diff --git "a/checkpoint-839520/trainer_state.json" "b/checkpoint-839520/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-839520/trainer_state.json" @@ -0,0 +1,9947 @@ +{ + "best_metric": 4.056793212890625, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/lstm/2/checkpoints/checkpoint-839520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 839520, + "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": 10.8197, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5521, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.055, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9903, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9127, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.7893, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.6787, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.5934, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.4969, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4322, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3551, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.2878, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2252, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1543, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1155, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0618, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0314, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.9886, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9447, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.909, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.8728, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8364, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.8061, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7687, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7504, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7207, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.6917, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6699, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6434, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6267, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.608, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.589, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.567, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5462, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5416, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5324, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5062, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4663, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.9681399509815164e-05, + "loss": 5.4706, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.9673013562304644e-05, + "loss": 5.4407, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.9664627614794124e-05, + "loss": 5.4422, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4263, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4138, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.39, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3948, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3814, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 5.3798, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 5.3627, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 5.3421, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 5.3365, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 5.3372, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 5.3141, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 5.3066, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 5.2921, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 5.2884, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2723, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 5.2861, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 5.2478, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 5.254, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 5.2463, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 5.2257, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2266, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 5.2152, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 5.1986, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 5.1905, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2068, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 5.1829, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1734, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1549, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1639, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.169, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1524, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1471, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1519, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.141, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1282, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1085, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 5.1141, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 5.0984, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.0965, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.0886, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0864, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 5.0949, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 5.0836, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 5.0569, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.058, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0608, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0565, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0469, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0413, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.0343, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.0202, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0263, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0195, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.01, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0176, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.9972, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.995, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.9826, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.979, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.9872, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.9711, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.9666, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.963, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.9619, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9448, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9344, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9413, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9454, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.9375, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.9334, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9196, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9248, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9116, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9156, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9107, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9085, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.9015, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.8954, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9019, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.8983, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8866, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.8888, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8787, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.8807, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.8623, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.8581, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8618, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8636, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8535, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.8648, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.8558, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.8395, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8449, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8492, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8403, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8382, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8276, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.831, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8344, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8169, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8109, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8156, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.8081, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.8056, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.8091, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.7984, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.7961, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.7904, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.757678985595703, + "eval_runtime": 298.6287, + "eval_samples_per_second": 1277.811, + "eval_steps_per_second": 39.933, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.7842, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.7871, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.7943, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7826, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7804, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7766, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.7783, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.756, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7801, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.7654, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.7728, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.7702, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.7496, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.7515, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.7467, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.7426, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.7496, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7371, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.735, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.7534, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7375, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.7314, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.7243, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7398, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.7181, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.7138, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.7151, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.717, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.7084, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.7087, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7105, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.7103, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.6968, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.7088, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.7102, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.703, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.6744, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.6842, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.6823, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.6873, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.6796, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.6811, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6701, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6835, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6773, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.6793, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.6784, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6585, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.666, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.6713, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.665, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.662, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.6512, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.6566, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.6417, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.6714, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6421, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6518, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6519, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.629, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6453, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6375, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.623, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.6229, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6421, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.6293, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.6201, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.6159, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6285, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6356, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.6277, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.6203, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.81389748048138e-05, + "loss": 4.6345, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813058885730328e-05, + "loss": 4.6283, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.625, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811383334108597e-05, + "loss": 4.6052, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.6161, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.6097, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.6055, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.608, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.6064, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.6206, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.6147, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.5908, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.5979, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.5992, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.601, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.5996, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.5971, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.5922, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.5822, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.5948, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.586, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.5866, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.593, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.5834, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.5772, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5748, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.5793, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912668873655876e-05, + "loss": 4.5829, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904282926145356e-05, + "loss": 4.5699, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895896978634836e-05, + "loss": 4.5684, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.5695, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.5703, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5602, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5457, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5638, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.564, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5603, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5599, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.5536, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.559, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.5477, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.5508, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786896039801804e-05, + "loss": 4.5556, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778510092291284e-05, + "loss": 4.5554, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.5478, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.5466, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.5535, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.5532, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.5392, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5515, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5374, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5503, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5291, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5284, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.5325, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.5393, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5282, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.76611559635552e-05, + "loss": 