, "learning_rate": 2.963363481452353e-05, "loss": 1.6057, "step": 621500 }, { "epoch": 4.08, "learning_rate": 2.961724996723031e-05, "loss": 1.6349, "step": 622000 }, { "epoch": 4.08, "learning_rate": 2.960086511993708e-05, "loss": 1.5904, "step": 622500 }, { "epoch": 4.08, "learning_rate": 2.958448027264386e-05, "loss": 1.6106, "step": 623000 }, { "epoch": 4.09, "learning_rate": 2.956809542535064e-05, "loss": 1.6033, "step": 623500 }, { "epoch": 4.09, "learning_rate": 2.9551710578057412e-05, "loss": 1.6135, "step": 624000 }, { "epoch": 4.09, "learning_rate": 2.953532573076419e-05, "loss": 1.6232, "step": 624500 }, { "epoch": 4.1, "learning_rate": 2.951894088347097e-05, "loss": 1.596, "step": 625000 }, { "epoch": 4.1, "learning_rate": 2.9502556036177744e-05, "loss": 1.6144, "step": 625500 }, { "epoch": 4.1, "learning_rate": 2.9486171188884522e-05, "loss": 1.5901, "step": 626000 }, { "epoch": 4.11, "learning_rate": 2.94697863415913e-05, "loss": 1.6027, "step": 626500 }, { "epoch": 4.11, "learning_rate": 2.945340149429807e-05, "loss": 1.5874, "step": 627000 }, { "epoch": 4.11, "learning_rate": 2.943701664700485e-05, "loss": 1.6218, "step": 627500 }, { "epoch": 4.12, "learning_rate": 2.9420631799711628e-05, "loss": 1.6269, "step": 628000 }, { "epoch": 4.12, "learning_rate": 2.9404246952418406e-05, "loss": 1.6039, "step": 628500 }, { "epoch": 4.12, "learning_rate": 2.938786210512518e-05, "loss": 1.6023, "step": 629000 }, { "epoch": 4.13, "learning_rate": 2.937147725783196e-05, "loss": 1.6203, "step": 629500 }, { "epoch": 4.13, "learning_rate": 2.9355092410538737e-05, "loss": 1.6297, "step": 630000 }, { "epoch": 4.13, "learning_rate": 2.933870756324551e-05, "loss": 1.6194, "step": 630500 }, { "epoch": 4.14, "learning_rate": 2.9322322715952287e-05, "loss": 1.6064, "step": 631000 }, { "epoch": 4.14, "learning_rate": 2.930593786865907e-05, "loss": 1.6222, "step": 631500 }, { "epoch": 4.14, "learning_rate": 2.928955302136584e-05, "loss": 1.6441, "step": 632000 }, { "epoch": 4.15, "learning_rate": 2.9273168174072618e-05, "loss": 1.6251, "step": 632500 }, { "epoch": 4.15, "learning_rate": 2.9256783326779396e-05, "loss": 1.6001, "step": 633000 }, { "epoch": 4.15, "learning_rate": 2.9240398479486175e-05, "loss": 1.6092, "step": 633500 }, { "epoch": 4.16, "learning_rate": 2.922401363219295e-05, "loss": 1.6248, "step": 634000 }, { "epoch": 4.16, "learning_rate": 2.9207628784899728e-05, "loss": 1.6229, "step": 634500 }, { "epoch": 4.16, "learning_rate": 2.9191243937606506e-05, "loss": 1.5711, "step": 635000 }, { "epoch": 4.17, "learning_rate": 2.9174859090313277e-05, "loss": 1.6036, "step": 635500 }, { "epoch": 4.17, "learning_rate": 2.9158474243020055e-05, "loss": 1.5931, "step": 636000 }, { "epoch": 4.17, "learning_rate": 2.9142089395726834e-05, "loss": 1.6267, "step": 636500 }, { "epoch": 4.17, "learning_rate": 2.912570454843361e-05, "loss": 1.6174, "step": 637000 }, { "epoch": 4.18, "learning_rate": 2.9109319701140387e-05, "loss": 1.6141, "step": 637500 }, { "epoch": 4.18, "learning_rate": 2.9092934853847165e-05, "loss": 1.6127, "step": 638000 }, { "epoch": 4.18, "learning_rate": 2.9076550006553936e-05, "loss": 1.612, "step": 638500 }, { "epoch": 4.19, "learning_rate": 2.9060165159260715e-05, "loss": 1.5836, "step": 639000 }, { "epoch": 4.19, "learning_rate": 2.9043780311967496e-05, "loss": 1.6083, "step": 639500 }, { "epoch": 4.19, "learning_rate": 2.9027395464674274e-05, "loss": 1.5401, "step": 640000 }, { "epoch": 4.2, "learning_rate": 2.9011010617381046e-05, "loss": 1.5761, "step": 640500 }, { "epoch": 4.2, "learning_rate": 2.8994625770087824e-05, "loss": 1.5742, "step": 641000 }, { "epoch": 4.2, "learning_rate": 2.8978240922794602e-05, "loss": 1.6362, "step": 641500 }, { "epoch": 4.21, "learning_rate": 2.8961856075501377e-05, "loss": 1.5842, "step": 642000 }, { "epoch": 4.21, "learning_rate": 2.8945471228208155e-05, "loss": 1.5992, "step": 642500 }, { "epoch": 4.21, "learning_rate": 2.8929086380914934e-05, "loss": 1.5929, "step": 643000 }, { "epoch": 4.22, "learning_rate": 2.8912701533621705e-05, "loss": 1.5754, "step": 643500 }, { "epoch": 4.22, "learning_rate": 2.8896316686328483e-05, "loss": 1.5847, "step": 644000 }, { "epoch": 4.22, "learning_rate": 2.887993183903526e-05, "loss": 1.6309, "step": 644500 }, { "epoch": 4.23, "learning_rate": 2.886354699174204e-05, "loss": 1.6078, "step": 645000 }, { "epoch": 4.23, "learning_rate": 2.8847162144448814e-05, "loss": 1.6173, "step": 645500 }, { "epoch": 4.23, "learning_rate": 2.8830777297155593e-05, "loss": 1.6248, "step": 646000 }, { "epoch": 4.24, "learning_rate": 2.881439244986237e-05, "loss": 1.6078, "step": 646500 }, { "epoch": 4.24, "learning_rate": 2.8798007602569142e-05, "loss": 1.5948, "step": 647000 }, { "epoch": 4.24, "learning_rate": 2.878162275527592e-05, "loss": 1.633, "step": 647500 }, { "epoch": 4.25, "learning_rate": 2.8765237907982702e-05, "loss": 1.5573, "step": 648000 }, { "epoch": 4.25, "learning_rate": 2.8748853060689474e-05, "loss": 1.6042, "step": 648500 }, { "epoch": 4.25, "learning_rate": 2.8732468213396252e-05, "loss": 1.6028, "step": 649000 }, { "epoch": 4.26, "learning_rate": 2.871608336610303e-05, "loss": 1.5859, "step": 649500 }, { "epoch": 4.26, "learning_rate": 2.8699698518809805e-05, "loss": 1.5955, "step": 650000 }, { "epoch": 4.26, "learning_rate": 2.8683313671516583e-05, "loss": 1.6427, "step": 650500 }, { "epoch": 4.27, "learning_rate": 2.866692882422336e-05, "loss": 1.5914, "step": 651000 }, { "epoch": 4.27, "learning_rate": 2.865054397693014e-05, "loss": 1.5965, "step": 651500 }, { "epoch": 4.27, "learning_rate": 2.863415912963691e-05, "loss": 1.5887, "step": 652000 }, { "epoch": 4.28, "learning_rate": 2.861777428234369e-05, "loss": 1.5775, "step": 652500 }, { "epoch": 4.28, "learning_rate": 2.8601389435050467e-05, "loss": 1.5827, "step": 653000 }, { "epoch": 4.28, "learning_rate": 2.8585004587757242e-05, "loss": 1.5902, "step": 653500 }, { "epoch": 4.29, "learning_rate": 2.856861974046402e-05, "loss": 1.6027, "step": 654000 }, { "epoch": 4.29, "learning_rate": 2.85522348931708e-05, "loss": 1.6045, "step": 654500 }, { "epoch": 4.29, "learning_rate": 2.853585004587757e-05, "loss": 1.6012, "step": 655000 }, { "epoch": 4.3, "learning_rate": 2.8519465198584348e-05, "loss": 1.6173, "step": 655500 }, { "epoch": 4.3, "learning_rate": 2.850308035129113e-05, "loss": 1.6578, "step": 656000 }, { "epoch": 4.3, "learning_rate": 2.8486695503997908e-05, "loss": 1.6138, "step": 656500 }, { "epoch": 4.31, "learning_rate": 2.847031065670468e-05, "loss": 1.5812, "step": 657000 }, { "epoch": 4.31, "learning_rate": 2.8453925809411458e-05, "loss": 1.6029, "step": 657500 }, { "epoch": 4.31, "learning_rate": 2.8437540962118236e-05, "loss": 1.5893, "step": 658000 }, { "epoch": 4.32, "learning_rate": 2.842115611482501e-05, "loss": 1.6228, "step": 658500 }, { "epoch": 4.32, "learning_rate": 2.840477126753179e-05, "loss": 1.6009, "step": 659000 }, { "epoch": 4.32, "learning_rate": 2.8388386420238567e-05, "loss": 1.5998, "step": 659500 }, { "epoch": 4.33, "learning_rate": 2.837200157294534e-05, "loss": 1.5759, "step": 660000 }, { "epoch": 4.33, "learning_rate": 2.8355616725652117e-05, "loss": 1.5773, "step": 660500 }, { "epoch": 4.33, "learning_rate": 2.8339231878358895e-05, "loss": 1.6169, "step": 661000 }, { "epoch": 4.34, "learning_rate": 2.832284703106567e-05, "loss": 1.5665, "step": 661500 }, { "epoch": 4.34, "learning_rate": 2.8306462183772448e-05, "loss": 1.6392, "step": 662000 }, { "epoch": 4.34, "learning_rate": 2.8290077336479226e-05, "loss": 1.6303, "step": 662500 }, { "epoch": 4.35, "learning_rate": 2.8273692489186004e-05, "loss": 1.6092, "step": 663000 }, { "epoch": 4.35, "learning_rate": 2.8257307641892776e-05, "loss": 1.6027, "step": 663500 }, { "epoch": 4.35, "learning_rate": 2.8240922794599557e-05, "loss": 1.5965, "step": 664000 }, { "epoch": 4.36, "learning_rate": 2.8224537947306336e-05, "loss": 1.5818, "step": 664500 }, { "epoch": 4.36, "learning_rate": 2.8208153100013107e-05, "loss": 1.6677, "step": 665000 }, { "epoch": 4.36, "learning_rate": 2.8191768252719885e-05, "loss": 1.6248, "step": 665500 }, { "epoch": 4.36, "learning_rate": 2.8175383405426664e-05, "loss": 1.6012, "step": 666000 }, { "epoch": 4.37, "learning_rate": 2.815899855813344e-05, "loss": 1.604, "step": 666500 }, { "epoch": 4.37, "learning_rate": 2.8142613710840217e-05, "loss": 1.6286, "step": 667000 }, { "epoch": 4.37, "learning_rate": 2.8126228863546995e-05, "loss": 1.5773, "step": 667500 }, { "epoch": 4.38, "learning_rate": 2.8109844016253773e-05, "loss": 1.6047, "step": 668000 }, { "epoch": 4.38, "learning_rate": 2.8093459168960544e-05, "loss": 1.6308, "step": 668500 }, { "epoch": 4.38, "learning_rate": 2.8077074321667323e-05, "loss": 1.5815, "step": 669000 }, { "epoch": 4.39, "learning_rate": 2.80606894743741e-05, "loss": 1.5851, "step": 669500 }, { "epoch": 4.39, "learning_rate": 2.8044304627080876e-05, "loss": 1.5674, "step": 670000 }, { "epoch": 4.39, "learning_rate": 2.8027919779787654e-05, "loss": 1.6056, "step": 670500 }, { "epoch": 4.4, "learning_rate": 2.8011534932494432e-05, "loss": 1.5953, "step": 671000 }, { "epoch": 4.4, "learning_rate": 2.7995150085201204e-05, "loss": 1.5603, "step": 671500 }, { "epoch": 4.4, "learning_rate": 2.7978765237907985e-05, "loss": 1.5855, "step": 672000 }, { "epoch": 4.41, "learning_rate": 2.7962380390614763e-05, "loss": 1.6094, "step": 672500 }, { "epoch": 4.41, "learning_rate": 2.794599554332154e-05, "loss": 1.59, "step": 673000 }, { "epoch": 4.41, "learning_rate": 2.7929610696028313e-05, "loss": 1.5786, "step": 673500 }, { "epoch": 4.42, "learning_rate": 2.791322584873509e-05, "loss": 1.5974, "step": 674000 }, { "epoch": 4.42, "learning_rate": 2.789684100144187e-05, "loss": 1.5815, "step": 674500 }, { "epoch": 4.42, "learning_rate": 2.7880456154148644e-05, "loss": 1.5951, "step": 675000 }, { "epoch": 4.43, "learning_rate": 2.7864071306855422e-05, "loss": 1.6037, "step": 675500 }, { "epoch": 4.43, "learning_rate": 2.78476864595622e-05, "loss": 1.6154, "step": 676000 }, { "epoch": 4.43, "learning_rate": 2.7831301612268972e-05, "loss": 1.5895, "step": 676500 }, { "epoch": 4.44, "learning_rate": 2.781491676497575e-05, "loss": 1.5823, "step": 677000 }, { "epoch": 4.44, "learning_rate": 2.779853191768253e-05, "loss": 1.589, "step": 677500 }, { "epoch": 4.44, "learning_rate": 2.7782147070389303e-05, "loss": 1.5976, "step": 678000 }, { "epoch": 4.45, "learning_rate": 2.776576222309608e-05, "loss": 1.5882, "step": 678500 }, { "epoch": 4.45, "learning_rate": 2.774937737580286e-05, "loss": 1.606, "step": 679000 }, { "epoch": 4.45, "learning_rate": 2.7732992528509638e-05, "loss": 1.5907, "step": 679500 }, { "epoch": 4.46, "learning_rate": 2.771660768121641e-05, "loss": 1.597, "step": 680000 }, { "epoch": 4.46, "learning_rate": 2.770022283392319e-05, "loss": 1.628, "step": 680500 }, { "epoch": 4.46, "learning_rate": 2.768383798662997e-05, "loss": 1.5911, "step": 681000 }, { "epoch": 4.47, "learning_rate": 2.766745313933674e-05, "loss": 1.6432, "step": 681500 }, { "epoch": 4.47, "learning_rate": 2.765106829204352e-05, "loss": 1.5957, "step": 682000 }, { "epoch": 4.47, "learning_rate": 2.7634683444750297e-05, "loss": 1.6163, "step": 682500 }, { "epoch": 4.48, "learning_rate": 2.7618298597457072e-05, "loss": 1.6107, "step": 683000 }, { "epoch": 4.48, "learning_rate": 2.760191375016385e-05, "loss": 1.5862, "step": 683500 }, { "epoch": 4.48, "learning_rate": 2.758552890287063e-05, "loss": 1.5876, "step": 684000 }, { "epoch": 4.49, "learning_rate": 2.7569144055577407e-05, "loss": 1.5656, "step": 684500 }, { "epoch": 4.49, "learning_rate": 2.7552759208284178e-05, "loss": 1.6196, "step": 685000 }, { "epoch": 4.49, "learning_rate": 2.7536374360990956e-05, "loss": 1.618, "step": 685500 }, { "epoch": 4.5, "learning_rate": 2.7519989513697734e-05, "loss": 1.5665, "step": 686000 }, { "epoch": 4.5, "learning_rate": 2.750360466640451e-05, "loss": 1.6042, "step": 686500 }, { "epoch": 4.5, "learning_rate": 2.7487219819111287e-05, "loss": 1.5825, "step": 687000 }, { "epoch": 4.51, "learning_rate": 2.7470834971818066e-05, "loss": 1.5854, "step": 687500 }, { "epoch": 4.51, "learning_rate": 2.7454450124524837e-05, "loss": 1.5704, "step": 688000 }, { "epoch": 4.51, "learning_rate": 2.743806527723162e-05, "loss": 1.5956, "step": 688500 }, { "epoch": 4.52, "learning_rate": 2.7421680429938397e-05, "loss": 1.5897, "step": 689000 }, { "epoch": 4.52, "learning_rate": 2.740529558264517e-05, "loss": 1.5646, "step": 689500 }, { "epoch": 4.52, "learning_rate": 2.7388910735351947e-05, "loss": 1.5655, "step": 690000 }, { "epoch": 4.53, "learning_rate": 2.7372525888058725e-05, "loss": 1.5892, "step": 690500 }, { "epoch": 4.53, "learning_rate": 2.7356141040765503e-05, "loss": 1.6187, "step": 691000 }, { "epoch": 4.53, "learning_rate": 2.7339756193472278e-05, "loss": 1.5821, "step": 691500 }, { "epoch": 4.54, "learning_rate": 2.7323371346179056e-05, "loss": 1.5845, "step": 692000 }, { "epoch": 4.54, "learning_rate": 2.7306986498885834e-05, "loss": 1.6016, "step": 692500 }, { "epoch": 4.54, "learning_rate": 2.7290601651592606e-05, "loss": 1.5713, "step": 693000 }, { "epoch": 4.55, "learning_rate": 2.7274216804299384e-05, "loss": 1.6007, "step": 693500 }, { "epoch": 4.55, "learning_rate": 2.7257831957006162e-05, "loss": 1.6018, "step": 694000 }, { "epoch": 4.55, "learning_rate": 2.7241447109712937e-05, "loss": 1.5718, "step": 694500 }, { "epoch": 4.55, "learning_rate": 2.7225062262419715e-05, "loss": 1.6022, "step": 695000 }, { "epoch": 4.56, "learning_rate": 2.7208677415126493e-05, "loss": 1.5779, "step": 695500 }, { "epoch": 4.56, "learning_rate": 2.719229256783327e-05, "loss": 1.5525, "step": 696000 }, { "epoch": 4.56, "learning_rate": 2.7175907720540046e-05, "loss": 1.6077, "step": 696500 }, { "epoch": 4.57, "learning_rate": 2.7159522873246825e-05, "loss": 1.6062, "step": 697000 }, { "epoch": 4.57, "learning_rate": 2.7143138025953603e-05, "loss": 1.5901, "step": 697500 }, { "epoch": 4.57, "learning_rate": 2.7126753178660374e-05, "loss": 1.5671, "step": 698000 }, { "epoch": 4.58, "learning_rate": 2.7110368331367152e-05, "loss": 1.6328, "step": 698500 }, { "epoch": 4.58, "learning_rate": 2.709398348407393e-05, "loss": 1.5538, "step": 699000 }, { "epoch": 4.58, "learning_rate": 2.7077598636780705e-05, "loss": 1.6142, "step": 699500 }, { "epoch": 4.59, "learning_rate": 2.7061213789487484e-05, "loss": 1.5975, "step": 700000 }, { "epoch": 4.59, "learning_rate": 2.7044828942194262e-05, "loss": 1.5696, "step": 700500 }, { "epoch": 4.59, "learning_rate": 2.7028444094901033e-05, "loss": 1.5841, "step": 701000 }, { "epoch": 4.6, "learning_rate": 2.701205924760781e-05, "loss": 1.5738, "step": 701500 }, { "epoch": 4.6, "learning_rate": 2.699567440031459e-05, "loss": 1.5809, "step": 702000 }, { "epoch": 4.6, "learning_rate": 2.6979289553021368e-05, "loss": 1.5707, "step": 702500 }, { "epoch": 4.61, "learning_rate": 2.6962904705728143e-05, "loss": 1.5729, "step": 703000 }, { "epoch": 4.61, "learning_rate": 2.694651985843492e-05, "loss": 1.5696, "step": 703500 }, { "epoch": 4.61, "learning_rate": 2.69301350111417e-05, "loss": 1.6052, "step": 704000 }, { "epoch": 4.62, "learning_rate": 2.6913750163848474e-05, "loss": 1.6077, "step": 704500 }, { "epoch": 4.62, "learning_rate": 2.6897365316555252e-05, "loss": 1.5952, "step": 705000 }, { "epoch": 4.62, "learning_rate": 2.688098046926203e-05, "loss": 1.5844, "step": 705500 }, { "epoch": 4.63, "learning_rate": 2.6864595621968802e-05, "loss": 1.609, "step": 706000 }, { "epoch": 4.63, "learning_rate": 2.684821077467558e-05, "loss": 1.6085, "step": 706500 }, { "epoch": 4.63, "learning_rate": 2.683182592738236e-05, "loss": 1.5633, "step": 707000 }, { "epoch": 4.64, "learning_rate": 2.6815441080089137e-05, "loss": 1.5747, "step": 707500 }, { "epoch": 4.64, "learning_rate": 2.679905623279591e-05, "loss": 1.5652, "step": 708000 }, { "epoch": 4.64, "learning_rate": 2.678267138550269e-05, "loss": 1.576, "step": 708500 }, { "epoch": 4.65, "learning_rate": 2.6766286538209468e-05, "loss": 1.6023, "step": 709000 }, { "epoch": 4.65, "learning_rate": 2.674990169091624e-05, "loss": 1.5813, "step": 709500 }, { "epoch": 4.65, "learning_rate": 2.6733516843623017e-05, "loss": 1.5887, "step": 710000 }, { "epoch": 4.66, "learning_rate": 2.6717131996329796e-05, "loss": 1.6026, "step": 710500 }, { "epoch": 4.66, "learning_rate": 2.670074714903657e-05, "loss": 1.5642, "step": 711000 }, { "epoch": 4.66, "learning_rate": 2.668436230174335e-05, "loss": 1.5409, "step": 711500 }, { "epoch": 4.67, "learning_rate": 2.6667977454450127e-05, "loss": 1.5863, "step": 712000 }, { "epoch": 4.67, "learning_rate": 2.66515926071569e-05, "loss": 1.5674, "step": 712500 }, { "epoch": 4.67, "learning_rate": 2.663520775986368e-05, "loss": 1.5973, "step": 713000 }, { "epoch": 4.68, "learning_rate": 2.6618822912570458e-05, "loss": 1.6226, "step": 713500 }, { "epoch": 4.68, "learning_rate": 2.6602438065277236e-05, "loss": 1.5885, "step": 714000 }, { "epoch": 4.68, "learning_rate": 2.6586053217984008e-05, "loss": 1.6066, "step": 714500 }, { "epoch": 4.69, "learning_rate": 2.6569668370690786e-05, "loss": 1.5496, "step": 715000 }, { "epoch": 4.69, "learning_rate": 2.6553283523397564e-05, "loss": 1.5458, "step": 715500 }, { "epoch": 4.69, "learning_rate": 2.653689867610434e-05, "loss": 1.5244, "step": 716000 }, { "epoch": 4.7, "learning_rate": 2.6520513828811117e-05, "loss": 1.5819, "step": 716500 }, { "epoch": 4.7, "learning_rate": 2.6504128981517895e-05, "loss": 1.5676, "step": 717000 }, { "epoch": 4.7, "learning_rate": 2.6487744134224667e-05, "loss": 1.6149, "step": 717500 }, { "epoch": 4.71, "learning_rate": 2.6471359286931445e-05, "loss": 1.547, "step": 718000 }, { "epoch": 4.71, "learning_rate": 2.6454974439638223e-05, "loss": 1.5974, "step": 718500 }, { "epoch": 4.71, "learning_rate": 2.6438589592345005e-05, "loss": 1.5829, "step": 719000 }, { "epoch": 4.72, "learning_rate": 2.6422204745051776e-05, "loss": 1.5516, "step": 719500 }, { "epoch": 4.72, "learning_rate": 2.6405819897758555e-05, "loss": 1.5873, "step": 720000 }, { "epoch": 4.72, "learning_rate": 2.6389435050465333e-05, "loss": 1.5724, "step": 720500 }, { "epoch": 4.73, "learning_rate": 2.6373050203172108e-05, "loss": 1.5633, "step": 721000 }, { "epoch": 4.73, "learning_rate": 2.6356665355878886e-05, "loss": 1.5789, "step": 721500 }, { "epoch": 4.73, "learning_rate": 2.6340280508585664e-05, "loss": 1.5578, "step": 722000 }, { "epoch": 4.74, "learning_rate": 2.6323895661292435e-05, "loss": 1.5642, "step": 722500 }, { "epoch": 4.74, "learning_rate": 2.6307510813999214e-05, "loss": 1.5529, "step": 723000 }, { "epoch": 4.74, "learning_rate": 2.6291125966705992e-05, "loss": 1.5588, "step": 723500 }, { "epoch": 4.75, "learning_rate": 2.6274741119412767e-05, "loss": 1.5766, "step": 724000 }, { "epoch": 4.75, "learning_rate": 2.6258356272119545e-05, "loss": 1.5967, "step": 724500 }, { "epoch": 4.75, "learning_rate": 2.6241971424826323e-05, "loss": 1.5628, "step": 725000 }, { "epoch": 4.75, "learning_rate": 2.62255865775331e-05, "loss": 1.5893, "step": 725500 }, { "epoch": 4.76, "learning_rate": 2.6209201730239873e-05, "loss": 1.5506, "step": 726000 }, { "epoch": 4.76, "learning_rate": 2.619281688294665e-05, "loss": 1.5684, "step": 726500 }, { "epoch": 4.76, "learning_rate": 2.6176432035653433e-05, "loss": 1.5972, "step": 727000 }, { "epoch": 4.77, "learning_rate": 2.6160047188360204e-05, "loss": 1.5552, "step": 727500 }, { "epoch": 4.77, "learning_rate": 2.6143662341066982e-05, "loss": 1.5642, "step": 728000 }, { "epoch": 4.77, "learning_rate": 2.612727749377376e-05, "loss": 1.5555, "step": 728500 }, { "epoch": 4.78, "learning_rate": 2.6110892646480535e-05, "loss": 1.5886, "step": 729000 }, { "epoch": 4.78, "learning_rate": 2.6094507799187314e-05, "loss": 1.5305, "step": 729500 }, { "epoch": 4.78, "learning_rate": 2.6078122951894092e-05, "loss": 1.5974, "step": 730000 }, { "epoch": 4.79, "learning_rate": 2.606173810460087e-05, "loss": 1.5947, "step": 730500 }, { "epoch": 4.79, "learning_rate": 2.604535325730764e-05, "loss": 1.5956, "step": 731000 }, { "epoch": 4.79, "learning_rate": 2.602896841001442e-05, "loss": 1.5655, "step": 731500 }, { "epoch": 4.8, "learning_rate": 2.6012583562721198e-05, "loss": 1.6261, "step": 732000 }, { "epoch": 4.8, "learning_rate": 2.5996198715427973e-05, "loss": 1.5577, "step": 732500 }, { "epoch": 4.8, "learning_rate": 2.597981386813475e-05, "loss": 1.5515, "step": 733000 }, { "epoch": 4.81, "learning_rate": 2.596342902084153e-05, "loss": 1.5466, "step": 733500 }, { "epoch": 4.81, "learning_rate": 2.59470441735483e-05, "loss": 1.5727, "step": 734000 }, { "epoch": 4.81, "learning_rate": 2.593065932625508e-05, "loss": 1.6047, "step": 734500 }, { "epoch": 4.82, "learning_rate": 2.5914274478961857e-05, "loss": 