diff --git "a/checkpoint-1221120/trainer_state.json" "b/checkpoint-1221120/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1221120/trainer_state.json" @@ -0,0 +1,14463 @@ +{ + "best_metric": 4.035419464111328, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/3/checkpoints/checkpoint-1221120", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1221120, + "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": 10.8193, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5528, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0655, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 7.0038, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9567, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9333, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7583, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6494, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5522, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4697, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4108, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3505, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.279, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.2115, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.163, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.1099, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.064, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 6.0229, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9858, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9451, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.9127, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8723, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.8504, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.8095, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7896, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7592, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7363, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.7164, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6864, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.661, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6484, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6377, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.6148, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5928, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5877, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5604, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5467, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.5138, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.517, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.495, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4865, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4727, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4673, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4368, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4292, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.4252, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.4094, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.4115, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3897, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3689, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3782, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3554, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956404538107908e-05, + "loss": 5.3494, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955565943356856e-05, + "loss": 5.3231, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954727348605804e-05, + "loss": 5.3342, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953888753854752e-05, + "loss": 5.3097, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.337, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2988, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2995, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2921, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2727, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2601, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2592, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 5.2427, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 5.2365, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2539, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 5.2348, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.2196, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1965, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1937, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.2021, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.199, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1908, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1877, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1795, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.172, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1582, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.1481, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.143, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.1294, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.1368, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.1283, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.1304, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 5.1112, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 5.0917, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.106, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.1017, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0989, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0846, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0866, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0716, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0666, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0659, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0585, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.0629, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0555, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.054, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0308, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 5.0282, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 5.0263, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 5.0243, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 5.0169, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 5.0106, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9992, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 5.0068, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9826, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9882, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.9854, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.9772, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.972, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907784059230996e-05, + "loss": 4.9762, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906945464479944e-05, + "loss": 4.963, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906106869728892e-05, + "loss": 4.9663, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052682749778396e-05, + "loss": 4.9583, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904431318107161e-05, + "loss": 4.9476, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903592723356109e-05, + "loss": 4.9528, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027541286050565e-05, + "loss": 4.9511, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019155338540045e-05, + "loss": 4.9449, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010769391029525e-05, + "loss": 4.9299, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.936, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.937, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.9266, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.9132, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896885603228066e-05, + "loss": 4.9205, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.9208, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.9077, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.9024, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8932, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8968, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.887, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.9026, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.8919, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.8734, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.88, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8784, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.874, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859887851055094e-05, + "loss": 4.8784, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8631, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8654, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8722, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8551, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8518, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.8525, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.8396, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879281664977466e-05, + "loss": 4.8387, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878443070226414e-05, + "loss": 4.8447, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877604475475362e-05, + "loss": 4.8284, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87676588072431e-05, + "loss": 4.8317, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875928923853632e-05, + "loss": 4.8373, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.87509032910258e-05, + "loss": 4.8327, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.789715766906738, + "eval_runtime": 296.8384, + "eval_samples_per_second": 1285.518, + "eval_steps_per_second": 40.173, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874251734351528e-05, + "loss": 4.8151, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873413139600475e-05, + "loss": 4.8145, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.8291, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871737587978745e-05, + "loss": 4.8121, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870898993227693e-05, + "loss": 4.8245, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.87006039847664e-05, + "loss": 4.7966, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.8152, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683848468549096e-05, + "loss": 4.7978, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.7922, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7973, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.8009, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.8013, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8641935109800225e-05, + "loss": 4.7841, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633549162289705e-05, + "loss": 4.7819, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625163214779185e-05, + "loss": 4.7754, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616777267268665e-05, + "loss": 4.7762, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.774, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.7742, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.7691, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7882, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.7655, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7741, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.761, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7688, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7565, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7563, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.751, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851617865474989e-05, + "loss": 4.7469, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850779270723937e-05, + "loss": 4.7304, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849940675972885e-05, + "loss": 4.7463, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849102081221833e-05, + "loss": 4.7427, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848265124351154e-05, + "loss": 4.7461, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847426529600102e-05, + "loss": 4.7357, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.84658793484905e-05, + "loss": 4.7385, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.7318, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449123832273194e-05, + "loss": 4.7271, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440737884762674e-05, + "loss": 4.7123, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432351937252154e-05, + "loss": 4.7198, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423965989741634e-05, + "loss": 4.7173, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.7149, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840719409472059e-05, + "loss": 4.7182, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839880814721007e-05, + "loss": 4.7172, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839043857850328e-05, + "loss": 4.7068, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838205263099276e-05, + "loss": 4.712, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.7121, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365280735971716e-05, + "loss": 4.6985, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.7099, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834852521975441e-05, + "loss": 4.6964, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834015565104763e-05, + "loss": 4.6847, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833176970353711e-05, + "loss": 4.7038, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832338375602659e-05, + "loss": 4.6868, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831499780851606e-05, + "loss": 4.6861, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830661186100554e-05, + "loss": 4.6745, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.6848, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.82898399659845e-05, + "loss": 4.6708, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828145401847398e-05, + "loss": 4.7047, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827306807096346e-05, + "loss": 4.6729, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826468212345294e-05, + "loss": 4.6864, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6799, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6672, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6574, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6714, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6572, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6562, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6737, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197627300976246e-05, + "loss": 4.6682, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189241353465726e-05, + "loss": 4.6522, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.6456, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.646, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164099889737895e-05, + "loss": 4.6578, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155713942227375e-05, + "loss": 4.6571, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147327994716854e-05, + "loss": 4.6546, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.6547, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6546, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812220290979276e-05, + "loss": 4.6548, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.6374, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.6412, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.6403, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.6251, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.6399, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.6376, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.6405, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.6218, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804676213980554e-05, + "loss": 4.6123, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803837619229502e-05, + "loss": 4.6298, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8029990244784504e-05, + "loss": 4.624, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.6306, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013218349763464e-05, + "loss": 4.6225, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.6237, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996446454742424e-05, + "loss": 4.6187, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.79880605072319e-05, + "loss": 4.6113, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797967455972138e-05, + "loss": 4.6174, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797128861221086e-05, + "loss": 4.613, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796290266470034e-05, + "loss": 4.6213, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.6214, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946147148483026e-05, + "loss": 4.6173, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937761200972506e-05, + "loss": 4.6048, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929375253461986e-05, + "loss": 4.6026, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.6014, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.6118, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790423378973416e-05, + "loss": 4.5968, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789584784222364e-05, + "loss": 4.5973, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788746189471312e-05, + "loss": 4.5909, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.78790759472026e-05, + "loss": 4.6058, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787070637849581e-05, + "loss": 4.5785, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5917, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.78539508622785e-05, + "loss": 4.5929, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784556491476798e-05, + "loss": 4.5862, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783717896725746e-05, + "loss": 4.5834, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782879301974694e-05, + "loss": 4.5951, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782040707223642e-05, + "loss": 4.5796, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812021124725906e-05, + "loss": 4.5825, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803635177215386e-05, + "loss": 4.5873, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795249229704866e-05, + "loss": 4.5734, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786879660998075e-05, + "loss": 4.5847, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778510092291284e-05, + "loss": 4.5881, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770124144780764e-05, + "loss": 4.5806, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761738197270244e-05, + "loss": 4.5692, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753352249759724e-05, + "loss": 4.5789, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744966302249204e-05, + "loss": 4.5791, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736580354738684e-05, + "loss": 4.5702, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.5644, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771982483852137e-05, + "loss": 4.569, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771143889101086e-05, + "loss": 4.5791, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770305294350034e-05, + "loss": 4.5664, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769466699598982e-05, + "loss": 4.564, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.76862810484793e-05, + "loss": 4.5531, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5607, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5547, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.572, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5675, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5468, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.5544, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5588, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5555, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5632, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760245433098156e-05, + "loss": 4.5486, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.551, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5585, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757731286725373e-05, + "loss": 4.5456, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5474, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5528, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5369, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5411, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.548, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527013560994335e-05, + "loss": 4.5321, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518627613483815e-05, + "loss": 4.5397, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.5431, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5393, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.501766681671143, + "eval_runtime": 297.3924, + "eval_samples_per_second": 1283.123, + "eval_steps_per_second": 40.099, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749346977095226e-05, + "loss": 4.5264, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748508382344174e-05, + "loss": 4.528, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747669787593122e-05, + "loss": 4.5475, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.5259, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5412, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.521, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.5358, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743476813837862e-05, + "loss": 4.5181, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426382190868095e-05, + "loss": 4.5296, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417996243357575e-05, + "loss": 4.525, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409610295847055e-05, + "loss": 4.5276, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401224348336535e-05, + "loss": 4.5342, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739285477962975e-05, + "loss": 4.5152, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738446883211923e-05, + "loss": 4.5156, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737608288460871e-05, + "loss": 4.5121, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736769693709819e-05, + "loss": 4.5088, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735931098958767e-05, + "loss": 4.5131, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735092504207715e-05, + "loss": 4.5168, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734253909456663e-05, + "loss": 4.5102, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733415314705611e-05, + "loss": 4.5325, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732576719954559e-05, + "loss": 4.5123, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.5189, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.5092, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730062573581776e-05, + "loss": 4.5184, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729223978830724e-05, + "loss": 4.5099, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.5035, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.507, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.5009, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258712377068895e-05, + "loss": 4.4857, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250326429558375e-05, + "loss": 4.5015, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241940482047855e-05, + "loss": 4.5069, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233554534537335e-05, + "loss": 4.5024, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722516858702681e-05, + "loss": 4.4991, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216799018320024e-05, + "loss": 4.5006, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4944, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720004350210271e-05, + "loss": 4.4899, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4854, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4838, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717488565957115e-05, + "loss": 4.485, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716651609086437e-05, + "loss": 4.4847, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715813014335385e-05, + "loss": 4.4932, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714974419584333e-05, + "loss": 4.4926, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714135824833281e-05, + "loss": 4.4808, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713297230082228e-05, + "loss": 4.4881, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4906, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711621678460498e-05, + "loss": 4.474, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710783083709446e-05, + "loss": 4.4876, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709944488958393e-05, + "loss": 4.4804, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4622, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4824, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4747, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4698, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.4653, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704916196212828e-05, + "loss": 4.4685, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4563, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.4859, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702402049840045e-05, + "loss": 4.4659, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015634550889924e-05, + "loss": 