{ "best_metric": 4.160358428955078, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/lstm/2/checkpoints/checkpoint-457920", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 457920, "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": 10.8205, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5515, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0564, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9912, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9444, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.8869, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.729, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.6174, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.5248, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4532, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.3956, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990777095618801e-05, "loss": 6.3294, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 6.2612, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 6.1984, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 6.1352, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 6.0769, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 6.0315, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.9936, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.95, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.9116, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8803, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.8347, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.8167, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.980713958606178e-05, "loss": 5.7806, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7629, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7271, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.701, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.6771, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6606, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.975684027980238e-05, "loss": 5.6377, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.974845433229186e-05, "loss": 5.6157, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.6045, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.569, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.972331286856403e-05, "loss": 5.5621, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714926921053515e-05, "loss": 5.5442, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5281, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5134, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.4746, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.9681399509815164e-05, "loss": 5.48, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.9673013562304644e-05, "loss": 5.4463, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.9664627614794124e-05, "loss": 5.4497, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.9656241667283604e-05, "loss": 5.4296, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.9647855719773084e-05, "loss": 5.4292, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963948615106629e-05, "loss": 5.4027, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963110020355577e-05, "loss": 5.387, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962271425604525e-05, "loss": 5.3915, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961432830853473e-05, "loss": 5.38, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960594236102421e-05, "loss": 5.3676, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959755641351369e-05, "loss": 5.3509, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958918684480691e-05, "loss": 5.3287, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958080089729639e-05, "loss": 5.3402, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957241494978587e-05, "loss": 5.321, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956402900227535e-05, "loss": 5.3203, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955564305476483e-05, "loss": 5.2892, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954725710725431e-05, "loss": 5.294, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953887115974379e-05, "loss": 5.2708, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530501591037e-05, "loss": 5.2921, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522132022330207e-05, "loss": 5.2556, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.9513746074819686e-05, "loss": 5.2587, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.9505360127309166e-05, "loss": 5.2429, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.9496974179798646e-05, "loss": 5.2313, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948858823228813e-05, "loss": 5.2331, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948021866358134e-05, "loss": 5.2199, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.1949, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.1988, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2096, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944669125234299e-05, "loss": 5.1863, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943830530483247e-05, "loss": 5.1766, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942991935732195e-05, "loss": 5.158, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942153340981143e-05, "loss": 5.1605, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413147462300904e-05, "loss": 5.1773, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404761514790384e-05, "loss": 5.1604, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.93963919460836e-05, "loss": 5.1465, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.938800599857309e-05, "loss": 5.1489, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.937962005106256e-05, "loss": 5.1452, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.937123410355204e-05, "loss": 5.128, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1117, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.117, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.934609263982421e-05, "loss": 5.099, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933770669231369e-05, "loss": 5.0993, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932932074480317e-05, "loss": 5.1042, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932093479729265e-05, "loss": 5.0913, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931254884978213e-05, "loss": 5.0932, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930416290227161e-05, "loss": 5.0812, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295793333564825e-05, "loss": 5.0613, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287407386054305e-05, "loss": 5.0647, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279021438543785e-05, "loss": 5.0604, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.9270651869836994e-05, "loss": 5.0674, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.9262265922326474e-05, "loss": 5.0476, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.9253879974815954e-05, "loss": 5.0467, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.9245494027305433e-05, "loss": 5.0451, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.9237108079794913e-05, "loss": 5.0376, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922873851108812e-05, "loss": 5.0358, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92203525635776e-05, "loss": 5.0232, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921196661606708e-05, "loss": 5.0098, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920358066855656e-05, "loss": 5.0179, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919519472104604e-05, "loss": 5.0072, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918680877353552e-05, "loss": 5.0008, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917843920482874e-05, "loss": 4.9941, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917005325731822e-05, "loss": 4.9928, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.91616673098077e-05, "loss": 4.9966, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915328136229718e-05, "loss": 4.984, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914491179359039e-05, "loss": 4.9748, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913652584607987e-05, "loss": 4.9703, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912813989856935e-05, "loss": 4.962, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911975395105883e-05, "loss": 4.948, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911136800354831e-05, "loss": 4.9438, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910298205603779e-05, "loss": 4.9493, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909459610852727e-05, "loss": 4.9453, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086226539820476e-05, "loss": 4.9323, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907784059230996e-05, "loss": 4.9299, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906945464479944e-05, "loss": 4.9305, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906106869728892e-05, "loss": 4.9336, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905269912858213e-05, "loss": 4.9296, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904431318107161e-05, "loss": 4.9217, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903592723356109e-05, "loss": 4.9186, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027541286050565e-05, "loss": 4.9174, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019155338540045e-05, "loss": 4.9057, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010769391029525e-05, "loss": 4.8991, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002383443519005e-05, "loss": 4.9049, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994013874812214e-05, "loss": 4.9016, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.89856279273017e-05, "loss": 