1.6565, "step": 735000 }, { "epoch": 4.82, "learning_rate": 2.5897889631668632e-05, "loss": 1.541, "step": 735500 }, { "epoch": 4.82, "learning_rate": 2.588150478437541e-05, "loss": 1.6138, "step": 736000 }, { "epoch": 4.83, "learning_rate": 2.5865119937082188e-05, "loss": 1.6345, "step": 736500 }, { "epoch": 4.83, "learning_rate": 2.5848735089788966e-05, "loss": 1.5712, "step": 737000 }, { "epoch": 4.83, "learning_rate": 2.583235024249574e-05, "loss": 1.5584, "step": 737500 }, { "epoch": 4.84, "learning_rate": 2.581596539520252e-05, "loss": 1.5731, "step": 738000 }, { "epoch": 4.84, "learning_rate": 2.5799580547909298e-05, "loss": 1.6005, "step": 738500 }, { "epoch": 4.84, "learning_rate": 2.578319570061607e-05, "loss": 1.5708, "step": 739000 }, { "epoch": 4.85, "learning_rate": 2.5766810853322847e-05, "loss": 1.59, "step": 739500 }, { "epoch": 4.85, "learning_rate": 2.5750426006029625e-05, "loss": 1.5331, "step": 740000 }, { "epoch": 4.85, "learning_rate": 2.57340411587364e-05, "loss": 1.5562, "step": 740500 }, { "epoch": 4.86, "learning_rate": 2.571765631144318e-05, "loss": 1.5879, "step": 741000 }, { "epoch": 4.86, "learning_rate": 2.5701271464149957e-05, "loss": 1.5136, "step": 741500 }, { "epoch": 4.86, "learning_rate": 2.5684886616856735e-05, "loss": 1.5383, "step": 742000 }, { "epoch": 4.87, "learning_rate": 2.5668501769563506e-05, "loss": 1.5912, "step": 742500 }, { "epoch": 4.87, "learning_rate": 2.5652116922270285e-05, "loss": 1.5671, "step": 743000 }, { "epoch": 4.87, "learning_rate": 2.5635732074977066e-05, "loss": 1.5677, "step": 743500 }, { "epoch": 4.88, "learning_rate": 2.5619347227683838e-05, "loss": 1.5718, "step": 744000 }, { "epoch": 4.88, "learning_rate": 2.5602962380390616e-05, "loss": 1.5854, "step": 744500 }, { "epoch": 4.88, "learning_rate": 2.5586577533097394e-05, "loss": 1.5924, "step": 745000 }, { "epoch": 4.89, "learning_rate": 2.557019268580417e-05, "loss": 1.5732, "step": 745500 }, { "epoch": 4.89, "learning_rate": 2.5553807838510947e-05, "loss": 1.55, "step": 746000 }, { "epoch": 4.89, "learning_rate": 2.5537422991217725e-05, "loss": 1.5525, "step": 746500 }, { "epoch": 4.9, "learning_rate": 2.5521038143924497e-05, "loss": 1.5904, "step": 747000 }, { "epoch": 4.9, "learning_rate": 2.5504653296631275e-05, "loss": 1.549, "step": 747500 }, { "epoch": 4.9, "learning_rate": 2.5488268449338053e-05, "loss": 1.5534, "step": 748000 }, { "epoch": 4.91, "learning_rate": 2.547188360204483e-05, "loss": 1.562, "step": 748500 }, { "epoch": 4.91, "learning_rate": 2.5455498754751606e-05, "loss": 1.5735, "step": 749000 }, { "epoch": 4.91, "learning_rate": 2.5439113907458384e-05, "loss": 1.5568, "step": 749500 }, { "epoch": 4.92, "learning_rate": 2.5422729060165163e-05, "loss": 1.5478, "step": 750000 }, { "epoch": 4.92, "learning_rate": 2.5406344212871934e-05, "loss": 1.5764, "step": 750500 }, { "epoch": 4.92, "learning_rate": 2.5389959365578712e-05, "loss": 1.5987, "step": 751000 }, { "epoch": 4.93, "learning_rate": 2.5373574518285494e-05, "loss": 1.5431, "step": 751500 }, { "epoch": 4.93, "learning_rate": 2.5357189670992265e-05, "loss": 1.5705, "step": 752000 }, { "epoch": 4.93, "learning_rate": 2.5340804823699044e-05, "loss": 1.5709, "step": 752500 }, { "epoch": 4.94, "learning_rate": 2.5324419976405822e-05, "loss": 1.5454, "step": 753000 }, { "epoch": 4.94, "learning_rate": 2.53080351291126e-05, "loss": 1.566, "step": 753500 }, { "epoch": 4.94, "learning_rate": 2.5291650281819375e-05, "loss": 1.5275, "step": 754000 }, { "epoch": 4.94, "learning_rate": 2.5275265434526153e-05, "loss": 1.5359, "step": 754500 }, { "epoch": 4.95, "learning_rate": 2.525888058723293e-05, "loss": 1.5689, "step": 755000 }, { "epoch": 4.95, "learning_rate": 2.5242495739939703e-05, "loss": 1.5787, "step": 755500 }, { "epoch": 4.95, "learning_rate": 2.522611089264648e-05, "loss": 1.5835, "step": 756000 }, { "epoch": 4.96, "learning_rate": 2.520972604535326e-05, "loss": 1.5459, "step": 756500 }, { "epoch": 4.96, "learning_rate": 2.5193341198060034e-05, "loss": 1.5356, "step": 757000 }, { "epoch": 4.96, "learning_rate": 2.5176956350766812e-05, "loss": 1.609, "step": 757500 }, { "epoch": 4.97, "learning_rate": 2.516057150347359e-05, "loss": 1.5783, "step": 758000 }, { "epoch": 4.97, "learning_rate": 2.5144186656180362e-05, "loss": 1.5721, "step": 758500 }, { "epoch": 4.97, "learning_rate": 2.512780180888714e-05, "loss": 1.5783, "step": 759000 }, { "epoch": 4.98, "learning_rate": 2.511141696159392e-05, "loss": 1.5751, "step": 759500 }, { "epoch": 4.98, "learning_rate": 2.50950321143007e-05, "loss": 1.5638, "step": 760000 }, { "epoch": 4.98, "learning_rate": 2.507864726700747e-05, "loss": 1.5429, "step": 760500 }, { "epoch": 4.99, "learning_rate": 2.506226241971425e-05, "loss": 1.5715, "step": 761000 }, { "epoch": 4.99, "learning_rate": 2.5045877572421028e-05, "loss": 1.5535, "step": 761500 }, { "epoch": 4.99, "learning_rate": 2.5029492725127802e-05, "loss": 1.5493, "step": 762000 }, { "epoch": 5.0, "learning_rate": 2.501310787783458e-05, "loss": 1.5716, "step": 762500 }, { "epoch": 5.0, "learning_rate": 2.4996723030541355e-05, "loss": 1.5593, "step": 763000 }, { "epoch": 5.0, "learning_rate": 2.4980338183248134e-05, "loss": 1.5349, "step": 763500 }, { "epoch": 5.01, "learning_rate": 2.496395333595491e-05, "loss": 1.5272, "step": 764000 }, { "epoch": 5.01, "learning_rate": 2.4947568488661687e-05, "loss": 1.5309, "step": 764500 }, { "epoch": 5.01, "learning_rate": 2.4931183641368465e-05, "loss": 1.5272, "step": 765000 }, { "epoch": 5.02, "learning_rate": 2.491479879407524e-05, "loss": 1.5346, "step": 765500 }, { "epoch": 5.02, "learning_rate": 2.4898413946782018e-05, "loss": 1.5449, "step": 766000 }, { "epoch": 5.02, "learning_rate": 2.4882029099488793e-05, "loss": 1.5526, "step": 766500 }, { "epoch": 5.03, "learning_rate": 2.486564425219557e-05, "loss": 1.5361, "step": 767000 }, { "epoch": 5.03, "learning_rate": 2.4849259404902346e-05, "loss": 1.5352, "step": 767500 }, { "epoch": 5.03, "learning_rate": 2.4832874557609124e-05, "loss": 1.5519, "step": 768000 }, { "epoch": 5.04, "learning_rate": 2.4816489710315902e-05, "loss": 1.5308, "step": 768500 }, { "epoch": 5.04, "learning_rate": 2.4800104863022677e-05, "loss": 1.564, "step": 769000 }, { "epoch": 5.04, "learning_rate": 2.4783720015729455e-05, "loss": 1.543, "step": 769500 }, { "epoch": 5.05, "learning_rate": 2.476733516843623e-05, "loss": 1.5615, "step": 770000 }, { "epoch": 5.05, "learning_rate": 2.475095032114301e-05, "loss": 1.581, "step": 770500 }, { "epoch": 5.05, "learning_rate": 2.4734565473849787e-05, "loss": 1.5279, "step": 771000 }, { "epoch": 5.06, "learning_rate": 2.471818062655656e-05, "loss": 1.5521, "step": 771500 }, { "epoch": 5.06, "learning_rate": 2.470179577926334e-05, "loss": 1.5338, "step": 772000 }, { "epoch": 5.06, "learning_rate": 2.4685410931970114e-05, "loss": 1.5311, "step": 772500 }, { "epoch": 5.07, "learning_rate": 2.4669026084676893e-05, "loss": 1.5376, "step": 773000 }, { "epoch": 5.07, "learning_rate": 2.465264123738367e-05, "loss": 1.5411, "step": 773500 }, { "epoch": 5.07, "learning_rate": 2.4636256390090446e-05, "loss": 1.5484, "step": 774000 }, { "epoch": 5.08, "learning_rate": 2.461987154279722e-05, "loss": 1.5226, "step": 774500 }, { "epoch": 5.08, "learning_rate": 2.4603486695504e-05, "loss": 1.5211, "step": 775000 }, { "epoch": 5.08, "learning_rate": 2.4587101848210774e-05, "loss": 1.5695, "step": 775500 }, { "epoch": 5.09, "learning_rate": 2.4570717000917555e-05, "loss": 1.5344, "step": 776000 }, { "epoch": 5.09, "learning_rate": 2.455433215362433e-05, "loss": 1.5608, "step": 776500 }, { "epoch": 5.09, "learning_rate": 2.4537947306331105e-05, "loss": 1.5466, "step": 777000 }, { "epoch": 5.1, "learning_rate": 2.4521562459037883e-05, "loss": 1.5344, "step": 777500 }, { "epoch": 5.1, "learning_rate": 2.4505177611744658e-05, "loss": 1.5101, "step": 778000 }, { "epoch": 5.1, "learning_rate": 2.4488792764451436e-05, "loss": 1.5748, "step": 778500 }, { "epoch": 5.11, "learning_rate": 2.4472407917158214e-05, "loss": 1.5583, "step": 779000 }, { "epoch": 5.11, "learning_rate": 2.445602306986499e-05, "loss": 1.5443, "step": 779500 }, { "epoch": 5.11, "learning_rate": 2.4439638222571767e-05, "loss": 1.5641, "step": 780000 }, { "epoch": 5.12, "learning_rate": 2.4423253375278542e-05, "loss": 1.563, "step": 780500 }, { "epoch": 5.12, "learning_rate": 2.440686852798532e-05, "loss": 1.5744, "step": 781000 }, { "epoch": 5.12, "learning_rate": 2.43904836806921e-05, "loss": 1.55, "step": 781500 }, { "epoch": 5.13, "learning_rate": 2.4374098833398873e-05, "loss": 1.5711, "step": 782000 }, { "epoch": 5.13, "learning_rate": 2.435771398610565e-05, "loss": 1.5225, "step": 782500 }, { "epoch": 5.13, "learning_rate": 2.4341329138812426e-05, "loss": 1.5382, "step": 783000 }, { "epoch": 5.14, "learning_rate": 2.4324944291519205e-05, "loss": 1.5279, "step": 783500 }, { "epoch": 5.14, "learning_rate": 2.4308559444225983e-05, "loss": 1.5508, "step": 784000 }, { "epoch": 5.14, "learning_rate": 2.4292174596932758e-05, "loss": 1.5484, "step": 784500 }, { "epoch": 5.14, "learning_rate": 2.4275789749639536e-05, "loss": 1.5276, "step": 785000 }, { "epoch": 5.15, "learning_rate": 2.425940490234631e-05, "loss": 1.5049, "step": 785500 }, { "epoch": 5.15, "learning_rate": 2.4243020055053085e-05, "loss": 1.5503, "step": 786000 }, { "epoch": 5.15, "learning_rate": 2.4226635207759864e-05, "loss": 1.5511, "step": 786500 }, { "epoch": 5.16, "learning_rate": 2.4210250360466642e-05, "loss": 1.5398, "step": 787000 }, { "epoch": 5.16, "learning_rate": 2.419386551317342e-05, "loss": 1.5681, "step": 787500 }, { "epoch": 5.16, "learning_rate": 2.4177480665880195e-05, "loss": 1.5408, "step": 788000 }, { "epoch": 5.17, "learning_rate": 2.416109581858697e-05, "loss": 1.5208, "step": 788500 }, { "epoch": 5.17, "learning_rate": 2.4144710971293748e-05, "loss": 1.5565, "step": 789000 }, { "epoch": 5.17, "learning_rate": 2.4128326124000526e-05, "loss": 1.53, "step": 789500 }, { "epoch": 5.18, "learning_rate": 2.4111941276707304e-05, "loss": 1.5311, "step": 790000 }, { "epoch": 5.18, "learning_rate": 2.409555642941408e-05, "loss": 1.5093, "step": 790500 }, { "epoch": 5.18, "learning_rate": 2.4079171582120854e-05, "loss": 1.5294, "step": 791000 }, { "epoch": 5.19, "learning_rate": 2.4062786734827632e-05, "loss": 1.5505, "step": 791500 }, { "epoch": 5.19, "learning_rate": 2.404640188753441e-05, "loss": 1.5489, "step": 792000 }, { "epoch": 5.19, "learning_rate": 2.403001704024119e-05, "loss": 1.5861, "step": 792500 }, { "epoch": 5.2, "learning_rate": 2.4013632192947964e-05, "loss": 1.5502, "step": 793000 }, { "epoch": 5.2, "learning_rate": 2.399724734565474e-05, "loss": 1.5958, "step": 793500 }, { "epoch": 5.2, "learning_rate": 2.3980862498361517e-05, "loss": 1.4997, "step": 794000 }, { "epoch": 5.21, "learning_rate": 2.396447765106829e-05, "loss": 1.5609, "step": 794500 }, { "epoch": 5.21, "learning_rate": 2.394809280377507e-05, "loss": 1.5715, "step": 795000 }, { "epoch": 5.21, "learning_rate": 2.3931707956481848e-05, "loss": 1.5375, "step": 795500 }, { "epoch": 5.22, "learning_rate": 2.3915323109188623e-05, "loss": 1.5486, "step": 796000 }, { "epoch": 5.22, "learning_rate": 2.38989382618954e-05, "loss": 1.5219, "step": 796500 }, { "epoch": 5.22, "learning_rate": 2.3882553414602176e-05, "loss": 1.5627, "step": 797000 }, { "epoch": 5.23, "learning_rate": 2.3866168567308954e-05, "loss": 1.5417, "step": 797500 }, { "epoch": 5.23, "learning_rate": 2.3849783720015732e-05, "loss": 1.5786, "step": 798000 }, { "epoch": 5.23, "learning_rate": 2.3833398872722507e-05, "loss": 1.5267, "step": 798500 }, { "epoch": 5.24, "learning_rate": 2.3817014025429285e-05, "loss": 1.5405, "step": 799000 }, { "epoch": 5.24, "learning_rate": 2.380062917813606e-05, "loss": 1.5348, "step": 799500 }, { "epoch": 5.24, "learning_rate": 2.3784244330842835e-05, "loss": 1.5498, "step": 800000 }, { "epoch": 5.25, "learning_rate": 2.3767859483549616e-05, "loss": 1.5597, "step": 800500 }, { "epoch": 5.25, "learning_rate": 2.375147463625639e-05, "loss": 1.5266, "step": 801000 }, { "epoch": 5.25, "learning_rate": 2.373508978896317e-05, "loss": 1.5663, "step": 801500 }, { "epoch": 5.26, "learning_rate": 2.3718704941669944e-05, "loss": 1.5628, "step": 802000 }, { "epoch": 5.26, "learning_rate": 2.370232009437672e-05, "loss": 1.5312, "step": 802500 }, { "epoch": 5.26, "learning_rate": 2.3685935247083497e-05, "loss": 1.5423, "step": 803000 }, { "epoch": 5.27, "learning_rate": 2.3669550399790275e-05, "loss": 1.5513, "step": 803500 }, { "epoch": 5.27, "learning_rate": 2.3653165552497054e-05, "loss": 1.5363, "step": 804000 }, { "epoch": 5.27, "learning_rate": 2.363678070520383e-05, "loss": 1.5155, "step": 804500 }, { "epoch": 5.28, "learning_rate": 2.3620395857910603e-05, "loss": 1.545, "step": 805000 }, { "epoch": 5.28, "learning_rate": 2.360401101061738e-05, "loss": 1.539, "step": 805500 }, { "epoch": 5.28, "learning_rate": 2.358762616332416e-05, "loss": 1.5296, "step": 806000 }, { "epoch": 5.29, "learning_rate": 2.3571241316030938e-05, "loss": 1.5217, "step": 806500 }, { "epoch": 5.29, "learning_rate": 2.3554856468737713e-05, "loss": 1.531, "step": 807000 }, { "epoch": 5.29, "learning_rate": 2.3538471621444488e-05, "loss": 1.5409, "step": 807500 }, { "epoch": 5.3, "learning_rate": 2.3522086774151266e-05, "loss": 1.5801, "step": 808000 }, { "epoch": 5.3, "learning_rate": 2.3505701926858044e-05, "loss": 1.5465, "step": 808500 }, { "epoch": 5.3, "learning_rate": 2.348931707956482e-05, "loss": 1.5304, "step": 809000 }, { "epoch": 5.31, "learning_rate": 2.3472932232271597e-05, "loss": 1.5531, "step": 809500 }, { "epoch": 5.31, "learning_rate": 2.3456547384978372e-05, "loss": 1.5281, "step": 810000 }, { "epoch": 5.31, "learning_rate": 2.344016253768515e-05, "loss": 1.5666, "step": 810500 }, { "epoch": 5.32, "learning_rate": 2.3423777690391925e-05, "loss": 1.5918, "step": 811000 }, { "epoch": 5.32, "learning_rate": 2.3407392843098703e-05, "loss": 1.5047, "step": 811500 }, { "epoch": 5.32, "learning_rate": 2.339100799580548e-05, "loss": 1.5285, "step": 812000 }, { "epoch": 5.33, "learning_rate": 2.3374623148512256e-05, "loss": 1.5578, "step": 812500 }, { "epoch": 5.33, "learning_rate": 2.3358238301219034e-05, "loss": 1.552, "step": 813000 }, { "epoch": 5.33, "learning_rate": 2.334185345392581e-05, "loss": 1.5203, "step": 813500 }, { "epoch": 5.33, "learning_rate": 2.3325468606632587e-05, "loss": 1.5339, "step": 814000 }, { "epoch": 5.34, "learning_rate": 2.3309083759339366e-05, "loss": 1.5465, "step": 814500 }, { "epoch": 5.34, "learning_rate": 2.329269891204614e-05, "loss": 1.5533, "step": 815000 }, { "epoch": 5.34, "learning_rate": 2.327631406475292e-05, "loss": 1.5437, "step": 815500 }, { "epoch": 5.35, "learning_rate": 2.3259929217459694e-05, "loss": 1.5499, "step": 816000 }, { "epoch": 5.35, "learning_rate": 2.3243544370166472e-05, "loss": 1.5555, "step": 816500 }, { "epoch": 5.35, "learning_rate": 2.322715952287325e-05, "loss": 1.534, "step": 817000 }, { "epoch": 5.36, "learning_rate": 2.3210774675580025e-05, "loss": 1.5332, "step": 817500 }, { "epoch": 5.36, "learning_rate": 2.3194389828286803e-05, "loss": 1.5495, "step": 818000 }, { "epoch": 5.36, "learning_rate": 2.3178004980993578e-05, "loss": 1.5575, "step": 818500 }, { "epoch": 5.37, "learning_rate": 2.3161620133700353e-05, "loss": 1.5202, "step": 819000 }, { "epoch": 5.37, "learning_rate": 2.3145235286407134e-05, "loss": 1.5391, "step": 819500 }, { "epoch": 5.37, "learning_rate": 2.312885043911391e-05, "loss": 1.5368, "step": 820000 }, { "epoch": 5.38, "learning_rate": 2.3112465591820687e-05, "loss": 1.501, "step": 820500 }, { "epoch": 5.38, "learning_rate": 2.3096080744527462e-05, "loss": 1.541, "step": 821000 }, { "epoch": 5.38, "learning_rate": 2.3079695897234237e-05, "loss": 1.5361, "step": 821500 }, { "epoch": 5.39, "learning_rate": 2.3063311049941015e-05, "loss": 1.5377, "step": 822000 }, { "epoch": 5.39, "learning_rate": 2.3046926202647793e-05, "loss": 1.5542, "step": 822500 }, { "epoch": 5.39, "learning_rate": 2.3030541355354568e-05, "loss": 1.5362, "step": 823000 }, { "epoch": 5.4, "learning_rate": 2.3014156508061346e-05, "loss": 1.5354, "step": 823500 }, { "epoch": 5.4, "learning_rate": 2.299777166076812e-05, "loss": 1.5083, "step": 824000 }, { "epoch": 5.4, "learning_rate": 2.29813868134749e-05, "loss": 1.5415, "step": 824500 }, { "epoch": 5.41, "learning_rate": 2.2965001966181678e-05, "loss": 1.5442, "step": 825000 }, { "epoch": 5.41, "learning_rate": 2.2948617118888452e-05, "loss": 1.5654, "step": 825500 }, { "epoch": 5.41, "learning_rate": 2.293223227159523e-05, "loss": 1.524, "step": 826000 }, { "epoch": 5.42, "learning_rate": 2.2915847424302005e-05, "loss": 1.5139, "step": 826500 }, { "epoch": 5.42, "learning_rate": 2.2899462577008784e-05, "loss": 1.4946, "step": 827000 }, { "epoch": 5.42, "learning_rate": 2.288307772971556e-05, "loss": 1.5487, "step": 827500 }, { "epoch": 5.43, "learning_rate": 2.2866692882422337e-05, "loss": 1.55, "step": 828000 }, { "epoch": 5.43, "learning_rate": 2.2850308035129115e-05, "loss": 1.5504, "step": 828500 }, { "epoch": 5.43, "learning_rate": 2.283392318783589e-05, "loss": 1.5646, "step": 829000 }, { "epoch": 5.44, "learning_rate": 2.2817538340542668e-05, "loss": 1.5004, "step": 829500 }, { "epoch": 5.44, "learning_rate": 2.2801153493249443e-05, "loss": 1.5288, "step": 830000 }, { "epoch": 5.44, "learning_rate": 2.278476864595622e-05, "loss": 1.4995, "step": 830500 }, { "epoch": 5.45, "learning_rate": 2.2768383798663e-05, "loss": 1.5217, "step": 831000 }, { "epoch": 5.45, "learning_rate": 2.2751998951369774e-05, "loss": 1.5222, "step": 831500 }, { "epoch": 5.45, "learning_rate": 2.2735614104076552e-05, "loss": 1.5648, "step": 832000 }, { "epoch": 5.46, "learning_rate": 2.2719229256783327e-05, "loss": 1.5312, "step": 832500 }, { "epoch": 5.46, "learning_rate": 2.2702844409490105e-05, "loss": 1.5303, "step": 833000 }, { "epoch": 5.46, "learning_rate": 2.2686459562196884e-05, "loss": 1.5742, "step": 833500 }, { "epoch": 5.47, "learning_rate": 2.267007471490366e-05, "loss": 1.5501, "step": 834000 }, { "epoch": 5.47, "learning_rate": 2.2653689867610433e-05, "loss": 1.5412, "step": 834500 }, { "epoch": 5.47, "learning_rate": 2.263730502031721e-05, "loss": 1.5464, "step": 835000 }, { "epoch": 5.48, "learning_rate": 2.2620920173023986e-05, "loss": 1.5247, "step": 835500 }, { "epoch": 5.48, "learning_rate": 2.2604535325730768e-05, "loss": 1.5271, "step": 836000 }, { "epoch": 5.48, "learning_rate": 2.2588150478437543e-05, "loss": 1.5402, "step": 836500 }, { "epoch": 5.49, "learning_rate": 2.2571765631144317e-05, "loss": 1.5576, "step": 837000 }, { "epoch": 5.49, "learning_rate": 2.2555380783851096e-05, "loss": 1.5434, "step": 837500 }, { "epoch": 5.49, "learning_rate": 2.253899593655787e-05, "loss": 1.5205, "step": 838000 }, { "epoch": 5.5, "learning_rate": 2.252261108926465e-05, "loss": 1.5826, "step": 838500 }, { "epoch": 5.5, "learning_rate": 2.2506226241971427e-05, "loss": 1.5133, "step": 839000 }, { "epoch": 5.5, "learning_rate": 2.2489841394678202e-05, "loss": 1.5376, "step": 839500 }, { "epoch": 5.51, "learning_rate": 2.247345654738498e-05, "loss": 1.4856, "step": 840000 }, { "epoch": 5.51, "learning_rate": 2.2457071700091755e-05, "loss": 1.492, "step": 840500 }, { "epoch": 5.51, "learning_rate": 2.2440686852798533e-05, "loss": 1.5506, "step": 841000 }, { "epoch": 5.52, "learning_rate": 2.242430200550531e-05, "loss": 1.5066, "step": 841500 }, { "epoch": 5.52, "learning_rate": 2.2407917158212086e-05, "loss": 1.5405, "step": 842000 }, { "epoch": 5.52, "learning_rate": 2.2391532310918864e-05, "loss": 1.5215, "step": 842500 }, { "epoch": 5.52, "learning_rate": 2.237514746362564e-05, "loss": 1.5144, "step": 843000 }, { "epoch": 5.53, "learning_rate": 2.2358762616332417e-05, "loss": 1.5152, "step": 843500 }, { "epoch": 5.53, "learning_rate": 2.2342377769039195e-05, "loss": 1.5176, "step": 844000 }, { "epoch": 5.53, "learning_rate": 2.232599292174597e-05, "loss": 1.5649, "step": 844500 }, { "epoch": 5.54, "learning_rate": 2.230960807445275e-05, "loss": 1.5197, "step": 845000 }, { "epoch": 5.54, "learning_rate": 2.2293223227159523e-05, "loss": 1.4945, "step": 845500 }, { "epoch": 5.54, "learning_rate": 2.2276838379866298e-05, "loss": 1.5354, "step": 846000 }, { "epoch": 5.55, "learning_rate": 2.2260453532573076e-05, "loss": 1.5312, "step": 846500 }, { "epoch": 5.55, "learning_rate": 2.2244068685279855e-05, "loss": 1.5619, "step": 847000 }, { "epoch": 5.55, "learning_rate": 2.2227683837986633e-05, "loss": 1.5436, "step": 847500 }, { "epoch": 5.56, "learning_rate": 2.2211298990693408e-05, "loss": 1.5591, "step": 848000 }, { "epoch": 5.56, "learning_rate": 2.2194914143400182e-05, "loss": 1.5267, "step": 848500 }, { "epoch": 5.56, "learning_rate": 