{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 487330, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.994962345843679e-05, "loss": 8.8184, "step": 500 }, { "epoch": 0.02, "learning_rate": 4.989832351794472e-05, "loss": 7.8259, "step": 1000 }, { "epoch": 0.03, "learning_rate": 4.984702357745265e-05, "loss": 7.4946, "step": 1500 }, { "epoch": 0.04, "learning_rate": 4.979572363696058e-05, "loss": 7.2174, "step": 2000 }, { "epoch": 0.05, "learning_rate": 4.974442369646851e-05, "loss": 7.0931, "step": 2500 }, { "epoch": 0.06, "learning_rate": 4.969312375597645e-05, "loss": 6.9066, "step": 3000 }, { "epoch": 0.07, "learning_rate": 4.964182381548438e-05, "loss": 6.8159, "step": 3500 }, { "epoch": 0.08, "learning_rate": 4.959052387499231e-05, "loss": 6.7744, "step": 4000 }, { "epoch": 0.09, "learning_rate": 4.953922393450024e-05, "loss": 6.6722, "step": 4500 }, { "epoch": 0.1, "learning_rate": 4.948792399400817e-05, "loss": 6.5736, "step": 5000 }, { "epoch": 0.11, "learning_rate": 4.94366240535161e-05, "loss": 6.5583, "step": 5500 }, { "epoch": 0.12, "learning_rate": 4.9385324113024026e-05, "loss": 6.4946, "step": 6000 }, { "epoch": 0.13, "learning_rate": 4.933402417253196e-05, "loss": 6.4229, "step": 6500 }, { "epoch": 0.14, "learning_rate": 4.928272423203989e-05, "loss": 6.3521, "step": 7000 }, { "epoch": 0.15, "learning_rate": 4.923142429154782e-05, "loss": 6.2802, "step": 7500 }, { "epoch": 0.16, "learning_rate": 4.918022695093674e-05, "loss": 6.2379, "step": 8000 }, { "epoch": 0.17, "learning_rate": 4.912892701044467e-05, "loss": 6.1997, "step": 8500 }, { "epoch": 0.18, "learning_rate": 4.90776270699526e-05, "loss": 6.1736, "step": 9000 }, { "epoch": 0.19, "learning_rate": 4.902632712946053e-05, "loss": 6.1003, "step": 9500 }, { "epoch": 0.21, "learning_rate": 4.897502718896846e-05, "loss": 6.1453, "step": 10000 }, { "epoch": 0.22, "learning_rate": 4.892372724847639e-05, "loss": 6.1247, "step": 10500 }, { "epoch": 0.23, "learning_rate": 4.887242730798433e-05, "loss": 6.0404, "step": 11000 }, { "epoch": 0.24, "learning_rate": 4.882112736749226e-05, "loss": 6.0285, "step": 11500 }, { "epoch": 0.25, "learning_rate": 4.876982742700019e-05, "loss": 5.9289, "step": 12000 }, { "epoch": 0.26, "learning_rate": 4.871852748650812e-05, "loss": 5.9026, "step": 12500 }, { "epoch": 0.27, "learning_rate": 4.8667227546016046e-05, "loss": 5.9464, "step": 13000 }, { "epoch": 0.28, "learning_rate": 4.861592760552398e-05, "loss": 5.8722, "step": 13500 }, { "epoch": 0.29, "learning_rate": 4.8564730264912896e-05, "loss": 5.8571, "step": 14000 }, { "epoch": 0.3, "learning_rate": 4.8513430324420826e-05, "loss": 5.8416, "step": 14500 }, { "epoch": 0.31, "learning_rate": 4.8462130383928756e-05, "loss": 5.7729, "step": 15000 }, { "epoch": 0.32, "learning_rate": 4.8410830443436686e-05, "loss": 5.8065, "step": 15500 }, { "epoch": 0.33, "learning_rate": 4.8359530502944615e-05, "loss": 5.7176, "step": 16000 }, { "epoch": 0.34, "learning_rate": 4.830823056245255e-05, "loss": 5.7107, "step": 16500 }, { "epoch": 0.35, "learning_rate": 4.825693062196048e-05, "loss": 5.676, "step": 17000 }, { "epoch": 0.36, "learning_rate": 4.820563068146841e-05, "loss": 5.6657, "step": 17500 }, { "epoch": 0.37, "learning_rate": 4.815433074097635e-05, "loss": 5.6036, "step": 18000 }, { "epoch": 0.38, "learning_rate": 4.810303080048427e-05, "loss": 5.617, "step": 18500 }, { "epoch": 0.39, "learning_rate": 4.805173085999221e-05, "loss": 5.5956, "step": 19000 }, { "epoch": 0.4, "learning_rate": 4.800053351938112e-05, "loss": 5.5803, "step": 19500 }, { "epoch": 0.41, "learning_rate": 4.794923357888905e-05, "loss": 5.5891, "step": 20000 }, { "epoch": 0.42, "learning_rate": 4.789793363839698e-05, "loss": 5.5668, "step": 20500 }, { "epoch": 0.43, "learning_rate": 4.784663369790492e-05, "loss": 5.5098, "step": 21000 }, { "epoch": 0.44, "learning_rate": 4.7795538957174814e-05, "loss": 5.5136, "step": 21500 }, { "epoch": 0.45, "learning_rate": 4.7744239016682744e-05, "loss": 5.4964, "step": 22000 }, { "epoch": 0.46, "learning_rate": 4.769293907619067e-05, "loss": 5.433, "step": 22500 }, { "epoch": 0.47, "learning_rate": 4.764163913569861e-05, "loss": 5.4654, "step": 23000 }, { "epoch": 0.48, "learning_rate": 4.759033919520653e-05, "loss": 5.3737, "step": 23500 }, { "epoch": 0.49, "learning_rate": 4.753903925471447e-05, "loss": 5.4051, "step": 24000 }, { "epoch": 0.5, "learning_rate": 4.74877393142224e-05, "loss": 5.4338, "step": 24500 }, { "epoch": 0.51, "learning_rate": 4.743643937373033e-05, "loss": 5.4018, "step": 25000 }, { "epoch": 0.52, "learning_rate": 4.738513943323826e-05, "loss": 5.3666, "step": 25500 }, { "epoch": 0.53, "learning_rate": 4.733383949274619e-05, "loss": 5.3332, "step": 26000 }, { "epoch": 0.54, "learning_rate": 4.7282539552254125e-05, "loss": 5.3543, "step": 26500 }, { "epoch": 0.55, "learning_rate": 4.7231239611762054e-05, "loss": 5.3672, "step": 27000 }, { "epoch": 0.56, "learning_rate": 4.7179939671269984e-05, "loss": 5.2982, "step": 27500 }, { "epoch": 0.57, "learning_rate": 4.7128639730777914e-05, "loss": 5.2833, "step": 28000 }, { "epoch": 0.58, "learning_rate": 4.7077339790285844e-05, "loss": 5.3131, "step": 28500 }, { "epoch": 0.6, "learning_rate": 4.702603984979377e-05, "loss": 5.2557, "step": 29000 }, { "epoch": 0.61, "learning_rate": 4.697473990930171e-05, "loss": 5.2611, "step": 29500 }, { "epoch": 0.62, "learning_rate": 4.692343996880964e-05, "loss": 5.2762, "step": 30000 }, { "epoch": 0.63, "learning_rate": 4.687224262819855e-05, "loss": 5.2073, "step": 30500 }, { "epoch": 0.64, "learning_rate": 4.682094268770649e-05, "loss": 5.239, "step": 31000 }, { "epoch": 0.65, "learning_rate": 4.676964274721441e-05, "loss": 5.2202, "step": 31500 }, { "epoch": 0.66, "learning_rate": 4.671834280672235e-05, "loss": 5.24, "step": 32000 }, { "epoch": 0.67, "learning_rate": 4.666704286623028e-05, "loss": 5.1645, "step": 32500 }, { "epoch": 0.68, "learning_rate": 4.661574292573821e-05, "loss": 5.1957, "step": 33000 }, { "epoch": 0.69, "learning_rate": 4.656444298524614e-05, "loss": 5.163, "step": 33500 }, { "epoch": 0.7, "learning_rate": 4.651314304475407e-05, "loss": 5.1395, "step": 34000 }, { "epoch": 0.71, "learning_rate": 4.646194570414298e-05, "loss": 5.156, "step": 34500 }, { "epoch": 0.72, "learning_rate": 4.641064576365092e-05, "loss": 5.1425, "step": 35000 }, { "epoch": 0.73, "learning_rate": 4.635934582315885e-05, "loss": 5.1205, "step": 35500 }, { "epoch": 0.74, "learning_rate": 4.630814848254776e-05, "loss": 5.0797, "step": 36000 }, { "epoch": 0.75, "learning_rate": 4.625684854205569e-05, "loss": 5.1206, "step": 36500 }, { "epoch": 0.76, "learning_rate": 4.620554860156363e-05, "loss": 5.0963, "step": 37000 }, { "epoch": 0.77, "learning_rate": 4.615424866107155e-05, "loss": 5.047, "step": 37500 }, { "epoch": 0.78, "learning_rate": 4.610294872057949e-05, "loss": 5.0337, "step": 38000 }, { "epoch": 0.79, "learning_rate": 4.6051648780087416e-05, "loss": 5.0447, "step": 38500 }, { "epoch": 0.8, "learning_rate": 4.600045143947633e-05, "loss": 5.0363, "step": 39000 }, { "epoch": 0.81, "learning_rate": 4.594915149898426e-05, "loss": 5.0541, "step": 39500 }, { "epoch": 0.82, "learning_rate": 4.5897851558492196e-05, "loss": 5.0135, "step": 40000 }, { "epoch": 0.83, "learning_rate": 4.5846551618000126e-05, "loss": 5.0131, "step": 40500 }, { "epoch": 0.84, "learning_rate": 4.5795251677508055e-05, "loss": 5.006, "step": 41000 }, { "epoch": 0.85, "learning_rate": 4.574395173701599e-05, "loss": 4.9761, "step": 41500 }, { "epoch": 0.86, "learning_rate": 4.5692754396404905e-05, "loss": 4.9729, "step": 42000 }, { "epoch": 0.87, "learning_rate": 4.5641454455912835e-05, "loss": 4.9476, "step": 42500 }, { "epoch": 0.88, "learning_rate": 4.5590154515420765e-05, "loss": 4.9783, "step": 43000 }, { "epoch": 0.89, "learning_rate": 4.5538854574928695e-05, "loss": 4.934, "step": 43500 }, { "epoch": 0.9, "learning_rate": 4.5487554634436624e-05, "loss": 4.942, "step": 44000 }, { "epoch": 0.91, "learning_rate": 4.543625469394456e-05, "loss": 4.971, "step": 44500 }, { "epoch": 0.92, "learning_rate": 4.5384954753452484e-05, "loss": 4.9091, "step": 45000 }, { "epoch": 0.93, "learning_rate": 4.5333757412841404e-05, "loss": 4.9071, "step": 45500 }, { "epoch": 0.94, "learning_rate": 4.5282457472349334e-05, "loss": 4.9298, "step": 46000 }, { "epoch": 0.95, "learning_rate": 4.5231157531857263e-05, "loss": 4.9334, "step": 46500 }, { "epoch": 0.96, "learning_rate": 4.517996019124618e-05, "loss": 4.9334, "step": 47000 }, { "epoch": 0.97, "learning_rate": 4.5128660250754113e-05, "loss": 4.9512, "step": 47500 }, { "epoch": 0.98, "learning_rate": 4.507736031026204e-05, "loss": 4.9052, "step": 48000 }, { "epoch": 1.0, "learning_rate": 4.502606036976997e-05, "loss": 4.8881, "step": 48500 }, { "epoch": 1.01, "learning_rate": 4.497476042927791e-05, "loss": 4.873, "step": 49000 }, { "epoch": 1.02, "learning_rate": 4.492346048878583e-05, "loss": 4.8642, "step": 49500 }, { "epoch": 1.03, "learning_rate": 4.487216054829377e-05, "loss": 4.8801, "step": 50000 }, { "epoch": 1.04, "learning_rate": 4.48208606078017e-05, "loss": 4.8548, "step": 50500 }, { "epoch": 1.05, "learning_rate": 4.476956066730963e-05, "loss": 4.8291, "step": 51000 }, { "epoch": 1.06, "learning_rate": 4.471826072681756e-05, "loss": 4.8631, "step": 51500 }, { "epoch": 1.07, "learning_rate": 4.466696078632549e-05, "loss": 4.8377, "step": 52000 }, { "epoch": 1.08, "learning_rate": 4.46157634457144e-05, "loss": 4.8645, "step": 52500 }, { "epoch": 1.09, "learning_rate": 4.456446350522234e-05, "loss": 4.7896, "step": 53000 }, { "epoch": 1.1, "learning_rate": 4.451316356473027e-05, "loss": 4.8434, "step": 53500 }, { "epoch": 1.11, "learning_rate": 4.44618636242382e-05, "loss": 4.8492, "step": 54000 }, { "epoch": 1.12, "learning_rate": 4.4410563683746134e-05, "loss": 4.8399, "step": 54500 }, { "epoch": 1.13, "learning_rate": 4.435936634313505e-05, "loss": 4.7979, "step": 55000 }, { "epoch": 1.14, "learning_rate": 4.430806640264297e-05, "loss": 4.8179, "step": 55500 }, { "epoch": 1.15, "learning_rate": 4.4256766462150907e-05, "loss": 4.821, "step": 56000 }, { "epoch": 1.16, "learning_rate": 4.4205466521658836e-05, "loss": 4.7995, "step": 56500 }, { "epoch": 1.17, "learning_rate": 4.4154166581166766e-05, "loss": 4.7851, "step": 57000 }, { "epoch": 1.18, "learning_rate": 4.41028666406747e-05, "loss": 4.7566, "step": 57500 }, { "epoch": 1.19, "learning_rate": 4.4051566700182625e-05, "loss": 4.7688, "step": 58000 }, { "epoch": 1.2, "learning_rate": 4.400026675969056e-05, "loss": 4.787, "step": 58500 }, { "epoch": 1.21, "learning_rate": 4.394917201896046e-05, "loss": 4.7602, "step": 59000 }, { "epoch": 1.22, "learning_rate": 4.389787207846839e-05, "loss": 4.7401, "step": 59500 }, { "epoch": 1.23, "learning_rate": 4.384657213797632e-05, "loss": 4.7633, "step": 60000 }, { "epoch": 1.24, "learning_rate": 4.3795272197484255e-05, "loss": 4.7525, "step": 60500 }, { "epoch": 1.25, "learning_rate": 4.3743972256992185e-05, "loss": 4.7159, "step": 61000 }, { "epoch": 1.26, "learning_rate": 4.3692672316500115e-05, "loss": 4.7274, "step": 61500 }, { "epoch": 1.27, "learning_rate": 4.3641372376008044e-05, "loss": 4.7038, "step": 62000 }, { "epoch": 1.28, "learning_rate": 4.3590072435515974e-05, "loss": 4.6976, "step": 62500 }, { "epoch": 1.29, "learning_rate": 4.353887509490489e-05, "loss": 4.6971, "step": 63000 }, { "epoch": 1.3, "learning_rate": 4.3487575154412824e-05, "loss": 4.697, "step": 63500 }, { "epoch": 1.31, "learning_rate": 4.3436275213920754e-05, "loss": 4.7002, "step": 64000 }, { "epoch": 1.32, "learning_rate": 4.3384975273428683e-05, "loss": 4.6913, "step": 64500 }, { "epoch": 1.33, "learning_rate": 4.333367533293662e-05, "loss": 4.6913, "step": 65000 }, { "epoch": 1.34, "learning_rate": 4.328237539244455e-05, "loss": 4.7019, "step": 65500 }, { "epoch": 1.35, "learning_rate": 4.323107545195248e-05, "loss": 4.6847, "step": 66000 }, { "epoch": 1.36, "learning_rate": 4.317987811134139e-05, "loss": 4.6411, "step": 66500 }, { "epoch": 1.37, "learning_rate": 4.312857817084933e-05, "loss": 4.6794, "step": 67000 }, { "epoch": 1.39, "learning_rate": 4.307727823035725e-05, "loss": 4.6893, "step": 67500 }, { "epoch": 1.4, "learning_rate": 4.302597828986519e-05, "loss": 4.6423, "step": 68000 }, { "epoch": 1.41, "learning_rate": 4.297467834937312e-05, "loss": 4.6048, "step": 68500 }, { "epoch": 1.42, "learning_rate": 4.292337840888105e-05, "loss": 4.6473, "step": 69000 }, { "epoch": 1.43, "learning_rate": 4.287218106826996e-05, "loss": 4.5908, "step": 69500 }, { "epoch": 1.44, "learning_rate": 4.28208811277779e-05, "loss": 4.6576, "step": 70000 }, { "epoch": 1.45, "learning_rate": 4.276958118728582e-05, "loss": 4.6422, "step": 70500 }, { "epoch": 1.46, "learning_rate": 4.271828124679376e-05, "loss": 4.6184, "step": 71000 }, { "epoch": 1.47, "learning_rate": 4.266698130630169e-05, "loss": 4.613, "step": 71500 }, { "epoch": 1.48, "learning_rate": 4.261568136580962e-05, "loss": 4.6211, "step": 72000 }, { "epoch": 1.49, "learning_rate": 4.2564381425317554e-05, "loss": 4.5722, "step": 72500 }, { "epoch": 1.5, "learning_rate": 4.2513081484825477e-05, "loss": 4.6272, "step": 73000 }, { "epoch": 1.51, "learning_rate": 4.246188414421439e-05, "loss": 4.6094, "step": 73500 }, { "epoch": 1.52, "learning_rate": 4.241068680360331e-05, "loss": 4.5994, "step": 74000 }, { "epoch": 1.53, "learning_rate": 4.235938686311124e-05, "loss": 4.5916, "step": 74500 }, { "epoch": 1.54, "learning_rate": 4.230808692261917e-05, "loss": 4.5789, "step": 75000 }, { "epoch": 1.55, "learning_rate": 4.22567869821271e-05, "loss": 4.5941, "step": 75500 }, { "epoch": 1.56, "learning_rate": 4.2205487041635036e-05, "loss": 4.5707, "step": 76000 }, { "epoch": 1.57, "learning_rate": 4.2154187101142966e-05, "loss": 4.6116, "step": 76500 }, { "epoch": 1.58, "learning_rate": 4.2102887160650895e-05, "loss": 4.598, "step": 77000 }, { "epoch": 1.59, "learning_rate": 4.2051587220158825e-05, "loss": 4.6079, "step": 77500 }, { "epoch": 1.6, "learning_rate": 4.2000287279666755e-05, "loss": 4.5904, "step": 78000 }, { "epoch": 1.61, "learning_rate": 4.1949089939055675e-05, "loss": 4.5436, "step": 78500 }, { "epoch": 1.62, "learning_rate": 4.189789259844459e-05, "loss": 4.5608, "step": 79000 }, { "epoch": 1.63, "learning_rate": 4.184659265795252e-05, "loss": 4.539, "step": 79500 }, { "epoch": 1.64, "learning_rate": 4.179529271746045e-05, "loss": 4.5659, "step": 80000 }, { "epoch": 1.65, "learning_rate": 4.1743992776968384e-05, "loss": 4.5041, "step": 80500 }, { "epoch": 1.66, "learning_rate": 4.169269283647631e-05, "loss": 4.5788, "step": 81000 }, { "epoch": 1.67, "learning_rate": 4.1641392895984244e-05, "loss": 4.542, "step": 81500 }, { "epoch": 1.68, "learning_rate": 4.1590092955492174e-05, "loss": 4.5193, "step": 82000 }, { "epoch": 1.69, "learning_rate": 4.1538793015000103e-05, "loss": 4.5562, "step": 82500 }, { "epoch": 1.7, "learning_rate": 4.148749307450804e-05, "loss": 4.4589, "step": 83000 }, { "epoch": 1.71, "learning_rate": 4.143629573389695e-05, "loss": 4.5263, "step": 83500 }, { "epoch": 1.72, "learning_rate": 4.1384995793404876e-05, "loss": 4.4958, "step": 84000 }, { "epoch": 1.73, "learning_rate": 4.1333798452793797e-05, "loss": 4.5111, "step": 84500 }, { "epoch": 1.74, "learning_rate": 4.1282498512301726e-05, "loss": 4.5035, "step": 85000 }, { "epoch": 1.75, "learning_rate": 4.123119857180966e-05, "loss": 4.5078, "step": 85500 }, { "epoch": 1.76, "learning_rate": 4.1179898631317586e-05, "loss": 4.491, "step": 86000 }, { "epoch": 1.77, "learning_rate": 4.112859869082552e-05, "loss": 4.4847, "step": 86500 }, { "epoch": 1.79, "learning_rate": 4.107729875033345e-05, "loss": 4.4864, "step": 87000 }, { "epoch": 1.8, "learning_rate": 4.102599880984138e-05, "loss": 4.4806, "step": 87500 }, { "epoch": 1.81, "learning_rate": 4.0974801469230295e-05, "loss": 4.5149, "step": 88000 }, { "epoch": 1.82, "learning_rate": 4.092350152873823e-05, "loss": 4.4806, "step": 88500 }, { "epoch": 1.83, "learning_rate": 4.087220158824616e-05, "loss": 4.5255, "step": 89000 }, { "epoch": 1.84, "learning_rate": 4.082090164775409e-05, "loss": 4.4811, "step": 89500 }, { "epoch": 1.85, "learning_rate": 4.076960170726202e-05, "loss": 4.4526, "step": 90000 }, { "epoch": 1.86, "learning_rate": 4.071830176676995e-05, "loss": 4.4444, "step": 90500 }, { "epoch": 1.87, "learning_rate": 4.066700182627789e-05, "loss": 4.4464, "step": 91000 }, { "epoch": 1.88, "learning_rate": 4.061570188578581e-05, "loss": 4.4321, "step": 91500 }, { "epoch": 1.89, "learning_rate": 4.0564607145055714e-05, "loss": 4.4777, "step": 92000 }, { "epoch": 1.9, "learning_rate": 4.0513307204563644e-05, "loss": 4.4735, "step": 92500 }, { "epoch": 1.91, "learning_rate": 4.046210986395256e-05, "loss": 4.466, "step": 93000 }, { "epoch": 1.92, "learning_rate": 4.0410809923460494e-05, "loss": 4.4724, "step": 93500 }, { "epoch": 1.93, "learning_rate": 4.035950998296842e-05, "loss": 4.431, "step": 94000 }, { "epoch": 1.94, "learning_rate": 4.030821004247635e-05, "loss": 4.4713, "step": 94500 }, { "epoch": 1.95, "learning_rate": 4.025691010198428e-05, "loss": 4.4095, "step": 95000 }, { "epoch": 1.96, "learning_rate": 4.020561016149221e-05, "loss": 4.4054, "step": 95500 }, { "epoch": 1.97, "learning_rate": 4.015431022100015e-05, "loss": 4.4136, "step": 96000 }, { "epoch": 1.98, "learning_rate": 4.010301028050807e-05, "loss": 4.4432, "step": 96500 }, { "epoch": 1.99, "learning_rate": 4.005171034001601e-05, "loss": 4.3887, "step": 97000 }, { "epoch": 2.0, "learning_rate": 4.000041039952394e-05, "loss": 4.4078, "step": 97500 }, { "epoch": 2.01, "learning_rate": 3.994911045903187e-05, "loss": 4.4154, "step": 98000 }, { "epoch": 2.02, "learning_rate": 3.9897810518539804e-05, "loss": 4.3906, "step": 98500 }, { "epoch": 2.03, "learning_rate": 3.984651057804773e-05, "loss": 4.4291, "step": 99000 }, { "epoch": 2.04, "learning_rate": 3.979531323743665e-05, "loss": 4.3558, "step": 99500 }, { "epoch": 2.05, "learning_rate": 3.974401329694458e-05, "loss": 4.3718, "step": 100000 }, { "epoch": 2.06, "learning_rate": 3.969281595633349e-05, "loss": 4.3902, "step": 100500 }, { "epoch": 2.07, "learning_rate": 3.964151601584142e-05, "loss": 4.3582, "step": 101000 }, { "epoch": 2.08, "learning_rate": 3.959021607534936e-05, "loss": 4.3659, "step": 101500 }, { "epoch": 2.09, "learning_rate": 3.953901873473827e-05, "loss": 4.3793, "step": 102000 }, { "epoch": 2.1, "learning_rate": 3.94877187942462e-05, "loss": 4.3694, "step": 102500 }, { "epoch": 2.11, "learning_rate": 3.943641885375413e-05, "loss": 4.3826, "step": 103000 }, { "epoch": 2.12, "learning_rate": 3.9385118913262066e-05, "loss": 4.375, "step": 103500 }, { "epoch": 2.13, "learning_rate": 3.933381897276999e-05, "loss": 4.4241, "step": 104000 }, { "epoch": 2.14, "learning_rate": 3.9282519032277926e-05, "loss": 4.3498, "step": 104500 }, { "epoch": 2.15, "learning_rate": 3.9231219091785856e-05, "loss": 4.3247, "step": 105000 }, { "epoch": 2.16, "learning_rate": 3.9179919151293785e-05, "loss": 4.3628, "step": 105500 }, { "epoch": 2.18, "learning_rate": 3.9128619210801715e-05, "loss": 4.3408, "step": 106000 }, { "epoch": 2.19, "learning_rate": 3.9077319270309645e-05, "loss": 4.372, "step": 106500 }, { "epoch": 2.2, "learning_rate": 3.902612192969856e-05, "loss": 4.3608, "step": 107000 }, { "epoch": 2.21, "learning_rate": 3.8974821989206495e-05, "loss": 4.353, "step": 107500 }, { "epoch": 2.22, "learning_rate": 3.892352204871443e-05, "loss": 4.3279, "step": 108000 }, { "epoch": 2.23, "learning_rate": 3.8872222108222354e-05, "loss": 4.3806, "step": 108500 }, { "epoch": 2.24, "learning_rate": 3.882092216773029e-05, "loss": 4.3484, "step": 109000 }, { "epoch": 2.25, "learning_rate": 3.8769622227238214e-05, "loss": 4.306, "step": 109500 }, { "epoch": 2.26, "learning_rate": 3.871832228674615e-05, "loss": 4.3324, "step": 110000 }, { "epoch": 2.27, "learning_rate": 3.866702234625408e-05, "loss": 4.3572, "step": 110500 }, { "epoch": 2.28, "learning_rate": 3.861572240576201e-05, "loss": 4.3448, "step": 111000 }, { "epoch": 2.29, "learning_rate": 3.8564422465269946e-05, "loss": 4.3358, "step": 111500 }, { "epoch": 2.3, "learning_rate": 3.851322512465886e-05, "loss": 4.2848, "step": 112000 }, { "epoch": 2.31, "learning_rate": 3.846202778404777e-05, "loss": 4.3378, "step": 112500 }, { "epoch": 2.32, "learning_rate": 3.84107278435557e-05, "loss": 4.3408, "step": 113000 }, { "epoch": 2.33, "learning_rate": 3.835942790306363e-05, "loss": 4.3114, "step": 113500 }, { "epoch": 2.34, "learning_rate": 3.830812796257157e-05, "loss": 4.3221, "step": 114000 }, { "epoch": 2.35, "learning_rate": 3.825682802207949e-05, "loss": 4.3448, "step": 114500 }, { "epoch": 2.36, "learning_rate": 3.820552808158743e-05, "loss": 4.2776, "step": 115000 }, { "epoch": 2.37, "learning_rate": 3.815422814109536e-05, "loss": 4.3126, "step": 115500 }, { "epoch": 2.38, "learning_rate": 3.810292820060329e-05, "loss": 4.2848, "step": 116000 }, { "epoch": 2.39, "learning_rate": 3.80517308599922e-05, "loss": 4.277, "step": 116500 }, { "epoch": 2.4, "learning_rate": 3.800043091950014e-05, "loss": 4.2941, "step": 117000 }, { "epoch": 2.41, "learning_rate": 3.794913097900807e-05, "loss": 4.3109, "step": 117500 }, { "epoch": 2.42, "learning_rate": 3.7897831038516e-05, "loss": 4.2839, "step": 118000 }, { "epoch": 2.43, "learning_rate": 3.784663369790491e-05, "loss": 4.2977, "step": 118500 }, { "epoch": 2.44, "learning_rate": 3.779533375741284e-05, "loss": 4.2763, "step": 119000 }, { "epoch": 2.45, "learning_rate": 3.774403381692078e-05, "loss": 4.2716, "step": 119500 }, { "epoch": 2.46, "learning_rate": 3.769273387642871e-05, "loss": 4.2914, "step": 120000 }, { "epoch": 2.47, "learning_rate": 3.7641433935936636e-05, "loss": 4.2892, "step": 120500 }, { "epoch": 2.48, "learning_rate": 3.7590133995444566e-05, "loss": 4.2721, "step": 121000 }, { "epoch": 2.49, "learning_rate": 3.7538834054952496e-05, "loss": 4.2827, "step": 121500 }, { "epoch": 2.5, "learning_rate": 3.7487534114460426e-05, "loss": 4.2514, "step": 122000 }, { "epoch": 2.51, "learning_rate": 3.743623417396836e-05, "loss": 4.3007, "step": 122500 }, { "epoch": 2.52, "learning_rate": 3.7385036833357276e-05, "loss": 4.3164, "step": 123000 }, { "epoch": 2.53, "learning_rate": 3.7333736892865205e-05, "loss": 4.2493, "step": 123500 }, { "epoch": 2.54, "learning_rate": 3.7282436952373135e-05, "loss": 4.272, "step": 124000 }, { "epoch": 2.55, "learning_rate": 3.7231239611762055e-05, "loss": 4.2676, "step": 124500 }, { "epoch": 2.56, "learning_rate": 3.717993967126998e-05, "loss": 4.2604, "step": 125000 }, { "epoch": 2.58, "learning_rate": 3.7128639730777915e-05, "loss": 4.2754, "step": 125500 }, { "epoch": 2.59, "learning_rate": 3.7077339790285844e-05, "loss": 4.2361, "step": 126000 }, { "epoch": 2.6, "learning_rate": 3.7026039849793774e-05, "loss": 4.2829, "step": 126500 }, { "epoch": 2.61, "learning_rate": 3.697484250918269e-05, "loss": 4.2507, "step": 127000 }, { "epoch": 2.62, "learning_rate": 3.6923542568690624e-05, "loss": 4.235, "step": 127500 }, { "epoch": 2.63, "learning_rate": 3.6872242628198554e-05, "loss": 4.2501, "step": 128000 }, { "epoch": 2.64, "learning_rate": 3.6820942687706484e-05, "loss": 4.2579, "step": 128500 }, { "epoch": 2.65, "learning_rate": 3.676964274721442e-05, "loss": 4.2095, "step": 129000 }, { "epoch": 2.66, "learning_rate": 3.671844540660333e-05, "loss": 4.2339, "step": 129500 }, { "epoch": 2.67, "learning_rate": 3.666714546611126e-05, "loss": 4.2573, "step": 130000 }, { "epoch": 2.68, "learning_rate": 3.661584552561919e-05, "loss": 4.253, "step": 130500 }, { "epoch": 2.69, "learning_rate": 3.656454558512712e-05, "loss": 4.2388, "step": 131000 }, { "epoch": 2.7, "learning_rate": 3.651324564463505e-05, "loss": 4.2168, "step": 131500 }, { "epoch": 2.71, "learning_rate": 3.646204830402397e-05, "loss": 4.2164, "step": 132000 }, { "epoch": 2.72, "learning_rate": 3.64107483635319e-05, "loss": 4.2099, "step": 132500 }, { "epoch": 2.73, "learning_rate": 3.635944842303983e-05, "loss": 4.2155, "step": 133000 }, { "epoch": 2.74, "learning_rate": 3.630814848254776e-05, "loss": 4.2385, "step": 133500 }, { "epoch": 2.75, "learning_rate": 3.625684854205569e-05, "loss": 4.1949, "step": 134000 }, { "epoch": 2.76, "learning_rate": 3.620554860156362e-05, "loss": 4.1929, "step": 134500 }, { "epoch": 2.77, "learning_rate": 3.615424866107156e-05, "loss": 4.2094, "step": 135000 }, { "epoch": 2.78, "learning_rate": 3.610294872057949e-05, "loss": 4.1766, "step": 135500 }, { "epoch": 2.79, "learning_rate": 3.605164878008742e-05, "loss": 4.2076, "step": 136000 }, { "epoch": 2.8, "learning_rate": 3.600045143947633e-05, "loss": 4.224, "step": 136500 }, { "epoch": 2.81, "learning_rate": 3.594915149898426e-05, "loss": 4.2378, "step": 137000 }, { "epoch": 2.82, "learning_rate": 3.58978515584922e-05, "loss": 4.1963, "step": 137500 }, { "epoch": 2.83, "learning_rate": 3.584655161800013e-05, "loss": 4.2194, "step": 138000 }, { "epoch": 2.84, "learning_rate": 3.5795251677508056e-05, "loss": 4.1876, "step": 138500 }, { "epoch": 2.85, "learning_rate": 3.574405433689697e-05, "loss": 4.1573, "step": 139000 }, { "epoch": 2.86, "learning_rate": 3.5692754396404906e-05, "loss": 4.1632, "step": 139500 }, { "epoch": 2.87, "learning_rate": 3.564145445591283e-05, "loss": 4.1946, "step": 140000 }, { "epoch": 2.88, "learning_rate": 3.5590154515420766e-05, "loss": 4.2068, "step": 140500 }, { "epoch": 2.89, "learning_rate": 3.553895717480968e-05, "loss": 4.1915, "step": 141000 }, { "epoch": 2.9, "learning_rate": 3.548765723431761e-05, "loss": 4.166, "step": 141500 }, { "epoch": 2.91, "learning_rate": 3.543635729382554e-05, "loss": 4.1631, "step": 142000 }, { "epoch": 2.92, "learning_rate": 3.5385057353333475e-05, "loss": 4.1724, "step": 142500 }, { "epoch": 2.93, "learning_rate": 3.533386001272239e-05, "loss": 4.1626, "step": 143000 }, { "epoch": 2.94, "learning_rate": 3.528256007223032e-05, "loss": 4.1848, "step": 143500 }, { "epoch": 2.95, "learning_rate": 3.523126013173825e-05, "loss": 4.1468, "step": 144000 }, { "epoch": 2.97, "learning_rate": 3.517996019124618e-05, "loss": 4.2017, "step": 144500 }, { "epoch": 2.98, "learning_rate": 3.512866025075411e-05, "loss": 4.2094, "step": 145000 }, { "epoch": 2.99, "learning_rate": 3.5077360310262044e-05, "loss": 4.1475, "step": 145500 }, { "epoch": 3.0, "learning_rate": 3.502616296965096e-05, "loss": 4.1887, "step": 146000 }, { "epoch": 3.01, "learning_rate": 3.497486302915889e-05, "loss": 4.1589, "step": 146500 }, { "epoch": 3.02, "learning_rate": 3.492356308866682e-05, "loss": 4.1307, "step": 147000 }, { "epoch": 3.03, "learning_rate": 3.487226314817475e-05, "loss": 4.1373, "step": 147500 }, { "epoch": 3.04, "learning_rate": 3.482096320768268e-05, "loss": 4.1346, "step": 148000 }, { "epoch": 3.05, "learning_rate": 3.476966326719061e-05, "loss": 4.1282, "step": 148500 }, { "epoch": 3.06, "learning_rate": 3.471836332669854e-05, "loss": 4.1611, "step": 149000 }, { "epoch": 3.07, "learning_rate": 3.466706338620647e-05, "loss": 4.154, "step": 149500 }, { "epoch": 3.08, "learning_rate": 3.46157634457144e-05, "loss": 4.1765, "step": 150000 }, { "epoch": 3.09, "learning_rate": 3.4564566105103316e-05, "loss": 4.1181, "step": 150500 }, { "epoch": 3.1, "learning_rate": 3.451326616461125e-05, "loss": 4.1712, "step": 151000 }, { "epoch": 3.11, "learning_rate": 3.446196622411918e-05, "loss": 4.1497, "step": 151500 }, { "epoch": 3.12, "learning_rate": 3.441066628362711e-05, "loss": 4.146, "step": 152000 }, { "epoch": 3.13, "learning_rate": 3.435936634313504e-05, "loss": 4.1196, "step": 152500 }, { "epoch": 3.14, "learning_rate": 3.430806640264297e-05, "loss": 4.1407, "step": 153000 }, { "epoch": 3.15, "learning_rate": 3.425676646215091e-05, "loss": 4.1269, "step": 153500 }, { "epoch": 3.16, "learning_rate": 3.420546652165884e-05, "loss": 4.1198, "step": 154000 }, { "epoch": 3.17, "learning_rate": 3.415426918104775e-05, "loss": 4.1264, "step": 154500 }, { "epoch": 3.18, "learning_rate": 3.410307184043667e-05, "loss": 4.1296, "step": 155000 }, { "epoch": 3.19, "learning_rate": 3.4051771899944594e-05, "loss": 4.1359, "step": 155500 }, { "epoch": 3.2, "learning_rate": 3.400047195945253e-05, "loss": 4.1061, "step": 156000 }, { "epoch": 3.21, "learning_rate": 3.394917201896046e-05, "loss": 4.1364, "step": 156500 }, { "epoch": 3.22, "learning_rate": 3.389787207846839e-05, "loss": 4.1629, "step": 157000 }, { "epoch": 3.23, "learning_rate": 3.3846572137976326e-05, "loss": 4.1114, "step": 157500 }, { "epoch": 3.24, "learning_rate": 3.379527219748425e-05, "loss": 4.1195, "step": 158000 }, { "epoch": 3.25, "learning_rate": 3.374407485687317e-05, "loss": 4.127, "step": 158500 }, { "epoch": 3.26, "learning_rate": 3.36927749163811e-05, "loss": 4.0762, "step": 159000 }, { "epoch": 3.27, "learning_rate": 3.364147497588903e-05, "loss": 4.1274, "step": 159500 }, { "epoch": 3.28, "learning_rate": 3.359017503539696e-05, "loss": 4.1027, "step": 160000 }, { "epoch": 3.29, "learning_rate": 3.3538875094904895e-05, "loss": 4.1181, "step": 160500 }, { "epoch": 3.3, "learning_rate": 3.348757515441282e-05, "loss": 4.1254, "step": 161000 }, { "epoch": 3.31, "learning_rate": 3.3436275213920755e-05, "loss": 4.0904, "step": 161500 }, { "epoch": 3.32, "learning_rate": 3.338518047319065e-05, "loss": 4.0986, "step": 162000 }, { "epoch": 3.33, "learning_rate": 3.333388053269859e-05, "loss": 4.124, "step": 162500 }, { "epoch": 3.34, "learning_rate": 3.328258059220651e-05, "loss": 4.0905, "step": 163000 }, { "epoch": 3.36, "learning_rate": 3.323128065171445e-05, "loss": 4.1261, "step": 163500 }, { "epoch": 3.37, "learning_rate": 3.317998071122238e-05, "loss": 4.0871, "step": 164000 }, { "epoch": 3.38, "learning_rate": 3.312868077073031e-05, "loss": 4.0878, "step": 164500 }, { "epoch": 3.39, "learning_rate": 3.307738083023824e-05, "loss": 4.0649, "step": 165000 }, { "epoch": 3.4, "learning_rate": 3.302608088974617e-05, "loss": 4.1072, "step": 165500 }, { "epoch": 3.41, "learning_rate": 3.29747809492541e-05, "loss": 4.0528, "step": 166000 }, { "epoch": 3.42, "learning_rate": 3.2923583608643017e-05, "loss": 4.0903, "step": 166500 }, { "epoch": 3.43, "learning_rate": 3.2872283668150946e-05, "loss": 4.0848, "step": 167000 }, { "epoch": 3.44, "learning_rate": 3.2820983727658876e-05, "loss": 4.039, "step": 167500 }, { "epoch": 3.45, "learning_rate": 3.276968378716681e-05, "loss": 4.0965, "step": 168000 }, { "epoch": 3.46, "learning_rate": 3.2718383846674736e-05, "loss": 4.1169, "step": 168500 }, { "epoch": 3.47, "learning_rate": 3.266708390618267e-05, "loss": 4.1324, "step": 169000 }, { "epoch": 3.48, "learning_rate": 3.26157839656906e-05, "loss": 4.1061, "step": 169500 }, { "epoch": 3.49, "learning_rate": 3.256448402519853e-05, "loss": 4.089, "step": 170000 }, { "epoch": 3.5, "learning_rate": 3.2513286684587445e-05, "loss": 4.094, "step": 170500 }, { "epoch": 3.51, "learning_rate": 3.246198674409538e-05, "loss": 4.0917, "step": 171000 }, { "epoch": 3.52, "learning_rate": 3.2410686803603304e-05, "loss": 4.0532, "step": 171500 }, { "epoch": 3.53, "learning_rate": 3.235938686311124e-05, "loss": 4.0729, "step": 172000 }, { "epoch": 3.54, "learning_rate": 3.2308189522500154e-05, "loss": 4.0459, "step": 172500 }, { "epoch": 3.55, "learning_rate": 3.2256889582008084e-05, "loss": 4.0761, "step": 173000 }, { "epoch": 3.56, "learning_rate": 3.2205589641516014e-05, "loss": 4.0617, "step": 173500 }, { "epoch": 3.57, "learning_rate": 3.215428970102395e-05, "loss": 4.0709, "step": 174000 }, { "epoch": 3.58, "learning_rate": 3.210298976053188e-05, "loss": 4.0661, "step": 174500 }, { "epoch": 3.59, "learning_rate": 3.205168982003981e-05, "loss": 4.0281, "step": 175000 }, { "epoch": 3.6, "learning_rate": 3.200049247942872e-05, "loss": 4.0545, "step": 175500 }, { "epoch": 3.61, "learning_rate": 3.194919253893666e-05, "loss": 4.0483, "step": 176000 }, { "epoch": 3.62, "learning_rate": 3.189789259844459e-05, "loss": 4.0512, "step": 176500 }, { "epoch": 3.63, "learning_rate": 3.184659265795252e-05, "loss": 4.0502, "step": 177000 }, { "epoch": 3.64, "learning_rate": 3.179529271746045e-05, "loss": 4.0288, "step": 177500 }, { "epoch": 3.65, "learning_rate": 3.174409537684936e-05, "loss": 4.0851, "step": 178000 }, { "epoch": 3.66, "learning_rate": 3.16927954363573e-05, "loss": 4.0473, "step": 178500 }, { "epoch": 3.67, "learning_rate": 3.164149549586523e-05, "loss": 4.0553, "step": 179000 }, { "epoch": 3.68, "learning_rate": 3.159029815525414e-05, "loss": 4.0329, "step": 179500 }, { "epoch": 3.69, "learning_rate": 3.153899821476207e-05, "loss": 4.0429, "step": 180000 }, { "epoch": 3.7, "learning_rate": 3.148769827427001e-05, "loss": 4.0339, "step": 180500 }, { "epoch": 3.71, "learning_rate": 3.143639833377793e-05, "loss": 4.0411, "step": 181000 }, { "epoch": 3.72, "learning_rate": 3.138509839328587e-05, "loss": 4.0174, "step": 181500 }, { "epoch": 3.73, "learning_rate": 3.13337984527938e-05, "loss": 4.0375, "step": 182000 }, { "epoch": 3.74, "learning_rate": 3.128249851230173e-05, "loss": 4.0391, "step": 182500 }, { "epoch": 3.76, "learning_rate": 3.123119857180966e-05, "loss": 4.027, "step": 183000 }, { "epoch": 3.77, "learning_rate": 3.118000123119858e-05, "loss": 4.0097, "step": 183500 }, { "epoch": 3.78, "learning_rate": 3.11287012907065e-05, "loss": 4.0425, "step": 184000 }, { "epoch": 3.79, "learning_rate": 