diff --git "a/checkpoint-2518560/trainer_state.json" "b/checkpoint-2518560/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2518560/trainer_state.json" @@ -0,0 +1,29803 @@ +{ + "best_metric": 3.977557897567749, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/2/checkpoints/checkpoint-2518560", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2518560, + "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 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995341868218764e-05, + "loss": 4.2745, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986955920708244e-05, + "loss": 4.2675, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978569973197724e-05, + "loss": 4.2857, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970184025687204e-05, + "loss": 4.2711, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961798078176684e-05, + "loss": 4.2933, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953412130666164e-05, + "loss": 4.272, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494502618315565e-05, + "loss": 4.2715, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493664023564513e-05, + "loss": 4.261, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492825428813461e-05, + "loss": 4.2783, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491986834062409e-05, + "loss": 4.2813, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491148239311357e-05, + "loss": 4.2752, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490309644560305e-05, + "loss": 4.2733, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489472687689626e-05, + "loss": 4.2621, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488634092938574e-05, + "loss": 4.2718, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487795498187522e-05, + "loss": 4.2691, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48695690343647e-05, + "loss": 4.2602, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2674, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.2732, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2655, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.2794, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.2701, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2723, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481088378059479e-05, + "loss": 4.2678, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480249783308427e-05, + "loss": 4.2781, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479412826437748e-05, + "loss": 4.2577, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478574231686696e-05, + "loss": 4.2695, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477735636935644e-05, + "loss": 4.2653, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476897042184592e-05, + "loss": 4.26, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47605844743354e-05, + "loss": 4.2532, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.2625, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474381257931436e-05, + "loss": 4.2679, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473544301060757e-05, + "loss": 4.2669, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472705706309705e-05, + "loss": 4.2681, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471867111558653e-05, + "loss": 4.2669, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471028516807601e-05, + "loss": 4.2633, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470189922056549e-05, + "loss": 4.2677, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.46935296518587e-05, + "loss": 4.2596, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468514370434818e-05, + "loss": 4.2616, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467675775683766e-05, + "loss": 4.255, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466837180932714e-05, + "loss": 4.2613, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2585, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2648, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2556, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2584, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2674, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461807250306775e-05, + "loss": 4.257, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.2595, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460130060804672e-05, + "loss": 4.2518, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592931039339926e-05, + "loss": 4.2329, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2609, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2535, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2485, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559403628101575e-05, + "loss": 4.2359, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551034059394784e-05, + "loss": 4.2458, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542648111884264e-05, + "loss": 4.2361, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2591, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525876216863224e-05, + "loss": 4.2403, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517490269352704e-05, + "loss": 4.2451, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450910432184219e-05, + "loss": 4.2564, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500718374331664e-05, + "loss": 4.2388, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492332426821144e-05, + "loss": 4.2437, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448396285811436e-05, + "loss": 4.2491, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447557691060384e-05, + "loss": 4.2258, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446719096309331e-05, + "loss": 4.2441, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445882139438653e-05, + "loss": 4.2453, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.2496, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.2322, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2401, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2293, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441689165683393e-05, + "loss": 4.2567, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440850570932341e-05, + "loss": 4.2491, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440011976181289e-05, + "loss": 4.2466, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2594, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2545, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.264, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436660872937827e-05, + "loss": 4.2382, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358222781867747e-05, + "loss": 4.2423, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4349836834357227e-05, + "loss": 4.2485, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341450886846707e-05, + "loss": 4.2331, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2473, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324678991825666e-05, + "loss": 4.2391, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316293044315146e-05, + "loss": 4.2471, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307907096804626e-05, + "loss": 4.243, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429952114929411e-05, + "loss": 4.2293, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429113520178359e-05, + "loss": 4.2425, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428278201188053e-05, + "loss": 4.2293, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427439606437001e-05, + "loss": 4.2455, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426601011685949e-05, + "loss": 4.2387, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425762416934897e-05, + "loss": 4.2342, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424923822183845e-05, + "loss": 4.2429, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424085227432793e-05, + "loss": 4.2367, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423246632681741e-05, + "loss": 4.2283, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422408037930689e-05, + "loss": 4.235, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421569443179637e-05, + "loss": 4.2433, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.239, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419893891557907e-05, + "loss": 4.2362, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419055296806855e-05, + "loss": 4.2238, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418216702055803e-05, + "loss": 4.2371, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41737810730475e-05, + "loss": 4.2276, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165411504340716e-05, + "loss": 4.2438, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157025556830196e-05, + "loss": 4.2419, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148639609319676e-05, + "loss": 4.2332, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414025366180915e-05, + "loss": 4.2267, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413186771429863e-05, + "loss": 4.2429, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412348176678811e-05, + "loss": 4.2137, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411509581927759e-05, + "loss": 4.226, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106726250570805e-05, + "loss": 4.2195, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098340303060284e-05, + "loss": 4.2331, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4089954355549764e-05, + "loss": 4.2188, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081568408039244e-05, + "loss": 4.2244, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073182460528724e-05, + "loss": 4.2225, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064796513018204e-05, + "loss": 4.2179, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.223, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404804099680089e-05, + "loss": 4.2213, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403965504929037e-05, + "loss": 4.2341, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403126910177985e-05, + "loss": 4.23, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402288315426933e-05, + "loss": 4.2291, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401449720675881e-05, + "loss": 4.2215, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400612763805202e-05, + "loss": 4.2316, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977416905415e-05, + "loss": 4.2272, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398935574303098e-05, + "loss": 4.2227, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398096979552047e-05, + "loss": 4.2396, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397258384800995e-05, + "loss": 4.2204, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396419790049943e-05, + "loss": 4.2262, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395581195298891e-05, + "loss": 4.214, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394744238428212e-05, + "loss": 4.2255, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.39390564367716e-05, + "loss": 4.2108, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393067048926108e-05, + "loss": 4.2157, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392228454175056e-05, + "loss": 4.213, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391389859424003e-05, + "loss": 4.2289, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390552902553325e-05, + "loss": 4.2244, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389714307802273e-05, + "loss": 4.2256, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888773509315936e-05, + "loss": 4.2149, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388038756180542e-05, + "loss": 4.2256, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.38720016142949e-05, + "loss": 4.2332, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386361566678438e-05, + "loss": 4.2237, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385522971927386e-05, + "loss": 4.2209, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.2287, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383847420305655e-05, + "loss": 4.2188, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383008825554603e-05, + "loss": 4.2276, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821702308035505e-05, + "loss": 4.2113, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813316360524985e-05, + "loss": 4.2226, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804930413014465e-05, + "loss": 4.2141, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796544465503944e-05, + "loss": 4.217, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788158517993424e-05, + "loss": 4.2186, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2152, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377140300177612e-05, + "loss": 4.2181, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763033433069336e-05, + "loss": 4.2113, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375464748555881e-05, + "loss": 4.2225, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.20582389831543, + "eval_runtime": 356.2608, + "eval_samples_per_second": 1071.1, + "eval_steps_per_second": 33.473, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374626153804829e-05, + "loss": 4.2126, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373787559053777e-05, + "loss": 4.2007, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372948964302725e-05, + "loss": 4.2213, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372110369551673e-05, + "loss": 4.2098, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371271774800621e-05, + "loss": 4.2261, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370433180049569e-05, + "loss": 4.2119, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.36959622317889e-05, + "loss": 4.1992, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687592663082114e-05, + "loss": 4.2052, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679206715571594e-05, + "loss": 4.2067, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670820768061074e-05, + "loss": 4.2182, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662434820550554e-05, + "loss": 4.2104, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654048873040034e-05, + "loss": 4.212, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364567930433324e-05, + "loss": 4.2028, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363729335682272e-05, + "loss": 4.2053, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36289074093122e-05, + "loss": 4.2096, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362052146180168e-05, + "loss": 4.1974, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361213551429116e-05, + "loss": 4.204, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360374956678064e-05, + "loss": 4.2096, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359536361927012e-05, + "loss": 4.2079, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35869776717596e-05, + "loss": 4.2152, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357860810305281e-05, + "loss": 4.2089, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.35702221555423e-05, + "loss": 4.2108, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356183620803178e-05, + "loss": 4.2083, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355345026052126e-05, + "loss": 4.2124, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354506431301074e-05, + "loss": 4.1971, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353667836550022e-05, + "loss": 4.2121, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352829241798969e-05, + "loss": 4.1979, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.351990647047917e-05, + "loss": 4.1983, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351152052296865e-05, + "loss": 4.196, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350313457545813e-05, + "loss": 4.2004, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349476500675134e-05, + "loss": 4.2065, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348637905924082e-05, + "loss": 4.2051, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.34779931117303e-05, + "loss": 4.2098, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346960716421978e-05, + "loss": 4.2124, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346122121670926e-05, + "loss": 4.2008, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345283526919875e-05, + "loss": 4.2077, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444465700491956e-05, + "loss": 4.2018, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436079752981436e-05, + "loss": 4.1994, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427693805470916e-05, + "loss": 4.1955, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419307857960396e-05, + "loss": 4.1965, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3410921910449876e-05, + "loss": 4.2037, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402552341743085e-05, + "loss": 4.2073, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394166394232565e-05, + "loss": 4.1933, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385780446722045e-05, + "loss": 4.2008, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377394499211525e-05, + "loss": 4.2057, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369008551701005e-05, + "loss": 4.1997, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360622604190485e-05, + "loss": 4.2003, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352236656679965e-05, + "loss": 4.1932, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343850709169445e-05, + "loss": 4.1704, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333549751926639e-05, + "loss": 4.2066, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.33271279505596e-05, + "loss": 4.1936, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331874200304908e-05, + "loss": 4.1941, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331035605553856e-05, + "loss": 4.1851, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330197010802804e-05, + "loss": 4.1805, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329358416051752e-05, + "loss": 4.1826, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285198213007e-05, + "loss": 4.1947, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327681226549648e-05, + "loss": 4.1828, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326842631798596e-05, + "loss": 4.1889, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326004037047544e-05, + "loss": 4.1971, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325165442296492e-05, + "loss": 4.1821, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243284854258134e-05, + "loss": 4.1848, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234898906747614e-05, + "loss": 4.1925, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3226512959237094e-05, + "loss": 4.173, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218127011726574e-05, + "loss": 4.1838, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209741064216054e-05, + "loss": 4.1877, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320135511670553e-05, + "loss": 4.1947, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319298554799874e-05, + "loss": 4.1728, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318461597929195e-05, + "loss": 4.1842, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317623003178143e-05, + "loss": 4.1728, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316784408427091e-05, + "loss": 4.1981, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315945813676039e-05, + "loss": 4.194, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315107218924987e-05, + "loss": 4.191, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314268624173935e-05, + "loss": 4.1991, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313430029422883e-05, + "loss": 4.2004, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312591434671831e-05, + "loss": 4.209, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311752839920779e-05, + "loss": 4.184, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109158830501e-05, + "loss": 4.1886, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310077288299048e-05, + "loss": 4.1882, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309238693547996e-05, + "loss": 4.1777, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308400098796944e-05, + "loss": 4.1956, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307561504045892e-05, + "loss": 4.1835, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.30672290929484e-05, + "loss": 4.1939, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305884314543788e-05, + "loss": 4.1892, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305045719792736e-05, + "loss": 4.1741, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042087629220577e-05, + "loss": 4.1873, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033701681710057e-05, + "loss": 4.1751, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025315734199536e-05, + "loss": 4.19, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016946165492746e-05, + "loss": 4.1861, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008560217982226e-05, + "loss": 4.1745, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000174270471705e-05, + "loss": 4.1929, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991788322961185e-05, + "loss": 4.181, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983402375450665e-05, + "loss": 4.1764, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975032806743874e-05, + "loss": 4.181, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966646859233354e-05, + "loss": 4.1928, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958260911722834e-05, + "loss": 4.1829, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949874964212314e-05, + "loss": 4.1878, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941489016701794e-05, + "loss": 4.1707, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933103069191274e-05, + "loss": 4.182, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924717121680754e-05, + "loss": 4.1761, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291633117417024e-05, + "loss": 4.1895, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290796160546345e-05, + "loss": 4.1894, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289959203675666e-05, + "loss": 4.1764, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289120608924614e-05, + "loss": 4.1791, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288282014173562e-05, + "loss": 4.1876, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28744341942251e-05, + "loss": 4.1621, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286606462551831e-05, + "loss": 4.1732, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285767867800779e-05, + "loss": 4.168, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284929273049727e-05, + "loss": 4.1782, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284090678298675e-05, + "loss": 4.169, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832537214279964e-05, + "loss": 4.1754, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824151266769444e-05, + "loss": 4.1689, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2815765319258924e-05, + "loss": 4.1664, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807379371748404e-05, + "loss": 4.1738, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798993424237884e-05, + "loss": 4.168, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790607476727364e-05, + "loss": 4.1807, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278222152921684e-05, + "loss": 4.1767, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277383558170632e-05, + "loss": 4.1782, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.27654496341958e-05, + "loss": 4.1703, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275706368668528e-05, + "loss": 4.1789, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748694117978486e-05, + "loss": 4.1798, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740308170467966e-05, + "loss": 4.1693, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273193860176118e-05, + "loss": 4.1907, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272355265425066e-05, + "loss": 4.1645, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271516670674014e-05, + "loss": 4.1765, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270678075922962e-05, + "loss": 4.1606, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26983948117191e-05, + "loss": 4.1766, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269000886420858e-05, + "loss": 4.1599, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268162291669806e-05, + "loss": 4.1683, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267323696918754e-05, + "loss": 4.1588, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266485102167702e-05, + "loss": 4.1832, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265648145297023e-05, + "loss": 4.1705, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264809550545971e-05, + "loss": 4.1773, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263970955794919e-05, + "loss": 4.1646, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263132361043867e-05, + "loss": 4.1775, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622954041731886e-05, + "loss": 4.1818, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614568094221366e-05, + "loss": 4.1737, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606182146710846e-05, + "loss": 4.1737, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597796199200326e-05, + "loss": 4.1736, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589410251689806e-05, + "loss": 4.1697, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581024304179286e-05, + "loss": 4.1785, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572638356668766e-05, + "loss": 4.162, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564252409158246e-05, + "loss": 4.1716, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2555882840451455e-05, + "loss": 4.1668, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547496892940935e-05, + "loss": 4.1688, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539127324234144e-05, + "loss": 4.1681, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530741376723624e-05, + "loss": 4.1605, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252237180801684e-05, + "loss": 4.1754, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251398586050632e-05, + "loss": 4.1578, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25055999129958e-05, + "loss": 4.1774, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.165280818939209, + "eval_runtime": 296.2522, + "eval_samples_per_second": 1288.061, + "eval_steps_per_second": 40.253, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249721396548528e-05, + "loss": 4.1663, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248882801797476e-05, + "loss": 4.1529, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248044207046424e-05, + "loss": 4.1703, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247205612295372e-05, + "loss": 4.1644, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24636701754432e-05, + "loss": 4.1747, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245528422793267e-05, + "loss": 4.1642, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244689828042215e-05, + "loss": 4.1528, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243851233291163e-05, + "loss": 4.155, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243012638540111e-05, + "loss": 4.1613, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242174043789059e-05, + "loss": 4.1698, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241335449038007e-05, + "loss": 4.1639, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240496854286955e-05, + "loss": 4.1603, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239659897416277e-05, + "loss": 4.1633, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238821302665225e-05, + "loss": 4.156, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237982707914173e-05, + "loss": 4.1582, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237144113163121e-05, + "loss": 4.148, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236305518412069e-05, + "loss": 4.159, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235466923661017e-05, + "loss": 4.1598, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234628328909965e-05, + "loss": 4.1596, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233789734158913e-05, + "loss": 4.1686, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232951139407861e-05, + "loss": 4.1676, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232114182537182e-05, + "loss": 4.1603, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127558778613e-05, + "loss": 4.1596, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304386309154506e-05, + "loss": 4.1692, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296000361643986e-05, + "loss": 4.1462, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228761441413347e-05, + "loss": 4.1693, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227922846662295e-05, + "loss": 4.1538, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227084251911243e-05, + "loss": 4.1491, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226245657160191e-05, + "loss": 4.1503, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254070624091386e-05, + "loss": 4.1569, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245684676580866e-05, + "loss": 4.1557, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237298729070346e-05, + "loss": 4.1613, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228912781559826e-05, + "loss": 4.1613, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220526834049306e-05, + "loss": 4.1647, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212140886538786e-05, + "loss": 4.1524, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1628, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219540174912521e-05, + "loss": 4.1589, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218701580161469e-05, + "loss": 4.1493, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217862985410417e-05, + "loss": 4.1515, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217024390659365e-05, + "loss": 4.1544, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216185795908313e-05, + "loss": 4.1539, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215347201157261e-05, + "loss": 4.1637, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214508606406209e-05, + "loss": 4.1478, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.21367164953553e-05, + "loss": 4.1514, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212833054784478e-05, + "loss": 4.1633, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211994460033426e-05, + "loss": 4.1514, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211155865282374e-05, + "loss": 4.1598, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210317270531322e-05, + "loss": 4.1498, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209480313660643e-05, + "loss": 4.1201, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208641718909591e-05, + "loss": 4.1645, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078031241585395e-05, + "loss": 4.1502, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069645294074875e-05, + "loss": 4.151, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061275725368084e-05, + "loss": 4.1415, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052889777857564e-05, + "loss": 4.1314, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044503830347044e-05, + "loss": 4.1416, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036117882836524e-05, + "loss": 4.1472, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027731935326004e-05, + "loss": 4.1422, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.1431, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1551, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200259047159817e-05, + "loss": 4.1367, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199420452408765e-05, + "loss": 4.1369, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198581857657713e-05, + "loss": 4.1527, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197743262906661e-05, + "loss": 4.1264, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196904668155609e-05, + "loss": 4.1394, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196066073404557e-05, + "loss": 4.1438, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195227478653505e-05, + "loss": 4.1555, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194388883902453e-05, + "loss": 4.1275, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193551927031775e-05, + "loss": 4.1453, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192714970161096e-05, + "loss": 4.1249, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191876375410044e-05, + "loss": 4.1553, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191037780658992e-05, + "loss": 4.1508, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.19019918590794e-05, + "loss": 4.1475, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189360591156887e-05, + "loss": 4.1527, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188521996405835e-05, + "loss": 4.157, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187683401654783e-05, + "loss": 4.1671, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186844806903731e-05, + "loss": 4.1429, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860078500330526e-05, + "loss": 4.1478, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851692552820006e-05, + "loss": 4.1484, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843306605309486e-05, + "loss": 4.1326, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1834920657798966e-05, + "loss": 4.1474, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826551089092175e-05, + "loss": 4.1427, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818165141581655e-05, + "loss": 4.1499, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809779194071135e-05, + "loss": 4.1549, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801393246560615e-05, + "loss": 4.1338, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793007299050095e-05, + "loss": 4.1386, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784621351539575e-05, + "loss": 4.1346, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776235404029055e-05, + "loss": 4.1506, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767849456518535e-05, + "loss": 4.1404, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175949626661548e-05, + "loss": 4.1376, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175111031910496e-05, + "loss": 4.1359, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174272437159444e-05, + "loss": 4.1472, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.1349, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.1365, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171756652906288e-05, + "loss": 4.1538, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170918058155236e-05, + "loss": 4.1428, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170079463404184e-05, + "loss": 4.1431, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169242506533505e-05, + "loss": 4.13, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168403911782453e-05, + "loss": 4.1381, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167565317031401e-05, + "loss": 4.1354, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166726722280349e-05, + "loss": 4.1475, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658897654096704e-05, + "loss": 4.1447, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650511706586184e-05, + "loss": 4.1422, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1405, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1432, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1224, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1339, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160859834783731e-05, + "loss": 4.1212, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160021240032679e-05, + "loss": 4.1404, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159182645281627e-05, + "loss": 4.1285, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158344050530575e-05, + "loss": 4.132, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575054557795226e-05, + "loss": 4.1266, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1566668610284706e-05, + "loss": 4.1283, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558282662774186e-05, + "loss": 4.1332, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154989671526367e-05, + "loss": 4.1268, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154151076775315e-05, + "loss": 4.1377, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153314119904636e-05, + "loss": 4.1414, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152475525153584e-05, + "loss": 4.1344, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151636930402532e-05, + "loss": 4.1379, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15079833565148e-05, + "loss": 4.1338, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149961378780801e-05, + "loss": 4.1388, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149122784029749e-05, + "loss": 4.1354, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482874650394436e-05, + "loss": 4.1446, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474488702883916e-05, + "loss": 4.1273, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466102755373396e-05, + "loss": 4.1368, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457716807862876e-05, + "loss": 4.1233, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449330860352356e-05, + "loss": 4.1306, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144096129164557e-05, + "loss": 4.1235, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143257534413505e-05, + "loss": 4.1264, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142418939662453e-05, + "loss": 4.1199, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415803449114005e-05, + "loss": 4.1394, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407417501603485e-05, + "loss": 4.1332, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399031554092965e-05, + "loss": 4.1356, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390645606582445e-05, + "loss": 4.1227, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382259659071925e-05, + "loss": 4.1407, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373873711561405e-05, + "loss": 4.1383, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365504142854614e-05, + "loss": 4.1374, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357118195344094e-05, + "loss": 4.1361, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134873224783358e-05, + "loss": 4.1323, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134034630032306e-05, + "loss": 4.133, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133197673161627e-05, + "loss": 4.1425, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132359078410575e-05, + "loss": 4.1203, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131520483659523e-05, + "loss": 4.1318, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130681888908471e-05, + "loss": 4.1323, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1315, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12900633728674e-05, + "loss": 4.1221, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128167742535688e-05, + "loss": 4.1218, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1375, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126492190913957e-05, + "loss": 4.122, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125655234043278e-05, + "loss": 4.1371, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.133861541748047, + "eval_runtime": 294.3283, + "eval_samples_per_second": 1296.481, + "eval_steps_per_second": 40.516, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124816639292226e-05, + "loss": 4.1247, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123978044541174e-05, + "loss": 4.1152, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123139449790122e-05, + "loss": 4.1335, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122302492919443e-05, + "loss": 4.1201, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121463898168391e-05, + "loss": 4.1337, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120625303417339e-05, + "loss": 4.1284, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119786708666287e-05, + "loss": 4.1174, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118948113915235e-05, + "loss": 4.117, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118109519164183e-05, + "loss": 4.1232, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117270924413131e-05, + "loss": 4.1296, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116432329662079e-05, + "loss": 4.1246, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115593734911027e-05, + "loss": 4.1216, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.1222, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1186, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1218, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.1121, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.1177, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.1228, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1228, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.1265, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1332, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072110631612536e-05, + "loss": 4.125, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106372468410201e-05, + "loss": 4.1209, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055355115395225e-05, + "loss": 4.1253, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1046969167884705e-05, + "loss": 4.1148, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038583220374185e-05, + "loss": 4.1287, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.115, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021811325353145e-05, + "loss": 4.1173, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013425377842625e-05, + "loss": 4.1147, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1167, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996653482821585e-05, + "loss": 4.1187, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.1249, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979897966604274e-05, + "loss": 4.1218, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097152839789748e-05, + "loss": 4.1265, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096314245038696e-05, + "loss": 4.1155, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095475650287644e-05, + "loss": 4.1298, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094637055536592e-05, + "loss": 4.1226, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09379846078554e-05, + "loss": 4.11, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092959866034489e-05, + "loss": 4.118, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092121271283437e-05, + "loss": 4.1181, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091282676532385e-05, + "loss": 4.1143, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090444081781333e-05, + "loss": 4.1252, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089605487030281e-05, + "loss": 4.1122, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088766892279229e-05, + "loss": 4.1153, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08792993540855e-05, + "loss": 4.1256, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087091340657498e-05, + "loss": 4.1164, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086252745906446e-05, + "loss": 4.1181, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085414151155394e-05, + "loss": 4.1167, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.0802, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083738599533663e-05, + "loss": 4.1317, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082900004782611e-05, + "loss": 4.1103, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082061410031559e-05, + "loss": 4.1177, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812228152805074e-05, + "loss": 4.1014, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803842205294554e-05, + "loss": 4.0978, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079547263658776e-05, + "loss": 4.1035, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078708668907724e-05, + "loss": 4.1094, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077870074156672e-05, + "loss": 4.1095, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770314794056196e-05, + "loss": 4.1036, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761928846545676e-05, + "loss": 4.1229, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753542899035156e-05, + "loss": 4.102, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745156951524636e-05, + "loss": 4.1014, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736771004014116e-05, + "loss": 4.1172, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728401435307325e-05, + "loss": 4.0905, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072001548779681e-05, + "loss": 4.1001, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071164591909002e-05, + "loss": 4.1091, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07032599715795e-05, + "loss": 4.1182, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069487402406898e-05, + "loss": 4.0935, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068648807655846e-05, + "loss": 4.1101, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067810212904794e-05, + "loss": 4.0916, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066971618153742e-05, + "loss": 4.1198, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.06613302340269e-05, + "loss": 4.1132, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065296066532011e-05, + "loss": 4.1121, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064457471780959e-05, + "loss": 4.1141, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063618877029907e-05, + "loss": 4.1213, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062780282278855e-05, + "loss": 4.1299, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061941687527803e-05, + "loss": 4.1083, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611047306571246e-05, + "loss": 4.1101, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602661359060726e-05, + "loss": 4.1156, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594275411550206e-05, + "loss": 4.0969, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585889464039686e-05, + "loss": 4.1077, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577503516529166e-05, + "loss": 4.1096, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569117569018645e-05, + "loss": 4.1161, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560731621508125e-05, + "loss": 4.1177, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552345673997605e-05, + "loss": 4.101, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543992484094544e-05, + "loss": 4.1014, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535606536584024e-05, + "loss": 4.1033, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527220589073504e-05, + "loss": 4.1142, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518834641562984e-05, + "loss": 4.1075, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510448694052463e-05, + "loss": 4.1025, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502062746541943e-05, + "loss": 4.102, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049369317783516e-05, + "loss": 4.113, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048530723032464e-05, + "loss": 4.1021, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047692128281412e-05, + "loss": 4.1021, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.04685353353036e-05, + "loss": 4.1168, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046014938779308e-05, + "loss": 4.1068, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045176344028256e-05, + "loss": 4.1079, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044337749277203e-05, + "loss": 4.098, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043499154526151e-05, + "loss": 4.1018, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042662197655473e-05, + "loss": 4.098, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1157, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1091, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040149689163063e-05, + "loss": 4.1087, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039311094412011e-05, + "loss": 4.1063, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038472499660959e-05, + "loss": 4.1049, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037633904909907e-05, + "loss": 4.0935, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.0948, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035956715407803e-05, + "loss": 4.0908, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351181206567506e-05, + "loss": 4.1059, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342795259056986e-05, + "loss": 4.0943, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334409311546466e-05, + "loss": 