2.217852929610696e-05, "loss": 1.5488, "step": 849000 }, { "epoch": 5.57, "learning_rate": 2.216214444881374e-05, "loss": 1.5526, "step": 849500 }, { "epoch": 5.57, "learning_rate": 2.2145759601520517e-05, "loss": 1.5221, "step": 850000 }, { "epoch": 5.57, "learning_rate": 2.2129374754227292e-05, "loss": 1.5289, "step": 850500 }, { "epoch": 5.58, "learning_rate": 2.2112989906934067e-05, "loss": 1.5152, "step": 851000 }, { "epoch": 5.58, "learning_rate": 2.2096605059640845e-05, "loss": 1.5462, "step": 851500 }, { "epoch": 5.58, "learning_rate": 2.2080220212347623e-05, "loss": 1.5044, "step": 852000 }, { "epoch": 5.59, "learning_rate": 2.20638353650544e-05, "loss": 1.5178, "step": 852500 }, { "epoch": 5.59, "learning_rate": 2.2047450517761176e-05, "loss": 1.521, "step": 853000 }, { "epoch": 5.59, "learning_rate": 2.203106567046795e-05, "loss": 1.4924, "step": 853500 }, { "epoch": 5.6, "learning_rate": 2.201468082317473e-05, "loss": 1.5097, "step": 854000 }, { "epoch": 5.6, "learning_rate": 2.1998295975881504e-05, "loss": 1.5284, "step": 854500 }, { "epoch": 5.6, "learning_rate": 2.1981911128588282e-05, "loss": 1.5634, "step": 855000 }, { "epoch": 5.61, "learning_rate": 2.196552628129506e-05, "loss": 1.5076, "step": 855500 }, { "epoch": 5.61, "learning_rate": 2.1949141434001835e-05, "loss": 1.5331, "step": 856000 }, { "epoch": 5.61, "learning_rate": 2.1932756586708614e-05, "loss": 1.5527, "step": 856500 }, { "epoch": 5.62, "learning_rate": 2.191637173941539e-05, "loss": 1.5542, "step": 857000 }, { "epoch": 5.62, "learning_rate": 2.1899986892122167e-05, "loss": 1.5308, "step": 857500 }, { "epoch": 5.62, "learning_rate": 2.1883602044828945e-05, "loss": 1.5364, "step": 858000 }, { "epoch": 5.63, "learning_rate": 2.186721719753572e-05, "loss": 1.5175, "step": 858500 }, { "epoch": 5.63, "learning_rate": 2.1850832350242498e-05, "loss": 1.5407, "step": 859000 }, { "epoch": 5.63, "learning_rate": 2.1834447502949273e-05, "loss": 1.5291, "step": 859500 }, { "epoch": 5.64, "learning_rate": 2.1818062655656047e-05, "loss": 1.5512, "step": 860000 }, { "epoch": 5.64, "learning_rate": 2.180167780836283e-05, "loss": 1.5495, "step": 860500 }, { "epoch": 5.64, "learning_rate": 2.1785292961069604e-05, "loss": 1.5178, "step": 861000 }, { "epoch": 5.65, "learning_rate": 2.1768908113776382e-05, "loss": 1.5375, "step": 861500 }, { "epoch": 5.65, "learning_rate": 2.1752523266483157e-05, "loss": 1.5264, "step": 862000 }, { "epoch": 5.65, "learning_rate": 2.1736138419189932e-05, "loss": 1.5251, "step": 862500 }, { "epoch": 5.66, "learning_rate": 2.171975357189671e-05, "loss": 1.5311, "step": 863000 }, { "epoch": 5.66, "learning_rate": 2.1703368724603488e-05, "loss": 1.5208, "step": 863500 }, { "epoch": 5.66, "learning_rate": 2.1686983877310266e-05, "loss": 1.532, "step": 864000 }, { "epoch": 5.67, "learning_rate": 2.167059903001704e-05, "loss": 1.5163, "step": 864500 }, { "epoch": 5.67, "learning_rate": 2.1654214182723816e-05, "loss": 1.5403, "step": 865000 }, { "epoch": 5.67, "learning_rate": 2.1637829335430594e-05, "loss": 1.5302, "step": 865500 }, { "epoch": 5.68, "learning_rate": 2.1621444488137372e-05, "loss": 1.5618, "step": 866000 }, { "epoch": 5.68, "learning_rate": 2.160505964084415e-05, "loss": 1.5148, "step": 866500 }, { "epoch": 5.68, "learning_rate": 2.1588674793550925e-05, "loss": 1.5313, "step": 867000 }, { "epoch": 5.69, "learning_rate": 2.15722899462577e-05, "loss": 1.5173, "step": 867500 }, { "epoch": 5.69, "learning_rate": 2.155590509896448e-05, "loss": 1.4857, "step": 868000 }, { "epoch": 5.69, "learning_rate": 2.1539520251671257e-05, "loss": 1.4951, "step": 868500 }, { "epoch": 5.7, "learning_rate": 2.152313540437803e-05, "loss": 1.5206, "step": 869000 }, { "epoch": 5.7, "learning_rate": 2.150675055708481e-05, "loss": 1.5444, "step": 869500 }, { "epoch": 5.7, "learning_rate": 2.1490365709791585e-05, "loss": 1.5376, "step": 870000 }, { "epoch": 5.71, "learning_rate": 2.1473980862498363e-05, "loss": 1.5106, "step": 870500 }, { "epoch": 5.71, "learning_rate": 2.1457596015205138e-05, "loss": 1.4959, "step": 871000 }, { "epoch": 5.71, "learning_rate": 2.1441211167911916e-05, "loss": 1.5102, "step": 871500 }, { "epoch": 5.72, "learning_rate": 2.1424826320618694e-05, "loss": 1.4997, "step": 872000 }, { "epoch": 5.72, "learning_rate": 2.140844147332547e-05, "loss": 1.5415, "step": 872500 }, { "epoch": 5.72, "learning_rate": 2.1392056626032247e-05, "loss": 1.5586, "step": 873000 }, { "epoch": 5.72, "learning_rate": 2.1375671778739022e-05, "loss": 1.4954, "step": 873500 }, { "epoch": 5.73, "learning_rate": 2.13592869314458e-05, "loss": 1.5539, "step": 874000 }, { "epoch": 5.73, "learning_rate": 2.134290208415258e-05, "loss": 1.5248, "step": 874500 }, { "epoch": 5.73, "learning_rate": 2.1326517236859353e-05, "loss": 1.53, "step": 875000 }, { "epoch": 5.74, "learning_rate": 2.131013238956613e-05, "loss": 1.5229, "step": 875500 }, { "epoch": 5.74, "learning_rate": 2.1293747542272906e-05, "loss": 1.4993, "step": 876000 }, { "epoch": 5.74, "learning_rate": 2.1277362694979684e-05, "loss": 1.5301, "step": 876500 }, { "epoch": 5.75, "learning_rate": 2.1260977847686463e-05, "loss": 1.5104, "step": 877000 }, { "epoch": 5.75, "learning_rate": 2.1244593000393237e-05, "loss": 1.5672, "step": 877500 }, { "epoch": 5.75, "learning_rate": 2.1228208153100016e-05, "loss": 1.4931, "step": 878000 }, { "epoch": 5.76, "learning_rate": 2.121182330580679e-05, "loss": 1.5437, "step": 878500 }, { "epoch": 5.76, "learning_rate": 2.1195438458513565e-05, "loss": 1.5085, "step": 879000 }, { "epoch": 5.76, "learning_rate": 2.1179053611220347e-05, "loss": 1.5349, "step": 879500 }, { "epoch": 5.77, "learning_rate": 2.1162668763927122e-05, "loss": 1.5399, "step": 880000 }, { "epoch": 5.77, "learning_rate": 2.1146283916633897e-05, "loss": 1.5292, "step": 880500 }, { "epoch": 5.77, "learning_rate": 2.1129899069340675e-05, "loss": 1.5239, "step": 881000 }, { "epoch": 5.78, "learning_rate": 2.111351422204745e-05, "loss": 1.5088, "step": 881500 }, { "epoch": 5.78, "learning_rate": 2.1097129374754228e-05, "loss": 1.5478, "step": 882000 }, { "epoch": 5.78, "learning_rate": 2.1080744527461006e-05, "loss": 1.4984, "step": 882500 }, { "epoch": 5.79, "learning_rate": 2.106435968016778e-05, "loss": 1.5347, "step": 883000 }, { "epoch": 5.79, "learning_rate": 2.104797483287456e-05, "loss": 1.5381, "step": 883500 }, { "epoch": 5.79, "learning_rate": 2.1031589985581334e-05, "loss": 1.5461, "step": 884000 }, { "epoch": 5.8, "learning_rate": 2.1015205138288112e-05, "loss": 1.5023, "step": 884500 }, { "epoch": 5.8, "learning_rate": 2.099882029099489e-05, "loss": 1.5247, "step": 885000 }, { "epoch": 5.8, "learning_rate": 2.0982435443701665e-05, "loss": 1.5051, "step": 885500 }, { "epoch": 5.81, "learning_rate": 2.0966050596408443e-05, "loss": 1.5133, "step": 886000 }, { "epoch": 5.81, "learning_rate": 2.0949665749115218e-05, "loss": 1.515, "step": 886500 }, { "epoch": 5.81, "learning_rate": 2.0933280901821996e-05, "loss": 1.5165, "step": 887000 }, { "epoch": 5.82, "learning_rate": 2.091689605452877e-05, "loss": 1.4966, "step": 887500 }, { "epoch": 5.82, "learning_rate": 2.090051120723555e-05, "loss": 1.4925, "step": 888000 }, { "epoch": 5.82, "learning_rate": 2.0884126359942328e-05, "loss": 1.5336, "step": 888500 }, { "epoch": 5.83, "learning_rate": 2.0867741512649102e-05, "loss": 1.5297, "step": 889000 }, { "epoch": 5.83, "learning_rate": 2.085135666535588e-05, "loss": 1.5236, "step": 889500 }, { "epoch": 5.83, "learning_rate": 2.0834971818062655e-05, "loss": 1.5247, "step": 890000 }, { "epoch": 5.84, "learning_rate": 2.0818586970769434e-05, "loss": 1.5072, "step": 890500 }, { "epoch": 5.84, "learning_rate": 2.0802202123476212e-05, "loss": 1.5175, "step": 891000 }, { "epoch": 5.84, "learning_rate": 2.0785817276182987e-05, "loss": 1.5186, "step": 891500 }, { "epoch": 5.85, "learning_rate": 2.076943242888976e-05, "loss": 1.5254, "step": 892000 }, { "epoch": 5.85, "learning_rate": 2.075304758159654e-05, "loss": 1.5423, "step": 892500 }, { "epoch": 5.85, "learning_rate": 2.0736662734303318e-05, "loss": 1.508, "step": 893000 }, { "epoch": 5.86, "learning_rate": 2.0720277887010096e-05, "loss": 1.5199, "step": 893500 }, { "epoch": 5.86, "learning_rate": 2.070389303971687e-05, "loss": 1.4746, "step": 894000 }, { "epoch": 5.86, "learning_rate": 2.0687508192423646e-05, "loss": 1.5037, "step": 894500 }, { "epoch": 5.87, "learning_rate": 2.0671123345130424e-05, "loss": 1.4973, "step": 895000 }, { "epoch": 5.87, "learning_rate": 2.06547384978372e-05, "loss": 1.4989, "step": 895500 }, { "epoch": 5.87, "learning_rate": 2.063835365054398e-05, "loss": 1.5571, "step": 896000 }, { "epoch": 5.88, "learning_rate": 2.0621968803250755e-05, "loss": 1.5107, "step": 896500 }, { "epoch": 5.88, "learning_rate": 2.060558395595753e-05, "loss": 1.5271, "step": 897000 }, { "epoch": 5.88, "learning_rate": 2.058919910866431e-05, "loss": 1.4993, "step": 897500 }, { "epoch": 5.89, "learning_rate": 2.0572814261371083e-05, "loss": 1.4724, "step": 898000 }, { "epoch": 5.89, "learning_rate": 2.055642941407786e-05, "loss": 1.5004, "step": 898500 }, { "epoch": 5.89, "learning_rate": 2.054004456678464e-05, "loss": 1.501, "step": 899000 }, { "epoch": 5.9, "learning_rate": 2.0523659719491414e-05, "loss": 1.5294, "step": 899500 }, { "epoch": 5.9, "learning_rate": 2.0507274872198193e-05, "loss": 1.4802, "step": 900000 }, { "epoch": 5.9, "learning_rate": 2.0490890024904967e-05, "loss": 1.4993, "step": 900500 }, { "epoch": 5.91, "learning_rate": 2.0474505177611746e-05, "loss": 1.5069, "step": 901000 }, { "epoch": 5.91, "learning_rate": 2.0458120330318524e-05, "loss": 1.5542, "step": 901500 }, { "epoch": 5.91, "learning_rate": 2.04417354830253e-05, "loss": 1.5162, "step": 902000 }, { "epoch": 5.91, "learning_rate": 2.0425350635732077e-05, "loss": 1.4917, "step": 902500 }, { "epoch": 5.92, "learning_rate": 2.0408965788438852e-05, "loss": 1.5397, "step": 903000 }, { "epoch": 5.92, "learning_rate": 2.0392580941145627e-05, "loss": 1.5366, "step": 903500 }, { "epoch": 5.92, "learning_rate": 2.0376196093852408e-05, "loss": 1.5027, "step": 904000 }, { "epoch": 5.93, "learning_rate": 2.0359811246559183e-05, "loss": 1.521, "step": 904500 }, { "epoch": 5.93, "learning_rate": 2.034342639926596e-05, "loss": 1.4742, "step": 905000 }, { "epoch": 5.93, "learning_rate": 2.0327041551972736e-05, "loss": 1.4914, "step": 905500 }, { "epoch": 5.94, "learning_rate": 2.031065670467951e-05, "loss": 1.5581, "step": 906000 }, { "epoch": 5.94, "learning_rate": 2.029427185738629e-05, "loss": 1.5058, "step": 906500 }, { "epoch": 5.94, "learning_rate": 2.0277887010093067e-05, "loss": 1.5113, "step": 907000 }, { "epoch": 5.95, "learning_rate": 2.0261502162799845e-05, "loss": 1.5208, "step": 907500 }, { "epoch": 5.95, "learning_rate": 2.024511731550662e-05, "loss": 1.5069, "step": 908000 }, { "epoch": 5.95, "learning_rate": 2.0228732468213395e-05, "loss": 1.504, "step": 908500 }, { "epoch": 5.96, "learning_rate": 2.0212347620920173e-05, "loss": 1.5095, "step": 909000 }, { "epoch": 5.96, "learning_rate": 2.019596277362695e-05, "loss": 1.4985, "step": 909500 }, { "epoch": 5.96, "learning_rate": 2.017957792633373e-05, "loss": 1.5677, "step": 910000 }, { "epoch": 5.97, "learning_rate": 2.0163193079040505e-05, "loss": 1.5384, "step": 910500 }, { "epoch": 5.97, "learning_rate": 2.014680823174728e-05, "loss": 1.5123, "step": 911000 }, { "epoch": 5.97, "learning_rate": 2.0130423384454058e-05, "loss": 1.5318, "step": 911500 }, { "epoch": 5.98, "learning_rate": 2.0114038537160836e-05, "loss": 1.5058, "step": 912000 }, { "epoch": 5.98, "learning_rate": 2.0097653689867614e-05, "loss": 1.5031, "step": 912500 }, { "epoch": 5.98, "learning_rate": 2.008126884257439e-05, "loss": 1.5041, "step": 913000 }, { "epoch": 5.99, "learning_rate": 2.0064883995281164e-05, "loss": 1.5245, "step": 913500 }, { "epoch": 5.99, "learning_rate": 2.0048499147987942e-05, "loss": 1.5267, "step": 914000 }, { "epoch": 5.99, "learning_rate": 2.0032114300694717e-05, "loss": 1.5167, "step": 914500 }, { "epoch": 6.0, "learning_rate": 2.0015729453401495e-05, "loss": 1.5392, "step": 915000 }, { "epoch": 6.0, "learning_rate": 1.9999344606108273e-05, "loss": 1.5297, "step": 915500 }, { "epoch": 6.0, "learning_rate": 1.9982959758815048e-05, "loss": 1.4714, "step": 916000 }, { "epoch": 6.01, "learning_rate": 1.9966574911521826e-05, "loss": 1.5138, "step": 916500 }, { "epoch": 6.01, "learning_rate": 1.99501900642286e-05, "loss": 1.5516, "step": 917000 }, { "epoch": 6.01, "learning_rate": 1.993380521693538e-05, "loss": 1.4906, "step": 917500 }, { "epoch": 6.02, "learning_rate": 1.9917420369642157e-05, "loss": 1.546, "step": 918000 }, { "epoch": 6.02, "learning_rate": 1.9901035522348932e-05, "loss": 1.4977, "step": 918500 }, { "epoch": 6.02, "learning_rate": 1.988465067505571e-05, "loss": 1.5164, "step": 919000 }, { "epoch": 6.03, "learning_rate": 1.9868265827762485e-05, "loss": 1.5009, "step": 919500 }, { "epoch": 6.03, "learning_rate": 1.985188098046926e-05, "loss": 1.4912, "step": 920000 }, { "epoch": 6.03, "learning_rate": 1.9835496133176042e-05, "loss": 1.5136, "step": 920500 }, { "epoch": 6.04, "learning_rate": 1.9819111285882817e-05, "loss": 1.4817, "step": 921000 }, { "epoch": 6.04, "learning_rate": 1.9802726438589595e-05, "loss": 1.5118, "step": 921500 }, { "epoch": 6.04, "learning_rate": 1.978634159129637e-05, "loss": 1.5062, "step": 922000 }, { "epoch": 6.05, "learning_rate": 1.9769956744003144e-05, "loss": 1.5183, "step": 922500 }, { "epoch": 6.05, "learning_rate": 1.9753571896709923e-05, "loss": 1.514, "step": 923000 }, { "epoch": 6.05, "learning_rate": 1.97371870494167e-05, "loss": 1.4961, "step": 923500 }, { "epoch": 6.06, "learning_rate": 1.972080220212348e-05, "loss": 1.473, "step": 924000 }, { "epoch": 6.06, "learning_rate": 1.9704417354830254e-05, "loss": 1.484, "step": 924500 }, { "epoch": 6.06, "learning_rate": 1.968803250753703e-05, "loss": 1.4864, "step": 925000 }, { "epoch": 6.07, "learning_rate": 1.9671647660243807e-05, "loss": 1.544, "step": 925500 }, { "epoch": 6.07, "learning_rate": 1.9655262812950585e-05, "loss": 1.5002, "step": 926000 }, { "epoch": 6.07, "learning_rate": 1.9638877965657363e-05, "loss": 1.4749, "step": 926500 }, { "epoch": 6.08, "learning_rate": 1.9622493118364138e-05, "loss": 1.4608, "step": 927000 }, { "epoch": 6.08, "learning_rate": 1.9606108271070913e-05, "loss": 1.5056, "step": 927500 }, { "epoch": 6.08, "learning_rate": 1.958972342377769e-05, "loss": 1.535, "step": 928000 }, { "epoch": 6.09, "learning_rate": 1.957333857648447e-05, "loss": 1.4965, "step": 928500 }, { "epoch": 6.09, "learning_rate": 1.9556953729191244e-05, "loss": 1.4838, "step": 929000 }, { "epoch": 6.09, "learning_rate": 1.9540568881898022e-05, "loss": 1.5253, "step": 929500 }, { "epoch": 6.1, "learning_rate": 1.9524184034604797e-05, "loss": 1.464, "step": 930000 }, { "epoch": 6.1, "learning_rate": 1.9507799187311575e-05, "loss": 1.4489, "step": 930500 }, { "epoch": 6.1, "learning_rate": 1.949141434001835e-05, "loss": 1.5422, "step": 931000 }, { "epoch": 6.1, "learning_rate": 1.947502949272513e-05, "loss": 1.4867, "step": 931500 }, { "epoch": 6.11, "learning_rate": 1.9458644645431907e-05, "loss": 1.493, "step": 932000 }, { "epoch": 6.11, "learning_rate": 1.944225979813868e-05, "loss": 1.4753, "step": 932500 }, { "epoch": 6.11, "learning_rate": 1.942587495084546e-05, "loss": 1.4917, "step": 933000 }, { "epoch": 6.12, "learning_rate": 1.9409490103552235e-05, "loss": 1.4947, "step": 933500 }, { "epoch": 6.12, "learning_rate": 1.9393105256259013e-05, "loss": 1.4896, "step": 934000 }, { "epoch": 6.12, "learning_rate": 1.937672040896579e-05, "loss": 1.5371, "step": 934500 }, { "epoch": 6.13, "learning_rate": 1.9360335561672566e-05, "loss": 1.482, "step": 935000 }, { "epoch": 6.13, "learning_rate": 1.9343950714379344e-05, "loss": 1.4803, "step": 935500 }, { "epoch": 6.13, "learning_rate": 1.932756586708612e-05, "loss": 1.5099, "step": 936000 }, { "epoch": 6.14, "learning_rate": 1.9311181019792897e-05, "loss": 1.5197, "step": 936500 }, { "epoch": 6.14, "learning_rate": 1.9294796172499675e-05, "loss": 1.4828, "step": 937000 }, { "epoch": 6.14, "learning_rate": 1.927841132520645e-05, "loss": 1.4841, "step": 937500 }, { "epoch": 6.15, "learning_rate": 1.926202647791323e-05, "loss": 1.4975, "step": 938000 }, { "epoch": 6.15, "learning_rate": 1.9245641630620003e-05, "loss": 1.5239, "step": 938500 }, { "epoch": 6.15, "learning_rate": 1.9229256783326778e-05, "loss": 1.4785, "step": 939000 }, { "epoch": 6.16, "learning_rate": 1.921287193603356e-05, "loss": 1.4812, "step": 939500 }, { "epoch": 6.16, "learning_rate": 1.9196487088740334e-05, "loss": 1.4982, "step": 940000 }, { "epoch": 6.16, "learning_rate": 1.918010224144711e-05, "loss": 1.5116, "step": 940500 }, { "epoch": 6.17, "learning_rate": 1.9163717394153887e-05, "loss": 1.4955, "step": 941000 }, { "epoch": 6.17, "learning_rate": 1.9147332546860662e-05, "loss": 1.452, "step": 941500 }, { "epoch": 6.17, "learning_rate": 1.913094769956744e-05, "loss": 1.5044, "step": 942000 }, { "epoch": 6.18, "learning_rate": 1.911456285227422e-05, "loss": 1.4958, "step": 942500 }, { "epoch": 6.18, "learning_rate": 1.9098178004980994e-05, "loss": 1.5173, "step": 943000 }, { "epoch": 6.18, "learning_rate": 1.9081793157687772e-05, "loss": 1.4999, "step": 943500 }, { "epoch": 6.19, "learning_rate": 1.9065408310394547e-05, "loss": 1.4626, "step": 944000 }, { "epoch": 6.19, "learning_rate": 1.9049023463101325e-05, "loss": 1.5035, "step": 944500 }, { "epoch": 6.19, "learning_rate": 1.9032638615808103e-05, "loss": 1.4737, "step": 945000 }, { "epoch": 6.2, "learning_rate": 1.9016253768514878e-05, "loss": 1.488, "step": 945500 }, { "epoch": 6.2, "learning_rate": 1.8999868921221656e-05, "loss": 1.4749, "step": 946000 }, { "epoch": 6.2, "learning_rate": 1.898348407392843e-05, "loss": 1.4926, "step": 946500 }, { "epoch": 6.21, "learning_rate": 1.896709922663521e-05, "loss": 1.4874, "step": 947000 }, { "epoch": 6.21, "learning_rate": 1.8950714379341984e-05, "loss": 1.5186, "step": 947500 }, { "epoch": 6.21, "learning_rate": 1.8934329532048762e-05, "loss": 1.5133, "step": 948000 }, { "epoch": 6.22, "learning_rate": 1.891794468475554e-05, "loss": 1.4519, "step": 948500 }, { "epoch": 6.22, "learning_rate": 1.8901559837462315e-05, "loss": 1.5024, "step": 949000 }, { "epoch": 6.22, "learning_rate": 1.8885174990169093e-05, "loss": 1.4821, "step": 949500 }, { "epoch": 6.23, "learning_rate": 1.8868790142875868e-05, "loss": 1.5169, "step": 950000 }, { "epoch": 6.23, "learning_rate": 1.8852405295582646e-05, "loss": 1.4936, "step": 950500 }, { "epoch": 6.23, "learning_rate": 1.8836020448289425e-05, "loss": 1.4674, "step": 951000 }, { "epoch": 6.24, "learning_rate": 1.88196356009962e-05, "loss": 1.4943, "step": 951500 }, { "epoch": 6.24, "learning_rate": 1.8803250753702974e-05, "loss": 1.5063, "step": 952000 }, { "epoch": 6.24, "learning_rate": 1.8786865906409752e-05, "loss": 1.5019, "step": 952500 }, { "epoch": 6.25, "learning_rate": 1.877048105911653e-05, "loss": 1.4795, "step": 953000 }, { "epoch": 6.25, "learning_rate": 1.875409621182331e-05, "loss": 1.5051, "step": 953500 }, { "epoch": 6.25, "learning_rate": 1.8737711364530084e-05, "loss": 1.513, "step": 954000 }, { "epoch": 6.26, "learning_rate": 1.872132651723686e-05, "loss": 1.513, "step": 954500 }, { "epoch": 6.26, "learning_rate": 1.8704941669943637e-05, "loss": 1.4646, "step": 955000 }, { "epoch": 6.26, "learning_rate": 1.868855682265041e-05, "loss": 1.5056, "step": 955500 }, { "epoch": 6.27, "learning_rate": 1.8672171975357193e-05, "loss": 1.5114, "step": 956000 }, { "epoch": 6.27, "learning_rate": 1.8655787128063968e-05, "loss": 1.4794, "step": 956500 }, { "epoch": 6.27, "learning_rate": 1.8639402280770743e-05, "loss": 1.5448, "step": 957000 }, { "epoch": 6.28, "learning_rate": 1.862301743347752e-05, "loss": 1.5126, "step": 957500 }, { "epoch": 6.28, "learning_rate": 1.8606632586184296e-05, "loss": 1.5012, "step": 958000 }, { "epoch": 6.28, "learning_rate": 1.8590247738891074e-05, "loss": 1.4875, "step": 958500 }, { "epoch": 6.29, "learning_rate": 1.8573862891597852e-05, "loss": 1.4962, "step": 959000 }, { "epoch": 6.29, "learning_rate": 1.8557478044304627e-05, "loss": 1.4952, "step": 959500 }, { "epoch": 6.29, "learning_rate": 1.8541093197011405e-05, "loss": 1.4883, "step": 960000 }, { "epoch": 6.3, "learning_rate": 1.852470834971818e-05, "loss": 1.4886, "step": 960500 }, { "epoch": 6.3, "learning_rate": 1.850832350242496e-05, "loss": 1.4854, "step": 961000 }, { "epoch": 6.3, "learning_rate": 1.8491938655131737e-05, "loss": 1.4986, "step": 961500 }, { "epoch": 6.3, "learning_rate": 1.847555380783851e-05, "loss": 1.478, "step": 962000 }, { "epoch": 6.31, "learning_rate": 1.845916896054529e-05, "loss": 1.4704, "step": 962500 }, { "epoch": 6.31, "learning_rate": 