4.5464, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765277001604468e-05, + "loss": 4.5351, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.5268, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.5299, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5393, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5313, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5303, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760248708858902e-05, + "loss": 4.5232, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941011410785e-05, + "loss": 4.5256, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5312, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5183, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5164, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5221, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755218778232963e-05, + "loss": 4.512, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754380183481911e-05, + "loss": 4.5129, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.5205, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.75270463186018e-05, + "loss": 4.5119, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751866037109128e-05, + "loss": 4.5122, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751027442358077e-05, + "loss": 4.511, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.5063, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.477365493774414, + "eval_runtime": 296.8326, + "eval_samples_per_second": 1285.543, + "eval_steps_per_second": 40.174, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.4996, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.5067, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.5177, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.5074, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5066, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.5014, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.5079, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.4869, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.5106, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.5058, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.503, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.5119, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392887537237216e-05, + "loss": 4.4868, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.492, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4978, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.48, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4917, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350974178488345e-05, + "loss": 4.4807, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342588230977825e-05, + "loss": 4.4837, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334202283467305e-05, + "loss": 4.5048, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325816335956784e-05, + "loss": 4.4858, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317430388446264e-05, + "loss": 4.4865, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730904444093574e-05, + "loss": 4.4758, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730065849342522e-05, + "loss": 4.4946, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292272545914704e-05, + "loss": 4.471, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283886598404184e-05, + "loss": 4.4721, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727551702969739e-05, + "loss": 4.4708, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4808, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4682, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4693, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4776, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723358729214479e-05, + "loss": 4.4793, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722520134463427e-05, + "loss": 4.4609, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721683177592748e-05, + "loss": 4.4756, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720844582841696e-05, + "loss": 4.4771, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720005988090644e-05, + "loss": 4.4712, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719167393339592e-05, + "loss": 4.448, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71832879858854e-05, + "loss": 4.4629, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717490203837488e-05, + "loss": 4.4505, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716651609086437e-05, + "loss": 4.4663, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715813014335385e-05, + "loss": 4.457, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4613, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4508, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4598, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712461911091923e-05, + "loss": 4.4602, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.4607, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4627, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4401, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4485, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4643, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4473, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4493, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.70575479096388e-05, + "loss": 4.4439, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704916196212828e-05, + "loss": 4.4471, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040776014617755e-05, + "loss": 4.4357, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032390067107235e-05, + "loss": 4.4544, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.4403, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4428, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4522, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4245, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4423, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982107139651573e-05, + "loss": 4.4347, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697372119214106e-05, + "loss": 4.4272, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.4236, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.4386, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.69485633496095e-05, + "loss": 4.4338, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694017740209898e-05, + "loss": 4.4218, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693179145458846e-05, + "loss": 4.4187, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692340550707794e-05, + "loss": 4.4365, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691503593837115e-05, + "loss": 4.4454, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690664999086063e-05, + "loss": 4.4308, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689828042215384e-05, + "loss": 4.4303, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4407, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.4371, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.4386, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864753010915494e-05, + "loss": 4.4137, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4292, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4302, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.4157, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831209220873414e-05, + "loss": 4.4256, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4218, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814437325852373e-05, + "loss": 4.4366, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806051378341853e-05, + "loss": 4.4279, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679768180963506e-05, + "loss": 4.4095, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4176, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4173, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.422, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4205, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4167, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4139, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4058, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673062698715837e-05, + "loss": 4.419, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4074, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.4143, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4186, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4114, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668869724960576e-05, + "loss": 4.4055, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668031130209524e-05, + "loss": 4.4047, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.4062, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.66635394070742e-05, + "loss": 4.4117, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655169838367416e-05, + "loss": 4.4014, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646783890856896e-05, + "loss": 4.3995, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638397943346376e-05, + "loss": 4.3975, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630011995835856e-05, + "loss": 4.4038, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621626048325336e-05, + "loss": 4.3944, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.3822, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660488691091176e-05, + "loss": 4.3935, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596500963401234e-05, + "loss": 4.4003, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.3931, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.4, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.3866, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.3963, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554571225848634e-05, + "loss": 4.3873, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.3862, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.3986, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652942976212081e-05, + "loss": 4.3957, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3887, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.389, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650430467719671e-05, + "loss": 4.3896, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649591872968619e-05, + "loss": 4.3942, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648753278217567e-05, + "loss": 4.3831, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.3949, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.3838, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646237493964411e-05, + "loss": 4.3949, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645398899213359e-05, + "loss": 4.3699, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644560304462307e-05, + "loss": 4.3811, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643723347591628e-05, + "loss": 4.376, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642886390720949e-05, + "loss": 4.3848, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642047795969897e-05, + "loss": 4.3764, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3957, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3834, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639532011716741e-05, + "loss": 4.3777, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638693416965689e-05, + "loss": 4.3732, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637854822214637e-05, + "loss": 4.3878, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.3827, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.3843, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.375, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.3774, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633661848459377e-05, + "loss": 4.3846, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632826529469072e-05, + "loss": 4.3724, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.63198793471802e-05, + "loss": 4.3692, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631149339966968e-05, + "loss": 4.3794, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630310745215916e-05, + "loss": 4.3692, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629472150464864e-05, + "loss": 4.3659, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628633555713812e-05, + "loss": 4.3723, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277949609627597e-05, + "loss": 4.3761, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626956366211707e-05, + "loss": 4.3674, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261194093410286e-05, + "loss": 4.3658, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252808145899766e-05, + "loss": 4.3601, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.34266996383667, + "eval_runtime": 350.4175, + "eval_samples_per_second": 1088.961, + "eval_steps_per_second": 34.031, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244422198389246e-05, + "loss": 4.3672, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236036250878726e-05, + "loss": 4.3628, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227650303368205e-05, + "loss": 4.3776, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219264355857685e-05, + "loss": 4.3644, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210878408347165e-05, + "loss": 4.3686, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202508839640374e-05, + "loss": 4.3615, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194122892129854e-05, + "loss": 4.368, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185736944619334e-05, + "loss": 4.3516, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.3734, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.3672, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3684, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615220953338098e-05, + "loss": 4.376, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.61438399646742e-05, + "loss": 4.3485, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613545401716368e-05, + "loss": 4.3567, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612706806965316e-05, + "loss": 4.3638, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611868212214264e-05, + "loss": 4.3513, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611029617463212e-05, + "loss": 4.3541, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.61019102271216e-05, + "loss": 4.3472, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609354065841481e-05, + "loss": 4.3524, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608515471090429e-05, + "loss": 4.3743, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607676876339377e-05, + "loss": 4.3526, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606838281588325e-05, + "loss": 4.354, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.605999686837273e-05, + "loss": 4.3467, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605161092086221e-05, + "loss": 4.3599, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604322497335169e-05, + "loss": 4.3442, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603483902584117e-05, + "loss": 4.3416, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602645307833065e-05, + "loss": 4.3448, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601806713082013e-05, + "loss": 4.3531, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009697562113344e-05, + "loss": 4.3366, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3444, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.3457, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984539719581783e-05, + "loss": 4.3524, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976153772071257e-05, + "loss": 4.3413, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967767824560737e-05, + "loss": 4.3471, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595939825585395e-05, + "loss": 4.351, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595101230834343e-05, + "loss": 4.3468, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942626360832906e-05, + "loss": 4.3245, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934240413322386e-05, + "loss": 4.3411, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925854465811865e-05, + "loss": 4.3249, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917468518301345e-05, + "loss": 4.3439, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590908257079083e-05, + "loss": 4.3308, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590071300208404e-05, + "loss": 4.3404, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589232705457352e-05, + "loss": 4.3329, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.334, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587557153835621e-05, + "loss": 4.3403, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586718559084569e-05, + "loss": 4.3365, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.3407, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.326, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3268, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583365817960734e-05, + "loss": 4.3436, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582527223209682e-05, + "loss": 4.3312, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58168862845863e-05, + "loss": 