diff --git "a/checkpoint-1526400/trainer_state.json" "b/checkpoint-1526400/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1526400/trainer_state.json" @@ -0,0 +1,18071 @@ +{ + "best_metric": 3.996687412261963, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/2/checkpoints/checkpoint-1526400", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1526400, + "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": 10.8216, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5604, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0668, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.999, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9512, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8869, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7317, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6248, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5301, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4596, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4014, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3423, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2755, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2058, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1542, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0875, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0564, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9992, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9548, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.921, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8852, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8459, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.8177, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7829, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7633, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7281, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 5.7072, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.676, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6523, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6343, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6143, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.5968, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5768, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5583, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5427, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5264, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5112, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4832, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4788, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 5.439, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 5.4393, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4291, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4257, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 5.3887, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 5.3912, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 5.3806, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3718, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3694, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3343, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3292, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3335, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3224, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3033, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2834, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2885, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2691, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.2891, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2383, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2493, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 5.2374, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 5.2352, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2312, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2077, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1907, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 5.1964, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2059, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 5.1761, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1756, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 5.1513, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 5.1521, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 5.1627, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 5.1606, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 5.1345, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 5.147, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 5.1447, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 5.134, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 5.1029, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 5.1099, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 5.0994, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 5.0918, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 5.0906, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 5.0855, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 5.087, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 5.0747, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 5.0577, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 5.0579, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 5.0578, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 5.0482, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0441, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 5.0293, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 5.0282, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 5.0182, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.0257, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.013, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 5.011, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 5.0087, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.9951, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.991, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.9818, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.9792, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.98, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.9626, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.9672, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.9631, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9494, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.946, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9413, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9388, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.9313, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.9328, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.9251, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9121, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.9256, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.9075, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.914, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.9065, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.9005, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.8972, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.8914, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.9066, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.893, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.8765, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8732, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.87, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8656, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8584, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8617, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8471, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8471, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8421, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8615, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8528, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.8357, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8335, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8278, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8382, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8293, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8278, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8235, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.8192, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8152, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8045, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8117, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.802, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.79, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.802, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.7984, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.7985, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.7871, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.7846, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.7475996017456055, + "eval_runtime": 296.429, + "eval_samples_per_second": 1287.293, + "eval_steps_per_second": 40.229, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.7784, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.775, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.788, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7724, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7751, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7598, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7737, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7559, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7576, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.755, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.7629, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.7565, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.7374, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.7425, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.7336, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.7349, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.7358, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7282, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.7318, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.7425, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7282, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.7265, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.7191, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.7329, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.7028, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.716, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.7028, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.7057, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.7015, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.6946, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7015, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.7093, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.6955, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.7016, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.685, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.6933, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.6781, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.6877, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.6654, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.6752, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.6717, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.6839, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6563, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6734, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6692, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.6624, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.6728, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6479, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.65, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.6661, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6527, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.6478, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.641, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6473, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.6375, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.6562, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6255, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6356, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6344, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6335, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.6387, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.6275, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.6092, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.6164, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.64, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.6128, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.6141, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.6072, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6083, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6229, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.6232, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.6074, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.6199, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.6226, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.6187, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.5928, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.6069, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.5993, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.6005, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.5964, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.5974, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.6049, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.5982, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.5804, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.586, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.5875, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.5909, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.5899, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.5762, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.5836, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.5686, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.5845, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.5797, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.5739, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.5809, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.572, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.5677, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5682, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.5696, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5658, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.5572, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5611, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5635, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.5587, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5431, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5559, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.556, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5493, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5488, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5484, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.5364, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.5578, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780368431362658e-05, + "loss": 4.5425, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779529836611606e-05, + "loss": 4.5465, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.5421, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5486, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5388, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776175457607397e-05, + "loss": 4.5412, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775336862856345e-05, + "loss": 4.5519, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774498268105293e-05, + "loss": 4.5429, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773659673354241e-05, + "loss": 4.5326, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5328, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5275, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5259, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5267, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5245, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.5164, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.5206, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5169, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.5342, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.5353, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.5214, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.5115, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5181, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5231, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5234, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.5159, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.5205, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5118, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5136, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5086, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5128, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5053, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.508, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5098, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751864399228755e-05, + "loss": 4.5114, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751025804477703e-05, + "loss": 4.4993, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750187209726651e-05, + "loss": 4.5007, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.469255447387695, + "eval_runtime": 295.4389, + "eval_samples_per_second": 1291.607, + "eval_steps_per_second": 40.364, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749348614975599e-05, + "loss": 4.4955, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748510020224547e-05, + "loss": 4.4918, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747671425473495e-05, + "loss": 4.5067, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746832830722443e-05, + "loss": 4.4968, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745994235971391e-05, + "loss": 4.502, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745155641220339e-05, + "loss": 4.4857, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744317046469287e-05, + "loss": 4.499, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743478451718235e-05, + "loss": 4.4848, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742639856967183e-05, + "loss": 4.4927, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741801262216131e-05, + "loss": 4.4883, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740962667465079e-05, + "loss": 4.4972, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401240727140264e-05, + "loss": 4.492, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.4758, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384485210922966e-05, + "loss": 4.4837, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376099263412446e-05, + "loss": 4.4759, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736771331590192e-05, + "loss": 4.4803, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.73593273683914e-05, + "loss": 4.4796, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735094142088088e-05, + "loss": 4.4723, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4782, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.4935, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4805, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4776, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.476, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4844, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4594, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283886598404184e-05, + "loss": 4.4714, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275500650893664e-05, + "loss": 4.4699, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267114703383144e-05, + "loss": 4.4649, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258728755872624e-05, + "loss": 4.4606, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4585, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4659, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4755, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225184965830544e-05, + "loss": 4.4638, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4657, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4576, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720004350210271e-05, + "loss": 4.4617, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4486, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4661, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717490203837488e-05, + "loss": 4.44, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716651609086437e-05, + "loss": 4.4525, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715813014335385e-05, + "loss": 4.4478, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714974419584333e-05, + "loss": 4.4618, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714135824833281e-05, + "loss": 4.441, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4518, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4525, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711621678460498e-05, + "loss": 4.4434, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4555, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4351, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.436, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4537, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4385, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4382, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.70575479096388e-05, + "loss": 4.4328, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704916196212828e-05, + "loss": 4.441, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040776014617755e-05, + "loss": 4.4269, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032390067107235e-05, + "loss": 4.4469, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.4191, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4328, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4365, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4284, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4346, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982107139651573e-05, + "loss": 4.4318, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697372119214106e-05, + "loss": 4.4104, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.421, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.4329, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694857972841323e-05, + "loss": 4.4216, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4239, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693180783339219e-05, + "loss": 4.409, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692342188588167e-05, + "loss": 4.4147, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691503593837115e-05, + "loss": 4.4327, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690664999086063e-05, + "loss": 4.4305, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.4142, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4308, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688149214832907e-05, + "loss": 4.4342, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687310620081855e-05, + "loss": 4.4327, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686472025330803e-05, + "loss": 4.4021, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685633430579751e-05, + "loss": 4.4229, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847964737090725e-05, + "loss": 4.4158, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839578789580204e-05, + "loss": 4.4114, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831192842069684e-05, + "loss": 4.4149, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4138, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4191, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4215, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679768180963506e-05, + "loss": 4.3965, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678929586212454e-05, + "loss": 4.4088, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678090991461402e-05, + "loss": 4.4067, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.67725239671035e-05, + "loss": 4.4114, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676413801959298e-05, + "loss": 4.4143, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675575207208246e-05, + "loss": 4.3977, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674736612457194e-05, + "loss": 4.4074, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.396, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673062698715837e-05, + "loss": 4.4095, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4051, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.401, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4072, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4041, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668869724960576e-05, + "loss": 4.3956, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668031130209524e-05, + "loss": 4.4001, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.4014, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.66635394070742e-05, + "loss": 4.3987, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665515345956368e-05, + "loss": 4.3855, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664676751205316e-05, + "loss": 4.3937, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663838156454265e-05, + "loss": 4.3985, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.3959, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.3762, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.39, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.3961, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.3856, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588098637086985e-05, + "loss": 4.3849, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.3871, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.3774, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562940794555425e-05, + "loss": 4.3957, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554571225848634e-05, + "loss": 4.38, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546185278338114e-05, + "loss": 4.3874, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.65377993308276e-05, + "loss": 4.3864, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652942976212081e-05, + "loss": 4.3902, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652104381461029e-05, + "loss": 4.3804, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651265786709977e-05, + "loss": 4.3877, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650427191958925e-05, + "loss": 4.3931, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649588597207873e-05, + "loss": 4.3864, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648750002456821e-05, + "loss": 4.3736, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647913045586142e-05, + "loss": 4.3779, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.64707445083509e-05, + "loss": 4.3736, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646235856084038e-05, + "loss": 4.3751, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645397261332986e-05, + "loss": 4.3714, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644558666581934e-05, + "loss": 4.3752, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643720071830882e-05, + "loss": 4.362, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.64288147707983e-05, + "loss": 4.3701, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420445202091514e-05, + "loss": 4.3649, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412059254580994e-05, + "loss": 4.3845, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403673307070474e-05, + "loss": 4.3823, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639528735955995e-05, + "loss": 4.3773, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638690141204943e-05, + "loss": 4.3624, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637851546453891e-05, + "loss": 4.3687, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637012951702839e-05, + "loss": 4.377, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636174356951787e-05, + "loss": 4.3742, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353374000811076e-05, + "loss": 4.3694, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6344988053300556e-05, + "loss": 4.3733, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336602105790036e-05, + "loss": 4.3682, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632821615827952e-05, + "loss": 4.3719, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319830210769e-05, + "loss": 4.3579, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631146064206221e-05, + "loss": 4.3719, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630307469455169e-05, + "loss": 4.3616, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629468874704117e-05, + "loss": 4.3546, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628630279953065e-05, + "loss": 4.3643, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627793323082386e-05, + "loss": 4.3706, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626954728331334e-05, + "loss": 4.3647, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626116133580282e-05, + "loss": 4.3593, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.62527753882923e-05, + "loss": 4.3565, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.335974216461182, + "eval_runtime": 298.1892, + "eval_samples_per_second": 1279.694, + "eval_steps_per_second": 39.991, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624438944078178e-05, + "loss": 4.3657, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623600349327126e-05, + "loss": 4.3508, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622761754576074e-05, + "loss": 4.3662, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621923159825022e-05, + "loss": 4.3545, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210862029543436e-05, + "loss": 4.3696, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202476082032916e-05, + "loss": 4.3455, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194090134522396e-05, + "loss": 4.364, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185704187011876e-05, + "loss": 4.346, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177318239501356e-05, + "loss": 4.3594, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168948670794565e-05, + "loss": 4.3544, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160562723284045e-05, + "loss": 4.3561, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152176775773525e-05, + "loss": 4.3635, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143790828263005e-05, + "loss": 4.3402, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135404880752485e-05, + "loss": 4.3488, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612701893324196e-05, + "loss": 4.342, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611863298573144e-05, + "loss": 4.347, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110247038220925e-05, + "loss": 4.3456, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610187746951414e-05, + "loss": 4.343, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093491522003614e-05, + "loss": 4.3459, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085105574493094e-05, + "loss": 4.3612, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076719626982574e-05, + "loss": 4.3479, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068333679472054e-05, + "loss": 4.347, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059947731961534e-05, + "loss": 4.3485, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605157816325474e-05, + "loss": 4.3531, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604320859454796e-05, + "loss": 4.3324, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603482264703743e-05, + "loss": 4.3503, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602643669952691e-05, + "loss": 