{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 296598, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.991571082744995e-05, "loss": 7.4188, "step": 500 }, { "epoch": 0.01, "learning_rate": 4.9831421654899904e-05, "loss": 6.5942, "step": 1000 }, { "epoch": 0.02, "learning_rate": 4.974713248234985e-05, "loss": 6.3042, "step": 1500 }, { "epoch": 0.02, "learning_rate": 4.96628433097998e-05, "loss": 6.0941, "step": 2000 }, { "epoch": 0.03, "learning_rate": 4.957855413724975e-05, "loss": 5.9195, "step": 2500 }, { "epoch": 0.03, "learning_rate": 4.94942649646997e-05, "loss": 5.7444, "step": 3000 }, { "epoch": 0.04, "learning_rate": 4.940997579214965e-05, "loss": 5.6261, "step": 3500 }, { "epoch": 0.04, "learning_rate": 4.932568661959959e-05, "loss": 5.5265, "step": 4000 }, { "epoch": 0.05, "learning_rate": 4.924139744704954e-05, "loss": 5.435, "step": 4500 }, { "epoch": 0.05, "learning_rate": 4.915710827449949e-05, "loss": 5.3506, "step": 5000 }, { "epoch": 0.06, "learning_rate": 4.907281910194944e-05, "loss": 5.2732, "step": 5500 }, { "epoch": 0.06, "learning_rate": 4.898852992939939e-05, "loss": 5.2168, "step": 6000 }, { "epoch": 0.07, "learning_rate": 4.890424075684934e-05, "loss": 5.1854, "step": 6500 }, { "epoch": 0.07, "learning_rate": 4.881995158429929e-05, "loss": 5.1008, "step": 7000 }, { "epoch": 0.08, "learning_rate": 4.873566241174924e-05, "loss": 5.0498, "step": 7500 }, { "epoch": 0.08, "learning_rate": 4.865137323919919e-05, "loss": 5.0117, "step": 8000 }, { "epoch": 0.09, "learning_rate": 4.856708406664914e-05, "loss": 4.9638, "step": 8500 }, { "epoch": 0.09, "learning_rate": 4.8482794894099085e-05, "loss": 4.9223, "step": 9000 }, { "epoch": 0.1, "learning_rate": 4.8398505721549036e-05, "loss": 4.8908, "step": 9500 }, { "epoch": 0.1, "learning_rate": 4.8314216548998987e-05, "loss": 4.8656, "step": 10000 }, { "epoch": 0.11, "learning_rate": 4.822992737644894e-05, "loss": 4.8205, "step": 10500 }, { "epoch": 0.11, "learning_rate": 4.814563820389888e-05, "loss": 4.7964, "step": 11000 }, { "epoch": 0.12, "learning_rate": 4.8061349031348826e-05, "loss": 4.7624, "step": 11500 }, { "epoch": 0.12, "learning_rate": 4.797705985879878e-05, "loss": 4.743, "step": 12000 }, { "epoch": 0.13, "learning_rate": 4.789277068624873e-05, "loss": 4.7151, "step": 12500 }, { "epoch": 0.13, "learning_rate": 4.780848151369868e-05, "loss": 4.6802, "step": 13000 }, { "epoch": 0.14, "learning_rate": 4.772419234114863e-05, "loss": 4.6724, "step": 13500 }, { "epoch": 0.14, "learning_rate": 4.7639903168598573e-05, "loss": 4.6377, "step": 14000 }, { "epoch": 0.15, "learning_rate": 4.7555613996048524e-05, "loss": 4.6276, "step": 14500 }, { "epoch": 0.15, "learning_rate": 4.7471324823498475e-05, "loss": 4.5913, "step": 15000 }, { "epoch": 0.16, "learning_rate": 4.7387035650948426e-05, "loss": 4.5709, "step": 15500 }, { "epoch": 0.16, "learning_rate": 4.730274647839838e-05, "loss": 4.5539, "step": 16000 }, { "epoch": 0.17, "learning_rate": 4.721845730584832e-05, "loss": 4.522, "step": 16500 }, { "epoch": 0.17, "learning_rate": 4.713416813329827e-05, "loss": 4.5208, "step": 17000 }, { "epoch": 0.18, "learning_rate": 4.704987896074822e-05, "loss": 4.5034, "step": 17500 }, { "epoch": 0.18, "learning_rate": 4.6965589788198174e-05, "loss": 4.4775, "step": 18000 }, { "epoch": 0.19, "learning_rate": 4.688130061564812e-05, "loss": 4.466, "step": 18500 }, { "epoch": 0.19, "learning_rate": 4.679701144309806e-05, "loss": 4.4464, "step": 19000 }, { "epoch": 0.2, "learning_rate": 4.671272227054801e-05, "loss": 4.4212, "step": 19500 }, { "epoch": 0.2, "learning_rate": 4.6628433097997964e-05, "loss": 4.4229, "step": 20000 }, { "epoch": 0.21, "learning_rate": 4.6544143925447915e-05, "loss": 4.4068, "step": 20500 }, { "epoch": 0.21, "learning_rate": 4.6459854752897866e-05, "loss": 4.3854, "step": 21000 }, { "epoch": 0.22, "learning_rate": 4.637556558034781e-05, "loss": 4.3701, "step": 21500 }, { "epoch": 0.22, "learning_rate": 4.629127640779776e-05, "loss": 4.3506, "step": 22000 }, { "epoch": 0.23, "learning_rate": 4.620698723524771e-05, "loss": 4.3524, "step": 22500 }, { "epoch": 0.23, "learning_rate": 4.612269806269766e-05, "loss": 4.3331, "step": 23000 }, { "epoch": 0.24, "learning_rate": 4.6038408890147614e-05, "loss": 4.3158, "step": 23500 }, { "epoch": 0.24, "learning_rate": 4.595411971759756e-05, "loss": 4.3148, "step": 24000 }, { "epoch": 0.25, "learning_rate": 4.586983054504751e-05, "loss": 4.2895, "step": 24500 }, { "epoch": 0.25, "learning_rate": 4.578554137249746e-05, "loss": 4.2758, "step": 25000 }, { "epoch": 0.26, "learning_rate": 4.5701252199947404e-05, "loss": 4.2797, "step": 25500 }, { "epoch": 0.26, "learning_rate": 4.5616963027397354e-05, "loss": 4.264, "step": 26000 }, { "epoch": 0.27, "learning_rate": 4.55326738548473e-05, "loss": 4.2432, "step": 26500 }, { "epoch": 0.27, "learning_rate": 4.544838468229725e-05, "loss": 4.224, "step": 27000 }, { "epoch": 0.28, "learning_rate": 4.53640955097472e-05, "loss": 4.2356, "step": 27500 }, { "epoch": 0.28, "learning_rate": 4.527980633719715e-05, "loss": 4.2152, "step": 28000 }, { "epoch": 0.29, "learning_rate": 4.51955171646471e-05, "loss": 4.2103, "step": 28500 }, { "epoch": 0.29, "learning_rate": 4.5111227992097046e-05, "loss": 4.201, "step": 29000 }, { "epoch": 0.3, "learning_rate": 4.5026938819547e-05, "loss": 4.1907, "step": 29500 }, { "epoch": 0.3, "learning_rate": 4.494264964699695e-05, "loss": 4.1798, "step": 30000 }, { "epoch": 0.31, "learning_rate": 4.48583604744469e-05, "loss": 4.1872, "step": 30500 }, { "epoch": 0.31, "learning_rate": 4.477407130189685e-05, "loss": 4.1445, "step": 31000 }, { "epoch": 0.32, "learning_rate": 4.4689782129346794e-05, "loss": 4.1435, "step": 31500 }, { "epoch": 0.32, "learning_rate": 4.4605492956796745e-05, "loss": 4.1367, "step": 32000 }, { "epoch": 0.33, "learning_rate": 4.4521203784246696e-05, "loss": 4.1454, "step": 32500 }, { "epoch": 0.33, "learning_rate": 4.443691461169664e-05, "loss": 4.1189, "step": 33000 }, { "epoch": 0.34, "learning_rate": 4.435262543914659e-05, "loss": 4.129, "step": 33500 }, { "epoch": 0.34, "learning_rate": 4.426833626659654e-05, "loss": 4.12, "step": 34000 }, { "epoch": 0.35, "learning_rate": 4.4184047094046486e-05, "loss": 4.1083, "step": 34500 }, { "epoch": 0.35, "learning_rate": 4.409975792149644e-05, "loss": 4.088, "step": 35000 }, { "epoch": 0.36, "learning_rate": 4.401546874894639e-05, "loss": 4.0912, "step": 35500 }, { "epoch": 0.36, "learning_rate": 4.393117957639634e-05, "loss": 4.0765, "step": 36000 }, { "epoch": 0.37, "learning_rate": 4.384689040384628e-05, "loss": 4.0731, "step": 36500 }, { "epoch": 0.37, "learning_rate": 4.3762601231296234e-05, "loss": 4.0675, "step": 37000 }, { "epoch": 0.38, "learning_rate": 4.3678312058746185e-05, "loss": 