{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 185860, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 4.986549015387927e-05, "loss": 6.3015, "step": 500 }, { "epoch": 0.05, "learning_rate": 4.9730980307758526e-05, "loss": 3.3139, "step": 1000 }, { "epoch": 0.08, "learning_rate": 4.95964704616378e-05, "loss": 2.4311, "step": 1500 }, { "epoch": 0.11, "learning_rate": 4.9461960615517056e-05, "loss": 1.9735, "step": 2000 }, { "epoch": 0.13, "learning_rate": 4.932745076939632e-05, "loss": 1.7423, "step": 2500 }, { "epoch": 0.16, "learning_rate": 4.9192940923275586e-05, "loss": 1.5339, "step": 3000 }, { "epoch": 0.19, "learning_rate": 4.905843107715485e-05, "loss": 1.3933, "step": 3500 }, { "epoch": 0.22, "learning_rate": 4.8923921231034117e-05, "loss": 1.3207, "step": 4000 }, { "epoch": 0.24, "learning_rate": 4.878941138491338e-05, "loss": 1.2438, "step": 4500 }, { "epoch": 0.27, "learning_rate": 4.865490153879264e-05, "loss": 1.1593, "step": 5000 }, { "epoch": 0.3, "learning_rate": 4.8520391692671905e-05, "loss": 1.1032, "step": 5500 }, { "epoch": 0.32, "learning_rate": 4.838588184655117e-05, "loss": 1.0557, "step": 6000 }, { "epoch": 0.35, "learning_rate": 4.8251372000430435e-05, "loss": 1.0058, "step": 6500 }, { "epoch": 0.38, "learning_rate": 4.81168621543097e-05, "loss": 0.9792, "step": 7000 }, { "epoch": 0.4, "learning_rate": 4.798235230818896e-05, "loss": 0.9469, "step": 7500 }, { "epoch": 0.43, "learning_rate": 4.7847842462068224e-05, "loss": 0.9362, "step": 8000 }, { "epoch": 0.46, "learning_rate": 4.771333261594749e-05, "loss": 0.8966, "step": 8500 }, { "epoch": 0.48, "learning_rate": 4.7578822769826754e-05, "loss": 0.8722, "step": 9000 }, { "epoch": 0.51, "learning_rate": 4.744431292370602e-05, "loss": 0.8568, "step": 9500 }, { "epoch": 0.54, "learning_rate": 4.730980307758528e-05, "loss": 0.8443, "step": 10000 }, { "epoch": 0.56, "learning_rate": 4.717529323146454e-05, "loss": 0.8178, "step": 10500 }, { "epoch": 0.59, "learning_rate": 4.7040783385343815e-05, "loss": 0.7986, "step": 11000 }, { "epoch": 0.62, "learning_rate": 4.690627353922307e-05, "loss": 0.7715, "step": 11500 }, { "epoch": 0.65, "learning_rate": 4.677176369310234e-05, "loss": 0.7645, "step": 12000 }, { "epoch": 0.67, "learning_rate": 4.6637253846981596e-05, "loss": 0.7501, "step": 12500 }, { "epoch": 0.7, "learning_rate": 4.650274400086087e-05, "loss": 0.7503, "step": 13000 }, { "epoch": 0.73, "learning_rate": 4.636823415474013e-05, "loss": 0.7413, "step": 13500 }, { "epoch": 0.75, "learning_rate": 4.623372430861939e-05, "loss": 0.723, "step": 14000 }, { "epoch": 0.78, "learning_rate": 4.609921446249866e-05, "loss": 0.7066, "step": 14500 }, { "epoch": 0.81, "learning_rate": 4.596470461637792e-05, "loss": 0.7066, "step": 15000 }, { "epoch": 0.83, "learning_rate": 4.583019477025719e-05, "loss": 0.7155, "step": 15500 }, { "epoch": 0.86, "learning_rate": 4.569568492413645e-05, "loss": 0.6763, "step": 16000 }, { "epoch": 0.89, "learning_rate": 4.556117507801571e-05, "loss": 0.6761, "step": 16500 }, { "epoch": 0.91, "learning_rate": 4.5426665231894976e-05, "loss": 0.6547, "step": 17000 }, { "epoch": 0.94, "learning_rate": 4.529215538577424e-05, "loss": 0.6674, "step": 17500 }, { "epoch": 0.97, "learning_rate": 4.5157645539653506e-05, "loss": 0.6558, "step": 18000 }, { "epoch": 1.0, "learning_rate": 4.502313569353277e-05, "loss": 0.6354, "step": 18500 }, { "epoch": 1.02, "learning_rate": 4.488862584741203e-05, "loss": 0.633, "step": 19000 }, { "epoch": 1.05, "learning_rate": 4.4754116001291294e-05, "loss": 0.629, "step": 19500 }, { "epoch": 1.08, "learning_rate": 4.461960615517056e-05, "loss": 0.6256, "step": 20000 }, { "epoch": 1.1, "learning_rate": 4.4485096309049825e-05, "loss": 0.6177, "step": 20500 }, { "epoch": 1.13, "learning_rate": 4.435058646292909e-05, "loss": 0.6183, "step": 21000 }, { "epoch": 1.16, "learning_rate": 4.4216076616808355e-05, "loss": 0.6162, "step": 21500 }, { "epoch": 1.18, "learning_rate": 4.408156677068761e-05, "loss": 0.61, "step": 22000 }, { "epoch": 1.21, "learning_rate": 4.3947056924566885e-05, "loss": 0.5876, "step": 22500 }, { "epoch": 1.24, "learning_rate": 4.381254707844614e-05, "loss": 0.5995, "step": 23000 }, { "epoch": 1.26, "learning_rate": 