4.8813, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897724197979118e-05, "loss": 4.8834, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.896885603228066e-05, "loss": 4.8802, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.896048646357387e-05, "loss": 4.8703, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.895210051606335e-05, "loss": 4.8738, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.894371456855283e-05, "loss": 4.8771, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893532862104231e-05, "loss": 4.8624, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892695905233552e-05, "loss": 4.8625, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918573104825e-05, "loss": 4.8513, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891018715731448e-05, "loss": 4.8679, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890180120980396e-05, "loss": 4.8586, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889341526229344e-05, "loss": 4.8496, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888502931478292e-05, "loss": 4.8464, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.8876659746076134e-05, "loss": 4.8466, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.8868273798565614e-05, "loss": 4.8456, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.8859887851055094e-05, "loss": 4.8347, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.8851501903544574e-05, "loss": 4.8328, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.8843115956034054e-05, "loss": 4.8332, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.8834730008523534e-05, "loss": 4.8295, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.8826344061013014e-05, "loss": 4.8294, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8817958113502494e-05, "loss": 4.8095, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809572165991974e-05, "loss": 4.8199, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801186218481454e-05, "loss": 4.805, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879281664977466e-05, "loss": 4.7947, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878443070226414e-05, "loss": 4.814, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877604475475362e-05, "loss": 4.8025, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87676588072431e-05, "loss": 4.8009, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875928923853632e-05, "loss": 4.8045, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.87509032910258e-05, "loss": 4.7844, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.7605061531066895, "eval_runtime": 306.4383, "eval_samples_per_second": 1245.246, "eval_steps_per_second": 38.915, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874251734351528e-05, "loss": 4.7863, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873413139600475e-05, "loss": 4.7841, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872574544849423e-05, "loss": 4.7993, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871737587978745e-05, "loss": 4.7787, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870898993227693e-05, "loss": 4.7871, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.87006039847664e-05, "loss": 4.7659, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869221803725588e-05, "loss": 4.7719, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868383208974536e-05, "loss": 4.761, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675462521038576e-05, "loss": 4.7671, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667076573528056e-05, "loss": 4.7659, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658690626017536e-05, "loss": 4.7688, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865032105731075e-05, "loss": 4.7683, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864195148860396e-05, "loss": 4.748, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863356554109344e-05, "loss": 4.7485, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862517959358292e-05, "loss": 4.743, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.86167936460724e-05, "loss": 4.7364, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608407698561874e-05, "loss": 4.7513, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.8600021751051354e-05, "loss": 4.7343, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591635803540834e-05, "loss": 4.7333, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583249856030314e-05, "loss": 4.7521, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574863908519794e-05, "loss": 4.7311, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566477961009274e-05, "loss": 4.7316, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855810839230249e-05, "loss": 4.7273, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854972244479197e-05, "loss": 4.7349, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854133649728145e-05, "loss": 4.7237, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853295054977093e-05, "loss": 4.7171, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852456460226041e-05, "loss": 4.7119, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851617865474989e-05, "loss": 4.7201, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850779270723937e-05, "loss": 4.7014, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849940675972885e-05, "loss": 4.7082, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849102081221833e-05, "loss": 4.7083, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848263486470781e-05, "loss": 4.7032, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847424891719729e-05, "loss": 4.7075, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.84658793484905e-05, "loss": 4.6983, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845749340097998e-05, "loss": 4.6982, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844910745346946e-05, "loss": 4.6991, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844072150595894e-05, "loss": 4.6753, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843233555844842e-05, "loss": 4.6873, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8423965989741634e-05, "loss": 4.6701, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415580042231114e-05, "loss": 4.6804, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840719409472059e-05, "loss": 4.6827, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839880814721007e-05, "loss": 4.6855, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839042219969955e-05, "loss": 4.675, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838203625218903e-05, "loss": 4.6743, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373666683482236e-05, "loss": 4.6794, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365280735971716e-05, "loss": 4.6741, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356894788461196e-05, "loss": 4.6694, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348508840950676e-05, "loss": 4.663, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340122893440156e-05, "loss": 4.6503, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833173694592964e-05, "loss": 4.6685, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832336737722285e-05, "loss": 4.6615, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831498142971233e-05, "loss": 4.6597, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830659548220181e-05, "loss": 4.646, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829820953469129e-05, "loss": 4.6548, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828982358718077e-05, "loss": 4.6388, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828143763967025e-05, "loss": 4.6607, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827305169215973e-05, "loss": 4.6406, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826468212345294e-05, "loss": 4.6505, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825629617594242e-05, "loss": 4.6389, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.82479102284319e-05, "loss": 4.6319, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823952428092138e-05, "loss": 4.6343, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823113833341086e-05, "loss": 4.6379, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822275238590034e-05, "loss": 4.6141, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821436643838983e-05, "loss": 4.6238, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.82059804908793e-05, "loss": 4.6347, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197610922172516e-05, "loss": 4.6219, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189241353465726e-05, "loss": 4.6152, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180855405955206e-05, "loss": 4.6136, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172469458444685e-05, "loss": 4.6114, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164099889737895e-05, "loss": 4.6346, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155713942227375e-05, "loss": 4.6246, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147327994716854e-05, "loss": 4.6148, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8138942047206334e-05, "loss": 4.621, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130556099695814e-05, "loss": 4.6214, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122170152185294e-05, "loss": 4.6138, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113784204674774e-05, "loss": 4.5986, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105398257164254e-05, "loss": 4.6126, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097012309653734e-05, "loss": 4.6035, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808864274094695e-05, "loss": 4.5978, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808025679343642e-05, "loss": 4.6103, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.80718708459259e-05, "loss": 4.6012, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806348489841538e-05, "loss": 4.6085, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805509895090486e-05, "loss": 