diff --git "a/checkpoint-2747503/trainer_state.json" "b/checkpoint-2747503/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747503/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 4.026012897491455, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/3/checkpoints/checkpoint-2671183", + "epoch": 2.025000606015738, + "eval_steps": 10, + "global_step": 2747503, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8197, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5807, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0567, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9828, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.953, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.858, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7027, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.5933, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5066, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.416, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3551, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.2845, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2164, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1439, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.0822, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0393, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 5.9923, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9439, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9108, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.869, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8431, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8055, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.7702, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7497, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7182, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.6916, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.6686, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.6477, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6137, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6011, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.5745, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.5564, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5438, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5274, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5055, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.4965, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 5.4836, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 5.4643, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 5.4477, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 5.437, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 5.4124, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4114, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.383, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.3832, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3751, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3664, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3403, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3392, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3343, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3127, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.2984, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.2951, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3003, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2678, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2887, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2499, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.26, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2385, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2342, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2247, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2193, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.1988, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2072, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.1893, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.1965, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.1779, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1677, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1516, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1594, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.153, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1339, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1353, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1265, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1236, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1212, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1151, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1009, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.0855, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.0928, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.0835, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.0844, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932093479729265e-05, + "loss": 5.076, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931254884978213e-05, + "loss": 5.0664, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930416290227161e-05, + "loss": 5.0458, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929577695476109e-05, + "loss": 5.0512, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.054, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0494, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0385, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0313, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0195, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.014, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.0113, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0195, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0088, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 4.9836, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 4.9862, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.9925, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.9892, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.9766, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9748, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.9639, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9615, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9686, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9625, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9368, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.9481, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9273, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.9324, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9299, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9193, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9184, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9084, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906108507609265e-05, + "loss": 4.9067, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9036, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9155, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.8904, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.8764, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.8849, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.8952, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.8782, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.8874, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8747, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.8738, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.8612, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.8626, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.8581, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.8626, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8421, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.8519, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.8475, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8342, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8418, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.835, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8399, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8368, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8179, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.813, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.8127, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.8174, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.8259, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8144, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8043, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8011, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.7995, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.7955, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.7921, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.8048, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.7901, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.7839, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.7782, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.794678688049316, + "eval_runtime": 547.8678, + "eval_samples_per_second": 696.502, + "eval_steps_per_second": 21.766, + "step": 76319 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.7917, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.7838, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.769, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.771, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.7599, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.7579, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.7537, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.7564, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.7538, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.7556, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.7517, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.758, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.7423, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.7338, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.7346, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.7165, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.7303, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7275, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.7239, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.7342, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7228, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.7219, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.7221, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7179, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.7079, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.7067, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.7134, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.6984, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.701, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.6872, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.6893, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.7017, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.6914, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.6925, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.6889, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.6892, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.6864, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.6841, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.6844, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.6724, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.6744, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.6622, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6674, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6767, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.6744, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.66, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.6614, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6674, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.6482, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.6462, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6489, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.661, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.6366, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.6637, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.6317, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.6449, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.638, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6402, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6326, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6353, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.625, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.634, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.6243, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.631, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.6212, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.6214, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.6026, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.6285, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6173, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6061, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.6142, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.6101, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.612, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.6181, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.6155, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.6028, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.595, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.6012, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.6035, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.6083, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.6005, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.5959, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.5779, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.5867, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.593, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803000662358823e-05, + "loss": 4.5916, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802162067607771e-05, + "loss": 4.5938, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.5855, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.5766, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.5818, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.5743, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.5817, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.5826, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.5611, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795456585360101e-05, + "loss": 4.5632, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794617990609049e-05, + "loss": 4.5738, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793779395857997e-05, + "loss": 4.5792, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5643, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.5713, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5629, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.5628, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5709, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.5676, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.549, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5654, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5454, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5485, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845597672375445e-05, + "loss": 4.5566, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.5441, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5454, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.5401, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.541, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780368431362658e-05, + "loss": 4.5406, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779529836611606e-05, + "loss": 4.556, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778692879740927e-05, + "loss": 4.5359, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777854284989875e-05, + "loss": 4.5275, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.5339, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.5418, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.5376, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.541, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.538, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5375, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5289, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5248, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5285, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.5347, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.5188, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.5224, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5354, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.5096, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.5232, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.5207, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.5297, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5236, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5095, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5081, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.5092, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941011410785e-05, + "loss": 4.5163, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5253, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5195, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756895967735067e-05, + "loss": 4.5055, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756057372984015e-05, + "loss": 4.5076, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755218778232963e-05, + "loss": 4.5103, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754380183481911e-05, + "loss": 4.5065, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.503, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.75270463186018e-05, + "loss": 4.5212, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751866037109128e-05, + "loss": 4.5003, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751027442358077e-05, + "loss": 4.5026, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.497, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.520559787750244, + "eval_runtime": 545.9213, + "eval_samples_per_second": 698.985, + "eval_steps_per_second": 21.844, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.5128, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.5073, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.494, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.4944, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.488, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.4891, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.4868, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.49, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.4866, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741804537976877e-05, + "loss": 4.4921, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740965943225825e-05, + "loss": 4.4931, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401273484747736e-05, + "loss": 4.4973, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392887537237216e-05, + "loss": 4.4835, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.4735, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4815, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.4615, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.478, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.4744, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.473, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.4879, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4764, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4763, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730904444093574e-05, + "loss": 4.4791, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730065849342522e-05, + "loss": 4.4722, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292272545914704e-05, + "loss": 4.4701, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283886598404184e-05, + "loss": 4.4646, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275500650893664e-05, + "loss": 4.4729, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267114703383144e-05, + "loss": 4.4639, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4653, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4499, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4587, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723358729214479e-05, + "loss": 4.47, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722520134463427e-05, + "loss": 4.4566, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4639, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4582, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720005988090644e-05, + "loss": 4.4619, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719167393339592e-05, + "loss": 4.4641, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71832879858854e-05, + "loss": 4.4605, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.459, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4498, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715814652215758e-05, + "loss": 4.4548, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4413, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4556, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4564, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4573, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711621678460498e-05, + "loss": 4.4434, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4454, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.4541, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091075320877147e-05, + "loss": 4.4341, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082689373366627e-05, + "loss": 4.4382, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4358, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4544, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.4293, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049145583324546e-05, + "loss": 4.4567, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4265, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.4338, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702402049840045e-05, + "loss": 4.4377, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015634550889924e-05, + "loss": 4.4366, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4325, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4441, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4168, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4326, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973704813337324e-05, + "loss": 