4.0637, "step": 37500 }, { "epoch": 0.38, "learning_rate": 4.3594022886196135e-05, "loss": 4.0523, "step": 38000 }, { "epoch": 0.39, "learning_rate": 4.3509733713646086e-05, "loss": 4.039, "step": 38500 }, { "epoch": 0.39, "learning_rate": 4.342544454109603e-05, "loss": 4.033, "step": 39000 }, { "epoch": 0.4, "learning_rate": 4.334115536854598e-05, "loss": 4.0292, "step": 39500 }, { "epoch": 0.4, "learning_rate": 4.3256866195995926e-05, "loss": 4.0159, "step": 40000 }, { "epoch": 0.41, "learning_rate": 4.3172577023445876e-05, "loss": 4.0237, "step": 40500 }, { "epoch": 0.41, "learning_rate": 4.308828785089583e-05, "loss": 4.0166, "step": 41000 }, { "epoch": 0.42, "learning_rate": 4.300399867834578e-05, "loss": 4.0101, "step": 41500 }, { "epoch": 0.42, "learning_rate": 4.291970950579572e-05, "loss": 4.0183, "step": 42000 }, { "epoch": 0.43, "learning_rate": 4.283542033324567e-05, "loss": 3.9846, "step": 42500 }, { "epoch": 0.43, "learning_rate": 4.2751131160695624e-05, "loss": 3.9761, "step": 43000 }, { "epoch": 0.44, "learning_rate": 4.2666841988145575e-05, "loss": 3.9846, "step": 43500 }, { "epoch": 0.45, "learning_rate": 4.258255281559552e-05, "loss": 3.9819, "step": 44000 }, { "epoch": 0.45, "learning_rate": 4.249826364304547e-05, "loss": 3.9751, "step": 44500 }, { "epoch": 0.46, "learning_rate": 4.241397447049542e-05, "loss": 3.9737, "step": 45000 }, { "epoch": 0.46, "learning_rate": 4.232968529794537e-05, "loss": 3.9579, "step": 45500 }, { "epoch": 0.47, "learning_rate": 4.224539612539532e-05, "loss": 3.9503, "step": 46000 }, { "epoch": 0.47, "learning_rate": 4.216110695284527e-05, "loss": 3.9301, "step": 46500 }, { "epoch": 0.48, "learning_rate": 4.207681778029522e-05, "loss": 3.934, "step": 47000 }, { "epoch": 0.48, "learning_rate": 4.199252860774516e-05, "loss": 3.9411, "step": 47500 }, { "epoch": 0.49, "learning_rate": 4.190823943519511e-05, "loss": 3.9227, "step": 48000 }, { "epoch": 0.49, "learning_rate": 4.1823950262645064e-05, "loss": 3.9293, "step": 48500 }, { "epoch": 0.5, "learning_rate": 4.1739661090095015e-05, "loss": 3.9195, "step": 49000 }, { "epoch": 0.5, "learning_rate": 4.165537191754496e-05, "loss": 3.9087, "step": 49500 }, { "epoch": 0.51, "learning_rate": 4.157108274499491e-05, "loss": 3.9028, "step": 50000 }, { "epoch": 0.51, "learning_rate": 4.148679357244486e-05, "loss": 3.8927, "step": 50500 }, { "epoch": 0.52, "learning_rate": 4.140250439989481e-05, "loss": 3.896, "step": 51000 }, { "epoch": 0.52, "learning_rate": 4.1318215227344756e-05, "loss": 3.8934, "step": 51500 }, { "epoch": 0.53, "learning_rate": 4.1233926054794707e-05, "loss": 3.8881, "step": 52000 }, { "epoch": 0.53, "learning_rate": 4.114963688224466e-05, "loss": 3.8783, "step": 52500 }, { "epoch": 0.54, "learning_rate": 4.106534770969461e-05, "loss": 3.8818, "step": 53000 }, { "epoch": 0.54, "learning_rate": 4.098105853714456e-05, "loss": 3.8691, "step": 53500 }, { "epoch": 0.55, "learning_rate": 4.08967693645945e-05, "loss": 3.8716, "step": 54000 }, { "epoch": 0.55, "learning_rate": 4.081248019204445e-05, "loss": 3.8566, "step": 54500 }, { "epoch": 0.56, "learning_rate": 4.07281910194944e-05, "loss": 3.8543, "step": 55000 }, { "epoch": 0.56, "learning_rate": 4.064390184694435e-05, "loss": 3.8287, "step": 55500 }, { "epoch": 0.57, "learning_rate": 4.05596126743943e-05, "loss": 3.8522, "step": 56000 }, { "epoch": 0.57, "learning_rate": 4.047532350184425e-05, "loss": 3.8494, "step": 56500 }, { "epoch": 0.58, "learning_rate": 4.0391034329294195e-05, "loss": 3.8555, "step": 57000 }, { "epoch": 0.58, "learning_rate": 4.0306745156744146e-05, "loss": 3.8425, "step": 57500 }, { "epoch": 0.59, "learning_rate": 4.02224559841941e-05, "loss": 3.8463, "step": 58000 }, { "epoch": 0.59, "learning_rate": 4.013816681164405e-05, "loss": 3.8137, "step": 58500 }, { "epoch": 0.6, "learning_rate": 4.005387763909399e-05, "loss": 3.8288, "step": 59000 }, { "epoch": 0.6, "learning_rate": 3.996958846654394e-05, "loss": 3.8284, "step": 59500 }, { "epoch": 0.61, "learning_rate": 3.9885299293993894e-05, "loss": 3.8064, "step": 60000 }, { "epoch": 0.61, "learning_rate": 3.9801010121443845e-05, "loss": 3.8119, "step": 60500 }, { "epoch": 0.62, "learning_rate": 3.9716720948893796e-05, "loss": 3.8089, "step": 61000 }, { "epoch": 0.62, "learning_rate": 3.963243177634374e-05, "loss": 3.8097, "step": 61500 }, { "epoch": 0.63, "learning_rate": 3.9548142603793684e-05, "loss": 3.7904, "step": 62000 }, { "epoch": 0.63, "learning_rate": 3.9463853431243635e-05, "loss": 3.7788, "step": 62500 }, { "epoch": 0.64, "learning_rate": 3.9379564258693586e-05, "loss": 3.7857, "step": 63000 }, { "epoch": 0.64, "learning_rate": 3.929527508614354e-05, "loss": 3.7879, "step": 63500 }, { "epoch": 0.65, "learning_rate": 3.921098591359349e-05, "loss": 3.7764, "step": 64000 }, { "epoch": 0.65, "learning_rate": 3.912669674104343e-05, "loss": 3.7828, "step": 64500 }, { "epoch": 0.66, "learning_rate": 3.904240756849338e-05, "loss": 3.7873, "step": 65000 }, { "epoch": 0.66, "learning_rate": 3.8958118395943333e-05, "loss": 3.7768, "step": 65500 }, { "epoch": 0.67, "learning_rate": 3.8873829223393284e-05, "loss": 3.7599, "step": 66000 }, { "epoch": 0.67, "learning_rate": 3.878954005084323e-05, "loss": 3.7777, "step": 66500 }, { "epoch": 0.68, "learning_rate": 3.870525087829318e-05, "loss": 3.7587, "step": 67000 }, { "epoch": 0.68, "learning_rate": 3.862096170574313e-05, "loss": 3.7525, "step": 67500 }, { "epoch": 0.69, "learning_rate": 3.853667253319308e-05, "loss": 3.7637, "step": 68000 }, { "epoch": 0.69, "learning_rate": 3.845238336064303e-05, "loss": 3.7542, "step": 68500 }, { "epoch": 0.7, "learning_rate": 3.8368094188092976e-05, "loss": 3.7428, "step": 69000 }, { "epoch": 0.7, "learning_rate": 3.828380501554292e-05, "loss": 3.7449, "step": 69500 }, { "epoch": 0.71, "learning_rate": 3.819951584299287e-05, "loss": 3.7293, "step": 70000 }, { "epoch": 0.71, "learning_rate": 3.811522667044282e-05, "loss": 3.7211, "step": 70500 }, { "epoch": 0.72, "learning_rate": 3.803093749789277e-05, "loss": 3.7334, "step": 71000 }, { "epoch": 0.72, "learning_rate": 3.7946648325342724e-05, "loss": 3.7358, "step": 71500 }, { "epoch": 0.73, "learning_rate": 3.786235915279267e-05, "loss": 3.7319, "step": 72000 }, { "epoch": 0.73, "learning_rate": 3.777806998024262e-05, "loss": 3.7033, "step": 72500 }, { "epoch": 0.74, "learning_rate": 3.769378080769257e-05, "loss": 3.7294, "step": 73000 }, { "epoch": 0.74, "learning_rate": 3.760949163514252e-05, "loss": 3.723, "step": 73500 }, { "epoch": 0.75, "learning_rate": 3.7525202462592465e-05, "loss": 3.7173, "step": 74000 }, { "epoch": 0.75, "learning_rate": 3.7440913290042416e-05, "loss": 3.6973, "step": 74500 }, { "epoch": 0.76, "learning_rate": 3.735662411749237e-05, "loss": 3.6998, "step": 75000 }, { "epoch": 0.76, "learning_rate": 3.727233494494232e-05, "loss": 3.6976, "step": 75500 }, { "epoch": 0.77, "learning_rate": 3.718804577239227e-05, "loss": 3.6987, "step": 76000 }, { "epoch": 0.77, "learning_rate": 3.710375659984221e-05, "loss": 3.6976, "step": 76500 }, { "epoch": 0.78, "learning_rate": 3.701946742729216e-05, "loss": 3.6878, "step": 77000 }, { "epoch": 0.78, "learning_rate": 3.693517825474211e-05, "loss": 3.6962, "step": 77500 }, { "epoch": 0.79, "learning_rate": 3.685088908219206e-05, "loss": 3.6938, "step": 78000 }, { "epoch": 0.79, "learning_rate": 3.676659990964201e-05, "loss": 3.6931, "step": 78500 }, { "epoch": 0.8, "learning_rate": 3.668231073709196e-05, "loss": 3.679, "step": 79000 }, { "epoch": 0.8, "learning_rate": 3.6598021564541905e-05, "loss": 3.6773, "step": 79500 }, { "epoch": 0.81, "learning_rate": 3.6513732391991855e-05, "loss": 3.6859, "step": 80000 }, { "epoch": 0.81, "learning_rate": 3.6429443219441806e-05, "loss": 3.6658, "step": 80500 }, { "epoch": 0.82, "learning_rate": 3.634515404689176e-05, "loss": 3.6704, "step": 81000 }, { "epoch": 0.82, "learning_rate": 3.62608648743417e-05, "loss": 3.667, "step": 81500 }, { "epoch": 0.83, "learning_rate": 3.617657570179165e-05, "loss": 3.6595, "step": 82000 }, { "epoch": 0.83, "learning_rate": 3.60922865292416e-05, "loss": 3.6664, "step": 82500 }, { "epoch": 0.84, "learning_rate": 3.6007997356691554e-05, "loss": 3.6504, "step": 83000 }, { "epoch": 0.84, "learning_rate": 3.5923708184141505e-05, "loss": 3.6594, "step": 83500 }, { "epoch": 0.85, "learning_rate": 3.583941901159145e-05, "loss": 3.6538, "step": 84000 }, { "epoch": 0.85, "learning_rate": 3.575512983904139e-05, "loss": 3.6424, "step": 84500 }, { "epoch": 0.86, "learning_rate": 3.5670840666491344e-05, "loss": 3.6572, "step": 85000 }, { "epoch": 0.86, "learning_rate": 3.5586551493941295e-05, "loss": 3.6385, "step": 85500 }, { "epoch": 0.87, "learning_rate": 3.5502262321391246e-05, "loss": 3.6424, "step": 86000 }, { "epoch": 0.87, "learning_rate": 3.54179731488412e-05, "loss": 3.6399, "step": 86500 }, { "epoch": 0.88, "learning_rate": 3.533368397629114e-05, "loss": 3.6462, "step": 87000 }, { "epoch": 0.89, "learning_rate": 3.524939480374109e-05, "loss": 3.6357, "step": 87500 }, { "epoch": 0.89, "learning_rate": 3.516510563119104e-05, "loss": 3.6225, "step": 88000 }, { "epoch": 0.9, "learning_rate": 3.5080816458640994e-05, "loss": 3.6315, "step": 88500 }, { "epoch": 0.9, "learning_rate": 3.499652728609094e-05, "loss": 3.6336, "step": 89000 }, { "epoch": 0.91, "learning_rate": 3.491223811354089e-05, "loss": 3.6243, "step": 89500 }, { "epoch": 0.91, "learning_rate": 3.482794894099084e-05, "loss": 3.6204, "step": 90000 }, { "epoch": 0.92, "learning_rate": 3.474365976844079e-05, "loss": 3.6198, "step": 90500 }, { "epoch": 0.92, "learning_rate": 3.4659370595890735e-05, "loss": 3.6144, "step": 91000 }, { "epoch": 0.93, "learning_rate": 3.4575081423340686e-05, "loss": 3.619, "step": 91500 }, { "epoch": 0.93, "learning_rate": 3.449079225079063e-05, "loss": 3.6076, "step": 92000 }, { "epoch": 0.94, "learning_rate": 3.440650307824058e-05, "loss": 3.6106, "step": 92500 }, { "epoch": 0.94, "learning_rate": 3.432221390569053e-05, "loss": 3.6107, "step": 93000 }, { "epoch": 0.95, "learning_rate": 3.423792473314048e-05, "loss": 3.5949, "step": 93500 }, { "epoch": 0.95, "learning_rate": 3.415363556059043e-05, "loss": 3.5943, "step": 94000 }, { "epoch": 0.96, "learning_rate": 3.406934638804038e-05, "loss": 3.6045, "step": 94500 }, { "epoch": 0.96, "learning_rate": 3.398505721549033e-05, "loss": 3.6008, "step": 95000 }, { "epoch": 0.97, "learning_rate": 3.390076804294028e-05, "loss": 3.5979, "step": 95500 }, { "epoch": 0.97, "learning_rate": 3.381647887039023e-05, "loss": 3.5954, "step": 96000 }, { "epoch": 0.98, "learning_rate": 3.3732189697840174e-05, "loss": 3.5933, "step": 96500 }, { "epoch": 0.98, "learning_rate": 3.3647900525290125e-05, "loss": 3.5832, "step": 97000 }, { "epoch": 0.99, "learning_rate": 3.3563611352740076e-05, "loss": 3.5921, "step": 97500 }, { "epoch": 0.99, "learning_rate": 3.347932218019003e-05, "loss": 3.5949, "step": 98000 }, { "epoch": 1.0, "learning_rate": 3.339503300763997e-05, "loss": 3.5662, "step": 98500 }, { "epoch": 1.0, "learning_rate": 3.331074383508992e-05, "loss": 3.579, "step": 99000 }, { "epoch": 1.01, "learning_rate": 3.3226454662539866e-05, "loss": 3.579, "step": 99500 }, { "epoch": 1.01, "learning_rate": 3.314216548998982e-05, "loss": 3.5618, "step": 100000 }, { "epoch": 1.02, "learning_rate": 3.305787631743977e-05, "loss": 3.5576, "step": 100500 }, { "epoch": 1.02, "learning_rate": 3.297358714488972e-05, "loss": 3.5554, "step": 101000 }, { "epoch": 1.03, "learning_rate": 3.288929797233967e-05, "loss": 3.5695, "step": 101500 }, { "epoch": 1.03, "learning_rate": 3.2805008799789614e-05, "loss": 3.562, "step": 102000 }, { "epoch": 1.04, "learning_rate": 3.2720719627239565e-05, "loss": 3.5669, "step": 102500 }, { "epoch": 1.04, "learning_rate": 3.2636430454689516e-05, "loss": 3.5589, "step": 103000 }, { "epoch": 1.05, "learning_rate": 3.2552141282139467e-05, "loss": 3.5386, "step": 103500 }, { "epoch": 1.05, "learning_rate": 3.246785210958941e-05, "loss": 3.5377, "step": 104000 }, { "epoch": 1.06, "learning_rate": 3.238356293703936e-05, "loss": 3.5474, "step": 104500 }, { "epoch": 1.06, "learning_rate": 3.229927376448931e-05, "loss": 3.5498, "step": 105000 }, { "epoch": 1.07, "learning_rate": 3.221498459193926e-05, "loss": 3.5591, "step": 105500 }, { "epoch": 1.07, "learning_rate": 3.213069541938921e-05, "loss": 3.5507, "step": 106000 }, { "epoch": 1.08, "learning_rate": 3.204640624683916e-05, "loss": 3.546, "step": 106500 }, { "epoch": 1.08, "learning_rate": 3.19621170742891e-05, "loss": 3.5427, "step": 107000 }, { "epoch": 1.09, "learning_rate": 3.1877827901739053e-05, "loss": 3.546, "step": 107500 }, { "epoch": 1.09, "learning_rate": 3.1793538729189004e-05, "loss": 3.522, "step": 108000 }, { "epoch": 1.1, "learning_rate": 3.1709249556638955e-05, "loss": 3.5437, "step": 108500 }, { "epoch": 1.1, "learning_rate": 3.1624960384088906e-05, "loss": 3.5379, "step": 109000 }, { "epoch": 1.11, "learning_rate": 3.154067121153885e-05, "loss": 3.5315, "step": 109500 }, { "epoch": 1.11, "learning_rate": 3.14563820389888e-05, "loss": 3.5331, "step": 110000 }, { "epoch": 1.12, "learning_rate": 3.137209286643875e-05, "loss": 3.5272, "step": 110500 }, { "epoch": 1.12, "learning_rate": 3.12878036938887e-05, "loss": 3.5269, "step": 111000 }, { "epoch": 1.13, "learning_rate": 3.120351452133865e-05, "loss": 3.518, "step": 111500 }, { "epoch": 1.13, "learning_rate": 3.11192253487886e-05, "loss": 3.5109, "step": 112000 }, { "epoch": 1.14, "learning_rate": 3.103493617623855e-05, "loss": 3.5091, "step": 112500 }, { "epoch": 