4.3262, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808500337075786e-05, + "loss": 4.3269, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800114389565266e-05, + "loss": 4.33, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791728442054746e-05, + "loss": 4.3173, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783342494544226e-05, + "loss": 4.3369, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774956547033706e-05, + "loss": 4.3233, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766570599523186e-05, + "loss": 4.3282, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758184652012666e-05, + "loss": 4.3342, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749798704502146e-05, + "loss": 4.3136, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574141275699162e-05, + "loss": 4.3197, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.57330268094811e-05, + "loss": 4.3223, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724657240774315e-05, + "loss": 4.3122, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716271293263794e-05, + "loss": 4.3112, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570788534575327e-05, + "loss": 4.3211, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699499398242754e-05, + "loss": 4.3222, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691113450732234e-05, + "loss": 4.3082, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.3062, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.3206, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.3296, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565760241829762e-05, + "loss": 4.317, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564921647078709e-05, + "loss": 4.3232, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564083052327657e-05, + "loss": 4.3261, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563244457576605e-05, + "loss": 4.3286, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562407500705927e-05, + "loss": 4.3293, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561568905954874e-05, + "loss": 4.3023, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560730311203822e-05, + "loss": 4.3178, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559891716452771e-05, + "loss": 4.3236, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559054759582092e-05, + "loss": 4.3036, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.55821616483104e-05, + "loss": 4.3203, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557377570079988e-05, + "loss": 4.312, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556538975328936e-05, + "loss": 4.3264, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555700380577884e-05, + "loss": 4.3211, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554861785826832e-05, + "loss": 4.2996, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55402319107578e-05, + "loss": 4.3118, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553184596324728e-05, + "loss": 4.3068, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523476394540486e-05, + "loss": 4.3126, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515090447029966e-05, + "loss": 4.3157, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506720878323175e-05, + "loss": 4.3083, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.3081, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.3018, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.3093, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.301, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546479114077058e-05, + "loss": 4.3112, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545640519326006e-05, + "loss": 4.3154, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544801924574954e-05, + "loss": 4.3064, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543963329823902e-05, + "loss": 4.2982, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54312473507285e-05, + "loss": 4.3042, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542286140321798e-05, + "loss": 4.3013, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414475455707455e-05, + "loss": 4.3081, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406089508196934e-05, + "loss": 4.3029, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539771993949015e-05, + "loss": 4.298, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538935037078336e-05, + "loss": 4.2912, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538096442327284e-05, + "loss": 4.306, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372578475762326e-05, + "loss": 4.2866, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364192528251806e-05, + "loss": 4.2854, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535580658074128e-05, + "loss": 4.2913, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534742063323076e-05, + "loss": 4.2969, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533903468572024e-05, + "loss": 4.2935, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330665117013455e-05, + "loss": 4.3062, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532227916950293e-05, + "loss": 4.2879, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531389322199241e-05, + "loss": 4.2887, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530550727448189e-05, + "loss": 4.2922, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529712132697137e-05, + "loss": 4.2808, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528875175826458e-05, + "loss": 4.3047, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280365810754064e-05, + "loss": 4.2974, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5271979863243544e-05, + "loss": 4.2925, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263593915733024e-05, + "loss": 4.2943, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255207968222504e-05, + "loss": 4.2854, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524683839951571e-05, + "loss": 4.2975, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523845245200519e-05, + "loss": 4.2868, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523006650449467e-05, + "loss": 4.3015, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.2846, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521331098827736e-05, + "loss": 4.2941, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.2801, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519653909325632e-05, + "loss": 4.2849, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.51881531457458e-05, + "loss": 4.2778, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517978357703902e-05, + "loss": 4.2916, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.51713976295285e-05, + "loss": 4.2798, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516301168201798e-05, + "loss": 4.2986, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515462573450746e-05, + "loss": 4.2914, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146256165800667e-05, + "loss": 4.2862, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137870218290147e-05, + "loss": 4.2751, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129484270779626e-05, + "loss": 4.2913, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121098323269106e-05, + "loss": 4.2872, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.294, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104326428248066e-05, + "loss": 4.2812, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095956859541275e-05, + "loss": 4.2815, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087570912030755e-05, + "loss": 4.2884, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.2845, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507081539581345e-05, + "loss": 4.274, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506242944830293e-05, + "loss": 4.2863, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505404350079241e-05, + "loss": 4.2774, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504565755328189e-05, + "loss": 4.2749, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503727160577137e-05, + "loss": 4.2802, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502888565826085e-05, + "loss": 4.286, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502049971075033e-05, + "loss": 4.2729, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501211376323981e-05, + "loss": 4.2711, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500372781572929e-05, + "loss": 4.2774, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.260177135467529, + "eval_runtime": 348.7269, + "eval_samples_per_second": 1094.24, + "eval_steps_per_second": 34.196, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995341868218764e-05, + "loss": 4.2707, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986955920708244e-05, + "loss": 4.2732, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978569973197724e-05, + "loss": 4.286, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970184025687204e-05, + "loss": 4.2736, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961798078176684e-05, + "loss": 4.2836, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953412130666164e-05, + "loss": 4.2715, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494502618315565e-05, + "loss": 4.2764, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493664023564513e-05, + "loss": 4.2641, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492825428813461e-05, + "loss": 4.2867, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491986834062409e-05, + "loss": 4.2767, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491148239311357e-05, + "loss": 4.2769, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490309644560305e-05, + "loss": 4.289, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489472687689626e-05, + "loss": 4.2609, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488634092938574e-05, + "loss": 4.2719, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487795498187522e-05, + "loss": 4.2757, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48695690343647e-05, + "loss": 4.2631, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486118308685418e-05, + "loss": 4.266, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485279713934365e-05, + "loss": 4.2619, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484441119183313e-05, + "loss": 4.2681, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483602524432262e-05, + "loss": 4.2835, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.48276392968121e-05, + "loss": 4.2675, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2682, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481088378059479e-05, + "loss": 4.2622, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480249783308427e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479411188557375e-05, + "loss": 4.2597, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478572593806323e-05, + "loss": 4.258, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477733999055271e-05, + "loss": 4.2563, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476895404304219e-05, + "loss": 4.267, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476056809553167e-05, + "loss": 4.2527, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.2634, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474381257931436e-05, + "loss": 4.2613, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473542663180384e-05, + "loss": 4.2686, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472705706309705e-05, + "loss": 4.257, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471867111558653e-05, + "loss": 4.2629, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471028516807601e-05, + "loss": 4.2681, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470189922056549e-05, + "loss": 4.2634, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469351327305497e-05, + "loss": 4.2463, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468512732554445e-05, + "loss": 4.2546, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467674137803393e-05, + "loss": 4.2444, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466835543052341e-05, + "loss": 4.259, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2498, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2585, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2517, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2559, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2583, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618088881871486e-05, + "loss": 4.255, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609702934360966e-05, + "loss": 4.2607, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601316986850446e-05, + "loss": 4.25, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592931039339926e-05, + "loss": 4.2392, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2632, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2501, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2464, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455938724929784e-05, + "loss": 4.2463, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551017680591055e-05, + "loss": 4.252, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542648111884264e-05, + "loss": 4.2359, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534262164373744e-05, + "loss": 4.2568, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452589259566696e-05, + "loss": 4.244, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451750664815644e-05, + "loss": 4.2489, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450912070064592e-05, + "loss": 4.2579, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.45007347531354e-05, + "loss": 4.2388, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449234880562488e-05, + "loss": 4.2372, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448396285811436e-05, + "loss": 4.2515, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447557691060384e-05, + "loss": 4.231, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446719096309331e-05, + "loss": 4.2342, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445880501558279e-05, + "loss": 4.2433, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445043544687601e-05, + "loss": 4.246, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444204949936548e-05, + "loss": 4.231, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443366355185496e-05, + "loss": 4.2302, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442527760434444e-05, + "loss": 4.2411, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441689165683393e-05, + "loss": 4.2499, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2456, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2438, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.43917501931061e-05, + "loss": 4.2509, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2479, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2579, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436659235057454e-05, + "loss": 4.2275, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.2435, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43498204555535e-05, + "loss": 4.2461, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434143450804298e-05, + "loss": 4.2268, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333081318139916e-05, + "loss": 4.2473, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324695370629396e-05, + "loss": 4.2367, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431630942311888e-05, + "loss": 4.2485, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430792347560836e-05, + "loss": 4.25, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429953752809784e-05, + "loss": 4.2258, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429115158058732e-05, + "loss": 4.2395, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42827656330768e-05, + "loss": 4.2304, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427437968556628e-05, + "loss": 4.2407, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426599373805576e-05, + "loss": 4.2403, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425765692695643e-05, + "loss": 4.2337, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424927097944591e-05, + "loss": 4.2352, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424088503193539e-05, + "loss": 4.2318, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423249908442487e-05, + "loss": 4.2329, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422411313691435e-05, + "loss": 4.2296, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157599470113e-05, + "loss": 4.2408, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420737399950078e-05, + "loss": 4.242, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419898805199026e-05, + "loss": 4.232, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190602104479734e-05, + "loss": 4.225, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182216156969214e-05, + "loss": 4.2305, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173830209458694e-05, + "loss": 4.2313, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165444261948174e-05, + "loss": 4.2383, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157058314437654e-05, + "loss": 