4.4273, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965318865826804e-05, + "loss": 4.436, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.4236, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.69485633496095e-05, + "loss": 4.4267, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694017740209898e-05, + "loss": 4.4093, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693179145458846e-05, + "loss": 4.4357, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692340550707794e-05, + "loss": 4.426, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691501955956742e-05, + "loss": 4.4167, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.69066336120569e-05, + "loss": 4.4226, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.4214, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4194, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688149214832907e-05, + "loss": 4.4325, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687310620081855e-05, + "loss": 4.4292, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864753010915494e-05, + "loss": 4.4171, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4102, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4146, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.4205, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831209220873414e-05, + "loss": 4.4237, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4165, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814437325852373e-05, + "loss": 4.4188, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806051378341853e-05, + "loss": 4.3963, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679768180963506e-05, + "loss": 4.4104, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4064, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4116, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.418, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.409, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675576845088619e-05, + "loss": 4.3981, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674738250337568e-05, + "loss": 4.4075, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.3991, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673061060835464e-05, + "loss": 4.4079, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4068, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713871470941056e-05, + "loss": 4.3905, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705485523430536e-05, + "loss": 4.3934, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697099575920016e-05, + "loss": 4.4, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688713628409496e-05, + "loss": 4.4072, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.3967, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671958112192185e-05, + "loss": 4.4048, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.3936, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.3958, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.4015, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.3985, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663004475344332e-05, + "loss": 4.3845, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.4028, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661327285842228e-05, + "loss": 4.3775, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660488691091176e-05, + "loss": 4.3813, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596500963401234e-05, + "loss": 4.3976, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.3801, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.3899, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.3797, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656297355216288e-05, + "loss": 4.3774, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.38, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.3989, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.3794, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.3745, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3716, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.381, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650430467719671e-05, + "loss": 4.3861, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6495935108489924e-05, + "loss": 4.3836, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487549160979403e-05, + "loss": 4.3792, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479163213468883e-05, + "loss": 4.3835, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647077726595836e-05, + "loss": 4.3746, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462391318447837e-05, + "loss": 4.3773, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645400537093732e-05, + "loss": 4.376, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.64456194234268e-05, + "loss": 4.3799, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643723347591628e-05, + "loss": 4.3691, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642884752840576e-05, + "loss": 4.3707, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642047795969897e-05, + "loss": 4.3848, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3622, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3702, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639532011716741e-05, + "loss": 4.3721, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638695054846062e-05, + "loss": 4.3819, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.63785646009501e-05, + "loss": 4.3722, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637017865343958e-05, + "loss": 4.3692, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636180908473279e-05, + "loss": 4.3591, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635342313722228e-05, + "loss": 4.362, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634503718971176e-05, + "loss": 4.3716, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633665124220124e-05, + "loss": 4.3794, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328281673494446e-05, + "loss": 4.3765, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.364, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3606, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303123830962886e-05, + "loss": 4.3719, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294754262256095e-05, + "loss": 4.3609, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286368314745575e-05, + "loss": 4.3609, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277982367235055e-05, + "loss": 4.3746, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269596419724535e-05, + "loss": 4.3597, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261210472214015e-05, + "loss": 4.363, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252824524703495e-05, + "loss": 4.3593, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.39060115814209, + "eval_runtime": 543.0154, + "eval_samples_per_second": 702.726, + "eval_steps_per_second": 21.961, + "step": 228957 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244438577192975e-05, + "loss": 4.3695, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623605262968246e-05, + "loss": 4.3707, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622768306097567e-05, + "loss": 4.3558, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621929711346515e-05, + "loss": 4.3552, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621091116595463e-05, + "loss": 4.3541, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620254159724784e-05, + "loss": 4.3496, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619415564973732e-05, + "loss": 4.3531, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.61857697022268e-05, + "loss": 4.3513, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617738375471628e-05, + "loss": 4.3526, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616901418600949e-05, + "loss": 4.3601, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616062823849897e-05, + "loss": 4.3565, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615224229098845e-05, + "loss": 4.3589, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614385634347793e-05, + "loss": 4.3527, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135470395967415e-05, + "loss": 4.344, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127084448456895e-05, + "loss": 4.3455, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611869850094637e-05, + "loss": 4.3284, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611031255343585e-05, + "loss": 4.3432, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6101942984729064e-05, + "loss": 4.3432, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093557037218544e-05, + "loss": 4.3427, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608517108970802e-05, + "loss": 4.3573, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.60767851421975e-05, + "loss": 4.3455, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606841557349071e-05, + "loss": 4.3492, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606004600478392e-05, + "loss": 4.3455, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.60516600572734e-05, + "loss": 4.3414, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604327410976288e-05, + "loss": 4.3412, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603488816225236e-05, + "loss": 4.3418, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602650221474184e-05, + "loss": 4.3401, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601811626723132e-05, + "loss": 4.3372, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600974669852454e-05, + "loss": 4.3378, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600136075101402e-05, + "loss": 4.3255, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599299118230723e-05, + "loss": 4.3344, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598460523479671e-05, + "loss": 4.3418, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597621928728619e-05, + "loss": 4.3342, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596783333977567e-05, + "loss": 4.3379, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595944739226514e-05, + "loss": 4.3339, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595106144475462e-05, + "loss": 4.3383, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.59426754972441e-05, + "loss": 4.3366, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934289549733587e-05, + "loss": 4.3427, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925903602223066e-05, + "loss": 4.3348, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917517654712546e-05, + "loss": 4.3284, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909131707202026e-05, + "loss": 4.3329, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900745759691506e-05, + "loss": 4.3175, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892359812180986e-05, + "loss": 4.3373, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883990243474195e-05, + "loss": 4.3373, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875604295963675e-05, + "loss": 4.3354, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867218348453155e-05, + "loss": 4.3239, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858848779746364e-05, + "loss": 4.3247, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850462832235844e-05, + "loss": 4.3359, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842076884725324e-05, + "loss": 4.3146, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833690937214804e-05, + "loss": 4.3214, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825304989704284e-05, + "loss": 4.3214, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581691904219377e-05, + "loss": 4.3347, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580853309468325e-05, + "loss": 4.3088, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580014714717273e-05, + "loss": 4.3408, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579179395726967e-05, + "loss": 4.3103, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578340800975915e-05, + "loss": 4.3127, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577502206224863e-05, + "loss": 4.3258, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576663611473811e-05, + "loss": 4.313, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575825016722759e-05, + "loss": 4.3254, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574986421971707e-05, + "loss": 4.3283, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574147827220655e-05, + "loss": 4.3052, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573309232469602e-05, + "loss": 4.3142, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572472275598924e-05, + "loss": 4.3185, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716336808478725e-05, + "loss": 4.3209, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707950860968205e-05, + "loss": 4.3094, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699581292261414e-05, + "loss": 4.3141, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691195344750894e-05, + "loss": 4.2948, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682809397240374e-05, + "loss": 4.3258, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674423449729854e-05, + "loss": 4.3126, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566605388102306e-05, + "loss": 4.3044, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565766793351254e-05, + "loss": 4.3118, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564928198600202e-05, + "loss": 4.3107, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5640896038491496e-05, + "loss": 4.3105, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632510090980976e-05, + "loss": 4.3171, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562412414347046e-05, + "loss": 4.3218, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561573819595994e-05, + "loss": 4.308, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.3041, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55989663009389e-05, + "loss": 4.3066, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559058035342838e-05, + "loss": 4.3075, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558219440591786e-05, + "loss": 4.32, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557382483721107e-05, + "loss": 4.3119, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3063, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555705294219003e-05, + "loss": 4.2937, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554866699467951e-05, + "loss": 4.3018, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.3024, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3057, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552350915214795e-05, + "loss": 4.3054, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551512320463743e-05, + "loss": 4.3043, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550675363593064e-05, + "loss": 4.2966, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549836768842013e-05, + "loss": 4.3042, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489998119713336e-05, + "loss": 4.2968, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481612172202816e-05, + "loss": 4.2985, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473226224692296e-05, + "loss": 4.3021, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.2877, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456454329671256e-05, + "loss": 4.2892, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448068382160736e-05, + "loss": 4.3025, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439682434650216e-05, + "loss": 4.2955, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543129648713969e-05, + "loss": 4.3012, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422926918432905e-05, + "loss": 4.299, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414540970922385e-05, + "loss": 4.2928, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406155023411865e-05, + "loss": 4.2917, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397769075901345e-05, + "loss": 4.3013, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538939950719456e-05, + "loss": 4.2992, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538101355968404e-05, + "loss": 4.2838, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372627612173514e-05, + "loss": 4.3034, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364241664662994e-05, + "loss": 4.2749, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355855717152473e-05, + "loss": 4.2854, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347469769641953e-05, + "loss": 4.2976, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533908382213143e-05, + "loss": 4.2801, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533069787462091e-05, + "loss": 4.2933, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532232830591412e-05, + "loss": 4.2793, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.53139423584036e-05, + "loss": 4.2779, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530555641089308e-05, + "loss": 4.2821, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529717046338256e-05, + "loss": 4.3017, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.2843, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.2757, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527202899965474e-05, + "loss": 4.2754, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526364305214422e-05, + "loss": 4.2824, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.52552571046337e-05, + "loss": 4.2909, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524687115712318e-05, + "loss": 4.2894, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523848520961266e-05, + "loss": 4.2796, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2904, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2805, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.2833, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520495779837431e-05, + "loss": 4.2806, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519657185086379e-05, + "loss": 4.2854, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518818590335327e-05, + "loss": 4.2761, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517979995584275e-05, + "loss": 4.2774, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517141400833223e-05, + "loss": 4.29, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516304443962544e-05, + "loss": 4.2688, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515465849211492e-05, + "loss": 4.2765, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.51462725446044e-05, + "loss": 4.2811, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137886597093876e-05, + "loss": 4.2873, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.2801, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512113108087657e-05, + "loss": 4.2786, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112745133366045e-05, + "loss": 4.2671, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104359185855525e-05, + "loss": 4.2701, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509598961714874e-05, + "loss": 4.2808, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508760366963822e-05, + "loss": 4.2863, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.50792177221277e-05, + "loss": 4.2855, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507083177461718e-05, + "loss": 4.2738, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062478584714125e-05, + "loss": 4.2669, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054092637203605e-05, + "loss": 4.2795, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045706689693085e-05, + "loss": 4.2712, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037320742182565e-05, + "loss": 4.272, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028934794672045e-05, + "loss": 4.2842, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502054884716152e-05, + "loss": 4.274, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012162899651e-05, + "loss": 4.2701, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500377695214048e-05, + "loss": 4.2699, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.3090386390686035, + "eval_runtime": 543.1539, + "eval_samples_per_second": 702.547, + "eval_steps_per_second": 21.955, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995407383433694e-05, + "loss": 4.2846, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987021435923174e-05, + "loss": 4.2779, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978635488412654e-05, + "loss": 4.2672, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970249540902134e-05, + "loss": 4.2642, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961863593391614e-05, + "loss": 4.2682, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953477645881094e-05, + "loss": 4.262, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945091698370574e-05, + "loss": 4.2655, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936705750860054e-05, + "loss": 4.2604, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928319803349534e-05, + "loss": 4.2678, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919933855839014e-05, + "loss": 4.277, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911547908328494e-05, + "loss": 4.2659, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903161960817974e-05, + "loss": 4.2669, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894776013307454e-05, + "loss": 4.2698, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886390065796934e-05, + "loss": 4.2603, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487800411828641e-05, + "loss": 4.261, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486961817077589e-05, + "loss": 4.2419, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861232223265373e-05, + "loss": 4.2574, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4852846275754853e-05, + "loss": 4.2565, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484446032824433e-05, + "loss": 4.2554, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483609075953754e-05, + "loss": 4.2778, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482770481202702e-05, + "loss": 4.259, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48193188645165e-05, + "loss": 4.2664, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481094929580971e-05, + "loss": 4.2574, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480256334829919e-05, + "loss": 4.2621, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479417740078867e-05, + "loss": 4.2523, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478579145327815e-05, + "loss": 4.2587, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477740550576763e-05, + "loss": 4.2558, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476901955825711e-05, + "loss": 4.2553, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476063361074659e-05, + "loss": 4.2535, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475224766323607e-05, + "loss": 4.2451, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474387809452929e-05, + "loss": 4.2471, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473549214701877e-05, + "loss": 4.2596, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472710619950825e-05, + "loss": 