4.4741, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4743, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4579, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4505, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4685, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973704813337324e-05, + "loss": 4.4539, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965318865826804e-05, + "loss": 4.4503, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695693291831629e-05, + "loss": 4.4696, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694854697080577e-05, + "loss": 4.4663, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4508, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693180783339219e-05, + "loss": 4.4449, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692342188588167e-05, + "loss": 4.4467, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691503593837115e-05, + "loss": 4.4565, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690664999086063e-05, + "loss": 4.4604, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.4573, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4598, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.4573, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.46, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686473663211176e-05, + "loss": 4.4458, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856350684601245e-05, + "loss": 4.4494, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4526, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683961154718766e-05, + "loss": 4.4333, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4479, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4532, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4513, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4378, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679768180963506e-05, + "loss": 4.4252, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678929586212454e-05, + "loss": 4.4457, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678090991461402e-05, + "loss": 4.4354, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.4502, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4401, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4433, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.437, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4285, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673062698715837e-05, + "loss": 4.4346, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4323, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.4458, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4479, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4384, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668869724960576e-05, + "loss": 4.4256, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.4291, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.4285, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.435, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.4238, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.4269, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.417, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.436, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.4078, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.4238, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.4166, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.4222, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.416, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.4258, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.4189, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.4147, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.4213, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.4071, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537832088435065e-05, + "loss": 4.4257, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652944614092454e-05, + "loss": 4.4288, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652106019341402e-05, + "loss": 4.414, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.65126742459035e-05, + "loss": 4.4103, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650428829839298e-05, + "loss": 4.4152, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649591872968619e-05, + "loss": 4.4153, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648753278217567e-05, + "loss": 4.4106, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.408, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.4067, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646237493964411e-05, + "loss": 4.4224, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645398899213359e-05, + "loss": 4.4115, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644560304462307e-05, + "loss": 4.4061, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.3952, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428831149602034e-05, + "loss": 4.4075, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642046158089524e-05, + "loss": 4.3977, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641207563338472e-05, + "loss": 4.4171, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64036896858742e-05, + "loss": 4.4126, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.3982, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638693416965689e-05, + "loss": 4.3967, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637854822214637e-05, + "loss": 4.4046, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.4016, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.4127, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.395, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634502081090802e-05, + "loss": 4.4049, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633663486339751e-05, + "loss": 4.4033, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632824891588699e-05, + "loss": 4.4012, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631986296837647e-05, + "loss": 4.4005, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631147702086595e-05, + "loss": 4.4022, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630309107335542e-05, + "loss": 4.3908, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629472150464864e-05, + "loss": 4.3963, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628633555713812e-05, + "loss": 4.4006, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277949609627597e-05, + "loss": 4.3913, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626956366211707e-05, + "loss": 4.3889, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.397, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.394, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.364997386932373, + "eval_runtime": 291.5075, + "eval_samples_per_second": 1309.026, + "eval_steps_per_second": 40.908, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244422198389246e-05, + "loss": 4.3874, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236036250878726e-05, + "loss": 4.3795, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227650303368205e-05, + "loss": 4.404, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219264355857685e-05, + "loss": 4.3843, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210878408347165e-05, + "loss": 4.4022, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202492460836645e-05, + "loss": 4.3758, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194106513326125e-05, + "loss": 4.3963, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185736944619334e-05, + "loss": 4.3803, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.3851, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.3879, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3862, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152193154577254e-05, + "loss": 4.3949, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614382358587046e-05, + "loss": 4.3797, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613543763835994e-05, + "loss": 4.3769, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612706806965316e-05, + "loss": 4.3799, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611868212214264e-05, + "loss": 4.3659, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611029617463212e-05, + "loss": 4.3784, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.61019102271216e-05, + "loss": 4.382, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609352427961108e-05, + "loss": 4.3725, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608513833210056e-05, + "loss": 4.3959, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607675238459004e-05, + "loss": 4.3805, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606836643707952e-05, + "loss": 4.3879, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059980489569e-05, + "loss": 4.3762, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605159454205848e-05, + "loss": 4.3832, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604320859454796e-05, + "loss": 4.378, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603482264703743e-05, + "loss": 4.3727, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602645307833065e-05, + "loss": 4.3758, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601806713082013e-05, + "loss": 4.3679, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600968118330961e-05, + "loss": 4.3621, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3665, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.3766, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984539719581783e-05, + "loss": 4.3753, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976153772071257e-05, + "loss": 4.3718, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967767824560737e-05, + "loss": 4.3745, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595939825585395e-05, + "loss": 4.3591, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595101230834343e-05, + "loss": 4.3635, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942626360832906e-05, + "loss": 4.3631, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593425679212612e-05, + "loss": 4.3539, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.59258708446156e-05, + "loss": 4.3613, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591748489710508e-05, + "loss": 4.356, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590909894959456e-05, + "loss": 4.3678, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590072938088778e-05, + "loss": 4.3662, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589234343337726e-05, + "loss": 4.3587, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588395748586673e-05, + "loss": 4.3581, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587557153835621e-05, + "loss": 4.3717, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586718559084569e-05, + "loss": 4.3507, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.364, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.3565, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3396, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583364180080361e-05, + "loss": 4.3632, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582525585329309e-05, + "loss": 4.3502, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581686990578257e-05, + "loss": 4.3533, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580848395827205e-05, + "loss": 4.3423, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.3476, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791744820858475e-05, + "loss": 4.3377, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.362, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774972925837435e-05, + "loss": 4.3484, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766586978326915e-05, + "loss": 4.3541, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3559, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749815083305875e-05, + "loss": 4.3424, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741429135795355e-05, + "loss": 4.3323, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733043188284835e-05, + "loss": 4.3522, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572468999838177e-05, + "loss": 4.3375, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571630405087125e-05, + "loss": 4.3337, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570791810336074e-05, + "loss": 4.3513, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569953215585022e-05, + "loss": 4.349, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569116258714343e-05, + "loss": 4.3373, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568277663963291e-05, + "loss": 4.3334, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567439069212239e-05, + "loss": 4.3278, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566600474461187e-05, + "loss": 4.3383, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565761879710135e-05, + "loss": 4.3481, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564923284959083e-05, + "loss": 4.3463, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564084690208031e-05, + "loss": 4.3461, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563246095456979e-05, + "loss": 4.342, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624091385863e-05, + "loss": 4.3538, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615721817156206e-05, + "loss": 4.3301, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560733586964569e-05, + "loss": 4.3401, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559894992213517e-05, + "loss": 4.3369, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559056397462465e-05, + "loss": 4.3199, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558219440591786e-05, + "loss": 4.3425, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557380845840734e-05, + "loss": 4.341, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556542251089682e-05, + "loss": 4.3365, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.55570365633863e-05, + "loss": 4.3291, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554865061587578e-05, + "loss": 4.3183, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.3331, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3325, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552350915214795e-05, + "loss": 4.3383, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551512320463743e-05, + "loss": 4.3277, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506770014734376e-05, + "loss": 4.3368, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498384067223856e-05, + "loss": 4.3248, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489998119713336e-05, + "loss": 4.3247, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481612172202816e-05, + "loss": 4.3251, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473226224692296e-05, + "loss": 4.3225, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.3408, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456454329671256e-05, + "loss": 4.3378, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448084760964465e-05, + "loss": 4.3376, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439698813453945e-05, + "loss": 4.3179, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431312865943425e-05, + "loss": 4.3251, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422926918432905e-05, + "loss": 4.325, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414540970922385e-05, + "loss": 4.3287, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406155023411865e-05, + "loss": 4.3202, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397769075901345e-05, + "loss": 4.3208, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389383128390824e-05, + "loss": 4.3117, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538101355968404e-05, + "loss": 4.3324, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372627612173514e-05, + "loss": 4.3058, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364241664662994e-05, + "loss": 4.3198, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355855717152473e-05, + "loss": 4.3164, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347469769641953e-05, + "loss": 4.3191, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533908382213143e-05, + "loss": 4.3143, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533069787462091e-05, + "loss": 4.3265, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532231192711039e-05, + "loss": 4.3169, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531392597959987e-05, + "loss": 4.3101, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530557278969682e-05, + "loss": 4.3242, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.52971868421863e-05, + "loss": 4.3069, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.3227, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.3295, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527202899965474e-05, + "loss": 4.3181, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526364305214422e-05, + "loss": 4.311, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.3126, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.3135, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.3132, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.3148, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221746072199076e-05, + "loss": 4.3032, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213360124688556e-05, + "loss": 4.3227, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.3159, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196588229667516e-05, + "loss": 4.3112, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.2951, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517983271345021e-05, + "loss": 4.311, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517144676593969e-05, + "loss": 4.3021, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516306081842917e-05, + "loss": 4.3139, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515467487091865e-05, + "loss": 4.3189, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.3071, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.294, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.3091, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512113108087657e-05, + "loss": 4.3053, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511277789097351e-05, + "loss": 4.3176, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104408322266726e-05, + "loss": 4.2971, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096022374756206e-05, + "loss": 4.3086, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087636427245685e-05, + "loss": 4.3088, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079250479735165e-05, + "loss": 4.311, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070864532224645e-05, + "loss": 4.3053, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062478584714125e-05, + "loss": 4.3061, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054092637203605e-05, + "loss": 4.2961, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045706689693085e-05, + "loss": 4.3045, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037320742182565e-05, + "loss": 4.3046, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028951173475774e-05, + "loss": 4.302, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020565225965254e-05, + "loss": 4.2936, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012179278454734e-05, + "loss": 4.3059, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003793330944214e-05, + "loss": 4.2992, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.280091285705566, + "eval_runtime": 291.7383, + "eval_samples_per_second": 1307.991, + "eval_steps_per_second": 40.876, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995407383433694e-05, + "loss": 4.2914, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987021435923174e-05, + "loss": 4.2903, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978635488412654e-05, + "loss": 4.3098, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970249540902134e-05, + "loss": 4.2949, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961863593391614e-05, + "loss": 4.3056, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953477645881094e-05, + "loss": 4.293, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945091698370574e-05, + "loss": 4.2998, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936705750860054e-05, + "loss": 4.2937, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928319803349534e-05, + "loss": 4.2937, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919933855839014e-05, + "loss": 4.2961, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911547908328494e-05, + "loss": 4.2971, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903161960817974e-05, + "loss": 4.3047, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489479239211118e-05, + "loss": 4.2893, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488642282340439e-05, + "loss": 4.2885, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487803687589387e-05, + "loss": 4.2894, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486965092838336e-05, + "loss": 4.2791, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486126498087284e-05, + "loss": 4.2889, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485287903336232e-05, + "loss": 4.2912, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48444930858518e-05, + "loss": 4.2863, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483610713834128e-05, + "loss": 4.3072, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482772119083076e-05, + "loss": 4.2942, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481933524332024e-05, + "loss": 4.3011, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481094929580971e-05, + "loss": 4.2907, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480256334829919e-05, + "loss": 4.2957, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479417740078867e-05, + "loss": 4.2894, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478579145327815e-05, + "loss": 4.2911, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477740550576763e-05, + "loss": 4.2876, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476903593706084e-05, + "loss": 4.2826, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476064998955033e-05, + "loss": 4.2799, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752280420843536e-05, + "loss": 4.2802, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743894473333016e-05, + "loss": 4.2878, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735508525822496e-05, + "loss": 4.2911, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727122578311976e-05, + "loss": 4.2863, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718736630801456e-05, + "loss": 4.288, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710367062094665e-05, + "loss": 4.2758, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701981114584145e-05, + "loss": 4.2807, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693595167073625e-05, + "loss": 4.2808, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685209219563105e-05, + "loss": 4.267, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676823272052585e-05, + "loss": 4.28, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668437324542065e-05, + "loss": 4.271, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466006775583528e-05, + "loss": 4.2857, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465169818712849e-05, + "loss": 4.2845, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464331223961797e-05, + "loss": 4.2792, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463492629210745e-05, + "loss": 4.2729, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462654034459693e-05, + "loss": 4.2897, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461815439708641e-05, + "loss": 4.2672, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460976844957589e-05, + "loss": 4.2828, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460138250206537e-05, + "loss": 4.273, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459299655455485e-05, + "loss": 4.2579, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458461060704433e-05, + "loss": 4.2838, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457624103833754e-05, + "loss": 4.2696, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456787146963075e-05, + "loss": 4.2699, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559485522120234e-05, + "loss": 4.2647, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551099574609714e-05, + "loss": 4.2618, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542713627099194e-05, + "loss": 4.2626, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534327679588674e-05, + "loss": 4.2736, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525941732078154e-05, + "loss": 4.2718, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517555784567634e-05, + "loss": 4.2741, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509169837057114e-05, + "loss": 4.2763, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450080026835032e-05, + "loss": 4.2652, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44924143208398e-05, + "loss": 4.2525, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448402837332928e-05, + "loss": 4.2748, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447564242581876e-05, + "loss": 4.2584, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446725647830824e-05, + "loss": 4.2535, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458870530797716e-05, + "loss": 4.2751, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.44504845832872e-05, + "loss": 4.2692, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444209863577668e-05, + "loss": 4.2597, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443371268826616e-05, + "loss": 4.2583, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442534311955937e-05, + "loss": 4.2466, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441695717204885e-05, + "loss": 4.26, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440857122453833e-05, + "loss": 4.2733, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440018527702781e-05, + "loss": 4.268, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439179932951729e-05, + "loss": 