{ "best_metric": 4.262835502624512, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/2/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "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": 10.8193, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5543, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0616, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.992, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9441, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.899, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.7351, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.6336, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.5381, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4683, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.4032, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 6.3381, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 6.2653, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 6.2021, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 6.1498, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 6.0901, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986582483983168e-05, "loss": 6.0446, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985743889232116e-05, "loss": 6.0028, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984905294481064e-05, "loss": 5.9639, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984066699730012e-05, "loss": 5.9241, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8872, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.8426, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.8187, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.980713958606178e-05, "loss": 5.7808, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.979875363855125e-05, "loss": 5.7581, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.979036769104073e-05, "loss": 5.7278, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.978198174353021e-05, "loss": 5.7038, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.977359579601969e-05, "loss": 5.6725, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6474, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6292, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.6027, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.5956, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5646, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 5.5562, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5465, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5251, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5112, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.4767, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4702, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4476, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4426, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4255, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.415, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.3848, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.3956, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.3822, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 5.3739, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960595873982795e-05, "loss": 5.3612, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959757279231743e-05, "loss": 5.3349, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 5.3263, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3295, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3142, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956404538107908e-05, "loss": 5.3019, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955565943356856e-05, "loss": 5.2764, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.2786, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953890391735125e-05, "loss": 5.2646, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530517969840727e-05, "loss": 5.2896, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522132022330207e-05, "loss": 5.2425, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.9513746074819686e-05, "loss": 5.2471, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.95053765061129e-05, "loss": 5.2424, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949699055860238e-05, "loss": 5.2219, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 5.2232, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 5.2088, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.1916, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.1906, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2071, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944669125234299e-05, "loss": 5.1811, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943830530483247e-05, "loss": 5.1708, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942991935732195e-05, "loss": 5.1554, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942154978861516e-05, "loss": 5.1558, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941316384110464e-05, "loss": 5.1654, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940477789359412e-05, "loss": 5.1608, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.93963919460836e-05, "loss": 5.1476, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.938800599857309e-05, "loss": 5.1548, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.937962005106256e-05, "loss": 5.148, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.937123410355204e-05, "loss": 5.1352, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1163, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.1067, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.934609263982421e-05, "loss": 5.1025, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933770669231369e-05, "loss": 5.0968, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329337123606905e-05, "loss": 5.0923, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932095117609638e-05, "loss": 5.089, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931256522858586e-05, "loss": 5.091, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930417928107534e-05, "loss": 5.0825, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295809712368554e-05, "loss": 5.0565, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287423764858034e-05, "loss": 5.0518, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279037817347514e-05, "loss": 5.0616, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.9270651869836994e-05, "loss": 5.0631, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.9262265922326474e-05, "loss": 5.0383, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925391273242342e-05, "loss": 5.0412, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.92455267849129e-05, "loss": 5.0429, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923714083740238e-05, "loss": 5.0267, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922875488989185e-05, "loss": 5.0215, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.0202, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 5.0097, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 5.015, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 5.0025, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 4.9886, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 4.9864, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917006963612195e-05, "loss": 4.9864, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.9828, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.9831, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.972, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136542224883596e-05, "loss": 4.9688, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128156277373076e-05, "loss": 4.9604, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119770329862556e-05, "loss": 4.9426, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111384382352036e-05, "loss": 4.9462, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9102998434841516e-05, "loss": 4.9449, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.9409, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.9324, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.928, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.9199, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.9217, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905271550738586e-05, "loss": 