{ "best_metric": 4.393002033233643, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/lstm/4/checkpoints/checkpoint-228960", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 228960, "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": 10.8195, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5627, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0613, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9898, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9202, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.7783, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.655, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.5569, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.4699, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992454285120906e-05, "loss": 6.398, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.991615690369854e-05, "loss": 6.3437, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990777095618801e-05, "loss": 6.2739, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 6.2187, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 6.1474, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 6.0987, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 6.0334, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986585759743914e-05, "loss": 6.0066, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985747164992862e-05, "loss": 5.9522, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.98490857024181e-05, "loss": 5.9096, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984069975490758e-05, "loss": 5.8792, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983231380739706e-05, "loss": 5.8584, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 5.8146, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 5.7927, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 5.7571, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7259, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7099, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.6728, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 5.6622, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 5.6369, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6098, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.5975, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.5742, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5614, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 5.5445, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5246, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5164, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5095, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 5.4711, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4617, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4483, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4321, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4199, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.4204, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.4004, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.3849, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.3784, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 5.3678, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 5.3617, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 5.3377, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 5.3256, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3342, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3236, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 5.31, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.2879, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.2967, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953890391735125e-05, "loss": 5.2745, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530517969840727e-05, "loss": 5.2905, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522132022330207e-05, "loss": 5.2562, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.9513746074819686e-05, "loss": 5.2603, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.9505360127309166e-05, "loss": 5.2399, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 5.2296, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 5.232, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 5.2168, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.2111, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.2033, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2122, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 5.1851, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 5.1755, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942993573612568e-05, "loss": 5.1604, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942154978861516e-05, "loss": 5.16, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 5.174, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404794272397856e-05, "loss": 5.1638, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396408324887336e-05, "loss": 5.1459, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388022377376816e-05, "loss": 5.1416, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379636429866296e-05, "loss": 5.1417, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371250482355776e-05, "loss": 5.1357, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362880913648985e-05, "loss": 5.1136, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354494966138465e-05, "loss": 5.1178, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346109018627945e-05, "loss": 5.1047, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337723071117425e-05, "loss": 5.1061, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329337123606905e-05, "loss": 5.101, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932095117609638e-05, "loss": 5.0895, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931256522858586e-05, "loss": 5.0926, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930417928107534e-05, "loss": 5.0819, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295809712368554e-05, "loss": 5.0666, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287423764858034e-05, "loss": 5.0658, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 5.0708, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 5.0638, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 5.0512, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925391273242342e-05, "loss": 5.0381, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.92455267849129e-05, "loss": 5.0418, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923714083740238e-05, "loss": 5.0302, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922875488989185e-05, "loss": 5.0405, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922036894238133e-05, "loss": 5.019, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921198299487081e-05, "loss": 5.0136, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 5.0313, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.9991, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918684153114299e-05, "loss": 4.9929, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917845558363247e-05, "loss": 4.9976, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.9954, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.9961, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.9851, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.9779, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136542224883596e-05, "loss": 4.9699, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128156277373076e-05, "loss": 4.9699, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119770329862556e-05, "loss": 4.954, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.9537, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9103014813645245e-05, "loss": 4.9583, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909462886613473e-05, "loss": 4.9465, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908624291862421e-05, "loss": 4.9388, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907785697111369e-05, "loss": 4.9357, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906947102360317e-05, "loss": 4.9266, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906108507609265e-05, "loss": 4.9353, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905269912858213e-05, "loss": 4.9216, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.9178, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903594361236482e-05, "loss": 4.9199, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.90275576648543e-05, "loss": 4.9133, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901917171734378e-05, "loss": 4.9077, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901080214863699e-05, "loss": 4.9067, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900241620112647e-05, "loss": 4.9049, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.9038, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898564430610543e-05, "loss": 4.8839, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897725835859491e-05, "loss": 4.8958, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.8874, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960519221181335e-05, "loss": 