4.3353, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601805075201639e-05, + "loss": 4.3363, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600966480450588e-05, + "loss": 4.3315, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600129523579909e-05, + "loss": 4.3366, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599290928828857e-05, + "loss": 4.3354, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598452334077805e-05, + "loss": 4.3497, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597613739326753e-05, + "loss": 4.3398, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596775144575701e-05, + "loss": 4.3389, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595936549824649e-05, + "loss": 4.3303, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5950995929539696e-05, + "loss": 4.3412, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942609982029176e-05, + "loss": 4.3241, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934224034518656e-05, + "loss": 4.3442, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925838087008136e-05, + "loss": 4.3165, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917452139497616e-05, + "loss": 4.3269, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590908257079083e-05, + "loss": 4.3277, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590069662328031e-05, + "loss": 4.3409, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589231067576979e-05, + "loss": 4.3218, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588392472825927e-05, + "loss": 4.3278, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587553878074875e-05, + "loss": 4.3297, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586715283323823e-05, + "loss": 4.3256, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585876688572771e-05, + "loss": 4.3338, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.3187, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3121, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583364180080361e-05, + "loss": 4.3336, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582525585329309e-05, + "loss": 4.3208, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581686990578257e-05, + "loss": 4.3183, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580848395827205e-05, + "loss": 4.3176, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580009801076153e-05, + "loss": 4.3219, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791712063251017e-05, + "loss": 4.3086, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783326115740497e-05, + "loss": 4.3285, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774956547033706e-05, + "loss": 4.3026, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766570599523186e-05, + "loss": 4.3161, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758184652012666e-05, + "loss": 4.3151, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749798704502146e-05, + "loss": 4.3201, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574141275699162e-05, + "loss": 4.3142, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733043188284835e-05, + "loss": 4.3188, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724657240774315e-05, + "loss": 4.2944, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716271293263794e-05, + "loss": 4.3101, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570788534575327e-05, + "loss": 4.3163, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699499398242754e-05, + "loss": 4.3118, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691113450732234e-05, + "loss": 4.3036, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.3027, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674357934514923e-05, + "loss": 4.3002, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.56659719870044e-05, + "loss": 4.3146, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565758603949388e-05, + "loss": 4.3202, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564920009198336e-05, + "loss": 4.3058, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564081414447284e-05, + "loss": 4.3174, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563242819696232e-05, + "loss": 4.3238, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56240422494518e-05, + "loss": 4.3266, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561567268074501e-05, + "loss": 4.2879, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560728673323449e-05, + "loss": 4.3095, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559890078572397e-05, + "loss": 4.3111, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559051483821345e-05, + "loss": 4.299, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558212889070293e-05, + "loss": 4.3063, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557374294319242e-05, + "loss": 4.3081, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556537337448563e-05, + "loss": 4.3138, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555698742697511e-05, + "loss": 4.3048, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554860147946459e-05, + "loss": 4.2955, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554021553195407e-05, + "loss": 4.2983, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553182958444355e-05, + "loss": 4.2975, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552346001573676e-05, + "loss": 4.3057, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551507406822624e-05, + "loss": 4.3092, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550668812071572e-05, + "loss": 4.2921, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498318552008926e-05, + "loss": 4.2977, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489932604498406e-05, + "loss": 4.2891, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481546656987886e-05, + "loss": 4.2987, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547316070947737e-05, + "loss": 4.3009, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546477476196685e-05, + "loss": 4.2925, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545640519326006e-05, + "loss": 4.3036, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544801924574954e-05, + "loss": 4.2984, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543963329823902e-05, + "loss": 4.2923, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54312473507285e-05, + "loss": 4.2964, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542286140321798e-05, + "loss": 4.2978, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414475455707455e-05, + "loss": 4.2994, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540610588700067e-05, + "loss": 4.2811, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539771993949015e-05, + "loss": 4.2911, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538933399197963e-05, + "loss": 4.2961, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538094804446911e-05, + "loss": 4.2977, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537256209695859e-05, + "loss": 4.2777, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536417614944807e-05, + "loss": 4.2834, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535579020193755e-05, + "loss": 4.2956, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534740425442703e-05, + "loss": 4.2863, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533903468572024e-05, + "loss": 4.2837, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330665117013455e-05, + "loss": 4.2842, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532227916950293e-05, + "loss": 4.2838, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531389322199241e-05, + "loss": 4.2902, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530550727448189e-05, + "loss": 4.2846, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529712132697137e-05, + "loss": 4.2823, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528873537946085e-05, + "loss": 4.2895, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280365810754064e-05, + "loss": 4.2925, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5271979863243544e-05, + "loss": 4.2899, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263593915733024e-05, + "loss": 4.281, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255207968222504e-05, + "loss": 4.2971, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246822020711984e-05, + "loss": 4.2887, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238436073201464e-05, + "loss": 4.2746, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523006650449467e-05, + "loss": 4.2813, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522169693578788e-05, + "loss": 4.2775, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521331098827736e-05, + "loss": 4.2809, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520492504076684e-05, + "loss": 4.2721, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519653909325632e-05, + "loss": 4.2825, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.51881531457458e-05, + "loss": 4.2666, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517976719823528e-05, + "loss": 4.2749, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517138125072476e-05, + "loss": 4.2697, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516299530321425e-05, + "loss": 4.2903, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515460935570373e-05, + "loss": 4.2832, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514622340819321e-05, + "loss": 4.2832, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513783746068269e-05, + "loss": 4.2669, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512945151317217e-05, + "loss": 4.2786, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512108194446538e-05, + "loss": 4.2855, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112712375758586e-05, + "loss": 4.2777, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104326428248066e-05, + "loss": 4.2761, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5095940480737546e-05, + "loss": 4.282, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087570912030755e-05, + "loss": 4.2765, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079184964520235e-05, + "loss": 4.2805, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070799017009715e-05, + "loss": 4.2629, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062413069499195e-05, + "loss": 4.2811, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505402712198868e-05, + "loss": 4.2686, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504564117447816e-05, + "loss": 4.2685, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503725522696764e-05, + "loss": 4.2727, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028869279457115e-05, + "loss": 4.279, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020483331946595e-05, + "loss": 4.2713, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012097384436075e-05, + "loss": 4.2667, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003711436925555e-05, + "loss": 4.2691, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.253751277923584, + "eval_runtime": 299.7428, + "eval_samples_per_second": 1273.061, + "eval_steps_per_second": 39.784, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995325489415035e-05, + "loss": 4.2697, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986939541904515e-05, + "loss": 4.2628, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978553594393995e-05, + "loss": 4.2739, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970167646883475e-05, + "loss": 4.2659, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961781699372955e-05, + "loss": 4.2787, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953395751862435e-05, + "loss": 4.2629, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945009804351915e-05, + "loss": 4.2699, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936623856841395e-05, + "loss": 4.258, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492823790933088e-05, + "loss": 4.2688, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919851961820354e-05, + "loss": 4.2712, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911466014309834e-05, + "loss": 4.2666, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903080066799314e-05, + "loss": 4.2703, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489471049809253e-05, + "loss": 4.2552, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886324550582003e-05, + "loss": 4.2628, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4877938603071483e-05, + "loss": 4.2566, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486955265556096e-05, + "loss": 4.2578, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486116670805044e-05, + "loss": 4.2605, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485278076053992e-05, + "loss": 4.2596, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48443948130294e-05, + "loss": 4.2594, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483600886551888e-05, + "loss": 4.271, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482762291800836e-05, + "loss": 4.266, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481925334930158e-05, + "loss": 4.262, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481086740179106e-05, + "loss": 4.2664, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480248145428054e-05, + "loss": 4.2682, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479409550677002e-05, + "loss": 4.2472, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47857095592595e-05, + "loss": 4.2635, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477732361174898e-05, + "loss": 4.25, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476893766423846e-05, + "loss": 4.2495, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476056809553167e-05, + "loss": 4.2468, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.2538, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474381257931436e-05, + "loss": 4.2511, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473542663180384e-05, + "loss": 4.2662, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472704068429332e-05, + "loss": 4.2585, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718654736782804e-05, + "loss": 4.2551, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471028516807601e-05, + "loss": 4.2496, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470189922056549e-05, + "loss": 4.2578, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469351327305497e-05, + "loss": 4.2502, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468512732554445e-05, + "loss": 4.2567, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467674137803393e-05, + "loss": 4.2348, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466835543052341e-05, + "loss": 4.2434, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.465996948301289e-05, + "loss": 4.2461, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651583535502366e-05, + "loss": 4.2599, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643197587991846e-05, + "loss": 4.245, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463482801928506e-05, + "loss": 4.2455, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462644207177454e-05, + "loss": 4.2496, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461805612426402e-05, + "loss": 4.2455, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609702934360966e-05, + "loss": 4.2526, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601316986850446e-05, + "loss": 4.2394, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592931039339926e-05, + "loss": 4.2322, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2537, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2397, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2415, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455938724929784e-05, + "loss": 4.2367, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455100130178732e-05, + "loss": 4.2457, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542631733080535e-05, + "loss": 4.2311, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453424578557001e-05, + "loss": 4.2441, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452585983805949e-05, + "loss": 4.2294, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517473890548975e-05, + "loss": 4.2357, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450910432184219e-05, + "loss": 4.2404, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500718374331664e-05, + "loss": 4.2394, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492332426821144e-05, + "loss": 4.2359, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448396285811436e-05, + "loss": 4.2462, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447557691060384e-05, + "loss": 4.2185, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446719096309331e-05, + "loss": 4.2288, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445880501558279e-05, + "loss": 4.239, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445041906807227e-05, + "loss": 4.2333, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444203312056175e-05, + "loss": 4.2315, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443364717305123e-05, + "loss": 4.2239, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442526122554071e-05, + "loss": 4.224, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441687527803019e-05, + "loss": 4.2352, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440848933051967e-05, + "loss": 4.2435, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440010338300916e-05, + "loss": 4.234, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439171743549864e-05, + "loss": 4.2402, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438333148798812e-05, + "loss": 4.2464, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.43749455404776e-05, + "loss": 4.2528, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436655959296708e-05, + "loss": 4.2188, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.2303, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43498204555535e-05, + "loss": 4.2417, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434143450804298e-05, + "loss": 4.2186, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433304856053246e-05, + "loss": 4.2356, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432466261302194e-05, + "loss": 4.2327, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431627666551142e-05, + "loss": 4.2379, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.43078907180009e-05, + "loss": 4.235, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429950477049038e-05, + "loss": 4.22, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429111882297986e-05, + "loss": 4.2267, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428273287546934e-05, + "loss": 4.2222, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427436330676255e-05, + "loss": 4.2308, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4265977359252026e-05, + "loss": 4.2373, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257591411741506e-05, + "loss": 4.2182, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249205464230986e-05, + "loss": 4.2259, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42408358955242e-05, + "loss": 4.2187, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423246632681741e-05, + "loss": 4.2249, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422408037930689e-05, + "loss": 4.2273, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421569443179637e-05, + "loss": 4.2246, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420730848428585e-05, + "loss": 4.2332, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419892253677533e-05, + "loss": 4.2225, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419053658926481e-05, + "loss": 4.2224, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418215064175429e-05, + "loss": 4.2231, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417376469424377e-05, + "loss": 4.2231, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416537874673325e-05, + "loss": 4.2306, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415699279922273e-05, + "loss": 4.2119, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414860685171221e-05, + "loss": 4.2206, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414022090420169e-05, + "loss": 4.2243, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413186771429863e-05, + "loss": 4.2276, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412348176678811e-05, + "loss": 4.2067, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411509581927759e-05, + "loss": 4.2152, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410670987176707e-05, + "loss": 4.2254, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409832392425655e-05, + "loss": 4.2176, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408993797674603e-05, + "loss": 4.21, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081552029235515e-05, + "loss": 4.2205, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073166081724995e-05, + "loss": 4.209, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064796513018204e-05, + "loss": 4.2246, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056410565507684e-05, + "loss": 4.2141, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048024617997164e-05, + "loss": 4.2085, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039638670486644e-05, + "loss": 4.2237, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031252722976124e-05, + "loss": 4.2274, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402288315426933e-05, + "loss": 4.2193, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401449720675881e-05, + "loss": 4.214, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400611125924829e-05, + "loss": 4.2222, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399772531173777e-05, + "loss": 4.2201, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398933936422725e-05, + "loss": 4.2084, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398095341671673e-05, + "loss": 4.2196, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397258384800995e-05, + "loss": 4.2086, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396421427930316e-05, + "loss": 4.2117, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395582833179264e-05, + "loss": 4.2051, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394744238428212e-05, + "loss": 4.2137, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.39390564367716e-05, + "loss": 4.1996, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393067048926108e-05, + "loss": 4.2045, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392228454175056e-05, + "loss": 4.2084, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391389859424003e-05, + "loss": 4.2203, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390551264672951e-05, + "loss": 4.2189, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389714307802273e-05, + "loss": 4.2175, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388875713051221e-05, + "loss": 4.1996, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388037118300169e-05, + "loss": 4.2159, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387198523549117e-05, + "loss": 4.2173, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863599287980647e-05, + "loss": 4.2131, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855213340470127e-05, + "loss": 4.2083, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846827392959606e-05, + "loss": 4.2196, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838441445449086e-05, + "loss": 4.2074, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830055497938566e-05, + "loss": 4.2165, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821685929231775e-05, + "loss": 4.1946, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813299981721255e-05, + "loss": 4.2201, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804914034210735e-05, + "loss": 4.201, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796528086700215e-05, + "loss": 4.204, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788142139189695e-05, + "loss": 4.2092, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779756191679175e-05, + "loss": 4.2081, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377138662297239e-05, + "loss": 4.212, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.37630170542656e-05, + "loss": 4.1982, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375464748555881e-05, + "loss": 4.211, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.197904109954834, + "eval_runtime": 296.9374, + "eval_samples_per_second": 1285.089, + "eval_steps_per_second": 40.16, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374626153804829e-05, + "loss": 4.2068, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373787559053777e-05, + "loss": 4.1991, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372948964302725e-05, + "loss": 4.2109, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372110369551673e-05, + "loss": 4.2017, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371271774800621e-05, + "loss": 4.2117, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370433180049569e-05, + "loss": 4.2006, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369594585298517e-05, + "loss": 4.2005, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368755990547465e-05, + "loss": 4.2005, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367917395796413e-05, + "loss": 4.2026, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367078801045361e-05, + "loss": 4.2072, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366240206294309e-05, + "loss": 4.2036, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.3654016115432576e-05, + "loss": 4.2103, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364563016792205e-05, + "loss": 4.1943, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363724422041153e-05, + "loss": 4.1998, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362885827290101e-05, + "loss": 4.1982, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.3620488704194225e-05, + "loss": 4.1915, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.36121027566837e-05, + "loss": 4.1999, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360371680917318e-05, + "loss": 4.1929, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359533086166266e-05, + "loss": 4.1956, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358694491415214e-05, + "loss": 4.2122, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357855896664162e-05, + "loss": 4.2027, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.35701730191311e-05, + "loss": 4.2067, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356178707162058e-05, + "loss": 4.2, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355340112411006e-05, + "loss": 4.2047, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354501517659954e-05, + "loss": 4.1861, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353666198669648e-05, + "loss": 4.2039, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352827603918596e-05, + "loss": 4.1928, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.351989009167544e-05, + "loss": 4.1837, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351150414416492e-05, + "loss": 4.1879, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.35031181966544e-05, + "loss": 4.1915, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349473224914388e-05, + "loss": 4.1937, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348634630163336e-05, + "loss": 4.2028, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347796035412284e-05, + "loss": 4.2018, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.346959078541605e-05, + "loss": 4.1937, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346122121670926e-05, + "loss": 4.1902, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345283526919875e-05, + "loss": 4.194, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344444932168823e-05, + "loss": 4.1899, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343606337417771e-05, + "loss": 4.195, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342767742666719e-05, + "loss": 4.1813, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341929147915667e-05, + "loss": 4.1815, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341090553164615e-05, + "loss": 4.1882, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402535962939356e-05, + "loss": 4.1983, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394150015428836e-05, + "loss": 4.188, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3385764067918316e-05, + "loss": 4.1857, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377378120407796e-05, + "loss": 4.1918, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3368992172897276e-05, + "loss": 4.1847, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3360606225386756e-05, + "loss": 4.1942, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335222027787623e-05, + "loss": 4.1809, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3343834330365716e-05, + "loss": 4.1732, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333546476165893e-05, + "loss": 4.1935, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332707881414841e-05, + "loss": 4.1857, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.3318692866637885e-05, + "loss": 4.1819, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.33103232979311e-05, + "loss": 4.1842, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330193735042058e-05, + "loss": 4.182, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3293551402910054e-05, + "loss": 4.1773, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285165455399534e-05, + "loss": 4.1807, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327679588669275e-05, + "loss": 4.1737, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326840993918223e-05, + "loss": 4.1764, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.32600239916717e-05, + "loss": 4.1881, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325163804416118e-05, + "loss": 4.1787, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324325209665067e-05, + "loss": 4.1799, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3234882527943885e-05, + "loss": 4.1897, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322649658043336e-05, + "loss": 4.1663, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321811063292284e-05, + "loss": 4.1709, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.320972468541232e-05, + "loss": 4.1786, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.32013387379018e-05, + "loss": 4.1819, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319296916919501e-05, + "loss": 4.1706, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318458322168449e-05, + "loss": 4.1719, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317619727417397e-05, + "loss": 4.1638, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316781132666345e-05, + "loss": 4.18, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315942537915293e-05, + "loss": 4.1862, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151055810446136e-05, + "loss": 4.1799, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314266986293562e-05, + "loss": 4.1842, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.31342839154251e-05, + "loss": 4.1844, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312589796791458e-05, + "loss": 4.2035, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311751202040406e-05, + "loss": 4.1656, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310912607289354e-05, + "loss": 4.1738, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310074012538302e-05, + "loss": 4.1889, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.30923541778725e-05, + "loss": 4.162, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308396823036198e-05, + "loss": 4.181, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307559866165519e-05, + "loss": 4.1777, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306721271414467e-05, + "loss": 4.1808, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305882676663415e-05, + "loss": 4.1797, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305044081912363e-05, + "loss": 4.1643, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304205487161311e-05, + "loss": 4.1794, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303368530290632e-05, + "loss": 4.1631, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.30252993553958e-05, + "loss": 4.1785, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301691340788529e-05, + "loss": 4.1839, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008543839178496e-05, + "loss": 4.1607, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000157891667976e-05, + "loss": 4.174, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2991788322961185e-05, + "loss": 4.1663, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983402375450665e-05, + "loss": 