4.2668, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43834297608105e-05, + "loss": 4.2633, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437504381329998e-05, + "loss": 4.281, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436667424459319e-05, + "loss": 4.2543, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435828829708267e-05, + "loss": 4.2656, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434990234957216e-05, + "loss": 4.2649, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434151640206164e-05, + "loss": 4.2387, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333130454551117e-05, + "loss": 4.2715, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324744507040597e-05, + "loss": 4.264, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316358559530076e-05, + "loss": 4.2631, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307972612019556e-05, + "loss": 4.2568, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299603043312766e-05, + "loss": 4.2401, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291217095802245e-05, + "loss": 4.2586, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282831148291725e-05, + "loss": 4.2567, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274445200781205e-05, + "loss": 4.2654, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266059253270685e-05, + "loss": 4.2533, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257706063367624e-05, + "loss": 4.2624, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249320115857104e-05, + "loss": 4.25, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424093416834659e-05, + "loss": 4.2542, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423254822083607e-05, + "loss": 4.249, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422416227332555e-05, + "loss": 4.2492, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421577632581503e-05, + "loss": 4.2661, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420739037830451e-05, + "loss": 4.2631, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419900443079399e-05, + "loss": 4.2683, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.41906348620872e-05, + "loss": 4.2423, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418224891457668e-05, + "loss": 4.2533, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417386296706616e-05, + "loss": 4.2532, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416547701955564e-05, + "loss": 4.2546, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415709107204512e-05, + "loss": 4.2514, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414872150333833e-05, + "loss": 4.2441, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414033555582781e-05, + "loss": 4.2452, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413194960831729e-05, + "loss": 4.2605, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123580039610504e-05, + "loss": 4.2331, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115194092099984e-05, + "loss": 4.2459, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410682452339319e-05, + "loss": 4.2399, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409843857588267e-05, + "loss": 4.2535, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409005262837215e-05, + "loss": 4.2426, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408166668086163e-05, + "loss": 4.2536, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407328073335111e-05, + "loss": 4.2455, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406489478584059e-05, + "loss": 4.2395, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405650883833007e-05, + "loss": 4.2529, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404812289081955e-05, + "loss": 4.239, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039736943309026e-05, + "loss": 4.2535, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403135099579851e-05, + "loss": 4.2569, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402296504828799e-05, + "loss": 4.2456, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401457910077747e-05, + "loss": 4.2398, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400619315326695e-05, + "loss": 4.2449, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399780720575643e-05, + "loss": 4.2412, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398942125824591e-05, + "loss": 4.2453, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398103531073539e-05, + "loss": 4.245, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39726657420286e-05, + "loss": 4.2356, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396427979451808e-05, + "loss": 4.2529, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395591022581129e-05, + "loss": 4.2452, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394752427830077e-05, + "loss": 4.2468, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393913833079025e-05, + "loss": 4.2273, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393075238327973e-05, + "loss": 4.2415, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922382814572946e-05, + "loss": 4.2332, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913996867062426e-05, + "loss": 4.2446, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905610919551906e-05, + "loss": 4.2477, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897224972041386e-05, + "loss": 4.2418, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888855403334595e-05, + "loss": 4.2252, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880469455824075e-05, + "loss": 4.2442, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872083508313555e-05, + "loss": 4.2376, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863697560803035e-05, + "loss": 4.2503, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855311613292515e-05, + "loss": 4.2293, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846942044585724e-05, + "loss": 4.2453, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838556097075204e-05, + "loss": 4.2414, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830170149564684e-05, + "loss": 4.2452, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821784202054164e-05, + "loss": 4.236, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813398254543644e-05, + "loss": 4.2395, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380501230703313e-05, + "loss": 4.2281, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379662635952261e-05, + "loss": 4.2398, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378824041201209e-05, + "loss": 4.2374, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.37798708433053e-05, + "loss": 4.2346, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377150127459851e-05, + "loss": 4.2285, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376311532708799e-05, + "loss": 4.2372, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375472937957747e-05, + "loss": 4.2379, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.222952365875244, + "eval_runtime": 293.7245, + "eval_samples_per_second": 1299.146, + "eval_steps_per_second": 40.599, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374634343206695e-05, + "loss": 4.2327, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373795748455643e-05, + "loss": 4.2243, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372957153704591e-05, + "loss": 4.2436, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372120196833912e-05, + "loss": 4.2291, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712832399632333e-05, + "loss": 4.2384, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704446452121813e-05, + "loss": 4.2301, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369606050461129e-05, + "loss": 4.2308, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368767455710077e-05, + "loss": 4.2321, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367928860959025e-05, + "loss": 4.2272, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367091904088346e-05, + "loss": 4.2331, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366253309337294e-05, + "loss": 4.2384, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365414714586242e-05, + "loss": 4.236, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364577757715563e-05, + "loss": 4.2278, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363739162964511e-05, + "loss": 4.2243, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362900568213459e-05, + "loss": 4.2282, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362061973462407e-05, + "loss": 4.2135, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361223378711355e-05, + "loss": 4.2254, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360384783960304e-05, + "loss": 4.2254, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359546189209251e-05, + "loss": 4.2274, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358707594458199e-05, + "loss": 4.2438, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357868999707147e-05, + "loss": 4.2336, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357030404956095e-05, + "loss": 4.2376, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356191810205043e-05, + "loss": 4.2296, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355353215453991e-05, + "loss": 4.2308, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354516258583312e-05, + "loss": 4.2281, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.35367766383226e-05, + "loss": 4.2287, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352839069081208e-05, + "loss": 4.2227, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352000474330156e-05, + "loss": 4.2218, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351161879579104e-05, + "loss": 4.2191, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350323284828052e-05, + "loss": 4.2194, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494863279573736e-05, + "loss": 4.2243, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486477332063216e-05, + "loss": 4.2279, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478091384552696e-05, + "loss": 4.2245, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469705437042175e-05, + "loss": 4.2305, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461319489531655e-05, + "loss": 4.2134, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452949920824865e-05, + "loss": 4.2216, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444563973314344e-05, + "loss": 4.2177, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436178025803824e-05, + "loss": 4.2085, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427792078293304e-05, + "loss": 4.2211, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419422509586514e-05, + "loss": 4.204, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411036562075993e-05, + "loss": 4.2227, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402650614565473e-05, + "loss": 4.2217, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339426466705496e-05, + "loss": 4.2231, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338587871954444e-05, + "loss": 4.2142, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337749277203392e-05, + "loss": 4.2301, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.33691068245234e-05, + "loss": 4.2063, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336073725581661e-05, + "loss": 4.2243, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335235130830609e-05, + "loss": 4.2133, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334396536079557e-05, + "loss": 4.1928, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333557941328505e-05, + "loss": 4.2276, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332720984457826e-05, + "loss": 4.209, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331882389706774e-05, + "loss": 4.216, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331043794955722e-05, + "loss": 4.2031, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330206838085043e-05, + "loss": 4.2026, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293682433339914e-05, + "loss": 4.2087, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285296485829394e-05, + "loss": 4.2103, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3276910538318874e-05, + "loss": 4.2154, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326852459080835e-05, + "loss": 4.2125, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326013864329783e-05, + "loss": 4.2234, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325175269578731e-05, + "loss": 4.2058, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324336674827679e-05, + "loss": 4.1964, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323498080076627e-05, + "loss": 4.2151, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322659485325575e-05, + "loss": 4.1958, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321820890574523e-05, + "loss": 4.1977, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209822958234707e-05, + "loss": 4.2164, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201453389527916e-05, + "loss": 4.2141, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193067442017396e-05, + "loss": 4.1997, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184681494506876e-05, + "loss": 4.2032, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317629554699636e-05, + "loss": 4.192, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316792597828957e-05, + "loss": 4.2023, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315955640958278e-05, + "loss": 4.2145, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315117046207226e-05, + "loss": 4.2104, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314278451456174e-05, + "loss": 4.2096, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313439856705122e-05, + "loss": 4.2076, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.31260126195407e-05, + "loss": 4.2227, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311762667203018e-05, + "loss": 4.1957, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310924072451966e-05, + "loss": 4.2094, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310087115581287e-05, + "loss": 4.2064, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309248520830235e-05, + "loss": 4.184, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308409926079183e-05, + "loss": 4.2126, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075729692085045e-05, + "loss": 4.2092, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067343744574525e-05, + "loss": 4.2061, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058957797064005e-05, + "loss": 4.204, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050571849553485e-05, + "loss": 4.1892, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042185902042965e-05, + "loss": 4.1957, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033799954532445e-05, + "loss": 4.2018, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025430385825654e-05, + "loss": 4.2091, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017044438315134e-05, + "loss": 4.1959, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008658490804614e-05, + "loss": 4.2082, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000272543294094e-05, + "loss": 4.1948, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991886595783574e-05, + "loss": 4.1983, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983500648273054e-05, + "loss": 4.1928, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975114700762534e-05, + "loss": 4.1959, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296674513205575e-05, + "loss": 4.2108, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295835918454523e-05, + "loss": 4.2094, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294997323703471e-05, + "loss": 4.2134, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294158728952418e-05, + "loss": 4.1864, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293320134201366e-05, + "loss": 4.2002, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292481539450314e-05, + "loss": 4.1941, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291642944699262e-05, + "loss": 4.2047, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.29080434994821e-05, + "loss": 4.1956, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289965755197158e-05, + "loss": 4.1949, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289127160446106e-05, + "loss": 4.1878, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288288565695054e-05, + "loss": 4.2035, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287449970944002e-05, + "loss": 4.1817, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286613014073324e-05, + "loss": 4.198, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285776057202645e-05, + "loss": 4.181, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284937462451593e-05, + "loss": 4.2019, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284098867700541e-05, + "loss": 4.1924, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283260272949489e-05, + "loss": 4.1943, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282421678198437e-05, + "loss": 4.1921, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281583083447385e-05, + "loss": 4.1936, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280744488696333e-05, + "loss": 4.1951, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279905893945281e-05, + "loss": 4.1896, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790689370746016e-05, + "loss": 4.1962, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782303423235496e-05, + "loss": 4.2088, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773933854528705e-05, + "loss": 4.1933, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276554790701819e-05, + "loss": 4.1884, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275716195950767e-05, + "loss": 4.1939, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274877601199715e-05, + "loss": 4.193, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274039006448663e-05, + "loss": 4.1871, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273202049577984e-05, + "loss": 4.1953, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272363454826932e-05, + "loss": 4.182, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.27152486007588e-05, + "loss": 4.1984, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270686265324828e-05, + "loss": 4.1975, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269847670573776e-05, + "loss": 4.1902, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269009075822724e-05, + "loss": 4.1805, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681704810716714e-05, + "loss": 4.1869, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673318863206194e-05, + "loss": 4.1863, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266494929449941e-05, + "loss": 4.1958, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.1912, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264817739947837e-05, + "loss": 4.1934, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263979145196785e-05, + "loss": 4.1721, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631421883261065e-05, + "loss": 4.194, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623052314554274e-05, + "loss": 4.1872, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614666367043754e-05, + "loss": 4.1966, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606280419533234e-05, + "loss": 4.1793, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597894472022714e-05, + "loss": 4.1986, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258950852451219e-05, + "loss": 4.1882, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258112257700167e-05, + "loss": 4.1943, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257273662949115e-05, + "loss": 4.182, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256435068198063e-05, + "loss": 4.1965, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255598111327384e-05, + "loss": 4.1738, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254759516576332e-05, + "loss": 4.189, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253922559705654e-05, + "loss": 4.1896, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253083964954602e-05, + "loss": 4.1809, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252245370203549e-05, + "loss": 4.1844, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251408413332871e-05, + "loss": 4.1808, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250569818581819e-05, + "loss": 4.1886, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.180971145629883, + "eval_runtime": 292.488, + "eval_samples_per_second": 1304.638, + "eval_steps_per_second": 40.771, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249731223830766e-05, + "loss": 4.1858, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248892629079714e-05, + "loss": 4.174, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248054034328662e-05, + "loss": 4.1913, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.24721543957761e-05, + "loss": 4.1791, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246376844826558e-05, + "loss": 4.1895, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245538250075506e-05, + "loss": 4.1804, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244699655324455e-05, + "loss": 4.1819, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243861060573403e-05, + "loss": 4.1859, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243022465822351e-05, + "loss": 4.1805, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242185508951672e-05, + "loss": 4.1836, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.24134691420062e-05, + "loss": 4.1891, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240508319449568e-05, + "loss": 4.1868, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239669724698516e-05, + "loss": 4.1802, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388311299474637e-05, + "loss": 4.1758, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379925351964117e-05, + "loss": 4.18, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371539404453596e-05, + "loss": 4.1618, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363153456943076e-05, + "loss": 4.1797, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235476750943255e-05, + "loss": 4.1776, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234638156192203e-05, + "loss": 4.1762, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337995614411516e-05, + "loss": 4.1964, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329609666900996e-05, + "loss": 4.1876, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321223719390476e-05, + "loss": 4.1922, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2312854150683685e-05, + "loss": 4.1775, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304468203173165e-05, + "loss": 4.1829, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296098634466374e-05, + "loss": 4.1804, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287712686955854e-05, + "loss": 4.1792, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279326739445334e-05, + "loss": 4.1775, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270940791934814e-05, + "loss": 4.177, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262554844424294e-05, + "loss": 4.1688, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254168896913774e-05, + "loss": 4.1712, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245782949403254e-05, + "loss": 4.1752, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237397001892734e-05, + "loss": 4.1841, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222902743318595e-05, + "loss": 4.1774, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222064148567543e-05, + "loss": 4.1841, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221225553816491e-05, + "loss": 4.1684, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220386959065439e-05, + "loss": 4.1708, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219548364314387e-05, + "loss": 4.1736, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218711407443708e-05, + "loss": 4.162, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217872812692656e-05, + "loss": 4.1711, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217034217941604e-05, + "loss": 4.1651, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216195623190552e-05, + "loss": 4.173, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153570284395e-05, + "loss": 4.1763, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214520071568821e-05, + "loss": 4.1731, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213681476817769e-05, + "loss": 4.1693, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212842882066717e-05, + "loss": 4.1808, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212004287315665e-05, + "loss": 4.1652, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111656925646134e-05, + "loss": 4.1772, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103270978135614e-05, + "loss": 4.1676, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094901409428823e-05, + "loss": 4.1451, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.20865154619183e-05, + "loss": 4.1889, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207812951440778e-05, + "loss": 4.1605, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206975994570099e-05, + "loss": 4.172, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206137399819047e-05, + "loss": 4.1536, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205298805067995e-05, + "loss": 4.161, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204460210316943e-05, + "loss": 4.1571, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203621615565891e-05, + "loss": 4.1677, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027830208148385e-05, + "loss": 4.1677, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201944426063787e-05, + "loss": 4.1696, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201105831312735e-05, + "loss": 4.1767, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200267236561683e-05, + "loss": 4.1637, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199430279691004e-05, + "loss": 