4.8875, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.8681, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.8786, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.8627, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8693, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8456, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8694, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890181758860769e-05, "loss": 4.8726, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889343164109717e-05, "loss": 4.8531, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888504569358665e-05, "loss": 4.8403, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.8876659746076134e-05, "loss": 4.8512, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.8868273798565614e-05, "loss": 4.8454, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885990422985882e-05, "loss": 4.8435, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515182823483e-05, "loss": 4.837, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884313233483778e-05, "loss": 4.8411, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883474638732726e-05, "loss": 4.8312, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.8254, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.8098, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.8225, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.8202, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.8087, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87844634598716e-05, "loss": 4.8218, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877607751236109e-05, "loss": 4.8005, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.8099, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.8103, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.7988, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.811893463134766, "eval_runtime": 292.9712, "eval_samples_per_second": 1302.486, "eval_steps_per_second": 40.704, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.7876, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.7943, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.7965, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.7868, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.7874, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.7719, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.7764, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683864847352826e-05, "loss": 4.7665, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675478899842306e-05, "loss": 4.7725, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667092952331785e-05, "loss": 4.7632, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865870700482127e-05, "loss": 4.7691, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.7712, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.7568, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.7552, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.7383, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.7496, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.7432, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.7373, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.7345, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.763, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.7341, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856651071861674e-05, "loss": 4.7351, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.7393, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.85497388235957e-05, "loss": 4.7291, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854135287608518e-05, "loss": 4.7254, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853296692857466e-05, "loss": 4.7136, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524597359867875e-05, "loss": 4.7218, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851621141235735e-05, "loss": 4.7193, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850782546484683e-05, "loss": 4.7051, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849943951733631e-05, "loss": 4.7141, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849105356982579e-05, "loss": 4.7043, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848266762231527e-05, "loss": 4.7141, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847428167480475e-05, "loss": 4.7124, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846589572729423e-05, "loss": 4.698, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845754253739117e-05, "loss": 4.7069, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844915658988065e-05, "loss": 4.7145, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844077064237013e-05, "loss": 4.6838, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843238469485961e-05, "loss": 4.6945, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842399874734909e-05, "loss": 4.6912, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841561279983857e-05, "loss": 4.6821, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840722685232805e-05, "loss": 4.6827, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839884090481753e-05, "loss": 4.6928, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839047133611074e-05, "loss": 4.6851, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.6797, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.6818, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.6762, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.6795, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.6619, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.6589, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.6755, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323432892437775e-05, "loss": 4.6735, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315046944927255e-05, "loss": 4.6629, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306660997416735e-05, "loss": 4.6543, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298275049906215e-05, "loss": 4.6628, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289889102395695e-05, "loss": 4.6448, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281503154885175e-05, "loss": 4.671, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273117207374655e-05, "loss": 4.651, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264731259864135e-05, "loss": 4.6617, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256345312353615e-05, "loss": 4.6443, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8247959364843095e-05, "loss": 4.6399, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823958979613631e-05, "loss": 4.6419, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.6478, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.6307, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821443195360475e-05, "loss": 4.6353, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820604600609423e-05, "loss": 4.649, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819766005858371e-05, "loss": 4.6293, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818929048987692e-05, "loss": 4.6194, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.81809045423664e-05, "loss": 4.6202, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817251859485588e-05, "loss": 4.6178, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816413264734535e-05, "loss": 4.64, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815574669983483e-05, "loss": 4.6351, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814736075232432e-05, "loss": 4.6184, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.81389748048138e-05, "loss": 4.6231, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813058885730328e-05, "loss": 4.6266, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812221928859649e-05, "loss": 4.6238, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113849719889704e-05, "loss": 4.6074, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105463772379184e-05, "loss": 4.6198, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097094203672393e-05, "loss": 4.6104, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.8088708256161873e-05, "loss": 4.615, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808032230865135e-05, "loss": 4.607, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.8071936361140827e-05, "loss": 4.6076, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063550413630307e-05, "loss": 4.6094, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055164466119786e-05, "loss": 4.6113, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804677851860927e-05, "loss": 4.5931, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803839257109875e-05, "loss": 4.6022, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803000662358823e-05, "loss": 4.6004, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802162067607771e-05, "loss": 4.6044, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801323472856719e-05, "loss": 4.5974, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800484878105667e-05, "loss": 4.5855, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799649559115361e-05, "loss": 