1.8442784113252064e-05, "loss": 1.4746, "step": 963000 }, { "epoch": 6.31, "learning_rate": 1.842639926595884e-05, "loss": 1.4681, "step": 963500 }, { "epoch": 6.32, "learning_rate": 1.841001441866562e-05, "loss": 1.4867, "step": 964000 }, { "epoch": 6.32, "learning_rate": 1.8393629571372396e-05, "loss": 1.4884, "step": 964500 }, { "epoch": 6.32, "learning_rate": 1.8377244724079174e-05, "loss": 1.4965, "step": 965000 }, { "epoch": 6.33, "learning_rate": 1.836085987678595e-05, "loss": 1.5384, "step": 965500 }, { "epoch": 6.33, "learning_rate": 1.8344475029492724e-05, "loss": 1.4698, "step": 966000 }, { "epoch": 6.33, "learning_rate": 1.8328090182199502e-05, "loss": 1.4984, "step": 966500 }, { "epoch": 6.34, "learning_rate": 1.831170533490628e-05, "loss": 1.4773, "step": 967000 }, { "epoch": 6.34, "learning_rate": 1.8295320487613058e-05, "loss": 1.496, "step": 967500 }, { "epoch": 6.34, "learning_rate": 1.8278935640319833e-05, "loss": 1.4947, "step": 968000 }, { "epoch": 6.35, "learning_rate": 1.8262550793026608e-05, "loss": 1.5042, "step": 968500 }, { "epoch": 6.35, "learning_rate": 1.8246165945733386e-05, "loss": 1.5056, "step": 969000 }, { "epoch": 6.35, "learning_rate": 1.8229781098440164e-05, "loss": 1.4609, "step": 969500 }, { "epoch": 6.36, "learning_rate": 1.8213396251146942e-05, "loss": 1.4954, "step": 970000 }, { "epoch": 6.36, "learning_rate": 1.8197011403853717e-05, "loss": 1.5153, "step": 970500 }, { "epoch": 6.36, "learning_rate": 1.8180626556560492e-05, "loss": 1.4635, "step": 971000 }, { "epoch": 6.37, "learning_rate": 1.816424170926727e-05, "loss": 1.4625, "step": 971500 }, { "epoch": 6.37, "learning_rate": 1.814785686197405e-05, "loss": 1.4967, "step": 972000 }, { "epoch": 6.37, "learning_rate": 1.8131472014680827e-05, "loss": 1.5283, "step": 972500 }, { "epoch": 6.38, "learning_rate": 1.81150871673876e-05, "loss": 1.4624, "step": 973000 }, { "epoch": 6.38, "learning_rate": 1.8098702320094376e-05, "loss": 1.5036, "step": 973500 }, { "epoch": 6.38, "learning_rate": 1.8082317472801155e-05, "loss": 1.4791, "step": 974000 }, { "epoch": 6.39, "learning_rate": 1.806593262550793e-05, "loss": 1.4981, "step": 974500 }, { "epoch": 6.39, "learning_rate": 1.8049547778214708e-05, "loss": 1.4633, "step": 975000 }, { "epoch": 6.39, "learning_rate": 1.8033162930921486e-05, "loss": 1.4897, "step": 975500 }, { "epoch": 6.4, "learning_rate": 1.801677808362826e-05, "loss": 1.5006, "step": 976000 }, { "epoch": 6.4, "learning_rate": 1.800039323633504e-05, "loss": 1.4931, "step": 976500 }, { "epoch": 6.4, "learning_rate": 1.7984008389041814e-05, "loss": 1.494, "step": 977000 }, { "epoch": 6.41, "learning_rate": 1.7967623541748592e-05, "loss": 1.5031, "step": 977500 }, { "epoch": 6.41, "learning_rate": 1.795123869445537e-05, "loss": 1.4736, "step": 978000 }, { "epoch": 6.41, "learning_rate": 1.7934853847162145e-05, "loss": 1.497, "step": 978500 }, { "epoch": 6.42, "learning_rate": 1.7918468999868923e-05, "loss": 1.4987, "step": 979000 }, { "epoch": 6.42, "learning_rate": 1.7902084152575698e-05, "loss": 1.476, "step": 979500 }, { "epoch": 6.42, "learning_rate": 1.7885699305282473e-05, "loss": 1.5058, "step": 980000 }, { "epoch": 6.43, "learning_rate": 1.7869314457989254e-05, "loss": 1.4867, "step": 980500 }, { "epoch": 6.43, "learning_rate": 1.785292961069603e-05, "loss": 1.4899, "step": 981000 }, { "epoch": 6.43, "learning_rate": 1.7836544763402807e-05, "loss": 1.4662, "step": 981500 }, { "epoch": 6.44, "learning_rate": 1.7820159916109582e-05, "loss": 1.4599, "step": 982000 }, { "epoch": 6.44, "learning_rate": 1.7803775068816357e-05, "loss": 1.4904, "step": 982500 }, { "epoch": 6.44, "learning_rate": 1.7787390221523135e-05, "loss": 1.4385, "step": 983000 }, { "epoch": 6.45, "learning_rate": 1.7771005374229914e-05, "loss": 1.482, "step": 983500 }, { "epoch": 6.45, "learning_rate": 1.7754620526936692e-05, "loss": 1.4975, "step": 984000 }, { "epoch": 6.45, "learning_rate": 1.7738235679643467e-05, "loss": 1.501, "step": 984500 }, { "epoch": 6.46, "learning_rate": 1.772185083235024e-05, "loss": 1.4952, "step": 985000 }, { "epoch": 6.46, "learning_rate": 1.770546598505702e-05, "loss": 1.4925, "step": 985500 }, { "epoch": 6.46, "learning_rate": 1.7689081137763798e-05, "loss": 1.5068, "step": 986000 }, { "epoch": 6.47, "learning_rate": 1.7672696290470573e-05, "loss": 1.4763, "step": 986500 }, { "epoch": 6.47, "learning_rate": 1.765631144317735e-05, "loss": 1.5098, "step": 987000 }, { "epoch": 6.47, "learning_rate": 1.7639926595884126e-05, "loss": 1.5093, "step": 987500 }, { "epoch": 6.48, "learning_rate": 1.7623541748590904e-05, "loss": 1.4819, "step": 988000 }, { "epoch": 6.48, "learning_rate": 1.7607156901297682e-05, "loss": 1.5049, "step": 988500 }, { "epoch": 6.48, "learning_rate": 1.7590772054004457e-05, "loss": 1.4753, "step": 989000 }, { "epoch": 6.49, "learning_rate": 1.7574387206711235e-05, "loss": 1.4799, "step": 989500 }, { "epoch": 6.49, "learning_rate": 1.755800235941801e-05, "loss": 1.4879, "step": 990000 }, { "epoch": 6.49, "learning_rate": 1.7541617512124788e-05, "loss": 1.4639, "step": 990500 }, { "epoch": 6.49, "learning_rate": 1.7525232664831563e-05, "loss": 1.4618, "step": 991000 }, { "epoch": 6.5, "learning_rate": 1.750884781753834e-05, "loss": 1.486, "step": 991500 }, { "epoch": 6.5, "learning_rate": 1.749246297024512e-05, "loss": 1.5034, "step": 992000 }, { "epoch": 6.5, "learning_rate": 1.7476078122951894e-05, "loss": 1.4761, "step": 992500 }, { "epoch": 6.51, "learning_rate": 1.7459693275658672e-05, "loss": 1.4567, "step": 993000 }, { "epoch": 6.51, "learning_rate": 1.7443308428365447e-05, "loss": 1.4793, "step": 993500 }, { "epoch": 6.51, "learning_rate": 1.7426923581072225e-05, "loss": 1.4819, "step": 994000 }, { "epoch": 6.52, "learning_rate": 1.7410538733779004e-05, "loss": 1.4836, "step": 994500 }, { "epoch": 6.52, "learning_rate": 1.739415388648578e-05, "loss": 1.484, "step": 995000 }, { "epoch": 6.52, "learning_rate": 1.7377769039192557e-05, "loss": 1.4901, "step": 995500 }, { "epoch": 6.53, "learning_rate": 1.736138419189933e-05, "loss": 1.4908, "step": 996000 }, { "epoch": 6.53, "learning_rate": 1.734499934460611e-05, "loss": 1.5059, "step": 996500 }, { "epoch": 6.53, "learning_rate": 1.7328614497312888e-05, "loss": 1.499, "step": 997000 }, { "epoch": 6.54, "learning_rate": 1.7312229650019663e-05, "loss": 1.4887, "step": 997500 }, { "epoch": 6.54, "learning_rate": 1.7295844802726438e-05, "loss": 1.4899, "step": 998000 }, { "epoch": 6.54, "learning_rate": 1.7279459955433216e-05, "loss": 1.4531, "step": 998500 }, { "epoch": 6.55, "learning_rate": 1.726307510813999e-05, "loss": 1.4798, "step": 999000 }, { "epoch": 6.55, "learning_rate": 1.7246690260846772e-05, "loss": 1.4757, "step": 999500 }, { "epoch": 6.55, "learning_rate": 1.7230305413553547e-05, "loss": 1.5046, "step": 1000000 }, { "epoch": 6.56, "learning_rate": 1.7213920566260322e-05, "loss": 1.4694, "step": 1000500 }, { "epoch": 6.56, "learning_rate": 1.71975357189671e-05, "loss": 1.4811, "step": 1001000 }, { "epoch": 6.56, "learning_rate": 1.7181150871673875e-05, "loss": 1.4713, "step": 1001500 }, { "epoch": 6.57, "learning_rate": 1.7164766024380653e-05, "loss": 1.4697, "step": 1002000 }, { "epoch": 6.57, "learning_rate": 1.714838117708743e-05, "loss": 1.5186, "step": 1002500 }, { "epoch": 6.57, "learning_rate": 1.7131996329794206e-05, "loss": 1.4999, "step": 1003000 }, { "epoch": 6.58, "learning_rate": 1.7115611482500984e-05, "loss": 1.5019, "step": 1003500 }, { "epoch": 6.58, "learning_rate": 1.709922663520776e-05, "loss": 1.4996, "step": 1004000 }, { "epoch": 6.58, "learning_rate": 1.7082841787914537e-05, "loss": 1.5195, "step": 1004500 }, { "epoch": 6.59, "learning_rate": 1.7066456940621316e-05, "loss": 1.4911, "step": 1005000 }, { "epoch": 6.59, "learning_rate": 1.705007209332809e-05, "loss": 1.5098, "step": 1005500 }, { "epoch": 6.59, "learning_rate": 1.703368724603487e-05, "loss": 1.4631, "step": 1006000 }, { "epoch": 6.6, "learning_rate": 1.7017302398741644e-05, "loss": 1.4501, "step": 1006500 }, { "epoch": 6.6, "learning_rate": 1.7000917551448422e-05, "loss": 1.4858, "step": 1007000 }, { "epoch": 6.6, "learning_rate": 1.6984532704155197e-05, "loss": 1.4895, "step": 1007500 }, { "epoch": 6.61, "learning_rate": 1.6968147856861975e-05, "loss": 1.479, "step": 1008000 }, { "epoch": 6.61, "learning_rate": 1.6951763009568753e-05, "loss": 1.5294, "step": 1008500 }, { "epoch": 6.61, "learning_rate": 1.6935378162275528e-05, "loss": 1.4624, "step": 1009000 }, { "epoch": 6.62, "learning_rate": 1.6918993314982306e-05, "loss": 1.5028, "step": 1009500 }, { "epoch": 6.62, "learning_rate": 1.690260846768908e-05, "loss": 1.5137, "step": 1010000 }, { "epoch": 6.62, "learning_rate": 1.688622362039586e-05, "loss": 1.4928, "step": 1010500 }, { "epoch": 6.63, "learning_rate": 1.6869838773102637e-05, "loss": 1.4764, "step": 1011000 }, { "epoch": 6.63, "learning_rate": 1.6853453925809412e-05, "loss": 1.479, "step": 1011500 }, { "epoch": 6.63, "learning_rate": 1.6837069078516187e-05, "loss": 1.4787, "step": 1012000 }, { "epoch": 6.64, "learning_rate": 1.6820684231222965e-05, "loss": 1.512, "step": 1012500 }, { "epoch": 6.64, "learning_rate": 1.6804299383929743e-05, "loss": 1.5086, "step": 1013000 }, { "epoch": 6.64, "learning_rate": 1.678791453663652e-05, "loss": 1.5077, "step": 1013500 }, { "epoch": 6.65, "learning_rate": 1.6771529689343296e-05, "loss": 1.4933, "step": 1014000 }, { "epoch": 6.65, "learning_rate": 1.675514484205007e-05, "loss": 1.5195, "step": 1014500 }, { "epoch": 6.65, "learning_rate": 1.673875999475685e-05, "loss": 1.4401, "step": 1015000 }, { "epoch": 6.66, "learning_rate": 1.6722375147463624e-05, "loss": 1.4974, "step": 1015500 }, { "epoch": 6.66, "learning_rate": 1.6705990300170406e-05, "loss": 1.4884, "step": 1016000 }, { "epoch": 6.66, "learning_rate": 1.668960545287718e-05, "loss": 1.4873, "step": 1016500 }, { "epoch": 6.67, "learning_rate": 1.6673220605583956e-05, "loss": 1.482, "step": 1017000 }, { "epoch": 6.67, "learning_rate": 1.6656835758290734e-05, "loss": 1.4519, "step": 1017500 }, { "epoch": 6.67, "learning_rate": 1.664045091099751e-05, "loss": 1.4943, "step": 1018000 }, { "epoch": 6.68, "learning_rate": 1.6624066063704287e-05, "loss": 1.4757, "step": 1018500 }, { "epoch": 6.68, "learning_rate": 1.6607681216411065e-05, "loss": 1.5157, "step": 1019000 }, { "epoch": 6.68, "learning_rate": 1.659129636911784e-05, "loss": 1.5083, "step": 1019500 }, { "epoch": 6.69, "learning_rate": 1.6574911521824618e-05, "loss": 1.4754, "step": 1020000 }, { "epoch": 6.69, "learning_rate": 1.6558526674531393e-05, "loss": 1.5052, "step": 1020500 }, { "epoch": 6.69, "learning_rate": 1.654214182723817e-05, "loss": 1.5212, "step": 1021000 }, { "epoch": 6.69, "learning_rate": 1.652575697994495e-05, "loss": 1.5147, "step": 1021500 }, { "epoch": 6.7, "learning_rate": 1.6509372132651724e-05, "loss": 1.4856, "step": 1022000 }, { "epoch": 6.7, "learning_rate": 1.6492987285358502e-05, "loss": 1.4988, "step": 1022500 }, { "epoch": 6.7, "learning_rate": 1.6476602438065277e-05, "loss": 1.4753, "step": 1023000 }, { "epoch": 6.71, "learning_rate": 1.6460217590772052e-05, "loss": 1.496, "step": 1023500 }, { "epoch": 6.71, "learning_rate": 1.6443832743478834e-05, "loss": 1.5253, "step": 1024000 }, { "epoch": 6.71, "learning_rate": 1.642744789618561e-05, "loss": 1.5035, "step": 1024500 }, { "epoch": 6.72, "learning_rate": 1.6411063048892387e-05, "loss": 1.4823, "step": 1025000 }, { "epoch": 6.72, "learning_rate": 1.639467820159916e-05, "loss": 1.495, "step": 1025500 }, { "epoch": 6.72, "learning_rate": 1.6378293354305936e-05, "loss": 1.4568, "step": 1026000 }, { "epoch": 6.73, "learning_rate": 1.6361908507012714e-05, "loss": 1.49, "step": 1026500 }, { "epoch": 6.73, "learning_rate": 1.6345523659719493e-05, "loss": 1.4626, "step": 1027000 }, { "epoch": 6.73, "learning_rate": 1.632913881242627e-05, "loss": 1.505, "step": 1027500 }, { "epoch": 6.74, "learning_rate": 1.6312753965133046e-05, "loss": 1.4859, "step": 1028000 }, { "epoch": 6.74, "learning_rate": 1.629636911783982e-05, "loss": 1.4888, "step": 1028500 }, { "epoch": 6.74, "learning_rate": 1.62799842705466e-05, "loss": 1.4886, "step": 1029000 }, { "epoch": 6.75, "learning_rate": 1.6263599423253377e-05, "loss": 1.4426, "step": 1029500 }, { "epoch": 6.75, "learning_rate": 1.6247214575960155e-05, "loss": 1.4829, "step": 1030000 }, { "epoch": 6.75, "learning_rate": 1.623082972866693e-05, "loss": 1.4914, "step": 1030500 }, { "epoch": 6.76, "learning_rate": 1.6214444881373705e-05, "loss": 1.4789, "step": 1031000 }, { "epoch": 6.76, "learning_rate": 1.6198060034080483e-05, "loss": 1.4612, "step": 1031500 }, { "epoch": 6.76, "learning_rate": 1.618167518678726e-05, "loss": 1.4691, "step": 1032000 }, { "epoch": 6.77, "learning_rate": 1.616529033949404e-05, "loss": 1.4767, "step": 1032500 }, { "epoch": 6.77, "learning_rate": 1.6148905492200814e-05, "loss": 1.488, "step": 1033000 }, { "epoch": 6.77, "learning_rate": 1.613252064490759e-05, "loss": 1.4701, "step": 1033500 }, { "epoch": 6.78, "learning_rate": 1.6116135797614367e-05, "loss": 1.4665, "step": 1034000 }, { "epoch": 6.78, "learning_rate": 1.6099750950321142e-05, "loss": 1.4946, "step": 1034500 }, { "epoch": 6.78, "learning_rate": 1.608336610302792e-05, "loss": 1.4744, "step": 1035000 }, { "epoch": 6.79, "learning_rate": 1.60669812557347e-05, "loss": 1.4704, "step": 1035500 }, { "epoch": 6.79, "learning_rate": 1.6050596408441473e-05, "loss": 1.5071, "step": 1036000 }, { "epoch": 6.79, "learning_rate": 1.603421156114825e-05, "loss": 1.5, "step": 1036500 }, { "epoch": 6.8, "learning_rate": 1.6017826713855026e-05, "loss": 1.4785, "step": 1037000 }, { "epoch": 6.8, "learning_rate": 1.6001441866561805e-05, "loss": 1.4702, "step": 1037500 }, { "epoch": 6.8, "learning_rate": 1.5985057019268583e-05, "loss": 1.4615, "step": 1038000 }, { "epoch": 6.81, "learning_rate": 1.5968672171975358e-05, "loss": 1.5064, "step": 1038500 }, { "epoch": 6.81, "learning_rate": 1.5952287324682136e-05, "loss": 1.4638, "step": 1039000 }, { "epoch": 6.81, "learning_rate": 1.593590247738891e-05, "loss": 1.4969, "step": 1039500 }, { "epoch": 6.82, "learning_rate": 1.5919517630095686e-05, "loss": 1.4674, "step": 1040000 }, { "epoch": 6.82, "learning_rate": 1.5903132782802467e-05, "loss": 1.4922, "step": 1040500 }, { "epoch": 6.82, "learning_rate": 1.5886747935509242e-05, "loss": 1.4686, "step": 1041000 }, { "epoch": 6.83, "learning_rate": 1.587036308821602e-05, "loss": 1.4941, "step": 1041500 }, { "epoch": 6.83, "learning_rate": 1.5853978240922795e-05, "loss": 1.4936, "step": 1042000 }, { "epoch": 6.83, "learning_rate": 1.583759339362957e-05, "loss": 1.501, "step": 1042500 }, { "epoch": 6.84, "learning_rate": 1.5821208546336348e-05, "loss": 1.4847, "step": 1043000 }, { "epoch": 6.84, "learning_rate": 1.5804823699043126e-05, "loss": 1.5159, "step": 1043500 }, { "epoch": 6.84, "learning_rate": 1.5788438851749904e-05, "loss": 1.4941, "step": 1044000 }, { "epoch": 6.85, "learning_rate": 1.577205400445668e-05, "loss": 1.4668, "step": 1044500 }, { "epoch": 6.85, "learning_rate": 1.5755669157163454e-05, "loss": 1.4944, "step": 1045000 }, { "epoch": 6.85, "learning_rate": 1.5739284309870232e-05, "loss": 1.4443, "step": 1045500 }, { "epoch": 6.86, "learning_rate": 1.572289946257701e-05, "loss": 1.5031, "step": 1046000 }, { "epoch": 6.86, "learning_rate": 1.5706514615283785e-05, "loss": 1.4896, "step": 1046500 }, { "epoch": 6.86, "learning_rate": 1.5690129767990564e-05, "loss": 1.4591, "step": 1047000 }, { "epoch": 6.87, "learning_rate": 1.567374492069734e-05, "loss": 1.4831, "step": 1047500 }, { "epoch": 6.87, "learning_rate": 1.5657360073404117e-05, "loss": 1.4882, "step": 1048000 }, { "epoch": 6.87, "learning_rate": 1.5640975226110895e-05, "loss": 1.4824, "step": 1048500 }, { "epoch": 6.88, "learning_rate": 1.562459037881767e-05, "loss": 1.4605, "step": 1049000 }, { "epoch": 6.88, "learning_rate": 1.5608205531524448e-05, "loss": 1.4596, "step": 1049500 }, { "epoch": 6.88, "learning_rate": 1.5591820684231223e-05, "loss": 1.4939, "step": 1050000 }, { "epoch": 6.88, "learning_rate": 1.5575435836938e-05, "loss": 1.521, "step": 1050500 }, { "epoch": 6.89, "learning_rate": 1.5559050989644776e-05, "loss": 1.4603, "step": 1051000 }, { "epoch": 6.89, "learning_rate": 1.5542666142351554e-05, "loss": 1.5153, "step": 1051500 }, { "epoch": 6.89, "learning_rate": 1.5526281295058332e-05, "loss": 1.503, "step": 1052000 }, { "epoch": 6.9, "learning_rate": 1.5509896447765107e-05, "loss": 1.4271, "step": 1052500 }, { "epoch": 6.9, "learning_rate": 1.5493511600471885e-05, "loss": 1.4793, "step": 1053000 }, { "epoch": 6.9, "learning_rate": 1.547712675317866e-05, "loss": 1.4524, "step": 1053500 }, { "epoch": 6.91, "learning_rate": 1.5460741905885438e-05, "loss": 1.4731, "step": 1054000 }, { "epoch": 6.91, "learning_rate": 1.5444357058592216e-05, "loss": 1.4577, "step": 1054500 }, { "epoch": 6.91, "learning_rate": 1.542797221129899e-05, "loss": 1.4669, "step": 1055000 }, { "epoch": 6.92, "learning_rate": 1.541158736400577e-05, "loss": 1.4671, "step": 1055500 }, { "epoch": 6.92, "learning_rate": 1.5395202516712544e-05, "loss": 1.5226, "step": 1056000 }, { "epoch": 6.92, "learning_rate": 1.5378817669419322e-05, "loss": 1.4637, "step": 1056500 }, { "epoch": 6.93, "learning_rate": 1.53624328221261e-05, "loss": 1.4855, "step": 1057000 }, { "epoch": 6.93, "learning_rate": 1.5346047974832876e-05, "loss": 1.4803, "step": 1057500 }, { "epoch": 6.93, "learning_rate": 1.532966312753965e-05, "loss": 1.4713, "step": 1058000 }, { "epoch": 6.94, "learning_rate": 1.531327828024643e-05, "loss": 1.475, "step": 1058500 }, { "epoch": 6.94, "learning_rate": 1.5296893432953203e-05, "loss": 1.4556, "step": 1059000 }, { "epoch": 6.94, "learning_rate": 1.5280508585659985e-05, "loss": 1.5164, "step": 1059500 }, { "epoch": 6.95, "learning_rate": 1.526412373836676e-05, "loss": 1.4973, "step": 1060000 }, { "epoch": 6.95, "learning_rate": 1.5247738891073535e-05, "loss": 1.4728, "step": 1060500 }, { "epoch": 6.95, "learning_rate": 1.5231354043780313e-05, "loss": 1.5081, "step": 1061000 }, { "epoch": 6.96, "learning_rate": 1.521496919648709e-05, "loss": 1.443, "step": 1061500 }, { "epoch": 6.96, "learning_rate": 1.5198584349193868e-05, "loss": 1.4878, "step": 1062000 }, { "epoch": 6.96, "learning_rate": 1.5182199501900642e-05, "loss": 1.4707, "step": 1062500 }, { "epoch": 6.97, "learning_rate": 1.5165814654607419e-05, "loss": 1.4767, "step": 1063000 }, { "epoch": 6.97, "learning_rate": 1.5149429807314197e-05, "loss": 1.4947, "step": 1063500 }, { "epoch": 6.97, "learning_rate": 1.5133044960020974e-05, "loss": 1.4756, "step": 1064000 }, { "epoch": 6.98, "learning_rate": 1.5116660112727752e-05, "loss": 1.47, "step": 1064500 }, { "epoch": 6.98, "learning_rate": 1.5100275265434527e-05, "loss": 1.4768, "step": 1065000 }, { "epoch": 6.98, "learning_rate": 1.5083890418141303e-05, "loss": 1.468, "step": 1065500 }, { "epoch": 6.99, "learning_rate": 1.5067505570848081e-05, "loss": 1.4819, "step": 1066000 }, { "epoch": 6.99, "learning_rate": 1.5051120723554856e-05, "loss": 1.4637, "step": 1066500 }, { "epoch": 6.99, "learning_rate": 1.5034735876261634e-05, "loss": 1.4915, "step": 1067000 }, { "epoch": 7.0, "learning_rate": 1.5018351028968411e-05, "loss": 1.4575, "step": 1067500 }, { "epoch": 7.0, "learning_rate": 1.5001966181675187e-05, "loss": 1.4914, "step": 1068000 }, { "epoch": 7.0, "learning_rate": 1.4985581334381966e-05, "loss": 1.4755, "step": 1068500 }, { "epoch": 7.01, "learning_rate": 1.496919648708874e-05, "loss": 1.4492, "step": 1069000 }, { "epoch": 7.01, "learning_rate": 1.4952811639795517e-05, "loss": 1.4648, "step": 1069500 }, { "epoch": 7.01, "learning_rate": 1.4936426792502295e-05, "loss": 1.5067, "step": 1070000 }, { "epoch": 7.02, "learning_rate": 1.492004194520907e-05, "loss": 1.4455, "step": 1070500 }, { "epoch": 7.02, "learning_rate": 1.4903657097915848e-05, "loss": 1.4662, "step": 1071000 }, { "epoch": 7.02, "learning_rate": 1.4887272250622625e-05, "loss": 1.4689, "step": 1071500 }, { "epoch": 7.03, "learning_rate": 1.48708874033294e-05, "loss": 1.4503, "step": 1072000 }, { "epoch": 7.03, "learning_rate": 1.485450255603618e-05, "loss": 1.4898, "step": 1072500 }, { "epoch": 7.03, "learning_rate": 1.4838117708742954e-05, "loss": 1.463, "step": 1073000 }, { "epoch": 7.04, "learning_rate": 1.4821732861449733e-05, "loss": 1.4791, "step": 1073500 }, { "epoch": 7.04, "learning_rate": 1.4805348014156509e-05, "loss": 1.4884, "step": 1074000 }, { "epoch": 7.04, "learning_rate": 1.4788963166863284e-05, "loss": 1.4382, "step": 1074500 }, { "epoch": 7.05, "learning_rate": 1.4772578319570062e-05, "loss": 1.4227, "step": 1075000 }, { "epoch": 7.05, "learning_rate": 1.4756193472276839e-05, "loss": 1.4857, "step": 1075500 }, { "epoch": 