{ "best_metric": 3.971170425415039, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/3/checkpoints/checkpoint-2823840", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 2823840, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.8198, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5508, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0546, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9887, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9426, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.915, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.7347, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.6264, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.5281, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4559, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.3935, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 6.3291, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 6.2547, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 6.1878, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 6.1296, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 6.0676, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986582483983168e-05, "loss": 6.0186, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985743889232116e-05, "loss": 5.9742, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984905294481064e-05, "loss": 5.9331, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984066699730012e-05, "loss": 5.8941, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8576, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.814, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.7914, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.980713958606178e-05, "loss": 5.7546, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7329, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7053, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.6822, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.6519, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6275, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6097, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.5838, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.5794, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5486, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.972331286856403e-05, "loss": 5.5386, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5314, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5107, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.4979, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.4634, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.9681399509815164e-05, "loss": 5.4573, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.437, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4312, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4135, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.4049, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.3742, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.3865, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.3751, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 5.3665, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960595873982795e-05, "loss": 5.3533, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959757279231743e-05, "loss": 5.3256, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958918684480691e-05, "loss": 5.3191, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3207, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3065, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 5.2952, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.2703, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.2708, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953890391735125e-05, "loss": 5.2579, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530517969840727e-05, "loss": 5.2837, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522132022330207e-05, "loss": 5.2368, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.9513746074819686e-05, "loss": 5.2413, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.9505360127309166e-05, "loss": 5.2355, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.9496974179798646e-05, "loss": 5.2152, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948858823228813e-05, "loss": 5.2171, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948021866358134e-05, "loss": 5.2008, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947183271607082e-05, "loss": 5.1848, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.94634467685603e-05, "loss": 5.1828, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945506082104978e-05, "loss": 5.2, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.9446674873539255e-05, "loss": 5.1739, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.9438288926028735e-05, "loss": 5.165, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.9429902978518215e-05, "loss": 5.1481, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421517031007695e-05, "loss": 5.1484, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413147462300904e-05, "loss": 5.1574, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940477789359412e-05, "loss": 5.1536, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.93963919460836e-05, "loss": 5.1402, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.938800599857309e-05, "loss": 5.1481, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.937962005106256e-05, "loss": 5.141, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.937123410355204e-05, "loss": 5.129, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1102, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.0985, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.934609263982421e-05, "loss": 5.0972, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933770669231369e-05, "loss": 5.0896, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329337123606905e-05, "loss": 5.0857, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932095117609638e-05, "loss": 5.0819, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931256522858586e-05, "loss": 5.0842, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930417928107534e-05, "loss": 5.0763, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295809712368554e-05, "loss": 5.05, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287423764858034e-05, "loss": 5.0449, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279037817347514e-05, "loss": 5.0553, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.9270651869836994e-05, "loss": 5.0557, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.92622823011302e-05, "loss": 5.0322, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925389635361968e-05, "loss": 5.0348, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924551040610916e-05, "loss": 5.0363, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923712445859864e-05, "loss": 5.0208, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922875488989185e-05, "loss": 5.0149, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.0145, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 5.0026, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 5.0076, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.9971, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 4.9818, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 4.9816, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917006963612195e-05, "loss": 4.981, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916168368861143e-05, "loss": 4.9758, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915329774110091e-05, "loss": 4.9761, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914491179359039e-05, "loss": 4.9668, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913652584607987e-05, "loss": 4.9643, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128156277373076e-05, "loss": 4.9535, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119770329862556e-05, "loss": 4.9354, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111384382352036e-05, "loss": 4.94, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9102998434841516e-05, "loss": 4.9388, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.9094612487330996e-05, "loss": 4.9354, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908624291862421e-05, "loss": 4.9258, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907785697111369e-05, "loss": 4.9232, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906947102360317e-05, "loss": 4.9143, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906108507609265e-05, "loss": 4.9155, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905269912858213e-05, "loss": 4.9094, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904431318107161e-05, "loss": 4.9097, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903592723356109e-05, "loss": 4.9011, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027541286050565e-05, "loss": 4.9005, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901917171734378e-05, "loss": 4.901, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901078576983326e-05, "loss": 4.8919, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900239982232274e-05, "loss": 4.8984, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.8966, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898564430610543e-05, "loss": 4.8811, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897725835859491e-05, "loss": 4.8873, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968872411084396e-05, "loss": 4.8701, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.875, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.8508, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.8636, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.849, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8519, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8331, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8643, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890181758860769e-05, "loss": 4.8515, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889343164109717e-05, "loss": 4.8391, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.8366, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.8324, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.8419, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.8351, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.8236, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884314871364151e-05, "loss": 4.8287, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883476276613099e-05, "loss": 4.8155, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882637681862047e-05, "loss": 4.8247, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881799087110995e-05, "loss": 4.808, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880960492359943e-05, "loss": 4.8093, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.8077, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.797, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.798, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.7987, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.7928, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.7986, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.7862, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.749021053314209, "eval_runtime": 316.6809, "eval_samples_per_second": 1204.97, "eval_steps_per_second": 37.656, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.7758, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.7701, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.7875, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.7705, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.7862, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.7582, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.7692, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.7475, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.7603, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.7568, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.7611, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.7563, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.7388, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.7396, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.7337, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.7303, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.7409, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.7344, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.7301, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.7454, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.7206, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.7289, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.722, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.7316, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541369254888915e-05, "loss": 4.7079, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.7144, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.706, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.7147, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.6943, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.6995, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.7082, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.6993, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.6997, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.7053, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.6986, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.6983, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.6799, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.6899, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.6733, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.6829, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840725960993552e-05, "loss": 4.6803, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398873662425e-05, "loss": 4.6772, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.6633, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.6781, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.6769, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.6699, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.6766, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.6471, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.6481, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.667, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.6551, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.6527, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.6356, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.6404, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.6352, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.6609, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.6298, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.6401, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.6436, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824799212245056e-05, "loss": 4.6251, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823960617494004e-05, "loss": 4.6304, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823122022742952e-05, "loss": 4.6242, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222834279919e-05, "loss": 4.6148, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.6207, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.6346, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819769281619117e-05, "loss": 4.623, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818930686868065e-05, "loss": 4.6109, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818092092117013e-05, "loss": 4.6113, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817253497365961e-05, "loss": 4.6102, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816416540495282e-05, "loss": 4.6266, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.6284, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147393509931785e-05, "loss": 4.6172, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139007562421265e-05, "loss": 4.6309, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130621614910745e-05, "loss": 4.6272, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122252046203954e-05, "loss": 4.6228, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.6077, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.6066, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809711058247612e-05, "loss": 4.6022, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887246349656e-05, "loss": 4.6022, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808033868745508e-05, "loss": 4.5984, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807195273994456e-05, "loss": 4.6026, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806356679243404e-05, "loss": 4.6112, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805518084492352e-05, "loss": 4.601, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046794897413e-05, "loss": 4.5852, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803840894990248e-05, "loss": 4.5855, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.80300393811957e-05, "loss": 4.5902, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802165343368518e-05, "loss": 4.6024, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801326748617466e-05, "loss": 4.5828, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800488153866413e-05, "loss": 4.5892, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799649559115361e-05, "loss": 4.5932, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798810964364309e-05, "loss": 4.5839, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979756453740036e-05, "loss": 4.5776, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971370506229516e-05, "loss": 4.5794, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7962984558718996e-05, "loss": 4.5782, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954598611208476e-05, "loss": 4.5796, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946212663697956e-05, "loss": 4.5815, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.7937826716187436e-05, "loss": 4.5649, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.7929440768676916e-05, "loss": 4.5726, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.7921054821166396e-05, "loss": 4.568, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.7912668873655876e-05, "loss": 4.5768, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.7904299304949085e-05, "loss": 4.5703, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895913357438565e-05, "loss": 4.571, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887527409928045e-05, "loss": 4.5673, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879141462417525e-05, "loss": 4.5631, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870755514907005e-05, "loss": 4.5479, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862369567396485e-05, "loss": 4.5519, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853983619885965e-05, "loss": 4.5569, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845597672375445e-05, "loss": 4.5538, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783722810366866e-05, "loss": 4.5502, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782885853496187e-05, "loss": 4.5474, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782047258745135e-05, "loss": 4.5426, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781208663994083e-05, "loss": 4.547, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780370069243031e-05, "loss": 4.5445, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779531474491979e-05, "loss": 4.5444, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778692879740927e-05, "loss": 4.5472, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777854284989875e-05, "loss": 4.5454, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777018965999569e-05, "loss": 4.547, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776180371248517e-05, "loss": 4.5417, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775341776497465e-05, "loss": 4.5503, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.7745031817464134e-05, "loss": 4.5494, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736645869953614e-05, "loss": 4.5365, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728259922443094e-05, "loss": 4.5471, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719873974932574e-05, "loss": 4.5342, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711488027422054e-05, "loss": 4.5418, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770311845871526e-05, "loss": 4.5176, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769473251120474e-05, "loss": 4.5354, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768634656369422e-05, "loss": 4.5167, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767797699498743e-05, "loss": 4.5251, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766959104747691e-05, "loss": 4.5117, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766120509996639e-05, "loss": 4.5418, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765281915245587e-05, "loss": 4.5325, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764443320494535e-05, "loss": 4.5257, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763604725743483e-05, "loss": 4.5186, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762766130992431e-05, "loss": 4.5225, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761927536241379e-05, "loss": 4.5318, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761088941490327e-05, "loss": 4.5252, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760251984619649e-05, "loss": 4.5188, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759413389868596e-05, "loss": 4.5229, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758574795117544e-05, "loss": 4.5147, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757736200366492e-05, "loss": 4.5276, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.75689760561544e-05, "loss": 4.5084, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756059010864388e-05, "loss": 4.5144, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755222053993709e-05, "loss": 4.5098, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754383459242657e-05, "loss": 4.5056, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753544864491605e-05, "loss": 4.5103, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527062697405536e-05, "loss": 4.5085, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518693128698745e-05, "loss": 4.5084, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510307181188225e-05, "loss": 4.5083, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7501921233677705e-05, "loss": 4.5033, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.471827507019043, "eval_runtime": 306.1033, "eval_samples_per_second": 1246.609, "eval_steps_per_second": 38.957, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493535286167185e-05, "loss": 4.4952, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485149338656665e-05, "loss": 4.4875, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476763391146145e-05, "loss": 4.5094, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468377443635625e-05, "loss": 4.4926, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7459991496125105e-05, "loss": 4.5133, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451605548614585e-05, "loss": 4.4833, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443219601104065e-05, "loss": 4.4959, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434833653593545e-05, "loss": 4.4784, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426447706083025e-05, "loss": 4.4947, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418061758572505e-05, "loss": 4.4905, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409675811061985e-05, "loss": 4.4959, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401289863551465e-05, "loss": 4.4917, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739293667364841e-05, "loss": 4.4758, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738455072613789e-05, "loss": 4.4835, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737616477862737e-05, "loss": 4.4784, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736777883111685e-05, "loss": 4.4749, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735939288360632e-05, "loss": 4.4788, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.73510069360958e-05, "loss": 4.4817, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734262098858528e-05, "loss": 4.4763, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733423504107476e-05, "loss": 4.4964, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732584909356424e-05, "loss": 4.4702, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731746314605372e-05, "loss": 4.4782, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73090771985432e-05, "loss": 4.4757, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730069125103269e-05, "loss": 4.4855, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729230530352217e-05, "loss": 4.4662, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728393573481538e-05, "loss": 4.4764, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727554978730486e-05, "loss": 4.465, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726716383979434e-05, "loss": 4.4723, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725877789228382e-05, "loss": 4.4574, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.72503919447733e-05, "loss": 4.4607, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724202237606651e-05, "loss": 4.4694, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723363642855599e-05, "loss": 4.4679, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722525048104547e-05, "loss": 4.4676, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721686453353495e-05, "loss": 4.4705, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720847858602443e-05, "loss": 4.4645, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720009263851391e-05, "loss": 4.4704, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719172306980712e-05, "loss": 4.45, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71833371222966e-05, "loss": 4.4659, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717495117478608e-05, "loss": 4.4478, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716656522727556e-05, "loss": 4.4584, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715819565856877e-05, "loss": 4.4552, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714980971105825e-05, "loss": 4.4585, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714142376354773e-05, "loss": 4.4514, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713303781603721e-05, "loss": 4.4521, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124651868526685e-05, "loss": 4.4592, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116265921016165e-05, "loss": 4.4526, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7107879973505645e-05, "loss": 4.4565, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099494025995125e-05, "loss": 4.4369, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709112445728834e-05, "loss": 4.4305, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708273850977782e-05, "loss": 4.4484, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074368941071037e-05, "loss": 4.4439, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065982993560517e-05, "loss": 4.4431, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705759704604999e-05, "loss": 4.4257, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704921109853947e-05, "loss": 4.4315, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704082515102895e-05, "loss": 4.4328, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703243920351843e-05, "loss": 4.4454, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702405325600791e-05, "loss": 4.4235, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701566730849739e-05, "loss": 4.4355, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.70072977397906e-05, "loss": 4.4382, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998928171083814e-05, "loss": 4.4242, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990542223573294e-05, "loss": 4.4292, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982156276062774e-05, "loss": 4.425, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973770328552254e-05, "loss": 4.4129, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965384381041734e-05, "loss": 4.427, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.6956998433531214e-05, "loss": 4.4293, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.6948612486020694e-05, "loss": 4.4326, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.6940226538510174e-05, "loss": 4.4101, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.6931840590999654e-05, "loss": 4.4181, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.6923454643489134e-05, "loss": 4.4141, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915068695978614e-05, "loss": 4.4404, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690669912727182e-05, "loss": 4.4269, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.68983131797613e-05, "loss": 4.4277, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688992723225078e-05, "loss": 4.4389, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688154128474026e-05, "loss": 4.4385, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687315533722974e-05, "loss": 4.4315, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686476938971923e-05, "loss": 4.4199, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685639982101244e-05, "loss": 4.4203, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684801387350192e-05, "loss": 4.4184, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.68396279259914e-05, "loss": 4.4145, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683125835728461e-05, "loss": 4.4159, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682287240977409e-05, "loss": 4.4166, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681448646226357e-05, "loss": 4.4271, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680610051475305e-05, "loss": 4.4157, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679771456724252e-05, "loss": 4.4069, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789328619732e-05, "loss": 4.4023, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678094267222148e-05, "loss": 4.4114, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677255672471097e-05, "loss": 4.419, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764187156004177e-05, "loss": 4.4074, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755801208493657e-05, "loss": 4.4088, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747415260983136e-05, "loss": 4.4181, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739029313472616e-05, "loss": 4.3978, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730659744765826e-05, "loss": 4.4055, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722273797255305e-05, "loss": 4.4009, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713887849744785e-05, "loss": 4.4085, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705501902234265e-05, "loss": 4.407, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697115954723745e-05, "loss": 4.4033, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688730007213225e-05, "loss": 4.3946, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680344059702705e-05, "loss": 4.403, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6671958112192185e-05, "loss": 4.394, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663572164681665e-05, "loss": 4.4105, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665520259597488e-05, "loss": 4.4018, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664681664846436e-05, "loss": 4.4014, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663843070095384e-05, "loss": 4.3934, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663006113224705e-05, "loss": 4.4029, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662167518473653e-05, "loss": 4.3793, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661328923722601e-05, "loss": 4.3864, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660490328971549e-05, "loss": 4.3896, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659651734220497e-05, "loss": 4.391, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658813139469445e-05, "loss": 4.3832, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657976182598766e-05, "loss": 4.3861, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657137587847714e-05, "loss": 4.379, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656298993096662e-05, "loss": 4.3864, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.65546039834561e-05, "loss": 4.3823, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546218035945586e-05, "loss": 4.3795, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537832088435065e-05, "loss": 4.3902, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529462519728275e-05, "loss": 4.3886, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521076572217755e-05, "loss": 4.3905, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.6512690624707234e-05, "loss": 4.38, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650430467719671e-05, "loss": 4.3912, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649591872968619e-05, "loss": 4.3882, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648753278217567e-05, "loss": 4.3797, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647914683466515e-05, "loss": 4.3973, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647077726595836e-05, "loss": 4.3752, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462391318447837e-05, "loss": 4.3864, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645400537093732e-05, "loss": 4.3654, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.64456194234268e-05, "loss": 4.3817, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643723347591628e-05, "loss": 4.3617, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642888028601323e-05, "loss": 4.3735, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642049433850271e-05, "loss": 4.3608, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641210839099218e-05, "loss": 4.3883, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640372244348166e-05, "loss": 4.3774, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639533649597114e-05, "loss": 4.3763, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638695054846062e-05, "loss": 4.3689, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.63785646009501e-05, "loss": 4.3716, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637017865343958e-05, "loss": 4.3871, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636179270592906e-05, "loss": 4.3754, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635342313722228e-05, "loss": 4.3689, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634503718971176e-05, "loss": 4.3794, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336667621004966e-05, "loss": 4.3687, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328281673494446e-05, "loss": 4.3777, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319895725983926e-05, "loss": 4.3625, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311509778473406e-05, "loss": 4.3712, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303123830962886e-05, "loss": 4.3653, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294737883452366e-05, "loss": 4.3657, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286351935941846e-05, "loss": 4.3629, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6277965988431326e-05, "loss": 4.3689, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269580040920806e-05, "loss": 4.3594, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261194093410286e-05, "loss": 4.3657, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6252808145899766e-05, "loss": 4.3621, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.3374714851379395, "eval_runtime": 295.9677, "eval_samples_per_second": 1289.299, "eval_steps_per_second": 40.292, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244438577192975e-05, "loss": 4.3592, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623605262968246e-05, "loss": 4.3484, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622766668217194e-05, "loss": 4.3675, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621928073466142e-05, "loss": 4.3507, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210894787150895e-05, "loss": 4.3766, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620252521844411e-05, "loss": 4.3435, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619413927093359e-05, "loss": 4.356, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618575332342307e-05, "loss": 4.3399, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177367375912543e-05, "loss": 4.3572, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616899780720576e-05, "loss": 4.3558, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616061185969524e-05, "loss": 4.3544, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615224229098845e-05, "loss": 4.3563, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614385634347793e-05, "loss": 4.3384, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135470395967415e-05, "loss": 4.35, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127084448456895e-05, "loss": 4.3452, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611869850094637e-05, "loss": 4.3437, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611031255343585e-05, "loss": 4.3439, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610192660592533e-05, "loss": 4.3472, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609354065841481e-05, "loss": 4.3462, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608517108970802e-05, "loss": 4.3603, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.60767851421975e-05, "loss": 4.3407, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606839919468698e-05, "loss": 4.3459, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606001324717646e-05, "loss": 4.3463, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605162729966594e-05, "loss": 4.3573, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604325773095915e-05, "loss": 4.336, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603487178344863e-05, "loss": 4.3477, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602648583593811e-05, "loss": 4.3364, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601809988842759e-05, "loss": 4.3402, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600971394091707e-05, "loss": 4.3278, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600134437221028e-05, "loss": 4.3392, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599295842469976e-05, "loss": 4.3391, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598457247718924e-05, "loss": 4.3431, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597618652967872e-05, "loss": 4.3381, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.59678005821682e-05, "loss": 4.3451, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595943101346141e-05, "loss": 4.3372, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595104506595089e-05, "loss": 4.3442, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.59426754972441e-05, "loss": 4.3306, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934289549733587e-05, "loss": 4.3398, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925903602223066e-05, "loss": 4.3241, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917517654712546e-05, "loss": 4.3337, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909131707202026e-05, "loss": 4.3332, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900745759691506e-05, "loss": 4.3377, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892359812180986e-05, "loss": 4.3285, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5883973864670466e-05, "loss": 4.331, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875587917159946e-05, "loss": 4.3354, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867201969649426e-05, "loss": 4.3323, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858832400942635e-05, "loss": 4.3343, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850446453432115e-05, "loss": 4.324, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842060505921595e-05, "loss": 4.3058, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833674558411075e-05, "loss": 4.3301, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.5825288610900555e-05, "loss": 4.3252, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5816902663390035e-05, "loss": 4.3204, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808516715879515e-05, "loss": 4.3142, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580014714717273e-05, "loss": 4.3126, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791761199662204e-05, "loss": 4.3116, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783375252151684e-05, "loss": 4.3282, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5774989304641164e-05, "loss": 4.3098, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576661973593438e-05, "loss": 4.3165, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575823378842385e-05, "loss": 4.3256, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574986421971707e-05, "loss": 4.3089, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574147827220655e-05, "loss": 4.3108, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573309232469602e-05, "loss": 4.3159, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572470637718551e-05, "loss": 4.2949, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716336808478725e-05, "loss": 4.3117, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5707950860968205e-05, "loss": 4.3172, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569956491345768e-05, "loss": 4.3168, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569117896594716e-05, "loss": 4.2996, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568279301843664e-05, "loss": 4.3072, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567440707092612e-05, "loss": 4.2995, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.56660211234156e-05, "loss": 4.322, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565763517590508e-05, "loss": 4.3164, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564926560719829e-05, "loss": 4.3177, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5640879659687767e-05, "loss": 4.3247, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632493712177247e-05, "loss": 4.3285, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624107764666726e-05, "loss": 4.3256, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561573819595994e-05, "loss": 4.303, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560735224844942e-05, "loss": 4.3117, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559898267974263e-05, "loss": 4.3138, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559059673223211e-05, "loss": 4.3031, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558221078472159e-05, "loss": 4.3123, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557382483721107e-05, "loss": 4.3045, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556543888970055e-05, "loss": 4.316, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555705294219003e-05, "loss": 4.3117, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554866699467951e-05, "loss": 4.2926, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554028104716899e-05, "loss": 4.2989, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553189509965847e-05, "loss": 4.3072, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523541909755416e-05, "loss": 4.3093, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515155962244896e-05, "loss": 4.3017, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506770014734376e-05, "loss": 4.3007, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498384067223856e-05, "loss": 4.3099, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5490014498517065e-05, "loss": 4.2952, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481644929810274e-05, "loss": 4.2969, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.5473258982299754e-05, "loss": 4.3009, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.5464873034789234e-05, "loss": 4.3064, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.5456487087278714e-05, "loss": 4.3043, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448101139768194e-05, "loss": 4.2979, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5439715192257674e-05, "loss": 4.2866, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431329244747154e-05, "loss": 4.3033, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5422943297236634e-05, "loss": 4.2891, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414557349726114e-05, "loss": 4.3097, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540618778101933e-05, "loss": 4.3005, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539780183350881e-05, "loss": 4.2976, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538941588599829e-05, "loss": 4.292, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538102993848777e-05, "loss": 4.3031, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537264399097725e-05, "loss": 4.2785, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536425804346673e-05, "loss": 4.2893, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535588847475994e-05, "loss": 4.2837, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534750252724942e-05, "loss": 4.291, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.53391165797389e-05, "loss": 4.2833, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533073063222838e-05, "loss": 4.2887, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532236106352159e-05, "loss": 4.2832, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.53139914948148e-05, "loss": 4.279, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530560554730428e-05, "loss": 4.2879, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529721959979376e-05, "loss": 4.2777, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528883365228324e-05, "loss": 4.2938, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528044770477272e-05, "loss": 4.2902, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.52720617572622e-05, "loss": 4.2915, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526367580975168e-05, "loss": 4.2836, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525528986224116e-05, "loss": 4.2934, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5246903914730636e-05, "loss": 4.2942, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238517967220116e-05, "loss": 4.2834, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230132019709596e-05, "loss": 4.2973, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221762451002805e-05, "loss": 4.2804, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213376503492285e-05, "loss": 4.2887, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520499055598177e-05, "loss": 4.2753, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519660460847125e-05, "loss": 4.2856, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518821866096073e-05, "loss": 4.2674, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517983271345021e-05, "loss": 4.2796, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517146314474342e-05, "loss": 4.2684, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.51630771972329e-05, "loss": 4.2896, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515469124972238e-05, "loss": 4.2807, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514630530221186e-05, "loss": 4.2845, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513791935470134e-05, "loss": 4.2746, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512953340719082e-05, "loss": 4.2807, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.51211474596803e-05, "loss": 4.2903, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511277789097351e-05, "loss": 4.2812, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510439194346299e-05, "loss": 4.2781, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509600599595247e-05, "loss": 4.2872, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087620048441956e-05, "loss": 4.2748, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079234100931436e-05, "loss": 4.2879, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070864532224645e-05, "loss": 4.2679, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062478584714125e-05, "loss": 4.2806, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054109016007334e-05, "loss": 4.2747, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045723068496814e-05, "loss": 4.2731, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037337120986294e-05, "loss": 4.2775, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5028951173475774e-05, "loss": 4.2706, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020565225965254e-05, "loss": 4.2712, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501219565725846e-05, "loss": 4.2727, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500380970974794e-05, "loss": 4.2771, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.2549028396606445, "eval_runtime": 293.1686, "eval_samples_per_second": 1301.609, "eval_steps_per_second": 40.676, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499542376223742e-05, "loss": 4.2664, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498703781472691e-05, "loss": 4.258, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497865186721639e-05, "loss": 4.2781, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497026591970587e-05, "loss": 4.2638, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496187997219535e-05, "loss": 4.2843, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495349402468482e-05, "loss": 4.2638, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.49451080771743e-05, "loss": 4.2622, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493672212966378e-05, "loss": 4.2508, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492833618215326e-05, "loss": 4.2698, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491995023464274e-05, "loss": 4.2726, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491156428713222e-05, "loss": 4.2654, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.49031783396217e-05, "loss": 4.2654, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489479239211118e-05, "loss": 4.2545, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488640644460066e-05, "loss": 4.2619, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487802049709014e-05, "loss": 4.2615, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486963454957962e-05, "loss": 4.2526, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.48612486020691e-05, "loss": 4.2588, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485287903336232e-05, "loss": 4.2648, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.48444930858518e-05, "loss": 4.2587, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483610713834128e-05, "loss": 4.2714, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482772119083076e-05, "loss": 4.2614, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481933524332024e-05, "loss": 4.264, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481096567461345e-05, "loss": 4.2601, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480257972710293e-05, "loss": 4.2702, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479419377959241e-05, "loss": 4.2514, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478580783208188e-05, "loss": 4.2597, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.4777438263375096e-05, "loss": 4.2568, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476906869466831e-05, "loss": 4.2535, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476069912596152e-05, "loss": 4.2456, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.4752313178451e-05, "loss": 4.2537, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474392723094048e-05, "loss": 4.2593, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473554128342996e-05, "loss": 4.2594, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472715533591944e-05, "loss": 4.2595, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471876938840892e-05, "loss": 4.2589, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.47103834408984e-05, "loss": 4.2547, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470199749338788e-05, "loss": 4.2597, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4693611545877354e-05, "loss": 4.2522, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685225598366834e-05, "loss": 4.2539, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4676839650856314e-05, "loss": 4.2457, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668453703345794e-05, "loss": 4.2532, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466006775583528e-05, "loss": 4.2521, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465168180832476e-05, "loss": 4.257, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464329586081424e-05, "loss": 4.2488, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463490991330372e-05, "loss": 4.2506, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462654034459693e-05, "loss": 4.259, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461815439708641e-05, "loss": 4.2495, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460976844957589e-05, "loss": 4.2516, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460138250206537e-05, "loss": 4.2447, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459301293335858e-05, "loss": 4.226, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458464336465179e-05, "loss": 4.254, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457625741714127e-05, "loss": 4.2456, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456787146963075e-05, "loss": 4.2436, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.4559485522120234e-05, "loss": 4.229, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551099574609714e-05, "loss": 4.237, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542713627099194e-05, "loss": 4.2301, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534344058392403e-05, "loss": 4.2519, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4525958110881883e-05, "loss": 4.2316, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451757216337136e-05, "loss": 4.2357, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450918621586084e-05, "loss": 4.2476, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450081664715405e-05, "loss": 4.2307, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449243069964353e-05, "loss": 4.2354, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448404475213301e-05, "loss": 4.2399, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447565880462249e-05, "loss": 4.2178, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446727285711197e-05, "loss": 4.2367, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445890328840519e-05, "loss": 4.2352, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445051734089467e-05, "loss": 4.2425, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444213139338415e-05, "loss": 4.2243, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443374544587363e-05, "loss": 4.2312, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442535949836311e-05, "loss": 4.2204, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441698992965632e-05, "loss": 4.247, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.44086039821458e-05, "loss": 4.2391, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440021803463528e-05, "loss": 4.2371, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439183208712476e-05, "loss": 4.2521, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438344613961424e-05, "loss": 4.2464, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437506019210372e-05, "loss": 4.2564, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436667424459319e-05, "loss": 4.2295, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.4358304675886406e-05, "loss": 4.2344, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4349918728375886e-05, "loss": 4.2394, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341532780865366e-05, "loss": 4.2254, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333146833354846e-05, "loss": 4.2403, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324760885844326e-05, "loss": 4.2292, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316374938333806e-05, "loss": 4.2406, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4307988990823286e-05, "loss": 4.2368, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4299619422116495e-05, "loss": 4.221, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291233474605975e-05, "loss": 4.2343, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4282847527095455e-05, "loss": 4.2229, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274461579584935e-05, "loss": 4.2381, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.4266092010878144e-05, "loss": 4.2307, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257706063367624e-05, "loss": 4.2266, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249320115857104e-05, "loss": 4.2357, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424093416834659e-05, "loss": 4.2286, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423254822083607e-05, "loss": 4.2202, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422416227332555e-05, "loss": 4.2252, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421577632581503e-05, "loss": 4.2358, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420739037830451e-05, "loss": 4.2314, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419902080959772e-05, "loss": 4.229, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.41906348620872e-05, "loss": 4.2141, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418226529338041e-05, "loss": 4.2295, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417387934586989e-05, "loss": 4.2189, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416549339835937e-05, "loss": 4.2358, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415710745084885e-05, "loss": 4.231, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414872150333833e-05, "loss": 4.226, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414033555582781e-05, "loss": 4.2206, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413194960831729e-05, "loss": 4.2344, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123563660806775e-05, "loss": 4.2034, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115194092099984e-05, "loss": 4.2201, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410682452339319e-05, "loss": 4.2115, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409843857588267e-05, "loss": 4.2258, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409005262837215e-05, "loss": 4.2107, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408166668086163e-05, "loss": 4.218, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407328073335111e-05, "loss": 4.2145, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406491116464432e-05, "loss": 4.2111, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.40565252171338e-05, "loss": 4.2165, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404813926962328e-05, "loss": 4.2131, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403975332211276e-05, "loss": 4.2251, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403136737460224e-05, "loss": 4.2227, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402298142709173e-05, "loss": 4.2212, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.40145954795812e-05, "loss": 4.2145, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400620953207068e-05, "loss": 4.2256, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399782358456016e-05, "loss": 4.2203, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398945401585338e-05, "loss": 4.2138, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398106806834285e-05, "loss": 4.2313, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397268212083233e-05, "loss": 4.2117, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.3964312552125546e-05, "loss": 4.2183, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3955926604615026e-05, "loss": 4.2064, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.39475406571045e-05, "loss": 4.2176, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393915470959398e-05, "loss": 4.2031, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.3930768762083466e-05, "loss": 4.2091, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.3922399193376675e-05, "loss": 4.2061, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3914013245866155e-05, "loss": 4.2211, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905627298355635e-05, "loss": 4.214, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897241350845115e-05, "loss": 4.2166, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3888855403334595e-05, "loss": 4.2062, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.3880485834627804e-05, "loss": 4.2186, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872099887117284e-05, "loss": 4.225, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3863713939606764e-05, "loss": 4.2154, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.3855327992096244e-05, "loss": 4.2124, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3846942044585724e-05, "loss": 4.2207, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383858885468267e-05, "loss": 4.2107, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383020290717215e-05, "loss": 4.22, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382181695966163e-05, "loss": 4.2037, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381343101215111e-05, "loss": 4.2146, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380504506464059e-05, "loss": 4.207, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379665911713007e-05, "loss": 4.2101, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378827316961955e-05, "loss": 4.2107, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.377988722210903e-05, "loss": 