{ "best_metric": 4.21055793762207, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/4/checkpoints/checkpoint-457914", "epoch": 1.0250002784396635, "eval_steps": 10, "global_step": 457914, "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": 10.8203, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5858, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0564, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9814, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9507, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.8259, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.677, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.5732, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.5007, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4261, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.3802, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 6.3211, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 6.2596, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 6.1876, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 6.1243, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 6.0805, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986582483983168e-05, "loss": 6.0353, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985743889232116e-05, "loss": 5.9862, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984905294481064e-05, "loss": 5.954, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.9125, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8839, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.847, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.8118, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 5.7882, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7578, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7294, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.7056, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.6831, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6504, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.975684027980238e-05, "loss": 5.6354, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.974845433229186e-05, "loss": 5.6081, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974006838478134e-05, "loss": 5.5898, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5751, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.972331286856403e-05, "loss": 5.5586, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714926921053515e-05, "loss": 5.537, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706540973542995e-05, "loss": 5.5273, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5134, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.4933, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4748, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4653, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4374, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4368, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.4078, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.4081, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.4001, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962271425604525e-05, "loss": 5.3892, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961432830853473e-05, "loss": 5.3635, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960595873982795e-05, "loss": 5.3616, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959757279231743e-05, "loss": 5.3566, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958918684480691e-05, "loss": 5.3346, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958080089729639e-05, "loss": 5.3186, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.95724313285896e-05, "loss": 5.3159, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956404538107908e-05, "loss": 5.3217, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955565943356856e-05, "loss": 5.2884, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954727348605804e-05, "loss": 5.3088, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953888753854752e-05, "loss": 5.2688, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530501591037e-05, "loss": 5.2788, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952211564352648e-05, "loss": 5.2563, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951372969601596e-05, "loss": 5.2536, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.9505360127309166e-05, "loss": 5.2447, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.9496974179798646e-05, "loss": 5.2383, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948860461109186e-05, "loss": 5.2191, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948021866358134e-05, "loss": 5.2251, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.2083, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.2142, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.1957, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944669125234299e-05, "loss": 5.1863, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943830530483247e-05, "loss": 5.171, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942991935732195e-05, "loss": 5.1783, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942153340981143e-05, "loss": 5.171, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413147462300904e-05, "loss": 5.1507, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404761514790384e-05, "loss": 5.1532, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.93963919460836e-05, "loss": 5.1456, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.938800599857309e-05, "loss": 5.1426, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.937962005106256e-05, "loss": 5.1385, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.937123410355204e-05, "loss": 5.1328, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1197, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.1023, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.934609263982421e-05, "loss": 5.1096, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337723071117425e-05, "loss": 5.1014, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329337123606905e-05, "loss": 5.1026, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932095117609638e-05, "loss": 5.0947, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931256522858586e-05, "loss": 5.0829, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930417928107534e-05, "loss": 5.0623, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295793333564825e-05, "loss": 5.0691, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287407386054305e-05, "loss": 5.0699, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279021438543785e-05, "loss": 5.0664, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.9270635491033264e-05, "loss": 5.0555, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.9262249543522744e-05, "loss": 5.0486, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.9253863596012224e-05, "loss": 5.0377, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.9245494027305433e-05, "loss": 5.0314, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923712445859864e-05, "loss": 5.0285, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922873851108812e-05, "loss": 5.036, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92203525635776e-05, "loss": 5.0258, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921196661606708e-05, "loss": 5.001, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920358066855656e-05, "loss": 5.0041, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919521109984978e-05, "loss": 5.0092, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918682515233926e-05, "loss": 5.0057, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917843920482874e-05, "loss": 4.9939, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917005325731822e-05, "loss": 4.9939, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.91616673098077e-05, "loss": 4.9805, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915328136229718e-05, "loss": 4.9795, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914489541478666e-05, "loss": 4.9856, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913650946727614e-05, "loss": 4.9799, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912812351976562e-05, "loss": 4.9539, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911973757225509e-05, "loss": 4.9633, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911136800354831e-05, "loss": 4.9453, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910298205603779e-05, "loss": 4.9493, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909459610852727e-05, "loss": 4.9463, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908621016101675e-05, "loss": 4.9355, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907784059230996e-05, "loss": 4.9335, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906945464479944e-05, "loss": 4.9238, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906106869728892e-05, "loss": 4.9227, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905269912858213e-05, "loss": 4.9195, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904431318107161e-05, "loss": 4.9317, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903592723356109e-05, "loss": 4.9073, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027541286050565e-05, "loss": 4.8913, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019155338540045e-05, "loss": 4.9003, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010769391029525e-05, "loss": 4.9118, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002383443519005e-05, "loss": 4.8951, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8993997496008485e-05, "loss": 4.902, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985611548497965e-05, "loss": 4.8905, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977225600987445e-05, "loss": 