3.1077401350214437e-05, "loss": 4.0201, "step": 184500 }, { "epoch": 3.8, "learning_rate": 3.1026101409722366e-05, "loss": 3.997, "step": 185000 }, { "epoch": 3.81, "learning_rate": 3.097490406911128e-05, "loss": 4.0319, "step": 185500 }, { "epoch": 3.82, "learning_rate": 3.092360412861921e-05, "loss": 4.0165, "step": 186000 }, { "epoch": 3.83, "learning_rate": 3.0872304188127146e-05, "loss": 3.9969, "step": 186500 }, { "epoch": 3.84, "learning_rate": 3.0821004247635076e-05, "loss": 3.9924, "step": 187000 }, { "epoch": 3.85, "learning_rate": 3.076980690702399e-05, "loss": 4.0224, "step": 187500 }, { "epoch": 3.86, "learning_rate": 3.071850696653192e-05, "loss": 3.9941, "step": 188000 }, { "epoch": 3.87, "learning_rate": 3.066720702603985e-05, "loss": 4.0328, "step": 188500 }, { "epoch": 3.88, "learning_rate": 3.0615907085547785e-05, "loss": 4.0028, "step": 189000 }, { "epoch": 3.89, "learning_rate": 3.0564607145055715e-05, "loss": 3.9965, "step": 189500 }, { "epoch": 3.9, "learning_rate": 3.0513307204563645e-05, "loss": 4.023, "step": 190000 }, { "epoch": 3.91, "learning_rate": 3.0462007264071574e-05, "loss": 3.9735, "step": 190500 }, { "epoch": 3.92, "learning_rate": 3.041080992346049e-05, "loss": 4.0157, "step": 191000 }, { "epoch": 3.93, "learning_rate": 3.035950998296842e-05, "loss": 4.0167, "step": 191500 }, { "epoch": 3.94, "learning_rate": 3.0308312642357334e-05, "loss": 4.0053, "step": 192000 }, { "epoch": 3.95, "learning_rate": 3.0257012701865267e-05, "loss": 4.0017, "step": 192500 }, { "epoch": 3.96, "learning_rate": 3.02057127613732e-05, "loss": 4.0052, "step": 193000 }, { "epoch": 3.97, "learning_rate": 3.0154412820881127e-05, "loss": 3.9906, "step": 193500 }, { "epoch": 3.98, "learning_rate": 3.010311288038906e-05, "loss": 3.976, "step": 194000 }, { "epoch": 3.99, "learning_rate": 3.005181293989699e-05, "loss": 4.0274, "step": 194500 }, { "epoch": 4.0, "learning_rate": 3.0000512999404923e-05, "loss": 4.0102, "step": 195000 }, { "epoch": 4.01, "learning_rate": 2.9949315658793836e-05, "loss": 3.9998, "step": 195500 }, { "epoch": 4.02, "learning_rate": 2.989801571830177e-05, "loss": 4.0075, "step": 196000 }, { "epoch": 4.03, "learning_rate": 2.9846715777809696e-05, "loss": 4.0114, "step": 196500 }, { "epoch": 4.04, "learning_rate": 2.9795415837317632e-05, "loss": 3.9899, "step": 197000 }, { "epoch": 4.05, "learning_rate": 2.974411589682556e-05, "loss": 3.9896, "step": 197500 }, { "epoch": 4.06, "learning_rate": 2.969281595633349e-05, "loss": 4.0081, "step": 198000 }, { "epoch": 4.07, "learning_rate": 2.9641516015841425e-05, "loss": 3.9918, "step": 198500 }, { "epoch": 4.08, "learning_rate": 2.9590216075349355e-05, "loss": 3.9877, "step": 199000 }, { "epoch": 4.09, "learning_rate": 2.9538916134857288e-05, "loss": 3.9619, "step": 199500 }, { "epoch": 4.1, "learning_rate": 2.9487616194365214e-05, "loss": 3.999, "step": 200000 }, { "epoch": 4.11, "learning_rate": 2.9436418853754134e-05, "loss": 3.9985, "step": 200500 }, { "epoch": 4.12, "learning_rate": 2.938511891326206e-05, "loss": 3.9828, "step": 201000 }, { "epoch": 4.13, "learning_rate": 2.933392157265098e-05, "loss": 3.9799, "step": 201500 }, { "epoch": 4.15, "learning_rate": 2.9282621632158907e-05, "loss": 3.9574, "step": 202000 }, { "epoch": 4.16, "learning_rate": 2.923132169166684e-05, "loss": 3.9762, "step": 202500 }, { "epoch": 4.17, "learning_rate": 2.918002175117477e-05, "loss": 3.9344, "step": 203000 }, { "epoch": 4.18, "learning_rate": 2.9128721810682703e-05, "loss": 4.0109, "step": 203500 }, { "epoch": 4.19, "learning_rate": 2.907742187019063e-05, "loss": 3.9805, "step": 204000 }, { "epoch": 4.2, "learning_rate": 2.9026121929698563e-05, "loss": 3.9499, "step": 204500 }, { "epoch": 4.21, "learning_rate": 2.8974821989206496e-05, "loss": 3.965, "step": 205000 }, { "epoch": 4.22, "learning_rate": 2.892362464859541e-05, "loss": 3.9572, "step": 205500 }, { "epoch": 4.23, "learning_rate": 2.887232470810334e-05, "loss": 3.993, "step": 206000 }, { "epoch": 4.24, "learning_rate": 2.8821024767611272e-05, "loss": 3.9494, "step": 206500 }, { "epoch": 4.25, "learning_rate": 2.8769724827119205e-05, "loss": 3.9585, "step": 207000 }, { "epoch": 4.26, "learning_rate": 2.871842488662713e-05, "loss": 3.9766, "step": 207500 }, { "epoch": 4.27, "learning_rate": 2.8667124946135064e-05, "loss": 3.9779, "step": 208000 }, { "epoch": 4.28, "learning_rate": 2.8615825005642994e-05, "loss": 3.9486, "step": 208500 }, { "epoch": 4.29, "learning_rate": 2.8564525065150927e-05, "loss": 3.977, "step": 209000 }, { "epoch": 4.3, "learning_rate": 2.851332772453984e-05, "loss": 3.9675, "step": 209500 }, { "epoch": 4.31, "learning_rate": 2.8462130383928754e-05, "loss": 3.9637, "step": 210000 }, { "epoch": 4.32, "learning_rate": 2.8410830443436687e-05, "loss": 3.9209, "step": 210500 }, { "epoch": 4.33, "learning_rate": 2.835953050294462e-05, "loss": 3.9515, "step": 211000 }, { "epoch": 4.34, "learning_rate": 2.8308230562452547e-05, "loss": 3.9693, "step": 211500 }, { "epoch": 4.35, "learning_rate": 2.825693062196048e-05, "loss": 3.9517, "step": 212000 }, { "epoch": 4.36, "learning_rate": 2.8205733281349393e-05, "loss": 3.9347, "step": 212500 }, { "epoch": 4.37, "learning_rate": 2.8154433340857326e-05, "loss": 3.9444, "step": 213000 }, { "epoch": 4.38, "learning_rate": 2.8103133400365256e-05, "loss": 3.9793, "step": 213500 }, { "epoch": 4.39, "learning_rate": 2.8051936059754173e-05, "loss": 3.9519, "step": 214000 }, { "epoch": 4.4, "learning_rate": 2.8000636119262103e-05, "loss": 3.9411, "step": 214500 }, { "epoch": 4.41, "learning_rate": 2.7949336178770036e-05, "loss": 4.0059, "step": 215000 }, { "epoch": 4.42, "learning_rate": 2.7898036238277962e-05, "loss": 3.9071, "step": 215500 }, { "epoch": 4.43, "learning_rate": 2.7846736297785895e-05, "loss": 3.9323, "step": 216000 }, { "epoch": 4.44, "learning_rate": 2.7795436357293825e-05, "loss": 3.9026, "step": 216500 }, { "epoch": 4.45, "learning_rate": 2.7744136416801758e-05, "loss": 3.9355, "step": 217000 }, { "epoch": 4.46, "learning_rate": 2.769293907619067e-05, "loss": 3.9487, "step": 217500 }, { "epoch": 4.47, "learning_rate": 2.7641639135698605e-05, "loss": 3.9103, "step": 218000 }, { "epoch": 4.48, "learning_rate": 2.759033919520653e-05, "loss": 3.9136, "step": 218500 }, { "epoch": 4.49, "learning_rate": 2.7539039254714468e-05, "loss": 3.9358, "step": 219000 }, { "epoch": 4.5, "learning_rate": 2.74877393142224e-05, "loss": 3.9526, "step": 219500 }, { "epoch": 4.51, "learning_rate": 2.7436439373730327e-05, "loss": 3.9287, "step": 220000 }, { "epoch": 4.52, "learning_rate": 2.738513943323826e-05, "loss": 3.9084, "step": 220500 }, { "epoch": 4.53, "learning_rate": 2.733383949274619e-05, "loss": 3.9103, "step": 221000 }, { "epoch": 4.55, "learning_rate": 2.7282539552254123e-05, "loss": 3.9452, "step": 221500 }, { "epoch": 4.56, "learning_rate": 2.723123961176205e-05, "loss": 3.9149, "step": 222000 }, { "epoch": 4.57, "learning_rate": 2.7179939671269982e-05, "loss": 3.8862, "step": 222500 }, { "epoch": 4.58, "learning_rate": 2.7128742330658896e-05, "loss": 3.905, "step": 223000 }, { "epoch": 4.59, "learning_rate": 2.707744239016683e-05, "loss": 3.9089, "step": 223500 }, { "epoch": 4.6, "learning_rate": 2.702614244967476e-05, "loss": 3.9231, "step": 224000 }, { "epoch": 4.61, "learning_rate": 2.6974842509182692e-05, "loss": 3.9382, "step": 224500 }, { "epoch": 4.62, "learning_rate": 2.6923542568690625e-05, "loss": 3.9066, "step": 225000 }, { "epoch": 4.63, "learning_rate": 2.687224262819855e-05, "loss": 3.8783, "step": 225500 }, { "epoch": 4.64, "learning_rate": 2.6820942687706484e-05, "loss": 3.8863, "step": 226000 }, { "epoch": 4.65, "learning_rate": 2.6769745347095398e-05, "loss": 3.9364, "step": 226500 }, { "epoch": 4.66, "learning_rate": 2.671844540660333e-05, "loss": 3.9386, "step": 227000 }, { "epoch": 4.67, "learning_rate": 2.666714546611126e-05, "loss": 3.9075, "step": 227500 }, { "epoch": 4.68, "learning_rate": 2.6615948125500174e-05, "loss": 3.8976, "step": 228000 }, { "epoch": 4.69, "learning_rate": 2.6564648185008107e-05, "loss": 3.9058, "step": 228500 }, { "epoch": 4.7, "learning_rate": 2.651334824451604e-05, "loss": 3.909, "step": 229000 }, { "epoch": 4.71, "learning_rate": 2.6462048304023967e-05, "loss": 3.9192, "step": 229500 }, { "epoch": 4.72, "learning_rate": 2.64107483635319e-05, "loss": 3.9413, "step": 230000 }, { "epoch": 4.73, "learning_rate": 2.635944842303983e-05, "loss": 3.8911, "step": 230500 }, { "epoch": 4.74, "learning_rate": 2.6308148482547763e-05, "loss": 3.8748, "step": 231000 }, { "epoch": 4.75, "learning_rate": 2.625684854205569e-05, "loss": 3.8669, "step": 231500 }, { "epoch": 4.76, "learning_rate": 2.6205548601563622e-05, "loss": 3.9275, "step": 232000 }, { "epoch": 4.77, "learning_rate": 2.6154248661071555e-05, "loss": 3.8816, "step": 232500 }, { "epoch": 4.78, "learning_rate": 2.610305132046047e-05, "loss": 3.8978, "step": 233000 }, { "epoch": 4.79, "learning_rate": 2.6051751379968402e-05, "loss": 3.9131, "step": 233500 }, { "epoch": 4.8, "learning_rate": 2.600045143947633e-05, "loss": 3.923, "step": 234000 }, { "epoch": 4.81, "learning_rate": 2.5949151498984265e-05, "loss": 3.9078, "step": 234500 }, { "epoch": 4.82, "learning_rate": 2.589785155849219e-05, "loss": 3.8891, "step": 235000 }, { "epoch": 4.83, "learning_rate": 2.584665421788111e-05, "loss": 3.9043, "step": 235500 }, { "epoch": 4.84, "learning_rate": 2.5795354277389038e-05, "loss": 3.9208, "step": 236000 }, { "epoch": 4.85, "learning_rate": 2.574405433689697e-05, "loss": 3.9073, "step": 236500 }, { "epoch": 4.86, "learning_rate": 2.56927543964049e-05, "loss": 3.887, "step": 237000 }, { "epoch": 4.87, "learning_rate": 2.5641454455912834e-05, "loss": 3.9111, "step": 237500 }, { "epoch": 4.88, "learning_rate": 2.559015451542076e-05, "loss": 3.865, "step": 238000 }, { "epoch": 4.89, "learning_rate": 2.5538854574928693e-05, "loss": 3.9018, "step": 238500 }, { "epoch": 4.9, "learning_rate": 2.548755463443663e-05, "loss": 3.8742, "step": 239000 }, { "epoch": 4.91, "learning_rate": 2.5436459893706527e-05, "loss": 3.8782, "step": 239500 }, { "epoch": 4.92, "learning_rate": 2.5385159953214453e-05, "loss": 3.8779, "step": 240000 }, { "epoch": 4.94, "learning_rate": 2.533386001272239e-05, "loss": 3.903, "step": 240500 }, { "epoch": 4.95, "learning_rate": 2.5282560072230316e-05, "loss": 3.8616, "step": 241000 }, { "epoch": 4.96, "learning_rate": 2.523126013173825e-05, "loss": 3.8687, "step": 241500 }, { "epoch": 4.97, "learning_rate": 2.5180062791127162e-05, "loss": 3.8893, "step": 242000 }, { "epoch": 4.98, "learning_rate": 2.5128762850635096e-05, "loss": 3.8935, "step": 242500 }, { "epoch": 4.99, "learning_rate": 2.5077462910143025e-05, "loss": 3.8659, "step": 243000 }, { "epoch": 5.0, "learning_rate": 2.502616296965096e-05, "loss": 3.9473, "step": 243500 }, { "epoch": 5.01, "learning_rate": 2.4974965629039872e-05, "loss": 3.8634, "step": 244000 }, { "epoch": 5.02, "learning_rate": 2.4923768288428785e-05, "loss": 3.8574, "step": 244500 }, { "epoch": 5.03, "learning_rate": 2.487246834793672e-05, "loss": 3.8773, "step": 245000 }, { "epoch": 