4.367803723232541e-05, "loss": 0.5866, "step": 23500 }, { "epoch": 1.29, "learning_rate": 4.3543527386204674e-05, "loss": 0.5742, "step": 24000 }, { "epoch": 1.32, "learning_rate": 4.340901754008393e-05, "loss": 0.5759, "step": 24500 }, { "epoch": 1.35, "learning_rate": 4.3274507693963204e-05, "loss": 0.571, "step": 25000 }, { "epoch": 1.37, "learning_rate": 4.313999784784246e-05, "loss": 0.5663, "step": 25500 }, { "epoch": 1.4, "learning_rate": 4.300548800172173e-05, "loss": 0.5594, "step": 26000 }, { "epoch": 1.43, "learning_rate": 4.287097815560099e-05, "loss": 0.5666, "step": 26500 }, { "epoch": 1.45, "learning_rate": 4.273646830948026e-05, "loss": 0.5546, "step": 27000 }, { "epoch": 1.48, "learning_rate": 4.260195846335952e-05, "loss": 0.55, "step": 27500 }, { "epoch": 1.51, "learning_rate": 4.246744861723879e-05, "loss": 0.553, "step": 28000 }, { "epoch": 1.53, "learning_rate": 4.2332938771118046e-05, "loss": 0.5587, "step": 28500 }, { "epoch": 1.56, "learning_rate": 4.219842892499731e-05, "loss": 0.5462, "step": 29000 }, { "epoch": 1.59, "learning_rate": 4.2063919078876576e-05, "loss": 0.5418, "step": 29500 }, { "epoch": 1.61, "learning_rate": 4.192940923275584e-05, "loss": 0.5441, "step": 30000 }, { "epoch": 1.64, "learning_rate": 4.1794899386635107e-05, "loss": 0.5348, "step": 30500 }, { "epoch": 1.67, "learning_rate": 4.1660389540514365e-05, "loss": 0.5353, "step": 31000 }, { "epoch": 1.69, "learning_rate": 4.152587969439363e-05, "loss": 0.5332, "step": 31500 }, { "epoch": 1.72, "learning_rate": 4.1391369848272895e-05, "loss": 0.5157, "step": 32000 }, { "epoch": 1.75, "learning_rate": 4.125686000215216e-05, "loss": 0.5117, "step": 32500 }, { "epoch": 1.78, "learning_rate": 4.1122350156031425e-05, "loss": 0.5202, "step": 33000 }, { "epoch": 1.8, "learning_rate": 4.0987840309910684e-05, "loss": 0.516, "step": 33500 }, { "epoch": 1.83, "learning_rate": 4.085333046378995e-05, "loss": 0.5115, "step": 34000 }, { "epoch": 1.86, "learning_rate": 4.071882061766922e-05, "loss": 0.5165, "step": 34500 }, { "epoch": 1.88, "learning_rate": 4.058431077154848e-05, "loss": 0.5145, "step": 35000 }, { "epoch": 1.91, "learning_rate": 4.0449800925427744e-05, "loss": 0.5012, "step": 35500 }, { "epoch": 1.94, "learning_rate": 4.0315291079307e-05, "loss": 0.5035, "step": 36000 }, { "epoch": 1.96, "learning_rate": 4.0180781233186274e-05, "loss": 0.5037, "step": 36500 }, { "epoch": 1.99, "learning_rate": 4.004627138706554e-05, "loss": 0.5043, "step": 37000 }, { "epoch": 2.02, "learning_rate": 3.99117615409448e-05, "loss": 0.4954, "step": 37500 }, { "epoch": 2.04, "learning_rate": 3.977725169482406e-05, "loss": 0.4935, "step": 38000 }, { "epoch": 2.07, "learning_rate": 3.964274184870333e-05, "loss": 0.4809, "step": 38500 }, { "epoch": 2.1, "learning_rate": 3.950823200258259e-05, "loss": 0.4818, "step": 39000 }, { "epoch": 2.13, "learning_rate": 3.937372215646186e-05, "loss": 0.4809, "step": 39500 }, { "epoch": 2.15, "learning_rate": 3.9239212310341117e-05, "loss": 0.4835, "step": 40000 }, { "epoch": 2.18, "learning_rate": 3.910470246422038e-05, "loss": 0.4804, "step": 40500 }, { "epoch": 2.21, "learning_rate": 3.897019261809965e-05, "loss": 0.4769, "step": 41000 }, { "epoch": 2.23, "learning_rate": 3.883568277197891e-05, "loss": 0.4774, "step": 41500 }, { "epoch": 2.26, "learning_rate": 3.870117292585818e-05, "loss": 0.4805, "step": 42000 }, { "epoch": 2.29, "learning_rate": 3.8566663079737435e-05, "loss": 0.4782, "step": 42500 }, { "epoch": 2.31, "learning_rate": 3.84321532336167e-05, "loss": 0.4736, "step": 43000 }, { "epoch": 2.34, "learning_rate": 3.8297643387495966e-05, "loss": 0.4786, "step": 43500 }, { "epoch": 2.37, "learning_rate": 3.816313354137523e-05, "loss": 0.4637, "step": 44000 }, { "epoch": 2.39, "learning_rate": 3.8028623695254496e-05, "loss": 0.4715, "step": 44500 }, { "epoch": 2.42, "learning_rate": 3.789411384913376e-05, "loss": 0.459, "step": 45000 }, { "epoch": 2.45, "learning_rate": 3.775960400301302e-05, "loss": 0.4609, "step": 45500 }, { "epoch": 2.47, "learning_rate": 3.7625094156892284e-05, "loss": 0.4603, "step": 46000 }, { "epoch": 2.5, "learning_rate": 3.749058431077155e-05, "loss": 0.465, "step": 46500 }, { "epoch": 2.53, "learning_rate": 3.7356074464650815e-05, "loss": 