4.0967, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032603974283968e-05, + "loss": 4.0895, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317653795329155e-05, + "loss": 4.0982, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030928422662237e-05, + "loss": 4.0991, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030089827911185e-05, + "loss": 4.0911, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029251233160133e-05, + "loss": 4.1087, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028412638409081e-05, + "loss": 4.1038, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027574043658029e-05, + "loss": 4.0994, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026735448906977e-05, + "loss": 4.1053, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025896854155925e-05, + "loss": 4.1, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025058259404873e-05, + "loss": 4.1006, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024219664653821e-05, + "loss": 4.1056, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023381069902769e-05, + "loss": 4.1074, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02254411303209e-05, + "loss": 4.0929, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021705518281038e-05, + "loss": 4.102, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020866923529986e-05, + "loss": 4.0931, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020028328778934e-05, + "loss": 4.0976, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191913719082555e-05, + "loss": 4.0881, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183527771572035e-05, + "loss": 4.0927, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175141824061515e-05, + "loss": 4.089, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166772255354724e-05, + "loss": 4.1052, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158386307844204e-05, + "loss": 4.099, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150000360333684e-05, + "loss": 4.1053, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141614412823164e-05, + "loss": 4.0867, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133228465312644e-05, + "loss": 4.11, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124842517802124e-05, + "loss": 4.1003, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0116456570291604e-05, + "loss": 4.104, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108070622781084e-05, + "loss": 4.103, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009970105407429e-05, + "loss": 4.1002, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009131510656377e-05, + "loss": 4.0956, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008292915905325e-05, + "loss": 4.1079, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007454321154274e-05, + "loss": 4.0899, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006615726403222e-05, + "loss": 4.0999, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005777131652169e-05, + "loss": 4.0979, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004940174781491e-05, + "loss": 4.0965, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004101580030439e-05, + "loss": 4.0906, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003262985279387e-05, + "loss": 4.0885, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002424390528334e-05, + "loss": 4.1048, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001587433657656e-05, + "loss": 4.0931, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000748838906604e-05, + "loss": 4.1039, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.108824253082275, + "eval_runtime": 295.3183, + "eval_samples_per_second": 1292.134, + "eval_steps_per_second": 40.38, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999910244155552e-05, + "loss": 4.0901, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999071649404499e-05, + "loss": 4.0875, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998233054653448e-05, + "loss": 4.0914, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997394459902396e-05, + "loss": 4.0929, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996555865151344e-05, + "loss": 4.1035, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995717270400292e-05, + "loss": 4.0963, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.99487867564924e-05, + "loss": 4.0854, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994040080898188e-05, + "loss": 4.0863, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993201486147136e-05, + "loss": 4.0874, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992362891396084e-05, + "loss": 4.1018, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991524296645032e-05, + "loss": 4.0914, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99068570189398e-05, + "loss": 4.0879, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989847107142928e-05, + "loss": 4.0983, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989008512391876e-05, + "loss": 4.0793, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988169917640823e-05, + "loss": 4.0867, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987331322889771e-05, + "loss": 4.0841, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9864943660190926e-05, + "loss": 4.0867, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856557712680406e-05, + "loss": 4.0918, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848171765169886e-05, + "loss": 4.0916, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839785817659366e-05, + "loss": 4.0908, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831399870148846e-05, + "loss": 4.1049, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823013922638326e-05, + "loss": 4.0932, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814627975127806e-05, + "loss": 4.0938, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806242027617286e-05, + "loss": 4.0892, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797856080106766e-05, + "loss": 4.0875, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789470132596246e-05, + "loss": 4.0956, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781084185085726e-05, + "loss": 4.0848, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772714616378935e-05, + "loss": 4.0877, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764328668868415e-05, + "loss": 4.0792, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755942721357895e-05, + "loss": 4.0861, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974757315265111e-05, + "loss": 4.0831, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973918720514059e-05, + "loss": 4.0893, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973080125763007e-05, + "loss": 4.095, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972241531011955e-05, + "loss": 4.0958, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971402936260903e-05, + "loss": 4.0865, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970564341509851e-05, + "loss": 4.0909, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.094, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.0839, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.0849, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967211600386016e-05, + "loss": 4.0853, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966373005634964e-05, + "loss": 4.0885, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655376866446584e-05, + "loss": 4.0881, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9646990918936064e-05, + "loss": 4.0881, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638604971425544e-05, + "loss": 4.0858, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630219023915024e-05, + "loss": 4.0913, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621833076404504e-05, + "loss": 4.0878, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613447128893984e-05, + "loss": 4.0885, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605061181383464e-05, + "loss": 4.0859, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596675233872944e-05, + "loss": 4.049, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958828928636242e-05, + "loss": 4.0983, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957991971765563e-05, + "loss": 4.0787, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957153377014511e-05, + "loss": 4.0882, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956314782263459e-05, + "loss": 4.0735, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554761875124066e-05, + "loss": 4.0683, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546375927613546e-05, + "loss": 4.0692, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953798998010303e-05, + "loss": 4.0776, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952960403259251e-05, + "loss": 4.08, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952121808508199e-05, + "loss": 4.0741, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951286489517894e-05, + "loss": 4.0891, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950447894766842e-05, + "loss": 4.0765, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949609300015789e-05, + "loss": 4.0707, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948770705264737e-05, + "loss": 4.0868, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947932110513685e-05, + "loss": 4.0636, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9470951536430066e-05, + "loss": 4.068, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946256558891954e-05, + "loss": 4.081, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945417964140902e-05, + "loss": 4.0852, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94457936938985e-05, + "loss": 4.0658, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437407746387986e-05, + "loss": 4.0766, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429021798877466e-05, + "loss": 4.0626, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420635851366946e-05, + "loss": 4.0869, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412249903856426e-05, + "loss": 4.0865, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403863956345906e-05, + "loss": 4.082, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395494387639115e-05, + "loss": 4.0866, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387108440128595e-05, + "loss": 4.09, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378722492618075e-05, + "loss": 4.1022, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370336545107555e-05, + "loss": 4.0799, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936198335520449e-05, + "loss": 4.0786, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935359740769397e-05, + "loss": 4.0811, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934521146018345e-05, + "loss": 4.0752, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933682551267294e-05, + "loss": 4.0757, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932843956516242e-05, + "loss": 4.0809, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.93200536176519e-05, + "loss": 4.0864, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931166767014138e-05, + "loss": 4.0911, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930328172263086e-05, + "loss": 4.0707, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929491215392407e-05, + "loss": 4.0717, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928654258521728e-05, + "loss": 4.0718, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927815663770676e-05, + "loss": 4.0878, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926977069019624e-05, + "loss": 4.0809, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926140112148945e-05, + "loss": 4.0681, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925301517397893e-05, + "loss": 4.0732, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924462922646841e-05, + "loss": 4.082, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236243278957894e-05, + "loss": 4.0755, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9227857331447374e-05, + "loss": 4.0704, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219471383936854e-05, + "loss": 4.0874, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211085436426334e-05, + "loss": 4.0807, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202699488915813e-05, + "loss": 4.0782, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194313541405293e-05, + "loss": 4.0736, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.91859439726985e-05, + "loss": 4.0711, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917755802518798e-05, + "loss": 4.0728, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916917207767746e-05, + "loss": 4.085, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916078613016694e-05, + "loss": 4.0802, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915240018265642e-05, + "loss": 4.0764, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144014235145896e-05, + "loss": 4.0801, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135628287635375e-05, + "loss": 4.073, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912724234012486e-05, + "loss": 4.0723, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911887277141808e-05, + "loss": 4.0637, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911050320271129e-05, + "loss": 4.0591, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910211725520077e-05, + "loss": 4.0783, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909373130769025e-05, + "loss": 4.0682, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085361738983456e-05, + "loss": 4.0644, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9076975791472936e-05, + "loss": 4.0622, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068589843962416e-05, + "loss": 4.0652, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060203896451896e-05, + "loss": 4.0743, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905181794894137e-05, + "loss": 4.0654, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904343200143085e-05, + "loss": 4.0783, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903504605392033e-05, + "loss": 4.0763, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026660106409816e-05, + "loss": 4.074, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018274158899296e-05, + "loss": 4.076, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009888211388776e-05, + "loss": 4.0709, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001502263878256e-05, + "loss": 4.0737, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993116316367736e-05, + "loss": 4.079, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984746747660945e-05, + "loss": 4.0775, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976377178954154e-05, + "loss": 4.0699, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967991231443634e-05, + "loss": 4.0739, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959605283933114e-05, + "loss": 4.0697, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951219336422594e-05, + "loss": 4.0671, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942833388912074e-05, + "loss": 4.0607, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893446382020528e-05, + "loss": 4.0653, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892607787269476e-05, + "loss": 4.0612, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891769192518425e-05, + "loss": 4.0772, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890930597767373e-05, + "loss": 4.0689, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890092003016321e-05, + "loss": 4.0806, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889255046145642e-05, + "loss": 4.0605, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88841645139459e-05, + "loss": 4.082, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887577856643538e-05, + "loss": 4.0744, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886739261892486e-05, + "loss": 4.0774, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885900667141434e-05, + "loss": 4.0752, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885062072390382e-05, + "loss": 4.071, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.88422347763933e-05, + "loss": 4.0722, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883384882888278e-05, + "loss": 4.0813, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882547926017599e-05, + "loss": 4.0617, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881709331266547e-05, + "loss": 4.0726, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880870736515495e-05, + "loss": 4.0706, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800321417644434e-05, + "loss": 4.0694, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879195184893764e-05, + "loss": 4.0674, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878356590142712e-05, + "loss": 4.0622, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.87751799539166e-05, + "loss": 4.0777, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876679400640608e-05, + "loss": 4.0687, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875842443769929e-05, + "loss": 4.0759, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.088820457458496, + "eval_runtime": 293.3677, + "eval_samples_per_second": 1300.726, + "eval_steps_per_second": 40.649, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875003849018877e-05, + "loss": 4.0605, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874165254267825e-05, + "loss": 4.0631, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873326659516773e-05, + "loss": 4.0653, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724880647657205e-05, + "loss": 4.0686, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716494700146685e-05, + "loss": 4.0782, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870810875263617e-05, + "loss": 4.0686, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869972280512565e-05, + "loss": 4.061, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869135323641886e-05, + "loss": 4.0618, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868298366771208e-05, + "loss": 4.0594, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674597720201557e-05, + "loss": 4.0734, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866621177269103e-05, + "loss": 4.0647, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865782582518051e-05, + "loss": 4.0629, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649456256473726e-05, + "loss": 4.0719, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641086687766935e-05, + "loss": 4.0538, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632700740256415e-05, + "loss": 4.0594, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624314792745895e-05, + "loss": 4.0554, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615928845235375e-05, + "loss": 4.0619, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607542897724855e-05, + "loss": 4.0582, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599156950214334e-05, + "loss": 4.0673, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590771002703814e-05, + "loss": 4.0655, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582385055193294e-05, + "loss": 4.0767, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573999107682774e-05, + "loss": 4.0647, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565613160172254e-05, + "loss": 4.0676, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557227212661734e-05, + "loss": 4.0616, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8548841265151214e-05, + "loss": 4.0646, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854047169644442e-05, + "loss": 4.0677, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85320857489339e-05, + "loss": 4.0554, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852369980142338e-05, + "loss": 4.0659, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851531385391286e-05, + "loss": 4.0528, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850692790640234e-05, + "loss": 4.0599, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849855833769556e-05, + "loss": 4.0593, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849018876898877e-05, + "loss": 4.0611, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848180282147825e-05, + "loss": 4.0728, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847343325277146e-05, + "loss": 4.0705, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846504730526094e-05, + "loss": 4.0618, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845666135775042e-05, + "loss": 4.0602, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84482754102399e-05, + "loss": 4.072, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843988946272938e-05, + "loss": 4.0563, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843150351521886e-05, + "loss": 4.0589, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423133946512066e-05, + "loss": 4.0607, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414747999001546e-05, + "loss": 4.064, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840636205149103e-05, + "loss": 4.0617, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839797610398051e-05, + "loss": 4.0597, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838959015646999e-05, + "loss": 4.0626, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838120420895947e-05, + "loss": 4.0641, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837281826144895e-05, + "loss": 4.0635, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836443231393843e-05, + "loss": 4.0616, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835604636642791e-05, + "loss": 4.0634, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834766041891739e-05, + "loss": 4.0268, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.83392908502106e-05, + "loss": 4.0702, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833090490270008e-05, + "loss": 4.0533, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832251895518956e-05, + "loss": 4.0682, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831413300767904e-05, + "loss": 4.0482, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305747060168515e-05, + "loss": 4.0442, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829737749146173e-05, + "loss": 4.0443, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828899154395121e-05, + "loss": 4.0527, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.82806055964407e-05, + "loss": 4.0619, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827221964893017e-05, + "loss": 4.0445, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826383370141965e-05, + "loss": 4.0662, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825544775390913e-05, + "loss": 4.0536, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824706180639861e-05, + "loss": 4.04, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823869223769182e-05, + "loss": 4.0617, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230322668985035e-05, + "loss": 4.0429, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221936721474515e-05, + "loss": 4.0417, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821355077396399e-05, + "loss": 4.056, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820516482645347e-05, + "loss": 4.0628, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819677887894295e-05, + "loss": 4.0465, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188392931432435e-05, + "loss": 4.0512, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180006983921915e-05, + "loss": 4.0403, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171621036411395e-05, + "loss": 4.0601, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163235088900875e-05, + "loss": 4.062, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154849141390355e-05, + "loss": 4.0567, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146463193879835e-05, + "loss": 4.0616, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138093625173044e-05, + "loss": 4.0646, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812972405646625e-05, + "loss": 4.0765, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812133810895573e-05, + "loss": 4.0563, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811296854024894e-05, + "loss": 4.0577, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810458259273842e-05, + "loss": 4.0529, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80961966452279e-05, + "loss": 4.0544, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808781069771739e-05, + "loss": 4.0503, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807942475020687e-05, + "loss": 4.0595, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807103880269635e-05, + "loss": 4.0615, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806265285518583e-05, + "loss": 4.0693, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805426690767531e-05, + "loss": 4.0449, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804588096016479e-05, + "loss": 4.0481, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803749501265427e-05, + "loss": 4.0514, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802910906514375e-05, + "loss": 4.0589, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802072311763323e-05, + "loss": 4.0587, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8012369927730166e-05, + "loss": 4.0491, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8003983980219646e-05, + "loss": 4.0491, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995598032709126e-05, + "loss": 4.058, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987212085198606e-05, + "loss": 4.0511, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978826137688086e-05, + "loss": 4.0448, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797044019017757e-05, + "loss": 4.0633, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796205424266705e-05, + "loss": 4.0562, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953668295156526e-05, + "loss": 4.0578, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794529872644974e-05, + "loss": 4.0478, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793691277893922e-05, + "loss": 4.048, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.79285268314287e-05, + "loss": 4.0479, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920140883918175e-05, + "loss": 4.0605, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7911754936407655e-05, + "loss": 4.0636, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790338536770087e-05, + "loss": 4.0476, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789499942019035e-05, + "loss": 4.0592, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886613472679824e-05, + "loss": 4.0509, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787822752516931e-05, + "loss": 4.0526, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786985795646253e-05, + "loss": 4.0401, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861472008952e-05, + "loss": 4.0398, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785308606144148e-05, + "loss": 4.0498, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784470011393096e-05, + "loss": 4.0514, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783631416642044e-05, + "loss": 4.0386, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782794459771365e-05, + "loss": 4.0421, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781955865020313e-05, + "loss": 4.0432, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781117270269261e-05, + "loss": 4.051, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780278675518209e-05, + "loss": 4.0427, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.77944171864753e-05, + "loss": 4.0556, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778603123896478e-05, + "loss": 4.0535, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777661670257994e-05, + "loss": 4.0525, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769275722747474e-05, + "loss": 4.049, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7760889775236954e-05, + "loss": 4.0542, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7752503827726433e-05, + "loss": 4.0518, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744117880215913e-05, + "loss": 4.0558, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7735731932705393e-05, + "loss": 4.0557, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772734598519487e-05, + "loss": 4.0454, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771896003768435e-05, + "loss": 4.0526, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.77106068477813e-05, + "loss": 4.0495, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770222090027077e-05, + "loss": 4.0405, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769383495276025e-05, + "loss": 4.0435, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768546538405347e-05, + "loss": 4.044, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767707943654295e-05, + "loss": 4.035, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766869348903243e-05, + "loss": 4.0557, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766030754152191e-05, + "loss": 4.0455, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765192159401139e-05, + "loss": 4.0569, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764353564650087e-05, + "loss": 4.0365, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763514969899035e-05, + "loss": 4.0568, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762676375147983e-05, + "loss": 4.0545, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761837780396931e-05, + "loss": 4.0551, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760999185645879e-05, + "loss": 4.0514, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760160590894827e-05, + "loss": 4.0458, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759321996143775e-05, + "loss": 4.0554, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584850392730956e-05, + "loss": 4.056, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576464445220436e-05, + "loss": 4.0416, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756809487651365e-05, + "loss": 4.0505, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755970892900313e-05, + "loss": 4.0493, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755132298149261e-05, + "loss": 4.0459, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754293703398209e-05, + "loss": 4.0445, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753455108647157e-05, + "loss": 4.0393, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752616513896105e-05, + "loss": 4.053, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751777919145053e-05, + "loss": 4.0481, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750939324394001e-05, + "loss": 4.0535, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.073829174041748, + "eval_runtime": 295.6355, + "eval_samples_per_second": 1290.748, + "eval_steps_per_second": 40.337, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750102367523322e-05, + "loss": 4.0326, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74926377277227e-05, + "loss": 4.0407, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748425178021218e-05, + "loss": 4.0407, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475865832701654e-05, + "loss": 4.0441, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467479885191134e-05, + "loss": 4.0564, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745909393768062e-05, + "loss": 4.0512, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74507079901701e-05, + "loss": 4.0362, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744232204265958e-05, + "loss": 4.0397, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743393609514906e-05, + "loss": 4.0375, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742555014763854e-05, + "loss": 4.0486, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741716420012802e-05, + "loss": 4.0452, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74087782526175e-05, + "loss": 4.0435, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740040868391071e-05, + "loss": 4.0496, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739202273640019e-05, + "loss": 4.0292, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738363678888967e-05, + "loss": 4.0383, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737525084137915e-05, + "loss": 4.0294, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736686489386863e-05, + "loss": 4.0455, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735847894635811e-05, + "loss": 4.0408, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735009299884759e-05, + "loss": 4.0442, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734170705133707e-05, + "loss": 4.042, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733332110382655e-05, + "loss": 4.0563, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732493515631603e-05, + "loss": 4.0419, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731654920880551e-05, + "loss": 4.0499, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730816326129499e-05, + "loss": 4.0409, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729977731378447e-05, + "loss": 4.0414, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729140774507768e-05, + "loss": 4.0469, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728302179756716e-05, + "loss": 4.0327, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727463585005664e-05, + "loss": 4.0412, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726624990254612e-05, + "loss": 4.0339, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725788033383933e-05, + "loss": 4.0374, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724949438632881e-05, + "loss": 4.0408, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241108438818287e-05, + "loss": 4.0401, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7232722491307767e-05, + "loss": 4.0417, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722435292260098e-05, + "loss": 4.0535, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721596697509046e-05, + "loss": 4.0397, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720758102757994e-05, + "loss": 4.04, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719919508006942e-05, + "loss": 4.0532, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719084189016637e-05, + "loss": 4.0345, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718245594265585e-05, + "loss": 4.0366, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717406999514532e-05, + "loss": 4.0407, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71656840476348e-05, + "loss": 4.037, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715729810012428e-05, + "loss": 4.0419, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714891215261376e-05, + "loss": 4.0356, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714052620510324e-05, + "loss": 4.046, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713214025759272e-05, + "loss": 4.0397, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712375431008221e-05, + "loss": 4.0439, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711536836257169e-05, + "loss": 4.0392, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7106998793864896e-05, + "loss": 4.044, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7098612846354376e-05, + "loss": 4.0077, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090226898843856e-05, + "loss": 4.0468, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081840951333336e-05, + "loss": 4.0282, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073455003822816e-05, + "loss": 4.0454, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065069056312296e-05, + "loss": 4.0266, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056683108801776e-05, + "loss": 4.0242, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048297161291256e-05, + "loss": 4.0225, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703991121378073e-05, + "loss": 4.0332, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703152526627021e-05, + "loss": 4.0402, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702313931875969e-05, + "loss": 4.0245, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014769750052905e-05, + "loss": 4.0437, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006383802542385e-05, + "loss": 4.036, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997997855031865e-05, + "loss": 4.0168, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989611907521345e-05, + "loss": 4.0406, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981225960010824e-05, + "loss": 4.02, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972840012500304e-05, + "loss": 4.0213, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964454064989784e-05, + "loss": 4.0357, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956068117479264e-05, + "loss": 4.0401, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947698548772473e-05, + "loss": 4.0217, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939312601261953e-05, + "loss": 4.0356, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693092665375143e-05, + "loss": 4.0209, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692254070624091e-05, + "loss": 4.0344, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691417113753413e-05, + "loss": 4.041, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690578519002361e-05, + "loss": 4.0378, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689739924251309e-05, + "loss": 4.0423, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688901329500257e-05, + "loss": 4.0411, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688064372629578e-05, + "loss": 4.0568, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687225777878526e-05, + "loss": 4.0363, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686387183127474e-05, + "loss": 4.0402, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685548588376422e-05, + "loss": 4.0289, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684711631505743e-05, + "loss": 4.0347, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683873036754691e-05, + "loss": 4.0302, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683034442003639e-05, + "loss": 4.0373, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682195847252587e-05, + "loss": 4.0425, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681357252501535e-05, + "loss": 4.0474, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680520295630856e-05, + "loss": 4.025, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679681700879804e-05, + "loss": 4.0287, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678843106128752e-05, + "loss": 4.0267, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678006149258073e-05, + "loss": 4.0383, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677167554507021e-05, + "loss": 4.0359, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676328959755969e-05, + "loss": 4.0292, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675490365004917e-05, + "loss": 4.0306, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674651770253865e-05, + "loss": 4.0356, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673813175502813e-05, + "loss": 4.0299, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672976218632134e-05, + "loss": 4.025, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672137623881082e-05, + "loss": 4.041, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.67129902913003e-05, + "loss": 4.039, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670460434378978e-05, + "loss": 4.0365, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669621839627926e-05, + "loss": 4.0264, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668783244876875e-05, + "loss": 4.0273, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667944650125822e-05, + "loss": 4.0305, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66710605537477e-05, + "loss": 4.0374, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666267460623718e-05, + "loss": 4.0437, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6654305037530396e-05, + "loss": 4.0258, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6645935468823605e-05, + "loss": 4.0395, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637549521313085e-05, + "loss": 4.0311, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629163573802565e-05, + "loss": 4.0297, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662077762629204e-05, + "loss": 4.022, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661239167878152e-05, + "loss": 4.0206, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604005731271e-05, + "loss": 4.0275, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595619783760485e-05, + "loss": 4.0286, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587233836249965e-05, + "loss": 4.0194, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578847888739445e-05, + "loss": 4.0219, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570478320032654e-05, + "loss": 4.0183, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562092372522134e-05, + "loss": 4.0309, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553706425011614e-05, + "loss": 4.0243, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545320477501094e-05, + "loss": 4.0322, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6536934529990574e-05, + "loss": 4.0328, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6528548582480054e-05, + "loss": 4.0305, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652017901377326e-05, + "loss": 4.0278, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651179306626274e-05, + "loss": 4.0369, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650340711875222e-05, + "loss": 4.0311, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64950211712417e-05, + "loss": 4.0392, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648663522373118e-05, + "loss": 4.0317, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64782656550244e-05, + "loss": 4.0304, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646987970751388e-05, + "loss": 4.0288, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646149376000336e-05, + "loss": 4.0275, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645310781249284e-05, + "loss": 4.0227, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644472186498232e-05, + "loss": 4.0223, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64363359174718e-05, + "loss": 4.0197, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642794996996128e-05, + "loss": 4.0177, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641956402245075e-05, + "loss": 4.0353, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641117807494023e-05, + "loss": 4.0273, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402824885037176e-05, + "loss": 4.0359, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394438937526656e-05, + "loss": 4.0197, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386052990016136e-05, + "loss": 4.0354, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637766704250562e-05, + "loss": 4.0328, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.63692810949951e-05, + "loss": 4.0332, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636089514748458e-05, + "loss": 4.0308, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6352509199974056e-05, + "loss": 4.0261, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344123252463536e-05, + "loss": 4.0381, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633575368375675e-05, + "loss": 4.0391, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327367736246225e-05, + "loss": 4.0203, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6318981788735705e-05, + "loss": 4.0292, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310595841225185e-05, + "loss": 4.0318, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.63022262725184e-05, + "loss": 4.0251, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0221, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.0233, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627706842998684e-05, + "loss": 4.031, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626868248247632e-05, + "loss": 4.0278, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.62602965349658e-05, + "loss": 4.0321, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.060328483581543, + "eval_runtime": 297.3237, + "eval_samples_per_second": 1283.419, + "eval_steps_per_second": 40.108, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625191058745528e-05, + "loss": 4.0164, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624354101874849e-05, + "loss": 4.0202, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623515507123797e-05, + "loss": 4.0211, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622676912372745e-05, + "loss": 4.0248, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621839955502066e-05, + "loss": 4.0327, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621001360751014e-05, + "loss": 4.0323, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620162765999962e-05, + "loss": 4.0193, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.61932417124891e-05, + "loss": 4.0217, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0147, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0237, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.0313, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6159697922447025e-05, + "loss": 4.0237, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0287, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0097, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134572837522923e-05, + "loss": 4.0225, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126186890012403e-05, + "loss": 4.0067, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611780094250188e-05, + "loss": 4.0265, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610941499499136e-05, + "loss": 4.0211, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610102904748084e-05, + "loss": 4.0225, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609264309997032e-05, + "loss": 4.0222, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.60842571524598e-05, + "loss": 4.0376, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607587120494928e-05, + "loss": 4.0195, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606750163624249e-05, + "loss": 4.0299, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605911568873198e-05, + "loss": 4.0214, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605072974122146e-05, + "loss": 4.0229, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604234379371094e-05, + "loss": 4.0286, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.0115, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602557189868989e-05, + "loss": 4.0206, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601718595117937e-05, + "loss": 4.0168, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600880000366885e-05, + "loss": 4.0176, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600041405615833e-05, + "loss": 4.0225, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599206086625528e-05, + "loss": 4.0228, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598367491874476e-05, + "loss": 4.0177, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597528897123424e-05, + "loss": 4.0391, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596690302372372e-05, + "loss": 4.0207, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.59585170762132e-05, + "loss": 4.0186, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595013112870268e-05, + "loss": 4.0301, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594176155999589e-05, + "loss": 4.0137, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933375612485366e-05, + "loss": 4.0173, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5924989664974846e-05, + "loss": 4.0263, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916603717464326e-05, + "loss": 4.0162, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908234148757535e-05, + "loss": 4.0227, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899848201247015e-05, + "loss": 4.02, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891462253736495e-05, + "loss": 4.018, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883076306225975e-05, + "loss": 4.0251, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874690358715455e-05, + "loss": 4.0228, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866304411204935e-05, + "loss": 4.0199, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0244, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58495325161839e-05, + "loss": 3.9909, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584116294747711e-05, + "loss": 4.0228, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583277699996659e-05, + "loss": 4.0134, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582439105245607e-05, + "loss": 4.0274, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581600510494555e-05, + "loss": 4.0093, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580761915743503e-05, + "loss": 4.0026, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579924958872824e-05, + "loss": 4.0071, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579086364121772e-05, + "loss": 4.0106, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57824776937072e-05, + "loss": 