1.14, "learning_rate": 3.095064700368849e-05, "loss": 3.5159, "step": 113000 }, { "epoch": 1.15, "learning_rate": 3.0866357831138444e-05, "loss": 3.5103, "step": 113500 }, { "epoch": 1.15, "learning_rate": 3.0782068658588395e-05, "loss": 3.5101, "step": 114000 }, { "epoch": 1.16, "learning_rate": 3.069777948603834e-05, "loss": 3.5093, "step": 114500 }, { "epoch": 1.16, "learning_rate": 3.061349031348829e-05, "loss": 3.5126, "step": 115000 }, { "epoch": 1.17, "learning_rate": 3.052920114093824e-05, "loss": 3.5123, "step": 115500 }, { "epoch": 1.17, "learning_rate": 3.0444911968388192e-05, "loss": 3.5007, "step": 116000 }, { "epoch": 1.18, "learning_rate": 3.036062279583814e-05, "loss": 3.4994, "step": 116500 }, { "epoch": 1.18, "learning_rate": 3.027633362328809e-05, "loss": 3.5073, "step": 117000 }, { "epoch": 1.19, "learning_rate": 3.0192044450738038e-05, "loss": 3.5034, "step": 117500 }, { "epoch": 1.19, "learning_rate": 3.010775527818799e-05, "loss": 3.5007, "step": 118000 }, { "epoch": 1.2, "learning_rate": 3.0023466105637936e-05, "loss": 3.4919, "step": 118500 }, { "epoch": 1.2, "learning_rate": 2.9939176933087887e-05, "loss": 3.5004, "step": 119000 }, { "epoch": 1.21, "learning_rate": 2.9854887760537838e-05, "loss": 3.488, "step": 119500 }, { "epoch": 1.21, "learning_rate": 2.977059858798778e-05, "loss": 3.4897, "step": 120000 }, { "epoch": 1.22, "learning_rate": 2.968630941543773e-05, "loss": 3.4937, "step": 120500 }, { "epoch": 1.22, "learning_rate": 2.960202024288768e-05, "loss": 3.4891, "step": 121000 }, { "epoch": 1.23, "learning_rate": 2.9517731070337628e-05, "loss": 3.4882, "step": 121500 }, { "epoch": 1.23, "learning_rate": 2.943344189778758e-05, "loss": 3.4956, "step": 122000 }, { "epoch": 1.24, "learning_rate": 2.9349152725237526e-05, "loss": 3.4793, "step": 122500 }, { "epoch": 1.24, "learning_rate": 2.9264863552687477e-05, "loss": 3.4645, "step": 123000 }, { "epoch": 1.25, "learning_rate": 2.9180574380137428e-05, "loss": 3.4715, "step": 123500 }, { "epoch": 1.25, "learning_rate": 2.9096285207587376e-05, "loss": 3.477, "step": 124000 }, { "epoch": 1.26, "learning_rate": 2.9011996035037327e-05, "loss": 3.4731, "step": 124500 }, { "epoch": 1.26, "learning_rate": 2.8927706862487274e-05, "loss": 3.4783, "step": 125000 }, { "epoch": 1.27, "learning_rate": 2.8843417689937225e-05, "loss": 3.4691, "step": 125500 }, { "epoch": 1.27, "learning_rate": 2.8759128517387172e-05, "loss": 3.4762, "step": 126000 }, { "epoch": 1.28, "learning_rate": 2.8674839344837123e-05, "loss": 3.469, "step": 126500 }, { "epoch": 1.28, "learning_rate": 2.8590550172287074e-05, "loss": 3.4829, "step": 127000 }, { "epoch": 1.29, "learning_rate": 2.8506260999737015e-05, "loss": 3.4696, "step": 127500 }, { "epoch": 1.29, "learning_rate": 2.8421971827186966e-05, "loss": 3.4639, "step": 128000 }, { "epoch": 1.3, "learning_rate": 2.8337682654636917e-05, "loss": 3.4525, "step": 128500 }, { "epoch": 1.3, "learning_rate": 2.8253393482086864e-05, "loss": 3.4614, "step": 129000 }, { "epoch": 1.31, "learning_rate": 2.8169104309536815e-05, "loss": 3.476, "step": 129500 }, { "epoch": 1.31, "learning_rate": 2.8084815136986763e-05, "loss": 3.4597, "step": 130000 }, { "epoch": 1.32, "learning_rate": 2.8000525964436714e-05, "loss": 3.4767, "step": 130500 }, { "epoch": 1.33, "learning_rate": 2.7916236791886665e-05, "loss": 3.4643, "step": 131000 }, { "epoch": 1.33, "learning_rate": 2.7831947619336612e-05, "loss": 3.4588, "step": 131500 }, { "epoch": 1.34, "learning_rate": 2.7747658446786563e-05, "loss": 3.4374, "step": 132000 }, { "epoch": 1.34, "learning_rate": 2.766336927423651e-05, "loss": 3.4423, "step": 132500 }, { "epoch": 1.35, "learning_rate": 2.757908010168646e-05, "loss": 3.4514, "step": 133000 }, { "epoch": 1.35, "learning_rate": 2.749479092913641e-05, "loss": 3.4419, "step": 133500 }, { "epoch": 1.36, "learning_rate": 2.741050175658636e-05, "loss": 3.4402, "step": 134000 }, { "epoch": 1.36, "learning_rate": 2.7326212584036304e-05, "loss": 3.4474, "step": 134500 }, { "epoch": 1.37, "learning_rate": 2.7241923411486255e-05, "loss": 3.448, "step": 135000 }, { "epoch": 1.37, "learning_rate": 2.7157634238936202e-05, "loss": 3.4272, "step": 135500 }, { "epoch": 1.38, "learning_rate": 2.7073345066386153e-05, "loss": 3.4551, "step": 136000 }, { "epoch": 1.38, "learning_rate": 2.69890558938361e-05, "loss": 3.437, "step": 136500 }, { "epoch": 1.39, "learning_rate": 2.690476672128605e-05, "loss": 3.4352, "step": 137000 }, { "epoch": 1.39, "learning_rate": 2.6820477548736e-05, "loss": 3.4597, "step": 137500 }, { "epoch": 1.4, "learning_rate": 2.673618837618595e-05, "loss": 3.4474, "step": 138000 }, { "epoch": 1.4, "learning_rate": 2.66518992036359e-05, "loss": 3.4377, "step": 138500 }, { "epoch": 1.41, "learning_rate": 2.656761003108585e-05, "loss": 3.4253, "step": 139000 }, { "epoch": 1.41, "learning_rate": 2.64833208585358e-05, "loss": 3.4227, "step": 139500 }, { "epoch": 1.42, "learning_rate": 2.6399031685985747e-05, "loss": 3.4424, "step": 140000 }, { "epoch": 1.42, "learning_rate": 2.6314742513435698e-05, "loss": 3.4195, "step": 140500 }, { "epoch": 1.43, "learning_rate": 2.6230453340885645e-05, "loss": 3.4337, "step": 141000 }, { "epoch": 1.43, "learning_rate": 2.6146164168335596e-05, "loss": 3.4189, "step": 141500 }, { "epoch": 1.44, "learning_rate": 2.606187499578554e-05, "loss": 3.4247, "step": 142000 }, { "epoch": 1.44, "learning_rate": 2.597758582323549e-05, "loss": 3.4337, "step": 142500 }, { "epoch": 1.45, "learning_rate": 2.589329665068544e-05, "loss": 3.4335, "step": 143000 }, { "epoch": 1.45, "learning_rate": 2.580900747813539e-05, "loss": 3.4212, "step": 143500 }, { "epoch": 1.46, "learning_rate": 2.5724718305585337e-05, "loss": 3.4237, "step": 144000 }, { "epoch": 1.46, "learning_rate": 2.5640429133035288e-05, "loss": 3.4107, "step": 144500 }, { "epoch": 1.47, "learning_rate": 2.5556139960485236e-05, "loss": 3.4138, "step": 145000 }, { "epoch": 1.47, "learning_rate": 2.5471850787935187e-05, "loss": 3.4264, "step": 145500 }, { "epoch": 1.48, "learning_rate": 2.5387561615385137e-05, "loss": 3.4199, "step": 146000 }, { "epoch": 1.48, "learning_rate": 2.5303272442835085e-05, "loss": 3.4047, "step": 146500 }, { "epoch": 1.49, "learning_rate": 2.5218983270285036e-05, "loss": 3.4153, "step": 147000 }, { "epoch": 1.49, "learning_rate": 2.5134694097734983e-05, "loss": 3.4125, "step": 147500 }, { "epoch": 1.5, "learning_rate": 2.5050404925184934e-05, "loss": 3.4182, "step": 148000 }, { "epoch": 1.5, "learning_rate": 2.4966115752634882e-05, "loss": 3.4104, "step": 148500 }, { "epoch": 1.51, "learning_rate": 2.488182658008483e-05, "loss": 3.4071, "step": 149000 }, { "epoch": 1.51, "learning_rate": 2.479753740753478e-05, "loss": 3.4031, "step": 149500 }, { "epoch": 1.52, "learning_rate": 