5.04, "learning_rate": 2.4821271007325632e-05, "loss": 3.843, "step": 245500 }, { "epoch": 5.05, "learning_rate": 2.4769971066833565e-05, "loss": 3.885, "step": 246000 }, { "epoch": 5.06, "learning_rate": 2.4718671126341495e-05, "loss": 3.8529, "step": 246500 }, { "epoch": 5.07, "learning_rate": 2.4667371185849424e-05, "loss": 3.8452, "step": 247000 }, { "epoch": 5.08, "learning_rate": 2.4616071245357354e-05, "loss": 3.8957, "step": 247500 }, { "epoch": 5.09, "learning_rate": 2.4564771304865287e-05, "loss": 3.8577, "step": 248000 }, { "epoch": 5.1, "learning_rate": 2.451347136437322e-05, "loss": 3.8598, "step": 248500 }, { "epoch": 5.11, "learning_rate": 2.446217142388115e-05, "loss": 3.8613, "step": 249000 }, { "epoch": 5.12, "learning_rate": 2.441087148338908e-05, "loss": 3.8774, "step": 249500 }, { "epoch": 5.13, "learning_rate": 2.435957154289701e-05, "loss": 3.8774, "step": 250000 }, { "epoch": 5.14, "learning_rate": 2.4308271602404943e-05, "loss": 3.8681, "step": 250500 }, { "epoch": 5.15, "learning_rate": 2.4256971661912872e-05, "loss": 3.8859, "step": 251000 }, { "epoch": 5.16, "learning_rate": 2.4205671721420806e-05, "loss": 3.862, "step": 251500 }, { "epoch": 5.17, "learning_rate": 2.4154371780928735e-05, "loss": 3.8659, "step": 252000 }, { "epoch": 5.18, "learning_rate": 2.410307184043667e-05, "loss": 3.8633, "step": 252500 }, { "epoch": 5.19, "learning_rate": 2.4051874499825582e-05, "loss": 3.838, "step": 253000 }, { "epoch": 5.2, "learning_rate": 2.4000677159214495e-05, "loss": 3.8674, "step": 253500 }, { "epoch": 5.21, "learning_rate": 2.394937721872243e-05, "loss": 3.8754, "step": 254000 }, { "epoch": 5.22, "learning_rate": 2.3898077278230358e-05, "loss": 3.8913, "step": 254500 }, { "epoch": 5.23, "learning_rate": 2.3846777337738288e-05, "loss": 3.8363, "step": 255000 }, { "epoch": 5.24, "learning_rate": 2.379547739724622e-05, "loss": 3.8495, "step": 255500 }, { "epoch": 5.25, "learning_rate": 2.374417745675415e-05, "loss": 3.8572, "step": 256000 }, { "epoch": 5.26, "learning_rate": 2.3692877516262084e-05, "loss": 3.8744, "step": 256500 }, { "epoch": 5.27, "learning_rate": 2.3641577575770014e-05, "loss": 3.8673, "step": 257000 }, { "epoch": 5.28, "learning_rate": 2.3590277635277943e-05, "loss": 3.8655, "step": 257500 }, { "epoch": 5.29, "learning_rate": 2.353908029466686e-05, "loss": 3.8382, "step": 258000 }, { "epoch": 5.3, "learning_rate": 2.348778035417479e-05, "loss": 3.8245, "step": 258500 }, { "epoch": 5.31, "learning_rate": 2.343648041368272e-05, "loss": 3.8232, "step": 259000 }, { "epoch": 5.32, "learning_rate": 2.3385180473190653e-05, "loss": 3.8636, "step": 259500 }, { "epoch": 5.34, "learning_rate": 2.3333880532698582e-05, "loss": 3.79, "step": 260000 }, { "epoch": 5.35, "learning_rate": 2.3282580592206516e-05, "loss": 3.8223, "step": 260500 }, { "epoch": 5.36, "learning_rate": 2.3231280651714445e-05, "loss": 3.8356, "step": 261000 }, { "epoch": 5.37, "learning_rate": 2.3180185910984346e-05, "loss": 3.8253, "step": 261500 }, { "epoch": 5.38, "learning_rate": 2.3128885970492276e-05, "loss": 3.8744, "step": 262000 }, { "epoch": 5.39, "learning_rate": 2.3077586030000205e-05, "loss": 3.8458, "step": 262500 }, { "epoch": 5.4, "learning_rate": 2.302628608950814e-05, "loss": 3.8637, "step": 263000 }, { "epoch": 5.41, "learning_rate": 2.2974986149016068e-05, "loss": 3.8397, "step": 263500 }, { "epoch": 5.42, "learning_rate": 2.2923686208523998e-05, "loss": 3.8044, "step": 264000 }, { "epoch": 5.43, "learning_rate": 2.287238626803193e-05, "loss": 3.8173, "step": 264500 }, { "epoch": 5.44, "learning_rate": 2.2821188927420844e-05, "loss": 3.8435, "step": 265000 }, { "epoch": 5.45, "learning_rate": 2.2769888986928774e-05, "loss": 3.8386, "step": 265500 }, { "epoch": 5.46, "learning_rate": 2.2718589046436707e-05, "loss": 3.835, "step": 266000 }, { "epoch": 5.47, "learning_rate": 2.266728910594464e-05, "loss": 3.8471, "step": 266500 }, { "epoch": 5.48, "learning_rate": 2.261598916545257e-05, "loss": 3.8465, "step": 267000 }, { "epoch": 5.49, "learning_rate": 2.25646892249605e-05, "loss": 3.8589, "step": 267500 }, { "epoch": 5.5, "learning_rate": 2.251338928446843e-05, "loss": 3.8235, "step": 268000 }, { "epoch": 5.51, "learning_rate": 2.2462089343976363e-05, "loss": 3.8023, "step": 268500 }, { "epoch": 5.52, "learning_rate": 2.2410789403484292e-05, "loss": 3.8117, "step": 269000 }, { "epoch": 5.53, "learning_rate": 2.235969466275419e-05, "loss": 3.8287, "step": 269500 }, { "epoch": 5.54, "learning_rate": 2.2308394722262123e-05, "loss": 3.8649, "step": 270000 }, { "epoch": 5.55, "learning_rate": 2.2257094781770056e-05, "loss": 3.8493, "step": 270500 }, { "epoch": 5.56, "learning_rate": 2.2205794841277986e-05, "loss": 3.8159, "step": 271000 }, { "epoch": 5.57, "learning_rate": 2.2154494900785915e-05, "loss": 3.8185, "step": 271500 }, { "epoch": 5.58, "learning_rate": 2.2103194960293845e-05, "loss": 3.789, "step": 272000 }, { "epoch": 5.59, "learning_rate": 2.2051895019801778e-05, "loss": 3.8325, "step": 272500 }, { "epoch": 5.6, "learning_rate": 2.200059507930971e-05, "loss": 3.8406, "step": 273000 }, { "epoch": 5.61, "learning_rate": 2.194929513881764e-05, "loss": 3.8304, "step": 273500 }, { "epoch": 5.62, "learning_rate": 2.189799519832557e-05, "loss": 3.828, "step": 274000 }, { "epoch": 5.63, "learning_rate": 2.1846797857714484e-05, "loss": 3.8338, "step": 274500 }, { "epoch": 5.64, "learning_rate": 2.1795497917222417e-05, "loss": 3.7988, "step": 275000 }, { "epoch": 5.65, "learning_rate": 2.174419797673035e-05, "loss": 3.8681, "step": 275500 }, { "epoch": 5.66, "learning_rate": 2.169289803623828e-05, "loss": 3.8073, "step": 276000 }, { "epoch": 5.67, "learning_rate": 2.1641700695627194e-05, "loss": 3.8385, "step": 276500 }, { "epoch": 5.68, "learning_rate": 2.1590400755135127e-05, "loss": 3.8167, "step": 277000 }, { "epoch": 5.69, "learning_rate": 2.153920341452404e-05, "loss": 3.8017, "step": 277500 }, { "epoch": 5.7, "learning_rate": 2.148790347403197e-05, "loss": 3.8083, "step": 278000 }, { "epoch": 5.71, "learning_rate": 2.1436603533539903e-05, "loss": 3.7946, "step": 278500 }, { "epoch": 5.73, "learning_rate": 2.1385303593047833e-05, "loss": 3.7821, "step": 279000 }, { "epoch": 5.74, "learning_rate": 2.1334003652555766e-05, "loss": 3.8217, "step": 279500 }, { "epoch": 5.75, "learning_rate": 2.1282703712063695e-05, "loss": 3.831, "step": 280000 }, { "epoch": 5.76, "learning_rate": 2.1231403771571625e-05, "loss": 3.8005, "step": 280500 }, { "epoch": 5.77, "learning_rate": 2.1180103831079555e-05, "loss": 3.8192, "step": 281000 }, { "epoch": 5.78, "learning_rate": 2.1128803890587488e-05, "loss": 3.8005, "step": 281500 }, { "epoch": 5.79, "learning_rate": 2.10776065499764e-05, "loss": 3.805, "step": 282000 }, { "epoch": 5.8, "learning_rate": 2.1026306609484335e-05, "loss": 3.7921, "step": 282500 }, { "epoch": 5.81, "learning_rate": 2.0975006668992264e-05, "loss": 3.7936, "step": 283000 }, { "epoch": 5.82, "learning_rate": 2.0923706728500194e-05, "loss": 3.8194, "step": 283500 }, { "epoch": 5.83, "learning_rate": 2.087250938788911e-05, "loss": 3.7764, "step": 284000 }, { "epoch": 5.84, "learning_rate": 2.082120944739704e-05, "loss": 3.7881, "step": 284500 }, { "epoch": 5.85, "learning_rate": 2.0769909506904974e-05, "loss": 3.7697, "step": 285000 }, { "epoch": 5.86, "learning_rate": 2.0718609566412903e-05, "loss": 3.8, "step": 285500 }, { "epoch": 5.87, "learning_rate": 2.0667309625920837e-05, "loss": 3.7786, "step": 286000 }, { "epoch": 5.88, "learning_rate": 2.0616009685428766e-05, "loss": 3.822, "step": 286500 }, { "epoch": 5.89, "learning_rate": 2.0564709744936696e-05, "loss": 3.7656, "step": 287000 }, { "epoch": 5.9, "learning_rate": 2.0513512404325613e-05, "loss": 3.796, "step": 287500 }, { "epoch": 5.91, "learning_rate": 2.0462212463833543e-05, "loss": 3.8181, "step": 288000 }, { "epoch": 5.92, "learning_rate": 2.0410912523341476e-05, "loss": 3.8336, "step": 288500 }, { "epoch": 5.93, "learning_rate": 2.035971518273039e-05, "loss": 3.7975, "step": 289000 }, { "epoch": 5.94, "learning_rate": 2.0308415242238322e-05, "loss": 3.7465, "step": 289500 }, { "epoch": 5.95, "learning_rate": 2.0257115301746252e-05, "loss": 3.7907, "step": 290000 }, { "epoch": 5.96, "learning_rate": 2.0205815361254182e-05, "loss": 3.7742, "step": 290500 }, { "epoch": 5.97, "learning_rate": 2.015451542076211e-05, "loss": 3.8057, "step": 291000 }, { "epoch": 5.98, "learning_rate": 2.0103215480270045e-05, "loss": 3.8435, "step": 291500 }, { "epoch": 5.99, "learning_rate": 2.0051915539777974e-05, "loss": 3.7912, "step": 292000 }, { "epoch": 6.0, "learning_rate": 2.0000615599285904e-05, "loss": 3.7894, "step": 292500 }, { "epoch": 6.01, "learning_rate": 1.994941825867482e-05, "loss": 3.7659, "step": 293000 }, { "epoch": 6.02, "learning_rate": 1.989811831818275e-05, "loss": 3.7678, "step": 293500 }, { "epoch": 6.03, "learning_rate": 1.9846920977571667e-05, "loss": 3.7787, "step": 294000 }, { "epoch": 6.04, "learning_rate": 1.9795621037079597e-05, "loss": 3.7889, "step": 294500 }, { "epoch": 6.05, "learning_rate": 1.9744321096587527e-05, "loss": 3.776, "step": 295000 }, { "epoch": 6.06, "learning_rate": 1.969302115609546e-05, "loss": 3.8081, "step": 295500 }, { "epoch": 6.07, "learning_rate": 1.9641823815484377e-05, "loss": 3.7669, "step": 296000 }, { "epoch": 6.08, "learning_rate": 1.9590523874992307e-05, "loss": 3.8278, "step": 296500 }, { "epoch": 6.09, "learning_rate": 1.9539223934500236e-05, "loss": 3.7803, "step": 297000 }, { "epoch": 6.1, "learning_rate": 1.9487923994008166e-05, "loss": 3.8018, "step": 297500 }, { "epoch": 6.11, "learning_rate": 1.94366240535161e-05, "loss": 3.7972, "step": 298000 }, { "epoch": 6.13, "learning_rate": 1.9385324113024032e-05, "loss": 3.7718, "step": 298500 }, { "epoch": 6.14, "learning_rate": 1.9334024172531962e-05, "loss": 3.766, "step": 299000 }, { "epoch": 6.15, "learning_rate": 1.9282724232039892e-05, "loss": 3.7857, "step": 299500 }, { "epoch": 6.16, "learning_rate": 1.9231526891428805e-05, "loss": 3.7604, "step": 300000 }, { "epoch": 6.17, "learning_rate": 1.9180226950936738e-05, "loss": 3.77, "step": 300500 }, { "epoch": 6.18, "learning_rate": 1.9128927010444668e-05, "loss": 3.7844, "step": 301000 }, { "epoch": 6.19, "learning_rate": 1.90776270699526e-05, "loss": 3.8153, "step": 301500 }, { "epoch": 6.2, "learning_rate": 1.902632712946053e-05, "loss": 3.7875, "step": 302000 }, { "epoch": 6.21, "learning_rate": 1.897502718896846e-05, "loss": 3.749, "step": 302500 }, { "epoch": 6.22, "learning_rate": 1.892372724847639e-05, "loss": 3.7781, "step": 303000 }, { "epoch": 6.23, "learning_rate": 1.8872427307984323e-05, "loss": 3.7711, "step": 303500 }, { "epoch": 6.24, "learning_rate": 1.8821127367492257e-05, "loss": 3.7755, "step": 304000 }, { "epoch": 6.25, "learning_rate": 1.8769827427000186e-05, "loss": 3.7479, "step": 304500 }, { "epoch": 6.26, "learning_rate": 1.8718527486508116e-05, "loss": 3.78, "step": 305000 }, { "epoch": 6.27, "learning_rate": 1.8667227546016046e-05, "loss": 3.7609, "step": 305500 }, { "epoch": 6.28, "learning_rate": 1.8616030205404963e-05, "loss": 3.7848, "step": 306000 }, { "epoch": 6.29, "learning_rate": 1.8564832864793876e-05, "loss": 3.7519, "step": 306500 }, { "epoch": 6.3, "learning_rate": 1.8513532924301806e-05, "loss": 3.7789, "step": 307000 }, { "epoch": 6.31, "learning_rate": 1.8462232983809742e-05, "loss": 3.759, "step": 307500 }, { "epoch": 6.32, "learning_rate": 1.8411035643198656e-05, "loss": 3.7669, "step": 308000 }, { "epoch": 6.33, "learning_rate": 1.8359735702706585e-05, "loss": 3.7612, "step": 308500 }, { "epoch": 6.34, "learning_rate": 1.830843576221452e-05, "loss": 3.7493, "step": 309000 }, { "epoch": 6.35, "learning_rate": 1.8257135821722448e-05, "loss": 3.7789, "step": 309500 }, { "epoch": 6.36, "learning_rate": 1.8205835881230378e-05, "loss": 3.7703, "step": 310000 }, { "epoch": 6.37, "learning_rate": 1.815453594073831e-05, "loss": 3.7513, "step": 310500 }, { "epoch": 6.38, "learning_rate": 1.810323600024624e-05, "loss": 3.745, "step": 311000 }, { "epoch": 6.39, "learning_rate": 1.805193605975417e-05, "loss": 3.743, "step": 311500 }, { "epoch": 6.4, "learning_rate": 1.80006361192621e-05, "loss": 3.7827, "step": 312000 }, { "epoch": 6.41, "learning_rate": 1.7949438778651017e-05, "loss": 3.766, "step": 312500 }, { "epoch": 6.42, "learning_rate": 1.7898241438039934e-05, "loss": 3.7877, "step": 313000 }, { "epoch": 6.43, "learning_rate": 1.7846941497547864e-05, "loss": 3.7391, "step": 313500 }, { "epoch": 6.44, "learning_rate": 1.7795641557055793e-05, "loss": 3.7594, "step": 314000 }, { "epoch": 6.45, "learning_rate": 1.7744341616563727e-05, "loss": 3.7925, "step": 314500 }, { "epoch": 6.46, "learning_rate": 1.769314427595264e-05, "loss": 3.7439, "step": 315000 }, { "epoch": 6.47, "learning_rate": 1.7641844335460573e-05, "loss": 3.7496, "step": 315500 }, { "epoch": 6.48, "learning_rate": 1.7590544394968503e-05, "loss": 3.7429, "step": 316000 }, { "epoch": 6.49, "learning_rate": 1.7539244454476433e-05, "loss": 3.7272, "step": 316500 }, { "epoch": 6.5, "learning_rate": 1.7487944513984362e-05, "loss": 3.7492, "step": 317000 }, { "epoch": 6.52, "learning_rate": 1.7436644573492295e-05, "loss": 3.7413, "step": 317500 }, { "epoch": 6.53, "learning_rate": 1.738534463300023e-05, "loss": 3.7537, "step": 318000 }, { "epoch": 6.54, "learning_rate": 1.7334044692508158e-05, "loss": 3.757, "step": 318500 }, { "epoch": 6.55, "learning_rate": 1.7282744752016088e-05, "loss": 3.763, "step": 319000 }, { "epoch": 6.56, "learning_rate": 1.723144481152402e-05, "loss": 3.7308, "step": 319500 }, { "epoch": 6.57, "learning_rate": 1.718014487103195e-05, "loss": 3.7588, "step": 320000 }, { "epoch": 6.58, "learning_rate": 1.712884493053988e-05, "loss": 3.7518, "step": 320500 }, { "epoch": 6.59, "learning_rate": 1.7077647589928797e-05, "loss": 3.7607, "step": 321000 }, { "epoch": 6.6, "learning_rate": 1.7026347649436727e-05, "loss": 3.7389, "step": 321500 }, { "epoch": 6.61, "learning_rate": 1.6975047708944657e-05, "loss": 3.7351, "step": 322000 }, { "epoch": 6.62, "learning_rate": 1.692374776845259e-05, "loss": 3.7515, "step": 322500 }, { "epoch": 6.63, "learning_rate": 1.687244782796052e-05, "loss": 3.7696, "step": 323000 }, { "epoch": 6.64, "learning_rate": 1.6821250487349437e-05, "loss": 3.7349, "step": 323500 }, { "epoch": 6.65, "learning_rate": 1.6769950546857366e-05, "loss": 3.7388, "step": 324000 }, { "epoch": 6.66, "learning_rate": 1.6718650606365296e-05, "loss": 3.7543, "step": 324500 }, { "epoch": 6.67, "learning_rate": 1.6667350665873226e-05, "loss": 3.7633, "step": 325000 }, { "epoch": 6.68, "learning_rate": 1.6616153325262143e-05, "loss": 3.7501, "step": 325500 }, { "epoch": 6.69, "learning_rate": 1.6564853384770072e-05, "loss": 3.7473, "step": 326000 }, { "epoch": 6.7, "learning_rate": 1.6513553444278005e-05, "loss": 3.7029, "step": 326500 }, { "epoch": 6.71, "learning_rate": 1.646235610366692e-05, "loss": 3.7224, "step": 327000 }, { "epoch": 6.72, "learning_rate": 1.6411056163174852e-05, "loss": 3.7497, "step": 327500 }, { "epoch": 6.73, "learning_rate": 1.635975622268278e-05, "loss": 3.7226, "step": 328000 }, { "epoch": 6.74, "learning_rate": 1.630845628219071e-05, "loss": 3.748, "step": 328500 }, { "epoch": 6.75, "learning_rate": 1.6257156341698645e-05, "loss": 3.7475, "step": 329000 }, { "epoch": 6.76, "learning_rate": 1.6205856401206578e-05, "loss": 3.7278, "step": 329500 }, { "epoch": 6.77, "learning_rate": 1.6154556460714507e-05, "loss": 3.6932, "step": 330000 }, { "epoch": 6.78, "learning_rate": 1.610335912010342e-05, "loss": 3.7137, "step": 330500 }, { "epoch": 6.79, "learning_rate": 1.6052059179611354e-05, "loss": 3.6953, "step": 331000 }, { "epoch": 6.8, "learning_rate": 1.6000759239119284e-05, "loss": 3.7323, "step": 331500 }, { "epoch": 6.81, "learning_rate": 1.5949459298627213e-05, "loss": 3.7612, "step": 332000 }, { "epoch": 6.82, "learning_rate": 1.5898159358135146e-05, "loss": 3.7452, "step": 332500 }, { "epoch": 6.83, "learning_rate": 1.5846859417643076e-05, "loss": 3.7379, "step": 333000 }, { "epoch": 6.84, "learning_rate": 1.5795662077031993e-05, "loss": 3.7193, "step": 333500 }, { "epoch": 6.85, "learning_rate": 1.5744362136539923e-05, "loss": 3.7023, "step": 334000 }, { "epoch": 6.86, "learning_rate": 1.5693062196047853e-05, "loss": 3.7158, "step": 334500 }, { "epoch": 6.87, "learning_rate": 1.564186485543677e-05, "loss": 3.7399, "step": 335000 }, { "epoch": 6.88, "learning_rate": 1.55905649149447e-05, "loss": 3.7258, "step": 335500 }, { "epoch": 6.89, "learning_rate": 1.553926497445263e-05, "loss": 3.7434, "step": 336000 }, { "epoch": 6.9, "learning_rate": 1.5487965033960562e-05, "loss": 3.7052, "step": 336500 }, { "epoch": 6.92, "learning_rate": 1.5436767693349475e-05, "loss": 3.7202, "step": 337000 }, { "epoch": 6.93, "learning_rate": 1.538546775285741e-05, "loss": 3.7165, "step": 337500 }, { "epoch": 6.94, "learning_rate": 1.5334167812365338e-05, "loss": 3.703, "step": 338000 }, { "epoch": 6.95, "learning_rate": 1.5282867871873268e-05, "loss": 3.698, "step": 338500 }, { "epoch": 6.96, "learning_rate": 1.52315679313812e-05, "loss": 3.7597, "step": 339000 }, { "epoch": 6.97, "learning_rate": 1.5180267990889132e-05, "loss": 3.7319, "step": 339500 }, { "epoch": 6.98, "learning_rate": 1.5128968050397064e-05, "loss": 3.7347, "step": 340000 }, { "epoch": 6.99, "learning_rate": 1.5077668109904994e-05, "loss": 3.7027, "step": 340500 }, { "epoch": 7.0, "learning_rate": 1.5026470769293907e-05, "loss": 3.7179, "step": 341000 }, { "epoch": 7.01, "learning_rate": 1.497517082880184e-05, "loss": 3.6961, "step": 341500 }, { "epoch": 7.02, "learning_rate": 1.4923870888309772e-05, "loss": 3.7059, "step": 342000 }, { "epoch": 7.03, "learning_rate": 1.4872570947817701e-05, "loss": 3.7243, "step": 342500 }, { "epoch": 7.04, "learning_rate": 1.4821271007325633e-05, "loss": 3.6775, "step": 343000 }, { "epoch": 7.05, "learning_rate": 1.4769971066833562e-05, "loss": 3.7294, "step": 343500 }, { "epoch": 7.06, "learning_rate": 1.4718671126341494e-05, "loss": 3.7296, "step": 344000 }, { "epoch": 7.07, "learning_rate": 1.4667371185849424e-05, "loss": 3.699, "step": 344500 }, { "epoch": 7.08, "learning_rate": 1.4616071245357357e-05, "loss": 3.6937, "step": 345000 }, { "epoch": 7.09, "learning_rate": 1.456487390474627e-05, "loss": 3.7385, "step": 345500 }, { "epoch": 7.1, "learning_rate": 1.4513573964254202e-05, "loss": 3.7215, "step": 346000 }, { "epoch": 7.11, "learning_rate": 1.4462274023762131e-05, "loss": 3.6759, "step": 346500 }, { "epoch": 7.12, "learning_rate": 1.4410974083270064e-05, "loss": 3.7289, "step": 347000 }, { "epoch": 7.13, "learning_rate": 1.4359674142777996e-05, "loss": 3.6964, "step": 347500 }, { "epoch": 7.14, "learning_rate": 1.4308374202285926e-05, "loss": 3.7005, "step": 348000 }, { "epoch": 7.15, "learning_rate": 1.4257074261793857e-05, "loss": 3.7368, "step": 348500 }, { "epoch": 7.16, "learning_rate": 1.4205774321301787e-05, "loss": 3.6993, "step": 349000 }, { "epoch": 7.17, "learning_rate": 1.4154576980690704e-05, "loss": 3.7237, "step": 349500 }, { "epoch": 7.18, "learning_rate": 1.4103277040198633e-05, "loss": 3.7022, "step": 350000 }, { "epoch": 7.19, "learning_rate": 1.4051977099706565e-05, "loss": 3.651, "step": 350500 }, { "epoch": 7.2, "learning_rate": 1.4000677159214494e-05, "loss": 3.7123, "step": 351000 }, { "epoch": 7.21, "learning_rate": 1.3949377218722426e-05, "loss": 3.7059, "step": 351500 }, { "epoch": 7.22, "learning_rate": 1.3898179878111343e-05, "loss": 3.7122, "step": 352000 }, { "epoch": 7.23, "learning_rate": 1.3846879937619272e-05, "loss": 3.7173, "step": 352500 }, { "epoch": 7.24, "learning_rate": 1.379568259700819e-05, "loss": 3.7134, "step": 353000 }, { "epoch": 7.25, "learning_rate": 1.3744382656516119e-05, "loss": 3.6982, "step": 353500 }, { "epoch": 7.26, "learning_rate": 1.369308271602405e-05, "loss": 3.7201, "step": 354000 }, { "epoch": 7.27, "learning_rate": 1.364178277553198e-05, "loss": 3.6949, "step": 354500 }, { "epoch": 7.28, "learning_rate": 1.3590482835039912e-05, "loss": 3.6863, "step": 355000 }, { "epoch": 7.29, "learning_rate": 1.3539285494428827e-05, "loss": 3.7027, "step": 355500 }, { "epoch": 7.31, "learning_rate": 1.3487985553936758e-05, "loss": 3.7029, "step": 356000 }, { "epoch": 7.32, "learning_rate": 1.3436685613444688e-05, "loss": 3.6962, "step": 356500 }, { "epoch": 7.33, "learning_rate": 1.338538567295262e-05, "loss": 3.7232, "step": 357000 }, { "epoch": 7.34, "learning_rate": 1.3334085732460552e-05, "loss": 3.7096, "step": 357500 }, { "epoch": 7.35, "learning_rate": 1.3282785791968482e-05, "loss": 3.7207, "step": 358000 }, { "epoch": 7.36, "learning_rate": 1.3231485851476414e-05, "loss": 3.7219, "step": 358500 }, { "epoch": 7.37, "learning_rate": 1.3180288510865327e-05, "loss": 3.7024, "step": 359000 }, { "epoch": 7.38, "learning_rate": 1.312898857037326e-05, "loss": 3.7225, "step": 359500 }, { "epoch": 7.39, "learning_rate": 1.307768862988119e-05, "loss": 3.6723, "step": 360000 }, { "epoch": 7.4, "learning_rate": 1.3026388689389121e-05, "loss": 3.7091, "step": 360500 }, { "epoch": 7.41, "learning_rate": 1.2975088748897051e-05, "loss": 3.6912, "step": 361000 }, { "epoch": 7.42, "learning_rate": 1.2923891408285968e-05, "loss": 3.6878, "step": 361500 }, { "epoch": 7.43, "learning_rate": 1.28725914677939e-05, "loss": 3.6944, "step": 362000 }, { "epoch": 7.44, "learning_rate": 1.2821291527301829e-05, "loss": 3.6658, "step": 362500 }, { "epoch": 7.45, "learning_rate": 1.276999158680976e-05, "loss": 3.7055, "step": 363000 }, { "epoch": 7.46, "learning_rate": 1.271869164631769e-05, "loss": 3.7103, "step": 363500 }, { "epoch": 7.47, "learning_rate": 1.2667391705825622e-05, "loss": 3.701, "step": 364000 }, { "epoch": 7.48, "learning_rate": 1.2616091765333555e-05, "loss": 3.6841, "step": 364500 }, { "epoch": 7.49, "learning_rate": 1.2564894424722468e-05, "loss": 3.6652, "step": 365000 }, { "epoch": 7.5, "learning_rate": 1.2513594484230398e-05, "loss": 3.7217, "step": 365500 }, { "epoch": 7.51, "learning_rate": 1.246229454373833e-05, "loss": 3.7033, "step": 366000 }, { "epoch": 7.52, "learning_rate": 1.241099460324626e-05, "loss": 3.7162, "step": 366500 }, { "epoch": 7.53, "learning_rate": 1.235969466275419e-05, "loss": 