4.8913, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968839653476924e-05, "loss": 4.8753, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.896045370596641e-05, "loss": 4.8795, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.895208413725962e-05, "loss": 4.8731, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.89436981897491e-05, "loss": 4.8774, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893532862104231e-05, "loss": 4.8563, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892694267353179e-05, "loss": 4.8654, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891855672602127e-05, "loss": 4.8617, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891017077851075e-05, "loss": 4.8474, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890178483100023e-05, "loss": 4.8574, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889341526229344e-05, "loss": 4.8488, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888502931478292e-05, "loss": 4.8536, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766433672724e-05, "loss": 4.849, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886825741976188e-05, "loss": 4.8315, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.8859871472251365e-05, "loss": 4.8282, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.8851485524740845e-05, "loss": 4.826, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.8843099577230325e-05, "loss": 4.8316, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.8834713629719805e-05, "loss": 4.8389, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.8826344061013014e-05, "loss": 4.8268, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8817958113502494e-05, "loss": 4.8165, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809572165991974e-05, "loss": 4.8127, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801186218481454e-05, "loss": 4.8129, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879281664977466e-05, "loss": 4.8089, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878443070226414e-05, "loss": 4.8047, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877604475475362e-05, "loss": 4.8191, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876767518604683e-05, "loss": 4.8028, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875928923853632e-05, "loss": 4.7948, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.87509032910258e-05, "loss": 4.7906, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.807467460632324, "eval_runtime": 553.5364, "eval_samples_per_second": 689.369, "eval_steps_per_second": 21.543, "step": 76319 }, { "epoch": 1.0, "learning_rate": 4.874251734351528e-05, "loss": 4.8038, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873413139600475e-05, "loss": 4.7947, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872574544849423e-05, "loss": 4.7795, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871735950098371e-05, "loss": 4.7838, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870897355347319e-05, "loss": 4.7708, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.87006039847664e-05, "loss": 4.7694, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869221803725588e-05, "loss": 4.7652, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868383208974536e-05, "loss": 4.7673, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867544614223484e-05, "loss": 4.7641, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667076573528056e-05, "loss": 4.7659, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658690626017536e-05, "loss": 4.7632, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650304678507016e-05, "loss": 4.7692, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8641918730996496e-05, "loss": 4.7549, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633532783485976e-05, "loss": 4.7445, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625146835975456e-05, "loss": 4.7438, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616760888464936e-05, "loss": 4.7266, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608391319758145e-05, "loss": 4.7399, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.8600005372247625e-05, "loss": 4.7373, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591619424737105e-05, "loss": 4.7349, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583233477226585e-05, "loss": 4.7443, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574847529716065e-05, "loss": 4.7327, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566461582205545e-05, "loss": 4.731, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558092013498754e-05, "loss": 4.7318, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854970606598824e-05, "loss": 4.7273, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854132011847772e-05, "loss": 4.7189, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.85329341709672e-05, "loss": 4.7169, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852456460226041e-05, "loss": 4.722, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851617865474989e-05, "loss": 4.7084, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850779270723937e-05, "loss": 4.7104, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849940675972885e-05, "loss": 4.6965, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849102081221833e-05, "loss": 4.6989, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848263486470781e-05, "loss": 4.7108, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847426529600102e-05, "loss": 4.7005, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.84658793484905e-05, "loss": 4.701, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845749340097998e-05, "loss": 4.6973, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844910745346946e-05, "loss": 4.7008, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844072150595894e-05, "loss": 4.6935, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432351937252154e-05, "loss": 4.6916, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8423965989741634e-05, "loss": 4.6933, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415580042231114e-05, "loss": 4.6801, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840719409472059e-05, "loss": 4.684, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.83988245260138e-05, "loss": 4.6691, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839043857850328e-05, "loss": 4.6765, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838205263099276e-05, "loss": 4.6863, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373666683482236e-05, "loss": 4.6832, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365280735971716e-05, "loss": 4.667, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356894788461196e-05, "loss": 4.6697, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348508840950676e-05, "loss": 4.6749, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834013927224389e-05, "loss": 4.6547, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833175332473337e-05, "loss": 4.6554, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832336737722285e-05, "loss": 4.6566, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831498142971233e-05, "loss": 4.6696, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830659548220181e-05, "loss": 4.6455, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829820953469129e-05, "loss": 4.6717, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828982358718077e-05, "loss": 4.6405, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828143763967025e-05, "loss": 4.6515, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827306807096346e-05, "loss": 4.6443, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826469850225667e-05, "loss": 4.6473, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825631255474615e-05, "loss": 4.6408, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824792660723563e-05, "loss": 4.6428, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823954065972511e-05, "loss": 4.6326, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.82311547122146e-05, "loss": 4.6401, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222785143507806e-05, "loss": 4.6321, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214399195997286e-05, "loss": 4.6382, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206013248486766e-05, "loss": 4.6297, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197627300976246e-05, "loss": 4.6288, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189241353465726e-05, "loss": 4.6091, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180855405955206e-05, "loss": 4.6356, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172469458444685e-05, "loss": 4.6252, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164083510934165e-05, "loss": 4.6124, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155730321031104e-05, "loss": 4.6215, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147344373520584e-05, "loss": 4.6163, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8138958426010064e-05, "loss": 4.6179, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813057247849955e-05, "loss": 4.6235, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812218653098903e-05, "loss": 4.6223, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811381696228224e-05, "loss": 4.6088, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810543101477172e-05, "loss": 4.6021, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.80970450672612e-05, "loss": 4.6056, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808865911975068e-05, "loss": 4.6091, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808027317224016e-05, "loss": 4.6149, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807190360353337e-05, "loss": 4.6083, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806351765602285e-05, "loss": 4.6023, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805513170851233e-05, "loss": 