2.4713248234984728e-05, "loss": 3.4078, "step": 150000 }, { "epoch": 1.52, "learning_rate": 2.462895906243468e-05, "loss": 3.403, "step": 150500 }, { "epoch": 1.53, "learning_rate": 2.4544669889884626e-05, "loss": 3.4055, "step": 151000 }, { "epoch": 1.53, "learning_rate": 2.4460380717334574e-05, "loss": 3.399, "step": 151500 }, { "epoch": 1.54, "learning_rate": 2.4376091544784525e-05, "loss": 3.404, "step": 152000 }, { "epoch": 1.54, "learning_rate": 2.4291802372234472e-05, "loss": 3.391, "step": 152500 }, { "epoch": 1.55, "learning_rate": 2.4207513199684423e-05, "loss": 3.396, "step": 153000 }, { "epoch": 1.55, "learning_rate": 2.4123224027134374e-05, "loss": 3.3899, "step": 153500 }, { "epoch": 1.56, "learning_rate": 2.403893485458432e-05, "loss": 3.398, "step": 154000 }, { "epoch": 1.56, "learning_rate": 2.395464568203427e-05, "loss": 3.4011, "step": 154500 }, { "epoch": 1.57, "learning_rate": 2.3870356509484216e-05, "loss": 3.3847, "step": 155000 }, { "epoch": 1.57, "learning_rate": 2.3786067336934167e-05, "loss": 3.3835, "step": 155500 }, { "epoch": 1.58, "learning_rate": 2.3701778164384118e-05, "loss": 3.391, "step": 156000 }, { "epoch": 1.58, "learning_rate": 2.3617488991834066e-05, "loss": 3.3798, "step": 156500 }, { "epoch": 1.59, "learning_rate": 2.3533199819284017e-05, "loss": 3.3743, "step": 157000 }, { "epoch": 1.59, "learning_rate": 2.3448910646733964e-05, "loss": 3.3826, "step": 157500 }, { "epoch": 1.6, "learning_rate": 2.336462147418391e-05, "loss": 3.378, "step": 158000 }, { "epoch": 1.6, "learning_rate": 2.3280332301633863e-05, "loss": 3.3859, "step": 158500 }, { "epoch": 1.61, "learning_rate": 2.319604312908381e-05, "loss": 3.3902, "step": 159000 }, { "epoch": 1.61, "learning_rate": 2.311175395653376e-05, "loss": 3.3868, "step": 159500 }, { "epoch": 1.62, "learning_rate": 2.302746478398371e-05, "loss": 3.3997, "step": 160000 }, { "epoch": 1.62, "learning_rate": 2.294317561143366e-05, "loss": 3.3777, "step": 160500 }, { "epoch": 1.63, "learning_rate": 2.285888643888361e-05, "loss": 3.3911, "step": 161000 }, { "epoch": 1.63, "learning_rate": 2.2774597266333558e-05, "loss": 3.3776, "step": 161500 }, { "epoch": 1.64, "learning_rate": 2.2690308093783505e-05, "loss": 3.3643, "step": 162000 }, { "epoch": 1.64, "learning_rate": 2.2606018921233453e-05, "loss": 3.3676, "step": 162500 }, { "epoch": 1.65, "learning_rate": 2.2521729748683404e-05, "loss": 3.373, "step": 163000 }, { "epoch": 1.65, "learning_rate": 2.2437440576133355e-05, "loss": 3.377, "step": 163500 }, { "epoch": 1.66, "learning_rate": 2.2353151403583302e-05, "loss": 3.3603, "step": 164000 }, { "epoch": 1.66, "learning_rate": 2.2268862231033253e-05, "loss": 3.3777, "step": 164500 }, { "epoch": 1.67, "learning_rate": 2.21845730584832e-05, "loss": 3.3623, "step": 165000 }, { "epoch": 1.67, "learning_rate": 2.2100283885933148e-05, "loss": 3.3751, "step": 165500 }, { "epoch": 1.68, "learning_rate": 2.20159947133831e-05, "loss": 3.3624, "step": 166000 }, { "epoch": 1.68, "learning_rate": 2.1931705540833047e-05, "loss": 3.3607, "step": 166500 }, { "epoch": 1.69, "learning_rate": 2.1847416368282997e-05, "loss": 3.3626, "step": 167000 }, { "epoch": 1.69, "learning_rate": 2.1763127195732945e-05, "loss": 3.3732, "step": 167500 }, { "epoch": 1.7, "learning_rate": 2.1678838023182896e-05, "loss": 3.3584, "step": 168000 }, { "epoch": 1.7, "learning_rate": 2.1594548850632847e-05, "loss": 3.357, "step": 168500 }, { "epoch": 1.71, "learning_rate": 2.151025967808279e-05, "loss": 3.3567, "step": 169000 }, { "epoch": 1.71, "learning_rate": 2.1425970505532742e-05, "loss": 3.3653, "step": 169500 }, { "epoch": 1.72, "learning_rate": 2.134168133298269e-05, "loss": 3.3602, "step": 170000 }, { "epoch": 1.72, "learning_rate": 2.125739216043264e-05, "loss": 3.3561, "step": 170500 }, { "epoch": 1.73, "learning_rate": 2.117310298788259e-05, "loss": 3.3508, "step": 171000 }, { "epoch": 1.73, "learning_rate": 2.108881381533254e-05, "loss": 3.3565, "step": 171500 }, { "epoch": 1.74, "learning_rate": 2.100452464278249e-05, "loss": 3.3519, "step": 172000 }, { "epoch": 1.74, "learning_rate": 2.0920235470232437e-05, "loss": 3.3565, "step": 172500 }, { "epoch": 1.75, "learning_rate": 2.0835946297682385e-05, "loss": 3.3485, "step": 173000 }, { "epoch": 1.75, "learning_rate": 2.0751657125132335e-05, "loss": 3.3522, "step": 173500 }, { "epoch": 1.76, "learning_rate": 2.0667367952582283e-05, "loss": 3.3568, "step": 174000 }, { "epoch": 1.77, "learning_rate": 2.0583078780032234e-05, "loss": 3.356, "step": 174500 }, { "epoch": 1.77, "learning_rate": 2.049878960748218e-05, "loss": 3.3491, "step": 175000 }, { "epoch": 1.78, "learning_rate": 2.0414500434932132e-05, "loss": 3.353, "step": 175500 }, { "epoch": 1.78, "learning_rate": 2.0330211262382083e-05, "loss": 3.3415, "step": 176000 }, { "epoch": 1.79, "learning_rate": 2.0245922089832027e-05, "loss": 3.352, "step": 176500 }, { "epoch": 1.79, "learning_rate": 2.0161632917281978e-05, "loss": 3.3519, "step": 177000 }, { "epoch": 1.8, "learning_rate": 2.0077343744731926e-05, "loss": 3.3407, "step": 177500 }, { "epoch": 1.8, "learning_rate": 1.9993054572181877e-05, "loss": 3.3326, "step": 178000 }, { "epoch": 1.81, "learning_rate": 1.9908765399631828e-05, "loss": 3.3403, "step": 178500 }, { "epoch": 1.81, "learning_rate": 1.9824476227081775e-05, "loss": 3.3317, "step": 179000 }, { "epoch": 1.82, "learning_rate": 1.9740187054531726e-05, "loss": 3.3356, "step": 179500 }, { "epoch": 1.82, "learning_rate": 1.9655897881981673e-05, "loss": 3.3359, "step": 180000 }, { "epoch": 1.83, "learning_rate": 1.957160870943162e-05, "loss": 3.3418, "step": 180500 }, { "epoch": 1.83, "learning_rate": 1.9487319536881572e-05, "loss": 3.35, "step": 181000 }, { "epoch": 1.84, "learning_rate": 1.940303036433152e-05, "loss": 3.3278, "step": 181500 }, { "epoch": 1.84, "learning_rate": 1.931874119178147e-05, "loss": 3.3191, "step": 182000 }, { "epoch": 1.85, "learning_rate": 1.9234452019231418e-05, "loss": 3.336, "step": 182500 }, { "epoch": 1.85, "learning_rate": 1.915016284668137e-05, "loss": 3.329, "step": 183000 }, { "epoch": 1.86, "learning_rate": 1.9065873674131316e-05, "loss": 3.3344, "step": 183500 }, { "epoch": 1.86, "learning_rate": 1.8981584501581264e-05, "loss": 3.3263, "step": 184000 }, { "epoch": 1.87, "learning_rate": 1.8897295329031215e-05, "loss": 3.328, "step": 184500 }, { "epoch": 1.87, "learning_rate": 1.8813006156481162e-05, "loss": 3.3303, "step": 185000 }, { "epoch": 1.88, "learning_rate": 1.8728716983931113e-05, "loss": 3.3303, "step": 185500 }, { "epoch": 1.88, "learning_rate": 1.8644427811381064e-05, "loss": 3.3189, "step": 186000 }, { "epoch": 1.89, "learning_rate": 1.856013863883101e-05, "loss": 3.3236, "step": 186500 }, { "epoch": 1.89, "learning_rate": 1.847584946628096e-05, "loss": 