4.9156, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.9154, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903594361236482e-05, "loss": 4.9069, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.90275576648543e-05, "loss": 4.9064, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901917171734378e-05, "loss": 4.9076, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901078576983326e-05, "loss": 4.8975, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.9042, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.9037, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.8883, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.8915, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.8776, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.8823, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952116894867085e-05, "loss": 4.8567, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943730947356565e-05, "loss": 4.8707, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.856, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8571, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8391, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8717, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.8579, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.8446, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.8432, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.8387, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.8491, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.8418, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.8309, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884314871364151e-05, "loss": 4.8359, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.8208, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.8312, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.8138, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.8154, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.8145, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.8029, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87844634598716e-05, "loss": 4.8047, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877607751236109e-05, "loss": 4.8053, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.7996, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.8048, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.7933, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.754898548126221, "eval_runtime": 309.1681, "eval_samples_per_second": 1234.251, "eval_steps_per_second": 38.571, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.7814, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.7767, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.7931, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.7761, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.7932, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.7633, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.7753, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683864847352826e-05, "loss": 4.7527, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867549527864604e-05, "loss": 4.7658, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866710933113552e-05, "loss": 4.7626, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658723383625e-05, "loss": 4.7686, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865033743611448e-05, "loss": 4.7627, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864195148860396e-05, "loss": 4.745, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863358191989717e-05, "loss": 4.7478, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.7408, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.7367, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.7466, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.741, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.7365, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.7523, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.7268, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.7363, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.7288, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.7394, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541369254888915e-05, "loss": 4.7137, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.7218, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.7132, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.7214, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.7004, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.705, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.8491069948629524e-05, "loss": 4.7142, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.8482684001119e-05, "loss": 4.7064, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847429805360848e-05, "loss": 4.7057, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.8465912106097964e-05, "loss": 4.7123, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845754253739117e-05, "loss": 4.7031, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.705, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.6856, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.6966, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.6815, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.6906, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840724323113178e-05, "loss": 4.6868, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839885728362126e-05, "loss": 4.6849, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839047133611074e-05, "loss": 4.6689, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838208538860022e-05, "loss": 4.6862, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.6845, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.6779, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.6828, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.6531, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834017202985136e-05, "loss": 4.654, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.6742, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.6618, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.6604, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.6416, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298258671102486e-05, "loss": 4.6459, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289872723591966e-05, "loss": 4.6421, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281486776081446e-05, "loss": 4.6687, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273133586178384e-05, "loss": 4.6373, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826474763866787e-05, "loss": 4.6456, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825636169115735e-05, "loss": 4.6503, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824797574364683e-05, "loss": 4.6326, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823958979613631e-05, "loss": 4.6383, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.6319, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.6226, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821444833240848e-05, "loss": 4.6279, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820606238489796e-05, "loss": 4.6418, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819767643738744e-05, "loss": 4.6304, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818929048987692e-05, "loss": 4.6187, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.81809045423664e-05, "loss": 4.6175, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817251859485588e-05, "loss": 4.6183, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816413264734535e-05, "loss": 4.6349, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815574669983483e-05, "loss": 4.635, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814736075232432e-05, "loss": 4.6248, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.81389748048138e-05, "loss": 4.6375, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813058885730328e-05, "loss": 4.6347, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812221928859649e-05, "loss": 4.6309, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811383334108597e-05, "loss": 