4.5828, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804674576100181e-05, "loss": 4.5931, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803835981349129e-05, "loss": 4.5982, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.802997386598077e-05, "loss": 4.5953, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802158791847025e-05, "loss": 4.5992, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801320197095973e-05, "loss": 4.5912, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004832402252944e-05, "loss": 4.5843, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996446454742424e-05, "loss": 4.5876, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.79880605072319e-05, "loss": 4.5804, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797967455972138e-05, "loss": 4.5875, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797130499101459e-05, "loss": 4.5894, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796295180111153e-05, "loss": 4.5661, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795456585360101e-05, "loss": 4.569, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794617990609049e-05, "loss": 4.5789, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.5853, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792940801106946e-05, "loss": 4.5696, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792102206355894e-05, "loss": 4.5764, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791263611604842e-05, "loss": 4.5697, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.79042501685379e-05, "loss": 4.5672, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789586422102737e-05, "loss": 4.5765, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788747827351685e-05, "loss": 4.5721, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879108704810067e-05, "loss": 4.5547, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870722757299546e-05, "loss": 4.5688, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786233680978902e-05, "loss": 4.5506, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.78539508622785e-05, "loss": 4.5531, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784556491476798e-05, "loss": 4.5604, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783717896725746e-05, "loss": 4.55, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828809398550675e-05, "loss": 4.5513, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820423451040155e-05, "loss": 4.545, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812037503529635e-05, "loss": 4.5465, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803651556019115e-05, "loss": 4.544, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795265608508595e-05, "loss": 4.56, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786879660998075e-05, "loss": 4.5409, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778510092291284e-05, "loss": 4.5324, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770124144780764e-05, "loss": 4.5388, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761738197270244e-05, "loss": 4.5454, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753352249759724e-05, "loss": 4.5421, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774498268105293e-05, "loss": 4.5453, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773659673354241e-05, "loss": 4.5414, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772821078603189e-05, "loss": 4.5411, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771982483852137e-05, "loss": 4.5338, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771143889101086e-05, "loss": 4.531, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770305294350034e-05, "loss": 4.5336, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769468337479355e-05, "loss": 4.538, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768629742728303e-05, "loss": 4.5224, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767791147977251e-05, "loss": 4.5259, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766952553226199e-05, "loss": 4.5397, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766113958475147e-05, "loss": 4.5139, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765275363724095e-05, "loss": 4.5286, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764438406853416e-05, "loss": 4.5236, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763599812102364e-05, "loss": 4.5349, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762761217351312e-05, "loss": 4.5262, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.76192262260026e-05, "loss": 4.5142, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761084027849208e-05, "loss": 4.513, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760245433098156e-05, "loss": 4.5134, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594084762274773e-05, "loss": 4.5231, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758569881476425e-05, "loss": 4.5289, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757731286725373e-05, "loss": 4.5239, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7568926919743206e-05, "loss": 4.5099, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560540972232686e-05, "loss": 4.5111, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.75521714035259e-05, "loss": 4.5152, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543785456015375e-05, "loss": 4.5112, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535399508504855e-05, "loss": 4.5087, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527013560994335e-05, "loss": 4.5254, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518627613483815e-05, "loss": 4.5052, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510241665973295e-05, "loss": 4.506, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750187209726651e-05, "loss": 4.5003, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.524855136871338, "eval_runtime": 548.3334, "eval_samples_per_second": 695.911, "eval_steps_per_second": 21.748, "step": 152638 }, { "epoch": 0.0, "learning_rate": 4.749348614975599e-05, "loss": 4.5169, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748510020224547e-05, "loss": 4.511, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747671425473495e-05, "loss": 4.4968, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746832830722443e-05, "loss": 4.4998, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745994235971391e-05, "loss": 4.4901, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745155641220339e-05, "loss": 4.4924, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744317046469287e-05, "loss": 4.4895, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743478451718235e-05, "loss": 4.4925, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742639856967183e-05, "loss": 4.4923, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741801262216131e-05, "loss": 4.4943, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740962667465079e-05, "loss": 4.4966, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401240727140264e-05, "loss": 4.5007, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739285477962975e-05, "loss": 4.4876, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738446883211923e-05, "loss": 4.4787, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737608288460871e-05, "loss": 4.4841, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736769693709819e-05, "loss": 4.464, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735931098958767e-05, "loss": 4.481, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735094142088088e-05, "loss": 4.4773, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734255547337036e-05, "loss": 4.4768, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733416952585984e-05, "loss": 4.4914, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732578357834932e-05, "loss": 4.4794, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.73173976308388e-05, "loss": 4.481, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730901168332828e-05, "loss": 4.4833, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730062573581776e-05, "loss": 4.4769, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729223978830724e-05, "loss": 4.4736, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728385384079672e-05, "loss": 4.47, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727548427208993e-05, "loss": 4.476, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267098324579415e-05, "loss": 4.4652, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258712377068895e-05, "loss": 4.4683, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250326429558375e-05, "loss": 4.4532, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7241956860851584e-05, "loss": 4.4614, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233570913341064e-05, "loss": 4.4735, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225184965830544e-05, "loss": 4.4601, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216799018320024e-05, "loss": 4.4665, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720842944961323e-05, "loss": 4.4612, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720005988090644e-05, "loss": 4.4661, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719167393339592e-05, "loss": 4.4659, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71832879858854e-05, "loss": 4.464, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717490203837488e-05, "loss": 4.4627, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716651609086437e-05, "loss": 4.4516, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715813014335385e-05, "loss": 4.4586, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714976057464706e-05, "loss": 4.444, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714137462713654e-05, "loss": 4.4594, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713298867962602e-05, "loss": 