3.3221, "step": 187000 }, { "epoch": 1.9, "learning_rate": 1.839156029373091e-05, "loss": 3.3199, "step": 187500 }, { "epoch": 1.9, "learning_rate": 1.8307271121180857e-05, "loss": 3.3126, "step": 188000 }, { "epoch": 1.91, "learning_rate": 1.822298194863081e-05, "loss": 3.3148, "step": 188500 }, { "epoch": 1.91, "learning_rate": 1.8138692776080756e-05, "loss": 3.3326, "step": 189000 }, { "epoch": 1.92, "learning_rate": 1.8054403603530707e-05, "loss": 3.3095, "step": 189500 }, { "epoch": 1.92, "learning_rate": 1.7970114430980654e-05, "loss": 3.3271, "step": 190000 }, { "epoch": 1.93, "learning_rate": 1.7885825258430605e-05, "loss": 3.321, "step": 190500 }, { "epoch": 1.93, "learning_rate": 1.7801536085880553e-05, "loss": 3.3205, "step": 191000 }, { "epoch": 1.94, "learning_rate": 1.77172469133305e-05, "loss": 3.3171, "step": 191500 }, { "epoch": 1.94, "learning_rate": 1.763295774078045e-05, "loss": 3.314, "step": 192000 }, { "epoch": 1.95, "learning_rate": 1.75486685682304e-05, "loss": 3.3134, "step": 192500 }, { "epoch": 1.95, "learning_rate": 1.746437939568035e-05, "loss": 3.307, "step": 193000 }, { "epoch": 1.96, "learning_rate": 1.73800902231303e-05, "loss": 3.3027, "step": 193500 }, { "epoch": 1.96, "learning_rate": 1.7295801050580248e-05, "loss": 3.313, "step": 194000 }, { "epoch": 1.97, "learning_rate": 1.7211511878030195e-05, "loss": 3.3052, "step": 194500 }, { "epoch": 1.97, "learning_rate": 1.7127222705480146e-05, "loss": 3.3026, "step": 195000 }, { "epoch": 1.98, "learning_rate": 1.7042933532930094e-05, "loss": 3.3115, "step": 195500 }, { "epoch": 1.98, "learning_rate": 1.6958644360380045e-05, "loss": 3.3035, "step": 196000 }, { "epoch": 1.99, "learning_rate": 1.6874355187829992e-05, "loss": 3.3073, "step": 196500 }, { "epoch": 1.99, "learning_rate": 1.6790066015279943e-05, "loss": 3.3058, "step": 197000 }, { "epoch": 2.0, "learning_rate": 1.670577684272989e-05, "loss": 3.2921, "step": 197500 }, { "epoch": 2.0, "learning_rate": 1.6621487670179838e-05, "loss": 3.2986, "step": 198000 }, { "epoch": 2.01, "learning_rate": 1.653719849762979e-05, "loss": 3.2941, "step": 198500 }, { "epoch": 2.01, "learning_rate": 1.6452909325079737e-05, "loss": 3.296, "step": 199000 }, { "epoch": 2.02, "learning_rate": 1.6368620152529688e-05, "loss": 3.3035, "step": 199500 }, { "epoch": 2.02, "learning_rate": 1.628433097997964e-05, "loss": 3.2866, "step": 200000 }, { "epoch": 2.03, "learning_rate": 1.6200041807429586e-05, "loss": 3.2806, "step": 200500 }, { "epoch": 2.03, "learning_rate": 1.6115752634879537e-05, "loss": 3.2788, "step": 201000 }, { "epoch": 2.04, "learning_rate": 1.6031463462329484e-05, "loss": 3.2898, "step": 201500 }, { "epoch": 2.04, "learning_rate": 1.5947174289779432e-05, "loss": 3.29, "step": 202000 }, { "epoch": 2.05, "learning_rate": 1.5862885117229383e-05, "loss": 3.2787, "step": 202500 }, { "epoch": 2.05, "learning_rate": 1.577859594467933e-05, "loss": 3.2854, "step": 203000 }, { "epoch": 2.06, "learning_rate": 1.569430677212928e-05, "loss": 3.2938, "step": 203500 }, { "epoch": 2.06, "learning_rate": 1.561001759957923e-05, "loss": 3.2756, "step": 204000 }, { "epoch": 2.07, "learning_rate": 1.552572842702918e-05, "loss": 3.276, "step": 204500 }, { "epoch": 2.07, "learning_rate": 1.5441439254479127e-05, "loss": 3.2743, "step": 205000 }, { "epoch": 2.08, "learning_rate": 1.5357150081929075e-05, "loss": 3.2817, "step": 205500 }, { "epoch": 2.08, "learning_rate": 1.5272860909379026e-05, "loss": 3.2703, "step": 206000 }, { "epoch": 2.09, "learning_rate": 1.5188571736828975e-05, "loss": 3.2833, "step": 206500 }, { "epoch": 2.09, "learning_rate": 1.5104282564278924e-05, "loss": 3.2815, "step": 207000 }, { "epoch": 2.1, "learning_rate": 1.5019993391728873e-05, "loss": 3.2765, "step": 207500 }, { "epoch": 2.1, "learning_rate": 1.4935704219178822e-05, "loss": 3.2763, "step": 208000 }, { "epoch": 2.11, "learning_rate": 1.4851415046628772e-05, "loss": 3.2712, "step": 208500 }, { "epoch": 2.11, "learning_rate": 1.4767125874078719e-05, "loss": 3.2684, "step": 209000 }, { "epoch": 2.12, "learning_rate": 1.4682836701528668e-05, "loss": 3.2727, "step": 209500 }, { "epoch": 2.12, "learning_rate": 1.4598547528978618e-05, "loss": 3.2753, "step": 210000 }, { "epoch": 2.13, "learning_rate": 1.4514258356428567e-05, "loss": 3.2593, "step": 210500 }, { "epoch": 2.13, "learning_rate": 1.4429969183878516e-05, "loss": 3.2815, "step": 211000 }, { "epoch": 2.14, "learning_rate": 1.4345680011328467e-05, "loss": 3.2616, "step": 211500 }, { "epoch": 2.14, "learning_rate": 1.4261390838778416e-05, "loss": 3.27, "step": 212000 }, { "epoch": 2.15, "learning_rate": 1.4177101666228362e-05, "loss": 3.2774, "step": 212500 }, { "epoch": 2.15, "learning_rate": 1.4092812493678311e-05, "loss": 3.2674, "step": 213000 }, { "epoch": 2.16, "learning_rate": 1.4008523321128262e-05, "loss": 3.2621, "step": 213500 }, { "epoch": 2.16, "learning_rate": 1.3924234148578211e-05, "loss": 3.2738, "step": 214000 }, { "epoch": 2.17, "learning_rate": 1.383994497602816e-05, "loss": 3.2665, "step": 214500 }, { "epoch": 2.17, "learning_rate": 1.375565580347811e-05, "loss": 3.2652, "step": 215000 }, { "epoch": 2.18, "learning_rate": 1.3671366630928059e-05, "loss": 3.2711, "step": 215500 }, { "epoch": 2.18, "learning_rate": 1.3587077458378008e-05, "loss": 3.2527, "step": 216000 }, { "epoch": 2.19, "learning_rate": 1.3502788285827956e-05, "loss": 3.2695, "step": 216500 }, { "epoch": 2.19, "learning_rate": 1.3418499113277905e-05, "loss": 3.2742, "step": 217000 }, { "epoch": 2.2, "learning_rate": 1.3334209940727854e-05, "loss": 3.2626, "step": 217500 }, { "epoch": 2.21, "learning_rate": 1.3249920768177803e-05, "loss": 3.2599, "step": 218000 }, { "epoch": 2.21, "learning_rate": 1.3165631595627752e-05, "loss": 3.2579, "step": 218500 }, { "epoch": 2.22, "learning_rate": 1.3081342423077703e-05, "loss": 3.2612, "step": 219000 }, { "epoch": 2.22, "learning_rate": 1.2997053250527652e-05, "loss": 3.2523, "step": 219500 }, { "epoch": 2.23, "learning_rate": 1.2912764077977598e-05, "loss": 3.2667, "step": 220000 }, { "epoch": 2.23, "learning_rate": 1.2828474905427548e-05, "loss": 3.2686, "step": 220500 }, { "epoch": 2.24, "learning_rate": 1.2744185732877498e-05, "loss": 3.2522, "step": 221000 }, { "epoch": 2.24, "learning_rate": 1.2659896560327448e-05, "loss": 3.2708, "step": 221500 }, { "epoch": 2.25, "learning_rate": 1.2575607387777397e-05, "loss": 3.2541, "step": 222000 }, { "epoch": 2.25, "learning_rate": 1.2491318215227344e-05, "loss": 3.2485, "step": 222500 }, { "epoch": 2.26, "learning_rate": 1.2407029042677294e-05, "loss": 3.2565, "step": 223000 }, { "epoch": 2.26, "learning_rate": 1.2322739870127244e-05, "loss": 3.246, "step": 223500 }, { "epoch": 2.27, "learning_rate": 1.2238450697577194e-05, "loss": 