4.2314, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148672366927134e-05, + "loss": 4.2253, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414030279822034e-05, + "loss": 4.2194, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413191685070982e-05, + "loss": 4.2324, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41235309031993e-05, + "loss": 4.2171, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411514495568879e-05, + "loss": 4.2196, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410675900817827e-05, + "loss": 4.2144, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409837306066775e-05, + "loss": 4.2287, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408998711315723e-05, + "loss": 4.2187, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408160116564671e-05, + "loss": 4.2377, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407321521813619e-05, + "loss": 4.2159, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406482927062567e-05, + "loss": 4.2213, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405645970191888e-05, + "loss": 4.2243, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404807375440836e-05, + "loss": 4.2107, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403968780689784e-05, + "loss": 4.2341, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403130185938732e-05, + "loss": 4.2291, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402293229068053e-05, + "loss": 4.2235, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401454634317001e-05, + "loss": 4.2235, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400616039565949e-05, + "loss": 4.2177, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399777444814897e-05, + "loss": 4.2295, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398938850063845e-05, + "loss": 4.2126, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398100255312793e-05, + "loss": 4.235, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397261660561741e-05, + "loss": 4.2206, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396423065810689e-05, + "loss": 4.2217, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3955861089400096e-05, + "loss": 4.2163, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394749152069331e-05, + "loss": 4.2163, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393910557318279e-05, + "loss": 4.2074, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930719625672265e-05, + "loss": 4.2256, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392235005696548e-05, + "loss": 4.2134, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391396410945496e-05, + "loss": 4.2296, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390557816194444e-05, + "loss": 4.2232, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389719221443392e-05, + "loss": 4.2219, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.38888062669234e-05, + "loss": 4.2077, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388043669821662e-05, + "loss": 4.2243, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387205075070609e-05, + "loss": 4.2208, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386366480319557e-05, + "loss": 4.2259, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385527885568505e-05, + "loss": 4.2145, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384689290817453e-05, + "loss": 4.2145, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383850696066401e-05, + "loss": 4.2209, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383012101315349e-05, + "loss": 4.2242, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382173506564297e-05, + "loss": 4.2077, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381334911813245e-05, + "loss": 4.2222, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380496317062193e-05, + "loss": 4.2079, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379657722311141e-05, + "loss": 4.2106, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788207654404625e-05, + "loss": 4.2203, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779821706894105e-05, + "loss": 4.2141, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771435759383585e-05, + "loss": 4.2108, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763049811873065e-05, + "loss": 4.2076, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754663864362545e-05, + "loss": 4.2116, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.202938079833984, + "eval_runtime": 293.1754, + "eval_samples_per_second": 1301.579, + "eval_steps_per_second": 40.675, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746277916852025e-05, + "loss": 4.211, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737891969341505e-05, + "loss": 4.2058, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372950602183098e-05, + "loss": 4.2229, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721136453124194e-05, + "loss": 4.213, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3712750505613674e-05, + "loss": 4.2145, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704364558103154e-05, + "loss": 4.2131, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369597861059263e-05, + "loss": 4.2082, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368760904188584e-05, + "loss": 4.2025, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367922309437533e-05, + "loss": 4.2167, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367083714686481e-05, + "loss": 4.218, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366245119935428e-05, + "loss": 4.2135, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365406525184376e-05, + "loss": 4.2232, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364572844074444e-05, + "loss": 4.1978, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363734249323392e-05, + "loss": 4.2091, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36289565457234e-05, + "loss": 4.2155, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362057059821288e-05, + "loss": 4.1974, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361218465070236e-05, + "loss": 4.2045, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360379870319184e-05, + "loss": 4.2004, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359541275568132e-05, + "loss": 4.204, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35870268081708e-05, + "loss": 4.2185, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578640860660284e-05, + "loss": 4.2088, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357025491314976e-05, + "loss": 4.2084, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356186896563924e-05, + "loss": 4.1979, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355349939693245e-05, + "loss": 4.2141, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545113449421926e-05, + "loss": 4.1957, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536727501911406e-05, + "loss": 4.1956, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528341554400886e-05, + "loss": 4.1979, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519955606890366e-05, + "loss": 4.2039, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511569659379846e-05, + "loss": 4.1899, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503183711869326e-05, + "loss": 4.2007, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494797764358805e-05, + "loss": 4.2047, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486411816848285e-05, + "loss": 4.2052, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478025869337765e-05, + "loss": 4.1981, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346965630063098e-05, + "loss": 4.2006, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346127035312046e-05, + "loss": 4.2082, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345288440560994e-05, + "loss": 4.2001, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344449845809942e-05, + "loss": 4.189, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.34361125105889e-05, + "loss": 4.1918, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342772656307838e-05, + "loss": 4.1872, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341934061556786e-05, + "loss": 4.1971, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341095466805734e-05, + "loss": 4.1924, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340258509935055e-05, + "loss": 4.1994, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339421553064376e-05, + "loss": 4.1915, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338582958313324e-05, + "loss": 4.1931, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337744363562272e-05, + "loss": 4.2054, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.33690576881122e-05, + "loss": 4.1937, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360671740601686e-05, + "loss": 4.2032, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352285793091166e-05, + "loss": 4.1879, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334389984558064e-05, + "loss": 4.1819, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335530276873855e-05, + "loss": 4.2089, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327144329363335e-05, + "loss": 4.1899, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318758381852815e-05, + "loss": 4.1886, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331037243434229e-05, + "loss": 4.186, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330198648683177e-05, + "loss": 4.1954, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329360053932125e-05, + "loss": 4.1775, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328521459181073e-05, + "loss": 4.1975, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327682864430021e-05, + "loss": 4.187, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268459075593424e-05, + "loss": 4.1868, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260073128082904e-05, + "loss": 4.2036, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3251687180572383e-05, + "loss": 4.1794, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243301233061863e-05, + "loss": 4.1826, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323491528555134e-05, + "loss": 4.1942, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322652933804082e-05, + "loss": 4.1766, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32181433905303e-05, + "loss": 4.1782, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320975744301978e-05, + "loss": 4.1823, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320138787431299e-05, + "loss": 4.1897, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319300192680247e-05, + "loss": 4.1771, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318461597929195e-05, + "loss": 4.1773, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317623003178143e-05, + "loss": 4.1796, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316786046307464e-05, + "loss": 4.1916, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315947451556412e-05, + "loss": 4.1889, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315108856805361e-05, + "loss": 4.1899, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314270262054309e-05, + "loss": 4.1914, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.31343330518363e-05, + "loss": 4.1927, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312594710432578e-05, + "loss": 4.2024, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117577535618986e-05, + "loss": 4.1691, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109191588108466e-05, + "loss": 4.1929, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100805640597946e-05, + "loss": 4.1931, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092419693087426e-05, + "loss": 4.1659, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084033745576906e-05, + "loss": 4.1951, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075647798066386e-05, + "loss": 4.1813, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067278229359595e-05, + "loss": 4.1952, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058892281849075e-05, + "loss": 4.1947, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305050633433856e-05, + "loss": 4.1724, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304213676563177e-05, + "loss": 4.1791, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303375081812125e-05, + "loss": 4.1774, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302536487061073e-05, + "loss": 4.1857, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301697892310021e-05, + "loss": 4.1828, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300860935439342e-05, + "loss": 4.1825, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.30002234068829e-05, + "loss": 4.1772, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299183745937238e-05, + "loss": 4.178, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298345151186186e-05, + "loss": 4.1789, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297506556435134e-05, + "loss": 4.174, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296667961684082e-05, + "loss": 4.1899, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.29582936693303e-05, + "loss": 4.1839, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294990772181978e-05, + "loss": 4.1849, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294152177430926e-05, + "loss": 4.1674, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293313582679874e-05, + "loss": 4.1766, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292476625809195e-05, + "loss": 4.1758, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291638031058143e-05, + "loss": 4.18, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290799436307091e-05, + "loss": 4.1804, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289960841556039e-05, + "loss": 4.174, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289122246804987e-05, + "loss": 4.1668, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288283652053935e-05, + "loss": 4.1785, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287445057302883e-05, + "loss": 4.1674, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286606462551831e-05, + "loss": 4.1645, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285767867800779e-05, + "loss": 4.1583, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284932548810473e-05, + "loss": 4.1738, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284093954059421e-05, + "loss": 4.1704, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283256997188742e-05, + "loss": 4.1808, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.28241840243769e-05, + "loss": 4.1658, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281579807686638e-05, + "loss": 4.1677, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280741212935586e-05, + "loss": 4.1726, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279902618184534e-05, + "loss": 4.158, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279064023433482e-05, + "loss": 4.1813, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.27822542868243e-05, + "loss": 4.1761, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277386833931378e-05, + "loss": 4.1707, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276549877060699e-05, + "loss": 4.1713, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275711282309647e-05, + "loss": 4.1675, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274872687558595e-05, + "loss": 4.1756, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274034092807543e-05, + "loss": 4.1554, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273195498056492e-05, + "loss": 4.1837, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.27235690330544e-05, + "loss": 4.165, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271518308554388e-05, + "loss": 4.1685, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2706813516837087e-05, + "loss": 4.1673, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698427569326566e-05, + "loss": 4.1635, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690041621816046e-05, + "loss": 4.1626, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681655674305526e-05, + "loss": 4.1704, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673269726795006e-05, + "loss": 4.1653, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664883779284486e-05, + "loss": 4.1768, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265649783177396e-05, + "loss": 4.1682, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264811188426344e-05, + "loss": 4.1753, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639742315556655e-05, + "loss": 4.1528, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631356368046135e-05, + "loss": 4.1759, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622970420535615e-05, + "loss": 4.1674, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614584473025095e-05, + "loss": 4.1749, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260621490431831e-05, + "loss": 4.1648, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259784533561152e-05, + "loss": 4.1625, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589459388101e-05, + "loss": 4.1728, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258107344059048e-05, + "loss": 4.1734, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257268749307996e-05, + "loss": 