4.4594, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.71246027321155e-05, "loss": 4.4608, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711623316340871e-05, "loss": 4.446, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710784721589819e-05, "loss": 4.448, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099461268387667e-05, "loss": 4.4556, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091075320877147e-05, "loss": 4.4369, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082689373366627e-05, "loss": 4.4415, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074319804659836e-05, "loss": 4.438, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706593385714932e-05, "loss": 4.4585, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.70575479096388e-05, "loss": 4.4342, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704916196212828e-05, "loss": 4.459, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040776014617755e-05, "loss": 4.4295, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032390067107235e-05, "loss": 4.4357, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024004119596715e-05, "loss": 4.4398, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015618172086195e-05, "loss": 4.4383, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.4353, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4456, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990476708358364e-05, "loss": 4.4197, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982090760847844e-05, "loss": 4.4352, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4292, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4379, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4275, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.69485633496095e-05, "loss": 4.429, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694019378090271e-05, "loss": 4.4105, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693180783339219e-05, "loss": 4.4367, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692342188588167e-05, "loss": 4.4283, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691503593837115e-05, "loss": 4.42, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690664999086063e-05, "loss": 4.4258, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689826404335011e-05, "loss": 4.4233, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688987809583959e-05, "loss": 4.4234, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688149214832907e-05, "loss": 4.4337, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4325, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864753010915494e-05, "loss": 4.4213, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856367063404974e-05, "loss": 4.4119, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847981115894454e-05, "loss": 4.416, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839595168383934e-05, "loss": 4.4223, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683122559967714e-05, "loss": 4.4273, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682283965216662e-05, "loss": 4.4199, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68144537046561e-05, "loss": 4.4214, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.3992, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679768180963506e-05, "loss": 4.4113, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678929586212454e-05, "loss": 4.4094, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678090991461402e-05, "loss": 4.4147, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.67725239671035e-05, "loss": 4.4198, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676415439839671e-05, "loss": 4.4111, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4019, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.4104, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673899655586516e-05, "loss": 4.4026, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673062698715837e-05, "loss": 4.4097, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672224103964785e-05, "loss": 4.4095, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713871470941056e-05, "loss": 4.3923, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705485523430536e-05, "loss": 4.3957, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697099575920016e-05, "loss": 4.4031, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688713628409496e-05, "loss": 4.4097, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680327680898976e-05, "loss": 4.4003, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6671941733388456e-05, "loss": 4.4068, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663555785877936e-05, "loss": 4.397, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655169838367416e-05, "loss": 4.3965, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664680026966063e-05, "loss": 4.4032, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663841432215011e-05, "loss": 4.4014, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663004475344332e-05, "loss": 4.3862, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.66216588059328e-05, "loss": 4.4053, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661327285842228e-05, "loss": 4.3781, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660488691091176e-05, "loss": 4.383, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596500963401234e-05, "loss": 4.3975, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588115015890714e-05, "loss": 4.3834, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579729068380194e-05, "loss": 4.3929, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571343120869674e-05, "loss": 4.3817, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656297355216288e-05, "loss": 4.3814, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655458760465237e-05, "loss": 4.3795, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654620165714185e-05, "loss": 4.4016, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653781570963133e-05, "loss": 4.3794, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652944614092454e-05, "loss": 4.3787, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652106019341402e-05, "loss": 4.3755, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.65126742459035e-05, "loss": 4.3852, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650428829839298e-05, "loss": 4.3886, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649591872968619e-05, "loss": 4.3854, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648753278217567e-05, "loss": 4.3821, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647914683466515e-05, "loss": 4.3842, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647076088715463e-05, "loss": 4.3772, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646237493964411e-05, "loss": 4.3795, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645398899213359e-05, "loss": 4.3779, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.64456194234268e-05, "loss": 4.3811, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643723347591628e-05, "loss": 4.3699, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642884752840576e-05, "loss": 4.3739, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642046158089524e-05, "loss": 4.3862, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641207563338472e-05, "loss": 4.3642, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.64036896858742e-05, "loss": 4.3749, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639530373836368e-05, "loss": 4.3743, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638691779085316e-05, "loss": 4.3849, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637854822214637e-05, "loss": 4.3756, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637017865343958e-05, "loss": 4.3721, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636180908473279e-05, "loss": 4.3616, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635342313722228e-05, "loss": 4.3647, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634503718971176e-05, "loss": 4.3743, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633665124220124e-05, "loss": 4.3818, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632826529469072e-05, "loss": 4.3774, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.63198793471802e-05, "loss": 4.365, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631149339966968e-05, "loss": 4.3629, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630310745215916e-05, "loss": 4.3746, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294737883452366e-05, "loss": 4.3634, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286351935941846e-05, "loss": 4.3646, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6277965988431326e-05, "loss": 4.3774, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269580040920806e-05, "loss": 4.3628, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261194093410286e-05, "loss": 4.364, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6252824524703495e-05, "loss": 4.3616, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.390356063842773, "eval_runtime": 548.5381, "eval_samples_per_second": 695.651, "eval_steps_per_second": 21.74, "step": 228957 }, { "epoch": 1.0, "learning_rate": 4.6244438577192975e-05, "loss": 4.3708, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623605262968246e-05, "loss": 4.3722, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622766668217194e-05, "loss": 4.3567, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621928073466142e-05, "loss": 4.3581, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210894787150895e-05, "loss": 4.354, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202508839640374e-05, "loss": 4.3523, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194122892129854e-05, "loss": 4.354, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618575332342307e-05, "loss": 