4.2544, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471872025199773e-05, + "loss": 4.257, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710350683290936e-05, + "loss": 4.2522, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701964735780416e-05, + "loss": 4.2572, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693578788269896e-05, + "loss": 4.2553, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685192840759376e-05, + "loss": 4.2608, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676823272052585e-05, + "loss": 4.2537, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668437324542065e-05, + "loss": 4.2443, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660051377031545e-05, + "loss": 4.256, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651665429521025e-05, + "loss": 4.2354, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464327948201051e-05, + "loss": 4.2535, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463489353449999e-05, + "loss": 4.2519, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462650758698947e-05, + "loss": 4.2584, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461812163947895e-05, + "loss": 4.2462, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609735691968425e-05, + "loss": 4.2403, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601349744457905e-05, + "loss": 4.2572, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592963796947384e-05, + "loss": 4.2403, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584577849436864e-05, + "loss": 4.2391, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576208280730074e-05, + "loss": 4.2443, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567822333219554e-05, + "loss": 4.2526, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559436385709033e-05, + "loss": 4.2346, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551050438198513e-05, + "loss": 4.2563, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454268086949173e-05, + "loss": 4.233, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453429492198121e-05, + "loss": 4.2367, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452590897447069e-05, + "loss": 4.2473, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451752302696017e-05, + "loss": 4.2318, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450913707944965e-05, + "loss": 4.2513, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450075113193913e-05, + "loss": 4.2537, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449236518442861e-05, + "loss": 4.2266, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448399561572182e-05, + "loss": 4.2344, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.44756096682113e-05, + "loss": 4.243, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446722372070078e-05, + "loss": 4.2487, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445883777319026e-05, + "loss": 4.2335, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445045182567974e-05, + "loss": 4.2367, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444206587816922e-05, + "loss": 4.2227, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44336799306587e-05, + "loss": 4.2444, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425310361951914e-05, + "loss": 4.2385, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441694079324512e-05, + "loss": 4.2283, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44085548457346e-05, + "loss": 4.2384, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440016889822408e-05, + "loss": 4.2355, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439178295071356e-05, + "loss": 4.2341, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438339700320304e-05, + "loss": 4.2428, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437501105569252e-05, + "loss": 4.2437, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366625108182e-05, + "loss": 4.2349, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435825553947521e-05, + "loss": 4.2322, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434986959196469e-05, + "loss": 4.2346, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434148364445417e-05, + "loss": 4.2297, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433309769694365e-05, + "loss": 4.2497, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432471174943313e-05, + "loss": 4.2352, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431632580192261e-05, + "loss": 4.2334, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430795623321583e-05, + "loss": 4.2167, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429957028570531e-05, + "loss": 4.2321, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429118433819479e-05, + "loss": 4.2252, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428279839068426e-05, + "loss": 4.2368, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427441244317374e-05, + "loss": 4.2307, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426602649566322e-05, + "loss": 4.2304, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42576405481527e-05, + "loss": 4.2237, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.2361, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424088503193539e-05, + "loss": 4.2216, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423249908442487e-05, + "loss": 4.2267, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422411313691435e-05, + "loss": 4.2353, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4215743568207565e-05, + "loss": 4.2145, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207357620697045e-05, + "loss": 4.2159, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198971673186525e-05, + "loss": 4.234, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190585725676005e-05, + "loss": 4.2213, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182199778165485e-05, + "loss": 4.2375, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173813830654965e-05, + "loss": 4.2281, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165427883144445e-05, + "loss": 4.2164, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157041935633925e-05, + "loss": 4.2217, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148672366927134e-05, + "loss": 4.229, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140286419416614e-05, + "loss": 4.228, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4131900471906094e-05, + "loss": 4.217, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123514524395574e-05, + "loss": 4.2322, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411514495568879e-05, + "loss": 4.2047, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410675900817827e-05, + "loss": 4.216, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409837306066775e-05, + "loss": 4.2287, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408998711315723e-05, + "loss": 4.2077, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408161754445044e-05, + "loss": 4.2235, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2178, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406486202823313e-05, + "loss": 4.2015, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405647608072261e-05, + "loss": 4.2134, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404809013321209e-05, + "loss": 4.2307, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403970418570157e-05, + "loss": 4.215, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403131823819105e-05, + "loss": 4.2108, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402293229068053e-05, + "loss": 4.2067, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401454634317001e-05, + "loss": 4.2138, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400617677446322e-05, + "loss": 4.2229, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977908269527e-05, + "loss": 4.2206, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398940487944218e-05, + "loss": 4.2133, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398101893193166e-05, + "loss": 4.2185, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397263298442114e-05, + "loss": 4.2135, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964247036910616e-05, + "loss": 4.2164, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3955861089400096e-05, + "loss": 4.2143, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394749152069331e-05, + "loss": 4.217, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393910557318279e-05, + "loss": 4.2056, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930719625672265e-05, + "loss": 4.2169, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392235005696548e-05, + "loss": 4.2195, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391396410945496e-05, + "loss": 4.2052, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390557816194444e-05, + "loss": 4.2087, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389719221443392e-05, + "loss": 4.217, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.38888062669234e-05, + "loss": 4.2164, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388042031941288e-05, + "loss": 4.2173, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387203437190236e-05, + "loss": 4.2109, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386364842439184e-05, + "loss": 4.2004, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385527885568505e-05, + "loss": 4.2042, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2131, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383852333946774e-05, + "loss": 4.2212, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383013739195722e-05, + "loss": 4.2229, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.38217514444467e-05, + "loss": 4.2087, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381336549693618e-05, + "loss": 4.2015, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380497954942566e-05, + "loss": 4.2157, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796593601915145e-05, + "loss": 4.2041, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788207654404625e-05, + "loss": 4.2052, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779854464501564e-05, + "loss": 4.2219, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771468516991044e-05, + "loss": 4.2123, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763082569480524e-05, + "loss": 4.2014, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754696621970004e-05, + "loss": 4.2082, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.253242492675781, + "eval_runtime": 538.6642, + "eval_samples_per_second": 708.402, + "eval_steps_per_second": 22.138, + "step": 381595 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746310674459483e-05, + "loss": 4.2161, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737924726948963e-05, + "loss": 4.2182, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729538779438443e-05, + "loss": 4.2008, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372115283192792e-05, + "loss": 4.2007, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371278326322113e-05, + "loss": 4.2085, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370439731571061e-05, + "loss": 4.198, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.36960113682001e-05, + "loss": 4.201, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368762542068958e-05, + "loss": 4.1926, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367925585198279e-05, + "loss": 4.2074, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670886283276e-05, + "loss": 4.2168, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366250033576548e-05, + "loss": 4.1991, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365411438825496e-05, + "loss": 4.203, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364572844074444e-05, + "loss": 4.2099, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363734249323392e-05, + "loss": 4.196, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36289565457234e-05, + "loss": 4.2001, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362057059821288e-05, + "loss": 4.1802, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361218465070236e-05, + "loss": 4.1922, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3603815081995566e-05, + "loss": 4.1949, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359544551328878e-05, + "loss": 4.1965, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358705956577826e-05, + "loss": 4.2174, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357867361826774e-05, + "loss": 4.1961, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357028767075722e-05, + "loss": 4.2075, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.1995, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355351577573618e-05, + "loss": 4.2014, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354514620702939e-05, + "loss": 4.1903, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353676025951887e-05, + "loss": 4.1961, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352837431200835e-05, + "loss": 4.1972, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.351998836449783e-05, + "loss": 4.1953, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351160241698731e-05, + "loss": 4.1934, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350323284828052e-05, + "loss": 4.1866, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494846900770006e-05, + "loss": 4.1843, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486460953259486e-05, + "loss": 4.2011, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478075005748966e-05, + "loss": 4.1967, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469689058238446e-05, + "loss": 4.1948, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461303110727926e-05, + "loss": 4.1921, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.34529171632174e-05, + "loss": 4.1958, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444547594510615e-05, + "loss": 4.1998, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436161647000095e-05, + "loss": 4.1969, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427775699489575e-05, + "loss": 4.1965, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341938975197905e-05, + "loss": 4.1878, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341100380446853e-05, + "loss": 4.1954, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340261785695801e-05, + "loss": 4.1797, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394248288251224e-05, + "loss": 4.1949, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385862340740704e-05, + "loss": 4.1919, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377476393230184e-05, + "loss": 4.2014, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369090445719664e-05, + "loss": 4.1895, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360704498209144e-05, + "loss": 4.1826, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352318550698624e-05, + "loss": 4.2011, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343932603188104e-05, + "loss": 4.1788, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335546655677584e-05, + "loss": 4.1834, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332717708697079e-05, + "loss": 4.1855, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331879113946027e-05, + "loss": 4.1924, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331040519194975e-05, + "loss": 4.1774, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330201924443923e-05, + "loss": 4.1942, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329364967573244e-05, + "loss": 4.1797, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328526372822193e-05, + "loss": 4.1791, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327687778071141e-05, + "loss": 4.1918, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326849183320089e-05, + "loss": 4.1775, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326010588569037e-05, + "loss": 4.1924, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325171993817985e-05, + "loss": 4.1936, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324333399066933e-05, + "loss": 4.176, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323494804315881e-05, + "loss": 4.1762, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322657847445202e-05, + "loss": 4.1819, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.32181925269415e-05, + "loss": 4.1954, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320980657943098e-05, + "loss": 4.1782, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320142063192046e-05, + "loss": 4.1822, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193051063213666e-05, + "loss": 4.165, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184665115703146e-05, + "loss": 4.1886, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176279168192626e-05, + "loss": 4.1789, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3167893220682106e-05, + "loss": 4.1754, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159507273171586e-05, + "loss": 4.18, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151121325661066e-05, + "loss": 4.1817, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314275175695428e-05, + "loss": 4.1785, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313436580944376e-05, + "loss": 4.1851, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3125979861933235e-05, + "loss": 4.1886, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117593914422715e-05, + "loss": 4.1785, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109207966912195e-05, + "loss": 4.1747, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100822019401675e-05, + "loss": 4.1825, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092452450694884e-05, + "loss": 4.1745, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084066503184364e-05, + "loss": 4.1901, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075680555673844e-05, + "loss": 4.1784, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306729460816333e-05, + "loss": 4.1831, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305890866065281e-05, + "loss": 4.1647, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305052271314229e-05, + "loss": 4.1761, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304213676563177e-05, + "loss": 4.1672, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303375081812125e-05, + "loss": 4.1836, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302538124941446e-05, + "loss": 4.1758, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301699530190394e-05, + "loss": 4.1764, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300860935439342e-05, + "loss": 4.1739, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.30002234068829e-05, + "loss": 4.1845, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299183745937238e-05, + "loss": 4.161, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298346789066559e-05, + "loss": 4.1711, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297508194315507e-05, + "loss": 4.1825, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966712374448285e-05, + "loss": 4.1612, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958326426937765e-05, + "loss": 4.1642, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949940479427244e-05, + "loss": 4.1803, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941554531916724e-05, + "loss": 4.1641, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933168584406204e-05, + "loss": 4.1868, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924782636895684e-05, + "loss": 4.1725, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916413068188893e-05, + "loss": 4.1636, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290802712067837e-05, + "loss": 4.1662, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289964117316785e-05, + "loss": 4.1781, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289125522565733e-05, + "loss": 4.1774, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288286927814681e-05, + "loss": 4.1623, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287449970944002e-05, + "loss": 4.1773, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.28661137619295e-05, + "loss": 4.1537, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285772781441898e-05, + "loss": 4.1628, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284934186690847e-05, + "loss": 4.1759, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284095591939795e-05, + "loss": 4.1581, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283256997188742e-05, + "loss": 4.1695, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.28241840243769e-05, + "loss": 4.1703, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281579807686638e-05, + "loss": 4.1463, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.28074285081596e-05, + "loss": 4.1629, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279904256064907e-05, + "loss": 4.1746, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279065661313855e-05, + "loss": 4.1686, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278227066562803e-05, + "loss": 4.1557, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277390109692124e-05, + "loss": 4.1558, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276551514941072e-05, + "loss": 4.162, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275712920190021e-05, + "loss": 4.1707, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274874325438969e-05, + "loss": 4.1711, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740373685682896e-05, + "loss": 4.1603, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2731987738172376e-05, + "loss": 4.1653, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2723601790661856e-05, + "loss": 4.1635, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715215843151336e-05, + "loss": 4.1668, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2706846274444545e-05, + "loss": 4.1621, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698460326934025e-05, + "loss": 4.164, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269009075822724e-05, + "loss": 4.1575, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681704810716714e-05, + "loss": 4.1668, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673318863206194e-05, + "loss": 4.1689, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266494929449941e-05, + "loss": 4.1513, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.1592, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264817739947837e-05, + "loss": 4.1706, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263979145196785e-05, + "loss": 4.1666, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263140550445733e-05, + "loss": 4.1655, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623035935750545e-05, + "loss": 4.1612, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261464998824002e-05, + "loss": 4.1478, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26062640407295e-05, + "loss": 4.1538, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259787809321898e-05, + "loss": 4.161, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258949214570846e-05, + "loss": 4.1778, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258110619819794e-05, + "loss": 