4.5939, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798810964364309e-05, "loss": 4.5867, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797972369613257e-05, "loss": 4.5986, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797133774862205e-05, "loss": 4.5782, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796295180111153e-05, "loss": 4.5829, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795456585360101e-05, "loss": 4.5951, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794617990609049e-05, "loss": 4.5845, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.5656, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5778, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792102206355894e-05, "loss": 4.5824, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791263611604842e-05, "loss": 4.583, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.79042501685379e-05, "loss": 4.5744, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895880599831107e-05, "loss": 4.5702, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887494652320587e-05, "loss": 4.566, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879125083613796e-05, "loss": 4.5728, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870739136103276e-05, "loss": 4.5536, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862353188592756e-05, "loss": 4.5606, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853967241082236e-05, "loss": 4.5671, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845581293571715e-05, "loss": 4.5655, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837211724864925e-05, "loss": 4.549, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782882577735441e-05, "loss": 4.5597, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782043982984389e-05, "loss": 4.5473, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781205388233337e-05, "loss": 4.5633, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780368431362658e-05, "loss": 4.5503, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779529836611606e-05, "loss": 4.5422, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778691241860554e-05, "loss": 4.5593, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777852647109502e-05, "loss": 4.5533, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777015690238823e-05, "loss": 4.5464, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776177095487771e-05, "loss": 4.5496, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775338500736719e-05, "loss": 4.5473, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774499905985666e-05, "loss": 4.5522, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773661311234615e-05, "loss": 4.5315, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772824354363936e-05, "loss": 4.5515, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719857596128845e-05, "loss": 4.539, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771147164861832e-05, "loss": 4.5432, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.77030857011078e-05, "loss": 4.5333, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769469975359728e-05, "loss": 4.5399, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686330184890494e-05, "loss": 4.5279, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76779606161837e-05, "loss": 4.5356, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766957466867318e-05, "loss": 4.5144, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766118872116266e-05, "loss": 4.5448, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.7652802773652136e-05, "loss": 4.5403, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.7644416826141616e-05, "loss": 4.5321, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636030878631096e-05, "loss": 4.5203, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762764493112058e-05, "loss": 4.5338, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761925898361006e-05, "loss": 4.5334, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761087303609954e-05, "loss": 4.5244, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760250346739275e-05, "loss": 4.5194, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759411751988223e-05, "loss": 4.5292, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758573157237171e-05, "loss": 4.522, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757734562486119e-05, "loss": 4.5287, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756895967735067e-05, "loss": 4.5059, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756057372984015e-05, "loss": 4.5218, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755218778232963e-05, "loss": 4.5196, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754380183481911e-05, "loss": 4.5113, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753543226611232e-05, "loss": 4.5258, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.75270463186018e-05, "loss": 4.5057, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751866037109128e-05, "loss": 4.5154, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751027442358077e-05, "loss": 4.5135, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750188847607025e-05, "loss": 4.5128, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.5289154052734375, "eval_runtime": 296.6014, "eval_samples_per_second": 1286.545, "eval_steps_per_second": 40.205, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749350252855973e-05, "loss": 4.5015, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748511658104921e-05, "loss": 4.5077, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747673063353868e-05, "loss": 4.5137, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746834468602816e-05, "loss": 4.5066, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745995873851764e-05, "loss": 4.5085, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745157279100712e-05, "loss": 4.4906, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.74431868434966e-05, "loss": 4.5, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743480089598608e-05, "loss": 4.4921, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742641494847556e-05, "loss": 4.5013, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741802900096504e-05, "loss": 4.4946, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740964305345452e-05, "loss": 4.5021, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401257105944e-05, "loss": 4.5031, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739287115843348e-05, "loss": 4.4863, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384485210922966e-05, "loss": 4.4911, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376099263412446e-05, "loss": 4.4744, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736771331590192e-05, "loss": 4.4862, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.73593273683914e-05, "loss": 4.4858, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735094142088088e-05, "loss": 4.479, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342571852174095e-05, "loss": 4.4782, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733418590466357e-05, "loss": 4.5053, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732579995715305e-05, "loss": 4.4835, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731741400964253e-05, "loss": 4.4809, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730902806213201e-05, "loss": 4.4885, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730064211462149e-05, "loss": 4.4837, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729225616711097e-05, "loss": 4.4768, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728387021960045e-05, "loss": 4.4678, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275500650893664e-05, "loss": 4.4774, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726713108218687e-05, "loss": 4.4712, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725874513467635e-05, "loss": 4.4651, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725035918716583e-05, "loss": 4.4735, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724197323965531e-05, "loss": 4.4637, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723358729214479e-05, "loss": 4.4767, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722520134463427e-05, "loss": 4.4713, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721683177592748e-05, "loss": 4.4609, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720844582841696e-05, "loss": 4.4723, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720005988090644e-05, "loss": 4.4836, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719169031219965e-05, "loss": 4.4495, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718330436468914e-05, "loss": 4.4683, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717491841717862e-05, "loss": 4.4577, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.71665324696681e-05, "loss": 4.4585, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715814652215758e-05, "loss": 4.4532, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714976057464706e-05, "loss": 4.4693, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714137462713654e-05, "loss": 4.4619, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713298867962602e-05, "loss": 