4.1553, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256430154556943e-05, + "loss": 4.1655, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255591559805891e-05, + "loss": 4.1625, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254752965054839e-05, + "loss": 4.1582, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253914370303787e-05, + "loss": 4.1702, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253075775552735e-05, + "loss": 4.1618, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252238818682057e-05, + "loss": 4.1657, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251400223931005e-05, + "loss": 4.1511, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250561629179953e-05, + "loss": 4.1665, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.161187171936035, + "eval_runtime": 293.4993, + "eval_samples_per_second": 1300.143, + "eval_steps_per_second": 40.63, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249723034428901e-05, + "loss": 4.162, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248884439677849e-05, + "loss": 4.1545, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248045844926797e-05, + "loss": 4.1721, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247207250175745e-05, + "loss": 4.1645, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246368655424693e-05, + "loss": 4.165, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245530060673641e-05, + "loss": 4.1633, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244691465922589e-05, + "loss": 4.1538, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243852871171537e-05, + "loss": 4.16, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243014276420485e-05, + "loss": 4.1633, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242175681669432e-05, + "loss": 4.1724, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241337086918381e-05, + "loss": 4.1636, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240498492167329e-05, + "loss": 4.1742, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.23966153529665e-05, + "loss": 4.1542, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238822940545598e-05, + "loss": 4.1569, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237984345794546e-05, + "loss": 4.1678, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237145751043494e-05, + "loss": 4.1476, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236307156292442e-05, + "loss": 4.1561, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23546856154139e-05, + "loss": 4.152, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234629966790338e-05, + "loss": 4.1588, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233791372039286e-05, + "loss": 4.1648, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232952777288234e-05, + "loss": 4.1649, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232114182537182e-05, + "loss": 4.1616, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127558778613e-05, + "loss": 4.1463, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230436993035078e-05, + "loss": 4.1671, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296000361643986e-05, + "loss": 4.1516, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228761441413347e-05, + "loss": 4.1492, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227922846662295e-05, + "loss": 4.1476, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227084251911243e-05, + "loss": 4.1532, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226245657160191e-05, + "loss": 4.1517, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225410338169885e-05, + "loss": 4.1489, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224571743418833e-05, + "loss": 4.1583, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223734786548154e-05, + "loss": 4.1603, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222897829677475e-05, + "loss": 4.1499, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222059234926423e-05, + "loss": 4.1584, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221220640175371e-05, + "loss": 4.1562, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203820454243196e-05, + "loss": 4.1541, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195434506732676e-05, + "loss": 4.1494, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187048559222156e-05, + "loss": 4.1401, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178662611711635e-05, + "loss": 4.1403, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170276664201115e-05, + "loss": 4.1503, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161890716690595e-05, + "loss": 4.1476, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153504769180075e-05, + "loss": 4.1513, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145118821669555e-05, + "loss": 4.1455, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136732874159035e-05, + "loss": 4.1469, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212834692664851e-05, + "loss": 4.1595, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119977357941724e-05, + "loss": 4.1461, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111591410431204e-05, + "loss": 4.1579, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210320546292068e-05, + "loss": 4.1424, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094819515410164e-05, + "loss": 4.1337, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208644994670338e-05, + "loss": 4.1632, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207806399919286e-05, + "loss": 4.1484, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206967805168233e-05, + "loss": 4.1403, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206129210417181e-05, + "loss": 4.1436, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205290615666129e-05, + "loss": 4.1459, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204452020915077e-05, + "loss": 4.1367, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203615064044398e-05, + "loss": 4.1467, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202776469293346e-05, + "loss": 4.1443, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201937874542294e-05, + "loss": 4.1445, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201099279791242e-05, + "loss": 4.1568, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.20026068504019e-05, + "loss": 4.1349, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199423728169512e-05, + "loss": 4.1389, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858513341846e-05, + "loss": 4.1528, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197746538667408e-05, + "loss": 4.132, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196909581796729e-05, + "loss": 4.1301, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196070987045677e-05, + "loss": 4.1387, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195232392294625e-05, + "loss": 4.1458, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943954354239456e-05, + "loss": 4.1312, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935568406728936e-05, + "loss": 4.1368, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927182459218416e-05, + "loss": 4.1315, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918796511707896e-05, + "loss": 4.1521, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910410564197376e-05, + "loss": 4.1442, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902024616686856e-05, + "loss": 4.146, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893638669176336e-05, + "loss": 4.1475, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885252721665816e-05, + "loss": 4.1491, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768667741553e-05, + "loss": 4.1601, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186849720544851e-05, + "loss": 4.1276, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186011125793799e-05, + "loss": 4.1472, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185172531042747e-05, + "loss": 4.1492, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184333936291695e-05, + "loss": 4.1261, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183495341540643e-05, + "loss": 4.1475, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182656746789591e-05, + "loss": 4.1395, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181818152038539e-05, + "loss": 4.151, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180979557287487e-05, + "loss": 4.1511, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801409625364344e-05, + "loss": 4.1346, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793023677853824e-05, + "loss": 4.1316, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784637730343304e-05, + "loss": 4.1336, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776251782832784e-05, + "loss": 4.1446, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767882214126e-05, + "loss": 4.1369, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759512645419216e-05, + "loss": 4.14, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751126697908696e-05, + "loss": 4.1381, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174274075039817e-05, + "loss": 4.1339, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173435480288765e-05, + "loss": 4.1399, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172596885537713e-05, + "loss": 4.1319, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171759928667034e-05, + "loss": 4.1469, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170921333915982e-05, + "loss": 4.1415, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.17008273916493e-05, + "loss": 4.1418, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169244144413878e-05, + "loss": 4.126, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168405549662826e-05, + "loss": 4.1346, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167566954911774e-05, + "loss": 4.1382, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166728360160722e-05, + "loss": 4.1379, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658897654096704e-05, + "loss": 4.1408, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650528085389914e-05, + "loss": 4.1283, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1299, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1335, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1234, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161700067415156e-05, + "loss": 4.1332, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160863110544477e-05, + "loss": 4.1118, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160024515793425e-05, + "loss": 4.1351, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159185921042373e-05, + "loss": 4.131, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158347326291321e-05, + "loss": 4.137, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157510369420643e-05, + "loss": 4.1252, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156671774669591e-05, + "loss": 4.1296, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155833179918539e-05, + "loss": 4.1323, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154994585167487e-05, + "loss": 4.1152, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154155990416435e-05, + "loss": 4.144, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153317395665383e-05, + "loss": 4.1319, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1524804387947036e-05, + "loss": 4.1323, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516418440436516e-05, + "loss": 4.1336, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508032492925996e-05, + "loss": 4.1192, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499646545415476e-05, + "loss": 4.1389, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491260597904956e-05, + "loss": 4.1197, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482874650394436e-05, + "loss": 4.1405, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474488702883916e-05, + "loss": 4.1228, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466102755373396e-05, + "loss": 4.1305, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457716807862876e-05, + "loss": 4.1247, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144934723915609e-05, + "loss": 4.124, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144096129164557e-05, + "loss": 4.1233, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143259172293878e-05, + "loss": 4.128, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142420577542826e-05, + "loss": 4.1273, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141581982791774e-05, + "loss": 4.1353, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140743388040722e-05, + "loss": 4.1289, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13990479328967e-05, + "loss": 4.1351, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390661985386174e-05, + "loss": 4.1141, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382276037875654e-05, + "loss": 4.1358, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373890090365134e-05, + "loss": 4.1302, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136552052165835e-05, + "loss": 4.1322, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357150952951565e-05, + "loss": 4.1259, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348765005441045e-05, + "loss": 4.1246, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340379057930525e-05, + "loss": 4.1302, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1331993110420005e-05, + "loss": 4.1371, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132360716290948e-05, + "loss": 4.1144, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131522121539896e-05, + "loss": 4.1275, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130683526788844e-05, + "loss": 4.1218, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1206, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129007975167113e-05, + "loss": 4.1272, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128169380416061e-05, + "loss": 4.1233, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127330785665009e-05, + "loss": 4.1252, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126492190913957e-05, + "loss": 4.1149, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125655234043278e-05, + "loss": 4.1321, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.130023956298828, + "eval_runtime": 290.094, + "eval_samples_per_second": 1315.405, + "eval_steps_per_second": 41.107, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124816639292226e-05, + "loss": 4.1222, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123979682421548e-05, + "loss": 4.1168, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123141087670495e-05, + "loss": 4.1302, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122304130799817e-05, + "loss": 4.1253, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121465536048765e-05, + "loss": 4.1252, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120626941297712e-05, + "loss": 4.1271, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.11978834654666e-05, + "loss": 4.1173, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118951389675982e-05, + "loss": 4.1166, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11811279492493e-05, + "loss": 4.1278, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117274200173877e-05, + "loss": 4.1315, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116435605422826e-05, + "loss": 4.1266, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115597010671774e-05, + "loss": 4.1342, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114760053801095e-05, + "loss": 4.1196, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139214590500426e-05, + "loss": 4.1173, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1130828642989906e-05, + "loss": 4.1279, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122442695479386e-05, + "loss": 4.1072, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114056747968866e-05, + "loss": 4.1203, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1105670800458346e-05, + "loss": 4.1132, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097301231751555e-05, + "loss": 4.1218, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1088915284241035e-05, + "loss": 4.1251, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080529336730515e-05, + "loss": 4.1326, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072143389219995e-05, + "loss": 4.1223, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063757441709475e-05, + "loss": 4.1105, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055371494198955e-05, + "loss": 4.1299, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1046985546688435e-05, + "loss": 4.1112, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103859959917792e-05, + "loss": 4.1151, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.10302136516674e-05, + "loss": 4.1073, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102182770415688e-05, + "loss": 4.1192, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101344175664636e-05, + "loss": 4.1092, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005055809135834e-05, + "loss": 4.1155, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099668624042905e-05, + "loss": 