4.2056, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377151765340224e-05, "loss": 4.2089, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376313170589172e-05, "loss": 4.2033, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.37547457583812e-05, "loss": 4.2156, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.198291778564453, "eval_runtime": 291.6012, "eval_samples_per_second": 1308.606, "eval_steps_per_second": 40.895, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374635981087068e-05, "loss": 4.2059, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373799024216389e-05, "loss": 4.1931, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.3729604294653374e-05, "loss": 4.2155, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372123472594658e-05, "loss": 4.2004, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371284877843606e-05, "loss": 4.217, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370446283092554e-05, "loss": 4.2042, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369607688341502e-05, "loss": 4.1907, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.36876909359045e-05, "loss": 4.1958, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367932136719771e-05, "loss": 4.1988, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367093541968719e-05, "loss": 4.2109, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366254947217667e-05, "loss": 4.202, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365416352466615e-05, "loss": 4.2041, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364577757715563e-05, "loss": 4.1944, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363739162964511e-05, "loss": 4.1952, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362900568213459e-05, "loss": 4.2032, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362061973462407e-05, "loss": 4.1891, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361223378711355e-05, "loss": 4.1944, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360384783960304e-05, "loss": 4.2001, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359547827089625e-05, "loss": 4.2013, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358709232338573e-05, "loss": 4.2083, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357870637587521e-05, "loss": 4.2024, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357032042836469e-05, "loss": 4.202, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356193448085416e-05, "loss": 4.199, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355354853334364e-05, "loss": 4.2049, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.3545178964636856e-05, "loss": 4.1892, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.3536793017126336e-05, "loss": 4.2047, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352840706961581e-05, "loss": 4.1895, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352002112210529e-05, "loss": 4.1912, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.3511635174594776e-05, "loss": 4.1886, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.3503249227084256e-05, "loss": 4.1925, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.3494863279573736e-05, "loss": 4.1972, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486477332063216e-05, "loss": 4.1968, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478107763356425e-05, "loss": 4.2018, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469721815845905e-05, "loss": 4.2043, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.3461335868335385e-05, "loss": 4.1916, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3452966299628594e-05, "loss": 4.201, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444580352118074e-05, "loss": 4.1932, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436194404607554e-05, "loss": 4.1916, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3427808457097034e-05, "loss": 4.1872, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419422509586514e-05, "loss": 4.1886, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411036562075993e-05, "loss": 4.1963, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340266699336921e-05, "loss": 4.2006, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.339428104585869e-05, "loss": 4.1873, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338589509834817e-05, "loss": 4.1927, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337750915083765e-05, "loss": 4.1992, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336913958213086e-05, "loss": 4.1934, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336075363462034e-05, "loss": 4.1941, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335236768710982e-05, "loss": 4.1856, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.33439817395993e-05, "loss": 4.1646, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333559579208878e-05, "loss": 4.1987, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332720984457826e-05, "loss": 4.1864, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331884027587147e-05, "loss": 4.1878, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331047070716468e-05, "loss": 4.1776, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330208475965416e-05, "loss": 4.173, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329369881214364e-05, "loss": 4.1759, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328531286463312e-05, "loss": 4.1864, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.32769269171226e-05, "loss": 4.1773, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326854096961208e-05, "loss": 4.1817, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326015502210156e-05, "loss": 4.1895, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325176907459104e-05, "loss": 4.1746, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324338312708052e-05, "loss": 4.1763, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323501355837373e-05, "loss": 4.1853, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322662761086321e-05, "loss": 4.1657, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321824166335269e-05, "loss": 4.1761, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.3209855715842165e-05, "loss": 4.1797, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320146976833165e-05, "loss": 4.1888, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319308382082113e-05, "loss": 4.1652, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318469787331061e-05, "loss": 4.1774, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317632830460382e-05, "loss": 4.1644, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.31679423570933e-05, "loss": 4.1894, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315955640958278e-05, "loss": 4.1844, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315117046207226e-05, "loss": 4.1812, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314278451456174e-05, "loss": 4.1931, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313439856705122e-05, "loss": 4.1935, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.31260126195407e-05, "loss": 4.2015, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311762667203018e-05, "loss": 4.1767, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310924072451966e-05, "loss": 4.1806, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310087115581287e-05, "loss": 4.1819, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309248520830235e-05, "loss": 4.1706, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.3084115639595565e-05, "loss": 4.1877, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3075729692085045e-05, "loss": 4.176, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067343744574525e-05, "loss": 4.1859, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3058957797064005e-05, "loss": 4.1814, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050571849553485e-05, "loss": 4.1668, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042185902042965e-05, "loss": 4.1788, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3033799954532445e-05, "loss": 4.1689, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025414007021925e-05, "loss": 4.1826, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3017044438315134e-05, "loss": 4.1796, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008658490804614e-05, "loss": 4.1672, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000272543294094e-05, "loss": 4.1868, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2991886595783574e-05, "loss": 4.1733, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298351702707678e-05, "loss": 4.1678, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297513107956627e-05, "loss": 4.1724, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296676151085948e-05, "loss": 4.1828, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295837556334896e-05, "loss": 4.1759, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.294998961583844e-05, "loss": 4.1798, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294160366832792e-05, "loss": 4.1618, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293323409962113e-05, "loss": 4.1757, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292484815211061e-05, "loss": 4.1693, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291646220460009e-05, "loss": 4.1807, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290807625708957e-05, "loss": 4.1805, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289970668838278e-05, "loss": 4.1683, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289132074087226e-05, "loss": 4.1749, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.2882934793361737e-05, "loss": 4.1797, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287454884585122e-05, "loss": 4.1561, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.28661628983407e-05, "loss": 4.1655, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285777695083018e-05, "loss": 4.1592, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.2849391003319656e-05, "loss": 4.1716, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284102143461287e-05, "loss": 4.1622, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283263548710235e-05, "loss": 4.1681, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824249539591825e-05, "loss": 4.1601, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2815863592081305e-05, "loss": 4.161, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807477644570785e-05, "loss": 4.1677, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2799108075864e-05, "loss": 4.1595, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2790722128353474e-05, "loss": 4.174, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278233618084296e-05, "loss": 4.1695, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277395023333244e-05, "loss": 4.1719, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276556428582192e-05, "loss": 4.1637, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275719471711513e-05, "loss": 4.1729, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274880876960461e-05, "loss": 4.1751, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274042282209409e-05, "loss": 4.1625, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273203687458357e-05, "loss": 4.1825, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272365092707305e-05, "loss": 4.1569, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271528135836626e-05, "loss": 4.169, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270689541085574e-05, "loss": 4.1529, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.269850946334522e-05, "loss": 4.1695, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.26901235158347e-05, "loss": 4.1512, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268173756832418e-05, "loss": 4.1627, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.2673367999617395e-05, "loss": 4.1515, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.2664982052106875e-05, "loss": 4.1743, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.2656596104596355e-05, "loss": 4.1615, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.2648210157085835e-05, "loss": 4.1674, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.2639840588379044e-05, "loss": 4.1557, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.2631454640868524e-05, "loss": 4.1703, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623068693358004e-05, "loss": 4.1727, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2614682745847484e-05, "loss": 4.1665, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.2606296798336964e-05, "loss": 4.1661, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.2597910850826443e-05, "loss": 4.167, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258954128211965e-05, "loss": 4.162, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258115533460913e-05, "loss": 4.1723, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257276938709861e-05, "loss": 4.1559, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256438343958809e-05, "loss": 4.1645, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255599749207758e-05, "loss": 4.1605, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254761154456706e-05, "loss": 4.1617, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253924197586027e-05, "loss": 4.163, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253085602834975e-05, "loss": 4.1525, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252247008083923e-05, "loss": 4.1679, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251408413332871e-05, "loss": 4.1498, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250569818581819e-05, "loss": 4.1699, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.158207416534424, "eval_runtime": 295.9808, "eval_samples_per_second": 1289.243, "eval_steps_per_second": 40.29, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249731223830766e-05, "loss": 4.1601, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248892629079714e-05, "loss": 4.1437, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248054034328662e-05, "loss": 4.164, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.24721543957761e-05, "loss": 4.1579, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.246376844826558e-05, "loss": 4.1667, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245538250075506e-05, "loss": 4.1571, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244699655324455e-05, "loss": 4.144, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243861060573403e-05, "loss": 4.1459, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243022465822351e-05, "loss": 4.1544, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242183871071299e-05, "loss": 4.1616, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241345276320247e-05, "loss": 4.155, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240508319449568e-05, "loss": 4.154, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239669724698516e-05, "loss": 4.1537, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.2388311299474637e-05, "loss": 4.1486, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2379925351964117e-05, "loss": 4.1524, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.2371539404453596e-05, "loss": 4.1398, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.2363153456943076e-05, "loss": 4.1502, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235476750943255e-05, "loss": 4.1516, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234638156192203e-05, "loss": 4.1521, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.2337995614411516e-05, "loss": 4.1613, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2329609666900996e-05, "loss": 4.1603, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321223719390476e-05, "loss": 4.151, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2312837771879956e-05, "loss": 4.1507, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304451824369436e-05, "loss": 4.1619, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.2296065876858916e-05, "loss": 4.1391, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.2287679929348396e-05, "loss": 4.1615, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.2279310360641605e-05, "loss": 4.1443, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.2270924413131085e-05, "loss": 4.1438, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.2262538465620565e-05, "loss": 4.1417, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254152518110045e-05, "loss": 4.1495, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2245766570599525e-05, "loss": 4.1495, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237380623089005e-05, "loss": 4.1528, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.2228994675578485e-05, "loss": 4.1514, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.22206251068717e-05, "loss": 4.1579, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221223915936118e-05, "loss": 4.1443, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220385321185066e-05, "loss": 4.1571, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219546726434014e-05, "loss": 4.1532, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218708131682962e-05, "loss": 4.1423, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.2178695369319094e-05, "loss": 4.1426, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217032580061231e-05, "loss": 4.1468, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216193985310179e-05, "loss": 4.1459, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215355390559126e-05, "loss": 4.1566, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214516795808074e-05, "loss": 4.1428, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.213678201057022e-05, "loss": 4.1448, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.21283960630597e-05, "loss": 4.1573, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.212001011554918e-05, "loss": 4.1445, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211162416803866e-05, "loss": 4.1527, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210325459933188e-05, "loss": 4.1417, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209486865182136e-05, "loss": 4.1117, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208648270431084e-05, "loss": 4.1595, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207811313560405e-05, "loss": 4.1415, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.206972718809353e-05, "loss": 4.1448, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206134124058301e-05, "loss": 4.1338, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.205295529307249e-05, "loss": 4.1239, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2044585724365696e-05, "loss": 4.1345, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036199776855176e-05, "loss": 4.1398, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.2027813829344656e-05, "loss": 4.1361, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.2019427881834136e-05, "loss": 4.1347, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.201105831312735e-05, "loss": 4.1496, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200267236561683e-05, "loss": 4.1292, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.199428641810631e-05, "loss": 4.1296, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.198591684939952e-05, "loss": 4.1444, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.1977530901889e-05, "loss": 4.1174, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.196914495437848e-05, "loss": 4.1318, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.196075900686796e-05, "loss": 4.1343, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195237305935744e-05, "loss": 4.1475, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194398711184692e-05, "loss": 4.1209, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.19356011643364e-05, "loss": 4.1372, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192721521682588e-05, "loss": 4.117, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.191882926931536e-05, "loss": 4.147, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191044332180484e-05, "loss": 4.1438, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190205737429432e-05, "loss": 4.1377, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.18936714267838e-05, "loss": 4.1448, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.1885301858077017e-05, "loss": 4.149, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.1876915910566496e-05, "loss": 4.161, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.1868546341859706e-05, "loss": 4.135, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.1860160394349186e-05, "loss": 4.1393, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.1851774446838665e-05, "loss": 4.141, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.1843388499328145e-05, "loss": 4.1244, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.1835002551817625e-05, "loss": 4.1406, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.18266166043071e-05, "loss": 4.1351, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.1818247035600314e-05, "loss": 4.1408, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.1809861088089794e-05, "loss": 4.1477, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.1801475140579274e-05, "loss": 4.1254, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.1793089193068754e-05, "loss": 4.1306, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.1784703245558234e-05, "loss": 4.1287, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.1776317298047714e-05, "loss": 4.1412, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1767931350537194e-05, "loss": 4.1346, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.17595617818304e-05, "loss": 4.131, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175117583431988e-05, "loss": 4.133, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174278988680936e-05, "loss": 4.1386, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173440393929884e-05, "loss": 4.1285, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172601799178832e-05, "loss": 4.1282, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171764842308153e-05, "loss": 4.1477, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170926247557101e-05, "loss": 4.1335, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170087652806049e-05, "loss": 4.1349, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169249058054998e-05, "loss": 4.1205, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.168410463303946e-05, "loss": 4.1331, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167571868552894e-05, "loss": 4.1274, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166733273801842e-05, "loss": 4.1385, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.16589467905079e-05, "loss": 4.1373, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165057722180111e-05, "loss": 4.134, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.164219127429059e-05, "loss": 4.1337, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163380532678007e-05, "loss": 4.1353, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162541937926955e-05, "loss": 4.1154, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.161703343175903e-05, "loss": 4.1265, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160866386305224e-05, "loss": 4.1131, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160027791554172e-05, "loss": 4.1329, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.1591891968031197e-05, "loss": 4.1217, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.1583506020520677e-05, "loss": 4.125, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575120073010156e-05, "loss": 4.1185, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156673412549964e-05, "loss": 4.122, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155836455679285e-05, "loss": 4.127, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.154997860928233e-05, "loss": 4.1186, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154159266177181e-05, "loss": 4.129, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.1533206714261285e-05, "loss": 4.1346, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.1524820766750765e-05, "loss": 4.1266, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.1516434819240245e-05, "loss": 4.1303, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.1508048871729725e-05, "loss": 4.1284, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.1499679303022934e-05, "loss": 4.1332, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.1491293355512414e-05, "loss": 4.1265, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.1482907408001894e-05, "loss": 4.1363, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147452146049138e-05, "loss": 4.1176, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146613551298086e-05, "loss": 4.1306, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145774956547034e-05, "loss": 4.1176, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144937999676355e-05, "loss": 4.1239, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144099404925303e-05, "loss": 4.1171, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143260810174251e-05, "loss": 4.1203, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.142422215423199e-05, "loss": 4.1135, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141583620672147e-05, "loss": 4.131, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140745025921095e-05, "loss": 4.1235, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139908069050416e-05, "loss": 4.1276, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139069474299364e-05, "loss": 4.1168, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138230879548312e-05, "loss": 4.1329, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.13739228479726e-05, "loss": 4.1315, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136553690046208e-05, "loss": 4.1297, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357150952951565e-05, "loss": 4.1274, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1348765005441045e-05, "loss": 4.1238, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340379057930525e-05, "loss": 4.1255, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.1331993110420005e-05, "loss": 4.1356, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132360716290948e-05, "loss": 4.1136, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315237594202694e-05, "loss": 4.1241, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1306851646692174e-05, "loss": 4.1279, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.129846569918165e-05, "loss": 4.1244, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.129009613047486e-05, "loss": 4.1157, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128171018296434e-05, "loss": 4.1157, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.127332423545382e-05, "loss": 4.129, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.12649382879433e-05, "loss": 4.1155, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125656871923652e-05, "loss": 4.1302, "step": 534016 }, { "epoch": 0.03, "eval_loss": 4.127338886260986, "eval_runtime": 294.1908, "eval_samples_per_second": 1297.087, "eval_steps_per_second": 40.535, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248182771726e-05, "loss": 4.1166, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.123979682421548e-05, "loss": 4.106, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.123141087670495e-05, "loss": 4.1276, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122304130799817e-05, "loss": 4.1118, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121465536048765e-05, "loss": 4.1253, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120626941297712e-05, "loss": 4.1226, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.11978834654666e-05, "loss": 4.1099, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.118949751795608e-05, "loss": 4.1092, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118111157044556e-05, "loss": 4.1181, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117272562293504e-05, "loss": 4.1212, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116433967542452e-05, "loss": 4.1171, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115597010671774e-05, "loss": 4.1141, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114760053801095e-05, "loss": 4.1151, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.1139214590500426e-05, "loss": 4.1115, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.1130828642989906e-05, "loss": 4.1154, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.1122442695479386e-05, "loss": 4.1049, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.1114056747968866e-05, "loss": 4.1106, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.1105670800458346e-05, "loss": 4.1143, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.1097284852947826e-05, "loss": 4.1163, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.1088898905437306e-05, "loss": 4.1188, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.1080512957926786e-05, "loss": 4.1271, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.1072127010416266e-05, "loss": 4.1164, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.1063741062905746e-05, "loss": 4.1141, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.1055355115395225e-05, "loss": 4.119, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104700192549217e-05, "loss": 4.1082, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103863235678538e-05, "loss": 4.1214, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103024640927486e-05, "loss": 4.1071, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102186046176434e-05, "loss": 4.1108, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101347451425382e-05, "loss": 4.1075, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.10050885667433e-05, "loss": 4.1087, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.099670261923278e-05, "loss": 4.1101, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.098831667172226e-05, "loss": 4.1157, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.097993072421174e-05, "loss": 4.1147, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.097154477670122e-05, "loss": 4.1201, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.096317520799443e-05, "loss": 4.1064, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.095478926048391e-05, "loss": 4.1225, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0946419691777124e-05, "loss": 4.1157, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938033744266604e-05, "loss": 4.1031, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0929647796756084e-05, "loss": 4.1093, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.0921261849245564e-05, "loss": 4.1092, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0912875901735044e-05, "loss": 4.1087, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0904489954224524e-05, "loss": 4.117, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.0896104006714004e-05, "loss": 4.1067, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.0887718059203484e-05, "loss": 4.1087, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087933211169296e-05, "loss": 4.1202, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087094616418244e-05, "loss": 4.1109, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086257659547565e-05, "loss": 4.1132, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085419064796513e-05, "loss": 4.1103, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084580470045461e-05, "loss": 4.0738, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083741875294409e-05, "loss": 4.1253, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082904918423731e-05, "loss": 4.103, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082066323672678e-05, "loss": 4.1135, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081227728921626e-05, "loss": 4.0949, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080389134170574e-05, "loss": 4.0909, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079552177299896e-05, "loss": 4.0987, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078713582548843e-05, "loss": 4.1018, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077874987797791e-05, "loss": 4.1034, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077036393046739e-05, "loss": 4.0947, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076197798295687e-05, "loss": 4.1164, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075360841425008e-05, "loss": 4.0957, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.0745222466739566e-05, "loss": 4.094, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0736836519229046e-05, "loss": 4.1097, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0728450571718526e-05, "loss": 4.083, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.0720064624208006e-05, "loss": 4.0927, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.0711678676697486e-05, "loss": 4.1007, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070332548679443e-05, "loss": 4.112, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.0694939539283904e-05, "loss": 4.0858, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.0686553591773384e-05, "loss": 4.1029, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.0678167644262864e-05, "loss": 4.0832, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.0669781696752344e-05, "loss": 4.111, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.0661395749241824e-05, "loss": 4.1065, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.0653009801731304e-05, "loss": 4.1045, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.0644623854220784e-05, "loss": 4.1068, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.0636237906710264e-05, "loss": 4.1147, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062785195919975e-05, "loss": 4.1253, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.061948239049296e-05, "loss": 4.1009, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061109644298244e-05, "loss": 4.1018, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.060272687427565e-05, "loss": 4.1086, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.059434092676513e-05, "loss": 4.092, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.058595497925461e-05, "loss": 4.103, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.057756903174409e-05, "loss": 4.1043, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.056918308423357e-05, "loss": 4.1094, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056079713672305e-05, "loss": 4.1104, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.055241118921253e-05, "loss": 4.0945, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.054404162050574e-05, "loss": 4.0924, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053565567299522e-05, "loss": 4.0959, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.05272697254847e-05, "loss": 4.1076, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.0518883777974184e-05, "loss": 4.1012, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.0510497830463664e-05, "loss": 4.0957, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.0502111882953144e-05, "loss": 4.0961, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049372593544262e-05, "loss": 4.1046, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.04853399879321e-05, "loss": 4.0956, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.0476970419225313e-05, "loss": 4.0935, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046858447171479e-05, "loss": 4.1126, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.0460214903008e-05, "loss": 4.0989, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045182895549748e-05, "loss": 4.1008, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044344300798696e-05, "loss": 4.0915, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043507343928017e-05, "loss": 4.094, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042668749176965e-05, "loss": 4.0923, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041830154425914e-05, "loss": 4.107, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.040991559674862e-05, "loss": 4.1006, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040152964923809e-05, "loss": 4.1022, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039314370172757e-05, "loss": 4.1004, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038475775421705e-05, "loss": 4.0996, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037637180670653e-05, "loss": 4.0865, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036798585919601e-05, "loss": 4.0893, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.035961629048922e-05, "loss": 4.0826, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.03512303429787e-05, "loss": 4.0998, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034284439546818e-05, "loss": 4.0867, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033445844795766e-05, "loss": 4.0901, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032607250044714e-05, "loss": 4.083, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031768655293662e-05, "loss": 4.0933, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030930060542611e-05, "loss": 4.0948, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030091465791559e-05, "loss": 4.0832, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.0292561468012525e-05, "loss": 4.1011, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284175520502005e-05, "loss": 4.0982, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.0275805951795214e-05, "loss": 4.0916, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.0267420004284694e-05, "loss": 4.0993, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.0259034056774174e-05, "loss": 4.0943, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.0250648109263654e-05, "loss": 4.0951, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.0242262161753134e-05, "loss": 4.0986, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.0233876214242614e-05, "loss": 4.099, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0225490266732094e-05, "loss": 4.0872, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217104319221574e-05, "loss": 4.098, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.020871837171106e-05, "loss": 4.089, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.020033242420054e-05, "loss": 4.0902, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019194647669002e-05, "loss": 4.0807, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.01835605291795e-05, "loss": 4.0877, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017519096047271e-05, "loss": 4.0827, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016680501296219e-05, "loss": 4.0965, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015841906545167e-05, "loss": 4.0917, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015003311794115e-05, "loss": 4.097, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014164717043063e-05, "loss": 4.0801, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013327760172384e-05, "loss": 4.1048, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012489165421332e-05, "loss": 4.0943, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.01165057067028e-05, "loss": 4.0984, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010811975919228e-05, "loss": 4.096, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.009973381168176e-05, "loss": 4.0912, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.0091364242974974e-05, "loss": 4.0907, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008299467426818e-05, "loss": 4.1018, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007460872675766e-05, "loss": 4.0838, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006622277924714e-05, "loss": 4.0937, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005783683173662e-05, "loss": 4.0935, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.00494508842261e-05, "loss": 4.0902, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.0041064936715576e-05, "loss": 4.0843, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.0032678989205056e-05, "loss": 4.0829, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002430942049827e-05, "loss": 4.0963, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001592347298775e-05, "loss": 4.0866, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000753752547723e-05, "loss": 4.0971, "step": 610304 }, { "epoch": 1.03, "eval_loss": 4.102852821350098, "eval_runtime": 293.4121, "eval_samples_per_second": 1300.529, "eval_steps_per_second": 40.642, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.999915157796671e-05, "loss": 4.0817, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999076563045619e-05, "loss": 4.08, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.998237968294567e-05, "loss": 4.087, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997399373543515e-05, "loss": 4.0861, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996560778792463e-05, "loss": 4.0958, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.995722184041411e-05, "loss": 4.0886, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994883589290359e-05, "loss": 4.0786, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994044994539307e-05, "loss": 4.0792, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993206399788255e-05, "loss": 4.0817, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992367805037203e-05, "loss": 4.0943, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991529210286151e-05, "loss": 4.0826, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.9906906155350984e-05, "loss": 4.0818, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.98985365866442e-05, "loss": 4.092, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.989015063913368e-05, "loss": 4.0723, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.988176469162316e-05, "loss": 4.0803, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.987337874411264e-05, "loss": 4.077, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.986499279660212e-05, "loss": 4.0787, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.98566068490916e-05, "loss": 4.0834, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.984822090158108e-05, "loss": 4.0847, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.983983495407056e-05, "loss": 4.0842, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.983144900656004e-05, "loss": 4.0981, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.982306305904952e-05, "loss": 4.0838, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9814677111539e-05, "loss": 4.0862, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.980629116402848e-05, "loss": 4.0837, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979792159532169e-05, "loss": 4.0805, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.978953564781117e-05, "loss": 4.0899, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978114970030065e-05, "loss": 4.0784, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.9772780131593865e-05, "loss": 4.0813, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.9764394184083345e-05, "loss": 4.0717, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.9756008236572825e-05, "loss": 4.0784, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.9747638667866034e-05, "loss": 4.0764, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.9739252720355514e-05, "loss": 4.0824, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.9730866772844994e-05, "loss": 4.089, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.9722480825334474e-05, "loss": 4.0894, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.9714094877823954e-05, "loss": 4.0787, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.9705708930313434e-05, "loss": 4.0841, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.9697322982802913e-05, "loss": 4.0879, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.9688937035292393e-05, "loss": 4.0761, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.9680551087781873e-05, "loss": 4.0762, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967216514027135e-05, "loss": 4.0783, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966377919276083e-05, "loss": 4.0809, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965540962405405e-05, "loss": 4.0805, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964702367654353e-05, "loss": 4.0839, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.9638637729033e-05, "loss": 4.0817, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.963025178152248e-05, "loss": 4.086, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962186583401196e-05, "loss": 4.0811, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961347988650144e-05, "loss": 4.0802, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960509393899092e-05, "loss": 4.0789, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.95967079914804e-05, "loss": 4.0436, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958833842277361e-05, "loss": 4.0917, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.957995247526309e-05, "loss": 4.0725, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957156652775257e-05, "loss": 4.0841, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956318058024205e-05, "loss": 4.0682, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955481101153527e-05, "loss": 4.0623, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954642506402475e-05, "loss": 4.0634, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.953803911651423e-05, "loss": 4.072, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.952965316900371e-05, "loss": 4.0735, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9521283600296916e-05, "loss": 4.068, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.9512897652786396e-05, "loss": 4.0838, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.9504511705275876e-05, "loss": 4.0691, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.9496125757765356e-05, "loss": 4.0645, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.9487756189058565e-05, "loss": 4.0783, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.9479370241548045e-05, "loss": 4.0568, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.947100067284126e-05, "loss": 4.0612, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946261472533074e-05, "loss": 4.073, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945422877782022e-05, "loss": 4.0804, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.94458428303097e-05, "loss": 4.0603, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943745688279918e-05, "loss": 4.0695, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.942907093528866e-05, "loss": 4.0544, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942068498777814e-05, "loss": 4.0799, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.941229904026762e-05, "loss": 4.0795, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.94039130927571e-05, "loss": 4.0727, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939552714524658e-05, "loss": 4.0788, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938714119773606e-05, "loss": 4.0838, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.9378755250225533e-05, "loss": 4.0977, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.937040206032248e-05, "loss": 4.0718, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936201611281196e-05, "loss": 4.0727, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935363016530144e-05, "loss": 4.0735, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.9345244217790925e-05, "loss": 4.0701, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.9336858270280405e-05, "loss": 4.0704, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.9328472322769885e-05, "loss": 4.0763, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.9320086375259365e-05, "loss": 4.0789, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931170042774884e-05, "loss": 4.083, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930331448023832e-05, "loss": 4.0629, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9294944911531534e-05, "loss": 4.0637, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.928655896402101e-05, "loss": 4.066, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.927817301651049e-05, "loss": 4.0807, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.92698034478037e-05, "loss": 4.0744, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926141750029318e-05, "loss": 4.0634, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925303155278266e-05, "loss": 4.0684, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924464560527214e-05, "loss": 4.0748, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.923627603656536e-05, "loss": 4.0689, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922789008905484e-05, "loss": 4.064, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.921950414154431e-05, "loss": 4.0819, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921111819403379e-05, "loss": 4.0734, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920273224652327e-05, "loss": 4.0704, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919434629901275e-05, "loss": 4.0646, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918596035150223e-05, "loss": 4.0655, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917757440399171e-05, "loss": 4.0657, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916920483528492e-05, "loss": 4.0785, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.91608188877744e-05, "loss": 4.0746, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.915243294026388e-05, "loss": 4.0697, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.914404699275336e-05, "loss": 4.0756, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.913566104524285e-05, "loss": 4.0667, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9127291476536056e-05, "loss": 4.0658, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.9118905529025536e-05, "loss": 4.0579, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.9110535960318745e-05, "loss": 4.0526, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.9102150012808225e-05, "loss": 4.0742, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.9093764065297705e-05, "loss": 4.0612, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.9085394496590914e-05, "loss": 4.0585, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.9077008549080394e-05, "loss": 4.0562, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.9068622601569874e-05, "loss": 4.0591, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.9060236654059354e-05, "loss": 4.0683, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905186708535257e-05, "loss": 4.059, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904348113784205e-05, "loss": 4.071, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.903509519033153e-05, "loss": 4.069, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.902670924282101e-05, "loss": 4.0693, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.901832329531049e-05, "loss": 4.0696, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.900993734779997e-05, "loss": 4.0662, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900155140028945e-05, "loss": 4.0684, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.899316545277893e-05, "loss": 4.0722, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898479588407214e-05, "loss": 4.0707, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897640993656162e-05, "loss": 4.0624, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.89680239890511e-05, "loss": 4.0697, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.895963804154058e-05, "loss": 4.0619, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.895125209403006e-05, "loss": 4.0627, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.894286614651954e-05, "loss": 4.0525, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893448019900902e-05, "loss": 4.0615, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.8926110630302235e-05, "loss": 4.0534, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.8917724682791715e-05, "loss": 4.0698, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.8909338735281195e-05, "loss": 4.0602, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.8900952787770674e-05, "loss": 4.0745, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889256684026015e-05, "loss": 4.0523, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.888418089274963e-05, "loss": 4.0746, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.8875811324042843e-05, "loss": 4.0683, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.886742537653232e-05, "loss": 4.0696, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859039429021797e-05, "loss": 4.0693, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8850653481511277e-05, "loss": 4.0648, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.8842267534000757e-05, "loss": 4.0675, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.883389796529397e-05, "loss": 4.076, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882551201778345e-05, "loss": 4.0566, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881712607027293e-05, "loss": 4.0671, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880874012276241e-05, "loss": 4.0646, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880035417525189e-05, "loss": 4.0633, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879196822774137e-05, "loss": 4.0623, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878358228023085e-05, "loss": 4.0566, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877519633272033e-05, "loss": 4.0695, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876682676401354e-05, "loss": 4.0628, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875845719530675e-05, "loss": 4.0699, "step": 686592 }, { "epoch": 0.03, "eval_loss": 4.083948612213135, "eval_runtime": 293.0728, "eval_samples_per_second": 1302.035, "eval_steps_per_second": 40.69, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875007124779623e-05, "loss": 4.0527, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874168530028571e-05, "loss": 4.056, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873329935277519e-05, "loss": 4.0587, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872491340526467e-05, "loss": 4.0608, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871652745775416e-05, "loss": 4.0732, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870814151024364e-05, "loss": 4.0619, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.869975556273312e-05, "loss": 4.0551, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.8691385994026326e-05, "loss": 4.0534, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.8683000046515806e-05, "loss": 4.0526, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.8674614099005286e-05, "loss": 4.0674, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.8666228151494766e-05, "loss": 4.057, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.8657842203984246e-05, "loss": 4.0559, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.8649472635277455e-05, "loss": 4.0672, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.8641086687766935e-05, "loss": 4.049, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.8632700740256415e-05, "loss": 4.0524, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.8624314792745895e-05, "loss": 4.0492, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861594522403911e-05, "loss": 4.0553, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860755927652859e-05, "loss": 4.0514, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.859917332901807e-05, "loss": 4.0609, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859078738150755e-05, "loss": 4.06, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858240143399703e-05, "loss": 4.0719, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.8574015486486503e-05, "loss": 4.058, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.8565629538975983e-05, "loss": 4.0605, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.8557243591465463e-05, "loss": 4.056, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.854887402275868e-05, "loss": 4.0573, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.854050445405189e-05, "loss": 4.062, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.853211850654137e-05, "loss": 4.0498, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.852373255903085e-05, "loss": 4.0592, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.851534661152033e-05, "loss": 4.0471, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.850696066400981e-05, "loss": 4.0527, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.849857471649929e-05, "loss": 4.0515, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849018876898877e-05, "loss": 4.0557, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.848181920028198e-05, "loss": 4.0632, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.847343325277146e-05, "loss": 4.0636, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846504730526094e-05, "loss": 4.0551, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845666135775042e-05, "loss": 4.0545, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.84482754102399e-05, "loss": 4.0674, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.8439905841533106e-05, "loss": 4.051, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843153627282632e-05, "loss": 4.0506, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.84231503253158e-05, "loss": 4.0535, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841476437780528e-05, "loss": 4.0568, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840637843029476e-05, "loss": 4.0548, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839799248278424e-05, "loss": 4.0547, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.838960653527372e-05, "loss": 4.0577, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.83812205877632e-05, "loss": 4.057, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837283464025268e-05, "loss": 4.057, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836444869274216e-05, "loss": 4.0568, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835606274523164e-05, "loss": 4.0566, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834767679772112e-05, "loss": 4.0218, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.833930722901433e-05, "loss": 4.0644, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.833092128150381e-05, "loss": 4.0472, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832253533399329e-05, "loss": 4.0603, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831414938648277e-05, "loss": 4.0417, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.830576343897225e-05, "loss": 4.0373, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.8297393870265466e-05, "loss": 4.0372, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.8289007922754946e-05, "loss": 4.0463, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.8280621975244426e-05, "loss": 4.0556, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.8272236027733906e-05, "loss": 4.0389, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.8263850080223386e-05, "loss": 4.0596, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.8255464132712866e-05, "loss": 4.0492, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824707818520234e-05, "loss": 4.0338, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.823869223769182e-05, "loss": 4.0535, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.8230322668985035e-05, "loss": 4.0368, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.8221936721474515e-05, "loss": 4.0348, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821355077396399e-05, "loss": 4.0481, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.820516482645347e-05, "loss": 4.0549, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.819677887894295e-05, "loss": 4.0387, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.8188409310236164e-05, "loss": 4.044, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.8180023362725644e-05, "loss": 4.0322, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.8171637415215124e-05, "loss": 4.0528, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.8163251467704604e-05, "loss": 4.0555, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.8154865520194084e-05, "loss": 4.05, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.814649595148729e-05, "loss": 4.0534, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.813811000397677e-05, "loss": 4.0593, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.812974043526999e-05, "loss": 4.0707, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.812135448775946e-05, "loss": 4.0501, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.811296854024894e-05, "loss": 4.0514, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810458259273842e-05, "loss": 4.0476, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.80961966452279e-05, "loss": 4.048, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808781069771739e-05, "loss": 4.0442, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.807942475020687e-05, "loss": 4.0538, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807103880269635e-05, "loss": 4.052, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.806266923398956e-05, "loss": 4.0633, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.805428328647904e-05, "loss": 4.0375, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804591371777225e-05, "loss": 4.0392, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.8037527770261727e-05, "loss": 4.0446, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.8029158201554936e-05, "loss": 4.0513, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.8020772254044416e-05, "loss": 4.0521, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8012386306533896e-05, "loss": 4.0423, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.8004000359023376e-05, "loss": 4.043, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.7995614411512856e-05, "loss": 4.0526, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.798722846400234e-05, "loss": 4.0454, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797884251649182e-05, "loss": 4.0373, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.79704565689813e-05, "loss": 4.0589, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.796207062147078e-05, "loss": 