{ "best_metric": 4.258720874786377, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/lstm/0/checkpoints/checkpoint-305276", "epoch": 1.0250002784396635, "eval_steps": 10, "global_step": 305276, "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": 10.8208, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5643, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0552, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9853, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9546, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.8345, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.6849, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.578, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.5051, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4266, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.3936, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 6.3397, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 6.2845, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 6.2212, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 6.1692, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987424354494966e-05, "loss": 6.1253, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986585759743914e-05, "loss": 6.0774, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985747164992862e-05, "loss": 6.0212, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.98490857024181e-05, "loss": 5.9826, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984069975490758e-05, "loss": 5.9437, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983231380739706e-05, "loss": 5.8964, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 5.8603, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 5.8387, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 5.8015, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7798, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.753, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.7306, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.7024, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6697, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6631, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.6306, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.6149, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5898, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.972331286856403e-05, "loss": 5.5863, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5553, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5464, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5332, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.5146, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.5046, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4821, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.458, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4517, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 5.4245, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 5.4377, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 5.4104, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.4062, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 5.39, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960595873982795e-05, "loss": 5.3878, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 5.3812, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 5.3515, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3399, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3333, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956404538107908e-05, "loss": 5.3401, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.3164, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.3222, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953890391735125e-05, "loss": 5.2935, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530517969840727e-05, "loss": 5.2899, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 5.2768, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 5.2704, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.95053765061129e-05, "loss": 5.2681, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949699055860238e-05, "loss": 5.2477, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948860461109186e-05, "loss": 5.2419, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948021866358134e-05, "loss": 5.2455, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.2254, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.2229, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2119, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944669125234299e-05, "loss": 5.2113, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943830530483247e-05, "loss": 5.1964, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942993573612568e-05, "loss": 5.1989, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942154978861516e-05, "loss": 5.1858, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941316384110464e-05, "loss": 5.1748, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940477789359412e-05, "loss": 5.178, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.93963919460836e-05, "loss": 5.1629, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.938800599857309e-05, "loss": 5.1712, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379636429866296e-05, "loss": 5.1684, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371250482355776e-05, "loss": 5.1604, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1398, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.1243, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346109018627945e-05, "loss": 5.1169, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337723071117425e-05, "loss": 5.1225, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 5.1249, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 5.1188, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 5.0935, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 5.0878, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295809712368554e-05, "loss": 5.0967, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287423764858034e-05, "loss": 5.0827, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279037817347514e-05, "loss": 5.0815, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 5.0732, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.92622823011302e-05, "loss": 5.0747, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925389635361968e-05, "loss": 5.0627, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924551040610916e-05, "loss": 5.0555, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923712445859864e-05, "loss": 5.0409, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922873851108812e-05, "loss": 5.0549, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.0393, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921198299487081e-05, "loss": 5.023, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920359704736029e-05, "loss": 5.0225, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919521109984978e-05, "loss": 5.0346, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918682515233926e-05, "loss": 5.0247, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917843920482874e-05, "loss": 5.0148, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917005325731822e-05, "loss": 