3.702, "step": 367000 }, { "epoch": 7.54, "learning_rate": 1.2308394722262124e-05, "loss": 3.6944, "step": 367500 }, { "epoch": 7.55, "learning_rate": 1.2257197381651039e-05, "loss": 3.7221, "step": 368000 }, { "epoch": 7.56, "learning_rate": 1.2205897441158968e-05, "loss": 3.6708, "step": 368500 }, { "epoch": 7.57, "learning_rate": 1.21545975006669e-05, "loss": 3.6831, "step": 369000 }, { "epoch": 7.58, "learning_rate": 1.2103297560174831e-05, "loss": 3.6817, "step": 369500 }, { "epoch": 7.59, "learning_rate": 1.2051997619682761e-05, "loss": 3.7204, "step": 370000 }, { "epoch": 7.6, "learning_rate": 1.2000697679190692e-05, "loss": 3.7261, "step": 370500 }, { "epoch": 7.61, "learning_rate": 1.1949397738698624e-05, "loss": 3.6543, "step": 371000 }, { "epoch": 7.62, "learning_rate": 1.1898200398087539e-05, "loss": 3.7125, "step": 371500 }, { "epoch": 7.63, "learning_rate": 1.1846900457595469e-05, "loss": 3.6821, "step": 372000 }, { "epoch": 7.64, "learning_rate": 1.17956005171034e-05, "loss": 3.6991, "step": 372500 }, { "epoch": 7.65, "learning_rate": 1.1744300576611332e-05, "loss": 3.6953, "step": 373000 }, { "epoch": 7.66, "learning_rate": 1.1693000636119263e-05, "loss": 3.7289, "step": 373500 }, { "epoch": 7.67, "learning_rate": 1.1641700695627193e-05, "loss": 3.6919, "step": 374000 }, { "epoch": 7.68, "learning_rate": 1.1590400755135126e-05, "loss": 3.7074, "step": 374500 }, { "epoch": 7.69, "learning_rate": 1.1539100814643056e-05, "loss": 3.7045, "step": 375000 }, { "epoch": 7.71, "learning_rate": 1.148790347403197e-05, "loss": 3.6862, "step": 375500 }, { "epoch": 7.72, "learning_rate": 1.14366035335399e-05, "loss": 3.661, "step": 376000 }, { "epoch": 7.73, "learning_rate": 1.1385303593047834e-05, "loss": 3.6478, "step": 376500 }, { "epoch": 7.74, "learning_rate": 1.1334003652555763e-05, "loss": 3.6391, "step": 377000 }, { "epoch": 7.75, "learning_rate": 1.1282703712063695e-05, "loss": 3.6802, "step": 377500 }, { "epoch": 7.76, "learning_rate": 1.123150637145261e-05, "loss": 3.67, "step": 378000 }, { "epoch": 7.77, "learning_rate": 1.1180206430960541e-05, "loss": 3.6543, "step": 378500 }, { "epoch": 7.78, "learning_rate": 1.1129009090349456e-05, "loss": 3.6902, "step": 379000 }, { "epoch": 7.79, "learning_rate": 1.1077709149857386e-05, "loss": 3.6943, "step": 379500 }, { "epoch": 7.8, "learning_rate": 1.1026511809246303e-05, "loss": 3.6582, "step": 380000 }, { "epoch": 7.81, "learning_rate": 1.0975211868754233e-05, "loss": 3.7017, "step": 380500 }, { "epoch": 7.82, "learning_rate": 1.0923911928262164e-05, "loss": 3.6806, "step": 381000 }, { "epoch": 7.83, "learning_rate": 1.0872611987770094e-05, "loss": 3.6638, "step": 381500 }, { "epoch": 7.84, "learning_rate": 1.0821312047278025e-05, "loss": 3.683, "step": 382000 }, { "epoch": 7.85, "learning_rate": 1.0770012106785957e-05, "loss": 3.699, "step": 382500 }, { "epoch": 7.86, "learning_rate": 1.0718712166293886e-05, "loss": 3.6675, "step": 383000 }, { "epoch": 7.87, "learning_rate": 1.066741222580182e-05, "loss": 3.6736, "step": 383500 }, { "epoch": 7.88, "learning_rate": 1.061611228530975e-05, "loss": 3.6253, "step": 384000 }, { "epoch": 7.89, "learning_rate": 1.056481234481768e-05, "loss": 3.6682, "step": 384500 }, { "epoch": 7.9, "learning_rate": 1.051351240432561e-05, "loss": 3.6791, "step": 385000 }, { "epoch": 7.91, "learning_rate": 1.0462212463833543e-05, "loss": 3.7102, "step": 385500 }, { "epoch": 7.92, "learning_rate": 1.0411015123222457e-05, "loss": 3.6935, "step": 386000 }, { "epoch": 7.93, "learning_rate": 1.0359715182730388e-05, "loss": 3.6438, "step": 386500 }, { "epoch": 7.94, "learning_rate": 1.030841524223832e-05, "loss": 3.6608, "step": 387000 }, { "epoch": 7.95, "learning_rate": 1.0257217901627235e-05, "loss": 3.6675, "step": 387500 }, { "epoch": 7.96, "learning_rate": 1.0205917961135165e-05, "loss": 3.6718, "step": 388000 }, { "epoch": 7.97, "learning_rate": 1.0154618020643096e-05, "loss": 3.668, "step": 388500 }, { "epoch": 7.98, "learning_rate": 1.0103318080151028e-05, "loss": 3.6562, "step": 389000 }, { "epoch": 7.99, "learning_rate": 1.0052018139658959e-05, "loss": 3.6583, "step": 389500 }, { "epoch": 8.0, "learning_rate": 1.0000718199166889e-05, "loss": 3.6691, "step": 390000 }, { "epoch": 8.01, "learning_rate": 9.949418258674822e-06, "loss": 3.6664, "step": 390500 }, { "epoch": 8.02, "learning_rate": 9.898118318182751e-06, "loss": 3.6405, "step": 391000 }, { "epoch": 8.03, "learning_rate": 9.846920977571667e-06, "loss": 3.6682, "step": 391500 }, { "epoch": 8.04, "learning_rate": 9.795723636960582e-06, "loss": 3.6599, "step": 392000 }, { "epoch": 8.05, "learning_rate": 9.744423696468513e-06, "loss": 3.6527, "step": 392500 }, { "epoch": 8.06, "learning_rate": 9.693123755976443e-06, "loss": 3.697, "step": 393000 }, { "epoch": 8.07, "learning_rate": 9.641823815484374e-06, "loss": 3.646, "step": 393500 }, { "epoch": 8.08, "learning_rate": 9.590523874992304e-06, "loss": 3.6486, "step": 394000 }, { "epoch": 8.1, "learning_rate": 9.539223934500237e-06, "loss": 3.643, "step": 394500 }, { "epoch": 8.11, "learning_rate": 9.488026593889152e-06, "loss": 3.6605, "step": 395000 }, { "epoch": 8.12, "learning_rate": 9.436726653397082e-06, "loss": 3.625, "step": 395500 }, { "epoch": 8.13, "learning_rate": 9.385426712905013e-06, "loss": 3.6781, "step": 396000 }, { "epoch": 8.14, "learning_rate": 9.334126772412945e-06, "loss": 3.684, "step": 396500 }, { "epoch": 8.15, "learning_rate": 9.282826831920875e-06, "loss": 3.6696, "step": 397000 }, { "epoch": 8.16, "learning_rate": 9.231526891428806e-06, "loss": 3.6563, "step": 397500 }, { "epoch": 8.17, "learning_rate": 9.180226950936737e-06, "loss": 3.6521, "step": 398000 }, { "epoch": 8.18, "learning_rate": 9.128927010444669e-06, "loss": 3.6741, "step": 398500 }, { "epoch": 8.19, "learning_rate": 9.077627069952599e-06, "loss": 3.6389, "step": 399000 }, { "epoch": 8.2, "learning_rate": 9.026429729341514e-06, "loss": 3.6597, "step": 399500 }, { "epoch": 8.21, "learning_rate": 8.975129788849445e-06, "loss": 3.669, "step": 400000 }, { "epoch": 8.22, "learning_rate": 8.923829848357377e-06, "loss": 3.6309, "step": 400500 }, { "epoch": 8.23, "learning_rate": 8.872529907865306e-06, "loss": 3.6264, "step": 401000 }, { "epoch": 8.24, "learning_rate": 8.821332567254223e-06, "loss": 3.6721, "step": 401500 }, { "epoch": 8.25, "learning_rate": 8.770032626762153e-06, "loss": 3.627, "step": 402000 }, { "epoch": 8.26, "learning_rate": 8.718835286151068e-06, "loss": 3.6375, "step": 402500 }, { "epoch": 8.27, "learning_rate": 8.667535345659e-06, "loss": 3.663, "step": 403000 }, { "epoch": 8.28, "learning_rate": 8.616235405166931e-06, "loss": 3.6765, "step": 403500 }, { "epoch": 8.29, "learning_rate": 8.56493546467486e-06, "loss": 3.6448, "step": 404000 }, { "epoch": 8.3, "learning_rate": 8.513635524182792e-06, "loss": 3.6436, "step": 404500 }, { "epoch": 8.31, "learning_rate": 8.462335583690723e-06, "loss": 3.664, "step": 405000 }, { "epoch": 8.32, "learning_rate": 8.411035643198655e-06, "loss": 3.658, "step": 405500 }, { "epoch": 8.33, "learning_rate": 8.359735702706585e-06, "loss": 3.642, "step": 406000 }, { "epoch": 8.34, "learning_rate": 8.308435762214516e-06, "loss": 3.6617, "step": 406500 }, { "epoch": 8.35, "learning_rate": 8.257238421603431e-06, "loss": 3.6868, "step": 407000 }, { "epoch": 8.36, "learning_rate": 8.205938481111363e-06, "loss": 3.6467, "step": 407500 }, { "epoch": 8.37, "learning_rate": 8.154638540619292e-06, "loss": 3.671, "step": 408000 }, { "epoch": 8.38, "learning_rate": 8.103338600127225e-06, "loss": 3.667, "step": 408500 }, { "epoch": 8.39, "learning_rate": 8.052141259516139e-06, "loss": 3.6418, "step": 409000 }, { "epoch": 8.4, "learning_rate": 8.00084131902407e-06, "loss": 3.6336, "step": 409500 }, { "epoch": 8.41, "learning_rate": 7.949541378532e-06, "loss": 3.6337, "step": 410000 }, { "epoch": 8.42, "learning_rate": 7.8984466378019e-06, "loss": 3.6312, "step": 410500 }, { "epoch": 8.43, "learning_rate": 7.847146697309832e-06, "loss": 3.6719, "step": 411000 }, { "epoch": 8.44, "learning_rate": 7.795846756817762e-06, "loss": 3.6541, "step": 411500 }, { "epoch": 8.45, "learning_rate": 7.744546816325693e-06, "loss": 3.6703, "step": 412000 }, { "epoch": 8.46, "learning_rate": 7.693246875833625e-06, "loss": 3.666, "step": 412500 }, { "epoch": 8.47, "learning_rate": 7.641946935341556e-06, "loss": 3.6529, "step": 413000 }, { "epoch": 8.49, "learning_rate": 7.590646994849486e-06, "loss": 3.6305, "step": 413500 }, { "epoch": 8.5, "learning_rate": 7.539347054357418e-06, "loss": 3.6171, "step": 414000 }, { "epoch": 8.51, "learning_rate": 7.488149713746332e-06, "loss": 3.6429, "step": 414500 }, { "epoch": 8.52, "learning_rate": 7.436849773254263e-06, "loss": 3.6609, "step": 415000 }, { "epoch": 8.53, "learning_rate": 7.3855498327621935e-06, "loss": 3.6829, "step": 415500 }, { "epoch": 8.54, "learning_rate": 7.334249892270126e-06, "loss": 3.6737, "step": 416000 }, { "epoch": 8.55, "learning_rate": 7.282949951778056e-06, "loss": 3.6503, "step": 416500 }, { "epoch": 8.56, "learning_rate": 7.231650011285987e-06, "loss": 3.5959, "step": 417000 }, { "epoch": 8.57, "learning_rate": 7.180350070793919e-06, "loss": 3.653, "step": 417500 }, { "epoch": 8.58, "learning_rate": 7.12905013030185e-06, "loss": 3.6283, "step": 418000 }, { "epoch": 8.59, "learning_rate": 7.077852789690764e-06, "loss": 3.6632, "step": 418500 }, { "epoch": 8.6, "learning_rate": 7.026552849198695e-06, "loss": 3.6649, "step": 419000 }, { "epoch": 8.61, "learning_rate": 6.975252908706627e-06, "loss": 3.6467, "step": 419500 }, { "epoch": 8.62, "learning_rate": 6.9239529682145574e-06, "loss": 3.672, "step": 420000 }, { "epoch": 8.63, "learning_rate": 6.872653027722488e-06, "loss": 3.6617, "step": 420500 }, { "epoch": 8.64, "learning_rate": 6.821455687111402e-06, "loss": 3.6675, "step": 421000 }, { "epoch": 8.65, "learning_rate": 6.770155746619335e-06, "loss": 3.6744, "step": 421500 }, { "epoch": 8.66, "learning_rate": 6.718855806127265e-06, "loss": 3.642, "step": 422000 }, { "epoch": 8.67, "learning_rate": 6.667555865635196e-06, "loss": 3.6462, "step": 422500 }, { "epoch": 8.68, "learning_rate": 6.616358525024112e-06, "loss": 3.6384, "step": 423000 }, { "epoch": 8.69, "learning_rate": 6.565058584532042e-06, "loss": 3.6566, "step": 423500 }, { "epoch": 8.7, "learning_rate": 6.513758644039973e-06, "loss": 3.627, "step": 424000 }, { "epoch": 8.71, "learning_rate": 6.4624587035479034e-06, "loss": 3.6055, "step": 424500 }, { "epoch": 8.72, "learning_rate": 6.411158763055836e-06, "loss": 3.6213, "step": 425000 }, { "epoch": 8.73, "learning_rate": 6.359858822563766e-06, "loss": 3.6507, "step": 425500 }, { "epoch": 8.74, "learning_rate": 6.308661481952681e-06, "loss": 3.6337, "step": 426000 }, { "epoch": 8.75, "learning_rate": 6.257361541460611e-06, "loss": 3.6383, "step": 426500 }, { "epoch": 8.76, "learning_rate": 6.2060616009685434e-06, "loss": 3.6197, "step": 427000 }, { "epoch": 8.77, "learning_rate": 6.154761660476474e-06, "loss": 3.6605, "step": 427500 }, { "epoch": 8.78, "learning_rate": 6.103461719984405e-06, "loss": 3.6235, "step": 428000 }, { "epoch": 