diff --git "a/checkpoint-1068480/trainer_state.json" "b/checkpoint-1068480/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1068480/trainer_state.json" @@ -0,0 +1,12653 @@ +{ + "best_metric": 4.029951572418213, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/lstm/2/checkpoints/checkpoint-1068480", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1068480, + "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 + }, + { + "epoch": 0.0, + "learning_rate": 4.24972794807002e-05, + "loss": 4.1688, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248889353318968e-05, + "loss": 4.1405, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248050758567916e-05, + "loss": 4.1641, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247212163816864e-05, + "loss": 4.1575, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246373569065812e-05, + "loss": 4.167, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.24553497431476e-05, + "loss": 4.1537, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446963795637076e-05, + "loss": 4.1437, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243857784812656e-05, + "loss": 4.1461, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243019190061604e-05, + "loss": 4.1551, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242180595310552e-05, + "loss": 4.1595, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413420005595e-05, + "loss": 4.1575, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240503405808448e-05, + "loss": 4.1649, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239666448937769e-05, + "loss": 4.1516, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238827854186717e-05, + "loss": 4.1536, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237989259435665e-05, + "loss": 4.1465, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237150664684613e-05, + "loss": 4.1359, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236312069933561e-05, + "loss": 4.1559, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235473475182509e-05, + "loss": 4.1459, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234634880431457e-05, + "loss": 4.1489, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233796285680405e-05, + "loss": 4.1553, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232959328809726e-05, + "loss": 4.16, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232120734058675e-05, + "loss": 4.1522, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231282139307623e-05, + "loss": 4.1489, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230443544556571e-05, + "loss": 4.1539, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229604949805519e-05, + "loss": 4.1498, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287679929348396e-05, + "loss": 4.1519, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279293981837876e-05, + "loss": 4.1421, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270908034327356e-05, + "loss": 4.1459, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262522086816836e-05, + "loss": 4.1488, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254152518110045e-05, + "loss": 4.1444, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245766570599525e-05, + "loss": 4.1454, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237380623089005e-05, + "loss": 4.1485, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228994675578485e-05, + "loss": 4.1499, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220608728067965e-05, + "loss": 4.1484, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212222780557445e-05, + "loss": 4.1386, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220386959065439e-05, + "loss": 4.1481, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219548364314387e-05, + "loss": 4.1443, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218709769563335e-05, + "loss": 4.1297, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217871174812283e-05, + "loss": 4.1355, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217032580061231e-05, + "loss": 4.1344, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216193985310179e-05, + "loss": 4.1403, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215355390559126e-05, + "loss": 4.1484, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214516795808074e-05, + "loss": 4.1414, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213678201057022e-05, + "loss": 4.1459, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.21283960630597e-05, + "loss": 4.1501, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212002649435292e-05, + "loss": 4.1385, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.21116405468424e-05, + "loss": 4.1437, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210325459933188e-05, + "loss": 4.1405, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209486865182136e-05, + "loss": 4.1142, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208648270431084e-05, + "loss": 4.158, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207809675680032e-05, + "loss": 4.135, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.20697108092898e-05, + "loss": 4.1531, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206132486177928e-05, + "loss": 4.1314, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052971671876216e-05, + "loss": 4.1379, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044585724365696e-05, + "loss": 4.1302, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036199776855176e-05, + "loss": 4.1344, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027813829344656e-05, + "loss": 4.1383, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019427881834136e-05, + "loss": 4.146, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011041934323616e-05, + "loss": 4.1427, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.20026559868131e-05, + "loss": 4.131, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199427003930258e-05, + "loss": 4.1217, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198590047059579e-05, + "loss": 4.1525, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197751452308527e-05, + "loss": 4.1185, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196912857557475e-05, + "loss": 4.1184, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196074262806423e-05, + "loss": 4.1362, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195235668055371e-05, + "loss": 4.1431, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194398711184692e-05, + "loss": 4.117, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.19356011643364e-05, + "loss": 4.1302, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192723159562961e-05, + "loss": 4.118, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191884564811909e-05, + "loss": 4.1421, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191045970060857e-05, + "loss": 4.1372, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902073753098057e-05, + "loss": 4.1368, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893687805587537e-05, + "loss": 4.131, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885301858077017e-05, + "loss": 4.138, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876932289370226e-05, + "loss": 4.1483, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868562720663435e-05, + "loss": 4.1164, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860176773152915e-05, + "loss": 4.1346, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851790825642395e-05, + "loss": 4.1352, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843404878131875e-05, + "loss": 4.1187, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835018930621355e-05, + "loss": 4.1366, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826632983110834e-05, + "loss": 4.1364, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818247035600314e-05, + "loss": 4.1372, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809861088089794e-05, + "loss": 4.1472, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801475140579274e-05, + "loss": 4.1203, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793089193068754e-05, + "loss": 4.1278, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784703245558234e-05, + "loss": 4.1252, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776317298047714e-05, + "loss": 4.1327, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176794772934093e-05, + "loss": 4.132, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.17595617818304e-05, + "loss": 4.1395, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175117583431988e-05, + "loss": 4.1237, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174278988680936e-05, + "loss": 4.1415, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173440393929884e-05, + "loss": 4.1294, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172603437059205e-05, + "loss": 4.1295, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171766480188527e-05, + "loss": 4.1317, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170927885437475e-05, + "loss": 4.1329, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170089290686423e-05, + "loss": 4.1374, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1202, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168412101184319e-05, + "loss": 4.1289, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167573506433267e-05, + "loss": 4.1328, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166734911682215e-05, + "loss": 4.1366, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165897954811536e-05, + "loss": 4.1312, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165059360060484e-05, + "loss": 4.1253, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164220765309432e-05, + "loss": 4.1264, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16338217055838e-05, + "loss": 4.1344, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162543575807328e-05, + "loss": 4.1047, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161704981056276e-05, + "loss": 4.1222, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1608680241855966e-05, + "loss": 4.1247, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600294294345446e-05, + "loss": 4.1235, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1591908346834926e-05, + "loss": 4.1178, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158352239932441e-05, + "loss": 4.1215, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157513645181389e-05, + "loss": 4.1193, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1319, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.13, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155001136688979e-05, + "loss": 4.1212, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154162541937927e-05, + "loss": 4.1286, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153323947186875e-05, + "loss": 4.137, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152485352435823e-05, + "loss": 4.1319, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151646757684771e-05, + "loss": 4.1148, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150808162933719e-05, + "loss": 4.1227, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149969568182667e-05, + "loss": 4.1292, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149130973431615e-05, + "loss": 4.1104, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482940165609366e-05, + "loss": 4.1182, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474554218098846e-05, + "loss": 4.126, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466184649392055e-05, + "loss": 4.1177, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457798701881535e-05, + "loss": 4.124, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449412754371015e-05, + "loss": 4.132, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441026806860495e-05, + "loss": 4.1132, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432640859349975e-05, + "loss": 4.1179, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424254911839455e-05, + "loss": 4.1205, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415868964328935e-05, + "loss": 4.1325, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140748301681841e-05, + "loss": 4.1243, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399113448111624e-05, + "loss": 4.1289, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390727500601104e-05, + "loss": 4.1141, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382341553090584e-05, + "loss": 4.1265, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373955605580064e-05, + "loss": 4.1319, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365569658069544e-05, + "loss": 4.122, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135720008936276e-05, + "loss": 4.1242, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134881414185223e-05, + "loss": 4.1221, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134042819434171e-05, + "loss": 4.12, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133204224683119e-05, + "loss": 4.1335, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132365629932067e-05, + "loss": 4.1126, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131527035181015e-05, + "loss": 4.1195, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130688440429963e-05, + "loss": 4.1119, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129849845678911e-05, + "loss": 4.1106, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129011250927859e-05, + "loss": 4.1205, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.12817429405718e-05, + "loss": 4.1159, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127335699306129e-05, + "loss": 4.1267, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649874243545e-05, + "loss": 