5.0016, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.91616673098077e-05, "loss": 5.0071, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915329774110091e-05, "loss": 4.9867, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914491179359039e-05, "loss": 5.0018, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913652584607987e-05, "loss": 5.0018, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912813989856935e-05, "loss": 4.9766, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911975395105883e-05, "loss": 4.9698, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111384382352036e-05, "loss": 4.9484, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9102998434841516e-05, "loss": 4.9585, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.9094612487330996e-05, "loss": 4.9589, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086226539820476e-05, "loss": 4.9543, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907785697111369e-05, "loss": 4.9548, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.9378, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.9401, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905271550738586e-05, "loss": 4.9402, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.9417, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.9285, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.917, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901918809614751e-05, "loss": 4.9183, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901080214863699e-05, "loss": 4.9209, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900241620112647e-05, "loss": 4.9158, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.9127, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898564430610543e-05, "loss": 4.9006, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897725835859491e-05, "loss": 4.8934, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968872411084396e-05, "loss": 4.8861, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.8922, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952116894867085e-05, "loss": 4.8892, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943730947356565e-05, "loss": 4.8909, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893534499984604e-05, "loss": 4.8653, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8795, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8787, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8649, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890181758860769e-05, "loss": 4.8806, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889343164109717e-05, "loss": 4.8592, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.8732, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.8616, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.8408, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885990422985882e-05, "loss": 4.84, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515182823483e-05, "loss": 4.8401, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884314871364151e-05, "loss": 4.842, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883476276613099e-05, "loss": 4.847, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.8436, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.8373, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.8266, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.8152, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.8153, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87844634598716e-05, "loss": 4.8211, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877607751236109e-05, "loss": 4.8283, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876769156485057e-05, "loss": 4.8185, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.802, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.8015, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.766555309295654, "eval_runtime": 557.3806, "eval_samples_per_second": 684.615, "eval_steps_per_second": 21.395, "step": 76319 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.8093, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.8013, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.87257782061017e-05, "loss": 4.7935, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871739225859118e-05, "loss": 4.7915, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709006311080657e-05, "loss": 4.7826, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700620363570137e-05, "loss": 4.7666, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692234416059616e-05, "loss": 4.7752, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683864847352826e-05, "loss": 4.7838, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675478899842306e-05, "loss": 4.767, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866710933113552e-05, "loss": 4.7745, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658723383625e-05, "loss": 4.777, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865033743611448e-05, "loss": 4.7775, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864195148860396e-05, "loss": 4.765, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863356554109344e-05, "loss": 4.7614, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862519597238665e-05, "loss": 4.7594, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861681002487613e-05, "loss": 4.7504, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860842407736561e-05, "loss": 4.7528, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860003812985509e-05, "loss": 4.7522, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859165218234457e-05, "loss": 4.7511, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858326623483405e-05, "loss": 4.75, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.7362, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856651071861674e-05, "loss": 4.7489, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.7349, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.85497388235957e-05, "loss": 4.744, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854135287608518e-05, "loss": 4.733, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853296692857466e-05, "loss": 4.7329, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524597359867875e-05, "loss": 4.7341, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851621141235735e-05, "loss": 4.7159, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850782546484683e-05, "loss": 4.7296, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849943951733631e-05, "loss": 4.7102, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849105356982579e-05, "loss": 4.7158, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848266762231527e-05, "loss": 4.7127, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847428167480475e-05, "loss": 4.72, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846589572729423e-05, "loss": 4.7078, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845750977978371e-05, "loss": 4.7009, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844915658988065e-05, "loss": 4.718, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844077064237013e-05, "loss": 4.7027, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843238469485961e-05, "loss": 4.7103, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842399874734909e-05, "loss": 