4.6042, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804672938219807e-05, "loss": 4.5812, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803834343468755e-05, "loss": 4.5944, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.802995748717703e-05, "loss": 4.5882, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802157153966652e-05, "loss": 4.5997, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013185592156e-05, "loss": 4.5899, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800479964464548e-05, "loss": 4.5939, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799643007593869e-05, "loss": 4.5919, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798804412842817e-05, "loss": 4.5874, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797965818091765e-05, "loss": 4.5915, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797127223340713e-05, "loss": 4.5836, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796288628589661e-05, "loss": 4.5719, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795451671718982e-05, "loss": 4.5833, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.79461307696793e-05, "loss": 4.582, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793774482216878e-05, "loss": 4.5729, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792935887465826e-05, "loss": 4.5778, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792098930595147e-05, "loss": 4.5761, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791260335844095e-05, "loss": 4.5869, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790421741093043e-05, "loss": 4.5707, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789583146341991e-05, "loss": 4.5622, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788744551590939e-05, "loss": 4.566, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787909232600633e-05, "loss": 4.5636, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787070637849581e-05, "loss": 4.5452, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786232043098529e-05, "loss": 4.5595, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785393448347477e-05, "loss": 4.559, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784554853596425e-05, "loss": 4.5575, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783716258845373e-05, "loss": 4.5513, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782879301974694e-05, "loss": 4.5434, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782040707223642e-05, "loss": 4.5511, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812021124725906e-05, "loss": 4.5621, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803635177215386e-05, "loss": 4.555, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795249229704866e-05, "loss": 4.5549, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786863282194346e-05, "loss": 4.5487, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778477334683826e-05, "loss": 4.5616, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770091387173306e-05, "loss": 4.5427, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761705439662786e-05, "loss": 4.5404, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775331949215226e-05, "loss": 4.5492, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774493354464174e-05, "loss": 4.5482, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736563975934955e-05, "loss": 4.5297, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728194407228164e-05, "loss": 4.5325, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719808459717644e-05, "loss": 4.5391, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771143889101086e-05, "loss": 4.5303, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770305294350034e-05, "loss": 4.5348, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769466699598982e-05, "loss": 4.5421, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.76862810484793e-05, "loss": 4.5227, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767789510096878e-05, "loss": 4.5332, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766950915345826e-05, "loss": 4.5209, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766112320594773e-05, "loss": 4.5438, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765273725843721e-05, "loss": 4.5352, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764436768973043e-05, "loss": 4.5233, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.76359817422199e-05, "loss": 4.5257, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762759579470938e-05, "loss": 4.5241, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761920984719886e-05, "loss": 4.531, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761082389968834e-05, "loss": 4.526, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760245433098156e-05, "loss": 4.5217, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759406838347104e-05, "loss": 4.5201, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758568243596052e-05, "loss": 4.5192, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757729648845e-05, "loss": 4.5209, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756891054093948e-05, "loss": 4.5081, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756052459342896e-05, "loss": 4.5184, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755213864591844e-05, "loss": 4.507, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754375269840792e-05, "loss": 4.4977, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535383129701126e-05, "loss": 4.5187, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7526997182190606e-05, "loss": 4.5073, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518611234680086e-05, "loss": 4.5111, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510225287169566e-05, "loss": 4.5119, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750185571846278e-05, "loss": 4.4982, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.476386547088623, "eval_runtime": 328.9214, "eval_samples_per_second": 1160.128, "eval_steps_per_second": 36.255, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749346977095226e-05, "loss": 4.5029, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748508382344174e-05, "loss": 4.4928, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747669787593122e-05, "loss": 4.5166, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.74683119284207e-05, "loss": 4.4944, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.745992598091018e-05, "loss": 4.5106, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745154003339966e-05, "loss": 4.4907, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744315408588914e-05, "loss": 4.4925, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743476813837862e-05, "loss": 4.4848, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426382190868095e-05, "loss": 4.4979, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7417996243357575e-05, "loss": 4.4955, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409610295847055e-05, "loss": 4.4984, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401224348336535e-05, "loss": 4.5014, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739285477962975e-05, "loss": 4.4834, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738446883211923e-05, "loss": 4.4855, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737608288460871e-05, "loss": 4.4802, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736769693709819e-05, "loss": 4.4766, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735931098958767e-05, "loss": 4.4868, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735092504207715e-05, "loss": 4.4786, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734253909456663e-05, "loss": 4.4772, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733415314705611e-05, "loss": 4.4934, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732576719954559e-05, "loss": 4.4778, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731738125203507e-05, "loss": 4.4782, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730899530452455e-05, "loss": 4.4773, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730060935701403e-05, "loss": 4.4877, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729223978830724e-05, "loss": 4.474, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728385384079672e-05, "loss": 4.4714, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.72754678932862e-05, "loss": 4.4701, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726708194577568e-05, "loss": 4.4719, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258728755872624e-05, "loss": 4.4619, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250342808362104e-05, "loss": 4.4672, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724197323965531e-05, "loss": 4.4683, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723358729214479e-05, "loss": 4.4656, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722520134463427e-05, "loss": 4.4736, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721681539712375e-05, "loss": 4.4604, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720842944961323e-05, "loss": 4.4629, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720004350210271e-05, "loss": 4.4641, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719165755459219e-05, "loss": 4.4483, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718327160708167e-05, "loss": 4.4525, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717490203837488e-05, "loss": 4.4439, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716651609086437e-05, "loss": 4.4495, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715813014335385e-05, "loss": 4.4583, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714974419584333e-05, "loss": 4.4598, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714135824833281e-05, "loss": 4.4509, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713297230082228e-05, "loss": 