4.1141, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1256617855647707e-05, + "loss": 4.1272, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.129605293273926, + "eval_runtime": 277.9176, + "eval_samples_per_second": 1373.036, + "eval_steps_per_second": 42.908, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248231908137186e-05, + "loss": 4.1132, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1239845960626666e-05, + "loss": 4.1041, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231460013116146e-05, + "loss": 4.125, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223074065605626e-05, + "loss": 4.1167, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214688118095106e-05, + "loss": 4.1251, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206302170584586e-05, + "loss": 4.1164, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197916223074066e-05, + "loss": 4.1092, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1189530275563546e-05, + "loss": 4.11, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181144328053026e-05, + "loss": 4.1166, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1172758380542506e-05, + "loss": 4.1202, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1164372433031986e-05, + "loss": 4.1176, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.11560028643252e-05, + "loss": 4.1258, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114763329561841e-05, + "loss": 4.1131, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113924734810789e-05, + "loss": 4.1139, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113086140059737e-05, + "loss": 4.1109, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112247545308685e-05, + "loss": 4.0989, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111408950557633e-05, + "loss": 4.1171, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110570355806581e-05, + "loss": 4.1106, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109731761055529e-05, + "loss": 4.112, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.10889480418485e-05, + "loss": 4.1107, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108056209433798e-05, + "loss": 4.1295, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107217614682746e-05, + "loss": 4.1151, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106379019931694e-05, + "loss": 4.1107, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105540425180642e-05, + "loss": 4.1131, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10470183042959e-05, + "loss": 4.1111, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103863235678538e-05, + "loss": 4.1123, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103024640927486e-05, + "loss": 4.1093, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102187684056807e-05, + "loss": 4.1106, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101349089305755e-05, + "loss": 4.1071, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005121324350764e-05, + "loss": 4.1026, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996735376840244e-05, + "loss": 4.1076, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098834942932972e-05, + "loss": 4.1139, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.09799634818192e-05, + "loss": 4.114, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097157753430868e-05, + "loss": 4.1115, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096319158679816e-05, + "loss": 4.104, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095482201809137e-05, + "loss": 4.1078, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094643607058085e-05, + "loss": 4.1088, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093805012307033e-05, + "loss": 4.0964, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092966417555981e-05, + "loss": 4.0985, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092129460685302e-05, + "loss": 4.0972, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.09129086593425e-05, + "loss": 4.1068, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090453909063572e-05, + "loss": 4.1104, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089615314312519e-05, + "loss": 4.1024, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088776719561467e-05, + "loss": 4.1143, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087938124810415e-05, + "loss": 4.1106, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087099530059363e-05, + "loss": 4.1015, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086260935308311e-05, + "loss": 4.1093, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08542234055726e-05, + "loss": 4.1041, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084583745806208e-05, + "loss": 4.0817, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083745151055156e-05, + "loss": 4.1167, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082906556304104e-05, + "loss": 4.0974, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082067961553052e-05, + "loss": 4.1154, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081229366802e-05, + "loss": 4.0985, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080392409931321e-05, + "loss": 4.101, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079553815180269e-05, + "loss": 4.0945, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078715220429217e-05, + "loss": 4.0977, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778766256781647e-05, + "loss": 4.1056, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770380309271127e-05, + "loss": 4.1072, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762010740564336e-05, + "loss": 4.1052, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753624793053816e-05, + "loss": 4.1004, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074525522434703e-05, + "loss": 4.0867, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073686927683651e-05, + "loss": 4.1165, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072848332932599e-05, + "loss": 4.0859, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072009738181547e-05, + "loss": 4.0776, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071171143430495e-05, + "loss": 4.1019, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070332548679443e-05, + "loss": 4.108, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069495591808764e-05, + "loss": 4.0845, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068656997057712e-05, + "loss": 4.0967, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.06781840230666e-05, + "loss": 4.08, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066979807555608e-05, + "loss": 4.1057, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661412128045553e-05, + "loss": 4.1037, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065302618053503e-05, + "loss": 4.0996, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064464023302452e-05, + "loss": 4.0986, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636254285514e-05, + "loss": 4.1029, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062788471680721e-05, + "loss": 4.112, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619515148100425e-05, + "loss": 4.0841, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611129200589905e-05, + "loss": 4.1007, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060274325307938e-05, + "loss": 4.0949, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059435730556886e-05, + "loss": 4.0895, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058597135805834e-05, + "loss": 4.0999, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057758541054782e-05, + "loss": 4.1038, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05691994630373e-05, + "loss": 4.0989, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056081351552678e-05, + "loss": 4.1153, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055242756801626e-05, + "loss": 4.0864, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544057999309474e-05, + "loss": 4.0896, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535672051798954e-05, + "loss": 4.0927, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527286104288434e-05, + "loss": 4.1003, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518900156777914e-05, + "loss": 4.0947, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051054696687485e-05, + "loss": 4.1082, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050216101936433e-05, + "loss": 4.0898, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049377507185381e-05, + "loss": 4.1087, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048538912434329e-05, + "loss": 4.1001, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047700317683277e-05, + "loss": 4.0918, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046863360812598e-05, + "loss": 4.0972, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046024766061546e-05, + "loss": 4.1013, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045186171310494e-05, + "loss": 4.1041, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044347576559443e-05, + "loss": 4.0888, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043508981808391e-05, + "loss": 4.0923, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042670387057339e-05, + "loss": 4.0976, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041831792306287e-05, + "loss": 4.1049, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040993197555235e-05, + "loss": 4.0989, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0401562406845556e-05, + "loss": 4.0903, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393176459335036e-05, + "loss": 4.0938, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0384790511824516e-05, + "loss": 4.101, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376420943117725e-05, + "loss": 4.0697, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368051374410934e-05, + "loss": 4.0897, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0359665426900414e-05, + "loss": 4.089, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351279479389894e-05, + "loss": 4.0942, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342893531879374e-05, + "loss": 4.0822, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033450758436886e-05, + "loss": 4.0906, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032612163685834e-05, + "loss": 4.0898, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031773568934782e-05, + "loss": 4.0948, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.03093497418373e-05, + "loss": 4.0945, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030096379432678e-05, + "loss": 4.0906, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029257784681626e-05, + "loss": 4.0963, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028420827810947e-05, + "loss": 4.1038, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027582233059895e-05, + "loss": 4.0956, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026743638308843e-05, + "loss": 4.0824, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025905043557791e-05, + "loss": 4.0913, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025066448806738e-05, + "loss": 4.0976, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024227854055686e-05, + "loss": 4.0779, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233925350653815e-05, + "loss": 4.088, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225539403143295e-05, + "loss": 4.0914, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217153455632775e-05, + "loss": 4.0861, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208767508122255e-05, + "loss": 4.0875, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200397939415464e-05, + "loss": 4.0984, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192011991904944e-05, + "loss": 4.0836, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183626044394424e-05, + "loss": 4.0851, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175240096883904e-05, + "loss": 4.0845, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166854149373383e-05, + "loss": 4.1033, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015846820186286e-05, + "loss": 4.0894, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015008225435234e-05, + "loss": 4.0984, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141696306841817e-05, + "loss": 4.0796, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133310359331297e-05, + "loss": 4.0945, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012492441182078e-05, + "loss": 4.0967, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011653846431026e-05, + "loss": 4.0917, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010815251679974e-05, + "loss": 4.091, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009978294809295e-05, + "loss": 4.0908, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009139700058243e-05, + "loss": 4.0876, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008301105307191e-05, + "loss": 4.101, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007462510556139e-05, + "loss": 4.0819, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.00662555368546e-05, + "loss": 4.0888, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005786958934408e-05, + "loss": 4.084, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004948364183356e-05, + "loss": 4.0799, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004109769432304e-05, + "loss": 4.0827, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003271174681252e-05, + "loss": 4.084, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002434217810574e-05, + "loss": 4.097, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001595623059522e-05, + "loss": 