4.1712, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257272025068742e-05, + "loss": 4.1552, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.25643343031769e-05, + "loss": 4.1577, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255594835566638e-05, + "loss": 4.1613, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254756240815586e-05, + "loss": 4.1581, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253917646064534e-05, + "loss": 4.1561, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530790513134825e-05, + "loss": 4.1739, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522404565624305e-05, + "loss": 4.1629, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514034996917514e-05, + "loss": 4.1503, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2505649049406994e-05, + "loss": 4.1581, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.211868762969971, + "eval_runtime": 528.4656, + "eval_samples_per_second": 722.074, + "eval_steps_per_second": 22.565, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497263101896474e-05, + "loss": 4.1716, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488877154385954e-05, + "loss": 4.1679, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480491206875434e-05, + "loss": 4.155, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247210525936491e-05, + "loss": 4.1541, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246371931185439e-05, + "loss": 4.1576, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245533336434387e-05, + "loss": 4.149, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244694741683335e-05, + "loss": 4.153, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243856146932283e-05, + "loss": 4.1465, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243017552181231e-05, + "loss": 4.1558, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2421789574301793e-05, + "loss": 4.1696, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413420005595e-05, + "loss": 4.1511, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240503405808448e-05, + "loss": 4.1539, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239664811057396e-05, + "loss": 4.1623, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238826216306344e-05, + "loss": 4.1478, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237987621555292e-05, + "loss": 4.1566, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.23714902680424e-05, + "loss": 4.1333, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236310432053188e-05, + "loss": 4.1404, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235471837302136e-05, + "loss": 4.1485, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234633242551084e-05, + "loss": 4.1463, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337946478000315e-05, + "loss": 4.1711, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329560530489795e-05, + "loss": 4.1512, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321174582979275e-05, + "loss": 4.161, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231278863546876e-05, + "loss": 4.1473, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230440268795824e-05, + "loss": 4.1528, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229603311925145e-05, + "loss": 4.1421, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228764717174093e-05, + "loss": 4.1489, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227926122423041e-05, + "loss": 4.1503, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227087527671989e-05, + "loss": 4.1433, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226248932920937e-05, + "loss": 4.1527, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225410338169885e-05, + "loss": 4.1363, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224571743418833e-05, + "loss": 4.1348, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223733148667781e-05, + "loss": 4.1554, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222896191797102e-05, + "loss": 4.15, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.22205759704605e-05, + "loss": 4.1521, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221219002294998e-05, + "loss": 4.1405, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220380407543946e-05, + "loss": 4.153, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195434506732676e-05, + "loss": 4.1494, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187048559222156e-05, + "loss": 4.1545, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178662611711635e-05, + "loss": 4.147, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170276664201115e-05, + "loss": 4.1421, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161907095494325e-05, + "loss": 4.1524, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153521147983804e-05, + "loss": 4.1311, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145135200473284e-05, + "loss": 4.1488, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136749252962764e-05, + "loss": 4.1479, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128363305452244e-05, + "loss": 4.1532, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2119977357941724e-05, + "loss": 4.1469, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111591410431204e-05, + "loss": 4.1354, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210320546292068e-05, + "loss": 4.1548, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209483589421389e-05, + "loss": 4.136, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208644994670338e-05, + "loss": 4.1368, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207806399919286e-05, + "loss": 4.1404, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206967805168233e-05, + "loss": 4.1445, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206130848297555e-05, + "loss": 4.1361, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205292253546503e-05, + "loss": 4.1443, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204455296675824e-05, + "loss": 4.1338, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203616701924772e-05, + "loss": 4.1394, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20277810717372e-05, + "loss": 4.1424, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201939512422668e-05, + "loss": 4.1365, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201100917671615e-05, + "loss": 4.1457, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200262322920563e-05, + "loss": 4.15, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199423728169512e-05, + "loss": 4.1321, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858513341846e-05, + "loss": 4.1316, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197748176547781e-05, + "loss": 4.1347, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196909581796729e-05, + "loss": 4.1535, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196070987045677e-05, + "loss": 4.1363, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195232392294625e-05, + "loss": 4.1363, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943954354239456e-05, + "loss": 4.1249, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935568406728936e-05, + "loss": 4.1408, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927182459218416e-05, + "loss": 4.1355, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918796511707896e-05, + "loss": 4.133, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910426943001105e-05, + "loss": 4.1362, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902040995490585e-05, + "loss": 4.1368, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189365504798007e-05, + "loss": 4.1369, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188526910046955e-05, + "loss": 4.1387, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187688315295903e-05, + "loss": 4.1489, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186851358425224e-05, + "loss": 4.1378, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186012763674172e-05, + "loss": 4.1325, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185175806803493e-05, + "loss": 4.1353, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184337212052441e-05, + "loss": 4.1333, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183498617301389e-05, + "loss": 4.1474, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182660022550337e-05, + "loss": 4.136, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181821427799285e-05, + "loss": 4.1405, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180984470928606e-05, + "loss": 4.1196, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180145876177554e-05, + "loss": 4.1365, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793072814265025e-05, + "loss": 4.1223, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784686866754505e-05, + "loss": 4.1405, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776300919243985e-05, + "loss": 4.135, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767914971733465e-05, + "loss": 4.1339, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759529024222945e-05, + "loss": 4.1292, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751143076712425e-05, + "loss": 4.1387, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1742773508005634e-05, + "loss": 4.1228, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734387560495114e-05, + "loss": 4.1294, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726001612984594e-05, + "loss": 4.1391, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1717615665474074e-05, + "loss": 4.1194, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170924609676728e-05, + "loss": 4.1219, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170086014925676e-05, + "loss": 4.1324, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169247420174624e-05, + "loss": 4.1239, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168408825423572e-05, + "loss": 4.1464, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167571868552894e-05, + "loss": 4.1291, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166733273801842e-05, + "loss": 4.125, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.16589467905079e-05, + "loss": 4.1242, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165056084299738e-05, + "loss": 4.1382, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164219127429059e-05, + "loss": 4.1354, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16338217055838e-05, + "loss": 4.1233, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162543575807328e-05, + "loss": 4.1325, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161704981056276e-05, + "loss": 4.1161, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160866386305224e-05, + "loss": 4.1184, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160027791554172e-05, + "loss": 4.1335, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1591891968031197e-05, + "loss": 4.1217, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583506020520677e-05, + "loss": 4.1271, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575120073010156e-05, + "loss": 4.1291, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156675050430337e-05, + "loss": 4.1062, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155836455679285e-05, + "loss": 4.1214, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154997860928233e-05, + "loss": 4.1395, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154160904057554e-05, + "loss": 4.1295, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153322309306502e-05, + "loss": 4.1115, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15248371455545e-05, + "loss": 4.1173, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151645119804398e-05, + "loss": 4.1217, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150806525053346e-05, + "loss": 4.1284, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499679303022934e-05, + "loss": 4.1313, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491293355512414e-05, + "loss": 4.121, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482907408001894e-05, + "loss": 4.1242, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147453783929511e-05, + "loss": 4.1225, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146615189178459e-05, + "loss": 4.1253, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145776594427407e-05, + "loss": 4.123, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449396375567286e-05, + "loss": 4.1258, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144101042805676e-05, + "loss": 4.1199, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143262448054624e-05, + "loss": 4.1254, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142423853303572e-05, + "loss": 4.126, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.14158525855252e-05, + "loss": 4.1102, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140748301681841e-05, + "loss": 4.1211, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399113448111624e-05, + "loss": 4.1279, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390727500601104e-05, + "loss": 4.1281, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382341553090584e-05, + "loss": 4.1265, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373955605580064e-05, + "loss": 4.1244, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365569658069544e-05, + "loss": 4.1103, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357183710559024e-05, + "loss": 4.1126, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1348797763048504e-05, + "loss": 4.1215, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340411815537984e-05, + "loss": 4.138, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133204224683119e-05, + "loss": 4.1328, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132365629932067e-05, + "loss": 4.1181, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131527035181015e-05, + "loss": 4.1145, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130688440429963e-05, + "loss": 4.1245, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129849845678911e-05, + "loss": 4.119, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129011250927859e-05, + "loss": 4.1157, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128172656176807e-05, + "loss": 4.1346, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127334061425755e-05, + "loss": 4.1245, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126497104555077e-05, + "loss": 4.1113, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125658509804025e-05, + "loss": 4.1228, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.181921482086182, + "eval_runtime": 541.997, + "eval_samples_per_second": 704.046, + "eval_steps_per_second": 22.002, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124819915052973e-05, + "loss": 4.1298, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.123981320301921e-05, + "loss": 4.1306, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123142725550869e-05, + "loss": 4.1205, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122304130799817e-05, + "loss": 4.1153, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121465536048765e-05, + "loss": 4.1149, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120626941297712e-05, + "loss": 4.1182, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.11978834654666e-05, + "loss": 4.1121, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.118949751795608e-05, + "loss": 4.1078, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118111157044556e-05, + "loss": 4.1162, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117272562293504e-05, + "loss": 4.1301, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116433967542452e-05, + "loss": 4.1141, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1155953727914e-05, + "loss": 4.1148, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.1286, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1085, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1208, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.0958, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.101, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.1135, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1075, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.133, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1080496579123056e-05, + "loss": 4.1169, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072127010416266e-05, + "loss": 4.1215, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1063741062905746e-05, + "loss": 4.111, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1055355115395225e-05, + "loss": 4.1186, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1046969167884705e-05, + "loss": 4.1029, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1038583220374185e-05, + "loss": 4.1131, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.1145, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1021811325353145e-05, + "loss": 4.1108, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1013425377842625e-05, + "loss": 4.109, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1049, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0996669861625314e-05, + "loss": 4.0978, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988283914114794e-05, + "loss": 4.1186, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0979897966604274e-05, + "loss": 4.1139, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0971512019093754e-05, + "loss": 4.1132, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096314245038696e-05, + "loss": 4.1086, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095477288168018e-05, + "loss": 4.1157, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094638693416966e-05, + "loss": 4.1117, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093800098665914e-05, + "loss": 4.1123, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.092961503914862e-05, + "loss": 4.1094, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.09212290916381e-05, + "loss": 4.1109, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091284314412758e-05, + "loss": 4.1091, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090445719661706e-05, + "loss": 4.0988, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089607124910654e-05, + "loss": 4.1166, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088770168039975e-05, + "loss": 4.1087, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087931573288923e-05, + "loss": 4.1188, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087092978537871e-05, + "loss": 4.1132, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086254383786819e-05, + "loss": 4.0969, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.08541742691614e-05, + "loss": 4.1194, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084578832165088e-05, + "loss": 4.0986, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083740237414036e-05, + "loss": 4.1049, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829016426629844e-05, + "loss": 4.1004, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.0820630479119323e-05, + "loss": 4.1112, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081226091041253e-05, + "loss": 4.1022, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080387496290201e-05, + "loss": 4.1075, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079550539419522e-05, + "loss": 4.1021, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.07871194466847e-05, + "loss": 4.099, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077873349917418e-05, + "loss": 4.1078, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077034755166366e-05, + "loss": 4.1014, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076196160415314e-05, + "loss": 4.1128, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075357565664262e-05, + "loss": 4.1103, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074520608793583e-05, + "loss": 4.102, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073682014042531e-05, + "loss": 4.0911, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.07284341929148e-05, + "loss": 4.102, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072004824540428e-05, + "loss": 4.1161, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071166229789376e-05, + "loss": 4.103, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070327635038324e-05, + "loss": 4.0982, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069489040287272e-05, + "loss": 4.0939, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1052, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678134886655406e-05, + "loss": 4.0971, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0669748939144886e-05, + "loss": 4.104, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0661362991634366e-05, + "loss": 4.1024, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0652977044123846e-05, + "loss": 4.0996, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1033, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.06362051491028e-05, + "loss": 4.1073, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062781920159228e-05, + "loss": 4.1104, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0619433254081766e-05, + "loss": 4.1013, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611063685374975e-05, + "loss": 4.0992, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060269411666819e-05, + "loss": 4.101, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059430816915767e-05, + "loss": 4.1, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0585922221647144e-05, + "loss": 4.1121, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0577536274136624e-05, + "loss": 4.1068, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569150326626104e-05, + "loss": 4.1071, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0560764379115584e-05, + "loss": 4.0873, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0552378431605064e-05, + "loss": 4.099, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0543992484094544e-05, + "loss": 4.0888, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053562291538775e-05, + "loss": 4.1049, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052723696787723e-05, + "loss": 4.1023, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051885102036671e-05, + "loss": 4.0994, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.05104650728562e-05, + "loss": 4.0996, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050209550414941e-05, + "loss": 4.1004, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049370955663889e-05, + "loss": 4.0908, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048532360912837e-05, + "loss": 4.0966, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047693766161785e-05, + "loss": 4.1046, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046855171410733e-05, + "loss": 4.0887, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.0884, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045179619789002e-05, + "loss": 4.0937, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.04434102503795e-05, + "loss": 4.0957, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043502430286898e-05, + "loss": 4.112, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.0928, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.0418268786651666e-05, + "loss": 