4.6155, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810544739357545e-05, "loss": 4.6147, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809706144606493e-05, "loss": 4.6113, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808869187735814e-05, "loss": 4.6106, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808030592984762e-05, "loss": 4.6059, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.80719199823371e-05, "loss": 4.6109, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063550413630307e-05, "loss": 4.6181, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055164466119786e-05, "loss": 4.6069, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804677851860927e-05, "loss": 4.5921, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803839257109875e-05, "loss": 4.5936, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803000662358823e-05, "loss": 4.5985, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802162067607771e-05, "loss": 4.6111, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801323472856719e-05, "loss": 4.5916, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800484878105667e-05, "loss": 4.5977, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799646283354615e-05, "loss": 4.6004, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798809326483936e-05, "loss": 4.5921, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797970731732884e-05, "loss": 4.5869, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797132136981832e-05, "loss": 4.5862, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.79629354223078e-05, "loss": 4.5857, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795454947479728e-05, "loss": 4.5865, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794617990609049e-05, "loss": 4.5884, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.5729, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5787, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792102206355894e-05, "loss": 4.5763, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791263611604842e-05, "loss": 4.5841, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.79042501685379e-05, "loss": 4.5795, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789586422102737e-05, "loss": 4.5778, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788747827351685e-05, "loss": 4.5762, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879108704810067e-05, "loss": 4.5728, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870722757299546e-05, "loss": 4.5575, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862353188592756e-05, "loss": 4.5596, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853967241082236e-05, "loss": 4.5654, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845581293571715e-05, "loss": 4.5606, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837211724864925e-05, "loss": 4.5584, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782882577735441e-05, "loss": 4.5553, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782043982984389e-05, "loss": 4.5508, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.78120702611371e-05, "loss": 4.5553, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780368431362658e-05, "loss": 4.5531, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779529836611606e-05, "loss": 4.5523, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778691241860554e-05, "loss": 4.5538, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777852647109502e-05, "loss": 4.5545, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777014052358449e-05, "loss": 4.5536, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776175457607397e-05, "loss": 4.548, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775336862856345e-05, "loss": 4.5589, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774498268105293e-05, "loss": 4.5564, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773659673354241e-05, "loss": 4.5438, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772821078603189e-05, "loss": 4.5554, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771984121732511e-05, "loss": 4.5422, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771145526981459e-05, "loss": 4.549, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770306932230407e-05, "loss": 4.523, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769468337479355e-05, "loss": 4.5447, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768629742728303e-05, "loss": 4.5268, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767791147977251e-05, "loss": 4.5331, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766954191106572e-05, "loss": 4.5192, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.76611559635552e-05, "loss": 4.55, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765277001604468e-05, "loss": 4.5413, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764438406853416e-05, "loss": 4.5329, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763599812102364e-05, "loss": 4.5277, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762761217351312e-05, "loss": 4.5306, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.76192262260026e-05, "loss": 4.539, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610856657295813e-05, "loss": 4.5335, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602470709785293e-05, "loss": 4.5278, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594084762274773e-05, "loss": 4.5311, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758569881476425e-05, "loss": 4.5222, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757732924605746e-05, "loss": 4.5368, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756894329854694e-05, "loss": 4.5161, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756055735103642e-05, "loss": 4.522, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.75521714035259e-05, "loss": 4.5178, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543785456015375e-05, "loss": 4.5144, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535399508504855e-05, "loss": 4.5191, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527013560994335e-05, "loss": 4.5173, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518627613483815e-05, "loss": 4.5179, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510241665973295e-05, "loss": 4.5173, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750187209726651e-05, "loss": 4.5118, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.479715824127197, "eval_runtime": 325.7634, "eval_samples_per_second": 1171.375, "eval_steps_per_second": 36.606, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749348614975599e-05, "loss": 4.5025, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748510020224547e-05, "loss": 4.4968, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747671425473495e-05, "loss": 4.516, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746832830722443e-05, "loss": 4.5, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745994235971391e-05, "loss": 4.5214, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745155641220339e-05, "loss": 4.4918, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744317046469287e-05, "loss": 4.505, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743478451718235e-05, "loss": 4.487, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742639856967183e-05, "loss": 4.5022, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741801262216131e-05, "loss": 4.499, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740964305345452e-05, "loss": 4.505, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401257105944e-05, "loss": 4.5008, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739287115843348e-05, "loss": 4.4837, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384485210922966e-05, "loss": 4.4929, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376099263412446e-05, "loss": 4.4874, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736771331590192e-05, "loss": 4.4835, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.73593273683914e-05, "loss": 4.4875, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7350957799684615e-05, "loss": 4.49, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342571852174095e-05, "loss": 