4.0832, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00075702830847e-05, + "loss": 4.0932, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.106261730194092, + "eval_runtime": 278.2488, + "eval_samples_per_second": 1371.402, + "eval_steps_per_second": 42.857, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999918433557418e-05, + "loss": 4.0902, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999079838806366e-05, + "loss": 4.073, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998241244055314e-05, + "loss": 4.0945, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997402649304262e-05, + "loss": 4.0881, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.99656405455321e-05, + "loss": 4.0931, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957254598021577e-05, + "loss": 4.0845, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994886865051105e-05, + "loss": 4.0838, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994048270300053e-05, + "loss": 4.0744, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993209675549001e-05, + "loss": 4.0832, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992371080797949e-05, + "loss": 4.0913, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991532486046897e-05, + "loss": 4.0846, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990693891295845e-05, + "loss": 4.0926, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898569344251665e-05, + "loss": 4.092, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890183396741145e-05, + "loss": 4.0754, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881797449230625e-05, + "loss": 4.0754, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873411501720105e-05, + "loss": 4.0734, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865025554209585e-05, + "loss": 4.0849, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856639606699065e-05, + "loss": 4.0809, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848253659188545e-05, + "loss": 4.076, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839867711678025e-05, + "loss": 4.083, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831481764167505e-05, + "loss": 4.095, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823095816656985e-05, + "loss": 4.0849, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981470986914646e-05, + "loss": 4.0837, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980632392163594e-05, + "loss": 4.0811, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979797073173288e-05, + "loss": 4.083, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978958478422237e-05, + "loss": 4.0828, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978119883671185e-05, + "loss": 4.0743, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977281288920133e-05, + "loss": 4.0862, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976442694169081e-05, + "loss": 4.0766, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975604099418029e-05, + "loss": 4.0707, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974765504666976e-05, + "loss": 4.08, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973926909915924e-05, + "loss": 4.0782, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973088315164872e-05, + "loss": 4.0832, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972251358294193e-05, + "loss": 4.0844, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971412763543141e-05, + "loss": 4.0729, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970575806672463e-05, + "loss": 4.077, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969737211921411e-05, + "loss": 4.0825, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968898617170359e-05, + "loss": 4.0622, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968060022419307e-05, + "loss": 4.0715, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967221427668255e-05, + "loss": 4.0681, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966382832917203e-05, + "loss": 4.0718, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965544238166151e-05, + "loss": 4.0791, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964705643415099e-05, + "loss": 4.075, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638686865444197e-05, + "loss": 4.0871, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630317296737406e-05, + "loss": 4.0755, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621931349226886e-05, + "loss": 4.0779, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613545401716366e-05, + "loss": 4.0776, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605159454205845e-05, + "loss": 4.075, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596773506695325e-05, + "loss": 4.0499, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958840393798854e-05, + "loss": 4.0878, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958001799047802e-05, + "loss": 4.0702, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95716320429675e-05, + "loss": 4.0845, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956324609545698e-05, + "loss": 4.069, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955486014794646e-05, + "loss": 4.0712, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954647420043594e-05, + "loss": 4.0602, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953808825292542e-05, + "loss": 4.0696, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.95297023054149e-05, + "loss": 4.0791, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952131635790438e-05, + "loss": 4.0703, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951296316800132e-05, + "loss": 4.0773, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95045772204908e-05, + "loss": 4.0757, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949619127298028e-05, + "loss": 4.0514, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.0857, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479419377959246e-05, + "loss": 4.0615, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471033430448726e-05, + "loss": 4.0511, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.0755, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454261535427686e-05, + "loss": 4.0716, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9445875587917166e-05, + "loss": 4.0559, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437506019210375e-05, + "loss": 4.0671, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429120071699855e-05, + "loss": 4.0561, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420750502993064e-05, + "loss": 4.0726, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412364555482544e-05, + "loss": 4.0749, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403978607972024e-05, + "loss": 4.0698, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395592660461504e-05, + "loss": 4.0719, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.0718, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378820765440464e-05, + "loss": 4.0826, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370434817929943e-05, + "loss": 4.056, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362048870419423e-05, + "loss": 4.0692, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935367930171264e-05, + "loss": 4.0662, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934529335420212e-05, + "loss": 4.0624, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933690740669159e-05, + "loss": 4.0722, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932853783798481e-05, + "loss": 4.0729, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932015189047429e-05, + "loss": 4.0714, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931176594296377e-05, + "loss": 4.0842, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930337999545324e-05, + "loss": 4.0573, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929499404794272e-05, + "loss": 4.0627, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928662447923594e-05, + "loss": 4.0632, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927823853172542e-05, + "loss": 4.0715, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.92698525842149e-05, + "loss": 4.0647, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926148301550811e-05, + "loss": 4.0754, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925309706799759e-05, + "loss": 4.0653, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9244711120487066e-05, + "loss": 4.0762, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236325172976546e-05, + "loss": 4.0691, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9227939225466026e-05, + "loss": 4.0652, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219553277955506e-05, + "loss": 4.0699, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211167330444986e-05, + "loss": 4.0705, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202797761738195e-05, + "loss": 4.0758, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194411814227675e-05, + "loss": 4.0627, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186025866717155e-05, + "loss": 4.0608, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9177639919206635e-05, + "loss": 4.0723, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169253971696115e-05, + "loss": 4.0786, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608680241856e-05, + "loss": 4.0694, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915248207667508e-05, + "loss": 4.0667, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914409612916456e-05, + "loss": 4.0651, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913571018165404e-05, + "loss": 4.0724, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912732423414352e-05, + "loss": 4.0449, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118938286633e-05, + "loss": 4.0648, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911055233912248e-05, + "loss": 4.0502, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910218277041569e-05, + "loss": 4.0655, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909379682290517e-05, + "loss": 4.0584, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908541087539465e-05, + "loss": 4.0672, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907702492788413e-05, + "loss": 4.0589, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068638980373604e-05, + "loss": 4.0689, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906026941166682e-05, + "loss": 4.0669, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.90518834641563e-05, + "loss": 4.0637, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043497516645786e-05, + "loss": 4.0691, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903511156913526e-05, + "loss": 4.0722, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026742000428475e-05, + "loss": 4.0696, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018372431721684e-05, + "loss": 4.0602, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009986484211164e-05, + "loss": 4.0589, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001600536700644e-05, + "loss": 4.0708, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993214589190124e-05, + "loss": 4.0566, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898484502048333e-05, + "loss": 4.0584, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897645907297281e-05, + "loss": 4.0616, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896807312546229e-05, + "loss": 4.0591, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895968717795177e-05, + "loss": 4.058, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895130123044125e-05, + "loss": 4.0734, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894293166173447e-05, + "loss": 4.0562, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893454571422395e-05, + "loss": 4.0595, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892615976671343e-05, + "loss": 4.057, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89177738192029e-05, + "loss": 4.0744, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890938787169238e-05, + "loss": 4.0649, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.89010183029856e-05, + "loss": 4.0661, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889263235547508e-05, + "loss": 4.0569, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888424640796455e-05, + "loss": 4.0701, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887586046045403e-05, + "loss": 4.0703, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886747451294351e-05, + "loss": 4.0674, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0652, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885071899672621e-05, + "loss": 4.0568, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884233304921569e-05, + "loss": 4.0633, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833947101705167e-05, + "loss": 4.0749, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825561154194647e-05, + "loss": 4.0546, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817175206684127e-05, + "loss": 4.0612, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808805637977336e-05, + "loss": 4.0594, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800419690466816e-05, + "loss": 4.0552, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792033742956296e-05, + "loss": 4.0529, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0575, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775278226738985e-05, + "loss": 4.0667, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766892279228465e-05, + "loss": 4.0607, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758506331717944e-05, + "loss": 4.0641, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.086506366729736, + "eval_runtime": 298.4361, + "eval_samples_per_second": 1278.635, + "eval_steps_per_second": 