4.6965, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841561279983857e-05, "loss": 4.6849, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840722685232805e-05, "loss": 4.6876, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839884090481753e-05, "loss": 4.6795, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839045495730701e-05, "loss": 4.6936, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838206900979649e-05, "loss": 4.6825, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83736994410897e-05, "loss": 4.6895, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836531349357918e-05, "loss": 4.6801, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835692754606866e-05, "loss": 4.6877, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834854159855814e-05, "loss": 4.6846, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834015565104763e-05, "loss": 4.6593, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833176970353711e-05, "loss": 4.6648, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832340013483032e-05, "loss": 4.663, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.83150141873198e-05, "loss": 4.6745, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830662823980928e-05, "loss": 4.6529, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829824229229876e-05, "loss": 4.6769, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828985634478824e-05, "loss": 4.6504, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828147039727771e-05, "loss": 4.6505, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827308444976719e-05, "loss": 4.653, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826469850225667e-05, "loss": 4.6485, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256328933549886e-05, "loss": 4.6501, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8247942986039366e-05, "loss": 4.6425, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823957341733258e-05, "loss": 4.6398, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823118746982206e-05, "loss": 4.6484, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222801522311535e-05, "loss": 4.6354, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214415574801015e-05, "loss": 4.6349, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820604600609423e-05, "loss": 4.6328, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819766005858371e-05, "loss": 4.638, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189274111073184e-05, "loss": 4.6225, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180888163562664e-05, "loss": 4.6415, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172502216052144e-05, "loss": 4.6283, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816413264734535e-05, "loss": 4.6265, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815574669983483e-05, "loss": 4.6312, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814736075232432e-05, "loss": 4.6191, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.81389748048138e-05, "loss": 4.6362, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813058885730328e-05, "loss": 4.6398, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812220290979276e-05, "loss": 4.6348, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811381696228224e-05, "loss": 4.6161, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810543101477172e-05, "loss": 4.6095, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809706144606493e-05, "loss": 4.6044, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808867549855441e-05, "loss": 4.6155, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808028955104389e-05, "loss": 4.6255, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807190360353337e-05, "loss": 4.6182, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806351765602285e-05, "loss": 4.6047, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805513170851233e-05, "loss": 4.5933, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804674576100181e-05, "loss": 4.6112, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803835981349129e-05, "loss": 4.5969, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8029990244784504e-05, "loss": 4.6, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802162067607771e-05, "loss": 4.6018, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801323472856719e-05, "loss": 4.6099, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800484878105667e-05, "loss": 4.5978, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799646283354615e-05, "loss": 4.5951, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798809326483936e-05, "loss": 4.5844, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797970731732884e-05, "loss": 4.5974, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797132136981832e-05, "loss": 4.5947, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.79629354223078e-05, "loss": 4.5723, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795454947479728e-05, "loss": 4.5805, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794616352728676e-05, "loss": 4.5964, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.5966, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5821, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792102206355894e-05, "loss": 4.5781, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791263611604842e-05, "loss": 4.5875, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.79042501685379e-05, "loss": 4.5677, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789586422102737e-05, "loss": 4.5834, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788747827351685e-05, "loss": 4.5865, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787909232600633e-05, "loss": 4.573, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787070637849581e-05, "loss": 4.5731, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786232043098529e-05, "loss": 4.5513, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785393448347477e-05, "loss": 4.5566, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784556491476798e-05, "loss": 4.563, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783717896725746e-05, "loss": 4.5636, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782879301974694e-05, "loss": 4.568, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782040707223642e-05, "loss": 4.5561, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812021124725906e-05, "loss": 4.554, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803651556019115e-05, "loss": 4.5605, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795265608508595e-05, "loss": 4.5666, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786879660998075e-05, "loss": 4.5541, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778493713487555e-05, "loss": 4.5549, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770124144780764e-05, "loss": 4.5507, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761738197270244e-05, "loss": 4.5556, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753352249759724e-05, "loss": 4.5553, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.7744966302249204e-05, "loss": 4.5483, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736580354738684e-05, "loss": 4.5469, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728194407228164e-05, "loss": 