4.0493, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795368467396026e-05, "loss": 4.0508, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.794531510525347e-05, "loss": 4.0392, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793692915774295e-05, "loss": 4.0422, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792854321023243e-05, "loss": 4.0401, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792015726272191e-05, "loss": 4.0515, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791177131521139e-05, "loss": 4.0554, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790338536770087e-05, "loss": 4.0427, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789501579899408e-05, "loss": 4.0515, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788662985148356e-05, "loss": 4.0439, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.787824390397304e-05, "loss": 4.0472, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.786985795646253e-05, "loss": 4.0341, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.7861488387755736e-05, "loss": 4.0324, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7853102440245216e-05, "loss": 4.044, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.7844716492734696e-05, "loss": 4.0433, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.7836330545224176e-05, "loss": 4.03, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.782794459771365e-05, "loss": 4.0345, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.781955865020313e-05, "loss": 4.0376, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.7811189081496345e-05, "loss": 4.0453, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.7802803133985825e-05, "loss": 4.035, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.77944171864753e-05, "loss": 4.0484, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778603123896478e-05, "loss": 4.0466, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.7777645291454264e-05, "loss": 4.0458, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.7769259343943744e-05, "loss": 4.0404, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.7760873396433224e-05, "loss": 4.0483, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.7752487448922704e-05, "loss": 4.0445, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.7744117880215913e-05, "loss": 4.0502, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.7735731932705393e-05, "loss": 4.0473, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.772734598519487e-05, "loss": 4.039, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771897641648808e-05, "loss": 4.0452, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771059046897756e-05, "loss": 4.0441, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770220452146704e-05, "loss": 4.0359, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769381857395652e-05, "loss": 4.0336, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768544900524973e-05, "loss": 4.0403, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767706305773921e-05, "loss": 4.029, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.76686771102287e-05, "loss": 4.049, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766029116271818e-05, "loss": 4.0355, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765190521520766e-05, "loss": 4.0507, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764351926769714e-05, "loss": 4.0312, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.763513332018662e-05, "loss": 4.0497, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.76267473726761e-05, "loss": 4.0476, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.761837780396931e-05, "loss": 4.0484, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.760999185645879e-05, "loss": 4.0446, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760160590894827e-05, "loss": 4.0397, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759321996143775e-05, "loss": 4.0498, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.7584850392730956e-05, "loss": 4.0507, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.7576464445220436e-05, "loss": 4.0371, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.7568078497709916e-05, "loss": 4.0425, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.7559692550199396e-05, "loss": 4.0443, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755130660268888e-05, "loss": 4.0404, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.754293703398209e-05, "loss": 4.0396, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.753455108647157e-05, "loss": 4.0343, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.752616513896105e-05, "loss": 4.0463, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.751777919145053e-05, "loss": 4.0419, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.750939324394001e-05, "loss": 4.0479, "step": 762880 }, { "epoch": 1.03, "eval_loss": 4.068617343902588, "eval_runtime": 294.5098, "eval_samples_per_second": 1295.682, "eval_steps_per_second": 40.491, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.750102367523322e-05, "loss": 4.0267, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.74926377277227e-05, "loss": 4.0331, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.748425178021218e-05, "loss": 4.0344, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.7475865832701654e-05, "loss": 4.0401, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.7467479885191134e-05, "loss": 4.0489, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.745909393768062e-05, "loss": 4.0445, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.74507079901701e-05, "loss": 4.0313, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.744232204265958e-05, "loss": 4.0317, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.743393609514906e-05, "loss": 4.0313, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742555014763854e-05, "loss": 4.0391, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.741716420012802e-05, "loss": 4.0369, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.74087782526175e-05, "loss": 4.0382, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.740040868391071e-05, "loss": 4.0434, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.739202273640019e-05, "loss": 4.0226, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.738363678888967e-05, "loss": 4.0323, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.737525084137915e-05, "loss": 4.0238, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736686489386863e-05, "loss": 4.0412, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.735847894635811e-05, "loss": 4.0311, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.735009299884759e-05, "loss": 4.0375, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.734170705133707e-05, "loss": 4.0346, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.733332110382655e-05, "loss": 4.0493, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732493515631603e-05, "loss": 4.0351, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731654920880551e-05, "loss": 4.0427, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.730816326129499e-05, "loss": 4.0343, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.72997936925882e-05, "loss": 4.0365, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729140774507768e-05, "loss": 4.0396, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728302179756716e-05, "loss": 4.0261, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.7274652228860374e-05, "loss": 4.0344, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726626628134985e-05, "loss": 4.0269, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725788033383933e-05, "loss": 4.03, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.724949438632881e-05, "loss": 4.0327, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.7241108438818287e-05, "loss": 4.0337, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.72327388701115e-05, "loss": 4.0352, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.722435292260098e-05, "loss": 4.0467, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.721596697509046e-05, "loss": 4.0318, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720758102757994e-05, "loss": 4.0327, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.719919508006942e-05, "loss": 4.0468, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.71908091325589e-05, "loss": 4.0297, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718242318504838e-05, "loss": 4.0289, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.717405361634159e-05, "loss": 4.0329, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.716566766883107e-05, "loss": 4.0299, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.715728172132055e-05, "loss": 4.0335, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.714889577381003e-05, "loss": 4.031, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.714050982629951e-05, "loss": 4.0404, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.713212387878899e-05, "loss": 4.033, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.712375431008221e-05, "loss": 4.0378, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711536836257169e-05, "loss": 4.0329, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.710698241506117e-05, "loss": 4.0382, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709859646755065e-05, "loss": 4.0019, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709021052004013e-05, "loss": 4.041, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.7081840951333336e-05, "loss": 4.0224, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.7073455003822816e-05, "loss": 4.0388, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.7065069056312296e-05, "loss": 4.0213, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.7056683108801776e-05, "loss": 4.0177, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.7048297161291256e-05, "loss": 4.0159, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.7039927592584465e-05, "loss": 4.025, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.7031541645073945e-05, "loss": 4.0348, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.7023155697563425e-05, "loss": 4.0156, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.7014769750052905e-05, "loss": 4.0395, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.7006383802542385e-05, "loss": 4.03, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.6997997855031865e-05, "loss": 4.011, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.698962828632508e-05, "loss": 4.0329, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.698124233881456e-05, "loss": 4.0136, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6972856391304034e-05, "loss": 4.0141, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.6964470443793514e-05, "loss": 4.0274, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.695610087508673e-05, "loss": 4.0327, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.69477149275762e-05, "loss": 4.0142, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.693932898006568e-05, "loss": 4.0288, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693094303255516e-05, "loss": 4.0127, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.692255708504464e-05, "loss": 4.0261, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691417113753413e-05, "loss": 4.0328, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690580156882734e-05, "loss": 4.0289, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689741562131682e-05, "loss": 4.035, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.68890296738063e-05, "loss": 4.0362, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688064372629578e-05, "loss": 4.0506, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687227415758899e-05, "loss": 4.0299, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686388821007847e-05, "loss": 4.033, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685550226256795e-05, "loss": 4.0211, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684711631505743e-05, "loss": 4.0283, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.6838746746350636e-05, "loss": 4.025, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.6830360798840116e-05, "loss": 4.0297, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.6821974851329596e-05, "loss": 4.0353, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.681358890381908e-05, "loss": 4.0404, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.680520295630856e-05, "loss": 4.0177, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.679681700879804e-05, "loss": 4.0209, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.678843106128752e-05, "loss": 4.0217, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6780045113777e-05, "loss": 4.0308, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.677165916626648e-05, "loss": 4.0286, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676328959755969e-05, "loss": 4.0221, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675490365004917e-05, "loss": 4.0253, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.674651770253865e-05, "loss": 4.0276, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.673813175502813e-05, "loss": 4.0226, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.672974580751761e-05, "loss": 4.0197, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672135986000709e-05, "loss": 4.0363, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.6712973912496565e-05, "loss": 4.0334, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.6704587964986045e-05, "loss": 4.0286, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.6696234775082996e-05, "loss": 4.0186, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.6687848827572476e-05, "loss": 4.0211, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.6679462880061956e-05, "loss": 4.0227, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.6671076932551436e-05, "loss": 4.0299, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.6662690985040916e-05, "loss": 4.0379, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.6654305037530396e-05, "loss": 4.0203, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.664591909001987e-05, "loss": 4.0328, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663753314250935e-05, "loss": 4.0254, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.6629163573802565e-05, "loss": 4.0244, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662077762629204e-05, "loss": 4.015, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.6612408057585254e-05, "loss": 4.014, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.6604022110074734e-05, "loss": 4.0223, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.6595636162564214e-05, "loss": 4.0223, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.6587250215053694e-05, "loss": 4.0144, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.6578864267543174e-05, "loss": 4.0137, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.6570478320032654e-05, "loss": 4.0115, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.6562092372522134e-05, "loss": 4.0262, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.6553706425011614e-05, "loss": 4.0178, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654533685630482e-05, "loss": 4.0248, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.65369509087943e-05, "loss": 4.0255, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.652856496128378e-05, "loss": 4.0238, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.652021177138073e-05, "loss": 4.0206, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.651182582387021e-05, "loss": 4.0304, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.650343987635969e-05, "loss": 4.0237, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.649505392884917e-05, "loss": 4.0326, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.6486684360142384e-05, "loss": 4.0237, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.6478298412631864e-05, "loss": 4.0209, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.6469912465121344e-05, "loss": 4.0235, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646152651761082e-05, "loss": 4.0242, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.64531405701003e-05, "loss": 4.018, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644475462258978e-05, "loss": 4.015, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.643636867507926e-05, "loss": 4.0149, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.642798272756874e-05, "loss": 4.012, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.6419596780058217e-05, "loss": 4.0269, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.6411210832547697e-05, "loss": 4.0214, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.6402824885037176e-05, "loss": 4.0262, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.6394438937526656e-05, "loss": 4.0154, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.6386052990016136e-05, "loss": 4.0288, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637768342130935e-05, "loss": 4.0275, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.636931385260256e-05, "loss": 4.0253, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.636092790509204e-05, "loss": 4.0243, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635254195758152e-05, "loss": 4.0199, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.6344156010071e-05, "loss": 4.0306, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.633577006256048e-05, "loss": 4.0322, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.632738411504996e-05, "loss": 4.0143, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.631899816753944e-05, "loss": 4.0209, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631061222002892e-05, "loss": 4.0274, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.630224265132213e-05, "loss": 4.0195, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.6293873082615346e-05, "loss": 4.0173, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.6285487135104826e-05, "loss": 4.0177, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.6277101187594306e-05, "loss": 4.0227, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.6268715240083786e-05, "loss": 4.0224, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.6260345671376995e-05, "loss": 4.0271, "step": 839168 }, { "epoch": 0.03, "eval_loss": 4.055795669555664, "eval_runtime": 299.9809, "eval_samples_per_second": 1272.051, "eval_steps_per_second": 39.753, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.6251959723866475e-05, "loss": 4.0038, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.6243573776355955e-05, "loss": 4.0131, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.6235187828845435e-05, "loss": 4.0155, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.6226801881334915e-05, "loss": 4.0202, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.6218415933824395e-05, "loss": 4.0261, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.6210029986313875e-05, "loss": 4.0262, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.620164403880335e-05, "loss": 4.0148, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.619325809129283e-05, "loss": 4.014, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.6184872143782315e-05, "loss": 4.0094, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.6176486196271795e-05, "loss": 4.0162, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.6168100248761275e-05, "loss": 4.0247, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.6159714301250754e-05, "loss": 4.0172, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.6151344732543964e-05, "loss": 4.0226, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.6142958785033444e-05, "loss": 4.0043, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.6134572837522923e-05, "loss": 4.0155, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.6126186890012403e-05, "loss": 3.9994, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.611780094250188e-05, "loss": 4.0226, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.610941499499136e-05, "loss": 4.0123, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.610102904748084e-05, "loss": 4.0155, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.609264309997032e-05, "loss": 4.0137, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.60842571524598e-05, "loss": 4.0334, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.607587120494928e-05, "loss": 4.0121, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.606748525743876e-05, "loss": 4.0243, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.605909930992824e-05, "loss": 4.0138, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.605071336241772e-05, "loss": 4.0172, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.604234379371094e-05, "loss": 4.0222, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603395784620042e-05, "loss": 4.006, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.602558827749363e-05, "loss": 4.0154, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.601720232998311e-05, "loss": 4.0095, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.600881638247259e-05, "loss": 4.0112, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.600043043496206e-05, "loss": 4.0155, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.599204448745154e-05, "loss": 4.0178, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.598365853994102e-05, "loss": 4.0107, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.59752725924305e-05, "loss": 4.0309, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.596690302372372e-05, "loss": 4.0151, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.595853345501693e-05, "loss": 4.0138, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.595014750750641e-05, "loss": 4.0246, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.594176155999589e-05, "loss": 4.0094, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.5933375612485366e-05, "loss": 4.0092, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.5924989664974846e-05, "loss": 4.0196, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.5916603717464326e-05, "loss": 4.0076, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.5908217769953806e-05, "loss": 4.0164, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.5899831822443286e-05, "loss": 4.0165, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.5891445874932766e-05, "loss": 4.0126, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.5883076306225975e-05, "loss": 4.0189, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.5874690358715455e-05, "loss": 4.0169, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.5866304411204935e-05, "loss": 4.0148, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.5857918463694414e-05, "loss": 4.0183, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.58495325161839e-05, "loss": 3.9839, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.584114656867338e-05, "loss": 4.0171, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.583276062116286e-05, "loss": 4.0095, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.582437467365234e-05, "loss": 4.0187, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.581600510494555e-05, "loss": 4.005, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.580763553623876e-05, "loss": 3.9959, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.579924958872824e-05, "loss": 4.0002, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.579086364121772e-05, "loss": 4.0044, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.57824776937072e-05, "loss": 4.0151, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.577409174619668e-05, "loss": 3.9949, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.576572217748989e-05, "loss": 4.0222, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.575733622997937e-05, "loss": 4.014, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.5748950282468855e-05, "loss": 3.9877, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.5740564334958335e-05, "loss": 4.0146, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.5732178387447815e-05, "loss": 3.9975, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.5723792439937295e-05, "loss": 3.9945, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.5715406492426775e-05, "loss": 4.0043, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.570702054491625e-05, "loss": 4.0162, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.569863459740573e-05, "loss": 3.9946, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.5690265028698944e-05, "loss": 4.0111, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.5681879081188424e-05, "loss": 3.9899, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.56734931336779e-05, "loss": 4.0078, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.566510718616738e-05, "loss": 4.0132, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.565673761746059e-05, "loss": 4.0149, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.564836804875381e-05, "loss": 4.0144, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.563998210124329e-05, "loss": 4.0162, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.563159615373277e-05, "loss": 4.0336, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.562321020622225e-05, "loss": 4.0127, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.561482425871172e-05, "loss": 4.0148, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.56064383112012e-05, "loss": 4.0006, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.559806874249442e-05, "loss": 4.0077, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.55896827949839e-05, "loss": 4.0053, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.558129684747337e-05, "loss": 4.0077, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.557291089996285e-05, "loss": 4.0165, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.556452495245233e-05, "loss": 4.0197, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.555613900494181e-05, "loss": 4.0017, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.554775305743129e-05, "loss": 4.001, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.553936710992077e-05, "loss": 3.9976, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.5530997541213986e-05, "loss": 4.0176, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.5522611593703466e-05, "loss": 4.0085, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.551427478260414e-05, "loss": 4.0015, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.550588883509362e-05, "loss": 4.0111, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.54975028875831e-05, "loss": 4.0062, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.548911694007258e-05, "loss": 4.0058, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.548073099256206e-05, "loss": 4.0014, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.547236142385527e-05, "loss": 4.018, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.546397547634475e-05, "loss": 4.0094, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.545558952883423e-05, "loss": 4.0117, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.544720358132371e-05, "loss": 3.9988, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.5438817633813196e-05, "loss": 4.0028, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.543043168630267e-05, "loss": 4.0042, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.542204573879215e-05, "loss": 4.013, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.541365979128163e-05, "loss": 4.0148, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.540527384377111e-05, "loss": 4.006, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.539688789626059e-05, "loss": 4.0111, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.538850194875007e-05, "loss": 4.0092, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.538011600123955e-05, "loss": 4.0048, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.537173005372903e-05, "loss": 3.996, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.536336048502224e-05, "loss": 3.9982, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.535497453751172e-05, "loss": 3.9989, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.53465885900012e-05, "loss": 4.0052, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.533820264249068e-05, "loss": 3.9953, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.5329816694980164e-05, "loss": 3.9963, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.5321430747469644e-05, "loss": 3.9946, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.5313061178762853e-05, "loss": 4.0027, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.5304675231252333e-05, "loss": 4.0018, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.529628928374181e-05, "loss": 4.0036, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.528790333623129e-05, "loss": 4.0065, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.52795337675245e-05, "loss": 4.0078, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.527114782001398e-05, "loss": 4.0024, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.526276187250346e-05, "loss": 4.0116, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.525437592499294e-05, "loss": 4.0053, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.524600635628615e-05, "loss": 4.0138, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.523762040877563e-05, "loss": 4.0046, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.522923446126512e-05, "loss": 4.0046, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.52208485137546e-05, "loss": 4.003, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521246256624408e-05, "loss": 4.0074, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.520407661873356e-05, "loss": 3.9998, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.519569067122303e-05, "loss": 3.9988, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.518730472371251e-05, "loss": 3.9906, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.517893515500573e-05, "loss": 3.9975, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.517054920749521e-05, "loss": 4.0078, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.516216325998468e-05, "loss": 4.0017, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.515377731247416e-05, "loss": 4.0091, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514539136496364e-05, "loss": 3.9901, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.513700541745312e-05, "loss": 4.0153, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.51286194699426e-05, "loss": 4.0105, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.512023352243209e-05, "loss": 4.0105, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.5111847574921567e-05, "loss": 3.9978, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.5103461627411047e-05, "loss": 4.0051, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.5095075679900526e-05, "loss": 4.0139, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.5086689732390006e-05, "loss": 4.0133, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.5078303784879486e-05, "loss": 3.9995, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.5069934216172696e-05, "loss": 4.0005, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.5061548268662175e-05, "loss": 4.0062, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.5053162321151655e-05, "loss": 4.0055, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.5044776373641135e-05, "loss": 3.9976, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.5036406804934344e-05, "loss": 4.0022, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.5028020857423824e-05, "loss": 4.001, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.5019634909913304e-05, "loss": 4.0026, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.5011248962402784e-05, "loss": 4.011, "step": 915456 }, { "epoch": 0.03, "eval_loss": 4.044595241546631, "eval_runtime": 295.5841, "eval_samples_per_second": 1290.973, "eval_steps_per_second": 40.344, "step": 915840 }, { "epoch": 1.0, "learning_rate": 3.5002863014892264e-05, "loss": 3.9985, "step": 915968 }, { "epoch": 1.0, "learning_rate": 3.4994477067381744e-05, "loss": 3.9908, "step": 916480 }, { "epoch": 1.0, "learning_rate": 3.4986091119871224e-05, "loss": 3.9974, "step": 916992 }, { "epoch": 1.0, "learning_rate": 3.4977705172360704e-05, "loss": 4.0056, "step": 917504 }, { "epoch": 1.0, "learning_rate": 3.4969319224850184e-05, "loss": 4.0015, "step": 918016 }, { "epoch": 1.0, "learning_rate": 3.496094965614339e-05, "loss": 4.0101, "step": 918528 }, { "epoch": 1.0, "learning_rate": 3.495256370863287e-05, "loss": 3.9982, "step": 919040 }, { "epoch": 1.0, "learning_rate": 3.494417776112235e-05, "loss": 3.9951, "step": 919552 }, { "epoch": 1.0, "learning_rate": 3.493579181361183e-05, "loss": 3.9906, "step": 920064 }, { "epoch": 1.0, "learning_rate": 3.492742224490504e-05, "loss": 4.0004, "step": 920576 }, { "epoch": 1.0, "learning_rate": 3.491903629739452e-05, "loss": 4.0062, "step": 921088 }, { "epoch": 1.0, "learning_rate": 3.491066672868774e-05, "loss": 3.999, "step": 921600 }, { "epoch": 1.0, "learning_rate": 3.4902297159980954e-05, "loss": 4.0108, "step": 922112 }, { "epoch": 1.0, "learning_rate": 3.4893911212470434e-05, "loss": 3.9827, "step": 922624 }, { "epoch": 1.0, "learning_rate": 3.4885525264959914e-05, "loss": 3.9952, "step": 923136 }, { "epoch": 1.0, "learning_rate": 3.4877139317449394e-05, "loss": 3.9862, "step": 923648 }, { "epoch": 1.0, "learning_rate": 3.486875336993887e-05, "loss": 4.0029, "step": 924160 }, { "epoch": 1.0, "learning_rate": 3.486036742242835e-05, "loss": 3.9967, "step": 924672 }, { "epoch": 1.0, "learning_rate": 3.485198147491783e-05, "loss": 3.9978, "step": 925184 }, { "epoch": 1.0, "learning_rate": 3.484361190621104e-05, "loss": 3.9928, "step": 925696 }, { "epoch": 1.0, "learning_rate": 3.4835225958700516e-05, "loss": 4.0183, "step": 926208 }, { "epoch": 1.0, "learning_rate": 3.4826840011189996e-05, "loss": 3.9959, "step": 926720 }, { "epoch": 1.0, "learning_rate": 3.4818454063679476e-05, "loss": 4.0056, "step": 927232 }, { "epoch": 1.0, "learning_rate": 3.4810068116168956e-05, "loss": 3.9962, "step": 927744 }, { "epoch": 1.0, "learning_rate": 3.480168216865844e-05, "loss": 4.0031, "step": 928256 }, { "epoch": 1.0, "learning_rate": 3.479329622114792e-05, "loss": 4.0024, "step": 928768 }, { "epoch": 1.0, "learning_rate": 3.47849102736374e-05, "loss": 3.9885, "step": 929280 }, { "epoch": 1.0, "learning_rate": 3.477654070493061e-05, "loss": 3.9965, "step": 929792 }, { "epoch": 1.0, "learning_rate": 3.476815475742009e-05, "loss": 3.9918, "step": 930304 }, { "epoch": 1.0, "learning_rate": 3.475976880990957e-05, "loss": 3.994, "step": 930816 }, { "epoch": 1.01, "learning_rate": 3.475138286239905e-05, "loss": 3.9998, "step": 931328 }, { "epoch": 1.01, "learning_rate": 3.474299691488853e-05, "loss": 3.9974, "step": 931840 }, { "epoch": 1.01, "learning_rate": 3.473461096737801e-05, "loss": 3.9948, "step": 932352 }, { "epoch": 1.01, "learning_rate": 3.472622501986749e-05, "loss": 4.0125, "step": 932864 }, { "epoch": 1.01, "learning_rate": 3.471783907235697e-05, "loss": 3.998, "step": 933376 }, { "epoch": 1.01, "learning_rate": 3.470946950365018e-05, "loss": 4.0005, "step": 933888 }, { "epoch": 1.01, "learning_rate": 3.4701099934943396e-05, "loss": 4.008, "step": 934400 }, { "epoch": 1.01, "learning_rate": 3.4692713987432876e-05, "loss": 3.9886, "step": 934912 }, { "epoch": 1.01, "learning_rate": 3.4684328039922356e-05, "loss": 3.9943, "step": 935424 }, { "epoch": 1.01, "learning_rate": 3.4675942092411836e-05, "loss": 3.9979, "step": 935936 }, { "epoch": 1.01, "learning_rate": 3.4667556144901316e-05, "loss": 3.9903, "step": 936448 }, { "epoch": 1.01, "learning_rate": 3.4659170197390796e-05, "loss": 4.0035, "step": 936960 }, { "epoch": 1.01, "learning_rate": 3.4650800628684005e-05, "loss": 4.0025, "step": 937472 }, { "epoch": 1.01, "learning_rate": 3.4642414681173485e-05, "loss": 3.995, "step": 937984 }, { "epoch": 1.01, "learning_rate": 3.4634028733662965e-05, "loss": 4.0, "step": 938496 }, { "epoch": 1.01, "learning_rate": 3.4625642786152445e-05, "loss": 4.0007, "step": 939008 }, { "epoch": 1.01, "learning_rate": 3.4617256838641925e-05, "loss": 3.9947, "step": 939520 }, { "epoch": 1.01, "learning_rate": 3.4608887269935134e-05, "loss": 4.0021, "step": 940032 }, { "epoch": 1.01, "learning_rate": 3.4600501322424614e-05, "loss": 3.9692, "step": 940544 }, { "epoch": 1.01, "learning_rate": 3.4592115374914094e-05, "loss": 3.9963, "step": 941056 }, { "epoch": 1.01, "learning_rate": 3.458372942740358e-05, "loss": 3.9979, "step": 941568 }, { "epoch": 1.01, "learning_rate": 3.457535985869679e-05, "loss": 4.0016, "step": 942080 }, { "epoch": 1.01, "learning_rate": 3.456697391118627e-05, "loss": 3.9872, "step": 942592 }, { "epoch": 1.01, "learning_rate": 3.455858796367575e-05, "loss": 3.9782, "step": 943104 }, { "epoch": 1.01, "learning_rate": 3.455020201616523e-05, "loss": 3.9824, "step": 943616 }, { "epoch": 1.01, "learning_rate": 3.45418160686547e-05, "loss": 3.9869, "step": 944128 }, { "epoch": 1.01, "learning_rate": 3.453343012114418e-05, "loss": 4.0037, "step": 944640 }, { "epoch": 1.01, "learning_rate": 3.452504417363366e-05, "loss": 3.9755, "step": 945152 }, { "epoch": 1.01, "learning_rate": 3.451665822612314e-05, "loss": 4.0057, "step": 945664 }, { "epoch": 1.01, "learning_rate": 3.450828865741635e-05, "loss": 3.9982, "step": 946176 }, { "epoch": 1.01, "learning_rate": 3.449990270990583e-05, "loss": 3.9751, "step": 946688 }, { "epoch": 1.01, "learning_rate": 3.449151676239532e-05, "loss": 3.9961, "step": 947200 }, { "epoch": 1.01, "learning_rate": 3.44831308148848e-05, "loss": 3.9798, "step": 947712 }, { "epoch": 1.01, "learning_rate": 3.447474486737428e-05, "loss": 3.9803, "step": 948224 }, { "epoch": 1.01, "learning_rate": 3.446637529866749e-05, "loss": 3.9842, "step": 948736 }, { "epoch": 1.01, "learning_rate": 3.445798935115697e-05, "loss": 3.9986, "step": 949248 }, { "epoch": 1.01, "learning_rate": 3.444960340364645e-05, "loss": 3.9835, "step": 949760 }, { "epoch": 1.01, "learning_rate": 3.444121745613593e-05, "loss": 3.9952, "step": 950272 }, { "epoch": 1.01, "learning_rate": 3.443283150862541e-05, "loss": 3.9742, "step": 950784 }, { "epoch": 1.01, "learning_rate": 3.442444556111489e-05, "loss": 3.9901, "step": 951296 }, { "epoch": 1.01, "learning_rate": 3.441605961360437e-05, "loss": 3.9986, "step": 951808 }, { "epoch": 1.01, "learning_rate": 3.440767366609385e-05, "loss": 3.9999, "step": 952320 }, { "epoch": 1.01, "learning_rate": 3.4399304097387056e-05, "loss": 3.9972, "step": 952832 }, { "epoch": 1.01, "learning_rate": 3.4390918149876536e-05, "loss": 3.9998, "step": 953344 }, { "epoch": 1.01, "learning_rate": 3.4382532202366016e-05, "loss": 4.0138, "step": 953856 }, { "epoch": 1.01, "learning_rate": 3.4374146254855496e-05, "loss": 3.9994, "step": 954368 }, { "epoch": 1.01, "learning_rate": 3.436576030734498e-05, "loss": 4.0011, "step": 954880 }, { "epoch": 1.01, "learning_rate": 3.435737435983446e-05, "loss": 3.9842, "step": 955392 }, { "epoch": 1.01, "learning_rate": 3.434900479112767e-05, "loss": 3.9933, "step": 955904 }, { "epoch": 1.01, "learning_rate": 3.434063522242088e-05, "loss": 3.9916, "step": 956416 }, { "epoch": 1.01, "learning_rate": 3.433224927491036e-05, "loss": 3.994, "step": 956928 }, { "epoch": 1.01, "learning_rate": 3.432386332739984e-05, "loss": 3.9996, "step": 957440 }, { "epoch": 1.01, "learning_rate": 3.431547737988932e-05, "loss": 4.0035, "step": 957952 }, { "epoch": 1.01, "learning_rate": 3.43070914323788e-05, "loss": 3.9909, "step": 958464 }, { "epoch": 1.01, "learning_rate": 3.429870548486828e-05, "loss": 3.9829, "step": 958976 }, { "epoch": 1.01, "learning_rate": 3.429033591616149e-05, "loss": 3.9836, "step": 959488 }, { "epoch": 1.01, "learning_rate": 3.428194996865097e-05, "loss": 3.9998, "step": 960000 }, { "epoch": 1.01, "learning_rate": 3.4273580399944186e-05, "loss": 3.9913, "step": 960512 }, { "epoch": 1.01, "learning_rate": 3.4265194452433666e-05, "loss": 3.9885, "step": 961024 }, { "epoch": 1.01, "learning_rate": 3.4256808504923146e-05, "loss": 3.9949, "step": 961536 }, { "epoch": 1.02, "learning_rate": 3.4248422557412625e-05, "loss": 3.9917, "step": 962048 }, { "epoch": 1.02, "learning_rate": 3.4240036609902105e-05, "loss": 3.9879, "step": 962560 }, { "epoch": 1.02, "learning_rate": 3.4231650662391585e-05, "loss": 3.9869, "step": 963072 }, { "epoch": 1.02, "learning_rate": 3.4223264714881065e-05, "loss": 4.0026, "step": 963584 }, { "epoch": 1.02, "learning_rate": 3.421487876737054e-05, "loss": 3.9985, "step": 964096 }, { "epoch": 1.02, "learning_rate": 3.4206509198663754e-05, "loss": 3.997, "step": 964608 }, { "epoch": 1.02, "learning_rate": 3.4198123251153234e-05, "loss": 3.9834, "step": 965120 }, { "epoch": 1.02, "learning_rate": 3.418973730364271e-05, "loss": 3.9884, "step": 965632 }, { "epoch": 1.02, "learning_rate": 3.418135135613219e-05, "loss": 3.9895, "step": 966144 }, { "epoch": 1.02, "learning_rate": 3.4172965408621674e-05, "loss": 3.9955, "step": 966656 }, { "epoch": 1.02, "learning_rate": 3.4164579461111154e-05, "loss": 4.0013, "step": 967168 }, { "epoch": 1.02, "learning_rate": 3.4156193513600634e-05, "loss": 3.9894, "step": 967680 }, { "epoch": 1.02, "learning_rate": 3.4147807566090114e-05, "loss": 3.9954, "step": 968192 }, { "epoch": 1.02, "learning_rate": 3.413943799738332e-05, "loss": 3.9923, "step": 968704 }, { "epoch": 1.02, "learning_rate": 3.41310520498728e-05, "loss": 3.9905, "step": 969216 }, { "epoch": 1.02, "learning_rate": 3.412266610236228e-05, "loss": 3.9831, "step": 969728 }, { "epoch": 1.02, "learning_rate": 3.411429653365549e-05, "loss": 3.9829, "step": 970240 }, { "epoch": 1.02, "learning_rate": 3.410591058614497e-05, "loss": 3.9855, "step": 970752 }, { "epoch": 1.02, "learning_rate": 3.409752463863445e-05, "loss": 3.9914, "step": 971264 }, { "epoch": 1.02, "learning_rate": 3.408913869112393e-05, "loss": 3.977, "step": 971776 }, { "epoch": 1.02, "learning_rate": 3.408075274361341e-05, "loss": 3.9831, "step": 972288 }, { "epoch": 1.02, "learning_rate": 3.407236679610289e-05, "loss": 3.9755, "step": 972800 }, { "epoch": 1.02, "learning_rate": 3.406398084859237e-05, "loss": 3.9943, "step": 973312 }, { "epoch": 1.02, "learning_rate": 3.405559490108186e-05, "loss": 3.9847, "step": 973824 }, { "epoch": 1.02, "learning_rate": 3.404720895357134e-05, "loss": 3.9915, "step": 974336 }, { "epoch": 1.02, "learning_rate": 3.403883938486455e-05, "loss": 3.9889, "step": 974848 }, { "epoch": 1.02, "learning_rate": 3.403045343735403e-05, "loss": 3.9942, "step": 975360 }, { "epoch": 1.02, "learning_rate": 3.402206748984351e-05, "loss": 3.9886, "step": 975872 }, { "epoch": 1.02, "learning_rate": 3.401368154233299e-05, "loss": 3.99, "step": 976384 }, { "epoch": 1.02, "learning_rate": 3.40053119736262e-05, "loss": 3.9968, "step": 976896 }, { "epoch": 1.02, "learning_rate": 3.399692602611568e-05, "loss": 3.9971, "step": 977408 }, { "epoch": 1.02, "learning_rate": 3.3988540078605157e-05, "loss": 3.9905, "step": 977920 }, { "epoch": 1.02, "learning_rate": 3.3980154131094637e-05, "loss": 3.9917, "step": 978432 }, { "epoch": 1.02, "learning_rate": 3.3971784562387846e-05, "loss": 3.9872, "step": 978944 }, { "epoch": 1.02, "learning_rate": 3.3963398614877326e-05, "loss": 3.9877, "step": 979456 }, { "epoch": 1.02, "learning_rate": 3.395502904617054e-05, "loss": 3.9841, "step": 979968 }, { "epoch": 1.02, "learning_rate": 3.394664309866002e-05, "loss": 3.9844, "step": 980480 }, { "epoch": 1.02, "learning_rate": 3.39382571511495e-05, "loss": 3.9758, "step": 980992 }, { "epoch": 1.02, "learning_rate": 3.392987120363898e-05, "loss": 3.9855, "step": 981504 }, { "epoch": 1.02, "learning_rate": 3.392148525612846e-05, "loss": 3.9881, "step": 982016 }, { "epoch": 1.02, "learning_rate": 3.391311568742167e-05, "loss": 3.9911, "step": 982528 }, { "epoch": 1.02, "learning_rate": 3.390472973991115e-05, "loss": 3.9897, "step": 983040 }, { "epoch": 1.02, "learning_rate": 3.389634379240063e-05, "loss": 3.9816, "step": 983552 }, { "epoch": 1.02, "learning_rate": 3.388795784489011e-05, "loss": 3.9974, "step": 984064 }, { "epoch": 1.02, "learning_rate": 3.387957189737959e-05, "loss": 3.9949, "step": 984576 }, { "epoch": 1.02, "learning_rate": 3.387118594986907e-05, "loss": 3.9911, "step": 985088 }, { "epoch": 1.02, "learning_rate": 3.386280000235855e-05, "loss": 3.986, "step": 985600 }, { "epoch": 1.02, "learning_rate": 3.385441405484803e-05, "loss": 3.9903, "step": 986112 }, { "epoch": 1.02, "learning_rate": 3.3846044486141246e-05, "loss": 3.9992, "step": 986624 }, { "epoch": 1.02, "learning_rate": 3.3837658538630726e-05, "loss": 3.9979, "step": 987136 }, { "epoch": 1.02, "learning_rate": 3.38292725911202e-05, "loss": 3.9872, "step": 987648 }, { "epoch": 1.02, "learning_rate": 3.382088664360968e-05, "loss": 3.9853, "step": 988160 }, { "epoch": 1.02, "learning_rate": 3.3812517074902895e-05, "loss": 3.9919, "step": 988672 }, { "epoch": 1.02, "learning_rate": 3.380413112739237e-05, "loss": 3.9883, "step": 989184 }, { "epoch": 1.02, "learning_rate": 3.379574517988185e-05, "loss": 3.9853, "step": 989696 }, { "epoch": 1.02, "learning_rate": 3.378735923237133e-05, "loss": 3.9873, "step": 990208 }, { "epoch": 1.02, "learning_rate": 3.3778989663664544e-05, "loss": 3.9868, "step": 990720 }, { "epoch": 1.02, "learning_rate": 3.377060371615402e-05, "loss": 3.9894, "step": 991232 }, { "epoch": 1.02, "learning_rate": 3.376223414744723e-05, "loss": 3.9945, "step": 991744 }, { "epoch": 1.03, "eval_loss": 4.036184310913086, "eval_runtime": 292.0553, "eval_samples_per_second": 1306.571, "eval_steps_per_second": 40.831, "step": 992160 }, { "epoch": 0.0, "learning_rate": 3.375384819993671e-05, "loss": 3.991, "step": 992256 }, { "epoch": 0.0, "learning_rate": 3.37454622524262e-05, "loss": 3.9759, "step": 992768 }, { "epoch": 0.0, "learning_rate": 3.373707630491567e-05, "loss": 3.9809, "step": 993280 }, { "epoch": 0.0, "learning_rate": 3.372869035740515e-05, "loss": 3.9951, "step": 993792 }, { "epoch": 0.0, "learning_rate": 3.372030440989463e-05, "loss": 3.9878, "step": 994304 }, { "epoch": 0.0, "learning_rate": 3.371191846238411e-05, "loss": 3.9957, "step": 994816 }, { "epoch": 0.0, "learning_rate": 3.370353251487359e-05, "loss": 3.9786, "step": 995328 }, { "epoch": 0.0, "learning_rate": 3.369514656736307e-05, "loss": 3.9821, "step": 995840 }, { "epoch": 0.0, "learning_rate": 3.368676061985255e-05, "loss": 3.9753, "step": 996352 }, { "epoch": 0.0, "learning_rate": 3.367837467234203e-05, "loss": 3.9906, "step": 996864 }, { "epoch": 0.0, "learning_rate": 3.366998872483151e-05, "loss": 3.9854, "step": 997376 }, { "epoch": 0.0, "learning_rate": 3.366160277732099e-05, "loss": 3.9857, "step": 997888 }, { "epoch": 0.0, "learning_rate": 3.36532332086142e-05, "loss": 3.9947, "step": 998400 }, { "epoch": 0.0, "learning_rate": 3.364484726110368e-05, "loss": 3.968, "step": 998912 }, { "epoch": 0.0, "learning_rate": 3.363646131359317e-05, "loss": 3.9826, "step": 999424 }, { "epoch": 0.0, "learning_rate": 3.362807536608265e-05, "loss": 3.9693, "step": 999936 }, { "epoch": 0.0, "learning_rate": 3.361968941857213e-05, "loss": 3.9883, "step": 1000448 }, { "epoch": 0.0, "learning_rate": 3.361130347106161e-05, "loss": 3.979, "step": 1000960 }, { "epoch": 0.0, "learning_rate": 3.360291752355109e-05, "loss": 3.9865, "step": 1001472 }, { "epoch": 0.0, "learning_rate": 3.359453157604056e-05, "loss": 3.9751, "step": 1001984 }, { "epoch": 0.0, "learning_rate": 3.358614562853004e-05, "loss": 4.0017, "step": 1002496 }, { "epoch": 0.0, "learning_rate": 3.357775968101952e-05, "loss": 3.984, "step": 1003008 }, { "epoch": 0.0, "learning_rate": 3.3569373733509e-05, "loss": 3.99, "step": 1003520 }, { "epoch": 0.0, "learning_rate": 3.356098778599848e-05, "loss": 3.9853, "step": 1004032 }, { "epoch": 0.0, "learning_rate": 3.355261821729169e-05, "loss": 3.9895, "step": 1004544 }, { "epoch": 0.0, "learning_rate": 3.3544248648584906e-05, "loss": 3.9843, "step": 1005056 }, { "epoch": 0.0, "learning_rate": 3.3535862701074386e-05, "loss": 3.9757, "step": 1005568 }, { "epoch": 0.0, "learning_rate": 3.3527476753563866e-05, "loss": 3.986, "step": 1006080 }, { "epoch": 0.0, "learning_rate": 3.3519090806053346e-05, "loss": 3.9749, "step": 1006592 }, { "epoch": 0.0, "learning_rate": 3.3510704858542826e-05, "loss": 3.9792, "step": 1007104 }, { "epoch": 0.01, "learning_rate": 3.3502318911032306e-05, "loss": 3.9839, "step": 1007616 }, { "epoch": 0.01, "learning_rate": 3.349396572112925e-05, "loss": 3.9801, "step": 1008128 }, { "epoch": 0.01, "learning_rate": 3.348557977361873e-05, "loss": 3.9819, "step": 1008640 }, { "epoch": 0.01, "learning_rate": 3.3477193826108204e-05, "loss": 3.9985, "step": 1009152 }, { "epoch": 0.01, "learning_rate": 3.3468807878597684e-05, "loss": 3.9838, "step": 1009664 }, { "epoch": 0.01, "learning_rate": 3.3460421931087164e-05, "loss": 3.99, "step": 1010176 }, { "epoch": 0.01, "learning_rate": 3.3452035983576644e-05, "loss": 3.9888, "step": 1010688 }, { "epoch": 0.01, "learning_rate": 3.3443650036066124e-05, "loss": 3.9749, "step": 1011200 }, { "epoch": 0.01, "learning_rate": 3.3435264088555604e-05, "loss": 3.9851, "step": 1011712 }, { "epoch": 0.01, "learning_rate": 3.342687814104509e-05, "loss": 3.9809, "step": 1012224 }, { "epoch": 0.01, "learning_rate": 3.341849219353457e-05, "loss": 3.976, "step": 1012736 }, { "epoch": 0.01, "learning_rate": 3.341012262482778e-05, "loss": 3.9881, "step": 1013248 }, { "epoch": 0.01, "learning_rate": 3.340173667731726e-05, "loss": 3.9905, "step": 1013760 }, { "epoch": 0.01, "learning_rate": 3.339335072980674e-05, "loss": 3.9762, "step": 1014272 }, { "epoch": 0.01, "learning_rate": 3.338496478229622e-05, "loss": 3.9882, "step": 1014784 }, { "epoch": 0.01, "learning_rate": 3.33765788347857e-05, "loss": 3.9886, "step": 1015296 }, { "epoch": 0.01, "learning_rate": 3.336819288727518e-05, "loss": 3.9801, "step": 1015808 }, { "epoch": 0.01, "learning_rate": 3.335980693976466e-05, "loss": 3.9889, "step": 1016320 }, { "epoch": 0.01, "learning_rate": 3.335142099225414e-05, "loss": 3.9537, "step": 1016832 }, { "epoch": 0.01, "learning_rate": 3.334305142354735e-05, "loss": 3.9812, "step": 1017344 }, { "epoch": 0.01, "learning_rate": 3.333468185484056e-05, "loss": 3.9813, "step": 1017856 }, { "epoch": 0.01, "learning_rate": 3.3326295907330044e-05, "loss": 3.9883, "step": 1018368 }, { "epoch": 0.01, "learning_rate": 3.3317909959819524e-05, "loss": 3.9739, "step": 1018880 }, { "epoch": 0.01, "learning_rate": 3.3309524012309004e-05, "loss": 3.9637, "step": 1019392 }, { "epoch": 0.01, "learning_rate": 3.3301138064798484e-05, "loss": 3.9651, "step": 1019904 }, { "epoch": 0.01, "learning_rate": 3.329276849609169e-05, "loss": 3.9686, "step": 1020416 }, { "epoch": 0.01, "learning_rate": 3.328438254858117e-05, "loss": 3.9908, "step": 1020928 }, { "epoch": 0.01, "learning_rate": 3.327599660107065e-05, "loss": 3.9625, "step": 1021440 }, { "epoch": 0.01, "learning_rate": 3.326761065356013e-05, "loss": 3.9883, "step": 1021952 }, { "epoch": 0.01, "learning_rate": 3.325922470604961e-05, "loss": 3.979, "step": 1022464 }, { "epoch": 0.01, "learning_rate": 3.325083875853909e-05, "loss": 3.9691, "step": 1022976 }, { "epoch": 0.01, "learning_rate": 3.3242452811028566e-05, "loss": 3.9784, "step": 1023488 }, { "epoch": 0.01, "learning_rate": 3.3234066863518046e-05, "loss": 3.9652, "step": 1024000 }, { "epoch": 0.01, "learning_rate": 3.322569729481126e-05, "loss": 3.9669, "step": 1024512 }, { "epoch": 0.01, "learning_rate": 3.321731134730074e-05, "loss": 3.9704, "step": 1025024 }, { "epoch": 0.01, "learning_rate": 3.320892539979022e-05, "loss": 3.984, "step": 1025536 }, { "epoch": 0.01, "learning_rate": 3.32005394522797e-05, "loss": 3.9704, "step": 1026048 }, { "epoch": 0.01, "learning_rate": 3.319215350476918e-05, "loss": 3.9746, "step": 1026560 }, { "epoch": 0.01, "learning_rate": 3.318378393606239e-05, "loss": 3.9622, "step": 1027072 }, { "epoch": 0.01, "learning_rate": 3.317539798855187e-05, "loss": 3.9743, "step": 1027584 }, { "epoch": 0.01, "learning_rate": 3.3167028419845087e-05, "loss": 3.9844, "step": 1028096 }, { "epoch": 0.01, "learning_rate": 3.3158642472334567e-05, "loss": 3.9847, "step": 1028608 }, { "epoch": 0.01, "learning_rate": 3.315025652482404e-05, "loss": 3.9832, "step": 1029120 }, { "epoch": 0.01, "learning_rate": 3.314187057731352e-05, "loss": 3.9861, "step": 1029632 }, { "epoch": 0.01, "learning_rate": 3.3133484629803e-05, "loss": 3.9991, "step": 1030144 }, { "epoch": 0.01, "learning_rate": 3.3125115061096215e-05, "loss": 3.9838, "step": 1030656 }, { "epoch": 0.01, "learning_rate": 3.311674549238943e-05, "loss": 3.9867, "step": 1031168 }, { "epoch": 0.01, "learning_rate": 3.310835954487891e-05, "loss": 3.9705, "step": 1031680 }, { "epoch": 0.01, "learning_rate": 3.309997359736839e-05, "loss": 3.9787, "step": 1032192 }, { "epoch": 0.01, "learning_rate": 3.3091587649857864e-05, "loss": 3.9747, "step": 1032704 }, { "epoch": 0.01, "learning_rate": 3.3083201702347344e-05, "loss": 3.9746, "step": 1033216 }, { "epoch": 0.01, "learning_rate": 3.3074815754836824e-05, "loss": 3.9853, "step": 1033728 }, { "epoch": 0.01, "learning_rate": 3.3066429807326304e-05, "loss": 3.9886, "step": 1034240 }, { "epoch": 0.01, "learning_rate": 3.3058043859815784e-05, "loss": 3.9846, "step": 1034752 }, { "epoch": 0.01, "learning_rate": 3.3049657912305264e-05, "loss": 3.9635, "step": 1035264 }, { "epoch": 0.01, "learning_rate": 3.3041271964794744e-05, "loss": 3.9694, "step": 1035776 }, { "epoch": 0.01, "learning_rate": 3.3032886017284224e-05, "loss": 3.9837, "step": 1036288 }, { "epoch": 0.01, "learning_rate": 3.302451644857743e-05, "loss": 3.9802, "step": 1036800 }, { "epoch": 0.01, "learning_rate": 3.301613050106691e-05, "loss": 3.9765, "step": 1037312 }, { "epoch": 0.01, "learning_rate": 3.30077445535564e-05, "loss": 3.9784, "step": 1037824 }, { "epoch": 0.02, "learning_rate": 3.299935860604588e-05, "loss": 3.9771, "step": 1038336 }, { "epoch": 0.02, "learning_rate": 3.299098903733909e-05, "loss": 3.9733, "step": 1038848 }, { "epoch": 0.02, "learning_rate": 3.298260308982857e-05, "loss": 3.9744, "step": 1039360 }, { "epoch": 0.02, "learning_rate": 3.297421714231805e-05, "loss": 3.9866, "step": 1039872 }, { "epoch": 0.02, "learning_rate": 3.296583119480753e-05, "loss": 3.9806, "step": 1040384 }, { "epoch": 0.02, "learning_rate": 3.295744524729701e-05, "loss": 3.9832, "step": 1040896 }, { "epoch": 0.02, "learning_rate": 3.294905929978649e-05, "loss": 3.968, "step": 1041408 }, { "epoch": 0.02, "learning_rate": 3.29406897310797e-05, "loss": 3.9729, "step": 1041920 }, { "epoch": 0.02, "learning_rate": 3.293230378356918e-05, "loss": 3.9773, "step": 1042432 }, { "epoch": 0.02, "learning_rate": 3.292391783605866e-05, "loss": 3.9814, "step": 1042944 }, { "epoch": 0.02, "learning_rate": 3.291553188854814e-05, "loss": 3.9863, "step": 1043456 }, { "epoch": 0.02, "learning_rate": 3.2907162319841354e-05, "loss": 3.9777, "step": 1043968 }, { "epoch": 0.02, "learning_rate": 3.2898776372330834e-05, "loss": 3.9804, "step": 1044480 }, { "epoch": 0.02, "learning_rate": 3.2890390424820314e-05, "loss": 3.975, "step": 1044992 }, { "epoch": 0.02, "learning_rate": 3.2882004477309793e-05, "loss": 3.9773, "step": 1045504 }, { "epoch": 0.02, "learning_rate": 3.2873618529799273e-05, "loss": 3.9695, "step": 1046016 }, { "epoch": 0.02, "learning_rate": 3.286524896109248e-05, "loss": 3.9671, "step": 1046528 }, { "epoch": 0.02, "learning_rate": 3.285686301358196e-05, "loss": 3.9746, "step": 1047040 }, { "epoch": 0.02, "learning_rate": 3.284847706607144e-05, "loss": 3.9751, "step": 1047552 }, { "epoch": 0.02, "learning_rate": 3.284009111856092e-05, "loss": 3.9646, "step": 1048064 }, { "epoch": 0.02, "learning_rate": 3.28317051710504e-05, "loss": 3.9659, "step": 1048576 }, { "epoch": 0.02, "learning_rate": 3.2823319223539876e-05, "loss": 3.9643, "step": 1049088 }, { "epoch": 0.02, "learning_rate": 3.2814933276029355e-05, "loss": 3.9744, "step": 1049600 }, { "epoch": 0.02, "learning_rate": 3.2806547328518835e-05, "loss": 3.9752, "step": 1050112 }, { "epoch": 0.02, "learning_rate": 3.279817775981205e-05, "loss": 3.9731, "step": 1050624 }, { "epoch": 0.02, "learning_rate": 3.278979181230153e-05, "loss": 3.9744, "step": 1051136 }, { "epoch": 0.02, "learning_rate": 3.278140586479101e-05, "loss": 3.9823, "step": 1051648 }, { "epoch": 0.02, "learning_rate": 3.277301991728049e-05, "loss": 3.9737, "step": 1052160 }, { "epoch": 0.02, "learning_rate": 3.27646503485737e-05, "loss": 3.9748, "step": 1052672 }, { "epoch": 0.02, "learning_rate": 3.275626440106318e-05, "loss": 3.984, "step": 1053184 }, { "epoch": 0.02, "learning_rate": 3.274787845355266e-05, "loss": 3.979, "step": 1053696 }, { "epoch": 0.02, "learning_rate": 3.273949250604214e-05, "loss": 3.9739, "step": 1054208 }, { "epoch": 0.02, "learning_rate": 3.273110655853162e-05, "loss": 3.9817, "step": 1054720 }, { "epoch": 0.02, "learning_rate": 3.27227206110211e-05, "loss": 3.9752, "step": 1055232 }, { "epoch": 0.02, "learning_rate": 3.271433466351058e-05, "loss": 3.9708, "step": 1055744 }, { "epoch": 0.02, "learning_rate": 3.270594871600006e-05, "loss": 3.9655, "step": 1056256 }, { "epoch": 0.02, "learning_rate": 3.269756276848954e-05, "loss": 3.9743, "step": 1056768 }, { "epoch": 0.02, "learning_rate": 3.2689193199782756e-05, "loss": 3.9666, "step": 1057280 }, { "epoch": 0.02, "learning_rate": 3.2680807252272236e-05, "loss": 3.9707, "step": 1057792 }, { "epoch": 0.02, "learning_rate": 3.2672421304761716e-05, "loss": 3.9669, "step": 1058304 }, { "epoch": 0.02, "learning_rate": 3.2664035357251196e-05, "loss": 3.9794, "step": 1058816 }, { "epoch": 0.02, "learning_rate": 3.2655665788544405e-05, "loss": 3.9743, "step": 1059328 }, { "epoch": 0.02, "learning_rate": 3.2647279841033885e-05, "loss": 3.9691, "step": 1059840 }, { "epoch": 0.02, "learning_rate": 3.2638893893523365e-05, "loss": 3.9809, "step": 1060352 }, { "epoch": 0.02, "learning_rate": 3.2630507946012845e-05, "loss": 3.9824, "step": 1060864 }, { "epoch": 0.02, "learning_rate": 3.2622138377306054e-05, "loss": 3.9808, "step": 1061376 }, { "epoch": 0.02, "learning_rate": 3.2613752429795534e-05, "loss": 3.9741, "step": 1061888 }, { "epoch": 0.02, "learning_rate": 3.2605366482285014e-05, "loss": 3.9713, "step": 1062400 }, { "epoch": 0.02, "learning_rate": 3.259699691357822e-05, "loss": 3.9877, "step": 1062912 }, { "epoch": 0.02, "learning_rate": 3.258861096606771e-05, "loss": 3.975, "step": 1063424 }, { "epoch": 0.02, "learning_rate": 3.258022501855719e-05, "loss": 3.981, "step": 1063936 }, { "epoch": 0.02, "learning_rate": 3.257183907104667e-05, "loss": 3.9695, "step": 1064448 }, { "epoch": 0.02, "learning_rate": 3.256345312353615e-05, "loss": 3.9765, "step": 1064960 }, { "epoch": 0.02, "learning_rate": 3.255506717602563e-05, "loss": 3.9736, "step": 1065472 }, { "epoch": 0.02, "learning_rate": 3.254668122851511e-05, "loss": 3.971, "step": 1065984 }, { "epoch": 0.02, "learning_rate": 3.253829528100459e-05, "loss": 3.9746, "step": 1066496 }, { "epoch": 0.02, "learning_rate": 3.252994209110153e-05, "loss": 3.9736, "step": 1067008 }, { "epoch": 0.02, "learning_rate": 3.252155614359101e-05, "loss": 3.9766, "step": 1067520 }, { "epoch": 0.02, "learning_rate": 3.2513186574884216e-05, "loss": 3.9758, "step": 1068032 }, { "epoch": 0.03, "eval_loss": 4.02774715423584, "eval_runtime": 293.5696, "eval_samples_per_second": 1299.831, "eval_steps_per_second": 40.621, "step": 1068480 }, { "epoch": 1.0, "learning_rate": 3.2504800627373696e-05, "loss": 3.9733, "step": 1068544 }, { "epoch": 1.0, "learning_rate": 3.2496414679863176e-05, "loss": 3.9643, "step": 1069056 }, { "epoch": 1.0, "learning_rate": 3.248802873235266e-05, "loss": 3.9658, "step": 1069568 }, { "epoch": 1.0, "learning_rate": 3.247964278484214e-05, "loss": 3.9817, "step": 1070080 }, { "epoch": 1.0, "learning_rate": 3.247125683733162e-05, "loss": 3.975, "step": 1070592 }, { "epoch": 1.0, "learning_rate": 3.24628708898211e-05, "loss": 3.9851, "step": 1071104 }, { "epoch": 1.0, "learning_rate": 3.245448494231058e-05, "loss": 3.9661, "step": 1071616 }, { "epoch": 1.0, "learning_rate": 3.244611537360379e-05, "loss": 3.9682, "step": 1072128 }, { "epoch": 1.0, "learning_rate": 3.243772942609327e-05, "loss": 3.9614, "step": 1072640 }, { "epoch": 1.0, "learning_rate": 3.242935985738648e-05, "loss": 3.9729, "step": 1073152 }, { "epoch": 1.0, "learning_rate": 3.242097390987596e-05, "loss": 3.9737, "step": 1073664 }, { "epoch": 1.0, "learning_rate": 3.241258796236544e-05, "loss": 3.9717, "step": 1074176 }, { "epoch": 1.0, "learning_rate": 3.240421839365865e-05, "loss": 3.9796, "step": 1074688 }, { "epoch": 1.0, "learning_rate": 3.239583244614813e-05, "loss": 3.9585, "step": 1075200 }, { "epoch": 1.0, "learning_rate": 3.238744649863762e-05, "loss": 3.966, "step": 1075712 }, { "epoch": 1.0, "learning_rate": 3.23790605511271e-05, "loss": 3.9607, "step": 1076224 }, { "epoch": 1.0, "learning_rate": 3.237067460361658e-05, "loss": 3.9746, "step": 1076736 }, { "epoch": 1.0, "learning_rate": 3.236228865610606e-05, "loss": 3.964, "step": 1077248 }, { "epoch": 1.0, "learning_rate": 3.2353902708595537e-05, "loss": 3.9741, "step": 1077760 }, { "epoch": 1.0, "learning_rate": 3.234551676108501e-05, "loss": 3.9629, "step": 1078272 }, { "epoch": 1.0, "learning_rate": 3.233713081357449e-05, "loss": 3.9881, "step": 1078784 }, { "epoch": 1.0, "learning_rate": 3.232874486606397e-05, "loss": 3.9707, "step": 1079296 }, { "epoch": 1.0, "learning_rate": 3.232035891855345e-05, "loss": 3.9704, "step": 1079808 }, { "epoch": 1.0, "learning_rate": 3.231197297104293e-05, "loss": 3.973, "step": 1080320 }, { "epoch": 1.0, "learning_rate": 3.230358702353241e-05, "loss": 3.9784, "step": 1080832 }, { "epoch": 1.0, "learning_rate": 3.229520107602189e-05, "loss": 3.971, "step": 1081344 }, { "epoch": 1.0, "learning_rate": 3.228681512851137e-05, "loss": 3.9635, "step": 1081856 }, { "epoch": 1.0, "learning_rate": 3.227842918100085e-05, "loss": 3.9721, "step": 1082368 }, { "epoch": 1.0, "learning_rate": 3.2270059612294065e-05, "loss": 3.9598, "step": 1082880 }, { "epoch": 1.0, "learning_rate": 3.2261673664783545e-05, "loss": 3.9662, "step": 1083392 }, { "epoch": 1.01, "learning_rate": 3.2253287717273025e-05, "loss": 3.9684, "step": 1083904 }, { "epoch": 1.01, "learning_rate": 3.2244901769762505e-05, "loss": 3.9657, "step": 1084416 }, { "epoch": 1.01, "learning_rate": 3.2236532201055714e-05, "loss": 3.9712, "step": 1084928 }, { "epoch": 1.01, "learning_rate": 3.222816263234892e-05, "loss": 3.9796, "step": 1085440 }, { "epoch": 1.01, "learning_rate": 3.22197766848384e-05, "loss": 3.9726, "step": 1085952 }, { "epoch": 1.01, "learning_rate": 3.221139073732788e-05, "loss": 3.9756, "step": 1086464 }, { "epoch": 1.01, "learning_rate": 3.220300478981736e-05, "loss": 3.976, "step": 1086976 }, { "epoch": 1.01, "learning_rate": 3.219463522111057e-05, "loss": 3.9603, "step": 1087488 }, { "epoch": 1.01, "learning_rate": 3.218624927360005e-05, "loss": 3.9755, "step": 1088000 }, { "epoch": 1.01, "learning_rate": 3.217786332608954e-05, "loss": 3.9652, "step": 1088512 }, { "epoch": 1.01, "learning_rate": 3.216947737857902e-05, "loss": 3.9662, "step": 1089024 }, { "epoch": 1.01, "learning_rate": 3.21610914310685e-05, "loss": 3.9716, "step": 1089536 }, { "epoch": 1.01, "learning_rate": 3.215270548355798e-05, "loss": 3.979, "step": 1090048 }, { "epoch": 1.01, "learning_rate": 3.214433591485119e-05, "loss": 3.96, "step": 1090560 }, { "epoch": 1.01, "learning_rate": 3.213594996734067e-05, "loss": 3.9799, "step": 1091072 }, { "epoch": 1.01, "learning_rate": 3.212756401983015e-05, "loss": 3.9702, "step": 1091584 }, { "epoch": 1.01, "learning_rate": 3.211917807231963e-05, "loss": 3.971, "step": 1092096 }, { "epoch": 1.01, "learning_rate": 3.211079212480911e-05, "loss": 3.9755, "step": 1092608 }, { "epoch": 1.01, "learning_rate": 3.210242255610232e-05, "loss": 3.9421, "step": 1093120 }, { "epoch": 1.01, "learning_rate": 3.20940366085918e-05, "loss": 3.9681, "step": 1093632 }, { "epoch": 1.01, "learning_rate": 3.208565066108128e-05, "loss": 3.9761, "step": 1094144 }, { "epoch": 1.01, "learning_rate": 3.207726471357076e-05, "loss": 3.971, "step": 1094656 }, { "epoch": 1.01, "learning_rate": 3.206889514486397e-05, "loss": 3.9576, "step": 1095168 }, { "epoch": 1.01, "learning_rate": 3.206050919735345e-05, "loss": 3.9542, "step": 1095680 }, { "epoch": 1.01, "learning_rate": 3.205212324984293e-05, "loss": 3.9495, "step": 1096192 }, { "epoch": 1.01, "learning_rate": 3.204373730233241e-05, "loss": 3.9552, "step": 1096704 }, { "epoch": 1.01, "learning_rate": 3.203536773362562e-05, "loss": 3.9822, "step": 1097216 }, { "epoch": 1.01, "learning_rate": 3.20269817861151e-05, "loss": 3.9471, "step": 1097728 }, { "epoch": 1.01, "learning_rate": 3.201859583860458e-05, "loss": 3.9765, "step": 1098240 }, { "epoch": 1.01, "learning_rate": 3.201020989109406e-05, "loss": 3.9659, "step": 1098752 }, { "epoch": 1.01, "learning_rate": 3.200182394358354e-05, "loss": 3.9516, "step": 1099264 }, { "epoch": 1.01, "learning_rate": 3.1993437996073015e-05, "loss": 3.9652, "step": 1099776 }, { "epoch": 1.01, "learning_rate": 3.1985052048562495e-05, "loss": 3.9548, "step": 1100288 }, { "epoch": 1.01, "learning_rate": 3.197668247985571e-05, "loss": 3.9535, "step": 1100800 }, { "epoch": 1.01, "learning_rate": 3.196829653234519e-05, "loss": 3.9523, "step": 1101312 }, { "epoch": 1.01, "learning_rate": 3.195991058483467e-05, "loss": 3.9715, "step": 1101824 }, { "epoch": 1.01, "learning_rate": 3.195152463732415e-05, "loss": 3.9627, "step": 1102336 }, { "epoch": 1.01, "learning_rate": 3.1943155068617366e-05, "loss": 3.9577, "step": 1102848 }, { "epoch": 1.01, "learning_rate": 3.1934769121106846e-05, "loss": 3.9526, "step": 1103360 }, { "epoch": 1.01, "learning_rate": 3.192638317359632e-05, "loss": 3.9601, "step": 1103872 }, { "epoch": 1.01, "learning_rate": 3.19179972260858e-05, "loss": 3.9732, "step": 1104384 }, { "epoch": 1.01, "learning_rate": 3.190961127857528e-05, "loss": 3.973, "step": 1104896 }, { "epoch": 1.01, "learning_rate": 3.190122533106476e-05, "loss": 3.9669, "step": 1105408 }, { "epoch": 1.01, "learning_rate": 3.189285576235797e-05, "loss": 3.9741, "step": 1105920 }, { "epoch": 1.01, "learning_rate": 3.188446981484745e-05, "loss": 3.9857, "step": 1106432 }, { "epoch": 1.01, "learning_rate": 3.187608386733693e-05, "loss": 3.9696, "step": 1106944 }, { "epoch": 1.01, "learning_rate": 3.186769791982641e-05, "loss": 3.9745, "step": 1107456 }, { "epoch": 1.01, "learning_rate": 3.1859311972315895e-05, "loss": 3.9613, "step": 1107968 }, { "epoch": 1.01, "learning_rate": 3.1850926024805375e-05, "loss": 3.9678, "step": 1108480 }, { "epoch": 1.01, "learning_rate": 3.1842540077294855e-05, "loss": 3.9633, "step": 1108992 }, { "epoch": 1.01, "learning_rate": 3.1834154129784335e-05, "loss": 3.96, "step": 1109504 }, { "epoch": 1.01, "learning_rate": 3.1825784561077544e-05, "loss": 3.9757, "step": 1110016 }, { "epoch": 1.01, "learning_rate": 3.1817398613567024e-05, "loss": 3.9784, "step": 1110528 }, { "epoch": 1.01, "learning_rate": 3.1809012666056504e-05, "loss": 3.9738, "step": 1111040 }, { "epoch": 1.01, "learning_rate": 3.1800626718545984e-05, "loss": 3.948, "step": 1111552 }, { "epoch": 1.01, "learning_rate": 3.179225714983919e-05, "loss": 3.9588, "step": 1112064 }, { "epoch": 1.01, "learning_rate": 3.178387120232867e-05, "loss": 3.9689, "step": 1112576 }, { "epoch": 1.01, "learning_rate": 3.177548525481815e-05, "loss": 3.9668, "step": 1113088 }, { "epoch": 1.01, "learning_rate": 3.176711568611136e-05, "loss": 3.962, "step": 1113600 }, { "epoch": 1.01, "learning_rate": 3.175872973860085e-05, "loss": 3.9685, "step": 1114112 }, { "epoch": 1.02, "learning_rate": 3.175034379109033e-05, "loss": 3.9635, "step": 1114624 }, { "epoch": 1.02, "learning_rate": 3.174195784357981e-05, "loss": 3.9612, "step": 1115136 }, { "epoch": 1.02, "learning_rate": 3.173357189606929e-05, "loss": 3.9604, "step": 1115648 }, { "epoch": 1.02, "learning_rate": 3.17252023273625e-05, "loss": 3.9764, "step": 1116160 }, { "epoch": 1.02, "learning_rate": 3.1716832758655707e-05, "loss": 3.9625, "step": 1116672 }, { "epoch": 1.02, "learning_rate": 3.1708446811145187e-05, "loss": 3.975, "step": 1117184 }, { "epoch": 1.02, "learning_rate": 3.1700060863634667e-05, "loss": 3.9562, "step": 1117696 }, { "epoch": 1.02, "learning_rate": 3.1691674916124146e-05, "loss": 3.9585, "step": 1118208 }, { "epoch": 1.02, "learning_rate": 3.1683288968613626e-05, "loss": 3.9657, "step": 1118720 }, { "epoch": 1.02, "learning_rate": 3.1674903021103106e-05, "loss": 3.9689, "step": 1119232 }, { "epoch": 1.02, "learning_rate": 3.1666517073592586e-05, "loss": 3.9728, "step": 1119744 }, { "epoch": 1.02, "learning_rate": 3.1658131126082066e-05, "loss": 3.9659, "step": 1120256 }, { "epoch": 1.02, "learning_rate": 3.1649745178571546e-05, "loss": 3.9659, "step": 1120768 }, { "epoch": 1.02, "learning_rate": 3.164135923106103e-05, "loss": 3.9639, "step": 1121280 }, { "epoch": 1.02, "learning_rate": 3.1632973283550506e-05, "loss": 3.9693, "step": 1121792 }, { "epoch": 1.02, "learning_rate": 3.1624587336039986e-05, "loss": 3.9521, "step": 1122304 }, { "epoch": 1.02, "learning_rate": 3.161623414613693e-05, "loss": 3.9585, "step": 1122816 }, { "epoch": 1.02, "learning_rate": 3.160784819862641e-05, "loss": 3.957, "step": 1123328 }, { "epoch": 1.02, "learning_rate": 3.159946225111589e-05, "loss": 3.9611, "step": 1123840 }, { "epoch": 1.02, "learning_rate": 3.159107630360537e-05, "loss": 3.9566, "step": 1124352 }, { "epoch": 1.02, "learning_rate": 3.158269035609485e-05, "loss": 3.9541, "step": 1124864 }, { "epoch": 1.02, "learning_rate": 3.1574304408584324e-05, "loss": 3.9511, "step": 1125376 }, { "epoch": 1.02, "learning_rate": 3.1565918461073804e-05, "loss": 3.9668, "step": 1125888 }, { "epoch": 1.02, "learning_rate": 3.155754889236702e-05, "loss": 3.9597, "step": 1126400 }, { "epoch": 1.02, "learning_rate": 3.15491629448565e-05, "loss": 3.96, "step": 1126912 }, { "epoch": 1.02, "learning_rate": 3.154077699734598e-05, "loss": 3.9626, "step": 1127424 }, { "epoch": 1.02, "learning_rate": 3.153239104983546e-05, "loss": 3.9709, "step": 1127936 }, { "epoch": 1.02, "learning_rate": 3.1524021481128676e-05, "loss": 3.9632, "step": 1128448 }, { "epoch": 1.02, "learning_rate": 3.151563553361815e-05, "loss": 3.9591, "step": 1128960 }, { "epoch": 1.02, "learning_rate": 3.1507265964911365e-05, "loss": 3.9737, "step": 1129472 }, { "epoch": 1.02, "learning_rate": 3.1498880017400845e-05, "loss": 3.9677, "step": 1129984 }, { "epoch": 1.02, "learning_rate": 3.1490494069890325e-05, "loss": 3.9572, "step": 1130496 }, { "epoch": 1.02, "learning_rate": 3.14821081223798e-05, "loss": 3.9678, "step": 1131008 }, { "epoch": 1.02, "learning_rate": 3.147372217486928e-05, "loss": 3.9617, "step": 1131520 }, { "epoch": 1.02, "learning_rate": 3.146533622735876e-05, "loss": 3.9639, "step": 1132032 }, { "epoch": 1.02, "learning_rate": 3.145695027984824e-05, "loss": 3.9512, "step": 1132544 }, { "epoch": 1.02, "learning_rate": 3.144856433233772e-05, "loss": 3.9642, "step": 1133056 }, { "epoch": 1.02, "learning_rate": 3.1440178384827204e-05, "loss": 3.9556, "step": 1133568 }, { "epoch": 1.02, "learning_rate": 3.1431808816120413e-05, "loss": 3.9609, "step": 1134080 }, { "epoch": 1.02, "learning_rate": 3.1423422868609893e-05, "loss": 3.9477, "step": 1134592 }, { "epoch": 1.02, "learning_rate": 3.1415036921099373e-05, "loss": 3.9726, "step": 1135104 }, { "epoch": 1.02, "learning_rate": 3.140665097358885e-05, "loss": 3.9641, "step": 1135616 }, { "epoch": 1.02, "learning_rate": 3.139826502607833e-05, "loss": 3.9539, "step": 1136128 }, { "epoch": 1.02, "learning_rate": 3.138987907856781e-05, "loss": 3.9705, "step": 1136640 }, { "epoch": 1.02, "learning_rate": 3.138149313105729e-05, "loss": 3.9673, "step": 1137152 }, { "epoch": 1.02, "learning_rate": 3.137310718354677e-05, "loss": 3.9703, "step": 1137664 }, { "epoch": 1.02, "learning_rate": 3.136473761483998e-05, "loss": 3.9621, "step": 1138176 }, { "epoch": 1.02, "learning_rate": 3.135636804613319e-05, "loss": 3.9634, "step": 1138688 }, { "epoch": 1.02, "learning_rate": 3.134798209862267e-05, "loss": 3.9735, "step": 1139200 }, { "epoch": 1.02, "learning_rate": 3.133959615111216e-05, "loss": 3.9615, "step": 1139712 }, { "epoch": 1.02, "learning_rate": 3.133121020360164e-05, "loss": 3.9694, "step": 1140224 }, { "epoch": 1.02, "learning_rate": 3.132282425609112e-05, "loss": 3.9569, "step": 1140736 }, { "epoch": 1.02, "learning_rate": 3.13144383085806e-05, "loss": 3.9656, "step": 1141248 }, { "epoch": 1.02, "learning_rate": 3.130605236107008e-05, "loss": 3.9594, "step": 1141760 }, { "epoch": 1.02, "learning_rate": 3.129766641355956e-05, "loss": 3.9585, "step": 1142272 }, { "epoch": 1.02, "learning_rate": 3.1289313223656496e-05, "loss": 3.9626, "step": 1142784 }, { "epoch": 1.02, "learning_rate": 3.1280927276145976e-05, "loss": 3.9612, "step": 1143296 }, { "epoch": 1.02, "learning_rate": 3.1272541328635456e-05, "loss": 3.9669, "step": 1143808 }, { "epoch": 1.02, "learning_rate": 3.1264155381124936e-05, "loss": 3.965, "step": 1144320 }, { "epoch": 1.03, "eval_loss": 4.020888805389404, "eval_runtime": 299.232, "eval_samples_per_second": 1275.235, "eval_steps_per_second": 39.852, "step": 1144800 }, { "epoch": 0.0, "learning_rate": 3.1255769433614416e-05, "loss": 3.8962, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.1247383486103896e-05, "loss": 3.9559, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.1238997538593376e-05, "loss": 3.9532, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.1230611591082856e-05, "loss": 3.9663, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.122222564357234e-05, "loss": 3.9592, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.1213839696061816e-05, "loss": 3.975, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.1205453748551296e-05, "loss": 3.9534, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.1197067801040776e-05, "loss": 3.9564, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.1188681853530256e-05, "loss": 3.9488, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.1180295906019735e-05, "loss": 3.9639, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.1171909958509215e-05, "loss": 3.9558, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.1163524010998695e-05, "loss": 3.9646, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.1155154442291904e-05, "loss": 3.967, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.1146768494781384e-05, "loss": 3.9482, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.1138382547270864e-05, "loss": 3.9507, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.1129996599760344e-05, "loss": 3.9501, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.1121610652249824e-05, "loss": 3.9579, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.111322470473931e-05, "loss": 3.9553, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.110483875722879e-05, "loss": 3.9595, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.109645280971827e-05, "loss": 3.9511, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.108808324101148e-05, "loss": 3.9737, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.107969729350096e-05, "loss": 3.9583, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.107131134599044e-05, "loss": 3.9619, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.106292539847992e-05, "loss": 3.9601, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.10545394509694e-05, "loss": 3.9675, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104615350345887e-05, "loss": 3.9591, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.103776755594835e-05, "loss": 3.9541, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.102938160843783e-05, "loss": 3.9594, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102099566092731e-05, "loss": 3.9471, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.101262609222053e-05, "loss": 3.9575, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.100424014471001e-05, "loss": 3.9524, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.099585419719949e-05, "loss": 3.9603, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.098746824968897e-05, "loss": 3.9552, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.097908230217845e-05, "loss": 3.9634, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.097071273347166e-05, "loss": 3.9667, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.096232678596114e-05, "loss": 3.9622, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.095394083845062e-05, "loss": 3.9621, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.09455548909401e-05, "loss": 3.9487, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.093716894342958e-05, "loss": 3.9635, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.092878299591906e-05, "loss": 3.9537, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.0920413427212267e-05, "loss": 3.9535, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.0912027479701747e-05, "loss": 3.9607, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.0903641532191227e-05, "loss": 3.9652, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.089525558468071e-05, "loss": 3.9504, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.088686963717019e-05, "loss": 3.9632, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.08785000684634e-05, "loss": 3.9598, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.087011412095288e-05, "loss": 3.9578, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.086172817344236e-05, "loss": 3.9647, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.085334222593184e-05, "loss": 3.9329, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.084495627842132e-05, "loss": 3.9486, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.08365703309108e-05, "loss": 3.9653, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.082818438340028e-05, "loss": 3.9593, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.081981481469349e-05, "loss": 3.9489, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.081142886718297e-05, "loss": 3.9379, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080304291967245e-05, "loss": 3.9464, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.079465697216193e-05, "loss": 3.937, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.078628740345515e-05, "loss": 3.9729, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077790145594463e-05, "loss": 3.9338, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.076951550843411e-05, "loss": 3.9615, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076112956092359e-05, "loss": 3.9528, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075274361341306e-05, "loss": 3.9426, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.074435766590254e-05, "loss": 3.951, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.0735988097195756e-05, "loss": 3.9463, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.0727602149685236e-05, "loss": 3.9407, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.071921620217471e-05, "loss": 3.9399, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071083025466419e-05, "loss": 3.9626, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.070244430715367e-05, "loss": 3.95, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.069405835964315e-05, "loss": 3.9466, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.0685672412132635e-05, "loss": 3.9382, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.0677286464622115e-05, "loss": 3.9471, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.0668916895915325e-05, "loss": 3.9592, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.0660530948404804e-05, "loss": 3.9631, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0652145000894284e-05, "loss": 3.9578, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.0643775432187494e-05, "loss": 3.9596, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.0635389484676973e-05, "loss": 3.9724, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.0627003537166453e-05, "loss": 3.9622, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.0618617589655933e-05, "loss": 3.9603, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.061023164214541e-05, "loss": 3.9475, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.060184569463489e-05, "loss": 3.9577, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.059345974712437e-05, "loss": 3.9499, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.058507379961385e-05, "loss": 3.9515, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.057670423090707e-05, "loss": 3.9603, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.056833466220028e-05, "loss": 3.968, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.055994871468976e-05, "loss": 3.9571, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.055157914598297e-05, "loss": 3.9404, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.054319319847245e-05, "loss": 3.946, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.053480725096193e-05, "loss": 3.9518, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.052642130345141e-05, "loss": 3.96, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.051803535594089e-05, "loss": 3.9463, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.0509649408430367e-05, "loss": 3.9584, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.050127983972358e-05, "loss": 3.9565, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.049289389221306e-05, "loss": 3.9468, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.048450794470254e-05, "loss": 3.9488, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.047612199719202e-05, "loss": 3.9618, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.04677360496815e-05, "loss": 3.9516, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.045935010217098e-05, "loss": 3.9633, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.045096415466046e-05, "loss": 3.9479, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.0442578207149943e-05, "loss": 3.9465, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.043420863844315e-05, "loss": 3.9525, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.042582269093263e-05, "loss": 3.9591, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.041743674342211e-05, "loss": 3.9576, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.040905079591159e-05, "loss": 3.9577, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0400681227204804e-05, "loss": 3.956, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0392295279694284e-05, "loss": 3.9526, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.0383909332183764e-05, "loss": 3.9547, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.0375523384673244e-05, "loss": 3.9396, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.0367153815966453e-05, "loss": 3.945, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.0358767868455933e-05, "loss": 3.952, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0350381920945413e-05, "loss": 3.9459, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.0341995973434896e-05, "loss": 3.9463, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.033361002592437e-05, "loss": 3.9439, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.0325240457217585e-05, "loss": 3.9383, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.0316854509707065e-05, "loss": 3.9533, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.0308468562196545e-05, "loss": 3.9429, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.0300082614686022e-05, "loss": 3.9538, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.0291696667175502e-05, "loss": 3.9488, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.028331071966498e-05, "loss": 3.958, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.027492477215446e-05, "loss": 3.9521, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.026653882464394e-05, "loss": 3.9494, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.0258185634740887e-05, "loss": 3.9576, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0249799687230367e-05, "loss": 3.956, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.0241413739719843e-05, "loss": 3.9505, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.0233027792209323e-05, "loss": 3.9562, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.0224641844698803e-05, "loss": 3.9511, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.0216255897188283e-05, "loss": 3.9519, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.0207869949677763e-05, "loss": 3.9432, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.0199484002167243e-05, "loss": 3.9481, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.0191114433460455e-05, "loss": 3.9431, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.0182728485949935e-05, "loss": 3.9475, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.0174342538439415e-05, "loss": 3.9378, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.0165956590928895e-05, "loss": 3.9651, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.0157570643418375e-05, "loss": 3.9514, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.0149184695907855e-05, "loss": 3.948, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.0140798748397335e-05, "loss": 3.9527, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.0132429179690548e-05, "loss": 3.9519, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.0124043232180028e-05, "loss": 3.9618, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0115657284669508e-05, "loss": 3.9528, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0107271337158987e-05, "loss": 3.9512, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0098901768452197e-05, "loss": 3.9603, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0090515820941677e-05, "loss": 3.9464, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.008212987343116e-05, "loss": 3.9578, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.007374392592064e-05, "loss": 3.9489, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.006535797841012e-05, "loss": 3.957, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.005698840970333e-05, "loss": 3.9512, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.004860246219281e-05, "loss": 3.9398, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.004021651468229e-05, "loss": 3.9551, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.003183056717177e-05, "loss": 3.9498, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.0023444619661252e-05, "loss": 3.954, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.001507505095446e-05, "loss": 3.9511, "step": 1220608 }, { "epoch": 0.03, "learning_rate": 3.000668910344394e-05, "loss": 3.9495, "step": 1221120 }, { "epoch": 0.03, "eval_loss": 4.01515531539917, "eval_runtime": 310.0572, "eval_samples_per_second": 1230.712, "eval_steps_per_second": 38.461, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.999830315593342e-05, "loss": 3.9435, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.99899172084229e-05, "loss": 3.9386, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.998153126091238e-05, "loss": 3.958, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.9973145313401858e-05, "loss": 3.9504, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.9964759365891338e-05, "loss": 3.9619, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.9956373418380817e-05, "loss": 3.9435, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.9947987470870297e-05, "loss": 3.9433, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.9939617902163507e-05, "loss": 3.935, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.993123195465299e-05, "loss": 3.9559, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.992284600714247e-05, "loss": 3.9454, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.991446005963195e-05, "loss": 3.953, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.990607411212143e-05, "loss": 3.9512, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.9897720922218375e-05, "loss": 3.9416, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.988933497470785e-05, "loss": 3.9402, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.9880965406001067e-05, "loss": 3.9411, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.9872579458490547e-05, "loss": 3.9397, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.9864193510980027e-05, "loss": 3.9487, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.98558075634695e-05, "loss": 3.9472, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.984742161595898e-05, "loss": 3.9406, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.983903566844846e-05, "loss": 3.9666, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.9830649720937944e-05, "loss": 3.9424, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.9822263773427424e-05, "loss": 3.9536, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.9813877825916903e-05, "loss": 3.9484, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.9805491878406383e-05, "loss": 3.957, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.9797105930895863e-05, "loss": 3.9434, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.9788752740992805e-05, "loss": 3.946, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.9780366793482285e-05, "loss": 3.9409, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9771980845971765e-05, "loss": 3.9437, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.9763594898461245e-05, "loss": 3.9422, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.9755208950950725e-05, "loss": 3.9409, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.9746823003440205e-05, "loss": 3.9491, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9738437055929685e-05, "loss": 3.9468, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.9730051108419165e-05, "loss": 3.9508, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.9721665160908645e-05, "loss": 3.9564, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.9713279213398128e-05, "loss": 3.9514, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.9704893265887608e-05, "loss": 3.9501, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.9696523697180817e-05, "loss": 3.9449, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.9688137749670297e-05, "loss": 3.9472, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.9679751802159777e-05, "loss": 3.9426, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.9671365854649257e-05, "loss": 3.9462, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.9662979907138737e-05, "loss": 3.946, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.965461033843195e-05, "loss": 3.9543, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.964624076972516e-05, "loss": 3.9395, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.963785482221464e-05, "loss": 3.9509, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.962946887470412e-05, "loss": 3.9513, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.96210829271936e-05, "loss": 3.9496, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.961269697968308e-05, "loss": 3.9505, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.960431103217256e-05, "loss": 3.924, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.959592508466204e-05, "loss": 3.9387, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.9587539137151515e-05, "loss": 3.9525, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.9579153189640995e-05, "loss": 3.9493, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.9570767242130475e-05, "loss": 3.9381, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.9562397673423687e-05, "loss": 3.927, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.9554011725913167e-05, "loss": 3.9335, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.9545642157206383e-05, "loss": 3.9288, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.9537256209695863e-05, "loss": 3.96, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.9528870262185336e-05, "loss": 3.9287, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.952048431467482e-05, "loss": 3.9486, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.95120983671643e-05, "loss": 3.9474, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.950371241965378e-05, "loss": 3.9298, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.949532647214326e-05, "loss": 3.9417, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.948694052463274e-05, "loss": 3.938, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.947855457712222e-05, "loss": 3.9276, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.94701686296117e-05, "loss": 3.9294, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.946178268210118e-05, "loss": 3.9539, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.945339673459066e-05, "loss": 3.9424, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.944501078708014e-05, "loss": 3.934, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.943664121837335e-05, "loss": 3.9297, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.942825527086283e-05, "loss": 3.9367, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.941986932335231e-05, "loss": 3.9485, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.941148337584179e-05, "loss": 3.9524, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.9403113807135e-05, "loss": 3.9455, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9394744238428213e-05, "loss": 3.9531, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9386358290917693e-05, "loss": 3.9589, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9377972343407173e-05, "loss": 3.951, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.9369586395896653e-05, "loss": 3.9472, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.9361200448386133e-05, "loss": 3.9391, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.9352830879679345e-05, "loss": 3.9479, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.9344444932168825e-05, "loss": 3.9439, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9336058984658305e-05, "loss": 3.9401, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9327673037147785e-05, "loss": 3.9468, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9319287089637265e-05, "loss": 3.9525, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9310901142126745e-05, "loss": 3.9506, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9302515194616225e-05, "loss": 3.9296, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.92941292471057e-05, "loss": 3.9335, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.928574329959518e-05, "loss": 3.9447, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.9277373730888397e-05, "loss": 3.9499, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.926898778337787e-05, "loss": 3.9393, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.9260618214671086e-05, "loss": 3.9452, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.9252232267160566e-05, "loss": 3.949, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.9243846319650046e-05, "loss": 3.936, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.9235460372139523e-05, "loss": 3.9374, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.9227074424629003e-05, "loss": 3.9475, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.921870485592222e-05, "loss": 3.9435, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.92103189084117e-05, "loss": 3.948, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.9201932960901175e-05, "loss": 3.9438, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.9193547013390655e-05, "loss": 3.9312, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.9185161065880135e-05, "loss": 3.9456, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.9176791497173344e-05, "loss": 3.9484, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.9168405549662824e-05, "loss": 3.9452, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.9160019602152304e-05, "loss": 3.9487, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.9151633654641784e-05, "loss": 3.9424, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.9143247707131268e-05, "loss": 3.9447, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.9134878138424477e-05, "loss": 3.9494, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.9126492190913957e-05, "loss": 3.927, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.9118106243403437e-05, "loss": 3.9316, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9109720295892916e-05, "loss": 3.9429, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9101334348382396e-05, "loss": 3.9405, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9092948400871876e-05, "loss": 3.9299, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.908456245336136e-05, "loss": 3.934, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.907617650585084e-05, "loss": 3.9332, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.906779055834032e-05, "loss": 3.9415, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.905942098963353e-05, "loss": 3.9368, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9051051420926738e-05, "loss": 3.9402, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.904266547341622e-05, "loss": 3.9394, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.90342795259057e-05, "loss": 3.9459, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.902589357839518e-05, "loss": 3.9443, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.901750763088466e-05, "loss": 3.9417, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.900912168337414e-05, "loss": 3.9497, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.900075211466735e-05, "loss": 3.9484, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.899236616715683e-05, "loss": 3.9359, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.8983980219646313e-05, "loss": 3.947, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.8975594272135793e-05, "loss": 3.9373, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.8967224703429002e-05, "loss": 3.9492, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.8958838755918482e-05, "loss": 3.9281, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.8950452808407962e-05, "loss": 3.9421, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.8942066860897442e-05, "loss": 3.9285, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.8933697292190655e-05, "loss": 3.9354, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.8925311344680135e-05, "loss": 3.9255, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.8916925397169615e-05, "loss": 3.9542, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.8908539449659095e-05, "loss": 3.9467, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.8900169880952304e-05, "loss": 3.9354, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.8891783933441784e-05, "loss": 3.9399, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.8883397985931264e-05, "loss": 3.9427, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.8875012038420747e-05, "loss": 3.9512, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.8866626090910227e-05, "loss": 3.9475, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.8858256522203436e-05, "loss": 3.9385, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.8849870574692916e-05, "loss": 3.9501, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.8841484627182396e-05, "loss": 3.9374, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8833098679671876e-05, "loss": 3.9508, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8824712732161356e-05, "loss": 3.938, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.8816326784650832e-05, "loss": 3.9426, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.880795721594405e-05, "loss": 3.9436, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.8799571268433528e-05, "loss": 3.9338, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.8791185320923008e-05, "loss": 3.9414, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8782799373412485e-05, "loss": 3.9422, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8774413425901965e-05, "loss": 3.9435, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8766027478391445e-05, "loss": 3.9432, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.8757641530880925e-05, "loss": 3.9368, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 4.0103278160095215, "eval_runtime": 322.3181, "eval_samples_per_second": 1183.896, "eval_steps_per_second": 36.998, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.8749255583370405e-05, "loss": 3.9316, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.8740869635859885e-05, "loss": 3.9308, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.8732483688349365e-05, "loss": 3.9473, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.8724097740838845e-05, "loss": 3.9363, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.8715711793328324e-05, "loss": 3.9558, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.8707325845817808e-05, "loss": 3.9327, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8698939898307288e-05, "loss": 3.9355, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.8690553950796768e-05, "loss": 3.9258, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.8682168003286248e-05, "loss": 3.9442, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.867378205577572e-05, "loss": 3.9377, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.86653961082652e-05, "loss": 3.9409, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.8657010160754684e-05, "loss": 3.9423, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.8648640592047893e-05, "loss": 3.9293, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.8640254644537373e-05, "loss": 3.9323, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8631868697026853e-05, "loss": 3.9321, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.8623482749516333e-05, "loss": 3.9283, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.8615096802005813e-05, "loss": 3.9366, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.8606710854495293e-05, "loss": 3.9366, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.8598324906984776e-05, "loss": 3.9324, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.8589938959474256e-05, "loss": 3.9569, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.8581569390767465e-05, "loss": 3.9322, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.8573183443256945e-05, "loss": 3.9432, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.8564797495746425e-05, "loss": 3.9399, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.8556411548235905e-05, "loss": 3.9485, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8548025600725385e-05, "loss": 3.9263, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8539639653214865e-05, "loss": 3.9377, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8531270084508078e-05, "loss": 3.9309, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8522884136997558e-05, "loss": 3.9411, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.8514498189487038e-05, "loss": 3.9246, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.8506112241976518e-05, "loss": 3.9304, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.8497726294465998e-05, "loss": 3.941, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.848935672575921e-05, "loss": 3.9373, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.848097077824869e-05, "loss": 3.9383, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.84726012095419e-05, "loss": 3.9481, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.846421526203138e-05, "loss": 3.9421, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.845582931452086e-05, "loss": 3.9391, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.844744336701034e-05, "loss": 3.933, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.843905741949982e-05, "loss": 3.9421, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.843068785079303e-05, "loss": 3.9301, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.842230190328251e-05, "loss": 3.936, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.841391595577199e-05, "loss": 3.9394, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.840553000826147e-05, "loss": 3.945, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.839714406075095e-05, "loss": 3.9279, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.838875811324043e-05, "loss": 3.939, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8380372165729908e-05, "loss": 3.9466, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8372002597023124e-05, "loss": 3.9387, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8363616649512604e-05, "loss": 3.9423, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8355230702002083e-05, "loss": 3.9143, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8346844754491557e-05, "loss": 3.9242, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.833845880698104e-05, "loss": 3.9448, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.833007285947052e-05, "loss": 3.9372, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.832168691196e-05, "loss": 3.9323, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.831330096444948e-05, "loss": 3.9182, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.830491501693896e-05, "loss": 3.9237, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.829652906942844e-05, "loss": 3.919, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.828815950072165e-05, "loss": 3.9464, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8279773553211132e-05, "loss": 3.9204, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.8271387605700612e-05, "loss": 3.9362, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.8263001658190092e-05, "loss": 3.939, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.8254615710679572e-05, "loss": 3.9233, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.8246229763169052e-05, "loss": 3.9298, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.8237843815658532e-05, "loss": 3.9264, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.8229457868148012e-05, "loss": 3.9208, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.8221088299441224e-05, "loss": 3.9212, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.8212718730734434e-05, "loss": 3.9383, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.8204332783223913e-05, "loss": 3.934, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.8195946835713393e-05, "loss": 3.9218, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.8187560888202873e-05, "loss": 3.9212, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.8179174940692353e-05, "loss": 3.9232, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.8170788993181833e-05, "loss": 3.9384, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.8162403045671317e-05, "loss": 3.9431, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.8154033476964526e-05, "loss": 3.9366, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.8145663908257735e-05, "loss": 3.9468, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8137277960747215e-05, "loss": 3.9448, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.8128892013236695e-05, "loss": 3.9448, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.8120506065726178e-05, "loss": 3.9362, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.8112120118215658e-05, "loss": 3.9324, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.8103734170705138e-05, "loss": 3.9367, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.8095348223194618e-05, "loss": 3.9327, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.808696227568409e-05, "loss": 3.9297, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.807857632817357e-05, "loss": 3.9373, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8070190380663054e-05, "loss": 3.9453, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8061804433152534e-05, "loss": 3.9359, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8053434864445744e-05, "loss": 3.9241, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.8045048916935223e-05, "loss": 3.9244, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.8036662969424703e-05, "loss": 3.9322, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.8028293400717916e-05, "loss": 3.9428, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.8019907453207396e-05, "loss": 3.9295, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.8011521505696876e-05, "loss": 3.9341, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8003135558186356e-05, "loss": 3.9388, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7994749610675836e-05, "loss": 3.929, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7986363663165316e-05, "loss": 3.9285, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7977977715654796e-05, "loss": 3.9322, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.7969591768144276e-05, "loss": 3.9367, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.7961222199437488e-05, "loss": 3.936, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.7952836251926968e-05, "loss": 3.9382, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.7944466683220177e-05, "loss": 3.9232, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.7936080735709657e-05, "loss": 3.936, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.7927694788199137e-05, "loss": 3.9334, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.7919308840688617e-05, "loss": 3.9415, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7910922893178097e-05, "loss": 3.9381, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.790255332447131e-05, "loss": 3.9345, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.789416737696079e-05, "loss": 3.9353, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.788578142945027e-05, "loss": 3.94, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.787739548193975e-05, "loss": 3.9189, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.786900953442923e-05, "loss": 3.9229, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.786062358691871e-05, "loss": 3.9317, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.785223763940819e-05, "loss": 3.9301, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7843851691897673e-05, "loss": 3.9215, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.7835465744387152e-05, "loss": 3.9241, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7827079796876632e-05, "loss": 3.925, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.7818693849366106e-05, "loss": 3.932, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7810307901855586e-05, "loss": 3.9262, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7801921954345066e-05, "loss": 3.9289, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7793552385638278e-05, "loss": 3.9328, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7785182816931494e-05, "loss": 3.9344, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.7776796869420974e-05, "loss": 3.9345, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.7768410921910454e-05, "loss": 3.9298, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.7760024974399927e-05, "loss": 3.9411, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.7751655405693143e-05, "loss": 3.9396, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.7743269458182626e-05, "loss": 3.9254, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.7734883510672106e-05, "loss": 3.9392, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.772649756316158e-05, "loss": 3.9278, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.771811161565106e-05, "loss": 3.9385, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.770972566814054e-05, "loss": 3.9166, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.7701356099433752e-05, "loss": 3.9365, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.7692986530726968e-05, "loss": 3.9162, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.7684600583216448e-05, "loss": 3.9251, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.7676214635705927e-05, "loss": 3.916, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.76678286881954e-05, "loss": 3.9448, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.765944274068488e-05, "loss": 3.9377, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.7651056793174364e-05, "loss": 3.9304, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7642670845663844e-05, "loss": 3.9281, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7634284898153324e-05, "loss": 3.9346, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.7625898950642804e-05, "loss": 3.9407, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.7617513003132284e-05, "loss": 3.935, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.7609127055621764e-05, "loss": 3.9303, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.7600741108111244e-05, "loss": 3.9367, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.7592355160600724e-05, "loss": 3.9303, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.7583985591893936e-05, "loss": 3.9437, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7575599644383416e-05, "loss": 3.9272, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.7567230075676625e-05, "loss": 3.932, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.7558844128166105e-05, "loss": 3.9312, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.7550458180655585e-05, "loss": 3.9251, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7542072233145065e-05, "loss": 3.9352, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7533702664438278e-05, "loss": 3.9292, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7525316716927758e-05, "loss": 3.934, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7516947148220967e-05, "loss": 3.9315, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7508561200710447e-05, "loss": 3.9259, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 4.005472660064697, "eval_runtime": 291.1903, "eval_samples_per_second": 1310.452, "eval_steps_per_second": 40.953, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.7500175253199927e-05, "loss": 3.9254, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.749178930568941e-05, "loss": 3.9227, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.748340335817889e-05, "loss": 3.9371, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.747501741066837e-05, "loss": 3.9257, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.746663146315785e-05, "loss": 3.948, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.745824551564733e-05, "loss": 3.9203, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.744985956813681e-05, "loss": 3.9267, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.744147362062629e-05, "loss": 3.9162, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7433104051919502e-05, "loss": 3.9356, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7424718104408982e-05, "loss": 3.9283, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.7416332156898462e-05, "loss": 3.9302, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.7407946209387935e-05, "loss": 3.9324, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.739957664068115e-05, "loss": 3.9181, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.739119069317063e-05, "loss": 3.9255, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.738280474566011e-05, "loss": 3.9242, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.7374418798149588e-05, "loss": 3.9223, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.7366032850639067e-05, "loss": 3.9244, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.7357646903128547e-05, "loss": 3.9279, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.7349260955618027e-05, "loss": 3.924, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.7340875008107507e-05, "loss": 3.9464, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7332489060596987e-05, "loss": 3.9242, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7324103113086467e-05, "loss": 3.9304, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.731571716557595e-05, "loss": 3.9313, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.730734759686916e-05, "loss": 3.9383, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.729896164935864e-05, "loss": 3.919, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.729057570184812e-05, "loss": 3.9323, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.728220613314133e-05, "loss": 3.9208, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7273820185630812e-05, "loss": 3.9296, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.7265434238120292e-05, "loss": 3.9169, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.7257048290609772e-05, "loss": 3.922, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.7248662343099252e-05, "loss": 3.9286, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.724029277439246e-05, "loss": 3.9315, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.723190682688194e-05, "loss": 3.9311, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.722352087937142e-05, "loss": 3.9377, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.7215134931860904e-05, "loss": 3.9286, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.7206748984350384e-05, "loss": 3.9325, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.7198379415643593e-05, "loss": 3.9208, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.7189993468133073e-05, "loss": 3.9348, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.7181607520622553e-05, "loss": 3.919, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.7173221573112033e-05, "loss": 3.9266, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.7164852004405246e-05, "loss": 3.926, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7156466056894726e-05, "loss": 3.9351, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7148080109384206e-05, "loss": 3.9259, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.7139694161873686e-05, "loss": 3.9253, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.7131308214363165e-05, "loss": 3.9366, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.7122922266852645e-05, "loss": 3.931, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.7114536319342125e-05, "loss": 3.93, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.7106150371831602e-05, "loss": 3.9151, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7097797181928547e-05, "loss": 3.9109, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7089411234418027e-05, "loss": 3.9293, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.7081025286907507e-05, "loss": 3.9285, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7072639339396987e-05, "loss": 3.9245, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7064253391886467e-05, "loss": 3.9097, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.705586744437595e-05, "loss": 3.9139, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7047481496865423e-05, "loss": 3.9152, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7039095549354903e-05, "loss": 3.9299, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7030709601844383e-05, "loss": 3.9133, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.70223400331376e-05, "loss": 3.927, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7013954085627076e-05, "loss": 3.9271, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7005568138116556e-05, "loss": 3.9161, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.699719856940977e-05, "loss": 3.9213, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6988812621899245e-05, "loss": 3.9194, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6980426674388725e-05, "loss": 3.9089, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.6972040726878205e-05, "loss": 3.9191, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.6963654779367688e-05, "loss": 3.9243, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.6955285210660897e-05, "loss": 3.9326, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.6946915641954113e-05, "loss": 3.9089, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.6938529694443593e-05, "loss": 3.9141, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.6930143746933066e-05, "loss": 3.9137, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.692175779942255e-05, "loss": 3.937, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.691337185191203e-05, "loss": 3.9254, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.690498590440151e-05, "loss": 3.9268, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.689659995689099e-05, "loss": 3.939, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.68882303881842e-05, "loss": 3.9359, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.687984444067368e-05, "loss": 3.9349, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.6871458493163158e-05, "loss": 3.9244, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.686307254565264e-05, "loss": 3.9275, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.685468659814212e-05, "loss": 3.9283, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.68463006506316e-05, "loss": 3.9225, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.683791470312108e-05, "loss": 3.9243, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.682952875561056e-05, "loss": 3.9256, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.682114280810004e-05, "loss": 3.9347, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.681275686058952e-05, "loss": 3.9262, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.680438729188273e-05, "loss": 3.919, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6796001344372214e-05, "loss": 3.9143, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6787615396861694e-05, "loss": 3.9247, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.6779245828154903e-05, "loss": 3.9311, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.6770859880644383e-05, "loss": 3.9234, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6762473933133863e-05, "loss": 3.923, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.6754087985623343e-05, "loss": 3.9311, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.6745702038112823e-05, "loss": 3.9131, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.6737316090602306e-05, "loss": 3.9245, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6728930143091786e-05, "loss": 3.9205, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.672054419558126e-05, "loss": 3.9304, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.6712174626874475e-05, "loss": 3.9286, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.6703788679363955e-05, "loss": 3.927, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669540273185343e-05, "loss": 3.9153, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668701678434291e-05, "loss": 3.9297, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.667863083683239e-05, "loss": 3.918, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.667024488932187e-05, "loss": 3.938, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.666185894181135e-05, "loss": 3.9261, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.665347299430083e-05, "loss": 3.9262, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.6645103425594044e-05, "loss": 3.9219, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6636717478083524e-05, "loss": 3.9335, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.6628331530573004e-05, "loss": 3.9089, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.6619945583062484e-05, "loss": 3.9151, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6611576014355693e-05, "loss": 3.9207, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6603190066845173e-05, "loss": 3.9222, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6594804119334653e-05, "loss": 3.9123, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6586418171824136e-05, "loss": 3.9173, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6578048603117345e-05, "loss": 3.9132, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6569662655606825e-05, "loss": 3.9228, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.6561276708096305e-05, "loss": 3.9169, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.6552890760585785e-05, "loss": 3.9138, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.6544504813075265e-05, "loss": 3.9289, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.6536135244368477e-05, "loss": 3.9285, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.6527749296857957e-05, "loss": 3.9264, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.6519363349347437e-05, "loss": 3.9179, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.6510977401836917e-05, "loss": 3.9334, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.6502607833130126e-05, "loss": 3.9266, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.6494221885619606e-05, "loss": 3.9189, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.648583593810909e-05, "loss": 3.9329, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.647744999059857e-05, "loss": 3.9165, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.646906404308805e-05, "loss": 3.9296, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.646067809557753e-05, "loss": 3.9102, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.645230852687074e-05, "loss": 