4.485, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733418590466357e-05, "loss": 4.5056, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732579995715305e-05, "loss": 4.4798, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731741400964253e-05, "loss": 4.4871, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730902806213201e-05, "loss": 4.4861, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730064211462149e-05, "loss": 4.4943, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729225616711097e-05, "loss": 4.4731, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728387021960045e-05, "loss": 4.4846, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727548427208993e-05, "loss": 4.4733, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267098324579415e-05, "loss": 4.4792, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258712377068895e-05, "loss": 4.4665, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250326429558375e-05, "loss": 4.4699, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7241940482047855e-05, "loss": 4.4771, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233554534537335e-05, "loss": 4.4773, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722516858702681e-05, "loss": 4.4767, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216799018320024e-05, "loss": 4.479, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720842944961323e-05, "loss": 4.4712, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720004350210271e-05, "loss": 4.4785, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719165755459219e-05, "loss": 4.4589, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718327160708167e-05, "loss": 4.4754, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717488565957115e-05, "loss": 4.4584, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716651609086437e-05, "loss": 4.4663, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715814652215758e-05, "loss": 4.4626, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714976057464706e-05, "loss": 4.4667, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714137462713654e-05, "loss": 4.4566, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713298867962602e-05, "loss": 4.4615, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.71246027321155e-05, "loss": 4.4681, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711621678460498e-05, "loss": 4.4628, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710783083709446e-05, "loss": 4.4646, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709944488958393e-05, "loss": 4.447, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709105894207341e-05, "loss": 4.4375, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708267299456289e-05, "loss": 4.4573, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074303425856106e-05, "loss": 4.4513, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065917478345586e-05, "loss": 4.4514, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057531530835066e-05, "loss": 4.4336, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.7049145583324546e-05, "loss": 4.4404, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040759635814026e-05, "loss": 4.4414, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032373688303506e-05, "loss": 4.456, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7023987740792986e-05, "loss": 4.434, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015601793282466e-05, "loss": 4.4437, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.447, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4326, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.69904930871621e-05, "loss": 4.4388, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982107139651573e-05, "loss": 4.4336, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4213, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4353, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4372, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.69485633496095e-05, "loss": 4.4404, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694017740209898e-05, "loss": 4.4208, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693179145458846e-05, "loss": 4.4259, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692340550707794e-05, "loss": 4.4229, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691503593837115e-05, "loss": 4.4498, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690666636966436e-05, "loss": 4.4344, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689828042215384e-05, "loss": 4.4349, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.447, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.4461, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4404, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686473663211176e-05, "loss": 4.4275, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856350684601245e-05, "loss": 4.4288, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847964737090725e-05, "loss": 4.4283, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839578789580204e-05, "loss": 4.4225, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831209220873414e-05, "loss": 4.4235, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822823273362894e-05, "loss": 4.4262, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814437325852373e-05, "loss": 4.4342, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806051378341853e-05, "loss": 4.4238, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679768180963506e-05, "loss": 4.4164, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678929586212454e-05, "loss": 4.4112, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678092629341775e-05, "loss": 4.4205, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677254034590723e-05, "loss": 4.4278, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676415439839671e-05, "loss": 4.4175, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4168, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.4248, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673899655586516e-05, "loss": 4.407, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673062698715837e-05, "loss": 4.4163, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672224103964785e-05, "loss": 4.411, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671385509213733e-05, "loss": 4.4169, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670546914462681e-05, "loss": 4.4148, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669708319711629e-05, "loss": 4.4108, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688713628409496e-05, "loss": 4.4059, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680327680898976e-05, "loss": 4.4123, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6671941733388456e-05, "loss": 4.4024, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663555785877936e-05, "loss": 4.4204, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655169838367416e-05, "loss": 4.4112, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.409, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638397943346376e-05, "loss": 4.403, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630011995835856e-05, "loss": 4.4111, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621626048325336e-05, "loss": 4.3881, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613256479618545e-05, "loss": 4.3945, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604870532108025e-05, "loss": 4.3979, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596484584597505e-05, "loss": 4.399, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588098637086985e-05, "loss": 4.3936, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579712689576465e-05, "loss": 4.3943, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571343120869674e-05, "loss": 4.3864, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562957173359154e-05, "loss": 4.3948, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554571225848634e-05, "loss": 4.3911, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546185278338114e-05, "loss": 4.3874, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65377993308276e-05, "loss": 4.3986, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652941338331708e-05, "loss": 