4.4504, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712458635331176e-05, "loss": 4.4598, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711620040580124e-05, "loss": 4.4478, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710783083709446e-05, "loss": 4.4512, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709944488958393e-05, "loss": 4.4468, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709105894207341e-05, "loss": 4.4299, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708267299456289e-05, "loss": 4.4528, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074303425856106e-05, "loss": 4.4423, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065917478345586e-05, "loss": 4.4462, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057531530835066e-05, "loss": 4.435, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.7049145583324546e-05, "loss": 4.4432, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040759635814026e-05, "loss": 4.4245, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032373688303506e-05, "loss": 4.4535, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024004119596715e-05, "loss": 4.4275, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015618172086195e-05, "loss": 4.4454, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007232224575675e-05, "loss": 4.4294, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998846277065155e-05, "loss": 4.4323, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990460329554635e-05, "loss": 4.4259, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982074382044115e-05, "loss": 4.4366, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973688434533595e-05, "loss": 4.4108, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965302487023075e-05, "loss": 4.4228, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4314, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.69485633496095e-05, "loss": 4.4235, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694017740209898e-05, "loss": 4.418, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693179145458846e-05, "loss": 4.4129, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692340550707794e-05, "loss": 4.4153, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691501955956742e-05, "loss": 4.4392, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.69066336120569e-05, "loss": 4.427, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689824766454638e-05, "loss": 4.4202, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688987809583959e-05, "loss": 4.4284, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688149214832907e-05, "loss": 4.4283, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687310620081855e-05, "loss": 4.4242, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686472025330803e-05, "loss": 4.4075, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856350684601245e-05, "loss": 4.4217, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6847981115894454e-05, "loss": 4.4184, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839595168383934e-05, "loss": 4.406, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831209220873414e-05, "loss": 4.4254, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822823273362894e-05, "loss": 4.414, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814437325852373e-05, "loss": 4.4179, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.42, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679768180963506e-05, "loss": 4.4006, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678929586212454e-05, "loss": 4.4111, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678090991461402e-05, "loss": 4.4062, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.67725239671035e-05, "loss": 4.4154, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676413801959298e-05, "loss": 4.4136, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4112, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674739888217941e-05, "loss": 4.4124, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673901293466889e-05, "loss": 4.4097, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673062698715837e-05, "loss": 4.4094, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672224103964785e-05, "loss": 4.4043, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671385509213733e-05, "loss": 4.4036, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670546914462681e-05, "loss": 4.4081, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669708319711629e-05, "loss": 4.4028, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668869724960576e-05, "loss": 4.3996, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668031130209524e-05, "loss": 4.4033, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667192535458472e-05, "loss": 4.4033, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.66635394070742e-05, "loss": 4.417, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665515345956368e-05, "loss": 4.3962, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.3952, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638397943346376e-05, "loss": 4.3969, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630011995835856e-05, "loss": 4.3947, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621626048325336e-05, "loss": 4.3748, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661327285842228e-05, "loss": 4.3907, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660488691091176e-05, "loss": 4.3933, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596500963401234e-05, "loss": 4.3859, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588115015890714e-05, "loss": 4.3904, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579729068380194e-05, "loss": 4.381, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571343120869674e-05, "loss": 4.3814, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656297355216288e-05, "loss": 4.4013, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655458760465237e-05, "loss": 4.3879, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654620165714185e-05, "loss": 4.396, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653781570963133e-05, "loss": 4.3862, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652942976212081e-05, "loss": 4.3993, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652106019341402e-05, "loss": 4.3858, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.65126742459035e-05, "loss": 4.3823, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650428829839298e-05, "loss": 4.3857, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649590235088246e-05, "loss": 4.39, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648753278217567e-05, "loss": 4.373, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647914683466515e-05, "loss": 4.3748, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647076088715463e-05, "loss": 4.3775, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646237493964411e-05, "loss": 4.3791, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645398899213359e-05, "loss": 4.3804, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.64456194234268e-05, "loss": 4.3877, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643723347591628e-05, "loss": 4.3661, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642884752840576e-05, "loss": 4.376, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642046158089524e-05, "loss": 4.3689, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641207563338472e-05, "loss": 4.3894, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.64036896858742e-05, "loss": 4.3861, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639530373836368e-05, "loss": 4.3745, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638691779085316e-05, "loss": 4.3697, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637854822214637e-05, "loss": 4.3749, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637016227463585e-05, "loss": 4.3793, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636177632712533e-05, "loss": 4.3792, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635340675841854e-05, "loss": 4.3712, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634502081090802e-05, "loss": 4.3727, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633663486339751e-05, "loss": 4.3727, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632824891588699e-05, "loss": 4.3764, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631986296837647e-05, "loss": 4.3627, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631147702086595e-05, "loss": 4.3683, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630309107335542e-05, "loss": 4.3647, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629472150464864e-05, "loss": 4.3493, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628633555713812e-05, "loss": 4.375, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6277949609627597e-05, "loss": 4.3619, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626956366211707e-05, "loss": 4.3653, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626117771460655e-05, "loss": 4.3698, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625279176709603e-05, "loss": 4.353, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.340369701385498, "eval_runtime": 291.5712, "eval_samples_per_second": 1308.74, "eval_steps_per_second": 40.899, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.6244422198389246e-05, "loss": 4.3626, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.6236036250878726e-05, "loss": 4.3491, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227650303368205e-05, "loss": 4.3732, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219264355857685e-05, "loss": 4.353, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210878408347165e-05, "loss": 4.3775, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202492460836645e-05, "loss": 4.3466, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194122892129854e-05, "loss": 