4.5414, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719808459717644e-05, "loss": 4.536, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711422512207124e-05, "loss": 4.5419, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703036564696604e-05, "loss": 4.5452, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694650617186084e-05, "loss": 4.5475, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686264669675564e-05, "loss": 4.5289, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7677878722165044e-05, "loss": 4.5387, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766950915345826e-05, "loss": 4.5503, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766113958475147e-05, "loss": 4.5321, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765277001604468e-05, "loss": 4.5458, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764438406853416e-05, "loss": 4.5315, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763599812102364e-05, "loss": 4.5482, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762761217351312e-05, "loss": 4.5357, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.76192262260026e-05, "loss": 4.5208, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761084027849208e-05, "loss": 4.5233, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760245433098156e-05, "loss": 4.52, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759406838347104e-05, "loss": 4.5297, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758568243596052e-05, "loss": 4.5318, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757729648845e-05, "loss": 4.533, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756891054093948e-05, "loss": 4.5285, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756052459342896e-05, "loss": 4.5203, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.75521714035259e-05, "loss": 4.5146, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543785456015375e-05, "loss": 4.5121, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535399508504855e-05, "loss": 4.5211, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527013560994335e-05, "loss": 4.534, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518627613483815e-05, "loss": 4.5185, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751025804477703e-05, "loss": 4.5094, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750187209726651e-05, "loss": 4.5084, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.478529930114746, "eval_runtime": 543.7518, "eval_samples_per_second": 701.774, "eval_steps_per_second": 21.931, "step": 152638 }, { "epoch": 0.0, "learning_rate": 4.749348614975599e-05, "loss": 4.52, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748510020224547e-05, "loss": 4.5158, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747671425473495e-05, "loss": 4.5033, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746832830722443e-05, "loss": 4.5046, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745994235971391e-05, "loss": 4.5017, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745155641220339e-05, "loss": 4.4877, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744317046469287e-05, "loss": 4.4971, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743478451718235e-05, "loss": 4.5087, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742639856967183e-05, "loss": 4.4885, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741801262216131e-05, "loss": 4.4977, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740962667465079e-05, "loss": 4.508, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401240727140264e-05, "loss": 4.5063, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739285477962975e-05, "loss": 4.4939, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384485210922966e-05, "loss": 4.4944, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376099263412446e-05, "loss": 4.4918, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736771331590192e-05, "loss": 4.4882, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.73593273683914e-05, "loss": 4.4858, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735094142088088e-05, "loss": 4.4919, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342571852174095e-05, "loss": 4.4929, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733418590466357e-05, "loss": 4.4909, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732579995715305e-05, "loss": 4.482, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731741400964253e-05, "loss": 4.4929, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730902806213201e-05, "loss": 4.4814, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730064211462149e-05, "loss": 4.4879, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729225616711097e-05, "loss": 4.4834, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728387021960045e-05, "loss": 4.4818, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727548427208993e-05, "loss": 4.4857, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267098324579415e-05, "loss": 4.4701, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258712377068895e-05, "loss": 4.4844, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250342808362104e-05, "loss": 4.4708, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7241956860851584e-05, "loss": 4.4733, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233570913341064e-05, "loss": 4.4729, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225184965830544e-05, "loss": 4.4773, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216799018320024e-05, "loss": 4.4704, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208413070809504e-05, "loss": 4.462, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720004350210271e-05, "loss": 4.4812, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719167393339592e-05, "loss": 4.4683, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71832879858854e-05, "loss": 4.4814, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717490203837488e-05, "loss": 4.4684, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716651609086437e-05, "loss": 4.4531, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715813014335385e-05, "loss": 4.4543, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714974419584333e-05, "loss": 4.4557, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714135824833281e-05, "loss": 4.4725, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713297230082228e-05, "loss": 4.4508, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712458635331176e-05, "loss": 4.4652, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711620040580124e-05, "loss": 4.4605, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710783083709446e-05, "loss": 4.4604, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709944488958393e-05, "loss": 4.4656, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709105894207341e-05, "loss": 4.4401, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708267299456289e-05, "loss": 4.4456, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707428704705237e-05, "loss": 4.4395, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706590109954185e-05, "loss": 4.4607, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705751515203134e-05, "loss": 4.4383, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704912920452082e-05, "loss": 