4.1503, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198591684939952e-05, + "loss": 4.1755, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977530901889e-05, + "loss": 4.1509, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196914495437848e-05, + "loss": 4.1485, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196075900686796e-05, + "loss": 4.1718, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195238943816117e-05, + "loss": 4.1714, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194400349065065e-05, + "loss": 4.1544, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193561754314013e-05, + "loss": 4.1622, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192723159562961e-05, + "loss": 4.1474, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191884564811909e-05, + "loss": 4.1587, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910476079412306e-05, + "loss": 4.1672, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902090131901786e-05, + "loss": 4.166, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893704184391266e-05, + "loss": 4.1676, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885318236880746e-05, + "loss": 4.1659, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876932289370226e-05, + "loss": 4.1747, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868546341859706e-05, + "loss": 4.1508, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860160394349186e-05, + "loss": 4.1682, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851790825642395e-05, + "loss": 4.1591, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843404878131875e-05, + "loss": 4.1483, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835018930621355e-05, + "loss": 4.1637, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826632983110834e-05, + "loss": 4.1672, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818263414404044e-05, + "loss": 4.1639, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809877466893524e-05, + "loss": 4.1612, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180149151938301e-05, + "loss": 4.146, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179310557187249e-05, + "loss": 4.1503, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178471962436197e-05, + "loss": 4.1616, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177633367685145e-05, + "loss": 4.1653, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176796410814466e-05, + "loss": 4.1536, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175957816063414e-05, + "loss": 4.1641, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175119221312362e-05, + "loss": 4.1448, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17428062656131e-05, + "loss": 4.1597, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173443669690631e-05, + "loss": 4.1527, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172605074939579e-05, + "loss": 4.155, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171766480188527e-05, + "loss": 4.1684, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170927885437475e-05, + "loss": 4.1681, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170089290686423e-05, + "loss": 4.1689, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1448, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684137390646924e-05, + "loss": 4.1592, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.16757514431364e-05, + "loss": 4.1496, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166736549562588e-05, + "loss": 4.1634, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165897954811536e-05, + "loss": 4.1534, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165059360060484e-05, + "loss": 4.1559, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164220765309432e-05, + "loss": 4.1474, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633838084387526e-05, + "loss": 4.1577, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625452136877006e-05, + "loss": 4.1435, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617066189366486e-05, + "loss": 4.1554, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1608680241855966e-05, + "loss": 4.1398, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600294294345446e-05, + "loss": 4.1615, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159192472563866e-05, + "loss": 4.1497, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158353877812814e-05, + "loss": 4.1525, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157515283061762e-05, + "loss": 4.1489, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1553, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.1541, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154999498808606e-05, + "loss": 4.1485, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154160904057554e-05, + "loss": 4.1572, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153322309306502e-05, + "loss": 4.1645, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152486990316196e-05, + "loss": 4.157, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151648395565144e-05, + "loss": 4.1499, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150809800814092e-05, + "loss": 4.1469, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.14997120606304e-05, + "loss": 4.1542, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149132611311988e-05, + "loss": 4.1448, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482956544413095e-05, + "loss": 4.1568, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474570596902575e-05, + "loss": 4.1396, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466184649392055e-05, + "loss": 4.1591, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457815080685264e-05, + "loss": 4.1553, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449429133174744e-05, + "loss": 4.1515, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441043185664224e-05, + "loss": 4.1408, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432657238153704e-05, + "loss": 4.1461, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424271290643184e-05, + "loss": 4.1446, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415885343132664e-05, + "loss": 4.1582, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407499395622144e-05, + "loss": 4.1518, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399113448111624e-05, + "loss": 4.15, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139074387940483e-05, + "loss": 4.133, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138237431069805e-05, + "loss": 4.1547, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137398836318753e-05, + "loss": 4.1464, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136560241567701e-05, + "loss": 4.1597, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135721646816649e-05, + "loss": 4.1414, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134883052065597e-05, + "loss": 4.1561, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134046095194918e-05, + "loss": 4.1468, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133207500443866e-05, + "loss": 4.1616, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132370543573187e-05, + "loss": 4.1411, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131531948822135e-05, + "loss": 4.1523, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130693354071083e-05, + "loss": 4.1367, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129854759320031e-05, + "loss": 4.1492, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129016164568979e-05, + "loss": 4.1493, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1281775698179273e-05, + "loss": 4.14, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273389750668753e-05, + "loss": 4.1501, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126500380315823e-05, + "loss": 4.139, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125663423445144e-05, + "loss": 4.153, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.150570869445801, + "eval_runtime": 297.8513, + "eval_samples_per_second": 1281.146, + "eval_steps_per_second": 40.037, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124824828694092e-05, + "loss": 4.1462, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12398623394304e-05, + "loss": 4.1353, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123147639191988e-05, + "loss": 4.1527, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223090444409356e-05, + "loss": 4.1399, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214704496898835e-05, + "loss": 4.1514, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206318549388315e-05, + "loss": 4.1447, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119794898068153e-05, + "loss": 4.1449, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118956303317101e-05, + "loss": 4.1474, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118117708566049e-05, + "loss": 4.14, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117279113814997e-05, + "loss": 4.1437, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116440519063945e-05, + "loss": 4.1488, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115601924312893e-05, + "loss": 4.1468, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1147666053225876e-05, + "loss": 4.1457, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139280105715356e-05, + "loss": 4.1361, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113089415820483e-05, + "loss": 4.1378, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112250821069431e-05, + "loss": 4.1295, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111412226318379e-05, + "loss": 4.139, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1105752694477005e-05, + "loss": 4.1423, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109736674696648e-05, + "loss": 4.136, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1088980799455965e-05, + "loss": 4.157, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080594851945445e-05, + "loss": 4.1531, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072208904434925e-05, + "loss": 4.153, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063839335728134e-05, + "loss": 4.1424, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055453388217614e-05, + "loss": 4.141, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047067440707094e-05, + "loss": 4.1486, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038681493196574e-05, + "loss": 4.1382, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030295545686054e-05, + "loss": 4.1383, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102192597697926e-05, + "loss": 4.1453, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101354002946874e-05, + "loss": 4.1296, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100515408195822e-05, + "loss": 4.1324, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.09967681344477e-05, + "loss": 4.1386, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098838218693718e-05, + "loss": 4.1408, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097999623942666e-05, + "loss": 4.1435, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097161029191615e-05, + "loss": 4.1443, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096322434440563e-05, + "loss": 4.1323, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095485477569884e-05, + "loss": 4.1325, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094646882818832e-05, + "loss": 4.1404, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09380828806778e-05, + "loss": 4.1252, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092969693316728e-05, + "loss": 4.1351, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092131098565676e-05, + "loss": 4.1241, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091292503814624e-05, + "loss": 4.1387, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090455546943945e-05, + "loss": 4.1338, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089616952192893e-05, + "loss": 4.137, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088778357441841e-05, + "loss": 4.1374, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087939762690789e-05, + "loss": 4.1394, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871028058201096e-05, + "loss": 4.1302, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086264211069058e-05, + "loss": 4.1385, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085425616318006e-05, + "loss": 4.1322, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084587021566954e-05, + "loss": 4.1102, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837484268159016e-05, + "loss": 4.1501, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829098320648496e-05, + "loss": 4.1227, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820712373137976e-05, + "loss": 4.1354, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081234280443119e-05, + "loss": 4.1224, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803956856920665e-05, + "loss": 4.1233, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0795570909410145e-05, + "loss": 4.1194, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787184961899625e-05, + "loss": 4.1288, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778799014389105e-05, + "loss": 4.1347, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770413066878585e-05, + "loss": 4.1305, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762027119368065e-05, + "loss": 4.1434, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075364117185755e-05, + "loss": 4.134, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074527160315076e-05, + "loss": 4.1105, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073688565564024e-05, + "loss": 4.1352, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072851608693345e-05, + "loss": 4.1186, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072013013942293e-05, + "loss": 4.1099, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071174419191241e-05, + "loss": 4.1423, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070335824440189e-05, + "loss": 4.1321, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069497229689137e-05, + "loss": 4.1182, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068658634938085e-05, + "loss": 4.1275, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067820040187033e-05, + "loss": 4.1141, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066981445435981e-05, + "loss": 4.1214, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661461264456754e-05, + "loss": 4.1296, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653075316946234e-05, + "loss": 4.1315, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0644689369435714e-05, + "loss": 4.1336, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636303421925194e-05, + "loss": 4.1274, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627917474414674e-05, + "loss": 4.1427, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061954790570788e-05, + "loss": 4.1144, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061116195819736e-05, + "loss": 4.1358, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060279238949057e-05, + "loss": 4.1221, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059440644198005e-05, + "loss": 4.1166, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058602049446953e-05, + "loss": 4.1283, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057763454695901e-05, + "loss": 4.1329, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056924859944849e-05, + "loss": 4.1282, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056086265193797e-05, + "loss": 4.1307, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055247670442746e-05, + "loss": 4.108, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054409075691694e-05, + "loss": 4.1136, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053570480940642e-05, + "loss": 4.126, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.05273188618959e-05, + "loss": 4.131, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051893291438538e-05, + "loss": 4.123, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051054696687485e-05, + "loss": 4.1292, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050217739816807e-05, + "loss": 4.1114, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049380782946128e-05, + "loss": 4.1259, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048542188195076e-05, + "loss": 4.1172, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047703593444024e-05, + "loss": 4.1186, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046864998692972e-05, + "loss": 4.1311, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460280418222926e-05, + "loss": 4.1326, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045191084951614e-05, + "loss": 4.1369, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044352490200562e-05, + "loss": 4.114, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04351389544951e-05, + "loss": 4.122, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042675300698458e-05, + "loss": 4.1177, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041836705947406e-05, + "loss": 4.1262, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040998111196354e-05, + "loss": 4.1201, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040159516445302e-05, + "loss": 4.1229, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393209216942495e-05, + "loss": 4.1134, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0384823269431975e-05, + "loss": 4.1194, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376437321921454e-05, + "loss": 4.1164, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368051374410934e-05, + "loss": 4.1189, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0359665426900414e-05, + "loss": 4.1024, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035129585819363e-05, + "loss": 4.1273, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034290991068311e-05, + "loss": 4.117, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0334540341976326e-05, + "loss": 4.1208, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.03261543944658e-05, + "loss": 4.1154, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031776844695528e-05, + "loss": 4.1215, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309398878248495e-05, + "loss": 4.1225, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030101293073797e-05, + "loss": 4.1144, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029262698322745e-05, + "loss": 4.1255, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028424103571693e-05, + "loss": 4.1297, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027585508820641e-05, + "loss": 4.1183, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026746914069589e-05, + "loss": 4.1237, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025908319318537e-05, + "loss": 4.1128, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025069724567485e-05, + "loss": 4.1191, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242327676968064e-05, + "loss": 4.1184, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233941729457544e-05, + "loss": 4.1221, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022557216075075e-05, + "loss": 4.1043, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021718621324023e-05, + "loss": 4.1251, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020880026572971e-05, + "loss": 4.1222, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020041431821919e-05, + "loss": 4.122, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019202837070867e-05, + "loss": 4.1078, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018364242319815e-05, + "loss": 4.1128, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017525647568763e-05, + "loss": 4.1105, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016687052817711e-05, + "loss": 4.1223, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015848458066659e-05, + "loss": 4.1193, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015009863315607e-05, + "loss": 4.1201, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014171268564555e-05, + "loss": 4.0997, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013334311693877e-05, + "loss": 4.1218, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012495716942825e-05, + "loss": 4.1145, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011657122191773e-05, + "loss": 4.1268, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010818527440721e-05, + "loss": 4.1099, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009979932689669e-05, + "loss": 4.1197, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009141337938616e-05, + "loss": 4.1133, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008302743187564e-05, + "loss": 4.13, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007465786316886e-05, + "loss": 4.11, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006627191565833e-05, + "loss": 4.1174, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005788596814781e-05, + "loss": 4.1102, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004950002063729e-05, + "loss": 4.1169, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041130451930506e-05, + "loss": 4.1124, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032744504419986e-05, + "loss": 4.1083, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024358556909466e-05, + "loss": 4.1171, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015972609398946e-05, + "loss": 4.105, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007586661888426e-05, + "loss": 4.1246, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.125660419464111, + "eval_runtime": 300.0087, + "eval_samples_per_second": 1271.933, + "eval_steps_per_second": 39.749, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999200714377906e-05, + "loss": 4.1099, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9990814766867386e-05, + "loss": 4.1059, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9982428819356866e-05, + "loss": 4.1169, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974042871846346e-05, + "loss": 4.1113, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965656924335826e-05, + "loss": 4.1217, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957270976825306e-05, + "loss": 4.1113, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9948885029314786e-05, + "loss": 4.1139, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940499081804266e-05, + "loss": 4.1161, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932113134293746e-05, + "loss": 4.1076, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992372718678322e-05, + "loss": 4.1148, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915341239272706e-05, + "loss": 4.1167, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906955291762185e-05, + "loss": 4.1171, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.98985857230554e-05, + "loss": 4.1167, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890199775544875e-05, + "loss": 4.1006, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881813828034354e-05, + "loss": 4.1091, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873427880523834e-05, + "loss": 4.0948, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865041933013314e-05, + "loss": 4.1108, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856655985502794e-05, + "loss": 4.1104, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848270037992274e-05, + "loss": 4.1038, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839884090481754e-05, + "loss": 4.1238, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831498142971234e-05, + "loss": 4.1204, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982312857426444e-05, + "loss": 4.1208, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981474262675392e-05, + "loss": 4.1151, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.98063566792434e-05, + "loss": 4.1124, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979797073173288e-05, + "loss": 4.118, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978958478422237e-05, + "loss": 4.1054, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978119883671185e-05, + "loss": 4.1062, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977281288920133e-05, + "loss": 4.1126, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976442694169081e-05, + "loss": 4.1008, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975604099418029e-05, + "loss": 4.1009, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.97476714254735e-05, + "loss": 4.1101, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973928547796298e-05, + "loss": 4.1127, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973089953045246e-05, + "loss": 4.1076, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972251358294193e-05, + "loss": 4.1182, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971416039303888e-05, + "loss": 4.1016, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970577444552836e-05, + "loss": 4.1022, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969740487682157e-05, + "loss": 4.1085, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968901892931105e-05, + "loss": 4.0924, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968063298180053e-05, + "loss": 4.1078, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967224703429001e-05, + "loss": 4.0984, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966386108677949e-05, + "loss": 4.1038, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965547513926897e-05, + "loss": 4.106, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964708919175845e-05, + "loss": 4.1062, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963870324424793e-05, + "loss": 4.1076, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630317296737406e-05, + "loss": 4.1088, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621931349226886e-05, + "loss": 4.101, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613545401716366e-05, + "loss": 4.1063, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605159454205845e-05, + "loss": 4.107, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959678988549906e-05, + "loss": 