39.958, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875012038420743e-05, + "loss": 4.0507, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874173443669691e-05, + "loss": 4.049, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873334848918639e-05, + "loss": 4.0654, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872496254167587e-05, + "loss": 4.0595, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871657659416535e-05, + "loss": 4.0693, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870820702545856e-05, + "loss": 4.0569, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869983745675177e-05, + "loss": 4.0573, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869145150924125e-05, + "loss": 4.0465, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868306556173073e-05, + "loss": 4.0568, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867467961422021e-05, + "loss": 4.0642, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866629366670969e-05, + "loss": 4.0577, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865790771919917e-05, + "loss": 4.0656, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864953815049238e-05, + "loss": 4.0688, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641152202981865e-05, + "loss": 4.0479, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632766255471345e-05, + "loss": 4.0493, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624380307960825e-05, + "loss": 4.0464, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615994360450305e-05, + "loss": 4.0616, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607608412939785e-05, + "loss": 4.0504, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599222465429265e-05, + "loss": 4.0538, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859083651791874e-05, + "loss": 4.0565, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582466949211954e-05, + "loss": 4.067, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574081001701434e-05, + "loss": 4.0599, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565695054190914e-05, + "loss": 4.0574, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855730910668039e-05, + "loss": 4.055, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854892315916987e-05, + "loss": 4.057, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854055359046308e-05, + "loss": 4.0594, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85321840217563e-05, + "loss": 4.0432, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852379807424578e-05, + "loss": 4.0612, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851541212673526e-05, + "loss": 4.0496, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850702617922474e-05, + "loss": 4.0447, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849864023171421e-05, + "loss": 4.0574, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849025428420369e-05, + "loss": 4.0522, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848186833669317e-05, + "loss": 4.0523, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847348238918265e-05, + "loss": 4.0619, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846511282047586e-05, + "loss": 4.047, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8456743251769076e-05, + "loss": 4.0512, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8448357304258556e-05, + "loss": 4.0569, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8439971356748036e-05, + "loss": 4.034, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8431585409237516e-05, + "loss": 4.0478, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423199461726996e-05, + "loss": 4.0451, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414813514216476e-05, + "loss": 4.0458, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8406427566705956e-05, + "loss": 4.0546, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398041619195436e-05, + "loss": 4.0466, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8389672050488645e-05, + "loss": 4.0598, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381286102978125e-05, + "loss": 4.0507, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372900155467605e-05, + "loss": 4.0546, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8364514207957085e-05, + "loss": 4.0509, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356144639250294e-05, + "loss": 4.0498, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8347758691739774e-05, + "loss": 4.0297, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339372744229254e-05, + "loss": 4.056, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833100317552247e-05, + "loss": 4.0451, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832261722801195e-05, + "loss": 4.061, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831423128050143e-05, + "loss": 4.0423, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830584533299091e-05, + "loss": 4.0473, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829745938548039e-05, + "loss": 4.0357, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828907343796987e-05, + "loss": 4.0448, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828068749045935e-05, + "loss": 4.0545, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827231792175256e-05, + "loss": 4.0439, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826393197424204e-05, + "loss": 4.0562, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825554602673152e-05, + "loss": 4.0501, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247160079221e-05, + "loss": 4.0238, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823877413171048e-05, + "loss": 4.0599, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823038818419996e-05, + "loss": 4.0363, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822200223668944e-05, + "loss": 4.0311, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213616289178925e-05, + "loss": 4.0472, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205246720472134e-05, + "loss": 4.0503, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819687715176534e-05, + "loss": 4.0326, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818849120425482e-05, + "loss": 4.0413, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.81801052567443e-05, + "loss": 4.03, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817171930923378e-05, + "loss": 4.0492, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816333336172326e-05, + "loss": 4.0501, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815494741421274e-05, + "loss": 4.0409, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814656146670222e-05, + "loss": 4.0499, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138175519191696e-05, + "loss": 4.0466, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129789571681176e-05, + "loss": 4.0586, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812142000297439e-05, + "loss": 4.0362, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811303405546387e-05, + "loss": 4.0432, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810466448675709e-05, + "loss": 4.0423, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809627853924657e-05, + "loss": 4.0392, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808789259173605e-05, + "loss": 4.0438, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807950664422552e-05, + "loss": 4.045, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071120696715e-05, + "loss": 4.0514, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806273474920448e-05, + "loss": 4.0581, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805434880169396e-05, + "loss": 4.0399, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804596285418344e-05, + "loss": 4.0364, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803759328547665e-05, + "loss": 4.0366, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029223716769866e-05, + "loss": 4.0484, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020837769259346e-05, + "loss": 4.0409, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8012451821748826e-05, + "loss": 4.0453, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004065874238306e-05, + "loss": 4.0499, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995679926727786e-05, + "loss": 4.0485, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987293979217266e-05, + "loss": 4.0444, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978908031706746e-05, + "loss": 4.0406, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7970538462999955e-05, + "loss": 4.0488, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962152515489435e-05, + "loss": 4.0479, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953766567978915e-05, + "loss": 4.0512, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945380620468395e-05, + "loss": 4.0345, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7936994672957874e-05, + "loss": 4.0416, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928608725447354e-05, + "loss": 4.0462, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920239156740564e-05, + "loss": 4.0548, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791185320923005e-05, + "loss": 4.0463, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790346726171953e-05, + "loss": 4.0428, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789508131420901e-05, + "loss": 4.0421, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788669536669849e-05, + "loss": 4.0463, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787830941918797e-05, + "loss": 4.0244, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786992347167745e-05, + "loss": 4.0364, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786153752416693e-05, + "loss": 4.0285, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785316795546014e-05, + "loss": 4.0442, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784478200794962e-05, + "loss": 4.0367, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.78363960604391e-05, + "loss": 4.0386, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782802649173231e-05, + "loss": 4.0361, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781964054422179e-05, + "loss": 4.0411, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781125459671127e-05, + "loss": 4.045, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780286864920075e-05, + "loss": 4.0393, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7794482701690235e-05, + "loss": 4.0468, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778609675417971e-05, + "loss": 4.0472, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777727185472924e-05, + "loss": 4.0429, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769341237962404e-05, + "loss": 4.0426, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7760955290451884e-05, + "loss": 4.0326, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775258572174509e-05, + "loss": 4.0436, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774419977423457e-05, + "loss": 4.0403, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773581382672405e-05, + "loss": 4.0283, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727427879213526e-05, + "loss": 4.0391, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719041931703006e-05, + "loss": 4.0356, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7710655984192486e-05, + "loss": 4.0385, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770227003668197e-05, + "loss": 4.047, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769388408917145e-05, + "loss": 4.0354, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768549814166093e-05, + "loss": 4.0357, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767712857295414e-05, + "loss": 4.0341, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766874262544362e-05, + "loss": 4.0492, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.76603566779331e-05, + "loss": 4.0407, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765197073042258e-05, + "loss": 4.0446, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764358478291206e-05, + "loss": 4.028, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763519883540154e-05, + "loss": 4.051, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762681288789102e-05, + "loss": 4.045, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761844331918423e-05, + "loss": 4.0448, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761005737167371e-05, + "loss": 4.0411, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760167142416319e-05, + "loss": 4.0371, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759328547665267e-05, + "loss": 4.0361, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758489952914215e-05, + "loss": 4.0569, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757651358163164e-05, + "loss": 4.0286, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756812763412112e-05, + "loss": 4.04, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75597416866106e-05, + "loss": 4.0371, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7551372117903806e-05, + "loss": 4.0265, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542986170393286e-05, + "loss": 4.032, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534616601686495e-05, + "loss": 4.036, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526230654175975e-05, + "loss": 4.0433, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517844706665455e-05, + "loss": 4.0387, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509458759154935e-05, + "loss": 4.0384, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.070992469787598, + "eval_runtime": 299.2538, + "eval_samples_per_second": 1275.142, + "eval_steps_per_second": 