4.1683, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2975016427940145e-05, + "loss": 4.17, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2966630480429625e-05, + "loss": 4.178, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958244532919105e-05, + "loss": 4.1814, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.2949858585408585e-05, + "loss": 4.1648, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.2941472637898065e-05, + "loss": 4.1664, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293308669038754e-05, + "loss": 4.1744, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.2924700742877025e-05, + "loss": 4.1685, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.2916314795366505e-05, + "loss": 4.1806, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.2907928847855985e-05, + "loss": 4.1609, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.2899542900345465e-05, + "loss": 4.1649, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.2891156952834945e-05, + "loss": 4.1716, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.2882787384128154e-05, + "loss": 4.1758, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874401436617634e-05, + "loss": 4.1538, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.2866015489107114e-05, + "loss": 4.1634, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2857629541596594e-05, + "loss": 4.1688, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.28492599728898e-05, + "loss": 4.1683, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284087402537928e-05, + "loss": 4.1557, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283248807786876e-05, + "loss": 4.1749, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282410213035824e-05, + "loss": 4.1553, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281571618284772e-05, + "loss": 4.1679, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280733023533721e-05, + "loss": 4.1645, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279896066663042e-05, + "loss": 4.1584, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.27905747191199e-05, + "loss": 4.17, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278218877160938e-05, + "loss": 4.1764, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277380282409886e-05, + "loss": 4.1682, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276541687658834e-05, + "loss": 4.1631, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275704730788155e-05, + "loss": 4.1714, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274866136037103e-05, + "loss": 4.169, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274027541286051e-05, + "loss": 4.1575, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273188946534999e-05, + "loss": 4.1653, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272350351783947e-05, + "loss": 4.1587, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271511757032895e-05, + "loss": 4.1595, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270673162281843e-05, + "loss": 4.1602, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269834567530791e-05, + "loss": 4.1592, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.268995972779739e-05, + "loss": 4.155, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268157378028687e-05, + "loss": 4.1516, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673204211580076e-05, + "loss": 4.1579, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2664818264069556e-05, + "loss": 4.168, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656432316559036e-05, + "loss": 4.1662, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648046369048516e-05, + "loss": 4.1686, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.2639676800341725e-05, + "loss": 4.1474, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.2631290852831205e-05, + "loss": 4.1684, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.2622904905320685e-05, + "loss": 4.1666, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2614518957810165e-05, + "loss": 4.1617, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260614938910338e-05, + "loss": 4.1631, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259776344159286e-05, + "loss": 4.165, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258937749408234e-05, + "loss": 4.1575, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258099154657182e-05, + "loss": 4.1725, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257262197786503e-05, + "loss": 4.1429, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256423603035451e-05, + "loss": 4.1678, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255585008284399e-05, + "loss": 4.1508, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.25474805141372e-05, + "loss": 4.1558, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253909456662668e-05, + "loss": 4.1602, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253070861911616e-05, + "loss": 4.1537, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252232267160564e-05, + "loss": 4.1689, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251393672409512e-05, + "loss": 4.1429, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.25055507765846e-05, + "loss": 4.1623, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 4.156124591827393, + "eval_runtime": 283.8799, + "eval_samples_per_second": 1344.199, + "eval_steps_per_second": 42.007, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2497164829074085e-05, + "loss": 4.1592, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.2488778881563565e-05, + "loss": 4.1477, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.2480392934053045e-05, + "loss": 4.1611, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.2472006986542525e-05, + "loss": 4.1546, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.2463621039032005e-05, + "loss": 4.1601, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.2455235091521485e-05, + "loss": 4.1535, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.2446849144010965e-05, + "loss": 4.1491, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.2438479575304174e-05, + "loss": 4.1535, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243011000659738e-05, + "loss": 4.1536, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242172405908686e-05, + "loss": 4.1571, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241333811157634e-05, + "loss": 4.157, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240495216406582e-05, + "loss": 4.1571, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.23965662165553e-05, + "loss": 4.1509, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238819664784852e-05, + "loss": 4.1492, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2379810700338e-05, + "loss": 4.15, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237142475282748e-05, + "loss": 4.1417, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236303880531696e-05, + "loss": 4.1511, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235465285780644e-05, + "loss": 4.1444, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234626691029591e-05, + "loss": 4.1474, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233788096278539e-05, + "loss": 4.1621, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.232949501527487e-05, + "loss": 4.1571, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232112544656809e-05, + "loss": 4.1581, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231273949905756e-05, + "loss": 4.1523, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230435355154704e-05, + "loss": 4.1585, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229596760403652e-05, + "loss": 4.1374, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.2287581656526e-05, + "loss": 4.157, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227921208781922e-05, + "loss": 4.1442, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227084251911243e-05, + "loss": 4.1355, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226245657160191e-05, + "loss": 4.1423, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.2254070624091386e-05, + "loss": 4.1464, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.2245684676580866e-05, + "loss": 4.1466, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.2237298729070346e-05, + "loss": 4.1565, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.2228912781559826e-05, + "loss": 4.1528, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.2220526834049306e-05, + "loss": 4.1497, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.2212157265342515e-05, + "loss": 4.1383, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1498, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.2195385370321475e-05, + "loss": 4.1484, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.2186999422810955e-05, + "loss": 4.1408, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217861347530044e-05, + "loss": 4.1376, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217022752778992e-05, + "loss": 4.1326, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.21618415802794e-05, + "loss": 4.1435, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215345563276888e-05, + "loss": 4.15, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214508606406209e-05, + "loss": 4.1444, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.213670011655157e-05, + "loss": 4.1389, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.212831416904105e-05, + "loss": 4.1459, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.211994460033426e-05, + "loss": 4.1373, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211155865282374e-05, + "loss": 4.1504, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210317270531322e-05, + "loss": 4.1352, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.20947867578027e-05, + "loss": 4.1228, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208640081029218e-05, + "loss": 4.1502, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207801486278166e-05, + "loss": 4.1398, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.206962891527114e-05, + "loss": 4.1403, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.2061242967760626e-05, + "loss": 4.135, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.2052873399053835e-05, + "loss": 4.1336, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.2044487451543315e-05, + "loss": 4.1352, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.2036101504032795e-05, + "loss": 4.1345, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.2027715556522275e-05, + "loss": 4.1299, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201932960901175e-05, + "loss": 4.1353, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1389, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.2002574092794444e-05, + "loss": 4.1331, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.1994188145283924e-05, + "loss": 4.1318, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.19858021977734e-05, + "loss": 4.15, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197741625026288e-05, + "loss": 4.1175, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196904668155609e-05, + "loss": 4.1238, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.196066073404557e-05, + "loss": 4.1351, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195227478653505e-05, + "loss": 4.1405, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194388883902453e-05, + "loss": 4.1279, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193550289151401e-05, + "loss": 4.128, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192713332280722e-05, + "loss": 4.1187, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.19187473752967e-05, + "loss": 4.1338, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191036142778618e-05, + "loss": 4.1438, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.19019918590794e-05, + "loss": 4.1344, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189360591156887e-05, + "loss": 4.1344, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188521996405835e-05, + "loss": 4.145, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187683401654783e-05, + "loss": 4.1578, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186844806903731e-05, + "loss": 4.1253, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.1860078500330526e-05, + "loss": 4.1312, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.1851692552820006e-05, + "loss": 4.1428, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.1843306605309486e-05, + "loss": 4.1184, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.1834920657798966e-05, + "loss": 4.1358, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.1826534710288446e-05, + "loss": 4.1348, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.1818148762777926e-05, + "loss": 4.1379, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.1809762815267406e-05, + "loss": 4.1399, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.1801376867756886e-05, + "loss": 4.1213, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.1792990920246366e-05, + "loss": 4.1338, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.1784604972735846e-05, + "loss": 4.1252, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.1776219025225326e-05, + "loss": 4.1326, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.1767833077714806e-05, + "loss": 4.1385, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.1759463509008015e-05, + "loss": 4.1206, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.1751077561497495e-05, + "loss": 4.1304, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174270799279071e-05, + "loss": 4.1238, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173432204528019e-05, + "loss": 4.123, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.172593609776967e-05, + "loss": 4.1313, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.171755015025915e-05, + "loss": 4.1331, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170916420274863e-05, + "loss": 4.1391, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.170077825523811e-05, + "loss": 4.1253, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1692392307727584e-05, + "loss": 4.1246, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684006360217064e-05, + "loss": 4.131, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1675620412706544e-05, + "loss": 4.1281, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166725084399975e-05, + "loss": 4.1344, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165886489648923e-05, + "loss": 4.1228, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.165047894897872e-05, + "loss": 4.1213, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.16420930014682e-05, + "loss": 4.1276, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.163370705395768e-05, + "loss": 4.1382, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.162532110644716e-05, + "loss": 4.1086, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.161693515893664e-05, + "loss": 4.1248, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160856559022985e-05, + "loss": 4.125, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160017964271933e-05, + "loss": 4.1281, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159179369520881e-05, + "loss": 4.1135, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158342412650202e-05, + "loss": 4.1299, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.15750381789915e-05, + "loss": 4.1213, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156665223148098e-05, + "loss": 4.122, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155826628397046e-05, + "loss": 4.1288, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.154988033645994e-05, + "loss": 4.1173, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154149438894942e-05, + "loss": 4.1247, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.1533108441438904e-05, + "loss": 4.1388, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.1524722493928384e-05, + "loss": 4.1289, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.1516336546417864e-05, + "loss": 4.1199, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150796697771107e-05, + "loss": 4.1314, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.149958103020055e-05, + "loss": 4.128, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149121146149376e-05, + "loss": 4.1129, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148282551398324e-05, + "loss": 4.1285, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147443956647272e-05, + "loss": 4.1166, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.14660536189622e-05, + "loss": 4.1172, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145766767145168e-05, + "loss": 4.1196, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144928172394116e-05, + "loss": 4.1192, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144089577643064e-05, + "loss": 4.1158, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143250982892012e-05, + "loss": 4.115, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.14241238814096e-05, + "loss": 4.1154, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.141573793389908e-05, + "loss": 4.131, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140735198638856e-05, + "loss": 4.1233, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139896603887804e-05, + "loss": 4.1257, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139058009136752e-05, + "loss": 4.1073, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138221052266073e-05, + "loss": 4.1337, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137382457515021e-05, + "loss": 4.1252, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136543862763969e-05, + "loss": 4.1234, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.1357085437736635e-05, + "loss": 4.1233, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1348699490226115e-05, + "loss": 4.1258, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1340313542715595e-05, + "loss": 4.1161, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.1331927595205075e-05, + "loss": 4.1363, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.1323541647694555e-05, + "loss": 4.1048, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.1315155700184035e-05, + "loss": 4.1258, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1306769752673515e-05, + "loss": 4.1155, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1298400183966724e-05, + "loss": 4.1161, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290014236456204e-05, + "loss": 4.1178, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128164466774942e-05, + "loss": 4.1146, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127325872023889e-05, + "loss": 4.1301, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.126487277272837e-05, + "loss": 4.1084, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125648682521785e-05, + "loss": 4.124, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 4.125783443450928, + "eval_runtime": 283.4627, + "eval_samples_per_second": 1346.177, + "eval_steps_per_second": 42.069, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124810087770733e-05, + "loss": 4.124, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.123971493019681e-05, + "loss": 4.1092, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123132898268629e-05, + "loss": 4.1231, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122294303517577e-05, + "loss": 4.1169, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121455708766526e-05, + "loss": 4.1192, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120617114015474e-05, + "loss": 4.1148, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119778519264422e-05, + "loss": 4.1165, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.11893992451337e-05, + "loss": 4.1099, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118101329762318e-05, + "loss": 4.1189, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117262735011266e-05, + "loss": 4.1209, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116424140260213e-05, + "loss": 4.1188, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115585545509161e-05, + "loss": 4.1169, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114748588638483e-05, + "loss": 4.114, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.11390999388743e-05, + "loss": 4.1115, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113071399136378e-05, + "loss": 4.114, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112232804385326e-05, + "loss": 4.1037, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111394209634274e-05, + "loss": 4.1117, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110555614883223e-05, + "loss": 4.1111, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109718658012544e-05, + "loss": 4.1112, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108880063261492e-05, + "loss": 4.1201, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.10804146851044e-05, + "loss": 4.1232, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107202873759388e-05, + "loss": 4.1195, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106364279008336e-05, + "loss": 4.1135, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1055273221376566e-05, + "loss": 4.1186, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1046887273866046e-05, + "loss": 4.1035, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1038501326355526e-05, + "loss": 4.1201, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030131757648735e-05, + "loss": 4.1065, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1021745810138215e-05, + "loss": 4.101, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1013359862627695e-05, + "loss": 4.1048, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100497391511718e-05, + "loss": 4.1107, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099658796760666e-05, + "loss": 4.109, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098820202009614e-05, + "loss": 4.1194, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.097981607258562e-05, + "loss": 4.1173, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.09714301250751e-05, + "loss": 4.1093, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096306055636831e-05, + "loss": 4.1043, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095467460885779e-05, + "loss": 4.1153, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094628866134727e-05, + "loss": 4.1123, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093790271383675e-05, + "loss": 4.1053, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.092951676632623e-05, + "loss": 4.1035, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092113081881571e-05, + "loss": 4.0947, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091274487130519e-05, + "loss": 4.1047, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904358923794664e-05, + "loss": 4.1175, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089597297628415e-05, + "loss": 4.1076, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088758702877363e-05, + "loss": 4.1022, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087920108126311e-05, + "loss": 4.111, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087081513375259e-05, + "loss": 4.0991, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.08624455650458e-05, + "loss": 4.115, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854075996339015e-05, + "loss": 4.1037, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0845690048828495e-05, + "loss": 4.0846, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083730410131797e-05, + "loss": 4.113, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082891815380745e-05, + "loss": 4.1039, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082053220629693e-05, + "loss": 4.1065, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081216263759014e-05, + "loss": 4.0983, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080377669007962e-05, + "loss": 4.0973, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.07953907425691e-05, + "loss": 4.0992, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078702117386231e-05, + "loss": 4.0965, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077863522635179e-05, + "loss": 4.0994, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077024927884127e-05, + "loss": 4.0968, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076186333133075e-05, + "loss": 4.1109, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075349376262397e-05, + "loss": 4.092, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074510781511344e-05, + "loss": 4.0999, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073672186760292e-05, + "loss": 4.1127, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.07283359200924e-05, + "loss": 4.0828, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.071994997258188e-05, + "loss": 4.0873, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071156402507136e-05, + "loss": 4.1039, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070317807756084e-05, + "loss": 4.103, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069479213005032e-05, + "loss": 4.0916, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.06864061825398e-05, + "loss": 4.0958, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067805299263675e-05, + "loss": 4.0835, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.066966704512623e-05, + "loss": 4.1017, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066128109761571e-05, + "loss": 4.1041, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065289515010519e-05, + "loss": 4.1004, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064450920259467e-05, + "loss": 4.1004, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636123255084147e-05, + "loss": 4.1105, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0627737307573627e-05, + "loss": 4.1205, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0619351360063106e-05, + "loss": 4.0904, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0610965412552586e-05, + "loss": 4.0949, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0602595843845796e-05, + "loss": 4.1097, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594209896335276e-05, + "loss": 4.087, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058584032762849e-05, + "loss": 4.0971, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057745438011797e-05, + "loss": 4.1007, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056906843260745e-05, + "loss": 4.1048, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056068248509693e-05, + "loss": 4.1073, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055229653758641e-05, + "loss": 4.0878, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054391059007589e-05, + "loss": 4.0969, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053552464256537e-05, + "loss": 4.0908, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052713869505485e-05, + "loss": 4.099, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0518752747544324e-05, + "loss": 4.1007, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0510366800033804e-05, + "loss": 4.0895, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0501980852523284e-05, + "loss": 4.0949, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.04936112838165e-05, + "loss": 4.0921, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048524171510971e-05, + "loss": 4.0889, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047685576759919e-05, + "loss": 4.0964, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0468469820088676e-05, + "loss": 4.0984, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460083872578156e-05, + "loss": 4.1045, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045169792506763e-05, + "loss": 4.0949, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044331197755711e-05, + "loss": 4.0875, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043492603004659e-05, + "loss": 4.0975, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.04265564613398e-05, + "loss": 4.0961, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041817051382928e-05, + "loss": 4.0969, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.040978456631876e-05, + "loss": 4.0923, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0401414997611974e-05, + "loss": 4.0883, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039302905010145e-05, + "loss": 4.093, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038464310259093e-05, + "loss": 4.1065, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376257155080414e-05, + "loss": 4.0777, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.0367871207569894e-05, + "loss": 4.0913, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.0359485260059374e-05, + "loss": 4.0897, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351099312548853e-05, + "loss": 4.094, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0342713365038333e-05, + "loss": 4.084, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033432741752781e-05, + "loss": 4.0982, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032595784882102e-05, + "loss": 4.0828, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031758828011423e-05, + "loss": 4.0923, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030920233260371e-05, + "loss": 4.0967, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030081638509319e-05, + "loss": 4.0817, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029243043758267e-05, + "loss": 4.0922, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028404449007215e-05, + "loss": 4.1042, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027565854256163e-05, + "loss": 4.095, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026727259505111e-05, + "loss": 4.0883, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025888664754059e-05, + "loss": 4.0939, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025050070003008e-05, + "loss": 4.0985, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024211475251956e-05, + "loss": 4.0831, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0233761562616496e-05, + "loss": 4.0951, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0225375615105976e-05, + "loss": 4.0797, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0216989667595456e-05, + "loss": 4.0857, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0208603720084936e-05, + "loss": 4.084, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200217772574416e-05, + "loss": 4.0882, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0191831825063896e-05, + "loss": 4.0831, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0183445877553376e-05, + "loss": 4.0844, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175059930042856e-05, + "loss": 4.0795, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0166673982532336e-05, + "loss": 4.0989, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0158304413825545e-05, + "loss": 4.0952, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.014991846631503e-05, + "loss": 4.0937, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014154889760824e-05, + "loss": 4.0763, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013316295009772e-05, + "loss": 4.102, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.01247770025872e-05, + "loss": 4.0878, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011639105507668e-05, + "loss": 4.0919, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010800510756616e-05, + "loss": 4.0961, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0099619160055634e-05, + "loss": 4.0877, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091233212545114e-05, + "loss": 4.0837, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0082847265034594e-05, + "loss": 4.1032, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0074461317524074e-05, + "loss": 4.0747, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006609174881728e-05, + "loss": 4.0942, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005770580130677e-05, + "loss": 4.0832, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.004931985379625e-05, + "loss": 4.0865, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004093390628573e-05, + "loss": 4.0831, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003256433757894e-05, + "loss": 4.082, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002417839006842e-05, + "loss": 4.0955, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0015808821361634e-05, + "loss": 4.0813, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000742287385111e-05, + "loss": 4.0886, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 4.101009368896484, + "eval_runtime": 290.5251, + "eval_samples_per_second": 1313.453, + "eval_steps_per_second": 41.046, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999903692634059e-05, + "loss": 