4.0203, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577409174619668e-05, + "loss": 4.0008, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576570579868616e-05, + "loss": 4.0285, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575731985117564e-05, + "loss": 4.0202, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5748950282468855e-05, + "loss": 3.9951, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5740564334958335e-05, + "loss": 4.0195, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5732178387447815e-05, + "loss": 4.0037, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5723792439937295e-05, + "loss": 4.0019, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5715406492426775e-05, + "loss": 4.0113, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707036923719984e-05, + "loss": 4.0247, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698650976209464e-05, + "loss": 4.0014, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5690265028698944e-05, + "loss": 4.0183, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568189545999215e-05, + "loss": 3.9983, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567350951248163e-05, + "loss": 4.0163, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566512356497111e-05, + "loss": 4.0205, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565673761746059e-05, + "loss": 4.0233, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564835166995007e-05, + "loss": 4.0203, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563996572243955e-05, + "loss": 4.022, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563157977492903e-05, + "loss": 4.0378, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562319382741851e-05, + "loss": 4.0181, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561482425871172e-05, + "loss": 4.0211, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.56064383112012e-05, + "loss": 4.0088, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559805236369068e-05, + "loss": 4.0138, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558966641618016e-05, + "loss": 4.0109, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558129684747337e-05, + "loss": 4.0151, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557291089996285e-05, + "loss": 4.0241, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556452495245233e-05, + "loss": 4.0266, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555613900494181e-05, + "loss": 4.0112, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554775305743129e-05, + "loss": 4.0096, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553936710992077e-05, + "loss": 4.0032, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553098116241026e-05, + "loss": 4.0249, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552259521489974e-05, + "loss": 4.0151, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514225646192946e-05, + "loss": 4.0095, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505839698682426e-05, + "loss": 4.0166, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5497453751171906e-05, + "loss": 4.0108, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5489067803661386e-05, + "loss": 4.0129, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5480681856150866e-05, + "loss": 4.0073, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472295908640346e-05, + "loss": 4.0224, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463909961129826e-05, + "loss": 4.0176, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455524013619306e-05, + "loss": 4.0205, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447154444912515e-05, + "loss": 4.0063, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438768497401995e-05, + "loss": 4.0092, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5430382549891475e-05, + "loss": 4.0116, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5421996602380955e-05, + "loss": 4.0197, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541361065487044e-05, + "loss": 4.0203, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540524108616365e-05, + "loss": 4.0135, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539685513865313e-05, + "loss": 4.0196, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538846919114261e-05, + "loss": 4.0147, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5380083243632084e-05, + "loss": 4.0122, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371697296121564e-05, + "loss": 4.0021, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536332772741478e-05, + "loss": 4.0044, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535494177990426e-05, + "loss": 4.0047, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534655583239373e-05, + "loss": 4.0117, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533816988488321e-05, + "loss": 4.001, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532978393737269e-05, + "loss": 4.0019, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532141436866591e-05, + "loss": 4.0027, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531302842115539e-05, + "loss": 4.011, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530464247364487e-05, + "loss": 4.0084, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529625652613435e-05, + "loss": 4.0119, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528788695742756e-05, + "loss": 4.0138, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527950100991704e-05, + "loss": 4.0151, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527111506240652e-05, + "loss": 4.0099, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526274549369973e-05, + "loss": 4.0184, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254359546189206e-05, + "loss": 4.0113, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5245973598678686e-05, + "loss": 4.0212, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237587651168166e-05, + "loss": 4.0134, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5229201703657646e-05, + "loss": 4.012, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522083213495086e-05, + "loss": 4.0088, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521244618744034e-05, + "loss": 4.0129, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520406023992982e-05, + "loss": 4.0039, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.51956742924193e-05, + "loss": 4.0074, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518728834490878e-05, + "loss": 3.9965, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517890239739826e-05, + "loss": 4.004, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517051644988774e-05, + "loss": 4.0146, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516213050237722e-05, + "loss": 4.0096, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.51537445548667e-05, + "loss": 4.0183, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514535860735618e-05, + "loss": 3.9973, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513698903864939e-05, + "loss": 4.0218, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512860309113887e-05, + "loss": 4.0162, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512021714362835e-05, + "loss": 4.0189, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511183119611783e-05, + "loss": 4.0024, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510344524860731e-05, + "loss": 4.0111, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095075679900526e-05, + "loss": 4.0199, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086689732390006e-05, + "loss": 4.0204, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078303784879486e-05, + "loss": 4.0068, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069917837368966e-05, + "loss": 4.009, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061548268662175e-05, + "loss": 4.0106, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053162321151655e-05, + "loss": 4.0119, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044776373641135e-05, + "loss": 4.0035, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036390426130615e-05, + "loss": 4.0097, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028004478620095e-05, + "loss": 4.0079, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501961853110957e-05, + "loss": 4.0088, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5011248962402784e-05, + "loss": 4.0166, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.048957347869873, + "eval_runtime": 296.0638, + "eval_samples_per_second": 1288.881, + "eval_steps_per_second": 40.278, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002863014892264e-05, + "loss": 4.0032, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4994477067381744e-05, + "loss": 3.9985, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986091119871224e-05, + "loss": 4.0062, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4977705172360704e-05, + "loss": 4.0118, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4969319224850184e-05, + "loss": 4.0094, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4960933277339664e-05, + "loss": 4.0176, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952547329829144e-05, + "loss": 4.0042, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4944161382318624e-05, + "loss": 4.0023, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4935775434808104e-05, + "loss": 3.9955, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4927389487297584e-05, + "loss": 4.0073, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4919003539787064e-05, + "loss": 4.0122, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910617592276544e-05, + "loss": 4.005, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490224802356975e-05, + "loss": 4.018, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489386207605923e-05, + "loss": 3.9903, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488547612854872e-05, + "loss": 4.0026, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.48770901810382e-05, + "loss": 3.9924, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486870423352768e-05, + "loss": 4.0078, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486031828601716e-05, + "loss": 4.0058, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485193233850663e-05, + "loss": 4.0037, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484354639099611e-05, + "loss": 3.9997, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483516044348559e-05, + "loss": 4.025, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482677449597507e-05, + "loss": 4.0029, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481838854846455e-05, + "loss": 4.0122, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481000260095403e-05, + "loss": 4.004, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480163303224724e-05, + "loss": 4.0081, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479324708473672e-05, + "loss": 4.0101, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47848611372262e-05, + "loss": 3.9946, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477647518971569e-05, + "loss": 4.0018, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476808924220517e-05, + "loss": 3.9986, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759736052302106e-05, + "loss": 4.0007, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751350104791586e-05, + "loss": 4.0076, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4742964157281066e-05, + "loss": 4.005, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4734578209770546e-05, + "loss": 4.0018, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726192262260026e-05, + "loss": 4.0208, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717806314749506e-05, + "loss": 4.0037, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709436746042715e-05, + "loss": 4.0064, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701050798532195e-05, + "loss": 4.0124, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469268122982541e-05, + "loss": 3.9951, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468429528231489e-05, + "loss": 4.0034, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467590933480437e-05, + "loss": 4.0055, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466752338729385e-05, + "loss": 3.9992, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465913743978333e-05, + "loss": 4.0088, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465075149227281e-05, + "loss": 4.0055, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464236554476229e-05, + "loss": 3.9972, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463397959725177e-05, + "loss": 4.0088, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462559364974125e-05, + "loss": 4.0057, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461722408103446e-05, + "loss": 4.0019, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460883813352394e-05, + "loss": 4.0064, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460045218601342e-05, + "loss": 3.9763, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.45920662385029e-05, + "loss": 4.0022, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458368029099238e-05, + "loss": 4.0001, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457529434348186e-05, + "loss": 4.0084, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566924774775075e-05, + "loss": 3.9932, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558538827264555e-05, + "loss": 3.9855, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550152879754035e-05, + "loss": 3.9897, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541766932243515e-05, + "loss": 3.9923, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533380984732995e-05, + "loss": 4.0076, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452499503722247e-05, + "loss": 3.9803, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516625468515684e-05, + "loss": 4.0126, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508239521005164e-05, + "loss": 4.002, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4499853573494644e-05, + "loss": 3.9815, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449146762598412e-05, + "loss": 4.0039, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.44830816784736e-05, + "loss": 3.987, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447469573096308e-05, + "loss": 3.989, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446630978345256e-05, + "loss": 3.9901, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445794021474577e-05, + "loss": 4.0051, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444955426723525e-05, + "loss": 3.9902, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444118469852847e-05, + "loss": 4.0027, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443279875101794e-05, + "loss": 3.9796, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442441280350742e-05, + "loss": 3.9999, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.44160268559969e-05, + "loss": 4.0045, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440764090848638e-05, + "loss": 4.0081, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439925496097586e-05, + "loss": 4.0042, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439086901346534e-05, + "loss": 4.006, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438248306595482e-05, + "loss": 4.0173, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43740971184443e-05, + "loss": 4.0051, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436571117093378e-05, + "loss": 4.0081, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435732522342326e-05, + "loss": 3.991, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434893927591274e-05, + "loss": 3.9997, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434056970720596e-05, + "loss": 3.9961, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433218375969544e-05, + "loss": 3.9996, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432379781218492e-05, + "loss": 4.0077, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.43154118646744e-05, + "loss": 4.0121, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430702591716388e-05, + "loss": 3.9996, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298656348457086e-05, + "loss": 3.99, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290270400946566e-05, + "loss": 3.9878, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281884453436046e-05, + "loss": 4.0071, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4273498505925526e-05, + "loss": 3.9983, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265128937218735e-05, + "loss": 3.9934, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4256742989708215e-05, + "loss": 4.0003, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424837342100143e-05, + "loss": 3.9983, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.423998747349091e-05, + "loss": 3.9938, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423160152598039e-05, + "loss": 3.9914, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422321557846987e-05, + "loss": 4.008, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421482963095935e-05, + "loss": 4.004, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420644368344883e-05, + "loss": 4.0046, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4198057735938304e-05, + "loss": 3.9919, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418968816723152e-05, + "loss": 3.9942, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181302219721e-05, + "loss": 3.9982, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417291627221048e-05, + "loss": 4.0019, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416453032469995e-05, + "loss": 4.0076, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415616075599317e-05, + "loss": 3.9955, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414777480848265e-05, + "loss": 4.0019, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413938886097213e-05, + "loss": 3.9981, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413100291346161e-05, + "loss": 3.9976, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122633344754825e-05, + "loss": 3.9882, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114247397244305e-05, + "loss": 3.9894, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410586144973378e-05, + "loss": 3.9908, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409747550222326e-05, + "loss": 3.9951, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408908955471274e-05, + "loss": 3.9829, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408071998600595e-05, + "loss": 3.9882, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407233403849543e-05, + "loss": 3.9816, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406394809098491e-05, + "loss": 3.9993, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405556214347439e-05, + "loss": 3.9922, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4047176195963874e-05, + "loss": 3.9968, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4038790248453354e-05, + "loss": 3.9955, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403042067974656e-05, + "loss": 4.0, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402203473223604e-05, + "loss": 3.9967, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401364878472552e-05, + "loss": 3.997, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005262837215e-05, + "loss": 4.0009, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399687688970448e-05, + "loss": 4.0044, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398849094219396e-05, + "loss": 3.9979, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398012137348717e-05, + "loss": 3.9985, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397173542597665e-05, + "loss": 3.9934, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396334947846613e-05, + "loss": 3.9922, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395496353095561e-05, + "loss": 3.9891, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394659396224882e-05, + "loss": 3.9934, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 3.9798, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3929838446031516e-05, + "loss": 3.9896, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921452498520996e-05, + "loss": 3.9953, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913066551010476e-05, + "loss": 3.9987, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904680603499956e-05, + "loss": 3.9991, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 3.988, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887925087282645e-05, + "loss": 4.0026, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879539139772125e-05, + "loss": 4.0, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871153192261605e-05, + "loss": 3.9978, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862767244751085e-05, + "loss": 3.9935, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854381297240565e-05, + "loss": 3.9968, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3845995349730045e-05, + "loss": 4.0056, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3837609402219525e-05, + "loss": 4.0028, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382923983351274e-05, + "loss": 3.9921, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382085388600222e-05, + "loss": 3.9913, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.38124679384917e-05, + "loss": 3.9958, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380408199098118e-05, + "loss": 3.994, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379569604347066e-05, + "loss": 3.9903, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378731009596014e-05, + "loss": 3.9932, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377894052725335e-05, + "loss": 3.9941, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377055457974283e-05, + "loss": 3.997, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376216863223231e-05, + "loss": 4.0006, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.039690017700195, + "eval_runtime": 298.7962, + "eval_samples_per_second": 1277.095, + "eval_steps_per_second": 39.91, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375378268472178e-05, + "loss": 3.9902, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374539673721126e-05, + "loss": 3.9816, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373701078970074e-05, + "loss": 3.99, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372862484219023e-05, + "loss": 3.9986, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372023889467971e-05, + "loss": 3.9944, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371185294716919e-05, + "loss": 4.0028, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370346699965867e-05, + "loss": 3.9864, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369509743095188e-05, + "loss": 3.9886, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368671148344136e-05, + "loss": 3.9786, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367832553593084e-05, + "loss": 3.9973, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366993958842032e-05, + "loss": 3.9923, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.36615536409098e-05, + "loss": 3.9932, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365318407220301e-05, + "loss": 4.0009, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3644814503496216e-05, + "loss": 3.9732, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3636428555985696e-05, + "loss": 3.9909, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362804260847518e-05, + "loss": 3.9747, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361965666096466e-05, + "loss": 3.9933, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361127071345414e-05, + "loss": 3.9862, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360288476594362e-05, + "loss": 3.9926, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.35944988184331e-05, + "loss": 3.9831, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358611287092258e-05, + "loss": 4.0071, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357772692341206e-05, + "loss": 3.9904, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356934097590154e-05, + "loss": 3.9947, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356095502839102e-05, + "loss": 3.9899, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.35525690808805e-05, + "loss": 3.9948, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354419951217371e-05, + "loss": 3.9909, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353581356466319e-05, + "loss": 3.9805, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352742761715267e-05, + "loss": 3.9896, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351904166964215e-05, + "loss": 3.9818, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.35106884797391e-05, + "loss": 3.9861, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502318911032306e-05, + "loss": 3.989, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493932963521786e-05, + "loss": 3.985, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485547016011266e-05, + "loss": 3.9892, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477161068500746e-05, + "loss": 4.0035, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468775120990226e-05, + "loss": 3.9876, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3460389173479706e-05, + "loss": 3.9947, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452003225969185e-05, + "loss": 3.9943, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443633657262395e-05, + "loss": 3.9798, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435247709751875e-05, + "loss": 3.9921, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342687814104509e-05, + "loss": 3.9857, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341849219353457e-05, + "loss": 3.9826, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 3.993, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340172029851353e-05, + "loss": 3.9949, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339333435100301e-05, + "loss": 3.9801, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338494840349249e-05, + "loss": 3.9932, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337656245598197e-05, + "loss": 3.9942, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336817650847144e-05, + "loss": 3.9862, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335979056096092e-05, + "loss": 3.9943, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.33514046134504e-05, + "loss": 3.9591, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334301866593988e-05, + "loss": 3.9879, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333463271842936e-05, + "loss": 3.985, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332624677091884e-05, + "loss": 3.9938, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331786082340832e-05, + "loss": 3.9782, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330949125470154e-05, + "loss": 3.9716, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330110530719102e-05, + "loss": 3.9717, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.32927193596805e-05, + "loss": 3.9741, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328433341216998e-05, + "loss": 3.9959, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327596384346319e-05, + "loss": 3.9687, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.32675942747564e-05, + "loss": 3.9924, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325920832724588e-05, + "loss": 3.9841, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325082237973536e-05, + "loss": 3.9725, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242452811028566e-05, + "loss": 3.9863, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234066863518046e-05, + "loss": 3.9718, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225680916007526e-05, + "loss": 3.9739, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217294968497006e-05, + "loss": 3.9755, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320890902098649e-05, + "loss": 3.9914, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320052307347597e-05, + "loss": 3.9755, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319213712596545e-05, + "loss": 3.9795, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318375117845493e-05, + "loss": 3.9697, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317536523094441e-05, + "loss": 3.9808, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316697928343389e-05, + "loss": 3.992, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315859333592337e-05, + "loss": 3.9917, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315020738841285e-05, + "loss": 3.9891, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314182144090233e-05, + "loss": 3.9911, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133435493391805e-05, + "loss": 4.0022, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125049545881285e-05, + "loss": 3.9886, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.31166799771745e-05, + "loss": 3.9923, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310831040846771e-05, + "loss": 3.9803, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.309992446095719e-05, + "loss": 3.9851, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309153851344668e-05, + "loss": 3.9805, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308315256593616e-05, + "loss": 3.9801, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074782997229366e-05, + "loss": 3.9938, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066397049718846e-05, + "loss": 3.9951, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058011102208326e-05, + "loss": 3.9891, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049625154697806e-05, + "loss": 3.9703, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304123920718728e-05, + "loss": 3.9749, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303285325967676e-05, + "loss": 3.9886, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302446731216624e-05, + "loss": 3.9848, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301608136465572e-05, + "loss": 3.98, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300771179594893e-05, + "loss": 3.9827, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999325848438415e-05, + "loss": 3.983, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2990939900927895e-05, + "loss": 3.9787, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298257033222111e-05, + "loss": 3.9784, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974184384710584e-05, + "loss": 3.993, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2965798437200064e-05, + "loss": 3.986, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2957412489689544e-05, + "loss": 3.9923, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2949026542179024e-05, + "loss": 3.9736, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294065697347223e-05, + "loss": 3.9785, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293227102596171e-05, + "loss": 3.9862, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292388507845119e-05, + "loss": 3.9876, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291549913094067e-05, + "loss": 3.9902, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290712956223388e-05, + "loss": 3.9823, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.28987599935271e-05, + "loss": 3.987, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890374046016584e-05, + "loss": 3.9813, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288198809850606e-05, + "loss": 3.9834, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287360215099554e-05, + "loss": 3.9747, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286521620348502e-05, + "loss": 3.9717, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.28568302559745e-05, + "loss": 3.9773, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284844430846398e-05, + "loss": 3.9807, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284005836095346e-05, + "loss": 3.9708, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283167241344294e-05, + "loss": 3.9733, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282328646593242e-05, + "loss": 3.9703, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.28149005184219e-05, + "loss": 3.9796, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280651457091138e-05, + "loss": 3.9783, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2798145002204586e-05, + "loss": 3.9809, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2789759054694066e-05, + "loss": 3.9811, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2781373107183546e-05, + "loss": 3.9874, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277298715967303e-05, + "loss": 3.9806, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276461759096624e-05, + "loss": 3.9813, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275623164345572e-05, + "loss": 3.9896, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.27478456959452e-05, + "loss": 3.9879, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273945974843468e-05, + "loss": 3.9818, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273109017972789e-05, + "loss": 3.9873, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272270423221737e-05, + "loss": 3.9795, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271431828470685e-05, + "loss": 3.9772, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270593233719633e-05, + "loss": 3.9708, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269756276848954e-05, + "loss": 3.9815, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268917682097902e-05, + "loss": 3.9721, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.26807908734685e-05, + "loss": 3.9759, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672404925957987e-05, + "loss": 3.9733, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664018978447467e-05, + "loss": 3.986, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265563303093694e-05, + "loss": 3.9823, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264724708342642e-05, + "loss": 3.9744, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2638877514719636e-05, + "loss": 3.9878, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630491567209115e-05, + "loss": 3.9864, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262210561969859e-05, + "loss": 3.9886, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261371967218807e-05, + "loss": 3.9793, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260533372467755e-05, + "loss": 3.9771, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596964155970764e-05, + "loss": 3.9936, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258857820846024e-05, + "loss": 3.9806, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580192260949724e-05, + "loss": 3.9838, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2571806313439204e-05, + "loss": 3.9756, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563436744732413e-05, + "loss": 3.9815, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255505079722189e-05, + "loss": 3.9775, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254668122851511e-05, + "loss": 3.975, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253829528100459e-05, + "loss": 3.9809, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252990933349406e-05, + "loss": 3.9797, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252152338598354e-05, + "loss": 3.9846, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251315381727676e-05, + "loss": 3.9825, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.031160354614258, + "eval_runtime": 295.5316, + "eval_samples_per_second": 1291.202, + "eval_steps_per_second": 40.351, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250476786976624e-05, + "loss": 3.9639, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249638192225571e-05, + "loss": 3.9693, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248799597474519e-05, + "loss": 3.9719, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247961002723468e-05, + "loss": 3.9866, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247122407972416e-05, + "loss": 3.9801, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246283813221364e-05, + "loss": 3.9899, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245445218470312e-05, + "loss": 3.9724, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24460662371926e-05, + "loss": 3.973, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243768028968208e-05, + "loss": 3.968, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242929434217156e-05, + "loss": 3.9793, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242090839466104e-05, + "loss": 3.9813, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241252244715052e-05, + "loss": 3.9795, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240415287844373e-05, + "loss": 3.9857, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239576693093321e-05, + "loss": 3.9638, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238738098342269e-05, + "loss": 3.9718, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237899503591217e-05, + "loss": 3.9641, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2370609088401647e-05, + "loss": 3.9788, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2362223140891127e-05, + "loss": 3.972, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353837193380606e-05, + "loss": 3.9786, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234546762467382e-05, + "loss": 3.9715, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.23370816771633e-05, + "loss": 3.9926, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2328695729652775e-05, + "loss": 3.9771, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2320309782142255e-05, + "loss": 3.9774, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2311923834631735e-05, + "loss": 3.9772, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303537887121215e-05, + "loss": 3.9834, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295151939610695e-05, + "loss": 3.9782, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286765992100175e-05, + "loss": 3.9694, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278380044589655e-05, + "loss": 3.9768, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2270010475882864e-05, + "loss": 3.966, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261624528372344e-05, + "loss": 3.9713, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253238580861824e-05, + "loss": 3.9768, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224485263335131e-05, + "loss": 3.9734, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223646668584079e-05, + "loss": 3.9756, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222808073833027e-05, + "loss": 3.9849, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221969479081975e-05, + "loss": 3.9767, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221130884330923e-05, + "loss": 3.9811, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220293927460244e-05, + "loss": 3.9799, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219455332709192e-05, + "loss": 3.9638, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21861673795814e-05, + "loss": 3.9822, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217779781087461e-05, + "loss": 3.9717, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216941186336409e-05, + "loss": 3.9703, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216102591585357e-05, + "loss": 3.978, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215263996834305e-05, + "loss": 3.9811, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214425402083253e-05, + "loss": 3.964, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135884452125745e-05, + "loss": 3.9862, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127498504615225e-05, + "loss": 3.9756, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119112557104705e-05, + "loss": 3.9772, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110726609594184e-05, + "loss": 3.9801, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102340662083664e-05, + "loss": 3.9468, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209395471457314e-05, + "loss": 3.9712, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208556876706262e-05, + "loss": 3.9787, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.20771828195521e-05, + "loss": 3.9776, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206879687204158e-05, + "loss": 3.9627, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206041092453106e-05, + "loss": 3.9599, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205202497702054e-05, + "loss": 3.9577, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043655408313746e-05, + "loss": 3.9617, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203526946080323e-05, + "loss": 3.9872, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202688351329271e-05, + "loss": 3.9526, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201851394458592e-05, + "loss": 3.9813, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20101279970754e-05, + "loss": 3.9708, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200174204956488e-05, + "loss": 3.9579, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199335610205436e-05, + "loss": 3.9714, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198497015454384e-05, + "loss": 3.9616, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197658420703332e-05, + "loss": 3.9611, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.19681982595228e-05, + "loss": 3.9586, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195981231201228e-05, + "loss": 3.979, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195144274330549e-05, + "loss": 3.9688, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.19430731745987e-05, + "loss": 3.9639, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193468722708819e-05, + "loss": 3.96, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192630127957767e-05, + "loss": 3.9658, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917931710870876e-05, + "loss": 3.98, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909545763360356e-05, + "loss": 3.9782, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1901159815849836e-05, + "loss": 3.9743, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1892773868339316e-05, + "loss": 3.9799, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884387920828796e-05, + "loss": 3.9911, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1876001973318276e-05, + "loss": 3.976, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867616025807756e-05, + "loss": 3.9789, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859230078297236e-05, + "loss": 3.9684, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850844130786716e-05, + "loss": 3.9717, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842458183276196e-05, + "loss": 3.968, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834072235765675e-05, + "loss": 3.9656, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825686288255155e-05, + "loss": 3.9815, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817316719548365e-05, + "loss": 3.9862, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180894715084158e-05, + "loss": 3.9791, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180056120333106e-05, + "loss": 3.9561, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179217525582054e-05, + "loss": 3.964, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178378930831002e-05, + "loss": 3.9737, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177541973960323e-05, + "loss": 3.9746, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176703379209271e-05, + "loss": 3.9657, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175864784458219e-05, + "loss": 3.9736, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175026189707167e-05, + "loss": 3.9679, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174187594956115e-05, + "loss": 3.9658, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173349000205062e-05, + "loss": 3.9656, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17251040545401e-05, + "loss": 3.9804, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171673448583332e-05, + "loss": 3.9696, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17083485383228e-05, + "loss": 3.9824, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169996259081228e-05, + "loss": 3.9635, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169157664330176e-05, + "loss": 3.9652, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168319069579124e-05, + "loss": 3.9752, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167480474828072e-05, + "loss": 3.9756, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.16664188007702e-05, + "loss": 3.9785, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165804923206341e-05, + "loss": 3.9702, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164966328455289e-05, + "loss": 3.9732, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164127733704237e-05, + "loss": 3.9701, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163289138953185e-05, + "loss": 3.9749, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162450544202133e-05, + "loss": 3.9565, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161611949451081e-05, + "loss": 3.9644, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160773354700029e-05, + "loss": 3.9637, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1599347599489773e-05, + "loss": 3.9674, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1590961651979253e-05, + "loss": 3.9611, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1582575704468733e-05, + "loss": 3.9589, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157418975695821e-05, + "loss": 3.9534, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156583656705515e-05, + "loss": 3.9713, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155745061954463e-05, + "loss": 3.9651, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154906467203411e-05, + "loss": 3.9676, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154067872452359e-05, + "loss": 3.97, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153229277701307e-05, + "loss": 3.9748, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152390682950255e-05, + "loss": 3.9695, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151552088199203e-05, + "loss": 3.9665, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150713493448151e-05, + "loss": 3.979, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149874898697099e-05, + "loss": 3.9743, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149036303946047e-05, + "loss": 3.9656, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148197709194995e-05, + "loss": 3.9734, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147360752324316e-05, + "loss": 3.9686, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146522157573264e-05, + "loss": 3.9671, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145683562822212e-05, + "loss": 3.9558, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448466059515336e-05, + "loss": 3.9718, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144008011200481e-05, + "loss": 3.9592, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143169416449429e-05, + "loss": 3.9638, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142330821698377e-05, + "loss": 3.9546, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141492226947325e-05, + "loss": 3.9778, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140653632196273e-05, + "loss": 3.9723, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139815037445221e-05, + "loss": 3.9581, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389764426941696e-05, + "loss": 3.9773, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381378479431176e-05, + "loss": 3.9722, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1372992531920656e-05, + "loss": 3.976, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1364606584410136e-05, + "loss": 3.968, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356220636899616e-05, + "loss": 3.9708, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347834689389095e-05, + "loss": 3.9807, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339465120682305e-05, + "loss": 3.9659, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1331095551975514e-05, + "loss": 3.9741, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1322709604464994e-05, + "loss": 3.9629, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1314323656954474e-05, + "loss": 3.9717, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1305937709443954e-05, + "loss": 3.9647, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1297551761933434e-05, + "loss": 3.9611, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128918219322665e-05, + "loss": 3.969, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128079624571613e-05, + "loss": 3.9659, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127242667700934e-05, + "loss": 3.974, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126404072949882e-05, + "loss": 3.9698, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.02421236038208, + "eval_runtime": 306.3935, + "eval_samples_per_second": 1245.428, + "eval_steps_per_second": 