4.0944, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.040988283914115e-05, + "loss": 4.0891, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040149689163063e-05, + "loss": 4.1064, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039311094412011e-05, + "loss": 4.0975, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038475775421705e-05, + "loss": 4.0907, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037637180670653e-05, + "loss": 4.1006, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036798585919601e-05, + "loss": 4.0812, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.035959991168549e-05, + "loss": 4.0817, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035121396417497e-05, + "loss": 4.1048, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034284439546818e-05, + "loss": 4.0884, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033445844795766e-05, + "loss": 4.0963, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032607250044714e-05, + "loss": 4.0933, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031768655293662e-05, + "loss": 4.0696, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030930060542611e-05, + "loss": 4.0914, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030091465791559e-05, + "loss": 4.105, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029252871040507e-05, + "loss": 4.0955, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284142762894547e-05, + "loss": 4.0834, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0275773194187756e-05, + "loss": 4.0832, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0267387246677236e-05, + "loss": 4.0845, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259001299166716e-05, + "loss": 4.0969, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0250631730459925e-05, + "loss": 4.0985, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242245782949405e-05, + "loss": 4.0895, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0233859835438885e-05, + "loss": 4.089, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0225473887928365e-05, + "loss": 4.0958, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217087940417845e-05, + "loss": 4.0919, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0208701992907324e-05, + "loss": 4.0866, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200316045396804e-05, + "loss": 4.0969, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0191930097886284e-05, + "loss": 4.0872, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.01835605291795e-05, + "loss": 4.088, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017519096047271e-05, + "loss": 4.1022, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016680501296219e-05, + "loss": 4.0746, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015841906545167e-05, + "loss": 4.0891, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015003311794115e-05, + "loss": 4.0975, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014164717043063e-05, + "loss": 4.0942, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.01332612229201e-05, + "loss": 4.093, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012487527540958e-05, + "loss": 4.0933, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.01165057067028e-05, + "loss": 4.0802, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010811975919228e-05, + "loss": 4.0787, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.009973381168176e-05, + "loss": 4.0929, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009134786417124e-05, + "loss": 4.0982, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008296191666072e-05, + "loss": 4.1038, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.00745759691502e-05, + "loss": 4.0855, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006619002163968e-05, + "loss": 4.0822, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005780407412916e-05, + "loss": 4.0952, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.004943450542237e-05, + "loss": 4.0845, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004104855791185e-05, + "loss": 4.0891, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003266261040133e-05, + "loss": 4.0965, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002427666289081e-05, + "loss": 4.0967, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0015907094184016e-05, + "loss": 4.0791, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0007521146673496e-05, + "loss": 4.0934, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 4.157905101776123, + "eval_runtime": 555.1002, + "eval_samples_per_second": 687.427, + "eval_steps_per_second": 21.483, + "step": 610552 + }, + { + "epoch": 1.0, + "learning_rate": 3.999913519916298e-05, + "loss": 4.0883, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999074925165246e-05, + "loss": 4.1015, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.99823960617494e-05, + "loss": 4.0871, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997401011423888e-05, + "loss": 4.0871, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996562416672836e-05, + "loss": 4.0809, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995723821921784e-05, + "loss": 4.0878, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994885227170732e-05, + "loss": 4.0865, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.99404663241968e-05, + "loss": 4.071, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993208037668628e-05, + "loss": 4.0846, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992369442917576e-05, + "loss": 4.0997, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991532486046897e-05, + "loss": 4.083, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990693891295845e-05, + "loss": 4.0824, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989855296544793e-05, + "loss": 4.0963, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.9890167017937416e-05, + "loss": 4.0774, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.9881781070426896e-05, + "loss": 4.0872, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.9873395122916376e-05, + "loss": 4.0674, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9865025554209585e-05, + "loss": 4.0684, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9856639606699065e-05, + "loss": 4.085, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.9848253659188545e-05, + "loss": 4.075, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.9839867711678025e-05, + "loss": 4.1014, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9831481764167505e-05, + "loss": 4.0868, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823095816656985e-05, + "loss": 4.0896, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981470986914646e-05, + "loss": 4.0804, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980632392163594e-05, + "loss": 4.0886, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979793797412542e-05, + "loss": 4.0741, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9789568405418634e-05, + "loss": 4.0805, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781182457908114e-05, + "loss": 4.0768, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9772796510397594e-05, + "loss": 4.0823, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976442694169081e-05, + "loss": 4.0823, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975604099418029e-05, + "loss": 4.0702, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974765504666976e-05, + "loss": 4.0693, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973926909915924e-05, + "loss": 4.0831, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973088315164872e-05, + "loss": 4.0847, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.97224972041382e-05, + "loss": 4.08, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971411125662768e-05, + "loss": 4.0785, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970572530911716e-05, + "loss": 4.0846, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969735574041037e-05, + "loss": 4.0818, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968896979289985e-05, + "loss": 4.0829, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968058384538934e-05, + "loss": 4.0789, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967219789787882e-05, + "loss": 4.0781, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966382832917203e-05, + "loss": 4.0814, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965544238166151e-05, + "loss": 4.0677, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964705643415099e-05, + "loss": 4.0806, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9638686865444197e-05, + "loss": 4.0855, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.9630317296737406e-05, + "loss": 4.0833, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9621931349226886e-05, + "loss": 4.0848, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9613545401716366e-05, + "loss": 4.0618, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605159454205845e-05, + "loss": 4.092, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9596773506695325e-05, + "loss": 4.0685, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9588387559184805e-05, + "loss": 4.0752, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958000161167429e-05, + "loss": 4.0723, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957161566416377e-05, + "loss": 4.0756, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956322971665325e-05, + "loss": 4.0796, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955484376914273e-05, + "loss": 4.0694, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954645782163221e-05, + "loss": 4.0754, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953807187412169e-05, + "loss": 4.0663, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.952968592661117e-05, + "loss": 4.0805, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952131635790438e-05, + "loss": 4.0701, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951293041039386e-05, + "loss": 4.0842, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950454446288334e-05, + "loss": 4.0761, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949615851537282e-05, + "loss": 4.0732, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.0653, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.9479419377959246e-05, + "loss": 4.0745, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.9471033430448726e-05, + "loss": 4.0804, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.0749, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.9454261535427686e-05, + "loss": 4.0713, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9445908345524624e-05, + "loss": 4.0647, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9437522398014104e-05, + "loss": 4.0721, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429136450503584e-05, + "loss": 4.0679, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9420750502993064e-05, + "loss": 4.0729, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9412364555482544e-05, + "loss": 4.0687, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.9403978607972024e-05, + "loss": 4.0703, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.9395592660461504e-05, + "loss": 4.0744, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.081, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.9378820765440464e-05, + "loss": 4.0756, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.9370434817929943e-05, + "loss": 4.0704, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.9362048870419423e-05, + "loss": 4.0721, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.9353662922908903e-05, + "loss": 4.0721, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934529335420212e-05, + "loss": 4.0666, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933690740669159e-05, + "loss": 4.0803, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932852145918107e-05, + "loss": 4.0779, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932013551167055e-05, + "loss": 4.0775, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.93117823217675e-05, + "loss": 4.0582, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930339637425698e-05, + "loss": 4.0678, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929501042674646e-05, + "loss": 4.0585, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928662447923594e-05, + "loss": 4.0797, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927823853172542e-05, + "loss": 4.0744, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.92698525842149e-05, + "loss": 4.0668, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926146663670438e-05, + "loss": 4.0696, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925308068919386e-05, + "loss": 4.0728, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924469474168334e-05, + "loss": 4.063, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.9236325172976546e-05, + "loss": 4.0649, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.9227939225466026e-05, + "loss": 4.0738, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9219553277955506e-05, + "loss": 4.0601, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211167330444986e-05, + "loss": 4.0637, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9202797761738195e-05, + "loss": 4.0621, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.9194411814227675e-05, + "loss": 4.0688, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.9186025866717155e-05, + "loss": 4.0798, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9177639919206635e-05, + "loss": 4.0649, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916927035049985e-05, + "loss": 4.0666, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916090078179307e-05, + "loss": 4.0631, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9152531213086276e-05, + "loss": 4.0742, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9144145265575756e-05, + "loss": 4.07, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9135759318065236e-05, + "loss": 4.063, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9127373370554716e-05, + "loss": 4.0711, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911898742304419e-05, + "loss": 4.0512, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911060147553367e-05, + "loss": 4.0556, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910221552802315e-05, + "loss": 4.0751, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909382958051263e-05, + "loss": 4.0656, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908544363300211e-05, + "loss": 4.06, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907705768549159e-05, + "loss": 4.0659, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906867173798107e-05, + "loss": 4.0443, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060285790470555e-05, + "loss": 4.0653, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9051916221763764e-05, + "loss": 4.0712, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9043530274253244e-05, + "loss": 4.0715, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.9035144326742724e-05, + "loss": 4.0529, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9026774758035933e-05, + "loss": 4.0588, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901838881052541e-05, + "loss": 4.0536, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901000286301489e-05, + "loss": 4.0675, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900161691550437e-05, + "loss": 4.0688, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899323096799385e-05, + "loss": 4.0623, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898484502048333e-05, + "loss": 4.0608, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897647545177654e-05, + "loss": 4.0673, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896808950426602e-05, + "loss": 4.0642, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.895970355675551e-05, + "loss": 4.0607, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895133398804872e-05, + "loss": 4.0626, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.89429480405382e-05, + "loss": 4.0611, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893456209302768e-05, + "loss": 4.0621, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892617614551716e-05, + "loss": 4.0687, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891779019800664e-05, + "loss": 4.0517, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.890940425049612e-05, + "loss": 4.0579, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.89010183029856e-05, + "loss": 4.0703, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889263235547508e-05, + "loss": 4.0625, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888424640796455e-05, + "loss": 4.0665, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887587683925777e-05, + "loss": 4.066, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886749089174725e-05, + "loss": 4.0573, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885910494423673e-05, + "loss": 4.0515, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885071899672621e-05, + "loss": 4.0612, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884233304921569e-05, + "loss": 4.0743, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8833947101705167e-05, + "loss": 4.0745, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.8825561154194647e-05, + "loss": 4.0563, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.8817191585487856e-05, + "loss": 4.0581, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.8808805637977336e-05, + "loss": 4.0631, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.8800419690466816e-05, + "loss": 4.0596, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.8792033742956296e-05, + "loss": 4.0634, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0679, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.8775261847935255e-05, + "loss": 4.0721, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.8766875900424735e-05, + "loss": 4.0536, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.8758489952914215e-05, + "loss": 4.0643, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 4.138033866882324, + "eval_runtime": 554.944, + "eval_samples_per_second": 687.621, + "eval_steps_per_second": 21.489, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875012038420743e-05, + "loss": 4.0694, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874173443669691e-05, + "loss": 4.0733, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873334848918639e-05, + "loss": 4.0623, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872496254167587e-05, + "loss": 4.0567, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871657659416535e-05, + "loss": 4.0562, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870819064665483e-05, + "loss": 4.0594, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.869980469914431e-05, + "loss": 4.0597, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869141875163379e-05, + "loss": 4.0467, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683032804123264e-05, + "loss": 4.0561, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8674646856612744e-05, + "loss": 4.0722, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666260909102224e-05, + "loss": 4.0553, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8657874961591704e-05, + "loss": 4.0533, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8649489014081184e-05, + "loss": 4.0705, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641103066570664e-05, + "loss": 4.0498, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8632717119060144e-05, + "loss": 4.0593, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8624331171549624e-05, + "loss": 4.0418, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861594522403911e-05, + "loss": 4.0417, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860755927652859e-05, + "loss": 4.0576, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859917332901807e-05, + "loss": 4.0493, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859078738150755e-05, + "loss": 4.0728, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858243419160449e-05, + "loss": 4.0582, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857404824409397e-05, + "loss": 4.0694, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856566229658345e-05, + "loss": 4.0537, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855727634907293e-05, + "loss": 4.059, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854889040156241e-05, + "loss": 4.0469, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854050445405189e-05, + "loss": 4.0579, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853211850654137e-05, + "loss": 4.0516, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852373255903085e-05, + "loss": 4.0567, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8515362990324064e-05, + "loss": 4.054, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8506977042813544e-05, + "loss": 4.0457, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849860747410675e-05, + "loss": 4.042, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849022152659623e-05, + "loss": 4.0606, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848183557908571e-05, + "loss": 4.0558, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847344963157519e-05, + "loss": 4.0556, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846506368406467e-05, + "loss": 4.0528, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845667773655415e-05, + "loss": 4.0588, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8448291789043626e-05, + "loss": 4.0517, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8439905841533106e-05, + "loss": 4.0564, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843153627282632e-05, + "loss": 4.0572, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842316670411953e-05, + "loss": 4.0535, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841478075660902e-05, + "loss": 4.0536, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.84063948090985e-05, + "loss": 4.0486, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839800886158798e-05, + "loss": 4.0499, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.838962291407745e-05, + "loss": 4.0617, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838125334537067e-05, + "loss": 4.0583, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837286739786015e-05, + "loss": 4.0592, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836448145034963e-05, + "loss": 4.0394, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.83560955028391e-05, + "loss": 4.0641, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834770955532858e-05, + "loss": 4.0467, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833932360781806e-05, + "loss": 4.0484, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833093766030754e-05, + "loss": 4.0485, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832255171279702e-05, + "loss": 4.0459, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.83141657652865e-05, + "loss": 4.0571, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8305796196579716e-05, + "loss": 4.0445, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8297410249069195e-05, + "loss": 