3.9271, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.644392257936022e-05, "loss": 3.9073, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.64355366318497e-05, "loss": 3.9178, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.6427150684339182e-05, "loss": 3.9086, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.6418764736828662e-05, "loss": 3.9348, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.6410378789318142e-05, "loss": 3.9276, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.640200922061135e-05, "loss": 3.9254, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.639362327310083e-05, "loss": 3.9188, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.638523732559031e-05, "loss": 3.9248, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.637685137807979e-05, "loss": 3.937, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6368465430569267e-05, "loss": 3.9242, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6360079483058747e-05, "loss": 3.9218, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.6351693535548227e-05, "loss": 3.9313, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.6343307588037707e-05, "loss": 3.9235, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.633493801933092e-05, "loss": 3.9305, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.63265520718204e-05, "loss": 3.9195, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.631816612430988e-05, "loss": 3.9248, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.630978017679936e-05, "loss": 3.9206, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.630139422928884e-05, "loss": 3.9207, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.629302466058205e-05, "loss": 3.9208, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.628463871307153e-05, "loss": 3.9267, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.6276252765561012e-05, "loss": 3.9198, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.626788319685422e-05, "loss": 3.9243, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.62594972493437e-05, "loss": 3.9195, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 4.001229286193848, "eval_runtime": 310.4923, "eval_samples_per_second": 1228.987, "eval_steps_per_second": 38.407, "step": 1450080 }, { "epoch": 0.0, "learning_rate": 2.625111130183318e-05, "loss": 3.9162, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.624272535432266e-05, "loss": 3.9149, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.623433940681214e-05, "loss": 3.9273, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.622595345930162e-05, "loss": 3.9174, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.62175675117911e-05, "loss": 3.9422, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.6209181564280584e-05, "loss": 3.9106, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.6200795616770064e-05, "loss": 3.9192, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.6192409669259544e-05, "loss": 3.9079, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.6184023721749024e-05, "loss": 3.9269, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.6175637774238504e-05, "loss": 3.9226, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.6167251826727977e-05, "loss": 3.9185, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.615886587921746e-05, "loss": 3.9235, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.6150496310510676e-05, "loss": 3.9106, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.6142110363000156e-05, "loss": 3.9172, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.613372441548963e-05, "loss": 3.9165, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.612533846797911e-05, "loss": 3.915, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.611695252046859e-05, "loss": 3.9151, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.610856657295807e-05, "loss": 3.9193, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.6100180625447553e-05, "loss": 3.9175, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.6091794677937033e-05, "loss": 3.9352, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6083408730426513e-05, "loss": 3.9168, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6075022782915993e-05, "loss": 3.9222, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6066636835405472e-05, "loss": 3.9235, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6058250887894952e-05, "loss": 3.9305, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.604988131918816e-05, "loss": 3.9113, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.6041495371677645e-05, "loss": 3.9263, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.6033125802970854e-05, "loss": 3.9134, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.6024739855460334e-05, "loss": 3.9189, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.6016353907949814e-05, "loss": 3.9057, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.6007967960439294e-05, "loss": 3.9205, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.5999582012928774e-05, "loss": 3.9164, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.5991196065418254e-05, "loss": 3.9245, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.5982826496711466e-05, "loss": 3.9211, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.5974440549200946e-05, "loss": 3.9289, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.5966054601690426e-05, "loss": 3.9178, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.5957668654179906e-05, "loss": 3.9249, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.5949299085473115e-05, "loss": 3.915, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.59409131379626e-05, "loss": 3.9247, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.593252719045208e-05, "loss": 3.9108, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.592414124294156e-05, "loss": 3.919, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.591575529543104e-05, "loss": 3.9178, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.590736934792052e-05, "loss": 3.9291, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.5898999779213727e-05, "loss": 3.9174, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.5890613831703207e-05, "loss": 3.919, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.588222788419269e-05, "loss": 3.9258, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.587384193668217e-05, "loss": 3.921, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.5865455989171644e-05, "loss": 3.9243, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.5857070041661124e-05, "loss": 3.9119, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.5848684094150604e-05, "loss": 3.897, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.5840330904247552e-05, "loss": 3.9222, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.5831944956737032e-05, "loss": 3.918, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.5823559009226512e-05, "loss": 3.9129, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.5815173061715992e-05, "loss": 3.9072, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.5806787114205465e-05, "loss": 3.9071, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.5798401166694945e-05, "loss": 3.9042, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.579001521918443e-05, "loss": 3.9229, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.578162927167391e-05, "loss": 3.9068, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.577324332416339e-05, "loss": 3.9154, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.576485737665287e-05, "loss": 3.9208, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.575647142914235e-05, "loss": 3.9087, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.574808548163183e-05, "loss": 3.909, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.5739699534121308e-05, "loss": 3.9153, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5731313586610788e-05, "loss": 3.8959, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.572296039670773e-05, "loss": 3.9134, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.571457444919721e-05, "loss": 3.9188, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.570618850168669e-05, "loss": 3.9199, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.569780255417617e-05, "loss": 3.9024, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.568941660666565e-05, "loss": 3.9084, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.568103065915513e-05, "loss": 3.9036, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.5672661090448342e-05, "loss": 3.9225, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.5664275142937822e-05, "loss": 3.9207, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.5655889195427302e-05, "loss": 3.9216, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.5647503247916782e-05, "loss": 3.9292, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.5639117300406262e-05, "loss": 3.9307, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.5630731352895742e-05, "loss": 3.9322, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5622378162992684e-05, "loss": 3.911, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.5613992215482163e-05, "loss": 3.9197, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.5605606267971643e-05, "loss": 3.9229, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.5597220320461123e-05, "loss": 3.9146, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.5588834372950603e-05, "loss": 3.9202, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.5580448425440083e-05, "loss": 3.9153, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5572078856733296e-05, "loss": 3.9249, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5563692909222776e-05, "loss": 3.9206, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.5555306961712256e-05, "loss": 3.9046, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.5546921014201736e-05, "loss": 3.9092, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.5538535066691216e-05, "loss": 3.9191, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.5530165497984425e-05, "loss": 3.9213, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.5521779550473908e-05, "loss": 3.9159, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.5513393602963388e-05, "loss": 3.9139, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.5505007655452868e-05, "loss": 3.9233, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.5496621707942348e-05, "loss": 3.9097, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.5488235760431828e-05, "loss": 3.9123, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.54798498129213e-05, "loss": 3.9173, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.5471463865410784e-05, "loss": 3.9235, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.5463077917900264e-05, "loss": 3.9225, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.5454691970389744e-05, "loss": 3.9165, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.5446306022879224e-05, "loss": 3.9026, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.5437920075368704e-05, "loss": 3.9254, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.5429550506661913e-05, "loss": 3.9076, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.5421164559151393e-05, "loss": 3.9294, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.5412778611640877e-05, "loss": 3.9196, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.5404392664130357e-05, "loss": 3.9175, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.5396006716619837e-05, "loss": 3.9137, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.5387620769109316e-05, "loss": 3.9265, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.5379234821598796e-05, "loss": 3.9019, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.5370848874088276e-05, "loss": 3.9103, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.5362495684185218e-05, "loss": 3.9076, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.5354109736674698e-05, "loss": 3.915, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.5345723789164178e-05, "loss": 3.9037, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.5337337841653658e-05, "loss": 3.9119, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5328951894143138e-05, "loss": 3.9097, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5320565946632618e-05, "loss": 3.9086, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.5312179999122098e-05, "loss": 3.9121, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.5303794051611578e-05, "loss": 3.9051, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.529542448290479e-05, "loss": 3.9243, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.528703853539427e-05, "loss": 3.9189, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.527866896668748e-05, "loss": 3.9213, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.527028301917696e-05, "loss": 3.9109, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.526189707166644e-05, "loss": 3.9233, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.525351112415592e-05, "loss": 3.9223, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5245125176645402e-05, "loss": 3.9079, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.523675560793861e-05, "loss": 3.9246, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.522836966042809e-05, "loss": 3.9097, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.521998371291757e-05, "loss": 3.921, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.521159776540705e-05, "loss": 3.9063, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.520321181789653e-05, "loss": 3.9175, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5194842249189744e-05, "loss": 3.8991, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.5186456301679224e-05, "loss": 3.9109, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.5178070354168704e-05, "loss": 3.9037, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.5169684406658184e-05, "loss": 3.9225, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.516129845914766e-05, "loss": 3.9129, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.5152928890440873e-05, "loss": 3.919, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.5144542942930356e-05, "loss": 3.9126, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.5136156995419836e-05, "loss": 3.9175, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.512777104790931e-05, "loss": 3.9265, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.511938510039879e-05, "loss": 3.9161, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.5111015531692005e-05, "loss": 3.9163, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.5102629584181485e-05, "loss": 3.923, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.5094260015474698e-05, "loss": 3.9146, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.5085874067964177e-05, "loss": 3.9259, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.5077488120453657e-05, "loss": 3.9073, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.506910217294313e-05, "loss": 3.9209, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.506071622543261e-05, "loss": 3.9134, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.505236303552956e-05, "loss": 3.9136, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.504397708801904e-05, "loss": 3.9186, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.503559114050852e-05, "loss": 3.9144, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.5027205192998e-05, "loss": 3.9125, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.501881924548748e-05, "loss": 3.9129, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.501043329797696e-05, "loss": 3.9172, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 3.9978137016296387, "eval_runtime": 297.9304, "eval_samples_per_second": 1280.806, "eval_steps_per_second": 40.026, "step": 1526400 }, { "epoch": 1.0, "learning_rate": 2.5002047350466435e-05, "loss": 3.9108, "step": 1526784 }, { "epoch": 1.0, "learning_rate": 2.499366140295592e-05, "loss": 3.9056, "step": 1527296 }, { "epoch": 1.0, "learning_rate": 2.49852754554454e-05, "loss": 3.9196, "step": 1527808 }, { "epoch": 1.0, "learning_rate": 2.4976889507934875e-05, "loss": 3.9097, "step": 1528320 }, { "epoch": 1.0, "learning_rate": 2.4968503560424355e-05, "loss": 3.9318, "step": 1528832 }, { "epoch": 1.0, "learning_rate": 2.4960117612913835e-05, "loss": 3.9135, "step": 1529344 }, { "epoch": 1.0, "learning_rate": 2.4951731665403315e-05, "loss": 3.9077, "step": 1529856 }, { "epoch": 1.0, "learning_rate": 2.4943345717892795e-05, "loss": 3.8987, "step": 1530368 }, { "epoch": 1.0, "learning_rate": 2.4934976149186007e-05, "loss": 3.9156, "step": 1530880 }, { "epoch": 1.0, "learning_rate": 2.4926590201675487e-05, "loss": 3.9183, "step": 1531392 }, { "epoch": 1.0, "learning_rate": 2.4918220632968697e-05, "loss": 3.9098, "step": 1531904 }, { "epoch": 1.0, "learning_rate": 2.4909834685458176e-05, "loss": 3.9122, "step": 1532416 }, { "epoch": 1.0, "learning_rate": 2.4901465116751392e-05, "loss": 3.9064, "step": 1532928 }, { "epoch": 1.0, "learning_rate": 2.4893079169240872e-05, "loss": 3.9089, "step": 1533440 }, { "epoch": 1.0, "learning_rate": 2.488469322173035e-05, "loss": 3.9104, "step": 1533952 }, { "epoch": 1.0, "learning_rate": 2.487630727421983e-05, "loss": 3.9031, "step": 1534464 }, { "epoch": 1.0, "learning_rate": 2.486792132670931e-05, "loss": 3.9088, "step": 1534976 }, { "epoch": 1.0, "learning_rate": 2.485953537919879e-05, "loss": 3.9142, "step": 1535488 }, { "epoch": 1.0, "learning_rate": 2.4851165810492e-05, "loss": 3.9093, "step": 1536000 }, { "epoch": 1.0, "learning_rate": 2.484277986298148e-05, "loss": 3.9227, "step": 1536512 }, { "epoch": 1.0, "learning_rate": 2.483439391547096e-05, "loss": 3.9133, "step": 1537024 }, { "epoch": 1.0, "learning_rate": 2.482600796796044e-05, "loss": 3.917, "step": 1537536 }, { "epoch": 1.0, "learning_rate": 2.481763839925365e-05, "loss": 3.9146, "step": 1538048 }, { "epoch": 1.0, "learning_rate": 2.480925245174313e-05, "loss": 3.9225, "step": 1538560 }, { "epoch": 1.0, "learning_rate": 2.480086650423261e-05, "loss": 3.9041, "step": 1539072 }, { "epoch": 1.0, "learning_rate": 2.4792480556722093e-05, "loss": 3.9147, "step": 1539584 }, { "epoch": 1.0, "learning_rate": 2.4784094609211573e-05, "loss": 3.9082, "step": 1540096 }, { "epoch": 1.0, "learning_rate": 2.4775708661701053e-05, "loss": 3.907, "step": 1540608 }, { "epoch": 1.0, "learning_rate": 2.476732271419053e-05, "loss": 3.9004, "step": 1541120 }, { "epoch": 1.0, "learning_rate": 2.475893676668001e-05, "loss": 3.9085, "step": 1541632 }, { "epoch": 1.01, "learning_rate": 2.475055081916949e-05, "loss": 3.9146, "step": 1542144 }, { "epoch": 1.01, "learning_rate": 2.474216487165897e-05, "loss": 3.9165, "step": 1542656 }, { "epoch": 1.01, "learning_rate": 2.473377892414845e-05, "loss": 3.9148, "step": 1543168 }, { "epoch": 1.01, "learning_rate": 2.4725392976637933e-05, "loss": 3.916, "step": 1543680 }, { "epoch": 1.01, "learning_rate": 2.4717007029127413e-05, "loss": 3.9122, "step": 1544192 }, { "epoch": 1.01, "learning_rate": 2.470862108161689e-05, "loss": 3.9159, "step": 1544704 }, { "epoch": 1.01, "learning_rate": 2.470023513410637e-05, "loss": 3.9124, "step": 1545216 }, { "epoch": 1.01, "learning_rate": 2.469184918659585e-05, "loss": 3.9143, "step": 1545728 }, { "epoch": 1.01, "learning_rate": 2.468346323908533e-05, "loss": 3.9046, "step": 1546240 }, { "epoch": 1.01, "learning_rate": 2.467507729157481e-05, "loss": 3.9112, "step": 1546752 }, { "epoch": 1.01, "learning_rate": 2.4666707722868022e-05, "loss": 3.9108, "step": 1547264 }, { "epoch": 1.01, "learning_rate": 2.4658321775357502e-05, "loss": 3.9201, "step": 1547776 }, { "epoch": 1.01, "learning_rate": 2.4649935827846982e-05, "loss": 3.9114, "step": 1548288 }, { "epoch": 1.01, "learning_rate": 2.4641549880336462e-05, "loss": 3.9122, "step": 1548800 }, { "epoch": 1.01, "learning_rate": 2.4633163932825942e-05, "loss": 3.9228, "step": 1549312 }, { "epoch": 1.01, "learning_rate": 2.462479436411915e-05, "loss": 3.9114, "step": 1549824 }, { "epoch": 1.01, "learning_rate": 2.4616408416608634e-05, "loss": 3.9155, "step": 1550336 }, { "epoch": 1.01, "learning_rate": 2.4608022469098114e-05, "loss": 3.9043, "step": 1550848 }, { "epoch": 1.01, "learning_rate": 2.459963652158759e-05, "loss": 3.8897, "step": 1551360 }, { "epoch": 1.01, "learning_rate": 2.4591266952880803e-05, "loss": 3.9184, "step": 1551872 }, { "epoch": 1.01, "learning_rate": 2.4582881005370283e-05, "loss": 3.9119, "step": 1552384 }, { "epoch": 1.01, "learning_rate": 2.4574495057859763e-05, "loss": 3.9067, "step": 1552896 }, { "epoch": 1.01, "learning_rate": 2.4566109110349243e-05, "loss": 3.895, "step": 1553408 }, { "epoch": 1.01, "learning_rate": 2.4557723162838723e-05, "loss": 3.9021, "step": 1553920 }, { "epoch": 1.01, "learning_rate": 2.4549337215328203e-05, "loss": 3.8934, "step": 1554432 }, { "epoch": 1.01, "learning_rate": 2.4540967646621415e-05, "loss": 3.9149, "step": 1554944 }, { "epoch": 1.01, "learning_rate": 2.4532581699110892e-05, "loss": 3.9005, "step": 1555456 }, { "epoch": 1.01, "learning_rate": 2.4524195751600372e-05, "loss": 3.9052, "step": 1555968 }, { "epoch": 1.01, "learning_rate": 2.4515809804089855e-05, "loss": 3.9156, "step": 1556480 }, { "epoch": 1.01, "learning_rate": 2.4507423856579335e-05, "loss": 3.9008, "step": 1556992 }, { "epoch": 1.01, "learning_rate": 2.4499037909068815e-05, "loss": 3.9019, "step": 1557504 }, { "epoch": 1.01, "learning_rate": 2.4490668340362024e-05, "loss": 3.9114, "step": 1558016 }, { "epoch": 1.01, "learning_rate": 2.4482282392851504e-05, "loss": 3.8875, "step": 1558528 }, { "epoch": 1.01, "learning_rate": 2.4473896445340984e-05, "loss": 3.9051, "step": 1559040 }, { "epoch": 1.01, "learning_rate": 2.4465510497830464e-05, "loss": 3.9075, "step": 1559552 }, { "epoch": 1.01, "learning_rate": 2.4457124550319948e-05, "loss": 3.9143, "step": 1560064 }, { "epoch": 1.01, "learning_rate": 2.4448738602809424e-05, "loss": 3.8946, "step": 1560576 }, { "epoch": 1.01, "learning_rate": 2.4440352655298904e-05, "loss": 3.9014, "step": 1561088 }, { "epoch": 1.01, "learning_rate": 2.4431966707788384e-05, "loss": 3.8925, "step": 1561600 }, { "epoch": 1.01, "learning_rate": 2.4423597139081597e-05, "loss": 3.9163, "step": 1562112 }, { "epoch": 1.01, "learning_rate": 2.441522757037481e-05, "loss": 3.9111, "step": 1562624 }, { "epoch": 1.01, "learning_rate": 2.440684162286429e-05, "loss": 3.9108, "step": 1563136 }, { "epoch": 1.01, "learning_rate": 2.439845567535377e-05, "loss": 3.9246, "step": 1563648 }, { "epoch": 1.01, "learning_rate": 2.4390069727843245e-05, "loss": 3.9156, "step": 1564160 }, { "epoch": 1.01, "learning_rate": 2.4381683780332725e-05, "loss": 3.9315, "step": 1564672 }, { "epoch": 1.01, "learning_rate": 2.4373297832822205e-05, "loss": 3.9059, "step": 1565184 }, { "epoch": 1.01, "learning_rate": 2.4364911885311685e-05, "loss": 3.9084, "step": 1565696 }, { "epoch": 1.01, "learning_rate": 2.4356525937801165e-05, "loss": 3.9169, "step": 1566208 }, { "epoch": 1.01, "learning_rate": 2.4348156369094378e-05, "loss": 3.9038, "step": 1566720 }, { "epoch": 1.01, "learning_rate": 2.433978680038759e-05, "loss": 3.9152, "step": 1567232 }, { "epoch": 1.01, "learning_rate": 2.433140085287707e-05, "loss": 3.9075, "step": 1567744 }, { "epoch": 1.01, "learning_rate": 2.4323014905366547e-05, "loss": 3.9167, "step": 1568256 }, { "epoch": 1.01, "learning_rate": 2.4314628957856027e-05, "loss": 3.9127, "step": 1568768 }, { "epoch": 1.01, "learning_rate": 2.430624301034551e-05, "loss": 3.8986, "step": 1569280 }, { "epoch": 1.01, "learning_rate": 2.429785706283499e-05, "loss": 3.91, "step": 1569792 }, { "epoch": 1.01, "learning_rate": 2.428947111532447e-05, "loss": 3.9016, "step": 1570304 }, { "epoch": 1.01, "learning_rate": 2.428108516781395e-05, "loss": 3.916, "step": 1570816 }, { "epoch": 1.01, "learning_rate": 2.427271559910716e-05, "loss": 3.9092, "step": 1571328 }, { "epoch": 1.01, "learning_rate": 2.426434603040037e-05, "loss": 3.9043, "step": 1571840 }, { "epoch": 1.02, "learning_rate": 2.425596008288985e-05, "loss": 3.9144, "step": 1572352 }, { "epoch": 1.02, "learning_rate": 2.424757413537933e-05, "loss": 3.9051, "step": 1572864 }, { "epoch": 1.02, "learning_rate": 2.423918818786881e-05, "loss": 3.9006, "step": 1573376 }, { "epoch": 1.02, "learning_rate": 2.423080224035829e-05, "loss": 3.9067, "step": 1573888 }, { "epoch": 1.02, "learning_rate": 2.422241629284777e-05, "loss": 3.9192, "step": 1574400 }, { "epoch": 1.02, "learning_rate": 2.421403034533725e-05, "loss": 3.9151, "step": 1574912 }, { "epoch": 1.02, "learning_rate": 2.4205660776630464e-05, "loss": 3.9114, "step": 1575424 }, { "epoch": 1.02, "learning_rate": 2.4197274829119944e-05, "loss": 3.8949, "step": 1575936 }, { "epoch": 1.02, "learning_rate": 2.4188888881609424e-05, "loss": 3.9135, "step": 1576448 }, { "epoch": 1.02, "learning_rate": 2.41805029340989e-05, "loss": 3.9016, "step": 1576960 }, { "epoch": 1.02, "learning_rate": 2.417211698658838e-05, "loss": 3.9195, "step": 1577472 }, { "epoch": 1.02, "learning_rate": 2.4163747417881593e-05, "loss": 3.9165, "step": 1577984 }, { "epoch": 1.02, "learning_rate": 2.4155361470371073e-05, "loss": 3.9092, "step": 1578496 }, { "epoch": 1.02, "learning_rate": 2.4146975522860553e-05, "loss": 3.904, "step": 1579008 }, { "epoch": 1.02, "learning_rate": 2.4138589575350033e-05, "loss": 3.921, "step": 1579520 }, { "epoch": 1.02, "learning_rate": 2.4130203627839513e-05, "loss": 3.8903, "step": 1580032 }, { "epoch": 1.02, "learning_rate": 2.4121834059132725e-05, "loss": 3.9058, "step": 1580544 }, { "epoch": 1.02, "learning_rate": 2.41134481116222e-05, "loss": 3.8967, "step": 1581056 }, { "epoch": 1.02, "learning_rate": 2.410506216411168e-05, "loss": 3.9124, "step": 1581568 }, { "epoch": 1.02, "learning_rate": 2.4096676216601165e-05, "loss": 3.8938, "step": 1582080 }, { "epoch": 1.02, "learning_rate": 2.4088290269090645e-05, "loss": 3.9028, "step": 1582592 }, { "epoch": 1.02, "learning_rate": 2.4079904321580125e-05, "loss": 3.9032, "step": 1583104 }, { "epoch": 1.02, "learning_rate": 2.4071518374069605e-05, "loss": 3.9017, "step": 1583616 }, { "epoch": 1.02, "learning_rate": 2.406313242655908e-05, "loss": 3.9038, "step": 1584128 }, { "epoch": 1.02, "learning_rate": 2.405474647904856e-05, "loss": 3.9024, "step": 1584640 }, { "epoch": 1.02, "learning_rate": 2.4046376910341774e-05, "loss": 3.9149, "step": 1585152 }, { "epoch": 1.02, "learning_rate": 2.4037990962831257e-05, "loss": 3.9137, "step": 1585664 }, { "epoch": 1.02, "learning_rate": 2.4029621394124466e-05, "loss": 3.9088, "step": 1586176 }, { "epoch": 1.02, "learning_rate": 2.4021235446613946e-05, "loss": 3.9021, "step": 1586688 }, { "epoch": 1.02, "learning_rate": 2.4012849499103426e-05, "loss": 3.9176, "step": 1587200 }, { "epoch": 1.02, "learning_rate": 2.4004479930396635e-05, "loss": 3.91, "step": 1587712 }, { "epoch": 1.02, "learning_rate": 2.399609398288612e-05, "loss": 3.9028, "step": 1588224 }, { "epoch": 1.02, "learning_rate": 2.39877080353756e-05, "loss": 3.9178, "step": 1588736 }, { "epoch": 1.02, "learning_rate": 2.397932208786508e-05, "loss": 3.9028, "step": 1589248 }, { "epoch": 1.02, "learning_rate": 2.3970936140354555e-05, "loss": 3.9113, "step": 1589760 }, { "epoch": 1.02, "learning_rate": 2.3962550192844035e-05, "loss": 3.8996, "step": 1590272 }, { "epoch": 1.02, "learning_rate": 2.3954164245333515e-05, "loss": 3.9107, "step": 1590784 }, { "epoch": 1.02, "learning_rate": 2.3945778297822995e-05, "loss": 3.8943, "step": 1591296 }, { "epoch": 1.02, "learning_rate": 2.3937408729116207e-05, "loss": 3.9014, "step": 1591808 }, { "epoch": 1.02, "learning_rate": 2.3929022781605687e-05, "loss": 3.9003, "step": 1592320 }, { "epoch": 1.02, "learning_rate": 2.3920636834095167e-05, "loss": 3.9129, "step": 1592832 }, { "epoch": 1.02, "learning_rate": 2.3912250886584647e-05, "loss": 3.9069, "step": 1593344 }, { "epoch": 1.02, "learning_rate": 2.3903864939074127e-05, "loss": 3.9124, "step": 1593856 }, { "epoch": 1.02, "learning_rate": 2.3895478991563607e-05, "loss": 3.9021, "step": 1594368 }, { "epoch": 1.02, "learning_rate": 2.3887093044053087e-05, "loss": 3.9123, "step": 1594880 }, { "epoch": 1.02, "learning_rate": 2.3878707096542567e-05, "loss": 3.9203, "step": 1595392 }, { "epoch": 1.02, "learning_rate": 2.387033752783578e-05, "loss": 3.9105, "step": 1595904 }, { "epoch": 1.02, "learning_rate": 2.386195158032526e-05, "loss": 3.9091, "step": 1596416 }, { "epoch": 1.02, "learning_rate": 2.3853565632814736e-05, "loss": 3.9133, "step": 1596928 }, { "epoch": 1.02, "learning_rate": 2.384519606410795e-05, "loss": 3.9082, "step": 1597440 }, { "epoch": 1.02, "learning_rate": 2.383681011659743e-05, "loss": 3.9185, "step": 1597952 }, { "epoch": 1.02, "learning_rate": 2.3828424169086912e-05, "loss": 3.9011, "step": 1598464 }, { "epoch": 1.02, "learning_rate": 2.382005460038012e-05, "loss": 3.9111, "step": 1598976 }, { "epoch": 1.02, "learning_rate": 2.38116686528696e-05, "loss": 3.9053, "step": 1599488 }, { "epoch": 1.02, "learning_rate": 2.380328270535908e-05, "loss": 3.9085, "step": 1600000 }, { "epoch": 1.02, "learning_rate": 2.3794896757848557e-05, "loss": 3.9084, "step": 1600512 }, { "epoch": 1.02, "learning_rate": 2.378651081033804e-05, "loss": 3.9075, "step": 1601024 }, { "epoch": 1.02, "learning_rate": 2.377812486282752e-05, "loss": 3.9071, "step": 1601536 }, { "epoch": 1.02, "learning_rate": 2.3769738915317e-05, "loss": 3.9017, "step": 1602048 }, { "epoch": 1.02, "learning_rate": 2.376135296780648e-05, "loss": 3.9128, "step": 1602560 }, { "epoch": 1.03, "eval_loss": 3.994572401046753, "eval_runtime": 305.0529, "eval_samples_per_second": 1250.901, "eval_steps_per_second": 39.092, "step": 1602720 }, { "epoch": 0.0, "learning_rate": 2.375296702029596e-05, "loss": 3.9013, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.374458107278544e-05, "loss": 3.8962, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.3736195125274917e-05, "loss": 3.9135, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3727809177764397e-05, "loss": 3.9042, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.371942323025388e-05, "loss": 3.9214, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.371103728274336e-05, "loss": 3.9073, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.370265133523284e-05, "loss": 3.8939, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.369426538772232e-05, "loss": 3.8981, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.36858794402118e-05, "loss": 3.9011, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.3677493492701277e-05, "loss": 3.9115, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.3669107545190757e-05, "loss": 3.9024, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.3660721597680237e-05, "loss": 3.9055, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.365235202897345e-05, "loss": 3.9011, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.364396608146293e-05, "loss": 3.898, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.363558013395241e-05, "loss": 3.9072, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.362719418644189e-05, "loss": 3.8947, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.361880823893137e-05, "loss": 3.8974, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.361042229142085e-05, "loss": 3.9044, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.360203634391033e-05, "loss": 3.9061, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.359365039639981e-05, "loss": 3.914, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.358526444888929e-05, "loss": 3.9082, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.35768948801825e-05, "loss": 3.9087, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.356850893267198e-05, "loss": 3.9077, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.3560122985161458e-05, "loss": 3.9102, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.3551737037650938e-05, "loss": 3.8947, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.354335109014042e-05, "loss": 3.9113, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.35349651426299e-05, "loss": 3.8976, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.352657919511938e-05, "loss": 3.9006, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.351819324760886e-05, "loss": 3.8966, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.350982367890207e-05, "loss": 3.9007, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.350143773139155e-05, "loss": 3.9064, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.349305178388103e-05, "loss": 3.9058, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3484665836370513e-05, "loss": 3.911, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.3476296267663722e-05, "loss": 3.9165, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.3467910320153202e-05, "loss": 3.9009, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.3459524372642682e-05, "loss": 3.908, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.345113842513216e-05, "loss": 3.9059, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.3442752477621642e-05, "loss": 3.9038, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.3434382908914855e-05, "loss": 3.8998, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.3425996961404335e-05, "loss": 3.8994, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.341761101389381e-05, "loss": 3.9066, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.3409241445187024e-05, "loss": 3.9134, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.3400855497676504e-05, "loss": 3.9012, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.3392469550165984e-05, "loss": 3.9047, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.3384083602655464e-05, "loss": 3.9124, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.3375697655144944e-05, "loss": 3.9063, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3367311707634424e-05, "loss": 3.9078, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.3358925760123903e-05, "loss": 3.8984, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.3350539812613383e-05, "loss": 3.8786, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3342170243906593e-05, "loss": 3.9139, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3333784296396076e-05, "loss": 3.9035, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3325398348885556e-05, "loss": 3.9018, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3317012401375036e-05, "loss": 3.8923, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3308642832668245e-05, "loss": 3.8869, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3300273263961457e-05, "loss": 3.8885, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.3291887316450937e-05, "loss": 3.9042, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.3283501368940417e-05, "loss": 3.8952, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3275115421429897e-05, "loss": 3.8996, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3266729473919377e-05, "loss": 3.9062, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3258343526408857e-05, "loss": 3.894, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3249957578898337e-05, "loss": 3.8952, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.3241571631387814e-05, "loss": 3.9042, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.3233185683877297e-05, "loss": 3.8825, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.322481611517051e-05, "loss": 3.8947, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.321643016765999e-05, "loss": 3.8988, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.3208044220149466e-05, "loss": 3.9078, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.3199658272638946e-05, "loss": 3.8859, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.319128870393216e-05, "loss": 3.897, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.318290275642164e-05, "loss": 3.8865, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.317451680891112e-05, "loss": 3.9096, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.31661308614006e-05, "loss": 3.9051, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.315776129269381e-05, "loss": 3.9026, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.314939172398702e-05, "loss": 3.9119, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.31410057764765e-05, "loss": 3.9123, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.3132619828965983e-05, "loss": 3.9232, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.3124233881455463e-05, "loss": 3.9014, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.311584793394494e-05, "loss": 3.9036, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.3107478365238152e-05, "loss": 3.9041, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.3099092417727632e-05, "loss": 3.8945, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.3090706470217112e-05, "loss": 3.9112, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.3082320522706592e-05, "loss": 3.9006, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.3073934575196072e-05, "loss": 3.9078, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.3065548627685552e-05, "loss": 3.9055, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.3057162680175032e-05, "loss": 3.8911, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.304879311146824e-05, "loss": 3.9023, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.304040716395772e-05, "loss": 3.893, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.3032021216447204e-05, "loss": 3.9093, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3023635268936684e-05, "loss": 3.9058, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3015265700229893e-05, "loss": 3.8909, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3006879752719373e-05, "loss": 3.911, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.2998493805208853e-05, "loss": 3.8998, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.2990107857698333e-05, "loss": 3.8949, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.2981721910187813e-05, "loss": 3.8998, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2973335962677293e-05, "loss": 3.9127, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2964950015166773e-05, "loss": 3.9057, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2956564067656253e-05, "loss": 3.9086, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2948178120145733e-05, "loss": 3.8889, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2939792172635213e-05, "loss": 3.9032, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2931406225124693e-05, "loss": 3.8963, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2923020277614173e-05, "loss": 3.9113, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.2914650708907385e-05, "loss": 3.9112, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2906264761396865e-05, "loss": 3.899, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2897895192690074e-05, "loss": 3.9035, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.2889509245179554e-05, "loss": 3.91, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2881123297669034e-05, "loss": 3.888, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.2872737350158514e-05, "loss": 3.8963, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.2864367781451727e-05, "loss": 3.8902, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.2855981833941207e-05, "loss": 3.9026, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.2847595886430687e-05, "loss": 3.8923, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2839209938920167e-05, "loss": 3.8993, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2830823991409647e-05, "loss": 3.8933, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.2822438043899123e-05, "loss": 3.8948, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.2814052096388607e-05, "loss": 3.8982, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.280568252768182e-05, "loss": 3.8934, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.27972965801713e-05, "loss": 3.9077, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.2788910632660776e-05, "loss": 3.9046, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.2780524685150256e-05, "loss": 3.9042, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2772138737639735e-05, "loss": 3.8952, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.2763752790129215e-05, "loss": 3.9065, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.27553668426187e-05, "loss": 3.9077, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.2746997273911908e-05, "loss": 3.8933, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.2738611326401388e-05, "loss": 3.9161, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.2730225378890868e-05, "loss": 3.8924, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.2721839431380348e-05, "loss": 3.9071, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.2713453483869828e-05, "loss": 3.889, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.2705067536359308e-05, "loss": 3.9074, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.269671434645625e-05, "loss": 3.8869, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.268832839894573e-05, "loss": 3.8963, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.267994245143521e-05, "loss": 3.8885, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.267155650392469e-05, "loss": 3.9111, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.266317055641417e-05, "loss": 3.8986, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.2654784608903652e-05, "loss": 3.9056, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.264639866139313e-05, "loss": 3.8953, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.263801271388261e-05, "loss": 3.9074, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.262962676637209e-05, "loss": 3.91, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.262124081886157e-05, "loss": 3.904, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2612871250154778e-05, "loss": 3.9035, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.260448530264426e-05, "loss": 3.9033, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.259609935513374e-05, "loss": 3.9012, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.258771340762322e-05, "loss": 3.9115, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.25793274601127e-05, "loss": 3.8954, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.257095789140591e-05, "loss": 3.9045, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.256257194389539e-05, "loss": 3.9003, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.255418599638487e-05, "loss": 3.9027, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.2545800048874354e-05, "loss": 3.8999, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.2537430480167563e-05, "loss": 3.8949, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.2529044532657043e-05, "loss": 3.9092, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.2520658585146523e-05, "loss": 3.8877, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.2512272637636002e-05, "loss": 3.9092, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 3.991856336593628, "eval_runtime": 294.8575, "eval_samples_per_second": 1294.154, "eval_steps_per_second": 40.443, "step": 1679040 }, { "epoch": 1.0, "learning_rate": 2.2503886690125482e-05, "loss": 3.898, "step": 1679360 }, { "epoch": 1.0, "learning_rate": 2.2495500742614962e-05, "loss": 3.8882, "step": 1679872 }, { "epoch": 1.0, "learning_rate": 2.2487114795104442e-05, "loss": 3.9046, "step": 1680384 }, { "epoch": 1.0, "learning_rate": 2.2478728847593922e-05, "loss": 3.8996, "step": 1680896 }, { "epoch": 1.0, "learning_rate": 2.2470342900083402e-05, "loss": 3.9117, "step": 1681408 }, { "epoch": 1.0, "learning_rate": 2.2461956952572882e-05, "loss": 3.9015, "step": 1681920 }, { "epoch": 1.0, "learning_rate": 2.245358738386609e-05, "loss": 3.8882, "step": 1682432 }, { "epoch": 1.0, "learning_rate": 2.244520143635557e-05, "loss": 3.8892, "step": 1682944 }, { "epoch": 1.0, "learning_rate": 2.2436815488845055e-05, "loss": 3.8985, "step": 1683456 }, { "epoch": 1.0, "learning_rate": 2.2428429541334535e-05, "loss": 3.9042, "step": 1683968 }, { "epoch": 1.0, "learning_rate": 2.2420059972627744e-05, "loss": 3.896, "step": 1684480 }, { "epoch": 1.0, "learning_rate": 2.2411690403920956e-05, "loss": 3.8969, "step": 1684992 }, { "epoch": 1.0, "learning_rate": 2.240332083521417e-05, "loss": 3.9, "step": 1685504 }, { "epoch": 1.0, "learning_rate": 2.239493488770365e-05, "loss": 3.8913, "step": 1686016 }, { "epoch": 1.0, "learning_rate": 2.238654894019313e-05, "loss": 3.8983, "step": 1686528 }, { "epoch": 1.0, "learning_rate": 2.237816299268261e-05, "loss": 3.8856, "step": 1687040 }, { "epoch": 1.0, "learning_rate": 2.2369777045172085e-05, "loss": 3.8935, "step": 1687552 }, { "epoch": 1.0, "learning_rate": 2.2361391097661565e-05, "loss": 3.898, "step": 1688064 }, { "epoch": 1.0, "learning_rate": 2.2353005150151045e-05, "loss": 3.8976, "step": 1688576 }, { "epoch": 1.0, "learning_rate": 2.2344619202640525e-05, "loss": 3.9055, "step": 1689088 }, { "epoch": 1.0, "learning_rate": 2.2336233255130008e-05, "loss": 3.9068, "step": 1689600 }, { "epoch": 1.0, "learning_rate": 2.2327847307619488e-05, "loss": 3.8987, "step": 1690112 }, { "epoch": 1.0, "learning_rate": 2.2319461360108965e-05, "loss": 3.8983, "step": 1690624 }, { "epoch": 1.0, "learning_rate": 2.2311075412598445e-05, "loss": 3.9067, "step": 1691136 }, { "epoch": 1.0, "learning_rate": 2.2302689465087925e-05, "loss": 3.8852, "step": 1691648 }, { "epoch": 1.0, "learning_rate": 2.2294319896381137e-05, "loss": 3.9106, "step": 1692160 }, { "epoch": 1.0, "learning_rate": 2.2285933948870617e-05, "loss": 3.8919, "step": 1692672 }, { "epoch": 1.0, "learning_rate": 2.2277548001360097e-05, "loss": 3.8922, "step": 1693184 }, { "epoch": 1.0, "learning_rate": 2.2269162053849577e-05, "loss": 3.8894, "step": 1693696 }, { "epoch": 1.0, "learning_rate": 2.226080886394652e-05, "loss": 3.8973, "step": 1694208 }, { "epoch": 1.01, "learning_rate": 2.2252422916436e-05, "loss": 3.8973, "step": 1694720 }, { "epoch": 1.01, "learning_rate": 2.224403696892548e-05, "loss": 3.9014, "step": 1695232 }, { "epoch": 1.01, "learning_rate": 2.2235651021414962e-05, "loss": 3.9013, "step": 1695744 }, { "epoch": 1.01, "learning_rate": 2.222726507390444e-05, "loss": 3.9086, "step": 1696256 }, { "epoch": 1.01, "learning_rate": 2.221887912639392e-05, "loss": 3.8939, "step": 1696768 }, { "epoch": 1.01, "learning_rate": 2.22104931788834e-05, "loss": 3.9037, "step": 1697280 }, { "epoch": 1.01, "learning_rate": 2.220210723137288e-05, "loss": 3.9018, "step": 1697792 }, { "epoch": 1.01, "learning_rate": 2.219372128386236e-05, "loss": 3.8923, "step": 1698304 }, { "epoch": 1.01, "learning_rate": 2.2185368093959303e-05, "loss": 3.8945, "step": 1698816 }, { "epoch": 1.01, "learning_rate": 2.2176982146448783e-05, "loss": 3.8941, "step": 1699328 }, { "epoch": 1.01, "learning_rate": 2.216859619893826e-05, "loss": 3.8962, "step": 1699840 }, { "epoch": 1.01, "learning_rate": 2.216021025142774e-05, "loss": 3.9085, "step": 1700352 }, { "epoch": 1.01, "learning_rate": 2.215182430391722e-05, "loss": 3.8937, "step": 1700864 }, { "epoch": 1.01, "learning_rate": 2.21434383564067e-05, "loss": 3.895, "step": 1701376 }, { "epoch": 1.01, "learning_rate": 2.213505240889618e-05, "loss": 3.9096, "step": 1701888 }, { "epoch": 1.01, "learning_rate": 2.2126666461385663e-05, "loss": 3.8972, "step": 1702400 }, { "epoch": 1.01, "learning_rate": 2.2118280513875143e-05, "loss": 3.9061, "step": 1702912 }, { "epoch": 1.01, "learning_rate": 2.2109910945168352e-05, "loss": 3.8941, "step": 1703424 }, { "epoch": 1.01, "learning_rate": 2.2101524997657832e-05, "loss": 3.8659, "step": 1703936 }, { "epoch": 1.01, "learning_rate": 2.2093139050147312e-05, "loss": 3.9114, "step": 1704448 }, { "epoch": 1.01, "learning_rate": 2.2084769481440524e-05, "loss": 3.8963, "step": 1704960 }, { "epoch": 1.01, "learning_rate": 2.2076383533930004e-05, "loss": 3.8962, "step": 1705472 }, { "epoch": 1.01, "learning_rate": 2.2067997586419484e-05, "loss": 3.8879, "step": 1705984 }, { "epoch": 1.01, "learning_rate": 2.2059611638908964e-05, "loss": 3.878, "step": 1706496 }, { "epoch": 1.01, "learning_rate": 2.205122569139844e-05, "loss": 3.8865, "step": 1707008 }, { "epoch": 1.01, "learning_rate": 2.204283974388792e-05, "loss": 3.8927, "step": 1707520 }, { "epoch": 1.01, "learning_rate": 2.2034470175181133e-05, "loss": 3.8905, "step": 1708032 }, { "epoch": 1.01, "learning_rate": 2.2026084227670617e-05, "loss": 3.8906, "step": 1708544 }, { "epoch": 1.01, "learning_rate": 2.2017698280160093e-05, "loss": 3.9023, "step": 1709056 }, { "epoch": 1.01, "learning_rate": 2.2009328711453306e-05, "loss": 3.8862, "step": 1709568 }, { "epoch": 1.01, "learning_rate": 2.2000942763942786e-05, "loss": 3.8853, "step": 1710080 }, { "epoch": 1.01, "learning_rate": 2.1992556816432266e-05, "loss": 3.9017, "step": 1710592 }, { "epoch": 1.01, "learning_rate": 2.1984170868921746e-05, "loss": 3.8739, "step": 1711104 }, { "epoch": 1.01, "learning_rate": 2.1975784921411226e-05, "loss": 3.8885, "step": 1711616 }, { "epoch": 1.01, "learning_rate": 2.1967398973900706e-05, "loss": 3.8921, "step": 1712128 }, { "epoch": 1.01, "learning_rate": 2.1959013026390185e-05, "loss": 3.9027, "step": 1712640 }, { "epoch": 1.01, "learning_rate": 2.1950627078879665e-05, "loss": 3.8778, "step": 1713152 }, { "epoch": 1.01, "learning_rate": 2.1942257510172875e-05, "loss": 3.8921, "step": 1713664 }, { "epoch": 1.01, "learning_rate": 2.1933871562662355e-05, "loss": 3.8773, "step": 1714176 }, { "epoch": 1.01, "learning_rate": 2.1925485615151838e-05, "loss": 3.9026, "step": 1714688 }, { "epoch": 1.01, "learning_rate": 2.1917099667641318e-05, "loss": 3.901, "step": 1715200 }, { "epoch": 1.01, "learning_rate": 2.1908713720130798e-05, "loss": 3.8981, "step": 1715712 }, { "epoch": 1.01, "learning_rate": 2.1900327772620274e-05, "loss": 3.9025, "step": 1716224 }, { "epoch": 1.01, "learning_rate": 2.1891941825109754e-05, "loss": 3.9057, "step": 1716736 }, { "epoch": 1.01, "learning_rate": 2.1883555877599234e-05, "loss": 3.9194, "step": 1717248 }, { "epoch": 1.01, "learning_rate": 2.187520268769618e-05, "loss": 3.8938, "step": 1717760 }, { "epoch": 1.01, "learning_rate": 2.186681674018566e-05, "loss": 3.8991, "step": 1718272 }, { "epoch": 1.01, "learning_rate": 2.185843079267514e-05, "loss": 3.9003, "step": 1718784 }, { "epoch": 1.01, "learning_rate": 2.185004484516462e-05, "loss": 3.8866, "step": 1719296 }, { "epoch": 1.01, "learning_rate": 2.1841658897654096e-05, "loss": 3.9005, "step": 1719808 }, { "epoch": 1.01, "learning_rate": 2.1833289328947308e-05, "loss": 3.8957, "step": 1720320 }, { "epoch": 1.01, "learning_rate": 2.1824903381436788e-05, "loss": 3.9006, "step": 1720832 }, { "epoch": 1.01, "learning_rate": 2.181651743392627e-05, "loss": 3.9059, "step": 1721344 }, { "epoch": 1.01, "learning_rate": 2.1808131486415748e-05, "loss": 3.8854, "step": 1721856 }, { "epoch": 1.01, "learning_rate": 2.1799745538905228e-05, "loss": 3.8893, "step": 1722368 }, { "epoch": 1.01, "learning_rate": 2.179137597019844e-05, "loss": 3.8891, "step": 1722880 }, { "epoch": 1.01, "learning_rate": 2.178299002268792e-05, "loss": 3.903, "step": 1723392 }, { "epoch": 1.01, "learning_rate": 2.17746040751774e-05, "loss": 3.8945, "step": 1723904 }, { "epoch": 1.01, "learning_rate": 2.1766234506470613e-05, "loss": 3.8906, "step": 1724416 }, { "epoch": 1.02, "learning_rate": 2.1757848558960093e-05, "loss": 3.8928, "step": 1724928 }, { "epoch": 1.02, "learning_rate": 2.174946261144957e-05, "loss": 3.8986, "step": 1725440 }, { "epoch": 1.02, "learning_rate": 2.174107666393905e-05, "loss": 3.8892, "step": 1725952 }, { "epoch": 1.02, "learning_rate": 2.173269071642853e-05, "loss": 3.8918, "step": 1726464 }, { "epoch": 1.02, "learning_rate": 2.172430476891801e-05, "loss": 3.9107, "step": 1726976 }, { "epoch": 1.02, "learning_rate": 2.1715918821407493e-05, "loss": 3.8981, "step": 1727488 }, { "epoch": 1.02, "learning_rate": 2.1707532873896973e-05, "loss": 3.9005, "step": 1728000 }, { "epoch": 1.02, "learning_rate": 2.1699146926386453e-05, "loss": 3.8838, "step": 1728512 }, { "epoch": 1.02, "learning_rate": 2.169076097887593e-05, "loss": 3.8981, "step": 1729024 }, { "epoch": 1.02, "learning_rate": 2.168237503136541e-05, "loss": 3.8908, "step": 1729536 }, { "epoch": 1.02, "learning_rate": 2.167398908385489e-05, "loss": 3.9035, "step": 1730048 }, { "epoch": 1.02, "learning_rate": 2.16656195151481e-05, "loss": 3.9008, "step": 1730560 }, { "epoch": 1.02, "learning_rate": 2.165723356763758e-05, "loss": 3.8981, "step": 1731072 }, { "epoch": 1.02, "learning_rate": 2.164884762012706e-05, "loss": 3.8998, "step": 1731584 }, { "epoch": 1.02, "learning_rate": 2.164046167261654e-05, "loss": 3.9016, "step": 1732096 }, { "epoch": 1.02, "learning_rate": 2.163209210390975e-05, "loss": 3.8825, "step": 1732608 }, { "epoch": 1.02, "learning_rate": 2.162370615639923e-05, "loss": 3.8917, "step": 1733120 }, { "epoch": 1.02, "learning_rate": 2.1615336587692446e-05, "loss": 3.881, "step": 1733632 }, { "epoch": 1.02, "learning_rate": 2.1606950640181926e-05, "loss": 3.8997, "step": 1734144 }, { "epoch": 1.02, "learning_rate": 2.1598564692671403e-05, "loss": 3.8863, "step": 1734656 }, { "epoch": 1.02, "learning_rate": 2.1590178745160883e-05, "loss": 3.8912, "step": 1735168 }, { "epoch": 1.02, "learning_rate": 2.1581809176454095e-05, "loss": 3.8858, "step": 1735680 }, { "epoch": 1.02, "learning_rate": 2.1573423228943572e-05, "loss": 3.8916, "step": 1736192 }, { "epoch": 1.02, "learning_rate": 2.1565037281433055e-05, "loss": 3.8915, "step": 1736704 }, { "epoch": 1.02, "learning_rate": 2.1556667712726268e-05, "loss": 3.8865, "step": 1737216 }, { "epoch": 1.02, "learning_rate": 2.1548281765215748e-05, "loss": 3.8974, "step": 1737728 }, { "epoch": 1.02, "learning_rate": 2.1539895817705224e-05, "loss": 3.9027, "step": 1738240 }, { "epoch": 1.02, "learning_rate": 2.1531509870194704e-05, "loss": 3.8944, "step": 1738752 }, { "epoch": 1.02, "learning_rate": 2.1523123922684184e-05, "loss": 3.8968, "step": 1739264 }, { "epoch": 1.02, "learning_rate": 2.1514737975173664e-05, "loss": 3.895, "step": 1739776 }, { "epoch": 1.02, "learning_rate": 2.1506352027663147e-05, "loss": 3.8997, "step": 1740288 }, { "epoch": 1.02, "learning_rate": 2.1497966080152627e-05, "loss": 3.8918, "step": 1740800 }, { "epoch": 1.02, "learning_rate": 2.1489596511445836e-05, "loss": 3.9023, "step": 1741312 }, { "epoch": 1.02, "learning_rate": 2.1481210563935316e-05, "loss": 3.8865, "step": 1741824 }, { "epoch": 1.02, "learning_rate": 2.1472824616424796e-05, "loss": 3.8997, "step": 1742336 }, { "epoch": 1.02, "learning_rate": 2.1464438668914276e-05, "loss": 3.8861, "step": 1742848 }, { "epoch": 1.02, "learning_rate": 2.1456052721403756e-05, "loss": 3.8933, "step": 1743360 }, { "epoch": 1.02, "learning_rate": 2.1447666773893236e-05, "loss": 3.8863, "step": 1743872 }, { "epoch": 1.02, "learning_rate": 2.143929720518645e-05, "loss": 3.8888, "step": 1744384 }, { "epoch": 1.02, "learning_rate": 2.1430927636479658e-05, "loss": 3.8849, "step": 1744896 }, { "epoch": 1.02, "learning_rate": 2.1422541688969138e-05, "loss": 3.9014, "step": 1745408 }, { "epoch": 1.02, "learning_rate": 2.1414155741458618e-05, "loss": 3.8948, "step": 1745920 }, { "epoch": 1.02, "learning_rate": 2.14057697939481e-05, "loss": 3.8997, "step": 1746432 }, { "epoch": 1.02, "learning_rate": 2.139738384643758e-05, "loss": 3.8874, "step": 1746944 }, { "epoch": 1.02, "learning_rate": 2.1388997898927058e-05, "loss": 3.9029, "step": 1747456 }, { "epoch": 1.02, "learning_rate": 2.1380611951416538e-05, "loss": 3.9041, "step": 1747968 }, { "epoch": 1.02, "learning_rate": 2.1372226003906017e-05, "loss": 3.8977, "step": 1748480 }, { "epoch": 1.02, "learning_rate": 2.1363840056395497e-05, "loss": 3.8984, "step": 1748992 }, { "epoch": 1.02, "learning_rate": 2.1355454108884977e-05, "loss": 3.8939, "step": 1749504 }, { "epoch": 1.02, "learning_rate": 2.1347068161374457e-05, "loss": 3.8978, "step": 1750016 }, { "epoch": 1.02, "learning_rate": 2.133869859266767e-05, "loss": 3.908, "step": 1750528 }, { "epoch": 1.02, "learning_rate": 2.133031264515715e-05, "loss": 3.8872, "step": 1751040 }, { "epoch": 1.02, "learning_rate": 2.132192669764663e-05, "loss": 3.8962, "step": 1751552 }, { "epoch": 1.02, "learning_rate": 2.131354075013611e-05, "loss": 3.8985, "step": 1752064 }, { "epoch": 1.02, "learning_rate": 2.1305154802625586e-05, "loss": 3.8986, "step": 1752576 }, { "epoch": 1.02, "learning_rate": 2.129676885511507e-05, "loss": 3.886, "step": 1753088 }, { "epoch": 1.02, "learning_rate": 2.1288399286408282e-05, "loss": 3.8898, "step": 1753600 }, { "epoch": 1.02, "learning_rate": 2.1280013338897762e-05, "loss": 3.9038, "step": 1754112 }, { "epoch": 1.02, "learning_rate": 2.127162739138724e-05, "loss": 3.8852, "step": 1754624 }, { "epoch": 1.02, "learning_rate": 2.126324144387672e-05, "loss": 3.9022, "step": 1755136 }, { "epoch": 1.03, "eval_loss": 3.9894936084747314, "eval_runtime": 295.3052, "eval_samples_per_second": 1292.192, "eval_steps_per_second": 40.382, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.12548554963662e-05, "loss": 3.8942, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.124646954885568e-05, "loss": 3.8823, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.123808360134516e-05, "loss": 3.9005, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.1229697653834642e-05, "loss": 3.8888, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.122131170632412e-05, "loss": 3.9026, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.1212925758813598e-05, "loss": 3.8974, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.1204539811303078e-05, "loss": 3.8848, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.1196153863792558e-05, "loss": 3.8857, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1187767916282038e-05, "loss": 3.8912, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.1179381968771518e-05, "loss": 3.8978, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.1170996021261e-05, "loss": 3.8889, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.1162610073750478e-05, "loss": 3.89, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.115425688384742e-05, "loss": 3.8914, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.11458709363369e-05, "loss": 3.8856, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.113748498882638e-05, "loss": 3.8911, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1129099041315863e-05, "loss": 3.8813, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1120713093805343e-05, "loss": 3.8853, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1112327146294823e-05, "loss": 3.8927, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.11039411987843e-05, "loss": 3.8941, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.109555525127378e-05, "loss": 3.896, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.108716930376326e-05, "loss": 3.9025, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.107878335625274e-05, "loss": 3.894, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.107039740874222e-05, "loss": 3.8929, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1062011461231703e-05, "loss": 3.8954, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1053625513721183e-05, "loss": 3.8857, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.104523956621066e-05, "loss": 3.9031, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.103685361870014e-05, "loss": 3.8851, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.102846767118962e-05, "loss": 3.8894, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.10200817236791e-05, "loss": 3.8848, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.101171215497231e-05, "loss": 3.889, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.100332620746179e-05, "loss": 3.8901, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.099494025995127e-05, "loss": 3.8972, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.098655431244075e-05, "loss": 3.8932, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.097818474373396e-05, "loss": 3.9001, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.096979879622344e-05, "loss": 3.8872, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.096141284871292e-05, "loss": 3.9006, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.0953043280006133e-05, "loss": 3.8953, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.0944657332495613e-05, "loss": 3.8859, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0936271384985093e-05, "loss": 3.8908, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0927885437474573e-05, "loss": 3.8896, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.0919515868767782e-05, "loss": 3.8896, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.0911129921257265e-05, "loss": 3.8993, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.0902743973746745e-05, "loss": 3.8872, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.0894358026236225e-05, "loss": 3.8902, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.0885972078725705e-05, "loss": 3.9004, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.0877602510018914e-05, "loss": 3.8918, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.0869216562508394e-05, "loss": 3.895, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.0860830614997874e-05, "loss": 3.891, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.0852444667487357e-05, "loss": 3.8585, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.0844075098780566e-05, "loss": 3.9063, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.0835689151270046e-05, "loss": 3.8886, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.0827303203759526e-05, "loss": 3.8945, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0818917256249006e-05, "loss": 3.8784, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0810531308738486e-05, "loss": 3.873, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0802145361227966e-05, "loss": 3.8793, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.079377579252118e-05, "loss": 3.886, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.078538984501066e-05, "loss": 3.8884, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0777003897500135e-05, "loss": 3.8804, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0768617949989615e-05, "loss": 3.9003, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0760232002479095e-05, "loss": 3.8831, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.0751846054968575e-05, "loss": 3.8808, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.074346010745806e-05, "loss": 