38.921, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.12556547819883e-05, + "loss": 3.9621, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124726883447778e-05, + "loss": 3.9627, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123888288696726e-05, + "loss": 3.9604, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123049693945674e-05, + "loss": 3.9705, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122211099194622e-05, + "loss": 3.9669, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.12137250444357e-05, + "loss": 3.9794, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120533909692517e-05, + "loss": 3.958, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119695314941465e-05, + "loss": 3.9603, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118856720190413e-05, + "loss": 3.9547, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118019763319735e-05, + "loss": 3.9694, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117181168568683e-05, + "loss": 3.9638, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116344211698004e-05, + "loss": 3.9722, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115505616946952e-05, + "loss": 3.9734, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146670221958996e-05, + "loss": 3.9533, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138284274448476e-05, + "loss": 3.9572, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129898326937956e-05, + "loss": 3.9554, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121512379427436e-05, + "loss": 3.9639, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113126431916916e-05, + "loss": 3.9628, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1104740484406396e-05, + "loss": 3.9668, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1096354536895876e-05, + "loss": 3.9587, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1087984968189085e-05, + "loss": 3.9796, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079599020678565e-05, + "loss": 3.963, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107121307316805e-05, + "loss": 3.968, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106282712565753e-05, + "loss": 3.9674, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105444117814701e-05, + "loss": 3.9717, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104605523063649e-05, + "loss": 3.9648, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103766928312597e-05, + "loss": 3.9579, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102929971441918e-05, + "loss": 3.9638, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102091376690866e-05, + "loss": 3.9523, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101252781939814e-05, + "loss": 3.9627, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100414187188762e-05, + "loss": 3.9604, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.09957559243771e-05, + "loss": 3.9654, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098736997686658e-05, + "loss": 3.9632, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0978984029356053e-05, + "loss": 3.9695, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970598081845533e-05, + "loss": 3.9703, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096222851313875e-05, + "loss": 3.9677, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953858944431965e-05, + "loss": 3.9677, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0945472996921445e-05, + "loss": 3.9549, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937087049410925e-05, + "loss": 3.972, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928717480704134e-05, + "loss": 3.9603, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920331533193614e-05, + "loss": 3.959, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0911945585683094e-05, + "loss": 3.967, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0903559638172574e-05, + "loss": 3.9684, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0895173690662054e-05, + "loss": 3.9554, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088678774315153e-05, + "loss": 3.9696, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087840179564101e-05, + "loss": 3.9658, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087001584813049e-05, + "loss": 3.9644, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0861629900619974e-05, + "loss": 3.9691, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853243953109454e-05, + "loss": 3.9367, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0844858005598934e-05, + "loss": 3.9541, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9691, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9658, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.9514, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9432, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080296102565379e-05, + "loss": 3.9514, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079457507814327e-05, + "loss": 3.9443, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078620550943648e-05, + "loss": 3.9777, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077781956192596e-05, + "loss": 3.9412, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076943361441544e-05, + "loss": 3.9677, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076104766690493e-05, + "loss": 3.9582, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075266171939441e-05, + "loss": 3.9486, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074427577188389e-05, + "loss": 3.9581, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0735906203177096e-05, + "loss": 3.952, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0727520255666576e-05, + "loss": 3.9489, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719134308156056e-05, + "loss": 3.945, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710748360645536e-05, + "loss": 3.9691, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702362413135016e-05, + "loss": 3.9556, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0693992844428225e-05, + "loss": 3.9508, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685606896917705e-05, + "loss": 3.9448, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677220949407185e-05, + "loss": 3.9556, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668835001896665e-05, + "loss": 3.9665, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660449054386145e-05, + "loss": 3.9693, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652063106875625e-05, + "loss": 3.9633, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0643677159365105e-05, + "loss": 3.9652, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063529121185459e-05, + "loss": 3.9787, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.06269216431478e-05, + "loss": 3.9685, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061853569563728e-05, + "loss": 3.9661, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061014974812676e-05, + "loss": 3.954, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060176380061624e-05, + "loss": 3.9621, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059337785310572e-05, + "loss": 3.9549, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058500828439893e-05, + "loss": 3.957, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057662233688841e-05, + "loss": 3.9685, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056823638937789e-05, + "loss": 3.976, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.055985044186736e-05, + "loss": 3.9634, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551497251964315e-05, + "loss": 3.9472, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543111304453795e-05, + "loss": 3.9515, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534725356943275e-05, + "loss": 3.9587, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526339409432755e-05, + "loss": 3.9681, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0517953461922235e-05, + "loss": 3.951, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509567514411715e-05, + "loss": 3.9625, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501181566901188e-05, + "loss": 3.961, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492811998194404e-05, + "loss": 3.9515, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484426050683884e-05, + "loss": 3.9556, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476040103173363e-05, + "loss": 3.9659, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046765415566284e-05, + "loss": 3.9573, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.045926820815232e-05, + "loss": 3.9704, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.04508822606418e-05, + "loss": 3.9542, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044249631313128e-05, + "loss": 3.9541, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043411036562076e-05, + "loss": 3.96, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425740796913972e-05, + "loss": 3.9668, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417354849403452e-05, + "loss": 3.964, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0408968901892932e-05, + "loss": 3.9606, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400582954382412e-05, + "loss": 3.9625, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039221338567562e-05, + "loss": 3.959, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.03838274381651e-05, + "loss": 3.9592, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037544149065458e-05, + "loss": 3.9449, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036705554314406e-05, + "loss": 3.9498, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358669595633545e-05, + "loss": 3.9572, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350283648123024e-05, + "loss": 3.9548, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341897700612504e-05, + "loss": 3.9516, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333511753101984e-05, + "loss": 3.95, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325142184395194e-05, + "loss": 3.9435, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316756236884673e-05, + "loss": 3.9587, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308370289374153e-05, + "loss": 3.9498, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0299984341863637e-05, + "loss": 3.9595, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291631151960575e-05, + "loss": 3.9543, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283245204450055e-05, + "loss": 3.9654, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274859256939535e-05, + "loss": 3.9597, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266473309429015e-05, + "loss": 3.9562, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258087361918498e-05, + "loss": 3.9634, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249701414407978e-05, + "loss": 3.9631, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241331845701187e-05, + "loss": 3.9584, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232962276994396e-05, + "loss": 3.9616, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224576329483876e-05, + "loss": 3.9587, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021619038197336e-05, + "loss": 3.9586, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020780443446284e-05, + "loss": 3.9491, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019941848695232e-05, + "loss": 3.9537, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.01910325394418e-05, + "loss": 3.9495, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018264659193128e-05, + "loss": 3.9511, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017426064442076e-05, + "loss": 3.9433, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016587469691024e-05, + "loss": 3.9715, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015748874939972e-05, + "loss": 3.9611, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149119180692932e-05, + "loss": 3.9545, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140733233182412e-05, + "loss": 3.9599, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132347285671892e-05, + "loss": 3.9587, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0123961338161372e-05, + "loss": 3.9677, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011557539065085e-05, + "loss": 3.9602, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107189443140328e-05, + "loss": 3.9561, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098803495629808e-05, + "loss": 3.9677, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090417548119288e-05, + "loss": 3.9525, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082047979412497e-05, + "loss": 3.9649, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073662031901977e-05, + "loss": 3.9532, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065276084391457e-05, + "loss": 3.9641, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056890136880937e-05, + "loss": 3.9579, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004852056817415e-05, + "loss": 3.9455, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004013462066363e-05, + "loss": 3.961, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003174867315311e-05, + "loss": 3.9569, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023379104446325e-05, + "loss": 3.96, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015009535739534e-05, + "loss": 3.9579, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006623588229014e-05, + "loss": 3.9569, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.018248081207275, + "eval_runtime": 304.9323, + "eval_samples_per_second": 1251.396, + "eval_steps_per_second": 39.107, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998237640718498e-05, + "loss": 3.9487, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.998985169320797e-05, + "loss": 3.9461, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998146574569745e-05, + "loss": 3.9622, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997307979818693e-05, + "loss": 3.9585, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996469385067641e-05, + "loss": 3.968, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995630790316589e-05, + "loss": 3.9476, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947921955655374e-05, + "loss": 3.9496, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939536008144854e-05, + "loss": 3.9404, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931150060634334e-05, + "loss": 3.9617, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922764113123814e-05, + "loss": 3.9531, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914378165613294e-05, + "loss": 3.9609, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905992218102774e-05, + "loss": 3.9601, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897622649395983e-05, + "loss": 3.9488, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889253080689195e-05, + "loss": 3.9485, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880867133178675e-05, + "loss": 3.9462, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872481185668155e-05, + "loss": 3.9454, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864095238157635e-05, + "loss": 3.955, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855709290647115e-05, + "loss": 3.9542, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847323343136595e-05, + "loss": 3.9463, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838937395626075e-05, + "loss": 3.9718, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830551448115555e-05, + "loss": 3.9502, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982216550060504e-05, + "loss": 3.9585, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981377955309451e-05, + "loss": 3.9547, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980539360558399e-05, + "loss": 3.9615, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979700765807347e-05, + "loss": 3.9504, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.978862171056295e-05, + "loss": 3.9522, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978023576305243e-05, + "loss": 3.9487, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771849815541915e-05, + "loss": 3.9496, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763463868031395e-05, + "loss": 3.9473, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755094299324604e-05, + "loss": 3.9486, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9746708351814084e-05, + "loss": 3.9577, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738338783107293e-05, + "loss": 3.9542, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9729952835596776e-05, + "loss": 3.9581, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721566888086256e-05, + "loss": 3.9599, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713180940575736e-05, + "loss": 3.959, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704794993065216e-05, + "loss": 3.9566, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696425424358425e-05, + "loss": 3.9486, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688039476847905e-05, + "loss": 3.9539, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679653529337385e-05, + "loss": 3.9498, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967126758182687e-05, + "loss": 3.9527, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966288163431635e-05, + "loss": 3.9537, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965449568680583e-05, + "loss": 3.9576, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964610973929531e-05, + "loss": 3.9453, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963772379178479e-05, + "loss": 3.9579, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.962937060188173e-05, + "loss": 3.9575, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962098465437121e-05, + "loss": 3.957, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961259870686069e-05, + "loss": 3.9562, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960421275935017e-05, + "loss": 3.9285, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959582681183965e-05, + "loss": 3.9448, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958744086432913e-05, + "loss": 3.956, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.957907129562234e-05, + "loss": 3.9549, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570685348111822e-05, + "loss": 3.9444, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562299400601302e-05, + "loss": 3.9347, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553913453090782e-05, + "loss": 3.94, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545527505580262e-05, + "loss": 3.9334, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537141558069742e-05, + "loss": 3.9645, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.952877198936295e-05, + "loss": 3.9356, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520402420656164e-05, + "loss": 3.9529, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512016473145644e-05, + "loss": 3.9532, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503630525635123e-05, + "loss": 3.9338, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495244578124603e-05, + "loss": 3.947, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486858630614083e-05, + "loss": 3.9426, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478472683103563e-05, + "loss": 3.9356, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470086735593043e-05, + "loss": 3.9342, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946170078808252e-05, + "loss": 3.9606, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453314840572e-05, + "loss": 3.9483, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944492889306148e-05, + "loss": 3.9398, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943654294555096e-05, + "loss": 3.9367, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942815699804044e-05, + "loss": 3.9445, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419787429333652e-05, + "loss": 3.9546, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411417860626868e-05, + "loss": 3.9593, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403031913116348e-05, + "loss": 3.9517, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939464596560582e-05, + "loss": 3.9603, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.93862600180953e-05, + "loss": 3.9643, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377890449388517e-05, + "loss": 3.9577, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936952088068173e-05, + "loss": 3.954, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936113493317121e-05, + "loss": 3.9473, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935274898566069e-05, + "loss": 3.9532, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934436303815017e-05, + "loss": 3.949, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335977090639643e-05, + "loss": 3.9464, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327591143129123e-05, + "loss": 3.9548, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319205195618606e-05, + "loss": 3.9621, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310819248108086e-05, + "loss": 3.9574, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302433300597566e-05, + "loss": 3.9361, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294047353087046e-05, + "loss": 3.9383, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9285661405576526e-05, + "loss": 3.9494, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9277275458066006e-05, + "loss": 3.9566, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268889510555486e-05, + "loss": 3.9432, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260519941848698e-05, + "loss": 3.9502, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252133994338178e-05, + "loss": 3.9558, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243748046827658e-05, + "loss": 3.9428, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235378478120867e-05, + "loss": 3.9441, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226992530610347e-05, + "loss": 3.9522, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218606583099827e-05, + "loss": 3.9499, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210220635589307e-05, + "loss": 3.9582, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201834688078787e-05, + "loss": 3.9519, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919344874056827e-05, + "loss": 3.9379, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918506279305775e-05, + "loss": 3.953, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917669322435096e-05, + "loss": 3.9536, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916830727684044e-05, + "loss": 3.9499, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.915992132932992e-05, + "loss": 3.9552, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.91515353818194e-05, + "loss": 3.949, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914314943430888e-05, + "loss": 3.951, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134763486798356e-05, + "loss": 3.9543, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126377539287836e-05, + "loss": 3.9332, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9117991591777316e-05, + "loss": 3.9388, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109605644266796e-05, + "loss": 3.9483, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101219696756276e-05, + "loss": 3.9458, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092850128049488e-05, + "loss": 3.9375, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084464180538968e-05, + "loss": 3.9404, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076078233028448e-05, + "loss": 3.9412, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067692285517928e-05, + "loss": 3.9464, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059306338007408e-05, + "loss": 3.9413, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050920390496888e-05, + "loss": 3.9472, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042534442986368e-05, + "loss": 3.9461, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034148495475848e-05, + "loss": 3.953, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902577892676906e-05, + "loss": 3.9511, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901739297925854e-05, + "loss": 3.9489, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.900900703174802e-05, + "loss": 3.9532, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900063746304123e-05, + "loss": 3.9541, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899225151553071e-05, + "loss": 3.9442, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983865568020192e-05, + "loss": 3.9548, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975479620509672e-05, + "loss": 3.9442, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967093672999152e-05, + "loss": 3.9552, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.895872410429236e-05, + "loss": 3.9338, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895033815678184e-05, + "loss": 3.9492, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894195220927132e-05, + "loss": 3.9342, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.89335662617608e-05, + "loss": 3.9389, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925180314250285e-05, + "loss": 3.932, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916794366739765e-05, + "loss": 3.9612, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908424798032974e-05, + "loss": 3.9568, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900038850522454e-05, + "loss": 3.9411, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891652903011934e-05, + "loss": 3.9477, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883266955501414e-05, + "loss": 3.9484, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874881007990894e-05, + "loss": 3.9576, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886649506048037e-05, + "loss": 3.9524, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885810911296985e-05, + "loss": 3.9445, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.884972316545933e-05, + "loss": 3.9569, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884135359675254e-05, + "loss": 3.9436, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8832984028045755e-05, + "loss": 3.9565, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882459808053524e-05, + "loss": 3.9453, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881621213302472e-05, + "loss": 3.9494, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880782618551419e-05, + "loss": 3.9483, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.879944023800367e-05, + "loss": 3.9405, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879105429049315e-05, + "loss": 3.9505, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878266834298263e-05, + "loss": 3.9474, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774298774275844e-05, + "loss": 3.9498, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765912826765324e-05, + "loss": 3.9497, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757526879254804e-05, + "loss": 3.9431, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.013632774353027, + "eval_runtime": 279.0511, + "eval_samples_per_second": 1367.459, + "eval_steps_per_second": 42.734, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749140931744284e-05, + "loss": 3.9396, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740754984233764e-05, + "loss": 3.9399, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8732369036723244e-05, + "loss": 3.9532, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8723983089212724e-05, + "loss": 3.943, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715597141702204e-05, + "loss": 3.9623, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707211194191687e-05, + "loss": 3.9374, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698841625484896e-05, + "loss": 3.942, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690455677974376e-05, + "loss": 3.9313, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682086109267585e-05, + "loss": 3.9512, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673700161757065e-05, + "loss": 3.9462, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866531421424655e-05, + "loss": 3.9482, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8656928266736028e-05, + "loss": 3.9482, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648558698029237e-05, + "loss": 3.9382, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640172750518717e-05, + "loss": 3.9401, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631786803008197e-05, + "loss": 3.9387, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623400855497677e-05, + "loss": 3.9343, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861503128679089e-05, + "loss": 3.9447, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860664533928037e-05, + "loss": 3.9447, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859825939176985e-05, + "loss": 3.9402, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.858987344425933e-05, + "loss": 3.9628, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858148749674881e-05, + "loss": 3.9384, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857310154923829e-05, + "loss": 3.9492, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856471560172777e-05, + "loss": 3.948, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556346033020982e-05, + "loss": 3.9549, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547960085510462e-05, + "loss": 3.9333, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539574137999942e-05, + "loss": 3.9444, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531188190489422e-05, + "loss": 3.9387, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522802242978902e-05, + "loss": 3.9471, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851441629546838e-05, + "loss": 3.9328, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506030347957858e-05, + "loss": 3.9373, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497644400447338e-05, + "loss": 3.9488, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489274831740554e-05, + "loss": 3.9444, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480905263033763e-05, + "loss": 3.9446, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472519315523243e-05, + "loss": 3.9537, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464133368012723e-05, + "loss": 3.9488, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.84557474205022e-05, + "loss": 3.9456, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844736147299168e-05, + "loss": 3.9396, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.843897552548116e-05, + "loss": 3.9475, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843058957797064e-05, + "loss": 3.9372, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842220363046012e-05, + "loss": 3.9433, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.84138176829496e-05, + "loss": 3.9465, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405448114242812e-05, + "loss": 3.9476, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397078545536028e-05, + "loss": 3.9345, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.83886925980255e-05, + "loss": 3.9444, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838030665051498e-05, + "loss": 3.9529, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837192070300446e-05, + "loss": 3.9469, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836353475549394e-05, + "loss": 3.948, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8355148807983424e-05, + "loss": 3.9198, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346762860472904e-05, + "loss": 3.9319, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338393291766113e-05, + "loss": 3.9486, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8330023723059322e-05, + "loss": 3.9439, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321637775548802e-05, + "loss": 3.9375, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313251828038286e-05, + "loss": 3.9242, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304865880527766e-05, + "loss": 3.9293, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296496311820975e-05, + "loss": 3.926, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288110364310455e-05, + "loss": 3.9518, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279724416799935e-05, + "loss": 3.9273, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271338469289415e-05, + "loss": 3.9437, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262952521778895e-05, + "loss": 3.9465, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254566574268378e-05, + "loss": 3.9282, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246197005561587e-05, + "loss": 3.9367, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237811058051067e-05, + "loss": 3.931, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229425110540547e-05, + "loss": 3.9285, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8221039163030027e-05, + "loss": 3.9288, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821266959432324e-05, + "loss": 3.9456, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820428364681272e-05, + "loss": 3.9408, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.81958976993022e-05, + "loss": 3.9277, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818751175179168e-05, + "loss": 3.9293, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.817912580428116e-05, + "loss": 3.933, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817073985677064e-05, + "loss": 3.945, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816235390926012e-05, + "loss": 3.9507, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.81539679617496e-05, + "loss": 3.9415, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814558201423908e-05, + "loss": 3.9518, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813721244553229e-05, + "loss": 3.9502, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.812882649802177e-05, + "loss": 3.9496, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812044055051125e-05, + "loss": 3.942, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811207098180446e-05, + "loss": 3.9402, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810368503429394e-05, + "loss": 3.9426, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809529908678342e-05, + "loss": 3.9393, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086929518076633e-05, + "loss": 3.936, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078543570566113e-05, + "loss": 3.9453, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070157623055593e-05, + "loss": 3.9532, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061771675545073e-05, + "loss": 3.9441, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053385728034553e-05, + "loss": 3.9323, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044999780524033e-05, + "loss": 3.9311, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803661383301351e-05, + "loss": 3.9361, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802822788550299e-05, + "loss": 3.9479, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801984193799247e-05, + "loss": 3.9357, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011472369285685e-05, + "loss": 3.9398, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8003086421775158e-05, + "loss": 3.9435, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799470047426464e-05, + "loss": 3.9347, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798631452675412e-05, + "loss": 3.9353, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.79779285792436e-05, + "loss": 3.9361, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796955901053681e-05, + "loss": 3.9426, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796117306302629e-05, + "loss": 3.9446, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795278711551577e-05, + "loss": 3.9459, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794440116800525e-05, + "loss": 3.9305, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7936015220494734e-05, + "loss": 3.9438, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927645651787943e-05, + "loss": 3.9405, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919259704277423e-05, + "loss": 3.9481, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910873756766903e-05, + "loss": 3.9424, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902487809256383e-05, + "loss": 3.9435, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894101861745863e-05, + "loss": 3.9395, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885715914235343e-05, + "loss": 3.9454, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877329966724826e-05, + "loss": 3.925, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868944019214306e-05, + "loss": 3.929, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860590829311244e-05, + "loss": 3.9381, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852204881800724e-05, + "loss": 3.9351, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843818934290204e-05, + "loss": 3.9297, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835432986779687e-05, + "loss": 3.9323, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827063418072897e-05, + "loss": 3.9303, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818677470562376e-05, + "loss": 3.9373, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810291523051856e-05, + "loss": 3.9324, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801905575541336e-05, + "loss": 3.9357, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793519628030816e-05, + "loss": 3.9382, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785133680520296e-05, + "loss": 3.9445, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777674773300978e-05, + "loss": 3.9407, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776837816430299e-05, + "loss": 3.9387, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.775999221679247e-05, + "loss": 3.9464, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775160626928195e-05, + "loss": 3.9443, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774322032177143e-05, + "loss": 3.9345, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773483437426091e-05, + "loss": 3.9468, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772646480555412e-05, + "loss": 3.9357, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.77180788580436e-05, + "loss": 3.948, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.770969291053308e-05, + "loss": 3.9211, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770130696302256e-05, + "loss": 3.9438, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769292101551204e-05, + "loss": 3.9241, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684567825608982e-05, + "loss": 3.9292, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676181878098462e-05, + "loss": 3.9226, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667795930587942e-05, + "loss": 3.952, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659409983077422e-05, + "loss": 3.947, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651024035566902e-05, + "loss": 3.9364, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642638088056382e-05, + "loss": 3.934, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634252140545862e-05, + "loss": 3.9416, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625866193035342e-05, + "loss": 3.947, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761748024552482e-05, + "loss": 3.9427, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609127055621764e-05, + "loss": 3.9396, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600741108111244e-05, + "loss": 3.9431, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592355160600724e-05, + "loss": 3.9368, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583969213090204e-05, + "loss": 3.9508, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575583265579687e-05, + "loss": 3.9342, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567197318069167e-05, + "loss": 3.9373, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.755881137055864e-05, + "loss": 3.9376, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755042542304812e-05, + "loss": 3.9312, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.75420394755376e-05, + "loss": 3.9416, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753365352802708e-05, + "loss": 3.9375, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525267580516563e-05, + "loss": 3.943, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516881633006043e-05, + "loss": 3.9393, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508512064299252e-05, + "loss": 3.9342, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.009161949157715, + "eval_runtime": 283.2227, + "eval_samples_per_second": 1347.318, + "eval_steps_per_second": 42.105, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500126116788732e-05, + "loss": 3.9298, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491740169278212e-05, + "loss": 3.9287, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483354221767692e-05, + "loss": 3.9433, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7474968274257172e-05, + "loss": 3.9314, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466582326746652e-05, + "loss": 3.9551, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458196379236135e-05, + "loss": 3.9278, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449810431725615e-05, + "loss": 3.9347, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441424484215095e-05, + "loss": 3.9224, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7433038536704575e-05, + "loss": 3.9417, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424652589194055e-05, + "loss": 3.9371, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741626664168353e-05, + "loss": 3.939, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407880694173012e-05, + "loss": 3.9392, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399511125466228e-05, + "loss": 3.9275, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391125177955708e-05, + "loss": 3.9338, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738273923044518e-05, + "loss": 3.9311, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737435328293466e-05, + "loss": 3.9288, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736596733542414e-05, + "loss": 3.9309, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735758138791362e-05, + "loss": 3.9364, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349195440403104e-05, + "loss": 3.9296, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340809492892584e-05, + "loss": 3.9543, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332423545382064e-05, + "loss": 3.9301, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7324037597871544e-05, + "loss": 3.9378, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315651650361024e-05, + "loss": 3.9376, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307265702850504e-05, + "loss": 3.9437, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298896134143713e-05, + "loss": 3.9268, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290510186633196e-05, + "loss": 3.9379, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282124239122676e-05, + "loss": 3.9292, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273738291612156e-05, + "loss": 3.9369, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265385101709094e-05, + "loss": 3.925, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7256999154198574e-05, + "loss": 3.9298, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248613206688058e-05, + "loss": 3.9355, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240227259177538e-05, + "loss": 3.9388, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7231857690470747e-05, + "loss": 3.937, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223471742960227e-05, + "loss": 3.9427, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215085795449707e-05, + "loss": 3.9368, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206699847939187e-05, + "loss": 3.9387, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198313900428667e-05, + "loss": 3.9282, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.718992795291815e-05, + "loss": 3.942, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718154200540763e-05, + "loss": 3.9285, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717315605789711e-05, + "loss": 3.9338, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716478648919032e-05, + "loss": 3.9366, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.71564005416798e-05, + "loss": 3.9397, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714801459416928e-05, + "loss": 3.932, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713962864665876e-05, + "loss": 3.9315, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7131242699148242e-05, + "loss": 3.9447, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7122856751637715e-05, + "loss": 3.938, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711448718293093e-05, + "loss": 3.939, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710610123542041e-05, + "loss": 3.9206, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709771528790989e-05, + "loss": 3.9187, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089329340399368e-05, + "loss": 3.9362, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080959771692584e-05, + "loss": 3.9359, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072573824182064e-05, + "loss": 3.9302, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064187876671543e-05, + "loss": 3.9153, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7055801929161017e-05, + "loss": 3.9204, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047415981650497e-05, + "loss": 3.9239, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.703903003413998e-05, + "loss": 3.9354, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703064408662946e-05, + "loss": 3.9189, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702227451792267e-05, + "loss": 3.9337, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701388857041215e-05, + "loss": 3.9349, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700550262290163e-05, + "loss": 3.9219, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699711667539111e-05, + "loss": 3.9255, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.698873072788059e-05, + "loss": 3.9249, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698034478037007e-05, + "loss": 3.9153, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6971958832859552e-05, + "loss": 3.9262, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963572885349032e-05, + "loss": 3.9305, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695521969544597e-05, + "loss": 3.9377, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694683374793545e-05, + "loss": 3.9139, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.693844780042493e-05, + "loss": 3.9217, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6930061852914414e-05, + "loss": 3.9204, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921675905403894e-05, + "loss": 3.9434, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913289957893373e-05, + "loss": 3.9344, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904904010382853e-05, + "loss": 3.9324, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896518062872333e-05, + "loss": 3.9449, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888148494165542e-05, + "loss": 3.9427, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879762546655022e-05, + "loss": 3.9401, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871392977948235e-05, + "loss": 3.9315, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6863007030437715e-05, + "loss": 3.9337, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6854621082927195e-05, + "loss": 3.9334, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6846235135416675e-05, + "loss": 3.9291, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837865566709884e-05, + "loss": 3.9326, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829479619199367e-05, + "loss": 3.9348, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6821093671688847e-05, + "loss": 3.9433, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812707724178327e-05, + "loss": 3.9333, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804321776667807e-05, + "loss": 3.9279, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795952207961016e-05, + "loss": 3.9188, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787566260450496e-05, + "loss": 3.9313, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779180312939976e-05, + "loss": 3.9375, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677081074423319e-05, + "loss": 3.9294, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676242479672267e-05, + "loss": 3.9283, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675403884921215e-05, + "loss": 3.9373, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674565290170163e-05, + "loss": 3.9209, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673726695419111e-05, + "loss": 3.9309, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.672888100668059e-05, + "loss": 3.9273, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672049505917007e-05, + "loss": 