4.0528, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289024301558675e-05, + "loss": 4.036, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8280638354048155e-05, + "loss": 4.0546, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8272252406537635e-05, + "loss": 4.0431, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8263882837830844e-05, + "loss": 4.0602, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8255496890320324e-05, + "loss": 4.0551, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8247110942809804e-05, + "loss": 4.0468, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8238724995299284e-05, + "loss": 4.041, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.8230339047788764e-05, + "loss": 4.0463, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822196947908197e-05, + "loss": 4.05, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821358353157145e-05, + "loss": 4.0526, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820519758406093e-05, + "loss": 4.0478, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819682801535415e-05, + "loss": 4.0404, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818844206784363e-05, + "loss": 4.047, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818005612033311e-05, + "loss": 4.0418, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817167017282259e-05, + "loss": 4.0482, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816328422531207e-05, + "loss": 4.0426, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815489827780155e-05, + "loss": 4.042, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814651233029103e-05, + "loss": 4.0538, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813812638278051e-05, + "loss": 4.0565, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.812975681407372e-05, + "loss": 4.0497, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812138724536693e-05, + "loss": 4.0476, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811300129785641e-05, + "loss": 4.0423, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810461535034589e-05, + "loss": 4.05, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096229402835374e-05, + "loss": 4.0439, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8087843455324854e-05, + "loss": 4.0531, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8079457507814334e-05, + "loss": 4.0564, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071071560303814e-05, + "loss": 4.0546, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806268561279329e-05, + "loss": 4.0381, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.80543160440865e-05, + "loss": 4.0396, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804593009657598e-05, + "loss": 4.0312, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803754414906546e-05, + "loss": 4.0566, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029158201554936e-05, + "loss": 4.0483, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802078863284815e-05, + "loss": 4.0472, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801240268533763e-05, + "loss": 4.0463, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800401673782711e-05, + "loss": 4.0469, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799563079031659e-05, + "loss": 4.0377, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798724484280607e-05, + "loss": 4.0407, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797887527409929e-05, + "loss": 4.0526, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797048932658876e-05, + "loss": 4.0333, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796210337907824e-05, + "loss": 4.0387, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7953733810371456e-05, + "loss": 4.0385, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7945347862860936e-05, + "loss": 4.045, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793696191535041e-05, + "loss": 4.0539, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792857596783989e-05, + "loss": 4.0422, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792019002032937e-05, + "loss": 4.0468, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791180407281885e-05, + "loss": 4.0398, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790341812530833e-05, + "loss": 4.0497, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789503217779781e-05, + "loss": 4.0448, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7886662609091025e-05, + "loss": 4.0396, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7878293040384234e-05, + "loss": 4.0435, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7869907092873714e-05, + "loss": 4.0308, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7861521145363194e-05, + "loss": 4.0332, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853135197852674e-05, + "loss": 4.0474, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784476562914588e-05, + "loss": 4.0418, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783637968163536e-05, + "loss": 4.0348, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782799373412484e-05, + "loss": 4.0438, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.781960778661432e-05, + "loss": 4.0223, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.78112218391038e-05, + "loss": 4.0384, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780283589159328e-05, + "loss": 4.0473, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779444994408276e-05, + "loss": 4.047, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778606399657225e-05, + "loss": 4.0335, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777769442786546e-05, + "loss": 4.0331, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.776930848035494e-05, + "loss": 4.0296, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776092253284442e-05, + "loss": 4.0407, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775255296413763e-05, + "loss": 4.0463, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774416701662711e-05, + "loss": 4.0437, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773578106911659e-05, + "loss": 4.0323, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772739512160607e-05, + "loss": 4.0488, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771902555289928e-05, + "loss": 4.0368, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7710639605388757e-05, + "loss": 4.039, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770227003668197e-05, + "loss": 4.0353, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769388408917145e-05, + "loss": 4.0425, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768549814166093e-05, + "loss": 4.0375, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767711219415041e-05, + "loss": 4.044, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766872624663989e-05, + "loss": 4.0314, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766034029912937e-05, + "loss": 4.0364, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765195435161885e-05, + "loss": 4.0492, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764356840410833e-05, + "loss": 4.0393, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763518245659781e-05, + "loss": 4.0415, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762679650908729e-05, + "loss": 4.0476, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761841056157677e-05, + "loss": 4.0305, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610024614066245e-05, + "loss": 4.0323, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7601638666555725e-05, + "loss": 4.0369, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7593252719045205e-05, + "loss": 4.0447, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758488315033842e-05, + "loss": 4.0559, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.75764972028279e-05, + "loss": 4.0351, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756812763412112e-05, + "loss": 4.0382, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.75597416866106e-05, + "loss": 4.0371, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755135573910007e-05, + "loss": 4.0368, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754296979158955e-05, + "loss": 4.0404, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7534600222882766e-05, + "loss": 4.0437, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752621427537224e-05, + "loss": 4.0458, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751782832786172e-05, + "loss": 4.031, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.75094423803512e-05, + "loss": 4.0416, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.122170925140381, + "eval_runtime": 543.8826, + "eval_samples_per_second": 701.605, + "eval_steps_per_second": 21.926, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.750105643284068e-05, + "loss": 4.041, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749267048533016e-05, + "loss": 4.0473, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748428453781964e-05, + "loss": 4.0415, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747589859030912e-05, + "loss": 4.0312, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7467512642798605e-05, + "loss": 4.0373, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459143074091815e-05, + "loss": 4.0337, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7450757126581294e-05, + "loss": 4.0405, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.7442371179070774e-05, + "loss": 4.0185, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.7433985231560254e-05, + "loss": 4.0337, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.7425599284049734e-05, + "loss": 4.0474, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.7417229715342943e-05, + "loss": 4.0347, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.7408843767832423e-05, + "loss": 4.0341, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.74004578203219e-05, + "loss": 4.0446, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739207187281138e-05, + "loss": 4.0259, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738368592530086e-05, + "loss": 4.0367, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737529997779034e-05, + "loss": 4.0184, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736691403027982e-05, + "loss": 4.0167, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735854446157304e-05, + "loss": 4.0387, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735015851406252e-05, + "loss": 4.0273, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7341772566552e-05, + "loss": 4.0516, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733338661904148e-05, + "loss": 4.0326, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732501705033469e-05, + "loss": 4.0463, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731663110282417e-05, + "loss": 4.0342, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730824515531365e-05, + "loss": 4.0354, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.729985920780313e-05, + "loss": 4.0232, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.72914732602926e-05, + "loss": 4.037, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728308731278208e-05, + "loss": 4.0297, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727470136527156e-05, + "loss": 4.0323, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726631541776104e-05, + "loss": 4.0291, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725794584905426e-05, + "loss": 4.0285, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.724955990154374e-05, + "loss": 4.0163, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724117395403322e-05, + "loss": 4.0381, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723280438532643e-05, + "loss": 4.0329, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7224418437815906e-05, + "loss": 4.0316, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216032490305386e-05, + "loss": 4.0321, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.72076629215986e-05, + "loss": 4.0342, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7199276974088075e-05, + "loss": 4.0337, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7190891026577555e-05, + "loss": 4.0339, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7182505079067035e-05, + "loss": 4.0318, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7174119131556515e-05, + "loss": 4.0317, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7165733184045995e-05, + "loss": 4.0311, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715734723653548e-05, + "loss": 4.028, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714896128902496e-05, + "loss": 4.0258, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714057534151444e-05, + "loss": 4.0363, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713218939400392e-05, + "loss": 4.0323, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.71238034464934e-05, + "loss": 4.0372, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711541749898288e-05, + "loss": 4.0183, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710706430907982e-05, + "loss": 4.0422, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.70986783615693e-05, + "loss": 4.0294, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709029241405878e-05, + "loss": 4.0228, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708190646654826e-05, + "loss": 4.027, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707352051903774e-05, + "loss": 4.0273, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706513457152722e-05, + "loss": 4.0327, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.70567486240167e-05, + "loss": 4.0224, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704836267650618e-05, + "loss": 4.0298, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.7039993107799395e-05, + "loss": 4.0126, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.7031607160288875e-05, + "loss": 4.0355, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7023221212778355e-05, + "loss": 4.0197, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7014835265267835e-05, + "loss": 4.0334, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7006465696561044e-05, + "loss": 4.0329, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6998079749050524e-05, + "loss": 4.0264, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6989693801540004e-05, + "loss": 4.0217, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6981307854029484e-05, + "loss": 4.021, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697293828532269e-05, + "loss": 4.0243, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696455233781217e-05, + "loss": 4.0337, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695616639030165e-05, + "loss": 4.0272, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694778044279113e-05, + "loss": 4.0173, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.693941087408435e-05, + "loss": 4.0233, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693104130537756e-05, + "loss": 4.0227, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692265535786704e-05, + "loss": 4.0267, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691426941035652e-05, + "loss": 4.0226, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6905883462846e-05, + "loss": 4.0247, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689749751533548e-05, + "loss": 4.0253, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688911156782496e-05, + "loss": 4.0361, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688072562031444e-05, + "loss": 4.0273, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687233967280391e-05, + "loss": 4.0229, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6863970104097126e-05, + "loss": 4.0242, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6855584156586606e-05, + "loss": 4.0293, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847198209076086e-05, + "loss": 4.0259, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6838812261565566e-05, + "loss": 4.0285, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6830426314055046e-05, + "loss": 4.0346, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6822040366544526e-05, + "loss": 4.0346, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6813654419034006e-05, + "loss": 4.019, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6805268471523486e-05, + "loss": 4.0133, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.6796898902816695e-05, + "loss": 4.0097, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.6788512955306175e-05, + "loss": 4.0334, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.6780127007795655e-05, + "loss": 4.0251, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.6771741060285135e-05, + "loss": 4.0274, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6763355112774615e-05, + "loss": 4.0232, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6754985544067824e-05, + "loss": 4.0265, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.6746599596557304e-05, + "loss": 4.0174, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673821364904679e-05, + "loss": 4.0197, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672984408034e-05, + "loss": 4.0315, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672145813282948e-05, + "loss": 4.0117, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671307218531896e-05, + "loss": 4.0167, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670468623780844e-05, + "loss": 4.016, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669630029029792e-05, + "loss": 4.0278, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.66879143427874e-05, + "loss": 4.0261, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.667952839527688e-05, + "loss": 4.0277, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667114244776636e-05, + "loss": 4.0233, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666275650025584e-05, + "loss": 4.018, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665438693154905e-05, + "loss": 4.0287, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664600098403853e-05, + "loss": 4.024, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663761503652801e-05, + "loss": 4.0227, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629245467821224e-05, + "loss": 4.0221, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6620859520310704e-05, + "loss": 4.0063, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6612473572800184e-05, + "loss": 4.013, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604087625289664e-05, + "loss": 4.0273, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6595701677779144e-05, + "loss": 4.0227, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6587315730268624e-05, + "loss": 4.0131, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657894616156183e-05, + "loss": 4.0244, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657056021405131e-05, + "loss": 4.0027, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656217426654079e-05, + "loss": 4.016, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655378831903027e-05, + "loss": 4.0255, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6545402371519746e-05, + "loss": 4.0274, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6537016424009226e-05, + "loss": 4.0132, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652863047649871e-05, + "loss": 4.0142, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652024452898819e-05, + "loss": 4.0061, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651185858147767e-05, + "loss": 4.0193, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650348901277088e-05, + "loss": 4.0261, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649510306526036e-05, + "loss": 4.0203, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648671711774984e-05, + "loss": 4.0118, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647833117023932e-05, + "loss": 4.0249, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.646996160153253e-05, + "loss": 4.0211, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646157565402201e-05, + "loss": 4.0167, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645318970651149e-05, + "loss": 4.0108, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644480375900097e-05, + "loss": 4.0275, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643641781149045e-05, + "loss": 4.0163, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642804824278366e-05, + "loss": 4.0233, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.641966229527315e-05, + "loss": 4.0112, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6411292726566356e-05, + "loss": 4.0128, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6402906779055836e-05, + "loss": 4.0247, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6394520831545316e-05, + "loss": 4.0201, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.6386134884034796e-05, + "loss": 4.021, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.6377748936524276e-05, + "loss": 4.0258, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.6369362989013756e-05, + "loss": 4.0134, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.6360993420306965e-05, + "loss": 4.0078, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6352607472796445e-05, + "loss": 4.0173, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6344221525285925e-05, + "loss": 4.0231, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6335835577775405e-05, + "loss": 4.0361, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6327449630264884e-05, + "loss": 4.0148, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319063682754364e-05, + "loss": 4.0172, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6310677735243844e-05, + "loss": 4.0167, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630229178773333e-05, + "loss": 4.0162, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629392221902654e-05, + "loss": 4.0194, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628555265031975e-05, + "loss": 4.0213, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627716670280923e-05, + "loss": 4.0286, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626878075529871e-05, + "loss": 4.0089, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626039480778819e-05, + "loss": 4.023, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.108505725860596, + "eval_runtime": 544.1634, + "eval_samples_per_second": 701.243, + "eval_steps_per_second": 21.914, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.625200886027767e-05, + "loss": 4.034, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624362291276715e-05, + "loss": 4.0272, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623523696525663e-05, + "loss": 4.0207, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622685101774611e-05, + "loss": 4.0109, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621846507023558e-05, + "loss": 4.0196, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621007912272507e-05, + "loss": 4.0136, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620169317521455e-05, + "loss": 4.019, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619330722770403e-05, + "loss": 4.0005, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618492128019351e-05, + "loss": 