39.849, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501089190448144e-05, + "loss": 4.0383, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492703242937624e-05, + "loss": 4.0264, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484317295427104e-05, + "loss": 4.0438, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747593134791659e-05, + "loss": 4.04, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746754540040607e-05, + "loss": 4.0438, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459159452895544e-05, + "loss": 4.037, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7450773505385024e-05, + "loss": 4.0333, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7442387557874504e-05, + "loss": 4.0252, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434001610363984e-05, + "loss": 4.0295, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425615662853463e-05, + "loss": 4.0437, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417229715342943e-05, + "loss": 4.0371, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408843767832423e-05, + "loss": 4.0455, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740047419912563e-05, + "loss": 4.0442, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739208825161511e-05, + "loss": 4.0253, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738370230410459e-05, + "loss": 4.0233, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737531635659407e-05, + "loss": 4.0238, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736693040908356e-05, + "loss": 4.0413, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735854446157304e-05, + "loss": 4.0291, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735015851406252e-05, + "loss": 4.029, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341772566552e-05, + "loss": 4.032, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733338661904148e-05, + "loss": 4.0446, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732500067153096e-05, + "loss": 4.0353, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731663110282417e-05, + "loss": 4.0387, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730824515531365e-05, + "loss": 4.032, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729985920780313e-05, + "loss": 4.0363, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.72914732602926e-05, + "loss": 4.0344, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728308731278208e-05, + "loss": 4.0201, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.72747177440753e-05, + "loss": 4.0387, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726633179656478e-05, + "loss": 4.0249, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725794584905426e-05, + "loss": 4.0206, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724955990154374e-05, + "loss": 4.0392, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724117395403322e-05, + "loss": 4.0301, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72327880065227e-05, + "loss": 4.0311, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722443481661964e-05, + "loss": 4.0402, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721604886910912e-05, + "loss": 4.0246, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.72076629215986e-05, + "loss": 4.0329, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199276974088075e-05, + "loss": 4.0336, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190891026577555e-05, + "loss": 4.0106, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182505079067035e-05, + "loss": 4.0254, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174119131556515e-05, + "loss": 4.022, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165733184045995e-05, + "loss": 4.0224, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715734723653548e-05, + "loss": 4.0341, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714896128902496e-05, + "loss": 4.027, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714057534151444e-05, + "loss": 4.0378, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713220577280765e-05, + "loss": 4.0295, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712381982529713e-05, + "loss": 4.0307, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711543387778661e-05, + "loss": 4.029, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710704793027609e-05, + "loss": 4.0274, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709866198276557e-05, + "loss": 4.0076, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709029241405878e-05, + "loss": 4.0351, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708190646654826e-05, + "loss": 4.0241, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707352051903774e-05, + "loss": 4.0384, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706513457152722e-05, + "loss": 4.0233, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.70567486240167e-05, + "loss": 4.0191, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704836267650618e-05, + "loss": 4.0197, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703997672899566e-05, + "loss": 4.0203, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031607160288875e-05, + "loss": 4.0324, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023221212778355e-05, + "loss": 4.021, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014851644071564e-05, + "loss": 4.0367, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006465696561044e-05, + "loss": 4.0316, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998079749050524e-05, + "loss": 4.0001, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989693801540004e-05, + "loss": 4.0412, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981307854029484e-05, + "loss": 4.0158, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972921906518964e-05, + "loss": 4.0108, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696453595900844e-05, + "loss": 4.0228, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695615001149792e-05, + "loss": 4.0296, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69477640639874e-05, + "loss": 4.01, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939378116476884e-05, + "loss": 4.0201, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693100854777009e-05, + "loss": 4.0118, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692263897906331e-05, + "loss": 4.0223, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691425303155279e-05, + "loss": 4.0325, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690586708404226e-05, + "loss": 4.0206, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689748113653174e-05, + "loss": 4.0297, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688909518902122e-05, + "loss": 4.0232, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.68807092415107e-05, + "loss": 4.0359, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687232329400018e-05, + "loss": 4.0147, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686393734648966e-05, + "loss": 4.0274, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685556777778287e-05, + "loss": 4.0179, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684718183027235e-05, + "loss": 4.0195, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683879588276184e-05, + "loss": 4.0265, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683040993525132e-05, + "loss": 4.0227, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68220239877408e-05, + "loss": 4.0283, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681363804023028e-05, + "loss": 4.0393, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680525209271976e-05, + "loss": 4.0222, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679686614520924e-05, + "loss": 4.0142, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6788496576502446e-05, + "loss": 4.016, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780127007795655e-05, + "loss": 4.0292, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6771741060285135e-05, + "loss": 4.017, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6763355112774615e-05, + "loss": 4.0296, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6754969165264095e-05, + "loss": 4.0284, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746599596557304e-05, + "loss": 4.0266, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673821364904679e-05, + "loss": 4.0227, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672982770153627e-05, + "loss": 4.0191, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672145813282948e-05, + "loss": 4.029, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671307218531896e-05, + "loss": 4.0253, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670468623780844e-05, + "loss": 4.03, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669630029029792e-05, + "loss": 4.019, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.66879143427874e-05, + "loss": 4.0179, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667952839527688e-05, + "loss": 4.0259, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667114244776636e-05, + "loss": 4.0336, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666275650025584e-05, + "loss": 4.0252, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665437055274532e-05, + "loss": 4.0212, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.66459846052348e-05, + "loss": 4.0239, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663761503652801e-05, + "loss": 4.0233, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662922908901749e-05, + "loss": 4.0079, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620843141506975e-05, + "loss": 4.014, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612457193996455e-05, + "loss": 4.0081, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660407124648593e-05, + "loss": 4.0246, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659568529897541e-05, + "loss": 4.0173, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658729935146489e-05, + "loss": 4.0192, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657891340395437e-05, + "loss": 4.0145, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657056021405131e-05, + "loss": 4.0264, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656217426654079e-05, + "loss": 4.0216, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655378831903027e-05, + "loss": 4.0205, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545402371519746e-05, + "loss": 4.0277, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537016424009226e-05, + "loss": 4.0282, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652864685530244e-05, + "loss": 4.0249, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652026090779192e-05, + "loss": 4.0204, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.65118749602814e-05, + "loss": 4.0115, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650348901277088e-05, + "loss": 4.0237, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649510306526036e-05, + "loss": 4.0226, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648673349655357e-05, + "loss": 4.0026, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647834754904305e-05, + "loss": 4.0227, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646996160153253e-05, + "loss": 4.0178, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646157565402201e-05, + "loss": 4.0171, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645320608531522e-05, + "loss": 4.0269, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64448201378047e-05, + "loss": 4.0146, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643643419029418e-05, + "loss": 4.0155, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642804824278366e-05, + "loss": 4.0126, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641966229527315e-05, + "loss": 4.0316, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641127634776263e-05, + "loss": 4.0207, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402890400252107e-05, + "loss": 4.023, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394504452741587e-05, + "loss": 4.0104, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386118505231067e-05, + "loss": 4.0267, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6377748936524276e-05, + "loss": 4.0233, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6369362989013756e-05, + "loss": 4.0248, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6360977041503236e-05, + "loss": 4.0224, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6352591093992715e-05, + "loss": 4.0138, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344221525285925e-05, + "loss": 4.0203, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6335835577775405e-05, + "loss": 4.0352, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327449630264884e-05, + "loss": 4.01, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319063682754364e-05, + "loss": 4.0175, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310677735243844e-05, + "loss": 4.0145, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630229178773333e-05, + "loss": 4.0119, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629390584022281e-05, + "loss": 4.0104, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6285519892712284e-05, + "loss": 4.0157, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.62771503240055e-05, + "loss": 4.0205, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626876437649498e-05, + "loss": 4.0262, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626039480778819e-05, + "loss": 4.0165, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.057788848876953, + "eval_runtime": 283.4015, + "eval_samples_per_second": 1346.468, + "eval_steps_per_second": 42.078, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625200886027767e-05, + "loss": 