7.05, "learning_rate": 1.4739808624983617e-05, "loss": 1.4502, "step": 1076000 }, { "epoch": 7.06, "learning_rate": 1.4723423777690393e-05, "loss": 1.4669, "step": 1076500 }, { "epoch": 7.06, "learning_rate": 1.4707038930397168e-05, "loss": 1.4553, "step": 1077000 }, { "epoch": 7.06, "learning_rate": 1.4690654083103946e-05, "loss": 1.477, "step": 1077500 }, { "epoch": 7.07, "learning_rate": 1.4674269235810723e-05, "loss": 1.4555, "step": 1078000 }, { "epoch": 7.07, "learning_rate": 1.4657884388517501e-05, "loss": 1.4728, "step": 1078500 }, { "epoch": 7.07, "learning_rate": 1.4641499541224276e-05, "loss": 1.4514, "step": 1079000 }, { "epoch": 7.07, "learning_rate": 1.4625114693931052e-05, "loss": 1.4358, "step": 1079500 }, { "epoch": 7.08, "learning_rate": 1.460872984663783e-05, "loss": 1.4688, "step": 1080000 }, { "epoch": 7.08, "learning_rate": 1.4592344999344607e-05, "loss": 1.4417, "step": 1080500 }, { "epoch": 7.08, "learning_rate": 1.4575960152051382e-05, "loss": 1.4449, "step": 1081000 }, { "epoch": 7.09, "learning_rate": 1.455957530475816e-05, "loss": 1.4377, "step": 1081500 }, { "epoch": 7.09, "learning_rate": 1.4543190457464937e-05, "loss": 1.4355, "step": 1082000 }, { "epoch": 7.09, "learning_rate": 1.4526805610171715e-05, "loss": 1.4617, "step": 1082500 }, { "epoch": 7.1, "learning_rate": 1.451042076287849e-05, "loss": 1.4849, "step": 1083000 }, { "epoch": 7.1, "learning_rate": 1.4494035915585266e-05, "loss": 1.4358, "step": 1083500 }, { "epoch": 7.1, "learning_rate": 1.4477651068292045e-05, "loss": 1.4619, "step": 1084000 }, { "epoch": 7.11, "learning_rate": 1.4461266220998821e-05, "loss": 1.4637, "step": 1084500 }, { "epoch": 7.11, "learning_rate": 1.44448813737056e-05, "loss": 1.4651, "step": 1085000 }, { "epoch": 7.11, "learning_rate": 1.4428496526412374e-05, "loss": 1.429, "step": 1085500 }, { "epoch": 7.12, "learning_rate": 1.441211167911915e-05, "loss": 1.4539, "step": 1086000 }, { "epoch": 7.12, "learning_rate": 1.4395726831825929e-05, "loss": 1.4504, "step": 1086500 }, { "epoch": 7.12, "learning_rate": 1.4379341984532704e-05, "loss": 1.4789, "step": 1087000 }, { "epoch": 7.13, "learning_rate": 1.4362957137239484e-05, "loss": 1.4557, "step": 1087500 }, { "epoch": 7.13, "learning_rate": 1.4346572289946258e-05, "loss": 1.4681, "step": 1088000 }, { "epoch": 7.13, "learning_rate": 1.4330187442653035e-05, "loss": 1.4587, "step": 1088500 }, { "epoch": 7.14, "learning_rate": 1.4313802595359813e-05, "loss": 1.4882, "step": 1089000 }, { "epoch": 7.14, "learning_rate": 1.4297417748066588e-05, "loss": 1.4613, "step": 1089500 }, { "epoch": 7.14, "learning_rate": 1.4281032900773366e-05, "loss": 1.4703, "step": 1090000 }, { "epoch": 7.15, "learning_rate": 1.4264648053480143e-05, "loss": 1.4687, "step": 1090500 }, { "epoch": 7.15, "learning_rate": 1.4248263206186917e-05, "loss": 1.4371, "step": 1091000 }, { "epoch": 7.15, "learning_rate": 1.4231878358893697e-05, "loss": 1.4864, "step": 1091500 }, { "epoch": 7.16, "learning_rate": 1.4215493511600472e-05, "loss": 1.443, "step": 1092000 }, { "epoch": 7.16, "learning_rate": 1.4199108664307249e-05, "loss": 1.5255, "step": 1092500 }, { "epoch": 7.16, "learning_rate": 1.4182723817014027e-05, "loss": 1.4537, "step": 1093000 }, { "epoch": 7.17, "learning_rate": 1.4166338969720802e-05, "loss": 1.454, "step": 1093500 }, { "epoch": 7.17, "learning_rate": 1.414995412242758e-05, "loss": 1.4555, "step": 1094000 }, { "epoch": 7.17, "learning_rate": 1.4133569275134356e-05, "loss": 1.4431, "step": 1094500 }, { "epoch": 7.18, "learning_rate": 1.4117184427841131e-05, "loss": 1.4659, "step": 1095000 }, { "epoch": 7.18, "learning_rate": 1.4100799580547911e-05, "loss": 1.4254, "step": 1095500 }, { "epoch": 7.18, "learning_rate": 1.4084414733254686e-05, "loss": 1.4883, "step": 1096000 }, { "epoch": 7.19, "learning_rate": 1.4068029885961464e-05, "loss": 1.4543, "step": 1096500 }, { "epoch": 7.19, "learning_rate": 1.405164503866824e-05, "loss": 1.4674, "step": 1097000 }, { "epoch": 7.19, "learning_rate": 1.4035260191375016e-05, "loss": 1.4547, "step": 1097500 }, { "epoch": 7.2, "learning_rate": 1.4018875344081794e-05, "loss": 1.4674, "step": 1098000 }, { "epoch": 7.2, "learning_rate": 1.400249049678857e-05, "loss": 1.4567, "step": 1098500 }, { "epoch": 7.2, "learning_rate": 1.3986105649495349e-05, "loss": 1.4525, "step": 1099000 }, { "epoch": 7.21, "learning_rate": 1.3969720802202123e-05, "loss": 1.462, "step": 1099500 }, { "epoch": 7.21, "learning_rate": 1.39533359549089e-05, "loss": 1.4888, "step": 1100000 }, { "epoch": 7.21, "learning_rate": 1.3936951107615678e-05, "loss": 1.4729, "step": 1100500 }, { "epoch": 7.22, "learning_rate": 1.3920566260322455e-05, "loss": 1.4689, "step": 1101000 }, { "epoch": 7.22, "learning_rate": 1.3904181413029233e-05, "loss": 1.4641, "step": 1101500 }, { "epoch": 7.22, "learning_rate": 1.3887796565736008e-05, "loss": 1.4628, "step": 1102000 }, { "epoch": 7.23, "learning_rate": 1.3871411718442784e-05, "loss": 1.4613, "step": 1102500 }, { "epoch": 7.23, "learning_rate": 1.3855026871149562e-05, "loss": 1.4598, "step": 1103000 }, { "epoch": 7.23, "learning_rate": 1.3838642023856337e-05, "loss": 1.5185, "step": 1103500 }, { "epoch": 7.24, "learning_rate": 1.3822257176563117e-05, "loss": 1.4787, "step": 1104000 }, { "epoch": 7.24, "learning_rate": 1.3805872329269892e-05, "loss": 1.4407, "step": 1104500 }, { "epoch": 7.24, "learning_rate": 1.3789487481976668e-05, "loss": 1.449, "step": 1105000 }, { "epoch": 7.25, "learning_rate": 1.3773102634683447e-05, "loss": 1.4636, "step": 1105500 }, { "epoch": 7.25, "learning_rate": 1.3756717787390221e-05, "loss": 1.4583, "step": 1106000 }, { "epoch": 7.25, "learning_rate": 1.3740332940096998e-05, "loss": 1.4807, "step": 1106500 }, { "epoch": 7.26, "learning_rate": 1.3723948092803776e-05, "loss": 1.4645, "step": 1107000 }, { "epoch": 7.26, "learning_rate": 1.3707563245510551e-05, "loss": 1.4442, "step": 1107500 }, { "epoch": 7.26, "learning_rate": 1.3691178398217331e-05, "loss": 1.4269, "step": 1108000 }, { "epoch": 7.27, "learning_rate": 1.3674793550924106e-05, "loss": 1.4535, "step": 1108500 }, { "epoch": 7.27, "learning_rate": 1.3658408703630882e-05, "loss": 1.4795, "step": 1109000 }, { "epoch": 7.27, "learning_rate": 1.364202385633766e-05, "loss": 1.5105, "step": 1109500 }, { "epoch": 7.27, "learning_rate": 1.3625639009044435e-05, "loss": 1.4338, "step": 1110000 }, { "epoch": 7.28, "learning_rate": 1.3609254161751214e-05, "loss": 1.4559, "step": 1110500 }, { "epoch": 7.28, "learning_rate": 1.359286931445799e-05, "loss": 1.452, "step": 1111000 }, { "epoch": 7.28, "learning_rate": 1.3576484467164765e-05, "loss": 1.4854, "step": 1111500 }, { "epoch": 7.29, "learning_rate": 1.3560099619871545e-05, "loss": 1.4538, "step": 1112000 }, { "epoch": 7.29, "learning_rate": 1.354371477257832e-05, "loss": 1.486, "step": 1112500 }, { "epoch": 7.29, "learning_rate": 1.3527329925285098e-05, "loss": 1.458, "step": 1113000 }, { "epoch": 7.3, "learning_rate": 1.3510945077991874e-05, "loss": 1.4394, "step": 1113500 }, { "epoch": 7.3, "learning_rate": 1.349456023069865e-05, "loss": 1.4555, "step": 1114000 }, { "epoch": 7.3, "learning_rate": 1.3478175383405427e-05, "loss": 1.4661, "step": 1114500 }, { "epoch": 7.31, "learning_rate": 1.3461790536112204e-05, "loss": 1.4746, "step": 1115000 }, { "epoch": 7.31, "learning_rate": 1.3445405688818982e-05, "loss": 1.4647, "step": 1115500 }, { "epoch": 7.31, "learning_rate": 1.3429020841525759e-05, "loss": 1.4798, "step": 1116000 }, { "epoch": 7.32, "learning_rate": 1.3412635994232533e-05, "loss": 1.4508, "step": 1116500 }, { "epoch": 7.32, "learning_rate": 1.3396251146939312e-05, "loss": 1.4618, "step": 1117000 }, { "epoch": 7.32, "learning_rate": 1.3379866299646088e-05, "loss": 1.4582, "step": 1117500 }, { "epoch": 7.33, "learning_rate": 1.3363481452352863e-05, "loss": 1.4519, "step": 1118000 }, { "epoch": 7.33, "learning_rate": 1.3347096605059641e-05, "loss": 1.472, "step": 1118500 }, { "epoch": 7.33, "learning_rate": 1.3330711757766418e-05, "loss": 1.4243, "step": 1119000 }, { "epoch": 7.34, "learning_rate": 1.3314326910473196e-05, "loss": 1.4803, "step": 1119500 }, { "epoch": 7.34, "learning_rate": 1.3297942063179972e-05, "loss": 1.4774, "step": 1120000 }, { "epoch": 7.34, "learning_rate": 1.3281557215886747e-05, "loss": 1.4687, "step": 1120500 }, { "epoch": 7.35, "learning_rate": 1.3265172368593526e-05, "loss": 1.4793, "step": 1121000 }, { "epoch": 7.35, "learning_rate": 1.3248787521300302e-05, "loss": 1.4786, "step": 1121500 }, { "epoch": 7.35, "learning_rate": 1.323240267400708e-05, "loss": 1.4709, "step": 1122000 }, { "epoch": 7.36, "learning_rate": 1.3216017826713855e-05, "loss": 1.4897, "step": 1122500 }, { "epoch": 7.36, "learning_rate": 1.3199632979420632e-05, "loss": 1.4845, "step": 1123000 }, { "epoch": 7.36, "learning_rate": 1.318324813212741e-05, "loss": 1.4824, "step": 1123500 }, { "epoch": 7.37, "learning_rate": 1.3166863284834186e-05, "loss": 1.444, "step": 1124000 }, { "epoch": 7.37, "learning_rate": 1.3150478437540965e-05, "loss": 1.4767, "step": 1124500 }, { "epoch": 7.37, "learning_rate": 1.313409359024774e-05, "loss": 1.4432, "step": 1125000 }, { "epoch": 7.38, "learning_rate": 1.3117708742954516e-05, "loss": 1.4512, "step": 1125500 }, { "epoch": 7.38, "learning_rate": 1.3101323895661294e-05, "loss": 1.4561, "step": 1126000 }, { "epoch": 7.38, "learning_rate": 1.3084939048368069e-05, "loss": 1.459, "step": 1126500 }, { "epoch": 7.39, "learning_rate": 1.3068554201074847e-05, "loss": 1.4631, "step": 1127000 }, { "epoch": 7.39, "learning_rate": 1.3052169353781624e-05, "loss": 1.4498, "step": 1127500 }, { "epoch": 7.39, "learning_rate": 1.30357845064884e-05, "loss": 1.4638, "step": 1128000 }, { "epoch": 7.4, "learning_rate": 1.3019399659195178e-05, "loss": 1.4647, "step": 1128500 }, { "epoch": 7.4, "learning_rate": 1.3003014811901953e-05, "loss": 1.4724, "step": 1129000 }, { "epoch": 7.4, "learning_rate": 1.298662996460873e-05, "loss": 1.4876, "step": 1129500 }, { "epoch": 7.41, "learning_rate": 1.2970245117315508e-05, "loss": 1.4457, "step": 1130000 }, { "epoch": 7.41, "learning_rate": 1.2953860270022283e-05, "loss": 1.4954, "step": 1130500 }, { "epoch": 7.41, "learning_rate": 1.2937475422729061e-05, "loss": 1.4709, "step": 1131000 }, { "epoch": 7.42, "learning_rate": 1.2921090575435837e-05, "loss": 1.4333, "step": 1131500 }, { "epoch": 7.42, "learning_rate": 1.2904705728142612e-05, "loss": 1.4576, "step": 1132000 }, { "epoch": 7.42, "learning_rate": 1.2888320880849392e-05, "loss": 1.4827, "step": 1132500 }, { "epoch": 7.43, "learning_rate": 1.2871936033556167e-05, "loss": 1.4865, "step": 1133000 }, { "epoch": 7.43, "learning_rate": 1.2855551186262945e-05, "loss": 1.4723, "step": 1133500 }, { "epoch": 7.43, "learning_rate": 1.2839166338969722e-05, "loss": 1.4533, "step": 1134000 }, { "epoch": 7.44, "learning_rate": 1.2822781491676497e-05, "loss": 1.4364, "step": 1134500 }, { "epoch": 7.44, "learning_rate": 1.2806396644383275e-05, "loss": 1.4816, "step": 1135000 }, { "epoch": 7.44, "learning_rate": 1.2790011797090051e-05, "loss": 1.5057, "step": 1135500 }, { "epoch": 7.45, "learning_rate": 1.277362694979683e-05, "loss": 1.4543, "step": 1136000 }, { "epoch": 7.45, "learning_rate": 1.2757242102503606e-05, "loss": 1.4459, "step": 1136500 }, { "epoch": 7.45, "learning_rate": 1.2740857255210381e-05, "loss": 1.4489, "step": 1137000 }, { "epoch": 7.46, "learning_rate": 1.2724472407917159e-05, "loss": 1.4583, "step": 1137500 }, { "epoch": 7.46, "learning_rate": 1.2708087560623936e-05, "loss": 1.4495, "step": 1138000 }, { "epoch": 7.46, "learning_rate": 1.2691702713330714e-05, "loss": 1.4476, "step": 1138500 }, { "epoch": 7.46, "learning_rate": 1.2675317866037489e-05, "loss": 1.434, "step": 1139000 }, { "epoch": 7.47, "learning_rate": 1.2658933018744265e-05, "loss": 1.4665, "step": 1139500 }, { "epoch": 7.47, "learning_rate": 1.2642548171451043e-05, "loss": 1.4583, "step": 1140000 }, { "epoch": 7.47, "learning_rate": 1.262616332415782e-05, "loss": 1.4704, "step": 1140500 }, { "epoch": 7.48, "learning_rate": 1.2609778476864595e-05, "loss": 1.4154, "step": 1141000 }, { "epoch": 7.48, "learning_rate": 1.2593393629571373e-05, "loss": 1.4962, "step": 1141500 }, { "epoch": 7.48, "learning_rate": 1.257700878227815e-05, "loss": 1.4562, "step": 1142000 }, { "epoch": 7.49, "learning_rate": 1.2560623934984928e-05, "loss": 1.4599, "step": 1142500 }, { "epoch": 7.49, "learning_rate": 1.2544239087691702e-05, "loss": 1.433, "step": 1143000 }, { "epoch": 7.49, "learning_rate": 1.2527854240398479e-05, "loss": 1.4014, "step": 1143500 }, { "epoch": 7.5, "learning_rate": 1.2511469393105257e-05, "loss": 1.4995, "step": 1144000 }, { "epoch": 7.5, "learning_rate": 1.2495084545812034e-05, "loss": 1.4314, "step": 1144500 }, { "epoch": 7.5, "learning_rate": 1.247869969851881e-05, "loss": 1.4703, "step": 1145000 }, { "epoch": 7.51, "learning_rate": 1.2462314851225587e-05, "loss": 1.4702, "step": 1145500 }, { "epoch": 7.51, "learning_rate": 1.2445930003932365e-05, "loss": 1.4524, "step": 1146000 }, { "epoch": 7.51, "learning_rate": 1.2429545156639141e-05, "loss": 1.4406, "step": 1146500 }, { "epoch": 7.52, "learning_rate": 1.2413160309345916e-05, "loss": 1.4781, "step": 1147000 }, { "epoch": 7.52, "learning_rate": 1.2396775462052695e-05, "loss": 1.4588, "step": 1147500 }, { "epoch": 7.52, "learning_rate": 1.2380390614759471e-05, "loss": 1.4323, "step": 1148000 }, { "epoch": 7.53, "learning_rate": 1.2364005767466248e-05, "loss": 1.4261, "step": 1148500 }, { "epoch": 7.53, "learning_rate": 1.2347620920173024e-05, "loss": 1.5142, "step": 1149000 }, { "epoch": 7.53, "learning_rate": 1.23312360728798e-05, "loss": 1.4662, "step": 1149500 }, { "epoch": 7.54, "learning_rate": 1.2314851225586579e-05, "loss": 1.4761, "step": 1150000 }, { "epoch": 7.54, "learning_rate": 1.2298466378293355e-05, "loss": 1.4942, "step": 1150500 }, { "epoch": 7.54, "learning_rate": 1.2282081531000132e-05, "loss": 1.4579, "step": 1151000 }, { "epoch": 7.55, "learning_rate": 1.2265696683706908e-05, "loss": 1.4521, "step": 1151500 }, { "epoch": 7.55, "learning_rate": 1.2249311836413685e-05, "loss": 1.4332, "step": 1152000 }, { "epoch": 7.55, "learning_rate": 1.2232926989120461e-05, "loss": 1.4331, "step": 1152500 }, { "epoch": 7.56, "learning_rate": 1.221654214182724e-05, "loss": 1.4841, "step": 1153000 }, { "epoch": 7.56, "learning_rate": 1.2200157294534016e-05, "loss": 1.4434, "step": 1153500 }, { "epoch": 7.56, "learning_rate": 1.2183772447240793e-05, "loss": 1.4729, "step": 1154000 }, { "epoch": 7.57, "learning_rate": 1.216738759994757e-05, "loss": 1.4661, "step": 1154500 }, { "epoch": 7.57, "learning_rate": 1.2151002752654346e-05, "loss": 1.4633, "step": 1155000 }, { "epoch": 7.57, "learning_rate": 1.2134617905361124e-05, "loss": 1.4638, "step": 1155500 }, { "epoch": 7.58, "learning_rate": 1.2118233058067899e-05, "loss": 1.4309, "step": 1156000 }, { "epoch": 7.58, "learning_rate": 1.2101848210774675e-05, "loss": 1.4611, "step": 1156500 }, { "epoch": 7.58, "learning_rate": 1.2085463363481453e-05, "loss": 1.4718, "step": 1157000 }, { "epoch": 7.59, "learning_rate": 1.206907851618823e-05, "loss": 1.4406, "step": 1157500 }, { "epoch": 7.59, "learning_rate": 1.2052693668895006e-05, "loss": 1.4544, "step": 1158000 }, { "epoch": 7.59, "learning_rate": 1.2036308821601783e-05, "loss": 1.4499, "step": 1158500 }, { "epoch": 7.6, "learning_rate": 1.201992397430856e-05, "loss": 1.4844, "step": 1159000 }, { "epoch": 7.6, "learning_rate": 1.2003539127015336e-05, "loss": 1.4407, "step": 1159500 }, { "epoch": 7.6, "learning_rate": 1.1987154279722114e-05, "loss": 1.4992, "step": 1160000 }, { "epoch": 7.61, "learning_rate": 1.1970769432428889e-05, "loss": 1.4465, "step": 1160500 }, { "epoch": 7.61, "learning_rate": 1.1954384585135667e-05, "loss": 1.4409, "step": 1161000 }, { "epoch": 7.61, "learning_rate": 1.1937999737842444e-05, "loss": 1.4594, "step": 1161500 }, { "epoch": 7.62, "learning_rate": 1.192161489054922e-05, "loss": 1.4187, "step": 1162000 }, { "epoch": 7.62, "learning_rate": 1.1905230043255999e-05, "loss": 1.4689, "step": 1162500 }, { "epoch": 7.62, "learning_rate": 1.1888845195962773e-05, "loss": 1.4807, "step": 1163000 }, { "epoch": 7.63, "learning_rate": 1.187246034866955e-05, "loss": 1.4756, "step": 1163500 }, { "epoch": 7.63, "learning_rate": 1.1856075501376328e-05, "loss": 1.4988, "step": 1164000 }, { "epoch": 7.63, "learning_rate": 1.1839690654083105e-05, "loss": 1.4183, "step": 1164500 }, { "epoch": 7.64, "learning_rate": 1.1823305806789881e-05, "loss": 1.4674, "step": 1165000 }, { "epoch": 7.64, "learning_rate": 1.1806920959496658e-05, "loss": 1.4273, "step": 1165500 }, { "epoch": 7.64, "learning_rate": 1.1790536112203434e-05, "loss": 1.4547, "step": 1166000 }, { "epoch": 7.65, "learning_rate": 1.1774151264910212e-05, "loss": 1.4519, "step": 1166500 }, { "epoch": 7.65, "learning_rate": 1.1757766417616989e-05, "loss": 1.4536, "step": 1167000 }, { "epoch": 7.65, "learning_rate": 1.1741381570323764e-05, "loss": 1.4581, "step": 1167500 }, { "epoch": 7.66, "learning_rate": 1.1724996723030542e-05, "loss": 1.4766, "step": 1168000 }, { "epoch": 7.66, "learning_rate": 1.1708611875737318e-05, "loss": 1.4543, "step": 1168500 }, { "epoch": 7.66, "learning_rate": 1.1692227028444095e-05, "loss": 1.4924, "step": 1169000 }, { "epoch": 7.66, "learning_rate": 1.1675842181150873e-05, "loss": 1.459, "step": 1169500 }, { "epoch": 7.67, "learning_rate": 1.1659457333857648e-05, "loss": 1.4613, "step": 1170000 }, { "epoch": 7.67, "learning_rate": 1.1643072486564426e-05, "loss": 1.451, "step": 1170500 }, { "epoch": 7.67, "learning_rate": 1.1626687639271203e-05, "loss": 1.4501, "step": 1171000 }, { "epoch": 7.68, "learning_rate": 1.161030279197798e-05, "loss": 1.4781, "step": 1171500 }, { "epoch": 7.68, "learning_rate": 1.1593917944684757e-05, "loss": 1.4532, "step": 1172000 }, { "epoch": 7.68, "learning_rate": 1.1577533097391532e-05, "loss": 1.4804, "step": 1172500 }, { "epoch": 7.69, "learning_rate": 1.1561148250098309e-05, "loss": 1.4382, "step": 1173000 }, { "epoch": 7.69, "learning_rate": 1.1544763402805087e-05, "loss": 1.4359, "step": 1173500 }, { "epoch": 7.69, "learning_rate": 1.1528378555511864e-05, "loss": 1.4712, "step": 1174000 }, { "epoch": 7.7, "learning_rate": 1.151199370821864e-05, "loss": 1.4534, "step": 1174500 }, { "epoch": 7.7, "learning_rate": 1.1495608860925417e-05, "loss": 1.4677, "step": 1175000 }, { "epoch": 7.7, "learning_rate": 1.1479224013632193e-05, "loss": 1.4278, "step": 1175500 }, { "epoch": 7.71, "learning_rate": 1.1462839166338971e-05, "loss": 1.4283, "step": 1176000 }, { "epoch": 7.71, "learning_rate": 1.1446454319045748e-05, "loss": 1.4331, "step": 1176500 }, { "epoch": 7.71, "learning_rate": 1.1430069471752523e-05, "loss": 1.4505, "step": 1177000 }, { "epoch": 7.72, "learning_rate": 1.1413684624459301e-05, "loss": 1.4727, "step": 1177500 }, { "epoch": 7.72, "learning_rate": 1.1397299777166077e-05, "loss": 1.4625, "step": 1178000 }, { "epoch": 7.72, "learning_rate": 1.1380914929872854e-05, "loss": 1.4608, "step": 1178500 }, { "epoch": 7.73, "learning_rate": 1.136453008257963e-05, "loss": 1.4624, "step": 1179000 }, { "epoch": 7.73, "learning_rate": 1.1348145235286407e-05, "loss": 1.4731, "step": 1179500 }, { "epoch": 7.73, "learning_rate": 1.1331760387993185e-05, "loss": 1.4519, "step": 1180000 }, { "epoch": 7.74, "learning_rate": 1.1315375540699962e-05, "loss": 1.4333, "step": 1180500 }, { "epoch": 7.74, "learning_rate": 1.1298990693406738e-05, "loss": 1.4683, "step": 1181000 }, { "epoch": 7.74, "learning_rate": 1.1282605846113515e-05, "loss": 1.4758, "step": 1181500 }, { "epoch": 7.75, "learning_rate": 1.1266220998820291e-05, "loss": 1.4787, "step": 1182000 }, { "epoch": 7.75, "learning_rate": 1.1249836151527068e-05, "loss": 1.4, "step": 1182500 }, { "epoch": 7.75, "learning_rate": 1.1233451304233846e-05, "loss": 1.44, "step": 1183000 }, { "epoch": 7.76, "learning_rate": 1.1217066456940622e-05, "loss": 1.4612, "step": 1183500 }, { "epoch": 7.76, "learning_rate": 1.1200681609647399e-05, "loss": 1.4972, "step": 1184000 }, { "epoch": 7.76, "learning_rate": 1.1184296762354176e-05, "loss": 1.4525, "step": 1184500 }, { "epoch": 7.77, "learning_rate": 1.1167911915060952e-05, "loss": 1.4619, "step": 1185000 }, { "epoch": 7.77, "learning_rate": 1.115152706776773e-05, "loss": 1.4268, "step": 1185500 }, { "epoch": 7.77, "learning_rate": 1.1135142220474505e-05, "loss": 1.4593, "step": 1186000 }, { "epoch": 7.78, "learning_rate": 1.1118757373181282e-05, "loss": 1.4562, "step": 1186500 }, { "epoch": 7.78, "learning_rate": 1.110237252588806e-05, "loss": 1.4393, "step": 1187000 }, { "epoch": 7.78, "learning_rate": 1.1085987678594836e-05, "loss": 1.449, "step": 1187500 }, { "epoch": 7.79, "learning_rate": 1.1069602831301613e-05, "loss": 1.459, "step": 1188000 }, { "epoch": 7.79, "learning_rate": 1.105321798400839e-05, "loss": 1.4085, "step": 1188500 }, { "epoch": 7.79, "learning_rate": 1.1036833136715166e-05, "loss": 1.4351, "step": 1189000 }, { "epoch": 7.8, "learning_rate": 1.1020448289421944e-05, "loss": 1.4362, "step": 1189500 }, { "epoch": 7.8, "learning_rate": 1.100406344212872e-05, "loss": 1.4881, "step": 1190000 }, { "epoch": 7.8, "learning_rate": 1.0987678594835495e-05, "loss": 1.4887, "step": 1190500 }, { "epoch": 7.81, "learning_rate": 1.0971293747542274e-05, "loss": 1.451, "step": 1191000 }, { "epoch": 7.81, "learning_rate": 1.095490890024905e-05, "loss": 1.4464, "step": 1191500 }, { "epoch": 7.81, "learning_rate": 1.0938524052955827e-05, "loss": 1.4212, "step": 1192000 }, { "epoch": 7.82, "learning_rate": 1.0922139205662605e-05, "loss": 1.4493, "step": 1192500 }, { "epoch": 7.82, "learning_rate": 1.090575435836938e-05, "loss": 1.4744, "step": 1193000 }, { "epoch": 7.82, "learning_rate": 1.0889369511076156e-05, "loss": 1.4258, "step": 1193500 }, { "epoch": 7.83, "learning_rate": 1.0872984663782934e-05, "loss": 1.439, "step": 1194000 }, { "epoch": 7.83, "learning_rate": 1.0856599816489711e-05, "loss": 1.4562, "step": 1194500 }, { "epoch": 7.83, "learning_rate": 1.0840214969196487e-05, "loss": 1.4765, "step": 1195000 }, { "epoch": 7.84, "learning_rate": 1.0823830121903264e-05, "loss": 1.4498, "step": 1195500 }, { "epoch": 7.84, "learning_rate": 1.080744527461004e-05, "loss": 1.436, "step": 1196000 }, { "epoch": 7.84, "learning_rate": 1.0791060427316819e-05, "loss": 1.4116, "step": 1196500 }, { "epoch": 7.85, "learning_rate": 1.0774675580023595e-05, "loss": 1.4569, "step": 1197000 }, { "epoch": 7.85, "learning_rate": 1.075829073273037e-05, "loss": 1.4358, "step": 1197500 }, { "epoch": 7.85, "learning_rate": 1.0741905885437148e-05, "loss": 1.4264, "step": 1198000 }, { "epoch": 7.85, "learning_rate": 1.0725521038143925e-05, "loss": 1.4382, "step": 1198500 }, { "epoch": 7.86, "learning_rate": 1.0709136190850701e-05, "loss": 1.4194, "step": 1199000 }, { "epoch": 7.86, "learning_rate": 1.069275134355748e-05, "loss": 1.4377, "step": 1199500 }, { "epoch": 7.86, "learning_rate": 1.0676366496264254e-05, "loss": 1.4627, "step": 1200000 }, { "epoch": 7.87, "learning_rate": 1.0659981648971033e-05, "loss": 1.4272, "step": 1200500 }, { "epoch": 7.87, "learning_rate": 1.0643596801677809e-05, "loss": 1.4583, "step": 1201000 }, { "epoch": 7.87, "learning_rate": 1.0627211954384586e-05, "loss": 1.4249, "step": 1201500 }, { "epoch": 7.88, "learning_rate": 1.0610827107091362e-05, "loss": 1.4692, "step": 1202000 }, { "epoch": 7.88, "learning_rate": 1.0594442259798139e-05, "loss": 1.4546, "step": 1202500 }, { "epoch": 7.88, "learning_rate": 1.0578057412504915e-05, "loss": 1.4386, "step": 1203000 }, { "epoch": 7.89, "learning_rate": 1.0561672565211693e-05, "loss": 1.5118, "step": 1203500 }, { "epoch": 7.89, "learning_rate": 1.054528771791847e-05, "loss": 1.4351, "step": 1204000 }, { "epoch": 7.89, "learning_rate": 1.0528902870625246e-05, "loss": 1.439, "step": 1204500 }, { "epoch": 7.9, "learning_rate": 1.0512518023332023e-05, "loss": 1.4634, "step": 1205000 }, { "epoch": 7.9, "learning_rate": 1.04961331760388e-05, "loss": 1.4317, "step": 1205500 }, { "epoch": 7.9, "learning_rate": 1.0479748328745578e-05, "loss": 1.4483, "step": 1206000 }, { "epoch": 7.91, "learning_rate": 1.0463363481452354e-05, "loss": 1.4465, "step": 1206500 }, { "epoch": 7.91, "learning_rate": 1.0446978634159129e-05, "loss": 1.4428, "step": 1207000 }, { "epoch": 7.91, "learning_rate": 1.0430593786865907e-05, "loss": 1.4653, "step": 1207500 }, { "epoch": 7.92, "learning_rate": 1.0414208939572684e-05, "loss": 1.4386, "step": 1208000 }, { "epoch": 7.92, "learning_rate": 1.039782409227946e-05, "loss": 1.4698, "step": 1208500 }, { "epoch": 7.92, "learning_rate": 1.0381439244986237e-05, "loss": 1.4336, "step": 1209000 }, { "epoch": 7.93, "learning_rate": 1.0365054397693013e-05, "loss": 1.45, "step": 1209500 }, { "epoch": 7.93, "learning_rate": 1.0348669550399791e-05, "loss": 1.4597, "step": 1210000 }, { "epoch": 7.93, "learning_rate": 1.0332284703106568e-05, "loss": 1.4364, "step": 1210500 }, { "epoch": 7.94, "learning_rate": 1.0315899855813345e-05, "loss": 1.4614, "step": 1211000 }, { "epoch": 7.94, "learning_rate": 1.0299515008520121e-05, "loss": 1.4695, "step": 1211500 }, { "epoch": 7.94, "learning_rate": 1.0283130161226898e-05, "loss": 1.4425, "step": 1212000 }, { "epoch": 7.95, "learning_rate": 1.0266745313933674e-05, "loss": 1.4773, "step": 1212500 }, { "epoch": 7.95, "learning_rate": 1.0250360466640452e-05, "loss": 1.4471, "step": 1213000 }, { "epoch": 7.95, "learning_rate": 1.0233975619347227e-05, "loss": 1.4834, "step": 1213500 }, { "epoch": 7.96, "learning_rate": 1.0217590772054005e-05, "loss": 1.4587, "step": 1214000 }, { "epoch": 7.96, "learning_rate": 1.0201205924760782e-05, "loss": 1.4663, "step": 1214500 }, { "epoch": 7.96, "learning_rate": 1.0184821077467558e-05, "loss": 1.4377, "step": 1215000 }, { "epoch": 7.97, "learning_rate": 1.0168436230174337e-05, "loss": 1.4419, "step": 1215500 }, { "epoch": 7.97, "learning_rate": 1.0152051382881111e-05, "loss": 1.4289, "step": 1216000 }, { "epoch": 7.97, "learning_rate": 1.0135666535587888e-05, "loss": 1.4944, "step": 1216500 }, { "epoch": 7.98, "learning_rate": 1.0119281688294666e-05, "loss": 1.4558, "step": 1217000 }, { "epoch": 7.98, "learning_rate": 1.0102896841001443e-05, "loss": 1.4273, "step": 1217500 }, { "epoch": 7.98, "learning_rate": 1.008651199370822e-05, "loss": 1.4294, "step": 1218000 }, { "epoch": 7.99, "learning_rate": 1.0070127146414996e-05, "loss": 1.4523, "step": 1218500 }, { "epoch": 7.99, "learning_rate": 1.0053742299121772e-05, "loss": 1.4594, "step": 1219000 }, { "epoch": 7.99, "learning_rate": 1.003735745182855e-05, "loss": 1.4469, "step": 1219500 }, { "epoch": 8.0, "learning_rate": 1.0020972604535327e-05, "loss": 1.4511, "step": 1220000 }, { "epoch": 8.0, "learning_rate": 1.0004587757242102e-05, "loss": 1.4332, "step": 1220500 }, { "epoch": 8.0, "learning_rate": 9.98820290994888e-06, "loss": 1.4385, "step": 1221000 }, { "epoch": 8.01, "learning_rate": 9.971818062655656e-06, "loss": 1.4629, "step": 1221500 }, { "epoch": 8.01, "learning_rate": 9.955433215362433e-06, "loss": 1.44, "step": 1222000 }, { "epoch": 8.01, "learning_rate": 9.939048368069211e-06, "loss": 1.4398, "step": 1222500 }, { "epoch": 8.02, "learning_rate": 9.922663520775986e-06, "loss": 1.4562, "step": 1223000 }, { "epoch": 8.02, "learning_rate": 9.906278673482763e-06, "loss": 1.4298, "step": 1223500 }, { "epoch": 8.02, "learning_rate": 9.88989382618954e-06, "loss": 1.4309, "step": 1224000 }, { "epoch": 8.03, "learning_rate": 9.873508978896317e-06, "loss": 1.4461, "step": 1224500 }, { "epoch": 8.03, "learning_rate": 9.857124131603094e-06, "loss": 1.4279, "step": 1225000 }, { "epoch": 8.03, "learning_rate": 9.84073928430987e-06, "loss": 1.4439, "step": 1225500 }, { "epoch": 8.04, "learning_rate": 9.824354437016647e-06, "loss": 1.4424, "step": 1226000 }, { "epoch": 8.04, "learning_rate": 9.807969589723425e-06, "loss": 1.483, "step": 1226500 }, { "epoch": 8.04, "learning_rate": 9.791584742430202e-06, "loss": 1.4268, "step": 1227000 }, { "epoch": 8.04, "learning_rate": 9.775199895136976e-06, "loss": 1.43, "step": 1227500 }, { "epoch": 8.05, "learning_rate": 9.758815047843755e-06, "loss": 1.447, "step": 1228000 }, { "epoch": 8.05, "learning_rate": 9.742430200550531e-06, "loss": 1.4181, "step": 1228500 }, { "epoch": 8.05, "learning_rate": 9.726045353257308e-06, "loss": 1.4381, "step": 1229000 }, { "epoch": 8.06, "learning_rate": 9.709660505964086e-06, "loss": 1.4372, "step": 1229500 }, { "epoch": 8.06, "learning_rate": 9.69327565867086e-06, "loss": 1.4274, "step": 1230000 }, { "epoch": 8.06, "learning_rate": 9.676890811377639e-06, "loss": 1.4279, "step": 1230500 }, { "epoch": 8.07, "learning_rate": 9.660505964084415e-06, "loss": 1.4509, "step": 1231000 }, { "epoch": 8.07, "learning_rate": 9.644121116791192e-06, "loss": 1.4608, "step": 1231500 }, { "epoch": 8.07, "learning_rate": 9.627736269497968e-06, "loss": 1.4322, "step": 1232000 }, { "epoch": 8.08, "learning_rate": 9.611351422204745e-06, "loss": 1.4098, "step": 1232500 }, { "epoch": 8.08, "learning_rate": 9.594966574911521e-06, "loss": 1.4406, "step": 1233000 }, { "epoch": 8.08, "learning_rate": 9.5785817276183e-06, "loss": 1.4757, "step": 1233500 }, { "epoch": 8.09, "learning_rate": 9.562196880325076e-06, "loss": 1.4314, "step": 1234000 }, { "epoch": 8.09, "learning_rate": 9.545812033031853e-06, "loss": 1.4108, "step": 1234500 }, { "epoch": 8.09, "learning_rate": 9.52942718573863e-06, "loss": 1.4957, "step": 1235000 }, { "epoch": 8.1, "learning_rate": 9.513042338445406e-06, "loss": 1.4502, "step": 1235500 }, { "epoch": 8.1, "learning_rate": 9.496657491152184e-06, "loss": 1.4514, "step": 1236000 }, { "epoch": 8.1, "learning_rate": 9.48027264385896e-06, "loss": 1.4084, "step": 1236500 }, { "epoch": 8.11, "learning_rate": 9.463887796565735e-06, "loss": 1.444, "step": 1237000 }, { "epoch": 8.11, "learning_rate": 9.447502949272514e-06, "loss": 1.4355, "step": 1237500 }, { "epoch": 8.11, "learning_rate": 9.43111810197929e-06, "loss": 1.431, "step": 1238000 }, { "epoch": 8.12, "learning_rate": 9.414733254686067e-06, "loss": 1.4355, "step": 1238500 }, { "epoch": 8.12, "learning_rate": 9.398348407392843e-06, "loss": 1.4645, "step": 1239000 }, { "epoch": 8.12, "learning_rate": 9.38196356009962e-06, "loss": 1.4668, "step": 1239500 }, { "epoch": 8.13, "learning_rate": 9.365578712806398e-06, "loss": 1.4083, "step": 1240000 }, { "epoch": 8.13, "learning_rate": 9.349193865513174e-06, "loss": 1.438, "step": 1240500 }, { "epoch": 8.13, "learning_rate": 9.332809018219951e-06, "loss": 1.4295, "step": 1241000 }, { "epoch": 8.14, "learning_rate": 9.316424170926727e-06, "loss": 1.4866, "step": 1241500 }, { "epoch": 8.14, "learning_rate": 9.300039323633504e-06, "loss": 1.48, "step": 1242000 }, { "epoch": 8.14, "learning_rate": 9.28365447634028e-06, "loss": 1.4324, "step": 1242500 }, { "epoch": 8.15, "learning_rate": 9.267269629047059e-06, "loss": 1.4076, "step": 1243000 }, { "epoch": 8.15, "learning_rate": 9.250884781753833e-06, "loss": 1.3799, "step": 1243500 }, { "epoch": 8.15, "learning_rate": 9.234499934460612e-06, "loss": 1.4266, "step": 1244000 }, { "epoch": 8.16, "learning_rate": 9.218115087167388e-06, "loss": 1.3834, "step": 1244500 }, { "epoch": 8.16, "learning_rate": 9.201730239874165e-06, "loss": 1.4469, "step": 1245000 }, { "epoch": 8.16, "learning_rate": 9.185345392580943e-06, "loss": 1.4418, "step": 1245500 }, { "epoch": 8.17, "learning_rate": 9.168960545287718e-06, "loss": 1.4313, "step": 1246000 }, { "epoch": 8.17, "learning_rate": 9.152575697994494e-06, "loss": 1.4509, "step": 1246500 }, { "epoch": 8.17, "learning_rate": 9.136190850701272e-06, "loss": 1.4494, "step": 1247000 }, { "epoch": 8.18, "learning_rate": 9.119806003408049e-06, "loss": 1.4509, "step": 1247500 }, { "epoch": 8.18, "learning_rate": 9.103421156114826e-06, "loss": 1.4878, "step": 1248000 }, { "epoch": 8.18, "learning_rate": 9.087036308821602e-06, "loss": 1.445, "step": 1248500 }, { "epoch": 8.19, "learning_rate": 9.070651461528379e-06, "loss": 1.4207, "step": 1249000 }, { "epoch": 8.19, "learning_rate": 9.054266614235157e-06, "loss": 1.4182, "step": 1249500 }, { "epoch": 8.19, "learning_rate": 9.037881766941933e-06, "loss": 1.4205, "step": 1250000 }, { "epoch": 8.2, "learning_rate": 9.021496919648708e-06, "loss": 1.3915, "step": 1250500 }, { "epoch": 8.2, "learning_rate": 9.005112072355486e-06, "loss": 1.4361, "step": 1251000 }, { "epoch": 8.2, "learning_rate": 8.988727225062263e-06, "loss": 1.4413, "step": 1251500 }, { "epoch": 8.21, "learning_rate": 8.97234237776904e-06, "loss": 1.4592, "step": 1252000 }, { "epoch": 8.21, "learning_rate": 8.955957530475818e-06, "loss": 1.4072, "step": 1252500 }, { "epoch": 8.21, "learning_rate": 8.939572683182592e-06, "loss": 1.4685, "step": 1253000 }, { "epoch": 8.22, "learning_rate": 8.923187835889369e-06, "loss": 1.4127, "step": 1253500 }, { "epoch": 8.22, "learning_rate": 8.906802988596147e-06, "loss": 1.4301, "step": 1254000 }, { "epoch": 8.22, "learning_rate": 8.890418141302924e-06, "loss": 1.4382, "step": 1254500 }, { "epoch": 8.23, "learning_rate": 8.8740332940097e-06, "loss": 1.4696, "step": 1255000 }, { "epoch": 8.23, "learning_rate": 8.857648446716477e-06, "loss": 1.4391, "step": 1255500 }, { "epoch": 8.23, "learning_rate": 8.841263599423253e-06, "loss": 1.4619, "step": 1256000 }, { "epoch": 8.24, "learning_rate": 8.824878752130031e-06, "loss": 1.4328, "step": 1256500 }, { "epoch": 8.24, "learning_rate": 8.808493904836808e-06, "loss": 1.434, "step": 1257000 }, { "epoch": 8.24, "learning_rate": 8.792109057543583e-06, "loss": 1.5038, "step": 1257500 }, { "epoch": 8.24, "learning_rate": 8.775724210250361e-06, "loss": 1.4083, "step": 1258000 }, { "epoch": 8.25, "learning_rate": 8.759339362957137e-06, "loss": 1.4407, "step": 1258500 }, { "epoch": 8.25, "learning_rate": 8.742954515663914e-06, "loss": 1.4398, "step": 1259000 }, { "epoch": 8.25, "learning_rate": 8.726569668370692e-06, "loss": 1.4669, "step": 1259500 }, { "epoch": 8.26, "learning_rate": 8.710184821077467e-06, "loss": 1.4523, "step": 1260000 }, { "epoch": 8.26, "learning_rate": 8.693799973784245e-06, "loss": 1.4432, "step": 1260500 }, { "epoch": 8.26, "learning_rate": 8.677415126491022e-06, "loss": 1.4403, "step": 1261000 }, { "epoch": 8.27, "learning_rate": 8.661030279197798e-06, "loss": 1.457, "step": 1261500 }, { "epoch": 8.27, "learning_rate": 8.644645431904575e-06, "loss": 1.4521, "step": 1262000 }, { "epoch": 8.27, "learning_rate": 8.628260584611351e-06, "loss": 1.4427, "step": 1262500 }, { "epoch": 8.28, "learning_rate": 8.611875737318128e-06, "loss": 1.433, "step": 1263000 }, { "epoch": 8.28, "learning_rate": 8.595490890024906e-06, "loss": 1.4879, "step": 1263500 }, { "epoch": 8.28, "learning_rate": 8.579106042731683e-06, "loss": 1.454, "step": 1264000 }, { "epoch": 8.29, "learning_rate": 8.562721195438459e-06, "loss": 1.4282, "step": 1264500 }, { "epoch": 8.29, "learning_rate": 8.546336348145236e-06, "loss": 1.4396, "step": 1265000 }, { "epoch": 8.29, "learning_rate": 8.529951500852012e-06, "loss": 1.4215, "step": 1265500 }, { "epoch": 8.3, "learning_rate": 8.51356665355879e-06, "loss": 1.4183, "step": 1266000 }, { "epoch": 8.3, "learning_rate": 8.497181806265567e-06, "loss": 1.4182, "step": 1266500 }, { "epoch": 8.3, "learning_rate": 8.480796958972342e-06, "loss": 1.4163, "step": 1267000 }, { "epoch": 8.31, "learning_rate": 8.46441211167912e-06, "loss": 1.4526, "step": 1267500 }, { "epoch": 8.31, "learning_rate": 8.448027264385896e-06, "loss": 1.4676, "step": 1268000 }, { "epoch": 8.31, "learning_rate": 8.431642417092673e-06, "loss": 1.4409, "step": 1268500 }, { "epoch": 8.32, "learning_rate": 8.41525756979945e-06, "loss": 1.4459, "step": 1269000 }, { "epoch": 8.32, "learning_rate": 8.398872722506226e-06, "loss": 1.4608, "step": 1269500 }, { "epoch": 8.32, "learning_rate": 8.382487875213004e-06, "loss": 1.4461, "step": 1270000 }, { "epoch": 8.33, "learning_rate": 8.36610302791978e-06, "loss": 1.4568, "step": 1270500 }, { "epoch": 8.33, "learning_rate": 8.349718180626557e-06, "loss": 1.4498, "step": 1271000 }, { "epoch": 8.33, "learning_rate": 8.333333333333334e-06, "loss": 1.4327, "step": 1271500 }, { "epoch": 8.34, "learning_rate": 8.31694848604011e-06, "loss": 1.4315, "step": 1272000 }, { "epoch": 8.34, "learning_rate": 8.300563638746887e-06, "loss": 1.4184, "step": 1272500 }, { "epoch": 8.34, "learning_rate": 8.284178791453665e-06, "loss": 1.398, "step": 1273000 }, { "epoch": 8.35, "learning_rate": 8.26779394416044e-06, "loss": 1.4309, "step": 1273500 }, { "epoch": 8.35, "learning_rate": 8.251409096867218e-06, "loss": 1.4143, "step": 1274000 }, { "epoch": 8.35, "learning_rate": 8.235024249573995e-06, "loss": 1.4488, "step": 1274500 }, { "epoch": 8.36, "learning_rate": 8.218639402280771e-06, "loss": 1.4456, "step": 1275000 }, { "epoch": 8.36, "learning_rate": 8.20225455498755e-06, "loss": 1.37, "step": 1275500 }, { "epoch": 8.36, "learning_rate": 8.185869707694324e-06, "loss": 1.4353, "step": 1276000 }, { "epoch": 8.37, "learning_rate": 8.1694848604011e-06, "loss": 1.4525, "step": 1276500 }, { "epoch": 8.37, "learning_rate": 8.153100013107879e-06, "loss": 1.4672, "step": 1277000 }, { "epoch": 8.37, "learning_rate": 8.136715165814655e-06, "loss": 1.4598, "step": 1277500 }, { "epoch": 8.38, "learning_rate": 8.120330318521432e-06, "loss": 1.4231, "step": 1278000 }, { "epoch": 8.38, "learning_rate": 8.103945471228208e-06, "loss": 1.4259, "step": 1278500 }, { "epoch": 8.38, "learning_rate": 8.087560623934985e-06, "loss": 1.432, "step": 1279000 }, { "epoch": 8.39, "learning_rate": 8.071175776641763e-06, "loss": 1.4408, "step": 1279500 }, { "epoch": 8.39, "learning_rate": 8.05479092934854e-06, "loss": 1.4803, "step": 1280000 }, { "epoch": 8.39, "learning_rate": 8.038406082055314e-06, "loss": 1.4435, "step": 1280500 }, { "epoch": 8.4, "learning_rate": 8.022021234762093e-06, "loss": 1.4366, "step": 1281000 }, { "epoch": 8.4, "learning_rate": 8.00563638746887e-06, "loss": 1.4395, "step": 1281500 }, { "epoch": 8.4, "learning_rate": 7.989251540175646e-06, "loss": 1.4399, "step": 1282000 }, { "epoch": 8.41, "learning_rate": 7.972866692882424e-06, "loss": 1.4422, "step": 1282500 }, { "epoch": 8.41, "learning_rate": 7.956481845589199e-06, "loss": 1.4494, "step": 1283000 }, { "epoch": 8.41, "learning_rate": 7.940096998295975e-06, "loss": 1.4475, "step": 1283500 }, { "epoch": 8.42, "learning_rate": 7.923712151002753e-06, "loss": 1.4277, "step": 1284000 }, { "epoch": 8.42, "learning_rate": 7.90732730370953e-06, "loss": 1.4023, "step": 1284500 }, { "epoch": 8.42, "learning_rate": 7.890942456416307e-06, "loss": 1.4146, "step": 1285000 }, { "epoch": 8.43, "learning_rate": 7.874557609123083e-06, "loss": 1.4445, "step": 1285500 }, { "epoch": 8.43, "learning_rate": 7.85817276182986e-06, "loss": 1.4172, "step": 1286000 }, { "epoch": 8.43, "learning_rate": 7.841787914536638e-06, "loss": 1.4402, "step": 1286500 }, { "epoch": 8.43, "learning_rate": 7.825403067243414e-06, "loss": 1.4586, "step": 1287000 }, { "epoch": 8.44, "learning_rate": 7.809018219950189e-06, "loss": 1.4238, "step": 1287500 }, { "epoch": 8.44, "learning_rate": 7.792633372656967e-06, "loss": 1.4172, "step": 1288000 }, { "epoch": 8.44, "learning_rate": 7.776248525363744e-06, "loss": 1.4415, "step": 1288500 }, { "epoch": 8.45, "learning_rate": 7.75986367807052e-06, "loss": 1.4585, "step": 1289000 }, { "epoch": 8.45, "learning_rate": 7.743478830777299e-06, "loss": 1.4691, "step": 1289500 }, { "epoch": 8.45, "learning_rate": 7.727093983484073e-06, "loss": 1.4232, "step": 1290000 }, { "epoch": 8.46, "learning_rate": 7.710709136190852e-06, "loss": 1.4365, "step": 1290500 }, { "epoch": 8.46, "learning_rate": 7.694324288897628e-06, "loss": 1.4412, "step": 1291000 }, { "epoch": 8.46, "learning_rate": 7.677939441604405e-06, "loss": 1.4406, "step": 1291500 }, { "epoch": 8.47, "learning_rate": 7.661554594311181e-06, "loss": 1.449, "step": 1292000 }, { "epoch": 8.47, "learning_rate": 7.645169747017958e-06, "loss": 1.4511, "step": 1292500 }, { "epoch": 8.47, "learning_rate": 7.628784899724735e-06, "loss": 1.4224, "step": 1293000 }, { "epoch": 8.48, "learning_rate": 7.612400052431512e-06, "loss": 1.4337, "step": 1293500 }, { "epoch": 8.48, "learning_rate": 7.596015205138289e-06, "loss": 1.4482, "step": 1294000 }, { "epoch": 8.48, "learning_rate": 7.579630357845065e-06, "loss": 1.4253, "step": 1294500 }, { "epoch": 8.49, "learning_rate": 7.563245510551842e-06, "loss": 1.4216, "step": 1295000 }, { "epoch": 8.49, "learning_rate": 7.546860663258619e-06, "loss": 1.4139, "step": 1295500 }, { "epoch": 8.49, "learning_rate": 7.530475815965396e-06, "loss": 1.4126, "step": 1296000 }, { "epoch": 8.5, "learning_rate": 7.5140909686721715e-06, "loss": 1.4307, "step": 1296500 }, { "epoch": 8.5, "learning_rate": 7.497706121378949e-06, "loss": 1.4384, "step": 1297000 }, { "epoch": 8.5, "learning_rate": 7.481321274085725e-06, "loss": 1.4668, "step": 1297500 }, { "epoch": 8.51, "learning_rate": 7.464936426792503e-06, "loss": 1.4265, "step": 1298000 }, { "epoch": 8.51, "learning_rate": 7.44855157949928e-06, "loss": 1.4547, "step": 1298500 }, { "epoch": 8.51, "learning_rate": 7.432166732206056e-06, "loss": 1.4333, "step": 1299000 }, { "epoch": 8.52, "learning_rate": 7.415781884912832e-06, "loss": 1.4274, "step": 1299500 }, { "epoch": 8.52, "learning_rate": 7.39939703761961e-06, "loss": 1.4559, "step": 1300000 }, { "epoch": 8.52, "learning_rate": 7.383012190326387e-06, "loss": 1.439, "step": 1300500 }, { "epoch": 8.53, "learning_rate": 7.3666273430331636e-06, "loss": 1.4339, "step": 1301000 }, { "epoch": 8.53, "learning_rate": 