4.016, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617653533268299e-05, + "loss": 4.025, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.61681657639762e-05, + "loss": 4.012, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.615977981646568e-05, + "loss": 4.015, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615139386895516e-05, + "loss": 4.0279, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614300792144464e-05, + "loss": 4.0088, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613462197393412e-05, + "loss": 4.0133, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.61262360264236e-05, + "loss": 4.001, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611785007891308e-05, + "loss": 3.9928, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.610946413140256e-05, + "loss": 4.0206, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610107818389204e-05, + "loss": 4.0052, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609269223638152e-05, + "loss": 4.0305, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6084306288871e-05, + "loss": 4.0157, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607592034136048e-05, + "loss": 4.0249, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606753439384996e-05, + "loss": 4.0115, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605914844633944e-05, + "loss": 4.0213, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605076249882892e-05, + "loss": 3.9982, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.60423765513184e-05, + "loss": 4.0186, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034006982611606e-05, + "loss": 4.0104, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6025621035101086e-05, + "loss": 4.0136, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6017235087590566e-05, + "loss": 4.0071, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6008849140080046e-05, + "loss": 4.0095, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6000479571373255e-05, + "loss": 3.997, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992093623862735e-05, + "loss": 4.0162, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5983707676352215e-05, + "loss": 4.0159, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.59753217288417e-05, + "loss": 4.0118, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596695216013491e-05, + "loss": 4.0129, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595856621262439e-05, + "loss": 4.0205, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595018026511387e-05, + "loss": 4.009, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594181069640708e-05, + "loss": 4.0151, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593342474889656e-05, + "loss": 4.0124, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592503880138604e-05, + "loss": 4.0147, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591665285387552e-05, + "loss": 4.0101, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908266906365e-05, + "loss": 4.0031, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.589988095885448e-05, + "loss": 4.0083, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589151139014769e-05, + "loss": 4.0174, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588312544263717e-05, + "loss": 4.0162, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5874739495126656e-05, + "loss": 4.0166, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5866353547616136e-05, + "loss": 4.0042, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5857967600105615e-05, + "loss": 4.0237, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5849581652595095e-05, + "loss": 4.008, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5841195705084575e-05, + "loss": 4.0007, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5832842515181514e-05, + "loss": 4.0014, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5824456567670994e-05, + "loss": 4.0112, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5816070620160474e-05, + "loss": 4.0147, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5807684672649953e-05, + "loss": 4.0022, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5799298725139433e-05, + "loss": 4.0128, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579091277762891e-05, + "loss": 3.9931, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578252683011839e-05, + "loss": 4.0167, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577414088260787e-05, + "loss": 4.0067, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576575493509735e-05, + "loss": 4.013, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575738536639057e-05, + "loss": 4.0089, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574899941888005e-05, + "loss": 4.0082, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574061347136953e-05, + "loss": 4.0048, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573222752385901e-05, + "loss": 4.0028, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572384157634848e-05, + "loss": 4.0052, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571545562883796e-05, + "loss": 4.0144, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570706968132744e-05, + "loss": 4.0093, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569870011262066e-05, + "loss": 3.9938, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569031416511013e-05, + "loss": 4.0075, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568192821759961e-05, + "loss": 4.0033, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567354227008909e-05, + "loss": 4.0103, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566515632257858e-05, + "loss": 3.9998, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565677037506806e-05, + "loss": 4.011, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564838442755754e-05, + "loss": 4.005, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.563999848004702e-05, + "loss": 4.0124, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.56316125325365e-05, + "loss": 4.012, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562324296382971e-05, + "loss": 4.0076, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561485701631919e-05, + "loss": 4.0025, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5606471068808667e-05, + "loss": 4.0081, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5598101500101876e-05, + "loss": 4.0044, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5589715552591356e-05, + "loss": 4.0171, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5581329605080836e-05, + "loss": 4.0139, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.5572943657570316e-05, + "loss": 4.0204, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556457408886353e-05, + "loss": 3.9996, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555618814135301e-05, + "loss": 3.9965, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554780219384249e-05, + "loss": 3.991, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553941624633197e-05, + "loss": 4.0141, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553103029882145e-05, + "loss": 4.0058, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552264435131093e-05, + "loss": 4.0072, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551427478260414e-05, + "loss": 4.0074, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550588883509362e-05, + "loss": 4.0074, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.54975028875831e-05, + "loss": 3.9948, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548911694007258e-05, + "loss": 4.0055, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548073099256206e-05, + "loss": 4.01, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547234504505154e-05, + "loss": 3.9946, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546395909754102e-05, + "loss": 3.9934, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.54555731500305e-05, + "loss": 4.0002, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544720358132371e-05, + "loss": 4.0098, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5438817633813196e-05, + "loss": 4.0077, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543043168630267e-05, + "loss": 4.0096, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422062117595885e-05, + "loss": 4.0086, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5413676170085365e-05, + "loss": 3.9955, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5405290222574845e-05, + "loss": 4.012, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539690427506432e-05, + "loss": 4.0074, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.53885183275538e-05, + "loss": 4.0015, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5380148758847014e-05, + "loss": 4.0004, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5371762811336494e-05, + "loss": 3.9957, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536337686382597e-05, + "loss": 3.997, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535499091631545e-05, + "loss": 4.0026, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5346604968804934e-05, + "loss": 4.0058, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.5338219021294414e-05, + "loss": 3.9987, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5329833073783894e-05, + "loss": 4.0042, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5321447126273373e-05, + "loss": 3.9881, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313061178762853e-05, + "loss": 3.9945, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530469161005606e-05, + "loss": 4.0089, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529630566254554e-05, + "loss": 4.0087, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528791971503502e-05, + "loss": 3.9946, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.52795337675245e-05, + "loss": 3.996, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527116419881771e-05, + "loss": 3.99, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526277825130719e-05, + "loss": 3.9998, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525439230379667e-05, + "loss": 4.0061, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524600635628615e-05, + "loss": 4.002, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523762040877563e-05, + "loss": 3.9941, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522925084006885e-05, + "loss": 4.0082, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522086489255833e-05, + "loss": 4.0014, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5212495323851536e-05, + "loss": 4.0053, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5204109376341016e-05, + "loss": 3.9922, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.5195723428830496e-05, + "loss": 4.0081, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.5187353860123705e-05, + "loss": 3.9964, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.5178967912613185e-05, + "loss": 4.0036, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.5170581965102665e-05, + "loss": 3.9965, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.5162196017592145e-05, + "loss": 3.9967, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.5153810070081625e-05, + "loss": 4.0042, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5145424122571105e-05, + "loss": 4.0077, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137038175060585e-05, + "loss": 4.0003, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512865222755007e-05, + "loss": 4.0067, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512026628003955e-05, + "loss": 3.9931, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511188033252903e-05, + "loss": 3.9933, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5103494385018505e-05, + "loss": 3.9989, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509512481631172e-05, + "loss": 4.0043, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.50867388688012e-05, + "loss": 4.0204, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507835292129068e-05, + "loss": 4.0009, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5069966973780154e-05, + "loss": 4.0009, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5061581026269634e-05, + "loss": 3.9962, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5053195078759114e-05, + "loss": 3.9962, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5044809131248594e-05, + "loss": 4.0034, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5036423183738074e-05, + "loss": 4.0087, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502805361503129e-05, + "loss": 4.0098, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501966766752077e-05, + "loss": 3.9919, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501128172001025e-05, + "loss": 4.004, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.097228050231934, + "eval_runtime": 622.3683, + "eval_samples_per_second": 613.127, + "eval_steps_per_second": 19.161, + "step": 915828 + }, + { + "epoch": 1.0, + "learning_rate": 3.500291215130346e-05, + "loss": 3.9994, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499452620379294e-05, + "loss": 4.0102, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498614025628242e-05, + "loss": 4.0042, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.49777543087719e-05, + "loss": 3.9931, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.496936836126138e-05, + "loss": 4.0019, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496099879255459e-05, + "loss": 3.994, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495261284504407e-05, + "loss": 4.0037, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494422689753355e-05, + "loss": 3.9818, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493584095002303e-05, + "loss": 4.0026, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492745500251251e-05, + "loss": 4.0024, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.491908543380572e-05, + "loss": 3.997, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.49106994862952e-05, + "loss": 3.997, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490231353878468e-05, + "loss": 4.0054, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489392759127416e-05, + "loss": 3.9995, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488554164376364e-05, + "loss": 3.9931, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487715569625312e-05, + "loss": 3.9841, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.48687697487426e-05, + "loss": 3.9766, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486038380123208e-05, + "loss": 3.9997, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485201423252529e-05, + "loss": 3.9907, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484362828501477e-05, + "loss": 4.0105, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483524233750425e-05, + "loss": 4.001, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482687276879746e-05, + "loss": 4.0084, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481848682128694e-05, + "loss": 3.9938, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481010087377643e-05, + "loss": 4.0041, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480171492626591e-05, + "loss": 3.9855, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479332897875539e-05, + "loss": 4.0002, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478494303124487e-05, + "loss": 3.9956, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477655708373434e-05, + "loss": 3.9962, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476817113622382e-05, + "loss": 3.9886, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.4759801567517036e-05, + "loss": 3.9928, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.4751415620006516e-05, + "loss": 3.9824, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4743046051299726e-05, + "loss": 3.9962, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4734660103789205e-05, + "loss": 3.9993, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4726274156278685e-05, + "loss": 3.9973, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4717888208768165e-05, + "loss": 3.9928, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.470951864006138e-05, + "loss": 4.0007, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470113269255086e-05, + "loss": 3.9972, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469274674504034e-05, + "loss": 3.9939, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4684360797529814e-05, + "loss": 3.9983, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4675974850019294e-05, + "loss": 3.9987, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4667588902508774e-05, + "loss": 3.9941, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4659202954998254e-05, + "loss": 3.9875, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4650817007487734e-05, + "loss": 3.9901, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464244743878094e-05, + "loss": 4.0009, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463406149127042e-05, + "loss": 4.0016, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.46256755437599e-05, + "loss": 4.0012, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461730597505312e-05, + "loss": 3.9883, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.46089200275426e-05, + "loss": 4.0082, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460053408003208e-05, + "loss": 3.9915, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459214813252156e-05, + "loss": 3.984, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458376218501104e-05, + "loss": 3.9842, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457537623750052e-05, + "loss": 3.9941, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456700666879373e-05, + "loss": 3.9997, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455862072128321e-05, + "loss": 3.986, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455023477377269e-05, + "loss": 3.9981, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454184882626217e-05, + "loss": 3.9761, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453346287875165e-05, + "loss": 3.9973, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452507693124113e-05, + "loss": 3.992, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451669098373061e-05, + "loss": 4.0013, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450833779382755e-05, + "loss": 3.9888, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.449995184631703e-05, + "loss": 3.9941, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449156589880651e-05, + "loss": 3.9906, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448317995129599e-05, + "loss": 3.9853, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447479400378547e-05, + "loss": 3.9904, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446640805627495e-05, + "loss": 4.0015, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445802210876443e-05, + "loss": 3.9958, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.444963616125391e-05, + "loss": 3.9749, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444125021374339e-05, + "loss": 3.9913, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443286426623287e-05, + "loss": 3.9892, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4424478318722345e-05, + "loss": 3.9901, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4416092371211825e-05, + "loss": 3.9848, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4407706423701305e-05, + "loss": 3.9972, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.439933685499452e-05, + "loss": 3.9888, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4390950907484e-05, + "loss": 3.9957, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438256495997348e-05, + "loss": 3.9953, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437417901246296e-05, + "loss": 3.9946, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436579306495244e-05, + "loss": 3.9916, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435742349624565e-05, + "loss": 3.9893, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4349053927538866e-05, + "loss": 3.9903, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4340667980028346e-05, + "loss": 3.9957, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433228203251782e-05, + "loss": 4.0003, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.43238960850073e-05, + "loss": 3.9977, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4315526516300515e-05, + "loss": 3.9854, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.4307140568789995e-05, + "loss": 3.9825, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4298754621279475e-05, + "loss": 3.9765, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4290368673768955e-05, + "loss": 3.997, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4281982726258435e-05, + "loss": 3.9868, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4273596778747915e-05, + "loss": 3.9986, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4265210831237395e-05, + "loss": 3.9879, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.4256824883726875e-05, + "loss": 3.9897, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4248455315020084e-05, + "loss": 3.9784, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.4240069367509564e-05, + "loss": 3.9929, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4231683419999044e-05, + "loss": 3.9946, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4223297472488524e-05, + "loss": 3.9796, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421492790378173e-05, + "loss": 3.9797, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420654195627121e-05, + "loss": 3.9815, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419815600876069e-05, + "loss": 3.9932, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.418977006125017e-05, + "loss": 3.9917, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418138411373966e-05, + "loss": 3.9971, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417299816622914e-05, + "loss": 3.9926, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416461221871862e-05, + "loss": 3.9792, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.41562262712081e-05, + "loss": 3.9918, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414785670250131e-05, + "loss": 3.989, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.413947075499079e-05, + "loss": 3.9926, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4131101186284e-05, + "loss": 3.9795, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412271523877348e-05, + "loss": 3.9858, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411432929126296e-05, + "loss": 3.9773, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410594334375244e-05, + "loss": 3.9868, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409755739624192e-05, + "loss": 3.9907, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4089187827535126e-05, + "loss": 3.9857, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408080188002461e-05, + "loss": 3.9884, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407241593251409e-05, + "loss": 3.9739, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406402998500357e-05, + "loss": 3.9761, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405564403749305e-05, + "loss": 