4.3524, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177367375912543e-05, "loss": 4.3546, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616899780720576e-05, "loss": 4.3619, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616061185969524e-05, "loss": 4.3574, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615222591218472e-05, "loss": 4.3626, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.61438399646742e-05, "loss": 4.3523, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613545401716368e-05, "loss": 4.3463, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612706806965316e-05, "loss": 4.3479, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611868212214264e-05, "loss": 4.3314, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611029617463212e-05, "loss": 4.3457, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610192660592533e-05, "loss": 4.3456, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093557037218544e-05, "loss": 4.3465, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608517108970802e-05, "loss": 4.3583, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.60767851421975e-05, "loss": 4.3489, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606839919468698e-05, "loss": 4.3521, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606002962598019e-05, "loss": 4.3469, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051643678469666e-05, "loss": 4.3433, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604325773095915e-05, "loss": 4.3428, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603487178344863e-05, "loss": 4.346, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602648583593811e-05, "loss": 4.3437, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601809988842759e-05, "loss": 4.3386, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600971394091707e-05, "loss": 4.3384, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600132799340655e-05, "loss": 4.3255, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599295842469976e-05, "loss": 4.3348, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598457247718924e-05, "loss": 4.3445, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597618652967872e-05, "loss": 4.3373, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596781696097193e-05, "loss": 4.3397, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595943101346141e-05, "loss": 4.3362, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595104506595089e-05, "loss": 4.342, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594265911844037e-05, "loss": 4.3378, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593427317092985e-05, "loss": 4.3443, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592588722341933e-05, "loss": 4.3361, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591750127590882e-05, "loss": 4.3273, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.59091153283983e-05, "loss": 4.3354, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900745759691506e-05, "loss": 4.3174, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892359812180986e-05, "loss": 4.34, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5883973864670466e-05, "loss": 4.3379, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875587917159946e-05, "loss": 4.3369, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867218348453155e-05, "loss": 4.3247, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858832400942635e-05, "loss": 4.3262, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850446453432115e-05, "loss": 4.3379, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842076884725324e-05, "loss": 4.3168, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833690937214804e-05, "loss": 4.3222, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.5825304989704284e-05, "loss": 4.3229, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581691904219377e-05, "loss": 4.3367, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580854947348698e-05, "loss": 4.3104, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580016352597646e-05, "loss": 4.3414, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579177757846594e-05, "loss": 4.3135, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578339163095542e-05, "loss": 4.3136, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.57750056834449e-05, "loss": 4.3272, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576661973593438e-05, "loss": 4.3154, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575823378842385e-05, "loss": 4.3273, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574984784091333e-05, "loss": 4.3285, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574147827220655e-05, "loss": 4.3081, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573309232469602e-05, "loss": 4.3168, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572472275598924e-05, "loss": 4.3185, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716336808478725e-05, "loss": 4.3212, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5707950860968205e-05, "loss": 4.3111, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569956491345768e-05, "loss": 4.3154, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569117896594716e-05, "loss": 4.2958, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568279301843664e-05, "loss": 4.3254, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567440707092612e-05, "loss": 4.3143, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566603750221933e-05, "loss": 4.3069, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565765155470881e-05, "loss": 4.3134, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564926560719829e-05, "loss": 4.3122, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5640879659687767e-05, "loss": 4.3136, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632493712177247e-05, "loss": 4.3194, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624107764666726e-05, "loss": 4.3239, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561573819595994e-05, "loss": 4.3119, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560735224844942e-05, "loss": 4.3042, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.55989663009389e-05, "loss": 4.3077, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559058035342838e-05, "loss": 4.3093, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558219440591786e-05, "loss": 4.3206, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557380845840734e-05, "loss": 4.3125, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556542251089682e-05, "loss": 4.3072, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555705294219003e-05, "loss": 4.2959, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554866699467951e-05, "loss": 4.3034, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554028104716899e-05, "loss": 4.302, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553189509965847e-05, "loss": 4.3077, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552350915214795e-05, "loss": 4.3079, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551512320463743e-05, "loss": 4.3057, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550673725712691e-05, "loss": 4.2991, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549835130961639e-05, "loss": 4.3061, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.548998174090961e-05, "loss": 4.2983, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548159579339909e-05, "loss": 4.2991, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547320984588857e-05, "loss": 4.3037, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.5464840277181776e-05, "loss": 4.2894, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.5456454329671256e-05, "loss": 4.2904, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448068382160736e-05, "loss": 4.3055, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5439682434650216e-05, "loss": 4.2975, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543129648713969e-05, "loss": 4.3037, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5422926918432905e-05, "loss": 4.2992, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414540970922385e-05, "loss": 4.2944, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406155023411865e-05, "loss": 4.2917, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397769075901345e-05, "loss": 4.3026, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389383128390824e-05, "loss": 4.2996, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538101355968404e-05, "loss": 4.2853, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372627612173514e-05, "loss": 4.3042, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364241664662994e-05, "loss": 4.2764, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5355855717152473e-05, "loss": 4.2863, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347469769641953e-05, "loss": 4.2977, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533910020093516e-05, "loss": 4.2827, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533071425342464e-05, "loss": 4.2946, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532232830591412e-05, "loss": 4.2801, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.53139423584036e-05, "loss": 4.2788, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530555641089308e-05, "loss": 4.2815, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.52971868421863e-05, "loss": 4.3024, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528880089467578e-05, "loss": 4.2849, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528041494716526e-05, "loss": 4.277, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527202899965474e-05, "loss": 4.2771, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526364305214422e-05, "loss": 4.2846, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525527348343743e-05, "loss": 4.2924, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524688753592691e-05, "loss": 