4.4621, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040776014617755e-05, "loss": 4.4366, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032390067107235e-05, "loss": 4.4376, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024004119596715e-05, "loss": 4.4398, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015618172086195e-05, "loss": 4.4352, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007232224575675e-05, "loss": 4.4437, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4377, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990476708358364e-05, "loss": 4.4271, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982090760847844e-05, "loss": 4.4433, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973704813337324e-05, "loss": 4.4305, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965318865826804e-05, "loss": 4.4354, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695693291831629e-05, "loss": 4.429, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694854697080577e-05, "loss": 4.4371, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694016102329525e-05, "loss": 4.4173, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693179145458846e-05, "loss": 4.4433, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692342188588167e-05, "loss": 4.4289, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691503593837115e-05, "loss": 4.4312, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690664999086063e-05, "loss": 4.4319, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689826404335011e-05, "loss": 4.4244, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.4407, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.4455, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4431, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686473663211176e-05, "loss": 4.4278, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856350684601245e-05, "loss": 4.418, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847964737090725e-05, "loss": 4.409, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839578789580204e-05, "loss": 4.43, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831192842069684e-05, "loss": 4.4356, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822806894559164e-05, "loss": 4.4316, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814437325852373e-05, "loss": 4.4178, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806051378341853e-05, "loss": 4.4075, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797665430831333e-05, "loss": 4.422, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678927948332081e-05, "loss": 4.4078, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6780893535810287e-05, "loss": 4.4144, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.67725239671035e-05, "loss": 4.4229, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676413801959298e-05, "loss": 4.4217, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675575207208246e-05, "loss": 4.4163, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674736612457194e-05, "loss": 4.4181, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673898017706142e-05, "loss": 4.4026, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.67305942295509e-05, "loss": 4.4154, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672220828204038e-05, "loss": 4.4133, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671383871333359e-05, "loss": 4.3977, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670545276582307e-05, "loss": 4.4032, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669706681831255e-05, "loss": 4.4181, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668868087080203e-05, "loss": 4.421, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668031130209524e-05, "loss": 4.405, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667192535458472e-05, "loss": 4.407, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663555785877936e-05, "loss": 4.4132, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655169838367416e-05, "loss": 4.395, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.4109, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638397943346376e-05, "loss": 4.4157, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630011995835856e-05, "loss": 4.4006, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621626048325336e-05, "loss": 4.4074, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613240100814816e-05, "loss": 4.3833, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604854153304296e-05, "loss": 4.3843, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596468205793776e-05, "loss": 4.3952, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588082258283256e-05, "loss": 4.3967, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579696310772736e-05, "loss": 4.4036, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571310363262216e-05, "loss": 4.3882, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562940794555425e-05, "loss": 4.3874, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554554847044905e-05, "loss": 4.3917, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546168899534385e-05, "loss": 4.4029, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537782952023865e-05, "loss": 4.3942, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652941338331708e-05, "loss": 4.3981, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652102743580656e-05, "loss": 4.3871, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651264148829604e-05, "loss": 4.3884, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650427191958925e-05, "loss": 4.4018, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649588597207873e-05, "loss": 4.3869, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648750002456821e-05, "loss": 4.389, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647911407705769e-05, "loss": 4.3856, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647072812954717e-05, "loss": 4.3773, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646234218203665e-05, "loss": 4.3845, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645397261332986e-05, "loss": 4.3852, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644558666581934e-05, "loss": 4.3939, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643720071830882e-05, "loss": 4.3715, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.64288147707983e-05, "loss": 4.3803, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420445202091514e-05, "loss": 4.3987, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412059254580994e-05, "loss": 4.3778, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403673307070474e-05, "loss": 4.3925, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639528735955995e-05, "loss": 4.3805, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638690141204943e-05, "loss": 4.3958, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637851546453891e-05, "loss": 4.3829, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637012951702839e-05, "loss": 4.3735, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361759948321596e-05, "loss": 4.3732, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353374000811076e-05, "loss": 4.3673, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6344988053300556e-05, "loss": 