3.8953, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.073507415994754e-05, "loss": 3.8686, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.0726704591240747e-05, "loss": 3.8782, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0718318643730227e-05, "loss": 3.8883, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0709932696219707e-05, "loss": 3.8966, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0701546748709187e-05, "loss": 3.8732, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.06931771800024e-05, "loss": 3.8879, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.068479123249188e-05, "loss": 3.8722, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.067640528498136e-05, "loss": 3.8975, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.066801933747084e-05, "loss": 3.8932, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.065964976876405e-05, "loss": 3.8916, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.065128020005726e-05, "loss": 3.8948, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.064289425254674e-05, "loss": 3.9019, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.063450830503622e-05, "loss": 3.9105, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.062613873632943e-05, "loss": 3.8896, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.061775278881891e-05, "loss": 3.8916, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.060936684130839e-05, "loss": 3.8961, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0600980893797874e-05, "loss": 3.88, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.0592594946287353e-05, "loss": 3.8898, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.0584208998776833e-05, "loss": 3.8927, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.0575823051266313e-05, "loss": 3.8959, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.056743710375579e-05, "loss": 3.8983, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.0559067535049002e-05, "loss": 3.8825, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.0550681587538482e-05, "loss": 3.8804, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.0542295640027966e-05, "loss": 3.8848, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.0533909692517442e-05, "loss": 3.8982, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0525523745006922e-05, "loss": 3.8902, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0517154176300135e-05, "loss": 3.8832, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.050876822878961e-05, "loss": 3.8855, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0500398660082827e-05, "loss": 3.8933, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0492012712572307e-05, "loss": 3.8862, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0483626765061787e-05, "loss": 3.884, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0475240817551264e-05, "loss": 3.9024, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.0466854870040744e-05, "loss": 3.8909, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.0458468922530224e-05, "loss": 3.8916, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.0450082975019704e-05, "loss": 3.8824, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.0441697027509183e-05, "loss": 3.8886, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.0433311079998667e-05, "loss": 3.8823, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.0424925132488143e-05, "loss": 3.8994, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0416539184977623e-05, "loss": 3.8932, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0408153237467103e-05, "loss": 3.8953, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0399783668760316e-05, "loss": 3.8928, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0391397721249796e-05, "loss": 3.8918, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.0383028152543008e-05, "loss": 3.8813, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.0374642205032488e-05, "loss": 3.8815, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.0366256257521968e-05, "loss": 3.8777, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.0357870310011445e-05, "loss": 3.8943, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.0349484362500925e-05, "loss": 3.8804, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.0341114793794137e-05, "loss": 3.8831, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.0332728846283617e-05, "loss": 3.8769, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.0324342898773097e-05, "loss": 3.8873, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0315956951262577e-05, "loss": 3.8862, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.030758738255579e-05, "loss": 3.8778, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.0299201435045266e-05, "loss": 3.8967, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.029081548753475e-05, "loss": 3.8927, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.028242954002423e-05, "loss": 3.8881, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0274059971317442e-05, "loss": 3.8918, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.026567402380692e-05, "loss": 3.8903, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.02572880762964e-05, "loss": 3.8908, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.024890212878588e-05, "loss": 3.8922, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.0240516181275358e-05, "loss": 3.8938, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.023213023376484e-05, "loss": 3.8826, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.022374428625432e-05, "loss": 3.8935, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0215358338743798e-05, "loss": 3.8854, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.020698877003701e-05, "loss": 3.8878, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.019860282252649e-05, "loss": 3.8788, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.019021687501597e-05, "loss": 3.8818, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0181847306309183e-05, "loss": 3.8793, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0173461358798663e-05, "loss": 3.8957, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0165075411288143e-05, "loss": 3.8868, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.0156689463777623e-05, "loss": 3.8949, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.01483035162671e-05, "loss": 3.8781, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.013991756875658e-05, "loss": 3.901, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.013153162124606e-05, "loss": 3.8919, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0123145673735543e-05, "loss": 3.8926, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0114759726225023e-05, "loss": 3.8945, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0106373778714503e-05, "loss": 3.889, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0098004210007712e-05, "loss": 3.8889, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.008961826249719e-05, "loss": 3.9005, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.008123231498667e-05, "loss": 3.8824, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.007284636747615e-05, "loss": 3.892, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.006446041996563e-05, "loss": 3.8939, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.005607447245511e-05, "loss": 3.8884, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.004768852494459e-05, "loss": 3.8831, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.003930257743407e-05, "loss": 3.883, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.003093300872728e-05, "loss": 3.8969, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.0022563440020496e-05, "loss": 3.8837, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.0014177492509976e-05, "loss": 3.8968, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.9873015880584717, "eval_runtime": 290.3675, "eval_samples_per_second": 1314.166, "eval_steps_per_second": 41.069, "step": 1831680 }, { "epoch": 1.0, "learning_rate": 2.0005791544999453e-05, "loss": 3.8808, "step": 1831936 }, { "epoch": 1.0, "learning_rate": 1.9997405597488933e-05, "loss": 3.8826, "step": 1832448 }, { "epoch": 1.0, "learning_rate": 1.9989019649978413e-05, "loss": 3.8874, "step": 1832960 }, { "epoch": 1.0, "learning_rate": 1.9980633702467893e-05, "loss": 3.887, "step": 1833472 }, { "epoch": 1.0, "learning_rate": 1.9972247754957373e-05, "loss": 3.8984, "step": 1833984 }, { "epoch": 1.0, "learning_rate": 1.9963861807446853e-05, "loss": 3.8892, "step": 1834496 }, { "epoch": 1.0, "learning_rate": 1.9955508617543798e-05, "loss": 3.8823, "step": 1835008 }, { "epoch": 1.0, "learning_rate": 1.9947122670033278e-05, "loss": 3.8813, "step": 1835520 }, { "epoch": 1.0, "learning_rate": 1.9938736722522754e-05, "loss": 3.8829, "step": 1836032 }, { "epoch": 1.0, "learning_rate": 1.9930350775012234e-05, "loss": 3.8941, "step": 1836544 }, { "epoch": 1.0, "learning_rate": 1.9921964827501714e-05, "loss": 3.8836, "step": 1837056 }, { "epoch": 1.0, "learning_rate": 1.9913578879991197e-05, "loss": 3.8822, "step": 1837568 }, { "epoch": 1.0, "learning_rate": 1.9905209311284407e-05, "loss": 3.8941, "step": 1838080 }, { "epoch": 1.0, "learning_rate": 1.9896823363773887e-05, "loss": 3.8743, "step": 1838592 }, { "epoch": 1.0, "learning_rate": 1.9888437416263366e-05, "loss": 3.8809, "step": 1839104 }, { "epoch": 1.0, "learning_rate": 1.9880051468752846e-05, "loss": 3.8793, "step": 1839616 }, { "epoch": 1.0, "learning_rate": 1.9871665521242326e-05, "loss": 3.8793, "step": 1840128 }, { "epoch": 1.0, "learning_rate": 1.9863279573731806e-05, "loss": 3.888, "step": 1840640 }, { "epoch": 1.0, "learning_rate": 1.985491000502502e-05, "loss": 3.887, "step": 1841152 }, { "epoch": 1.0, "learning_rate": 1.98465240575145e-05, "loss": 3.8872, "step": 1841664 }, { "epoch": 1.0, "learning_rate": 1.983813811000398e-05, "loss": 3.8996, "step": 1842176 }, { "epoch": 1.0, "learning_rate": 1.9829752162493455e-05, "loss": 3.889, "step": 1842688 }, { "epoch": 1.0, "learning_rate": 1.9821366214982935e-05, "loss": 3.8899, "step": 1843200 }, { "epoch": 1.0, "learning_rate": 1.9812980267472415e-05, "loss": 3.8847, "step": 1843712 }, { "epoch": 1.0, "learning_rate": 1.98045943199619e-05, "loss": 3.8822, "step": 1844224 }, { "epoch": 1.0, "learning_rate": 1.979620837245138e-05, "loss": 3.8951, "step": 1844736 }, { "epoch": 1.0, "learning_rate": 1.9787838803744588e-05, "loss": 3.8814, "step": 1845248 }, { "epoch": 1.0, "learning_rate": 1.97794692350378e-05, "loss": 3.8865, "step": 1845760 }, { "epoch": 1.0, "learning_rate": 1.977108328752728e-05, "loss": 3.8764, "step": 1846272 }, { "epoch": 1.0, "learning_rate": 1.9762713718820493e-05, "loss": 3.8844, "step": 1846784 }, { "epoch": 1.01, "learning_rate": 1.9754327771309973e-05, "loss": 3.8799, "step": 1847296 }, { "epoch": 1.01, "learning_rate": 1.9745941823799452e-05, "loss": 3.8879, "step": 1847808 }, { "epoch": 1.01, "learning_rate": 1.973755587628893e-05, "loss": 3.8919, "step": 1848320 }, { "epoch": 1.01, "learning_rate": 1.972916992877841e-05, "loss": 3.8931, "step": 1848832 }, { "epoch": 1.01, "learning_rate": 1.972078398126789e-05, "loss": 3.8851, "step": 1849344 }, { "epoch": 1.01, "learning_rate": 1.971239803375737e-05, "loss": 3.8886, "step": 1849856 }, { "epoch": 1.01, "learning_rate": 1.9704012086246852e-05, "loss": 3.8925, "step": 1850368 }, { "epoch": 1.01, "learning_rate": 1.9695626138736332e-05, "loss": 3.8813, "step": 1850880 }, { "epoch": 1.01, "learning_rate": 1.9687240191225812e-05, "loss": 3.8822, "step": 1851392 }, { "epoch": 1.01, "learning_rate": 1.967885424371529e-05, "loss": 3.8821, "step": 1851904 }, { "epoch": 1.01, "learning_rate": 1.967046829620477e-05, "loss": 3.8855, "step": 1852416 }, { "epoch": 1.01, "learning_rate": 1.9662115106301714e-05, "loss": 3.8858, "step": 1852928 }, { "epoch": 1.01, "learning_rate": 1.9653729158791194e-05, "loss": 3.8887, "step": 1853440 }, { "epoch": 1.01, "learning_rate": 1.9645343211280674e-05, "loss": 3.8878, "step": 1853952 }, { "epoch": 1.01, "learning_rate": 1.9636957263770154e-05, "loss": 3.892, "step": 1854464 }, { "epoch": 1.01, "learning_rate": 1.9628571316259634e-05, "loss": 3.8869, "step": 1854976 }, { "epoch": 1.01, "learning_rate": 1.962018536874911e-05, "loss": 3.8883, "step": 1855488 }, { "epoch": 1.01, "learning_rate": 1.9611815800042323e-05, "loss": 3.8873, "step": 1856000 }, { "epoch": 1.01, "learning_rate": 1.9603429852531806e-05, "loss": 3.8517, "step": 1856512 }, { "epoch": 1.01, "learning_rate": 1.9595043905021286e-05, "loss": 3.8992, "step": 1857024 }, { "epoch": 1.01, "learning_rate": 1.9586657957510762e-05, "loss": 3.881, "step": 1857536 }, { "epoch": 1.01, "learning_rate": 1.9578272010000242e-05, "loss": 3.8887, "step": 1858048 }, { "epoch": 1.01, "learning_rate": 1.9569886062489722e-05, "loss": 3.8745, "step": 1858560 }, { "epoch": 1.01, "learning_rate": 1.9561500114979202e-05, "loss": 3.8696, "step": 1859072 }, { "epoch": 1.01, "learning_rate": 1.9553130546272415e-05, "loss": 3.869, "step": 1859584 }, { "epoch": 1.01, "learning_rate": 1.9544744598761895e-05, "loss": 3.8794, "step": 1860096 }, { "epoch": 1.01, "learning_rate": 1.9536358651251375e-05, "loss": 3.8841, "step": 1860608 }, { "epoch": 1.01, "learning_rate": 1.9527972703740855e-05, "loss": 3.8739, "step": 1861120 }, { "epoch": 1.01, "learning_rate": 1.9519603135034064e-05, "loss": 3.8923, "step": 1861632 }, { "epoch": 1.01, "learning_rate": 1.9511217187523544e-05, "loss": 3.88, "step": 1862144 }, { "epoch": 1.01, "learning_rate": 1.9502831240013024e-05, "loss": 3.8738, "step": 1862656 }, { "epoch": 1.01, "learning_rate": 1.9494461671306236e-05, "loss": 3.8892, "step": 1863168 }, { "epoch": 1.01, "learning_rate": 1.9486075723795716e-05, "loss": 3.8662, "step": 1863680 }, { "epoch": 1.01, "learning_rate": 1.9477689776285196e-05, "loss": 3.8712, "step": 1864192 }, { "epoch": 1.01, "learning_rate": 1.9469303828774676e-05, "loss": 3.8841, "step": 1864704 }, { "epoch": 1.01, "learning_rate": 1.9460917881264156e-05, "loss": 3.8883, "step": 1865216 }, { "epoch": 1.01, "learning_rate": 1.945254831255737e-05, "loss": 3.8718, "step": 1865728 }, { "epoch": 1.01, "learning_rate": 1.944416236504685e-05, "loss": 3.8789, "step": 1866240 }, { "epoch": 1.01, "learning_rate": 1.943577641753633e-05, "loss": 3.8658, "step": 1866752 }, { "epoch": 1.01, "learning_rate": 1.942739047002581e-05, "loss": 3.8893, "step": 1867264 }, { "epoch": 1.01, "learning_rate": 1.9419004522515288e-05, "loss": 3.8896, "step": 1867776 }, { "epoch": 1.01, "learning_rate": 1.9410618575004765e-05, "loss": 3.8865, "step": 1868288 }, { "epoch": 1.01, "learning_rate": 1.9402249006297977e-05, "loss": 3.8902, "step": 1868800 }, { "epoch": 1.01, "learning_rate": 1.939386305878746e-05, "loss": 3.895, "step": 1869312 }, { "epoch": 1.01, "learning_rate": 1.938547711127694e-05, "loss": 3.9065, "step": 1869824 }, { "epoch": 1.01, "learning_rate": 1.9377091163766417e-05, "loss": 3.8835, "step": 1870336 }, { "epoch": 1.01, "learning_rate": 1.9368705216255897e-05, "loss": 3.8851, "step": 1870848 }, { "epoch": 1.01, "learning_rate": 1.9360319268745377e-05, "loss": 3.8843, "step": 1871360 }, { "epoch": 1.01, "learning_rate": 1.9351933321234857e-05, "loss": 3.8819, "step": 1871872 }, { "epoch": 1.01, "learning_rate": 1.9343547373724337e-05, "loss": 3.882, "step": 1872384 }, { "epoch": 1.01, "learning_rate": 1.9335161426213817e-05, "loss": 3.8869, "step": 1872896 }, { "epoch": 1.01, "learning_rate": 1.93267754787033e-05, "loss": 3.8891, "step": 1873408 }, { "epoch": 1.01, "learning_rate": 1.9318389531192777e-05, "loss": 3.895, "step": 1873920 }, { "epoch": 1.01, "learning_rate": 1.931001996248599e-05, "loss": 3.8748, "step": 1874432 }, { "epoch": 1.01, "learning_rate": 1.930163401497547e-05, "loss": 3.8753, "step": 1874944 }, { "epoch": 1.01, "learning_rate": 1.9293248067464946e-05, "loss": 3.8794, "step": 1875456 }, { "epoch": 1.01, "learning_rate": 1.928486211995443e-05, "loss": 3.8935, "step": 1875968 }, { "epoch": 1.01, "learning_rate": 1.927647617244391e-05, "loss": 3.8874, "step": 1876480 }, { "epoch": 1.01, "learning_rate": 1.926810660373712e-05, "loss": 3.8757, "step": 1876992 }, { "epoch": 1.02, "learning_rate": 1.9259720656226598e-05, "loss": 3.88, "step": 1877504 }, { "epoch": 1.02, "learning_rate": 1.9251334708716078e-05, "loss": 3.8874, "step": 1878016 }, { "epoch": 1.02, "learning_rate": 1.9242948761205558e-05, "loss": 3.8812, "step": 1878528 }, { "epoch": 1.02, "learning_rate": 1.9234562813695038e-05, "loss": 3.8772, "step": 1879040 }, { "epoch": 1.02, "learning_rate": 1.922617686618452e-05, "loss": 3.8945, "step": 1879552 }, { "epoch": 1.02, "learning_rate": 1.9217790918674e-05, "loss": 3.8884, "step": 1880064 }, { "epoch": 1.02, "learning_rate": 1.9209404971163478e-05, "loss": 3.8864, "step": 1880576 }, { "epoch": 1.02, "learning_rate": 1.920103540245669e-05, "loss": 3.8793, "step": 1881088 }, { "epoch": 1.02, "learning_rate": 1.919264945494617e-05, "loss": 3.8793, "step": 1881600 }, { "epoch": 1.02, "learning_rate": 1.918426350743565e-05, "loss": 3.88, "step": 1882112 }, { "epoch": 1.02, "learning_rate": 1.917587755992513e-05, "loss": 3.8923, "step": 1882624 }, { "epoch": 1.02, "learning_rate": 1.916749161241461e-05, "loss": 3.8886, "step": 1883136 }, { "epoch": 1.02, "learning_rate": 1.915910566490409e-05, "loss": 3.8864, "step": 1883648 }, { "epoch": 1.02, "learning_rate": 1.9150736096197303e-05, "loss": 3.8901, "step": 1884160 }, { "epoch": 1.02, "learning_rate": 1.914235014868678e-05, "loss": 3.8824, "step": 1884672 }, { "epoch": 1.02, "learning_rate": 1.913396420117626e-05, "loss": 3.8825, "step": 1885184 }, { "epoch": 1.02, "learning_rate": 1.912557825366574e-05, "loss": 3.8721, "step": 1885696 }, { "epoch": 1.02, "learning_rate": 1.9117225063762684e-05, "loss": 3.8682, "step": 1886208 }, { "epoch": 1.02, "learning_rate": 1.9108839116252164e-05, "loss": 3.8895, "step": 1886720 }, { "epoch": 1.02, "learning_rate": 1.9100453168741644e-05, "loss": 3.8764, "step": 1887232 }, { "epoch": 1.02, "learning_rate": 1.9092067221231124e-05, "loss": 3.8736, "step": 1887744 }, { "epoch": 1.02, "learning_rate": 1.9083697652524337e-05, "loss": 3.8742, "step": 1888256 }, { "epoch": 1.02, "learning_rate": 1.9075311705013817e-05, "loss": 3.8779, "step": 1888768 }, { "epoch": 1.02, "learning_rate": 1.9066925757503296e-05, "loss": 3.8839, "step": 1889280 }, { "epoch": 1.02, "learning_rate": 1.9058539809992776e-05, "loss": 3.8755, "step": 1889792 }, { "epoch": 1.02, "learning_rate": 1.9050153862482253e-05, "loss": 3.8887, "step": 1890304 }, { "epoch": 1.02, "learning_rate": 1.9041767914971733e-05, "loss": 3.8862, "step": 1890816 }, { "epoch": 1.02, "learning_rate": 1.9033381967461213e-05, "loss": 3.8861, "step": 1891328 }, { "epoch": 1.02, "learning_rate": 1.9024996019950693e-05, "loss": 3.8844, "step": 1891840 }, { "epoch": 1.02, "learning_rate": 1.9016610072440176e-05, "loss": 3.8838, "step": 1892352 }, { "epoch": 1.02, "learning_rate": 1.9008256882537118e-05, "loss": 3.884, "step": 1892864 }, { "epoch": 1.02, "learning_rate": 1.8999870935026598e-05, "loss": 3.8882, "step": 1893376 }, { "epoch": 1.02, "learning_rate": 1.8991484987516074e-05, "loss": 3.886, "step": 1893888 }, { "epoch": 1.02, "learning_rate": 1.8983099040005554e-05, "loss": 3.8814, "step": 1894400 }, { "epoch": 1.02, "learning_rate": 1.8974713092495038e-05, "loss": 3.8873, "step": 1894912 }, { "epoch": 1.02, "learning_rate": 1.8966327144984518e-05, "loss": 3.8815, "step": 1895424 }, { "epoch": 1.02, "learning_rate": 1.8957941197473998e-05, "loss": 3.8802, "step": 1895936 }, { "epoch": 1.02, "learning_rate": 1.8949555249963478e-05, "loss": 3.8712, "step": 1896448 }, { "epoch": 1.02, "learning_rate": 1.8941169302452957e-05, "loss": 3.8763, "step": 1896960 }, { "epoch": 1.02, "learning_rate": 1.89328161125499e-05, "loss": 3.874, "step": 1897472 }, { "epoch": 1.02, "learning_rate": 1.892443016503938e-05, "loss": 3.8883, "step": 1897984 }, { "epoch": 1.02, "learning_rate": 1.891604421752886e-05, "loss": 3.8806, "step": 1898496 }, { "epoch": 1.02, "learning_rate": 1.890765827001834e-05, "loss": 3.8931, "step": 1899008 }, { "epoch": 1.02, "learning_rate": 1.889927232250782e-05, "loss": 3.8728, "step": 1899520 }, { "epoch": 1.02, "learning_rate": 1.88908863749973e-05, "loss": 3.8934, "step": 1900032 }, { "epoch": 1.02, "learning_rate": 1.888250042748678e-05, "loss": 3.8866, "step": 1900544 }, { "epoch": 1.02, "learning_rate": 1.8874114479976255e-05, "loss": 3.8875, "step": 1901056 }, { "epoch": 1.02, "learning_rate": 1.886572853246574e-05, "loss": 3.8869, "step": 1901568 }, { "epoch": 1.02, "learning_rate": 1.885734258495522e-05, "loss": 3.8843, "step": 1902080 }, { "epoch": 1.02, "learning_rate": 1.88489566374447e-05, "loss": 3.8868, "step": 1902592 }, { "epoch": 1.02, "learning_rate": 1.8840587068737908e-05, "loss": 3.8956, "step": 1903104 }, { "epoch": 1.02, "learning_rate": 1.8832201121227388e-05, "loss": 3.8752, "step": 1903616 }, { "epoch": 1.02, "learning_rate": 1.8823815173716868e-05, "loss": 3.8874, "step": 1904128 }, { "epoch": 1.02, "learning_rate": 1.8815429226206348e-05, "loss": 3.8842, "step": 1904640 }, { "epoch": 1.02, "learning_rate": 1.880704327869583e-05, "loss": 3.8825, "step": 1905152 }, { "epoch": 1.02, "learning_rate": 1.879865733118531e-05, "loss": 3.881, "step": 1905664 }, { "epoch": 1.02, "learning_rate": 1.8790271383674787e-05, "loss": 3.8766, "step": 1906176 }, { "epoch": 1.02, "learning_rate": 1.8781885436164267e-05, "loss": 3.8893, "step": 1906688 }, { "epoch": 1.02, "learning_rate": 1.877353224626121e-05, "loss": 3.8809, "step": 1907200 }, { "epoch": 1.02, "learning_rate": 1.8765146298750692e-05, "loss": 3.8901, "step": 1907712 }, { "epoch": 1.03, "eval_loss": 3.9852066040039062, "eval_runtime": 295.3935, "eval_samples_per_second": 1291.806, "eval_steps_per_second": 40.37, "step": 1908000 }, { "epoch": 0.0, "learning_rate": 1.8756760351240172e-05, "loss": 3.8706, "step": 1908224 }, { "epoch": 0.0, "learning_rate": 1.8748374403729652e-05, "loss": 3.8769, "step": 1908736 }, { "epoch": 0.0, "learning_rate": 1.8739988456219132e-05, "loss": 3.8789, "step": 1909248 }, { "epoch": 0.0, "learning_rate": 1.8731602508708612e-05, "loss": 3.8832, "step": 1909760 }, { "epoch": 0.0, "learning_rate": 1.872321656119809e-05, "loss": 3.8948, "step": 1910272 }, { "epoch": 0.0, "learning_rate": 1.871483061368757e-05, "loss": 3.8848, "step": 1910784 }, { "epoch": 0.0, "learning_rate": 1.870644466617705e-05, "loss": 3.8775, "step": 1911296 }, { "epoch": 0.0, "learning_rate": 1.8698058718666532e-05, "loss": 3.878, "step": 1911808 }, { "epoch": 0.0, "learning_rate": 1.8689672771156012e-05, "loss": 3.8739, "step": 1912320 }, { "epoch": 0.0, "learning_rate": 1.8681286823645492e-05, "loss": 3.8903, "step": 1912832 }, { "epoch": 0.0, "learning_rate": 1.867290087613497e-05, "loss": 3.879, "step": 1913344 }, { "epoch": 0.0, "learning_rate": 1.866451492862445e-05, "loss": 3.8777, "step": 1913856 }, { "epoch": 0.0, "learning_rate": 1.865614535991766e-05, "loss": 3.8886, "step": 1914368 }, { "epoch": 0.0, "learning_rate": 1.864775941240714e-05, "loss": 3.8707, "step": 1914880 }, { "epoch": 0.0, "learning_rate": 1.863937346489662e-05, "loss": 3.8747, "step": 1915392 }, { "epoch": 0.0, "learning_rate": 1.86309875173861e-05, "loss": 3.8744, "step": 1915904 }, { "epoch": 0.0, "learning_rate": 1.862260156987558e-05, "loss": 3.8774, "step": 1916416 }, { "epoch": 0.0, "learning_rate": 1.861421562236506e-05, "loss": 3.8753, "step": 1916928 }, { "epoch": 0.0, "learning_rate": 1.860582967485454e-05, "loss": 3.8847, "step": 1917440 }, { "epoch": 0.0, "learning_rate": 1.859744372734402e-05, "loss": 3.8833, "step": 1917952 }, { "epoch": 0.0, "learning_rate": 1.85890577798335e-05, "loss": 3.8944, "step": 1918464 }, { "epoch": 0.0, "learning_rate": 1.858067183232298e-05, "loss": 3.8801, "step": 1918976 }, { "epoch": 0.0, "learning_rate": 1.857228588481246e-05, "loss": 3.886, "step": 1919488 }, { "epoch": 0.0, "learning_rate": 1.856389993730194e-05, "loss": 3.8791, "step": 1920000 }, { "epoch": 0.0, "learning_rate": 1.855551398979142e-05, "loss": 3.8799, "step": 1920512 }, { "epoch": 0.0, "learning_rate": 1.854714442108463e-05, "loss": 3.8857, "step": 1921024 }, { "epoch": 0.0, "learning_rate": 1.853875847357411e-05, "loss": 3.874, "step": 1921536 }, { "epoch": 0.0, "learning_rate": 1.8530372526063593e-05, "loss": 3.8832, "step": 1922048 }, { "epoch": 0.0, "learning_rate": 1.8521986578553073e-05, "loss": 3.8686, "step": 1922560 }, { "epoch": 0.0, "learning_rate": 1.8513617009846282e-05, "loss": 3.8785, "step": 1923072 }, { "epoch": 0.01, "learning_rate": 1.8505231062335762e-05, "loss": 3.8767, "step": 1923584 }, { "epoch": 0.01, "learning_rate": 1.8496845114825242e-05, "loss": 3.8796, "step": 1924096 }, { "epoch": 0.01, "learning_rate": 1.8488459167314722e-05, "loss": 3.8893, "step": 1924608 }, { "epoch": 0.01, "learning_rate": 1.8480073219804202e-05, "loss": 3.89, "step": 1925120 }, { "epoch": 0.01, "learning_rate": 1.8471703651097414e-05, "loss": 3.8796, "step": 1925632 }, { "epoch": 0.01, "learning_rate": 1.8463317703586894e-05, "loss": 3.8779, "step": 1926144 }, { "epoch": 0.01, "learning_rate": 1.8454931756076374e-05, "loss": 3.8913, "step": 1926656 }, { "epoch": 0.01, "learning_rate": 1.8446562187369583e-05, "loss": 3.878, "step": 1927168 }, { "epoch": 0.01, "learning_rate": 1.8438176239859063e-05, "loss": 3.8755, "step": 1927680 }, { "epoch": 0.01, "learning_rate": 1.8429790292348547e-05, "loss": 3.8774, "step": 1928192 }, { "epoch": 0.01, "learning_rate": 1.8421404344838026e-05, "loss": 3.8833, "step": 1928704 }, { "epoch": 0.01, "learning_rate": 1.8413018397327506e-05, "loss": 3.8806, "step": 1929216 }, { "epoch": 0.01, "learning_rate": 1.8404632449816983e-05, "loss": 3.8818, "step": 1929728 }, { "epoch": 0.01, "learning_rate": 1.8396246502306463e-05, "loss": 3.8825, "step": 1930240 }, { "epoch": 0.01, "learning_rate": 1.8387876933599675e-05, "loss": 3.8834, "step": 1930752 }, { "epoch": 0.01, "learning_rate": 1.8379490986089155e-05, "loss": 3.8835, "step": 1931264 }, { "epoch": 0.01, "learning_rate": 1.8371105038578635e-05, "loss": 3.8829, "step": 1931776 }, { "epoch": 0.01, "learning_rate": 1.8362719091068115e-05, "loss": 3.8828, "step": 1932288 }, { "epoch": 0.01, "learning_rate": 1.8354333143557595e-05, "loss": 3.8495, "step": 1932800 }, { "epoch": 0.01, "learning_rate": 1.8345947196047075e-05, "loss": 3.8896, "step": 1933312 }, { "epoch": 0.01, "learning_rate": 1.8337577627340284e-05, "loss": 3.8753, "step": 1933824 }, { "epoch": 0.01, "learning_rate": 1.8329191679829764e-05, "loss": 3.8871, "step": 1934336 }, { "epoch": 0.01, "learning_rate": 1.8320805732319248e-05, "loss": 3.8693, "step": 1934848 }, { "epoch": 0.01, "learning_rate": 1.8312419784808728e-05, "loss": 3.8638, "step": 1935360 }, { "epoch": 0.01, "learning_rate": 1.8304050216101937e-05, "loss": 3.8628, "step": 1935872 }, { "epoch": 0.01, "learning_rate": 1.8295664268591417e-05, "loss": 3.8729, "step": 1936384 }, { "epoch": 0.01, "learning_rate": 1.8287278321080897e-05, "loss": 3.8839, "step": 1936896 }, { "epoch": 0.01, "learning_rate": 1.8278892373570377e-05, "loss": 3.867, "step": 1937408 }, { "epoch": 0.01, "learning_rate": 1.827052280486359e-05, "loss": 3.8875, "step": 1937920 }, { "epoch": 0.01, "learning_rate": 1.826213685735307e-05, "loss": 3.8782, "step": 1938432 }, { "epoch": 0.01, "learning_rate": 1.825375090984255e-05, "loss": 3.8629, "step": 1938944 }, { "epoch": 0.01, "learning_rate": 1.824536496233203e-05, "loss": 3.8843, "step": 1939456 }, { "epoch": 0.01, "learning_rate": 1.823697901482151e-05, "loss": 3.8647, "step": 1939968 }, { "epoch": 0.01, "learning_rate": 1.8228593067310985e-05, "loss": 3.8613, "step": 1940480 }, { "epoch": 0.01, "learning_rate": 1.82202234986042e-05, "loss": 3.8786, "step": 1940992 }, { "epoch": 0.01, "learning_rate": 1.821183755109368e-05, "loss": 3.8827, "step": 1941504 }, { "epoch": 0.01, "learning_rate": 1.820345160358316e-05, "loss": 3.8686, "step": 1942016 }, { "epoch": 0.01, "learning_rate": 1.8195065656072638e-05, "loss": 3.8724, "step": 1942528 }, { "epoch": 0.01, "learning_rate": 1.8186679708562118e-05, "loss": 3.8638, "step": 1943040 }, { "epoch": 0.01, "learning_rate": 1.8178293761051598e-05, "loss": 3.8814, "step": 1943552 }, { "epoch": 0.01, "learning_rate": 1.8169907813541078e-05, "loss": 3.8839, "step": 1944064 }, { "epoch": 0.01, "learning_rate": 1.8161521866030558e-05, "loss": 3.8791, "step": 1944576 }, { "epoch": 0.01, "learning_rate": 1.815315229732377e-05, "loss": 3.8827, "step": 1945088 }, { "epoch": 0.01, "learning_rate": 1.8144782728616983e-05, "loss": 3.8894, "step": 1945600 }, { "epoch": 0.01, "learning_rate": 1.813639678110646e-05, "loss": 3.8982, "step": 1946112 }, { "epoch": 0.01, "learning_rate": 1.812802721239967e-05, "loss": 3.8826, "step": 1946624 }, { "epoch": 0.01, "learning_rate": 1.8119641264889155e-05, "loss": 3.8836, "step": 1947136 }, { "epoch": 0.01, "learning_rate": 1.8111255317378635e-05, "loss": 3.8768, "step": 1947648 }, { "epoch": 0.01, "learning_rate": 1.810286936986811e-05, "loss": 3.8806, "step": 1948160 }, { "epoch": 0.01, "learning_rate": 1.809448342235759e-05, "loss": 3.8736, "step": 1948672 }, { "epoch": 0.01, "learning_rate": 1.808609747484707e-05, "loss": 3.8838, "step": 1949184 }, { "epoch": 0.01, "learning_rate": 1.807771152733655e-05, "loss": 3.8812, "step": 1949696 }, { "epoch": 0.01, "learning_rate": 1.806932557982603e-05, "loss": 3.8923, "step": 1950208 }, { "epoch": 0.01, "learning_rate": 1.806093963231551e-05, "loss": 3.866, "step": 1950720 }, { "epoch": 0.01, "learning_rate": 1.805255368480499e-05, "loss": 3.87, "step": 1951232 }, { "epoch": 0.01, "learning_rate": 1.8044184116098204e-05, "loss": 3.8774, "step": 1951744 }, { "epoch": 0.01, "learning_rate": 1.8035798168587684e-05, "loss": 3.8827, "step": 1952256 }, { "epoch": 0.01, "learning_rate": 1.8027412221077164e-05, "loss": 3.8837, "step": 1952768 }, { "epoch": 0.01, "learning_rate": 1.8019042652370373e-05, "loss": 3.8737, "step": 1953280 }, { "epoch": 0.02, "learning_rate": 1.8010656704859856e-05, "loss": 3.8741, "step": 1953792 }, { "epoch": 0.02, "learning_rate": 1.8002270757349336e-05, "loss": 3.8807, "step": 1954304 }, { "epoch": 0.02, "learning_rate": 1.7993884809838813e-05, "loss": 3.8762, "step": 1954816 }, { "epoch": 0.02, "learning_rate": 1.7985498862328293e-05, "loss": 3.8697, "step": 1955328 }, { "epoch": 0.02, "learning_rate": 1.7977112914817772e-05, "loss": 3.8904, "step": 1955840 }, { "epoch": 0.02, "learning_rate": 1.7968726967307252e-05, "loss": 3.8818, "step": 1956352 }, { "epoch": 0.02, "learning_rate": 1.7960341019796732e-05, "loss": 3.8826, "step": 1956864 }, { "epoch": 0.02, "learning_rate": 1.7951955072286212e-05, "loss": 3.8732, "step": 1957376 }, { "epoch": 0.02, "learning_rate": 1.7943585503579425e-05, "loss": 3.8741, "step": 1957888 }, { "epoch": 0.02, "learning_rate": 1.7935199556068905e-05, "loss": 3.8715, "step": 1958400 }, { "epoch": 0.02, "learning_rate": 1.7926813608558385e-05, "loss": 3.886, "step": 1958912 }, { "epoch": 0.02, "learning_rate": 1.7918427661047865e-05, "loss": 3.8865, "step": 1959424 }, { "epoch": 0.02, "learning_rate": 1.7910041713537345e-05, "loss": 3.8765, "step": 1959936 }, { "epoch": 0.02, "learning_rate": 1.7901655766026825e-05, "loss": 3.8843, "step": 1960448 }, { "epoch": 0.02, "learning_rate": 1.7893269818516305e-05, "loss": 3.8783, "step": 1960960 }, { "epoch": 0.02, "learning_rate": 1.7884883871005784e-05, "loss": 3.8812, "step": 1961472 }, { "epoch": 0.02, "learning_rate": 1.7876514302298994e-05, "loss": 3.8662, "step": 1961984 }, { "epoch": 0.02, "learning_rate": 1.7868128354788474e-05, "loss": 3.8673, "step": 1962496 }, { "epoch": 0.02, "learning_rate": 1.7859742407277954e-05, "loss": 3.8776, "step": 1963008 }, { "epoch": 0.02, "learning_rate": 1.7851356459767433e-05, "loss": 3.8778, "step": 1963520 }, { "epoch": 0.02, "learning_rate": 1.7842970512256917e-05, "loss": 3.865, "step": 1964032 }, { "epoch": 0.02, "learning_rate": 1.7834600943550126e-05, "loss": 3.8705, "step": 1964544 }, { "epoch": 0.02, "learning_rate": 1.782623137484334e-05, "loss": 3.8711, "step": 1965056 }, { "epoch": 0.02, "learning_rate": 1.781784542733282e-05, "loss": 3.8777, "step": 1965568 }, { "epoch": 0.02, "learning_rate": 1.7809459479822295e-05, "loss": 3.8685, "step": 1966080 }, { "epoch": 0.02, "learning_rate": 1.7801073532311778e-05, "loss": 3.8843, "step": 1966592 }, { "epoch": 0.02, "learning_rate": 1.7792687584801258e-05, "loss": 3.8816, "step": 1967104 }, { "epoch": 0.02, "learning_rate": 1.7784301637290738e-05, "loss": 3.8818, "step": 1967616 }, { "epoch": 0.02, "learning_rate": 1.7775915689780218e-05, "loss": 3.8755, "step": 1968128 }, { "epoch": 0.02, "learning_rate": 1.7767529742269698e-05, "loss": 3.8835, "step": 1968640 }, { "epoch": 0.02, "learning_rate": 1.7759160173562907e-05, "loss": 3.8802, "step": 1969152 }, { "epoch": 0.02, "learning_rate": 1.7750774226052387e-05, "loss": 3.8851, "step": 1969664 }, { "epoch": 0.02, "learning_rate": 1.77424046573456e-05, "loss": 3.8808, "step": 1970176 }, { "epoch": 0.02, "learning_rate": 1.773401870983508e-05, "loss": 3.8747, "step": 1970688 }, { "epoch": 0.02, "learning_rate": 1.772563276232456e-05, "loss": 3.8807, "step": 1971200 }, { "epoch": 0.02, "learning_rate": 1.771724681481404e-05, "loss": 3.8812, "step": 1971712 }, { "epoch": 0.02, "learning_rate": 1.770886086730352e-05, "loss": 3.874, "step": 1972224 }, { "epoch": 0.02, "learning_rate": 1.7700474919793e-05, "loss": 3.8702, "step": 1972736 }, { "epoch": 0.02, "learning_rate": 1.769208897228248e-05, "loss": 3.8732, "step": 1973248 }, { "epoch": 0.02, "learning_rate": 1.768370302477196e-05, "loss": 3.8659, "step": 1973760 }, { "epoch": 0.02, "learning_rate": 1.767531707726144e-05, "loss": 3.8836, "step": 1974272 }, { "epoch": 0.02, "learning_rate": 1.766693112975092e-05, "loss": 3.8724, "step": 1974784 }, { "epoch": 0.02, "learning_rate": 1.76585451822404e-05, "loss": 3.886, "step": 1975296 }, { "epoch": 0.02, "learning_rate": 1.765015923472988e-05, "loss": 3.868, "step": 1975808 }, { "epoch": 0.02, "learning_rate": 1.7641789666023088e-05, "loss": 3.885, "step": 1976320 }, { "epoch": 0.02, "learning_rate": 1.763340371851257e-05, "loss": 3.8856, "step": 1976832 }, { "epoch": 0.02, "learning_rate": 1.762501777100205e-05, "loss": 3.8842, "step": 1977344 }, { "epoch": 0.02, "learning_rate": 1.761663182349153e-05, "loss": 3.8815, "step": 1977856 }, { "epoch": 0.02, "learning_rate": 1.7608245875981008e-05, "loss": 3.8756, "step": 1978368 }, { "epoch": 0.02, "learning_rate": 1.759987630727422e-05, "loss": 3.8856, "step": 1978880 }, { "epoch": 0.02, "learning_rate": 1.7591506738567433e-05, "loss": 3.8883, "step": 1979392 }, { "epoch": 0.02, "learning_rate": 1.7583120791056913e-05, "loss": 3.8742, "step": 1979904 }, { "epoch": 0.02, "learning_rate": 1.7574734843546393e-05, "loss": 3.8805, "step": 1980416 }, { "epoch": 0.02, "learning_rate": 1.7566348896035873e-05, "loss": 3.8809, "step": 1980928 }, { "epoch": 0.02, "learning_rate": 1.7557962948525353e-05, "loss": 3.8768, "step": 1981440 }, { "epoch": 0.02, "learning_rate": 1.754957700101483e-05, "loss": 3.8755, "step": 1981952 }, { "epoch": 0.02, "learning_rate": 1.7541207432308042e-05, "loss": 3.871, "step": 1982464 }, { "epoch": 0.02, "learning_rate": 1.7532837863601254e-05, "loss": 3.8815, "step": 1982976 }, { "epoch": 0.02, "learning_rate": 1.7524451916090734e-05, "loss": 3.8774, "step": 1983488 }, { "epoch": 0.02, "learning_rate": 1.7516065968580214e-05, "loss": 3.8836, "step": 1984000 }, { "epoch": 0.03, "eval_loss": 3.9835472106933594, "eval_runtime": 297.2741, "eval_samples_per_second": 1283.633, "eval_steps_per_second": 40.114, "step": 1984320 }, { "epoch": 1.0, "learning_rate": 1.7507680021069694e-05, "loss": 3.8686, "step": 1984512 }, { "epoch": 1.0, "learning_rate": 1.7499294073559174e-05, "loss": 3.8741, "step": 1985024 }, { "epoch": 1.0, "learning_rate": 1.749090812604865e-05, "loss": 3.8734, "step": 1985536 }, { "epoch": 1.0, "learning_rate": 1.7482522178538134e-05, "loss": 3.8784, "step": 1986048 }, { "epoch": 1.0, "learning_rate": 1.7474136231027614e-05, "loss": 3.8898, "step": 1986560 }, { "epoch": 1.0, "learning_rate": 1.7465750283517094e-05, "loss": 3.8828, "step": 1987072 }, { "epoch": 1.0, "learning_rate": 1.7457364336006574e-05, "loss": 3.87, "step": 1987584 }, { "epoch": 1.0, "learning_rate": 1.7448978388496054e-05, "loss": 3.8739, "step": 1988096 }, { "epoch": 1.0, "learning_rate": 1.7440592440985534e-05, "loss": 3.8692, "step": 1988608 }, { "epoch": 1.0, "learning_rate": 1.7432222872278743e-05, "loss": 3.8781, "step": 1989120 }, { "epoch": 1.0, "learning_rate": 1.7423836924768226e-05, "loss": 3.8763, "step": 1989632 }, { "epoch": 1.0, "learning_rate": 1.7415450977257706e-05, "loss": 3.8763, "step": 1990144 }, { "epoch": 1.0, "learning_rate": 1.7407081408550915e-05, "loss": 3.8818, "step": 1990656 }, { "epoch": 1.0, "learning_rate": 1.7398695461040395e-05, "loss": 3.8615, "step": 1991168 }, { "epoch": 1.0, "learning_rate": 1.7390309513529875e-05, "loss": 3.8715, "step": 1991680 }, { "epoch": 1.0, "learning_rate": 1.7381923566019355e-05, "loss": 3.8643, "step": 1992192 }, { "epoch": 1.0, "learning_rate": 1.7373537618508835e-05, "loss": 3.8787, "step": 1992704 }, { "epoch": 1.0, "learning_rate": 1.7365151670998315e-05, "loss": 3.872, "step": 1993216 }, { "epoch": 1.0, "learning_rate": 1.7356765723487795e-05, "loss": 3.8773, "step": 1993728 }, { "epoch": 1.0, "learning_rate": 1.7348379775977275e-05, "loss": 3.8756, "step": 1994240 }, { "epoch": 1.0, "learning_rate": 1.7339993828466755e-05, "loss": 3.8884, "step": 1994752 }, { "epoch": 1.0, "learning_rate": 1.7331624259759964e-05, "loss": 3.8737, "step": 1995264 }, { "epoch": 1.0, "learning_rate": 1.7323238312249444e-05, "loss": 3.8826, "step": 1995776 }, { "epoch": 1.0, "learning_rate": 1.7314852364738927e-05, "loss": 3.874, "step": 1996288 }, { "epoch": 1.0, "learning_rate": 1.7306466417228407e-05, "loss": 3.8755, "step": 1996800 }, { "epoch": 1.0, "learning_rate": 1.7298096848521616e-05, "loss": 3.8807, "step": 1997312 }, { "epoch": 1.0, "learning_rate": 1.7289710901011096e-05, "loss": 3.8677, "step": 1997824 }, { "epoch": 1.0, "learning_rate": 1.7281324953500576e-05, "loss": 3.8755, "step": 1998336 }, { "epoch": 1.0, "learning_rate": 1.7272939005990056e-05, "loss": 3.8682, "step": 1998848 }, { "epoch": 1.0, "learning_rate": 1.7264553058479536e-05, "loss": 3.8728, "step": 1999360 }, { "epoch": 1.01, "learning_rate": 1.7256167110969016e-05, "loss": 3.8742, "step": 1999872 }, { "epoch": 1.01, "learning_rate": 1.724779754226223e-05, "loss": 3.8763, "step": 2000384 }, { "epoch": 1.01, "learning_rate": 1.723941159475171e-05, "loss": 3.8765, "step": 2000896 }, { "epoch": 1.01, "learning_rate": 1.723102564724119e-05, "loss": 3.8898, "step": 2001408 }, { "epoch": 1.01, "learning_rate": 1.7222639699730665e-05, "loss": 3.8742, "step": 2001920 }, { "epoch": 1.01, "learning_rate": 1.721425375222015e-05, "loss": 3.8733, "step": 2002432 }, { "epoch": 1.01, "learning_rate": 1.720588418351336e-05, "loss": 3.8878, "step": 2002944 }, { "epoch": 1.01, "learning_rate": 1.719749823600284e-05, "loss": 3.8712, "step": 2003456 }, { "epoch": 1.01, "learning_rate": 1.7189112288492318e-05, "loss": 3.8722, "step": 2003968 }, { "epoch": 1.01, "learning_rate": 1.7180726340981798e-05, "loss": 3.8757, "step": 2004480 }, { "epoch": 1.01, "learning_rate": 1.7172340393471277e-05, "loss": 3.8722, "step": 2004992 }, { "epoch": 1.01, "learning_rate": 1.7163954445960757e-05, "loss": 3.8777, "step": 2005504 }, { "epoch": 1.01, "learning_rate": 1.7155568498450237e-05, "loss": 3.875, "step": 2006016 }, { "epoch": 1.01, "learning_rate": 1.714718255093972e-05, "loss": 3.8814, "step": 2006528 }, { "epoch": 1.01, "learning_rate": 1.7138796603429197e-05, "loss": 3.8739, "step": 2007040 }, { "epoch": 1.01, "learning_rate": 1.713042703472241e-05, "loss": 3.8801, "step": 2007552 }, { "epoch": 1.01, "learning_rate": 1.712204108721189e-05, "loss": 3.8765, "step": 2008064 }, { "epoch": 1.01, "learning_rate": 1.711365513970137e-05, "loss": 3.8805, "step": 2008576 }, { "epoch": 1.01, "learning_rate": 1.710526919219085e-05, "loss": 3.8447, "step": 2009088 }, { "epoch": 1.01, "learning_rate": 1.7096899623484062e-05, "loss": 3.8835, "step": 2009600 }, { "epoch": 1.01, "learning_rate": 1.7088513675973542e-05, "loss": 3.8682, "step": 2010112 }, { "epoch": 1.01, "learning_rate": 1.7080127728463022e-05, "loss": 3.8802, "step": 2010624 }, { "epoch": 1.01, "learning_rate": 1.70717417809525e-05, "loss": 3.8648, "step": 2011136 }, { "epoch": 1.01, "learning_rate": 1.706337221224571e-05, "loss": 3.8592, "step": 2011648 }, { "epoch": 1.01, "learning_rate": 1.7055002643538924e-05, "loss": 3.8595, "step": 2012160 }, { "epoch": 1.01, "learning_rate": 1.7046616696028404e-05, "loss": 3.8673, "step": 2012672 }, { "epoch": 1.01, "learning_rate": 1.7038230748517883e-05, "loss": 3.8795, "step": 2013184 }, { "epoch": 1.01, "learning_rate": 1.7029861179811093e-05, "loss": 3.8591, "step": 2013696 }, { "epoch": 1.01, "learning_rate": 1.7021475232300573e-05, "loss": 3.8812, "step": 2014208 }, { "epoch": 1.01, "learning_rate": 1.7013089284790053e-05, "loss": 3.876, "step": 2014720 }, { "epoch": 1.01, "learning_rate": 1.7004719716083265e-05, "loss": 3.8554, "step": 2015232 }, { "epoch": 1.01, "learning_rate": 1.6996333768572745e-05, "loss": 3.8772, "step": 2015744 }, { "epoch": 1.01, "learning_rate": 1.6987947821062225e-05, "loss": 3.8593, "step": 2016256 }, { "epoch": 1.01, "learning_rate": 1.6979561873551705e-05, "loss": 3.8575, "step": 2016768 }, { "epoch": 1.01, "learning_rate": 1.6971175926041185e-05, "loss": 3.8726, "step": 2017280 }, { "epoch": 1.01, "learning_rate": 1.6962789978530665e-05, "loss": 3.8769, "step": 2017792 }, { "epoch": 1.01, "learning_rate": 1.6954404031020145e-05, "loss": 3.8603, "step": 2018304 }, { "epoch": 1.01, "learning_rate": 1.6946018083509625e-05, "loss": 3.8728, "step": 2018816 }, { "epoch": 1.01, "learning_rate": 1.6937632135999105e-05, "loss": 3.8586, "step": 2019328 }, { "epoch": 1.01, "learning_rate": 1.6929246188488585e-05, "loss": 3.8714, "step": 2019840 }, { "epoch": 1.01, "learning_rate": 1.6920860240978065e-05, "loss": 3.8781, "step": 2020352 }, { "epoch": 1.01, "learning_rate": 1.6912474293467544e-05, "loss": 3.8746, "step": 2020864 }, { "epoch": 1.01, "learning_rate": 1.6904088345957024e-05, "loss": 3.8796, "step": 2021376 }, { "epoch": 1.01, "learning_rate": 1.6895702398446504e-05, "loss": 3.8805, "step": 2021888 }, { "epoch": 1.01, "learning_rate": 1.6887316450935984e-05, "loss": 3.8955, "step": 2022400 }, { "epoch": 1.01, "learning_rate": 1.6878946882229197e-05, "loss": 3.8774, "step": 2022912 }, { "epoch": 1.01, "learning_rate": 1.6870560934718673e-05, "loss": 3.88, "step": 2023424 }, { "epoch": 1.01, "learning_rate": 1.6862174987208153e-05, "loss": 3.8679, "step": 2023936 }, { "epoch": 1.01, "learning_rate": 1.6853789039697633e-05, "loss": 3.8752, "step": 2024448 }, { "epoch": 1.01, "learning_rate": 1.6845419470990846e-05, "loss": 3.8708, "step": 2024960 }, { "epoch": 1.01, "learning_rate": 1.6837033523480326e-05, "loss": 3.8765, "step": 2025472 }, { "epoch": 1.01, "learning_rate": 1.6828647575969806e-05, "loss": 3.8803, "step": 2025984 }, { "epoch": 1.01, "learning_rate": 1.6820261628459286e-05, "loss": 3.8861, "step": 2026496 }, { "epoch": 1.01, "learning_rate": 1.6811875680948766e-05, "loss": 3.8634, "step": 2027008 }, { "epoch": 1.01, "learning_rate": 1.6803506112241975e-05, "loss": 3.8676, "step": 2027520 }, { "epoch": 1.01, "learning_rate": 1.6795120164731458e-05, "loss": 3.8682, "step": 2028032 }, { "epoch": 1.01, "learning_rate": 1.6786734217220938e-05, "loss": 3.8796, "step": 2028544 }, { "epoch": 1.01, "learning_rate": 1.6778348269710418e-05, "loss": 3.8759, "step": 2029056 }, { "epoch": 1.01, "learning_rate": 1.6769962322199898e-05, "loss": 3.8699, "step": 2029568 }, { "epoch": 1.01, "learning_rate": 1.6761592753493107e-05, "loss": 3.8716, "step": 2030080 }, { "epoch": 1.02, "learning_rate": 1.6753206805982587e-05, "loss": 3.8748, "step": 2030592 }, { "epoch": 1.02, "learning_rate": 1.6744820858472067e-05, "loss": 3.8707, "step": 2031104 }, { "epoch": 1.02, "learning_rate": 1.673643491096155e-05, "loss": 3.8671, "step": 2031616 }, { "epoch": 1.02, "learning_rate": 1.672804896345103e-05, "loss": 3.8841, "step": 2032128 }, { "epoch": 1.02, "learning_rate": 1.6719663015940507e-05, "loss": 3.8818, "step": 2032640 }, { "epoch": 1.02, "learning_rate": 1.6711277068429987e-05, "loss": 3.8767, "step": 2033152 }, { "epoch": 1.02, "learning_rate": 1.6702891120919467e-05, "loss": 3.8685, "step": 2033664 }, { "epoch": 1.02, "learning_rate": 1.669452155221268e-05, "loss": 3.8695, "step": 2034176 }, { "epoch": 1.02, "learning_rate": 1.668613560470216e-05, "loss": 3.8716, "step": 2034688 }, { "epoch": 1.02, "learning_rate": 1.667774965719164e-05, "loss": 3.8772, "step": 2035200 }, { "epoch": 1.02, "learning_rate": 1.666936370968112e-05, "loss": 3.8848, "step": 2035712 }, { "epoch": 1.02, "learning_rate": 1.66609777621706e-05, "loss": 3.8691, "step": 2036224 }, { "epoch": 1.02, "learning_rate": 1.6652608193463808e-05, "loss": 3.8817, "step": 2036736 }, { "epoch": 1.02, "learning_rate": 1.6644222245953288e-05, "loss": 3.8749, "step": 2037248 }, { "epoch": 1.02, "learning_rate": 1.6635836298442768e-05, "loss": 3.8729, "step": 2037760 }, { "epoch": 1.02, "learning_rate": 1.662745035093225e-05, "loss": 3.8633, "step": 2038272 }, { "epoch": 1.02, "learning_rate": 1.661908078222546e-05, "loss": 3.8642, "step": 2038784 }, { "epoch": 1.02, "learning_rate": 1.661069483471494e-05, "loss": 3.8698, "step": 2039296 }, { "epoch": 1.02, "learning_rate": 1.660230888720442e-05, "loss": 3.8707, "step": 2039808 }, { "epoch": 1.02, "learning_rate": 1.659393931849763e-05, "loss": 3.8618, "step": 2040320 }, { "epoch": 1.02, "learning_rate": 1.6585553370987113e-05, "loss": 3.8648, "step": 2040832 }, { "epoch": 1.02, "learning_rate": 1.6577167423476593e-05, "loss": 3.8598, "step": 2041344 }, { "epoch": 1.02, "learning_rate": 1.6568781475966073e-05, "loss": 3.8729, "step": 2041856 }, { "epoch": 1.02, "learning_rate": 1.6560395528455553e-05, "loss": 3.8671, "step": 2042368 }, { "epoch": 1.02, "learning_rate": 1.6552025959748762e-05, "loss": 3.8752, "step": 2042880 }, { "epoch": 1.02, "learning_rate": 1.6543640012238242e-05, "loss": 3.877, "step": 2043392 }, { "epoch": 1.02, "learning_rate": 1.6535254064727722e-05, "loss": 3.8742, "step": 2043904 }, { "epoch": 1.02, "learning_rate": 1.6526868117217205e-05, "loss": 3.8702, "step": 2044416 }, { "epoch": 1.02, "learning_rate": 1.6518482169706685e-05, "loss": 3.8807, "step": 2044928 }, { "epoch": 1.02, "learning_rate": 1.651009622219616e-05, "loss": 3.8752, "step": 2045440 }, { "epoch": 1.02, "learning_rate": 1.650171027468564e-05, "loss": 3.8828, "step": 2045952 }, { "epoch": 1.02, "learning_rate": 1.649332432717512e-05, "loss": 3.8717, "step": 2046464 }, { "epoch": 1.02, "learning_rate": 1.64849383796646e-05, "loss": 3.872, "step": 2046976 }, { "epoch": 1.02, "learning_rate": 1.647655243215408e-05, "loss": 3.8727, "step": 2047488 }, { "epoch": 1.02, "learning_rate": 1.646816648464356e-05, "loss": 3.8745, "step": 2048000 }, { "epoch": 1.02, "learning_rate": 1.6459796915936774e-05, "loss": 3.8674, "step": 2048512 }, { "epoch": 1.02, "learning_rate": 1.6451410968426254e-05, "loss": 3.8663, "step": 2049024 }, { "epoch": 1.02, "learning_rate": 1.6443025020915734e-05, "loss": 3.8641, "step": 2049536 }, { "epoch": 1.02, "learning_rate": 1.6434655452208943e-05, "loss": 3.8635, "step": 2050048 }, { "epoch": 1.02, "learning_rate": 1.6426269504698423e-05, "loss": 3.8794, "step": 2050560 }, { "epoch": 1.02, "learning_rate": 1.6417883557187906e-05, "loss": 3.8712, "step": 2051072 }, { "epoch": 1.02, "learning_rate": 1.6409497609677386e-05, "loss": 3.8791, "step": 2051584 }, { "epoch": 1.02, "learning_rate": 1.6401111662166866e-05, "loss": 3.867, "step": 2052096 }, { "epoch": 1.02, "learning_rate": 1.6392725714656343e-05, "loss": 3.8779, "step": 2052608 }, { "epoch": 1.02, "learning_rate": 1.6384356145949555e-05, "loss": 3.8766, "step": 2053120 }, { "epoch": 1.02, "learning_rate": 1.6375970198439035e-05, "loss": 3.8754, "step": 2053632 }, { "epoch": 1.02, "learning_rate": 1.6367584250928515e-05, "loss": 3.8746, "step": 2054144 }, { "epoch": 1.02, "learning_rate": 1.6359198303417995e-05, "loss": 3.871, "step": 2054656 }, { "epoch": 1.02, "learning_rate": 1.6350828734711207e-05, "loss": 3.8836, "step": 2055168 }, { "epoch": 1.02, "learning_rate": 1.6342442787200687e-05, "loss": 3.8842, "step": 2055680 }, { "epoch": 1.02, "learning_rate": 1.6334056839690164e-05, "loss": 3.8675, "step": 2056192 }, { "epoch": 1.02, "learning_rate": 1.6325670892179644e-05, "loss": 3.8732, "step": 2056704 }, { "epoch": 1.02, "learning_rate": 1.6317284944669127e-05, "loss": 3.8778, "step": 2057216 }, { "epoch": 1.02, "learning_rate": 1.630891537596234e-05, "loss": 3.8721, "step": 2057728 }, { "epoch": 1.02, "learning_rate": 1.6300529428451816e-05, "loss": 3.8689, "step": 2058240 }, { "epoch": 1.02, "learning_rate": 1.6292143480941296e-05, "loss": 3.8688, "step": 2058752 }, { "epoch": 1.02, "learning_rate": 1.6283757533430776e-05, "loss": 3.8771, "step": 2059264 }, { "epoch": 1.02, "learning_rate": 1.627538796472399e-05, "loss": 3.8733, "step": 2059776 }, { "epoch": 1.02, "learning_rate": 1.62670183960172e-05, "loss": 3.8778, "step": 2060288 }, { "epoch": 1.03, "eval_loss": 3.981863498687744, "eval_runtime": 293.9862, "eval_samples_per_second": 1297.99, "eval_steps_per_second": 40.563, "step": 2060640 }, { "epoch": 0.0, "learning_rate": 1.625863244850668e-05, "loss": 3.858, "step": 2060800 }, { "epoch": 0.0, "learning_rate": 1.625024650099616e-05, "loss": 3.8667, "step": 2061312 }, { "epoch": 0.0, "learning_rate": 1.6241860553485638e-05, "loss": 3.8685, "step": 2061824 }, { "epoch": 0.0, "learning_rate": 1.6233474605975118e-05, "loss": 3.8736, "step": 2062336 }, { "epoch": 0.0, "learning_rate": 1.6225088658464598e-05, "loss": 3.8813, "step": 2062848 }, { "epoch": 0.0, "learning_rate": 1.6216702710954078e-05, "loss": 3.8774, "step": 2063360 }, { "epoch": 0.0, "learning_rate": 1.620831676344356e-05, "loss": 3.8701, "step": 2063872 }, { "epoch": 0.0, "learning_rate": 1.619993081593304e-05, "loss": 3.8694, "step": 2064384 }, { "epoch": 0.0, "learning_rate": 1.619154486842252e-05, "loss": 3.8624, "step": 2064896 }, { "epoch": 0.0, "learning_rate": 1.6183158920911997e-05, "loss": 3.8703, "step": 2065408 }, { "epoch": 0.0, "learning_rate": 1.6174772973401477e-05, "loss": 3.8762, "step": 2065920 }, { "epoch": 0.0, "learning_rate": 1.6166387025890957e-05, "loss": 3.8706, "step": 2066432 }, { "epoch": 0.0, "learning_rate": 1.615801745718417e-05, "loss": 3.8743, "step": 2066944 }, { "epoch": 0.0, "learning_rate": 1.614963150967365e-05, "loss": 3.8588, "step": 2067456 }, { "epoch": 0.0, "learning_rate": 1.614124556216313e-05, "loss": 3.8699, "step": 2067968 }, { "epoch": 0.0, "learning_rate": 1.613285961465261e-05, "loss": 3.8539, "step": 2068480 }, { "epoch": 0.0, "learning_rate": 1.612447366714209e-05, "loss": 3.8727, "step": 2068992 }, { "epoch": 0.0, "learning_rate": 1.611608771963157e-05, "loss": 3.8681, "step": 2069504 }, { "epoch": 0.0, "learning_rate": 1.610770177212105e-05, "loss": 3.8693, "step": 2070016 }, { "epoch": 0.0, "learning_rate": 1.609931582461053e-05, "loss": 3.8694, "step": 2070528 }, { "epoch": 0.0, "learning_rate": 1.609092987710001e-05, "loss": 3.8884, "step": 2071040 }, { "epoch": 0.0, "learning_rate": 1.6082560308393222e-05, "loss": 3.8662, "step": 2071552 }, { "epoch": 0.0, "learning_rate": 1.607419073968643e-05, "loss": 3.8789, "step": 2072064 }, { "epoch": 0.0, "learning_rate": 1.606580479217591e-05, "loss": 3.8685, "step": 2072576 }, { "epoch": 0.0, "learning_rate": 1.605741884466539e-05, "loss": 3.8722, "step": 2073088 }, { "epoch": 0.0, "learning_rate": 1.6049032897154874e-05, "loss": 3.8777, "step": 2073600 }, { "epoch": 0.0, "learning_rate": 1.604064694964435e-05, "loss": 3.861, "step": 2074112 }, { "epoch": 0.0, "learning_rate": 1.603226100213383e-05, "loss": 3.8696, "step": 2074624 }, { "epoch": 0.0, "learning_rate": 1.6023891433427043e-05, "loss": 3.8635, "step": 2075136 }, { "epoch": 0.0, "learning_rate": 1.6015505485916523e-05, "loss": 3.8661, "step": 2075648 }, { "epoch": 0.01, "learning_rate": 1.6007119538406e-05, "loss": 3.8696, "step": 2076160 }, { "epoch": 0.01, "learning_rate": 1.5998733590895483e-05, "loss": 3.8723, "step": 2076672 }, { "epoch": 0.01, "learning_rate": 1.5990347643384963e-05, "loss": 3.8663, "step": 2077184 }, { "epoch": 0.01, "learning_rate": 1.5981961695874443e-05, "loss": 3.8877, "step": 2077696 }, { "epoch": 0.01, "learning_rate": 1.5973575748363923e-05, "loss": 3.8703, "step": 2078208 }, { "epoch": 0.01, "learning_rate": 1.5965189800853403e-05, "loss": 3.8685, "step": 2078720 }, { "epoch": 0.01, "learning_rate": 1.5956803853342883e-05, "loss": 3.8794, "step": 2079232 }, { "epoch": 0.01, "learning_rate": 1.594841790583236e-05, "loss": 3.8646, "step": 2079744 }, { "epoch": 0.01, "learning_rate": 1.5940048337125575e-05, "loss": 3.8654, "step": 2080256 }, { "epoch": 0.01, "learning_rate": 1.5931662389615055e-05, "loss": 3.8735, "step": 2080768 }, { "epoch": 0.01, "learning_rate": 1.5923276442104532e-05, "loss": 3.8658, "step": 2081280 }, { "epoch": 0.01, "learning_rate": 1.5914890494594012e-05, "loss": 3.8713, "step": 2081792 }, { "epoch": 0.01, "learning_rate": 1.5906504547083492e-05, "loss": 3.8754, "step": 2082304 }, { "epoch": 0.01, "learning_rate": 1.5898118599572972e-05, "loss": 3.8693, "step": 2082816 }, { "epoch": 0.01, "learning_rate": 1.5889732652062452e-05, "loss": 3.8744, "step": 2083328 }, { "epoch": 0.01, "learning_rate": 1.588134670455193e-05, "loss": 3.8738, "step": 2083840 }, { "epoch": 0.01, "learning_rate": 1.5872977135845144e-05, "loss": 3.8705, "step": 2084352 }, { "epoch": 0.01, "learning_rate": 1.5864591188334624e-05, "loss": 3.8757, "step": 2084864 }, { "epoch": 0.01, "learning_rate": 1.5856205240824104e-05, "loss": 3.8422, "step": 2085376 }, { "epoch": 0.01, "learning_rate": 1.5847819293313584e-05, "loss": 3.8748, "step": 2085888 }, { "epoch": 0.01, "learning_rate": 1.583946610341053e-05, "loss": 3.8663, "step": 2086400 }, { "epoch": 0.01, "learning_rate": 1.5831080155900006e-05, "loss": 3.8761, "step": 2086912 }, { "epoch": 0.01, "learning_rate": 1.5822694208389486e-05, "loss": 3.8609, "step": 2087424 }, { "epoch": 0.01, "learning_rate": 1.5814308260878965e-05, "loss": 3.8516, "step": 2087936 }, { "epoch": 0.01, "learning_rate": 1.5805938692172178e-05, "loss": 3.8596, "step": 2088448 }, { "epoch": 0.01, "learning_rate": 1.5797552744661655e-05, "loss": 3.8617, "step": 2088960 }, { "epoch": 0.01, "learning_rate": 1.5789166797151138e-05, "loss": 3.8741, "step": 2089472 }, { "epoch": 0.01, "learning_rate": 1.578079722844435e-05, "loss": 3.8513, "step": 2089984 }, { "epoch": 0.01, "learning_rate": 1.577241128093383e-05, "loss": 3.8806, "step": 2090496 }, { "epoch": 0.01, "learning_rate": 1.5764025333423307e-05, "loss": 3.8736, "step": 2091008 }, { "epoch": 0.01, "learning_rate": 1.5755639385912787e-05, "loss": 3.848, "step": 2091520 }, { "epoch": 0.01, "learning_rate": 1.5747253438402267e-05, "loss": 3.8727, "step": 2092032 }, { "epoch": 0.01, "learning_rate": 1.5738867490891747e-05, "loss": 3.8566, "step": 2092544 }, { "epoch": 0.01, "learning_rate": 1.573048154338123e-05, "loss": 3.8528, "step": 2093056 }, { "epoch": 0.01, "learning_rate": 1.572209559587071e-05, "loss": 3.8639, "step": 2093568 }, { "epoch": 0.01, "learning_rate": 1.5713709648360187e-05, "loss": 3.8748, "step": 2094080 }, { "epoch": 0.01, "learning_rate": 1.57053400796534e-05, "loss": 3.855, "step": 2094592 }, { "epoch": 0.01, "learning_rate": 1.569695413214288e-05, "loss": 3.8685, "step": 2095104 }, { "epoch": 0.01, "learning_rate": 1.568856818463236e-05, "loss": 3.85, "step": 2095616 }, { "epoch": 0.01, "learning_rate": 1.568018223712184e-05, "loss": 3.8664, "step": 2096128 }, { "epoch": 0.01, "learning_rate": 1.567179628961132e-05, "loss": 3.872, "step": 2096640 }, { "epoch": 0.01, "learning_rate": 1.56634103421008e-05, "loss": 3.8756, "step": 2097152 }, { "epoch": 0.01, "learning_rate": 1.565502439459028e-05, "loss": 3.873, "step": 2097664 }, { "epoch": 0.01, "learning_rate": 1.564663844707976e-05, "loss": 3.8755, "step": 2098176 }, { "epoch": 0.01, "learning_rate": 1.5638268878372968e-05, "loss": 3.8907, "step": 2098688 }, { "epoch": 0.01, "learning_rate": 1.5629882930862448e-05, "loss": 3.8714, "step": 2099200 }, { "epoch": 0.01, "learning_rate": 1.562151336215566e-05, "loss": 3.8767, "step": 2099712 }, { "epoch": 0.01, "learning_rate": 1.561312741464514e-05, "loss": 3.8619, "step": 2100224 }, { "epoch": 0.01, "learning_rate": 1.560474146713462e-05, "loss": 3.8695, "step": 2100736 }, { "epoch": 0.01, "learning_rate": 1.55963555196241e-05, "loss": 3.8655, "step": 2101248 }, { "epoch": 0.01, "learning_rate": 1.558796957211358e-05, "loss": 3.8691, "step": 2101760 }, { "epoch": 0.01, "learning_rate": 1.5579600003406793e-05, "loss": 3.8766, "step": 2102272 }, { "epoch": 0.01, "learning_rate": 1.5571214055896273e-05, "loss": 3.8802, "step": 2102784 }, { "epoch": 0.01, "learning_rate": 1.5562828108385753e-05, "loss": 3.8636, "step": 2103296 }, { "epoch": 0.01, "learning_rate": 1.5554442160875233e-05, "loss": 3.8617, "step": 2103808 }, { "epoch": 0.01, "learning_rate": 1.5546056213364712e-05, "loss": 3.8604, "step": 2104320 }, { "epoch": 0.01, "learning_rate": 1.553768664465792e-05, "loss": 3.8782, "step": 2104832 }, { "epoch": 0.01, "learning_rate": 1.55293006971474e-05, "loss": 3.8685, "step": 2105344 }, { "epoch": 0.01, "learning_rate": 1.5520914749636885e-05, "loss": 3.863, "step": 2105856 }, { "epoch": 0.01, "learning_rate": 1.5512528802126365e-05, "loss": 3.8724, "step": 2106368 }, { "epoch": 0.02, "learning_rate": 1.550414285461584e-05, "loss": 3.8674, "step": 2106880 }, { "epoch": 0.02, "learning_rate": 1.5495773285909054e-05, "loss": 3.8665, "step": 2107392 }, { "epoch": 0.02, "learning_rate": 1.5487387338398534e-05, "loss": 3.8642, "step": 2107904 }, { "epoch": 0.02, "learning_rate": 1.5479001390888014e-05, "loss": 3.8791, "step": 2108416 }, { "epoch": 0.02, "learning_rate": 1.5470615443377494e-05, "loss": 3.875, "step": 2108928 }, { "epoch": 0.02, "learning_rate": 1.5462229495866974e-05, "loss": 3.8744, "step": 2109440 }, { "epoch": 0.02, "learning_rate": 1.5453843548356454e-05, "loss": 3.8614, "step": 2109952 }, { "epoch": 0.02, "learning_rate": 1.5445457600845934e-05, "loss": 3.8657, "step": 2110464 }, { "epoch": 0.02, "learning_rate": 1.5437088032139143e-05, "loss": 3.8658, "step": 2110976 }, { "epoch": 0.02, "learning_rate": 1.5428702084628623e-05, "loss": 3.8743, "step": 2111488 }, { "epoch": 0.02, "learning_rate": 1.5420316137118103e-05, "loss": 3.8782, "step": 2112000 }, { "epoch": 0.02, "learning_rate": 1.5411930189607586e-05, "loss": 3.8683, "step": 2112512 }, { "epoch": 0.02, "learning_rate": 1.5403544242097066e-05, "loss": 3.8736, "step": 2113024 }, { "epoch": 0.02, "learning_rate": 1.5395158294586546e-05, "loss": 3.871, "step": 2113536 }, { "epoch": 0.02, "learning_rate": 1.5386772347076022e-05, "loss": 3.8684, "step": 2114048 }, { "epoch": 0.02, "learning_rate": 1.5378402778369235e-05, "loss": 3.8598, "step": 2114560 }, { "epoch": 0.02, "learning_rate": 1.5370016830858715e-05, "loss": 3.8614, "step": 2115072 }, { "epoch": 0.02, "learning_rate": 1.5361630883348195e-05, "loss": 3.8625, "step": 2115584 }, { "epoch": 0.02, "learning_rate": 1.5353244935837675e-05, "loss": 3.8668, "step": 2116096 }, { "epoch": 0.02, "learning_rate": 1.5344858988327155e-05, "loss": 3.857, "step": 2116608 }, { "epoch": 0.02, "learning_rate": 1.5336473040816635e-05, "loss": 3.8578, "step": 2117120 }, { "epoch": 0.02, "learning_rate": 1.5328087093306115e-05, "loss": 3.8594, "step": 2117632 }, { "epoch": 0.02, "learning_rate": 1.5319701145795595e-05, "loss": 3.8665, "step": 2118144 }, { "epoch": 0.02, "learning_rate": 1.5311331577088807e-05, "loss": 3.8656, "step": 2118656 }, { "epoch": 0.02, "learning_rate": 1.5302945629578287e-05, "loss": 3.8674, "step": 2119168 }, { "epoch": 0.02, "learning_rate": 1.5294559682067767e-05, "loss": 3.8708, "step": 2119680 }, { "epoch": 0.02, "learning_rate": 1.5286173734557247e-05, "loss": 3.874, "step": 2120192 }, { "epoch": 0.02, "learning_rate": 1.5277804165850456e-05, "loss": 3.8638, "step": 2120704 }, { "epoch": 0.02, "learning_rate": 1.5269418218339936e-05, "loss": 3.8741, "step": 2121216 }, { "epoch": 0.02, "learning_rate": 1.5261032270829416e-05, "loss": 3.8687, "step": 2121728 }, { "epoch": 0.02, "learning_rate": 1.5252646323318898e-05, "loss": 3.8768, "step": 2122240 }, { "epoch": 0.02, "learning_rate": 1.5244260375808378e-05, "loss": 3.869, "step": 2122752 }, { "epoch": 0.02, "learning_rate": 1.5235890807101588e-05, "loss": 3.8674, "step": 2123264 }, { "epoch": 0.02, "learning_rate": 1.5227504859591068e-05, "loss": 3.8671, "step": 2123776 }, { "epoch": 0.02, "learning_rate": 1.5219118912080548e-05, "loss": 3.8721, "step": 2124288 }, { "epoch": 0.02, "learning_rate": 1.5210732964570027e-05, "loss": 3.8639, "step": 2124800 }, { "epoch": 0.02, "learning_rate": 1.5202347017059506e-05, "loss": 3.8616, "step": 2125312 }, { "epoch": 0.02, "learning_rate": 1.5193977448352719e-05, "loss": 3.8534, "step": 2125824 }, { "epoch": 0.02, "learning_rate": 1.518560787964593e-05, "loss": 3.8616, "step": 2126336 }, { "epoch": 0.02, "learning_rate": 1.517722193213541e-05, "loss": 3.8724, "step": 2126848 }, { "epoch": 0.02, "learning_rate": 1.5168835984624891e-05, "loss": 3.8673, "step": 2127360 }, { "epoch": 0.02, "learning_rate": 1.5160450037114371e-05, "loss": 3.8744, "step": 2127872 }, { "epoch": 0.02, "learning_rate": 1.5152064089603848e-05, "loss": 3.8554, "step": 2128384 }, { "epoch": 0.02, "learning_rate": 1.514367814209333e-05, "loss": 3.8798, "step": 2128896 }, { "epoch": 0.02, "learning_rate": 1.513529219458281e-05, "loss": 3.8738, "step": 2129408 }, { "epoch": 0.02, "learning_rate": 1.512690624707229e-05, "loss": 3.8754, "step": 2129920 }, { "epoch": 0.02, "learning_rate": 1.511852029956177e-05, "loss": 3.8615, "step": 2130432 }, { "epoch": 0.02, "learning_rate": 1.511013435205125e-05, "loss": 3.869, "step": 2130944 }, { "epoch": 0.02, "learning_rate": 1.510176478334446e-05, "loss": 3.8786, "step": 2131456 }, { "epoch": 0.02, "learning_rate": 1.509337883583394e-05, "loss": 3.8797, "step": 2131968 }, { "epoch": 0.02, "learning_rate": 1.5084992888323422e-05, "loss": 3.8649, "step": 2132480 }, { "epoch": 0.02, "learning_rate": 1.5076606940812902e-05, "loss": 3.8647, "step": 2132992 }, { "epoch": 0.02, "learning_rate": 1.5068220993302382e-05, "loss": 