4.0852, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999065097883007e-05, + "loss": 4.0817, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998226503131955e-05, + "loss": 4.0861, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997387908380903e-05, + "loss": 4.0839, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996549313629851e-05, + "loss": 4.092, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995710718878799e-05, + "loss": 4.0798, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.99487376200812e-05, + "loss": 4.0887, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994035167257068e-05, + "loss": 4.0816, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993196572506016e-05, + "loss": 4.0843, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992357977754964e-05, + "loss": 4.0922, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991519383003912e-05, + "loss": 4.0853, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990682426133233e-05, + "loss": 4.0832, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989843831382181e-05, + "loss": 4.09, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989005236631129e-05, + "loss": 4.0725, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988166641880077e-05, + "loss": 4.0815, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987329685009398e-05, + "loss": 4.0734, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986491090258346e-05, + "loss": 4.083, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985652495507294e-05, + "loss": 4.0785, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984813900756242e-05, + "loss": 4.0771, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.983975306005191e-05, + "loss": 4.0901, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983136711254139e-05, + "loss": 4.0946, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823013922638326e-05, + "loss": 4.0929, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9814627975127806e-05, + "loss": 4.0802, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9806242027617286e-05, + "loss": 4.0846, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9797856080106766e-05, + "loss": 4.0767, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9789470132596246e-05, + "loss": 4.086, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781084185085726e-05, + "loss": 4.0791, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9772698237575205e-05, + "loss": 4.0763, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.9764312290064685e-05, + "loss": 4.0726, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.9755942721357895e-05, + "loss": 4.078, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9747556773847374e-05, + "loss": 4.0743, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973917082633686e-05, + "loss": 4.0904, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973078487882634e-05, + "loss": 4.0849, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972239893131582e-05, + "loss": 4.0802, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.9714012983805294e-05, + "loss": 4.0738, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.9705627036294774e-05, + "loss": 4.0821, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.9697241088784254e-05, + "loss": 4.0815, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9688855141273734e-05, + "loss": 4.0767, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968048557256694e-05, + "loss": 4.0768, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967209962505642e-05, + "loss": 4.0647, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.96637136775459e-05, + "loss": 4.0698, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965532773003538e-05, + "loss": 4.0851, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964694178252486e-05, + "loss": 4.0806, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963855583501434e-05, + "loss": 4.0691, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963016988750382e-05, + "loss": 4.0799, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962178393999331e-05, + "loss": 4.0698, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.961339799248279e-05, + "loss": 4.0812, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605028423776e-05, + "loss": 4.076, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959664247626548e-05, + "loss": 4.0495, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958827290755869e-05, + "loss": 4.0859, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.957988696004817e-05, + "loss": 4.073, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957150101253765e-05, + "loss": 4.0785, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956311506502713e-05, + "loss": 4.0718, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955472911751661e-05, + "loss": 4.0677, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954635954880982e-05, + "loss": 4.0652, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.95379736012993e-05, + "loss": 4.0672, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.952958765378878e-05, + "loss": 4.0677, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.9521201706278263e-05, + "loss": 4.065, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951283213757147e-05, + "loss": 4.0804, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950444619006095e-05, + "loss": 4.0641, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949606024255043e-05, + "loss": 4.0709, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948769067384364e-05, + "loss": 4.0824, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947930472633312e-05, + "loss": 4.0535, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.94709187788226e-05, + "loss": 4.0582, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946253283131208e-05, + "loss": 4.073, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945414688380156e-05, + "loss": 4.0718, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944576093629104e-05, + "loss": 4.0633, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943737498878052e-05, + "loss": 4.0662, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942898904127e-05, + "loss": 4.0587, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942060309375948e-05, + "loss": 4.0683, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941221714624896e-05, + "loss": 4.0752, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940383119873844e-05, + "loss": 4.0697, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939544525122792e-05, + "loss": 4.0748, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938707568252113e-05, + "loss": 4.0794, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937868973501061e-05, + "loss": 4.0935, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937030378750009e-05, + "loss": 4.0593, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936191783998957e-05, + "loss": 4.0729, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935354827128278e-05, + "loss": 4.0769, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934516232377226e-05, + "loss": 4.0609, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933677637626174e-05, + "loss": 4.0644, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932839042875122e-05, + "loss": 4.0771, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.93200044812407e-05, + "loss": 4.0746, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.9311634912533915e-05, + "loss": 4.0799, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.9303248965023395e-05, + "loss": 4.0574, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9294863017512875e-05, + "loss": 4.0644, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9286477070002355e-05, + "loss": 4.0643, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278107501295564e-05, + "loss": 4.0717, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9269721553785044e-05, + "loss": 4.0718, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.9261335606274524e-05, + "loss": 4.0639, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.9252949658764004e-05, + "loss": 4.0584, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924458009005721e-05, + "loss": 4.0661, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923619414254669e-05, + "loss": 4.0609, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922780819503617e-05, + "loss": 4.0673, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.921942224752565e-05, + "loss": 4.0743, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921103630001514e-05, + "loss": 4.0739, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920266673130835e-05, + "loss": 4.0651, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919429716260156e-05, + "loss": 4.0608, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918591121509104e-05, + "loss": 4.0689, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917752526758052e-05, + "loss": 4.0655, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916913932007e-05, + "loss": 4.0699, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916075337255948e-05, + "loss": 4.0678, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915236742504896e-05, + "loss": 4.0563, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9143997856342166e-05, + "loss": 4.0726, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9135611908831646e-05, + "loss": 4.0732, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9127225961321126e-05, + "loss": 4.0491, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.9118840013810606e-05, + "loss": 4.0622, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.9110454066300086e-05, + "loss": 4.0567, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910206811878957e-05, + "loss": 4.0714, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909368217127905e-05, + "loss": 4.0529, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908531260257226e-05, + "loss": 4.0716, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907692665506174e-05, + "loss": 4.0546, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906854070755122e-05, + "loss": 4.0645, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.90601547600407e-05, + "loss": 4.0664, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905176881253018e-05, + "loss": 4.0572, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904338286501966e-05, + "loss": 4.063, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903499691750914e-05, + "loss": 4.0773, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9026610969998615e-05, + "loss": 4.064, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9018225022488095e-05, + "loss": 4.0654, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9009839074977575e-05, + "loss": 4.0644, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.9001453127467055e-05, + "loss": 4.0689, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899306717995654e-05, + "loss": 4.0627, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898469761124975e-05, + "loss": 4.0651, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897631166373923e-05, + "loss": 4.0507, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896792571622871e-05, + "loss": 4.0597, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.895955614752192e-05, + "loss": 4.0563, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.89511702000114e-05, + "loss": 4.0606, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894278425250088e-05, + "loss": 4.0538, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893439830499036e-05, + "loss": 4.0602, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892601235747984e-05, + "loss": 4.0523, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891762640996932e-05, + "loss": 4.0752, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.89092404624588e-05, + "loss": 4.0624, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890085451494828e-05, + "loss": 4.0716, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889246856743776e-05, + "loss": 4.0455, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888408261992724e-05, + "loss": 4.0761, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8875696672416726e-05, + "loss": 4.059, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8867343482513664e-05, + "loss": 4.0662, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8858957535003144e-05, + "loss": 4.0657, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.8850571587492624e-05, + "loss": 4.0609, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.8842185639982104e-05, + "loss": 4.061, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8833799692471584e-05, + "loss": 4.0752, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.8825413744961064e-05, + "loss": 4.0437, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.8817027797450544e-05, + "loss": 4.0684, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.8808641849940024e-05, + "loss": 4.0617, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.88002559024295e-05, + "loss": 4.0537, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879188633372271e-05, + "loss": 4.0584, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878350038621219e-05, + "loss": 4.0563, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877511443870168e-05, + "loss": 4.0706, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876672849119115e-05, + "loss": 4.0586, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875835892248437e-05, + "loss": 4.0601, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 4.082034111022949, + "eval_runtime": 291.1278, + "eval_samples_per_second": 1310.733, + "eval_steps_per_second": 40.961, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.874997297497385e-05, + "loss": 4.0579, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874158702746333e-05, + "loss": 4.0576, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.87332010799528e-05, + "loss": 4.0573, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872481513244228e-05, + "loss": 4.0615, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871642918493176e-05, + "loss": 4.0693, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870804323742124e-05, + "loss": 4.0527, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.869965728991072e-05, + "loss": 4.0613, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.86912713424002e-05, + "loss": 4.0551, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868288539488968e-05, + "loss": 4.0594, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867449944737916e-05, + "loss": 4.0666, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866611349986864e-05, + "loss": 4.0567, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865774393116186e-05, + "loss": 4.0575, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.864935798365134e-05, + "loss": 4.0676, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864097203614082e-05, + "loss": 4.0444, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.86325860886303e-05, + "loss": 4.0542, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862420014111978e-05, + "loss": 4.0457, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861581419360926e-05, + "loss": 4.0566, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860742824609874e-05, + "loss": 4.053, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599058677391946e-05, + "loss": 4.0527, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8590672729881426e-05, + "loss": 4.0627, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8582286782370906e-05, + "loss": 4.0673, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8573900834860386e-05, + "loss": 4.0665, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8565514887349866e-05, + "loss": 4.057, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557128939839346e-05, + "loss": 4.0551, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854875937113256e-05, + "loss": 4.0499, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854038980242577e-05, + "loss": 4.0593, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853200385491525e-05, + "loss": 4.0552, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852361790740473e-05, + "loss": 4.0526, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851523195989421e-05, + "loss": 4.0459, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850684601238369e-05, + "loss": 4.0528, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8498460064873164e-05, + "loss": 4.0461, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490074117362644e-05, + "loss": 4.0643, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8481688169852124e-05, + "loss": 4.0605, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8473302222341604e-05, + "loss": 4.0543, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846493265363482e-05, + "loss": 4.05, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.84565467061243e-05, + "loss": 4.0522, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844816075861378e-05, + "loss": 4.0584, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.843977481110326e-05, + "loss": 4.0539, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843138886359274e-05, + "loss": 4.0498, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842300291608222e-05, + "loss": 4.0389, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.84146169685717e-05, + "loss": 4.0484, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840623102106118e-05, + "loss": 4.0555, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839784507355066e-05, + "loss": 4.0556, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.838947550484387e-05, + "loss": 4.0506, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838108955733335e-05, + "loss": 4.0495, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837270360982283e-05, + "loss": 4.048, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836431766231231e-05, + "loss": 4.0537, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835593171480179e-05, + "loss": 4.0498, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834754576729127e-05, + "loss": 4.0245, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833915981978075e-05, + "loss": 4.06, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833077387227023e-05, + "loss": 4.049, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8322404303563444e-05, + "loss": 4.0539, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314018356052924e-05, + "loss": 4.0454, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8305632408542404e-05, + "loss": 4.0431, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829724646103188e-05, + "loss": 4.0423, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828887689232509e-05, + "loss": 4.0389, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828049094481457e-05, + "loss": 4.0488, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8272104997304046e-05, + "loss": 4.0317, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8263719049793526e-05, + "loss": 4.0544, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8255333102283006e-05, + "loss": 4.0442, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8246947154772486e-05, + "loss": 4.0404, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823856120726197e-05, + "loss": 4.062, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823017525975145e-05, + "loss": 4.0317, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822180569104466e-05, + "loss": 4.0318, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821341974353414e-05, + "loss": 4.0498, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820503379602362e-05, + "loss": 4.0493, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.81966478485131e-05, + "loss": 4.0387, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818827827980631e-05, + "loss": 4.0428, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.817989233229579e-05, + "loss": 4.0277, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817150638478527e-05, + "loss": 4.0451, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816312043727475e-05, + "loss": 4.0496, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815473448976423e-05, + "loss": 4.0503, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814634854225371e-05, + "loss": 4.0472, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813796259474319e-05, + "loss": 4.0523, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.812957664723267e-05, + "loss": 4.0685, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8121207078525886e-05, + "loss": 4.0379, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8112821131015366e-05, + "loss": 4.0494, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8104435183504846e-05, + "loss": 4.0478, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096065614798055e-05, + "loss": 4.0402, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8087679667287535e-05, + "loss": 4.0355, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8079293719777015e-05, + "loss": 4.0554, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8070907772266495e-05, + "loss": 4.0484, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8062521824755975e-05, + "loss": 4.0528, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8054135877245455e-05, + "loss": 4.0333, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8045749929734935e-05, + "loss": 4.0395, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803736398222441e-05, + "loss": 4.0426, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802897803471389e-05, + "loss": 4.046, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8020592087203375e-05, + "loss": 4.0478, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8012206139692855e-05, + "loss": 4.0424, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8003836570986064e-05, + "loss": 4.0322, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799546700227928e-05, + "loss": 4.0471, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798709743357249e-05, + "loss": 4.0382, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797871148606197e-05, + "loss": 4.0412, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797032553855145e-05, + "loss": 4.0483, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796193959104093e-05, + "loss": 4.049, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795355364353041e-05, + "loss": 4.0395, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794516769601988e-05, + "loss": 4.0372, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793678174850936e-05, + "loss": 4.0407, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792839580099884e-05, + "loss": 4.0404, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792000985348833e-05, + "loss": 4.0483, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791162390597781e-05, + "loss": 4.041, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790323795846729e-05, + "loss": 4.0353, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789485201095677e-05, + "loss": 4.0442, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788648244224998e-05, + "loss": 4.0495, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7878112873543186e-05, + "loss": 4.0269, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7869726926032666e-05, + "loss": 4.0403, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7861340978522146e-05, + "loss": 4.0324, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7852955031011626e-05, + "loss": 4.0459, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7844569083501106e-05, + "loss": 4.0296, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7836183135990586e-05, + "loss": 4.0472, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7827797188480066e-05, + "loss": 4.0291, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781942761977328e-05, + "loss": 4.0474, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781104167226276e-05, + "loss": 4.0406, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780265572475224e-05, + "loss": 4.0317, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779426977724172e-05, + "loss": 4.0413, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.77858838297312e-05, + "loss": 4.0526, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777749788222068e-05, + "loss": 4.0414, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776911193471016e-05, + "loss": 4.0453, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776072598719964e-05, + "loss": 4.0372, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775235641849285e-05, + "loss": 4.0426, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774398684978606e-05, + "loss": 4.0434, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773560090227554e-05, + "loss": 4.0361, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772721495476502e-05, + "loss": 4.03, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.77188290072545e-05, + "loss": 4.0373, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771044305974398e-05, + "loss": 4.0359, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702057112233467e-05, + "loss": 4.0372, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7693671164722946e-05, + "loss": 4.0326, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7685285217212426e-05, + "loss": 4.0355, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.76768992697019e-05, + "loss": 4.0279, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7668529700995115e-05, + "loss": 4.0487, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7660143753484595e-05, + "loss": 4.0384, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765175780597407e-05, + "loss": 4.0459, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764337185846355e-05, + "loss": 4.0247, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763498591095303e-05, + "loss": 4.0512, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762659996344251e-05, + "loss": 4.0399, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761823039473572e-05, + "loss": 4.0418, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7609844447225204e-05, + "loss": 4.0407, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7601458499714684e-05, + "loss": 4.0384, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593072552204164e-05, + "loss": 4.0384, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7584686604693644e-05, + "loss": 4.0528, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757631703598685e-05, + "loss": 4.0245, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756793108847633e-05, + "loss": 4.0441, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.755954514096581e-05, + "loss": 4.0367, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755117557225902e-05, + "loss": 4.0329, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.75427896247485e-05, + "loss": 4.0369, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753440367723798e-05, + "loss": 4.0318, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752601772972746e-05, + "loss": 4.0427, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751764816102067e-05, + "loss": 4.0411, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750926221351015e-05, + "loss": 4.0352, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.066238880157471, + "eval_runtime": 296.9197, + "eval_samples_per_second": 1285.166, + "eval_steps_per_second": 40.162, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750087626599964e-05, + "loss": 4.0333, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749249031848912e-05, + "loss": 4.0332, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.74841043709786e-05, + "loss": 4.0336, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747571842346808e-05, + "loss": 4.0422, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746733247595756e-05, + "loss": 4.0436, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745894652844704e-05, + "loss": 4.0308, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745057695974025e-05, + "loss": 4.0359, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744219101222973e-05, + "loss": 4.0356, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743380506471921e-05, + "loss": 4.0351, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742541911720869e-05, + "loss": 4.0406, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741703316969817e-05, + "loss": 4.0339, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.7408663600991376e-05, + "loss": 4.0368, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7400277653480856e-05, + "loss": 4.0437, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7391891705970336e-05, + "loss": 4.0236, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738350575845982e-05, + "loss": 4.0331, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.73751198109493e-05, + "loss": 4.0212, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736673386343878e-05, + "loss": 4.0365, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735836429473199e-05, + "loss": 4.0304, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.73499947260252e-05, + "loss": 4.0273, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734160877851468e-05, + "loss": 4.0392, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733322283100416e-05, + "loss": 4.0413, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732483688349364e-05, + "loss": 4.0435, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731645093598312e-05, + "loss": 4.0376, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.73080649884726e-05, + "loss": 4.0339, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.729969541976581e-05, + "loss": 4.0328, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729130947225529e-05, + "loss": 4.032, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7282923524744776e-05, + "loss": 4.0304, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7274537577234256e-05, + "loss": 4.0333, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7266168008527465e-05, + "loss": 4.0263, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7257782061016945e-05, + "loss": 4.0283, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7249396113506425e-05, + "loss": 4.0272, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7241010165995905e-05, + "loss": 4.0339, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723262421848538e-05, + "loss": 4.0419, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722423827097486e-05, + "loss": 4.0331, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721585232346434e-05, + "loss": 4.0308, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7207482754757554e-05, + "loss": 4.027, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719909680724703e-05, + "loss": 4.041, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7190710859736514e-05, + "loss": 4.0296, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7182324912225994e-05, + "loss": 4.0281, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7173938964715474e-05, + "loss": 4.0157, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716556939600868e-05, + "loss": 4.0297, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715718344849816e-05, + "loss": 4.0288, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714879750098764e-05, + "loss": 4.0337, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714041155347712e-05, + "loss": 4.0293, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.71320256059666e-05, + "loss": 4.0295, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712363965845608e-05, + "loss": 4.025, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711525371094556e-05, + "loss": 4.0318, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710686776343504e-05, + "loss": 4.0309, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709849819472825e-05, + "loss": 4.0019, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709011224721773e-05, + "loss": 4.0352, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708172629970721e-05, + "loss": 4.0251, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707334035219669e-05, + "loss": 4.0351, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706497078348991e-05, + "loss": 4.0237, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705658483597939e-05, + "loss": 4.0209, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704819888846887e-05, + "loss": 4.0176, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.703981294095835e-05, + "loss": 4.0195, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703142699344783e-05, + "loss": 4.0307, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7023057424741036e-05, + "loss": 4.0077, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7014687856034245e-05, + "loss": 4.0353, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7006301908523725e-05, + "loss": 4.0199, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6997915961013205e-05, + "loss": 4.0174, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6989530013502685e-05, + "loss": 