4.0801, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958840393798854e-05, + "loss": 4.115, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958001799047802e-05, + "loss": 4.0951, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95716320429675e-05, + "loss": 4.1083, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956324609545698e-05, + "loss": 4.0928, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955486014794646e-05, + "loss": 4.0908, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954649057923967e-05, + "loss": 4.0919, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953810463172915e-05, + "loss": 4.0938, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952971868421863e-05, + "loss": 4.1086, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952133273670811e-05, + "loss": 4.0957, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951294678919759e-05, + "loss": 4.116, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950456084168707e-05, + "loss": 4.1043, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949619127298028e-05, + "loss": 4.0808, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.1024, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479419377959246e-05, + "loss": 4.0942, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471033430448726e-05, + "loss": 4.0826, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.108, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454277914231415e-05, + "loss": 4.1016, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9445891966720895e-05, + "loss": 4.0898, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437506019210375e-05, + "loss": 4.0988, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429120071699855e-05, + "loss": 4.0811, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420734124189335e-05, + "loss": 4.0936, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412348176678815e-05, + "loss": 4.1006, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403962229168295e-05, + "loss": 4.1002, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939557628165777e-05, + "loss": 4.1069, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.0951, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378820765440464e-05, + "loss": 4.1099, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937045119673368e-05, + "loss": 4.0919, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936206524922316e-05, + "loss": 4.1036, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935367930171264e-05, + "loss": 4.0916, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934529335420212e-05, + "loss": 4.0883, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933692378549533e-05, + "loss": 4.0987, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932855421678854e-05, + "loss": 4.1058, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932016826927802e-05, + "loss": 4.0985, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.93117823217675e-05, + "loss": 4.1024, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930339637425698e-05, + "loss": 4.0784, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929501042674646e-05, + "loss": 4.0842, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928662447923594e-05, + "loss": 4.0989, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927825491052915e-05, + "loss": 4.0986, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926986896301863e-05, + "loss": 4.0924, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926148301550811e-05, + "loss": 4.099, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925309706799759e-05, + "loss": 4.0857, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9244711120487066e-05, + "loss": 4.0947, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236325172976546e-05, + "loss": 4.0885, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922795560426976e-05, + "loss": 4.091, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921956965675924e-05, + "loss": 4.1025, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211183709248715e-05, + "loss": 4.1033, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202797761738195e-05, + "loss": 4.106, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194411814227675e-05, + "loss": 4.0861, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186025866717155e-05, + "loss": 4.0925, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9177639919206635e-05, + "loss": 4.0892, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169253971696115e-05, + "loss": 4.0971, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608680241856e-05, + "loss": 4.0914, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915249845547881e-05, + "loss": 4.0905, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914411250796829e-05, + "loss": 4.0908, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913572656045777e-05, + "loss": 4.0887, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912734061294725e-05, + "loss": 4.0855, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911895466543673e-05, + "loss": 4.0889, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911056871792621e-05, + "loss": 4.0773, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910218277041569e-05, + "loss": 4.0979, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.90938132017089e-05, + "loss": 4.0906, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908542725419838e-05, + "loss": 4.0865, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907704130668786e-05, + "loss": 4.092, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906865535917734e-05, + "loss": 4.0901, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060285790470555e-05, + "loss": 4.0943, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051899842960035e-05, + "loss": 4.0847, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043513895449515e-05, + "loss": 4.0997, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035127947938995e-05, + "loss": 4.0993, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026758379232204e-05, + "loss": 4.0933, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018372431721684e-05, + "loss": 4.0905, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009986484211164e-05, + "loss": 4.0865, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001600536700644e-05, + "loss": 4.087, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993214589190124e-05, + "loss": 4.092, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984828641679604e-05, + "loss": 4.0932, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897644269416908e-05, + "loss": 4.0731, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896807312546229e-05, + "loss": 4.1003, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895968717795177e-05, + "loss": 4.0925, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895130123044125e-05, + "loss": 4.0937, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894291528293073e-05, + "loss": 4.0824, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893452933542021e-05, + "loss": 4.0848, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892614338790969e-05, + "loss": 4.0835, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891775744039917e-05, + "loss": 4.093, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890938787169238e-05, + "loss": 4.0913, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890100192418186e-05, + "loss": 4.0926, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889261597667134e-05, + "loss": 4.0708, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888424640796455e-05, + "loss": 4.0956, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887586046045403e-05, + "loss": 4.0867, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886747451294351e-05, + "loss": 4.101, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0828, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885070261792248e-05, + "loss": 4.0871, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884231667041196e-05, + "loss": 4.09, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883393072290144e-05, + "loss": 4.0978, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882554477539092e-05, + "loss": 4.0817, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817175206684127e-05, + "loss": 4.0917, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808789259173606e-05, + "loss": 4.0852, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800403311663086e-05, + "loss": 4.0938, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792017364152566e-05, + "loss": 4.0819, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0816, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775261847935255e-05, + "loss": 4.0891, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766875900424735e-05, + "loss": 4.0809, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758489952914215e-05, + "loss": 4.094, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.105848789215088, + "eval_runtime": 281.8961, + "eval_samples_per_second": 1353.658, + "eval_steps_per_second": 42.303, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875012038420743e-05, + "loss": 4.0812, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874175081550064e-05, + "loss": 4.0781, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873336486799012e-05, + "loss": 4.0885, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.87249789204796e-05, + "loss": 4.0843, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871659297296908e-05, + "loss": 4.095, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870820702545856e-05, + "loss": 4.0831, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869982107794804e-05, + "loss": 4.0828, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869143513043752e-05, + "loss": 4.0928, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868306556173073e-05, + "loss": 4.0805, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867467961422021e-05, + "loss": 4.0856, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866629366670969e-05, + "loss": 4.089, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86579240980029e-05, + "loss": 4.09, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864953815049238e-05, + "loss": 4.0888, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641152202981865e-05, + "loss": 4.075, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632766255471345e-05, + "loss": 4.0816, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624380307960825e-05, + "loss": 4.0669, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615994360450305e-05, + "loss": 4.0834, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607608412939785e-05, + "loss": 4.0875, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599222465429265e-05, + "loss": 4.0747, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590852896722474e-05, + "loss": 4.0964, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582466949211954e-05, + "loss": 4.091, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857409738050516e-05, + "loss": 4.0913, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856571143299464e-05, + "loss": 4.0905, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855732548548412e-05, + "loss": 4.085, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.85489395379736e-05, + "loss": 4.0882, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854055359046308e-05, + "loss": 4.0859, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853216764295256e-05, + "loss": 4.0736, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852378169544204e-05, + "loss": 4.0883, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851539574793152e-05, + "loss": 4.0724, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507009800421e-05, + "loss": 4.0771, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849862385291048e-05, + "loss": 4.0848, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849023790539996e-05, + "loss": 4.0868, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848186833669317e-05, + "loss": 4.0811, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847348238918265e-05, + "loss": 4.0904, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846509644167213e-05, + "loss": 4.0776, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845671049416161e-05, + "loss": 4.0721, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844832454665109e-05, + "loss": 4.0846, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84399549779443e-05, + "loss": 4.0661, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843156903043379e-05, + "loss": 4.0782, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423199461726996e-05, + "loss": 4.0773, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414813514216476e-05, + "loss": 4.0753, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8406427566705956e-05, + "loss": 4.0794, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398041619195436e-05, + "loss": 4.081, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8389655671684916e-05, + "loss": 4.081, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381269724174396e-05, + "loss": 4.083, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372883776663876e-05, + "loss": 4.0745, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8364514207957085e-05, + "loss": 4.0799, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356128260446565e-05, + "loss": 4.0814, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8347742312936045e-05, + "loss": 4.0572, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339356365425525e-05, + "loss": 4.0869, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8330970417915005e-05, + "loss": 4.069, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322584470404485e-05, + "loss": 4.079, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831419852289397e-05, + "loss": 4.0661, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830581257538345e-05, + "loss": 4.065, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829744300667666e-05, + "loss": 4.0678, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828905705916614e-05, + "loss": 4.0693, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828067111165562e-05, + "loss": 4.0842, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.82722851641451e-05, + "loss": 4.07, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263899216634574e-05, + "loss": 4.0907, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825552964792779e-05, + "loss": 4.0808, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824714370041727e-05, + "loss": 4.0554, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823875775290675e-05, + "loss": 4.0755, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823037180539622e-05, + "loss": 4.0626, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822198585788571e-05, + "loss": 4.0632, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213616289178925e-05, + "loss": 4.0805, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.82052303416684e-05, + "loss": 4.0756, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196860772961614e-05, + "loss": 4.066, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188474825451094e-05, + "loss": 4.0742, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180088877940574e-05, + "loss": 4.0588, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817170293043005e-05, + "loss": 4.0619, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816331698291953e-05, + "loss": 4.0751, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815493103540901e-05, + "loss": 4.0752, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814654508789849e-05, + "loss": 4.0812, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813815914038797e-05, + "loss": 4.0678, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812977319287745e-05, + "loss": 4.0885, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812138724536693e-05, + "loss": 4.0644, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811300129785641e-05, + "loss": 4.0829, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810463172914962e-05, + "loss": 4.0627, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80962457816391e-05, + "loss": 4.0664, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808785983412858e-05, + "loss": 4.0718, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807947388661806e-05, + "loss": 4.0795, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807108793910754e-05, + "loss": 4.0738, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806271837040075e-05, + "loss": 4.0801, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805433242289023e-05, + "loss": 4.0546, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804594647537971e-05, + "loss": 4.0572, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803756052786919e-05, + "loss": 4.0749, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802917458035867e-05, + "loss": 4.0737, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802078863284815e-05, + "loss": 4.066, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801240268533763e-05, + "loss": 4.0739, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800401673782711e-05, + "loss": 4.0675, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799563079031659e-05, + "loss": 4.0665, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798726122160981e-05, + "loss": 4.0646, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797887527409929e-05, + "loss": 4.0652, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797048932658876e-05, + "loss": 4.0781, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962119757881976e-05, + "loss": 4.0811, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953733810371456e-05, + "loss": 4.0822, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945364241664665e-05, + "loss": 4.0605, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7936978294154145e-05, + "loss": 4.0699, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928592346643625e-05, + "loss": 4.0649, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920206399133105e-05, + "loss": 4.075, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791182045162258e-05, + "loss": 4.0708, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7903434504112065e-05, + "loss": 4.0629, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895048556601545e-05, + "loss": 4.067, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886662609091025e-05, + "loss": 4.0609, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878276661580505e-05, + "loss": 4.0644, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869907092873714e-05, + "loss": 4.0656, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861521145363194e-05, + "loss": 4.0564, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853135197852674e-05, + "loss": 4.0706, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7844749250342154e-05, + "loss": 4.0659, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836363302831634e-05, + "loss": 4.0626, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7827977355321114e-05, + "loss": 4.0646, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819591407810594e-05, + "loss": 4.0669, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811205460300074e-05, + "loss": 4.0715, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780285227039702e-05, + "loss": 4.0601, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.77944663228865e-05, + "loss": 4.0755, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778608037537598e-05, + "loss": 4.0747, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777769442786546e-05, + "loss": 4.0714, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776930848035494e-05, + "loss": 4.0669, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776092253284442e-05, + "loss": 4.064, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77525365853339e-05, + "loss": 4.0607, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774415063782338e-05, + "loss": 4.0714, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773578106911659e-05, + "loss": 4.0646, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.77274115004098e-05, + "loss": 4.0541, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771902555289928e-05, + "loss": 4.0758, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7710639605388757e-05, + "loss": 4.0707, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702253657878237e-05, + "loss": 4.0687, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7693867710367717e-05, + "loss": 4.0581, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.76854817628572e-05, + "loss": 4.0584, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767709581534668e-05, + "loss": 4.0596, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766870986783616e-05, + "loss": 4.0711, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766034029912937e-05, + "loss": 4.0674, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765197073042258e-05, + "loss": 4.0729, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764358478291206e-05, + "loss": 4.0462, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763519883540154e-05, + "loss": 4.0756, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762681288789102e-05, + "loss": 4.062, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.76184269403805e-05, + "loss": 4.0748, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761004099286998e-05, + "loss": 4.0627, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760165504535946e-05, + "loss": 4.0579, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759326909784894e-05, + "loss": 4.0673, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758488315033842e-05, + "loss": 4.0771, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757651358163164e-05, + "loss": 4.0603, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756812763412112e-05, + "loss": 4.0697, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75597416866106e-05, + "loss": 4.0612, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755135573910007e-05, + "loss": 4.0679, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754296979158955e-05, + "loss": 4.0594, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753458384407903e-05, + "loss": 4.0587, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752621427537224e-05, + "loss": 4.0656, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751782832786172e-05, + "loss": 4.0584, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.75094423803512e-05, + "loss": 4.0747, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.090492248535156, + "eval_runtime": 278.7772, + "eval_samples_per_second": 1368.803, + "eval_steps_per_second": 42.776, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750105643284068e-05, + "loss": 4.0576, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749267048533016e-05, + "loss": 4.054, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748428453781964e-05, + "loss": 4.0669, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747589859030912e-05, + "loss": 4.0615, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467512642798605e-05, + "loss": 4.0745, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459126695288085e-05, + "loss": 4.0617, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7450740747777565e-05, + "loss": 4.0608, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7442354800267045e-05, + "loss": 4.0695, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433968852756525e-05, + "loss": 4.0573, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425582905246005e-05, + "loss": 4.0568, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417196957735485e-05, + "loss": 4.0695, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740881101022496e-05, + "loss": 4.0678, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400441441518174e-05, + "loss": 4.0666, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392055494007654e-05, + "loss": 4.0517, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738366954649713e-05, + "loss": 4.0593, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737528359898661e-05, + "loss": 4.0435, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736689765147609e-05, + "loss": 4.0631, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358511703965574e-05, + "loss": 4.0664, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735014213525878e-05, + "loss": 4.0493, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734175618774826e-05, + "loss": 4.0723, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733337024023774e-05, + "loss": 4.0723, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732498429272722e-05, + "loss": 4.0681, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.73165983452167e-05, + "loss": 4.067, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730821239770618e-05, + "loss": 4.0625, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729982645019566e-05, + "loss": 4.0656, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729144050268514e-05, + "loss": 4.0621, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728305455517462e-05, + "loss": 4.0525, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.72746686076641e-05, + "loss": 4.0649, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726628266015358e-05, + "loss": 4.0523, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725789671264306e-05, + "loss": 4.0503, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724952714393627e-05, + "loss": 4.0636, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724114119642576e-05, + "loss": 4.0605, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723277162771897e-05, + "loss": 4.0612, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722440205901218e-05, + "loss": 4.0653, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216016111501657e-05, + "loss": 4.053, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7207630163991137e-05, + "loss": 4.054, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199244216480616e-05, + "loss": 4.0609, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190874647773826e-05, + "loss": 4.0437, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182488700263306e-05, + "loss": 