4.0054, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624363929157088e-05, + "loss": 4.0049, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623525334406036e-05, + "loss": 4.0219, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622686739654984e-05, + "loss": 4.02, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621848144903932e-05, + "loss": 4.0248, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.62100955015288e-05, + "loss": 4.019, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6201709554018285e-05, + "loss": 4.0156, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619332360650776e-05, + "loss": 4.0056, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618493765899724e-05, + "loss": 4.0103, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617655171148672e-05, + "loss": 4.0142, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.61681657639762e-05, + "loss": 4.0243, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615979619526941e-05, + "loss": 4.0243, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615142662656262e-05, + "loss": 4.0282, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.61430406790521e-05, + "loss": 4.001, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613465473154158e-05, + "loss": 4.0114, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126268784031056e-05, + "loss": 3.997, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117882836520536e-05, + "loss": 4.0218, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610949688901002e-05, + "loss": 4.0115, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610112732030323e-05, + "loss": 4.0052, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609274137279271e-05, + "loss": 4.0118, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608435542528219e-05, + "loss": 4.0298, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607596947777167e-05, + "loss": 4.0101, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606758353026115e-05, + "loss": 4.021, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605919758275063e-05, + "loss": 4.014, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605081163524011e-05, + "loss": 4.0168, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604244206653332e-05, + "loss": 4.0151, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60340561190228e-05, + "loss": 4.0046, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602567017151228e-05, + "loss": 4.0147, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601728422400176e-05, + "loss": 4.0096, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600889827649124e-05, + "loss": 4.0033, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600051232898072e-05, + "loss": 4.0168, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599212638147021e-05, + "loss": 4.0092, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598374043395969e-05, + "loss": 4.0125, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597535448644917e-05, + "loss": 4.0196, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596696853893865e-05, + "loss": 4.0062, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5958615349035585e-05, + "loss": 4.0114, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5950229401525065e-05, + "loss": 4.0137, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5941843454014545e-05, + "loss": 3.9914, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933457506504025e-05, + "loss": 4.0077, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925071558993505e-05, + "loss": 4.0005, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916685611482985e-05, + "loss": 4.0021, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908316042776194e-05, + "loss": 4.0152, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899930095265674e-05, + "loss": 4.0158, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891544147755154e-05, + "loss": 4.0093, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588315820024464e-05, + "loss": 4.0159, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587477225273412e-05, + "loss": 4.0075, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866386305223594e-05, + "loss": 4.0123, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858000357713074e-05, + "loss": 4.0062, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849614410202554e-05, + "loss": 3.9934, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841228462692034e-05, + "loss": 4.0111, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583285889398524e-05, + "loss": 4.0081, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582448932527846e-05, + "loss": 4.0179, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581610337776794e-05, + "loss": 4.0067, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580771743025742e-05, + "loss": 4.0028, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579933148274689e-05, + "loss": 3.9992, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579094553523638e-05, + "loss": 3.9984, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578255958772586e-05, + "loss": 4.0196, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577417364021534e-05, + "loss": 3.996, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576578769270482e-05, + "loss": 4.0205, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57574017451943e-05, + "loss": 4.0121, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574901579768378e-05, + "loss": 3.9848, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574064622897699e-05, + "loss": 4.0154, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573226028146647e-05, + "loss": 3.998, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572387433395595e-05, + "loss": 3.9923, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571548838644543e-05, + "loss": 4.0031, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570710243893491e-05, + "loss": 4.0095, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569871649142439e-05, + "loss": 3.9947, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5690346922717596e-05, + "loss": 4.0063, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5681960975207076e-05, + "loss": 3.9905, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567357502769656e-05, + "loss": 4.005, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566518908018604e-05, + "loss": 4.0139, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565680313267552e-05, + "loss": 4.0029, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5648417185165e-05, + "loss": 4.0112, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564003123765448e-05, + "loss": 4.0048, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631645290143956e-05, + "loss": 4.0181, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562327572143717e-05, + "loss": 3.9991, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561490615273038e-05, + "loss": 4.0057, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560652020521986e-05, + "loss": 3.9984, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559813425770934e-05, + "loss": 4.0026, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558974831019882e-05, + "loss": 4.0104, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558137874149203e-05, + "loss": 4.0002, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5572992793981517e-05, + "loss": 4.0109, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5564606846470997e-05, + "loss": 4.0209, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556220898960476e-05, + "loss": 4.0057, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547834951449956e-05, + "loss": 3.9889, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5539465382743166e-05, + "loss": 4.0003, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531079435232645e-05, + "loss": 4.008, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522693487722125e-05, + "loss": 4.0032, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514307540211605e-05, + "loss": 4.006, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550592159270108e-05, + "loss": 4.0111, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549753564519056e-05, + "loss": 4.0071, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548914969768004e-05, + "loss": 4.0053, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548076375016952e-05, + "loss": 4.0009, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472377802659e-05, + "loss": 4.01, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546402461275595e-05, + "loss": 4.0061, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545563866524543e-05, + "loss": 4.015, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.54472527177349e-05, + "loss": 3.9926, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543886677022438e-05, + "loss": 4.0065, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.54304972015176e-05, + "loss": 4.0079, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542211125400708e-05, + "loss": 4.0108, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541372530649655e-05, + "loss": 4.0111, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540533935898603e-05, + "loss": 3.9988, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539695341147551e-05, + "loss": 4.0061, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538856746396499e-05, + "loss": 4.0039, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538018151645447e-05, + "loss": 3.9975, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537179556894395e-05, + "loss": 3.9915, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536342600023717e-05, + "loss": 3.9915, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535504005272665e-05, + "loss": 4.0046, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534665410521613e-05, + "loss": 4.0016, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533826815770561e-05, + "loss": 3.9961, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532989858899882e-05, + "loss": 3.9926, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53215126414883e-05, + "loss": 4.0113, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531312669397778e-05, + "loss": 4.005, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530474074646726e-05, + "loss": 4.0019, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5296371177760466e-05, + "loss": 4.0093, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5287985230249946e-05, + "loss": 4.0108, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5279599282739426e-05, + "loss": 4.0059, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5271213335228906e-05, + "loss": 3.9991, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5262827387718386e-05, + "loss": 3.9967, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52544578190116e-05, + "loss": 4.0009, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524607187150108e-05, + "loss": 4.0111, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237718681598027e-05, + "loss": 3.9809, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.52293327340875e-05, + "loss": 4.0065, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5220963165380716e-05, + "loss": 4.0007, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5212577217870196e-05, + "loss": 4.0009, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520419127035967e-05, + "loss": 4.0075, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519580532284915e-05, + "loss": 3.9977, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518741937533863e-05, + "loss": 3.9987, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517903342782811e-05, + "loss": 3.9914, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170647480317595e-05, + "loss": 4.0151, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162261532807075e-05, + "loss": 4.0007, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153875585296555e-05, + "loss": 4.0094, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145489637786035e-05, + "loss": 3.9923, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137103690275515e-05, + "loss": 4.0059, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128717742764995e-05, + "loss": 4.0117, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120331795254475e-05, + "loss": 4.0031, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111945847743955e-05, + "loss": 4.0063, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103559900233435e-05, + "loss": 3.9983, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095190331526644e-05, + "loss": 4.0014, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086804384016124e-05, + "loss": 4.0146, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078418436505604e-05, + "loss": 3.997, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070032488995084e-05, + "loss": 3.9979, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506166292028829e-05, + "loss": 4.0012, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505329335158151e-05, + "loss": 3.994, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504490740407099e-05, + "loss": 3.9929, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503652145656047e-05, + "loss": 4.0023, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502813550904995e-05, + "loss": 3.998, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501974956153943e-05, + "loss": 4.0061, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501136361402891e-05, + "loss": 4.0021, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.047115802764893, + "eval_runtime": 281.8183, + "eval_samples_per_second": 1354.032, + "eval_steps_per_second": 42.314, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500299404532212e-05, + "loss": 