4.0429, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6981144065992165e-05, + "loss": 4.0144, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6972758118481645e-05, + "loss": 4.0089, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696437217097113e-05, + "loss": 4.0286, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695598622346061e-05, + "loss": 4.0267, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694761665475382e-05, + "loss": 4.0163, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.69392307072433e-05, + "loss": 4.0229, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693084475973278e-05, + "loss": 4.008, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692245881222226e-05, + "loss": 4.0222, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691407286471174e-05, + "loss": 4.0299, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6905686917201214e-05, + "loss": 4.0263, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6897300969690694e-05, + "loss": 4.0246, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688893140098391e-05, + "loss": 4.0308, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688054545347339e-05, + "loss": 4.0467, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687215950596287e-05, + "loss": 4.0223, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6863789937256086e-05, + "loss": 4.0263, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6855403989745566e-05, + "loss": 4.0245, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684701804223504e-05, + "loss": 4.0227, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683863209472452e-05, + "loss": 4.0151, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6830246147214e-05, + "loss": 4.0344, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682186019970348e-05, + "loss": 4.0285, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681347425219296e-05, + "loss": 4.0347, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680508830468244e-05, + "loss": 4.0099, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679671873597565e-05, + "loss": 4.0202, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678833278846513e-05, + "loss": 4.0205, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.677994684095461e-05, + "loss": 4.0233, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677156089344409e-05, + "loss": 4.0242, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.67631913247373e-05, + "loss": 4.0248, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675480537722678e-05, + "loss": 4.0092, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674643580851999e-05, + "loss": 4.0227, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673804986100947e-05, + "loss": 4.0183, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672966391349895e-05, + "loss": 4.0179, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672127796598843e-05, + "loss": 4.0303, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671289201847791e-05, + "loss": 4.0308, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670450607096739e-05, + "loss": 4.0187, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.66961365022606e-05, + "loss": 4.0185, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668775055475008e-05, + "loss": 4.0204, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.667936460723956e-05, + "loss": 4.0154, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667097865972904e-05, + "loss": 4.0286, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666259271221852e-05, + "loss": 4.0198, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665420676470801e-05, + "loss": 4.0195, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664582081719749e-05, + "loss": 4.0234, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663743486968697e-05, + "loss": 4.0219, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662904892217645e-05, + "loss": 4.0167, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662066297466593e-05, + "loss": 4.0154, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661229340595914e-05, + "loss": 4.0115, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660390745844862e-05, + "loss": 4.0247, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.65955215109381e-05, + "loss": 4.0159, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6587135563427577e-05, + "loss": 4.0198, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657874961591705e-05, + "loss": 4.0048, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657036366840653e-05, + "loss": 4.0243, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656197772089601e-05, + "loss": 4.0253, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6553608152189226e-05, + "loss": 4.0123, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6545222204678705e-05, + "loss": 4.0232, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6536836257168185e-05, + "loss": 4.0318, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6528450309657665e-05, + "loss": 4.0168, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6520064362147145e-05, + "loss": 4.0261, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6511694793440354e-05, + "loss": 4.0185, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6503308845929834e-05, + "loss": 4.0232, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6494922898419314e-05, + "loss": 4.0225, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6486553329712523e-05, + "loss": 4.0132, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6478167382202003e-05, + "loss": 4.0125, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.646978143469148e-05, + "loss": 4.0168, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646139548718096e-05, + "loss": 4.0183, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645300953967044e-05, + "loss": 4.0197, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644463997096366e-05, + "loss": 4.0061, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643625402345314e-05, + "loss": 4.0174, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642786807594262e-05, + "loss": 4.0071, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.64194821284321e-05, + "loss": 4.0298, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641109618092158e-05, + "loss": 4.0178, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640271023341106e-05, + "loss": 4.0259, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639432428590054e-05, + "loss": 4.0091, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638595471719375e-05, + "loss": 4.0257, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637756876968323e-05, + "loss": 4.0209, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636918282217271e-05, + "loss": 4.0185, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636079687466219e-05, + "loss": 4.0232, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635241092715167e-05, + "loss": 4.017, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634402497964115e-05, + "loss": 4.0179, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633563903213063e-05, + "loss": 4.0332, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6327269463423844e-05, + "loss": 4.0056, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6318883515913324e-05, + "loss": 4.0225, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6310497568402804e-05, + "loss": 4.0152, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6302111620892283e-05, + "loss": 4.0151, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6293725673381763e-05, + "loss": 4.0158, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6285339725871237e-05, + "loss": 4.012, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6276953778360717e-05, + "loss": 4.0241, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6268567830850197e-05, + "loss": 4.0224, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626019826214341e-05, + "loss": 4.015, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.053439617156982, + "eval_runtime": 298.0313, + "eval_samples_per_second": 1280.372, + "eval_steps_per_second": 40.013, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6251812314632886e-05, + "loss": 4.0141, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6243426367122366e-05, + "loss": 4.014, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.6235040419611845e-05, + "loss": 4.0163, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622665447210133e-05, + "loss": 4.0204, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621826852459081e-05, + "loss": 4.0232, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.620988257708029e-05, + "loss": 4.0135, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620149662956977e-05, + "loss": 4.0197, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619311068205925e-05, + "loss": 4.0159, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618472473454873e-05, + "loss": 4.013, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617633878703821e-05, + "loss": 4.0159, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616796921833142e-05, + "loss": 4.0215, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.61595832708209e-05, + "loss": 4.0149, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615119732331038e-05, + "loss": 4.0234, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614281137579986e-05, + "loss": 4.0045, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613442542828934e-05, + "loss": 4.0127, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612603948077882e-05, + "loss": 3.9969, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.61176535332683e-05, + "loss": 4.0218, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.610926758575778e-05, + "loss": 4.0107, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610088163824726e-05, + "loss": 4.0072, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609249569073674e-05, + "loss": 4.0187, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608410974322622e-05, + "loss": 4.0215, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.60757237957157e-05, + "loss": 4.0208, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606735422700891e-05, + "loss": 4.0197, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605896827949839e-05, + "loss": 4.0137, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605058233198787e-05, + "loss": 4.0157, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604221276328108e-05, + "loss": 4.0172, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603382681577056e-05, + "loss": 4.0052, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602544086826004e-05, + "loss": 4.0136, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601705492074952e-05, + "loss": 4.0088, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6008668973239e-05, + "loss": 4.006, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600028302572848e-05, + "loss": 4.0084, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5991897078217965e-05, + "loss": 4.0173, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5983527509511174e-05, + "loss": 4.0183, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.5975141562000654e-05, + "loss": 4.0206, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.5966755614490134e-05, + "loss": 4.0081, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.5958369666979614e-05, + "loss": 4.008, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.5949983719469094e-05, + "loss": 4.0216, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5941597771958574e-05, + "loss": 4.008, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5933211824448054e-05, + "loss": 4.0115, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5924825876937534e-05, + "loss": 3.9997, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591645630823074e-05, + "loss": 4.006, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590810311832769e-05, + "loss": 4.011, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.589971717081717e-05, + "loss": 4.0153, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589133122330665e-05, + "loss": 4.0121, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588294527579613e-05, + "loss": 4.0084, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587455932828561e-05, + "loss": 4.0084, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586618975957882e-05, + "loss": 4.0103, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.58578038120683e-05, + "loss": 4.0148, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.584941786455778e-05, + "loss": 3.986, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584103191704726e-05, + "loss": 4.014, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583264596953674e-05, + "loss": 4.0058, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582426002202622e-05, + "loss": 4.0171, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.58158740745157e-05, + "loss": 4.0058, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5807504505808906e-05, + "loss": 4.0027, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5799118558298386e-05, + "loss": 4.0012, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579073261078787e-05, + "loss": 4.0006, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578234666327735e-05, + "loss": 4.0123, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577396071576683e-05, + "loss": 3.9882, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576557476825631e-05, + "loss": 4.019, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5757188820745786e-05, + "loss": 4.0021, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5748802873235265e-05, + "loss": 3.9973, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.5740416925724745e-05, + "loss": 4.0218, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5732030978214225e-05, + "loss": 3.9967, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5723645030703705e-05, + "loss": 3.9928, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5715259083193185e-05, + "loss": 4.0094, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5706889514486394e-05, + "loss": 4.0076, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5698503566975874e-05, + "loss": 3.9947, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569013399826909e-05, + "loss": 4.0068, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568174805075857e-05, + "loss": 3.9883, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567336210324805e-05, + "loss": 4.0029, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566497615573753e-05, + "loss": 4.0124, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565659020822701e-05, + "loss": 4.0091, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564822063952022e-05, + "loss": 4.0075, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.56398346920097e-05, + "loss": 4.0111, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563144874449918e-05, + "loss": 4.0268, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562306279698866e-05, + "loss": 4.0044, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561467684947814e-05, + "loss": 4.0095, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560629090196762e-05, + "loss": 4.0016, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559792133326083e-05, + "loss": 4.0044, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.558953538575031e-05, + "loss": 4.0005, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5581149438239795e-05, + "loss": 4.0142, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.5572763490729275e-05, + "loss": 4.0105, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.5564377543218755e-05, + "loss": 4.0151, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5555991595708235e-05, + "loss": 3.9967, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5547605648197715e-05, + "loss": 4.0019, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5539219700687195e-05, + "loss": 4.0018, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.5530833753176674e-05, + "loss": 4.0033, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552248056327361e-05, + "loss": 4.0054, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551409461576309e-05, + "loss": 4.0082, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550570866825257e-05, + "loss": 3.9936, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549732272074205e-05, + "loss": 4.0034, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548893677323153e-05, + "loss": 4.001, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548055082572101e-05, + "loss": 3.9973, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547216487821049e-05, + "loss": 4.0103, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546379530950371e-05, + "loss": 4.0143, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545540936199319e-05, + "loss": 4.004, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544702341448267e-05, + "loss": 3.9973, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543863746697215e-05, + "loss": 4.0051, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543025151946162e-05, + "loss": 3.9972, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.54218655719511e-05, + "loss": 4.0073, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541347962444058e-05, + "loss": 4.0061, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540509367693006e-05, + "loss": 3.9957, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539670772941954e-05, + "loss": 4.0076, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538833816071275e-05, + "loss": 4.0013, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.537995221320223e-05, + "loss": 4.0014, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537156626569171e-05, + "loss": 3.9968, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.53631803181812e-05, + "loss": 3.9955, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5354810749474406e-05, + "loss": 4.0052, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5346424801963886e-05, + "loss": 4.0033, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.5338038854453366e-05, + "loss": 3.9997, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5329652906942846e-05, + "loss": 3.9882, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5321266959432326e-05, + "loss": 4.0035, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5312897390725535e-05, + "loss": 4.009, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5304511443215015e-05, + "loss": 3.9957, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5296141874508224e-05, + "loss": 4.0072, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5287755926997704e-05, + "loss": 4.0113, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5279369979487184e-05, + "loss": 4.0035, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5270984031976664e-05, + "loss": 4.0043, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526259808446615e-05, + "loss": 4.0043, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525421213695563e-05, + "loss": 4.0038, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524582618944511e-05, + "loss": 4.0054, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523744024193459e-05, + "loss": 3.9945, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.52290706732278e-05, + "loss": 3.9938, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522068472571728e-05, + "loss": 4.0011, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521229877820676e-05, + "loss": 3.9996, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520391283069624e-05, + "loss": 3.999, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519552688318572e-05, + "loss": 3.9958, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.51871409356752e-05, + "loss": 3.9931, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517875498816468e-05, + "loss": 3.9906, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517036904065415e-05, + "loss": 4.0132, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516199947194737e-05, + "loss": 3.9995, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515361352443685e-05, + "loss": 4.0104, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5145227576926335e-05, + "loss": 3.9892, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5136858008219544e-05, + "loss": 4.0107, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5128472060709024e-05, + "loss": 4.005, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5120086113198504e-05, + "loss": 4.0017, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5111700165687984e-05, + "loss": 3.9987, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510331421817746e-05, + "loss": 4.0037, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509492827066694e-05, + "loss": 4.0033, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508655870196015e-05, + "loss": 4.0103, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5078172754449626e-05, + "loss": 3.9937, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5069786806939106e-05, + "loss": 3.9995, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5061400859428586e-05, + "loss": 4.0018, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505301491191807e-05, + "loss": 3.9982, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504462896440755e-05, + "loss": 3.9954, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503624301689703e-05, + "loss": 3.9993, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502787344819024e-05, + "loss": 4.0027, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501948750067972e-05, + "loss": 4.0028, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.50111015531692e-05, + "loss": 3.9975, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.042985916137695, + "eval_runtime": 296.7507, + "eval_samples_per_second": 1285.898, + "eval_steps_per_second": 40.185, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500271560565868e-05, + "loss": 3.9975, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499434603695189e-05, + "loss": 3.993, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498596008944137e-05, + "loss": 3.9985, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497757414193085e-05, + "loss": 4.0054, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.496918819442033e-05, + "loss": 4.0009, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496080224690981e-05, + "loss": 4.0005, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4952432678203026e-05, + "loss": 4.0029, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4944046730692506e-05, + "loss": 3.9985, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4935660783181986e-05, + "loss": 3.9929, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4927274835671466e-05, + "loss": 3.9992, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4918888888160946e-05, + "loss": 4.0065, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4910519319454155e-05, + "loss": 3.9957, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4902149750747364e-05, + "loss": 4.0134, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4893763803236844e-05, + "loss": 3.9818, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.4885377855726324e-05, + "loss": 3.9935, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4876991908215804e-05, + "loss": 3.9821, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4868605960705284e-05, + "loss": 4.0048, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4860220013194764e-05, + "loss": 3.9926, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4851834065684244e-05, + "loss": 3.9918, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4843448118173724e-05, + "loss": 3.9985, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483507854946694e-05, + "loss": 4.0059, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482670898076015e-05, + "loss": 4.0057, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481832303324963e-05, + "loss": 4.0009, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.480993708573911e-05, + "loss": 3.9968, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480155113822859e-05, + "loss": 4.0001, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479316519071807e-05, + "loss": 3.9981, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478477924320755e-05, + "loss": 3.9871, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477639329569703e-05, + "loss": 3.9968, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476800734818651e-05, + "loss": 3.9933, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.475962140067599e-05, + "loss": 3.9898, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475123545316546e-05, + "loss": 3.9945, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474286588445868e-05, + "loss": 3.9968, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473447993694816e-05, + "loss": 4.0009, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4726093989437645e-05, + "loss": 4.0042, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4717724420730854e-05, + "loss": 3.9923, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4709338473220334e-05, + "loss": 3.9907, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4700952525709814e-05, + "loss": 4.0041, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469256657819929e-05, + "loss": 3.9892, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468418063068877e-05, + "loss": 3.995, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467581106198198e-05, + "loss": 3.9877, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466742511447146e-05, + "loss": 3.9856, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4659039166960936e-05, + "loss": 3.9949, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4650653219450416e-05, + "loss": 3.9992, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.4642267271939896e-05, + "loss": 3.9917, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463388132442938e-05, + "loss": 3.9932, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462549537691886e-05, + "loss": 3.9912, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461710942940834e-05, + "loss": 3.9919, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460872348189782e-05, + "loss": 3.9985, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460035391319103e-05, + "loss": 3.971, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459196796568051e-05, + "loss": 3.9985, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458358201816999e-05, + "loss": 3.9879, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457519607065947e-05, + "loss": 4.0011, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456682650195268e-05, + "loss": 3.9871, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455844055444216e-05, + "loss": 3.9887, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455005460693164e-05, + "loss": 3.9836, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454166865942112e-05, + "loss": 3.984, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4533299090714336e-05, + "loss": 3.9961, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4524913143203816e-05, + "loss": 3.9714, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4516527195693296e-05, + "loss": 4.0014, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4508141248182776e-05, + "loss": 3.9875, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4499755300672256e-05, + "loss": 3.9784, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4491369353161736e-05, + "loss": 4.0073, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4482983405651216e-05, + "loss": 3.9759, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4474597458140696e-05, + "loss": 3.9771, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.4466211510630176e-05, + "loss": 3.9905, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4457841941923385e-05, + "loss": 3.9937, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.4449455994412865e-05, + "loss": 3.9823, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.4441086425706074e-05, + "loss": 3.991, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4432700478195554e-05, + "loss": 3.9699, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4424314530685034e-05, + "loss": 3.9855, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441592858317452e-05, + "loss": 3.9961, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440755901446773e-05, + "loss": 3.9951, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.439917306695721e-05, + "loss": 3.9895, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439078711944669e-05, + "loss": 3.9945, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438240117193617e-05, + "loss": 4.0111, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437401522442565e-05, + "loss": 3.9885, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436562927691512e-05, + "loss": 3.9975, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.43572433294046e-05, + "loss": 3.982, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434885738189408e-05, + "loss": 3.9896, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434050419199103e-05, + "loss": 3.9794, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433213462328424e-05, + "loss": 3.9988, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432374867577372e-05, + "loss": 3.9945, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.43153627282632e-05, + "loss": 4.0006, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430697678075268e-05, + "loss": 3.9824, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429859083324216e-05, + "loss": 3.9841, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429020488573164e-05, + "loss": 3.9817, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428181893822112e-05, + "loss": 3.9934, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4273432990710596e-05, + "loss": 3.9861, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4265047043200076e-05, + "loss": 3.9924, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.4256661095689556e-05, + "loss": 3.9796, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4248275148179036e-05, + "loss": 3.9873, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.4239889200668516e-05, + "loss": 3.985, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4231519631961725e-05, + "loss": 3.9829, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4223133684451205e-05, + "loss": 3.9906, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421474773694069e-05, + "loss": 4.0002, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420636178943017e-05, + "loss": 3.9898, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419797584191965e-05, + "loss": 3.9843, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.418958989440913e-05, + "loss": 3.9855, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418122032570234e-05, + "loss": 3.9839, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417283437819182e-05, + "loss": 3.9927, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.41644484306813e-05, + "loss": 3.9894, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415606248317078e-05, + "loss": 3.9793, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414767653566026e-05, + "loss": 3.9932, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.413929058814974e-05, + "loss": 3.9882, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413090464063922e-05, + "loss": 3.9841, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41225186931287e-05, + "loss": 3.9812, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411413274561818e-05, + "loss": 3.982, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410576317691139e-05, + "loss": 3.9849, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4097393608204605e-05, + "loss": 3.9887, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4089007660694085e-05, + "loss": 3.9837, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4080621713183565e-05, + "loss": 3.9725, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4072235765673045e-05, + "loss": 3.987, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4063849818162525e-05, + "loss": 3.9944, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4055463870652005e-05, + "loss": 3.9837, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.4047077923141485e-05, + "loss": 3.9878, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403869197563096e-05, + "loss": 3.9932, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403030602812044e-05, + "loss": 3.9885, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402192008060992e-05, + "loss": 3.9889, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4013550511903134e-05, + "loss": 3.9869, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4005164564392614e-05, + "loss": 3.9903, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3996778616882094e-05, + "loss": 3.9961, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398840904817531e-05, + "loss": 