4.0554, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174102752752785e-05, + "loss": 4.0553, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165716805242265e-05, + "loss": 4.051, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7157330857731745e-05, + "loss": 4.0592, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7148944910221225e-05, + "loss": 4.0621, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7140558962710705e-05, + "loss": 4.0561, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713217301520019e-05, + "loss": 4.0619, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712378706768967e-05, + "loss": 4.0494, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115401120179145e-05, + "loss": 4.0583, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710703155147236e-05, + "loss": 4.0571, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709864560396184e-05, + "loss": 4.037, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709025965645132e-05, + "loss": 4.0625, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081873708940794e-05, + "loss": 4.0479, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073487761430274e-05, + "loss": 4.0577, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065101813919754e-05, + "loss": 4.046, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056715866409234e-05, + "loss": 4.0408, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704834629770244e-05, + "loss": 4.045, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703996035019193e-05, + "loss": 4.0436, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703157440268141e-05, + "loss": 4.0656, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702318845517089e-05, + "loss": 4.0453, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701480250766037e-05, + "loss": 4.069, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700641656014985e-05, + "loss": 4.0593, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699803061263933e-05, + "loss": 4.0329, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698964466512881e-05, + "loss": 4.0536, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698125871761829e-05, + "loss": 4.0436, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697287277010777e-05, + "loss": 4.038, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696450320140098e-05, + "loss": 4.0558, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695613363269419e-05, + "loss": 4.0569, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694774768518367e-05, + "loss": 4.0441, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693936173767315e-05, + "loss": 4.0555, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693097579016263e-05, + "loss": 4.0358, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6922606221455843e-05, + "loss": 4.0445, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691422027394532e-05, + "loss": 4.0516, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.69058343264348e-05, + "loss": 4.0567, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689744837892428e-05, + "loss": 4.0542, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688906243141376e-05, + "loss": 4.0506, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688067648390324e-05, + "loss": 4.0649, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687229053639272e-05, + "loss": 4.0467, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.68639045888822e-05, + "loss": 4.0595, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855518641371676e-05, + "loss": 4.0398, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847132693861156e-05, + "loss": 4.0458, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683876312515437e-05, + "loss": 4.0489, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683037717764385e-05, + "loss": 4.0543, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682199123013333e-05, + "loss": 4.0551, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681360528262281e-05, + "loss": 4.0572, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680521933511229e-05, + "loss": 4.0394, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679683338760177e-05, + "loss": 4.0316, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678844744009125e-05, + "loss": 4.0543, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678006149258073e-05, + "loss": 4.0508, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677169192387394e-05, + "loss": 4.0463, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676332235516715e-05, + "loss": 4.0528, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675493640765663e-05, + "loss": 4.0479, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674655046014611e-05, + "loss": 4.0426, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738180891439326e-05, + "loss": 4.0448, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729794943928806e-05, + "loss": 4.043, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721408996418286e-05, + "loss": 4.0581, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713023048907766e-05, + "loss": 4.0587, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704637101397246e-05, + "loss": 4.0603, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6696251153886726e-05, + "loss": 4.0373, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6687881585179935e-05, + "loss": 4.0454, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6679495637669415e-05, + "loss": 4.0476, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671109690158895e-05, + "loss": 4.0483, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6662723742648375e-05, + "loss": 4.0515, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6654337795137854e-05, + "loss": 4.0399, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6645951847627334e-05, + "loss": 4.048, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637565900116814e-05, + "loss": 4.0387, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629179952606294e-05, + "loss": 4.0435, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620810383899503e-05, + "loss": 4.0447, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612424436388983e-05, + "loss": 4.0379, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660403848887847e-05, + "loss": 4.0491, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659565254136795e-05, + "loss": 4.0442, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658726659385743e-05, + "loss": 4.0409, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657888064634691e-05, + "loss": 4.0459, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657051107764012e-05, + "loss": 4.0421, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.65621251301296e-05, + "loss": 4.0489, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655375556142281e-05, + "loss": 4.0444, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654536961391229e-05, + "loss": 4.0499, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653698366640177e-05, + "loss": 4.0565, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652859771889125e-05, + "loss": 4.0491, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652021177138073e-05, + "loss": 4.046, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651182582387021e-05, + "loss": 4.0458, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650343987635969e-05, + "loss": 4.0413, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649505392884917e-05, + "loss": 4.0509, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648666798133865e-05, + "loss": 4.0442, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647828203382813e-05, + "loss": 4.0346, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646992884392507e-05, + "loss": 4.0541, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646154289641455e-05, + "loss": 4.0506, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645315694890403e-05, + "loss": 4.0491, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644477100139351e-05, + "loss": 4.0373, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6436385053882986e-05, + "loss": 4.0419, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.64280154851762e-05, + "loss": 4.0361, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641962953766568e-05, + "loss": 4.0535, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641124359015516e-05, + "loss": 4.0456, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640285764264464e-05, + "loss": 4.0509, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639447169513412e-05, + "loss": 4.0227, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.63860857476236e-05, + "loss": 4.0564, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637769980011308e-05, + "loss": 4.0402, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636931385260256e-05, + "loss": 4.0602, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6360960662699506e-05, + "loss": 4.039, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6352574715188986e-05, + "loss": 4.0396, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634418876767846e-05, + "loss": 4.0459, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633580282016794e-05, + "loss": 4.0602, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327433251461155e-05, + "loss": 4.0355, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319047303950635e-05, + "loss": 4.0517, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310661356440115e-05, + "loss": 4.0367, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6302275408929595e-05, + "loss": 4.0502, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293889461419075e-05, + "loss": 4.0382, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6285503513908555e-05, + "loss": 4.0429, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277117566398035e-05, + "loss": 4.0432, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268731618887515e-05, + "loss": 4.038, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260345671376995e-05, + "loss": 4.0519, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.077012538909912, + "eval_runtime": 304.4604, + "eval_samples_per_second": 1253.335, + "eval_steps_per_second": 39.168, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251959723866475e-05, + "loss": 4.0377, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243573776355955e-05, + "loss": 4.0338, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6235187828845435e-05, + "loss": 4.046, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6226818260138644e-05, + "loss": 4.0385, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6218432312628124e-05, + "loss": 4.0546, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210046365117604e-05, + "loss": 4.0439, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6201660417607084e-05, + "loss": 4.041, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6193274470096564e-05, + "loss": 4.0498, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618490490138978e-05, + "loss": 4.0393, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617651895387926e-05, + "loss": 4.0352, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616813300636874e-05, + "loss": 4.0522, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615976343766195e-05, + "loss": 4.0447, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615137749015143e-05, + "loss": 4.0507, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614299154264091e-05, + "loss": 4.0303, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613460559513039e-05, + "loss": 4.0344, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612621964761987e-05, + "loss": 4.0277, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611783370010935e-05, + "loss": 4.0437, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610944775259882e-05, + "loss": 4.041, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61010618050883e-05, + "loss": 4.035, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609267585757778e-05, + "loss": 4.0465, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608428991006727e-05, + "loss": 4.0578, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607590396255675e-05, + "loss": 4.0458, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606753439384996e-05, + "loss": 4.0462, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605914844633944e-05, + "loss": 4.045, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605076249882892e-05, + "loss": 4.048, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.60423765513184e-05, + "loss": 4.0407, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603399060380788e-05, + "loss": 4.0326, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602560465629736e-05, + "loss": 4.0451, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601721870878684e-05, + "loss": 4.0328, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008849140080046e-05, + "loss": 4.0322, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6000463192569526e-05, + "loss": 4.0433, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992077245059006e-05, + "loss": 4.0393, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5983691297548486e-05, + "loss": 4.0441, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5975305350037966e-05, + "loss": 4.0455, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596693578133118e-05, + "loss": 4.0359, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595854983382066e-05, + "loss": 4.0365, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595016388631014e-05, + "loss": 4.0389, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594177793879962e-05, + "loss": 4.025, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.59333919912891e-05, + "loss": 4.0401, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592500604377858e-05, + "loss": 4.0311, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591662009626806e-05, + "loss": 4.0326, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590825052756127e-05, + "loss": 4.0387, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589986458005075e-05, + "loss": 4.047, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589147863254023e-05, + "loss": 4.0313, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588309268502971e-05, + "loss": 4.0425, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874706737519184e-05, + "loss": 4.0366, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.58663371688124e-05, + "loss": 4.033, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857951221301886e-05, + "loss": 4.0391, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849581652595095e-05, + "loss": 4.0197, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841195705084575e-05, + "loss": 4.04, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5832809757574055e-05, + "loss": 4.0322, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824423810063535e-05, + "loss": 4.0406, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581603786255301e-05, + "loss": 4.0265, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580765191504249e-05, + "loss": 4.0192, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579926596753197e-05, + "loss": 4.0266, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790896398825184e-05, + "loss": 4.022, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578251045131466e-05, + "loss": 4.0497, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577414088260787e-05, + "loss": 4.0262, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576575493509735e-05, + "loss": 4.0495, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575736898758683e-05, + "loss": 4.0387, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574898304007631e-05, + "loss": 4.0175, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574059709256579e-05, + "loss": 4.0331, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573221114505527e-05, + "loss": 4.0257, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572382519754475e-05, + "loss": 4.0205, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571543925003423e-05, + "loss": 4.0361, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570705330252371e-05, + "loss": 4.0385, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569868373381692e-05, + "loss": 4.024, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569031416511013e-05, + "loss": 4.0377, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568192821759961e-05, + "loss": 4.0139, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567354227008909e-05, + "loss": 4.0273, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566515632257858e-05, + "loss": 4.0324, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565677037506806e-05, + "loss": 4.0389, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564838442755754e-05, + "loss": 4.0339, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563999848004702e-05, + "loss": 4.0284, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563162891134023e-05, + "loss": 4.0459, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562324296382971e-05, + "loss": 4.0296, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561485701631919e-05, + "loss": 4.0395, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5606471068808667e-05, + "loss": 4.0236, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598085121298147e-05, + "loss": 4.0272, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589699173787627e-05, + "loss": 4.0285, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581329605080836e-05, + "loss": 4.034, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5572943657570316e-05, + "loss": 4.0343, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5564557710059796e-05, + "loss": 4.041, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556171762549275e-05, + "loss": 4.0222, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547785815038755e-05, + "loss": 4.0121, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553939986752824e-05, + "loss": 4.0303, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553101392001772e-05, + "loss": 4.0368, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522627972507195e-05, + "loss": 4.0279, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514242024996675e-05, + "loss": 4.0347, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505856077486155e-05, + "loss": 4.0285, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549748650877937e-05, + "loss": 4.0239, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548911694007258e-05, + "loss": 4.0272, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548073099256206e-05, + "loss": 4.024, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547234504505154e-05, + "loss": 4.0363, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546395909754102e-05, + "loss": 4.0414, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.54555731500305e-05, + "loss": 4.0429, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544718720251998e-05, + "loss": 4.019, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543880125500946e-05, + "loss": 4.0315, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543041530749894e-05, + "loss": 4.0236, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542202935998842e-05, + "loss": 4.0317, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.54136434124779e-05, + "loss": 4.0344, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540525746496738e-05, + "loss": 4.0224, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539687151745686e-05, + "loss": 4.0281, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538848556994634e-05, + "loss": 4.022, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538011600123955e-05, + "loss": 4.0246, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537174643253276e-05, + "loss": 4.0273, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536336048502224e-05, + "loss": 4.0195, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535497453751172e-05, + "loss": 4.0281, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.53465885900012e-05, + "loss": 4.0295, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5338219021294414e-05, + "loss": 4.0209, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5329833073783894e-05, + "loss": 4.0265, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5321447126273373e-05, + "loss": 4.0272, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313061178762853e-05, + "loss": 4.0319, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5304675231252333e-05, + "loss": 4.0268, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529628928374181e-05, + "loss": 4.0273, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528790333623129e-05, + "loss": 4.0379, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527951738872077e-05, + "loss": 4.0377, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527113144121025e-05, + "loss": 4.0246, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526276187250346e-05, + "loss": 4.0284, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525437592499294e-05, + "loss": 4.02, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524598997748242e-05, + "loss": 4.0334, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.52376040299719e-05, + "loss": 4.0269, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522921808246138e-05, + "loss": 4.017, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52208485137546e-05, + "loss": 4.035, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521246256624408e-05, + "loss": 4.0333, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520407661873356e-05, + "loss": 4.0283, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519569067122303e-05, + "loss": 4.0238, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518730472371251e-05, + "loss": 4.0193, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517891877620199e-05, + "loss": 4.0162, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517053282869147e-05, + "loss": 4.0341, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516214688118095e-05, + "loss": 4.0278, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153793691277896e-05, + "loss": 4.0349, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145424122571105e-05, + "loss": 4.01, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137038175060585e-05, + "loss": 4.0315, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512865222755007e-05, + "loss": 4.0263, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512026628003955e-05, + "loss": 4.0348, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511188033252903e-05, + "loss": 4.0228, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103494385018505e-05, + "loss": 4.0214, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095108437507985e-05, + "loss": 4.0286, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086722489997465e-05, + "loss": 4.0393, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078336542486945e-05, + "loss": 4.0215, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069966973780154e-05, + "loss": 4.0314, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061581026269634e-05, + "loss": 4.0218, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053195078759114e-05, + "loss": 4.0281, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044809131248594e-05, + "loss": 4.0222, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036423183738074e-05, + "loss": 4.0227, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028037236227554e-05, + "loss": 4.0237, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501965128871704e-05, + "loss": 4.025, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501126534120652e-05, + "loss": 4.0312, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.065519332885742, + "eval_runtime": 306.4933, + "eval_samples_per_second": 1245.022, + "eval_steps_per_second": 38.908, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002879393696e-05, + "loss": 4.0384, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499449344618548e-05, + "loss": 4.009, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498610749867496e-05, + "loss": 4.0277, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497772155116444e-05, + "loss": 4.0245, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496933560365392e-05, + "loss": 4.0322, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496094965614339e-05, + "loss": 4.0301, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495256370863287e-05, + "loss": 4.0215, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494417776112235e-05, + "loss": 4.031, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493579181361183e-05, + "loss": 4.022, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492740586610131e-05, + "loss": 4.0226, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491901991859079e-05, + "loss": 4.0308, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491063397108027e-05, + "loss": 4.0285, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490226440237349e-05, + "loss": 4.0327, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489387845486297e-05, + "loss": 4.013, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488549250735245e-05, + "loss": 4.0149, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487710655984193e-05, + "loss": 4.0128, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486872061233141e-05, + "loss": 4.0273, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486033466482089e-05, + "loss": 4.0209, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485194871731037e-05, + "loss": 4.0201, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484356276979985e-05, + "loss": 4.0279, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483517682228933e-05, + "loss": 4.0421, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482680725358254e-05, + "loss": 4.0282, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481842130607202e-05, + "loss": 4.0274, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48100353585615e-05, + "loss": 4.0287, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480164941105098e-05, + "loss": 4.0334, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479326346354046e-05, + "loss": 