4.3555, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185736944619334e-05, "loss": 4.3405, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177350997108814e-05, "loss": 4.3617, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168965049598294e-05, "loss": 4.3567, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.61605954808915e-05, "loss": 4.3577, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615220953338098e-05, "loss": 4.3708, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.61438399646742e-05, "loss": 4.3441, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613545401716368e-05, "loss": 4.3523, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612706806965316e-05, "loss": 4.3443, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611868212214264e-05, "loss": 4.3432, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611029617463212e-05, "loss": 4.3488, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.61019102271216e-05, "loss": 4.3459, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609352427961108e-05, "loss": 4.3439, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608513833210056e-05, "loss": 4.3579, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607675238459004e-05, "loss": 4.3476, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606838281588325e-05, "loss": 4.3453, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.605999686837273e-05, "loss": 4.3494, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605162729966594e-05, "loss": 4.3528, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604324135215542e-05, "loss": 4.3428, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.60348554046449e-05, "loss": 4.3418, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602646945713438e-05, "loss": 4.3404, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018083509623864e-05, "loss": 4.3352, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009697562113344e-05, "loss": 4.3354, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600132799340655e-05, "loss": 4.3353, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599294204589603e-05, "loss": 4.344, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598455609838551e-05, "loss": 4.3382, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597617015087499e-05, "loss": 4.3464, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596778420336447e-05, "loss": 4.3358, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595939825585395e-05, "loss": 4.3338, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595101230834343e-05, "loss": 4.3346, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942626360832906e-05, "loss": 4.3261, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593425679212612e-05, "loss": 4.3249, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.59258708446156e-05, "loss": 4.3191, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591748489710508e-05, "loss": 4.3244, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.59091153283983e-05, "loss": 4.3355, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590072938088778e-05, "loss": 4.333, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589234343337726e-05, "loss": 4.3304, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588395748586673e-05, "loss": 4.3294, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587557153835621e-05, "loss": 4.3392, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586718559084569e-05, "loss": 4.3236, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585879964333517e-05, "loss": 4.3281, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585041369582465e-05, "loss": 4.3237, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584204412711786e-05, "loss": 4.3099, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583365817960734e-05, "loss": 4.3353, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582527223209682e-05, "loss": 4.3189, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.58168862845863e-05, "loss": 4.3254, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808500337075786e-05, "loss": 4.3135, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.5800114389565266e-05, "loss": 4.3285, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791728442054746e-05, "loss": 4.3053, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783342494544226e-05, "loss": 4.3314, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5774972925837435e-05, "loss": 4.3138, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.5766603357130644e-05, "loss": 4.3238, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758217409620124e-05, "loss": 4.3183, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5749831462109604e-05, "loss": 4.3101, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741445514599084e-05, "loss": 4.3082, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733059567088564e-05, "loss": 4.3258, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724673619578044e-05, "loss": 4.2968, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716287672067524e-05, "loss": 4.3016, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570791810336074e-05, "loss": 4.3183, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569954853465395e-05, "loss": 4.312, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569116258714343e-05, "loss": 4.3015, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568277663963291e-05, "loss": 4.3027, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567439069212239e-05, "loss": 4.2997, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566600474461187e-05, "loss": 4.3221, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565761879710135e-05, "loss": 4.3117, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564923284959083e-05, "loss": 4.3075, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564084690208031e-05, "loss": 4.3136, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563247733337352e-05, "loss": 4.3187, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624091385863e-05, "loss": 4.3155, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561570543835248e-05, "loss": 4.2947, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560731949084196e-05, "loss": 4.3094, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559894992213517e-05, "loss": 4.3067, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559056397462465e-05, "loss": 4.2959, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558219440591786e-05, "loss": 4.3175, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557380845840734e-05, "loss": 4.3026, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556542251089682e-05, "loss": 4.3106, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.55570365633863e-05, "loss": 4.3108, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554865061587578e-05, "loss": 4.2961, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554026466836526e-05, "loss": 4.3005, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553189509965847e-05, "loss": 4.2997, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552350915214795e-05, "loss": 4.3044, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551512320463743e-05, "loss": 4.3058, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550673725712691e-05, "loss": 4.3033, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549835130961639e-05, "loss": 4.3068, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.548996536210587e-05, "loss": 4.3074, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548157941459535e-05, "loss": 4.3, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547319346708483e-05, "loss": 4.2986, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546482389837804e-05, "loss": 4.2965, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545643795086752e-05, "loss": 4.3064, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448052003357e-05, "loss": 4.2979, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543966605584648e-05, "loss": 4.2963, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543129648713969e-05, "loss": 4.2984, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542291053962917e-05, "loss": 4.2962, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541452459211865e-05, "loss": 4.3117, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540613864460813e-05, "loss": 4.2948, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539775269709761e-05, "loss": 4.2935, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389366749587095e-05, "loss": 4.2921, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5380980802076575e-05, "loss": 4.2951, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372594854566055e-05, "loss": 4.2729, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364225285859264e-05, "loss": 4.2859, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5355839338348744e-05, "loss": 4.2934, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347453390838224e-05, "loss": 4.287, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339067443327704e-05, "loss": 4.2845, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533069787462091e-05, "loss": 4.282, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532231192711039e-05, "loss": 4.28, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531392597959987e-05, "loss": 4.3031, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530554003208935e-05, "loss": 4.2838, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529715408457883e-05, "loss": 4.2931, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528876813706831e-05, "loss": 4.2886, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528039856836153e-05, "loss": 4.302, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527201262085101e-05, "loss": 4.2883, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526362667334049e-05, "loss": 4.2783, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525524072582997e-05, "loss": 