4.2904, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523850158841639e-05, "loss": 4.2815, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523011564090587e-05, "loss": 4.2914, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522172969339535e-05, "loss": 4.28, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521334374588483e-05, "loss": 4.2835, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520495779837431e-05, "loss": 4.2823, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519657185086379e-05, "loss": 4.2852, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188202282157e-05, "loss": 4.2762, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517981633464648e-05, "loss": 4.2792, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517143038713596e-05, "loss": 4.2901, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516304443962544e-05, "loss": 4.2699, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515467487091865e-05, "loss": 4.2789, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514630530221186e-05, "loss": 4.2833, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513791935470134e-05, "loss": 4.291, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512953340719082e-05, "loss": 4.2809, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.51211474596803e-05, "loss": 4.2801, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511276151216978e-05, "loss": 4.2674, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510437556465926e-05, "loss": 4.2717, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509598961714874e-05, "loss": 4.281, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508760366963822e-05, "loss": 4.2877, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079234100931436e-05, "loss": 4.2862, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070848153420916e-05, "loss": 4.2735, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062462205910396e-05, "loss": 4.2666, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054076258399876e-05, "loss": 4.2819, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045706689693085e-05, "loss": 4.2728, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037320742182565e-05, "loss": 4.2744, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5028951173475774e-05, "loss": 4.2856, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020565225965254e-05, "loss": 4.2756, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012179278454734e-05, "loss": 4.2709, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5003793330944214e-05, "loss": 4.2704, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.308167934417725, "eval_runtime": 546.8979, "eval_samples_per_second": 697.737, "eval_steps_per_second": 21.805, "step": 305276 }, { "epoch": 0.0, "learning_rate": 4.4995407383433694e-05, "loss": 4.2858, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4987021435923174e-05, "loss": 4.2818, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.4978635488412654e-05, "loss": 4.266, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970249540902134e-05, "loss": 4.2655, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4961863593391614e-05, "loss": 4.2667, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953477645881094e-05, "loss": 4.2631, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945091698370574e-05, "loss": 4.265, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.4936705750860054e-05, "loss": 4.2614, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.4928319803349534e-05, "loss": 4.2671, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491995023464274e-05, "loss": 4.276, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491156428713222e-05, "loss": 4.2665, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.49031783396217e-05, "loss": 4.2677, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489479239211118e-05, "loss": 4.2696, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488640644460066e-05, "loss": 4.2609, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487802049709014e-05, "loss": 4.2612, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486963454957962e-05, "loss": 4.2433, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.48612486020691e-05, "loss": 4.2587, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485286265455859e-05, "loss": 4.2588, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484447670704806e-05, "loss": 4.2574, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483609075953754e-05, "loss": 4.2776, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482770481202702e-05, "loss": 4.2606, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.48193188645165e-05, "loss": 4.2669, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481093291700598e-05, "loss": 4.2585, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480254696949546e-05, "loss": 4.2626, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479416102198494e-05, "loss": 4.2541, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478577507447442e-05, "loss": 4.2595, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477740550576763e-05, "loss": 4.2589, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476901955825711e-05, "loss": 4.2563, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476063361074659e-05, "loss": 4.251, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475224766323607e-05, "loss": 4.2445, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474387809452929e-05, "loss": 4.2456, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473549214701877e-05, "loss": 4.2608, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472710619950825e-05, "loss": 4.256, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471872025199773e-05, "loss": 4.2579, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710350683290936e-05, "loss": 4.2524, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4701981114584145e-05, "loss": 4.2576, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4693595167073625e-05, "loss": 4.2547, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685225598366834e-05, "loss": 4.2628, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4676839650856314e-05, "loss": 4.2532, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668453703345794e-05, "loss": 4.2446, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466006775583528e-05, "loss": 4.257, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465169818712849e-05, "loss": 4.2343, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464331223961797e-05, "loss": 4.2559, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463492629210745e-05, "loss": 4.2548, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462654034459693e-05, "loss": 4.2611, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461815439708641e-05, "loss": 4.2459, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460976844957589e-05, "loss": 4.2418, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460138250206537e-05, "loss": 4.2568, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459299655455485e-05, "loss": 4.2389, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458461060704433e-05, "loss": 4.2398, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457622465953381e-05, "loss": 4.2446, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456783871202329e-05, "loss": 4.2524, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.45594691433165e-05, "loss": 4.2355, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455108319580598e-05, "loss": 4.2553, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542697248295465e-05, "loss": 4.234, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534311300784945e-05, "loss": 4.2382, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4525925353274425e-05, "loss": 4.2477, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517555784567634e-05, "loss": 4.2322, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.4509169837057114e-05, "loss": 4.2521, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.4500783889546594e-05, "loss": 4.2529, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449239794203607e-05, "loss": 4.2278, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448401199452555e-05, "loss": 4.2349, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447564242581876e-05, "loss": 4.243, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446725647830824e-05, "loss": 4.2469, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.4458870530797716e-05, "loss": 4.2332, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.44504845832872e-05, "loss": 4.2365, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444211501458041e-05, "loss": 4.2233, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.44337290670699e-05, "loss": 4.2446, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442534311955937e-05, "loss": 4.2388, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441695717204885e-05, "loss": 4.2296, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440857122453833e-05, "loss": 4.2394, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440018527702781e-05, "loss": 4.2348, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439181570832102e-05, "loss": 4.2347, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.43834297608105e-05, "loss": 4.244, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437504381329998e-05, "loss": 4.2452, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436665786578946e-05, "loss": 4.2355, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435828829708267e-05, "loss": 4.2325, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.434990234957216e-05, "loss": 4.2354, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434151640206164e-05, "loss": 4.2304, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333130454551117e-05, "loss": 4.2496, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324744507040597e-05, "loss": 