4.0218, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478489389483367e-05, + "loss": 4.0142, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477650794732315e-05, + "loss": 4.0295, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476812199981263e-05, + "loss": 4.0099, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759736052302106e-05, + "loss": 4.0172, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751350104791586e-05, + "loss": 4.0253, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47429805360848e-05, + "loss": 4.0216, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473459458857428e-05, + "loss": 4.0304, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726208641063755e-05, + "loss": 4.0238, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717822693553235e-05, + "loss": 4.0214, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.470945312484645e-05, + "loss": 4.0195, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470106717733593e-05, + "loss": 4.0224, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469268122982541e-05, + "loss": 4.0066, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468429528231489e-05, + "loss": 4.0236, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467590933480437e-05, + "loss": 4.0134, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466753976609758e-05, + "loss": 4.0171, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465915381858706e-05, + "loss": 4.0214, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465076787107654e-05, + "loss": 4.0299, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464238192356602e-05, + "loss": 4.0131, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46339959760555e-05, + "loss": 4.0236, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462562640734871e-05, + "loss": 4.0207, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461724045983819e-05, + "loss": 4.014, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460885451232767e-05, + "loss": 4.0254, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460046856481715e-05, + "loss": 4.0052, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592098996110365e-05, + "loss": 4.018, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583713048599845e-05, + "loss": 4.0195, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575327101089325e-05, + "loss": 4.0222, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566941153578805e-05, + "loss": 4.0109, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558555206068285e-05, + "loss": 4.005, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550185637361494e-05, + "loss": 4.0077, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.45418160686547e-05, + "loss": 4.003, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453343012114418e-05, + "loss": 4.0359, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452504417363366e-05, + "loss": 4.0081, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451665822612314e-05, + "loss": 4.0322, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450827227861262e-05, + "loss": 4.0216, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44998863311021e-05, + "loss": 4.0027, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449150038359158e-05, + "loss": 4.0148, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448311443608106e-05, + "loss": 4.0099, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447472848857054e-05, + "loss": 4.0057, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446634254106003e-05, + "loss": 4.0148, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445795659354951e-05, + "loss": 4.0226, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444957064603899e-05, + "loss": 4.0109, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444121745613593e-05, + "loss": 4.0196, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443283150862541e-05, + "loss": 3.9963, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442444556111489e-05, + "loss": 4.0088, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441605961360437e-05, + "loss": 4.0155, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440767366609385e-05, + "loss": 4.0238, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439928771858333e-05, + "loss": 4.0208, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439090177107281e-05, + "loss": 4.014, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438251582356229e-05, + "loss": 4.0234, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437412987605177e-05, + "loss": 4.0118, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436576030734498e-05, + "loss": 4.023, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435739073863819e-05, + "loss": 4.0095, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434900479112767e-05, + "loss": 4.0148, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434061884361715e-05, + "loss": 4.0091, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433223289610663e-05, + "loss": 4.0161, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432384694859611e-05, + "loss": 4.0236, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431546100108559e-05, + "loss": 4.0229, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307075053575065e-05, + "loss": 4.0103, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298689106064545e-05, + "loss": 3.993, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290303158554025e-05, + "loss": 4.0167, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281917211043505e-05, + "loss": 4.0168, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427354764233672e-05, + "loss": 4.0121, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42651616948262e-05, + "loss": 4.0177, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4256792126119416e-05, + "loss": 4.0137, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424840617860889e-05, + "loss": 4.0055, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424002023109837e-05, + "loss": 4.0135, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423163428358785e-05, + "loss": 4.0088, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422324833607733e-05, + "loss": 4.0171, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 4.0237, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420647644105629e-05, + "loss": 4.0269, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.41981068723495e-05, + "loss": 4.0034, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418972092483898e-05, + "loss": 4.0147, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418133497732846e-05, + "loss": 4.0121, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417294902981794e-05, + "loss": 4.0137, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416456308230742e-05, + "loss": 4.0172, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156177134796905e-05, + "loss": 4.0065, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147791187286385e-05, + "loss": 4.0106, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139405239775865e-05, + "loss": 4.005, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131019292265345e-05, + "loss": 4.0128, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122633344754825e-05, + "loss": 4.0096, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114247397244305e-05, + "loss": 4.0045, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4105877828537514e-05, + "loss": 4.0144, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4097491881026994e-05, + "loss": 4.0084, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4089105933516474e-05, + "loss": 4.0058, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408071998600595e-05, + "loss": 4.0115, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407233403849543e-05, + "loss": 4.0074, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406394809098491e-05, + "loss": 4.0191, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405557852227812e-05, + "loss": 4.0116, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.40471925747676e-05, + "loss": 4.0127, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403880662725708e-05, + "loss": 4.0177, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403042067974656e-05, + "loss": 4.0242, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402205111103978e-05, + "loss": 4.0098, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401366516352925e-05, + "loss": 4.0131, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400527921601873e-05, + "loss": 4.0072, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399689326850821e-05, + "loss": 4.017, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398850732099769e-05, + "loss": 4.0133, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39801377522909e-05, + "loss": 4.0009, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3971768183584117e-05, + "loss": 4.0151, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963382236073596e-05, + "loss": 4.0183, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3954996288563076e-05, + "loss": 4.0148, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946610341052556e-05, + "loss": 4.0065, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 4.0021, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3929838446031516e-05, + "loss": 4.0039, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921452498520996e-05, + "loss": 4.0219, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913066551010476e-05, + "loss": 4.009, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904696982303685e-05, + "loss": 4.0181, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 3.9944, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887941466086374e-05, + "loss": 4.0159, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879555518575854e-05, + "loss": 4.0141, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871169571065334e-05, + "loss": 4.0194, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862783623554814e-05, + "loss": 4.0075, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854397676044294e-05, + "loss": 4.0073, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846011728533774e-05, + "loss": 4.0114, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383762578102326e-05, + "loss": 4.0263, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382923983351274e-05, + "loss": 4.0062, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382087026480595e-05, + "loss": 4.0158, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381248431729543e-05, + "loss": 4.0092, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380409836978491e-05, + "loss": 4.0143, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379571242227439e-05, + "loss": 4.0041, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378732647476387e-05, + "loss": 4.0123, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377895690605708e-05, + "loss": 4.0037, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377058733735029e-05, + "loss": 4.0081, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376220138983977e-05, + "loss": 4.017, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.056612968444824, + "eval_runtime": 311.6695, + "eval_samples_per_second": 1224.345, + "eval_steps_per_second": 38.262, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375381544232925e-05, + "loss": 4.01, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374542949481873e-05, + "loss": 3.9974, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3737043547308215e-05, + "loss": 4.0103, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728657599797694e-05, + "loss": 4.0178, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720271652287174e-05, + "loss": 4.0124, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3711885704776654e-05, + "loss": 4.0169, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3703499757266134e-05, + "loss": 4.0036, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3695130188559343e-05, + "loss": 4.0173, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3686744241048823e-05, + "loss": 4.0049, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.36783582935383e-05, + "loss": 4.0061, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366997234602778e-05, + "loss": 4.0133, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3661586398517256e-05, + "loss": 4.0111, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365321682981047e-05, + "loss": 4.0209, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364483088229995e-05, + "loss": 3.9972, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363644493478943e-05, + "loss": 3.9978, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362805898727891e-05, + "loss": 4.0006, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361967303976839e-05, + "loss": 4.0111, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361128709225787e-05, + "loss": 4.0046, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360291752355109e-05, + "loss": 4.0038, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359453157604056e-05, + "loss": 4.0149, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358614562853004e-05, + "loss": 4.0221, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357775968101952e-05, + "loss": 4.0178, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3569373733509e-05, + "loss": 4.0115, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356098778599848e-05, + "loss": 4.0126, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355260183848796e-05, + "loss": 4.0165, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354421589097744e-05, + "loss": 4.0095, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353584632227065e-05, + "loss": 3.9974, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352746037476014e-05, + "loss": 4.0176, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3519090806053346e-05, + "loss": 3.9916, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3510704858542826e-05, + "loss": 4.0029, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502318911032306e-05, + "loss": 4.0067, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493932963521786e-05, + "loss": 4.0116, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485547016011266e-05, + "loss": 4.0128, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477161068500746e-05, + "loss": 4.0096, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468775120990226e-05, + "loss": 4.007, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3460405552283435e-05, + "loss": 4.0038, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452019604772915e-05, + "loss": 4.003, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443633657262395e-05, + "loss": 3.9904, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435247709751875e-05, + "loss": 4.0096, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342687814104509e-05, + "loss": 4.0004, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341849219353457e-05, + "loss": 4.004, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 4.005, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340172029851353e-05, + "loss": 4.0141, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339333435100301e-05, + "loss": 4.0014, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338494840349249e-05, + "loss": 4.0094, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337656245598197e-05, + "loss": 4.0057, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336817650847144e-05, + "loss": 4.0007, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335980693976466e-05, + "loss": 4.0062, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335142099225414e-05, + "loss": 3.9922, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334303504474362e-05, + "loss": 4.0022, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333464909723309e-05, + "loss": 4.0083, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332626314972257e-05, + "loss": 4.0041, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331787720221205e-05, + "loss": 3.9945, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330949125470154e-05, + "loss": 3.9868, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330110530719102e-05, + "loss": 3.9961, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329273573848423e-05, + "loss": 3.9877, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328434979097371e-05, + "loss": 4.0224, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327596384346319e-05, + "loss": 3.9904, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326757789595267e-05, + "loss": 4.0201, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325919194844215e-05, + "loss": 4.0034, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325080600093163e-05, + "loss": 3.9888, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324242005342111e-05, + "loss": 3.9972, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323405048471432e-05, + "loss": 3.9958, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.32256645372038e-05, + "loss": 3.9949, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321727858969328e-05, + "loss": 3.9965, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320889264218276e-05, + "loss": 4.0093, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320050669467224e-05, + "loss": 3.9993, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319212074716172e-05, + "loss": 3.9987, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318375117845493e-05, + "loss": 3.9858, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317536523094441e-05, + "loss": 3.9943, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316697928343389e-05, + "loss": 3.9983, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315859333592337e-05, + "loss": 4.0121, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315020738841285e-05, + "loss": 4.0046, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314182144090233e-05, + "loss": 3.9997, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3133435493391805e-05, + "loss": 4.0076, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3125049545881285e-05, + "loss": 4.0022, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3116663598370765e-05, + "loss": 4.0033, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310829402966398e-05, + "loss": 3.9952, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.309990808215346e-05, + "loss": 4.0025, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309152213464294e-05, + "loss": 3.9928, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308315256593616e-05, + "loss": 4.0022, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307476661842564e-05, + "loss": 4.0098, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306638067091511e-05, + "loss": 4.0073, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305799472340459e-05, + "loss": 3.9957, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304960877589407e-05, + "loss": 3.9744, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304122282838355e-05, + "loss": 4.0027, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303285325967676e-05, + "loss": 4.0022, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302446731216624e-05, + "loss": 3.9989, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301608136465572e-05, + "loss": 3.9978, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.30076954171452e-05, + "loss": 4.0043, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299930946963468e-05, + "loss": 3.9903, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299092352212416e-05, + "loss": 3.9978, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2982537574613646e-05, + "loss": 3.9933, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2974151627103126e-05, + "loss": 4.003, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2965782058396335e-05, + "loss": 4.0096, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2957396110885815e-05, + "loss": 4.0108, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2949010163375295e-05, + "loss": 3.993, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2940624215864775e-05, + "loss": 3.9993, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2932254647157984e-05, + "loss": 3.9985, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2923868699647464e-05, + "loss": 4.0002, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2915482752136944e-05, + "loss": 4.0006, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2907096804626423e-05, + "loss": 3.9933, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2898710857115903e-05, + "loss": 3.9945, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890324909605383e-05, + "loss": 3.9896, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288195534089859e-05, + "loss": 4.0015, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287356939338808e-05, + "loss": 3.9886, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286518344587756e-05, + "loss": 3.9919, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285679749836704e-05, + "loss": 3.9988, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284841155085652e-05, + "loss": 3.9928, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284002560334599e-05, + "loss": 3.9928, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283163965583547e-05, + "loss": 4.0027, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282325370832495e-05, + "loss": 3.9896, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281488413961817e-05, + "loss": 4.0018, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280649819210764e-05, + "loss": 3.9968, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279812862340086e-05, + "loss": 3.9948, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278974267589034e-05, + "loss": 4.0027, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278135672837982e-05, + "loss": 4.0099, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27729707808693e-05, + "loss": 3.9982, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276458483335878e-05, + "loss": 3.9976, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275619888584826e-05, + "loss": 3.9908, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274781293833774e-05, + "loss": 4.0012, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273942699082722e-05, + "loss": 3.9958, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2731057422120426e-05, + "loss": 3.9916, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2722671474609906e-05, + "loss": 3.997, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2714301905903115e-05, + "loss": 4.007, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2705915958392595e-05, + "loss": 3.9963, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2697530010882075e-05, + "loss": 3.9943, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2689144063371555e-05, + "loss": 3.9872, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2680758115861035e-05, + "loss": 3.9887, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672372168350515e-05, + "loss": 4.0019, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266400259964373e-05, + "loss": 3.9958, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265561665213321e-05, + "loss": 4.006, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264723070462269e-05, + "loss": 3.9804, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.26388611359159e-05, + "loss": 4.0008, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263047518840538e-05, + "loss": 3.9992, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262208924089486e-05, + "loss": 4.0018, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261370329338434e-05, + "loss": 3.9901, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260531734587382e-05, + "loss": 3.9927, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25969313983633e-05, + "loss": 4.0032, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258854545085278e-05, + "loss": 4.0089, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258017588214599e-05, + "loss": 3.9934, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257178993463547e-05, + "loss": 3.997, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563403987124955e-05, + "loss": 3.9941, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2555018039614435e-05, + "loss": 3.998, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2546632092103915e-05, + "loss": 3.9915, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2538246144593395e-05, + "loss": 3.9968, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2529860197082875e-05, + "loss": 3.9903, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2521474249572355e-05, + "loss": 3.9946, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251308830206183e-05, + "loss": 3.9986, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.048257350921631, + "eval_runtime": 310.6587, + "eval_samples_per_second": 1228.329, + "eval_steps_per_second": 38.386, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250470235455131e-05, + "loss": 3.9842, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249631640704079e-05, + "loss": 3.9892, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248793045953027e-05, + "loss": 3.9921, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247954451201975e-05, + "loss": 4.0004, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247115856450923e-05, + "loss": 3.9984, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246277261699871e-05, + "loss": 4.003, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245438666948819e-05, + "loss": 3.9876, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244600072197767e-05, + "loss": 4.0002, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243761477446715e-05, + "loss": 3.9921, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2429228826956634e-05, + "loss": 3.9929, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2420842879446114e-05, + "loss": 3.9953, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2412456931935594e-05, + "loss": 3.9998, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2404087363228803e-05, + "loss": 4.0083, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239570141571828e-05, + "loss": 