4.1165, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098831667172226e-05, + "loss": 4.1266, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097993072421174e-05, + "loss": 4.1147, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097154477670122e-05, + "loss": 4.1144, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.09631588291907e-05, + "loss": 4.1199, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095477288168018e-05, + "loss": 4.1171, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094638693416966e-05, + "loss": 4.1146, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093800098665914e-05, + "loss": 4.0991, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092961503914862e-05, + "loss": 4.1044, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921245470441835e-05, + "loss": 4.1098, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091285952293131e-05, + "loss": 4.1149, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090447357542079e-05, + "loss": 4.1126, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896104006714004e-05, + "loss": 4.1085, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0887718059203484e-05, + "loss": 4.1076, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087933211169296e-05, + "loss": 4.1222, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087094616418244e-05, + "loss": 4.1068, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086256021667192e-05, + "loss": 4.129, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08541742691614e-05, + "loss": 4.1027, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084578832165088e-05, + "loss": 4.0902, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083740237414036e-05, + "loss": 4.1308, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082903280543357e-05, + "loss": 4.1096, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082064685792305e-05, + "loss": 4.1095, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1071, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1067, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079548901539149e-05, + "loss": 4.1024, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.07871194466847e-05, + "loss": 4.1086, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077873349917418e-05, + "loss": 4.1083, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077036393046739e-05, + "loss": 4.1094, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076197798295687e-05, + "loss": 4.1226, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075359203544635e-05, + "loss": 4.0978, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074520608793583e-05, + "loss": 4.0992, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073682014042531e-05, + "loss": 4.1173, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.07284341929148e-05, + "loss": 4.093, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072004824540428e-05, + "loss": 4.0938, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071166229789376e-05, + "loss": 4.1044, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703292729186966e-05, + "loss": 4.1098, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0694906781676446e-05, + "loss": 4.0937, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0686520834165926e-05, + "loss": 4.1034, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678151265459135e-05, + "loss": 4.0962, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0669765317948615e-05, + "loss": 4.1147, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661379370438095e-05, + "loss": 4.1126, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652993422927575e-05, + "loss": 4.1055, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0644607475417055e-05, + "loss": 4.1127, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636221527906535e-05, + "loss": 4.1136, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627835580396015e-05, + "loss": 4.1258, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061946601168923e-05, + "loss": 4.09, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061108006417871e-05, + "loss": 4.1164, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060269411666819e-05, + "loss": 4.1093, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059430816915767e-05, + "loss": 4.0956, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585922221647144e-05, + "loss": 4.1085, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577536274136624e-05, + "loss": 4.1075, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569150326626104e-05, + "loss": 4.1141, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560764379115584e-05, + "loss": 4.1195, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552378431605064e-05, + "loss": 4.0979, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543992484094544e-05, + "loss": 4.0941, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053562291538775e-05, + "loss": 4.1011, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052723696787723e-05, + "loss": 4.1088, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051885102036671e-05, + "loss": 4.1051, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051048145165993e-05, + "loss": 4.1038, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050209550414941e-05, + "loss": 4.0985, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049370955663889e-05, + "loss": 4.101, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048532360912837e-05, + "loss": 4.1044, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047693766161785e-05, + "loss": 4.0999, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046855171410733e-05, + "loss": 4.1092, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.1091, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045179619789002e-05, + "loss": 4.1058, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.04434102503795e-05, + "loss": 4.0933, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043502430286898e-05, + "loss": 4.103, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.0995, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1029, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1066, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040149689163063e-05, + "loss": 4.0985, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039311094412011e-05, + "loss": 4.0926, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038472499660959e-05, + "loss": 4.0961, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037633904909907e-05, + "loss": 4.0959, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.0942, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035956715407803e-05, + "loss": 4.0796, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351181206567506e-05, + "loss": 4.1006, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034281163786072e-05, + "loss": 4.0996, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.03344256903502e-05, + "loss": 4.0995, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032603974283968e-05, + "loss": 4.0863, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317653795329155e-05, + "loss": 4.1039, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309267847818635e-05, + "loss": 4.0948, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030088190030812e-05, + "loss": 4.085, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02924959527976e-05, + "loss": 4.1076, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028411000528708e-05, + "loss": 4.0988, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275756815384027e-05, + "loss": 4.0966, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267370867873506e-05, + "loss": 4.104, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259001299166716e-05, + "loss": 4.087, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250615351656196e-05, + "loss": 4.1057, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242229404145675e-05, + "loss": 4.0898, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233843456635155e-05, + "loss": 4.1021, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022545750912463e-05, + "loss": 4.0906, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021707156161411e-05, + "loss": 4.0985, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020868561410359e-05, + "loss": 4.0922, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200299666593075e-05, + "loss": 4.0896, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191913719082555e-05, + "loss": 4.0865, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183527771572035e-05, + "loss": 4.0957, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175158202865244e-05, + "loss": 4.0973, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166772255354724e-05, + "loss": 4.104, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158386307844204e-05, + "loss": 4.0901, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150000360333684e-05, + "loss": 4.1075, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141614412823164e-05, + "loss": 4.0802, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013324484411637e-05, + "loss": 4.1037, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012485889660585e-05, + "loss": 4.0972, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011647294909533e-05, + "loss": 4.0992, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010808700158481e-05, + "loss": 4.0916, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009970105407429e-05, + "loss": 4.0957, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009133148536751e-05, + "loss": 4.0955, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008294553785699e-05, + "loss": 4.1063, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007455959034647e-05, + "loss": 4.0833, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006617364283595e-05, + "loss": 4.0957, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005778769532543e-05, + "loss": 4.0887, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004941812661864e-05, + "loss": 4.0928, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004103217910812e-05, + "loss": 4.0879, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.00326462315976e-05, + "loss": 4.091, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002426028408708e-05, + "loss": 4.097, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001587433657656e-05, + "loss": 4.0796, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000748838906604e-05, + "loss": 4.1002, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.105032444000244, + "eval_runtime": 290.5141, + "eval_samples_per_second": 1313.503, + "eval_steps_per_second": 41.048, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999910244155552e-05, + "loss": 4.0902, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999071649404499e-05, + "loss": 4.0872, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998233054653448e-05, + "loss": 4.0962, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997394459902396e-05, + "loss": 4.0922, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996555865151344e-05, + "loss": 4.0979, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995717270400292e-05, + "loss": 4.0917, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.99487867564924e-05, + "loss": 4.09, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994040080898188e-05, + "loss": 4.0891, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993201486147136e-05, + "loss": 4.0937, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992362891396084e-05, + "loss": 4.101, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991524296645032e-05, + "loss": 4.0964, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99068570189398e-05, + "loss": 4.1007, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898487450233006e-05, + "loss": 4.086, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890101502722486e-05, + "loss": 4.0889, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881715555211966e-05, + "loss": 4.0968, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873329607701446e-05, + "loss": 4.0779, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9864943660190926e-05, + "loss": 4.0875, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856557712680406e-05, + "loss": 4.0827, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984818814397362e-05, + "loss": 4.0882, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983981857526683e-05, + "loss": 4.0926, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983143262775631e-05, + "loss": 4.1028, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982304668024579e-05, + "loss": 4.0905, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981466073273527e-05, + "loss": 4.0805, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980627478522475e-05, + "loss": 4.0945, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979788883771423e-05, + "loss": 4.085, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789502890203704e-05, + "loss": 4.0842, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781116942693184e-05, + "loss": 4.0767, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772730995182664e-05, + "loss": 4.0872, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764345047672144e-05, + "loss": 4.0838, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975595910016163e-05, + "loss": 4.0799, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974757315265111e-05, + "loss": 4.0842, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973918720514059e-05, + "loss": 4.0943, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973080125763007e-05, + "loss": 4.0821, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972241531011955e-05, + "loss": 4.0824, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971402936260903e-05, + "loss": 4.0874, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970564341509851e-05, + "loss": 4.091, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.082, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.0683, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.0751, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967211600386016e-05, + "loss": 4.0798, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966373005634964e-05, + "loss": 4.0824, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965536048764285e-05, + "loss": 4.0829, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964697454013233e-05, + "loss": 4.0796, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963858859262181e-05, + "loss": 4.0818, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630219023915024e-05, + "loss": 4.0894, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621833076404504e-05, + "loss": 4.0783, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613447128893984e-05, + "loss": 4.0942, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605061181383464e-05, + "loss": 4.0762, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596675233872944e-05, + "loss": 4.0579, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958828928636242e-05, + "loss": 4.1013, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95799033388519e-05, + "loss": 4.0765, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957151739134138e-05, + "loss": 4.0841, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956316420143832e-05, + "loss": 4.0762, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.95547782539278e-05, + "loss": 4.0746, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954639230641728e-05, + "loss": 4.0745, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953800635890676e-05, + "loss": 4.0773, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952963679019998e-05, + "loss": 4.0812, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952125084268946e-05, + "loss": 4.0795, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951286489517894e-05, + "loss": 4.0935, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950447894766842e-05, + "loss": 4.0696, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949609300015789e-05, + "loss": 4.0692, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948770705264737e-05, + "loss": 4.0907, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947932110513685e-05, + "loss": 4.0625, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947093515762633e-05, + "loss": 4.0616, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946256558891954e-05, + "loss": 4.0762, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945417964140902e-05, + "loss": 4.079, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94457936938985e-05, + "loss": 4.0673, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437407746387986e-05, + "loss": 4.075, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429038177681195e-05, + "loss": 4.0663, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420652230170675e-05, + "loss": 4.0849, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412266282660155e-05, + "loss": 4.0798, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403880335149635e-05, + "loss": 4.0792, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395510766442844e-05, + "loss": 4.0823, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387124818932324e-05, + "loss": 