0.45, "step": 47000 }, { "epoch": 2.56, "learning_rate": 3.722156461853008e-05, "loss": 0.4584, "step": 47500 }, { "epoch": 2.58, "learning_rate": 3.708705477240934e-05, "loss": 0.4539, "step": 48000 }, { "epoch": 2.61, "learning_rate": 3.695254492628861e-05, "loss": 0.4534, "step": 48500 }, { "epoch": 2.64, "learning_rate": 3.681803508016787e-05, "loss": 0.4605, "step": 49000 }, { "epoch": 2.66, "learning_rate": 3.668352523404713e-05, "loss": 0.46, "step": 49500 }, { "epoch": 2.69, "learning_rate": 3.65490153879264e-05, "loss": 0.4568, "step": 50000 }, { "epoch": 2.72, "learning_rate": 3.641450554180566e-05, "loss": 0.443, "step": 50500 }, { "epoch": 2.74, "learning_rate": 3.627999569568493e-05, "loss": 0.4369, "step": 51000 }, { "epoch": 2.77, "learning_rate": 3.6145485849564194e-05, "loss": 0.4521, "step": 51500 }, { "epoch": 2.8, "learning_rate": 3.601097600344345e-05, "loss": 0.4278, "step": 52000 }, { "epoch": 2.82, "learning_rate": 3.587646615732272e-05, "loss": 0.4282, "step": 52500 }, { "epoch": 2.85, "learning_rate": 3.574195631120198e-05, "loss": 0.4342, "step": 53000 }, { "epoch": 2.88, "learning_rate": 3.560744646508125e-05, "loss": 0.4305, "step": 53500 }, { "epoch": 2.91, "learning_rate": 3.547293661896051e-05, "loss": 0.4342, "step": 54000 }, { "epoch": 2.93, "learning_rate": 3.533842677283977e-05, "loss": 0.4302, "step": 54500 }, { "epoch": 2.96, "learning_rate": 3.5203916926719036e-05, "loss": 0.4295, "step": 55000 }, { "epoch": 2.99, "learning_rate": 3.50694070805983e-05, "loss": 0.4404, "step": 55500 }, { "epoch": 3.01, "learning_rate": 3.4934897234477566e-05, "loss": 0.4063, "step": 56000 }, { "epoch": 3.04, "learning_rate": 3.480038738835683e-05, "loss": 0.4205, "step": 56500 }, { "epoch": 3.07, "learning_rate": 3.466587754223609e-05, "loss": 0.4267, "step": 57000 }, { "epoch": 3.09, "learning_rate": 3.4531367696115355e-05, "loss": 0.4291, "step": 57500 }, { "epoch": 3.12, "learning_rate": 3.439685784999463e-05, "loss": 0.4228, "step": 58000 }, { "epoch": 3.15, "learning_rate": 3.4262348003873885e-05, "loss": 0.4258, "step": 58500 }, { "epoch": 3.17, "learning_rate": 3.412783815775315e-05, "loss": 0.4154, "step": 59000 }, { "epoch": 3.2, "learning_rate": 3.399332831163241e-05, "loss": 0.4224, "step": 59500 }, { "epoch": 3.23, "learning_rate": 3.3858818465511674e-05, "loss": 0.4191, "step": 60000 }, { "epoch": 3.26, "learning_rate": 3.3724308619390946e-05, "loss": 0.4125, "step": 60500 }, { "epoch": 3.28, "learning_rate": 3.3589798773270204e-05, "loss": 0.4002, "step": 61000 }, { "epoch": 3.31, "learning_rate": 3.345528892714947e-05, "loss": 0.4144, "step": 61500 }, { "epoch": 3.34, "learning_rate": 3.332077908102873e-05, "loss": 0.4111, "step": 62000 }, { "epoch": 3.36, "learning_rate": 3.3186269234908e-05, "loss": 0.4145, "step": 62500 }, { "epoch": 3.39, "learning_rate": 3.3051759388787264e-05, "loss": 0.4168, "step": 63000 }, { "epoch": 3.42, "learning_rate": 3.291724954266652e-05, "loss": 0.4103, "step": 63500 }, { "epoch": 3.44, "learning_rate": 3.278273969654579e-05, "loss": 0.4127, "step": 64000 }, { "epoch": 3.47, "learning_rate": 3.264822985042505e-05, "loss": 0.4097, "step": 64500 }, { "epoch": 3.5, "learning_rate": 3.251372000430432e-05, "loss": 0.4091, "step": 65000 }, { "epoch": 3.52, "learning_rate": 3.237921015818358e-05, "loss": 0.4092, "step": 65500 }, { "epoch": 3.55, "learning_rate": 3.224470031206284e-05, "loss": 0.3997, "step": 66000 }, { "epoch": 3.58, "learning_rate": 3.2110190465942107e-05, "loss": 0.3943, "step": 66500 }, { "epoch": 3.6, "learning_rate": 3.197568061982137e-05, "loss": 0.4089, "step": 67000 }, { "epoch": 3.63, "learning_rate": 3.184117077370064e-05, "loss": 0.4046, "step": 67500 }, { "epoch": 3.66, "learning_rate": 3.17066609275799e-05, "loss": 0.397, "step": 68000 }, { "epoch": 3.69, "learning_rate": 3.157215108145917e-05, "loss": 0.3862, "step": 68500 }, { "epoch": 3.71, "learning_rate": 3.1437641235338425e-05, "loss": 0.4012, "step": 69000 }, { "epoch": 3.74, "learning_rate": 3.130313138921769e-05, "loss": 0.4019, "step": 69500 }, { "epoch": 3.77, "learning_rate": 3.1168621543096956e-05, "loss": 0.4011, "step": 70000 }, { "epoch": 3.79, "learning_rate": 3.103411169697622e-05, "loss": 0.406, "step": 70500 }, { "epoch": 