3.9875, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238731546820776e-05, + "loss": 3.9771, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237892952069724e-05, + "loss": 3.9874, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2370543573186716e-05, + "loss": 3.9926, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2362157625676196e-05, + "loss": 3.9937, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353771678165676e-05, + "loss": 3.9887, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2345385730655156e-05, + "loss": 3.9975, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2336999783144636e-05, + "loss": 4.0108, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2328613835634116e-05, + "loss": 3.9988, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232024426692733e-05, + "loss": 4.001, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231185831941681e-05, + "loss": 3.9978, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230347237190629e-05, + "loss": 4.0022, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229508642439577e-05, + "loss": 3.9915, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228671685568898e-05, + "loss": 3.9906, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227833090817846e-05, + "loss": 3.9975, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.226994496066794e-05, + "loss": 3.9812, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226155901315742e-05, + "loss": 3.9851, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22531730656469e-05, + "loss": 3.9931, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224480349694011e-05, + "loss": 3.9961, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223641754942959e-05, + "loss": 4.0036, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222803160191907e-05, + "loss": 3.9879, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221964565440856e-05, + "loss": 4.0001, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2211276085701766e-05, + "loss": 3.9866, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2202890138191246e-05, + "loss": 3.986, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2194504190680726e-05, + "loss": 3.9789, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2186118243170206e-05, + "loss": 3.9941, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2177732295659686e-05, + "loss": 3.9835, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2169362726952895e-05, + "loss": 3.9886, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2160976779442375e-05, + "loss": 3.992, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2152590831931855e-05, + "loss": 4.0014, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2144204884421335e-05, + "loss": 3.9841, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135818936910814e-05, + "loss": 3.9937, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127432989400294e-05, + "loss": 3.994, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119047041889774e-05, + "loss": 3.9848, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110661094379254e-05, + "loss": 3.9932, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210229152567247e-05, + "loss": 3.9799, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209392195696568e-05, + "loss": 3.984, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208553600945516e-05, + "loss": 3.9984, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207715006194464e-05, + "loss": 3.9872, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206876411443412e-05, + "loss": 3.9816, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.20603781669236e-05, + "loss": 3.9701, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205200859821681e-05, + "loss": 3.9873, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204362265070629e-05, + "loss": 3.9699, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203523670319577e-05, + "loss": 4.0097, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202685075568525e-05, + "loss": 3.979, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201846480817473e-05, + "loss": 4.0083, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201007886066421e-05, + "loss": 3.9907, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200169291315369e-05, + "loss": 3.9731, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199330696564317e-05, + "loss": 3.9838, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198493739693638e-05, + "loss": 3.9874, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197655144942586e-05, + "loss": 3.9774, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196816550191534e-05, + "loss": 3.9756, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195977955440482e-05, + "loss": 3.9989, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.19513936068943e-05, + "loss": 3.9901, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1943024038187506e-05, + "loss": 3.9799, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1934638090676986e-05, + "loss": 3.9729, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1926252143166466e-05, + "loss": 3.9801, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917866195655946e-05, + "loss": 3.9846, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909480248145426e-05, + "loss": 3.9974, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190112705824238e-05, + "loss": 3.9891, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189274111073185e-05, + "loss": 3.9892, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188435516322133e-05, + "loss": 3.993, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1875985594514547e-05, + "loss": 3.9874, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867599647004027e-05, + "loss": 3.9916, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.18592136994935e-05, + "loss": 3.9821, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185082775198298e-05, + "loss": 3.9889, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184244180447246e-05, + "loss": 3.9813, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183405585696194e-05, + "loss": 3.9848, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182566990945142e-05, + "loss": 3.9951, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18172839619409e-05, + "loss": 3.9978, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180889801443038e-05, + "loss": 3.9815, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800512066919866e-05, + "loss": 3.9648, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792126119409346e-05, + "loss": 3.9926, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783740171898826e-05, + "loss": 3.9838, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1775354224388306e-05, + "loss": 3.9909, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1766968276877786e-05, + "loss": 3.9838, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1758582329367266e-05, + "loss": 3.9889, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175019638185674e-05, + "loss": 3.9816, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1741826813149955e-05, + "loss": 3.9805, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1733440865639435e-05, + "loss": 3.9814, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1725071296932644e-05, + "loss": 3.9881, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1716685349422124e-05, + "loss": 3.9966, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1708299401911604e-05, + "loss": 3.9984, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1699913454401084e-05, + "loss": 3.9815, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1691527506890564e-05, + "loss": 3.9845, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683141559380044e-05, + "loss": 3.9876, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674755611869524e-05, + "loss": 3.9897, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166638604316274e-05, + "loss": 3.9845, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165800009565221e-05, + "loss": 3.982, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164961414814169e-05, + "loss": 3.9837, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164122820063117e-05, + "loss": 3.9733, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163284225312065e-05, + "loss": 3.9926, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162445630561013e-05, + "loss": 3.9718, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161607035809961e-05, + "loss": 3.9781, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160768441058909e-05, + "loss": 3.9906, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.15993148418823e-05, + "loss": 3.9812, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159092889437179e-05, + "loss": 3.9774, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158254294686127e-05, + "loss": 3.9912, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157415699935075e-05, + "loss": 3.9764, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156577105184023e-05, + "loss": 3.9904, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155738510432971e-05, + "loss": 3.9839, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154899915681919e-05, + "loss": 3.9833, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154061320930867e-05, + "loss": 3.9896, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1532260019405606e-05, + "loss": 3.9941, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1523890450698815e-05, + "loss": 3.988, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1515504503188295e-05, + "loss": 3.9815, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1507118555677775e-05, + "loss": 3.9804, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1498732608167255e-05, + "loss": 3.9888, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149034666065674e-05, + "loss": 3.9818, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148196071314622e-05, + "loss": 3.9814, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147359114443943e-05, + "loss": 3.9823, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146520519692891e-05, + "loss": 3.9906, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145681924941839e-05, + "loss": 3.9841, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144843330190787e-05, + "loss": 3.9827, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144004735439735e-05, + "loss": 3.9752, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143166140688683e-05, + "loss": 3.9784, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142327545937631e-05, + "loss": 3.9834, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141488951186579e-05, + "loss": 3.9864, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140653632196273e-05, + "loss": 3.9891, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139815037445221e-05, + "loss": 3.9713, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389764426941696e-05, + "loss": 3.9902, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381378479431176e-05, + "loss": 3.9859, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1372992531920656e-05, + "loss": 3.9889, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1364606584410136e-05, + "loss": 3.9765, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356220636899616e-05, + "loss": 3.9825, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347834689389095e-05, + "loss": 3.9886, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339448741878575e-05, + "loss": 3.9955, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133106279436805e-05, + "loss": 3.9812, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132267684685753e-05, + "loss": 3.9814, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131429089934701e-05, + "loss": 3.9845, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1305921330640224e-05, + "loss": 3.9834, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1297551761933434e-05, + "loss": 3.9782, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1289165814422913e-05, + "loss": 3.9881, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1280779866912393e-05, + "loss": 3.9752, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127239391940187e-05, + "loss": 3.9887, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126400797189135e-05, + "loss": 3.981, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.041386127471924, + "eval_runtime": 286.8969, + "eval_samples_per_second": 1330.063, + "eval_steps_per_second": 41.565, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125562202438083e-05, + "loss": 3.9833, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124723607687031e-05, + "loss": 3.9778, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123886650816352e-05, + "loss": 3.9772, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230480560653e-05, + "loss": 3.9887, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122209461314248e-05, + "loss": 3.9866, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121370866563196e-05, + "loss": 3.9922, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120532271812144e-05, + "loss": 3.9766, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119693677061092e-05, + "loss": 3.9899, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118858358070787e-05, + "loss": 3.9779, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118019763319735e-05, + "loss": 3.9827, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117181168568683e-05, + "loss": 3.9813, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116342573817631e-05, + "loss": 3.9899, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115503979066579e-05, + "loss": 3.9896, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146670221958996e-05, + "loss": 3.9807, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138284274448476e-05, + "loss": 3.9701, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129898326937956e-05, + "loss": 3.9754, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121512379427436e-05, + "loss": 3.9741, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113126431916916e-05, + "loss": 3.9804, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1104740484406396e-05, + "loss": 3.9788, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1096354536895876e-05, + "loss": 3.982, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1087968589385356e-05, + "loss": 4.0006, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079599020678565e-05, + "loss": 3.9855, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107121307316805e-05, + "loss": 3.9897, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106282712565753e-05, + "loss": 3.9867, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105444117814701e-05, + "loss": 3.9935, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104605523063649e-05, + "loss": 3.9763, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.10376856619297e-05, + "loss": 3.9802, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102931609322291e-05, + "loss": 3.9849, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102093014571239e-05, + "loss": 3.9741, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101254419820187e-05, + "loss": 3.9691, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100415825069135e-05, + "loss": 3.9797, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099577230318083e-05, + "loss": 3.9875, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098738635567031e-05, + "loss": 3.9868, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097901678696352e-05, + "loss": 3.9798, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970630839453005e-05, + "loss": 3.9873, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962244891942485e-05, + "loss": 3.976, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953858944431965e-05, + "loss": 3.9743, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0945472996921445e-05, + "loss": 3.9663, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937087049410925e-05, + "loss": 3.9833, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928701101900405e-05, + "loss": 3.9709, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920315154389885e-05, + "loss": 3.9794, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091192920687936e-05, + "loss": 3.977, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0903559638172574e-05, + "loss": 3.9929, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0895173690662054e-05, + "loss": 3.9703, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088678774315153e-05, + "loss": 3.9827, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087840179564101e-05, + "loss": 3.9835, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087001584813049e-05, + "loss": 3.9691, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0861629900619974e-05, + "loss": 3.9861, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085326033191318e-05, + "loss": 3.9683, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084487438440266e-05, + "loss": 3.9741, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9833, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9768, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.9719, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9581, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080294464685006e-05, + "loss": 3.9768, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079455869933954e-05, + "loss": 3.9591, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078620550943648e-05, + "loss": 3.9957, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077781956192596e-05, + "loss": 3.9707, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076943361441544e-05, + "loss": 3.9889, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076104766690493e-05, + "loss": 3.9841, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075266171939441e-05, + "loss": 3.9643, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074427577188389e-05, + "loss": 3.9688, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073588982437337e-05, + "loss": 3.9764, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072750387686285e-05, + "loss": 3.9666, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719134308156056e-05, + "loss": 3.9632, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710748360645536e-05, + "loss": 3.9883, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702378791938745e-05, + "loss": 3.9832, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0693992844428225e-05, + "loss": 3.9692, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685623275721434e-05, + "loss": 3.9567, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677237328210914e-05, + "loss": 3.9678, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668851380700394e-05, + "loss": 3.9725, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066046543318988e-05, + "loss": 3.9882, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065207948567936e-05, + "loss": 3.9773, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064369353816884e-05, + "loss": 3.9773, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063530759065832e-05, + "loss": 3.9768, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.06269216431478e-05, + "loss": 3.9808, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061853569563728e-05, + "loss": 3.9752, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061016612693049e-05, + "loss": 3.9731, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060178017941997e-05, + "loss": 3.9821, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059339423190945e-05, + "loss": 3.9682, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058500828439893e-05, + "loss": 3.9727, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057662233688841e-05, + "loss": 3.9828, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056825276818162e-05, + "loss": 3.9813, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.05598668206711e-05, + "loss": 3.9717, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055148087316058e-05, + "loss": 3.9527, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054309492565006e-05, + "loss": 3.9771, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534708978139546e-05, + "loss": 3.9749, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052632303062902e-05, + "loss": 3.975, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0517953461922235e-05, + "loss": 3.9761, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509583893215444e-05, + "loss": 3.9769, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501197945704924e-05, + "loss": 3.9691, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492811998194404e-05, + "loss": 3.9648, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484426050683884e-05, + "loss": 3.97, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476040103173363e-05, + "loss": 3.9779, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046765415566284e-05, + "loss": 3.9826, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.045926820815232e-05, + "loss": 3.9825, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.04508822606418e-05, + "loss": 3.9787, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442512691935016e-05, + "loss": 3.969, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043412674442449e-05, + "loss": 3.9751, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425740796913972e-05, + "loss": 3.9786, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417354849403452e-05, + "loss": 3.9758, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0408968901892932e-05, + "loss": 3.9716, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400582954382412e-05, + "loss": 3.9699, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392197006871892e-05, + "loss": 3.9593, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.03838274381651e-05, + "loss": 3.9828, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037544149065458e-05, + "loss": 3.9572, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036705554314406e-05, + "loss": 3.9688, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358669595633545e-05, + "loss": 3.9777, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035031640573049e-05, + "loss": 3.973, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341930458219963e-05, + "loss": 3.9669, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333544510709443e-05, + "loss": 3.9737, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325158563198926e-05, + "loss": 3.9702, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316772615688406e-05, + "loss": 3.9768, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308386668177886e-05, + "loss": 3.9733, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0300017099471095e-05, + "loss": 3.972, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291631151960575e-05, + "loss": 3.9778, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283245204450055e-05, + "loss": 3.985, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274859256939535e-05, + "loss": 3.9738, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266473309429015e-05, + "loss": 3.968, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258087361918498e-05, + "loss": 3.9729, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249701414407978e-05, + "loss": 3.9753, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241315466897458e-05, + "loss": 3.9686, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232929519386938e-05, + "loss": 3.9685, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224559950680147e-05, + "loss": 3.9727, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216174003169627e-05, + "loss": 3.983, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207788055659107e-05, + "loss": 3.9728, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019940210814859e-05, + "loss": 3.9726, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019101616063807e-05, + "loss": 3.9642, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018264659193128e-05, + "loss": 3.9713, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017426064442076e-05, + "loss": 3.9681, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016587469691024e-05, + "loss": 3.9801, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015748874939972e-05, + "loss": 3.9772, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.01491028018892e-05, + "loss": 3.9588, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140716854378676e-05, + "loss": 3.973, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132330906868156e-05, + "loss": 3.9784, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0123961338161372e-05, + "loss": 3.9773, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011557539065085e-05, + "loss": 3.9684, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107189443140328e-05, + "loss": 3.9693, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098803495629808e-05, + "loss": 3.9786, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090417548119288e-05, + "loss": 3.9847, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082047979412497e-05, + "loss": 3.971, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073662031901977e-05, + "loss": 3.9708, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065276084391457e-05, + "loss": 3.9729, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056890136880937e-05, + "loss": 3.9699, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004850418937042e-05, + "loss": 3.97, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.00401182418599e-05, + "loss": 3.9802, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003174867315311e-05, + "loss": 3.9639, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002336272564259e-05, + "loss": 3.975, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.00149931569358e-05, + "loss": 3.9691, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006607209425282e-05, + "loss": 3.9739, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.035419464111328, + "eval_runtime": 288.1032, + "eval_samples_per_second": 1324.494, + "eval_steps_per_second": 41.391, + "step": 1221120 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 5.0175504094938035e+17, + "trial_name": null, + "trial_params": null +}