7.350242495739939e-06, "loss": 1.4417, "step": 1301500 }, { "epoch": 8.53, "learning_rate": 7.333857648446717e-06, "loss": 1.4711, "step": 1302000 }, { "epoch": 8.54, "learning_rate": 7.317472801153494e-06, "loss": 1.4091, "step": 1302500 }, { "epoch": 8.54, "learning_rate": 7.3010879538602705e-06, "loss": 1.43, "step": 1303000 }, { "epoch": 8.54, "learning_rate": 7.284703106567046e-06, "loss": 1.4499, "step": 1303500 }, { "epoch": 8.55, "learning_rate": 7.2683182592738235e-06, "loss": 1.4618, "step": 1304000 }, { "epoch": 8.55, "learning_rate": 7.251933411980601e-06, "loss": 1.4296, "step": 1304500 }, { "epoch": 8.55, "learning_rate": 7.235548564687377e-06, "loss": 1.4364, "step": 1305000 }, { "epoch": 8.56, "learning_rate": 7.219163717394155e-06, "loss": 1.4078, "step": 1305500 }, { "epoch": 8.56, "learning_rate": 7.2027788701009304e-06, "loss": 1.4561, "step": 1306000 }, { "epoch": 8.56, "learning_rate": 7.186394022807708e-06, "loss": 1.4275, "step": 1306500 }, { "epoch": 8.57, "learning_rate": 7.170009175514484e-06, "loss": 1.4395, "step": 1307000 }, { "epoch": 8.57, "learning_rate": 7.153624328221262e-06, "loss": 1.4623, "step": 1307500 }, { "epoch": 8.57, "learning_rate": 7.137239480928037e-06, "loss": 1.4413, "step": 1308000 }, { "epoch": 8.58, "learning_rate": 7.120854633634815e-06, "loss": 1.434, "step": 1308500 }, { "epoch": 8.58, "learning_rate": 7.104469786341591e-06, "loss": 1.4475, "step": 1309000 }, { "epoch": 8.58, "learning_rate": 7.088084939048369e-06, "loss": 1.4526, "step": 1309500 }, { "epoch": 8.59, "learning_rate": 7.071700091755146e-06, "loss": 1.4732, "step": 1310000 }, { "epoch": 8.59, "learning_rate": 7.055315244461922e-06, "loss": 1.4369, "step": 1310500 }, { "epoch": 8.59, "learning_rate": 7.038930397168698e-06, "loss": 1.4487, "step": 1311000 }, { "epoch": 8.6, "learning_rate": 7.0225455498754755e-06, "loss": 1.4472, "step": 1311500 }, { "epoch": 8.6, "learning_rate": 7.006160702582253e-06, "loss": 1.459, "step": 1312000 }, { "epoch": 8.6, "learning_rate": 6.989775855289029e-06, "loss": 1.4371, "step": 1312500 }, { "epoch": 8.61, "learning_rate": 6.973391007995805e-06, "loss": 1.4732, "step": 1313000 }, { "epoch": 8.61, "learning_rate": 6.9570061607025824e-06, "loss": 1.4407, "step": 1313500 }, { "epoch": 8.61, "learning_rate": 6.94062131340936e-06, "loss": 1.4238, "step": 1314000 }, { "epoch": 8.62, "learning_rate": 6.924236466116136e-06, "loss": 1.43, "step": 1314500 }, { "epoch": 8.62, "learning_rate": 6.907851618822912e-06, "loss": 1.4136, "step": 1315000 }, { "epoch": 8.62, "learning_rate": 6.891466771529689e-06, "loss": 1.4217, "step": 1315500 }, { "epoch": 8.62, "learning_rate": 6.875081924236467e-06, "loss": 1.4662, "step": 1316000 }, { "epoch": 8.63, "learning_rate": 6.858697076943243e-06, "loss": 1.4494, "step": 1316500 }, { "epoch": 8.63, "learning_rate": 6.842312229650021e-06, "loss": 1.4271, "step": 1317000 }, { "epoch": 8.63, "learning_rate": 6.825927382356796e-06, "loss": 1.4175, "step": 1317500 }, { "epoch": 8.64, "learning_rate": 6.809542535063574e-06, "loss": 1.4445, "step": 1318000 }, { "epoch": 8.64, "learning_rate": 6.79315768777035e-06, "loss": 1.4398, "step": 1318500 }, { "epoch": 8.64, "learning_rate": 6.7767728404771275e-06, "loss": 1.4527, "step": 1319000 }, { "epoch": 8.65, "learning_rate": 6.760387993183905e-06, "loss": 1.4676, "step": 1319500 }, { "epoch": 8.65, "learning_rate": 6.7440031458906806e-06, "loss": 1.4267, "step": 1320000 }, { "epoch": 8.65, "learning_rate": 6.727618298597457e-06, "loss": 1.4007, "step": 1320500 }, { "epoch": 8.66, "learning_rate": 6.7112334513042344e-06, "loss": 1.4167, "step": 1321000 }, { "epoch": 8.66, "learning_rate": 6.694848604011012e-06, "loss": 1.4245, "step": 1321500 }, { "epoch": 8.66, "learning_rate": 6.6784637567177875e-06, "loss": 1.4338, "step": 1322000 }, { "epoch": 8.67, "learning_rate": 6.662078909424564e-06, "loss": 1.4551, "step": 1322500 }, { "epoch": 8.67, "learning_rate": 6.645694062131341e-06, "loss": 1.438, "step": 1323000 }, { "epoch": 8.67, "learning_rate": 6.629309214838119e-06, "loss": 1.396, "step": 1323500 }, { "epoch": 8.68, "learning_rate": 6.612924367544895e-06, "loss": 1.4483, "step": 1324000 }, { "epoch": 8.68, "learning_rate": 6.596539520251671e-06, "loss": 1.3997, "step": 1324500 }, { "epoch": 8.68, "learning_rate": 6.580154672958448e-06, "loss": 1.4208, "step": 1325000 }, { "epoch": 8.69, "learning_rate": 6.563769825665226e-06, "loss": 1.4323, "step": 1325500 }, { "epoch": 8.69, "learning_rate": 6.547384978372002e-06, "loss": 1.4518, "step": 1326000 }, { "epoch": 8.69, "learning_rate": 6.531000131078778e-06, "loss": 1.4101, "step": 1326500 }, { "epoch": 8.7, "learning_rate": 6.514615283785555e-06, "loss": 1.4339, "step": 1327000 }, { "epoch": 8.7, "learning_rate": 6.4982304364923326e-06, "loss": 1.3869, "step": 1327500 }, { "epoch": 8.7, "learning_rate": 6.481845589199109e-06, "loss": 1.4457, "step": 1328000 }, { "epoch": 8.71, "learning_rate": 6.4654607419058865e-06, "loss": 1.4736, "step": 1328500 }, { "epoch": 8.71, "learning_rate": 6.449075894612662e-06, "loss": 1.4183, "step": 1329000 }, { "epoch": 8.71, "learning_rate": 6.432691047319439e-06, "loss": 1.4174, "step": 1329500 }, { "epoch": 8.72, "learning_rate": 6.416306200026216e-06, "loss": 1.432, "step": 1330000 }, { "epoch": 8.72, "learning_rate": 6.399921352732993e-06, "loss": 1.4099, "step": 1330500 }, { "epoch": 8.72, "learning_rate": 6.38353650543977e-06, "loss": 1.4228, "step": 1331000 }, { "epoch": 8.73, "learning_rate": 6.3671516581465456e-06, "loss": 1.4025, "step": 1331500 }, { "epoch": 8.73, "learning_rate": 6.350766810853323e-06, "loss": 1.4383, "step": 1332000 }, { "epoch": 8.73, "learning_rate": 6.3343819635601e-06, "loss": 1.4294, "step": 1332500 }, { "epoch": 8.74, "learning_rate": 6.317997116266877e-06, "loss": 1.41, "step": 1333000 }, { "epoch": 8.74, "learning_rate": 6.3016122689736525e-06, "loss": 1.4277, "step": 1333500 }, { "epoch": 8.74, "learning_rate": 6.28522742168043e-06, "loss": 1.4054, "step": 1334000 }, { "epoch": 8.75, "learning_rate": 6.268842574387207e-06, "loss": 1.3942, "step": 1334500 }, { "epoch": 8.75, "learning_rate": 6.252457727093984e-06, "loss": 1.4525, "step": 1335000 }, { "epoch": 8.75, "learning_rate": 6.23607287980076e-06, "loss": 1.4429, "step": 1335500 }, { "epoch": 8.76, "learning_rate": 6.219688032507538e-06, "loss": 1.4224, "step": 1336000 }, { "epoch": 8.76, "learning_rate": 6.203303185214314e-06, "loss": 1.4269, "step": 1336500 }, { "epoch": 8.76, "learning_rate": 6.186918337921091e-06, "loss": 1.4456, "step": 1337000 }, { "epoch": 8.77, "learning_rate": 6.170533490627867e-06, "loss": 1.4019, "step": 1337500 }, { "epoch": 8.77, "learning_rate": 6.1541486433346445e-06, "loss": 1.4472, "step": 1338000 }, { "epoch": 8.77, "learning_rate": 6.137763796041422e-06, "loss": 1.433, "step": 1338500 }, { "epoch": 8.78, "learning_rate": 6.121378948748198e-06, "loss": 1.4547, "step": 1339000 }, { "epoch": 8.78, "learning_rate": 6.104994101454975e-06, "loss": 1.4193, "step": 1339500 }, { "epoch": 8.78, "learning_rate": 6.0886092541617515e-06, "loss": 1.447, "step": 1340000 }, { "epoch": 8.79, "learning_rate": 6.072224406868529e-06, "loss": 1.4262, "step": 1340500 }, { "epoch": 8.79, "learning_rate": 6.0558395595753045e-06, "loss": 1.4219, "step": 1341000 }, { "epoch": 8.79, "learning_rate": 6.039454712282082e-06, "loss": 1.426, "step": 1341500 }, { "epoch": 8.8, "learning_rate": 6.023069864988858e-06, "loss": 1.397, "step": 1342000 }, { "epoch": 8.8, "learning_rate": 6.006685017695636e-06, "loss": 1.4205, "step": 1342500 }, { "epoch": 8.8, "learning_rate": 5.990300170402412e-06, "loss": 1.4694, "step": 1343000 }, { "epoch": 8.81, "learning_rate": 5.973915323109189e-06, "loss": 1.4087, "step": 1343500 }, { "epoch": 8.81, "learning_rate": 5.957530475815966e-06, "loss": 1.4621, "step": 1344000 }, { "epoch": 8.81, "learning_rate": 5.941145628522742e-06, "loss": 1.429, "step": 1344500 }, { "epoch": 8.82, "learning_rate": 5.924760781229519e-06, "loss": 1.4095, "step": 1345000 }, { "epoch": 8.82, "learning_rate": 5.908375933936296e-06, "loss": 1.3976, "step": 1345500 }, { "epoch": 8.82, "learning_rate": 5.891991086643073e-06, "loss": 1.4534, "step": 1346000 }, { "epoch": 8.82, "learning_rate": 5.87560623934985e-06, "loss": 1.4267, "step": 1346500 }, { "epoch": 8.83, "learning_rate": 5.859221392056626e-06, "loss": 1.4601, "step": 1347000 }, { "epoch": 8.83, "learning_rate": 5.8428365447634035e-06, "loss": 1.4087, "step": 1347500 }, { "epoch": 8.83, "learning_rate": 5.82645169747018e-06, "loss": 1.43, "step": 1348000 }, { "epoch": 8.84, "learning_rate": 5.8100668501769565e-06, "loss": 1.4312, "step": 1348500 }, { "epoch": 8.84, "learning_rate": 5.793682002883733e-06, "loss": 1.4348, "step": 1349000 }, { "epoch": 8.84, "learning_rate": 5.77729715559051e-06, "loss": 1.4639, "step": 1349500 }, { "epoch": 8.85, "learning_rate": 5.760912308297287e-06, "loss": 1.4419, "step": 1350000 }, { "epoch": 8.85, "learning_rate": 5.7445274610040634e-06, "loss": 1.4493, "step": 1350500 }, { "epoch": 8.85, "learning_rate": 5.728142613710841e-06, "loss": 1.4016, "step": 1351000 }, { "epoch": 8.86, "learning_rate": 5.711757766417617e-06, "loss": 1.4149, "step": 1351500 }, { "epoch": 8.86, "learning_rate": 5.695372919124394e-06, "loss": 1.4637, "step": 1352000 }, { "epoch": 8.86, "learning_rate": 5.67898807183117e-06, "loss": 1.4376, "step": 1352500 }, { "epoch": 8.87, "learning_rate": 5.662603224537948e-06, "loss": 1.4254, "step": 1353000 }, { "epoch": 8.87, "learning_rate": 5.646218377244725e-06, "loss": 1.462, "step": 1353500 }, { "epoch": 8.87, "learning_rate": 5.629833529951501e-06, "loss": 1.4151, "step": 1354000 }, { "epoch": 8.88, "learning_rate": 5.613448682658278e-06, "loss": 1.4318, "step": 1354500 }, { "epoch": 8.88, "learning_rate": 5.597063835365055e-06, "loss": 1.4325, "step": 1355000 }, { "epoch": 8.88, "learning_rate": 5.580678988071832e-06, "loss": 1.426, "step": 1355500 }, { "epoch": 8.89, "learning_rate": 5.564294140778608e-06, "loss": 1.4374, "step": 1356000 }, { "epoch": 8.89, "learning_rate": 5.547909293485385e-06, "loss": 1.4458, "step": 1356500 }, { "epoch": 8.89, "learning_rate": 5.5315244461921616e-06, "loss": 1.4652, "step": 1357000 }, { "epoch": 8.9, "learning_rate": 5.515139598898939e-06, "loss": 1.4682, "step": 1357500 }, { "epoch": 8.9, "learning_rate": 5.4987547516057154e-06, "loss": 1.4497, "step": 1358000 }, { "epoch": 8.9, "learning_rate": 5.482369904312492e-06, "loss": 1.4697, "step": 1358500 }, { "epoch": 8.91, "learning_rate": 5.465985057019269e-06, "loss": 1.4094, "step": 1359000 }, { "epoch": 8.91, "learning_rate": 5.449600209726045e-06, "loss": 1.4449, "step": 1359500 }, { "epoch": 8.91, "learning_rate": 5.433215362432822e-06, "loss": 1.4242, "step": 1360000 }, { "epoch": 8.92, "learning_rate": 5.416830515139599e-06, "loss": 1.4245, "step": 1360500 }, { "epoch": 8.92, "learning_rate": 5.400445667846376e-06, "loss": 1.4806, "step": 1361000 }, { "epoch": 8.92, "learning_rate": 5.384060820553153e-06, "loss": 1.4133, "step": 1361500 }, { "epoch": 8.93, "learning_rate": 5.367675973259929e-06, "loss": 1.4709, "step": 1362000 }, { "epoch": 8.93, "learning_rate": 5.351291125966707e-06, "loss": 1.4428, "step": 1362500 }, { "epoch": 8.93, "learning_rate": 5.334906278673483e-06, "loss": 1.4302, "step": 1363000 }, { "epoch": 8.94, "learning_rate": 5.31852143138026e-06, "loss": 1.4299, "step": 1363500 }, { "epoch": 8.94, "learning_rate": 5.302136584087036e-06, "loss": 1.4406, "step": 1364000 }, { "epoch": 8.94, "learning_rate": 5.2857517367938136e-06, "loss": 1.4465, "step": 1364500 }, { "epoch": 8.95, "learning_rate": 5.26936688950059e-06, "loss": 1.464, "step": 1365000 }, { "epoch": 8.95, "learning_rate": 5.252982042207367e-06, "loss": 1.4207, "step": 1365500 }, { "epoch": 8.95, "learning_rate": 5.236597194914144e-06, "loss": 1.4138, "step": 1366000 }, { "epoch": 8.96, "learning_rate": 5.2202123476209205e-06, "loss": 1.4086, "step": 1366500 }, { "epoch": 8.96, "learning_rate": 5.203827500327697e-06, "loss": 1.3989, "step": 1367000 }, { "epoch": 8.96, "learning_rate": 5.1874426530344735e-06, "loss": 1.414, "step": 1367500 }, { "epoch": 8.97, "learning_rate": 5.171057805741251e-06, "loss": 1.439, "step": 1368000 }, { "epoch": 8.97, "learning_rate": 5.154672958448027e-06, "loss": 1.4472, "step": 1368500 }, { "epoch": 8.97, "learning_rate": 5.138288111154804e-06, "loss": 1.4411, "step": 1369000 }, { "epoch": 8.98, "learning_rate": 5.121903263861581e-06, "loss": 1.4205, "step": 1369500 }, { "epoch": 8.98, "learning_rate": 5.105518416568358e-06, "loss": 1.4255, "step": 1370000 }, { "epoch": 8.98, "learning_rate": 5.089133569275135e-06, "loss": 1.4568, "step": 1370500 }, { "epoch": 8.99, "learning_rate": 5.072748721981911e-06, "loss": 1.4363, "step": 1371000 }, { "epoch": 8.99, "learning_rate": 5.056363874688688e-06, "loss": 1.4382, "step": 1371500 }, { "epoch": 8.99, "learning_rate": 5.039979027395465e-06, "loss": 1.4246, "step": 1372000 }, { "epoch": 9.0, "learning_rate": 5.023594180102242e-06, "loss": 1.4276, "step": 1372500 }, { "epoch": 9.0, "learning_rate": 5.007209332809019e-06, "loss": 1.4404, "step": 1373000 }, { "epoch": 9.0, "learning_rate": 4.990824485515795e-06, "loss": 1.4378, "step": 1373500 }, { "epoch": 9.01, "learning_rate": 4.9744396382225725e-06, "loss": 1.4407, "step": 1374000 }, { "epoch": 9.01, "learning_rate": 4.958054790929348e-06, "loss": 1.4046, "step": 1374500 }, { "epoch": 9.01, "learning_rate": 4.9416699436361255e-06, "loss": 1.4382, "step": 1375000 }, { "epoch": 9.01, "learning_rate": 4.925285096342902e-06, "loss": 1.4065, "step": 1375500 }, { "epoch": 9.02, "learning_rate": 4.908900249049679e-06, "loss": 1.4092, "step": 1376000 }, { "epoch": 9.02, "learning_rate": 4.892515401756456e-06, "loss": 1.4245, "step": 1376500 }, { "epoch": 9.02, "learning_rate": 4.8761305544632324e-06, "loss": 1.4327, "step": 1377000 }, { "epoch": 9.03, "learning_rate": 4.85974570717001e-06, "loss": 1.3995, "step": 1377500 }, { "epoch": 9.03, "learning_rate": 4.843360859876786e-06, "loss": 1.4266, "step": 1378000 }, { "epoch": 9.03, "learning_rate": 4.826976012583563e-06, "loss": 1.4268, "step": 1378500 }, { "epoch": 9.04, "learning_rate": 4.810591165290339e-06, "loss": 1.453, "step": 1379000 }, { "epoch": 9.04, "learning_rate": 4.794206317997117e-06, "loss": 1.4184, "step": 1379500 }, { "epoch": 9.04, "learning_rate": 4.777821470703893e-06, "loss": 1.4109, "step": 1380000 }, { "epoch": 9.05, "learning_rate": 4.76143662341067e-06, "loss": 1.4155, "step": 1380500 }, { "epoch": 9.05, "learning_rate": 4.745051776117447e-06, "loss": 1.3998, "step": 1381000 }, { "epoch": 9.05, "learning_rate": 4.728666928824224e-06, "loss": 1.4467, "step": 1381500 }, { "epoch": 9.06, "learning_rate": 4.712282081531e-06, "loss": 1.4456, "step": 1382000 }, { "epoch": 9.06, "learning_rate": 4.695897234237777e-06, "loss": 1.4385, "step": 1382500 }, { "epoch": 9.06, "learning_rate": 4.679512386944554e-06, "loss": 1.4347, "step": 1383000 }, { "epoch": 9.07, "learning_rate": 4.6631275396513306e-06, "loss": 1.4411, "step": 1383500 }, { "epoch": 9.07, "learning_rate": 4.646742692358107e-06, "loss": 1.4507, "step": 1384000 }, { "epoch": 9.07, "learning_rate": 4.6303578450648845e-06, "loss": 1.4007, "step": 1384500 }, { "epoch": 9.08, "learning_rate": 4.613972997771661e-06, "loss": 1.4327, "step": 1385000 }, { "epoch": 9.08, "learning_rate": 4.597588150478438e-06, "loss": 1.4107, "step": 1385500 }, { "epoch": 9.08, "learning_rate": 4.581203303185214e-06, "loss": 1.4153, "step": 1386000 }, { "epoch": 9.09, "learning_rate": 4.564818455891991e-06, "loss": 1.4182, "step": 1386500 }, { "epoch": 9.09, "learning_rate": 4.548433608598768e-06, "loss": 1.4511, "step": 1387000 }, { "epoch": 9.09, "learning_rate": 4.532048761305545e-06, "loss": 1.4194, "step": 1387500 }, { "epoch": 9.1, "learning_rate": 4.515663914012322e-06, "loss": 1.4224, "step": 1388000 }, { "epoch": 9.1, "learning_rate": 4.499279066719098e-06, "loss": 1.4449, "step": 1388500 }, { "epoch": 9.1, "learning_rate": 4.482894219425876e-06, "loss": 1.4285, "step": 1389000 }, { "epoch": 9.11, "learning_rate": 4.466509372132651e-06, "loss": 1.4403, "step": 1389500 }, { "epoch": 9.11, "learning_rate": 4.450124524839429e-06, "loss": 1.4391, "step": 1390000 }, { "epoch": 9.11, "learning_rate": 4.433739677546205e-06, "loss": 1.4491, "step": 1390500 }, { "epoch": 9.12, "learning_rate": 4.417354830252983e-06, "loss": 1.4243, "step": 1391000 }, { "epoch": 9.12, "learning_rate": 4.400969982959759e-06, "loss": 1.4299, "step": 1391500 }, { "epoch": 9.12, "learning_rate": 4.384585135666536e-06, "loss": 1.4577, "step": 1392000 }, { "epoch": 9.13, "learning_rate": 4.368200288373313e-06, "loss": 1.4042, "step": 1392500 }, { "epoch": 9.13, "learning_rate": 4.3518154410800895e-06, "loss": 1.3979, "step": 1393000 }, { "epoch": 9.13, "learning_rate": 4.335430593786866e-06, "loss": 1.4192, "step": 1393500 }, { "epoch": 9.14, "learning_rate": 4.3190457464936425e-06, "loss": 1.4492, "step": 1394000 }, { "epoch": 9.14, "learning_rate": 4.30266089920042e-06, "loss": 1.4525, "step": 1394500 }, { "epoch": 9.14, "learning_rate": 4.286276051907196e-06, "loss": 1.4356, "step": 1395000 }, { "epoch": 9.15, "learning_rate": 4.269891204613973e-06, "loss": 1.393, "step": 1395500 }, { "epoch": 9.15, "learning_rate": 4.25350635732075e-06, "loss": 1.3998, "step": 1396000 }, { "epoch": 9.15, "learning_rate": 4.237121510027527e-06, "loss": 1.4205, "step": 1396500 }, { "epoch": 9.16, "learning_rate": 4.220736662734303e-06, "loss": 1.4022, "step": 1397000 }, { "epoch": 9.16, "learning_rate": 4.20435181544108e-06, "loss": 1.4078, "step": 1397500 }, { "epoch": 9.16, "learning_rate": 4.187966968147857e-06, "loss": 1.4029, "step": 1398000 }, { "epoch": 9.17, "learning_rate": 4.171582120854634e-06, "loss": 1.4275, "step": 1398500 }, { "epoch": 9.17, "learning_rate": 4.15519727356141e-06, "loss": 1.4334, "step": 1399000 }, { "epoch": 9.17, "learning_rate": 4.138812426268188e-06, "loss": 1.4456, "step": 1399500 }, { "epoch": 9.18, "learning_rate": 4.122427578974964e-06, "loss": 1.4133, "step": 1400000 }, { "epoch": 9.18, "learning_rate": 4.1060427316817415e-06, "loss": 1.4343, "step": 1400500 }, { "epoch": 9.18, "learning_rate": 4.089657884388517e-06, "loss": 1.3931, "step": 1401000 }, { "epoch": 9.19, "learning_rate": 4.0732730370952945e-06, "loss": 1.3933, "step": 1401500 }, { "epoch": 9.19, "learning_rate": 4.056888189802071e-06, "loss": 1.4734, "step": 1402000 }, { "epoch": 9.19, "learning_rate": 4.0405033425088484e-06, "loss": 1.4302, "step": 1402500 }, { "epoch": 9.2, "learning_rate": 4.024118495215625e-06, "loss": 1.4257, "step": 1403000 }, { "epoch": 9.2, "learning_rate": 4.0077336479224015e-06, "loss": 1.4591, "step": 1403500 }, { "epoch": 9.2, "learning_rate": 3.991348800629179e-06, "loss": 1.445, "step": 1404000 }, { "epoch": 9.21, "learning_rate": 3.9749639533359545e-06, "loss": 1.4239, "step": 1404500 }, { "epoch": 9.21, "learning_rate": 3.958579106042732e-06, "loss": 1.448, "step": 1405000 }, { "epoch": 9.21, "learning_rate": 3.942194258749508e-06, "loss": 1.4164, "step": 1405500 }, { "epoch": 9.21, "learning_rate": 3.925809411456286e-06, "loss": 1.4232, "step": 1406000 }, { "epoch": 9.22, "learning_rate": 3.909424564163062e-06, "loss": 1.3911, "step": 1406500 }, { "epoch": 9.22, "learning_rate": 3.893039716869839e-06, "loss": 1.4227, "step": 1407000 }, { "epoch": 9.22, "learning_rate": 3.876654869576616e-06, "loss": 1.4039, "step": 1407500 }, { "epoch": 9.23, "learning_rate": 3.860270022283393e-06, "loss": 1.4361, "step": 1408000 }, { "epoch": 9.23, "learning_rate": 3.843885174990169e-06, "loss": 1.4385, "step": 1408500 }, { "epoch": 9.23, "learning_rate": 3.827500327696946e-06, "loss": 1.4467, "step": 1409000 }, { "epoch": 9.24, "learning_rate": 3.811115480403723e-06, "loss": 1.4024, "step": 1409500 }, { "epoch": 9.24, "learning_rate": 3.794730633110499e-06, "loss": 1.4146, "step": 1410000 }, { "epoch": 9.24, "learning_rate": 3.7783457858172765e-06, "loss": 1.4276, "step": 1410500 }, { "epoch": 9.25, "learning_rate": 3.7619609385240535e-06, "loss": 1.3828, "step": 1411000 }, { "epoch": 9.25, "learning_rate": 3.74557609123083e-06, "loss": 1.4345, "step": 1411500 }, { "epoch": 9.25, "learning_rate": 3.729191243937607e-06, "loss": 1.4152, "step": 1412000 }, { "epoch": 9.26, "learning_rate": 3.712806396644383e-06, "loss": 1.4088, "step": 1412500 }, { "epoch": 9.26, "learning_rate": 3.6964215493511604e-06, "loss": 1.4267, "step": 1413000 }, { "epoch": 9.26, "learning_rate": 3.6800367020579365e-06, "loss": 1.4362, "step": 1413500 }, { "epoch": 9.27, "learning_rate": 3.663651854764714e-06, "loss": 1.4338, "step": 1414000 }, { "epoch": 9.27, "learning_rate": 3.647267007471491e-06, "loss": 1.441, "step": 1414500 }, { "epoch": 