3.82, "learning_rate": 3.0899601850855486e-05, "loss": 0.3802, "step": 71000 }, { "epoch": 3.85, "learning_rate": 3.0765092004734744e-05, "loss": 0.393, "step": 71500 }, { "epoch": 3.87, "learning_rate": 3.0630582158614016e-05, "loss": 0.4034, "step": 72000 }, { "epoch": 3.9, "learning_rate": 3.0496072312493274e-05, "loss": 0.3874, "step": 72500 }, { "epoch": 3.93, "learning_rate": 3.036156246637254e-05, "loss": 0.3957, "step": 73000 }, { "epoch": 3.95, "learning_rate": 3.0227052620251805e-05, "loss": 0.3992, "step": 73500 }, { "epoch": 3.98, "learning_rate": 3.0092542774131066e-05, "loss": 0.3802, "step": 74000 }, { "epoch": 4.01, "learning_rate": 2.995803292801033e-05, "loss": 0.3922, "step": 74500 }, { "epoch": 4.04, "learning_rate": 2.98235230818896e-05, "loss": 0.3898, "step": 75000 }, { "epoch": 4.06, "learning_rate": 2.9689013235768858e-05, "loss": 0.3807, "step": 75500 }, { "epoch": 4.09, "learning_rate": 2.9554503389648123e-05, "loss": 0.3781, "step": 76000 }, { "epoch": 4.12, "learning_rate": 2.9419993543527385e-05, "loss": 0.385, "step": 76500 }, { "epoch": 4.14, "learning_rate": 2.928548369740665e-05, "loss": 0.3823, "step": 77000 }, { "epoch": 4.17, "learning_rate": 2.915097385128592e-05, "loss": 0.3786, "step": 77500 }, { "epoch": 4.2, "learning_rate": 2.9016464005165177e-05, "loss": 0.3792, "step": 78000 }, { "epoch": 4.22, "learning_rate": 2.8881954159044446e-05, "loss": 0.3825, "step": 78500 }, { "epoch": 4.25, "learning_rate": 2.8747444312923704e-05, "loss": 0.3822, "step": 79000 }, { "epoch": 4.28, "learning_rate": 2.8612934466802972e-05, "loss": 0.3823, "step": 79500 }, { "epoch": 4.3, "learning_rate": 2.8478424620682237e-05, "loss": 0.3719, "step": 80000 }, { "epoch": 4.33, "learning_rate": 2.8343914774561496e-05, "loss": 0.3738, "step": 80500 }, { "epoch": 4.36, "learning_rate": 2.8209404928440764e-05, "loss": 0.3656, "step": 81000 }, { "epoch": 4.39, "learning_rate": 2.807489508232003e-05, "loss": 0.3724, "step": 81500 }, { "epoch": 4.41, "learning_rate": 2.794038523619929e-05, "loss": 0.3649, "step": 82000 }, { "epoch": 4.44, "learning_rate": 2.7805875390078556e-05, "loss": 0.3791, "step": 82500 }, { "epoch": 4.47, "learning_rate": 2.7671365543957818e-05, "loss": 0.3835, "step": 83000 }, { "epoch": 4.49, "learning_rate": 2.7536855697837083e-05, "loss": 0.3763, "step": 83500 }, { "epoch": 4.52, "learning_rate": 2.7402345851716348e-05, "loss": 0.3697, "step": 84000 }, { "epoch": 4.55, "learning_rate": 2.726783600559561e-05, "loss": 0.3657, "step": 84500 }, { "epoch": 4.57, "learning_rate": 2.7133326159474875e-05, "loss": 0.3794, "step": 85000 }, { "epoch": 4.6, "learning_rate": 2.6998816313354137e-05, "loss": 0.3699, "step": 85500 }, { "epoch": 4.63, "learning_rate": 2.6864306467233402e-05, "loss": 0.3698, "step": 86000 }, { "epoch": 4.65, "learning_rate": 2.6729796621112667e-05, "loss": 0.3613, "step": 86500 }, { "epoch": 4.68, "learning_rate": 2.659528677499193e-05, "loss": 0.369, "step": 87000 }, { "epoch": 4.71, "learning_rate": 2.6460776928871194e-05, "loss": 0.3631, "step": 87500 }, { "epoch": 4.73, "learning_rate": 2.6326267082750462e-05, "loss": 0.3559, "step": 88000 }, { "epoch": 4.76, "learning_rate": 2.619175723662972e-05, "loss": 0.3649, "step": 88500 }, { "epoch": 4.79, "learning_rate": 2.605724739050899e-05, "loss": 0.3595, "step": 89000 }, { "epoch": 4.82, "learning_rate": 2.5922737544388248e-05, "loss": 0.3597, "step": 89500 }, { "epoch": 4.84, "learning_rate": 2.5788227698267513e-05, "loss": 0.3695, "step": 90000 }, { "epoch": 4.87, "learning_rate": 2.565371785214678e-05, "loss": 0.3698, "step": 90500 }, { "epoch": 4.9, "learning_rate": 2.551920800602604e-05, "loss": 0.3502, "step": 91000 }, { "epoch": 4.92, "learning_rate": 2.5384698159905308e-05, "loss": 0.3638, "step": 91500 }, { "epoch": 4.95, "learning_rate": 2.5250188313784573e-05, "loss": 0.3498, "step": 92000 }, { "epoch": 4.98, "learning_rate": 2.5115678467663835e-05, "loss": 0.3635, "step": 92500 }, { "epoch": 5.0, "learning_rate": 2.4981168621543097e-05, "loss": 0.3542, "step": 93000 }, { "epoch": 5.03, "learning_rate": 2.484665877542236e-05, "loss": 0.353, "step": 93500 }, { "epoch": 5.06, "learning_rate": 2.4712148929301627e-05, "loss": 0.3526, "step": 94000 }, { "epoch": 