4.4572, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.71246027321155e-05, "loss": 4.4584, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711621678460498e-05, "loss": 4.4507, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710783083709446e-05, "loss": 4.4617, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709944488958393e-05, "loss": 4.4421, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091075320877147e-05, "loss": 4.443, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082689373366627e-05, "loss": 4.4556, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074303425856106e-05, "loss": 4.455, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065917478345586e-05, "loss": 4.4462, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.70575479096388e-05, "loss": 4.4437, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704916196212828e-05, "loss": 4.4515, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040776014617755e-05, "loss": 4.4335, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703240644591097e-05, "loss": 4.4582, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702402049840045e-05, "loss": 4.4424, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015634550889924e-05, "loss": 4.4515, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.4439, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4352, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990476708358364e-05, "loss": 4.4338, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982107139651573e-05, "loss": 4.4444, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4235, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4337, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.444, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.69485633496095e-05, "loss": 4.4335, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694017740209898e-05, "loss": 4.419, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693179145458846e-05, "loss": 4.4203, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692340550707794e-05, "loss": 4.4196, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691505231717488e-05, "loss": 4.4459, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690666636966436e-05, "loss": 4.4355, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689828042215384e-05, "loss": 4.4253, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.4332, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.4288, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4333, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864753010915494e-05, "loss": 4.4158, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.68563834422087e-05, "loss": 4.4298, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684799749469818e-05, "loss": 4.4235, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683961154718766e-05, "loss": 4.4228, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683122559967714e-05, "loss": 4.4178, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682283965216662e-05, "loss": 4.4219, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68144537046561e-05, "loss": 4.4225, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.4244, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679769818843879e-05, "loss": 4.4124, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678931224092827e-05, "loss": 4.4166, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678092629341775e-05, "loss": 4.4152, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677254034590723e-05, "loss": 4.4195, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676415439839671e-05, "loss": 4.4193, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.402, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.413, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673899655586516e-05, "loss": 4.4102, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673061060835464e-05, "loss": 4.4189, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672222466084412e-05, "loss": 4.3989, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671385509213733e-05, "loss": 4.4081, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670546914462681e-05, "loss": 4.4185, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669708319711629e-05, "loss": 4.4074, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668869724960576e-05, "loss": 4.3915, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668031130209524e-05, "loss": 4.4037, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667192535458472e-05, "loss": 4.4096, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.66635394070742e-05, "loss": 4.4091, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665515345956368e-05, "loss": 4.4047, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.3964, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638397943346376e-05, "loss": 4.3967, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630011995835856e-05, "loss": 4.4005, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621626048325336e-05, "loss": 4.3866, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613240100814816e-05, "loss": 4.3934, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604870532108025e-05, "loss": 4.3981, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596484584597505e-05, "loss": 4.3974, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588098637086985e-05, "loss": 4.3783, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579712689576465e-05, "loss": 4.3957, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571326742065945e-05, "loss": 4.3821, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562940794555425e-05, "loss": 4.3945, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554554847044905e-05, "loss": 4.39, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546185278338114e-05, "loss": 4.3804, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65377993308276e-05, "loss": 4.3951, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652942976212081e-05, "loss": 4.394, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652104381461029e-05, "loss": 4.3824, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651265786709977e-05, "loss": 4.3898, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650427191958925e-05, "loss": 4.3882, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649588597207873e-05, "loss": 4.3893, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648750002456821e-05, "loss": 4.3758, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647911407705769e-05, "loss": 4.3891, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.64707445083509e-05, "loss": 4.3839, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646235856084038e-05, "loss": 4.3845, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645397261332986e-05, "loss": 4.3797, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644558666581934e-05, "loss": 4.3873, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643720071830882e-05, "loss": 4.3675, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.64288147707983e-05, "loss": 4.3807, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642042882328778e-05, "loss": 4.3614, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641204287577726e-05, "loss": 4.3919, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403673307070474e-05, "loss": 4.3826, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639528735955995e-05, "loss": 4.3794, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638690141204943e-05, "loss": 4.3683, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637851546453891e-05, "loss": 4.3827, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637014589583212e-05, "loss": 4.385, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361759948321596e-05, "loss": 4.3732, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353374000811076e-05, "loss": 4.3706, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634500443210429e-05, "loss": 4.3794, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633661848459377e-05, "loss": 4.373, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632823253708325e-05, "loss": 4.3798, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631984658957273e-05, "loss": 4.3613, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631146064206221e-05, "loss": 4.3736, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630307469455169e-05, "loss": 4.3707, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629468874704117e-05, "loss": 4.3639, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628630279953065e-05, "loss": 4.3823, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627793323082386e-05, "loss": 4.3588, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626954728331334e-05, "loss": 4.3686, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626116133580282e-05, "loss": 4.3718, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.62527753882923e-05, "loss": 4.3661, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.393002033233643, "eval_runtime": 290.8721, "eval_samples_per_second": 1311.886, "eval_steps_per_second": 40.997, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 8.818453998502757e+16, "trial_name": null, "trial_params": null }