3.9747, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398002310066478e-05, + "loss": 3.984, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397163715315426e-05, + "loss": 3.9801, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396325120564374e-05, + "loss": 3.985, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395486525813322e-05, + "loss": 3.9852, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.39464793106227e-05, + "loss": 3.9791, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393809336311218e-05, + "loss": 3.9749, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.392972379440539e-05, + "loss": 3.9785, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392133784689487e-05, + "loss": 3.9967, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391295189938435e-05, + "loss": 3.9865, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390456595187383e-05, + "loss": 3.9908, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389618000436331e-05, + "loss": 3.9782, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.38877940568528e-05, + "loss": 3.9914, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.387940810934228e-05, + "loss": 3.9912, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387103854063549e-05, + "loss": 3.9855, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386265259312497e-05, + "loss": 3.9829, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385426664561445e-05, + "loss": 3.9899, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384588069810393e-05, + "loss": 3.9888, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3837511129397137e-05, + "loss": 3.9934, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3829125181886616e-05, + "loss": 3.9801, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3820739234376096e-05, + "loss": 3.9816, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3812369665669306e-05, + "loss": 3.9851, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3803983718158785e-05, + "loss": 3.9849, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3795597770648265e-05, + "loss": 3.9778, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378721182313775e-05, + "loss": 3.9862, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.377882587562723e-05, + "loss": 3.9814, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377043992811671e-05, + "loss": 3.9927, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376205398060619e-05, + "loss": 3.9816, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 4.034016132354736, + "eval_runtime": 295.8953, + "eval_samples_per_second": 1289.615, + "eval_steps_per_second": 40.301, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375366803309567e-05, + "loss": 3.9949, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3745282085585145e-05, + "loss": 3.9781, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3736896138074625e-05, + "loss": 3.9829, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3728510190564105e-05, + "loss": 3.9911, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3720124243053585e-05, + "loss": 3.9846, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3711738295543065e-05, + "loss": 3.9855, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3703352348032545e-05, + "loss": 3.9838, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3694966400522025e-05, + "loss": 3.9814, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3686580453011505e-05, + "loss": 3.9789, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3678194505500985e-05, + "loss": 3.9905, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3669808557990465e-05, + "loss": 3.9833, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3661422610479945e-05, + "loss": 3.987, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365305304177316e-05, + "loss": 3.9958, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364468347306637e-05, + "loss": 3.968, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363629752555585e-05, + "loss": 3.9791, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362791157804533e-05, + "loss": 3.9666, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361952563053481e-05, + "loss": 3.99, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361113968302429e-05, + "loss": 3.9772, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360275373551377e-05, + "loss": 3.977, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359436778800325e-05, + "loss": 3.9804, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358598184049273e-05, + "loss": 3.9935, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357759589298221e-05, + "loss": 3.9866, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356920994547168e-05, + "loss": 3.9891, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.35608403767649e-05, + "loss": 3.9814, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3552470808058114e-05, + "loss": 3.9873, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3544084860547594e-05, + "loss": 3.9802, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3535698913037074e-05, + "loss": 3.976, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3527312965526554e-05, + "loss": 3.9806, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3518927018016034e-05, + "loss": 3.9775, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351054107050551e-05, + "loss": 3.9742, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350215512299499e-05, + "loss": 3.9786, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349376917548447e-05, + "loss": 3.9816, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348539960677768e-05, + "loss": 3.9884, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3477013659267156e-05, + "loss": 3.986, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3468627711756636e-05, + "loss": 3.976, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346024176424612e-05, + "loss": 3.9766, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.34518558167356e-05, + "loss": 3.994, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344346986922508e-05, + "loss": 3.9668, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343508392171456e-05, + "loss": 3.9843, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342669797420404e-05, + "loss": 3.9748, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341832840549725e-05, + "loss": 3.9667, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.340995883679046e-05, + "loss": 3.9809, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340157288927994e-05, + "loss": 3.9861, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339318694176942e-05, + "loss": 3.9754, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.33848009942589e-05, + "loss": 3.9798, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337641504674838e-05, + "loss": 3.9765, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336802909923786e-05, + "loss": 3.9761, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.335964315172734e-05, + "loss": 3.9861, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335125720421682e-05, + "loss": 3.9583, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.33428712567063e-05, + "loss": 3.9789, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3334501687999516e-05, + "loss": 3.9778, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3326115740488996e-05, + "loss": 3.9886, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3317729792978476e-05, + "loss": 3.9681, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3309343845467956e-05, + "loss": 3.9764, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3300974276761165e-05, + "loss": 3.9606, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3292588329250645e-05, + "loss": 3.9713, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3284202381740125e-05, + "loss": 3.9841, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3275816434229605e-05, + "loss": 3.9546, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3267430486719085e-05, + "loss": 3.9858, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3259044539208565e-05, + "loss": 3.9742, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3250674970501774e-05, + "loss": 3.9676, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242289022991254e-05, + "loss": 3.9891, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323390307548074e-05, + "loss": 3.9614, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322553350677395e-05, + "loss": 3.9633, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321714755926343e-05, + "loss": 3.9727, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320876161175291e-05, + "loss": 3.9834, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320037566424239e-05, + "loss": 3.9668, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319198971673187e-05, + "loss": 3.9736, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318360376922134e-05, + "loss": 3.9566, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317521782171082e-05, + "loss": 3.972, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.31668318742003e-05, + "loss": 3.9795, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315844592668978e-05, + "loss": 3.9847, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315007635798299e-05, + "loss": 3.9734, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314169041047248e-05, + "loss": 3.9808, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313330446296196e-05, + "loss": 3.9922, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312491851545144e-05, + "loss": 3.9753, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311653256794092e-05, + "loss": 3.9777, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.31081466204304e-05, + "loss": 3.9726, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.309977705172361e-05, + "loss": 3.9762, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309140748301682e-05, + "loss": 3.9656, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.30830215355063e-05, + "loss": 3.9797, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307463558799578e-05, + "loss": 3.9762, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306624964048526e-05, + "loss": 3.9893, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305786369297474e-05, + "loss": 3.9729, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3049494124267946e-05, + "loss": 3.965, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304110817675743e-05, + "loss": 3.966, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303272222924691e-05, + "loss": 3.9789, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302433628173639e-05, + "loss": 3.9677, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301595033422587e-05, + "loss": 3.9793, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300756438671535e-05, + "loss": 3.9694, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.299917843920483e-05, + "loss": 3.9664, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299080887049804e-05, + "loss": 3.9711, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298242292298752e-05, + "loss": 3.9698, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2974036975477e-05, + "loss": 3.9763, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296565102796648e-05, + "loss": 3.981, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295726508045596e-05, + "loss": 3.9782, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294887913294544e-05, + "loss": 3.9634, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294049318543492e-05, + "loss": 3.9733, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.29321072379244e-05, + "loss": 3.9682, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292373766921762e-05, + "loss": 3.9768, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.29153517217071e-05, + "loss": 3.9778, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290696577419658e-05, + "loss": 3.9603, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289857982668606e-05, + "loss": 3.9764, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289019387917553e-05, + "loss": 3.9721, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288180793166501e-05, + "loss": 3.9685, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2873438362958226e-05, + "loss": 3.9682, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2865052415447706e-05, + "loss": 3.9655, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285666646793718e-05, + "loss": 3.9715, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284828052042666e-05, + "loss": 3.9734, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2839910951719875e-05, + "loss": 3.9672, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2831525004209355e-05, + "loss": 3.9583, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2823139056698835e-05, + "loss": 3.969, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281476948799205e-05, + "loss": 3.9806, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280638354048153e-05, + "loss": 3.9663, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2797997592971004e-05, + "loss": 3.9722, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2789611645460484e-05, + "loss": 3.9745, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.27812420767537e-05, + "loss": 3.9798, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277285612924318e-05, + "loss": 3.9732, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276447018173265e-05, + "loss": 3.9714, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275608423422213e-05, + "loss": 3.9788, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274769828671161e-05, + "loss": 3.9788, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273931233920109e-05, + "loss": 3.9603, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273092639169057e-05, + "loss": 3.9704, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272255682298379e-05, + "loss": 3.9598, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271417087547327e-05, + "loss": 3.9735, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270578492796275e-05, + "loss": 3.9688, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269739898045223e-05, + "loss": 3.9612, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.268901303294171e-05, + "loss": 3.9592, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268062708543119e-05, + "loss": 3.9661, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267224113792067e-05, + "loss": 3.9793, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266385519041015e-05, + "loss": 3.9739, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265548562170336e-05, + "loss": 3.973, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264709967419284e-05, + "loss": 3.9639, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263871372668232e-05, + "loss": 3.9792, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.26303277791718e-05, + "loss": 3.9762, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262194183166128e-05, + "loss": 3.9739, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2613572262954486e-05, + "loss": 3.9669, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260518631544397e-05, + "loss": 3.9739, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259681674673718e-05, + "loss": 3.9756, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258843079922666e-05, + "loss": 3.979, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258004485171614e-05, + "loss": 3.9671, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257165890420562e-05, + "loss": 3.9636, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.25632729566951e-05, + "loss": 3.9746, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255488700918458e-05, + "loss": 3.9684, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254650106167406e-05, + "loss": 3.9614, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253811511416354e-05, + "loss": 3.9744, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2529729166653015e-05, + "loss": 3.9678, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2521343219142495e-05, + "loss": 3.9802, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251297365043571e-05, + "loss": 3.9597, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.026220798492432, + "eval_runtime": 295.1214, + "eval_samples_per_second": 1292.997, + "eval_steps_per_second": 40.407, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250458770292519e-05, + "loss": 3.9833, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249620175541467e-05, + "loss": 3.9639, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248781580790415e-05, + "loss": 3.9689, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247942986039363e-05, + "loss": 3.9769, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247104391288311e-05, + "loss": 3.9709, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246265796537259e-05, + "loss": 3.9712, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245427201786207e-05, + "loss": 3.9685, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244588607035155e-05, + "loss": 3.9684, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243750012284103e-05, + "loss": 3.9656, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242911417533051e-05, + "loss": 3.9737, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242072822781999e-05, + "loss": 3.9711, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241234228030947e-05, + "loss": 3.9729, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240397271160268e-05, + "loss": 3.9803, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239558676409216e-05, + "loss": 3.9549, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238720081658164e-05, + "loss": 3.9645, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2378814869071126e-05, + "loss": 3.9514, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2370428921560606e-05, + "loss": 3.9782, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236204297405008e-05, + "loss": 3.9614, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353673405343295e-05, + "loss": 3.9623, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2345287457832775e-05, + "loss": 3.9716, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2336901510322255e-05, + "loss": 3.9782, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232851556281173e-05, + "loss": 3.9743, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232012961530121e-05, + "loss": 3.9704, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231174366779069e-05, + "loss": 3.971, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230335772028017e-05, + "loss": 3.9732, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229497177276965e-05, + "loss": 3.9634, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286602204062864e-05, + "loss": 3.9648, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278216256552343e-05, + "loss": 3.9687, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2269830309041823e-05, + "loss": 3.9606, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261444361531303e-05, + "loss": 3.9583, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225307479282451e-05, + "loss": 3.9644, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224468884531399e-05, + "loss": 3.9633, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22363192766072e-05, + "loss": 3.9782, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222793332909668e-05, + "loss": 3.9731, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221954738158616e-05, + "loss": 3.9626, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221116143407564e-05, + "loss": 3.9655, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220277548656512e-05, + "loss": 3.9791, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.21943895390546e-05, + "loss": 3.9531, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218600359154408e-05, + "loss": 3.9728, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217761764403356e-05, + "loss": 3.9539, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216923169652304e-05, + "loss": 3.9564, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216084574901253e-05, + "loss": 3.9677, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2152492559109466e-05, + "loss": 3.9779, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2144122990402675e-05, + "loss": 3.9577, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2135737042892155e-05, + "loss": 3.966, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127351095381635e-05, + "loss": 3.9644, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2118965147871115e-05, + "loss": 3.9614, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110579200360595e-05, + "loss": 3.9698, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102193252850075e-05, + "loss": 3.9463, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2093807305339555e-05, + "loss": 3.9664, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2085421357829035e-05, + "loss": 3.9671, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2077035410318515e-05, + "loss": 3.972, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2068649462807995e-05, + "loss": 3.9531, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206026351529748e-05, + "loss": 3.9575, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205187756778696e-05, + "loss": 3.956, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204350799908017e-05, + "loss": 3.9515, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203512205156965e-05, + "loss": 3.9726, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202673610405913e-05, + "loss": 3.9431, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201835015654861e-05, + "loss": 3.9677, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.200996420903809e-05, + "loss": 3.9625, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.20015946403313e-05, + "loss": 3.9559, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199320869282078e-05, + "loss": 3.9743, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198482274531026e-05, + "loss": 3.9501, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197643679779973e-05, + "loss": 3.9494, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196805085028922e-05, + "loss": 3.9528, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1959681281582435e-05, + "loss": 3.973, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1951295334071915e-05, + "loss": 3.9544, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194290938656139e-05, + "loss": 3.9532, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193452343905087e-05, + "loss": 3.9474, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1926153870344084e-05, + "loss": 3.9535, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917767922833564e-05, + "loss": 3.9667, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190938197532304e-05, + "loss": 3.9716, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190101240661625e-05, + "loss": 3.9569, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189262645910573e-05, + "loss": 3.9701, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884240511595206e-05, + "loss": 3.9775, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1875854564084686e-05, + "loss": 3.9632, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.18674849953779e-05, + "loss": 3.9631, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.185909904786739e-05, + "loss": 3.961, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185071310035686e-05, + "loss": 3.9633, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184232715284634e-05, + "loss": 3.9552, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183395758413956e-05, + "loss": 3.9639, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182557163662903e-05, + "loss": 3.9658, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181718568911851e-05, + "loss": 3.9745, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180879974160799e-05, + "loss": 3.9628, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180041379409747e-05, + "loss": 3.9497, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179202784658695e-05, + "loss": 3.9526, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178364189907643e-05, + "loss": 3.9651, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177525595156591e-05, + "loss": 3.9525, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176687000405539e-05, + "loss": 3.9645, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175848405654487e-05, + "loss": 3.9587, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175011448783809e-05, + "loss": 3.9554, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1741728540327567e-05, + "loss": 3.9536, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1733342592817047e-05, + "loss": 3.9599, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1724956645306526e-05, + "loss": 3.9634, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1716587076599736e-05, + "loss": 3.967, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1708217507892945e-05, + "loss": 3.9621, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1699831560382425e-05, + "loss": 3.9512, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1691445612871905e-05, + "loss": 3.9595, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683059665361385e-05, + "loss": 3.9588, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674690096654594e-05, + "loss": 3.9619, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166630414914408e-05, + "loss": 3.9646, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165793458043729e-05, + "loss": 3.9484, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164954863292677e-05, + "loss": 3.9639, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164116268541625e-05, + "loss": 3.9591, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163279311670946e-05, + "loss": 3.9574, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162440716919894e-05, + "loss": 3.9534, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161602122168842e-05, + "loss": 3.956, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.16076352741779e-05, + "loss": 3.9585, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.159924932666738e-05, + "loss": 3.9631, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159086337915686e-05, + "loss": 3.9534, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158247743164634e-05, + "loss": 3.9464, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157409148413582e-05, + "loss": 3.9532, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.15657055366253e-05, + "loss": 3.9683, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155731958911478e-05, + "loss": 3.9558, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154893364160426e-05, + "loss": 3.9579, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1540547694093745e-05, + "loss": 3.9637, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1532161746583225e-05, + "loss": 3.9652, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.15237757990727e-05, + "loss": 3.9595, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151538985156218e-05, + "loss": 3.9604, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150700390405166e-05, + "loss": 3.965, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149863433534487e-05, + "loss": 3.9621, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149024838783435e-05, + "loss": 3.9478, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148186244032383e-05, + "loss": 3.9587, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147349287161704e-05, + "loss": 3.9545, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1465106924106516e-05, + "loss": 3.9556, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456720976595996e-05, + "loss": 3.9559, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144833502908548e-05, + "loss": 3.9503, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.143994908157496e-05, + "loss": 3.9513, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143156313406444e-05, + "loss": 3.9561, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142317718655392e-05, + "loss": 3.9565, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.14147912390434e-05, + "loss": 3.9657, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140640529153288e-05, + "loss": 3.9643, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139801934402236e-05, + "loss": 3.9498, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.138964977531557e-05, + "loss": 3.9644, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138126382780505e-05, + "loss": 3.9619, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137287788029453e-05, + "loss": 3.9611, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136449193278401e-05, + "loss": 3.9555, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135612236407722e-05, + "loss": 3.9631, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.13477364165667e-05, + "loss": 3.963, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133935046905618e-05, + "loss": 3.964, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133096452154567e-05, + "loss": 3.955, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132257857403515e-05, + "loss": 3.9526, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131419262652463e-05, + "loss": 3.9607, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1305823057817836e-05, + "loss": 3.9538, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1297437110307316e-05, + "loss": 3.9475, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1289067541600525e-05, + "loss": 3.9616, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1280681594090005e-05, + "loss": 3.956, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1272295646579485e-05, + "loss": 3.9691, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1263909699068965e-05, + "loss": 3.9482, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.019271373748779, + "eval_runtime": 286.3674, + "eval_samples_per_second": 1332.523, + "eval_steps_per_second": 41.642, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255523751558445e-05, + "loss": 3.9552, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1247154182851654e-05, + "loss": 3.9564, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1238768235341134e-05, + "loss": 3.9538, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123038228783062e-05, + "loss": 3.9654, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.12219963403201e-05, + "loss": 3.9551, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121361039280958e-05, + "loss": 3.963, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1205224445299054e-05, + "loss": 3.9547, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1196838497788534e-05, + "loss": 3.9544, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1188452550278014e-05, + "loss": 3.9548, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118008298157123e-05, + "loss": 3.9617, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.11716970340607e-05, + "loss": 3.9543, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116332746535392e-05, + "loss": 3.9671, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115495789664713e-05, + "loss": 3.9659, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114657194913661e-05, + "loss": 3.9435, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113818600162609e-05, + "loss": 3.9494, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129800054115574e-05, + "loss": 3.9418, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121414106605054e-05, + "loss": 3.9612, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111302815909453e-05, + "loss": 3.9558, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110465859038774e-05, + "loss": 3.9487, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109627264287722e-05, + "loss": 3.955, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.10878866953667e-05, + "loss": 3.966, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079500747856176e-05, + "loss": 3.9622, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1071114800345656e-05, + "loss": 3.9558, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1062728852835136e-05, + "loss": 3.9571, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1054342905324616e-05, + "loss": 3.9661, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1045956957814096e-05, + "loss": 3.9486, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1037571010303576e-05, + "loss": 3.9505, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1029185062793056e-05, + "loss": 3.9582, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1020799115282536e-05, + "loss": 3.9448, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101241316777202e-05, + "loss": 3.9491, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100404359906523e-05, + "loss": 3.95, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099565765155471e-05, + "loss": 