5.08, "learning_rate": 2.457763908318089e-05, "loss": 0.3448, "step": 94500 }, { "epoch": 5.11, "learning_rate": 2.4443129237060154e-05, "loss": 0.3534, "step": 95000 }, { "epoch": 5.14, "learning_rate": 2.430861939093942e-05, "loss": 0.3529, "step": 95500 }, { "epoch": 5.17, "learning_rate": 2.4174109544818684e-05, "loss": 0.3422, "step": 96000 }, { "epoch": 5.19, "learning_rate": 2.4039599698697946e-05, "loss": 0.3589, "step": 96500 }, { "epoch": 5.22, "learning_rate": 2.3905089852577207e-05, "loss": 0.3528, "step": 97000 }, { "epoch": 5.25, "learning_rate": 2.3770580006456476e-05, "loss": 0.3448, "step": 97500 }, { "epoch": 5.27, "learning_rate": 2.3636070160335738e-05, "loss": 0.3508, "step": 98000 }, { "epoch": 5.3, "learning_rate": 2.3501560314215003e-05, "loss": 0.3508, "step": 98500 }, { "epoch": 5.33, "learning_rate": 2.3367050468094264e-05, "loss": 0.3452, "step": 99000 }, { "epoch": 5.35, "learning_rate": 2.323254062197353e-05, "loss": 0.3507, "step": 99500 }, { "epoch": 5.38, "learning_rate": 2.3098030775852795e-05, "loss": 0.3404, "step": 100000 }, { "epoch": 5.41, "learning_rate": 2.2963520929732056e-05, "loss": 0.3454, "step": 100500 }, { "epoch": 5.43, "learning_rate": 2.282901108361132e-05, "loss": 0.3534, "step": 101000 }, { "epoch": 5.46, "learning_rate": 2.2694501237490583e-05, "loss": 0.3388, "step": 101500 }, { "epoch": 5.49, "learning_rate": 2.255999139136985e-05, "loss": 0.3554, "step": 102000 }, { "epoch": 5.51, "learning_rate": 2.2425481545249113e-05, "loss": 0.3434, "step": 102500 }, { "epoch": 5.54, "learning_rate": 2.229097169912838e-05, "loss": 0.3387, "step": 103000 }, { "epoch": 5.57, "learning_rate": 2.215646185300764e-05, "loss": 0.3524, "step": 103500 }, { "epoch": 5.6, "learning_rate": 2.2021952006886905e-05, "loss": 0.3415, "step": 104000 }, { "epoch": 5.62, "learning_rate": 2.188744216076617e-05, "loss": 0.341, "step": 104500 }, { "epoch": 5.65, "learning_rate": 2.1752932314645432e-05, "loss": 0.339, "step": 105000 }, { "epoch": 5.68, "learning_rate": 2.1618422468524697e-05, "loss": 0.3391, "step": 105500 }, { "epoch": 5.7, "learning_rate": 2.1483912622403962e-05, "loss": 0.344, "step": 106000 }, { "epoch": 5.73, "learning_rate": 2.1349402776283224e-05, "loss": 0.336, "step": 106500 }, { "epoch": 5.76, "learning_rate": 2.121489293016249e-05, "loss": 0.3343, "step": 107000 }, { "epoch": 5.78, "learning_rate": 2.108038308404175e-05, "loss": 0.3393, "step": 107500 }, { "epoch": 5.81, "learning_rate": 2.094587323792102e-05, "loss": 0.3472, "step": 108000 }, { "epoch": 5.84, "learning_rate": 2.081136339180028e-05, "loss": 0.3285, "step": 108500 }, { "epoch": 5.86, "learning_rate": 2.0676853545679546e-05, "loss": 0.3505, "step": 109000 }, { "epoch": 5.89, "learning_rate": 2.0542343699558808e-05, "loss": 0.3461, "step": 109500 }, { "epoch": 5.92, "learning_rate": 2.040783385343807e-05, "loss": 0.3371, "step": 110000 }, { "epoch": 5.95, "learning_rate": 2.0273324007317338e-05, "loss": 0.3465, "step": 110500 }, { "epoch": 5.97, "learning_rate": 2.01388141611966e-05, "loss": 0.3301, "step": 111000 }, { "epoch": 6.0, "learning_rate": 2.0004304315075865e-05, "loss": 0.3392, "step": 111500 }, { "epoch": 6.03, "learning_rate": 1.9869794468955127e-05, "loss": 0.3345, "step": 112000 }, { "epoch": 6.05, "learning_rate": 1.9735284622834392e-05, "loss": 0.3407, "step": 112500 }, { "epoch": 6.08, "learning_rate": 1.9600774776713657e-05, "loss": 0.3334, "step": 113000 }, { "epoch": 6.11, "learning_rate": 1.946626493059292e-05, "loss": 0.3331, "step": 113500 }, { "epoch": 6.13, "learning_rate": 1.9331755084472184e-05, "loss": 0.3385, "step": 114000 }, { "epoch": 6.16, "learning_rate": 1.919724523835145e-05, "loss": 0.3352, "step": 114500 }, { "epoch": 6.19, "learning_rate": 1.9062735392230714e-05, "loss": 0.3294, "step": 115000 }, { "epoch": 6.21, "learning_rate": 1.8928225546109976e-05, "loss": 0.3294, "step": 115500 }, { "epoch": 6.24, "learning_rate": 1.879371569998924e-05, "loss": 0.3207, "step": 116000 }, { "epoch": 6.27, "learning_rate": 1.8659205853868503e-05, "loss": 0.3233, "step": 116500 }, { "epoch": 6.3, "learning_rate": 1.8524696007747768e-05, "loss": 0.3189, "step": 117000 }, { "epoch": 6.32, "learning_rate": 1.8390186161627033e-05, "loss": 