3.2602, "step": 224000 }, { "epoch": 2.27, "learning_rate": 1.2154161525027141e-05, "loss": 3.2527, "step": 224500 }, { "epoch": 2.28, "learning_rate": 1.206987235247709e-05, "loss": 3.2549, "step": 225000 }, { "epoch": 2.28, "learning_rate": 1.198558317992704e-05, "loss": 3.2394, "step": 225500 }, { "epoch": 2.29, "learning_rate": 1.1901294007376989e-05, "loss": 3.2547, "step": 226000 }, { "epoch": 2.29, "learning_rate": 1.1817004834826938e-05, "loss": 3.2565, "step": 226500 }, { "epoch": 2.3, "learning_rate": 1.1732715662276887e-05, "loss": 3.2601, "step": 227000 }, { "epoch": 2.3, "learning_rate": 1.1648426489726836e-05, "loss": 3.2535, "step": 227500 }, { "epoch": 2.31, "learning_rate": 1.1564137317176784e-05, "loss": 3.2529, "step": 228000 }, { "epoch": 2.31, "learning_rate": 1.1479848144626735e-05, "loss": 3.2463, "step": 228500 }, { "epoch": 2.32, "learning_rate": 1.1395558972076684e-05, "loss": 3.2493, "step": 229000 }, { "epoch": 2.32, "learning_rate": 1.1311269799526633e-05, "loss": 3.2414, "step": 229500 }, { "epoch": 2.33, "learning_rate": 1.122698062697658e-05, "loss": 3.259, "step": 230000 }, { "epoch": 2.33, "learning_rate": 1.114269145442653e-05, "loss": 3.2394, "step": 230500 }, { "epoch": 2.34, "learning_rate": 1.1058402281876481e-05, "loss": 3.2401, "step": 231000 }, { "epoch": 2.34, "learning_rate": 1.0974113109326428e-05, "loss": 3.2528, "step": 231500 }, { "epoch": 2.35, "learning_rate": 1.0889823936776378e-05, "loss": 3.249, "step": 232000 }, { "epoch": 2.35, "learning_rate": 1.0805534764226327e-05, "loss": 3.256, "step": 232500 }, { "epoch": 2.36, "learning_rate": 1.0721245591676276e-05, "loss": 3.2299, "step": 233000 }, { "epoch": 2.36, "learning_rate": 1.0636956419126225e-05, "loss": 3.2402, "step": 233500 }, { "epoch": 2.37, "learning_rate": 1.0552667246576174e-05, "loss": 3.2514, "step": 234000 }, { "epoch": 2.37, "learning_rate": 1.0468378074026124e-05, "loss": 3.2347, "step": 234500 }, { "epoch": 2.38, "learning_rate": 1.0384088901476073e-05, "loss": 3.243, "step": 235000 }, { "epoch": 2.38, "learning_rate": 1.029979972892602e-05, "loss": 3.2348, "step": 235500 }, { "epoch": 2.39, "learning_rate": 1.0215510556375971e-05, "loss": 3.2387, "step": 236000 }, { "epoch": 2.39, "learning_rate": 1.013122138382592e-05, "loss": 3.2401, "step": 236500 }, { "epoch": 2.4, "learning_rate": 1.0046932211275868e-05, "loss": 3.2334, "step": 237000 }, { "epoch": 2.4, "learning_rate": 9.962643038725817e-06, "loss": 3.2494, "step": 237500 }, { "epoch": 2.41, "learning_rate": 9.878353866175766e-06, "loss": 3.2376, "step": 238000 }, { "epoch": 2.41, "learning_rate": 9.794064693625717e-06, "loss": 3.2244, "step": 238500 }, { "epoch": 2.42, "learning_rate": 9.709775521075665e-06, "loss": 3.2591, "step": 239000 }, { "epoch": 2.42, "learning_rate": 9.625486348525614e-06, "loss": 3.2344, "step": 239500 }, { "epoch": 2.43, "learning_rate": 9.541197175975563e-06, "loss": 3.2332, "step": 240000 }, { "epoch": 2.43, "learning_rate": 9.456908003425512e-06, "loss": 3.2327, "step": 240500 }, { "epoch": 2.44, "learning_rate": 9.372618830875462e-06, "loss": 3.2389, "step": 241000 }, { "epoch": 2.44, "learning_rate": 9.288329658325411e-06, "loss": 3.2296, "step": 241500 }, { "epoch": 2.45, "learning_rate": 9.20404048577536e-06, "loss": 3.2311, "step": 242000 }, { "epoch": 2.45, "learning_rate": 9.119751313225308e-06, "loss": 3.2278, "step": 242500 }, { "epoch": 2.46, "learning_rate": 9.035462140675257e-06, "loss": 3.2366, "step": 243000 }, { "epoch": 2.46, "learning_rate": 8.951172968125208e-06, "loss": 3.2244, "step": 243500 }, { "epoch": 2.47, "learning_rate": 8.866883795575157e-06, "loss": 3.2276, "step": 244000 }, { "epoch": 2.47, "learning_rate": 8.782594623025104e-06, "loss": 3.2363, "step": 244500 }, { "epoch": 2.48, "learning_rate": 8.698305450475054e-06, "loss": 3.2348, "step": 245000 }, { "epoch": 2.48, "learning_rate": 8.614016277925003e-06, "loss": 3.2288, "step": 245500 }, { "epoch": 2.49, "learning_rate": 8.529727105374952e-06, "loss": 3.2224, "step": 246000 }, { "epoch": 2.49, "learning_rate": 8.445437932824901e-06, "loss": 3.2237, "step": 246500 }, { "epoch": 2.5, "learning_rate": 8.36114876027485e-06, "loss": 3.2272, "step": 247000 }, { "epoch": 2.5, "learning_rate": 8.2768595877248e-06, "loss": 3.2271, "step": 247500 }, { "epoch": 2.51, "learning_rate": 8.192570415174749e-06, "loss": 3.2187, "step": 248000 }, { "epoch": 2.51, "learning_rate": 8.108281242624698e-06, "loss": 3.2145, "step": 248500 }, { "epoch": 2.52, "learning_rate": 8.023992070074647e-06, "loss": 3.222, "step": 249000 }, { "epoch": 2.52, "learning_rate": 7.939702897524597e-06, "loss": 3.2217, "step": 249500 }, { "epoch": 2.53, "learning_rate": 7.855413724974544e-06, "loss": 3.2261, "step": 250000 }, { "epoch": 2.53, "learning_rate": 7.771124552424495e-06, "loss": 3.2171, "step": 250500 }, { "epoch": 2.54, "learning_rate": 7.686835379874444e-06, "loss": 3.2241, "step": 251000 }, { "epoch": 2.54, "learning_rate": 7.602546207324392e-06, "loss": 3.2165, "step": 251500 }, { "epoch": 2.55, "learning_rate": 7.518257034774341e-06, "loss": 3.2177, "step": 252000 }, { "epoch": 2.55, "learning_rate": 7.433967862224291e-06, "loss": 3.2338, "step": 252500 }, { "epoch": 2.56, "learning_rate": 7.34967868967424e-06, "loss": 3.2106, "step": 253000 }, { "epoch": 2.56, "learning_rate": 7.2653895171241885e-06, "loss": 3.2205, "step": 253500 }, { "epoch": 2.57, "learning_rate": 7.181100344574138e-06, "loss": 3.2173, "step": 254000 }, { "epoch": 2.57, "learning_rate": 7.096811172024087e-06, "loss": 3.2152, "step": 254500 }, { "epoch": 2.58, "learning_rate": 7.012521999474036e-06, "loss": 3.2214, "step": 255000 }, { "epoch": 2.58, "learning_rate": 6.9282328269239845e-06, "loss": 3.2276, "step": 255500 }, { "epoch": 2.59, "learning_rate": 6.843943654373934e-06, "loss": 3.2153, "step": 256000 }, { "epoch": 2.59, "learning_rate": 6.759654481823884e-06, "loss": 3.2151, "step": 256500 }, { "epoch": 2.6, "learning_rate": 6.675365309273831e-06, "loss": 3.212, "step": 257000 }, { "epoch": 2.6, "learning_rate": 6.591076136723781e-06, "loss": 3.2194, "step": 257500 }, { "epoch": 2.61, "learning_rate": 6.5067869641737305e-06, "loss": 3.2182, "step": 258000 }, { "epoch": 2.61, "learning_rate": 6.42249779162368e-06, "loss": 3.2116, "step": 258500 }, { "epoch": 2.62, "learning_rate": 6.338208619073628e-06, "loss": 3.2236, "step": 259000 }, { "epoch": 2.62, "learning_rate": 6.253919446523577e-06, "loss": 3.2076, "step": 259500 }, { "epoch": 2.63, "learning_rate": 6.169630273973527e-06, "loss": 3.1989, "step": 260000 }, { "epoch": 2.63, "learning_rate": 6.085341101423476e-06, "loss": 3.2188, "step": 260500 }, { "epoch": 2.64, "learning_rate": 6.001051928873425e-06, "loss": 3.2172, "step": 261000 }, { "epoch": 2.64, "learning_rate": 