4.3978, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652104381461029e-05, "loss": 4.3979, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651265786709977e-05, "loss": 4.3884, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650427191958925e-05, "loss": 4.3989, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649588597207873e-05, "loss": 4.3963, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648750002456821e-05, "loss": 4.3874, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647913045586142e-05, "loss": 4.404, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.64707445083509e-05, "loss": 4.3839, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646235856084038e-05, "loss": 4.394, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645397261332986e-05, "loss": 4.3737, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644558666581934e-05, "loss": 4.3912, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643720071830882e-05, "loss": 4.3705, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428831149602034e-05, "loss": 4.383, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420445202091514e-05, "loss": 4.3692, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641207563338472e-05, "loss": 4.3965, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.64036896858742e-05, "loss": 4.39, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639530373836368e-05, "loss": 4.3876, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638691779085316e-05, "loss": 4.3791, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637853184334264e-05, "loss": 4.38, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637014589583212e-05, "loss": 4.3961, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361759948321596e-05, "loss": 4.3841, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353374000811076e-05, "loss": 4.3781, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6344988053300556e-05, "loss": 4.3895, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633661848459377e-05, "loss": 4.378, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632823253708325e-05, "loss": 4.3867, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631984658957273e-05, "loss": 4.3706, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631146064206221e-05, "loss": 4.3791, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630307469455169e-05, "loss": 4.3731, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.62947051258449e-05, "loss": 4.3774, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628631917833438e-05, "loss": 4.372, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627793323082386e-05, "loss": 4.3781, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626954728331334e-05, "loss": 4.3692, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626117771460655e-05, "loss": 4.3755, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625279176709603e-05, "loss": 4.3703, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.345709800720215, "eval_runtime": 295.2131, "eval_samples_per_second": 1292.595, "eval_steps_per_second": 40.395, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624440581958551e-05, "loss": 4.3679, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623601987207499e-05, "loss": 4.3586, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227650303368205e-05, "loss": 4.3763, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219264355857685e-05, "loss": 4.3593, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210878408347165e-05, "loss": 4.3863, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202492460836645e-05, "loss": 4.3532, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194106513326125e-05, "loss": 4.3662, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185720565815605e-05, "loss": 4.3489, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177334618305085e-05, "loss": 4.3655, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168948670794565e-05, "loss": 4.3653, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160562723284045e-05, "loss": 4.3624, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152176775773525e-05, "loss": 4.3676, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614382358587046e-05, "loss": 4.348, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613543763835994e-05, "loss": 4.3601, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612705169084942e-05, "loss": 4.3546, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611866574333891e-05, "loss": 4.3521, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611027979582839e-05, "loss": 4.3536, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610189384831787e-05, "loss": 4.3567, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609350790080735e-05, "loss": 4.3547, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608512195329683e-05, "loss": 4.3692, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607675238459004e-05, "loss": 4.3493, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606836643707952e-05, "loss": 4.3555, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6059980489569e-05, "loss": 4.3554, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605159454205848e-05, "loss": 4.364, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604320859454796e-05, "loss": 4.3439, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603482264703743e-05, "loss": 4.3564, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602643669952691e-05, "loss": 4.346, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601806713082013e-05, "loss": 4.3479, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600968118330961e-05, "loss": 4.3371, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001311614602824e-05, "loss": 4.3477, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5992925667092303e-05, "loss": 4.3472, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.5984539719581783e-05, "loss": 4.3522, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976153772071257e-05, "loss": 4.3489, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5967767824560737e-05, "loss": 4.3545, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959381877050217e-05, "loss": 4.3466, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5950995929539696e-05, "loss": 4.3523, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942609982029176e-05, "loss": 4.339, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934240413322386e-05, "loss": 4.3479, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925854465811865e-05, "loss": 4.3341, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917468518301345e-05, "loss": 4.3428, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590909894959456e-05, "loss": 4.3415, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590071300208404e-05, "loss": 4.3462, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589232705457352e-05, "loss": 4.3348, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5883941107063e-05, "loss": 4.3408, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587555515955248e-05, "loss": 4.3456, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586716921204196e-05, "loss": 4.3403, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585878326453144e-05, "loss": 4.3422, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585039731702092e-05, "loss": 4.3333, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.58420113695104e-05, "loss": 4.3125, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583364180080361e-05, "loss": 4.339, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582525585329309e-05, "loss": 4.3321, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581686990578257e-05, "loss": 4.3276, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808500337075786e-05, "loss": 4.323, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.5800114389565266e-05, "loss": 4.3215, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791728442054746e-05, "loss": 4.3198, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783342494544226e-05, "loss": 4.3377, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5774956547033706e-05, "loss": 4.3183, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.5766570599523186e-05, "loss": 4.3258, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758184652012666e-05, "loss": 