4.0842, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378738871421804e-05, + "loss": 4.0959, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370352923911284e-05, + "loss": 4.064, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361966976400764e-05, + "loss": 4.0861, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353581028890244e-05, + "loss": 4.0758, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934521146018345e-05, + "loss": 4.0693, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933682551267294e-05, + "loss": 4.08, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932843956516242e-05, + "loss": 4.081, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.93200536176519e-05, + "loss": 4.0838, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931168404894511e-05, + "loss": 4.0905, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930329810143459e-05, + "loss": 4.0688, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929491215392407e-05, + "loss": 4.0624, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928652620641355e-05, + "loss": 4.0737, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927814025890303e-05, + "loss": 4.0834, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926975431139251e-05, + "loss": 4.0767, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926138474268572e-05, + "loss": 4.0779, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92529987951752e-05, + "loss": 4.0681, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924461284766468e-05, + "loss": 4.0689, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923622690015416e-05, + "loss": 4.0786, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922784095264364e-05, + "loss": 4.069, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219471383936854e-05, + "loss": 4.0796, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211085436426334e-05, + "loss": 4.0823, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202699488915813e-05, + "loss": 4.0757, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194313541405293e-05, + "loss": 4.0684, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918592759389477e-05, + "loss": 4.0708, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917754164638425e-05, + "loss": 4.0719, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169155698873727e-05, + "loss": 4.0732, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9160769751363206e-05, + "loss": 4.0782, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915240018265642e-05, + "loss": 4.073, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144014235145896e-05, + "loss": 4.0693, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913564466643911e-05, + "loss": 4.0611, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912725871892859e-05, + "loss": 4.0731, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911887277141808e-05, + "loss": 4.065, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911048682390755e-05, + "loss": 4.0514, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910211725520077e-05, + "loss": 4.0758, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909373130769025e-05, + "loss": 4.0706, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908534536017973e-05, + "loss": 4.073, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.90769594126692e-05, + "loss": 4.0574, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906857346515868e-05, + "loss": 4.0741, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906018751764816e-05, + "loss": 4.0685, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905181794894137e-05, + "loss": 4.0572, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904343200143085e-05, + "loss": 4.0825, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903504605392033e-05, + "loss": 4.0729, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026676485213545e-05, + "loss": 4.0688, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018290537703025e-05, + "loss": 4.0749, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009904590192505e-05, + "loss": 4.057, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001518642681985e-05, + "loss": 4.0761, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993132695171465e-05, + "loss": 4.0671, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984746747660945e-05, + "loss": 4.0719, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976360800150425e-05, + "loss": 4.0638, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967991231443634e-05, + "loss": 4.074, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959605283933114e-05, + "loss": 4.067, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951219336422594e-05, + "loss": 4.061, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942833388912074e-05, + "loss": 4.0588, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934447441401554e-05, + "loss": 4.0715, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926061493891034e-05, + "loss": 4.0666, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891769192518425e-05, + "loss": 4.0739, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890930597767373e-05, + "loss": 4.0662, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890092003016321e-05, + "loss": 4.081, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889253408265269e-05, + "loss": 4.054, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888414813514217e-05, + "loss": 4.0757, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887576218763165e-05, + "loss": 4.0729, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886737624012113e-05, + "loss": 4.0743, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885899029261061e-05, + "loss": 4.065, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885062072390382e-05, + "loss": 4.0659, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.88422347763933e-05, + "loss": 4.0666, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883384882888278e-05, + "loss": 4.0859, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882546288137226e-05, + "loss": 4.0556, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881707693386173e-05, + "loss": 4.0675, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880869098635122e-05, + "loss": 4.0607, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.88003050388407e-05, + "loss": 4.0689, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879191909133018e-05, + "loss": 4.0584, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878353314381966e-05, + "loss": 4.0669, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877514719630914e-05, + "loss": 4.0676, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876677762760235e-05, + "loss": 4.0588, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875839168009183e-05, + "loss": 4.0704, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.085982799530029, + "eval_runtime": 288.2773, + "eval_samples_per_second": 1323.694, + "eval_steps_per_second": 41.366, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875000573258131e-05, + "loss": 4.059, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874161978507079e-05, + "loss": 4.0594, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733250216363996e-05, + "loss": 4.0711, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724864268853476e-05, + "loss": 4.0652, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716478321342956e-05, + "loss": 4.073, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708092373832436e-05, + "loss": 4.0656, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8699706426321916e-05, + "loss": 4.0612, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86913204788114e-05, + "loss": 4.0632, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868293453130088e-05, + "loss": 4.0635, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867456496259409e-05, + "loss": 4.0748, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866617901508357e-05, + "loss": 4.0723, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865779306757305e-05, + "loss": 4.0697, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864942349886626e-05, + "loss": 4.0694, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864103755135574e-05, + "loss": 4.0536, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863265160384522e-05, + "loss": 4.0707, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.86242656563347e-05, + "loss": 4.0544, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861587970882418e-05, + "loss": 4.0592, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860749376131366e-05, + "loss": 4.0581, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859910781380314e-05, + "loss": 4.0588, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859072186629262e-05, + "loss": 4.0633, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.85823359187821e-05, + "loss": 4.0783, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857394997127158e-05, + "loss": 4.0693, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565580402564796e-05, + "loss": 4.0544, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557194455054276e-05, + "loss": 4.0641, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854880850754375e-05, + "loss": 4.0582, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854042256003323e-05, + "loss": 4.0598, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853203661252271e-05, + "loss": 4.0517, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852366704381592e-05, + "loss": 4.0652, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.85152810963054e-05, + "loss": 4.0554, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850689514879488e-05, + "loss": 4.0557, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849850920128436e-05, + "loss": 4.0557, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490139632577574e-05, + "loss": 4.0695, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8481753685067054e-05, + "loss": 4.0571, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8473367737556534e-05, + "loss": 4.0588, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8464981790046014e-05, + "loss": 4.0617, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8456595842535494e-05, + "loss": 4.0619, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84482262738287e-05, + "loss": 4.0609, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843984032631818e-05, + "loss": 4.0457, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843145437880766e-05, + "loss": 4.049, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842308481010087e-05, + "loss": 4.0536, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841469886259035e-05, + "loss": 4.054, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840631291507983e-05, + "loss": 4.0561, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839792696756931e-05, + "loss": 4.0543, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838954102005879e-05, + "loss": 4.0598, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838115507254827e-05, + "loss": 4.0592, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837276912503776e-05, + "loss": 4.055, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836438317752724e-05, + "loss": 4.0667, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835601360882045e-05, + "loss": 4.0546, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834762766130993e-05, + "loss": 4.0353, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833924171379941e-05, + "loss": 4.0701, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833085576628889e-05, + "loss": 4.0521, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322486197582096e-05, + "loss": 4.059, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314100250071576e-05, + "loss": 4.055, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305714302561056e-05, + "loss": 4.0487, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297328355050536e-05, + "loss": 4.0482, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8288942407540016e-05, + "loss": 4.0511, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8280556460029496e-05, + "loss": 4.0605, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272170512518976e-05, + "loss": 4.0516, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263784565008456e-05, + "loss": 4.0685, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255398617497936e-05, + "loss": 4.0507, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247012669987416e-05, + "loss": 4.0391, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823864310128063e-05, + "loss": 4.0667, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230257153770105e-05, + "loss": 4.0401, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221871206259585e-05, + "loss": 4.0371, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213485258749065e-05, + "loss": 4.0534, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205099311238545e-05, + "loss": 4.0514, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196713363728025e-05, + "loss": 4.0436, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188327416217505e-05, + "loss": 4.049, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8179941468706985e-05, + "loss": 4.0425, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171555521196465e-05, + "loss": 4.0576, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816318595248968e-05, + "loss": 4.0606, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815481638378289e-05, + "loss": 4.0544, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814643043627237e-05, + "loss": 4.0577, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813804448876185e-05, + "loss": 4.0573, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812967492005506e-05, + "loss": 4.0693, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812128897254454e-05, + "loss": 4.0421, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811290302503402e-05, + "loss": 4.0623, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.81045170775235e-05, + "loss": 4.0483, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809613113001298e-05, + "loss": 4.0479, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808774518250246e-05, + "loss": 4.0513, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807935923499194e-05, + "loss": 4.0584, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807097328748142e-05, + "loss": 4.0598, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80625873399709e-05, + "loss": 4.0661, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805420139246038e-05, + "loss": 4.0412, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804581544494986e-05, + "loss": 4.0427, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8037429497439345e-05, + "loss": 4.0493, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029059928732554e-05, + "loss": 4.056, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020673981222034e-05, + "loss": 4.0468, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801230441251524e-05, + "loss": 4.0521, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800391846500472e-05, + "loss": 4.0465, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.79955325174942e-05, + "loss": 4.0493, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798716294878741e-05, + "loss": 4.0502, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797877700127689e-05, + "loss": 4.045, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797039105376637e-05, + "loss": 4.0562, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796200510625585e-05, + "loss": 4.0579, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795361915874533e-05, + "loss": 4.055, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794523321123481e-05, + "loss": 4.0461, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.79368472637243e-05, + "loss": 4.0449, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792846131621377e-05, + "loss": 4.0486, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792007536870325e-05, + "loss": 4.049, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791168942119273e-05, + "loss": 4.0533, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790330347368221e-05, + "loss": 4.0483, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789491752617169e-05, + "loss": 4.044, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78865479574649e-05, + "loss": 4.0354, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787816200995438e-05, + "loss": 4.0522, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786977606244386e-05, + "loss": 4.0411, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786139011493334e-05, + "loss": 4.0272, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785302054622655e-05, + "loss": 4.0468, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7844650977519766e-05, + "loss": 4.0557, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836265030009246e-05, + "loss": 4.0447, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7827879082498725e-05, + "loss": 4.0362, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819493134988205e-05, + "loss": 4.0454, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811107187477685e-05, + "loss": 