4.3786, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336602105790036e-05, "loss": 4.3877, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632823253708325e-05, "loss": 4.384, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631984658957273e-05, "loss": 4.3789, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631146064206221e-05, "loss": 4.3715, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630307469455169e-05, "loss": 4.3695, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629468874704117e-05, "loss": 4.3651, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628631917833438e-05, "loss": 4.375, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627793323082386e-05, "loss": 4.3848, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626954728331334e-05, "loss": 4.3745, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626116133580282e-05, "loss": 4.3671, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.62527753882923e-05, "loss": 4.3627, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.342203617095947, "eval_runtime": 526.193, "eval_samples_per_second": 725.192, "eval_steps_per_second": 22.663, "step": 228957 }, { "epoch": 1.0, "learning_rate": 4.624440581958551e-05, "loss": 4.3743, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623601987207499e-05, "loss": 4.3768, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227633924564476e-05, "loss": 4.3617, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219247977053956e-05, "loss": 4.3602, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210862029543436e-05, "loss": 4.3632, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202492460836645e-05, "loss": 4.347, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194106513326125e-05, "loss": 4.3557, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185720565815605e-05, "loss": 4.3658, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177334618305085e-05, "loss": 4.3542, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168965049598294e-05, "loss": 4.3616, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160579102087774e-05, "loss": 4.3678, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152193154577254e-05, "loss": 4.3642, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6143807207066734e-05, "loss": 4.3569, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135421259556214e-05, "loss": 4.3619, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127035312045694e-05, "loss": 4.3539, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118649364535174e-05, "loss": 4.3537, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110263417024654e-05, "loss": 4.3485, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610187746951414e-05, "loss": 4.3558, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609350790080735e-05, "loss": 4.3587, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608512195329683e-05, "loss": 4.3603, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607673600578631e-05, "loss": 4.3521, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606835005827578e-05, "loss": 4.3611, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.605996411076526e-05, "loss": 4.3507, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605157816325474e-05, "loss": 4.3508, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604320859454796e-05, "loss": 4.3527, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603482264703743e-05, "loss": 4.3487, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602643669952691e-05, "loss": 4.354, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601805075201639e-05, "loss": 4.3411, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600966480450588e-05, "loss": 4.3555, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600127885699536e-05, "loss": 4.3411, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599289290948484e-05, "loss": 4.3435, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598452334077805e-05, "loss": 4.3456, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597613739326753e-05, "loss": 4.3537, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596775144575701e-05, "loss": 4.339, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595936549824649e-05, "loss": 4.3414, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5950995929539696e-05, "loss": 4.3498, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942609982029176e-05, "loss": 4.3414, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934224034518656e-05, "loss": 4.3604, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925838087008136e-05, "loss": 4.3416, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917468518301345e-05, "loss": 4.3289, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590908257079083e-05, "loss": 4.3315, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590069662328031e-05, "loss": 4.3293, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589231067576979e-05, "loss": 4.349, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588392472825927e-05, "loss": 4.3304, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587553878074875e-05, "loss": 4.3413, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586715283323823e-05, "loss": 4.3383, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585876688572771e-05, "loss": 4.3381, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585039731702092e-05, "loss": 4.3442, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.58420113695104e-05, "loss": 4.3217, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583362542199988e-05, "loss": 4.3214, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582523947448936e-05, "loss": 4.326, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581685352697884e-05, "loss": 4.3394, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580846757946832e-05, "loss": 4.318, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580009801076153e-05, "loss": 4.3396, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791712063251017e-05, "loss": 4.3201, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783326115740497e-05, "loss": 4.3159, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577494016822997e-05, "loss": 4.325, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576655422071945e-05, "loss": 4.3134, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575816827320893e-05, "loss": 4.3312, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574978232569841e-05, "loss": 4.3225, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574139637818789e-05, "loss": 4.3085, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.57330268094811e-05, "loss": 4.3255, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572464086197058e-05, "loss": 4.3156, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716271293263794e-05, "loss": 4.3206, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570788534575327e-05, "loss": 4.3112, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699499398242754e-05, "loss": 4.3248, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691113450732234e-05, "loss": 4.3037, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682727503221714e-05, "loss": 4.3274, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674341555711194e-05, "loss": 4.3133, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5665955608200674e-05, "loss": 