4.3345, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5749798704502146e-05, "loss": 4.317, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741429135795355e-05, "loss": 4.3191, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733043188284835e-05, "loss": 4.3252, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724657240774315e-05, "loss": 4.3037, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716271293263794e-05, "loss": 4.3215, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570788534575327e-05, "loss": 4.3267, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699515777046484e-05, "loss": 4.3233, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691129829535963e-05, "loss": 4.3073, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682743882025443e-05, "loss": 4.315, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674357934514923e-05, "loss": 4.3088, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566598836580814e-05, "loss": 4.3311, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565760241829762e-05, "loss": 4.3251, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564923284959083e-05, "loss": 4.3264, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564084690208031e-05, "loss": 4.3335, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563246095456979e-05, "loss": 4.3353, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562407500705927e-05, "loss": 4.3326, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561568905954874e-05, "loss": 4.3141, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560730311203822e-05, "loss": 4.3195, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559891716452771e-05, "loss": 4.3224, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559054759582092e-05, "loss": 4.3122, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.55821616483104e-05, "loss": 4.3205, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557377570079988e-05, "loss": 4.3144, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556538975328936e-05, "loss": 4.3236, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555700380577884e-05, "loss": 4.318, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554861785826832e-05, "loss": 4.3009, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.55402319107578e-05, "loss": 4.3085, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553184596324728e-05, "loss": 4.3151, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552346001573676e-05, "loss": 4.3182, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551507406822624e-05, "loss": 4.3114, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506704499519446e-05, "loss": 4.3085, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498318552008926e-05, "loss": 4.3167, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5489932604498406e-05, "loss": 4.3039, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481546656987886e-05, "loss": 4.3059, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.54731770882811e-05, "loss": 4.3092, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546479114077058e-05, "loss": 4.3135, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545640519326006e-05, "loss": 4.313, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544801924574954e-05, "loss": 4.3046, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543963329823902e-05, "loss": 4.2963, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.54312473507285e-05, "loss": 4.3117, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542286140321798e-05, "loss": 4.2975, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541449183451119e-05, "loss": 4.3184, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540610588700067e-05, "loss": 4.3095, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539771993949015e-05, "loss": 4.3062, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538933399197963e-05, "loss": 4.2991, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538094804446911e-05, "loss": 4.3104, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372578475762326e-05, "loss": 4.2868, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364192528251806e-05, "loss": 4.2961, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535580658074128e-05, "loss": 4.293, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534742063323076e-05, "loss": 4.2983, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339051064523975e-05, "loss": 4.2911, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330665117013455e-05, "loss": 4.2968, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532227916950293e-05, "loss": 4.2907, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531389322199241e-05, "loss": 4.2856, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530550727448189e-05, "loss": 4.2949, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529712132697137e-05, "loss": 4.2863, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528873537946085e-05, "loss": 4.3032, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528034943195033e-05, "loss": 4.2986, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527196348443981e-05, "loss": 4.3005, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5263593915733024e-05, "loss": 4.2917, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255207968222504e-05, "loss": 4.3, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5246822020711984e-05, "loss": 4.3007, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238436073201464e-05, "loss": 4.2899, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523006650449467e-05, "loss": 4.3041, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522168055698415e-05, "loss": 4.2893, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521329460947363e-05, "loss": 4.2957, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520490866196311e-05, "loss": 4.2824, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519652271445259e-05, "loss": 4.2928, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518813676694207e-05, "loss": 4.2758, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517978357703902e-05, "loss": 4.2865, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.51713976295285e-05, "loss": 4.2765, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516301168201798e-05, "loss": 4.2977, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515462573450746e-05, "loss": 4.2907, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514623978699694e-05, "loss": 4.295, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513785383948642e-05, "loss": 4.2837, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.51294678919759e-05, "loss": 4.289, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512108194446538e-05, "loss": 4.3001, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511269599695486e-05, "loss": 4.2887, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510431004944434e-05, "loss": 4.288, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5095940480737546e-05, "loss": 4.297, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087554533227026e-05, "loss": 4.2841, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079168585716506e-05, "loss": 4.2942, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070782638205986e-05, "loss": 4.2756, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062396690695466e-05, "loss": 4.2893, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505402712198868e-05, "loss": 4.2801, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504564117447816e-05, "loss": 4.2817, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503725522696764e-05, "loss": 4.2846, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5028869279457115e-05, "loss": 4.2788, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020483331946595e-05, "loss": 4.2801, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501211376323981e-05, "loss": 4.2809, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500372781572929e-05, "loss": 4.2844, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.262835502624512, "eval_runtime": 290.7805, "eval_samples_per_second": 1312.299, "eval_steps_per_second": 41.01, "step": 305280 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.2603086607342746e+17, "trial_name": null, "trial_params": null }