0.3315, "step": 117500 }, { "epoch": 6.35, "learning_rate": 1.8255676315506295e-05, "loss": 0.3195, "step": 118000 }, { "epoch": 6.38, "learning_rate": 1.812116646938556e-05, "loss": 0.3327, "step": 118500 }, { "epoch": 6.4, "learning_rate": 1.7986656623264825e-05, "loss": 0.3191, "step": 119000 }, { "epoch": 6.43, "learning_rate": 1.7852146777144087e-05, "loss": 0.3212, "step": 119500 }, { "epoch": 6.46, "learning_rate": 1.771763693102335e-05, "loss": 0.3355, "step": 120000 }, { "epoch": 6.48, "learning_rate": 1.7583127084902613e-05, "loss": 0.3242, "step": 120500 }, { "epoch": 6.51, "learning_rate": 1.7448617238781882e-05, "loss": 0.3252, "step": 121000 }, { "epoch": 6.54, "learning_rate": 1.7314107392661144e-05, "loss": 0.3178, "step": 121500 }, { "epoch": 6.56, "learning_rate": 1.717959754654041e-05, "loss": 0.3226, "step": 122000 }, { "epoch": 6.59, "learning_rate": 1.704508770041967e-05, "loss": 0.3231, "step": 122500 }, { "epoch": 6.62, "learning_rate": 1.6910577854298936e-05, "loss": 0.3269, "step": 123000 }, { "epoch": 6.64, "learning_rate": 1.67760680081782e-05, "loss": 0.3218, "step": 123500 }, { "epoch": 6.67, "learning_rate": 1.6641558162057462e-05, "loss": 0.3237, "step": 124000 }, { "epoch": 6.7, "learning_rate": 1.6507048315936728e-05, "loss": 0.3169, "step": 124500 }, { "epoch": 6.73, "learning_rate": 1.637253846981599e-05, "loss": 0.3257, "step": 125000 }, { "epoch": 6.75, "learning_rate": 1.6238028623695258e-05, "loss": 0.3256, "step": 125500 }, { "epoch": 6.78, "learning_rate": 1.610351877757452e-05, "loss": 0.3315, "step": 126000 }, { "epoch": 6.81, "learning_rate": 1.596900893145378e-05, "loss": 0.3126, "step": 126500 }, { "epoch": 6.83, "learning_rate": 1.5834499085333046e-05, "loss": 0.3292, "step": 127000 }, { "epoch": 6.86, "learning_rate": 1.569998923921231e-05, "loss": 0.3176, "step": 127500 }, { "epoch": 6.89, "learning_rate": 1.5565479393091577e-05, "loss": 0.3229, "step": 128000 }, { "epoch": 6.91, "learning_rate": 1.5430969546970838e-05, "loss": 0.3182, "step": 128500 }, { "epoch": 6.94, "learning_rate": 1.5296459700850103e-05, "loss": 0.325, "step": 129000 }, { "epoch": 6.97, "learning_rate": 1.5161949854729368e-05, "loss": 0.325, "step": 129500 }, { "epoch": 6.99, "learning_rate": 1.5027440008608632e-05, "loss": 0.3217, "step": 130000 }, { "epoch": 7.02, "learning_rate": 1.4892930162487895e-05, "loss": 0.3191, "step": 130500 }, { "epoch": 7.05, "learning_rate": 1.4758420316367159e-05, "loss": 0.3166, "step": 131000 }, { "epoch": 7.08, "learning_rate": 1.4623910470246422e-05, "loss": 0.3109, "step": 131500 }, { "epoch": 7.1, "learning_rate": 1.4489400624125687e-05, "loss": 0.3113, "step": 132000 }, { "epoch": 7.13, "learning_rate": 1.435489077800495e-05, "loss": 0.3187, "step": 132500 }, { "epoch": 7.16, "learning_rate": 1.4220380931884214e-05, "loss": 0.3116, "step": 133000 }, { "epoch": 7.18, "learning_rate": 1.4085871085763478e-05, "loss": 0.3148, "step": 133500 }, { "epoch": 7.21, "learning_rate": 1.3951361239642743e-05, "loss": 0.3154, "step": 134000 }, { "epoch": 7.24, "learning_rate": 1.3816851393522006e-05, "loss": 0.3071, "step": 134500 }, { "epoch": 7.26, "learning_rate": 1.368234154740127e-05, "loss": 0.3067, "step": 135000 }, { "epoch": 7.29, "learning_rate": 1.3547831701280533e-05, "loss": 0.3147, "step": 135500 }, { "epoch": 7.32, "learning_rate": 1.34133218551598e-05, "loss": 0.3157, "step": 136000 }, { "epoch": 7.34, "learning_rate": 1.3278812009039063e-05, "loss": 0.3132, "step": 136500 }, { "epoch": 7.37, "learning_rate": 1.3144302162918327e-05, "loss": 0.3044, "step": 137000 }, { "epoch": 7.4, "learning_rate": 1.300979231679759e-05, "loss": 0.3094, "step": 137500 }, { "epoch": 7.42, "learning_rate": 1.2875282470676855e-05, "loss": 0.3048, "step": 138000 }, { "epoch": 7.45, "learning_rate": 1.2740772624556118e-05, "loss": 0.3157, "step": 138500 }, { "epoch": 7.48, "learning_rate": 1.2606262778435382e-05, "loss": 0.3106, "step": 139000 }, { "epoch": 7.51, "learning_rate": 1.2471752932314645e-05, "loss": 0.3065, "step": 139500 }, { "epoch": 7.53, "learning_rate": 1.233724308619391e-05, "loss": 0.3147, "step": 140000 }, { "epoch": 7.56, "learning_rate": 1.2202733240073174e-05, "loss": 0.3128, "step": 140500 }, { "epoch": 