4.3146, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657569660690154e-05, "loss": 4.3204, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564921647078709e-05, "loss": 4.3143, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564083052327657e-05, "loss": 4.3238, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563244457576605e-05, "loss": 4.3344, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562405862825553e-05, "loss": 4.329, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561568905954874e-05, "loss": 4.3153, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560730311203822e-05, "loss": 4.309, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559891716452771e-05, "loss": 4.3013, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559053121701719e-05, "loss": 4.3175, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558214526950667e-05, "loss": 4.3253, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557375932199615e-05, "loss": 4.3212, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556537337448563e-05, "loss": 4.3061, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555698742697511e-05, "loss": 4.2982, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554860147946459e-05, "loss": 4.3179, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554021553195407e-05, "loss": 4.2941, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553184596324728e-05, "loss": 4.3083, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552346001573676e-05, "loss": 4.3112, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515090447029966e-05, "loss": 4.3138, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506704499519446e-05, "loss": 4.3103, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498318552008926e-05, "loss": 4.3143, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5489932604498406e-05, "loss": 4.2951, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481546656987886e-05, "loss": 4.3061, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.54731770882811e-05, "loss": 4.3043, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546479114077058e-05, "loss": 4.2961, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545640519326006e-05, "loss": 4.2961, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544801924574954e-05, "loss": 4.3163, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543963329823902e-05, "loss": 4.3093, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.54312473507285e-05, "loss": 4.3066, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542286140321798e-05, "loss": 4.3011, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414475455707455e-05, "loss": 4.309, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406089508196934e-05, "loss": 4.2922, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397703560686414e-05, "loss": 4.3059, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389317613175894e-05, "loss": 4.312, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5380931665665374e-05, "loss": 4.292, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537256209695859e-05, "loss": 4.3106, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536417614944807e-05, "loss": 4.2758, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535579020193755e-05, "loss": 4.2827, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534742063323076e-05, "loss": 4.2946, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533903468572024e-05, "loss": 4.2956, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533064873820972e-05, "loss": 4.3044, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.53222627906992e-05, "loss": 4.2857, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531387684318868e-05, "loss": 4.2855, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530549089567816e-05, "loss": 4.2907, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529710494816764e-05, "loss": 4.3032, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528871900065712e-05, "loss": 4.2969, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528034943195033e-05, "loss": 4.2987, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527199624204728e-05, "loss": 4.2864, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526361029453675e-05, "loss": 4.2888, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525522434702623e-05, "loss": 4.3051, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524683839951571e-05, "loss": 4.2878, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523845245200519e-05, "loss": 4.2857, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523006650449467e-05, "loss": 4.2901, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522168055698415e-05, "loss": 4.2765, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521329460947363e-05, "loss": 4.2904, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520490866196311e-05, "loss": 4.2876, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519652271445259e-05, "loss": 4.2974, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.51881531457458e-05, "loss": 4.2756, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517976719823528e-05, "loss": 4.2811, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517138125072476e-05, "loss": 4.3047, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516301168201798e-05, "loss": 4.2816, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515462573450746e-05, "loss": 4.2914, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514623978699694e-05, "loss": 4.2889, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513785383948642e-05, "loss": 4.2994, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.51294678919759e-05, "loss": 4.2897, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512108194446538e-05, "loss": 4.2802, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511269599695486e-05, "loss": 4.2751, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510431004944434e-05, "loss": 4.2733, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509592410193382e-05, "loss": 4.2836, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508753815442329e-05, "loss": 4.2938, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507915220691277e-05, "loss": 4.2887, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507076625940225e-05, "loss": 4.2893, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062396690695466e-05, "loss": 4.2769, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505402712198868e-05, "loss": 4.2783, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504564117447816e-05, "loss": 4.2708, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503725522696764e-05, "loss": 4.2841, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5028869279457115e-05, "loss": 4.2861, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020483331946595e-05, "loss": 4.2903, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012097384436075e-05, "loss": 4.2732, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5003711436925555e-05, "loss": 4.2719, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.258720874786377, "eval_runtime": 536.684, "eval_samples_per_second": 711.016, "eval_steps_per_second": 22.22, "step": 305276 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.2599023283746029e+17, "trial_name": null, "trial_params": null }