4.2888, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524687115712318e-05, "loss": 4.2913, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523848520961266e-05, "loss": 4.2743, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523009926210214e-05, "loss": 4.2764, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522171331459162e-05, "loss": 4.2834, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.52133273670811e-05, "loss": 4.283, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520494141957057e-05, "loss": 4.2801, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519657185086379e-05, "loss": 4.2964, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518818590335327e-05, "loss": 4.2671, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517979995584275e-05, "loss": 4.28, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517141400833223e-05, "loss": 4.2719, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516302806082171e-05, "loss": 4.2922, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.5154642113311187e-05, "loss": 4.2888, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.5146256165800667e-05, "loss": 4.2812, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5137870218290147e-05, "loss": 4.2731, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.5129500649583356e-05, "loss": 4.2837, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121114702072836e-05, "loss": 4.2839, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5112728754562316e-05, "loss": 4.2824, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104342807051795e-05, "loss": 4.2798, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5095973238345005e-05, "loss": 4.2767, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508760366963822e-05, "loss": 4.2789, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.50792177221277e-05, "loss": 4.2881, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507083177461718e-05, "loss": 4.2664, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506244582710666e-05, "loss": 4.2722, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505405987959614e-05, "loss": 4.2711, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504567393208562e-05, "loss": 4.2613, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.50372879845751e-05, "loss": 4.28, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502890203706458e-05, "loss": 4.2702, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502053246835779e-05, "loss": 4.2741, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501214652084727e-05, "loss": 4.2738, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500376057333675e-05, "loss": 4.2698, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.257408618927002, "eval_runtime": 292.9166, "eval_samples_per_second": 1302.729, "eval_steps_per_second": 40.711, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499537462582623e-05, "loss": 4.2733, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498698867831571e-05, "loss": 4.2592, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497860273080519e-05, "loss": 4.2809, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497021678329467e-05, "loss": 4.2647, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496183083578415e-05, "loss": 4.2847, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953444888273636e-05, "loss": 4.264, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945058940763116e-05, "loss": 4.2625, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493667299325259e-05, "loss": 4.2537, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492828704574207e-05, "loss": 4.269, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491990109823155e-05, "loss": 4.2719, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491151515072103e-05, "loss": 4.2703, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490312920321051e-05, "loss": 4.2766, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489474325569999e-05, "loss": 4.2585, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488635730818947e-05, "loss": 4.2628, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487797136067895e-05, "loss": 4.258, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486960179197216e-05, "loss": 4.2506, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486121584446164e-05, "loss": 4.2633, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485282989695112e-05, "loss": 4.2612, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844443949440604e-05, "loss": 4.2563, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836058001930084e-05, "loss": 4.2681, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827672054419564e-05, "loss": 4.2638, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.4819286106909044e-05, "loss": 4.261, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.4810900159398524e-05, "loss": 4.2608, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.4802514211888004e-05, "loss": 4.2695, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479412826437748e-05, "loss": 4.2527, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478574231686696e-05, "loss": 4.262, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477735636935644e-05, "loss": 4.2512, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476900317945338e-05, "loss": 4.2525, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476061723194286e-05, "loss": 4.252, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475223128443234e-05, "loss": 4.2527, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474384533692182e-05, "loss": 4.2573, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.47354593894113e-05, "loss": 4.256, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472707344190078e-05, "loss": 4.2589, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471868749439026e-05, "loss": 4.2532, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471031792568348e-05, "loss": 4.2476, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470193197817295e-05, "loss": 4.2541, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469354603066243e-05, "loss": 4.2445, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468516008315191e-05, "loss": 4.24, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467677413564139e-05, "loss": 4.241, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466838818813087e-05, "loss": 4.2409, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466001861942408e-05, "loss": 4.2514, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4651649050717296e-05, "loss": 4.2547, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.4643263103206776e-05, "loss": 4.247, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4634877155696256e-05, "loss": 4.2432, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.4626491208185736e-05, "loss": 4.2573, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.4618105260675215e-05, "loss": 4.2461, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.4609719313164695e-05, "loss": 4.2456, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.4601333365654175e-05, "loss": 4.2424, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4592947418143655e-05, "loss": 4.2281, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584577849436864e-05, "loss": 4.257, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576191901926344e-05, "loss": 4.2388, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4567805954415824e-05, "loss": 4.2478, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.4559420006905304e-05, "loss": 4.2408, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551034059394784e-05, "loss": 4.2394, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.454266449068799e-05, "loss": 4.2321, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453427854317748e-05, "loss": 4.2444, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452589259566696e-05, "loss": 4.2373, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451752302696017e-05, "loss": 4.2488, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450913707944965e-05, "loss": 4.2376, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450075113193913e-05, "loss": 4.2335, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449236518442861e-05, "loss": 4.2294, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448397923691809e-05, "loss": 4.2459, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.44756096682113e-05, "loss": 4.2238, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446722372070078e-05, "loss": 4.2251, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445883777319026e-05, "loss": 4.2366, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445045182567974e-05, "loss": 4.2376, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444206587816922e-05, "loss": 4.2253, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.44336799306587e-05, "loss": 4.2259, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442529398314818e-05, "loss": 4.2209, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441690803563766e-05, "loss": 4.2424, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.4408538466930874e-05, "loss": 4.2383, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400152519420354e-05, "loss": 4.2343, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.4391766571909834e-05, "loss": 4.2372, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.4383380624399314e-05, "loss": 4.239, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437501105569252e-05, "loss": 4.2426, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.4366625108182e-05, "loss": 4.223, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435823916067148e-05, "loss": 4.2296, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4349853213160956e-05, "loss": 4.2332, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341467265650436e-05, "loss": 4.2167, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333081318139916e-05, "loss": 