9.27, "learning_rate": 3.6308821601782673e-06, "loss": 1.3949, "step": 1415000 }, { "epoch": 9.28, "learning_rate": 3.6144973128850443e-06, "loss": 1.4256, "step": 1415500 }, { "epoch": 9.28, "learning_rate": 3.5981124655918208e-06, "loss": 1.4389, "step": 1416000 }, { "epoch": 9.28, "learning_rate": 3.5817276182985977e-06, "loss": 1.4292, "step": 1416500 }, { "epoch": 9.29, "learning_rate": 3.5653427710053742e-06, "loss": 1.4231, "step": 1417000 }, { "epoch": 9.29, "learning_rate": 3.548957923712151e-06, "loss": 1.4072, "step": 1417500 }, { "epoch": 9.29, "learning_rate": 3.532573076418928e-06, "loss": 1.4194, "step": 1418000 }, { "epoch": 9.3, "learning_rate": 3.5161882291257046e-06, "loss": 1.4401, "step": 1418500 }, { "epoch": 9.3, "learning_rate": 3.4998033818324816e-06, "loss": 1.4453, "step": 1419000 }, { "epoch": 9.3, "learning_rate": 3.483418534539258e-06, "loss": 1.4019, "step": 1419500 }, { "epoch": 9.31, "learning_rate": 3.467033687246035e-06, "loss": 1.4393, "step": 1420000 }, { "epoch": 9.31, "learning_rate": 3.4506488399528116e-06, "loss": 1.4177, "step": 1420500 }, { "epoch": 9.31, "learning_rate": 3.4342639926595885e-06, "loss": 1.4117, "step": 1421000 }, { "epoch": 9.32, "learning_rate": 3.417879145366366e-06, "loss": 1.4315, "step": 1421500 }, { "epoch": 9.32, "learning_rate": 3.401494298073142e-06, "loss": 1.3908, "step": 1422000 }, { "epoch": 9.32, "learning_rate": 3.3851094507799193e-06, "loss": 1.4349, "step": 1422500 }, { "epoch": 9.33, "learning_rate": 3.3687246034866954e-06, "loss": 1.4099, "step": 1423000 }, { "epoch": 9.33, "learning_rate": 3.3523397561934728e-06, "loss": 1.4228, "step": 1423500 }, { "epoch": 9.33, "learning_rate": 3.335954908900249e-06, "loss": 1.4308, "step": 1424000 }, { "epoch": 9.34, "learning_rate": 3.3195700616070262e-06, "loss": 1.4459, "step": 1424500 }, { "epoch": 9.34, "learning_rate": 3.3031852143138023e-06, "loss": 1.4341, "step": 1425000 }, { "epoch": 9.34, "learning_rate": 3.2868003670205797e-06, "loss": 1.4113, "step": 1425500 }, { "epoch": 9.35, "learning_rate": 3.2704155197273566e-06, "loss": 1.4235, "step": 1426000 }, { "epoch": 9.35, "learning_rate": 3.254030672434133e-06, "loss": 1.4449, "step": 1426500 }, { "epoch": 9.35, "learning_rate": 3.23764582514091e-06, "loss": 1.447, "step": 1427000 }, { "epoch": 9.36, "learning_rate": 3.221260977847686e-06, "loss": 1.4077, "step": 1427500 }, { "epoch": 9.36, "learning_rate": 3.2048761305544636e-06, "loss": 1.4432, "step": 1428000 }, { "epoch": 9.36, "learning_rate": 3.1884912832612397e-06, "loss": 1.4269, "step": 1428500 }, { "epoch": 9.37, "learning_rate": 3.172106435968017e-06, "loss": 1.4055, "step": 1429000 }, { "epoch": 9.37, "learning_rate": 3.155721588674794e-06, "loss": 1.4341, "step": 1429500 }, { "epoch": 9.37, "learning_rate": 3.1393367413815705e-06, "loss": 1.4233, "step": 1430000 }, { "epoch": 9.38, "learning_rate": 3.122951894088347e-06, "loss": 1.4415, "step": 1430500 }, { "epoch": 9.38, "learning_rate": 3.1065670467951244e-06, "loss": 1.4278, "step": 1431000 }, { "epoch": 9.38, "learning_rate": 3.090182199501901e-06, "loss": 1.4209, "step": 1431500 }, { "epoch": 9.39, "learning_rate": 3.073797352208678e-06, "loss": 1.4158, "step": 1432000 }, { "epoch": 9.39, "learning_rate": 3.0574125049154543e-06, "loss": 1.4478, "step": 1432500 }, { "epoch": 9.39, "learning_rate": 3.0410276576222313e-06, "loss": 1.4529, "step": 1433000 }, { "epoch": 9.4, "learning_rate": 3.024642810329008e-06, "loss": 1.4295, "step": 1433500 }, { "epoch": 9.4, "learning_rate": 3.0082579630357847e-06, "loss": 1.4488, "step": 1434000 }, { "epoch": 9.4, "learning_rate": 2.9918731157425613e-06, "loss": 1.4466, "step": 1434500 }, { "epoch": 9.4, "learning_rate": 2.975488268449338e-06, "loss": 1.4174, "step": 1435000 }, { "epoch": 9.41, "learning_rate": 2.959103421156115e-06, "loss": 1.4135, "step": 1435500 }, { "epoch": 9.41, "learning_rate": 2.9427185738628917e-06, "loss": 1.4134, "step": 1436000 }, { "epoch": 9.41, "learning_rate": 2.9263337265696686e-06, "loss": 1.4304, "step": 1436500 }, { "epoch": 9.42, "learning_rate": 2.909948879276445e-06, "loss": 1.412, "step": 1437000 }, { "epoch": 9.42, "learning_rate": 2.893564031983222e-06, "loss": 1.4313, "step": 1437500 }, { "epoch": 9.42, "learning_rate": 2.8771791846899986e-06, "loss": 1.4207, "step": 1438000 }, { "epoch": 9.43, "learning_rate": 2.860794337396776e-06, "loss": 1.4272, "step": 1438500 }, { "epoch": 9.43, "learning_rate": 2.8444094901035525e-06, "loss": 1.3976, "step": 1439000 }, { "epoch": 9.43, "learning_rate": 2.8280246428103294e-06, "loss": 1.3888, "step": 1439500 }, { "epoch": 9.44, "learning_rate": 2.811639795517106e-06, "loss": 1.4399, "step": 1440000 }, { "epoch": 9.44, "learning_rate": 2.795254948223883e-06, "loss": 1.44, "step": 1440500 }, { "epoch": 9.44, "learning_rate": 2.7788701009306594e-06, "loss": 1.4157, "step": 1441000 }, { "epoch": 9.45, "learning_rate": 2.7624852536374363e-06, "loss": 1.4689, "step": 1441500 }, { "epoch": 9.45, "learning_rate": 2.746100406344213e-06, "loss": 1.4049, "step": 1442000 }, { "epoch": 9.45, "learning_rate": 2.72971555905099e-06, "loss": 1.4334, "step": 1442500 }, { "epoch": 9.46, "learning_rate": 2.7133307117577667e-06, "loss": 1.4332, "step": 1443000 }, { "epoch": 9.46, "learning_rate": 2.6969458644645433e-06, "loss": 1.3959, "step": 1443500 }, { "epoch": 9.46, "learning_rate": 2.68056101717132e-06, "loss": 1.4336, "step": 1444000 }, { "epoch": 9.47, "learning_rate": 2.6641761698780967e-06, "loss": 1.3995, "step": 1444500 }, { "epoch": 9.47, "learning_rate": 2.6477913225848737e-06, "loss": 1.4231, "step": 1445000 }, { "epoch": 9.47, "learning_rate": 2.63140647529165e-06, "loss": 1.3982, "step": 1445500 }, { "epoch": 9.48, "learning_rate": 2.615021627998427e-06, "loss": 1.4044, "step": 1446000 }, { "epoch": 9.48, "learning_rate": 2.598636780705204e-06, "loss": 1.4188, "step": 1446500 }, { "epoch": 9.48, "learning_rate": 2.582251933411981e-06, "loss": 1.4168, "step": 1447000 }, { "epoch": 9.49, "learning_rate": 2.5658670861187575e-06, "loss": 1.4274, "step": 1447500 }, { "epoch": 9.49, "learning_rate": 2.5494822388255345e-06, "loss": 1.4419, "step": 1448000 }, { "epoch": 9.49, "learning_rate": 2.533097391532311e-06, "loss": 1.4095, "step": 1448500 }, { "epoch": 9.5, "learning_rate": 2.516712544239088e-06, "loss": 1.4032, "step": 1449000 }, { "epoch": 9.5, "learning_rate": 2.5003276969458644e-06, "loss": 1.3918, "step": 1449500 }, { "epoch": 9.5, "learning_rate": 2.4839428496526414e-06, "loss": 1.3973, "step": 1450000 }, { "epoch": 9.51, "learning_rate": 2.4675580023594183e-06, "loss": 1.4203, "step": 1450500 }, { "epoch": 9.51, "learning_rate": 2.451173155066195e-06, "loss": 1.4315, "step": 1451000 }, { "epoch": 9.51, "learning_rate": 2.4347883077729718e-06, "loss": 1.4056, "step": 1451500 }, { "epoch": 9.52, "learning_rate": 2.4184034604797483e-06, "loss": 1.4177, "step": 1452000 }, { "epoch": 9.52, "learning_rate": 2.4020186131865252e-06, "loss": 1.4422, "step": 1452500 }, { "epoch": 9.52, "learning_rate": 2.3856337658933018e-06, "loss": 1.4246, "step": 1453000 }, { "epoch": 9.53, "learning_rate": 2.3692489186000787e-06, "loss": 1.4044, "step": 1453500 }, { "epoch": 9.53, "learning_rate": 2.3528640713068556e-06, "loss": 1.4053, "step": 1454000 }, { "epoch": 9.53, "learning_rate": 2.3364792240136326e-06, "loss": 1.4028, "step": 1454500 }, { "epoch": 9.54, "learning_rate": 2.320094376720409e-06, "loss": 1.4126, "step": 1455000 }, { "epoch": 9.54, "learning_rate": 2.303709529427186e-06, "loss": 1.4333, "step": 1455500 }, { "epoch": 9.54, "learning_rate": 2.2873246821339626e-06, "loss": 1.463, "step": 1456000 }, { "epoch": 9.55, "learning_rate": 2.2709398348407395e-06, "loss": 1.418, "step": 1456500 }, { "epoch": 9.55, "learning_rate": 2.254554987547516e-06, "loss": 1.4075, "step": 1457000 }, { "epoch": 9.55, "learning_rate": 2.238170140254293e-06, "loss": 1.411, "step": 1457500 }, { "epoch": 9.56, "learning_rate": 2.22178529296107e-06, "loss": 1.4144, "step": 1458000 }, { "epoch": 9.56, "learning_rate": 2.2054004456678464e-06, "loss": 1.3886, "step": 1458500 }, { "epoch": 9.56, "learning_rate": 2.1890155983746234e-06, "loss": 1.4217, "step": 1459000 }, { "epoch": 9.57, "learning_rate": 2.1726307510814e-06, "loss": 1.3974, "step": 1459500 }, { "epoch": 9.57, "learning_rate": 2.156245903788177e-06, "loss": 1.4548, "step": 1460000 }, { "epoch": 9.57, "learning_rate": 2.1398610564949533e-06, "loss": 1.4288, "step": 1460500 }, { "epoch": 9.58, "learning_rate": 2.1234762092017303e-06, "loss": 1.4306, "step": 1461000 }, { "epoch": 9.58, "learning_rate": 2.1070913619085072e-06, "loss": 1.4316, "step": 1461500 }, { "epoch": 9.58, "learning_rate": 2.090706514615284e-06, "loss": 1.4129, "step": 1462000 }, { "epoch": 9.59, "learning_rate": 2.0743216673220607e-06, "loss": 1.4192, "step": 1462500 }, { "epoch": 9.59, "learning_rate": 2.0579368200288376e-06, "loss": 1.4051, "step": 1463000 }, { "epoch": 9.59, "learning_rate": 2.041551972735614e-06, "loss": 1.4223, "step": 1463500 }, { "epoch": 9.59, "learning_rate": 2.025167125442391e-06, "loss": 1.4391, "step": 1464000 }, { "epoch": 9.6, "learning_rate": 2.0087822781491676e-06, "loss": 1.4146, "step": 1464500 }, { "epoch": 9.6, "learning_rate": 1.9923974308559445e-06, "loss": 1.3882, "step": 1465000 }, { "epoch": 9.6, "learning_rate": 1.9760125835627215e-06, "loss": 1.4124, "step": 1465500 }, { "epoch": 9.61, "learning_rate": 1.959627736269498e-06, "loss": 1.4069, "step": 1466000 }, { "epoch": 9.61, "learning_rate": 1.943242888976275e-06, "loss": 1.4291, "step": 1466500 }, { "epoch": 9.61, "learning_rate": 1.9268580416830515e-06, "loss": 1.3966, "step": 1467000 }, { "epoch": 9.62, "learning_rate": 1.9104731943898284e-06, "loss": 1.4056, "step": 1467500 }, { "epoch": 9.62, "learning_rate": 1.8940883470966051e-06, "loss": 1.4175, "step": 1468000 }, { "epoch": 9.62, "learning_rate": 1.8777034998033819e-06, "loss": 1.4132, "step": 1468500 }, { "epoch": 9.63, "learning_rate": 1.8613186525101588e-06, "loss": 1.4269, "step": 1469000 }, { "epoch": 9.63, "learning_rate": 1.8449338052169355e-06, "loss": 1.4193, "step": 1469500 }, { "epoch": 9.63, "learning_rate": 1.8285489579237123e-06, "loss": 1.4263, "step": 1470000 }, { "epoch": 9.64, "learning_rate": 1.812164110630489e-06, "loss": 1.4032, "step": 1470500 }, { "epoch": 9.64, "learning_rate": 1.7957792633372657e-06, "loss": 1.4237, "step": 1471000 }, { "epoch": 9.64, "learning_rate": 1.7793944160440425e-06, "loss": 1.4573, "step": 1471500 }, { "epoch": 9.65, "learning_rate": 1.7630095687508192e-06, "loss": 1.412, "step": 1472000 }, { "epoch": 9.65, "learning_rate": 1.7466247214575963e-06, "loss": 1.4254, "step": 1472500 }, { "epoch": 9.65, "learning_rate": 1.730239874164373e-06, "loss": 1.3988, "step": 1473000 }, { "epoch": 9.66, "learning_rate": 1.7138550268711498e-06, "loss": 1.4201, "step": 1473500 }, { "epoch": 9.66, "learning_rate": 1.6974701795779265e-06, "loss": 1.396, "step": 1474000 }, { "epoch": 9.66, "learning_rate": 1.6810853322847033e-06, "loss": 1.4017, "step": 1474500 }, { "epoch": 9.67, "learning_rate": 1.66470048499148e-06, "loss": 1.389, "step": 1475000 }, { "epoch": 9.67, "learning_rate": 1.6483156376982567e-06, "loss": 1.4188, "step": 1475500 }, { "epoch": 9.67, "learning_rate": 1.6319307904050335e-06, "loss": 1.4418, "step": 1476000 }, { "epoch": 9.68, "learning_rate": 1.6155459431118104e-06, "loss": 1.4486, "step": 1476500 }, { "epoch": 9.68, "learning_rate": 1.5991610958185871e-06, "loss": 1.4326, "step": 1477000 }, { "epoch": 9.68, "learning_rate": 1.5827762485253639e-06, "loss": 1.4227, "step": 1477500 }, { "epoch": 9.69, "learning_rate": 1.5663914012321406e-06, "loss": 1.4278, "step": 1478000 }, { "epoch": 9.69, "learning_rate": 1.5500065539389173e-06, "loss": 1.4551, "step": 1478500 }, { "epoch": 9.69, "learning_rate": 1.533621706645694e-06, "loss": 1.4549, "step": 1479000 }, { "epoch": 9.7, "learning_rate": 1.517236859352471e-06, "loss": 1.4469, "step": 1479500 }, { "epoch": 9.7, "learning_rate": 1.5008520120592477e-06, "loss": 1.4348, "step": 1480000 }, { "epoch": 9.7, "learning_rate": 1.4844671647660245e-06, "loss": 1.4044, "step": 1480500 }, { "epoch": 9.71, "learning_rate": 1.4680823174728012e-06, "loss": 1.3681, "step": 1481000 }, { "epoch": 9.71, "learning_rate": 1.4516974701795781e-06, "loss": 1.4035, "step": 1481500 }, { "epoch": 9.71, "learning_rate": 1.4353126228863549e-06, "loss": 1.4101, "step": 1482000 }, { "epoch": 9.72, "learning_rate": 1.4189277755931316e-06, "loss": 1.4248, "step": 1482500 }, { "epoch": 9.72, "learning_rate": 1.4025429282999083e-06, "loss": 1.395, "step": 1483000 }, { "epoch": 9.72, "learning_rate": 1.386158081006685e-06, "loss": 1.4091, "step": 1483500 }, { "epoch": 9.73, "learning_rate": 1.3697732337134618e-06, "loss": 1.4276, "step": 1484000 }, { "epoch": 9.73, "learning_rate": 1.3533883864202385e-06, "loss": 1.4171, "step": 1484500 }, { "epoch": 9.73, "learning_rate": 1.3370035391270154e-06, "loss": 1.4256, "step": 1485000 }, { "epoch": 9.74, "learning_rate": 1.3206186918337922e-06, "loss": 1.4128, "step": 1485500 }, { "epoch": 9.74, "learning_rate": 1.304233844540569e-06, "loss": 1.4222, "step": 1486000 }, { "epoch": 9.74, "learning_rate": 1.2878489972473456e-06, "loss": 1.414, "step": 1486500 }, { "epoch": 9.75, "learning_rate": 1.2714641499541226e-06, "loss": 1.4142, "step": 1487000 }, { "epoch": 9.75, "learning_rate": 1.2550793026608993e-06, "loss": 1.4348, "step": 1487500 }, { "epoch": 9.75, "learning_rate": 1.238694455367676e-06, "loss": 1.445, "step": 1488000 }, { "epoch": 9.76, "learning_rate": 1.2223096080744528e-06, "loss": 1.4179, "step": 1488500 }, { "epoch": 9.76, "learning_rate": 1.2059247607812297e-06, "loss": 1.3961, "step": 1489000 }, { "epoch": 9.76, "learning_rate": 1.1895399134880064e-06, "loss": 1.4559, "step": 1489500 }, { "epoch": 9.77, "learning_rate": 1.1731550661947832e-06, "loss": 1.4542, "step": 1490000 }, { "epoch": 9.77, "learning_rate": 1.15677021890156e-06, "loss": 1.4237, "step": 1490500 }, { "epoch": 9.77, "learning_rate": 1.1403853716083366e-06, "loss": 1.4282, "step": 1491000 }, { "epoch": 9.78, "learning_rate": 1.1240005243151134e-06, "loss": 1.4147, "step": 1491500 }, { "epoch": 9.78, "learning_rate": 1.10761567702189e-06, "loss": 1.4771, "step": 1492000 }, { "epoch": 9.78, "learning_rate": 1.091230829728667e-06, "loss": 1.4506, "step": 1492500 }, { "epoch": 9.79, "learning_rate": 1.0748459824354438e-06, "loss": 1.4259, "step": 1493000 }, { "epoch": 9.79, "learning_rate": 1.0584611351422205e-06, "loss": 1.4234, "step": 1493500 }, { "epoch": 9.79, "learning_rate": 1.0420762878489972e-06, "loss": 1.4249, "step": 1494000 }, { "epoch": 9.79, "learning_rate": 1.0256914405557742e-06, "loss": 1.386, "step": 1494500 }, { "epoch": 9.8, "learning_rate": 1.0093065932625509e-06, "loss": 1.3938, "step": 1495000 }, { "epoch": 9.8, "learning_rate": 9.929217459693276e-07, "loss": 1.4227, "step": 1495500 }, { "epoch": 9.8, "learning_rate": 9.765368986761044e-07, "loss": 1.4445, "step": 1496000 }, { "epoch": 9.81, "learning_rate": 9.601520513828813e-07, "loss": 1.4498, "step": 1496500 }, { "epoch": 9.81, "learning_rate": 9.437672040896579e-07, "loss": 1.4349, "step": 1497000 }, { "epoch": 9.81, "learning_rate": 9.273823567964346e-07, "loss": 1.4153, "step": 1497500 }, { "epoch": 9.82, "learning_rate": 9.109975095032114e-07, "loss": 1.4075, "step": 1498000 }, { "epoch": 9.82, "learning_rate": 8.946126622099883e-07, "loss": 1.4085, "step": 1498500 }, { "epoch": 9.82, "learning_rate": 8.78227814916765e-07, "loss": 1.3816, "step": 1499000 }, { "epoch": 9.83, "learning_rate": 8.618429676235418e-07, "loss": 1.4165, "step": 1499500 }, { "epoch": 9.83, "learning_rate": 8.454581203303186e-07, "loss": 1.428, "step": 1500000 }, { "epoch": 9.83, "learning_rate": 8.290732730370953e-07, "loss": 1.4301, "step": 1500500 }, { "epoch": 9.84, "learning_rate": 8.126884257438721e-07, "loss": 1.4516, "step": 1501000 }, { "epoch": 9.84, "learning_rate": 7.963035784506488e-07, "loss": 1.4109, "step": 1501500 }, { "epoch": 9.84, "learning_rate": 7.799187311574256e-07, "loss": 1.4422, "step": 1502000 }, { "epoch": 9.85, "learning_rate": 7.635338838642025e-07, "loss": 1.4524, "step": 1502500 }, { "epoch": 9.85, "learning_rate": 7.471490365709792e-07, "loss": 1.4256, "step": 1503000 }, { "epoch": 9.85, "learning_rate": 7.307641892777559e-07, "loss": 1.4278, "step": 1503500 }, { "epoch": 9.86, "learning_rate": 7.143793419845327e-07, "loss": 1.4528, "step": 1504000 }, { "epoch": 9.86, "learning_rate": 6.979944946913095e-07, "loss": 1.4071, "step": 1504500 }, { "epoch": 9.86, "learning_rate": 6.816096473980862e-07, "loss": 1.401, "step": 1505000 }, { "epoch": 9.87, "learning_rate": 6.652248001048631e-07, "loss": 1.4211, "step": 1505500 }, { "epoch": 9.87, "learning_rate": 6.488399528116398e-07, "loss": 1.4316, "step": 1506000 }, { "epoch": 9.87, "learning_rate": 6.324551055184166e-07, "loss": 1.4382, "step": 1506500 }, { "epoch": 9.88, "learning_rate": 6.160702582251934e-07, "loss": 1.3906, "step": 1507000 }, { "epoch": 9.88, "learning_rate": 5.996854109319701e-07, "loss": 1.4536, "step": 1507500 }, { "epoch": 9.88, "learning_rate": 5.833005636387469e-07, "loss": 1.4173, "step": 1508000 }, { "epoch": 9.89, "learning_rate": 5.669157163455237e-07, "loss": 1.405, "step": 1508500 }, { "epoch": 9.89, "learning_rate": 5.505308690523005e-07, "loss": 1.4067, "step": 1509000 }, { "epoch": 9.89, "learning_rate": 5.341460217590772e-07, "loss": 1.4311, "step": 1509500 }, { "epoch": 9.9, "learning_rate": 5.177611744658541e-07, "loss": 1.3951, "step": 1510000 }, { "epoch": 9.9, "learning_rate": 5.013763271726308e-07, "loss": 1.4041, "step": 1510500 }, { "epoch": 9.9, "learning_rate": 4.849914798794075e-07, "loss": 1.4422, "step": 1511000 }, { "epoch": 9.91, "learning_rate": 4.686066325861843e-07, "loss": 1.4195, "step": 1511500 }, { "epoch": 9.91, "learning_rate": 4.522217852929611e-07, "loss": 1.4371, "step": 1512000 }, { "epoch": 9.91, "learning_rate": 4.358369379997378e-07, "loss": 1.3904, "step": 1512500 }, { "epoch": 9.92, "learning_rate": 4.1945209070651465e-07, "loss": 1.4391, "step": 1513000 }, { "epoch": 9.92, "learning_rate": 4.030672434132914e-07, "loss": 1.4469, "step": 1513500 }, { "epoch": 9.92, "learning_rate": 3.8668239612006817e-07, "loss": 1.4253, "step": 1514000 }, { "epoch": 9.93, "learning_rate": 3.7029754882684495e-07, "loss": 1.4124, "step": 1514500 }, { "epoch": 9.93, "learning_rate": 3.5391270153362173e-07, "loss": 1.4119, "step": 1515000 }, { "epoch": 9.93, "learning_rate": 3.375278542403985e-07, "loss": 1.3886, "step": 1515500 }, { "epoch": 9.94, "learning_rate": 3.2114300694717524e-07, "loss": 1.4036, "step": 1516000 }, { "epoch": 9.94, "learning_rate": 3.0475815965395203e-07, "loss": 1.4449, "step": 1516500 }, { "epoch": 9.94, "learning_rate": 2.883733123607288e-07, "loss": 1.4018, "step": 1517000 }, { "epoch": 9.95, "learning_rate": 2.719884650675056e-07, "loss": 1.4258, "step": 1517500 }, { "epoch": 9.95, "learning_rate": 2.556036177742823e-07, "loss": 1.4184, "step": 1518000 }, { "epoch": 9.95, "learning_rate": 2.392187704810591e-07, "loss": 1.4223, "step": 1518500 }, { "epoch": 9.96, "learning_rate": 2.228339231878359e-07, "loss": 1.4246, "step": 1519000 }, { "epoch": 9.96, "learning_rate": 2.0644907589461265e-07, "loss": 1.458, "step": 1519500 }, { "epoch": 9.96, "learning_rate": 1.9006422860138946e-07, "loss": 1.3689, "step": 1520000 }, { "epoch": 9.97, "learning_rate": 1.736793813081662e-07, "loss": 1.4232, "step": 1520500 }, { "epoch": 9.97, "learning_rate": 1.57294534014943e-07, "loss": 1.4544, "step": 1521000 }, { "epoch": 9.97, "learning_rate": 1.4090968672171975e-07, "loss": 1.4263, "step": 1521500 }, { "epoch": 9.98, "learning_rate": 1.2452483942849653e-07, "loss": 1.4285, "step": 1522000 }, { "epoch": 9.98, "learning_rate": 1.0813999213527332e-07, "loss": 1.4112, "step": 1522500 }, { "epoch": 9.98, "learning_rate": 9.175514484205007e-08, "loss": 1.4315, "step": 1523000 }, { "epoch": 9.98, "learning_rate": 7.537029754882686e-08, "loss": 1.4506, "step": 1523500 }, { "epoch": 9.99, "learning_rate": 5.898545025560362e-08, "loss": 1.4227, "step": 1524000 }, { "epoch": 9.99, "learning_rate": 4.260060296238039e-08, "loss": 1.4301, "step": 1524500 }, { "epoch": 9.99, "learning_rate": 2.6215755669157166e-08, "loss": 1.4285, "step": 1525000 }, { "epoch": 10.0, "learning_rate": 9.830908375933937e-09, "loss": 1.4311, "step": 1525500 }, { "epoch": 10.0, "step": 1525800, "total_flos": 3.525314949676892e+17, "train_loss": 1.7898551662303561, "train_runtime": 329774.3211, "train_samples_per_second": 18.507, "train_steps_per_second": 4.627 } ], "max_steps": 1525800, "num_train_epochs": 10, "total_flos": 3.525314949676892e+17, "trial_name": null, "trial_params": null }