5.916762756323374e-06, "loss": 3.2088, "step": 261500 }, { "epoch": 2.65, "learning_rate": 5.8324735837733225e-06, "loss": 3.209, "step": 262000 }, { "epoch": 2.66, "learning_rate": 5.7481844112232726e-06, "loss": 3.2116, "step": 262500 }, { "epoch": 2.66, "learning_rate": 5.663895238673221e-06, "loss": 3.2153, "step": 263000 }, { "epoch": 2.67, "learning_rate": 5.57960606612317e-06, "loss": 3.2152, "step": 263500 }, { "epoch": 2.67, "learning_rate": 5.495316893573119e-06, "loss": 3.2063, "step": 264000 }, { "epoch": 2.68, "learning_rate": 5.4110277210230685e-06, "loss": 3.2073, "step": 264500 }, { "epoch": 2.68, "learning_rate": 5.326738548473018e-06, "loss": 3.2123, "step": 265000 }, { "epoch": 2.69, "learning_rate": 5.242449375922967e-06, "loss": 3.2031, "step": 265500 }, { "epoch": 2.69, "learning_rate": 5.158160203372916e-06, "loss": 3.2115, "step": 266000 }, { "epoch": 2.7, "learning_rate": 5.0738710308228645e-06, "loss": 3.2075, "step": 266500 }, { "epoch": 2.7, "learning_rate": 4.989581858272814e-06, "loss": 3.2074, "step": 267000 }, { "epoch": 2.71, "learning_rate": 4.905292685722763e-06, "loss": 3.1989, "step": 267500 }, { "epoch": 2.71, "learning_rate": 4.821003513172712e-06, "loss": 3.1995, "step": 268000 }, { "epoch": 2.72, "learning_rate": 4.736714340622661e-06, "loss": 3.2031, "step": 268500 }, { "epoch": 2.72, "learning_rate": 4.6524251680726106e-06, "loss": 3.2088, "step": 269000 }, { "epoch": 2.73, "learning_rate": 4.568135995522559e-06, "loss": 3.1957, "step": 269500 }, { "epoch": 2.73, "learning_rate": 4.483846822972509e-06, "loss": 3.2017, "step": 270000 }, { "epoch": 2.74, "learning_rate": 4.399557650422457e-06, "loss": 3.2033, "step": 270500 }, { "epoch": 2.74, "learning_rate": 4.3152684778724066e-06, "loss": 3.2041, "step": 271000 }, { "epoch": 2.75, "learning_rate": 4.230979305322356e-06, "loss": 3.1984, "step": 271500 }, { "epoch": 2.75, "learning_rate": 4.146690132772305e-06, "loss": 3.1903, "step": 272000 }, { "epoch": 2.76, "learning_rate": 4.062400960222254e-06, "loss": 3.2089, "step": 272500 }, { "epoch": 2.76, "learning_rate": 3.9781117876722025e-06, "loss": 3.1958, "step": 273000 }, { "epoch": 2.77, "learning_rate": 3.893822615122153e-06, "loss": 3.1924, "step": 273500 }, { "epoch": 2.77, "learning_rate": 3.809533442572101e-06, "loss": 3.2067, "step": 274000 }, { "epoch": 2.78, "learning_rate": 3.7252442700220506e-06, "loss": 3.2007, "step": 274500 }, { "epoch": 2.78, "learning_rate": 3.6409550974719994e-06, "loss": 3.2017, "step": 275000 }, { "epoch": 2.79, "learning_rate": 3.556665924921948e-06, "loss": 3.1978, "step": 275500 }, { "epoch": 2.79, "learning_rate": 3.4723767523718974e-06, "loss": 3.1916, "step": 276000 }, { "epoch": 2.8, "learning_rate": 3.388087579821846e-06, "loss": 3.1939, "step": 276500 }, { "epoch": 2.8, "learning_rate": 3.303798407271796e-06, "loss": 3.1959, "step": 277000 }, { "epoch": 2.81, "learning_rate": 3.2195092347217446e-06, "loss": 3.1918, "step": 277500 }, { "epoch": 2.81, "learning_rate": 3.1352200621716942e-06, "loss": 3.1964, "step": 278000 }, { "epoch": 2.82, "learning_rate": 3.0509308896216426e-06, "loss": 3.1972, "step": 278500 }, { "epoch": 2.82, "learning_rate": 2.9666417170715918e-06, "loss": 3.1946, "step": 279000 }, { "epoch": 2.83, "learning_rate": 2.882352544521541e-06, "loss": 3.1985, "step": 279500 }, { "epoch": 2.83, "learning_rate": 2.79806337197149e-06, "loss": 3.2023, "step": 280000 }, { "epoch": 2.84, "learning_rate": 2.7137741994214394e-06, "loss": 3.1974, "step": 280500 }, { "epoch": 2.84, "learning_rate": 2.629485026871388e-06, "loss": 3.2045, "step": 281000 }, { "epoch": 2.85, "learning_rate": 2.5451958543213374e-06, "loss": 3.1955, "step": 281500 }, { "epoch": 2.85, "learning_rate": 2.4609066817712866e-06, "loss": 3.1986, "step": 282000 }, { "epoch": 2.86, "learning_rate": 2.376617509221236e-06, "loss": 3.1882, "step": 282500 }, { "epoch": 2.86, "learning_rate": 2.2923283366711846e-06, "loss": 3.2025, "step": 283000 }, { "epoch": 2.87, "learning_rate": 2.208039164121134e-06, "loss": 3.1917, "step": 283500 }, { "epoch": 2.87, "learning_rate": 2.1237499915710826e-06, "loss": 3.1918, "step": 284000 }, { "epoch": 2.88, "learning_rate": 2.039460819021032e-06, "loss": 3.1926, "step": 284500 }, { "epoch": 2.88, "learning_rate": 1.955171646470981e-06, "loss": 3.2043, "step": 285000 }, { "epoch": 2.89, "learning_rate": 1.8708824739209302e-06, "loss": 3.1967, "step": 285500 }, { "epoch": 2.89, "learning_rate": 1.7865933013708792e-06, "loss": 3.186, "step": 286000 }, { "epoch": 2.9, "learning_rate": 1.7023041288208284e-06, "loss": 3.1924, "step": 286500 }, { "epoch": 2.9, "learning_rate": 1.6180149562707774e-06, "loss": 3.2045, "step": 287000 }, { "epoch": 2.91, "learning_rate": 1.5337257837207264e-06, "loss": 3.1928, "step": 287500 }, { "epoch": 2.91, "learning_rate": 1.4494366111706756e-06, "loss": 3.186, "step": 288000 }, { "epoch": 2.92, "learning_rate": 1.3651474386206246e-06, "loss": 3.1957, "step": 288500 }, { "epoch": 2.92, "learning_rate": 1.2808582660705736e-06, "loss": 3.1995, "step": 289000 }, { "epoch": 2.93, "learning_rate": 1.1965690935205228e-06, "loss": 3.1894, "step": 289500 }, { "epoch": 2.93, "learning_rate": 1.1122799209704718e-06, "loss": 3.1982, "step": 290000 }, { "epoch": 2.94, "learning_rate": 1.027990748420421e-06, "loss": 3.1937, "step": 290500 }, { "epoch": 2.94, "learning_rate": 9.437015758703701e-07, "loss": 3.1946, "step": 291000 }, { "epoch": 2.95, "learning_rate": 8.59412403320319e-07, "loss": 3.179, "step": 291500 }, { "epoch": 2.95, "learning_rate": 7.751232307702682e-07, "loss": 3.2011, "step": 292000 }, { "epoch": 2.96, "learning_rate": 6.908340582202172e-07, "loss": 3.1906, "step": 292500 }, { "epoch": 2.96, "learning_rate": 6.065448856701664e-07, "loss": 3.1801, "step": 293000 }, { "epoch": 2.97, "learning_rate": 5.222557131201154e-07, "loss": 3.1943, "step": 293500 }, { "epoch": 2.97, "learning_rate": 4.3796654057006455e-07, "loss": 3.1945, "step": 294000 }, { "epoch": 2.98, "learning_rate": 3.5367736802001365e-07, "loss": 3.192, "step": 294500 }, { "epoch": 2.98, "learning_rate": 2.693881954699627e-07, "loss": 3.1862, "step": 295000 }, { "epoch": 2.99, "learning_rate": 1.850990229199118e-07, "loss": 3.1977, "step": 295500 }, { "epoch": 2.99, "learning_rate": 1.0080985036986089e-07, "loss": 3.195, "step": 296000 }, { "epoch": 3.0, "learning_rate": 1.652067781980998e-08, "loss": 3.1874, "step": 296500 }, { "epoch": 3.0, "step": 296598, "total_flos": 3.482044692514826e+18, "train_loss": 3.5860012905026264, "train_runtime": 1342569.7438, "train_samples_per_second": 56.555, "train_steps_per_second": 0.221 } ], "max_steps": 296598, "num_train_epochs": 3, "total_flos": 3.482044692514826e+18, "trial_name": null, "trial_params": null }