4.246, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324695370629396e-05, "loss": 4.2268, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431630942311888e-05, "loss": 4.2362, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430793985441209e-05, "loss": 4.2436, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429955390690157e-05, "loss": 4.2219, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429116795939105e-05, "loss": 4.2259, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.428278201188053e-05, "loss": 4.2255, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427439606437001e-05, "loss": 4.2302, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426601011685949e-05, "loss": 4.2325, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.42576405481527e-05, "loss": 4.2313, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424925460064218e-05, "loss": 4.2331, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424086865313166e-05, "loss": 4.2329, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423248270562114e-05, "loss": 4.2234, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422409675811062e-05, "loss": 4.227, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.42157108106001e-05, "loss": 4.2256, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.4207341241893316e-05, "loss": 4.2341, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.4198955294382796e-05, "loss": 4.2261, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.4190569346872276e-05, "loss": 4.2228, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.4182183399361756e-05, "loss": 4.2249, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.4173797451851236e-05, "loss": 4.2255, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165411504340716e-05, "loss": 4.2423, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157041935633925e-05, "loss": 4.2241, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4148655988123405e-05, "loss": 4.222, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140270040612885e-05, "loss": 4.2207, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4131884093102365e-05, "loss": 4.226, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123498145591845e-05, "loss": 4.2016, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411511219808132e-05, "loss": 4.2138, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4106742629374534e-05, "loss": 4.2215, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409835668186402e-05, "loss": 4.2208, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.408998711315723e-05, "loss": 4.2143, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408160116564671e-05, "loss": 4.2109, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407321521813619e-05, "loss": 4.2112, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406482927062567e-05, "loss": 4.2294, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405644332311514e-05, "loss": 4.22, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404805737560462e-05, "loss": 4.2221, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.40396714280941e-05, "loss": 4.2207, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403128548058358e-05, "loss": 4.2303, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402291591187679e-05, "loss": 4.2213, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401452996436627e-05, "loss": 4.21, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400614401685576e-05, "loss": 4.2174, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399775806934524e-05, "loss": 4.2243, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398937212183472e-05, "loss": 4.2072, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.39809861743242e-05, "loss": 4.2115, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397261660561741e-05, "loss": 4.2128, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396423065810689e-05, "loss": 4.2147, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395584471059637e-05, "loss": 4.2129, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394745876308585e-05, "loss": 4.2266, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393907281557533e-05, "loss": 4.1983, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393068686806481e-05, "loss": 4.2142, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392230092055429e-05, "loss": 4.2027, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3913931351847496e-05, "loss": 4.2287, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905545404336976e-05, "loss": 4.2149, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389717583563019e-05, "loss": 4.2207, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388878988811967e-05, "loss": 4.2002, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388040394060915e-05, "loss": 4.2176, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387201799309863e-05, "loss": 4.2231, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386363204558811e-05, "loss": 4.2132, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385524609807759e-05, "loss": 4.2102, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384686015056707e-05, "loss": 4.2177, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383847420305655e-05, "loss": 4.2095, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383010463434976e-05, "loss": 4.2224, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382173506564297e-05, "loss": 4.1992, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381334911813245e-05, "loss": 4.2086, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380496317062193e-05, "loss": 4.2039, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379657722311141e-05, "loss": 4.1988, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.3788207654404625e-05, "loss": 4.2121, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3779821706894105e-05, "loss": 4.206, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771435759383585e-05, "loss": 4.211, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763049811873065e-05, "loss": 4.2077, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.3754663864362545e-05, "loss": 4.2071, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.201841354370117, "eval_runtime": 301.0367, "eval_samples_per_second": 1267.59, "eval_steps_per_second": 39.613, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.3746277916852025e-05, "loss": 4.205, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.3737891969341505e-05, "loss": 4.1918, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372950602183098e-05, "loss": 4.218, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721136453124194e-05, "loss": 4.2026, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.3712750505613674e-05, "loss": 4.2185, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.3704364558103154e-05, "loss": 4.2021, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369597861059263e-05, "loss": 4.1937, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368762542068958e-05, "loss": 4.1927, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367923947317906e-05, "loss": 4.2046, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367085352566854e-05, "loss": 4.209, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366246757815802e-05, "loss": 4.2059, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365409800945123e-05, "loss": 4.2151, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364572844074444e-05, "loss": 4.1961, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363734249323392e-05, "loss": 4.202, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36289565457234e-05, "loss": 4.1966, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362057059821288e-05, "loss": 4.1871, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.3612201029506086e-05, "loss": 4.2007, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.3603815081995566e-05, "loss": 4.1962, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359542913448505e-05, "loss": 4.1951, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358704318697453e-05, "loss": 4.2052, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357865723946401e-05, "loss": 4.2057, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357027129195349e-05, "loss": 4.1997, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356188534444297e-05, "loss": 4.1973, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355351577573618e-05, "loss": 4.2041, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354512982822566e-05, "loss": 4.193, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353674388071514e-05, "loss": 4.2001, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352835793320462e-05, "loss": 4.1905, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.35199719856941e-05, "loss": 4.1923, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351160241698731e-05, "loss": 4.1941, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350321646947679e-05, "loss": 4.1877, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349483052196627e-05, "loss": 4.197, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348644457445575e-05, "loss": 4.1984, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347805862694523e-05, "loss": 4.1967, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.346967267943471e-05, "loss": 4.1915, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346128673192419e-05, "loss": 4.1844, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345290078441367e-05, "loss": 4.2004, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344451483690315e-05, "loss": 4.187, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343612888939263e-05, "loss": 4.1746, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342774294188211e-05, "loss": 4.1842, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.341935699437159e-05, "loss": 4.1796, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.34109874256648e-05, "loss": 