4.0447, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7802721239967165e-05, + "loss": 4.034, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7794335292456645e-05, + "loss": 4.0597, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7785949344946125e-05, + "loss": 4.0497, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777579776239334e-05, + "loss": 4.0422, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769210207532543e-05, + "loss": 4.0501, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776084063882576e-05, + "loss": 4.0386, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775245469131524e-05, + "loss": 4.0504, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774406874380472e-05, + "loss": 4.0453, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.77356827962942e-05, + "loss": 4.0461, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772729684878368e-05, + "loss": 4.04, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771891090127316e-05, + "loss": 4.0516, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771052495376264e-05, + "loss": 4.045, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770215538505585e-05, + "loss": 4.0398, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769376943754533e-05, + "loss": 4.0341, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768538349003481e-05, + "loss": 4.0465, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767699754252429e-05, + "loss": 4.041, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766861159501377e-05, + "loss": 4.0527, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766022564750325e-05, + "loss": 4.0429, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765183969999273e-05, + "loss": 4.0554, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764345375248221e-05, + "loss": 4.0301, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763506780497169e-05, + "loss": 4.0547, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7626681857461175e-05, + "loss": 4.0477, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7618295909950654e-05, + "loss": 4.0503, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760990996244013e-05, + "loss": 4.046, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7601540393733344e-05, + "loss": 4.0418, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593154446222823e-05, + "loss": 4.0424, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758478487751603e-05, + "loss": 4.0642, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757639893000551e-05, + "loss": 4.0294, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756801298249499e-05, + "loss": 4.0448, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755962703498447e-05, + "loss": 4.0405, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755124108747395e-05, + "loss": 4.0413, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542855139963426e-05, + "loss": 4.0355, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753446919245291e-05, + "loss": 4.0464, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752609962374613e-05, + "loss": 4.0413, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.75177136762356e-05, + "loss": 4.0406, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750932772872508e-05, + "loss": 4.0439, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.070503234863281, + "eval_runtime": 288.5075, + "eval_samples_per_second": 1322.638, + "eval_steps_per_second": 41.333, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750094178121456e-05, + "loss": 4.0397, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749255583370404e-05, + "loss": 4.0383, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748416988619352e-05, + "loss": 4.0465, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475783938683e-05, + "loss": 4.0456, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746739799117248e-05, + "loss": 4.0491, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745901204366196e-05, + "loss": 4.044, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745062609615144e-05, + "loss": 4.0384, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744224014864092e-05, + "loss": 4.0391, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.74338542011304e-05, + "loss": 4.0415, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742546825361988e-05, + "loss": 4.0509, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741708230610936e-05, + "loss": 4.048, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740869635859884e-05, + "loss": 4.0506, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740032678989206e-05, + "loss": 4.0499, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739194084238154e-05, + "loss": 4.0284, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383554894871017e-05, + "loss": 4.0508, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737516894736049e-05, + "loss": 4.0281, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736678299984997e-05, + "loss": 4.035, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735839705233945e-05, + "loss": 4.0371, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735001110482893e-05, + "loss": 4.0348, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734162515731841e-05, + "loss": 4.0431, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733323920980789e-05, + "loss": 4.0529, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.73248696411011e-05, + "loss": 4.0481, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731648369359058e-05, + "loss": 4.0355, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730809774608006e-05, + "loss": 4.0364, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7299711798569545e-05, + "loss": 4.0424, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7291325851059025e-05, + "loss": 4.034, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282939903548505e-05, + "loss": 4.0309, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274553956037985e-05, + "loss": 4.045, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7266168008527465e-05, + "loss": 4.0296, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7257782061016945e-05, + "loss": 4.0354, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7249412492310154e-05, + "loss": 4.0299, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241026544799634e-05, + "loss": 4.0461, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723265697609284e-05, + "loss": 4.0402, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722427102858232e-05, + "loss": 4.0331, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72158850810718e-05, + "loss": 4.0422, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720749913356128e-05, + "loss": 4.036, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719911318605076e-05, + "loss": 4.0409, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719072723854024e-05, + "loss": 4.0278, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718235766983346e-05, + "loss": 4.0233, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717397172232294e-05, + "loss": 4.0293, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716558577481242e-05, + "loss": 4.0356, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.71571998273019e-05, + "loss": 4.0304, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714881387979138e-05, + "loss": 4.0291, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714042793228085e-05, + "loss": 4.0386, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713204198477033e-05, + "loss": 4.0352, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712365603725981e-05, + "loss": 4.035, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711530284735676e-05, + "loss": 4.0484, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710691689984624e-05, + "loss": 4.0308, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709853095233572e-05, + "loss": 4.0096, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.70901450048252e-05, + "loss": 4.0489, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081759057314677e-05, + "loss": 4.03, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073373109804157e-05, + "loss": 4.0371, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7064987162293637e-05, + "loss": 4.0307, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705661759358685e-05, + "loss": 4.0288, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048231646076326e-05, + "loss": 4.0262, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039845698565806e-05, + "loss": 4.0265, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031459751055285e-05, + "loss": 4.0434, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.70230901823485e-05, + "loss": 4.0251, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014704234837975e-05, + "loss": 4.0465, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006318287327454e-05, + "loss": 4.0297, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997932339816934e-05, + "loss": 4.0159, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698954639230642e-05, + "loss": 4.0425, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.69811604447959e-05, + "loss": 4.0258, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697277449728538e-05, + "loss": 4.0143, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696438854977486e-05, + "loss": 4.0299, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695601898106807e-05, + "loss": 4.0278, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694763303355755e-05, + "loss": 4.0228, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693924708604703e-05, + "loss": 4.0268, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693086113853651e-05, + "loss": 4.0237, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692249156982972e-05, + "loss": 4.0364, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691412200112293e-05, + "loss": 4.0397, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690573605361241e-05, + "loss": 4.0297, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689735010610189e-05, + "loss": 4.0377, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688896415859137e-05, + "loss": 4.0353, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6880578211080855e-05, + "loss": 4.0478, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6872208642374064e-05, + "loss": 4.0216, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6863822694863544e-05, + "loss": 4.042, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855436747353024e-05, + "loss": 4.0274, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847050799842504e-05, + "loss": 4.0264, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683868123113571e-05, + "loss": 4.0335, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683029528362519e-05, + "loss": 4.0315, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682190933611467e-05, + "loss": 4.0403, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681352338860415e-05, + "loss": 4.0458, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680513744109363e-05, + "loss": 4.0229, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679675149358311e-05, + "loss": 4.0196, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678836554607259e-05, + "loss": 4.0263, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.677997959856207e-05, + "loss": 4.0397, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677159365105155e-05, + "loss": 4.0224, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676322408234477e-05, + "loss": 4.03, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675483813483425e-05, + "loss": 4.032, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674645218732373e-05, + "loss": 4.0227, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673806623981321e-05, + "loss": 4.0319, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672969667110642e-05, + "loss": 4.0209, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.67213107235959e-05, + "loss": 4.0346, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671292477608538e-05, + "loss": 4.0325, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670453882857486e-05, + "loss": 4.0362, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669615288106434e-05, + "loss": 4.022, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668776693355381e-05, + "loss": 4.0276, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667938098604329e-05, + "loss": 4.0263, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667099503853278e-05, + "loss": 4.029, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666260909102226e-05, + "loss": 4.0347, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665422314351174e-05, + "loss": 4.025, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664583719600122e-05, + "loss": 4.027, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.66374512484907e-05, + "loss": 4.0168, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662906530098018e-05, + "loss": 4.0265, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662067935346966e-05, + "loss": 4.0228, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612326163566595e-05, + "loss": 4.0057, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6603940216056075e-05, + "loss": 4.0272, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595554268545555e-05, + "loss": 4.0292, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587168321035035e-05, + "loss": 4.0239, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578782373524515e-05, + "loss": 4.0155, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570396426013995e-05, + "loss": 4.0248, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656202685730721e-05, + "loss": 4.0244, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655364090979669e-05, + "loss": 4.0126, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654525496228617e-05, + "loss": 4.0424, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653686901477565e-05, + "loss": 4.025, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652848306726513e-05, + "loss": 4.0234, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652011349855834e-05, + "loss": 4.03, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651172755104782e-05, + "loss": 4.0174, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.65033416035373e-05, + "loss": 4.0298, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649495565602678e-05, + "loss": 4.0271, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648658608731999e-05, + "loss": 4.022, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647820013980947e-05, + "loss": 4.0239, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646981419229895e-05, + "loss": 4.0284, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646142824478843e-05, + "loss": 4.0263, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453058676081644e-05, + "loss": 4.0177, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6444672728571124e-05, + "loss": 4.0186, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6436286781060604e-05, + "loss": 4.0209, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6427900833550084e-05, + "loss": 4.0214, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6419514886039564e-05, + "loss": 4.0332, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411128938529044e-05, + "loss": 4.0236, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402742991018524e-05, + "loss": 4.0338, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394357043508e-05, + "loss": 4.0075, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638598747480121e-05, + "loss": 4.0373, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637760152729069e-05, + "loss": 4.0253, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6369215579780166e-05, + "loss": 4.0309, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636082963226965e-05, + "loss": 4.0267, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635244368475913e-05, + "loss": 4.0179, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634409049485608e-05, + "loss": 4.0233, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633570454734556e-05, + "loss": 4.0409, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632731859983504e-05, + "loss": 4.0122, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631893265232452e-05, + "loss": 4.0266, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310546704814e-05, + "loss": 4.0178, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630216075730347e-05, + "loss": 4.0234, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629377480979295e-05, + "loss": 4.0178, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628538886228243e-05, + "loss": 4.0234, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627701929357564e-05, + "loss": 4.0219, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268649724868856e-05, + "loss": 4.023, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260263777358336e-05, + "loss": 4.0207, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.056793212890625, + "eval_runtime": 294.8075, + "eval_samples_per_second": 1294.373, + "eval_steps_per_second": 40.45, + "step": 839520 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 3.4829826501146995e+17, + "trial_name": null, + "trial_params": null +}