7.59, "learning_rate": 1.2068223393952437e-05, "loss": 0.3127, "step": 141000 }, { "epoch": 7.61, "learning_rate": 1.19337135478317e-05, "loss": 0.3005, "step": 141500 }, { "epoch": 7.64, "learning_rate": 1.1799203701710966e-05, "loss": 0.3085, "step": 142000 }, { "epoch": 7.67, "learning_rate": 1.166469385559023e-05, "loss": 0.3004, "step": 142500 }, { "epoch": 7.69, "learning_rate": 1.1530184009469494e-05, "loss": 0.3017, "step": 143000 }, { "epoch": 7.72, "learning_rate": 1.1395674163348758e-05, "loss": 0.3065, "step": 143500 }, { "epoch": 7.75, "learning_rate": 1.1261164317228023e-05, "loss": 0.3084, "step": 144000 }, { "epoch": 7.77, "learning_rate": 1.1126654471107285e-05, "loss": 0.3047, "step": 144500 }, { "epoch": 7.8, "learning_rate": 1.099214462498655e-05, "loss": 0.3071, "step": 145000 }, { "epoch": 7.83, "learning_rate": 1.0857634778865813e-05, "loss": 0.3087, "step": 145500 }, { "epoch": 7.86, "learning_rate": 1.0723124932745078e-05, "loss": 0.3074, "step": 146000 }, { "epoch": 7.88, "learning_rate": 1.0588615086624342e-05, "loss": 0.2943, "step": 146500 }, { "epoch": 7.91, "learning_rate": 1.0454105240503605e-05, "loss": 0.316, "step": 147000 }, { "epoch": 7.94, "learning_rate": 1.031959539438287e-05, "loss": 0.3063, "step": 147500 }, { "epoch": 7.96, "learning_rate": 1.0185085548262132e-05, "loss": 0.302, "step": 148000 }, { "epoch": 7.99, "learning_rate": 1.0050575702141397e-05, "loss": 0.3028, "step": 148500 }, { "epoch": 8.02, "learning_rate": 9.91606585602066e-06, "loss": 0.3111, "step": 149000 }, { "epoch": 8.04, "learning_rate": 9.781556009899926e-06, "loss": 0.3055, "step": 149500 }, { "epoch": 8.07, "learning_rate": 9.647046163779189e-06, "loss": 0.2982, "step": 150000 }, { "epoch": 8.1, "learning_rate": 9.512536317658454e-06, "loss": 0.3046, "step": 150500 }, { "epoch": 8.12, "learning_rate": 9.378026471537718e-06, "loss": 0.2987, "step": 151000 }, { "epoch": 8.15, "learning_rate": 9.243516625416981e-06, "loss": 0.3013, "step": 151500 }, { "epoch": 8.18, "learning_rate": 9.109006779296244e-06, "loss": 0.3041, "step": 152000 }, { "epoch": 8.21, "learning_rate": 8.97449693317551e-06, "loss": 0.2993, "step": 152500 }, { "epoch": 8.23, "learning_rate": 8.839987087054773e-06, "loss": 0.2958, "step": 153000 }, { "epoch": 8.26, "learning_rate": 8.705477240934038e-06, "loss": 0.2959, "step": 153500 }, { "epoch": 8.29, "learning_rate": 8.570967394813301e-06, "loss": 0.2996, "step": 154000 }, { "epoch": 8.31, "learning_rate": 8.436457548692565e-06, "loss": 0.3005, "step": 154500 }, { "epoch": 8.34, "learning_rate": 8.301947702571828e-06, "loss": 0.2944, "step": 155000 }, { "epoch": 8.37, "learning_rate": 8.167437856451092e-06, "loss": 0.2935, "step": 155500 }, { "epoch": 8.39, "learning_rate": 8.032928010330357e-06, "loss": 0.3005, "step": 156000 }, { "epoch": 8.42, "learning_rate": 7.89841816420962e-06, "loss": 0.3022, "step": 156500 }, { "epoch": 8.45, "learning_rate": 7.763908318088885e-06, "loss": 0.3017, "step": 157000 }, { "epoch": 8.47, "learning_rate": 7.629398471968149e-06, "loss": 0.2987, "step": 157500 }, { "epoch": 8.5, "learning_rate": 7.494888625847413e-06, "loss": 0.299, "step": 158000 }, { "epoch": 8.53, "learning_rate": 7.360378779726676e-06, "loss": 0.2957, "step": 158500 }, { "epoch": 8.55, "learning_rate": 7.225868933605941e-06, "loss": 0.2985, "step": 159000 }, { "epoch": 8.58, "learning_rate": 7.091359087485204e-06, "loss": 0.2945, "step": 159500 }, { "epoch": 8.61, "learning_rate": 6.956849241364468e-06, "loss": 0.2996, "step": 160000 }, { "epoch": 8.64, "learning_rate": 6.822339395243732e-06, "loss": 0.3017, "step": 160500 }, { "epoch": 8.66, "learning_rate": 6.687829549122997e-06, "loss": 0.2942, "step": 161000 }, { "epoch": 8.69, "learning_rate": 6.55331970300226e-06, "loss": 0.2946, "step": 161500 }, { "epoch": 8.72, "learning_rate": 6.418809856881525e-06, "loss": 0.2986, "step": 162000 }, { "epoch": 8.74, "learning_rate": 6.284300010760788e-06, "loss": 0.2909, "step": 162500 }, { "epoch": 8.77, "learning_rate": 6.149790164640052e-06, "loss": 0.299, "step": 163000 }, { "epoch": 8.8, "learning_rate": 6.015280318519316e-06, "loss": 0.2883, "step": 163500 }, { "epoch": 8.82, "learning_rate": 5.88077047239858e-06, "loss": 0.2977, "step": 164000 }, { "epoch": 8.85, "learning_rate": 5.746260626277844e-06, "loss": 0.2866, "step": 164500 }, { "epoch": 8.88, "learning_rate": 5.611750780157108e-06, "loss": 0.2957, "step": 165000 }, { "epoch": 8.9, "learning_rate": 5.477240934036372e-06, "loss": 0.2962, "step": 165500 }, { "epoch": 8.93, "learning_rate": 5.342731087915636e-06, "loss": 0.3018, "step": 166000 }, { "epoch": 8.96, "learning_rate": 5.2082212417949e-06, "loss": 0.2972, "step": 166500 }, { "epoch": 8.99, "learning_rate": 5.073711395674163e-06, "loss": 0.2982, "step": 167000 }, { "epoch": 9.01, "learning_rate": 4.939201549553427e-06, "loss": 0.2938, "step": 167500 }, { "epoch": 9.04, "learning_rate": 4.8046917034326915e-06, "loss": 0.2867, "step": 168000 }, { "epoch": 9.07, "learning_rate": 4.670181857311955e-06, "loss": 0.2979, "step": 168500 }, { "epoch": 9.09, "learning_rate": 4.535672011191219e-06, "loss": 0.3057, "step": 169000 }, { "epoch": 9.12, "learning_rate": 4.4011621650704835e-06, "loss": 0.2974, "step": 169500 }, { "epoch": 9.15, "learning_rate": 4.266652318949747e-06, "loss": 0.289, "step": 170000 }, { "epoch": 9.17, "learning_rate": 4.132142472829011e-06, "loss": 0.3038, "step": 170500 }, { "epoch": 9.2, "learning_rate": 3.9976326267082754e-06, "loss": 0.2891, "step": 171000 }, { "epoch": 9.23, "learning_rate": 3.86312278058754e-06, "loss": 0.2817, "step": 171500 }, { "epoch": 9.25, "learning_rate": 3.728612934466803e-06, "loss": 0.2821, "step": 172000 }, { "epoch": 9.28, "learning_rate": 3.5941030883460674e-06, "loss": 0.2817, "step": 172500 }, { "epoch": 9.31, "learning_rate": 3.4595932422253312e-06, "loss": 0.2922, "step": 173000 }, { "epoch": 9.33, "learning_rate": 3.3250833961045955e-06, "loss": 0.2874, "step": 173500 }, { "epoch": 9.36, "learning_rate": 3.1905735499838585e-06, "loss": 0.294, "step": 174000 }, { "epoch": 9.39, "learning_rate": 3.056063703863123e-06, "loss": 0.2887, "step": 174500 }, { "epoch": 9.42, "learning_rate": 2.921553857742387e-06, "loss": 0.2816, "step": 175000 }, { "epoch": 9.44, "learning_rate": 2.787044011621651e-06, "loss": 0.2937, "step": 175500 }, { "epoch": 9.47, "learning_rate": 2.6525341655009147e-06, "loss": 0.2888, "step": 176000 }, { "epoch": 9.5, "learning_rate": 2.5180243193801786e-06, "loss": 0.2916, "step": 176500 }, { "epoch": 9.52, "learning_rate": 2.383514473259443e-06, "loss": 0.2923, "step": 177000 }, { "epoch": 9.55, "learning_rate": 2.2490046271387067e-06, "loss": 0.2819, "step": 177500 }, { "epoch": 9.58, "learning_rate": 2.1144947810179705e-06, "loss": 0.2812, "step": 178000 }, { "epoch": 9.6, "learning_rate": 1.9799849348972348e-06, "loss": 0.284, "step": 178500 }, { "epoch": 9.63, "learning_rate": 1.8454750887764986e-06, "loss": 0.2886, "step": 179000 }, { "epoch": 9.66, "learning_rate": 1.7109652426557627e-06, "loss": 0.2867, "step": 179500 }, { "epoch": 9.68, "learning_rate": 1.5764553965350263e-06, "loss": 0.2925, "step": 180000 }, { "epoch": 9.71, "learning_rate": 1.4419455504142906e-06, "loss": 0.2829, "step": 180500 }, { "epoch": 9.74, "learning_rate": 1.3074357042935542e-06, "loss": 0.2796, "step": 181000 }, { "epoch": 9.77, "learning_rate": 1.1729258581728182e-06, "loss": 0.2909, "step": 181500 }, { "epoch": 9.79, "learning_rate": 1.0384160120520823e-06, "loss": 0.2841, "step": 182000 }, { "epoch": 9.82, "learning_rate": 9.039061659313462e-07, "loss": 0.287, "step": 182500 }, { "epoch": 9.85, "learning_rate": 7.693963198106102e-07, "loss": 0.2873, "step": 183000 }, { "epoch": 9.87, "learning_rate": 6.348864736898741e-07, "loss": 0.2928, "step": 183500 }, { "epoch": 9.9, "learning_rate": 5.003766275691381e-07, "loss": 0.2872, "step": 184000 }, { "epoch": 9.93, "learning_rate": 3.6586678144840204e-07, "loss": 0.2819, "step": 184500 }, { "epoch": 9.95, "learning_rate": 2.31356935327666e-07, "loss": 0.2846, "step": 185000 }, { "epoch": 9.98, "learning_rate": 9.684708920692995e-08, "loss": 0.2905, "step": 185500 }, { "epoch": 10.0, "step": 185860, "total_flos": 7.83596674285056e+17, "train_loss": 0.4548698722488796, "train_runtime": 66289.7119, "train_samples_per_second": 22.43, "train_steps_per_second": 2.804 } ], "max_steps": 185860, "num_train_epochs": 10, "total_flos": 7.83596674285056e+17, "trial_name": null, "trial_params": null }