4.1891, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340261785695801e-05, "loss": 4.1973, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.339423190944749e-05, "loss": 4.1872, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3385845961936975e-05, "loss": 4.1897, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377460014426455e-05, "loss": 4.1953, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369074066915935e-05, "loss": 4.1843, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336072087701287e-05, "loss": 4.1908, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335233492950235e-05, "loss": 4.1839, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334394898199183e-05, "loss": 4.166, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333556303448131e-05, "loss": 4.1982, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332717708697079e-05, "loss": 4.1804, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.3318807518264e-05, "loss": 4.1919, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331042157075348e-05, "loss": 4.1816, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330203562324296e-05, "loss": 4.1786, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329364967573244e-05, "loss": 4.1774, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328526372822193e-05, "loss": 4.1821, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327689415951514e-05, "loss": 4.1828, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326850821200462e-05, "loss": 4.1889, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.32601222644941e-05, "loss": 4.1812, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325173631698358e-05, "loss": 4.1817, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324335036947306e-05, "loss": 4.1655, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323496442196254e-05, "loss": 4.1922, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322657847445202e-05, "loss": 4.1675, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.32181925269415e-05, "loss": 4.1659, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.320980657943098e-05, "loss": 4.1812, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320142063192046e-05, "loss": 4.1821, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319303468440994e-05, "loss": 4.1644, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.3184665115703146e-05, "loss": 4.1731, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.3176279168192626e-05, "loss": 4.1582, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.3167893220682106e-05, "loss": 4.1904, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.3159507273171586e-05, "loss": 4.1797, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.31511377044648e-05, "loss": 4.179, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314275175695428e-05, "loss": 4.1779, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313436580944376e-05, "loss": 4.1815, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312599624073697e-05, "loss": 4.1892, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311761029322645e-05, "loss": 4.1633, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310922434571593e-05, "loss": 4.1779, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310083839820541e-05, "loss": 4.1764, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.3092452450694884e-05, "loss": 4.1616, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.3084066503184364e-05, "loss": 4.1829, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3075680555673844e-05, "loss": 4.1774, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306729460816333e-05, "loss": 4.1788, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305890866065281e-05, "loss": 4.1894, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305053909194602e-05, "loss": 4.1666, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.30421531444355e-05, "loss": 4.1716, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.303376719692498e-05, "loss": 4.1675, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.302538124941446e-05, "loss": 4.1753, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.301699530190394e-05, "loss": 4.1766, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300860935439342e-05, "loss": 4.1775, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.30002234068829e-05, "loss": 4.1737, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299183745937238e-05, "loss": 4.1804, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298346789066559e-05, "loss": 4.1696, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.29750983219588e-05, "loss": 4.172, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2966712374448285e-05, "loss": 4.1739, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958326426937765e-05, "loss": 4.1772, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2949940479427244e-05, "loss": 4.1758, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.2941554531916724e-05, "loss": 4.1644, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.2933168584406204e-05, "loss": 4.1734, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.2924782636895684e-05, "loss": 4.1722, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.2916396689385164e-05, "loss": 4.1815, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290802712067837e-05, "loss": 4.1699, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289964117316785e-05, "loss": 4.1682, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289125522565733e-05, "loss": 4.1632, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288286927814681e-05, "loss": 4.1781, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287448333063629e-05, "loss": 4.1468, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.2866097383125766e-05, "loss": 4.1636, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285772781441898e-05, "loss": 4.1672, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284934186690847e-05, "loss": 4.1632, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284095591939795e-05, "loss": 4.1626, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283256997188742e-05, "loss": 4.1587, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.28241840243769e-05, "loss": 4.1607, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.281579807686638e-05, "loss": 4.1749, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.280741212935586e-05, "loss": 4.1689, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.279902618184534e-05, "loss": 4.165, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279065661313855e-05, "loss": 4.1714, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278227066562803e-05, "loss": 4.1768, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277390109692124e-05, "loss": 4.1696, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276551514941072e-05, "loss": 4.1562, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275712920190021e-05, "loss": 4.1667, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274874325438969e-05, "loss": 4.1687, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274035730687917e-05, "loss": 4.1529, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2731987738172376e-05, "loss": 4.158, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.2723601790661856e-05, "loss": 4.1643, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.2715215843151336e-05, "loss": 4.1616, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2706829895640816e-05, "loss": 4.1615, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.2698460326934025e-05, "loss": 4.1726, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.2690074379423505e-05, "loss": 4.1495, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.2681688431912985e-05, "loss": 4.1614, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.2673318863206194e-05, "loss": 4.155, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.2664932915695674e-05, "loss": 4.1737, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.2656546968185154e-05, "loss": 4.1644, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264816102067464e-05, "loss": 4.1683, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.263977507316412e-05, "loss": 4.1534, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.26313891256536e-05, "loss": 4.1662, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.262300317814308e-05, "loss": 4.1708, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261461723063256e-05, "loss": 4.1624, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260624766192577e-05, "loss": 4.1616, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259786171441525e-05, "loss": 4.1651, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258947576690473e-05, "loss": 4.1589, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258108981939421e-05, "loss": 4.174, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257273662949115e-05, "loss": 4.1495, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256435068198063e-05, "loss": 4.1609, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255596473447011e-05, "loss": 4.149, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2547578786959594e-05, "loss": 4.1508, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539192839449074e-05, "loss": 4.1643, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.2530806891938554e-05, "loss": 4.1519, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.2522420944428034e-05, "loss": 4.1678, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2514034996917514e-05, "loss": 4.1509, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.2505649049406994e-05, "loss": 4.1635, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.160358428955078, "eval_runtime": 296.2181, "eval_samples_per_second": 1288.21, "eval_steps_per_second": 40.258, "step": 457920 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.881850522548004e+17, "trial_name": null, "trial_params": null }