4.0195, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49946080978116e-05, + "loss": 3.9872, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498622215030108e-05, + "loss": 4.0008, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497783620279056e-05, + "loss": 4.0068, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496945025528003e-05, + "loss": 4.0038, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496106430776952e-05, + "loss": 4.0036, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952678360259e-05, + "loss": 3.9979, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494429241274848e-05, + "loss": 3.99, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493590646523796e-05, + "loss": 3.992, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492752051772744e-05, + "loss": 3.9982, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491913457021692e-05, + "loss": 4.0049, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49107486227064e-05, + "loss": 4.0072, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902379053999606e-05, + "loss": 4.0168, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893993106489086e-05, + "loss": 3.9813, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885607158978566e-05, + "loss": 3.9934, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877221211468046e-05, + "loss": 3.9808, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868835263957526e-05, + "loss": 4.0073, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860449316447006e-05, + "loss": 3.9965, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852063368936486e-05, + "loss": 3.9891, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843677421425966e-05, + "loss": 3.9935, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835291473915446e-05, + "loss": 4.0112, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482692190520866e-05, + "loss": 3.9944, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481853595769814e-05, + "loss": 4.0036, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481015001018762e-05, + "loss": 3.9974, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48017640626771e-05, + "loss": 4.0035, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793378115166575e-05, + "loss": 3.9956, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4784992167656055e-05, + "loss": 3.9878, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4776606220145535e-05, + "loss": 4.0002, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768220272635015e-05, + "loss": 3.9865, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759850703928224e-05, + "loss": 3.9868, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751464756417704e-05, + "loss": 4.0016, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743078808907184e-05, + "loss": 3.9938, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4734692861396664e-05, + "loss": 3.9953, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472632329268988e-05, + "loss": 4.0041, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471793734517936e-05, + "loss": 3.9904, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709567776472575e-05, + "loss": 3.9946, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470118182896205e-05, + "loss": 3.999, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469279588145153e-05, + "loss": 3.9759, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468440993394101e-05, + "loss": 3.994, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467602398643049e-05, + "loss": 3.9825, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466763803891997e-05, + "loss": 3.9878, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465925209140945e-05, + "loss": 3.9951, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465088252270266e-05, + "loss": 3.9986, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464249657519214e-05, + "loss": 3.9939, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463411062768162e-05, + "loss": 3.9981, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4625724680171104e-05, + "loss": 3.9941, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617338732660584e-05, + "loss": 3.9937, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608952785150064e-05, + "loss": 3.9917, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600566837639544e-05, + "loss": 3.9765, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592180890129024e-05, + "loss": 3.9926, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458382770022596e-05, + "loss": 3.9959, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457544175271544e-05, + "loss": 3.9987, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456707218400865e-05, + "loss": 3.9912, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455868623649813e-05, + "loss": 3.9839, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455030028898761e-05, + "loss": 3.9821, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454191434147709e-05, + "loss": 3.9809, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453352839396657e-05, + "loss": 4.003, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452514244645606e-05, + "loss": 3.9831, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451675649894554e-05, + "loss": 4.0048, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450837055143502e-05, + "loss": 3.9927, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44999846039245e-05, + "loss": 3.9765, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449159865641398e-05, + "loss": 3.9969, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448322908770719e-05, + "loss": 3.9815, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447484314019667e-05, + "loss": 3.9767, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446645719268615e-05, + "loss": 3.9827, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458071245175627e-05, + "loss": 3.9941, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449685297665107e-05, + "loss": 3.9765, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444129935015458e-05, + "loss": 3.9931, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443291340264406e-05, + "loss": 3.9703, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442452745513354e-05, + "loss": 3.9871, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416157886426756e-05, + "loss": 3.9987, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4407771938916235e-05, + "loss": 3.9888, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4399385991405715e-05, + "loss": 3.9921, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391000043895195e-05, + "loss": 3.9855, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382630475188404e-05, + "loss": 4.0, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437426090648162e-05, + "loss": 3.9835, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.43658749589711e-05, + "loss": 3.9902, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435748901146058e-05, + "loss": 3.9835, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349103063950053e-05, + "loss": 3.9841, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340717116439533e-05, + "loss": 3.9897, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433233116892901e-05, + "loss": 3.9838, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432396160022223e-05, + "loss": 3.9979, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4315592031515445e-05, + "loss": 4.0026, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307206084004925e-05, + "loss": 3.9939, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298820136494405e-05, + "loss": 3.9753, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429043418898388e-05, + "loss": 3.9813, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428204824147336e-05, + "loss": 3.9908, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427366229396284e-05, + "loss": 3.9893, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426527634645232e-05, + "loss": 3.9886, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.42568903989418e-05, + "loss": 3.9943, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424850445143128e-05, + "loss": 3.9916, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424011850392076e-05, + "loss": 3.9876, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423173255641024e-05, + "loss": 3.9881, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422334660889972e-05, + "loss": 3.9939, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4214977040192934e-05, + "loss": 3.9915, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4206591092682414e-05, + "loss": 3.9994, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419822152397562e-05, + "loss": 3.9792, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41898355764651e-05, + "loss": 3.9858, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418144962895458e-05, + "loss": 3.9925, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417306368144406e-05, + "loss": 3.9928, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416469411273727e-05, + "loss": 3.997, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415630816522675e-05, + "loss": 3.9849, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414792221771623e-05, + "loss": 3.9886, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413953627020571e-05, + "loss": 3.9856, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413115032269519e-05, + "loss": 3.981, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41227807539884e-05, + "loss": 3.9749, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411439480647789e-05, + "loss": 3.9777, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410600885896737e-05, + "loss": 3.9885, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409762291145685e-05, + "loss": 3.9871, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408923696394633e-05, + "loss": 3.9818, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408085101643581e-05, + "loss": 3.9738, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407246506892529e-05, + "loss": 3.993, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406407912141477e-05, + "loss": 3.9902, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4055709552707976e-05, + "loss": 3.9867, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4047323605197456e-05, + "loss": 3.9956, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4038954036490665e-05, + "loss": 3.9927, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4030568088980145e-05, + "loss": 3.9879, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022182141469625e-05, + "loss": 3.9854, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013812572762834e-05, + "loss": 3.9827, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400542662525232e-05, + "loss": 3.9886, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39970406777418e-05, + "loss": 3.9958, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398865473023128e-05, + "loss": 3.9669, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398026878272076e-05, + "loss": 3.99, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397188283521024e-05, + "loss": 3.982, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963496887699714e-05, + "loss": 3.9832, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955110940189194e-05, + "loss": 3.9929, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394674137148241e-05, + "loss": 3.9824, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393835542397189e-05, + "loss": 3.9797, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392996947646136e-05, + "loss": 3.9779, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392158352895084e-05, + "loss": 3.9983, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391319758144032e-05, + "loss": 3.9837, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.39048116339298e-05, + "loss": 3.9929, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389642568641929e-05, + "loss": 3.9787, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.38880561177125e-05, + "loss": 3.9913, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387967017020198e-05, + "loss": 3.9928, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387128422269146e-05, + "loss": 3.9875, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386289827518094e-05, + "loss": 3.9899, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385451232767042e-05, + "loss": 3.9823, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38461263801599e-05, + "loss": 3.9871, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383774043264938e-05, + "loss": 4.003, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382935448513886e-05, + "loss": 3.9834, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382098491643207e-05, + "loss": 3.98, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812615347725277e-05, + "loss": 3.9875, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804229400214757e-05, + "loss": 3.9807, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379584345270424e-05, + "loss": 3.9742, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378745750519372e-05, + "loss": 3.9917, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.37790715576832e-05, + "loss": 3.9774, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377068561017268e-05, + "loss": 3.9899, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376229966266216e-05, + "loss": 3.9893, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.038329124450684, + "eval_runtime": 318.0779, + "eval_samples_per_second": 1199.678, + "eval_steps_per_second": 37.491, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375393009395537e-05, + "loss": 3.9769, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374554414644485e-05, + "loss": 