3.9388, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671210911165955e-05, + "loss": 3.936, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6703723164149025e-05, + "loss": 3.9342, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6695337216638505e-05, + "loss": 3.9223, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668696764793172e-05, + "loss": 3.9362, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.66785817004212e-05, + "loss": 3.9258, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670195752910677e-05, + "loss": 3.9431, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661809805400157e-05, + "loss": 3.9325, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653423857889637e-05, + "loss": 3.9345, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645054289182846e-05, + "loss": 3.9279, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636668341672326e-05, + "loss": 3.9415, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628282394161806e-05, + "loss": 3.9147, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.661989644665129e-05, + "loss": 3.9216, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611543256748234e-05, + "loss": 3.9288, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603157309237714e-05, + "loss": 3.9283, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594771361727194e-05, + "loss": 3.9203, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586385414216674e-05, + "loss": 3.9245, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657799946670615e-05, + "loss": 3.9202, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.656961351919563e-05, + "loss": 3.9285, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656122757168511e-05, + "loss": 3.9223, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655284162417459e-05, + "loss": 3.9217, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654445567666407e-05, + "loss": 3.9348, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653608610795728e-05, + "loss": 3.9366, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652770016044676e-05, + "loss": 3.9351, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519314212936243e-05, + "loss": 3.9261, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510928265425723e-05, + "loss": 3.9378, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502542317915203e-05, + "loss": 3.9335, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494156370404683e-05, + "loss": 3.9265, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485770422894163e-05, + "loss": 3.9439, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477384475383643e-05, + "loss": 3.9246, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6468998527873123e-05, + "loss": 3.9362, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460645337970064e-05, + "loss": 3.9164, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452259390459544e-05, + "loss": 3.9348, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6443873442949024e-05, + "loss": 3.9144, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6435487495438504e-05, + "loss": 3.9241, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6427101547927984e-05, + "loss": 3.9164, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418715600417464e-05, + "loss": 3.9404, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410329652906944e-05, + "loss": 3.9362, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6401943705396424e-05, + "loss": 3.9314, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393574136689637e-05, + "loss": 3.9253, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6385188189179117e-05, + "loss": 3.9297, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376802241668597e-05, + "loss": 3.9435, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368416294158077e-05, + "loss": 3.9316, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6360046725451286e-05, + "loss": 3.9282, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351677156744498e-05, + "loss": 3.94, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343307588037707e-05, + "loss": 3.9304, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334921640527187e-05, + "loss": 3.9371, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326535693016667e-05, + "loss": 3.9246, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318149745506147e-05, + "loss": 3.9327, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630976379799563e-05, + "loss": 3.9285, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630137785048511e-05, + "loss": 3.9297, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629299190297459e-05, + "loss": 3.9284, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628460595546407e-05, + "loss": 3.9342, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627622000795355e-05, + "loss": 3.9293, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626783406044303e-05, + "loss": 3.9309, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259448112932507e-05, + "loss": 3.9276, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.005577087402344, + "eval_runtime": 294.6194, + "eval_samples_per_second": 1295.2, + "eval_steps_per_second": 40.476, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6251062165421987e-05, + "loss": 3.9257, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6242708975518932e-05, + "loss": 3.9232, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623432302800841e-05, + "loss": 3.935, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622593708049789e-05, + "loss": 3.9227, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621755113298737e-05, + "loss": 3.9483, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.620916518547685e-05, + "loss": 3.9178, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620077923796633e-05, + "loss": 3.9258, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192393290455808e-05, + "loss": 3.9143, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6184023721749024e-05, + "loss": 3.9327, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175637774238504e-05, + "loss": 3.9307, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167251826727977e-05, + "loss": 3.9261, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.615886587921746e-05, + "loss": 3.9319, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150496310510676e-05, + "loss": 3.9164, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142110363000156e-05, + "loss": 3.9245, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613372441548963e-05, + "loss": 3.9243, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612533846797911e-05, + "loss": 3.9222, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611695252046859e-05, + "loss": 3.9218, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.610856657295807e-05, + "loss": 3.9266, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100180625447553e-05, + "loss": 3.9263, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091794677937033e-05, + "loss": 3.9424, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083408730426513e-05, + "loss": 3.9239, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6075022782915993e-05, + "loss": 3.927, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066636835405472e-05, + "loss": 3.929, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058250887894952e-05, + "loss": 3.938, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.604988131918816e-05, + "loss": 3.9174, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041495371677645e-05, + "loss": 3.9305, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6033125802970854e-05, + "loss": 3.9217, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024739855460334e-05, + "loss": 3.9248, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016353907949814e-05, + "loss": 3.9152, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6007967960439294e-05, + "loss": 3.9265, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.5999582012928774e-05, + "loss": 3.9249, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5991212444221986e-05, + "loss": 3.9316, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5982826496711466e-05, + "loss": 3.9276, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974440549200946e-05, + "loss": 3.9347, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5966054601690426e-05, + "loss": 3.9263, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957668654179906e-05, + "loss": 3.9306, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949299085473115e-05, + "loss": 3.9221, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.59409131379626e-05, + "loss": 3.9324, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593252719045208e-05, + "loss": 3.9191, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924157621745288e-05, + "loss": 3.9263, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5915771674234768e-05, + "loss": 3.928, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907385726724247e-05, + "loss": 3.9335, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898999779213727e-05, + "loss": 3.9228, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890613831703207e-05, + "loss": 3.9257, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588222788419269e-05, + "loss": 3.9319, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587384193668217e-05, + "loss": 3.9296, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865455989171644e-05, + "loss": 3.9301, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5857070041661124e-05, + "loss": 3.9181, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5848684094150604e-05, + "loss": 3.904, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5840298146640084e-05, + "loss": 3.9287, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5831928577933296e-05, + "loss": 3.9249, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5823559009226512e-05, + "loss": 3.9203, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815173061715992e-05, + "loss": 3.9144, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806787114205465e-05, + "loss": 3.9122, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798401166694945e-05, + "loss": 3.9123, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579001521918443e-05, + "loss": 3.9288, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578162927167391e-05, + "loss": 3.914, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577324332416339e-05, + "loss": 3.9222, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576485737665287e-05, + "loss": 3.9303, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575647142914235e-05, + "loss": 3.9145, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748101860435557e-05, + "loss": 3.9151, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.573973229172877e-05, + "loss": 3.9219, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573134634421825e-05, + "loss": 3.9045, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572296039670773e-05, + "loss": 3.9191, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571457444919721e-05, + "loss": 3.9248, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570620488049042e-05, + "loss": 3.927, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.56978189329799e-05, + "loss": 3.9071, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.568943298546938e-05, + "loss": 3.9161, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5681047037958862e-05, + "loss": 3.9104, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672661090448342e-05, + "loss": 3.9309, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664275142937822e-05, + "loss": 3.9279, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5655889195427302e-05, + "loss": 3.9274, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647503247916782e-05, + "loss": 3.9358, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639117300406262e-05, + "loss": 3.9367, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630731352895742e-05, + "loss": 3.935, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622345405385222e-05, + "loss": 3.9197, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613959457874702e-05, + "loss": 3.9258, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605589889167914e-05, + "loss": 3.93, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597203941657394e-05, + "loss": 3.9208, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5588834372950603e-05, + "loss": 3.9269, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5580448425440083e-05, + "loss": 3.9244, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5572062477929563e-05, + "loss": 3.9329, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563676530419047e-05, + "loss": 3.9284, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5555290582908527e-05, + "loss": 3.9118, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546921014201736e-05, + "loss": 3.9148, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538535066691216e-05, + "loss": 3.9231, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530149119180696e-05, + "loss": 3.9276, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521763171670176e-05, + "loss": 3.9222, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513393602963388e-05, + "loss": 3.9191, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5505007655452868e-05, + "loss": 3.9284, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496621707942348e-05, + "loss": 3.9167, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488235760431828e-05, + "loss": 3.9182, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.54798498129213e-05, + "loss": 3.9215, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471463865410784e-05, + "loss": 3.9303, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5463077917900264e-05, + "loss": 3.9322, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454708349193473e-05, + "loss": 3.9246, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446322401682953e-05, + "loss": 3.9103, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437936454172433e-05, + "loss": 3.931, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5429550506661913e-05, + "loss": 3.9147, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5421164559151393e-05, + "loss": 3.9373, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5412778611640877e-05, + "loss": 3.9269, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5404392664130357e-05, + "loss": 3.9254, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5396006716619837e-05, + "loss": 3.9194, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5387620769109316e-05, + "loss": 3.933, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379234821598796e-05, + "loss": 3.9079, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5370848874088276e-05, + "loss": 3.9178, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5362479305381485e-05, + "loss": 3.9145, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535409335787097e-05, + "loss": 3.9206, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534570741036045e-05, + "loss": 3.9124, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337337841653658e-05, + "loss": 3.9201, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328951894143138e-05, + "loss": 3.9151, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320565946632618e-05, + "loss": 3.914, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312179999122098e-05, + "loss": 3.9189, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303794051611578e-05, + "loss": 3.9117, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529542448290479e-05, + "loss": 3.9308, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528703853539427e-05, + "loss": 3.9269, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.527865258788375e-05, + "loss": 3.9275, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527026664037323e-05, + "loss": 3.9182, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526188069286271e-05, + "loss": 3.9283, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525349474535219e-05, + "loss": 3.9303, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245125176645402e-05, + "loss": 3.9184, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236739229134882e-05, + "loss": 3.9313, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228353281624362e-05, + "loss": 3.9181, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5219967334113836e-05, + "loss": 3.9271, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211581386603315e-05, + "loss": 3.9146, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203195439092795e-05, + "loss": 3.9243, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519480949158228e-05, + "loss": 3.9063, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186439922875488e-05, + "loss": 3.9159, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5178053975364968e-05, + "loss": 3.9091, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169668027854448e-05, + "loss": 3.9272, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161282080343928e-05, + "loss": 3.9238, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152896132833408e-05, + "loss": 3.9272, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.514452656412662e-05, + "loss": 3.9185, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.51361406166161e-05, + "loss": 3.9243, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512777104790931e-05, + "loss": 3.9326, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.511938510039879e-05, + "loss": 3.9212, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511099915288827e-05, + "loss": 3.9222, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102629584181485e-05, + "loss": 3.9314, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509424363667096e-05, + "loss": 3.9226, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508585768916044e-05, + "loss": 3.9301, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507747174164992e-05, + "loss": 3.9131, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.50690857941394e-05, + "loss": 3.9263, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506069984662888e-05, + "loss": 3.9204, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505231389911836e-05, + "loss": 3.9188, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504392795160784e-05, + "loss": 3.9232, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035542004097325e-05, + "loss": 3.9227, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027156056586805e-05, + "loss": 3.9206, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018770109076285e-05, + "loss": 3.9188, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5010384161565765e-05, + "loss": 3.9232, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.002486228942871, + "eval_runtime": 293.0047, + "eval_samples_per_second": 1302.337, + "eval_steps_per_second": 40.699, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5001998214055244e-05, + "loss": 3.9147, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499361226654472e-05, + "loss": 3.9126, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.49852263190342e-05, + "loss": 3.927, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497684037152368e-05, + "loss": 3.9143, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968454424013164e-05, + "loss": 3.9384, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496006847650264e-05, + "loss": 3.9176, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495168252899212e-05, + "loss": 3.913, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.49432965814816e-05, + "loss": 3.9053, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493491063397108e-05, + "loss": 3.9224, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492652468646056e-05, + "loss": 3.9273, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.491813873895004e-05, + "loss": 3.9168, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909752791439524e-05, + "loss": 3.9208, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901383222732733e-05, + "loss": 3.912, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4892997275222213e-05, + "loss": 3.9189, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4884611327711693e-05, + "loss": 3.9173, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4876225380201173e-05, + "loss": 3.9111, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486783943269065e-05, + "loss": 3.9149, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4859453485180133e-05, + "loss": 3.9223, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851067537669613e-05, + "loss": 3.917, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842681590159093e-05, + "loss": 3.9298, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4834295642648573e-05, + "loss": 3.9208, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4825926073941782e-05, + "loss": 3.922, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4817540126431262e-05, + "loss": 3.9204, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4809154178920742e-05, + "loss": 3.9286, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4800768231410225e-05, + "loss": 3.9094, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792382283899705e-05, + "loss": 3.9218, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4784012715192914e-05, + "loss": 3.917, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775626767682394e-05, + "loss": 3.9131, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4767240820171874e-05, + "loss": 3.9075, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4758854872661354e-05, + "loss": 3.9157, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4750468925150834e-05, + "loss": 3.9213, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742099356444046e-05, + "loss": 3.9217, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733713408933526e-05, + "loss": 3.921, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4725343840226736e-05, + "loss": 3.9241, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4716974271519948e-05, + "loss": 3.9174, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4708588324009428e-05, + "loss": 3.9224, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4700202376498908e-05, + "loss": 3.9181, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4691816428988388e-05, + "loss": 3.9189, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683430481477868e-05, + "loss": 3.9132, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4675044533967348e-05, + "loss": 3.9184, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666658586456828e-05, + "loss": 3.9207, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658272638946304e-05, + "loss": 3.9261, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4649886691435788e-05, + "loss": 3.9162, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4641500743925268e-05, + "loss": 3.9154, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633114796414748e-05, + "loss": 3.9278, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624728848904228e-05, + "loss": 3.9194, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616342901393707e-05, + "loss": 3.9201, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4607956953883184e-05, + "loss": 3.9091, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599571006372664e-05, + "loss": 3.8953, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459120143766588e-05, + "loss": 3.9243, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458281549015536e-05, + "loss": 3.9179, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4574429542644836e-05, + "loss": 3.9128, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566043595134316e-05, + "loss": 3.9021, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557657647623796e-05, + "loss": 3.9079, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549271700113276e-05, + "loss": 3.9024, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454090213140649e-05, + "loss": 3.92, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453251618389597e-05, + "loss": 3.9077, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452413023638545e-05, + "loss": 3.9119, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451574428887493e-05, + "loss": 3.9227, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450735834136441e-05, + "loss": 3.9062, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4498988772657618e-05, + "loss": 3.9098, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490602825147098e-05, + "loss": 3.9161, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448221687763658e-05, + "loss": 3.8955, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447383093012606e-05, + "loss": 3.912, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446544498261554e-05, + "loss": 3.9128, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445707541390875e-05, + "loss": 3.9211, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.444868946639823e-05, + "loss": 3.9006, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444030351888771e-05, + "loss": 3.9096, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443191757137719e-05, + "loss": 3.9, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442353162386667e-05, + "loss": 3.9261, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415162055159882e-05, + "loss": 3.9196, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406776107649362e-05, + "loss": 3.917, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.439839016013884e-05, + "loss": 3.929, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439000421262832e-05, + "loss": 3.9215, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381618265117802e-05, + "loss": 3.9355, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373232317607282e-05, + "loss": 3.9121, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436486274890049e-05, + "loss": 3.9162, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435647680138997e-05, + "loss": 3.9211, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434809085387945e-05, + "loss": 3.9098, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.433970490636893e-05, + "loss": 3.9221, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433131895885841e-05, + "loss": 3.9174, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4322949390151623e-05, + "loss": 3.9244, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314563442641103e-05, + "loss": 3.9186, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306177495130583e-05, + "loss": 3.9085, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4297791547620063e-05, + "loss": 3.9174, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4289421978913272e-05, + "loss": 3.9065, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4281036031402756e-05, + "loss": 3.9229, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4272650083892236e-05, + "loss": 3.9139, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264264136381716e-05, + "loss": 3.9112, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255894567674925e-05, + "loss": 3.9203, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247508620164405e-05, + "loss": 3.9139, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4239122672653885e-05, + "loss": 3.9063, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4230736725143365e-05, + "loss": 3.9117, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4222367156436577e-05, + "loss": 3.9263, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4213981208926057e-05, + "loss": 3.9235, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205595261415537e-05, + "loss": 3.9189, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197209313905017e-05, + "loss": 3.904, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4188823366394494e-05, + "loss": 3.9193, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180437418883974e-05, + "loss": 3.9093, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172051471373457e-05, + "loss": 3.926, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163665523862937e-05, + "loss": 3.921, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155279576352417e-05, + "loss": 3.9188, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4146910007645626e-05, + "loss": 3.9099, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138524060135106e-05, + "loss": 3.9288, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130138112624586e-05, + "loss": 3.8974, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121768543917798e-05, + "loss": 3.9101, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113382596407278e-05, + "loss": 3.9049, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4104996648896758e-05, + "loss": 3.9195, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096610701386238e-05, + "loss": 3.9019, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088241132679447e-05, + "loss": 3.9101, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079855185168927e-05, + "loss": 3.9093, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407146923765841e-05, + "loss": 3.9064, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406308329014789e-05, + "loss": 3.9109, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405469734263737e-05, + "loss": 3.907, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4046311395126847e-05, + "loss": 3.9203, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4037925447616327e-05, + "loss": 3.9215, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029539500105807e-05, + "loss": 3.916, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021153552595287e-05, + "loss": 3.9107, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012767605084767e-05, + "loss": 3.9221, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400439803637798e-05, + "loss": 3.9191, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399601208886746e-05, + "loss": 3.9105, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398762614135694e-05, + "loss": 3.9269, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.397924019384642e-05, + "loss": 3.9093, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.39708542463359e-05, + "loss": 3.9155, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396246829882538e-05, + "loss": 3.9051, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395408235131486e-05, + "loss": 3.9157, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394569640380434e-05, + "loss": 3.9015, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393734321390128e-05, + "loss": 3.9063, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.392895726639076e-05, + "loss": 3.9062, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392057131888024e-05, + "loss": 3.9189, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391218537136972e-05, + "loss": 3.9168, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903799423859204e-05, + "loss": 3.9172, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389541347634868e-05, + "loss": 3.9083, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388702752883816e-05, + "loss": 3.9195, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3878657960131373e-05, + "loss": 3.9263, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3870272012620853e-05, + "loss": 3.9164, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386188606511033e-05, + "loss": 3.915, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3853500117599813e-05, + "loss": 3.9208, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845114170089293e-05, + "loss": 3.9153, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836744601382502e-05, + "loss": 3.9232, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828358653871982e-05, + "loss": 3.9076, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.381997270636146e-05, + "loss": 3.9189, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381158675885094e-05, + "loss": 3.9115, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380320081134042e-05, + "loss": 3.9129, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794814863829905e-05, + "loss": 3.9127, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786428916319385e-05, + "loss": 3.9136, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778059347612594e-05, + "loss": 3.9166, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3769673400102074e-05, + "loss": 3.9091, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3761287452591554e-05, + "loss": 3.9196, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.998938798904419, + "eval_runtime": 310.2175, + "eval_samples_per_second": 1230.076, + "eval_steps_per_second": 38.441, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3752901505081034e-05, + "loss": 3.9073, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744515557570514e-05, + "loss": 3.9053, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736129610059994e-05, + "loss": 3.9215, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727743662549474e-05, + "loss": 3.9084, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719357715038954e-05, + "loss": 3.9288, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3710971767528434e-05, + "loss": 3.9132, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702585820017914e-05, + "loss": 3.9004, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369419987250739e-05, + "loss": 3.905, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685813924996873e-05, + "loss": 3.9086, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677427977486353e-05, + "loss": 3.9198, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669042029975833e-05, + "loss": 3.9094, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660656082465313e-05, + "loss": 3.9146, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652286513758522e-05, + "loss": 3.9076, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3643900566248002e-05, + "loss": 3.907, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635514618737482e-05, + "loss": 3.9129, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627128671226966e-05, + "loss": 3.9042, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618742723716446e-05, + "loss": 3.9066, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610356776205926e-05, + "loss": 3.9121, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3601970828695402e-05, + "loss": 3.9124, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593584881184882e-05, + "loss": 3.9223, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585198933674362e-05, + "loss": 3.9148, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3576812986163842e-05, + "loss": 3.9145, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568427038653322e-05, + "loss": 3.914, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560041091142805e-05, + "loss": 3.918, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551671522436014e-05, + "loss": 3.9008, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543285574925494e-05, + "loss": 3.9191, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534899627414974e-05, + "loss": 3.9049, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526513679904454e-05, + "loss": 3.9059, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518144111197667e-05, + "loss": 3.904, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509758163687147e-05, + "loss": 3.9077, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501372216176627e-05, + "loss": 3.915, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3492986268666103e-05, + "loss": 3.9132, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484600321155583e-05, + "loss": 3.9156, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476230752448796e-05, + "loss": 3.9214, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3467844804938276e-05, + "loss": 3.9096, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3459458857427756e-05, + "loss": 3.9147, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451072909917236e-05, + "loss": 3.912, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442703341210448e-05, + "loss": 3.9101, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434317393699928e-05, + "loss": 3.9062, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425931446189405e-05, + "loss": 3.9071, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417545498678885e-05, + "loss": 3.9143, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.34091759299721e-05, + "loss": 3.9181, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400789982461577e-05, + "loss": 3.9059, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339242041375479e-05, + "loss": 3.911, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338403446624427e-05, + "loss": 3.9189, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375664897537482e-05, + "loss": 3.9129, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3367278950026962e-05, + "loss": 3.9126, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3358893002516442e-05, + "loss": 3.9055, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3350507055005922e-05, + "loss": 3.8848, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3342121107495402e-05, + "loss": 3.9206, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3333735159984878e-05, + "loss": 3.9096, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325349212474358e-05, + "loss": 3.9086, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316963264963838e-05, + "loss": 3.9018, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.330857731745332e-05, + "loss": 3.8935, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330020774874653e-05, + "loss": 3.897, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3291838180039743e-05, + "loss": 3.909, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3283452232529223e-05, + "loss": 3.9023, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.32750662850187e-05, + "loss": 3.9046, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3266680337508183e-05, + "loss": 3.915, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258294389997663e-05, + "loss": 3.8997, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249908442487143e-05, + "loss": 3.9028, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3241522494976623e-05, + "loss": 3.9105, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233136547466103e-05, + "loss": 3.8914, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224750599955583e-05, + "loss": 3.902, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321636465244506e-05, + "loss": 3.905, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320797870493454e-05, + "loss": 3.9159, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199592757424023e-05, + "loss": 3.8916, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191223188717232e-05, + "loss": 3.904, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3182853620010444e-05, + "loss": 3.8923, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3174467672499924e-05, + "loss": 3.9157, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3166081724989404e-05, + "loss": 3.9131, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157695777478884e-05, + "loss": 3.9076, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149309829968364e-05, + "loss": 3.9209, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140923882457844e-05, + "loss": 3.9179, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132537934947324e-05, + "loss": 3.9298, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124151987436804e-05, + "loss": 3.9062, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115782418730013e-05, + "loss": 3.9114, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107396471219493e-05, + "loss": 3.9114, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099026902512705e-05, + "loss": 3.9, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090640955002185e-05, + "loss": 3.9185, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082255007491665e-05, + "loss": 3.9086, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073869059981145e-05, + "loss": 3.9172, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065499491274354e-05, + "loss": 3.9124, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057113543763838e-05, + "loss": 3.8998, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048727596253318e-05, + "loss": 3.9078, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040341648742798e-05, + "loss": 3.8976, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031955701232278e-05, + "loss": 3.9158, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023569753721758e-05, + "loss": 3.9108, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015200185014967e-05, + "loss": 3.8984, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006814237504447e-05, + "loss": 3.9173, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299844466879766e-05, + "loss": 3.9047, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299005872128714e-05, + "loss": 3.9011, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298167277377662e-05, + "loss": 3.9045, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.29732868262661e-05, + "loss": 3.9201, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296490087875558e-05, + "loss": 3.9136, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295651493124506e-05, + "loss": 3.9169, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.294812898373454e-05, + "loss": 3.8969, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.293974303622402e-05, + "loss": 3.9105, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.29313570887135e-05, + "loss": 3.9056, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292298752000671e-05, + "loss": 3.9173, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914601572496188e-05, + "loss": 3.9165, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906215624985668e-05, + "loss": 3.9065, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897829677475148e-05, + "loss": 3.9084, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.288944372996463e-05, + "loss": 3.9178, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288107416125784e-05, + "loss": 3.892, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287268821374732e-05, + "loss": 3.9013, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.28643022662368e-05, + "loss": 3.8964, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285591631872628e-05, + "loss": 3.9097, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284753037121576e-05, + "loss": 3.8985, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839160802508972e-05, + "loss": 3.9049, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830774854998452e-05, + "loss": 3.9007, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822388907487932e-05, + "loss": 3.9017, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814002959977412e-05, + "loss": 3.9057, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280563339127062e-05, + "loss": 3.9008, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.27972474437601e-05, + "loss": 3.9135, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788861496249585e-05, + "loss": 3.9114, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780475548739065e-05, + "loss": 3.9124, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277208960122854e-05, + "loss": 3.9024, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276370365371802e-05, + "loss": 3.9119, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.27553177062075e-05, + "loss": 3.9145, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274693175869698e-05, + "loss": 3.9021, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738562189990194e-05, + "loss": 3.9218, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730176242479674e-05, + "loss": 3.8978, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721790294969154e-05, + "loss": 3.9111, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713404347458633e-05, + "loss": 3.8959, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705034778751843e-05, + "loss": 3.9125, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696648831241323e-05, + "loss": 3.8934, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268827926253454e-05, + "loss": 3.9013, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679893315024015e-05, + "loss": 3.8933, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671507367513495e-05, + "loss": 3.9163, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663121420002975e-05, + "loss": 3.9065, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654735472492455e-05, + "loss": 3.9121, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646349524981935e-05, + "loss": 3.9005, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2637963577471415e-05, + "loss": 3.9118, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2629577629960895e-05, + "loss": 3.9171, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2621208061254107e-05, + "loss": 3.9117, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612838492547316e-05, + "loss": 3.9082, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260446892384053e-05, + "loss": 3.9103, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259608297633001e-05, + "loss": 3.91, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.258769702881949e-05, + "loss": 3.9163, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257931108130897e-05, + "loss": 3.9009, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257092513379845e-05, + "loss": 3.9113, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256253918628793e-05, + "loss": 3.9067, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255415323877741e-05, + "loss": 3.9086, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254576729126689e-05, + "loss": 3.9057, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253738134375637e-05, + "loss": 3.9017, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252899539624585e-05, + "loss": 3.9171, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252062582753906e-05, + "loss": 3.8962, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251223988002854e-05, + "loss": 3.9162, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.9960339069366455, + "eval_runtime": 301.9675, + "eval_samples_per_second": 1263.682, + "eval_steps_per_second": 39.491, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2503853932518017e-05, + "loss": 3.9036, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2495467985007497e-05, + "loss": 3.8962, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2487082037496977e-05, + "loss": 3.9101, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.247869608998646e-05, + "loss": 3.9048, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247031014247594e-05, + "loss": 3.9177, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246192419496542e-05, + "loss": 3.9069, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245355462625863e-05, + "loss": 3.8948, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445185057551842e-05, + "loss": 3.896, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436799110041322e-05, + "loss": 3.9043, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428413162530802e-05, + "loss": 3.9132, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2420027215020282e-05, + "loss": 3.9052, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411641267509762e-05, + "loss": 3.9051, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.240327169880297e-05, + "loss": 3.9068, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239488575129245e-05, + "loss": 3.8982, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238649980378193e-05, + "loss": 3.9039, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378113856271414e-05, + "loss": 3.8917, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369727908760894e-05, + "loss": 3.9029, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361341961250374e-05, + "loss": 3.9046, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235295601373985e-05, + "loss": 3.9053, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234457006622933e-05, + "loss": 3.913, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336200497522543e-05, + "loss": 3.9139, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327814550012023e-05, + "loss": 3.9051, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319428602501503e-05, + "loss": 3.904, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2311042654990983e-05, + "loss": 3.9143, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302656707480463e-05, + "loss": 3.8901, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294270759969943e-05, + "loss": 3.9159, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2285884812459423e-05, + "loss": 3.8977, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2277498864948903e-05, + "loss": 3.8978, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2269129296242115e-05, + "loss": 3.8954, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2260743348731595e-05, + "loss": 3.9034, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252357401221075e-05, + "loss": 3.9036, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2244004211318017e-05, + "loss": 3.9082, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235618263807493e-05, + "loss": 3.9071, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227232316296977e-05, + "loss": 3.9161, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2218846368786457e-05, + "loss": 