3.8713, "step": 2133504 }, { "epoch": 0.02, "learning_rate": 1.505983504579186e-05, "loss": 3.8707, "step": 2134016 }, { "epoch": 0.02, "learning_rate": 1.5051465477085072e-05, "loss": 3.8629, "step": 2134528 }, { "epoch": 0.02, "learning_rate": 1.5043079529574552e-05, "loss": 3.8669, "step": 2135040 }, { "epoch": 0.02, "learning_rate": 1.503469358206403e-05, "loss": 3.8663, "step": 2135552 }, { "epoch": 0.02, "learning_rate": 1.502630763455351e-05, "loss": 3.8686, "step": 2136064 }, { "epoch": 0.02, "learning_rate": 1.5017938065846723e-05, "loss": 3.876, "step": 2136576 }, { "epoch": 0.03, "eval_loss": 3.9802908897399902, "eval_runtime": 310.2865, "eval_samples_per_second": 1229.802, "eval_steps_per_second": 38.432, "step": 2136960 }, { "epoch": 1.0, "learning_rate": 1.5009552118336203e-05, "loss": 3.8649, "step": 2137088 }, { "epoch": 1.0, "learning_rate": 1.5001166170825681e-05, "loss": 3.858, "step": 2137600 }, { "epoch": 1.0, "learning_rate": 1.4992780223315161e-05, "loss": 3.864, "step": 2138112 }, { "epoch": 1.0, "learning_rate": 1.4984394275804641e-05, "loss": 3.8717, "step": 2138624 }, { "epoch": 1.0, "learning_rate": 1.4976008328294123e-05, "loss": 3.8716, "step": 2139136 }, { "epoch": 1.0, "learning_rate": 1.4967622380783603e-05, "loss": 3.8759, "step": 2139648 }, { "epoch": 1.0, "learning_rate": 1.4959236433273083e-05, "loss": 3.8665, "step": 2140160 }, { "epoch": 1.0, "learning_rate": 1.4950850485762563e-05, "loss": 3.8629, "step": 2140672 }, { "epoch": 1.0, "learning_rate": 1.4942464538252041e-05, "loss": 3.8576, "step": 2141184 }, { "epoch": 1.0, "learning_rate": 1.4934078590741521e-05, "loss": 3.8669, "step": 2141696 }, { "epoch": 1.0, "learning_rate": 1.4925692643231001e-05, "loss": 3.8722, "step": 2142208 }, { "epoch": 1.0, "learning_rate": 1.4917323074524212e-05, "loss": 3.8675, "step": 2142720 }, { "epoch": 1.0, "learning_rate": 1.4908969884621155e-05, "loss": 3.8762, "step": 2143232 }, { "epoch": 1.0, "learning_rate": 1.4900583937110635e-05, "loss": 3.8504, "step": 2143744 }, { "epoch": 1.0, "learning_rate": 1.4892197989600115e-05, "loss": 3.8621, "step": 2144256 }, { "epoch": 1.0, "learning_rate": 1.4883812042089595e-05, "loss": 3.855, "step": 2144768 }, { "epoch": 1.0, "learning_rate": 1.4875426094579077e-05, "loss": 3.8681, "step": 2145280 }, { "epoch": 1.0, "learning_rate": 1.4867040147068556e-05, "loss": 3.8639, "step": 2145792 }, { "epoch": 1.0, "learning_rate": 1.4858654199558036e-05, "loss": 3.8652, "step": 2146304 }, { "epoch": 1.0, "learning_rate": 1.4850268252047515e-05, "loss": 3.8609, "step": 2146816 }, { "epoch": 1.0, "learning_rate": 1.4841898683340727e-05, "loss": 3.8858, "step": 2147328 }, { "epoch": 1.0, "learning_rate": 1.4833512735830207e-05, "loss": 3.8623, "step": 2147840 }, { "epoch": 1.0, "learning_rate": 1.4825126788319685e-05, "loss": 3.873, "step": 2148352 }, { "epoch": 1.0, "learning_rate": 1.4816740840809165e-05, "loss": 3.8638, "step": 2148864 }, { "epoch": 1.0, "learning_rate": 1.4808354893298645e-05, "loss": 3.8679, "step": 2149376 }, { "epoch": 1.0, "learning_rate": 1.4799985324591858e-05, "loss": 3.8694, "step": 2149888 }, { "epoch": 1.0, "learning_rate": 1.4791599377081336e-05, "loss": 3.856, "step": 2150400 }, { "epoch": 1.0, "learning_rate": 1.4783213429570816e-05, "loss": 3.8641, "step": 2150912 }, { "epoch": 1.0, "learning_rate": 1.4774827482060296e-05, "loss": 3.8594, "step": 2151424 }, { "epoch": 1.0, "learning_rate": 1.4766441534549778e-05, "loss": 3.8625, "step": 2151936 }, { "epoch": 1.01, "learning_rate": 1.4758055587039258e-05, "loss": 3.8677, "step": 2152448 }, { "epoch": 1.01, "learning_rate": 1.4749669639528738e-05, "loss": 3.8669, "step": 2152960 }, { "epoch": 1.01, "learning_rate": 1.4741300070821948e-05, "loss": 3.8629, "step": 2153472 }, { "epoch": 1.01, "learning_rate": 1.4732914123311428e-05, "loss": 3.8819, "step": 2153984 }, { "epoch": 1.01, "learning_rate": 1.4724528175800908e-05, "loss": 3.8652, "step": 2154496 }, { "epoch": 1.01, "learning_rate": 1.4716142228290388e-05, "loss": 3.8677, "step": 2155008 }, { "epoch": 1.01, "learning_rate": 1.4707756280779866e-05, "loss": 3.8745, "step": 2155520 }, { "epoch": 1.01, "learning_rate": 1.4699386712073079e-05, "loss": 3.8576, "step": 2156032 }, { "epoch": 1.01, "learning_rate": 1.4691000764562559e-05, "loss": 3.8645, "step": 2156544 }, { "epoch": 1.01, "learning_rate": 1.468261481705204e-05, "loss": 3.8664, "step": 2157056 }, { "epoch": 1.01, "learning_rate": 1.4674228869541517e-05, "loss": 3.8598, "step": 2157568 }, { "epoch": 1.01, "learning_rate": 1.4665859300834731e-05, "loss": 3.8696, "step": 2158080 }, { "epoch": 1.01, "learning_rate": 1.465748973212794e-05, "loss": 3.8727, "step": 2158592 }, { "epoch": 1.01, "learning_rate": 1.464910378461742e-05, "loss": 3.8635, "step": 2159104 }, { "epoch": 1.01, "learning_rate": 1.4640717837106902e-05, "loss": 3.8704, "step": 2159616 }, { "epoch": 1.01, "learning_rate": 1.4632331889596382e-05, "loss": 3.8691, "step": 2160128 }, { "epoch": 1.01, "learning_rate": 1.4623945942085862e-05, "loss": 3.8652, "step": 2160640 }, { "epoch": 1.01, "learning_rate": 1.461555999457534e-05, "loss": 3.8704, "step": 2161152 }, { "epoch": 1.01, "learning_rate": 1.460717404706482e-05, "loss": 3.8394, "step": 2161664 }, { "epoch": 1.01, "learning_rate": 1.45987880995543e-05, "loss": 3.8651, "step": 2162176 }, { "epoch": 1.01, "learning_rate": 1.459040215204378e-05, "loss": 3.8673, "step": 2162688 }, { "epoch": 1.01, "learning_rate": 1.4582016204533262e-05, "loss": 3.8708, "step": 2163200 }, { "epoch": 1.01, "learning_rate": 1.4573630257022742e-05, "loss": 3.8584, "step": 2163712 }, { "epoch": 1.01, "learning_rate": 1.4565244309512222e-05, "loss": 3.8461, "step": 2164224 }, { "epoch": 1.01, "learning_rate": 1.4556874740805432e-05, "loss": 3.8516, "step": 2164736 }, { "epoch": 1.01, "learning_rate": 1.4548488793294912e-05, "loss": 3.8543, "step": 2165248 }, { "epoch": 1.01, "learning_rate": 1.4540119224588123e-05, "loss": 3.8734, "step": 2165760 }, { "epoch": 1.01, "learning_rate": 1.4531733277077603e-05, "loss": 3.8441, "step": 2166272 }, { "epoch": 1.01, "learning_rate": 1.4523347329567083e-05, "loss": 3.8748, "step": 2166784 }, { "epoch": 1.01, "learning_rate": 1.4514961382056563e-05, "loss": 3.8673, "step": 2167296 }, { "epoch": 1.01, "learning_rate": 1.4506575434546043e-05, "loss": 3.8472, "step": 2167808 }, { "epoch": 1.01, "learning_rate": 1.4498205865839254e-05, "loss": 3.8653, "step": 2168320 }, { "epoch": 1.01, "learning_rate": 1.4489819918328734e-05, "loss": 3.8515, "step": 2168832 }, { "epoch": 1.01, "learning_rate": 1.4481433970818215e-05, "loss": 3.8504, "step": 2169344 }, { "epoch": 1.01, "learning_rate": 1.4473048023307695e-05, "loss": 3.8554, "step": 2169856 }, { "epoch": 1.01, "learning_rate": 1.4464662075797172e-05, "loss": 3.8668, "step": 2170368 }, { "epoch": 1.01, "learning_rate": 1.4456276128286654e-05, "loss": 3.8559, "step": 2170880 }, { "epoch": 1.01, "learning_rate": 1.4447890180776133e-05, "loss": 3.8664, "step": 2171392 }, { "epoch": 1.01, "learning_rate": 1.4439520612069343e-05, "loss": 3.8461, "step": 2171904 }, { "epoch": 1.01, "learning_rate": 1.4431134664558824e-05, "loss": 3.8624, "step": 2172416 }, { "epoch": 1.01, "learning_rate": 1.4422748717048304e-05, "loss": 3.8672, "step": 2172928 }, { "epoch": 1.01, "learning_rate": 1.4414362769537784e-05, "loss": 3.8718, "step": 2173440 }, { "epoch": 1.01, "learning_rate": 1.4405976822027264e-05, "loss": 3.8683, "step": 2173952 }, { "epoch": 1.01, "learning_rate": 1.4397590874516744e-05, "loss": 3.8719, "step": 2174464 }, { "epoch": 1.01, "learning_rate": 1.4389204927006226e-05, "loss": 3.8848, "step": 2174976 }, { "epoch": 1.01, "learning_rate": 1.4380818979495702e-05, "loss": 3.8696, "step": 2175488 }, { "epoch": 1.01, "learning_rate": 1.4372449410788916e-05, "loss": 3.8745, "step": 2176000 }, { "epoch": 1.01, "learning_rate": 1.4364063463278396e-05, "loss": 3.8566, "step": 2176512 }, { "epoch": 1.01, "learning_rate": 1.4355677515767876e-05, "loss": 3.8647, "step": 2177024 }, { "epoch": 1.01, "learning_rate": 1.4347291568257355e-05, "loss": 3.8617, "step": 2177536 }, { "epoch": 1.01, "learning_rate": 1.4338938378354296e-05, "loss": 3.8651, "step": 2178048 }, { "epoch": 1.01, "learning_rate": 1.4330552430843778e-05, "loss": 3.8711, "step": 2178560 }, { "epoch": 1.01, "learning_rate": 1.4322166483333258e-05, "loss": 3.8771, "step": 2179072 }, { "epoch": 1.01, "learning_rate": 1.4313780535822738e-05, "loss": 3.8638, "step": 2179584 }, { "epoch": 1.01, "learning_rate": 1.4305394588312218e-05, "loss": 3.8548, "step": 2180096 }, { "epoch": 1.01, "learning_rate": 1.4297008640801698e-05, "loss": 3.8567, "step": 2180608 }, { "epoch": 1.01, "learning_rate": 1.4288639072094908e-05, "loss": 3.8719, "step": 2181120 }, { "epoch": 1.01, "learning_rate": 1.4280253124584388e-05, "loss": 3.8631, "step": 2181632 }, { "epoch": 1.01, "learning_rate": 1.42718835558776e-05, "loss": 3.861, "step": 2182144 }, { "epoch": 1.01, "learning_rate": 1.426349760836708e-05, "loss": 3.8663, "step": 2182656 }, { "epoch": 1.02, "learning_rate": 1.425511166085656e-05, "loss": 3.8619, "step": 2183168 }, { "epoch": 1.02, "learning_rate": 1.424672571334604e-05, "loss": 3.8596, "step": 2183680 }, { "epoch": 1.02, "learning_rate": 1.423833976583552e-05, "loss": 3.8586, "step": 2184192 }, { "epoch": 1.02, "learning_rate": 1.4229953818324997e-05, "loss": 3.8732, "step": 2184704 }, { "epoch": 1.02, "learning_rate": 1.4221567870814479e-05, "loss": 3.8717, "step": 2185216 }, { "epoch": 1.02, "learning_rate": 1.4213181923303959e-05, "loss": 3.8708, "step": 2185728 }, { "epoch": 1.02, "learning_rate": 1.4204795975793439e-05, "loss": 3.8573, "step": 2186240 }, { "epoch": 1.02, "learning_rate": 1.4196410028282919e-05, "loss": 3.8605, "step": 2186752 }, { "epoch": 1.02, "learning_rate": 1.4188024080772399e-05, "loss": 3.8626, "step": 2187264 }, { "epoch": 1.02, "learning_rate": 1.417963813326188e-05, "loss": 3.8668, "step": 2187776 }, { "epoch": 1.02, "learning_rate": 1.4171252185751357e-05, "loss": 3.8738, "step": 2188288 }, { "epoch": 1.02, "learning_rate": 1.4162882617044571e-05, "loss": 3.8636, "step": 2188800 }, { "epoch": 1.02, "learning_rate": 1.4154496669534051e-05, "loss": 3.8683, "step": 2189312 }, { "epoch": 1.02, "learning_rate": 1.4146110722023531e-05, "loss": 3.8665, "step": 2189824 }, { "epoch": 1.02, "learning_rate": 1.413772477451301e-05, "loss": 3.8654, "step": 2190336 }, { "epoch": 1.02, "learning_rate": 1.4129355205806222e-05, "loss": 3.8566, "step": 2190848 }, { "epoch": 1.02, "learning_rate": 1.4120969258295702e-05, "loss": 3.8574, "step": 2191360 }, { "epoch": 1.02, "learning_rate": 1.4112599689588913e-05, "loss": 3.8603, "step": 2191872 }, { "epoch": 1.02, "learning_rate": 1.4104213742078393e-05, "loss": 3.8628, "step": 2192384 }, { "epoch": 1.02, "learning_rate": 1.4095827794567873e-05, "loss": 3.8507, "step": 2192896 }, { "epoch": 1.02, "learning_rate": 1.4087441847057352e-05, "loss": 3.8586, "step": 2193408 }, { "epoch": 1.02, "learning_rate": 1.407905589954683e-05, "loss": 3.8505, "step": 2193920 }, { "epoch": 1.02, "learning_rate": 1.4070686330840043e-05, "loss": 3.8666, "step": 2194432 }, { "epoch": 1.02, "learning_rate": 1.4062300383329525e-05, "loss": 3.8617, "step": 2194944 }, { "epoch": 1.02, "learning_rate": 1.4053914435819005e-05, "loss": 3.8616, "step": 2195456 }, { "epoch": 1.02, "learning_rate": 1.4045528488308481e-05, "loss": 3.8619, "step": 2195968 }, { "epoch": 1.02, "learning_rate": 1.4037142540797963e-05, "loss": 3.8707, "step": 2196480 }, { "epoch": 1.02, "learning_rate": 1.4028756593287443e-05, "loss": 3.8621, "step": 2196992 }, { "epoch": 1.02, "learning_rate": 1.4020370645776923e-05, "loss": 3.8643, "step": 2197504 }, { "epoch": 1.02, "learning_rate": 1.4011984698266403e-05, "loss": 3.8697, "step": 2198016 }, { "epoch": 1.02, "learning_rate": 1.4003615129559614e-05, "loss": 3.8706, "step": 2198528 }, { "epoch": 1.02, "learning_rate": 1.3995261939656557e-05, "loss": 3.8649, "step": 2199040 }, { "epoch": 1.02, "learning_rate": 1.3986875992146037e-05, "loss": 3.8646, "step": 2199552 }, { "epoch": 1.02, "learning_rate": 1.3978490044635517e-05, "loss": 3.8643, "step": 2200064 }, { "epoch": 1.02, "learning_rate": 1.3970104097124997e-05, "loss": 3.864, "step": 2200576 }, { "epoch": 1.02, "learning_rate": 1.3961718149614479e-05, "loss": 3.859, "step": 2201088 }, { "epoch": 1.02, "learning_rate": 1.3953332202103955e-05, "loss": 3.8604, "step": 2201600 }, { "epoch": 1.02, "learning_rate": 1.3944946254593435e-05, "loss": 3.849, "step": 2202112 }, { "epoch": 1.02, "learning_rate": 1.393657668588665e-05, "loss": 3.8588, "step": 2202624 }, { "epoch": 1.02, "learning_rate": 1.3928190738376126e-05, "loss": 3.8646, "step": 2203136 }, { "epoch": 1.02, "learning_rate": 1.3919804790865606e-05, "loss": 3.8673, "step": 2203648 }, { "epoch": 1.02, "learning_rate": 1.3911418843355087e-05, "loss": 3.866, "step": 2204160 }, { "epoch": 1.02, "learning_rate": 1.3903032895844567e-05, "loss": 3.8576, "step": 2204672 }, { "epoch": 1.02, "learning_rate": 1.3894646948334047e-05, "loss": 3.8709, "step": 2205184 }, { "epoch": 1.02, "learning_rate": 1.3886261000823527e-05, "loss": 3.8704, "step": 2205696 }, { "epoch": 1.02, "learning_rate": 1.3877875053313009e-05, "loss": 3.8668, "step": 2206208 }, { "epoch": 1.02, "learning_rate": 1.3869489105802485e-05, "loss": 3.8628, "step": 2206720 }, { "epoch": 1.02, "learning_rate": 1.3861103158291965e-05, "loss": 3.866, "step": 2207232 }, { "epoch": 1.02, "learning_rate": 1.385273358958518e-05, "loss": 3.8755, "step": 2207744 }, { "epoch": 1.02, "learning_rate": 1.3844347642074656e-05, "loss": 3.8719, "step": 2208256 }, { "epoch": 1.02, "learning_rate": 1.3835961694564136e-05, "loss": 3.8639, "step": 2208768 }, { "epoch": 1.02, "learning_rate": 1.3827575747053618e-05, "loss": 3.8592, "step": 2209280 }, { "epoch": 1.02, "learning_rate": 1.3819189799543098e-05, "loss": 3.8674, "step": 2209792 }, { "epoch": 1.02, "learning_rate": 1.3810803852032578e-05, "loss": 3.8645, "step": 2210304 }, { "epoch": 1.02, "learning_rate": 1.3802434283325788e-05, "loss": 3.8621, "step": 2210816 }, { "epoch": 1.02, "learning_rate": 1.3794048335815268e-05, "loss": 3.8618, "step": 2211328 }, { "epoch": 1.02, "learning_rate": 1.3785662388304748e-05, "loss": 3.8632, "step": 2211840 }, { "epoch": 1.02, "learning_rate": 1.3777276440794228e-05, "loss": 3.8651, "step": 2212352 }, { "epoch": 1.02, "learning_rate": 1.376890687208744e-05, "loss": 3.8693, "step": 2212864 }, { "epoch": 1.03, "eval_loss": 3.9785614013671875, "eval_runtime": 339.8257, "eval_samples_per_second": 1122.902, "eval_steps_per_second": 35.092, "step": 2213280 }, { "epoch": 0.0, "learning_rate": 1.3760520924576919e-05, "loss": 3.8675, "step": 2213376 }, { "epoch": 0.0, "learning_rate": 1.3752134977066399e-05, "loss": 3.8507, "step": 2213888 }, { "epoch": 0.0, "learning_rate": 1.374374902955588e-05, "loss": 3.8589, "step": 2214400 }, { "epoch": 0.0, "learning_rate": 1.373536308204536e-05, "loss": 3.8707, "step": 2214912 }, { "epoch": 0.0, "learning_rate": 1.3726977134534837e-05, "loss": 3.8644, "step": 2215424 }, { "epoch": 0.0, "learning_rate": 1.3718591187024319e-05, "loss": 3.8735, "step": 2215936 }, { "epoch": 0.0, "learning_rate": 1.3710205239513799e-05, "loss": 3.8578, "step": 2216448 }, { "epoch": 0.0, "learning_rate": 1.3701819292003279e-05, "loss": 3.8607, "step": 2216960 }, { "epoch": 0.0, "learning_rate": 1.3693433344492759e-05, "loss": 3.8516, "step": 2217472 }, { "epoch": 0.0, "learning_rate": 1.368504739698224e-05, "loss": 3.8675, "step": 2217984 }, { "epoch": 0.0, "learning_rate": 1.367666144947172e-05, "loss": 3.8612, "step": 2218496 }, { "epoch": 0.0, "learning_rate": 1.3668275501961197e-05, "loss": 3.8646, "step": 2219008 }, { "epoch": 0.0, "learning_rate": 1.3659905933254411e-05, "loss": 3.8713, "step": 2219520 }, { "epoch": 0.0, "learning_rate": 1.3651519985743891e-05, "loss": 3.8457, "step": 2220032 }, { "epoch": 0.0, "learning_rate": 1.3643134038233371e-05, "loss": 3.8598, "step": 2220544 }, { "epoch": 0.0, "learning_rate": 1.363474809072285e-05, "loss": 3.8484, "step": 2221056 }, { "epoch": 0.0, "learning_rate": 1.362636214321233e-05, "loss": 3.8659, "step": 2221568 }, { "epoch": 0.0, "learning_rate": 1.361797619570181e-05, "loss": 3.8557, "step": 2222080 }, { "epoch": 0.0, "learning_rate": 1.3609590248191289e-05, "loss": 3.8635, "step": 2222592 }, { "epoch": 0.0, "learning_rate": 1.3601204300680769e-05, "loss": 3.8541, "step": 2223104 }, { "epoch": 0.0, "learning_rate": 1.359281835317025e-05, "loss": 3.8803, "step": 2223616 }, { "epoch": 0.0, "learning_rate": 1.3584432405659727e-05, "loss": 3.8596, "step": 2224128 }, { "epoch": 0.0, "learning_rate": 1.3576046458149207e-05, "loss": 3.8678, "step": 2224640 }, { "epoch": 0.0, "learning_rate": 1.3567676889442421e-05, "loss": 3.861, "step": 2225152 }, { "epoch": 0.0, "learning_rate": 1.3559290941931901e-05, "loss": 3.868, "step": 2225664 }, { "epoch": 0.0, "learning_rate": 1.355090499442138e-05, "loss": 3.8644, "step": 2226176 }, { "epoch": 0.0, "learning_rate": 1.354251904691086e-05, "loss": 3.856, "step": 2226688 }, { "epoch": 0.0, "learning_rate": 1.353413309940034e-05, "loss": 3.8627, "step": 2227200 }, { "epoch": 0.0, "learning_rate": 1.3525763530693552e-05, "loss": 3.8536, "step": 2227712 }, { "epoch": 0.0, "learning_rate": 1.351737758318303e-05, "loss": 3.8565, "step": 2228224 }, { "epoch": 0.01, "learning_rate": 1.350899163567251e-05, "loss": 3.8612, "step": 2228736 }, { "epoch": 0.01, "learning_rate": 1.350060568816199e-05, "loss": 3.856, "step": 2229248 }, { "epoch": 0.01, "learning_rate": 1.3492252498258934e-05, "loss": 3.8607, "step": 2229760 }, { "epoch": 0.01, "learning_rate": 1.3483866550748414e-05, "loss": 3.8767, "step": 2230272 }, { "epoch": 0.01, "learning_rate": 1.3475480603237895e-05, "loss": 3.8614, "step": 2230784 }, { "epoch": 0.01, "learning_rate": 1.3467094655727375e-05, "loss": 3.8665, "step": 2231296 }, { "epoch": 0.01, "learning_rate": 1.3458708708216852e-05, "loss": 3.8659, "step": 2231808 }, { "epoch": 0.01, "learning_rate": 1.3450339139510066e-05, "loss": 3.8541, "step": 2232320 }, { "epoch": 0.01, "learning_rate": 1.3441953191999546e-05, "loss": 3.864, "step": 2232832 }, { "epoch": 0.01, "learning_rate": 1.3433567244489026e-05, "loss": 3.8595, "step": 2233344 }, { "epoch": 0.01, "learning_rate": 1.3425181296978504e-05, "loss": 3.8544, "step": 2233856 }, { "epoch": 0.01, "learning_rate": 1.3416811728271717e-05, "loss": 3.8657, "step": 2234368 }, { "epoch": 0.01, "learning_rate": 1.3408425780761196e-05, "loss": 3.8696, "step": 2234880 }, { "epoch": 0.01, "learning_rate": 1.3400039833250675e-05, "loss": 3.8545, "step": 2235392 }, { "epoch": 0.01, "learning_rate": 1.3391653885740155e-05, "loss": 3.8656, "step": 2235904 }, { "epoch": 0.01, "learning_rate": 1.3383267938229635e-05, "loss": 3.8684, "step": 2236416 }, { "epoch": 0.01, "learning_rate": 1.3374881990719115e-05, "loss": 3.8594, "step": 2236928 }, { "epoch": 0.01, "learning_rate": 1.3366496043208596e-05, "loss": 3.8669, "step": 2237440 }, { "epoch": 0.01, "learning_rate": 1.3358110095698076e-05, "loss": 3.8344, "step": 2237952 }, { "epoch": 0.01, "learning_rate": 1.3349724148187556e-05, "loss": 3.8611, "step": 2238464 }, { "epoch": 0.01, "learning_rate": 1.3341338200677034e-05, "loss": 3.8621, "step": 2238976 }, { "epoch": 0.01, "learning_rate": 1.3332952253166514e-05, "loss": 3.8685, "step": 2239488 }, { "epoch": 0.01, "learning_rate": 1.3324582684459727e-05, "loss": 3.8547, "step": 2240000 }, { "epoch": 0.01, "learning_rate": 1.3316196736949205e-05, "loss": 3.8439, "step": 2240512 }, { "epoch": 0.01, "learning_rate": 1.3307810789438685e-05, "loss": 3.8453, "step": 2241024 }, { "epoch": 0.01, "learning_rate": 1.3299441220731898e-05, "loss": 3.8481, "step": 2241536 }, { "epoch": 0.01, "learning_rate": 1.3291055273221378e-05, "loss": 3.8733, "step": 2242048 }, { "epoch": 0.01, "learning_rate": 1.3282669325710856e-05, "loss": 3.8427, "step": 2242560 }, { "epoch": 0.01, "learning_rate": 1.3274283378200336e-05, "loss": 3.8683, "step": 2243072 }, { "epoch": 0.01, "learning_rate": 1.3265897430689816e-05, "loss": 3.8607, "step": 2243584 }, { "epoch": 0.01, "learning_rate": 1.3257511483179297e-05, "loss": 3.8504, "step": 2244096 }, { "epoch": 0.01, "learning_rate": 1.3249125535668777e-05, "loss": 3.8602, "step": 2244608 }, { "epoch": 0.01, "learning_rate": 1.3240739588158257e-05, "loss": 3.8459, "step": 2245120 }, { "epoch": 0.01, "learning_rate": 1.3232353640647737e-05, "loss": 3.8467, "step": 2245632 }, { "epoch": 0.01, "learning_rate": 1.3223984071940948e-05, "loss": 3.8505, "step": 2246144 }, { "epoch": 0.01, "learning_rate": 1.3215598124430428e-05, "loss": 3.8644, "step": 2246656 }, { "epoch": 0.01, "learning_rate": 1.3207212176919908e-05, "loss": 3.851, "step": 2247168 }, { "epoch": 0.01, "learning_rate": 1.3198826229409386e-05, "loss": 3.8548, "step": 2247680 }, { "epoch": 0.01, "learning_rate": 1.3190440281898866e-05, "loss": 3.8445, "step": 2248192 }, { "epoch": 0.01, "learning_rate": 1.3182054334388346e-05, "loss": 3.8555, "step": 2248704 }, { "epoch": 0.01, "learning_rate": 1.3173668386877828e-05, "loss": 3.865, "step": 2249216 }, { "epoch": 0.01, "learning_rate": 1.3165282439367308e-05, "loss": 3.8662, "step": 2249728 }, { "epoch": 0.01, "learning_rate": 1.3156912870660518e-05, "loss": 3.8629, "step": 2250240 }, { "epoch": 0.01, "learning_rate": 1.3148526923149998e-05, "loss": 3.868, "step": 2250752 }, { "epoch": 0.01, "learning_rate": 1.3140140975639478e-05, "loss": 3.8793, "step": 2251264 }, { "epoch": 0.01, "learning_rate": 1.3131755028128958e-05, "loss": 3.8668, "step": 2251776 }, { "epoch": 0.01, "learning_rate": 1.3123385459422169e-05, "loss": 3.8705, "step": 2252288 }, { "epoch": 0.01, "learning_rate": 1.3114999511911649e-05, "loss": 3.8547, "step": 2252800 }, { "epoch": 0.01, "learning_rate": 1.3106613564401129e-05, "loss": 3.8622, "step": 2253312 }, { "epoch": 0.01, "learning_rate": 1.309824399569434e-05, "loss": 3.858, "step": 2253824 }, { "epoch": 0.01, "learning_rate": 1.308985804818382e-05, "loss": 3.8562, "step": 2254336 }, { "epoch": 0.01, "learning_rate": 1.30814721006733e-05, "loss": 3.8654, "step": 2254848 }, { "epoch": 0.01, "learning_rate": 1.3073086153162781e-05, "loss": 3.8697, "step": 2255360 }, { "epoch": 0.01, "learning_rate": 1.3064700205652261e-05, "loss": 3.8655, "step": 2255872 }, { "epoch": 0.01, "learning_rate": 1.3056314258141741e-05, "loss": 3.8462, "step": 2256384 }, { "epoch": 0.01, "learning_rate": 1.304792831063122e-05, "loss": 3.8517, "step": 2256896 }, { "epoch": 0.01, "learning_rate": 1.30395423631207e-05, "loss": 3.8652, "step": 2257408 }, { "epoch": 0.01, "learning_rate": 1.303115641561018e-05, "loss": 3.8612, "step": 2257920 }, { "epoch": 0.01, "learning_rate": 1.3022803225707123e-05, "loss": 3.8569, "step": 2258432 }, { "epoch": 0.01, "learning_rate": 1.3014417278196603e-05, "loss": 3.8606, "step": 2258944 }, { "epoch": 0.02, "learning_rate": 1.3006031330686083e-05, "loss": 3.8591, "step": 2259456 }, { "epoch": 0.02, "learning_rate": 1.2997645383175563e-05, "loss": 3.8543, "step": 2259968 }, { "epoch": 0.02, "learning_rate": 1.2989259435665041e-05, "loss": 3.8574, "step": 2260480 }, { "epoch": 0.02, "learning_rate": 1.2980873488154521e-05, "loss": 3.8679, "step": 2260992 }, { "epoch": 0.02, "learning_rate": 1.2972503919447735e-05, "loss": 3.8652, "step": 2261504 }, { "epoch": 0.02, "learning_rate": 1.2964117971937215e-05, "loss": 3.8679, "step": 2262016 }, { "epoch": 0.02, "learning_rate": 1.2955732024426692e-05, "loss": 3.8508, "step": 2262528 }, { "epoch": 0.02, "learning_rate": 1.2947346076916173e-05, "loss": 3.8552, "step": 2263040 }, { "epoch": 0.02, "learning_rate": 1.2938960129405653e-05, "loss": 3.8609, "step": 2263552 }, { "epoch": 0.02, "learning_rate": 1.2930574181895133e-05, "loss": 3.8644, "step": 2264064 }, { "epoch": 0.02, "learning_rate": 1.2922188234384613e-05, "loss": 3.8695, "step": 2264576 }, { "epoch": 0.02, "learning_rate": 1.2913802286874093e-05, "loss": 3.8607, "step": 2265088 }, { "epoch": 0.02, "learning_rate": 1.2905416339363575e-05, "loss": 3.8619, "step": 2265600 }, { "epoch": 0.02, "learning_rate": 1.2897046770656784e-05, "loss": 3.86, "step": 2266112 }, { "epoch": 0.02, "learning_rate": 1.2888660823146265e-05, "loss": 3.8627, "step": 2266624 }, { "epoch": 0.02, "learning_rate": 1.2880274875635745e-05, "loss": 3.8517, "step": 2267136 }, { "epoch": 0.02, "learning_rate": 1.2871888928125222e-05, "loss": 3.8512, "step": 2267648 }, { "epoch": 0.02, "learning_rate": 1.2863502980614704e-05, "loss": 3.8577, "step": 2268160 }, { "epoch": 0.02, "learning_rate": 1.2855117033104184e-05, "loss": 3.8591, "step": 2268672 }, { "epoch": 0.02, "learning_rate": 1.2846731085593664e-05, "loss": 3.8483, "step": 2269184 }, { "epoch": 0.02, "learning_rate": 1.2838345138083144e-05, "loss": 3.8494, "step": 2269696 }, { "epoch": 0.02, "learning_rate": 1.2829959190572623e-05, "loss": 3.8488, "step": 2270208 }, { "epoch": 0.02, "learning_rate": 1.2821589621865834e-05, "loss": 3.8565, "step": 2270720 }, { "epoch": 0.02, "learning_rate": 1.2813203674355314e-05, "loss": 3.8563, "step": 2271232 }, { "epoch": 0.02, "learning_rate": 1.2804834105648525e-05, "loss": 3.8573, "step": 2271744 }, { "epoch": 0.02, "learning_rate": 1.2796448158138005e-05, "loss": 3.8593, "step": 2272256 }, { "epoch": 0.02, "learning_rate": 1.2788078589431217e-05, "loss": 3.868, "step": 2272768 }, { "epoch": 0.02, "learning_rate": 1.2779692641920696e-05, "loss": 3.8584, "step": 2273280 }, { "epoch": 0.02, "learning_rate": 1.2771306694410176e-05, "loss": 3.8618, "step": 2273792 }, { "epoch": 0.02, "learning_rate": 1.2762920746899656e-05, "loss": 3.8664, "step": 2274304 }, { "epoch": 0.02, "learning_rate": 1.2754534799389137e-05, "loss": 3.8632, "step": 2274816 }, { "epoch": 0.02, "learning_rate": 1.2746148851878617e-05, "loss": 3.8575, "step": 2275328 }, { "epoch": 0.02, "learning_rate": 1.2737762904368097e-05, "loss": 3.8652, "step": 2275840 }, { "epoch": 0.02, "learning_rate": 1.2729376956857577e-05, "loss": 3.8588, "step": 2276352 }, { "epoch": 0.02, "learning_rate": 1.2721007388150788e-05, "loss": 3.8566, "step": 2276864 }, { "epoch": 0.02, "learning_rate": 1.2712621440640268e-05, "loss": 3.8483, "step": 2277376 }, { "epoch": 0.02, "learning_rate": 1.2704235493129748e-05, "loss": 3.8593, "step": 2277888 }, { "epoch": 0.02, "learning_rate": 1.2695849545619226e-05, "loss": 3.8509, "step": 2278400 }, { "epoch": 0.02, "learning_rate": 1.2687479976912439e-05, "loss": 3.8545, "step": 2278912 }, { "epoch": 0.02, "learning_rate": 1.267909402940192e-05, "loss": 3.852, "step": 2279424 }, { "epoch": 0.02, "learning_rate": 1.26707080818914e-05, "loss": 3.8649, "step": 2279936 }, { "epoch": 0.02, "learning_rate": 1.2662322134380877e-05, "loss": 3.8608, "step": 2280448 }, { "epoch": 0.02, "learning_rate": 1.2653936186870358e-05, "loss": 3.8539, "step": 2280960 }, { "epoch": 0.02, "learning_rate": 1.2645550239359838e-05, "loss": 3.8668, "step": 2281472 }, { "epoch": 0.02, "learning_rate": 1.2637164291849318e-05, "loss": 3.8649, "step": 2281984 }, { "epoch": 0.02, "learning_rate": 1.2628794723142529e-05, "loss": 3.8671, "step": 2282496 }, { "epoch": 0.02, "learning_rate": 1.2620408775632009e-05, "loss": 3.8605, "step": 2283008 }, { "epoch": 0.02, "learning_rate": 1.2612022828121489e-05, "loss": 3.8564, "step": 2283520 }, { "epoch": 0.02, "learning_rate": 1.2603636880610969e-05, "loss": 3.8723, "step": 2284032 }, { "epoch": 0.02, "learning_rate": 1.259525093310045e-05, "loss": 3.8604, "step": 2284544 }, { "epoch": 0.02, "learning_rate": 1.258686498558993e-05, "loss": 3.867, "step": 2285056 }, { "epoch": 0.02, "learning_rate": 1.2578479038079407e-05, "loss": 3.8546, "step": 2285568 }, { "epoch": 0.02, "learning_rate": 1.2570093090568889e-05, "loss": 3.8615, "step": 2286080 }, { "epoch": 0.02, "learning_rate": 1.2561707143058369e-05, "loss": 3.8585, "step": 2286592 }, { "epoch": 0.02, "learning_rate": 1.2553321195547849e-05, "loss": 3.8548, "step": 2287104 }, { "epoch": 0.02, "learning_rate": 1.254495162684106e-05, "loss": 3.8615, "step": 2287616 }, { "epoch": 0.02, "learning_rate": 1.253656567933054e-05, "loss": 3.8591, "step": 2288128 }, { "epoch": 0.02, "learning_rate": 1.252817973182002e-05, "loss": 3.8629, "step": 2288640 }, { "epoch": 0.02, "learning_rate": 1.25197937843095e-05, "loss": 3.8607, "step": 2289152 }, { "epoch": 0.03, "eval_loss": 3.9771511554718018, "eval_runtime": 301.5962, "eval_samples_per_second": 1265.238, "eval_steps_per_second": 39.54, "step": 2289600 }, { "epoch": 1.0, "learning_rate": 1.251140783679898e-05, "loss": 3.857, "step": 2289664 }, { "epoch": 1.0, "learning_rate": 1.2503021889288461e-05, "loss": 3.8505, "step": 2290176 }, { "epoch": 1.0, "learning_rate": 1.249465232058167e-05, "loss": 3.8537, "step": 2290688 }, { "epoch": 1.0, "learning_rate": 1.2486282751874883e-05, "loss": 3.8674, "step": 2291200 }, { "epoch": 1.0, "learning_rate": 1.2477896804364362e-05, "loss": 3.8626, "step": 2291712 }, { "epoch": 1.0, "learning_rate": 1.246951085685384e-05, "loss": 3.8706, "step": 2292224 }, { "epoch": 1.0, "learning_rate": 1.2461124909343322e-05, "loss": 3.8529, "step": 2292736 }, { "epoch": 1.0, "learning_rate": 1.2452738961832802e-05, "loss": 3.8545, "step": 2293248 }, { "epoch": 1.0, "learning_rate": 1.244435301432228e-05, "loss": 3.8498, "step": 2293760 }, { "epoch": 1.0, "learning_rate": 1.2435967066811762e-05, "loss": 3.8604, "step": 2294272 }, { "epoch": 1.0, "learning_rate": 1.2427581119301242e-05, "loss": 3.8604, "step": 2294784 }, { "epoch": 1.0, "learning_rate": 1.2419195171790722e-05, "loss": 3.8609, "step": 2295296 }, { "epoch": 1.0, "learning_rate": 1.2410841981887664e-05, "loss": 3.8656, "step": 2295808 }, { "epoch": 1.0, "learning_rate": 1.2402456034377144e-05, "loss": 3.8449, "step": 2296320 }, { "epoch": 1.0, "learning_rate": 1.2394070086866624e-05, "loss": 3.8519, "step": 2296832 }, { "epoch": 1.0, "learning_rate": 1.2385684139356105e-05, "loss": 3.8481, "step": 2297344 }, { "epoch": 1.0, "learning_rate": 1.2377298191845584e-05, "loss": 3.8596, "step": 2297856 }, { "epoch": 1.0, "learning_rate": 1.2368912244335064e-05, "loss": 3.8511, "step": 2298368 }, { "epoch": 1.0, "learning_rate": 1.2360526296824544e-05, "loss": 3.8614, "step": 2298880 }, { "epoch": 1.0, "learning_rate": 1.2352140349314023e-05, "loss": 3.8491, "step": 2299392 }, { "epoch": 1.0, "learning_rate": 1.2343754401803503e-05, "loss": 3.8745, "step": 2299904 }, { "epoch": 1.0, "learning_rate": 1.2335368454292983e-05, "loss": 3.8582, "step": 2300416 }, { "epoch": 1.0, "learning_rate": 1.2326982506782463e-05, "loss": 3.8578, "step": 2300928 }, { "epoch": 1.0, "learning_rate": 1.2318596559271943e-05, "loss": 3.8586, "step": 2301440 }, { "epoch": 1.0, "learning_rate": 1.2310226990565154e-05, "loss": 3.8672, "step": 2301952 }, { "epoch": 1.0, "learning_rate": 1.2301857421858367e-05, "loss": 3.8606, "step": 2302464 }, { "epoch": 1.0, "learning_rate": 1.2293471474347845e-05, "loss": 3.8505, "step": 2302976 }, { "epoch": 1.0, "learning_rate": 1.2285085526837325e-05, "loss": 3.8593, "step": 2303488 }, { "epoch": 1.0, "learning_rate": 1.2276715958130537e-05, "loss": 3.8471, "step": 2304000 }, { "epoch": 1.0, "learning_rate": 1.2268330010620017e-05, "loss": 3.8535, "step": 2304512 }, { "epoch": 1.01, "learning_rate": 1.2259944063109497e-05, "loss": 3.8562, "step": 2305024 }, { "epoch": 1.01, "learning_rate": 1.2251558115598977e-05, "loss": 3.855, "step": 2305536 }, { "epoch": 1.01, "learning_rate": 1.2243172168088457e-05, "loss": 3.8578, "step": 2306048 }, { "epoch": 1.01, "learning_rate": 1.2234786220577935e-05, "loss": 3.8684, "step": 2306560 }, { "epoch": 1.01, "learning_rate": 1.2226400273067417e-05, "loss": 3.8612, "step": 2307072 }, { "epoch": 1.01, "learning_rate": 1.2218014325556897e-05, "loss": 3.8631, "step": 2307584 }, { "epoch": 1.01, "learning_rate": 1.2209628378046375e-05, "loss": 3.8627, "step": 2308096 }, { "epoch": 1.01, "learning_rate": 1.2201258809339588e-05, "loss": 3.8479, "step": 2308608 }, { "epoch": 1.01, "learning_rate": 1.2192872861829068e-05, "loss": 3.8635, "step": 2309120 }, { "epoch": 1.01, "learning_rate": 1.2184486914318548e-05, "loss": 3.8525, "step": 2309632 }, { "epoch": 1.01, "learning_rate": 1.2176100966808026e-05, "loss": 3.8526, "step": 2310144 }, { "epoch": 1.01, "learning_rate": 1.2167731398101238e-05, "loss": 3.86, "step": 2310656 }, { "epoch": 1.01, "learning_rate": 1.2159345450590718e-05, "loss": 3.8677, "step": 2311168 }, { "epoch": 1.01, "learning_rate": 1.2150959503080198e-05, "loss": 3.8492, "step": 2311680 }, { "epoch": 1.01, "learning_rate": 1.2142573555569678e-05, "loss": 3.8669, "step": 2312192 }, { "epoch": 1.01, "learning_rate": 1.2134187608059158e-05, "loss": 3.8611, "step": 2312704 }, { "epoch": 1.01, "learning_rate": 1.2125801660548638e-05, "loss": 3.8598, "step": 2313216 }, { "epoch": 1.01, "learning_rate": 1.2117415713038118e-05, "loss": 3.8631, "step": 2313728 }, { "epoch": 1.01, "learning_rate": 1.2109029765527598e-05, "loss": 3.8299, "step": 2314240 }, { "epoch": 1.01, "learning_rate": 1.2100643818017078e-05, "loss": 3.8551, "step": 2314752 }, { "epoch": 1.01, "learning_rate": 1.2092290628114021e-05, "loss": 3.8656, "step": 2315264 }, { "epoch": 1.01, "learning_rate": 1.20839046806035e-05, "loss": 3.8588, "step": 2315776 }, { "epoch": 1.01, "learning_rate": 1.207551873309298e-05, "loss": 3.8482, "step": 2316288 }, { "epoch": 1.01, "learning_rate": 1.2067132785582461e-05, "loss": 3.8425, "step": 2316800 }, { "epoch": 1.01, "learning_rate": 1.2058763216875672e-05, "loss": 3.8399, "step": 2317312 }, { "epoch": 1.01, "learning_rate": 1.2050377269365152e-05, "loss": 3.8421, "step": 2317824 }, { "epoch": 1.01, "learning_rate": 1.2041991321854632e-05, "loss": 3.8726, "step": 2318336 }, { "epoch": 1.01, "learning_rate": 1.2033605374344112e-05, "loss": 3.8362, "step": 2318848 }, { "epoch": 1.01, "learning_rate": 1.202521942683359e-05, "loss": 3.8644, "step": 2319360 }, { "epoch": 1.01, "learning_rate": 1.2016833479323072e-05, "loss": 3.8555, "step": 2319872 }, { "epoch": 1.01, "learning_rate": 1.2008463910616283e-05, "loss": 3.8413, "step": 2320384 }, { "epoch": 1.01, "learning_rate": 1.2000077963105763e-05, "loss": 3.8552, "step": 2320896 }, { "epoch": 1.01, "learning_rate": 1.1991692015595242e-05, "loss": 3.8466, "step": 2321408 }, { "epoch": 1.01, "learning_rate": 1.1983306068084722e-05, "loss": 3.8443, "step": 2321920 }, { "epoch": 1.01, "learning_rate": 1.1974920120574202e-05, "loss": 3.8432, "step": 2322432 }, { "epoch": 1.01, "learning_rate": 1.1966534173063682e-05, "loss": 3.8609, "step": 2322944 }, { "epoch": 1.01, "learning_rate": 1.1958164604356893e-05, "loss": 3.8549, "step": 2323456 }, { "epoch": 1.01, "learning_rate": 1.1949795035650106e-05, "loss": 3.8482, "step": 2323968 }, { "epoch": 1.01, "learning_rate": 1.1941409088139586e-05, "loss": 3.8428, "step": 2324480 }, { "epoch": 1.01, "learning_rate": 1.1933023140629064e-05, "loss": 3.8501, "step": 2324992 }, { "epoch": 1.01, "learning_rate": 1.1924637193118544e-05, "loss": 3.8618, "step": 2325504 }, { "epoch": 1.01, "learning_rate": 1.1916251245608025e-05, "loss": 3.863, "step": 2326016 }, { "epoch": 1.01, "learning_rate": 1.1907865298097504e-05, "loss": 3.8578, "step": 2326528 }, { "epoch": 1.01, "learning_rate": 1.1899479350586984e-05, "loss": 3.8634, "step": 2327040 }, { "epoch": 1.01, "learning_rate": 1.1891093403076464e-05, "loss": 3.8743, "step": 2327552 }, { "epoch": 1.01, "learning_rate": 1.1882707455565945e-05, "loss": 3.8598, "step": 2328064 }, { "epoch": 1.01, "learning_rate": 1.1874337886859154e-05, "loss": 3.8661, "step": 2328576 }, { "epoch": 1.01, "learning_rate": 1.1865951939348634e-05, "loss": 3.852, "step": 2329088 }, { "epoch": 1.01, "learning_rate": 1.1857565991838116e-05, "loss": 3.8583, "step": 2329600 }, { "epoch": 1.01, "learning_rate": 1.1849196423131327e-05, "loss": 3.8536, "step": 2330112 }, { "epoch": 1.01, "learning_rate": 1.1840810475620807e-05, "loss": 3.851, "step": 2330624 }, { "epoch": 1.01, "learning_rate": 1.1832424528110287e-05, "loss": 3.8649, "step": 2331136 }, { "epoch": 1.01, "learning_rate": 1.1824038580599767e-05, "loss": 3.8689, "step": 2331648 }, { "epoch": 1.01, "learning_rate": 1.1815652633089245e-05, "loss": 3.8646, "step": 2332160 }, { "epoch": 1.01, "learning_rate": 1.1807266685578727e-05, "loss": 3.8386, "step": 2332672 }, { "epoch": 1.01, "learning_rate": 1.1798897116871937e-05, "loss": 3.8518, "step": 2333184 }, { "epoch": 1.01, "learning_rate": 1.1790511169361417e-05, "loss": 3.8592, "step": 2333696 }, { "epoch": 1.01, "learning_rate": 1.1782125221850897e-05, "loss": 3.8588, "step": 2334208 }, { "epoch": 1.01, "learning_rate": 1.1773755653144108e-05, "loss": 3.8508, "step": 2334720 }, { "epoch": 1.01, "learning_rate": 1.1765369705633588e-05, "loss": 3.8607, "step": 2335232 }, { "epoch": 1.02, "learning_rate": 1.1756983758123068e-05, "loss": 3.8532, "step": 2335744 }, { "epoch": 1.02, "learning_rate": 1.1748597810612548e-05, "loss": 3.8522, "step": 2336256 }, { "epoch": 1.02, "learning_rate": 1.1740211863102028e-05, "loss": 3.852, "step": 2336768 }, { "epoch": 1.02, "learning_rate": 1.1731825915591508e-05, "loss": 3.8658, "step": 2337280 }, { "epoch": 1.02, "learning_rate": 1.1723439968080988e-05, "loss": 3.8566, "step": 2337792 }, { "epoch": 1.02, "learning_rate": 1.1715054020570468e-05, "loss": 3.8659, "step": 2338304 }, { "epoch": 1.02, "learning_rate": 1.1706668073059948e-05, "loss": 3.848, "step": 2338816 }, { "epoch": 1.02, "learning_rate": 1.1698282125549428e-05, "loss": 3.8492, "step": 2339328 }, { "epoch": 1.02, "learning_rate": 1.1689896178038908e-05, "loss": 3.8586, "step": 2339840 }, { "epoch": 1.02, "learning_rate": 1.1681510230528388e-05, "loss": 3.8602, "step": 2340352 }, { "epoch": 1.02, "learning_rate": 1.1673124283017866e-05, "loss": 3.8629, "step": 2340864 }, { "epoch": 1.02, "learning_rate": 1.1664738335507347e-05, "loss": 3.8594, "step": 2341376 }, { "epoch": 1.02, "learning_rate": 1.1656352387996827e-05, "loss": 3.8575, "step": 2341888 }, { "epoch": 1.02, "learning_rate": 1.1647982819290038e-05, "loss": 3.8573, "step": 2342400 }, { "epoch": 1.02, "learning_rate": 1.1639596871779518e-05, "loss": 3.8621, "step": 2342912 }, { "epoch": 1.02, "learning_rate": 1.1631210924268998e-05, "loss": 3.8432, "step": 2343424 }, { "epoch": 1.02, "learning_rate": 1.1622824976758478e-05, "loss": 3.851, "step": 2343936 }, { "epoch": 1.02, "learning_rate": 1.161445540805169e-05, "loss": 3.8507, "step": 2344448 }, { "epoch": 1.02, "learning_rate": 1.1606069460541169e-05, "loss": 3.8531, "step": 2344960 }, { "epoch": 1.02, "learning_rate": 1.1597683513030649e-05, "loss": 3.849, "step": 2345472 }, { "epoch": 1.02, "learning_rate": 1.158929756552013e-05, "loss": 3.8452, "step": 2345984 }, { "epoch": 1.02, "learning_rate": 1.1580911618009609e-05, "loss": 3.8415, "step": 2346496 }, { "epoch": 1.02, "learning_rate": 1.1572525670499089e-05, "loss": 3.8589, "step": 2347008 }, { "epoch": 1.02, "learning_rate": 1.1564139722988569e-05, "loss": 3.8527, "step": 2347520 }, { "epoch": 1.02, "learning_rate": 1.1555753775478049e-05, "loss": 3.8521, "step": 2348032 }, { "epoch": 1.02, "learning_rate": 1.154738420677126e-05, "loss": 3.8561, "step": 2348544 }, { "epoch": 1.02, "learning_rate": 1.1539014638064472e-05, "loss": 3.8651, "step": 2349056 }, { "epoch": 1.02, "learning_rate": 1.1530628690553952e-05, "loss": 3.8547, "step": 2349568 }, { "epoch": 1.02, "learning_rate": 1.152224274304343e-05, "loss": 3.8524, "step": 2350080 }, { "epoch": 1.02, "learning_rate": 1.1513856795532912e-05, "loss": 3.866, "step": 2350592 }, { "epoch": 1.02, "learning_rate": 1.1505470848022392e-05, "loss": 3.8599, "step": 2351104 }, { "epoch": 1.02, "learning_rate": 1.149708490051187e-05, "loss": 3.8518, "step": 2351616 }, { "epoch": 1.02, "learning_rate": 1.148869895300135e-05, "loss": 3.8597, "step": 2352128 }, { "epoch": 1.02, "learning_rate": 1.1480313005490832e-05, "loss": 3.8572, "step": 2352640 }, { "epoch": 1.02, "learning_rate": 1.1471927057980311e-05, "loss": 3.8581, "step": 2353152 }, { "epoch": 1.02, "learning_rate": 1.146354111046979e-05, "loss": 3.8452, "step": 2353664 }, { "epoch": 1.02, "learning_rate": 1.1455171541763002e-05, "loss": 3.8565, "step": 2354176 }, { "epoch": 1.02, "learning_rate": 1.1446785594252482e-05, "loss": 3.8462, "step": 2354688 }, { "epoch": 1.02, "learning_rate": 1.1438416025545693e-05, "loss": 3.8542, "step": 2355200 }, { "epoch": 1.02, "learning_rate": 1.1430030078035173e-05, "loss": 3.8422, "step": 2355712 }, { "epoch": 1.02, "learning_rate": 1.1421644130524653e-05, "loss": 3.8664, "step": 2356224 }, { "epoch": 1.02, "learning_rate": 1.1413258183014133e-05, "loss": 3.8575, "step": 2356736 }, { "epoch": 1.02, "learning_rate": 1.1404872235503613e-05, "loss": 3.8481, "step": 2357248 }, { "epoch": 1.02, "learning_rate": 1.1396486287993093e-05, "loss": 3.8645, "step": 2357760 }, { "epoch": 1.02, "learning_rate": 1.1388100340482573e-05, "loss": 3.8609, "step": 2358272 }, { "epoch": 1.02, "learning_rate": 1.1379714392972051e-05, "loss": 3.8648, "step": 2358784 }, { "epoch": 1.02, "learning_rate": 1.1371328445461533e-05, "loss": 3.8559, "step": 2359296 }, { "epoch": 1.02, "learning_rate": 1.1362942497951013e-05, "loss": 3.8584, "step": 2359808 }, { "epoch": 1.02, "learning_rate": 1.1354572929244223e-05, "loss": 3.8694, "step": 2360320 }, { "epoch": 1.02, "learning_rate": 1.1346186981733703e-05, "loss": 3.8564, "step": 2360832 }, { "epoch": 1.02, "learning_rate": 1.1337801034223183e-05, "loss": 3.8641, "step": 2361344 }, { "epoch": 1.02, "learning_rate": 1.1329415086712663e-05, "loss": 3.852, "step": 2361856 }, { "epoch": 1.02, "learning_rate": 1.1321029139202143e-05, "loss": 3.8597, "step": 2362368 }, { "epoch": 1.02, "learning_rate": 1.1312643191691623e-05, "loss": 3.8547, "step": 2362880 }, { "epoch": 1.02, "learning_rate": 1.1304257244181103e-05, "loss": 3.8514, "step": 2363392 }, { "epoch": 1.02, "learning_rate": 1.1295871296670583e-05, "loss": 3.8568, "step": 2363904 }, { "epoch": 1.02, "learning_rate": 1.1287518106767525e-05, "loss": 3.8558, "step": 2364416 }, { "epoch": 1.02, "learning_rate": 1.1279132159257005e-05, "loss": 3.8622, "step": 2364928 }, { "epoch": 1.02, "learning_rate": 1.1270746211746486e-05, "loss": 3.8579, "step": 2365440 }, { "epoch": 1.03, "eval_loss": 3.9760265350341797, "eval_runtime": 300.4878, "eval_samples_per_second": 1269.905, "eval_steps_per_second": 39.685, "step": 2365920 }, { "epoch": 0.0, "learning_rate": 1.1262360264235966e-05, "loss": 3.8018, "step": 2365952 }, { "epoch": 0.0, "learning_rate": 1.1253974316725444e-05, "loss": 3.8498, "step": 2366464 }, { "epoch": 0.0, "learning_rate": 1.1245588369214924e-05, "loss": 3.8487, "step": 2366976 }, { "epoch": 0.0, "learning_rate": 1.1237202421704406e-05, "loss": 3.8622, "step": 2367488 }, { "epoch": 0.0, "learning_rate": 1.1228816474193884e-05, "loss": 3.8539, "step": 2368000 }, { "epoch": 0.0, "learning_rate": 1.1220430526683364e-05, "loss": 3.8694, "step": 2368512 }, { "epoch": 0.0, "learning_rate": 1.1212044579172844e-05, "loss": 3.8485, "step": 2369024 }, { "epoch": 0.0, "learning_rate": 1.1203658631662324e-05, "loss": 3.8503, "step": 2369536 }, { "epoch": 0.0, "learning_rate": 1.1195272684151804e-05, "loss": 3.8464, "step": 2370048 }, { "epoch": 0.0, "learning_rate": 1.1186886736641284e-05, "loss": 3.86, "step": 2370560 }, { "epoch": 0.0, "learning_rate": 1.1178500789130766e-05, "loss": 3.8513, "step": 2371072 }, { "epoch": 0.0, "learning_rate": 1.1170114841620244e-05, "loss": 3.8586, "step": 2371584 }, { "epoch": 0.0, "learning_rate": 1.1161745272913455e-05, "loss": 3.8628, "step": 2372096 }, { "epoch": 0.0, "learning_rate": 1.1153375704206667e-05, "loss": 3.8431, "step": 2372608 }, { "epoch": 0.0, "learning_rate": 1.1144989756696147e-05, "loss": 3.8446, "step": 2373120 }, { "epoch": 0.0, "learning_rate": 1.1136603809185627e-05, "loss": 3.8454, "step": 2373632 }, { "epoch": 0.0, "learning_rate": 1.1128217861675107e-05, "loss": 3.8543, "step": 2374144 }, { "epoch": 0.0, "learning_rate": 1.1119831914164587e-05, "loss": 3.8504, "step": 2374656 }, { "epoch": 0.0, "learning_rate": 1.1111445966654065e-05, "loss": 3.8554, "step": 2375168 }, { "epoch": 0.0, "learning_rate": 1.1103060019143547e-05, "loss": 3.8483, "step": 2375680 }, { "epoch": 0.0, "learning_rate": 1.1094674071633027e-05, "loss": 3.868, "step": 2376192 }, { "epoch": 0.0, "learning_rate": 1.1086288124122505e-05, "loss": 3.8529, "step": 2376704 }, { "epoch": 0.0, "learning_rate": 1.1077902176611985e-05, "loss": 3.859, "step": 2377216 }, { "epoch": 0.0, "learning_rate": 1.1069516229101467e-05, "loss": 3.8561, "step": 2377728 }, { "epoch": 0.0, "learning_rate": 1.1061130281590945e-05, "loss": 3.8626, "step": 2378240 }, { "epoch": 0.0, "learning_rate": 1.1052760712884156e-05, "loss": 3.854, "step": 2378752 }, { "epoch": 0.0, "learning_rate": 1.1044374765373638e-05, "loss": 3.8486, "step": 2379264 }, { "epoch": 0.0, "learning_rate": 1.1035988817863118e-05, "loss": 3.8551, "step": 2379776 }, { "epoch": 0.0, "learning_rate": 1.1027619249156328e-05, "loss": 3.8425, "step": 2380288 }, { "epoch": 0.0, "learning_rate": 1.1019233301645808e-05, "loss": 3.8524, "step": 2380800 }, { "epoch": 0.01, "learning_rate": 1.1010847354135288e-05, "loss": 3.8483, "step": 2381312 }, { "epoch": 0.01, "learning_rate": 1.1002461406624768e-05, "loss": 3.8565, "step": 2381824 }, { "epoch": 0.01, "learning_rate": 1.0994075459114248e-05, "loss": 3.8513, "step": 2382336 }, { "epoch": 0.01, "learning_rate": 1.0985689511603728e-05, "loss": 3.8623, "step": 2382848 }, { "epoch": 0.01, "learning_rate": 1.0977303564093208e-05, "loss": 3.8615, "step": 2383360 }, { "epoch": 0.01, "learning_rate": 1.0968917616582686e-05, "loss": 3.8583, "step": 2383872 }, { "epoch": 0.01, "learning_rate": 1.0960548047875899e-05, "loss": 3.8583, "step": 2384384 }, { "epoch": 0.01, "learning_rate": 1.0952162100365379e-05, "loss": 3.8445, "step": 2384896 }, { "epoch": 0.01, "learning_rate": 1.0943776152854859e-05, "loss": 3.8594, "step": 2385408 }, { "epoch": 0.01, "learning_rate": 1.0935390205344339e-05, "loss": 3.8479, "step": 2385920 }, { "epoch": 0.01, "learning_rate": 1.0927004257833819e-05, "loss": 3.8506, "step": 2386432 }, { "epoch": 0.01, "learning_rate": 1.0918618310323299e-05, "loss": 3.8571, "step": 2386944 }, { "epoch": 0.01, "learning_rate": 1.091024874161651e-05, "loss": 3.862, "step": 2387456 }, { "epoch": 0.01, "learning_rate": 1.090186279410599e-05, "loss": 3.8478, "step": 2387968 }, { "epoch": 0.01, "learning_rate": 1.089347684659547e-05, "loss": 3.8597, "step": 2388480 }, { "epoch": 0.01, "learning_rate": 1.0885090899084951e-05, "loss": 3.8559, "step": 2388992 }, { "epoch": 0.01, "learning_rate": 1.087670495157443e-05, "loss": 3.8549, "step": 2389504 }, { "epoch": 0.01, "learning_rate": 1.086831900406391e-05, "loss": 3.8622, "step": 2390016 }, { "epoch": 0.01, "learning_rate": 1.0859933056553389e-05, "loss": 3.8298, "step": 2390528 }, { "epoch": 0.01, "learning_rate": 1.08515634878466e-05, "loss": 3.849, "step": 2391040 }, { "epoch": 0.01, "learning_rate": 1.084317754033608e-05, "loss": 3.8628, "step": 2391552 }, { "epoch": 0.01, "learning_rate": 1.083479159282556e-05, "loss": 3.8577, "step": 2392064 }, { "epoch": 0.01, "learning_rate": 1.0826405645315041e-05, "loss": 3.846, "step": 2392576 }, { "epoch": 0.01, "learning_rate": 1.081801969780452e-05, "loss": 3.8336, "step": 2393088 }, { "epoch": 0.01, "learning_rate": 1.0809650129097732e-05, "loss": 3.8426, "step": 2393600 }, { "epoch": 0.01, "learning_rate": 1.0801264181587212e-05, "loss": 3.8351, "step": 2394112 }, { "epoch": 0.01, "learning_rate": 1.079287823407669e-05, "loss": 3.8709, "step": 2394624 }, { "epoch": 0.01, "learning_rate": 1.078449228656617e-05, "loss": 3.833, "step": 2395136 }, { "epoch": 0.01, "learning_rate": 1.0776106339055652e-05, "loss": 3.8578, "step": 2395648 }, { "epoch": 0.01, "learning_rate": 1.0767736770348863e-05, "loss": 3.8501, "step": 2396160 }, { "epoch": 0.01, "learning_rate": 1.0759350822838341e-05, "loss": 3.8421, "step": 2396672 }, { "epoch": 0.01, "learning_rate": 1.0750964875327823e-05, "loss": 3.8502, "step": 2397184 }, { "epoch": 0.01, "learning_rate": 1.0742578927817303e-05, "loss": 3.846, "step": 2397696 }, { "epoch": 0.01, "learning_rate": 1.0734192980306781e-05, "loss": 3.8405, "step": 2398208 }, { "epoch": 0.01, "learning_rate": 1.0725823411599993e-05, "loss": 3.8379, "step": 2398720 }, { "epoch": 0.01, "learning_rate": 1.0717437464089473e-05, "loss": 3.8619, "step": 2399232 }, { "epoch": 0.01, "learning_rate": 1.0709051516578953e-05, "loss": 3.8477, "step": 2399744 }, { "epoch": 0.01, "learning_rate": 1.0700665569068433e-05, "loss": 3.8434, "step": 2400256 }, { "epoch": 0.01, "learning_rate": 1.0692279621557913e-05, "loss": 3.8363, "step": 2400768 }, { "epoch": 0.01, "learning_rate": 1.0683910052851124e-05, "loss": 3.8469, "step": 2401280 }, { "epoch": 0.01, "learning_rate": 1.0675524105340606e-05, "loss": 3.8564, "step": 2401792 }, { "epoch": 0.01, "learning_rate": 1.0667138157830084e-05, "loss": 3.8611, "step": 2402304 }, { "epoch": 0.01, "learning_rate": 1.0658752210319564e-05, "loss": 3.8582, "step": 2402816 }, { "epoch": 0.01, "learning_rate": 1.0650382641612776e-05, "loss": 3.8584, "step": 2403328 }, { "epoch": 0.01, "learning_rate": 1.0641996694102255e-05, "loss": 3.8703, "step": 2403840 }, { "epoch": 0.01, "learning_rate": 1.0633610746591735e-05, "loss": 3.8605, "step": 2404352 }, { "epoch": 0.01, "learning_rate": 1.0625224799081215e-05, "loss": 3.8598, "step": 2404864 }, { "epoch": 0.01, "learning_rate": 1.0616838851570696e-05, "loss": 3.8473, "step": 2405376 }, { "epoch": 0.01, "learning_rate": 1.0608452904060174e-05, "loss": 3.8565, "step": 2405888 }, { "epoch": 0.01, "learning_rate": 1.0600066956549654e-05, "loss": 3.8478, "step": 2406400 }, { "epoch": 0.01, "learning_rate": 1.0591681009039134e-05, "loss": 3.8506, "step": 2406912 }, { "epoch": 0.01, "learning_rate": 1.0583327819136078e-05, "loss": 3.8587, "step": 2407424 }, { "epoch": 0.01, "learning_rate": 1.0574941871625558e-05, "loss": 3.8656, "step": 2407936 }, { "epoch": 0.01, "learning_rate": 1.0566555924115038e-05, "loss": 3.8571, "step": 2408448 }, { "epoch": 0.01, "learning_rate": 1.0558169976604518e-05, "loss": 3.8406, "step": 2408960 }, { "epoch": 0.01, "learning_rate": 1.0549784029093998e-05, "loss": 3.8476, "step": 2409472 }, { "epoch": 0.01, "learning_rate": 1.0541398081583477e-05, "loss": 3.8526, "step": 2409984 }, { "epoch": 0.01, "learning_rate": 1.0533012134072957e-05, "loss": 3.859, "step": 2410496 }, { "epoch": 0.01, "learning_rate": 1.0524626186562436e-05, "loss": 3.8436, "step": 2411008 }, { "epoch": 0.01, "learning_rate": 1.0516256617855648e-05, "loss": 3.8584, "step": 2411520 }, { "epoch": 0.02, "learning_rate": 1.0507870670345128e-05, "loss": 3.8539, "step": 2412032 }, { "epoch": 0.02, "learning_rate": 1.0499484722834608e-05, "loss": 3.8472, "step": 2412544 }, { "epoch": 0.02, "learning_rate": 1.0491098775324088e-05, "loss": 3.8493, "step": 2413056 }, { "epoch": 0.02, "learning_rate": 1.0482712827813568e-05, "loss": 3.8602, "step": 2413568 }, { "epoch": 0.02, "learning_rate": 1.0474326880303048e-05, "loss": 3.8513, "step": 2414080 }, { "epoch": 0.02, "learning_rate": 1.0465940932792526e-05, "loss": 3.8608, "step": 2414592 }, { "epoch": 0.02, "learning_rate": 1.0457571364085739e-05, "loss": 3.8479, "step": 2415104 }, { "epoch": 0.02, "learning_rate": 1.0449185416575219e-05, "loss": 3.8464, "step": 2415616 }, { "epoch": 0.02, "learning_rate": 1.0440799469064699e-05, "loss": 3.853, "step": 2416128 }, { "epoch": 0.02, "learning_rate": 1.0432413521554179e-05, "loss": 3.8599, "step": 2416640 }, { "epoch": 0.02, "learning_rate": 1.0424027574043659e-05, "loss": 3.8566, "step": 2417152 }, { "epoch": 0.02, "learning_rate": 1.0415641626533138e-05, "loss": 3.8572, "step": 2417664 }, { "epoch": 0.02, "learning_rate": 1.0407255679022618e-05, "loss": 3.8555, "step": 2418176 }, { "epoch": 0.02, "learning_rate": 1.039888611031583e-05, "loss": 3.8552, "step": 2418688 }, { "epoch": 0.02, "learning_rate": 1.039050016280531e-05, "loss": 3.856, "step": 2419200 }, { "epoch": 0.02, "learning_rate": 1.0382114215294791e-05, "loss": 3.8381, "step": 2419712 }, { "epoch": 0.02, "learning_rate": 1.0373728267784269e-05, "loss": 3.847, "step": 2420224 }, { "epoch": 0.02, "learning_rate": 1.036535869907748e-05, "loss": 3.8537, "step": 2420736 }, { "epoch": 0.02, "learning_rate": 1.0356972751566962e-05, "loss": 3.848, "step": 2421248 }, { "epoch": 0.02, "learning_rate": 1.034858680405644e-05, "loss": 3.8442, "step": 2421760 }, { "epoch": 0.02, "learning_rate": 1.034020085654592e-05, "loss": 3.843, "step": 2422272 }, { "epoch": 0.02, "learning_rate": 1.03318149090354e-05, "loss": 3.84, "step": 2422784 }, { "epoch": 0.02, "learning_rate": 1.0323445340328612e-05, "loss": 3.8553, "step": 2423296 }, { "epoch": 0.02, "learning_rate": 1.031505939281809e-05, "loss": 3.8446, "step": 2423808 }, { "epoch": 0.02, "learning_rate": 1.0306673445307572e-05, "loss": 3.8541, "step": 2424320 }, { "epoch": 0.02, "learning_rate": 1.0298287497797052e-05, "loss": 3.8501, "step": 2424832 }, { "epoch": 0.02, "learning_rate": 1.028990155028653e-05, "loss": 3.8613, "step": 2425344 }, { "epoch": 0.02, "learning_rate": 1.0281531981579743e-05, "loss": 3.8539, "step": 2425856 }, { "epoch": 0.02, "learning_rate": 1.0273146034069223e-05, "loss": 3.8518, "step": 2426368 }, { "epoch": 0.02, "learning_rate": 1.0264760086558703e-05, "loss": 3.8593, "step": 2426880 }, { "epoch": 0.02, "learning_rate": 1.0256374139048181e-05, "loss": 3.8556, "step": 2427392 }, { "epoch": 0.02, "learning_rate": 1.0247988191537663e-05, "loss": 3.8515, "step": 2427904 }, { "epoch": 0.02, "learning_rate": 1.0239602244027143e-05, "loss": 3.8554, "step": 2428416 }, { "epoch": 0.02, "learning_rate": 1.0231216296516621e-05, "loss": 3.8526, "step": 2428928 }, { "epoch": 0.02, "learning_rate": 1.0222830349006103e-05, "loss": 3.8543, "step": 2429440 }, { "epoch": 0.02, "learning_rate": 1.0214460780299313e-05, "loss": 3.8443, "step": 2429952 }, { "epoch": 0.02, "learning_rate": 1.0206074832788793e-05, "loss": 3.849, "step": 2430464 }, { "epoch": 0.02, "learning_rate": 1.0197705264082004e-05, "loss": 3.8444, "step": 2430976 }, { "epoch": 0.02, "learning_rate": 1.0189335695375215e-05, "loss": 3.8461, "step": 2431488 }, { "epoch": 0.02, "learning_rate": 1.0180949747864696e-05, "loss": 3.8382, "step": 2432000 }, { "epoch": 0.02, "learning_rate": 1.0172563800354176e-05, "loss": 3.8665, "step": 2432512 }, { "epoch": 0.02, "learning_rate": 1.0164177852843655e-05, "loss": 3.8547, "step": 2433024 }, { "epoch": 0.02, "learning_rate": 1.0155791905333135e-05, "loss": 3.8501, "step": 2433536 }, { "epoch": 0.02, "learning_rate": 1.0147405957822616e-05, "loss": 3.8536, "step": 2434048 }, { "epoch": 0.02, "learning_rate": 1.0139020010312095e-05, "loss": 3.854, "step": 2434560 }, { "epoch": 0.02, "learning_rate": 1.0130634062801575e-05, "loss": 3.8637, "step": 2435072 }, { "epoch": 0.02, "learning_rate": 1.0122248115291054e-05, "loss": 3.8545, "step": 2435584 }, { "epoch": 0.02, "learning_rate": 1.0113862167780536e-05, "loss": 3.8542, "step": 2436096 }, { "epoch": 0.02, "learning_rate": 1.0105476220270014e-05, "loss": 3.8634, "step": 2436608 }, { "epoch": 0.02, "learning_rate": 1.0097106651563227e-05, "loss": 3.8493, "step": 2437120 }, { "epoch": 0.02, "learning_rate": 1.0088720704052707e-05, "loss": 3.8592, "step": 2437632 }, { "epoch": 0.02, "learning_rate": 1.0080334756542185e-05, "loss": 3.8496, "step": 2438144 }, { "epoch": 0.02, "learning_rate": 1.0071948809031665e-05, "loss": 3.8579, "step": 2438656 }, { "epoch": 0.02, "learning_rate": 1.0063579240324878e-05, "loss": 3.8541, "step": 2439168 }, { "epoch": 0.02, "learning_rate": 1.0055209671618088e-05, "loss": 3.8419, "step": 2439680 }, { "epoch": 0.02, "learning_rate": 1.0046823724107568e-05, "loss": 3.8575, "step": 2440192 }, { "epoch": 0.02, "learning_rate": 1.0038437776597048e-05, "loss": 3.8532, "step": 2440704 }, { "epoch": 0.02, "learning_rate": 1.0030051829086528e-05, "loss": 3.8562, "step": 2441216 }, { "epoch": 0.02, "learning_rate": 1.0021665881576008e-05, "loss": 3.8524, "step": 2441728 }, { "epoch": 0.03, "learning_rate": 1.0013279934065488e-05, "loss": 3.8521, "step": 2442240 }, { "epoch": 0.03, "eval_loss": 3.9749772548675537, "eval_runtime": 299.4935, "eval_samples_per_second": 1274.121, "eval_steps_per_second": 39.817, "step": 2442240 }, { "epoch": 1.0, "learning_rate": 1.0004893986554968e-05, "loss": 3.8462, "step": 2442752 }, { "epoch": 1.0, "learning_rate": 9.996508039044448e-06, "loss": 3.8417, "step": 2443264 }, { "epoch": 1.0, "learning_rate": 9.988138470337659e-06, "loss": 3.8598, "step": 2443776 }, { "epoch": 1.0, "learning_rate": 9.97976890163087e-06, "loss": 3.8548, "step": 2444288 }, { "epoch": 1.0, "learning_rate": 9.971382954120351e-06, "loss": 3.8651, "step": 2444800 }, { "epoch": 1.0, "learning_rate": 9.962997006609831e-06, "loss": 3.8466, "step": 2445312 }, { "epoch": 1.0, "learning_rate": 9.95461105909931e-06, "loss": 3.8457, "step": 2445824 }, { "epoch": 1.0, "learning_rate": 9.946225111588791e-06, "loss": 3.8391, "step": 2446336 }, { "epoch": 1.0, "learning_rate": 9.937839164078271e-06, "loss": 3.8572, "step": 2446848 }, { "epoch": 1.0, "learning_rate": 9.92945321656775e-06, "loss": 3.8474, "step": 2447360 }, { "epoch": 1.0, "learning_rate": 9.92106726905723e-06, "loss": 3.8571, "step": 2447872 }, { "epoch": 1.0, "learning_rate": 9.912681321546711e-06, "loss": 3.8552, "step": 2448384 }, { "epoch": 1.0, "learning_rate": 9.904311752839922e-06, "loss": 3.845, "step": 2448896 }, { "epoch": 1.0, "learning_rate": 9.8959258053294e-06, "loss": 3.8409, "step": 2449408 }, { "epoch": 1.0, "learning_rate": 9.887556236622612e-06, "loss": 3.845, "step": 2449920 }, { "epoch": 1.0, "learning_rate": 9.879170289112092e-06, "loss": 3.845, "step": 2450432 }, { "epoch": 1.0, "learning_rate": 9.870784341601572e-06, "loss": 3.851, "step": 2450944 }, { "epoch": 1.0, "learning_rate": 9.862398394091052e-06, "loss": 3.852, "step": 2451456 }, { "epoch": 1.0, "learning_rate": 9.854028825384263e-06, "loss": 3.8435, "step": 2451968 }, { "epoch": 1.0, "learning_rate": 9.845642877873743e-06, "loss": 3.8691, "step": 2452480 }, { "epoch": 1.0, "learning_rate": 9.837256930363223e-06, "loss": 3.8471, "step": 2452992 }, { "epoch": 1.0, "learning_rate": 9.828870982852703e-06, "loss": 3.8558, "step": 2453504 }, { "epoch": 1.0, "learning_rate": 9.820485035342183e-06, "loss": 3.8512, "step": 2454016 }, { "epoch": 1.0, "learning_rate": 9.812099087831663e-06, "loss": 3.8593, "step": 2454528 }, { "epoch": 1.0, "learning_rate": 9.803713140321143e-06, "loss": 3.8472, "step": 2455040 }, { "epoch": 1.0, "learning_rate": 9.795327192810623e-06, "loss": 3.8509, "step": 2455552 }, { "epoch": 1.0, "learning_rate": 9.786941245300103e-06, "loss": 3.8466, "step": 2456064 }, { "epoch": 1.0, "learning_rate": 9.778555297789583e-06, "loss": 3.8457, "step": 2456576 }, { "epoch": 1.0, "learning_rate": 9.770169350279063e-06, "loss": 3.8449, "step": 2457088 }, { "epoch": 1.01, "learning_rate": 9.761783402768543e-06, "loss": 3.8451, "step": 2457600 }, { "epoch": 1.01, "learning_rate": 9.753430212865486e-06, "loss": 3.8522, "step": 2458112 }, { "epoch": 1.01, "learning_rate": 9.745044265354964e-06, "loss": 3.8515, "step": 2458624 }, { "epoch": 1.01, "learning_rate": 9.736658317844446e-06, "loss": 3.8544, "step": 2459136 }, { "epoch": 1.01, "learning_rate": 9.728272370333926e-06, "loss": 3.8607, "step": 2459648 }, { "epoch": 1.01, "learning_rate": 9.719886422823404e-06, "loss": 3.8553, "step": 2460160 }, { "epoch": 1.01, "learning_rate": 9.711516854116617e-06, "loss": 3.8547, "step": 2460672 }, { "epoch": 1.01, "learning_rate": 9.703130906606097e-06, "loss": 3.8468, "step": 2461184 }, { "epoch": 1.01, "learning_rate": 9.694744959095576e-06, "loss": 3.8527, "step": 2461696 }, { "epoch": 1.01, "learning_rate": 9.686359011585055e-06, "loss": 3.8469, "step": 2462208 }, { "epoch": 1.01, "learning_rate": 9.677989442878267e-06, "loss": 3.849, "step": 2462720 }, { "epoch": 1.01, "learning_rate": 9.669603495367747e-06, "loss": 3.8519, "step": 2463232 }, { "epoch": 1.01, "learning_rate": 9.661217547857227e-06, "loss": 3.8605, "step": 2463744 }, { "epoch": 1.01, "learning_rate": 9.652831600346707e-06, "loss": 3.843, "step": 2464256 }, { "epoch": 1.01, "learning_rate": 9.644445652836187e-06, "loss": 3.8545, "step": 2464768 }, { "epoch": 1.01, "learning_rate": 9.6360760841294e-06, "loss": 3.8546, "step": 2465280 }, { "epoch": 1.01, "learning_rate": 9.627690136618878e-06, "loss": 3.8547, "step": 2465792 }, { "epoch": 1.01, "learning_rate": 9.619304189108358e-06, "loss": 3.8536, "step": 2466304 }, { "epoch": 1.01, "learning_rate": 9.610918241597838e-06, "loss": 3.8273, "step": 2466816 }, { "epoch": 1.01, "learning_rate": 9.602532294087318e-06, "loss": 3.8439, "step": 2467328 }, { "epoch": 1.01, "learning_rate": 9.594162725380528e-06, "loss": 3.8568, "step": 2467840 }, { "epoch": 1.01, "learning_rate": 9.585793156673741e-06, "loss": 3.8547, "step": 2468352 }, { "epoch": 1.01, "learning_rate": 9.577407209163221e-06, "loss": 3.844, "step": 2468864 }, { "epoch": 1.01, "learning_rate": 9.5690212616527e-06, "loss": 3.8326, "step": 2469376 }, { "epoch": 1.01, "learning_rate": 9.56063531414218e-06, "loss": 3.8398, "step": 2469888 }, { "epoch": 1.01, "learning_rate": 9.55224936663166e-06, "loss": 3.8322, "step": 2470400 }, { "epoch": 1.01, "learning_rate": 9.54386341912114e-06, "loss": 3.8664, "step": 2470912 }, { "epoch": 1.01, "learning_rate": 9.535477471610619e-06, "loss": 3.8331, "step": 2471424 }, { "epoch": 1.01, "learning_rate": 9.5270915241001e-06, "loss": 3.8539, "step": 2471936 }, { "epoch": 1.01, "learning_rate": 9.51870557658958e-06, "loss": 3.8508, "step": 2472448 }, { "epoch": 1.01, "learning_rate": 9.510319629079059e-06, "loss": 3.8356, "step": 2472960 }, { "epoch": 1.01, "learning_rate": 9.501933681568539e-06, "loss": 3.8473, "step": 2473472 }, { "epoch": 1.01, "learning_rate": 9.49354773405802e-06, "loss": 3.8436, "step": 2473984 }, { "epoch": 1.01, "learning_rate": 9.485178165351231e-06, "loss": 3.832, "step": 2474496 }, { "epoch": 1.01, "learning_rate": 9.476792217840711e-06, "loss": 3.8341, "step": 2475008 }, { "epoch": 1.01, "learning_rate": 9.468422649133922e-06, "loss": 3.8595, "step": 2475520 }, { "epoch": 1.01, "learning_rate": 9.460036701623402e-06, "loss": 3.8482, "step": 2476032 }, { "epoch": 1.01, "learning_rate": 9.451650754112882e-06, "loss": 3.8395, "step": 2476544 }, { "epoch": 1.01, "learning_rate": 9.443264806602362e-06, "loss": 3.8371, "step": 2477056 }, { "epoch": 1.01, "learning_rate": 9.434878859091842e-06, "loss": 3.8416, "step": 2477568 }, { "epoch": 1.01, "learning_rate": 9.426492911581322e-06, "loss": 3.8532, "step": 2478080 }, { "epoch": 1.01, "learning_rate": 9.418123342874533e-06, "loss": 3.8593, "step": 2478592 }, { "epoch": 1.01, "learning_rate": 9.409737395364013e-06, "loss": 3.8506, "step": 2479104 }, { "epoch": 1.01, "learning_rate": 9.401351447853492e-06, "loss": 3.8592, "step": 2479616 }, { "epoch": 1.01, "learning_rate": 9.392965500342972e-06, "loss": 3.8646, "step": 2480128 }, { "epoch": 1.01, "learning_rate": 9.384595931636183e-06, "loss": 3.8569, "step": 2480640 }, { "epoch": 1.01, "learning_rate": 9.376226362929396e-06, "loss": 3.8538, "step": 2481152 }, { "epoch": 1.01, "learning_rate": 9.367840415418876e-06, "loss": 3.8466, "step": 2481664 }, { "epoch": 1.01, "learning_rate": 9.359454467908354e-06, "loss": 3.8542, "step": 2482176 }, { "epoch": 1.01, "learning_rate": 9.351068520397836e-06, "loss": 3.8493, "step": 2482688 }, { "epoch": 1.01, "learning_rate": 9.342682572887316e-06, "loss": 3.8447, "step": 2483200 }, { "epoch": 1.01, "learning_rate": 9.334296625376795e-06, "loss": 3.8534, "step": 2483712 }, { "epoch": 1.01, "learning_rate": 9.325910677866274e-06, "loss": 3.8577, "step": 2484224 }, { "epoch": 1.01, "learning_rate": 9.317524730355755e-06, "loss": 3.8572, "step": 2484736 }, { "epoch": 1.01, "learning_rate": 9.309138782845235e-06, "loss": 3.8364, "step": 2485248 }, { "epoch": 1.01, "learning_rate": 9.300752835334714e-06, "loss": 3.8416, "step": 2485760 }, { "epoch": 1.01, "learning_rate": 9.292366887824194e-06, "loss": 3.8516, "step": 2486272 }, { "epoch": 1.01, "learning_rate": 9.283980940313675e-06, "loss": 3.8567, "step": 2486784 }, { "epoch": 1.01, "learning_rate": 9.275627750410617e-06, "loss": 3.8458, "step": 2487296 }, { "epoch": 1.01, "learning_rate": 9.267258181703828e-06, "loss": 3.8522, "step": 2487808 }, { "epoch": 1.02, "learning_rate": 9.258872234193308e-06, "loss": 3.8541, "step": 2488320 }, { "epoch": 1.02, "learning_rate": 9.25048628668279e-06, "loss": 3.8453, "step": 2488832 }, { "epoch": 1.02, "learning_rate": 9.24210033917227e-06, "loss": 3.8428, "step": 2489344 }, { "epoch": 1.02, "learning_rate": 9.233714391661747e-06, "loss": 3.8542, "step": 2489856 }, { "epoch": 1.02, "learning_rate": 9.225328444151227e-06, "loss": 3.8505, "step": 2490368 }, { "epoch": 1.02, "learning_rate": 9.216942496640709e-06, "loss": 3.8561, "step": 2490880 }, { "epoch": 1.02, "learning_rate": 9.208556549130187e-06, "loss": 3.8529, "step": 2491392 }, { "epoch": 1.02, "learning_rate": 9.200170601619667e-06, "loss": 3.8374, "step": 2491904 }, { "epoch": 1.02, "learning_rate": 9.191784654109147e-06, "loss": 3.8536, "step": 2492416 }, { "epoch": 1.02, "learning_rate": 9.183415085402358e-06, "loss": 3.855, "step": 2492928 }, { "epoch": 1.02, "learning_rate": 9.175029137891838e-06, "loss": 3.8502, "step": 2493440 }, { "epoch": 1.02, "learning_rate": 9.16664319038132e-06, "loss": 3.857, "step": 2493952 }, { "epoch": 1.02, "learning_rate": 9.1582572428708e-06, "loss": 3.8476, "step": 2494464 }, { "epoch": 1.02, "learning_rate": 9.149871295360278e-06, "loss": 3.8522, "step": 2494976 }, { "epoch": 1.02, "learning_rate": 9.141485347849758e-06, "loss": 3.8565, "step": 2495488 }, { "epoch": 1.02, "learning_rate": 9.13309940033924e-06, "loss": 3.8348, "step": 2496000 }, { "epoch": 1.02, "learning_rate": 9.124713452828718e-06, "loss": 3.8395, "step": 2496512 }, { "epoch": 1.02, "learning_rate": 9.116343884121929e-06, "loss": 3.8483, "step": 2497024 }, { "epoch": 1.02, "learning_rate": 9.10795793661141e-06, "loss": 3.8488, "step": 2497536 }, { "epoch": 1.02, "learning_rate": 9.09957198910089e-06, "loss": 3.8377, "step": 2498048 }, { "epoch": 1.02, "learning_rate": 9.091202420394101e-06, "loss": 3.8406, "step": 2498560 }, { "epoch": 1.02, "learning_rate": 9.082816472883581e-06, "loss": 3.8412, "step": 2499072 }, { "epoch": 1.02, "learning_rate": 9.07443052537306e-06, "loss": 3.8487, "step": 2499584 }, { "epoch": 1.02, "learning_rate": 9.066044577862539e-06, "loss": 3.8412, "step": 2500096 }, { "epoch": 1.02, "learning_rate": 9.05765863035202e-06, "loss": 3.8478, "step": 2500608 }, { "epoch": 1.02, "learning_rate": 9.0492726828415e-06, "loss": 3.8492, "step": 2501120 }, { "epoch": 1.02, "learning_rate": 9.040903114134711e-06, "loss": 3.8556, "step": 2501632 }, { "epoch": 1.02, "learning_rate": 9.032517166624191e-06, "loss": 3.8513, "step": 2502144 }, { "epoch": 1.02, "learning_rate": 9.024131219113671e-06, "loss": 3.8512, "step": 2502656 }, { "epoch": 1.02, "learning_rate": 9.015745271603151e-06, "loss": 3.8562, "step": 2503168 }, { "epoch": 1.02, "learning_rate": 9.007359324092631e-06, "loss": 3.8557, "step": 2503680 }, { "epoch": 1.02, "learning_rate": 8.998973376582111e-06, "loss": 3.8436, "step": 2504192 }, { "epoch": 1.02, "learning_rate": 8.990603807875322e-06, "loss": 3.8544, "step": 2504704 }, { "epoch": 1.02, "learning_rate": 8.982217860364802e-06, "loss": 3.8453, "step": 2505216 }, { "epoch": 1.02, "learning_rate": 8.973831912854282e-06, "loss": 3.8574, "step": 2505728 }, { "epoch": 1.02, "learning_rate": 8.965445965343762e-06, "loss": 3.8364, "step": 2506240 }, { "epoch": 1.02, "learning_rate": 8.957060017833242e-06, "loss": 3.8496, "step": 2506752 }, { "epoch": 1.02, "learning_rate": 8.948674070322722e-06, "loss": 3.8364, "step": 2507264 }, { "epoch": 1.02, "learning_rate": 8.940304501615933e-06, "loss": 3.8434, "step": 2507776 }, { "epoch": 1.02, "learning_rate": 8.931918554105413e-06, "loss": 3.8347, "step": 2508288 }, { "epoch": 1.02, "learning_rate": 8.923532606594894e-06, "loss": 3.863, "step": 2508800 }, { "epoch": 1.02, "learning_rate": 8.915146659084372e-06, "loss": 3.8561, "step": 2509312 }, { "epoch": 1.02, "learning_rate": 8.906760711573852e-06, "loss": 3.8464, "step": 2509824 }, { "epoch": 1.02, "learning_rate": 8.898391142867065e-06, "loss": 3.8503, "step": 2510336 }, { "epoch": 1.02, "learning_rate": 8.890005195356545e-06, "loss": 3.852, "step": 2510848 }, { "epoch": 1.02, "learning_rate": 8.881619247846023e-06, "loss": 3.8594, "step": 2511360 }, { "epoch": 1.02, "learning_rate": 8.873233300335503e-06, "loss": 3.8556, "step": 2511872 }, { "epoch": 1.02, "learning_rate": 8.864847352824985e-06, "loss": 3.8467, "step": 2512384 }, { "epoch": 1.02, "learning_rate": 8.856477784118194e-06, "loss": 3.8595, "step": 2512896 }, { "epoch": 1.02, "learning_rate": 8.848091836607675e-06, "loss": 3.8456, "step": 2513408 }, { "epoch": 1.02, "learning_rate": 8.839705889097155e-06, "loss": 3.8607, "step": 2513920 }, { "epoch": 1.02, "learning_rate": 8.831319941586635e-06, "loss": 3.8494, "step": 2514432 }, { "epoch": 1.02, "learning_rate": 8.822933994076114e-06, "loss": 3.8507, "step": 2514944 }, { "epoch": 1.02, "learning_rate": 8.814548046565595e-06, "loss": 3.8532, "step": 2515456 }, { "epoch": 1.02, "learning_rate": 8.806194856662537e-06, "loss": 3.8427, "step": 2515968 }, { "epoch": 1.02, "learning_rate": 8.797808909152019e-06, "loss": 3.8512, "step": 2516480 }, { "epoch": 1.02, "learning_rate": 8.789422961641497e-06, "loss": 3.8505, "step": 2516992 }, { "epoch": 1.02, "learning_rate": 8.781037014130977e-06, "loss": 3.8518, "step": 2517504 }, { "epoch": 1.02, "learning_rate": 8.772651066620457e-06, "loss": 3.8516, "step": 2518016 }, { "epoch": 1.02, "learning_rate": 8.764265119109937e-06, "loss": 3.8445, "step": 2518528 }, { "epoch": 1.03, "eval_loss": 3.9739441871643066, "eval_runtime": 296.2465, "eval_samples_per_second": 1288.086, "eval_steps_per_second": 40.254, "step": 2518560 }, { "epoch": 0.0, "learning_rate": 8.755879171599417e-06, "loss": 3.84, "step": 2519040 }, { "epoch": 0.0, "learning_rate": 8.747493224088897e-06, "loss": 3.8418, "step": 2519552 }, { "epoch": 0.0, "learning_rate": 8.739107276578377e-06, "loss": 3.8574, "step": 2520064 }, { "epoch": 0.0, "learning_rate": 8.730721329067857e-06, "loss": 3.8475, "step": 2520576 }, { "epoch": 0.0, "learning_rate": 8.722335381557336e-06, "loss": 3.866, "step": 2521088 }, { "epoch": 0.0, "learning_rate": 8.713949434046816e-06, "loss": 3.8433, "step": 2521600 }, { "epoch": 0.0, "learning_rate": 8.705563486536296e-06, "loss": 3.8459, "step": 2522112 }, { "epoch": 0.0, "learning_rate": 8.697177539025776e-06, "loss": 3.8349, "step": 2522624 }, { "epoch": 0.0, "learning_rate": 8.688791591515256e-06, "loss": 3.8531, "step": 2523136 }, { "epoch": 0.0, "learning_rate": 8.680405644004736e-06, "loss": 3.8481, "step": 2523648 }, { "epoch": 0.0, "learning_rate": 8.672019696494216e-06, "loss": 3.8512, "step": 2524160 }, { "epoch": 0.0, "learning_rate": 8.663633748983696e-06, "loss": 3.8528, "step": 2524672 }, { "epoch": 0.0, "learning_rate": 8.655264180276907e-06, "loss": 3.8408, "step": 2525184 }, { "epoch": 0.0, "learning_rate": 8.646878232766387e-06, "loss": 3.8405, "step": 2525696 }, { "epoch": 0.0, "learning_rate": 8.638492285255867e-06, "loss": 3.842, "step": 2526208 }, { "epoch": 0.0, "learning_rate": 8.630106337745347e-06, "loss": 3.8388, "step": 2526720 }, { "epoch": 0.0, "learning_rate": 8.621720390234827e-06, "loss": 3.8462, "step": 2527232 }, { "epoch": 0.0, "learning_rate": 8.613334442724307e-06, "loss": 3.8481, "step": 2527744 }, { "epoch": 0.0, "learning_rate": 8.604948495213787e-06, "loss": 3.8432, "step": 2528256 }, { "epoch": 0.0, "learning_rate": 8.596562547703265e-06, "loss": 3.8674, "step": 2528768 }, { "epoch": 0.0, "learning_rate": 8.588176600192747e-06, "loss": 3.844, "step": 2529280 }, { "epoch": 0.0, "learning_rate": 8.579790652682227e-06, "loss": 3.8529, "step": 2529792 }, { "epoch": 0.0, "learning_rate": 8.571404705171705e-06, "loss": 3.8509, "step": 2530304 }, { "epoch": 0.0, "learning_rate": 8.563035136464917e-06, "loss": 3.8602, "step": 2530816 }, { "epoch": 0.0, "learning_rate": 8.554649188954397e-06, "loss": 3.8381, "step": 2531328 }, { "epoch": 0.0, "learning_rate": 8.54627962024761e-06, "loss": 3.8469, "step": 2531840 }, { "epoch": 0.0, "learning_rate": 8.537893672737088e-06, "loss": 3.8414, "step": 2532352 }, { "epoch": 0.0, "learning_rate": 8.529507725226568e-06, "loss": 3.8524, "step": 2532864 }, { "epoch": 0.0, "learning_rate": 8.521121777716048e-06, "loss": 3.8359, "step": 2533376 }, { "epoch": 0.01, "learning_rate": 8.51273583020553e-06, "loss": 3.8414, "step": 2533888 }, { "epoch": 0.01, "learning_rate": 8.504366261498739e-06, "loss": 3.8521, "step": 2534400 }, { "epoch": 0.01, "learning_rate": 8.495980313988219e-06, "loss": 3.8482, "step": 2534912 }, { "epoch": 0.01, "learning_rate": 8.4875943664777e-06, "loss": 3.85, "step": 2535424 }, { "epoch": 0.01, "learning_rate": 8.479208418967179e-06, "loss": 3.8585, "step": 2535936 }, { "epoch": 0.01, "learning_rate": 8.470822471456658e-06, "loss": 3.851, "step": 2536448 }, { "epoch": 0.01, "learning_rate": 8.462452902749871e-06, "loss": 3.8503, "step": 2536960 }, { "epoch": 0.01, "learning_rate": 8.454066955239351e-06, "loss": 3.8435, "step": 2537472 }, { "epoch": 0.01, "learning_rate": 8.44568100772883e-06, "loss": 3.8518, "step": 2537984 }, { "epoch": 0.01, "learning_rate": 8.43729506021831e-06, "loss": 3.8407, "step": 2538496 }, { "epoch": 0.01, "learning_rate": 8.42890911270779e-06, "loss": 3.8461, "step": 2539008 }, { "epoch": 0.01, "learning_rate": 8.420523165197269e-06, "loss": 3.8514, "step": 2539520 }, { "epoch": 0.01, "learning_rate": 8.412137217686749e-06, "loss": 3.8552, "step": 2540032 }, { "epoch": 0.01, "learning_rate": 8.40375127017623e-06, "loss": 3.8405, "step": 2540544 }, { "epoch": 0.01, "learning_rate": 8.395381701469441e-06, "loss": 3.85, "step": 2541056 }, { "epoch": 0.01, "learning_rate": 8.38699575395892e-06, "loss": 3.8574, "step": 2541568 }, { "epoch": 0.01, "learning_rate": 8.378626185252132e-06, "loss": 3.8499, "step": 2542080 }, { "epoch": 0.01, "learning_rate": 8.370240237741612e-06, "loss": 3.8527, "step": 2542592 }, { "epoch": 0.01, "learning_rate": 8.361854290231092e-06, "loss": 3.8255, "step": 2543104 }, { "epoch": 0.01, "learning_rate": 8.353468342720572e-06, "loss": 3.8344, "step": 2543616 }, { "epoch": 0.01, "learning_rate": 8.345082395210052e-06, "loss": 3.8552, "step": 2544128 }, { "epoch": 0.01, "learning_rate": 8.336712826503265e-06, "loss": 3.8495, "step": 2544640 }, { "epoch": 0.01, "learning_rate": 8.328326878992743e-06, "loss": 3.8439, "step": 2545152 }, { "epoch": 0.01, "learning_rate": 8.319957310285954e-06, "loss": 3.8273, "step": 2545664 }, { "epoch": 0.01, "learning_rate": 8.311571362775435e-06, "loss": 3.8352, "step": 2546176 }, { "epoch": 0.01, "learning_rate": 8.303185415264915e-06, "loss": 3.8293, "step": 2546688 }, { "epoch": 0.01, "learning_rate": 8.294799467754393e-06, "loss": 3.858, "step": 2547200 }, { "epoch": 0.01, "learning_rate": 8.286413520243873e-06, "loss": 3.8326, "step": 2547712 }, { "epoch": 0.01, "learning_rate": 8.278027572733355e-06, "loss": 3.8494, "step": 2548224 }, { "epoch": 0.01, "learning_rate": 8.269641625222833e-06, "loss": 3.8499, "step": 2548736 }, { "epoch": 0.01, "learning_rate": 8.261255677712313e-06, "loss": 3.8361, "step": 2549248 }, { "epoch": 0.01, "learning_rate": 8.252869730201793e-06, "loss": 3.8434, "step": 2549760 }, { "epoch": 0.01, "learning_rate": 8.244500161495006e-06, "loss": 3.8381, "step": 2550272 }, { "epoch": 0.01, "learning_rate": 8.236114213984484e-06, "loss": 3.8327, "step": 2550784 }, { "epoch": 0.01, "learning_rate": 8.227728266473966e-06, "loss": 3.8342, "step": 2551296 }, { "epoch": 0.01, "learning_rate": 8.219358697767176e-06, "loss": 3.8518, "step": 2551808 }, { "epoch": 0.01, "learning_rate": 8.210972750256656e-06, "loss": 3.8454, "step": 2552320 }, { "epoch": 0.01, "learning_rate": 8.202586802746136e-06, "loss": 3.836, "step": 2552832 }, { "epoch": 0.01, "learning_rate": 8.194200855235616e-06, "loss": 3.8343, "step": 2553344 }, { "epoch": 0.01, "learning_rate": 8.185814907725096e-06, "loss": 3.8369, "step": 2553856 }, { "epoch": 0.01, "learning_rate": 8.177428960214576e-06, "loss": 3.8497, "step": 2554368 }, { "epoch": 0.01, "learning_rate": 8.169043012704056e-06, "loss": 3.8548, "step": 2554880 }, { "epoch": 0.01, "learning_rate": 8.160657065193536e-06, "loss": 3.8471, "step": 2555392 }, { "epoch": 0.01, "learning_rate": 8.152271117683014e-06, "loss": 3.8611, "step": 2555904 }, { "epoch": 0.01, "learning_rate": 8.143885170172496e-06, "loss": 3.8561, "step": 2556416 }, { "epoch": 0.01, "learning_rate": 8.135499222661976e-06, "loss": 3.8579, "step": 2556928 }, { "epoch": 0.01, "learning_rate": 8.127129653955187e-06, "loss": 3.8499, "step": 2557440 }, { "epoch": 0.01, "learning_rate": 8.118743706444667e-06, "loss": 3.8452, "step": 2557952 }, { "epoch": 0.01, "learning_rate": 8.110357758934147e-06, "loss": 3.8506, "step": 2558464 }, { "epoch": 0.01, "learning_rate": 8.101971811423627e-06, "loss": 3.8447, "step": 2558976 }, { "epoch": 0.01, "learning_rate": 8.093602242716839e-06, "loss": 3.8432, "step": 2559488 }, { "epoch": 0.01, "learning_rate": 8.085216295206317e-06, "loss": 3.8508, "step": 2560000 }, { "epoch": 0.01, "learning_rate": 8.076830347695797e-06, "loss": 3.8569, "step": 2560512 }, { "epoch": 0.01, "learning_rate": 8.068444400185277e-06, "loss": 3.8493, "step": 2561024 }, { "epoch": 0.01, "learning_rate": 8.060058452674757e-06, "loss": 3.8372, "step": 2561536 }, { "epoch": 0.01, "learning_rate": 8.051688883967968e-06, "loss": 3.8384, "step": 2562048 }, { "epoch": 0.01, "learning_rate": 8.04330293645745e-06, "loss": 3.846, "step": 2562560 }, { "epoch": 0.01, "learning_rate": 8.034916988946928e-06, "loss": 3.8548, "step": 2563072 }, { "epoch": 0.01, "learning_rate": 8.026531041436408e-06, "loss": 3.8437, "step": 2563584 }, { "epoch": 0.01, "learning_rate": 8.01816147272962e-06, "loss": 3.8476, "step": 2564096 }, { "epoch": 0.02, "learning_rate": 8.0097755252191e-06, "loss": 3.851, "step": 2564608 }, { "epoch": 0.02, "learning_rate": 8.001389577708579e-06, "loss": 3.8422, "step": 2565120 }, { "epoch": 0.02, "learning_rate": 7.993003630198059e-06, "loss": 3.8431, "step": 2565632 }, { "epoch": 0.02, "learning_rate": 7.98461768268754e-06, "loss": 3.8458, "step": 2566144 }, { "epoch": 0.02, "learning_rate": 7.976231735177018e-06, "loss": 3.8501, "step": 2566656 }, { "epoch": 0.02, "learning_rate": 7.967845787666498e-06, "loss": 3.8503, "step": 2567168 }, { "epoch": 0.02, "learning_rate": 7.959476218959711e-06, "loss": 3.8524, "step": 2567680 }, { "epoch": 0.02, "learning_rate": 7.95109027144919e-06, "loss": 3.8361, "step": 2568192 }, { "epoch": 0.02, "learning_rate": 7.942704323938669e-06, "loss": 3.8508, "step": 2568704 }, { "epoch": 0.02, "learning_rate": 7.93431837642815e-06, "loss": 3.8461, "step": 2569216 }, { "epoch": 0.02, "learning_rate": 7.92593242891763e-06, "loss": 3.8536, "step": 2569728 }, { "epoch": 0.02, "learning_rate": 7.917546481407109e-06, "loss": 3.8505, "step": 2570240 }, { "epoch": 0.02, "learning_rate": 7.909160533896589e-06, "loss": 3.8489, "step": 2570752 }, { "epoch": 0.02, "learning_rate": 7.900790965189801e-06, "loss": 3.8519, "step": 2571264 }, { "epoch": 0.02, "learning_rate": 7.892405017679281e-06, "loss": 3.8542, "step": 2571776 }, { "epoch": 0.02, "learning_rate": 7.884019070168761e-06, "loss": 3.8335, "step": 2572288 }, { "epoch": 0.02, "learning_rate": 7.875633122658241e-06, "loss": 3.8379, "step": 2572800 }, { "epoch": 0.02, "learning_rate": 7.867263553951452e-06, "loss": 3.8458, "step": 2573312 }, { "epoch": 0.02, "learning_rate": 7.858877606440932e-06, "loss": 3.843, "step": 2573824 }, { "epoch": 0.02, "learning_rate": 7.850491658930412e-06, "loss": 3.8358, "step": 2574336 }, { "epoch": 0.02, "learning_rate": 7.842122090223623e-06, "loss": 3.8396, "step": 2574848 }, { "epoch": 0.02, "learning_rate": 7.833736142713104e-06, "loss": 3.8385, "step": 2575360 }, { "epoch": 0.02, "learning_rate": 7.825350195202583e-06, "loss": 3.845, "step": 2575872 }, { "epoch": 0.02, "learning_rate": 7.816964247692063e-06, "loss": 3.8399, "step": 2576384 }, { "epoch": 0.02, "learning_rate": 7.808578300181543e-06, "loss": 3.8421, "step": 2576896 }, { "epoch": 0.02, "learning_rate": 7.800192352671024e-06, "loss": 3.8468, "step": 2577408 }, { "epoch": 0.02, "learning_rate": 7.791806405160503e-06, "loss": 3.852, "step": 2577920 }, { "epoch": 0.02, "learning_rate": 7.783420457649982e-06, "loss": 3.8485, "step": 2578432 }, { "epoch": 0.02, "learning_rate": 7.775034510139462e-06, "loss": 3.8448, "step": 2578944 }, { "epoch": 0.02, "learning_rate": 7.766648562628942e-06, "loss": 3.8562, "step": 2579456 }, { "epoch": 0.02, "learning_rate": 7.758262615118422e-06, "loss": 3.8536, "step": 2579968 }, { "epoch": 0.02, "learning_rate": 7.749876667607902e-06, "loss": 3.8391, "step": 2580480 }, { "epoch": 0.02, "learning_rate": 7.741507098901115e-06, "loss": 3.8548, "step": 2580992 }, { "epoch": 0.02, "learning_rate": 7.733121151390593e-06, "loss": 3.8433, "step": 2581504 }, { "epoch": 0.02, "learning_rate": 7.724735203880073e-06, "loss": 3.8535, "step": 2582016 }, { "epoch": 0.02, "learning_rate": 7.716349256369555e-06, "loss": 3.8329, "step": 2582528 }, { "epoch": 0.02, "learning_rate": 7.707963308859033e-06, "loss": 3.8505, "step": 2583040 }, { "epoch": 0.02, "learning_rate": 7.699577361348513e-06, "loss": 3.8315, "step": 2583552 }, { "epoch": 0.02, "learning_rate": 7.691207792641725e-06, "loss": 3.8394, "step": 2584064 }, { "epoch": 0.02, "learning_rate": 7.682821845131205e-06, "loss": 3.8302, "step": 2584576 }, { "epoch": 0.02, "learning_rate": 7.674435897620684e-06, "loss": 3.8609, "step": 2585088 }, { "epoch": 0.02, "learning_rate": 7.666049950110164e-06, "loss": 3.8529, "step": 2585600 }, { "epoch": 0.02, "learning_rate": 7.657664002599645e-06, "loss": 3.8472, "step": 2586112 }, { "epoch": 0.02, "learning_rate": 7.649278055089123e-06, "loss": 3.8419, "step": 2586624 }, { "epoch": 0.02, "learning_rate": 7.640908486382336e-06, "loss": 3.8486, "step": 2587136 }, { "epoch": 0.02, "learning_rate": 7.632522538871816e-06, "loss": 3.857, "step": 2587648 }, { "epoch": 0.02, "learning_rate": 7.624136591361296e-06, "loss": 3.851, "step": 2588160 }, { "epoch": 0.02, "learning_rate": 7.615750643850775e-06, "loss": 3.8476, "step": 2588672 }, { "epoch": 0.02, "learning_rate": 7.6073810751439866e-06, "loss": 3.8532, "step": 2589184 }, { "epoch": 0.02, "learning_rate": 7.5989951276334665e-06, "loss": 3.844, "step": 2589696 }, { "epoch": 0.02, "learning_rate": 7.590609180122946e-06, "loss": 3.8618, "step": 2590208 }, { "epoch": 0.02, "learning_rate": 7.582239611416157e-06, "loss": 3.8442, "step": 2590720 }, { "epoch": 0.02, "learning_rate": 7.573853663905637e-06, "loss": 3.8479, "step": 2591232 }, { "epoch": 0.02, "learning_rate": 7.565467716395118e-06, "loss": 3.8472, "step": 2591744 }, { "epoch": 0.02, "learning_rate": 7.557081768884597e-06, "loss": 3.8419, "step": 2592256 }, { "epoch": 0.02, "learning_rate": 7.548695821374077e-06, "loss": 3.8509, "step": 2592768 }, { "epoch": 0.02, "learning_rate": 7.540326252667289e-06, "loss": 3.8458, "step": 2593280 }, { "epoch": 0.02, "learning_rate": 7.5319403051567695e-06, "loss": 3.8527, "step": 2593792 }, { "epoch": 0.02, "learning_rate": 7.523554357646248e-06, "loss": 3.8469, "step": 2594304 }, { "epoch": 0.02, "learning_rate": 7.515168410135729e-06, "loss": 3.8406, "step": 2594816 }, { "epoch": 0.03, "eval_loss": 3.9732656478881836, "eval_runtime": 322.5878, "eval_samples_per_second": 1182.906, "eval_steps_per_second": 36.967, "step": 2594880 }, { "epoch": 1.0, "learning_rate": 7.5067824626252085e-06, "loss": 3.8422, "step": 2595328 }, { "epoch": 1.0, "learning_rate": 7.498396515114688e-06, "loss": 3.8399, "step": 2595840 }, { "epoch": 1.0, "learning_rate": 7.490010567604168e-06, "loss": 3.8533, "step": 2596352 }, { "epoch": 1.0, "learning_rate": 7.481640998897379e-06, "loss": 3.8435, "step": 2596864 }, { "epoch": 1.0, "learning_rate": 7.473255051386858e-06, "loss": 3.8637, "step": 2597376 }, { "epoch": 1.0, "learning_rate": 7.464869103876339e-06, "loss": 3.8381, "step": 2597888 }, { "epoch": 1.0, "learning_rate": 7.456483156365819e-06, "loss": 3.8443, "step": 2598400 }, { "epoch": 1.0, "learning_rate": 7.448097208855299e-06, "loss": 3.8348, "step": 2598912 }, { "epoch": 1.0, "learning_rate": 7.439711261344778e-06, "loss": 3.8506, "step": 2599424 }, { "epoch": 1.0, "learning_rate": 7.431325313834259e-06, "loss": 3.8456, "step": 2599936 }, { "epoch": 1.0, "learning_rate": 7.422939366323739e-06, "loss": 3.8475, "step": 2600448 }, { "epoch": 1.0, "learning_rate": 7.414569797616949e-06, "loss": 3.8487, "step": 2600960 }, { "epoch": 1.0, "learning_rate": 7.4062002289101605e-06, "loss": 3.8373, "step": 2601472 }, { "epoch": 1.0, "learning_rate": 7.397814281399641e-06, "loss": 3.8421, "step": 2601984 }, { "epoch": 1.0, "learning_rate": 7.389428333889121e-06, "loss": 3.8407, "step": 2602496 }, { "epoch": 1.0, "learning_rate": 7.3810423863786e-06, "loss": 3.8373, "step": 2603008 }, { "epoch": 1.0, "learning_rate": 7.372656438868081e-06, "loss": 3.8407, "step": 2603520 }, { "epoch": 1.0, "learning_rate": 7.364270491357561e-06, "loss": 3.8453, "step": 2604032 }, { "epoch": 1.0, "learning_rate": 7.35588454384704e-06, "loss": 3.84, "step": 2604544 }, { "epoch": 1.0, "learning_rate": 7.34749859633652e-06, "loss": 3.8643, "step": 2605056 }, { "epoch": 1.0, "learning_rate": 7.339112648826001e-06, "loss": 3.8413, "step": 2605568 }, { "epoch": 1.0, "learning_rate": 7.330743080119213e-06, "loss": 3.8459, "step": 2606080 }, { "epoch": 1.0, "learning_rate": 7.322357132608691e-06, "loss": 3.8485, "step": 2606592 }, { "epoch": 1.0, "learning_rate": 7.313971185098172e-06, "loss": 3.854, "step": 2607104 }, { "epoch": 1.0, "learning_rate": 7.305601616391383e-06, "loss": 3.8355, "step": 2607616 }, { "epoch": 1.0, "learning_rate": 7.297215668880863e-06, "loss": 3.8495, "step": 2608128 }, { "epoch": 1.0, "learning_rate": 7.288829721370342e-06, "loss": 3.8396, "step": 2608640 }, { "epoch": 1.0, "learning_rate": 7.280443773859822e-06, "loss": 3.8478, "step": 2609152 }, { "epoch": 1.0, "learning_rate": 7.272057826349303e-06, "loss": 3.8331, "step": 2609664 }, { "epoch": 1.01, "learning_rate": 7.263671878838782e-06, "loss": 3.8382, "step": 2610176 }, { "epoch": 1.01, "learning_rate": 7.255285931328262e-06, "loss": 3.8476, "step": 2610688 }, { "epoch": 1.01, "learning_rate": 7.246916362621474e-06, "loss": 3.8481, "step": 2611200 }, { "epoch": 1.01, "learning_rate": 7.238530415110955e-06, "loss": 3.8483, "step": 2611712 }, { "epoch": 1.01, "learning_rate": 7.230144467600433e-06, "loss": 3.8544, "step": 2612224 }, { "epoch": 1.01, "learning_rate": 7.221758520089914e-06, "loss": 3.8462, "step": 2612736 }, { "epoch": 1.01, "learning_rate": 7.213372572579394e-06, "loss": 3.8495, "step": 2613248 }, { "epoch": 1.01, "learning_rate": 7.204986625068873e-06, "loss": 3.8381, "step": 2613760 }, { "epoch": 1.01, "learning_rate": 7.196600677558353e-06, "loss": 3.852, "step": 2614272 }, { "epoch": 1.01, "learning_rate": 7.1882147300478336e-06, "loss": 3.8371, "step": 2614784 }, { "epoch": 1.01, "learning_rate": 7.179845161341045e-06, "loss": 3.8426, "step": 2615296 }, { "epoch": 1.01, "learning_rate": 7.171459213830524e-06, "loss": 3.8465, "step": 2615808 }, { "epoch": 1.01, "learning_rate": 7.163073266320004e-06, "loss": 3.8532, "step": 2616320 }, { "epoch": 1.01, "learning_rate": 7.154687318809484e-06, "loss": 3.8426, "step": 2616832 }, { "epoch": 1.01, "learning_rate": 7.146301371298963e-06, "loss": 3.8424, "step": 2617344 }, { "epoch": 1.01, "learning_rate": 7.137915423788444e-06, "loss": 3.855, "step": 2617856 }, { "epoch": 1.01, "learning_rate": 7.129529476277924e-06, "loss": 3.849, "step": 2618368 }, { "epoch": 1.01, "learning_rate": 7.121143528767403e-06, "loss": 3.8504, "step": 2618880 }, { "epoch": 1.01, "learning_rate": 7.112773960060615e-06, "loss": 3.83, "step": 2619392 }, { "epoch": 1.01, "learning_rate": 7.104388012550095e-06, "loss": 3.829, "step": 2619904 }, { "epoch": 1.01, "learning_rate": 7.096002065039576e-06, "loss": 3.8492, "step": 2620416 }, { "epoch": 1.01, "learning_rate": 7.087616117529054e-06, "loss": 3.8467, "step": 2620928 }, { "epoch": 1.01, "learning_rate": 7.079230170018535e-06, "loss": 3.843, "step": 2621440 }, { "epoch": 1.01, "learning_rate": 7.070844222508015e-06, "loss": 3.8254, "step": 2621952 }, { "epoch": 1.01, "learning_rate": 7.062458274997494e-06, "loss": 3.8319, "step": 2622464 }, { "epoch": 1.01, "learning_rate": 7.0540723274869745e-06, "loss": 3.8344, "step": 2622976 }, { "epoch": 1.01, "learning_rate": 7.045702758780186e-06, "loss": 3.8471, "step": 2623488 }, { "epoch": 1.01, "learning_rate": 7.037316811269666e-06, "loss": 3.8321, "step": 2624000 }, { "epoch": 1.01, "learning_rate": 7.028930863759145e-06, "loss": 3.8457, "step": 2624512 }, { "epoch": 1.01, "learning_rate": 7.020544916248625e-06, "loss": 3.845, "step": 2625024 }, { "epoch": 1.01, "learning_rate": 7.012175347541837e-06, "loss": 3.8357, "step": 2625536 }, { "epoch": 1.01, "learning_rate": 7.003789400031318e-06, "loss": 3.839, "step": 2626048 }, { "epoch": 1.01, "learning_rate": 6.9954198313245276e-06, "loss": 3.8367, "step": 2626560 }, { "epoch": 1.01, "learning_rate": 6.9870338838140075e-06, "loss": 3.8264, "step": 2627072 }, { "epoch": 1.01, "learning_rate": 6.978664315107219e-06, "loss": 3.8377, "step": 2627584 }, { "epoch": 1.01, "learning_rate": 6.9702783675967e-06, "loss": 3.8407, "step": 2628096 }, { "epoch": 1.01, "learning_rate": 6.961892420086179e-06, "loss": 3.8504, "step": 2628608 }, { "epoch": 1.01, "learning_rate": 6.953506472575659e-06, "loss": 3.8285, "step": 2629120 }, { "epoch": 1.01, "learning_rate": 6.945120525065139e-06, "loss": 3.8337, "step": 2629632 }, { "epoch": 1.01, "learning_rate": 6.936734577554618e-06, "loss": 3.8316, "step": 2630144 }, { "epoch": 1.01, "learning_rate": 6.928348630044099e-06, "loss": 3.8549, "step": 2630656 }, { "epoch": 1.01, "learning_rate": 6.919962682533579e-06, "loss": 3.8441, "step": 2631168 }, { "epoch": 1.01, "learning_rate": 6.911576735023058e-06, "loss": 3.846, "step": 2631680 }, { "epoch": 1.01, "learning_rate": 6.90320716631627e-06, "loss": 3.8579, "step": 2632192 }, { "epoch": 1.01, "learning_rate": 6.8948212188057495e-06, "loss": 3.8557, "step": 2632704 }, { "epoch": 1.01, "learning_rate": 6.88643527129523e-06, "loss": 3.8537, "step": 2633216 }, { "epoch": 1.01, "learning_rate": 6.8780493237847095e-06, "loss": 3.8458, "step": 2633728 }, { "epoch": 1.01, "learning_rate": 6.869679755077921e-06, "loss": 3.8481, "step": 2634240 }, { "epoch": 1.01, "learning_rate": 6.861293807567401e-06, "loss": 3.8468, "step": 2634752 }, { "epoch": 1.01, "learning_rate": 6.85290786005688e-06, "loss": 3.8431, "step": 2635264 }, { "epoch": 1.01, "learning_rate": 6.84452191254636e-06, "loss": 3.8413, "step": 2635776 }, { "epoch": 1.01, "learning_rate": 6.836152343839572e-06, "loss": 3.8463, "step": 2636288 }, { "epoch": 1.01, "learning_rate": 6.8277663963290526e-06, "loss": 3.8542, "step": 2636800 }, { "epoch": 1.01, "learning_rate": 6.819380448818531e-06, "loss": 3.8459, "step": 2637312 }, { "epoch": 1.01, "learning_rate": 6.810994501308012e-06, "loss": 3.8385, "step": 2637824 }, { "epoch": 1.01, "learning_rate": 6.8026085537974916e-06, "loss": 3.8332, "step": 2638336 }, { "epoch": 1.01, "learning_rate": 6.794238985090703e-06, "loss": 3.8458, "step": 2638848 }, { "epoch": 1.01, "learning_rate": 6.785869416383914e-06, "loss": 3.8491, "step": 2639360 }, { "epoch": 1.01, "learning_rate": 6.777483468873394e-06, "loss": 3.8428, "step": 2639872 }, { "epoch": 1.01, "learning_rate": 6.769097521362874e-06, "loss": 3.8433, "step": 2640384 }, { "epoch": 1.02, "learning_rate": 6.760711573852353e-06, "loss": 3.8503, "step": 2640896 }, { "epoch": 1.02, "learning_rate": 6.752325626341834e-06, "loss": 3.8323, "step": 2641408 }, { "epoch": 1.02, "learning_rate": 6.743939678831314e-06, "loss": 3.8454, "step": 2641920 }, { "epoch": 1.02, "learning_rate": 6.735553731320795e-06, "loss": 3.8402, "step": 2642432 }, { "epoch": 1.02, "learning_rate": 6.727167783810273e-06, "loss": 3.8508, "step": 2642944 }, { "epoch": 1.02, "learning_rate": 6.7187982151034845e-06, "loss": 3.8487, "step": 2643456 }, { "epoch": 1.02, "learning_rate": 6.710412267592965e-06, "loss": 3.8471, "step": 2643968 }, { "epoch": 1.02, "learning_rate": 6.702026320082444e-06, "loss": 3.8347, "step": 2644480 }, { "epoch": 1.02, "learning_rate": 6.693640372571924e-06, "loss": 3.8502, "step": 2644992 }, { "epoch": 1.02, "learning_rate": 6.685270803865136e-06, "loss": 3.8367, "step": 2645504 }, { "epoch": 1.02, "learning_rate": 6.676884856354616e-06, "loss": 3.8582, "step": 2646016 }, { "epoch": 1.02, "learning_rate": 6.668515287647827e-06, "loss": 3.847, "step": 2646528 }, { "epoch": 1.02, "learning_rate": 6.660129340137307e-06, "loss": 3.8464, "step": 2647040 }, { "epoch": 1.02, "learning_rate": 6.6517433926267875e-06, "loss": 3.8422, "step": 2647552 }, { "epoch": 1.02, "learning_rate": 6.6433574451162674e-06, "loss": 3.8554, "step": 2648064 }, { "epoch": 1.02, "learning_rate": 6.6349714976057466e-06, "loss": 3.8289, "step": 2648576 }, { "epoch": 1.02, "learning_rate": 6.6265855500952265e-06, "loss": 3.8352, "step": 2649088 }, { "epoch": 1.02, "learning_rate": 6.618199602584707e-06, "loss": 3.8418, "step": 2649600 }, { "epoch": 1.02, "learning_rate": 6.609830033877917e-06, "loss": 3.8433, "step": 2650112 }, { "epoch": 1.02, "learning_rate": 6.601444086367398e-06, "loss": 3.8307, "step": 2650624 }, { "epoch": 1.02, "learning_rate": 6.593058138856878e-06, "loss": 3.8351, "step": 2651136 }, { "epoch": 1.02, "learning_rate": 6.584672191346358e-06, "loss": 3.8342, "step": 2651648 }, { "epoch": 1.02, "learning_rate": 6.576286243835837e-06, "loss": 3.8438, "step": 2652160 }, { "epoch": 1.02, "learning_rate": 6.567900296325318e-06, "loss": 3.8368, "step": 2652672 }, { "epoch": 1.02, "learning_rate": 6.559514348814798e-06, "loss": 3.835, "step": 2653184 }, { "epoch": 1.02, "learning_rate": 6.551128401304277e-06, "loss": 3.8499, "step": 2653696 }, { "epoch": 1.02, "learning_rate": 6.542742453793757e-06, "loss": 3.8503, "step": 2654208 }, { "epoch": 1.02, "learning_rate": 6.534356506283238e-06, "loss": 3.8476, "step": 2654720 }, { "epoch": 1.02, "learning_rate": 6.525986937576449e-06, "loss": 3.838, "step": 2655232 }, { "epoch": 1.02, "learning_rate": 6.517600990065928e-06, "loss": 3.8522, "step": 2655744 }, { "epoch": 1.02, "learning_rate": 6.509215042555408e-06, "loss": 3.847, "step": 2656256 }, { "epoch": 1.02, "learning_rate": 6.500829095044888e-06, "loss": 3.8378, "step": 2656768 }, { "epoch": 1.02, "learning_rate": 6.4924431475343675e-06, "loss": 3.855, "step": 2657280 }, { "epoch": 1.02, "learning_rate": 6.4840572000238474e-06, "loss": 3.8371, "step": 2657792 }, { "epoch": 1.02, "learning_rate": 6.475671252513328e-06, "loss": 3.8509, "step": 2658304 }, { "epoch": 1.02, "learning_rate": 6.467285305002807e-06, "loss": 3.8331, "step": 2658816 }, { "epoch": 1.02, "learning_rate": 6.458915736296019e-06, "loss": 3.8474, "step": 2659328 }, { "epoch": 1.02, "learning_rate": 6.450529788785499e-06, "loss": 3.8292, "step": 2659840 }, { "epoch": 1.02, "learning_rate": 6.4421602200787106e-06, "loss": 3.8368, "step": 2660352 }, { "epoch": 1.02, "learning_rate": 6.43377427256819e-06, "loss": 3.8285, "step": 2660864 }, { "epoch": 1.02, "learning_rate": 6.42538832505767e-06, "loss": 3.8553, "step": 2661376 }, { "epoch": 1.02, "learning_rate": 6.4170023775471504e-06, "loss": 3.8488, "step": 2661888 }, { "epoch": 1.02, "learning_rate": 6.40861643003663e-06, "loss": 3.8475, "step": 2662400 }, { "epoch": 1.02, "learning_rate": 6.4002304825261095e-06, "loss": 3.8418, "step": 2662912 }, { "epoch": 1.02, "learning_rate": 6.3918445350155895e-06, "loss": 3.8438, "step": 2663424 }, { "epoch": 1.02, "learning_rate": 6.38345858750507e-06, "loss": 3.858, "step": 2663936 }, { "epoch": 1.02, "learning_rate": 6.37508901879828e-06, "loss": 3.8429, "step": 2664448 }, { "epoch": 1.02, "learning_rate": 6.366703071287761e-06, "loss": 3.8432, "step": 2664960 }, { "epoch": 1.02, "learning_rate": 6.358317123777241e-06, "loss": 3.8515, "step": 2665472 }, { "epoch": 1.02, "learning_rate": 6.349931176266721e-06, "loss": 3.8459, "step": 2665984 }, { "epoch": 1.02, "learning_rate": 6.3415452287562e-06, "loss": 3.8521, "step": 2666496 }, { "epoch": 1.02, "learning_rate": 6.333159281245681e-06, "loss": 3.8405, "step": 2667008 }, { "epoch": 1.02, "learning_rate": 6.324773333735161e-06, "loss": 3.8485, "step": 2667520 }, { "epoch": 1.02, "learning_rate": 6.31638738622464e-06, "loss": 3.8445, "step": 2668032 }, { "epoch": 1.02, "learning_rate": 6.30800143871412e-06, "loss": 3.8424, "step": 2668544 }, { "epoch": 1.02, "learning_rate": 6.299615491203601e-06, "loss": 3.842, "step": 2669056 }, { "epoch": 1.02, "learning_rate": 6.291229543693079e-06, "loss": 3.8482, "step": 2669568 }, { "epoch": 1.02, "learning_rate": 6.282859974986291e-06, "loss": 3.8403, "step": 2670080 }, { "epoch": 1.02, "learning_rate": 6.274490406279503e-06, "loss": 3.8454, "step": 2670592 }, { "epoch": 1.02, "learning_rate": 6.266104458768983e-06, "loss": 3.8394, "step": 2671104 }, { "epoch": 1.03, "eval_loss": 3.972667694091797, "eval_runtime": 323.2638, "eval_samples_per_second": 1180.432, "eval_steps_per_second": 36.889, "step": 2671200 }, { "epoch": 0.0, "learning_rate": 6.257718511258462e-06, "loss": 3.837, "step": 2671616 }, { "epoch": 0.0, "learning_rate": 6.249332563747942e-06, "loss": 3.8373, "step": 2672128 }, { "epoch": 0.0, "learning_rate": 6.240946616237423e-06, "loss": 3.8504, "step": 2672640 }, { "epoch": 0.0, "learning_rate": 6.232560668726902e-06, "loss": 3.8376, "step": 2673152 }, { "epoch": 0.0, "learning_rate": 6.224174721216382e-06, "loss": 3.8656, "step": 2673664 }, { "epoch": 0.0, "learning_rate": 6.215788773705862e-06, "loss": 3.8337, "step": 2674176 }, { "epoch": 0.0, "learning_rate": 6.207402826195342e-06, "loss": 3.8409, "step": 2674688 }, { "epoch": 0.0, "learning_rate": 6.199016878684822e-06, "loss": 3.8312, "step": 2675200 }, { "epoch": 0.0, "learning_rate": 6.190630931174302e-06, "loss": 3.8481, "step": 2675712 }, { "epoch": 0.0, "learning_rate": 6.182244983663781e-06, "loss": 3.8466, "step": 2676224 }, { "epoch": 0.0, "learning_rate": 6.173859036153262e-06, "loss": 3.84, "step": 2676736 }, { "epoch": 0.0, "learning_rate": 6.165473088642741e-06, "loss": 3.8448, "step": 2677248 }, { "epoch": 0.0, "learning_rate": 6.157103519935952e-06, "loss": 3.8336, "step": 2677760 }, { "epoch": 0.0, "learning_rate": 6.148717572425432e-06, "loss": 3.8379, "step": 2678272 }, { "epoch": 0.0, "learning_rate": 6.140331624914913e-06, "loss": 3.8405, "step": 2678784 }, { "epoch": 0.0, "learning_rate": 6.131945677404392e-06, "loss": 3.8387, "step": 2679296 }, { "epoch": 0.0, "learning_rate": 6.123576108697604e-06, "loss": 3.8365, "step": 2679808 }, { "epoch": 0.0, "learning_rate": 6.115190161187084e-06, "loss": 3.842, "step": 2680320 }, { "epoch": 0.0, "learning_rate": 6.106804213676563e-06, "loss": 3.8423, "step": 2680832 }, { "epoch": 0.0, "learning_rate": 6.098418266166044e-06, "loss": 3.8568, "step": 2681344 }, { "epoch": 0.0, "learning_rate": 6.090032318655523e-06, "loss": 3.8394, "step": 2681856 }, { "epoch": 0.0, "learning_rate": 6.081646371145004e-06, "loss": 3.8439, "step": 2682368 }, { "epoch": 0.0, "learning_rate": 6.0732768024382145e-06, "loss": 3.8455, "step": 2682880 }, { "epoch": 0.0, "learning_rate": 6.0648908549276944e-06, "loss": 3.8528, "step": 2683392 }, { "epoch": 0.0, "learning_rate": 6.056504907417174e-06, "loss": 3.8351, "step": 2683904 }, { "epoch": 0.0, "learning_rate": 6.048118959906654e-06, "loss": 3.8477, "step": 2684416 }, { "epoch": 0.0, "learning_rate": 6.039749391199866e-06, "loss": 3.8362, "step": 2684928 }, { "epoch": 0.0, "learning_rate": 6.031363443689345e-06, "loss": 3.8424, "step": 2685440 }, { "epoch": 0.0, "learning_rate": 6.022977496178826e-06, "loss": 3.8288, "step": 2685952 }, { "epoch": 0.01, "learning_rate": 6.014591548668305e-06, "loss": 3.8403, "step": 2686464 }, { "epoch": 0.01, "learning_rate": 6.006205601157785e-06, "loss": 3.8376, "step": 2686976 }, { "epoch": 0.01, "learning_rate": 5.997819653647265e-06, "loss": 3.8469, "step": 2687488 }, { "epoch": 0.01, "learning_rate": 5.989433706136745e-06, "loss": 3.8457, "step": 2688000 }, { "epoch": 0.01, "learning_rate": 5.981047758626225e-06, "loss": 3.8525, "step": 2688512 }, { "epoch": 0.01, "learning_rate": 5.972661811115705e-06, "loss": 3.8435, "step": 2689024 }, { "epoch": 0.01, "learning_rate": 5.964292242408916e-06, "loss": 3.8481, "step": 2689536 }, { "epoch": 0.01, "learning_rate": 5.955906294898396e-06, "loss": 3.839, "step": 2690048 }, { "epoch": 0.01, "learning_rate": 5.9475203473878755e-06, "loss": 3.8463, "step": 2690560 }, { "epoch": 0.01, "learning_rate": 5.939134399877356e-06, "loss": 3.8324, "step": 2691072 }, { "epoch": 0.01, "learning_rate": 5.930764831170567e-06, "loss": 3.8392, "step": 2691584 }, { "epoch": 0.01, "learning_rate": 5.922378883660047e-06, "loss": 3.8431, "step": 2692096 }, { "epoch": 0.01, "learning_rate": 5.913992936149527e-06, "loss": 3.8528, "step": 2692608 }, { "epoch": 0.01, "learning_rate": 5.905606988639007e-06, "loss": 3.8405, "step": 2693120 }, { "epoch": 0.01, "learning_rate": 5.897221041128487e-06, "loss": 3.8423, "step": 2693632 }, { "epoch": 0.01, "learning_rate": 5.888835093617966e-06, "loss": 3.8505, "step": 2694144 }, { "epoch": 0.01, "learning_rate": 5.880449146107447e-06, "loss": 3.8459, "step": 2694656 }, { "epoch": 0.01, "learning_rate": 5.872063198596926e-06, "loss": 3.8479, "step": 2695168 }, { "epoch": 0.01, "learning_rate": 5.863710008693869e-06, "loss": 3.8354, "step": 2695680 }, { "epoch": 0.01, "learning_rate": 5.855324061183349e-06, "loss": 3.8206, "step": 2696192 }, { "epoch": 0.01, "learning_rate": 5.846938113672829e-06, "loss": 3.8478, "step": 2696704 }, { "epoch": 0.01, "learning_rate": 5.838552166162309e-06, "loss": 3.8434, "step": 2697216 }, { "epoch": 0.01, "learning_rate": 5.830166218651789e-06, "loss": 3.8355, "step": 2697728 }, { "epoch": 0.01, "learning_rate": 5.821780271141269e-06, "loss": 3.8292, "step": 2698240 }, { "epoch": 0.01, "learning_rate": 5.813410702434481e-06, "loss": 3.8302, "step": 2698752 }, { "epoch": 0.01, "learning_rate": 5.80502475492396e-06, "loss": 3.8262, "step": 2699264 }, { "epoch": 0.01, "learning_rate": 5.79663880741344e-06, "loss": 3.8471, "step": 2699776 }, { "epoch": 0.01, "learning_rate": 5.78825285990292e-06, "loss": 3.8311, "step": 2700288 }, { "epoch": 0.01, "learning_rate": 5.7798669123924e-06, "loss": 3.8391, "step": 2700800 }, { "epoch": 0.01, "learning_rate": 5.771497343685611e-06, "loss": 3.8466, "step": 2701312 }, { "epoch": 0.01, "learning_rate": 5.763111396175091e-06, "loss": 3.8329, "step": 2701824 }, { "epoch": 0.01, "learning_rate": 5.754725448664571e-06, "loss": 3.8338, "step": 2702336 }, { "epoch": 0.01, "learning_rate": 5.746339501154051e-06, "loss": 3.8396, "step": 2702848 }, { "epoch": 0.01, "learning_rate": 5.73795355364353e-06, "loss": 3.8205, "step": 2703360 }, { "epoch": 0.01, "learning_rate": 5.729583984936742e-06, "loss": 3.8374, "step": 2703872 }, { "epoch": 0.01, "learning_rate": 5.721198037426222e-06, "loss": 3.8417, "step": 2704384 }, { "epoch": 0.01, "learning_rate": 5.712812089915702e-06, "loss": 3.845, "step": 2704896 }, { "epoch": 0.01, "learning_rate": 5.704426142405182e-06, "loss": 3.8262, "step": 2705408 }, { "epoch": 0.01, "learning_rate": 5.696040194894662e-06, "loss": 3.8333, "step": 2705920 }, { "epoch": 0.01, "learning_rate": 5.687654247384142e-06, "loss": 3.8267, "step": 2706432 }, { "epoch": 0.01, "learning_rate": 5.679284678677353e-06, "loss": 3.8468, "step": 2706944 }, { "epoch": 0.01, "learning_rate": 5.670898731166832e-06, "loss": 3.8425, "step": 2707456 }, { "epoch": 0.01, "learning_rate": 5.662512783656312e-06, "loss": 3.8449, "step": 2707968 }, { "epoch": 0.01, "learning_rate": 5.654126836145793e-06, "loss": 3.8531, "step": 2708480 }, { "epoch": 0.01, "learning_rate": 5.645740888635272e-06, "loss": 3.8545, "step": 2708992 }, { "epoch": 0.01, "learning_rate": 5.637354941124753e-06, "loss": 3.857, "step": 2709504 }, { "epoch": 0.01, "learning_rate": 5.628985372417964e-06, "loss": 3.8365, "step": 2710016 }, { "epoch": 0.01, "learning_rate": 5.620599424907444e-06, "loss": 3.8447, "step": 2710528 }, { "epoch": 0.01, "learning_rate": 5.612213477396924e-06, "loss": 3.8471, "step": 2711040 }, { "epoch": 0.01, "learning_rate": 5.603827529886403e-06, "loss": 3.8405, "step": 2711552 }, { "epoch": 0.01, "learning_rate": 5.595441582375884e-06, "loss": 3.8461, "step": 2712064 }, { "epoch": 0.01, "learning_rate": 5.5870720136690945e-06, "loss": 3.8398, "step": 2712576 }, { "epoch": 0.01, "learning_rate": 5.5786860661585744e-06, "loss": 3.8482, "step": 2713088 }, { "epoch": 0.01, "learning_rate": 5.570300118648054e-06, "loss": 3.8447, "step": 2713600 }, { "epoch": 0.01, "learning_rate": 5.561914171137534e-06, "loss": 3.8293, "step": 2714112 }, { "epoch": 0.01, "learning_rate": 5.553544602430746e-06, "loss": 3.836, "step": 2714624 }, { "epoch": 0.01, "learning_rate": 5.545158654920226e-06, "loss": 3.8453, "step": 2715136 }, { "epoch": 0.01, "learning_rate": 5.536772707409706e-06, "loss": 3.8476, "step": 2715648 }, { "epoch": 0.01, "learning_rate": 5.528386759899185e-06, "loss": 3.8412, "step": 2716160 }, { "epoch": 0.01, "learning_rate": 5.520017191192397e-06, "loss": 3.8379, "step": 2716672 }, { "epoch": 0.02, "learning_rate": 5.511631243681877e-06, "loss": 3.8463, "step": 2717184 }, { "epoch": 0.02, "learning_rate": 5.5032452961713565e-06, "loss": 3.8334, "step": 2717696 }, { "epoch": 0.02, "learning_rate": 5.4948593486608365e-06, "loss": 3.8383, "step": 2718208 }, { "epoch": 0.02, "learning_rate": 5.4864734011503165e-06, "loss": 3.8415, "step": 2718720 }, { "epoch": 0.02, "learning_rate": 5.478103832443528e-06, "loss": 3.8485, "step": 2719232 }, { "epoch": 0.02, "learning_rate": 5.469717884933008e-06, "loss": 3.8508, "step": 2719744 }, { "epoch": 0.02, "learning_rate": 5.461331937422488e-06, "loss": 3.8425, "step": 2720256 }, { "epoch": 0.02, "learning_rate": 5.452945989911967e-06, "loss": 3.8289, "step": 2720768 }, { "epoch": 0.02, "learning_rate": 5.444560042401448e-06, "loss": 3.8504, "step": 2721280 }, { "epoch": 0.02, "learning_rate": 5.436174094890927e-06, "loss": 3.8342, "step": 2721792 }, { "epoch": 0.02, "learning_rate": 5.427788147380407e-06, "loss": 3.8563, "step": 2722304 }, { "epoch": 0.02, "learning_rate": 5.419402199869887e-06, "loss": 3.8474, "step": 2722816 }, { "epoch": 0.02, "learning_rate": 5.411016252359367e-06, "loss": 3.8436, "step": 2723328 }, { "epoch": 0.02, "learning_rate": 5.402630304848847e-06, "loss": 3.8405, "step": 2723840 }, { "epoch": 0.02, "learning_rate": 5.394260736142058e-06, "loss": 3.8512, "step": 2724352 }, { "epoch": 0.02, "learning_rate": 5.3858747886315384e-06, "loss": 3.828, "step": 2724864 }, { "epoch": 0.02, "learning_rate": 5.3774888411210175e-06, "loss": 3.8365, "step": 2725376 }, { "epoch": 0.02, "learning_rate": 5.3691028936104975e-06, "loss": 3.8334, "step": 2725888 }, { "epoch": 0.02, "learning_rate": 5.3607169460999775e-06, "loss": 3.841, "step": 2726400 }, { "epoch": 0.02, "learning_rate": 5.352330998589457e-06, "loss": 3.8306, "step": 2726912 }, { "epoch": 0.02, "learning_rate": 5.343945051078938e-06, "loss": 3.8361, "step": 2727424 }, { "epoch": 0.02, "learning_rate": 5.335559103568417e-06, "loss": 3.8349, "step": 2727936 }, { "epoch": 0.02, "learning_rate": 5.327189534861629e-06, "loss": 3.8344, "step": 2728448 }, { "epoch": 0.02, "learning_rate": 5.318803587351109e-06, "loss": 3.837, "step": 2728960 }, { "epoch": 0.02, "learning_rate": 5.310450397448051e-06, "loss": 3.8316, "step": 2729472 }, { "epoch": 0.02, "learning_rate": 5.302064449937531e-06, "loss": 3.8501, "step": 2729984 }, { "epoch": 0.02, "learning_rate": 5.293678502427011e-06, "loss": 3.8452, "step": 2730496 }, { "epoch": 0.02, "learning_rate": 5.285292554916491e-06, "loss": 3.8468, "step": 2731008 }, { "epoch": 0.02, "learning_rate": 5.276906607405971e-06, "loss": 3.8358, "step": 2731520 }, { "epoch": 0.02, "learning_rate": 5.268520659895451e-06, "loss": 3.848, "step": 2732032 }, { "epoch": 0.02, "learning_rate": 5.260151091188662e-06, "loss": 3.8484, "step": 2732544 }, { "epoch": 0.02, "learning_rate": 5.251765143678143e-06, "loss": 3.8349, "step": 2733056 }, { "epoch": 0.02, "learning_rate": 5.243379196167622e-06, "loss": 3.8494, "step": 2733568 }, { "epoch": 0.02, "learning_rate": 5.234993248657103e-06, "loss": 3.8368, "step": 2734080 }, { "epoch": 0.02, "learning_rate": 5.226607301146582e-06, "loss": 3.8464, "step": 2734592 }, { "epoch": 0.02, "learning_rate": 5.218221353636062e-06, "loss": 3.8327, "step": 2735104 }, { "epoch": 0.02, "learning_rate": 5.209835406125542e-06, "loss": 3.8427, "step": 2735616 }, { "epoch": 0.02, "learning_rate": 5.201449458615022e-06, "loss": 3.8252, "step": 2736128 }, { "epoch": 0.02, "learning_rate": 5.193079889908233e-06, "loss": 3.835, "step": 2736640 }, { "epoch": 0.02, "learning_rate": 5.184726700005177e-06, "loss": 3.8305, "step": 2737152 }, { "epoch": 0.02, "learning_rate": 5.176340752494656e-06, "loss": 3.8487, "step": 2737664 }, { "epoch": 0.02, "learning_rate": 5.167954804984136e-06, "loss": 3.8424, "step": 2738176 }, { "epoch": 0.02, "learning_rate": 5.159568857473616e-06, "loss": 3.8474, "step": 2738688 }, { "epoch": 0.02, "learning_rate": 5.151182909963096e-06, "loss": 3.8387, "step": 2739200 }, { "epoch": 0.02, "learning_rate": 5.1427969624525755e-06, "loss": 3.8457, "step": 2739712 }, { "epoch": 0.02, "learning_rate": 5.1344110149420555e-06, "loss": 3.8535, "step": 2740224 }, { "epoch": 0.02, "learning_rate": 5.126025067431535e-06, "loss": 3.8438, "step": 2740736 }, { "epoch": 0.02, "learning_rate": 5.117639119921015e-06, "loss": 3.8422, "step": 2741248 }, { "epoch": 0.02, "learning_rate": 5.1092531724104945e-06, "loss": 3.8503, "step": 2741760 }, { "epoch": 0.02, "learning_rate": 5.100867224899975e-06, "loss": 3.8406, "step": 2742272 }, { "epoch": 0.02, "learning_rate": 5.0924812773894544e-06, "loss": 3.8519, "step": 2742784 }, { "epoch": 0.02, "learning_rate": 5.084095329878934e-06, "loss": 3.8345, "step": 2743296 }, { "epoch": 0.02, "learning_rate": 5.075709382368414e-06, "loss": 3.8455, "step": 2743808 }, { "epoch": 0.02, "learning_rate": 5.067323434857894e-06, "loss": 3.8413, "step": 2744320 }, { "epoch": 0.02, "learning_rate": 5.0589866237585684e-06, "loss": 3.8409, "step": 2744832 }, { "epoch": 0.02, "learning_rate": 5.050600676248049e-06, "loss": 3.8446, "step": 2745344 }, { "epoch": 0.02, "learning_rate": 5.042214728737528e-06, "loss": 3.8411, "step": 2745856 }, { "epoch": 0.02, "learning_rate": 5.033828781227008e-06, "loss": 3.8405, "step": 2746368 }, { "epoch": 0.02, "learning_rate": 5.025442833716488e-06, "loss": 3.8378, "step": 2746880 }, { "epoch": 0.02, "learning_rate": 5.017056886205968e-06, "loss": 3.8421, "step": 2747392 }, { "epoch": 0.03, "eval_loss": 3.9717962741851807, "eval_runtime": 292.4939, "eval_samples_per_second": 1304.612, "eval_steps_per_second": 40.77, "step": 2747520 }, { "epoch": 1.0, "learning_rate": 5.008670938695448e-06, "loss": 3.8367, "step": 2747904 }, { "epoch": 1.0, "learning_rate": 5.000284991184928e-06, "loss": 3.8338, "step": 2748416 }, { "epoch": 1.0, "learning_rate": 4.991899043674408e-06, "loss": 3.8478, "step": 2748928 }, { "epoch": 1.0, "learning_rate": 4.98352947496762e-06, "loss": 3.8351, "step": 2749440 }, { "epoch": 1.0, "learning_rate": 4.975143527457099e-06, "loss": 3.8593, "step": 2749952 }, { "epoch": 1.0, "learning_rate": 4.96675757994658e-06, "loss": 3.8395, "step": 2750464 }, { "epoch": 1.0, "learning_rate": 4.958371632436059e-06, "loss": 3.8366, "step": 2750976 }, { "epoch": 1.0, "learning_rate": 4.9499856849255396e-06, "loss": 3.8257, "step": 2751488 }, { "epoch": 1.0, "learning_rate": 4.941599737415019e-06, "loss": 3.8429, "step": 2752000 }, { "epoch": 1.0, "learning_rate": 4.933213789904499e-06, "loss": 3.8467, "step": 2752512 }, { "epoch": 1.0, "learning_rate": 4.9248278423939786e-06, "loss": 3.8369, "step": 2753024 }, { "epoch": 1.0, "learning_rate": 4.9164418948834585e-06, "loss": 3.8399, "step": 2753536 }, { "epoch": 1.0, "learning_rate": 4.908088704980401e-06, "loss": 3.8355, "step": 2754048 }, { "epoch": 1.0, "learning_rate": 4.899702757469881e-06, "loss": 3.836, "step": 2754560 }, { "epoch": 1.0, "learning_rate": 4.891316809959362e-06, "loss": 3.8394, "step": 2755072 }, { "epoch": 1.0, "learning_rate": 4.882930862448841e-06, "loss": 3.8332, "step": 2755584 }, { "epoch": 1.0, "learning_rate": 4.8745612937420525e-06, "loss": 3.8342, "step": 2756096 }, { "epoch": 1.0, "learning_rate": 4.8661753462315325e-06, "loss": 3.8403, "step": 2756608 }, { "epoch": 1.0, "learning_rate": 4.857789398721012e-06, "loss": 3.8367, "step": 2757120 }, { "epoch": 1.0, "learning_rate": 4.849403451210492e-06, "loss": 3.8515, "step": 2757632 }, { "epoch": 1.0, "learning_rate": 4.8410175036999715e-06, "loss": 3.8422, "step": 2758144 }, { "epoch": 1.0, "learning_rate": 4.832631556189452e-06, "loss": 3.8438, "step": 2758656 }, { "epoch": 1.0, "learning_rate": 4.824245608678931e-06, "loss": 3.8421, "step": 2759168 }, { "epoch": 1.0, "learning_rate": 4.815859661168411e-06, "loss": 3.8498, "step": 2759680 }, { "epoch": 1.0, "learning_rate": 4.807490092461623e-06, "loss": 3.8336, "step": 2760192 }, { "epoch": 1.0, "learning_rate": 4.799104144951103e-06, "loss": 3.8441, "step": 2760704 }, { "epoch": 1.0, "learning_rate": 4.790718197440583e-06, "loss": 3.8373, "step": 2761216 }, { "epoch": 1.0, "learning_rate": 4.782332249930063e-06, "loss": 3.8354, "step": 2761728 }, { "epoch": 1.0, "learning_rate": 4.773946302419543e-06, "loss": 3.8279, "step": 2762240 }, { "epoch": 1.0, "learning_rate": 4.765560354909023e-06, "loss": 3.8375, "step": 2762752 }, { "epoch": 1.01, "learning_rate": 4.757190786202234e-06, "loss": 3.8415, "step": 2763264 }, { "epoch": 1.01, "learning_rate": 4.7488048386917135e-06, "loss": 3.8438, "step": 2763776 }, { "epoch": 1.01, "learning_rate": 4.7404188911811935e-06, "loss": 3.8455, "step": 2764288 }, { "epoch": 1.01, "learning_rate": 4.732032943670673e-06, "loss": 3.8488, "step": 2764800 }, { "epoch": 1.01, "learning_rate": 4.723646996160153e-06, "loss": 3.8396, "step": 2765312 }, { "epoch": 1.01, "learning_rate": 4.715261048649633e-06, "loss": 3.8436, "step": 2765824 }, { "epoch": 1.01, "learning_rate": 4.706891479942845e-06, "loss": 3.839, "step": 2766336 }, { "epoch": 1.01, "learning_rate": 4.698505532432325e-06, "loss": 3.8415, "step": 2766848 }, { "epoch": 1.01, "learning_rate": 4.690135963725536e-06, "loss": 3.8329, "step": 2767360 }, { "epoch": 1.01, "learning_rate": 4.6817500162150165e-06, "loss": 3.8393, "step": 2767872 }, { "epoch": 1.01, "learning_rate": 4.673364068704496e-06, "loss": 3.8405, "step": 2768384 }, { "epoch": 1.01, "learning_rate": 4.664978121193976e-06, "loss": 3.8474, "step": 2768896 }, { "epoch": 1.01, "learning_rate": 4.6565921736834555e-06, "loss": 3.8392, "step": 2769408 }, { "epoch": 1.01, "learning_rate": 4.6482062261729355e-06, "loss": 3.8389, "step": 2769920 }, { "epoch": 1.01, "learning_rate": 4.6398202786624154e-06, "loss": 3.8501, "step": 2770432 }, { "epoch": 1.01, "learning_rate": 4.631434331151895e-06, "loss": 3.8392, "step": 2770944 }, { "epoch": 1.01, "learning_rate": 4.6230483836413745e-06, "loss": 3.8435, "step": 2771456 }, { "epoch": 1.01, "learning_rate": 4.614662436130855e-06, "loss": 3.8311, "step": 2771968 }, { "epoch": 1.01, "learning_rate": 4.606276488620334e-06, "loss": 3.8198, "step": 2772480 }, { "epoch": 1.01, "learning_rate": 4.597923298717278e-06, "loss": 3.8474, "step": 2772992 }, { "epoch": 1.01, "learning_rate": 4.589537351206758e-06, "loss": 3.8424, "step": 2773504 }, { "epoch": 1.01, "learning_rate": 4.581151403696238e-06, "loss": 3.8359, "step": 2774016 }, { "epoch": 1.01, "learning_rate": 4.572765456185718e-06, "loss": 3.8231, "step": 2774528 }, { "epoch": 1.01, "learning_rate": 4.5643795086751976e-06, "loss": 3.8309, "step": 2775040 }, { "epoch": 1.01, "learning_rate": 4.5559935611646775e-06, "loss": 3.823, "step": 2775552 }, { "epoch": 1.01, "learning_rate": 4.547607613654157e-06, "loss": 3.8452, "step": 2776064 }, { "epoch": 1.01, "learning_rate": 4.5392216661436374e-06, "loss": 3.8301, "step": 2776576 }, { "epoch": 1.01, "learning_rate": 4.5308357186331165e-06, "loss": 3.8351, "step": 2777088 }, { "epoch": 1.01, "learning_rate": 4.522449771122597e-06, "loss": 3.845, "step": 2777600 }, { "epoch": 1.01, "learning_rate": 4.5140638236120765e-06, "loss": 3.8297, "step": 2778112 }, { "epoch": 1.01, "learning_rate": 4.505677876101556e-06, "loss": 3.8321, "step": 2778624 }, { "epoch": 1.01, "learning_rate": 4.497308307394768e-06, "loss": 3.8416, "step": 2779136 }, { "epoch": 1.01, "learning_rate": 4.48893873868798e-06, "loss": 3.8161, "step": 2779648 }, { "epoch": 1.01, "learning_rate": 4.48055279117746e-06, "loss": 3.8339, "step": 2780160 }, { "epoch": 1.01, "learning_rate": 4.472166843666939e-06, "loss": 3.8357, "step": 2780672 }, { "epoch": 1.01, "learning_rate": 4.4637808961564195e-06, "loss": 3.8454, "step": 2781184 }, { "epoch": 1.01, "learning_rate": 4.455394948645899e-06, "loss": 3.8245, "step": 2781696 }, { "epoch": 1.01, "learning_rate": 4.4470090011353795e-06, "loss": 3.8313, "step": 2782208 }, { "epoch": 1.01, "learning_rate": 4.4386230536248586e-06, "loss": 3.8223, "step": 2782720 }, { "epoch": 1.01, "learning_rate": 4.4302371061143385e-06, "loss": 3.8466, "step": 2783232 }, { "epoch": 1.01, "learning_rate": 4.42186753740755e-06, "loss": 3.8405, "step": 2783744 }, { "epoch": 1.01, "learning_rate": 4.41348158989703e-06, "loss": 3.8399, "step": 2784256 }, { "epoch": 1.01, "learning_rate": 4.40509564238651e-06, "loss": 3.8532, "step": 2784768 }, { "epoch": 1.01, "learning_rate": 4.396726073679721e-06, "loss": 3.8469, "step": 2785280 }, { "epoch": 1.01, "learning_rate": 4.388340126169202e-06, "loss": 3.8606, "step": 2785792 }, { "epoch": 1.01, "learning_rate": 4.3799705574624125e-06, "loss": 3.8344, "step": 2786304 }, { "epoch": 1.01, "learning_rate": 4.371584609951892e-06, "loss": 3.84, "step": 2786816 }, { "epoch": 1.01, "learning_rate": 4.363198662441372e-06, "loss": 3.8456, "step": 2787328 }, { "epoch": 1.01, "learning_rate": 4.354812714930852e-06, "loss": 3.8351, "step": 2787840 }, { "epoch": 1.01, "learning_rate": 4.346426767420332e-06, "loss": 3.8454, "step": 2788352 }, { "epoch": 1.01, "learning_rate": 4.338040819909811e-06, "loss": 3.8361, "step": 2788864 }, { "epoch": 1.01, "learning_rate": 4.329654872399292e-06, "loss": 3.846, "step": 2789376 }, { "epoch": 1.01, "learning_rate": 4.321268924888771e-06, "loss": 3.841, "step": 2789888 }, { "epoch": 1.01, "learning_rate": 4.312882977378252e-06, "loss": 3.8273, "step": 2790400 }, { "epoch": 1.01, "learning_rate": 4.304497029867731e-06, "loss": 3.8393, "step": 2790912 }, { "epoch": 1.01, "learning_rate": 4.296127461160943e-06, "loss": 3.8303, "step": 2791424 }, { "epoch": 1.01, "learning_rate": 4.287741513650423e-06, "loss": 3.8462, "step": 2791936 }, { "epoch": 1.01, "learning_rate": 4.279355566139903e-06, "loss": 3.8417, "step": 2792448 }, { "epoch": 1.01, "learning_rate": 4.270969618629383e-06, "loss": 3.8346, "step": 2792960 }, { "epoch": 1.02, "learning_rate": 4.262583671118863e-06, "loss": 3.8435, "step": 2793472 }, { "epoch": 1.02, "learning_rate": 4.254214102412074e-06, "loss": 3.8365, "step": 2793984 }, { "epoch": 1.02, "learning_rate": 4.245828154901553e-06, "loss": 3.8325, "step": 2794496 }, { "epoch": 1.02, "learning_rate": 4.237442207391033e-06, "loss": 3.8377, "step": 2795008 }, { "epoch": 1.02, "learning_rate": 4.229056259880513e-06, "loss": 3.85, "step": 2795520 }, { "epoch": 1.02, "learning_rate": 4.220670312369993e-06, "loss": 3.8475, "step": 2796032 }, { "epoch": 1.02, "learning_rate": 4.212284364859473e-06, "loss": 3.8421, "step": 2796544 }, { "epoch": 1.02, "learning_rate": 4.203898417348953e-06, "loss": 3.8257, "step": 2797056 }, { "epoch": 1.02, "learning_rate": 4.195512469838433e-06, "loss": 3.8441, "step": 2797568 }, { "epoch": 1.02, "learning_rate": 4.187126522327913e-06, "loss": 3.8324, "step": 2798080 }, { "epoch": 1.02, "learning_rate": 4.178756953621124e-06, "loss": 3.8515, "step": 2798592 }, { "epoch": 1.02, "learning_rate": 4.170371006110605e-06, "loss": 3.8474, "step": 2799104 }, { "epoch": 1.02, "learning_rate": 4.1620014374038155e-06, "loss": 3.8406, "step": 2799616 }, { "epoch": 1.02, "learning_rate": 4.1536154898932954e-06, "loss": 3.8378, "step": 2800128 }, { "epoch": 1.02, "learning_rate": 4.145245921186506e-06, "loss": 3.8518, "step": 2800640 }, { "epoch": 1.02, "learning_rate": 4.136859973675987e-06, "loss": 3.8235, "step": 2801152 }, { "epoch": 1.02, "learning_rate": 4.128474026165466e-06, "loss": 3.8352, "step": 2801664 }, { "epoch": 1.02, "learning_rate": 4.120088078654947e-06, "loss": 3.8289, "step": 2802176 }, { "epoch": 1.02, "learning_rate": 4.111702131144427e-06, "loss": 3.8431, "step": 2802688 }, { "epoch": 1.02, "learning_rate": 4.103316183633906e-06, "loss": 3.8242, "step": 2803200 }, { "epoch": 1.02, "learning_rate": 4.094930236123387e-06, "loss": 3.8351, "step": 2803712 }, { "epoch": 1.02, "learning_rate": 4.086544288612866e-06, "loss": 3.8329, "step": 2804224 }, { "epoch": 1.02, "learning_rate": 4.078158341102347e-06, "loss": 3.8333, "step": 2804736 }, { "epoch": 1.02, "learning_rate": 4.069772393591826e-06, "loss": 3.8341, "step": 2805248 }, { "epoch": 1.02, "learning_rate": 4.0614028248850375e-06, "loss": 3.8329, "step": 2805760 }, { "epoch": 1.02, "learning_rate": 4.0530168773745174e-06, "loss": 3.8476, "step": 2806272 }, { "epoch": 1.02, "learning_rate": 4.0446309298639965e-06, "loss": 3.843, "step": 2806784 }, { "epoch": 1.02, "learning_rate": 4.036244982353477e-06, "loss": 3.8422, "step": 2807296 }, { "epoch": 1.02, "learning_rate": 4.0278590348429564e-06, "loss": 3.8323, "step": 2807808 }, { "epoch": 1.02, "learning_rate": 4.019473087332437e-06, "loss": 3.8478, "step": 2808320 }, { "epoch": 1.02, "learning_rate": 4.011087139821916e-06, "loss": 3.8398, "step": 2808832 }, { "epoch": 1.02, "learning_rate": 4.002701192311396e-06, "loss": 3.8333, "step": 2809344 }, { "epoch": 1.02, "learning_rate": 3.994331623604608e-06, "loss": 3.8499, "step": 2809856 }, { "epoch": 1.02, "learning_rate": 3.985945676094088e-06, "loss": 3.8334, "step": 2810368 }, { "epoch": 1.02, "learning_rate": 3.977559728583568e-06, "loss": 3.8424, "step": 2810880 }, { "epoch": 1.02, "learning_rate": 3.969173781073048e-06, "loss": 3.8313, "step": 2811392 }, { "epoch": 1.02, "learning_rate": 3.9608042123662595e-06, "loss": 3.8425, "step": 2811904 }, { "epoch": 1.02, "learning_rate": 3.9524182648557386e-06, "loss": 3.828, "step": 2812416 }, { "epoch": 1.02, "learning_rate": 3.94404869614895e-06, "loss": 3.8304, "step": 2812928 }, { "epoch": 1.02, "learning_rate": 3.935679127442162e-06, "loss": 3.832, "step": 2813440 }, { "epoch": 1.02, "learning_rate": 3.927293179931642e-06, "loss": 3.8445, "step": 2813952 }, { "epoch": 1.02, "learning_rate": 3.918907232421122e-06, "loss": 3.8389, "step": 2814464 }, { "epoch": 1.02, "learning_rate": 3.910521284910602e-06, "loss": 3.8435, "step": 2814976 }, { "epoch": 1.02, "learning_rate": 3.902135337400082e-06, "loss": 3.8332, "step": 2815488 }, { "epoch": 1.02, "learning_rate": 3.893749389889561e-06, "loss": 3.8447, "step": 2816000 }, { "epoch": 1.02, "learning_rate": 3.8853634423790416e-06, "loss": 3.8506, "step": 2816512 }, { "epoch": 1.02, "learning_rate": 3.876977494868521e-06, "loss": 3.84, "step": 2817024 }, { "epoch": 1.02, "learning_rate": 3.8685915473580015e-06, "loss": 3.8395, "step": 2817536 }, { "epoch": 1.02, "learning_rate": 3.860205599847481e-06, "loss": 3.8454, "step": 2818048 }, { "epoch": 1.02, "learning_rate": 3.8518196523369606e-06, "loss": 3.8406, "step": 2818560 }, { "epoch": 1.02, "learning_rate": 3.843450083630172e-06, "loss": 3.8511, "step": 2819072 }, { "epoch": 1.02, "learning_rate": 3.835080514923384e-06, "loss": 3.8335, "step": 2819584 }, { "epoch": 1.02, "learning_rate": 3.826694567412863e-06, "loss": 3.8426, "step": 2820096 }, { "epoch": 1.02, "learning_rate": 3.818308619902343e-06, "loss": 3.8361, "step": 2820608 }, { "epoch": 1.02, "learning_rate": 3.8099226723918233e-06, "loss": 3.8404, "step": 2821120 }, { "epoch": 1.02, "learning_rate": 3.801536724881303e-06, "loss": 3.84, "step": 2821632 }, { "epoch": 1.02, "learning_rate": 3.793150777370783e-06, "loss": 3.8375, "step": 2822144 }, { "epoch": 1.02, "learning_rate": 3.7847648298602627e-06, "loss": 3.8413, "step": 2822656 }, { "epoch": 1.02, "learning_rate": 3.7763952611534744e-06, "loss": 3.8329, "step": 2823168 }, { "epoch": 1.02, "learning_rate": 3.768009313642954e-06, "loss": 3.8447, "step": 2823680 }, { "epoch": 1.03, "eval_loss": 3.971170425415039, "eval_runtime": 295.0088, "eval_samples_per_second": 1293.49, "eval_steps_per_second": 40.423, "step": 2823840 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.1657855111792026e+18, "trial_name": null, "trial_params": null }