4.2357, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316374938333806e-05, "loss": 4.2335, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4307988990823286e-05, "loss": 4.2171, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4299619422116495e-05, "loss": 4.2317, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291233474605975e-05, "loss": 4.2244, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4282847527095455e-05, "loss": 4.2373, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274461579584935e-05, "loss": 4.231, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.4266075632074415e-05, "loss": 4.2312, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257689684563894e-05, "loss": 4.2239, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249303737053374e-05, "loss": 4.2353, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.4240917789542854e-05, "loss": 4.2238, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423254822083607e-05, "loss": 4.2246, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422416227332555e-05, "loss": 4.233, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421577632581503e-05, "loss": 4.2132, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420739037830451e-05, "loss": 4.2169, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419900443079399e-05, "loss": 4.2334, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419061848328347e-05, "loss": 4.2216, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418223253577295e-05, "loss": 4.2372, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417384658826243e-05, "loss": 4.2269, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.41654606407519e-05, "loss": 4.2176, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415709107204512e-05, "loss": 4.2222, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.41487051245346e-05, "loss": 4.2294, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414031917702408e-05, "loss": 4.227, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413194960831729e-05, "loss": 4.2168, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123563660806775e-05, "loss": 4.23, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115177713296255e-05, "loss": 4.2052, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4106791765785735e-05, "loss": 4.2166, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409840581827521e-05, "loss": 4.2276, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409001987076469e-05, "loss": 4.2102, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408163392325417e-05, "loss": 4.2241, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407324797574365e-05, "loss": 4.2178, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406487840703686e-05, "loss": 4.201, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405649245952634e-05, "loss": 4.2116, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404810651201582e-05, "loss": 4.2305, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.40397205645053e-05, "loss": 4.2145, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403135099579851e-05, "loss": 4.2117, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402296504828799e-05, "loss": 4.2078, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.40145954795812e-05, "loss": 4.2148, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400620953207068e-05, "loss": 4.2243, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399782358456016e-05, "loss": 4.2213, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398943763704964e-05, "loss": 4.2134, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398105168953912e-05, "loss": 4.2183, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.39726657420286e-05, "loss": 4.2142, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396427979451808e-05, "loss": 4.2145, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395589384700756e-05, "loss": 4.2151, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394752427830077e-05, "loss": 4.2143, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393913833079025e-05, "loss": 4.205, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393075238327973e-05, "loss": 4.2166, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392236643576921e-05, "loss": 4.218, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3913996867062426e-05, "loss": 4.2035, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905610919551906e-05, "loss": 4.2097, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897224972041386e-05, "loss": 4.2182, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3888855403334595e-05, "loss": 4.2187, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.3880469455824075e-05, "loss": 4.218, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872083508313555e-05, "loss": 4.212, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3863697560803035e-05, "loss": 4.1998, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.3855311613292515e-05, "loss": 4.2051, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3846925665781995e-05, "loss": 4.2124, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.3838539718271475e-05, "loss": 4.2205, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.3830153770760955e-05, "loss": 4.2212, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.38218005808579e-05, "loss": 4.2097, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381341463334738e-05, "loss": 4.2009, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380502868583686e-05, "loss": 4.2172, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379664273832634e-05, "loss": 4.2041, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378827316961955e-05, "loss": 4.2082, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.377988722210903e-05, "loss": 4.2223, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377150127459851e-05, "loss": 4.2125, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376311532708799e-05, "loss": 4.2022, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375472937957747e-05, "loss": 4.2086, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.251522064208984, "eval_runtime": 554.599, "eval_samples_per_second": 688.049, "eval_steps_per_second": 21.502, "step": 381595 }, { "epoch": 1.0, "learning_rate": 4.374635981087068e-05, "loss": 4.2163, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373797386336016e-05, "loss": 4.2204, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372958791584964e-05, "loss": 4.2004, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372120196833912e-05, "loss": 4.1986, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.37128160208286e-05, "loss": 4.2069, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.3704446452121813e-05, "loss": 4.1993, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369606050461129e-05, "loss": 4.2021, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368767455710077e-05, "loss": 4.1915, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367928860959025e-05, "loss": 4.2053, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367093541968719e-05, "loss": 4.2178, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366254947217667e-05, "loss": 4.1984, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365416352466615e-05, "loss": 4.2036, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364577757715563e-05, "loss": 4.2092, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363739162964511e-05, "loss": 4.1973, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362900568213459e-05, "loss": 4.2015, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362061973462407e-05, "loss": 4.1827, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361223378711355e-05, "loss": 4.1937, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360384783960304e-05, "loss": 4.1965, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359546189209251e-05, "loss": 4.1962, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358709232338573e-05, "loss": 4.2181, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357870637587521e-05, "loss": 4.1972, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357032042836469e-05, "loss": 4.2071, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356193448085416e-05, "loss": 4.1982, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355354853334364e-05, "loss": 4.2013, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354516258583312e-05, "loss": 4.1902, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.35367766383226e-05, "loss": 4.1978, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352840706961581e-05, "loss": 4.2015, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.3520037500909025e-05, "loss": 4.1959, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.3511651553398505e-05, "loss": 4.1907, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.3503265605887985e-05, "loss": 4.1868, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.3494879658377465e-05, "loss": 4.1814, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486493710866945e-05, "loss": 4.2029, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478107763356425e-05, "loss": 4.1975, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469721815845905e-05, "loss": 4.1945, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.3461335868335385e-05, "loss": 4.1926, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3452949920824865e-05, "loss": 4.1966, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444580352118074e-05, "loss": 4.1998, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343621078341128e-05, "loss": 4.1994, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342782483590076e-05, "loss": 4.1955, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.341943888839024e-05, "loss": 4.1859, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.341105294087973e-05, "loss": 