3.901, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2210460421275937e-05, + "loss": 3.9106, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2202090852569146e-05, + "loss": 3.9075, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193704905058626e-05, + "loss": 3.9007, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185318957548106e-05, + "loss": 3.9031, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2176933010037586e-05, + "loss": 3.9029, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.216854706252707e-05, + "loss": 3.9036, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216016111501655e-05, + "loss": 3.9132, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215177516750603e-05, + "loss": 3.8984, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2143389219995506e-05, + "loss": 3.9016, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2135003272484985e-05, + "loss": 3.916, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126617324974465e-05, + "loss": 3.9042, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118231377463945e-05, + "loss": 3.9107, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2109845429953425e-05, + "loss": 3.8991, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210149224005037e-05, + "loss": 3.8706, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209310629253985e-05, + "loss": 3.9177, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084720345029327e-05, + "loss": 3.9035, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076334397518807e-05, + "loss": 3.9027, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067964828812023e-05, + "loss": 3.8929, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2059578881301503e-05, + "loss": 3.8838, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205119293379098e-05, + "loss": 3.8952, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204280698628046e-05, + "loss": 3.9002, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203442103876994e-05, + "loss": 3.8956, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2026051470063148e-05, + "loss": 3.8979, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.201766552255263e-05, + "loss": 3.9101, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.200927957504211e-05, + "loss": 3.8923, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200089362753159e-05, + "loss": 3.8922, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.19925240588248e-05, + "loss": 3.9104, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198413811131428e-05, + "loss": 3.8815, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197575216380376e-05, + "loss": 3.8953, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196736621629324e-05, + "loss": 3.8991, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958980268782724e-05, + "loss": 3.9116, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950594321272204e-05, + "loss": 3.8852, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942208373761684e-05, + "loss": 3.8985, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1933838805054893e-05, + "loss": 3.8829, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1925452857544373e-05, + "loss": 3.9123, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1917066910033853e-05, + "loss": 3.9096, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908680962523333e-05, + "loss": 3.9018, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900295015012813e-05, + "loss": 3.9091, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891909067502293e-05, + "loss": 3.9103, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883539498795505e-05, + "loss": 3.9246, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875169930088714e-05, + "loss": 3.8996, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1866783982578194e-05, + "loss": 3.9039, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858398035067677e-05, + "loss": 3.9067, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1850012087557157e-05, + "loss": 3.8937, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841626140046634e-05, + "loss": 3.9058, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833256571339846e-05, + "loss": 3.903, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824870623829326e-05, + "loss": 3.9071, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816484676318803e-05, + "loss": 3.9155, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1808098728808286e-05, + "loss": 3.8932, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799712781297766e-05, + "loss": 3.8956, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791326833787246e-05, + "loss": 3.8938, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782940886276726e-05, + "loss": 3.9095, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774554938766206e-05, + "loss": 3.9005, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766168991255686e-05, + "loss": 3.8972, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757799422548895e-05, + "loss": 3.8982, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.174941347503838e-05, + "loss": 3.9059, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174102752752786e-05, + "loss": 3.8945, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173264158001734e-05, + "loss": 3.8972, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724272011310548e-05, + "loss": 3.9162, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715886063800028e-05, + "loss": 3.9045, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707500116289507e-05, + "loss": 3.9087, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1699114168778987e-05, + "loss": 3.8914, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690728221268467e-05, + "loss": 3.904, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168235865256168e-05, + "loss": 3.8994, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167398908385489e-05, + "loss": 3.9094, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166560313634437e-05, + "loss": 3.9069, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.165723356763758e-05, + "loss": 3.9067, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.164884762012706e-05, + "loss": 3.9027, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164046167261654e-05, + "loss": 3.9086, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163207572510602e-05, + "loss": 3.8853, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.16236897775955e-05, + "loss": 3.8973, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161530383008498e-05, + "loss": 3.8855, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160691788257446e-05, + "loss": 3.9056, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.159853193506394e-05, + "loss": 3.8921, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159014598755342e-05, + "loss": 3.8971, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.15817600400429e-05, + "loss": 3.8909, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157337409253238e-05, + "loss": 3.8961, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156498814502186e-05, + "loss": 3.8988, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155660219751134e-05, + "loss": 3.8922, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.154823262880455e-05, + "loss": 3.9051, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1539846681294033e-05, + "loss": 3.9115, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531460733783513e-05, + "loss": 3.9029, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152307478627299e-05, + "loss": 3.9029, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1514705217566202e-05, + "loss": 3.9008, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1506319270055682e-05, + "loss": 3.9055, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1497933322545162e-05, + "loss": 3.902, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489547375034642e-05, + "loss": 3.9111, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481161427524122e-05, + "loss": 3.8934, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472791858817335e-05, + "loss": 3.9061, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464405911306815e-05, + "loss": 3.8928, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145601996379629e-05, + "loss": 3.8988, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144763401628577e-05, + "loss": 3.8941, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439264447578987e-05, + "loss": 3.8948, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430894878872196e-05, + "loss": 3.8884, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422508931361676e-05, + "loss": 3.9057, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414122983851156e-05, + "loss": 3.903, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1405737036340636e-05, + "loss": 3.9067, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1397351088830116e-05, + "loss": 3.8922, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1388965141319596e-05, + "loss": 3.9082, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380579193809076e-05, + "loss": 3.9077, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137220962510229e-05, + "loss": 3.9073, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363823677591765e-05, + "loss": 3.9046, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355437730081245e-05, + "loss": 3.9017, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1347051782570725e-05, + "loss": 3.904, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1338665835060205e-05, + "loss": 3.9124, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330279887549688e-05, + "loss": 3.8923, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321893940039168e-05, + "loss": 3.9019, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313524371332377e-05, + "loss": 3.9049, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305138423821857e-05, + "loss": 3.9048, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296752476311337e-05, + "loss": 3.891, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288366528800817e-05, + "loss": 3.8961, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1279980581290297e-05, + "loss": 3.9115, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1271594633779777e-05, + "loss": 3.8932, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1263208686269257e-05, + "loss": 3.9099, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9930543899536133, + "eval_runtime": 301.9547, + "eval_samples_per_second": 1263.736, + "eval_steps_per_second": 39.493, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1254822738758737e-05, + "loss": 3.8998, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1246436791248217e-05, + "loss": 3.8891, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1238050843737697e-05, + "loss": 3.9065, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1229664896227177e-05, + "loss": 3.8925, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1221278948716657e-05, + "loss": 3.9105, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1212893001206137e-05, + "loss": 3.9042, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1204507053695617e-05, + "loss": 3.8924, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196121106185097e-05, + "loss": 3.891, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187735158674576e-05, + "loss": 3.8977, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179349211164056e-05, + "loss": 3.905, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1170963263653533e-05, + "loss": 3.898, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1162577316143013e-05, + "loss": 3.8964, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115420774743623e-05, + "loss": 3.8984, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114582179992571e-05, + "loss": 3.8951, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1137435852415185e-05, + "loss": 3.8965, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1129049904904665e-05, + "loss": 3.8882, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120663957394145e-05, + "loss": 3.8929, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1112278009883625e-05, + "loss": 3.8998, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1103892062373105e-05, + "loss": 3.8996, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109550611486259e-05, + "loss": 3.9039, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087120167352065e-05, + "loss": 3.9084, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078750598645278e-05, + "loss": 3.9022, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070364651134758e-05, + "loss": 3.8968, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1061978703624237e-05, + "loss": 3.9022, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1053592756113717e-05, + "loss": 3.8906, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104522318740693e-05, + "loss": 3.9062, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103683723989641e-05, + "loss": 3.8902, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.102845129238589e-05, + "loss": 3.8958, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.10200817236791e-05, + "loss": 3.8921, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101169577616858e-05, + "loss": 3.8943, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100330982865806e-05, + "loss": 3.8961, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099492388114754e-05, + "loss": 3.9031, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098653793363702e-05, + "loss": 3.8996, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.09781519861265e-05, + "loss": 3.9053, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.096976603861598e-05, + "loss": 3.8943, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096138009110546e-05, + "loss": 3.9076, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095299414359494e-05, + "loss": 3.902, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094462457488815e-05, + "loss": 3.8913, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093623862737763e-05, + "loss": 3.8973, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.092785267986711e-05, + "loss": 3.8958, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.091946673235659e-05, + "loss": 3.8965, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091108078484607e-05, + "loss": 3.9061, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090271121613928e-05, + "loss": 3.8929, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089432526862876e-05, + "loss": 3.895, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885939321118243e-05, + "loss": 3.9086, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.087755337360772e-05, + "loss": 3.8984, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.08691674260972e-05, + "loss": 3.9024, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086078147858668e-05, + "loss": 3.8973, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085239553107616e-05, + "loss": 3.8625, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084400958356564e-05, + "loss": 3.9119, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835640014858852e-05, + "loss": 3.893, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827254067348332e-05, + "loss": 3.9011, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0818884498641545e-05, + "loss": 3.8847, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0810514929934754e-05, + "loss": 3.8805, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0802128982424234e-05, + "loss": 3.8855, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793743034913714e-05, + "loss": 3.893, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785357087403194e-05, + "loss": 3.8922, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776971139892674e-05, + "loss": 3.8889, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768585192382153e-05, + "loss": 3.907, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760199244871633e-05, + "loss": 3.8878, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0751813297361113e-05, + "loss": 3.885, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0743427349850593e-05, + "loss": 3.9016, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0735057781143806e-05, + "loss": 3.8738, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0726671833633286e-05, + "loss": 3.8833, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718285886122766e-05, + "loss": 3.8945, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0709916317415975e-05, + "loss": 3.9032, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0701530369905455e-05, + "loss": 3.8798, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0693144422394935e-05, + "loss": 3.8925, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0684758474884418e-05, + "loss": 3.8777, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676372527373898e-05, + "loss": 3.9053, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0667986579863375e-05, + "loss": 3.901, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0659600632352855e-05, + "loss": 3.899, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651214684842335e-05, + "loss": 3.9011, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0642828737331814e-05, + "loss": 3.9054, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0634442789821294e-05, + "loss": 3.9163, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0626056842310774e-05, + "loss": 3.894, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0617670894800258e-05, + "loss": 3.8979, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0609284947289734e-05, + "loss": 3.9015, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0600915378582947e-05, + "loss": 3.8858, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592529431072427e-05, + "loss": 3.8946, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0584159862365636e-05, + "loss": 3.8994, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057577391485512e-05, + "loss": 3.9043, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.05673879673446e-05, + "loss": 3.9061, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.055900201983408e-05, + "loss": 3.8906, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550616072323556e-05, + "loss": 3.8874, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542230124813036e-05, + "loss": 3.8892, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533860556106248e-05, + "loss": 3.9032, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0525474608595728e-05, + "loss": 3.8959, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0517088661085208e-05, + "loss": 3.8904, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0508702713574688e-05, + "loss": 3.8913, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0500316766064168e-05, + "loss": 3.8998, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0491947197357377e-05, + "loss": 3.8908, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483561249846857e-05, + "loss": 3.89, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475175302336337e-05, + "loss": 3.9081, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046678935482582e-05, + "loss": 3.8981, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.04584034073153e-05, + "loss": 3.8992, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045001745980478e-05, + "loss": 3.8889, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044164789109799e-05, + "loss": 3.8926, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043326194358747e-05, + "loss": 3.8915, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042487599607695e-05, + "loss": 3.9072, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041649004856643e-05, + "loss": 3.8975, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408104101055912e-05, + "loss": 3.9004, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.039971815354539e-05, + "loss": 3.899, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039133220603487e-05, + "loss": 3.898, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038294625852435e-05, + "loss": 3.8859, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0374576689817558e-05, + "loss": 3.887, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036619074230704e-05, + "loss": 3.8831, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.035780479479652e-05, + "loss": 3.8986, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349435226089734e-05, + "loss": 3.8874, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034104927857921e-05, + "loss": 3.8887, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033266333106869e-05, + "loss": 3.8831, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032427738355817e-05, + "loss": 3.8949, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031589143604765e-05, + "loss": 3.8912, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.030750548853713e-05, + "loss": 3.8838, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0299119541026614e-05, + "loss": 3.9032, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0290733593516094e-05, + "loss": 3.899, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0282364024809303e-05, + "loss": 3.8949, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0273978077298783e-05, + "loss": 3.899, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0265592129788263e-05, + "loss": 3.8941, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0257222561081475e-05, + "loss": 3.8962, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0248836613570955e-05, + "loss": 3.8986, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240450666060435e-05, + "loss": 3.9026, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0232064718549915e-05, + "loss": 3.8882, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223695149843124e-05, + "loss": 3.8982, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215309202332604e-05, + "loss": 3.8902, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0206923254822084e-05, + "loss": 3.8936, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0198537307311567e-05, + "loss": 3.8857, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190167738604776e-05, + "loss": 3.8887, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181781791094256e-05, + "loss": 3.8836, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173395843583736e-05, + "loss": 3.8998, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0165009896073213e-05, + "loss": 3.8945, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0156623948562696e-05, + "loss": 3.9027, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0148238001052176e-05, + "loss": 3.883, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0139852053541656e-05, + "loss": 3.9065, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131466106031136e-05, + "loss": 3.8975, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0123080158520616e-05, + "loss": 3.8995, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0114710589813825e-05, + "loss": 3.8998, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0106341021107038e-05, + "loss": 3.8959, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0097955073596518e-05, + "loss": 3.8951, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0089569126085997e-05, + "loss": 3.9051, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081183178575477e-05, + "loss": 3.8891, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072797231064957e-05, + "loss": 3.8955, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064411283554437e-05, + "loss": 3.8986, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0056025336043917e-05, + "loss": 3.8943, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0047639388533397e-05, + "loss": 3.8859, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.003926981982661e-05, + "loss": 3.8896, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003088387231609e-05, + "loss": 3.9036, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002249792480557e-05, + "loss": 3.8907, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014111977295046e-05, + "loss": 3.9031, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.9905812740325928, + "eval_runtime": 290.3729, + "eval_samples_per_second": 1314.141, + "eval_steps_per_second": 41.068, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0005726029784526e-05, + "loss": 3.8857, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9997340082274006e-05, + "loss": 3.888, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.998895413476349e-05, + "loss": 3.8924, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.998056818725297e-05, + "loss": 3.8922, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997219861854618e-05, + "loss": 3.9036, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996381267103566e-05, + "loss": 3.8957, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995542672352514e-05, + "loss": 3.886, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994704077601462e-05, + "loss": 3.8868, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99386548285041e-05, + "loss": 3.8889, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993026888099358e-05, + "loss": 3.9026, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992189931228679e-05, + "loss": 3.8899, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991351336477627e-05, + "loss": 3.8896, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990514379606948e-05, + "loss": 3.9, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989675784855896e-05, + "loss": 3.8792, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888371901048443e-05, + "loss": 3.8892, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9879985953537923e-05, + "loss": 3.8854, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.98716000060274e-05, + "loss": 3.8869, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986321405851688e-05, + "loss": 3.8926, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985482811100636e-05, + "loss": 3.8939, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984644216349584e-05, + "loss": 3.893, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.983805621598532e-05, + "loss": 3.9061, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.98296702684748e-05, + "loss": 3.8953, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821284320964283e-05, + "loss": 3.8963, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981289837345376e-05, + "loss": 3.8915, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980451242594324e-05, + "loss": 3.8865, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9796142857236452e-05, + "loss": 3.8991, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9787756909725932e-05, + "loss": 3.8861, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.977937096221541e-05, + "loss": 3.8929, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977098501470489e-05, + "loss": 3.8831, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9762615445998104e-05, + "loss": 3.89, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975422949848758e-05, + "loss": 3.8878, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974584355097706e-05, + "loss": 3.8951, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.973745760346654e-05, + "loss": 3.8975, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.972907165595602e-05, + "loss": 3.8996, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9720702087249233e-05, + "loss": 3.8905, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712316139738713e-05, + "loss": 3.8955, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9703930192228193e-05, + "loss": 3.8985, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695544244717673e-05, + "loss": 3.8877, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9687158297207153e-05, + "loss": 3.89, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678772349696633e-05, + "loss": 3.8886, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670386402186113e-05, + "loss": 3.8948, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9662016833479325e-05, + "loss": 3.8907, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653647264772534e-05, + "loss": 3.8935, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645277696065747e-05, + "loss": 3.8915, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636891748555227e-05, + "loss": 3.8997, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9628505801044707e-05, + "loss": 3.8958, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9620119853534187e-05, + "loss": 3.8958, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9611733906023667e-05, + "loss": 3.8899, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9603347958513147e-05, + "loss": 3.8573, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9594978389806356e-05, + "loss": 3.9036, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586592442295836e-05, + "loss": 3.8872, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9578206494785316e-05, + "loss": 3.8964, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.95698205472748e-05, + "loss": 3.881, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956143459976428e-05, + "loss": 3.8769, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955304865225376e-05, + "loss": 3.8779, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9544662704743235e-05, + "loss": 3.8846, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9536276757232715e-05, + "loss": 3.8887, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9527907188525928e-05, + "loss": 3.8827, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9519521241015408e-05, + "loss": 3.8962, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951115167230862e-05, + "loss": 3.8853, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.95027657247981e-05, + "loss": 3.8803, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949437977728758e-05, + "loss": 3.8941, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948599382977706e-05, + "loss": 3.8723, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9477607882266537e-05, + "loss": 3.8767, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469221934756017e-05, + "loss": 3.8899, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.94608359872455e-05, + "loss": 3.8937, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945245003973498e-05, + "loss": 3.8755, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944406409222446e-05, + "loss": 3.8849, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.94357109023214e-05, + "loss": 3.872, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942732495481088e-05, + "loss": 3.8955, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.941893900730036e-05, + "loss": 3.8959, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941055305978984e-05, + "loss": 3.8919, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940216711227932e-05, + "loss": 3.8938, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9393797543572534e-05, + "loss": 3.8991, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938541159606201e-05, + "loss": 3.9099, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937702564855149e-05, + "loss": 3.891, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.936863970104097e-05, + "loss": 3.8922, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9360253753530454e-05, + "loss": 3.8914, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9351867806019934e-05, + "loss": 3.8873, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9343481858509414e-05, + "loss": 3.8888, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933509591099889e-05, + "loss": 3.8933, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932670996348837e-05, + "loss": 3.8969, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.931832401597785e-05, + "loss": 3.902, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.930993806846733e-05, + "loss": 3.8813, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9301552120956813e-05, + "loss": 3.881, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293166173446293e-05, + "loss": 3.8816, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9284796604739502e-05, + "loss": 3.8995, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927642703603271e-05, + "loss": 3.8933, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.926804108852219e-05, + "loss": 3.8796, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259655141011675e-05, + "loss": 3.8873, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251269193501155e-05, + "loss": 3.8945, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242899624794364e-05, + "loss": 3.8877, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234513677283844e-05, + "loss": 3.8822, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226127729773324e-05, + "loss": 3.9017, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9217741782262804e-05, + "loss": 3.8949, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9209372213556016e-05, + "loss": 3.8948, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9200986266045496e-05, + "loss": 3.8856, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192600318534976e-05, + "loss": 3.8869, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184214371024456e-05, + "loss": 3.8868, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175828423513936e-05, + "loss": 3.8995, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167442476003416e-05, + "loss": 3.8935, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9159056528492893e-05, + "loss": 3.8925, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915068695978611e-05, + "loss": 3.8957, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914230101227559e-05, + "loss": 3.8894, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913391506476507e-05, + "loss": 3.8862, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125529117254545e-05, + "loss": 3.88, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117143169744025e-05, + "loss": 3.8741, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108757222233505e-05, + "loss": 3.8947, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9100371274722985e-05, + "loss": 3.8835, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9092001706016197e-05, + "loss": 3.8796, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9083615758505677e-05, + "loss": 3.8786, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9075229810995157e-05, + "loss": 3.883, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9066843863484637e-05, + "loss": 3.8914, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058457915974117e-05, + "loss": 3.8805, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9050071968463597e-05, + "loss": 3.8939, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9041686020953077e-05, + "loss": 3.8946, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9033300073442557e-05, + "loss": 3.8919, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9024914125932037e-05, + "loss": 3.8922, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9016528178421517e-05, + "loss": 3.8887, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9008142230910997e-05, + "loss": 3.892, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.8999756283400477e-05, + "loss": 3.8946, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8991386714693686e-05, + "loss": 3.8921, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898300076718317e-05, + "loss": 3.8859, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897463119847638e-05, + "loss": 3.8912, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896626162976959e-05, + "loss": 3.8879, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895787568225907e-05, + "loss": 3.8871, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8949489734748547e-05, + "loss": 3.8786, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8941120166041763e-05, + "loss": 3.8811, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8932734218531243e-05, + "loss": 3.8774, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8924348271020723e-05, + "loss": 3.8933, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.89159623235102e-05, + "loss": 3.886, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890757637599968e-05, + "loss": 3.8992, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.889919042848916e-05, + "loss": 3.877, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889080448097864e-05, + "loss": 3.8994, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882418533468123e-05, + "loss": 3.8934, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8874032585957603e-05, + "loss": 3.8964, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8865646638447083e-05, + "loss": 3.893, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.885726069093656e-05, + "loss": 3.8896, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.884887474342604e-05, + "loss": 3.8926, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884048879591552e-05, + "loss": 3.8996, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832102848405e-05, + "loss": 3.8805, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882371690089448e-05, + "loss": 3.8928, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8815330953383963e-05, + "loss": 3.89, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8806977763480904e-05, + "loss": 3.8888, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.879859181597038e-05, + "loss": 3.8857, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879020586845986e-05, + "loss": 3.8819, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878181992094934e-05, + "loss": 3.8971, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8773433973438824e-05, + "loss": 3.8868, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8765048025928304e-05, + "loss": 3.8944, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.988081693649292, + "eval_runtime": 292.8589, + "eval_samples_per_second": 1302.986, + "eval_steps_per_second": 40.719, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756678457221513e-05, + "loss": 3.878, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748292509710993e-05, + "loss": 3.8843, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8739906562200473e-05, + "loss": 3.8864, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731520614689953e-05, + "loss": 3.8861, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723134667179433e-05, + "loss": 3.9013, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714748719668913e-05, + "loss": 3.8889, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706362772158393e-05, + "loss": 3.8826, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8697976824647873e-05, + "loss": 3.882, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689590877137353e-05, + "loss": 3.8818, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681204929626833e-05, + "loss": 3.8964, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672818982116313e-05, + "loss": 3.8858, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664433034605793e-05, + "loss": 3.8865, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656063465899005e-05, + "loss": 3.8952, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647677518388485e-05, + "loss": 3.8771, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639291570877965e-05, + "loss": 3.8825, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863090562336744e-05, + "loss": 3.8787, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862251967585692e-05, + "loss": 3.8826, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.86141337283464e-05, + "loss": 3.8811, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605747780835885e-05, + "loss": 3.8917, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597361833325365e-05, + "loss": 3.8886, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8588975885814845e-05, + "loss": 3.8996, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580606317108054e-05, + "loss": 3.8857, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572220369597534e-05, + "loss": 3.8919, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563834422087014e-05, + "loss": 3.8842, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555448474576494e-05, + "loss": 3.8868, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8547078905869706e-05, + "loss": 3.8924, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538692958359186e-05, + "loss": 3.8788, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530307010848666e-05, + "loss": 3.8899, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8521921063338146e-05, + "loss": 3.8778, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8513535115827623e-05, + "loss": 3.8839, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850516554712084e-05, + "loss": 3.8826, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849677959961032e-05, + "loss": 3.8873, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.84883936520998e-05, + "loss": 3.8954, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8480007704589275e-05, + "loss": 3.8959, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471621757078755e-05, + "loss": 3.886, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8463235809568235e-05, + "loss": 3.8836, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8454866240861447e-05, + "loss": 3.8985, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8446480293350927e-05, + "loss": 3.8828, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8438094345840407e-05, + "loss": 3.8827, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.842972477713362e-05, + "loss": 3.8844, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421338829623096e-05, + "loss": 3.8887, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8412952882112576e-05, + "loss": 3.8867, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8404566934602056e-05, + "loss": 3.8861, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839618098709154e-05, + "loss": 3.8875, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.838779503958102e-05, + "loss": 3.8871, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.83794090920705e-05, + "loss": 3.8902, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837102314455998e-05, + "loss": 3.8881, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8362637197049456e-05, + "loss": 3.887, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8354251249538936e-05, + "loss": 3.8516, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8345865302028416e-05, + "loss": 3.8957, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8337479354517896e-05, + "loss": 3.8812, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.832910978581111e-05, + "loss": 3.8938, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832072383830059e-05, + "loss": 3.8737, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8312337890790068e-05, + "loss": 3.8705, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8303951943279548e-05, + "loss": 3.8701, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295582374572757e-05, + "loss": 3.8781, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828719642706224e-05, + "loss": 3.8898, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.827881047955172e-05, + "loss": 3.8718, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.82704245320412e-05, + "loss": 3.8924, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826203858453068e-05, + "loss": 3.8823, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825366901582389e-05, + "loss": 3.8657, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824528306831337e-05, + "loss": 3.8884, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823689712080285e-05, + "loss": 3.8709, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228511173292333e-05, + "loss": 3.8691, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220125225781813e-05, + "loss": 3.8837, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211755657075022e-05, + "loss": 3.8906, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8203369709564502e-05, + "loss": 3.8731, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8194983762053982e-05, + "loss": 3.8787, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818659781454346e-05, + "loss": 3.8681, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178211867032942e-05, + "loss": 3.8872, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169858677129883e-05, + "loss": 3.8922, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161472729619363e-05, + "loss": 3.8852, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8153086782108843e-05, + "loss": 3.8887, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8144700834598323e-05, + "loss": 3.8935, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136314887087803e-05, + "loss": 3.9033, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8127928939577283e-05, + "loss": 3.8865, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119559370870496e-05, + "loss": 3.8884, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111173423359976e-05, + "loss": 3.8825, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102787475849456e-05, + "loss": 3.8836, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094401528338932e-05, + "loss": 3.8801, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8086015580828412e-05, + "loss": 3.8933, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077629633317895e-05, + "loss": 3.8882, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069243685807375e-05, + "loss": 3.9008, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060857738296855e-05, + "loss": 3.8741, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052471790786335e-05, + "loss": 3.8767, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044085843275815e-05, + "loss": 3.8812, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035699895765292e-05, + "loss": 3.8896, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027313948254772e-05, + "loss": 3.888, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8018944379547988e-05, + "loss": 3.8801, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8010558432037464e-05, + "loss": 3.881, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002172484526944e-05, + "loss": 3.8885, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993802915820157e-05, + "loss": 3.8824, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985416968309637e-05, + "loss": 3.8756, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7977031020799117e-05, + "loss": 3.8967, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7968645073288597e-05, + "loss": 3.8882, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7960259125778076e-05, + "loss": 3.8909, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7951873178267556e-05, + "loss": 3.8788, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943487230757036e-05, + "loss": 3.8834, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935101283246516e-05, + "loss": 3.879, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926715335735996e-05, + "loss": 3.892, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918329388225473e-05, + "loss": 3.8928, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7909943440714956e-05, + "loss": 3.8826, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790157387200817e-05, + "loss": 3.8912, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7893187924497645e-05, + "loss": 3.8842, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7884801976987125e-05, + "loss": 3.8845, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7876416029476605e-05, + "loss": 3.8718, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7868046460769818e-05, + "loss": 3.8721, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7859660513259298e-05, + "loss": 3.8824, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7851274565748778e-05, + "loss": 3.8835, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7842888618238258e-05, + "loss": 3.87, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7834502670727737e-05, + "loss": 3.8751, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7826116723217217e-05, + "loss": 3.8775, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7817747154510427e-05, + "loss": 3.8835, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.780936120699991e-05, + "loss": 3.8754, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780097525948939e-05, + "loss": 3.8911, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779258931197887e-05, + "loss": 3.8883, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778420336446835e-05, + "loss": 3.8863, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7775817416957826e-05, + "loss": 3.8793, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7767431469447306e-05, + "loss": 3.8866, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7759045521936786e-05, + "loss": 3.8863, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750675953230002e-05, + "loss": 3.8899, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.774229000571948e-05, + "loss": 3.8878, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.773390405820896e-05, + "loss": 3.8787, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772551811069844e-05, + "loss": 3.8857, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.771714854199165e-05, + "loss": 3.8849, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708762594481128e-05, + "loss": 3.8763, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770037664697061e-05, + "loss": 