3.9538, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098727170404419e-05, + "loss": 3.9658, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097888575653367e-05, + "loss": 3.9548, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097049980902315e-05, + "loss": 3.953, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096214661912009e-05, + "loss": 3.9519, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.09537770504133e-05, + "loss": 3.9643, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094539110290278e-05, + "loss": 3.9425, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937005155392266e-05, + "loss": 3.9591, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928619207881746e-05, + "loss": 3.9446, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920233260371226e-05, + "loss": 3.9444, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0911847312860706e-05, + "loss": 3.9547, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0903461365350186e-05, + "loss": 3.9677, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0895075417839666e-05, + "loss": 3.9413, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0886689470329146e-05, + "loss": 3.9571, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0878303522818625e-05, + "loss": 3.9538, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0869917575308105e-05, + "loss": 3.9504, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0861531627797585e-05, + "loss": 3.9567, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853145680287065e-05, + "loss": 3.9315, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0844776111580274e-05, + "loss": 3.9525, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0836390164069754e-05, + "loss": 3.9594, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0828004216559234e-05, + "loss": 3.9568, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0819618269048714e-05, + "loss": 3.9442, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081124870034193e-05, + "loss": 3.9434, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080287913163514e-05, + "loss": 3.9467, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079449318412462e-05, + "loss": 3.9364, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.07861072366141e-05, + "loss": 3.964, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077772128910358e-05, + "loss": 3.9292, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076933534159306e-05, + "loss": 3.9535, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076094939408254e-05, + "loss": 3.9519, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075256344657201e-05, + "loss": 3.9451, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074417749906149e-05, + "loss": 3.9589, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073579155155097e-05, + "loss": 3.9412, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072740560404045e-05, + "loss": 3.9377, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.071901965652993e-05, + "loss": 3.9403, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071065008782315e-05, + "loss": 3.9648, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070226414031263e-05, + "loss": 3.9405, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069387819280211e-05, + "loss": 3.9417, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068549224529159e-05, + "loss": 3.9338, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067710629778107e-05, + "loss": 3.9427, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066873672907428e-05, + "loss": 3.956, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066035078156376e-05, + "loss": 3.9581, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065196483405324e-05, + "loss": 3.9424, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064357888654272e-05, + "loss": 3.9585, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06351929390322e-05, + "loss": 3.9656, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062680699152168e-05, + "loss": 3.9558, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0618421044011157e-05, + "loss": 3.9462, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0610035096500637e-05, + "loss": 3.9497, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060168190659758e-05, + "loss": 3.952, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059329595908706e-05, + "loss": 3.9457, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058491001157654e-05, + "loss": 3.9474, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057652406406602e-05, + "loss": 3.9579, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.05681381165555e-05, + "loss": 3.9619, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.055976854784871e-05, + "loss": 3.9542, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055138260033819e-05, + "loss": 3.9353, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054299665282767e-05, + "loss": 3.9412, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053461070531715e-05, + "loss": 3.9541, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052624113661036e-05, + "loss": 3.9435, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051785518909984e-05, + "loss": 3.9526, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509469241589323e-05, + "loss": 3.9438, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501083294078803e-05, + "loss": 3.9446, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492697346568283e-05, + "loss": 3.9408, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484311399057763e-05, + "loss": 3.9515, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0475925451547243e-05, + "loss": 3.9492, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467555882840455e-05, + "loss": 3.955, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459169935329935e-05, + "loss": 3.9538, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450783987819415e-05, + "loss": 3.9357, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442398040308895e-05, + "loss": 3.951, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434012092798375e-05, + "loss": 3.947, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042562614528785e-05, + "loss": 3.9505, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417256576581067e-05, + "loss": 3.9535, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0408870629070547e-05, + "loss": 3.937, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040048468156002e-05, + "loss": 3.9473, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.03920987340495e-05, + "loss": 3.9496, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038371278653898e-05, + "loss": 3.9476, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037532683902846e-05, + "loss": 3.9417, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0366940891517944e-05, + "loss": 3.9448, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358554944007424e-05, + "loss": 3.9461, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350185375300633e-05, + "loss": 3.9501, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034181580659385e-05, + "loss": 3.9407, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333429859083322e-05, + "loss": 3.9395, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325043911572805e-05, + "loss": 3.9395, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316657964062285e-05, + "loss": 3.9561, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308272016551765e-05, + "loss": 3.9441, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0299902447844974e-05, + "loss": 3.9473, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291516500334454e-05, + "loss": 3.9551, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283130552823934e-05, + "loss": 3.9552, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274760984117147e-05, + "loss": 3.9468, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266375036606626e-05, + "loss": 3.9472, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0257989089096106e-05, + "loss": 3.9571, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249603141585586e-05, + "loss": 3.9486, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241217194075066e-05, + "loss": 3.9376, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232831246564546e-05, + "loss": 3.9476, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224445299054026e-05, + "loss": 3.9382, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216059351543506e-05, + "loss": 3.9448, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020768978283672e-05, + "loss": 3.941, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.01993038353262e-05, + "loss": 3.9449, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019091788781568e-05, + "loss": 3.9392, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018253194030516e-05, + "loss": 3.9427, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017414599279464e-05, + "loss": 3.9434, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016579280289158e-05, + "loss": 3.9547, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015740685538106e-05, + "loss": 3.9544, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.014902090787054e-05, + "loss": 3.9433, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014063496036002e-05, + "loss": 3.9455, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.01322490128495e-05, + "loss": 3.9476, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012386306533898e-05, + "loss": 3.9505, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011547711782846e-05, + "loss": 3.9493, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010709117031794e-05, + "loss": 3.9507, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098721601611152e-05, + "loss": 3.9516, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090335654100632e-05, + "loss": 3.9512, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0081949706590112e-05, + "loss": 3.9464, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073563759079592e-05, + "loss": 3.9402, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065177811569072e-05, + "loss": 3.9482, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056808242862285e-05, + "loss": 3.9439, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048422295351765e-05, + "loss": 3.9363, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040036347841245e-05, + "loss": 3.9531, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031650400330724e-05, + "loss": 3.946, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023264452820204e-05, + "loss": 3.9515, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0014878505309678e-05, + "loss": 3.9391, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006508936602893e-05, + "loss": 3.9446, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.01361083984375, + "eval_runtime": 291.8305, + "eval_samples_per_second": 1307.578, + "eval_steps_per_second": 40.863, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998122989092377e-05, + "loss": 3.9447, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989737041581857e-05, + "loss": 3.9379, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998135109407133e-05, + "loss": 3.955, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997296514656081e-05, + "loss": 3.9459, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996457919905029e-05, + "loss": 3.951, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995619325153977e-05, + "loss": 3.9428, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947807304029253e-05, + "loss": 3.9467, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939421356518733e-05, + "loss": 3.9399, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931035409008213e-05, + "loss": 3.9513, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922649461497693e-05, + "loss": 3.9431, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914263513987173e-05, + "loss": 3.9563, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905877566476653e-05, + "loss": 3.9526, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897507997769862e-05, + "loss": 3.9392, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889122050259345e-05, + "loss": 3.9401, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880736102748825e-05, + "loss": 3.9294, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872350155238305e-05, + "loss": 3.9459, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9863964207727785e-05, + "loss": 3.9443, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855578260217265e-05, + "loss": 3.9429, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847208691510474e-05, + "loss": 3.9397, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838839122803687e-05, + "loss": 3.9581, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830453175293167e-05, + "loss": 3.9473, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822067227782647e-05, + "loss": 3.9489, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813681280272127e-05, + "loss": 3.9476, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805295332761607e-05, + "loss": 3.9544, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796909385251087e-05, + "loss": 3.9377, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788523437740567e-05, + "loss": 3.9438, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780137490230043e-05, + "loss": 3.9412, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771751542719523e-05, + "loss": 3.9363, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763365595209003e-05, + "loss": 3.9382, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9754979647698483e-05, + "loss": 3.9396, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9746593700187963e-05, + "loss": 3.9424, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738224131481175e-05, + "loss": 3.9546, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9729838183970655e-05, + "loss": 3.9457, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721452236460135e-05, + "loss": 3.9414, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713082667753344e-05, + "loss": 3.9439, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704696720242824e-05, + "loss": 3.9507, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696310772732304e-05, + "loss": 3.9375, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9687924825221784e-05, + "loss": 3.9485, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679555256514997e-05, + "loss": 3.932, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671169309004477e-05, + "loss": 3.9366, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662783361493957e-05, + "loss": 3.9425, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654397413983437e-05, + "loss": 3.9525, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646011466472917e-05, + "loss": 3.9322, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9637625518962397e-05, + "loss": 3.9435, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629239571451876e-05, + "loss": 3.9418, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620853623941356e-05, + "loss": 3.9379, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961246767643084e-05, + "loss": 3.9505, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960408172892032e-05, + "loss": 3.9195, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959571216021353e-05, + "loss": 3.9391, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958732621270301e-05, + "loss": 3.9474, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.957894026519249e-05, + "loss": 3.9487, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957055431768197e-05, + "loss": 3.937, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956216837017145e-05, + "loss": 3.9274, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955379880146466e-05, + "loss": 3.9393, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954541285395414e-05, + "loss": 3.9252, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953704328524735e-05, + "loss": 3.9536, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.952865733773683e-05, + "loss": 3.9192, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952027139022631e-05, + "loss": 3.944, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511885442715793e-05, + "loss": 3.9397, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503499495205273e-05, + "loss": 3.9336, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495113547694753e-05, + "loss": 3.947, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486727600184233e-05, + "loss": 3.9318, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478341652673707e-05, + "loss": 3.9261, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9469955705163186e-05, + "loss": 3.9297, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946156975765267e-05, + "loss": 3.9515, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945318381014215e-05, + "loss": 3.9343, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944481424143536e-05, + "loss": 3.9343, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943642829392484e-05, + "loss": 3.9231, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942804234641432e-05, + "loss": 3.9296, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.94196563989038e-05, + "loss": 3.9449, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941128683019701e-05, + "loss": 3.9502, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940290088268649e-05, + "loss": 3.9321, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.93945313139797e-05, + "loss": 3.9473, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938614536646918e-05, + "loss": 3.9556, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937775941895866e-05, + "loss": 3.9447, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.936937347144814e-05, + "loss": 3.9331, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9360987523937623e-05, + "loss": 3.9424, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352601576427103e-05, + "loss": 3.9418, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344215628916583e-05, + "loss": 3.9356, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335829681406063e-05, + "loss": 3.9381, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327443733895543e-05, + "loss": 3.9419, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319057786385023e-05, + "loss": 3.9504, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310688217678232e-05, + "loss": 3.9456, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302302270167716e-05, + "loss": 3.9254, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9293916322657196e-05, + "loss": 3.9345, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9285530375146676e-05, + "loss": 3.939, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9277144427636156e-05, + "loss": 3.9379, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268758480125636e-05, + "loss": 3.9395, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260388911418845e-05, + "loss": 3.937, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252002963908325e-05, + "loss": 3.9354, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243617016397808e-05, + "loss": 3.9268, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235231068887288e-05, + "loss": 3.9386, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226845121376768e-05, + "loss": 3.9374, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921845917386624e-05, + "loss": 3.9421, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921007322635572e-05, + "loss": 3.9442, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.92016872788452e-05, + "loss": 3.9314, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919333408894215e-05, + "loss": 3.9375, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918496452023536e-05, + "loss": 3.9384, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917657857272484e-05, + "loss": 3.9374, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916819262521432e-05, + "loss": 3.9442, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159806677703798e-05, + "loss": 3.9283, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151420730193278e-05, + "loss": 3.9361, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914305116148649e-05, + "loss": 3.9389, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913466521397597e-05, + "loss": 3.9387, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912627926646545e-05, + "loss": 3.9303, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911789331895493e-05, + "loss": 3.9336, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.910950737144441e-05, + "loss": 3.9418, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101137802737623e-05, + "loss": 3.935, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092751855227103e-05, + "loss": 3.9348, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084365907716583e-05, + "loss": 3.93, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9075979960206063e-05, + "loss": 3.9286, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067610391499272e-05, + "loss": 3.9482, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059224443988752e-05, + "loss": 3.9305, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050838496478232e-05, + "loss": 3.9357, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042452548967712e-05, + "loss": 3.9414, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903406660145719e-05, + "loss": 3.9432, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025697032750404e-05, + "loss": 3.9349, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017311085239884e-05, + "loss": 3.936, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9008925137729364e-05, + "loss": 3.9483, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900053919021884e-05, + "loss": 3.9375, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992169621512057e-05, + "loss": 3.9274, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983783674001537e-05, + "loss": 3.9357, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897539772649101e-05, + "loss": 3.9308, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896701177898049e-05, + "loss": 3.9335, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.895862583146997e-05, + "loss": 3.9314, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895023988395945e-05, + "loss": 3.9362, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941853936448933e-05, + "loss": 3.9256, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933467988938413e-05, + "loss": 3.9313, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925082041427893e-05, + "loss": 3.9289, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916712472721102e-05, + "loss": 3.9506, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908326525210582e-05, + "loss": 3.9452, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8899940577700062e-05, + "loss": 3.9332, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891554630189542e-05, + "loss": 3.9358, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883168682679025e-05, + "loss": 3.936, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874782735168505e-05, + "loss": 3.9425, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866396787657985e-05, + "loss": 3.9399, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858010840147465e-05, + "loss": 3.9379, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849641271440674e-05, + "loss": 3.9434, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841255323930154e-05, + "loss": 3.9383, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8832869376419634e-05, + "loss": 3.9374, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824483428909117e-05, + "loss": 3.9306, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816097481398597e-05, + "loss": 3.9416, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807711533888077e-05, + "loss": 3.9337, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.879932558637755e-05, + "loss": 3.923, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879093963886703e-05, + "loss": 3.9417, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878255369135651e-05, + "loss": 3.9359, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774184122649723e-05, + "loss": 3.9426, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876581455394294e-05, + "loss": 3.9284, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875742860643242e-05, + "loss": 3.9322, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.008388996124268, + "eval_runtime": 294.9093, + "eval_samples_per_second": 1293.926, + "eval_steps_per_second": 40.436, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.87490426589219e-05, + "loss": 3.935, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740656711411372e-05, + "loss": 3.9307, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8732270763900855e-05, + "loss": 3.9436, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872390119519407e-05, + "loss": 3.9329, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871551524768355e-05, + "loss": 3.9437, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707129300173024e-05, + "loss": 3.9314, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698743352662504e-05, + "loss": 3.9373, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690357405151984e-05, + "loss": 3.929, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8681971457641464e-05, + "loss": 3.9397, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673585510130947e-05, + "loss": 3.9365, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8665199562620427e-05, + "loss": 3.9444, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8656813615109907e-05, + "loss": 3.9395, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648444046403116e-05, + "loss": 3.9273, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640058098892596e-05, + "loss": 3.9301, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631672151382076e-05, + "loss": 3.9252, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623286203871556e-05, + "loss": 3.9254, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861490025636104e-05, + "loss": 3.9332, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860653068765425e-05, + "loss": 3.9304, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859814474014373e-05, + "loss": 3.931, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.858975879263321e-05, + "loss": 3.9495, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858137284512269e-05, + "loss": 3.9356, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.85730032764159e-05, + "loss": 3.9394, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856461732890538e-05, + "loss": 3.9351, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855623138139486e-05, + "loss": 3.9461, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854784543388434e-05, + "loss": 3.9209, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.853945948637382e-05, + "loss": 3.9393, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.85310735388633e-05, + "loss": 3.9275, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852270397015651e-05, + "loss": 3.9289, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851431802264599e-05, + "loss": 3.9267, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8505932075135473e-05, + "loss": 3.9259, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497546127624953e-05, + "loss": 3.9323, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489160180114433e-05, + "loss": 3.945, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480774232603913e-05, + "loss": 3.9315, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472388285093386e-05, + "loss": 3.9373, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464018716386602e-05, + "loss": 3.9279, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455632768876082e-05, + "loss": 3.9366, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844724682136556e-05, + "loss": 3.9271, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.843886087385504e-05, + "loss": 3.9376, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843047492634452e-05, + "loss": 3.9228, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422088978834e-05, + "loss": 3.9277, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841370303132348e-05, + "loss": 3.9307, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840533346261669e-05, + "loss": 3.9432, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839694751510617e-05, + "loss": 3.9204, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.838856156759565e-05, + "loss": 3.9349, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838017562008513e-05, + "loss": 3.9333, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837178967257461e-05, + "loss": 3.9265, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836340372506409e-05, + "loss": 3.9385, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835501777755357e-05, + "loss": 3.9127, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834663183004305e-05, + "loss": 3.9262, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338262261336263e-05, + "loss": 3.9395, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329876313825743e-05, + "loss": 3.9319, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321490366315223e-05, + "loss": 3.9259, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313104418804703e-05, + "loss": 3.9225, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304734850097912e-05, + "loss": 3.9289, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296348902587396e-05, + "loss": 3.9181, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8287962955076875e-05, + "loss": 3.9383, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279577007566355e-05, + "loss": 3.9137, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271207438859565e-05, + "loss": 3.9296, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262821491349044e-05, + "loss": 3.929, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254435543838524e-05, + "loss": 3.9254, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246049596328004e-05, + "loss": 3.9339, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237680027621217e-05, + "loss": 3.9257, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229294080110697e-05, + "loss": 3.9139, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8220924511403906e-05, + "loss": 3.9163, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212538563893386e-05, + "loss": 3.9435, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204152616382866e-05, + "loss": 3.9233, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819576666887235e-05, + "loss": 3.9218, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818738072136183e-05, + "loss": 3.9153, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.817899477385131e-05, + "loss": 3.9219, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170625205144518e-05, + "loss": 3.9331, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162239257633998e-05, + "loss": 3.9376, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8153853310123478e-05, + "loss": 3.9274, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145467362612958e-05, + "loss": 3.9374, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813708141510244e-05, + "loss": 3.942, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.812869546759192e-05, + "loss": 3.9399, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120309520081395e-05, + "loss": 3.9196, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8111923572570874e-05, + "loss": 3.9333, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8103537625060354e-05, + "loss": 3.9305, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809516805635357e-05, + "loss": 3.9265, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086798487646783e-05, + "loss": 3.925, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078412540136263e-05, + "loss": 3.9299, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070042971429472e-05, + "loss": 3.9407, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061657023918952e-05, + "loss": 3.9343, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053271076408432e-05, + "loss": 3.9138, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044885128897912e-05, + "loss": 3.9213, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036499181387395e-05, + "loss": 3.9266, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028113233876868e-05, + "loss": 3.9301, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8019727286366348e-05, + "loss": 3.9309, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011341338855828e-05, + "loss": 3.9213, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8002955391345308e-05, + "loss": 3.9301, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994569443834788e-05, + "loss": 3.9148, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798618349632427e-05, + "loss": 