3.9758, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373715819893433e-05, + "loss": 3.9815, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372877225142381e-05, + "loss": 3.9956, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372038630391329e-05, + "loss": 3.9869, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371200035640277e-05, + "loss": 3.9908, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370363078769598e-05, + "loss": 3.9787, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369524484018546e-05, + "loss": 3.9761, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368685889267494e-05, + "loss": 3.9734, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367847294516443e-05, + "loss": 3.988, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.36700869976539e-05, + "loss": 3.9847, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366170105014338e-05, + "loss": 3.9961, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.36533314814366e-05, + "loss": 3.9953, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364494553392608e-05, + "loss": 3.9668, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363655958641555e-05, + "loss": 3.9783, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362817363890503e-05, + "loss": 3.9689, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361978769139451e-05, + "loss": 3.9894, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361140174388399e-05, + "loss": 3.9783, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360301579637347e-05, + "loss": 3.9756, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359462984886295e-05, + "loss": 3.9795, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3586276658959895e-05, + "loss": 3.9918, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3577890711449375e-05, + "loss": 3.9829, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3569504763938855e-05, + "loss": 3.9848, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3561118816428334e-05, + "loss": 3.9841, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3552732868917814e-05, + "loss": 3.9853, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3544346921407294e-05, + "loss": 3.9846, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3535977352700503e-05, + "loss": 3.9696, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3527591405189983e-05, + "loss": 3.9878, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3519205457679463e-05, + "loss": 3.9706, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351081951016894e-05, + "loss": 3.9745, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350243356265842e-05, + "loss": 3.9828, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.34940476151479e-05, + "loss": 3.9768, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348567804644111e-05, + "loss": 3.9804, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.34772920989306e-05, + "loss": 3.9866, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346890615142008e-05, + "loss": 3.9781, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346053658271329e-05, + "loss": 3.9817, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345215063520277e-05, + "loss": 3.9803, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344376468769225e-05, + "loss": 3.9623, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343537874018173e-05, + "loss": 3.9781, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342699279267121e-05, + "loss": 3.9671, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341860684516069e-05, + "loss": 3.977, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341022089765017e-05, + "loss": 3.9762, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340183495013965e-05, + "loss": 3.9848, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339344900262913e-05, + "loss": 3.9766, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338506305511861e-05, + "loss": 3.9821, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337667710760808e-05, + "loss": 3.9777, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336829116009757e-05, + "loss": 3.98, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335995434899824e-05, + "loss": 3.9767, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335156840148772e-05, + "loss": 3.9605, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.33431824539772e-05, + "loss": 3.9743, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333479650646668e-05, + "loss": 3.9841, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332641055895616e-05, + "loss": 3.9824, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331802461144564e-05, + "loss": 3.9729, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330963866393512e-05, + "loss": 3.9695, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.33012527164246e-05, + "loss": 3.968, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329286676891408e-05, + "loss": 3.9648, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328449720020729e-05, + "loss": 3.9926, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327611125269677e-05, + "loss": 3.9639, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326772530518625e-05, + "loss": 3.9858, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325933935767574e-05, + "loss": 3.9788, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325095341016521e-05, + "loss": 3.9615, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324256746265469e-05, + "loss": 3.9803, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234197893947906e-05, + "loss": 3.9661, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225811946437386e-05, + "loss": 3.9632, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321742599892686e-05, + "loss": 3.9652, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320904005141634e-05, + "loss": 3.9784, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320065410390582e-05, + "loss": 3.9617, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319228453519903e-05, + "loss": 3.9743, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318389858768851e-05, + "loss": 3.9578, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317551264017799e-05, + "loss": 3.9696, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3167126692667475e-05, + "loss": 3.9817, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3158740745156955e-05, + "loss": 3.9763, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3150371176450164e-05, + "loss": 3.9764, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3141985228939644e-05, + "loss": 3.9712, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133599281429124e-05, + "loss": 3.9841, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125213333918604e-05, + "loss": 3.9666, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116827386408084e-05, + "loss": 3.9739, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108441438897564e-05, + "loss": 3.9706, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3100055491387044e-05, + "loss": 3.9715, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091669543876524e-05, + "loss": 3.9736, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308329997516973e-05, + "loss": 3.9714, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307491402765921e-05, + "loss": 3.9813, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306652808014869e-05, + "loss": 3.9898, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305815851144191e-05, + "loss": 3.9747, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304977256393139e-05, + "loss": 3.9626, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304138661642087e-05, + "loss": 3.967, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303300066891035e-05, + "loss": 3.9781, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302461472139983e-05, + "loss": 3.9757, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301622877388931e-05, + "loss": 3.9726, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300785920518252e-05, + "loss": 3.9802, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999473257672e-05, + "loss": 3.9771, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299108731016148e-05, + "loss": 3.9721, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298270136265096e-05, + "loss": 3.9748, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974331793944166e-05, + "loss": 3.9785, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2965945846433646e-05, + "loss": 3.971, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2957559898923126e-05, + "loss": 3.986, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2949173951412606e-05, + "loss": 3.9609, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294078800390209e-05, + "loss": 3.9783, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293240205639157e-05, + "loss": 3.9777, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2924016108881046e-05, + "loss": 3.9768, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2915630161370526e-05, + "loss": 3.9826, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290726059266374e-05, + "loss": 3.9696, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289887464515322e-05, + "loss": 3.9735, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289050507644643e-05, + "loss": 3.9723, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288211912893591e-05, + "loss": 3.9686, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287373318142539e-05, + "loss": 3.9596, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2865347233914864e-05, + "loss": 3.9662, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2856961286404344e-05, + "loss": 3.9679, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284857533889383e-05, + "loss": 3.9746, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284018939138331e-05, + "loss": 3.9639, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283180344387279e-05, + "loss": 3.9633, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282341749636227e-05, + "loss": 3.9758, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2815064306459216e-05, + "loss": 3.9752, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806678358948696e-05, + "loss": 3.9696, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279829241143817e-05, + "loss": 3.9814, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278990646392765e-05, + "loss": 3.9762, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2781536895220865e-05, + "loss": 3.9804, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277315094771034e-05, + "loss": 3.9673, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276476500019982e-05, + "loss": 3.9693, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.27563790526893e-05, + "loss": 3.9721, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2747993105178784e-05, + "loss": 3.9823, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2739623536471994e-05, + "loss": 3.9542, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273125396776521e-05, + "loss": 3.9746, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272286802025469e-05, + "loss": 3.9654, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271448207274416e-05, + "loss": 3.9713, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270609612523364e-05, + "loss": 3.9771, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269771017772312e-05, + "loss": 3.9702, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.26893242302126e-05, + "loss": 3.9627, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268093828270208e-05, + "loss": 3.9646, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267255233519156e-05, + "loss": 3.9817, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266416638768104e-05, + "loss": 3.9697, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265579681897425e-05, + "loss": 3.9796, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264741087146374e-05, + "loss": 3.9622, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263902492395322e-05, + "loss": 3.9802, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.26306389764427e-05, + "loss": 3.978, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262225302893218e-05, + "loss": 3.9749, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261386708142166e-05, + "loss": 3.9684, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260549751271487e-05, + "loss": 3.9712, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259711156520435e-05, + "loss": 3.9754, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258872561769383e-05, + "loss": 3.9824, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258033967018331e-05, + "loss": 3.9733, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257195372267279e-05, + "loss": 3.9633, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256356777516227e-05, + "loss": 3.9759, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2555198206455476e-05, + "loss": 3.9623, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2546812258944956e-05, + "loss": 3.9592, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2538426311434436e-05, + "loss": 3.9778, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253004036392392e-05, + "loss": 3.9644, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.25216544164134e-05, + "loss": 3.9771, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251328484770661e-05, + "loss": 3.9697, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.029951572418213, + "eval_runtime": 307.2515, + "eval_samples_per_second": 1241.95, + "eval_steps_per_second": 38.812, + "step": 1068480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 4.390984552612009e+17, + "trial_name": null, + "trial_params": null +}