3.8779, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7692023457067553e-05, + "loss": 3.8785, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683637509557033e-05, + "loss": 3.8684, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7675251562046513e-05, + "loss": 3.8915, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666865614535992e-05, + "loss": 3.8801, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658479667025472e-05, + "loss": 3.8952, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650093719514952e-05, + "loss": 3.8726, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641707772004432e-05, + "loss": 3.8914, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633321824493912e-05, + "loss": 3.8897, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7624935876983392e-05, + "loss": 3.8919, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7616549929472872e-05, + "loss": 3.885, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7608163981962352e-05, + "loss": 3.882, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.759977803445183e-05, + "loss": 3.8928, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591408465745045e-05, + "loss": 3.8912, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7583022518234525e-05, + "loss": 3.8797, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574636570724005e-05, + "loss": 3.8866, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756625062321348e-05, + "loss": 3.8881, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557881054506694e-05, + "loss": 3.8831, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549495106996174e-05, + "loss": 3.8788, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7541125538289386e-05, + "loss": 3.8773, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532739590778866e-05, + "loss": 3.8911, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524370022072075e-05, + "loss": 3.8844, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7515984074561555e-05, + "loss": 3.8894, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.985943555831909, + "eval_runtime": 509.9466, + "eval_samples_per_second": 748.296, + "eval_steps_per_second": 23.385, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7507598127051035e-05, + "loss": 3.8725, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.749921217954052e-05, + "loss": 3.8809, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7490826232029998e-05, + "loss": 3.8786, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7482440284519478e-05, + "loss": 3.8821, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7474054337008955e-05, + "loss": 3.8956, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7465668389498435e-05, + "loss": 3.8898, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7457282441987915e-05, + "loss": 3.8748, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7448896494477395e-05, + "loss": 3.8778, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7440510546966875e-05, + "loss": 3.875, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7432124599456358e-05, + "loss": 3.8869, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7423755030749567e-05, + "loss": 3.8822, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7415369083239047e-05, + "loss": 3.8839, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7406999514532256e-05, + "loss": 3.889, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7398613567021736e-05, + "loss": 3.868, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739022761951122e-05, + "loss": 3.8772, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.73818416720007e-05, + "loss": 3.87, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737345572449018e-05, + "loss": 3.8845, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736506977697966e-05, + "loss": 3.8774, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7356683829469136e-05, + "loss": 3.8835, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.734831426076235e-05, + "loss": 3.8816, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7339928313251828e-05, + "loss": 3.8942, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733154236574131e-05, + "loss": 3.8805, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7323156418230788e-05, + "loss": 3.8898, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7314770470720268e-05, + "loss": 3.8822, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7306384523209748e-05, + "loss": 3.8815, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7298014954502957e-05, + "loss": 3.8874, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7289629006992437e-05, + "loss": 3.8732, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728124305948192e-05, + "loss": 3.8817, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.72728571119714e-05, + "loss": 3.8757, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726448754326461e-05, + "loss": 3.8794, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.725610159575409e-05, + "loss": 3.8812, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.724771564824357e-05, + "loss": 3.8812, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.723932970073305e-05, + "loss": 3.8826, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7230960132026262e-05, + "loss": 3.8937, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7222574184515742e-05, + "loss": 3.8797, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7214188237005222e-05, + "loss": 3.8814, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7205802289494702e-05, + "loss": 3.892, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7197416341984182e-05, + "loss": 3.8758, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.718903039447366e-05, + "loss": 3.8784, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718064444696314e-05, + "loss": 3.8808, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717225849945262e-05, + "loss": 3.8792, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7163888930745834e-05, + "loss": 3.8837, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7155502983235314e-05, + "loss": 3.8774, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.714711703572479e-05, + "loss": 3.8855, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7138747467018003e-05, + "loss": 3.8846, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7130361519507483e-05, + "loss": 3.887, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7121975571996966e-05, + "loss": 3.8818, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7113589624486443e-05, + "loss": 3.8847, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7105203676975923e-05, + "loss": 3.8503, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7096817729465403e-05, + "loss": 3.8896, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7088431781954883e-05, + "loss": 3.8733, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7080045834444363e-05, + "loss": 3.8871, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7071676265737575e-05, + "loss": 3.8706, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7063306697030788e-05, + "loss": 3.8665, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7054920749520264e-05, + "loss": 3.8652, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7046534802009744e-05, + "loss": 3.8734, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7038148854499224e-05, + "loss": 3.8816, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7029762906988704e-05, + "loss": 3.8667, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7021376959478184e-05, + "loss": 3.8884, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7012991011967667e-05, + "loss": 3.879, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7004621443260877e-05, + "loss": 3.8593, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6996235495750357e-05, + "loss": 3.8841, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6987865927043566e-05, + "loss": 3.8655, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6979479979533046e-05, + "loss": 3.8643, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697109403202253e-05, + "loss": 3.8801, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696270808451201e-05, + "loss": 3.8824, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695432213700149e-05, + "loss": 3.8643, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694593618949097e-05, + "loss": 3.8789, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6937550241980445e-05, + "loss": 3.8644, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6929164294469925e-05, + "loss": 3.8779, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6920778346959405e-05, + "loss": 3.8847, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691239239944889e-05, + "loss": 3.8816, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690400645193837e-05, + "loss": 3.8851, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689562050442785e-05, + "loss": 3.885, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.688726731452479e-05, + "loss": 3.9006, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6878881367014267e-05, + "loss": 3.8822, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687049541950375e-05, + "loss": 3.8853, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686210947199323e-05, + "loss": 3.8739, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685372352448271e-05, + "loss": 3.8801, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684535395577592e-05, + "loss": 3.8761, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.68369680082654e-05, + "loss": 3.8847, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.682858206075488e-05, + "loss": 3.8882, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682019611324436e-05, + "loss": 3.8931, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6811810165733842e-05, + "loss": 3.8702, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6803424218223322e-05, + "loss": 3.8728, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679505464951653e-05, + "loss": 3.8718, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678666870200601e-05, + "loss": 3.8832, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.677828275449549e-05, + "loss": 3.8801, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6769913185788704e-05, + "loss": 3.8752, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6761527238278184e-05, + "loss": 3.8776, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6753141290767664e-05, + "loss": 3.8816, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6744755343257144e-05, + "loss": 3.8753, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6736369395746624e-05, + "loss": 3.8718, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.67279834482361e-05, + "loss": 3.8901, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.671959750072558e-05, + "loss": 3.887, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671121155321506e-05, + "loss": 3.8852, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6702825605704543e-05, + "loss": 3.8724, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6694439658194023e-05, + "loss": 3.8753, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6686053710683503e-05, + "loss": 3.8793, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.667766776317298e-05, + "loss": 3.883, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6669298194466192e-05, + "loss": 3.8882, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6660912246955672e-05, + "loss": 3.8762, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6652542678248885e-05, + "loss": 3.8876, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6644156730738365e-05, + "loss": 3.8814, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6635770783227845e-05, + "loss": 3.8784, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6627384835717325e-05, + "loss": 3.8685, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6619015267010534e-05, + "loss": 3.8682, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6610629319500014e-05, + "loss": 3.8757, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6602243371989497e-05, + "loss": 3.8771, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6593857424478977e-05, + "loss": 3.8672, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6585471476968454e-05, + "loss": 3.87, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6577085529457934e-05, + "loss": 3.8663, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6568715960751146e-05, + "loss": 3.8792, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6560330013240626e-05, + "loss": 3.8758, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6551944065730106e-05, + "loss": 3.8814, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6543558118219586e-05, + "loss": 3.8845, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6535172170709066e-05, + "loss": 3.8818, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652680260200228e-05, + "loss": 3.8775, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6518416654491755e-05, + "loss": 3.8845, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6510030706981235e-05, + "loss": 3.8812, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6501644759470715e-05, + "loss": 3.8877, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6493275190763927e-05, + "loss": 3.8784, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6484889243253407e-05, + "loss": 3.878, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6476503295742887e-05, + "loss": 3.8772, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6468117348232367e-05, + "loss": 3.8798, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6459731400721847e-05, + "loss": 3.8727, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6451345453211327e-05, + "loss": 3.8715, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644297588450454e-05, + "loss": 3.8704, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643458993699402e-05, + "loss": 3.8673, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.64262039894835e-05, + "loss": 3.8842, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.641781804197298e-05, + "loss": 3.8772, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.640943209446246e-05, + "loss": 3.8861, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6401046146951936e-05, + "loss": 3.8708, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6392676578245152e-05, + "loss": 3.8869, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6384290630734632e-05, + "loss": 3.8842, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637590468322411e-05, + "loss": 3.8836, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6367518735713588e-05, + "loss": 3.8793, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6359132788203068e-05, + "loss": 3.8761, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6350746840692548e-05, + "loss": 3.8889, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6342360893182028e-05, + "loss": 3.8891, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6333974945671508e-05, + "loss": 3.8705, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632558899816099e-05, + "loss": 3.8792, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.63172194294542e-05, + "loss": 3.8832, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.630883348194368e-05, + "loss": 3.8787, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630046391323689e-05, + "loss": 3.8725, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629207796572637e-05, + "loss": 3.8756, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6283692018215853e-05, + "loss": 3.8807, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6275306070705333e-05, + "loss": 3.8833, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6266920123194813e-05, + "loss": 3.884, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.983928680419922, + "eval_runtime": 502.6244, + "eval_samples_per_second": 759.197, + "eval_steps_per_second": 23.725, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.625853417568429e-05, + "loss": 3.8617, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625014822817377e-05, + "loss": 3.8741, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624176228066325e-05, + "loss": 3.8759, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623337633315273e-05, + "loss": 3.8785, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622499038564221e-05, + "loss": 3.8892, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6216604438131693e-05, + "loss": 3.8855, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6208218490621172e-05, + "loss": 3.8751, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.619983254311065e-05, + "loss": 3.8749, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619144659560013e-05, + "loss": 3.869, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618306064808961e-05, + "loss": 3.8783, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617467470057909e-05, + "loss": 3.8846, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616628875306857e-05, + "loss": 3.8775, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.615791918436178e-05, + "loss": 3.8824, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6149549615654994e-05, + "loss": 3.865, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614116366814447e-05, + "loss": 3.8755, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613277772063395e-05, + "loss": 3.8611, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612439177312343e-05, + "loss": 3.8805, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6116005825612914e-05, + "loss": 3.8744, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6107619878102394e-05, + "loss": 3.8769, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6099233930591874e-05, + "loss": 3.8761, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6090847983081354e-05, + "loss": 3.8918, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608246203557083e-05, + "loss": 3.8722, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607407608806031e-05, + "loss": 3.8839, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.606569014054979e-05, + "loss": 3.8751, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.605730419303927e-05, + "loss": 3.8764, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6048918245528753e-05, + "loss": 3.8825, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6040532298018233e-05, + "loss": 3.8678, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603214635050771e-05, + "loss": 3.8762, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6023776781800922e-05, + "loss": 3.8722, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601540721309413e-05, + "loss": 3.8738, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6007021265583615e-05, + "loss": 3.8765, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.5998635318073095e-05, + "loss": 3.8778, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5990249370562575e-05, + "loss": 3.8731, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5981863423052055e-05, + "loss": 3.8941, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5973477475541535e-05, + "loss": 3.8763, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5965107906834744e-05, + "loss": 3.8762, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5956721959324224e-05, + "loss": 3.8849, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5948336011813707e-05, + "loss": 3.8701, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5939950064303184e-05, + "loss": 3.875, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5931564116792664e-05, + "loss": 3.8824, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5923178169282143e-05, + "loss": 3.8722, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5914792221771623e-05, + "loss": 3.8777, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5906406274261103e-05, + "loss": 3.8806, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5898036705554316e-05, + "loss": 3.8745, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5889650758043796e-05, + "loss": 3.882, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5881264810533276e-05, + "loss": 3.88, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5872878863022756e-05, + "loss": 3.8774, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5864492915512236e-05, + "loss": 3.8801, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5856106968001716e-05, + "loss": 3.8482, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5847721020491192e-05, + "loss": 3.8813, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5839335072980676e-05, + "loss": 3.8727, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5830965504273888e-05, + "loss": 3.8839, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5822579556763365e-05, + "loss": 3.8676, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5814193609252845e-05, + "loss": 3.8605, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5805807661742325e-05, + "loss": 3.8646, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5797421714231804e-05, + "loss": 3.8693, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5789035766721284e-05, + "loss": 3.8782, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5780649819210764e-05, + "loss": 3.8582, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5772263871700248e-05, + "loss": 3.8872, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5763894302993457e-05, + "loss": 3.8774, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5755508355482937e-05, + "loss": 3.8528, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5747122407972417e-05, + "loss": 3.8799, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5738736460461893e-05, + "loss": 3.8627, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573036689175511e-05, + "loss": 3.8603, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572198094424459e-05, + "loss": 3.8697, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571359499673407e-05, + "loss": 3.8832, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5705225428027278e-05, + "loss": 3.8619, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5696839480516758e-05, + "loss": 3.877, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5688453533006238e-05, + "loss": 3.858, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5680067585495718e-05, + "loss": 3.876, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5671681637985198e-05, + "loss": 3.8795, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5663295690474678e-05, + "loss": 3.8813, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565492612176789e-05, + "loss": 3.8785, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5646540174257367e-05, + "loss": 3.8818, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5638154226746847e-05, + "loss": 3.8964, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.562976827923633e-05, + "loss": 3.8797, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562138233172581e-05, + "loss": 3.8831, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561299638421529e-05, + "loss": 3.8688, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560461043670477e-05, + "loss": 3.8731, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.559624086799798e-05, + "loss": 3.871, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.558785492048746e-05, + "loss": 3.8762, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.557946897297694e-05, + "loss": 3.8865, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5571083025466423e-05, + "loss": 3.8868, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5562697077955902e-05, + "loss": 3.8701, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555432750924911e-05, + "loss": 3.8673, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554594156173859e-05, + "loss": 3.8637, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.553755561422807e-05, + "loss": 3.8848, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5529169666717548e-05, + "loss": 3.8765, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5520800098010764e-05, + "loss": 3.8705, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5512414150500244e-05, + "loss": 3.8791, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5504028202989724e-05, + "loss": 3.8723, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.54956422554792e-05, + "loss": 3.8707, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548725630796868e-05, + "loss": 3.8694, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.547887036045816e-05, + "loss": 3.8854, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547048441294764e-05, + "loss": 3.8793, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5462098465437124e-05, + "loss": 3.8837, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5453728896730333e-05, + "loss": 3.8686, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5445342949219813e-05, + "loss": 3.8717, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5436957001709293e-05, + "loss": 3.8743, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5428571054198773e-05, + "loss": 3.8793, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5420201485491985e-05, + "loss": 3.8808, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5411815537981465e-05, + "loss": 3.8755, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5403429590470945e-05, + "loss": 3.8812, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5395060021764154e-05, + "loss": 3.8778, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5386674074253634e-05, + "loss": 3.8746, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5378288126743114e-05, + "loss": 3.863, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5369902179232594e-05, + "loss": 3.8667, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5361516231722077e-05, + "loss": 3.8675, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5353130284211557e-05, + "loss": 3.8758, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5344744336701034e-05, + "loss": 3.8647, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5336358389190514e-05, + "loss": 3.8625, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5328005199287455e-05, + "loss": 3.8669, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.531961925177694e-05, + "loss": 3.8731, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531123330426642e-05, + "loss": 3.8732, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.53028473567559e-05, + "loss": 3.8739, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529446140924538e-05, + "loss": 3.8793, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5286075461734855e-05, + "loss": 3.8799, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5277689514224335e-05, + "loss": 3.8742, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5269303566713815e-05, + "loss": 3.8795, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526093399800703e-05, + "loss": 3.8765, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5252548050496508e-05, + "loss": 3.8848, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5244162102985987e-05, + "loss": 3.875, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5235776155475467e-05, + "loss": 3.875, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227390207964947e-05, + "loss": 3.8719, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5219020639258158e-05, + "loss": 3.8793, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5210634691747638e-05, + "loss": 3.8688, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5202248744237118e-05, + "loss": 3.8713, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.51938627967266e-05, + "loss": 3.8599, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5185493228019809e-05, + "loss": 3.8662, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5177107280509289e-05, + "loss": 3.878, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.516872133299877e-05, + "loss": 3.8742, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.516033538548825e-05, + "loss": 3.8829, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515194943797773e-05, + "loss": 3.8612, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5143563490467209e-05, + "loss": 3.8854, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5135177542956689e-05, + "loss": 3.8797, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5126791595446169e-05, + "loss": 3.8834, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5118422026739381e-05, + "loss": 3.8675, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.511003607922886e-05, + "loss": 3.8749, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5101666510522072e-05, + "loss": 3.8866, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5093280563011553e-05, + "loss": 3.884, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5084894615501033e-05, + "loss": 3.8709, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.507650866799051e-05, + "loss": 3.8724, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5068122720479992e-05, + "loss": 3.877, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5059736772969472e-05, + "loss": 3.8768, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.505136720426268e-05, + "loss": 3.8688, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5042981256752162e-05, + "loss": 3.8761, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5034595309241642e-05, + "loss": 3.8741, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5026209361731122e-05, + "loss": 3.8758, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5017839793024333e-05, + "loss": 3.882, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.9828054904937744, + "eval_runtime": 303.9472, + "eval_samples_per_second": 1255.452, + "eval_steps_per_second": 39.234, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5009453845513813e-05, + "loss": 3.8699, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5001067898003293e-05, + "loss": 3.8646, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4992681950492773e-05, + "loss": 3.874, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4984296002982255e-05, + "loss": 3.8764, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4975910055471734e-05, + "loss": 3.8771, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4967524107961214e-05, + "loss": 3.8844, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4959138160450693e-05, + "loss": 3.8715, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4950752212940173e-05, + "loss": 3.8692, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4942366265429653e-05, + "loss": 3.8645, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4933980317919133e-05, + "loss": 3.8762, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925594370408612e-05, + "loss": 3.8815, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4917208422898094e-05, + "loss": 3.8732, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4908838854191303e-05, + "loss": 3.8837, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900452906680785e-05, + "loss": 3.8571, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4892066959170265e-05, + "loss": 3.8679, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883681011659745e-05, + "loss": 3.8627, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875295064149223e-05, + "loss": 3.8762, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4866909116638703e-05, + "loss": 3.8711, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4858523169128183e-05, + "loss": 3.8715, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4850137221617663e-05, + "loss": 3.8702, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4841767652910874e-05, + "loss": 3.8917, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4833381705400354e-05, + "loss": 3.8695, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4824995757889834e-05, + "loss": 3.8795, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816609810379314e-05, + "loss": 3.8719, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808240241672524e-05, + "loss": 3.8765, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4799854294162004e-05, + "loss": 3.8763, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4791468346651486e-05, + "loss": 3.8637, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4783082399140966e-05, + "loss": 3.8714, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4774696451630446e-05, + "loss": 3.8676, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4766310504119926e-05, + "loss": 3.8708, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4757924556609404e-05, + "loss": 3.8761, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749538609098884e-05, + "loss": 3.8729, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4741169040392097e-05, + "loss": 3.8698, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4732783092881578e-05, + "loss": 3.8885, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4724397145371055e-05, + "loss": 3.8723, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4716011197860535e-05, + "loss": 3.8751, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4707641629153749e-05, + "loss": 3.882, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4699255681643225e-05, + "loss": 3.8616, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690869734132705e-05, + "loss": 3.8725, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4682483786622187e-05, + "loss": 3.8733, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4674097839111667e-05, + "loss": 3.8671, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4665711891601147e-05, + "loss": 3.8776, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657325944090627e-05, + "loss": 3.8767, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4648939996580107e-05, + "loss": 3.8701, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640586806677049e-05, + "loss": 3.878, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632200859166528e-05, + "loss": 3.8774, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4623814911656008e-05, + "loss": 3.8731, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4615445342949221e-05, + "loss": 3.8776, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.46070593954387e-05, + "loss": 3.8471, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598673447928179e-05, + "loss": 3.873, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590287500417659e-05, + "loss": 3.8722, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.458190155290714e-05, + "loss": 3.8783, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.457351560539662e-05, + "loss": 3.8648, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.45651296578861e-05, + "loss": 3.8555, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.455674371037558e-05, + "loss": 3.8586, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4548357762865059e-05, + "loss": 3.8619, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4539971815354539e-05, + "loss": 3.8793, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4531585867844019e-05, + "loss": 3.8504, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.452321629913723e-05, + "loss": 3.8826, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4514846730430442e-05, + "loss": 3.8738, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4506460782919922e-05, + "loss": 3.8523, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4498074835409404e-05, + "loss": 3.8748, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.448968888789888e-05, + "loss": 3.858, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.448130294038836e-05, + "loss": 3.8598, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4472916992877842e-05, + "loss": 3.8621, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4464531045367322e-05, + "loss": 3.8764, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4456145097856802e-05, + "loss": 3.86, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4447759150346282e-05, + "loss": 3.8735, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4439373202835763e-05, + "loss": 3.8522, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.443098725532524e-05, + "loss": 3.8697, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.442260130781472e-05, + "loss": 3.8772, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4414215360304202e-05, + "loss": 3.8799, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.440584579159741e-05, + "loss": 3.875, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.439745984408689e-05, + "loss": 3.8779, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4389073896576372e-05, + "loss": 3.8904, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4380687949065852e-05, + "loss": 3.8754, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4372302001555332e-05, + "loss": 3.8802, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4363932432848543e-05, + "loss": 3.8622, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355546485338023e-05, + "loss": 3.8714, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4347160537827503e-05, + "loss": 3.8701, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4338774590316983e-05, + "loss": 3.8723, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4330405021610194e-05, + "loss": 3.8807, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4322019074099674e-05, + "loss": 3.8838, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313633126589153e-05, + "loss": 3.8715, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4305263557882364e-05, + "loss": 3.8619, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4296877610371844e-05, + "loss": 3.8628, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4288491662861326e-05, + "loss": 3.8781, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4280105715350806e-05, + "loss": 3.8712, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4271719767840286e-05, + "loss": 3.8664, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263350199133497e-05, + "loss": 3.8737, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4254964251622977e-05, + "loss": 3.8703, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246578304112457e-05, + "loss": 3.8655, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4238192356601936e-05, + "loss": 3.8659, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4229806409091418e-05, + "loss": 3.8799, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4221420461580895e-05, + "loss": 3.8788, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4213034514070375e-05, + "loss": 3.8792, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204648566559856e-05, + "loss": 3.8646, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4196278997853065e-05, + "loss": 3.8695, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4187893050342545e-05, + "loss": 3.8705, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.417952348163576e-05, + "loss": 3.8739, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.417113753412524e-05, + "loss": 3.88, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4162751586614718e-05, + "loss": 3.869, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4154365639104198e-05, + "loss": 3.876, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4145979691593678e-05, + "loss": 3.8727, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4137593744083158e-05, + "loss": 3.8721, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129207796572638e-05, + "loss": 3.861, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.412082184906212e-05, + "loss": 3.8643, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.41124359015516e-05, + "loss": 3.8657, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4104049954041076e-05, + "loss": 3.8707, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095664006530557e-05, + "loss": 3.8568, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087278059020037e-05, + "loss": 3.8631, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.407892486911698e-05, + "loss": 3.8574, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.407053892160646e-05, + "loss": 3.8738, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.406215297409594e-05, + "loss": 3.8676, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.405376702658542e-05, + "loss": 3.8725, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045381079074899e-05, + "loss": 3.8712, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4036995131564379e-05, + "loss": 3.8775, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4028625562857591e-05, + "loss": 3.8707, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020255994150802e-05, + "loss": 3.8712, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4011870046640282e-05, + "loss": 3.8762, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4003484099129764e-05, + "loss": 3.8775, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3995098151619244e-05, + "loss": 3.8725, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.398671220410872e-05, + "loss": 3.8733, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.39783262565982e-05, + "loss": 3.8692, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3969940309087682e-05, + "loss": 3.8699, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3961554361577162e-05, + "loss": 3.8651, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3953168414066642e-05, + "loss": 3.87, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3944798845359852e-05, + "loss": 3.8547, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3936429276653065e-05, + "loss": 3.8667, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3928043329142543e-05, + "loss": 3.8716, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3919657381632023e-05, + "loss": 3.8748, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3911271434121503e-05, + "loss": 3.8768, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3902885486610983e-05, + "loss": 3.8637, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3894499539100465e-05, + "loss": 3.8793, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3886113591589945e-05, + "loss": 3.8755, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3877727644079425e-05, + "loss": 3.8759, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3869341696568903e-05, + "loss": 3.8685, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3860972127862115e-05, + "loss": 3.8708, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3852602559155326e-05, + "loss": 3.8835, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3844216611644806e-05, + "loss": 3.8776, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3835847042938015e-05, + "loss": 3.8702, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3827461095427497e-05, + "loss": 3.8677, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3819075147916977e-05, + "loss": 3.8739, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3810689200406457e-05, + "loss": 3.8704, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3802303252895937e-05, + "loss": 3.8681, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3793917305385418e-05, + "loss": 3.8701, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3785531357874898e-05, + "loss": 3.8697, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3777145410364375e-05, + "loss": 3.8734, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3768759462853857e-05, + "loss": 3.8767, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9818830490112305, + "eval_runtime": 302.8364, + "eval_samples_per_second": 1260.057, + "eval_steps_per_second": 39.378, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3760373515343337e-05, + "loss": 3.8672, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3751987567832816e-05, + "loss": 3.8604, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3743617999126027e-05, + "loss": 3.8673, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3735232051615507e-05, + "loss": 3.8769, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3726846104104987e-05, + "loss": 3.8729, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3718460156594467e-05, + "loss": 3.8802, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3710074209083947e-05, + "loss": 3.8645, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3701688261573429e-05, + "loss": 3.8671, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3693302314062905e-05, + "loss": 3.8585, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.368493274535612e-05, + "loss": 3.8758, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.36765467978456e-05, + "loss": 3.8714, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.366816085033508e-05, + "loss": 3.8723, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.365979128162829e-05, + "loss": 3.8813, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.365140533411777e-05, + "loss": 3.8543, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.364301938660725e-05, + "loss": 3.8686, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.363463343909673e-05, + "loss": 3.854, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3626247491586208e-05, + "loss": 3.8714, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3617861544075688e-05, + "loss": 3.8651, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3609475596565168e-05, + "loss": 3.8725, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.360108964905465e-05, + "loss": 3.863, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.359270370154413e-05, + "loss": 3.8868, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.358431775403361e-05, + "loss": 3.8684, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3575931806523088e-05, + "loss": 3.8737, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3567545859012568e-05, + "loss": 3.8695, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.355917629030578e-05, + "loss": 3.8743, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.355079034279526e-05, + "loss": 3.8697, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3542404395284739e-05, + "loss": 3.8621, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3534018447774219e-05, + "loss": 3.8714, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3525632500263699e-05, + "loss": 3.8606, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.351724655275318e-05, + "loss": 3.8652, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.350887698404639e-05, + "loss": 3.8699, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.350049103653587e-05, + "loss": 3.8664, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3492105089025351e-05, + "loss": 3.8694, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3483719141514831e-05, + "loss": 3.8811, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3475349572808042e-05, + "loss": 3.8686, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3466963625297522e-05, + "loss": 3.875, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3458577677787002e-05, + "loss": 3.8752, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3450191730276482e-05, + "loss": 3.8606, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3441805782765962e-05, + "loss": 3.8719, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3433419835255443e-05, + "loss": 3.8666, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.342503388774492e-05, + "loss": 3.8632, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.34166479402344e-05, + "loss": 3.8745, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3408278371527614e-05, + "loss": 3.8755, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.339989242401709e-05, + "loss": 3.8614, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.339150647650657e-05, + "loss": 3.8748, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3383120528996052e-05, + "loss": 3.8734, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3374734581485532e-05, + "loss": 3.8702, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3366365012778743e-05, + "loss": 3.8749, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3357995444071955e-05, + "loss": 3.839, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3349609496561435e-05, + "loss": 3.8691, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3341223549050915e-05, + "loss": 3.8687, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3332837601540393e-05, + "loss": 3.8763, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3324451654029873e-05, + "loss": 3.8598, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3316065706519353e-05, + "loss": 3.8539, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3307696137812564e-05, + "loss": 3.853, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3299310190302044e-05, + "loss": 3.8556, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3290924242791524e-05, + "loss": 3.8776, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282538295281006e-05, + "loss": 3.8514, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274152347770486e-05, + "loss": 3.8748, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3265782779063696e-05, + "loss": 3.8678, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257396831553176e-05, + "loss": 3.8553, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3249027262846389e-05, + "loss": 3.8684, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240641315335867e-05, + "loss": 3.8525, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3232255367825347e-05, + "loss": 3.8559, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3223869420314827e-05, + "loss": 