4.1947, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340266699336921e-05, "loss": 4.1788, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.339428104585869e-05, "loss": 4.1963, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338589509834817e-05, "loss": 4.1941, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337750915083765e-05, "loss": 4.2011, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336912320332713e-05, "loss": 4.1895, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336073725581661e-05, "loss": 4.1827, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335235130830609e-05, "loss": 4.2011, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.33439817395993e-05, "loss": 4.1784, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333559579208878e-05, "loss": 4.1844, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332720984457826e-05, "loss": 4.185, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331882389706774e-05, "loss": 4.1927, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331043794955722e-05, "loss": 4.178, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330206838085043e-05, "loss": 4.192, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.3293682433339914e-05, "loss": 4.1805, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328531286463312e-05, "loss": 4.1786, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.32769269171226e-05, "loss": 4.1914, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326854096961208e-05, "loss": 4.178, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326015502210156e-05, "loss": 4.1934, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325176907459104e-05, "loss": 4.1946, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324338312708052e-05, "loss": 4.1767, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.3234997179569996e-05, "loss": 4.1766, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.3226611232059476e-05, "loss": 4.1821, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321824166335269e-05, "loss": 4.1946, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.3209855715842165e-05, "loss": 4.1785, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320146976833165e-05, "loss": 4.1824, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319308382082113e-05, "loss": 4.1665, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318469787331061e-05, "loss": 4.1897, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317631192580009e-05, "loss": 4.18, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316792597828957e-05, "loss": 4.1758, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315954003077905e-05, "loss": 4.1825, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315117046207226e-05, "loss": 4.1817, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314278451456174e-05, "loss": 4.1794, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313439856705122e-05, "loss": 4.186, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.31260126195407e-05, "loss": 4.1883, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311762667203018e-05, "loss": 4.181, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310925710332339e-05, "loss": 4.1756, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310087115581287e-05, "loss": 4.1835, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309248520830235e-05, "loss": 4.1762, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308409926079183e-05, "loss": 4.189, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3075746070888774e-05, "loss": 4.1801, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067360123378254e-05, "loss": 4.1833, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3058974175867734e-05, "loss": 4.1658, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305060460716094e-05, "loss": 4.1775, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.304221865965042e-05, "loss": 4.1662, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.30338327121399e-05, "loss": 4.1847, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.302544676462938e-05, "loss": 4.1769, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.301706081711886e-05, "loss": 4.1771, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300867486960834e-05, "loss": 4.1731, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300028892209782e-05, "loss": 4.1843, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.29919029745873e-05, "loss": 4.1626, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298351702707678e-05, "loss": 4.1705, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297513107956627e-05, "loss": 4.1802, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296676151085948e-05, "loss": 4.1609, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295837556334896e-05, "loss": 4.164, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.294998961583844e-05, "loss": 4.1805, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294160366832792e-05, "loss": 4.1659, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.29332177208174e-05, "loss": 4.1866, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292483177330688e-05, "loss": 4.1727, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291644582579636e-05, "loss": 4.1651, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290805987828583e-05, "loss": 4.1657, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289969030957905e-05, "loss": 4.1784, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289130436206853e-05, "loss": 4.177, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.2882934793361737e-05, "loss": 4.1619, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287454884585122e-05, "loss": 4.1766, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.28661628983407e-05, "loss": 4.1536, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285777695083018e-05, "loss": 4.1628, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.2849391003319656e-05, "loss": 4.1755, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.2841005055809136e-05, "loss": 4.1587, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283263548710235e-05, "loss": 4.1711, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824249539591825e-05, "loss": 4.1708, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2815863592081305e-05, "loss": 4.1469, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807477644570785e-05, "loss": 4.1608, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2799091697060265e-05, "loss": 4.1761, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2790705749549745e-05, "loss": 4.1684, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.2782319802039225e-05, "loss": 4.1565, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.2773933854528705e-05, "loss": 4.1559, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276558066462566e-05, "loss": 4.1649, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275719471711513e-05, "loss": 4.1714, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274880876960461e-05, "loss": 4.1707, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274042282209409e-05, "loss": 4.1612, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273203687458357e-05, "loss": 4.1667, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272365092707305e-05, "loss": 4.1636, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271526497956253e-05, "loss": 4.1652, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270687903205201e-05, "loss": 4.1619, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.269849308454149e-05, "loss": 4.1643, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269013989463843e-05, "loss": 4.1579, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.2681753947127915e-05, "loss": 4.1663, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.2673367999617395e-05, "loss": 4.1674, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.2664982052106875e-05, "loss": 4.1513, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.2656596104596355e-05, "loss": 4.1597, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.2648210157085835e-05, "loss": 4.171, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.2639824209575315e-05, "loss": 4.1666, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.2631454640868524e-05, "loss": 4.1677, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623068693358004e-05, "loss": 4.1623, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2614682745847484e-05, "loss": 4.1463, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.2606296798336964e-05, "loss": 4.1536, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.2597910850826443e-05, "loss": 4.1623, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258954128211965e-05, "loss": 4.1768, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258115533460913e-05, "loss": 4.1706, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257276938709861e-05, "loss": 4.1552, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256438343958809e-05, "loss": 4.1573, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255599749207758e-05, "loss": 4.1617, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254761154456706e-05, "loss": 4.1577, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.253922559705654e-05, "loss": 4.1583, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253085602834975e-05, "loss": 4.1741, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252247008083923e-05, "loss": 4.165, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251408413332871e-05, "loss": 4.1497, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250569818581819e-05, "loss": 4.1599, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.21055793762207, "eval_runtime": 548.3608, "eval_samples_per_second": 695.876, "eval_steps_per_second": 21.747, "step": 457914 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.762137680804871e+17, "trial_name": null, "trial_params": null }