3.9282, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797779754881375e-05, + "loss": 3.9289, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796941160130323e-05, + "loss": 3.9278, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796104203259644e-05, + "loss": 3.9351, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795265608508592e-05, + "loss": 3.9227, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.79442701375754e-05, + "loss": 3.9244, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935900568868613e-05, + "loss": 3.9297, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927514621358093e-05, + "loss": 3.9319, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919128673847573e-05, + "loss": 3.9283, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910742726337053e-05, + "loss": 3.9214, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902356778826533e-05, + "loss": 3.9241, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7893970831316013e-05, + "loss": 3.9309, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885584883805493e-05, + "loss": 3.9313, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877198936294972e-05, + "loss": 3.9119, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868829367588185e-05, + "loss": 3.9264, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860443420077665e-05, + "loss": 3.9318, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852057472567145e-05, + "loss": 3.9269, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843671525056625e-05, + "loss": 3.92, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835301956349834e-05, + "loss": 3.9208, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7826916008839314e-05, + "loss": 3.9189, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818546440132526e-05, + "loss": 3.9384, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810160492622006e-05, + "loss": 3.9224, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801774545111486e-05, + "loss": 3.9281, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793388597600966e-05, + "loss": 3.9279, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785002650090446e-05, + "loss": 3.938, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776616702579926e-05, + "loss": 3.9238, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776824713387314e-05, + "loss": 3.9275, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.775986118636262e-05, + "loss": 3.9362, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.77514752388521e-05, + "loss": 3.9275, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774308929134158e-05, + "loss": 3.9201, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734719722634788e-05, + "loss": 3.9249, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726333775124268e-05, + "loss": 3.919, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771794782761375e-05, + "loss": 3.9233, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.770956188010323e-05, + "loss": 3.9258, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701175932592704e-05, + "loss": 3.9219, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7692789985082184e-05, + "loss": 3.9153, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684404037571664e-05, + "loss": 3.9216, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676018090061144e-05, + "loss": 3.9205, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667632142550627e-05, + "loss": 3.9385, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659246195040107e-05, + "loss": 3.9386, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7650860247529587e-05, + "loss": 3.9259, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642490678822796e-05, + "loss": 3.9186, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634104731312276e-05, + "loss": 3.9288, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625718783801756e-05, + "loss": 3.9299, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617332836291236e-05, + "loss": 3.932, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.760894688878072e-05, + "loss": 3.9261, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.76005609412702e-05, + "loss": 3.933, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759217499375968e-05, + "loss": 3.9256, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758378904624916e-05, + "loss": 3.9283, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757540309873864e-05, + "loss": 3.9234, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756703353003185e-05, + "loss": 3.9282, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.755864758252133e-05, + "loss": 3.9243, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755026163501081e-05, + "loss": 3.9159, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754187568750029e-05, + "loss": 3.9284, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533489739989765e-05, + "loss": 3.9288, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752512017128298e-05, + "loss": 3.9339, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751673422377246e-05, + "loss": 3.9202, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.750834827626194e-05, + "loss": 3.9218, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.003854274749756, + "eval_runtime": 298.4857, + "eval_samples_per_second": 1278.423, + "eval_steps_per_second": 39.952, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7499962328751417e-05, + "loss": 3.9243, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491576381240897e-05, + "loss": 3.9209, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483190433730377e-05, + "loss": 3.9338, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7474804486219857e-05, + "loss": 3.9235, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466418538709337e-05, + "loss": 3.9347, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458032591198817e-05, + "loss": 3.9174, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449646643688297e-05, + "loss": 3.9291, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441260696177777e-05, + "loss": 3.9195, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743287474866726e-05, + "loss": 3.9315, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742448880115674e-05, + "loss": 3.9257, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741610285364622e-05, + "loss": 3.9355, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.74077169061357e-05, + "loss": 3.9286, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.739934733742891e-05, + "loss": 3.9168, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739096138991839e-05, + "loss": 3.9212, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738257544240787e-05, + "loss": 3.9186, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7374189494897352e-05, + "loss": 3.9196, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7365803547386832e-05, + "loss": 3.9236, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357417599876306e-05, + "loss": 3.9191, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349031652365786e-05, + "loss": 3.9211, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340645704855265e-05, + "loss": 3.9419, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733227613614848e-05, + "loss": 3.928, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7323890188637958e-05, + "loss": 3.9269, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315504241127438e-05, + "loss": 3.9286, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307134672420654e-05, + "loss": 3.933, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298748724910127e-05, + "loss": 3.9119, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290362777399607e-05, + "loss": 3.9273, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728197682988909e-05, + "loss": 3.9226, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727359088237857e-05, + "loss": 3.9201, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726522131367178e-05, + "loss": 3.9155, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725683536616126e-05, + "loss": 3.9159, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.724844941865074e-05, + "loss": 3.9256, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724006347114022e-05, + "loss": 3.9365, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.72316775236297e-05, + "loss": 3.9242, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223291576119182e-05, + "loss": 3.9279, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7214938386216127e-05, + "loss": 3.9212, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.72065524387056e-05, + "loss": 3.9237, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.719816649119508e-05, + "loss": 3.9156, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.718978054368456e-05, + "loss": 3.933, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181394596174044e-05, + "loss": 3.9105, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173025027467253e-05, + "loss": 3.9199, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164639079956733e-05, + "loss": 3.9198, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156253132446213e-05, + "loss": 3.934, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7147867184935693e-05, + "loss": 3.9141, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7139481237425173e-05, + "loss": 3.9213, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7131095289914653e-05, + "loss": 3.9257, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7122709342404136e-05, + "loss": 3.9187, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7114339773697345e-05, + "loss": 3.9288, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7105953826186825e-05, + "loss": 3.9058, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097567878676305e-05, + "loss": 3.916, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089181931165785e-05, + "loss": 3.932, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080795983655265e-05, + "loss": 3.9215, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072410036144745e-05, + "loss": 3.9172, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064040467437957e-05, + "loss": 3.9133, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7055654519927437e-05, + "loss": 3.9218, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047268572416917e-05, + "loss": 3.9082, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7038882624906397e-05, + "loss": 3.9249, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030496677395877e-05, + "loss": 3.9038, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022110729885357e-05, + "loss": 3.9191, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7013724782374837e-05, + "loss": 3.9238, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005338834864314e-05, + "loss": 3.9149, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699696926615753e-05, + "loss": 3.9216, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.698858331864701e-05, + "loss": 3.9237, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698019737113649e-05, + "loss": 3.9023, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6971811423625966e-05, + "loss": 3.913, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963425476115446e-05, + "loss": 3.9252, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6955055907408662e-05, + "loss": 3.9195, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6946669959898142e-05, + "loss": 3.9161, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938284012387615e-05, + "loss": 3.8997, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6929898064877095e-05, + "loss": 3.9098, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921512117366575e-05, + "loss": 3.9248, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913142548659787e-05, + "loss": 3.9279, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904756601149267e-05, + "loss": 3.9132, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896370653638747e-05, + "loss": 3.9294, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6887984706128227e-05, + "loss": 3.9315, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879598758617707e-05, + "loss": 3.9351, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687122918991092e-05, + "loss": 3.9056, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.68628432424004e-05, + "loss": 3.9262, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685445729488988e-05, + "loss": 3.9174, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684607134737936e-05, + "loss": 3.9174, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683770177867257e-05, + "loss": 3.9208, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.682931583116205e-05, + "loss": 3.9201, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682092988365153e-05, + "loss": 3.9275, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681254393614101e-05, + "loss": 3.9287, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804157988630492e-05, + "loss": 3.9058, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795772041119972e-05, + "loss": 3.9148, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787386093609452e-05, + "loss": 3.9162, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.677901652490266e-05, + "loss": 3.9213, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677063057739214e-05, + "loss": 3.925, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676224462988162e-05, + "loss": 3.9121, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.67538586823711e-05, + "loss": 3.9213, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745472734860584e-05, + "loss": 3.9072, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737086787350064e-05, + "loss": 3.9184, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6728700839839544e-05, + "loss": 3.9192, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6720314892329024e-05, + "loss": 3.916, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6711928944818504e-05, + "loss": 3.9241, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6703575754915446e-05, + "loss": 3.9222, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6695206186208655e-05, + "loss": 3.9112, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6686820238698135e-05, + "loss": 3.9227, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6678434291187615e-05, + "loss": 3.9225, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670048343677095e-05, + "loss": 3.9211, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661662396166575e-05, + "loss": 3.9082, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653276448656054e-05, + "loss": 3.9173, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6644890501145538e-05, + "loss": 3.9202, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636504553635018e-05, + "loss": 3.9245, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628134984928227e-05, + "loss": 3.9002, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619749037417707e-05, + "loss": 3.9162, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611363089907187e-05, + "loss": 3.9257, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6602977142396667e-05, + "loss": 3.918, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594591194886147e-05, + "loss": 3.909, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586205247375623e-05, + "loss": 3.9142, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6577819299865103e-05, + "loss": 3.9115, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569433352354583e-05, + "loss": 3.9272, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6561047404844063e-05, + "loss": 3.9121, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6552677836137276e-05, + "loss": 3.9208, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544291888626756e-05, + "loss": 3.9203, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653592231991997e-05, + "loss": 3.9252, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527536372409445e-05, + "loss": 3.916, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519150424898925e-05, + "loss": 3.9225, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510764477388405e-05, + "loss": 3.9273, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502378529877885e-05, + "loss": 3.9191, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6493992582367368e-05, + "loss": 3.9097, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485623013660577e-05, + "loss": 3.9178, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477237066150057e-05, + "loss": 3.9104, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6468851118639537e-05, + "loss": 3.9171, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460465171129017e-05, + "loss": 3.9142, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452079223618497e-05, + "loss": 3.9173, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6443693276107977e-05, + "loss": 3.9031, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643532370740119e-05, + "loss": 3.9114, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642693775989067e-05, + "loss": 3.9097, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.641855181238015e-05, + "loss": 3.9298, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641016586486963e-05, + "loss": 3.9288, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640177991735911e-05, + "loss": 3.9205, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639339396984859e-05, + "loss": 3.9112, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638500802233807e-05, + "loss": 3.9186, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637663845363128e-05, + "loss": 3.9236, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.636825250612076e-05, + "loss": 3.9212, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.635986655861024e-05, + "loss": 3.9189, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635148061109972e-05, + "loss": 3.9216, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63430946635892e-05, + "loss": 3.9195, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633470871607868e-05, + "loss": 3.9244, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632632276856816e-05, + "loss": 3.9097, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6317936821057638e-05, + "loss": 3.9228, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6309550873547118e-05, + "loss": 3.915, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6301164926036598e-05, + "loss": 3.9059, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6292795357329807e-05, + "loss": 3.9191, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6284409409819287e-05, + "loss": 3.9237, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627602346230877e-05, + "loss": 3.9207, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626763751479825e-05, + "loss": 3.9151, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.625926794609146e-05, + "loss": 3.9099, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.9997711181640625, + "eval_runtime": 292.0665, + "eval_samples_per_second": 1306.521, + "eval_steps_per_second": 40.83, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6250898377384675e-05, + "loss": 3.9239, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6242512429874155e-05, + "loss": 3.9127, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6234126482363635e-05, + "loss": 3.9243, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622574053485311e-05, + "loss": 3.9116, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621735458734259e-05, + "loss": 3.9316, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.620896863983207e-05, + "loss": 3.9081, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620058269232155e-05, + "loss": 3.9219, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619219674481103e-05, + "loss": 3.9095, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618381079730051e-05, + "loss": 3.9228, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175441228593724e-05, + "loss": 3.9168, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167055281083204e-05, + "loss": 3.9201, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6158669333572684e-05, + "loss": 3.9247, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150299764865893e-05, + "loss": 3.9071, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6141913817355373e-05, + "loss": 3.9132, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133527869844853e-05, + "loss": 3.9098, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125141922334333e-05, + "loss": 3.9133, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6116755974823816e-05, + "loss": 3.9136, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108370027313296e-05, + "loss": 3.9114, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6099984079802776e-05, + "loss": 3.9144, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091598132292256e-05, + "loss": 3.9331, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083212184781736e-05, + "loss": 3.918, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6074842616074945e-05, + "loss": 3.918, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6066456668564425e-05, + "loss": 3.9218, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6058070721053908e-05, + "loss": 3.9229, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6049684773543388e-05, + "loss": 3.905, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041315204836597e-05, + "loss": 3.9254, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6032929257326077e-05, + "loss": 3.9093, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024543309815557e-05, + "loss": 3.9114, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016157362305037e-05, + "loss": 3.9049, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6007771414794517e-05, + "loss": 3.9131, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.599940184608773e-05, + "loss": 3.9114, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599101589857721e-05, + "loss": 3.9286, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598262995106669e-05, + "loss": 3.9174, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597424400355617e-05, + "loss": 3.9183, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596587443484938e-05, + "loss": 3.9091, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957488487338862e-05, + "loss": 3.9217, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949102539828342e-05, + "loss": 3.9037, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940716592317822e-05, + "loss": 3.9261, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932330644807295e-05, + "loss": 3.9003, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5923944697296775e-05, + "loss": 3.9099, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591557512858999e-05, + "loss": 3.9122, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907189181079467e-05, + "loss": 3.9262, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898803233568947e-05, + "loss": 3.9087, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890417286058427e-05, + "loss": 3.9117, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5882031338547907e-05, + "loss": 3.9142, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5873645391037387e-05, + "loss": 3.9127, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865259443526867e-05, + "loss": 3.9196, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5856873496016347e-05, + "loss": 3.9029, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5848487548505827e-05, + "loss": 3.9019, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584010160099531e-05, + "loss": 3.9224, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583173203228852e-05, + "loss": 3.9115, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5823346084778e-05, + "loss": 3.9094, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581496013726748e-05, + "loss": 3.9069, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580657418975696e-05, + "loss": 3.9121, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798204621050172e-05, + "loss": 3.8978, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.578983505234338e-05, + "loss": 3.9169, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578144910483286e-05, + "loss": 3.896, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577306315732234e-05, + "loss": 3.9141, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576467720981182e-05, + "loss": 3.9096, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.57562912623013e-05, + "loss": 3.9144, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574790531479078e-05, + "loss": 3.9098, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739519367280264e-05, + "loss": 3.915, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731133419769744e-05, + "loss": 3.8941, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5722763851062953e-05, + "loss": 3.9075, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714377903552433e-05, + "loss": 3.9164, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706008334845642e-05, + "loss": 3.9135, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697622387335125e-05, + "loss": 3.9024, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689236439824605e-05, + "loss": 3.8991, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5680850492314085e-05, + "loss": 3.8999, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672464544803565e-05, + "loss": 3.9121, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664078597293045e-05, + "loss": 3.919, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5655692649782525e-05, + "loss": 3.9093, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647306702272005e-05, + "loss": 3.9221, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5638920754761482e-05, + "loss": 3.9233, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630534807250962e-05, + "loss": 3.9322, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622165238544178e-05, + "loss": 3.8944, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613795669837387e-05, + "loss": 3.9164, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605409722326867e-05, + "loss": 3.918, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597023774816347e-05, + "loss": 3.9049, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5588637827305827e-05, + "loss": 3.9139, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5580251879795303e-05, + "loss": 3.916, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5571865932284783e-05, + "loss": 3.9212, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563479984774263e-05, + "loss": 3.9122, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555511041606748e-05, + "loss": 3.9018, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546724468556955e-05, + "loss": 3.9054, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538338521046435e-05, + "loss": 3.9068, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.552996895233965e-05, + "loss": 3.9145, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552158300482913e-05, + "loss": 3.9171, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513197057318604e-05, + "loss": 3.902, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5504811109808084e-05, + "loss": 3.9114, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496425162297564e-05, + "loss": 3.9009, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488039214787048e-05, + "loss": 3.9089, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479653267276528e-05, + "loss": 3.9114, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471267319766008e-05, + "loss": 3.9059, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5462881372255488e-05, + "loss": 3.9183, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454511803548697e-05, + "loss": 3.9142, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446125856038177e-05, + "loss": 3.9051, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437739908527657e-05, + "loss": 3.9147, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.542935396101714e-05, + "loss": 3.9144, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542096801350662e-05, + "loss": 3.9162, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541259844479983e-05, + "loss": 3.9005, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540421249728931e-05, + "loss": 3.9088, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539582654977879e-05, + "loss": 3.9128, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538744060226827e-05, + "loss": 3.9195, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.537907103356148e-05, + "loss": 3.8971, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537068508605096e-05, + "loss": 3.9037, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536229913854044e-05, + "loss": 3.9175, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535391319102992e-05, + "loss": 3.91, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.53455272435194e-05, + "loss": 3.9009, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533715767481261e-05, + "loss": 3.903, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328771727302094e-05, + "loss": 3.9095, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320385779791574e-05, + "loss": 3.9126, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5311999832281053e-05, + "loss": 3.9079, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303613884770533e-05, + "loss": 3.9069, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295227937260013e-05, + "loss": 3.9142, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5286841989749487e-05, + "loss": 3.9174, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.527845604223897e-05, + "loss": 3.9149, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527007009472845e-05, + "loss": 3.905, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5261700526021666e-05, + "loss": 3.9221, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525331457851114e-05, + "loss": 3.9114, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524492863100062e-05, + "loss": 3.8978, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.52365426834901e-05, + "loss": 3.9099, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.522815673597958e-05, + "loss": 3.9048, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.521977078846906e-05, + "loss": 3.9101, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211384840958542e-05, + "loss": 3.9035, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520301527225175e-05, + "loss": 3.912, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519462932474123e-05, + "loss": 3.8978, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518624337723071e-05, + "loss": 3.9056, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517785742972019e-05, + "loss": 3.9023, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169487861013404e-05, + "loss": 3.923, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161101913502883e-05, + "loss": 3.9163, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152715965992363e-05, + "loss": 3.9163, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144346397285573e-05, + "loss": 3.9006, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5135960449775052e-05, + "loss": 3.9154, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127574502264532e-05, + "loss": 3.9195, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119188554754012e-05, + "loss": 3.9096, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5110802607243496e-05, + "loss": 3.9081, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102416659732976e-05, + "loss": 3.9134, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094047091026185e-05, + "loss": 3.911, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5085661143515665e-05, + "loss": 3.9181, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077275196005145e-05, + "loss": 3.8985, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5068889248494625e-05, + "loss": 3.9141, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060503300984105e-05, + "loss": 3.9055, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052133732277317e-05, + "loss": 3.9039, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043747784766797e-05, + "loss": 3.909, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035361837256277e-05, + "loss": 3.9164, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5026975889745757e-05, + "loss": 3.9089, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018589942235237e-05, + "loss": 3.9039, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501022037352845e-05, + "loss": 3.9053, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.996687412261963, + "eval_runtime": 293.0373, + "eval_samples_per_second": 1302.193, + "eval_steps_per_second": 40.694, + "step": 1526400 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 6.308165527496252e+17, + "trial_name": null, + "trial_params": null +}