3.8568, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3215483472804307e-05, + "loss": 3.8753, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3207097525293789e-05, + "loss": 3.8593, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3198711577783269e-05, + "loss": 3.8622, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3190325630272745e-05, + "loss": 3.853, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3181939682762227e-05, + "loss": 3.8642, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.317357011405544e-05, + "loss": 3.8729, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.316520054534865e-05, + "loss": 3.8751, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.315681459783813e-05, + "loss": 3.8706, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.314842865032761e-05, + "loss": 3.8728, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.314004270281709e-05, + "loss": 3.8858, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.313165675530657e-05, + "loss": 3.8717, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3123270807796048e-05, + "loss": 3.8754, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3114884860285528e-05, + "loss": 3.864, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3106498912775008e-05, + "loss": 3.8653, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.309811296526449e-05, + "loss": 3.8633, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.308972701775397e-05, + "loss": 3.8644, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.308134107024345e-05, + "loss": 3.8778, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.307297150153666e-05, + "loss": 3.8775, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.306458555402614e-05, + "loss": 3.8742, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.305619960651562e-05, + "loss": 3.8534, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3047830037808831e-05, + "loss": 3.8587, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3039444090298311e-05, + "loss": 3.8729, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3031058142787791e-05, + "loss": 3.8695, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3022672195277271e-05, + "loss": 3.8625, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3014302626570482e-05, + "loss": 3.8682, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3005916679059962e-05, + "loss": 3.8677, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997547110353173e-05, + "loss": 3.8625, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2989161162842653e-05, + "loss": 3.865, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2980775215332132e-05, + "loss": 3.8754, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2972389267821614e-05, + "loss": 3.872, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2964003320311094e-05, + "loss": 3.8761, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2955617372800574e-05, + "loss": 3.8602, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2947231425290052e-05, + "loss": 3.8636, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2938861856583265e-05, + "loss": 3.8692, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2930475909072745e-05, + "loss": 3.8709, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2922089961562225e-05, + "loss": 3.8756, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2913704014051703e-05, + "loss": 3.8694, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2905318066541183e-05, + "loss": 3.8705, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2896932119030663e-05, + "loss": 3.8686, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2888546171520145e-05, + "loss": 3.8683, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2880160224009624e-05, + "loss": 3.8599, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2871790655302835e-05, + "loss": 3.8581, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2863404707792315e-05, + "loss": 3.8642, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2855018760281795e-05, + "loss": 3.8686, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2846632812771275e-05, + "loss": 3.8554, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2838246865260755e-05, + "loss": 3.8582, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2829860917750233e-05, + "loss": 3.8567, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2821507727847177e-05, + "loss": 3.8653, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2813121780336657e-05, + "loss": 3.8637, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2804735832826137e-05, + "loss": 3.8651, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2796349885315617e-05, + "loss": 3.8678, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2787980316608827e-05, + "loss": 3.8752, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2779594369098307e-05, + "loss": 3.8661, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2771208421587787e-05, + "loss": 3.8679, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2762822474077269e-05, + "loss": 3.8751, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2754436526566749e-05, + "loss": 3.8734, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2746050579056229e-05, + "loss": 3.8658, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2737664631545707e-05, + "loss": 3.8723, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2729278684035187e-05, + "loss": 3.867, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2720892736524667e-05, + "loss": 3.8629, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2712506789014147e-05, + "loss": 3.8569, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2704120841503629e-05, + "loss": 3.868, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2695734893993109e-05, + "loss": 3.8589, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2687365325286318e-05, + "loss": 3.8611, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.26789793777758e-05, + "loss": 3.8599, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.267059343026528e-05, + "loss": 3.8722, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.266220748275476e-05, + "loss": 3.8693, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.265383791404797e-05, + "loss": 3.8605, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.264545196653745e-05, + "loss": 3.8737, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.263706601902693e-05, + "loss": 3.8732, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.262868007151641e-05, + "loss": 3.8748, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.262031050280962e-05, + "loss": 3.8669, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.26119245552991e-05, + "loss": 3.8635, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2603538607788582e-05, + "loss": 3.8826, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2595152660278059e-05, + "loss": 3.868, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2586783091571271e-05, + "loss": 3.8725, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2578397144060753e-05, + "loss": 3.8631, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2570011196550233e-05, + "loss": 3.8683, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.256162524903971e-05, + "loss": 3.8665, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2553239301529191e-05, + "loss": 3.8631, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2544853354018671e-05, + "loss": 3.8688, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2536467406508151e-05, + "loss": 3.8666, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2528097837801362e-05, + "loss": 3.8723, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2519711890290842e-05, + "loss": 3.8683, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9806668758392334, + "eval_runtime": 303.9175, + "eval_samples_per_second": 1255.574, + "eval_steps_per_second": 39.238, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2511325942780322e-05, + "loss": 3.8494, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2502939995269802e-05, + "loss": 3.8581, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2494554047759283e-05, + "loss": 3.8642, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2486168100248762e-05, + "loss": 3.8736, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2477782152738242e-05, + "loss": 3.8701, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2469396205227722e-05, + "loss": 3.8788, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2461010257717201e-05, + "loss": 3.8597, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2452624310206681e-05, + "loss": 3.8624, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2444238362696161e-05, + "loss": 3.8571, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2435852415185641e-05, + "loss": 3.8689, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2427466467675121e-05, + "loss": 3.8707, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2419080520164601e-05, + "loss": 3.8666, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2410710951457814e-05, + "loss": 3.8735, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2402325003947292e-05, + "loss": 3.8523, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2393939056436772e-05, + "loss": 3.8603, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2385553108926252e-05, + "loss": 3.8552, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2377167161415732e-05, + "loss": 3.8679, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2368781213905212e-05, + "loss": 3.8605, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2360395266394692e-05, + "loss": 3.869, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2352025697687904e-05, + "loss": 3.8591, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2343639750177383e-05, + "loss": 3.8795, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2335253802666862e-05, + "loss": 3.8654, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2326867855156342e-05, + "loss": 3.865, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2318481907645822e-05, + "loss": 3.8673, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2310095960135302e-05, + "loss": 3.8748, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2301710012624782e-05, + "loss": 3.8653, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2293324065114262e-05, + "loss": 3.859, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2284938117603742e-05, + "loss": 3.8671, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2276552170093222e-05, + "loss": 3.8566, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2268166222582702e-05, + "loss": 3.8615, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2259796653875913e-05, + "loss": 3.8657, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2251410706365393e-05, + "loss": 3.8612, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2243024758854873e-05, + "loss": 3.8652, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2234638811344353e-05, + "loss": 3.8756, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2226252863833833e-05, + "loss": 3.8672, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2217866916323313e-05, + "loss": 3.8704, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2209497347616525e-05, + "loss": 3.8709, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2201111400106003e-05, + "loss": 3.8553, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2192725452595483e-05, + "loss": 3.8741, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2184339505084965e-05, + "loss": 3.8606, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2175953557574443e-05, + "loss": 3.8606, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2167583988867654e-05, + "loss": 3.8691, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2159198041357136e-05, + "loss": 3.8737, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2150812093846616e-05, + "loss": 3.8548, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2142426146336094e-05, + "loss": 3.878, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2134056577629306e-05, + "loss": 3.8673, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2125670630118786e-05, + "loss": 3.8668, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2117284682608266e-05, + "loss": 3.8701, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2108898735097746e-05, + "loss": 3.8379, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2100512787587226e-05, + "loss": 3.8617, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2092143218880437e-05, + "loss": 3.8693, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2083757271369917e-05, + "loss": 3.8704, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2075371323859397e-05, + "loss": 3.8536, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2066985376348877e-05, + "loss": 3.8509, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2058599428838357e-05, + "loss": 3.85, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2050229860131568e-05, + "loss": 3.8523, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2041843912621048e-05, + "loss": 3.8786, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2033457965110528e-05, + "loss": 3.8442, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2025072017600008e-05, + "loss": 3.871, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2016686070089487e-05, + "loss": 3.8634, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2008300122578967e-05, + "loss": 3.8485, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.1999914175068447e-05, + "loss": 3.8643, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1991528227557927e-05, + "loss": 3.8527, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1983158658851138e-05, + "loss": 3.8544, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.197477271134062e-05, + "loss": 3.8505, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1966386763830098e-05, + "loss": 3.8702, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1958000816319578e-05, + "loss": 3.8602, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1949614868809058e-05, + "loss": 3.8556, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.194124530010227e-05, + "loss": 3.8512, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1932875731395481e-05, + "loss": 3.8581, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1924489783884961e-05, + "loss": 3.8711, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1916103836374441e-05, + "loss": 3.8706, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1907717888863921e-05, + "loss": 3.8659, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1899348320157132e-05, + "loss": 3.8686, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1890962372646612e-05, + "loss": 3.8821, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1882576425136092e-05, + "loss": 3.8664, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1874206856429304e-05, + "loss": 3.8732, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1865820908918783e-05, + "loss": 3.8608, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1857434961408263e-05, + "loss": 3.8664, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1849049013897744e-05, + "loss": 3.8625, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1840663066387222e-05, + "loss": 3.8582, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1832277118876702e-05, + "loss": 3.8743, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1823891171366182e-05, + "loss": 3.8773, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1815505223855662e-05, + "loss": 3.8734, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1807119276345142e-05, + "loss": 3.8479, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1798733328834622e-05, + "loss": 3.8575, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1790347381324104e-05, + "loss": 3.8668, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1781977812617313e-05, + "loss": 3.8669, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1773591865106793e-05, + "loss": 3.8575, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1765205917596275e-05, + "loss": 3.8672, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1756819970085753e-05, + "loss": 3.8616, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1748450401378965e-05, + "loss": 3.8595, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1740064453868445e-05, + "loss": 3.8594, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1731678506357925e-05, + "loss": 3.8747, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1723292558847403e-05, + "loss": 3.864, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1714906611336885e-05, + "loss": 3.8771, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1706537042630096e-05, + "loss": 3.8568, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1698151095119574e-05, + "loss": 3.8589, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1689781526412787e-05, + "loss": 3.8683, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1681395578902267e-05, + "loss": 3.8684, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1673009631391747e-05, + "loss": 3.8709, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1664623683881227e-05, + "loss": 3.8647, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1656237736370706e-05, + "loss": 3.8662, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1647851788860186e-05, + "loss": 3.8647, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1639465841349666e-05, + "loss": 3.8681, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1631079893839146e-05, + "loss": 3.8507, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1622710325132357e-05, + "loss": 3.8581, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1614324377621839e-05, + "loss": 3.8587, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1605938430111317e-05, + "loss": 3.8628, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1597552482600797e-05, + "loss": 3.8559, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1589166535090277e-05, + "loss": 3.8553, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.158079696638349e-05, + "loss": 3.8494, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1572411018872968e-05, + "loss": 3.8663, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1564025071362448e-05, + "loss": 3.8594, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.155563912385193e-05, + "loss": 3.8627, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1547253176341408e-05, + "loss": 3.8652, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1538867228830888e-05, + "loss": 3.8709, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1530481281320367e-05, + "loss": 3.8644, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1522095333809847e-05, + "loss": 3.8606, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1513725765103058e-05, + "loss": 3.8748, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.150533981759254e-05, + "loss": 3.868, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.149695387008202e-05, + "loss": 3.8592, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1488567922571498e-05, + "loss": 3.8695, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.148019835386471e-05, + "loss": 3.8619, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.147181240635419e-05, + "loss": 3.8633, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.146342645884367e-05, + "loss": 3.8524, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.145504051133315e-05, + "loss": 3.8683, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1446670942626361e-05, + "loss": 3.8539, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1438301373919574e-05, + "loss": 3.8591, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1429915426409054e-05, + "loss": 3.8491, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1421529478898532e-05, + "loss": 3.8747, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1413143531388012e-05, + "loss": 3.8673, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1404757583877494e-05, + "loss": 3.8547, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1396371636366972e-05, + "loss": 3.8713, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1387985688856452e-05, + "loss": 3.8674, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1379599741345932e-05, + "loss": 3.8721, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1371213793835412e-05, + "loss": 3.8624, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1362827846324892e-05, + "loss": 3.8653, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1354458277618102e-05, + "loss": 3.8764, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1346072330107584e-05, + "loss": 3.8627, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1337686382597062e-05, + "loss": 3.87, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1329300435086542e-05, + "loss": 3.8592, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1320930866379755e-05, + "loss": 3.8688, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1312561297672966e-05, + "loss": 3.8611, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1304175350162446e-05, + "loss": 3.8586, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1295789402651925e-05, + "loss": 3.865, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1287403455141405e-05, + "loss": 3.8618, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1279017507630885e-05, + "loss": 3.8689, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1270631560120365e-05, + "loss": 3.8646, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.979696035385132, + "eval_runtime": 299.3117, + "eval_samples_per_second": 1274.895, + "eval_steps_per_second": 39.841, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1262261991413576e-05, + "loss": 3.8599, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1253876043903056e-05, + "loss": 3.8607, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1245490096392536e-05, + "loss": 3.8573, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1237104148882016e-05, + "loss": 3.867, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1228718201371496e-05, + "loss": 3.864, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1220332253860976e-05, + "loss": 3.8756, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1211946306350456e-05, + "loss": 3.8543, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1203560358839936e-05, + "loss": 3.8591, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1195190790133148e-05, + "loss": 3.8535, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1186804842622627e-05, + "loss": 3.8696, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1178418895112107e-05, + "loss": 3.8605, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1170032947601586e-05, + "loss": 3.8686, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1161663378894799e-05, + "loss": 3.8716, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.115329381018801e-05, + "loss": 3.8513, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.114490786267749e-05, + "loss": 3.8548, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.113652191516697e-05, + "loss": 3.8541, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1128135967656448e-05, + "loss": 3.8618, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.111975002014593e-05, + "loss": 3.8597, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.111136407263541e-05, + "loss": 3.8643, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.110299450392862e-05, + "loss": 3.8567, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.10946085564181e-05, + "loss": 3.8764, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.108622260890758e-05, + "loss": 3.8596, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.107783666139706e-05, + "loss": 3.865, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.106945071388654e-05, + "loss": 3.8652, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.106106476637602e-05, + "loss": 3.8707, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.10526788188655e-05, + "loss": 3.8625, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1044292871354978e-05, + "loss": 3.8554, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.103590692384446e-05, + "loss": 3.8627, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.102752097633394e-05, + "loss": 3.8515, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.101913502882342e-05, + "loss": 3.8611, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.101076546011663e-05, + "loss": 3.8581, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.100237951260611e-05, + "loss": 3.8642, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.099399356509559e-05, + "loss": 3.8601, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.098560761758507e-05, + "loss": 3.8682, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.097722167007455e-05, + "loss": 3.8695, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.096883572256403e-05, + "loss": 3.8668, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.096044977505351e-05, + "loss": 3.868, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0952080206346721e-05, + "loss": 3.8544, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0943694258836201e-05, + "loss": 3.8696, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0935308311325681e-05, + "loss": 3.8587, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0926922363815161e-05, + "loss": 3.8586, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0918552795108372e-05, + "loss": 3.8651, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0910166847597852e-05, + "loss": 3.8678, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0901780900087333e-05, + "loss": 3.8534, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0893394952576812e-05, + "loss": 3.8702, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0885009005066292e-05, + "loss": 3.8647, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0876623057555772e-05, + "loss": 3.8644, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0868237110045252e-05, + "loss": 3.8686, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0859851162534732e-05, + "loss": 3.8364, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0851497972631675e-05, + "loss": 3.8549, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0843128403924886e-05, + "loss": 3.868, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0834742456414367e-05, + "loss": 3.8671, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0826356508903846e-05, + "loss": 3.8524, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0817970561393326e-05, + "loss": 3.8434, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0809584613882805e-05, + "loss": 3.8518, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0801198666372285e-05, + "loss": 3.8441, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0792812718861765e-05, + "loss": 3.8784, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0784426771351245e-05, + "loss": 3.8414, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0776040823840725e-05, + "loss": 3.868, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0767671255133936e-05, + "loss": 3.8591, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0759285307623416e-05, + "loss": 3.8473, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0750899360112896e-05, + "loss": 3.8585, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0742513412602376e-05, + "loss": 3.8523, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0734127465091856e-05, + "loss": 3.8477, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0725757896385068e-05, + "loss": 3.8442, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0717371948874548e-05, + "loss": 3.868, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0708986001364027e-05, + "loss": 3.8547, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0700600053853507e-05, + "loss": 3.8504, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0692214106342988e-05, + "loss": 3.8461, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0683844537636197e-05, + "loss": 3.8562, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0675458590125679e-05, + "loss": 3.8676, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0667072642615159e-05, + "loss": 3.87, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.065870307390837e-05, + "loss": 3.8614, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.065031712639785e-05, + "loss": 3.8641, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.064193117888733e-05, + "loss": 3.878, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.063354523137681e-05, + "loss": 3.8673, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0625159283866288e-05, + "loss": 3.866, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.061677333635577e-05, + "loss": 3.8547, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.060838738884525e-05, + "loss": 3.863, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060000144133473e-05, + "loss": 3.8569, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0591615493824208e-05, + "loss": 3.86, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.058324592511742e-05, + "loss": 3.8689, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.05748599776069e-05, + "loss": 3.8732, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.056647403009638e-05, + "loss": 3.8648, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.055808808258586e-05, + "loss": 3.8486, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.054971851387907e-05, + "loss": 3.8524, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0541332566368552e-05, + "loss": 3.8597, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.053294661885803e-05, + "loss": 3.8692, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.052456067134751e-05, + "loss": 3.8501, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.051617472383699e-05, + "loss": 3.8654, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0507805155130201e-05, + "loss": 3.8616, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0499419207619681e-05, + "loss": 3.8533, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0491033260109161e-05, + "loss": 3.8568, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0482647312598643e-05, + "loss": 3.8676, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0474277743891852e-05, + "loss": 3.8615, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0465891796381334e-05, + "loss": 3.8721, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0457505848870814e-05, + "loss": 3.8557, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0449119901360292e-05, + "loss": 3.8559, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0440733953849772e-05, + "loss": 3.8608, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0432348006339254e-05, + "loss": 3.8657, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0423962058828734e-05, + "loss": 3.8643, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0415592490121943e-05, + "loss": 3.8645, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0407206542611424e-05, + "loss": 3.8635, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0398820595100904e-05, + "loss": 3.8631, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0390434647590382e-05, + "loss": 3.8626, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0382048700079864e-05, + "loss": 3.8462, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0373662752569344e-05, + "loss": 3.8536, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0365276805058824e-05, + "loss": 3.8598, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0356890857548302e-05, + "loss": 3.8567, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0348504910037784e-05, + "loss": 3.8521, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0340118962527264e-05, + "loss": 3.8526, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0331733015016742e-05, + "loss": 3.8469, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0323347067506222e-05, + "loss": 3.8603, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0314961119995704e-05, + "loss": 3.8535, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0306591551288915e-05, + "loss": 3.8642, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0298205603778393e-05, + "loss": 3.8592, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0289819656267874e-05, + "loss": 3.8684, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0281433708757354e-05, + "loss": 3.8609, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0273064140050565e-05, + "loss": 3.8578, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0264694571343776e-05, + "loss": 3.8656, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0256308623833256e-05, + "loss": 3.864, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0247922676322738e-05, + "loss": 3.8588, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0239536728812216e-05, + "loss": 3.8631, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0231167160105427e-05, + "loss": 3.8585, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0222781212594908e-05, + "loss": 3.8611, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0214395265084388e-05, + "loss": 3.8527, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0206009317573867e-05, + "loss": 3.8569, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0197623370063346e-05, + "loss": 3.8521, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0189253801356559e-05, + "loss": 3.8536, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0180867853846037e-05, + "loss": 3.8452, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0172481906335519e-05, + "loss": 3.873, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0164095958824999e-05, + "loss": 3.8658, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.015572639011821e-05, + "loss": 3.8581, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.014734044260769e-05, + "loss": 3.8608, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.013895449509717e-05, + "loss": 3.8611, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.013056854758665e-05, + "loss": 3.8728, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0122182600076128e-05, + "loss": 3.8623, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.011381303136934e-05, + "loss": 3.8609, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.010542708385882e-05, + "loss": 3.8718, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.00970411363483e-05, + "loss": 3.8563, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.008865518883778e-05, + "loss": 3.8661, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.008026924132726e-05, + "loss": 3.8587, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.007188329381674e-05, + "loss": 3.8659, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.006349734630622e-05, + "loss": 3.8605, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.00551113987957e-05, + "loss": 3.8493, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.004674183008891e-05, + "loss": 3.866, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0038372261382123e-05, + "loss": 3.8597, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0029986313871601e-05, + "loss": 3.8639, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0021600366361081e-05, + "loss": 3.8602, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0013214418850563e-05, + "loss": 3.8608, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.9788131713867188, + "eval_runtime": 289.6473, + "eval_samples_per_second": 1317.433, + "eval_steps_per_second": 41.171, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0004828471340043e-05, + "loss": 3.8537, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.996442523829521e-06, + "loss": 3.8521, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.988056576319001e-06, + "loss": 3.8657, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.979670628808483e-06, + "loss": 3.8632, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.971284681297961e-06, + "loss": 3.87, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.962898733787441e-06, + "loss": 3.854, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.954512786276921e-06, + "loss": 3.8535, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.946126838766401e-06, + "loss": 3.8464, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.937740891255881e-06, + "loss": 3.8672, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.929354943745361e-06, + "loss": 3.8586, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.920968996234841e-06, + "loss": 3.8643, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.91258304872432e-06, + "loss": 3.8644, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.904213480017532e-06, + "loss": 3.854, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.895827532507013e-06, + "loss": 3.8528, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.887441584996492e-06, + "loss": 3.8517, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.879055637485971e-06, + "loss": 3.8505, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.870669689975451e-06, + "loss": 3.8604, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.862283742464931e-06, + "loss": 3.8576, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.853897794954411e-06, + "loss": 3.8511, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.845511847443891e-06, + "loss": 3.8771, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.837125899933371e-06, + "loss": 3.8544, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.828739952422851e-06, + "loss": 3.8635, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.820354004912331e-06, + "loss": 3.8608, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.811984436205544e-06, + "loss": 3.8674, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.803598488695022e-06, + "loss": 3.8544, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.795212541184502e-06, + "loss": 3.8579, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.786826593673982e-06, + "loss": 3.8534, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.778440646163463e-06, + "loss": 3.8538, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.770071077456673e-06, + "loss": 3.8546, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.761685129946154e-06, + "loss": 3.8536, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.753299182435634e-06, + "loss": 3.8626, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.744913234925112e-06, + "loss": 3.8572, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.736543666218325e-06, + "loss": 3.863, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.728157718707805e-06, + "loss": 3.8655, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.719771771197285e-06, + "loss": 3.862, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.711402202490496e-06, + "loss": 3.8623, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.703016254979976e-06, + "loss": 3.8563, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.694630307469456e-06, + "loss": 3.8605, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.686244359958936e-06, + "loss": 3.8547, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.677858412448415e-06, + "loss": 3.8587, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.669488843741626e-06, + "loss": 3.8606, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.661102896231106e-06, + "loss": 3.8644, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.652716948720586e-06, + "loss": 3.8499, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.644331001210066e-06, + "loss": 3.8656, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.635945053699546e-06, + "loss": 3.8631, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.627559106189028e-06, + "loss": 3.8638, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.619189537482237e-06, + "loss": 3.8605, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.610803589971717e-06, + "loss": 3.8343, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.602417642461198e-06, + "loss": 3.8523, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.594031694950677e-06, + "loss": 3.8632, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.585645747440157e-06, + "loss": 3.8643, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.577259799929637e-06, + "loss": 3.8507, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.568873852419118e-06, + "loss": 3.8397, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.560487904908597e-06, + "loss": 3.8482, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.552101957398076e-06, + "loss": 3.8414, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.543716009887556e-06, + "loss": 3.871, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.535346441180767e-06, + "loss": 3.8414, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.526960493670247e-06, + "loss": 3.8613, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.51859092496346e-06, + "loss": 3.8589, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.51022135625667e-06, + "loss": 3.8422, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.50183540874615e-06, + "loss": 3.8548, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.49344946123563e-06, + "loss": 3.8503, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.48506351372511e-06, + "loss": 3.8426, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.47667756621459e-06, + "loss": 3.8418, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.46829161870407e-06, + "loss": 3.8681, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.45990567119355e-06, + "loss": 3.8549, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.45151972368303e-06, + "loss": 3.8473, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.44313377617251e-06, + "loss": 3.8436, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.434764207465721e-06, + "loss": 3.8504, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.4263782599552e-06, + "loss": 3.8619, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.417992312444682e-06, + "loss": 3.8663, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.40960636493416e-06, + "loss": 3.859, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.40122041742364e-06, + "loss": 3.8647, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.39283446991312e-06, + "loss": 3.8725, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.3844485224026e-06, + "loss": 3.8635, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.37606257489208e-06, + "loss": 3.8618, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.36767662738156e-06, + "loss": 3.8535, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.35929067987104e-06, + "loss": 3.8628, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.35090473236052e-06, + "loss": 3.8565, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.34251878485e-06, + "loss": 3.8549, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.334149216143211e-06, + "loss": 3.8639, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.325779647436422e-06, + "loss": 3.8689, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.317393699925902e-06, + "loss": 3.8658, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.309007752415384e-06, + "loss": 3.8441, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.300638183708594e-06, + "loss": 3.8482, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.292252236198074e-06, + "loss": 3.859, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.283866288687554e-06, + "loss": 3.8649, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.275480341177034e-06, + "loss": 3.8521, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.267094393666512e-06, + "loss": 3.8602, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.258708446155994e-06, + "loss": 3.8603, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.250322498645474e-06, + "loss": 3.8505, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.241936551134952e-06, + "loss": 3.8536, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.233550603624432e-06, + "loss": 3.8598, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.225164656113914e-06, + "loss": 3.8586, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.216778708603394e-06, + "loss": 3.8662, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.208409139896603e-06, + "loss": 3.8594, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.200023192386085e-06, + "loss": 3.8467, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.191637244875565e-06, + "loss": 3.8624, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.183251297365043e-06, + "loss": 3.8621, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.174865349854523e-06, + "loss": 3.8583, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.166495781147735e-06, + "loss": 3.8649, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.158109833637215e-06, + "loss": 3.857, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.149740264930426e-06, + "loss": 3.8609, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.141354317419906e-06, + "loss": 3.8623, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.132968369909386e-06, + "loss": 3.8429, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.124582422398868e-06, + "loss": 3.8465, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.116196474888346e-06, + "loss": 3.8582, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.107810527377826e-06, + "loss": 3.8557, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.099424579867306e-06, + "loss": 3.8458, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.091038632356786e-06, + "loss": 3.8496, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.082652684846266e-06, + "loss": 3.8487, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.074266737335746e-06, + "loss": 3.8553, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.065897168628958e-06, + "loss": 3.852, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.057511221118436e-06, + "loss": 3.8568, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.049125273607916e-06, + "loss": 3.8546, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.040739326097396e-06, + "loss": 3.8623, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.032353378586876e-06, + "loss": 3.8598, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.023967431076356e-06, + "loss": 3.8606, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.015597862369569e-06, + "loss": 3.862, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.007211914859049e-06, + "loss": 3.863, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 8.998825967348527e-06, + "loss": 3.8513, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.990440019838007e-06, + "loss": 3.8616, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.982054072327489e-06, + "loss": 3.854, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.973684503620698e-06, + "loss": 3.8639, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.96529855611018e-06, + "loss": 3.8454, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.95691260859966e-06, + "loss": 3.8593, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.94852666108914e-06, + "loss": 3.8428, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.94017347118608e-06, + "loss": 3.8481, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.93178752367556e-06, + "loss": 3.8426, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.92340157616504e-06, + "loss": 3.8703, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.915015628654522e-06, + "loss": 3.8663, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.906629681144e-06, + "loss": 3.8511, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.89824373363348e-06, + "loss": 3.8549, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.88985778612296e-06, + "loss": 3.8581, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.88147183861244e-06, + "loss": 3.8694, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.873102269905651e-06, + "loss": 3.8621, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.864716322395131e-06, + "loss": 3.8523, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.856330374884613e-06, + "loss": 3.8675, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.847944427374091e-06, + "loss": 3.8536, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.839558479863571e-06, + "loss": 3.8656, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.831172532353053e-06, + "loss": 3.8541, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.822802963646262e-06, + "loss": 3.8595, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.814417016135742e-06, + "loss": 3.8601, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.806047447428954e-06, + "loss": 3.849, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.797661499918434e-06, + "loss": 3.8587, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.789275552407914e-06, + "loss": 3.8578, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.780889604897394e-06, + "loss": 3.8619, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.772503657386874e-06, + "loss": 3.8599, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.764117709876352e-06, + "loss": 3.8515, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.977557897567749, + "eval_runtime": 293.6915, + "eval_samples_per_second": 1299.292, + "eval_steps_per_second": 40.604, + "step": 2518560 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0397546451057765e+18, + "trial_name": null, + "trial_params": null +}