8.79, "learning_rate": 6.052161779492336e-06, "loss": 3.6859, "step": 428500 }, { "epoch": 8.8, "learning_rate": 6.000861839000267e-06, "loss": 3.6256, "step": 429000 }, { "epoch": 8.81, "learning_rate": 5.949561898508198e-06, "loss": 3.6361, "step": 429500 }, { "epoch": 8.82, "learning_rate": 5.898261958016129e-06, "loss": 3.6645, "step": 430000 }, { "epoch": 8.83, "learning_rate": 5.84696201752406e-06, "loss": 3.6387, "step": 430500 }, { "epoch": 8.84, "learning_rate": 5.7956620770319905e-06, "loss": 3.6499, "step": 431000 }, { "epoch": 8.85, "learning_rate": 5.744362136539922e-06, "loss": 3.6571, "step": 431500 }, { "epoch": 8.86, "learning_rate": 5.693164795928837e-06, "loss": 3.6678, "step": 432000 }, { "epoch": 8.87, "learning_rate": 5.6418648554367685e-06, "loss": 3.62, "step": 432500 }, { "epoch": 8.89, "learning_rate": 5.590564914944699e-06, "loss": 3.602, "step": 433000 }, { "epoch": 8.9, "learning_rate": 5.539367574333614e-06, "loss": 3.6465, "step": 433500 }, { "epoch": 8.91, "learning_rate": 5.488067633841545e-06, "loss": 3.6149, "step": 434000 }, { "epoch": 8.92, "learning_rate": 5.436767693349476e-06, "loss": 3.6184, "step": 434500 }, { "epoch": 8.93, "learning_rate": 5.385467752857408e-06, "loss": 3.6606, "step": 435000 }, { "epoch": 8.94, "learning_rate": 5.334167812365338e-06, "loss": 3.6463, "step": 435500 }, { "epoch": 8.95, "learning_rate": 5.282970471754253e-06, "loss": 3.6765, "step": 436000 }, { "epoch": 8.96, "learning_rate": 5.231670531262184e-06, "loss": 3.6274, "step": 436500 }, { "epoch": 8.97, "learning_rate": 5.180370590770115e-06, "loss": 3.608, "step": 437000 }, { "epoch": 8.98, "learning_rate": 5.129070650278046e-06, "loss": 3.6366, "step": 437500 }, { "epoch": 8.99, "learning_rate": 5.077770709785977e-06, "loss": 3.6295, "step": 438000 }, { "epoch": 9.0, "learning_rate": 5.026573369174892e-06, "loss": 3.61, "step": 438500 }, { "epoch": 9.01, "learning_rate": 4.975273428682823e-06, "loss": 3.623, "step": 439000 }, { "epoch": 9.02, "learning_rate": 4.9239734881907545e-06, "loss": 3.6587, "step": 439500 }, { "epoch": 9.03, "learning_rate": 4.872673547698685e-06, "loss": 3.6401, "step": 440000 }, { "epoch": 9.04, "learning_rate": 4.821373607206616e-06, "loss": 3.6167, "step": 440500 }, { "epoch": 9.05, "learning_rate": 4.770073666714546e-06, "loss": 3.6441, "step": 441000 }, { "epoch": 9.06, "learning_rate": 4.718773726222478e-06, "loss": 3.6181, "step": 441500 }, { "epoch": 9.07, "learning_rate": 4.667473785730408e-06, "loss": 3.644, "step": 442000 }, { "epoch": 9.08, "learning_rate": 4.616379045000308e-06, "loss": 3.6274, "step": 442500 }, { "epoch": 9.09, "learning_rate": 4.5650791045082385e-06, "loss": 3.6162, "step": 443000 }, { "epoch": 9.1, "learning_rate": 4.5138817638971545e-06, "loss": 3.6448, "step": 443500 }, { "epoch": 9.11, "learning_rate": 4.462581823405085e-06, "loss": 3.6333, "step": 444000 }, { "epoch": 9.12, "learning_rate": 4.411281882913016e-06, "loss": 3.638, "step": 444500 }, { "epoch": 9.13, "learning_rate": 4.359981942420947e-06, "loss": 3.603, "step": 445000 }, { "epoch": 9.14, "learning_rate": 4.308682001928878e-06, "loss": 3.5923, "step": 445500 }, { "epoch": 9.15, "learning_rate": 4.257382061436809e-06, "loss": 3.6077, "step": 446000 }, { "epoch": 9.16, "learning_rate": 4.206184720825724e-06, "loss": 3.6197, "step": 446500 }, { "epoch": 9.17, "learning_rate": 4.154884780333655e-06, "loss": 3.6563, "step": 447000 }, { "epoch": 9.18, "learning_rate": 4.103584839841585e-06, "loss": 3.5986, "step": 447500 }, { "epoch": 9.19, "learning_rate": 4.052284899349517e-06, "loss": 3.6303, "step": 448000 }, { "epoch": 9.2, "learning_rate": 4.000984958857447e-06, "loss": 3.611, "step": 448500 }, { "epoch": 9.21, "learning_rate": 3.949685018365379e-06, "loss": 3.5932, "step": 449000 }, { "epoch": 9.22, "learning_rate": 3.89838507787331e-06, "loss": 3.6529, "step": 449500 }, { "epoch": 9.23, "learning_rate": 3.847085137381241e-06, "loss": 3.6276, "step": 450000 }, { "epoch": 9.24, "learning_rate": 3.795785196889172e-06, "loss": 3.6366, "step": 450500 }, { "epoch": 9.25, "learning_rate": 3.7445878562780865e-06, "loss": 3.635, "step": 451000 }, { "epoch": 9.26, "learning_rate": 3.693287915786018e-06, "loss": 3.6248, "step": 451500 }, { "epoch": 9.28, "learning_rate": 3.6419879752939485e-06, "loss": 3.6092, "step": 452000 }, { "epoch": 9.29, "learning_rate": 3.59068803480188e-06, "loss": 3.6406, "step": 452500 }, { "epoch": 9.3, "learning_rate": 3.539388094309811e-06, "loss": 3.6074, "step": 453000 }, { "epoch": 9.31, "learning_rate": 3.4880881538177415e-06, "loss": 3.6201, "step": 453500 }, { "epoch": 9.32, "learning_rate": 3.436890813206657e-06, "loss": 3.5992, "step": 454000 }, { "epoch": 9.33, "learning_rate": 3.3855908727145877e-06, "loss": 3.6067, "step": 454500 }, { "epoch": 9.34, "learning_rate": 3.334290932222519e-06, "loss": 3.6521, "step": 455000 }, { "epoch": 9.35, "learning_rate": 3.2829909917304496e-06, "loss": 3.618, "step": 455500 }, { "epoch": 9.36, "learning_rate": 3.2316910512383806e-06, "loss": 3.5911, "step": 456000 }, { "epoch": 9.37, "learning_rate": 3.1803911107463112e-06, "loss": 3.6177, "step": 456500 }, { "epoch": 9.38, "learning_rate": 3.1290911702542426e-06, "loss": 3.6153, "step": 457000 }, { "epoch": 9.39, "learning_rate": 3.0777912297621736e-06, "loss": 3.6284, "step": 457500 }, { "epoch": 9.4, "learning_rate": 3.0265938891510888e-06, "loss": 3.6215, "step": 458000 }, { "epoch": 9.41, "learning_rate": 2.9752939486590198e-06, "loss": 3.6314, "step": 458500 }, { "epoch": 9.42, "learning_rate": 2.9239940081669508e-06, "loss": 3.6157, "step": 459000 }, { "epoch": 9.43, "learning_rate": 2.8726940676748818e-06, "loss": 3.6239, "step": 459500 }, { "epoch": 9.44, "learning_rate": 2.8213941271828128e-06, "loss": 3.6236, "step": 460000 }, { "epoch": 9.45, "learning_rate": 2.7700941866907438e-06, "loss": 3.6384, "step": 460500 }, { "epoch": 9.46, "learning_rate": 2.7187942461986743e-06, "loss": 3.6349, "step": 461000 }, { "epoch": 9.47, "learning_rate": 2.6675969055875895e-06, "loss": 3.6125, "step": 461500 }, { "epoch": 9.48, "learning_rate": 2.6162969650955205e-06, "loss": 3.622, "step": 462000 }, { "epoch": 9.49, "learning_rate": 2.5649970246034515e-06, "loss": 3.6161, "step": 462500 }, { "epoch": 9.5, "learning_rate": 2.513697084111383e-06, "loss": 3.6401, "step": 463000 }, { "epoch": 9.51, "learning_rate": 2.4623971436193135e-06, "loss": 3.637, "step": 463500 }, { "epoch": 9.52, "learning_rate": 2.4110972031272445e-06, "loss": 3.6228, "step": 464000 }, { "epoch": 9.53, "learning_rate": 2.3600024623971438e-06, "loss": 3.6225, "step": 464500 }, { "epoch": 9.54, "learning_rate": 2.3087025219050748e-06, "loss": 3.638, "step": 465000 }, { "epoch": 9.55, "learning_rate": 2.2574025814130058e-06, "loss": 3.6288, "step": 465500 }, { "epoch": 9.56, "learning_rate": 2.2061026409209368e-06, "loss": 3.6212, "step": 466000 }, { "epoch": 9.57, "learning_rate": 2.1548027004288673e-06, "loss": 3.6176, "step": 466500 }, { "epoch": 9.58, "learning_rate": 2.1035027599367983e-06, "loss": 3.6476, "step": 467000 }, { "epoch": 9.59, "learning_rate": 2.0522028194447293e-06, "loss": 3.633, "step": 467500 }, { "epoch": 9.6, "learning_rate": 2.0009028789526607e-06, "loss": 3.6141, "step": 468000 }, { "epoch": 9.61, "learning_rate": 1.9496029384605917e-06, "loss": 3.6138, "step": 468500 }, { "epoch": 9.62, "learning_rate": 1.8983029979685225e-06, "loss": 3.5803, "step": 469000 }, { "epoch": 9.63, "learning_rate": 1.8471056573574377e-06, "loss": 3.6189, "step": 469500 }, { "epoch": 9.64, "learning_rate": 1.7958057168653685e-06, "loss": 3.5963, "step": 470000 }, { "epoch": 9.65, "learning_rate": 1.7445057763732995e-06, "loss": 3.6222, "step": 470500 }, { "epoch": 9.66, "learning_rate": 1.6933084357622146e-06, "loss": 3.6233, "step": 471000 }, { "epoch": 9.68, "learning_rate": 1.6420084952701454e-06, "loss": 3.6486, "step": 471500 }, { "epoch": 9.69, "learning_rate": 1.5907085547780764e-06, "loss": 3.5778, "step": 472000 }, { "epoch": 9.7, "learning_rate": 1.5394086142860074e-06, "loss": 3.6264, "step": 472500 }, { "epoch": 9.71, "learning_rate": 1.4882112736749225e-06, "loss": 3.6235, "step": 473000 }, { "epoch": 9.72, "learning_rate": 1.4369113331828535e-06, "loss": 3.6006, "step": 473500 }, { "epoch": 9.73, "learning_rate": 1.3856113926907845e-06, "loss": 3.5967, "step": 474000 }, { "epoch": 9.74, "learning_rate": 1.3343114521987155e-06, "loss": 3.6154, "step": 474500 }, { "epoch": 9.75, "learning_rate": 1.2830115117066465e-06, "loss": 3.6179, "step": 475000 }, { "epoch": 9.76, "learning_rate": 1.2317115712145775e-06, "loss": 3.6382, "step": 475500 }, { "epoch": 9.77, "learning_rate": 1.1804116307225085e-06, "loss": 3.5936, "step": 476000 }, { "epoch": 9.78, "learning_rate": 1.1292142901114235e-06, "loss": 3.652, "step": 476500 }, { "epoch": 9.79, "learning_rate": 1.0779143496193545e-06, "loss": 3.5949, "step": 477000 }, { "epoch": 9.8, "learning_rate": 1.0266144091272855e-06, "loss": 3.6016, "step": 477500 }, { "epoch": 9.81, "learning_rate": 9.753144686352164e-07, "loss": 3.5945, "step": 478000 }, { "epoch": 9.82, "learning_rate": 9.241171280241316e-07, "loss": 3.608, "step": 478500 }, { "epoch": 9.83, "learning_rate": 8.728171875320625e-07, "loss": 3.6227, "step": 479000 }, { "epoch": 9.84, "learning_rate": 8.215172470399935e-07, "loss": 3.6483, "step": 479500 }, { "epoch": 9.85, "learning_rate": 7.702173065479245e-07, "loss": 3.6404, "step": 480000 }, { "epoch": 9.86, "learning_rate": 7.189173660558555e-07, "loss": 3.5914, "step": 480500 }, { "epoch": 9.87, "learning_rate": 6.676174255637864e-07, "loss": 3.622, "step": 481000 }, { "epoch": 9.88, "learning_rate": 6.163174850717174e-07, "loss": 3.5945, "step": 481500 }, { "epoch": 9.89, "learning_rate": 5.650175445796483e-07, "loss": 3.598, "step": 482000 }, { "epoch": 9.9, "learning_rate": 5.137176040875793e-07, "loss": 3.6166, "step": 482500 }, { "epoch": 9.91, "learning_rate": 4.624176635955103e-07, "loss": 3.5921, "step": 483000 }, { "epoch": 9.92, "learning_rate": 4.111177231034412e-07, "loss": 3.6098, "step": 483500 }, { "epoch": 9.93, "learning_rate": 3.5992038249235634e-07, "loss": 3.6096, "step": 484000 }, { "epoch": 9.94, "learning_rate": 3.086204420002873e-07, "loss": 3.6214, "step": 484500 }, { "epoch": 9.95, "learning_rate": 2.5732050150821823e-07, "loss": 3.6553, "step": 485000 }, { "epoch": 9.96, "learning_rate": 2.0602056101614925e-07, "loss": 3.5965, "step": 485500 }, { "epoch": 9.97, "learning_rate": 1.547206205240802e-07, "loss": 3.618, "step": 486000 }, { "epoch": 9.98, "learning_rate": 1.0342068003201116e-07, "loss": 3.6041, "step": 486500 }, { "epoch": 9.99, "learning_rate": 5.2223339420926276e-08, "loss": 3.6081, "step": 487000 }, { "epoch": 10.0, "step": 487330, "total_flos": 1.5431436054208512e+18, "train_loss": 4.106789583444884, "train_runtime": 101886.156, "train_samples_per_second": 57.397, "train_steps_per_second": 4.783 } ], "logging_steps": 500, "max_steps": 487330, "num_train_epochs": 10, "save_steps": 100000, "total_flos": 1.5431436054208512e+18, "trial_name": null, "trial_params": null }