3.9919, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404725808998253e-05, + "loss": 3.9966, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4038872142472006e-05, + "loss": 3.9748, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.4030486194961486e-05, + "loss": 3.9806, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.4022100247450966e-05, + "loss": 3.9798, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401373067874418e-05, + "loss": 3.9831, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400536111003739e-05, + "loss": 3.9909, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399697516252687e-05, + "loss": 3.9836, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398858921501635e-05, + "loss": 3.9791, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398020326750583e-05, + "loss": 3.9934, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397181731999531e-05, + "loss": 3.9832, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396343137248479e-05, + "loss": 3.9897, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.3955061803778007e-05, + "loss": 3.9768, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394667585626748e-05, + "loss": 3.9894, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3938306287560696e-05, + "loss": 3.9836, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3929920340050176e-05, + "loss": 3.9884, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.3921534392539655e-05, + "loss": 3.9805, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391314844502913e-05, + "loss": 3.977, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390476249751861e-05, + "loss": 3.9884, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389637655000809e-05, + "loss": 3.996, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388799060249757e-05, + "loss": 3.9854, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.387960465498705e-05, + "loss": 3.9907, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.3871218707476535e-05, + "loss": 3.9804, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3862849138769744e-05, + "loss": 3.9741, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3854463191259224e-05, + "loss": 3.9854, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3846077243748704e-05, + "loss": 3.9883, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3837691296238184e-05, + "loss": 4.0066, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3829305348727664e-05, + "loss": 3.9807, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3820919401217144e-05, + "loss": 3.9877, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3812533453706624e-05, + "loss": 3.9788, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3804147506196104e-05, + "loss": 3.9853, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379579431629304e-05, + "loss": 3.9867, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378740836878252e-05, + "loss": 3.9903, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779022421272e-05, + "loss": 3.9976, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377063647376149e-05, + "loss": 3.9765, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376225052625097e-05, + "loss": 3.9818, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 4.087806224822998, + "eval_runtime": 624.7945, + "eval_samples_per_second": 610.746, + "eval_steps_per_second": 19.086, + "step": 992147 + }, + { + "epoch": 0.0, + "learning_rate": 3.375388095754418e-05, + "loss": 4.0005, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374549501003366e-05, + "loss": 3.9953, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373710906252314e-05, + "loss": 3.9924, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372872311501262e-05, + "loss": 3.9766, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.37203371675021e-05, + "loss": 3.988, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371195121999158e-05, + "loss": 3.9839, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370356527248106e-05, + "loss": 3.9836, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369517932497054e-05, + "loss": 3.971, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368679337746002e-05, + "loss": 3.985, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367840742994949e-05, + "loss": 3.9859, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367003786124271e-05, + "loss": 3.9821, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3661651913732187e-05, + "loss": 3.9836, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3653265966221667e-05, + "loss": 3.991, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3644880018711147e-05, + "loss": 3.9809, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3636494071200626e-05, + "loss": 3.981, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3628108123690106e-05, + "loss": 3.971, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3619722176179586e-05, + "loss": 3.9624, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3611336228669066e-05, + "loss": 3.9812, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3602950281158546e-05, + "loss": 3.9791, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3594564333648026e-05, + "loss": 3.9927, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3586178386137506e-05, + "loss": 3.9864, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3577792438626986e-05, + "loss": 3.9892, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3569406491116466e-05, + "loss": 3.9801, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3561020543605946e-05, + "loss": 3.9884, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3552634596095426e-05, + "loss": 3.9703, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3544248648584906e-05, + "loss": 3.9826, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353587907987812e-05, + "loss": 3.9835, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.35274931323676e-05, + "loss": 3.9805, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351910718485708e-05, + "loss": 3.9728, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351073761615029e-05, + "loss": 3.9824, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350235166863977e-05, + "loss": 3.9668, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349396572112925e-05, + "loss": 3.9779, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348557977361873e-05, + "loss": 3.9856, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3477193826108204e-05, + "loss": 3.9816, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3468807878597684e-05, + "loss": 3.9823, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.3460421931087164e-05, + "loss": 3.9807, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345205236238038e-05, + "loss": 3.9828, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344366641486986e-05, + "loss": 3.9817, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343528046735934e-05, + "loss": 3.9766, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342689451984882e-05, + "loss": 3.9874, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.34185085723383e-05, + "loss": 3.9786, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341012262482778e-05, + "loss": 3.968, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340173667731726e-05, + "loss": 3.9819, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339336710861047e-05, + "loss": 3.9824, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338498116109995e-05, + "loss": 3.9861, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337659521358943e-05, + "loss": 3.9827, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336820926607891e-05, + "loss": 3.9749, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.335982331856839e-05, + "loss": 3.9921, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335143737105787e-05, + "loss": 3.9772, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334305142354735e-05, + "loss": 3.9702, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333466547603683e-05, + "loss": 3.9725, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332627952852631e-05, + "loss": 3.9773, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331789358101579e-05, + "loss": 3.9792, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3309524012309004e-05, + "loss": 3.9747, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330115444360221e-05, + "loss": 3.9874, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329276849609169e-05, + "loss": 3.9545, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328438254858117e-05, + "loss": 3.9842, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327599660107065e-05, + "loss": 3.9808, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326761065356013e-05, + "loss": 3.9814, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.325922470604961e-05, + "loss": 3.9824, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325083875853909e-05, + "loss": 3.9755, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242452811028566e-05, + "loss": 3.9757, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323408324232178e-05, + "loss": 3.9696, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322569729481126e-05, + "loss": 3.9736, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321731134730074e-05, + "loss": 3.9879, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320892539979022e-05, + "loss": 3.9834, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320057220988717e-05, + "loss": 3.9625, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319218626237665e-05, + "loss": 3.9732, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318380031486613e-05, + "loss": 3.9781, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317541436735561e-05, + "loss": 3.9728, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3167028419845087e-05, + "loss": 3.9696, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3158642472334567e-05, + "loss": 3.9808, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315025652482404e-05, + "loss": 3.9762, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314187057731352e-05, + "loss": 3.9814, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3133501008606736e-05, + "loss": 3.9846, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3125115061096215e-05, + "loss": 3.9775, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3116729113585695e-05, + "loss": 3.9788, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3108343166075175e-05, + "loss": 3.9719, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.309997359736839e-05, + "loss": 3.9754, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3091587649857864e-05, + "loss": 3.9826, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3083201702347344e-05, + "loss": 3.9864, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3074815754836824e-05, + "loss": 3.9834, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3066429807326304e-05, + "loss": 3.9677, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3058043859815784e-05, + "loss": 3.9722, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3049657912305264e-05, + "loss": 3.9629, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3041271964794744e-05, + "loss": 3.9791, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303290239608795e-05, + "loss": 3.9763, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302451644857743e-05, + "loss": 3.9856, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301613050106691e-05, + "loss": 3.9731, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.30077445535564e-05, + "loss": 3.973, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.299937498484961e-05, + "loss": 3.9688, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299098903733909e-05, + "loss": 3.9774, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298260308982857e-05, + "loss": 3.9785, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297421714231805e-05, + "loss": 3.9688, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296583119480753e-05, + "loss": 3.9612, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295746162610074e-05, + "loss": 3.968, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294907567859022e-05, + "loss": 3.9771, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.29406897310797e-05, + "loss": 3.9759, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293230378356918e-05, + "loss": 3.9829, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292393421486239e-05, + "loss": 3.9756, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291554826735187e-05, + "loss": 3.9686, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.2907162319841354e-05, + "loss": 3.9727, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289879275113456e-05, + "loss": 3.9768, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289040680362404e-05, + "loss": 3.9835, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288203723491725e-05, + "loss": 3.9626, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287365128740673e-05, + "loss": 3.9697, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286526533989621e-05, + "loss": 3.9613, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285687939238569e-05, + "loss": 3.9721, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284849344487517e-05, + "loss": 3.976, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284010749736465e-05, + "loss": 3.9729, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283172154985413e-05, + "loss": 3.9738, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282333560234361e-05, + "loss": 3.9595, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281496603363682e-05, + "loss": 3.961, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280658008612631e-05, + "loss": 3.974, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279819413861579e-05, + "loss": 3.9831, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.278980819110527e-05, + "loss": 3.965, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278142224359475e-05, + "loss": 3.9594, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277303629608423e-05, + "loss": 3.9645, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.27646503485737e-05, + "loss": 3.966, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275626440106318e-05, + "loss": 3.976, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274787845355266e-05, + "loss": 3.9736, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273949250604214e-05, + "loss": 3.9692, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273110655853162e-05, + "loss": 3.978, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.27227206110211e-05, + "loss": 3.97, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271433466351058e-05, + "loss": 3.9737, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270594871600006e-05, + "loss": 3.9649, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269757914729327e-05, + "loss": 3.9794, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2689193199782756e-05, + "loss": 3.965, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2680807252272236e-05, + "loss": 3.9736, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672437683565445e-05, + "loss": 3.969, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2664051736054925e-05, + "loss": 3.9623, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2655665788544405e-05, + "loss": 3.9775, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2647279841033885e-05, + "loss": 3.982, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2638893893523365e-05, + "loss": 3.9683, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2630524324816574e-05, + "loss": 3.9797, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2622138377306054e-05, + "loss": 3.9649, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2613752429795534e-05, + "loss": 3.9619, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2605366482285014e-05, + "loss": 3.9719, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2596980534774494e-05, + "loss": 3.9708, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2588594587263974e-05, + "loss": 3.9925, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2580208639753453e-05, + "loss": 3.972, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257183907104667e-05, + "loss": 3.9721, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256345312353615e-05, + "loss": 3.9639, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255506717602563e-05, + "loss": 3.972, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254668122851511e-05, + "loss": 3.9721, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253829528100459e-05, + "loss": 3.9789, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.252990933349406e-05, + "loss": 3.9804, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252152338598354e-05, + "loss": 3.9677, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251313743847302e-05, + "loss": 3.9693, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.080323696136475, + "eval_runtime": 544.2988, + "eval_samples_per_second": 701.069, + "eval_steps_per_second": 21.909, + "step": 1068466 + }, + { + "epoch": 1.0, + "learning_rate": 3.250476786976624e-05, + "loss": 3.9722, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249638192225571e-05, + "loss": 3.9856, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248799597474519e-05, + "loss": 3.9729, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247962640603841e-05, + "loss": 3.9652, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247124045852789e-05, + "loss": 3.9775, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246285451101737e-05, + "loss": 3.9682, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245446856350685e-05, + "loss": 3.968, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244608261599633e-05, + "loss": 3.9585, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243769666848581e-05, + "loss": 3.9726, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2429327099779016e-05, + "loss": 3.9673, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242095753107223e-05, + "loss": 3.9696, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241257158356171e-05, + "loss": 3.9758, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2404185636051185e-05, + "loss": 3.9701, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.2395799688540665e-05, + "loss": 3.9744, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2387413741030145e-05, + "loss": 3.9649, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237902779351963e-05, + "loss": 3.9596, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237065822481284e-05, + "loss": 3.946, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236227227730232e-05, + "loss": 3.9687, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.23538863297918e-05, + "loss": 3.9643, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234550038228128e-05, + "loss": 3.9766, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233711443477076e-05, + "loss": 3.9792, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232872848726024e-05, + "loss": 3.9724, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232034253974972e-05, + "loss": 3.9659, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.23119565922392e-05, + "loss": 3.9752, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230357064472868e-05, + "loss": 3.9603, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229520107602189e-05, + "loss": 3.9643, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228681512851137e-05, + "loss": 3.9697, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227842918100085e-05, + "loss": 3.9664, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227004323349033e-05, + "loss": 3.9605, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2261657285979816e-05, + "loss": 3.9658, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2253271338469296e-05, + "loss": 3.9565, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2244885390958776e-05, + "loss": 3.9616, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223649944344825e-05, + "loss": 3.9746, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2228129874741465e-05, + "loss": 3.9675, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2219743927230945e-05, + "loss": 3.9666, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2211374358524154e-05, + "loss": 3.9679, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220300478981736e-05, + "loss": 3.975, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219461884230684e-05, + "loss": 3.9682, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218623289479632e-05, + "loss": 3.9667, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.21778469472858e-05, + "loss": 3.9696, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.216946099977528e-05, + "loss": 3.9653, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216107505226476e-05, + "loss": 3.9567, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215268910475425e-05, + "loss": 3.9638, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214430315724372e-05, + "loss": 3.9688, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.21359172097332e-05, + "loss": 3.9751, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212754764102642e-05, + "loss": 3.9681, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.21191616935159e-05, + "loss": 3.9637, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211077574600537e-05, + "loss": 3.9782, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210238979849485e-05, + "loss": 3.9632, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209400385098433e-05, + "loss": 3.9531, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208563428227754e-05, + "loss": 3.9645, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207724833476702e-05, + "loss": 3.9597, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.20688623872565e-05, + "loss": 3.9717, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206047643974599e-05, + "loss": 3.9592, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205209049223547e-05, + "loss": 3.9745, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204370454472495e-05, + "loss": 3.9445, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203531859721443e-05, + "loss": 3.9679, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2026949028507636e-05, + "loss": 3.9677, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2018563080997116e-05, + "loss": 3.9665, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2010177133486596e-05, + "loss": 3.9686, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2001791185976076e-05, + "loss": 3.9611, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1993405238465556e-05, + "loss": 3.9586, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1985019290955036e-05, + "loss": 3.9623, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1976633343444516e-05, + "loss": 3.9579, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1968247395933996e-05, + "loss": 3.9771, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1959861448423476e-05, + "loss": 3.9649, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1951475500912956e-05, + "loss": 3.9553, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194310593220617e-05, + "loss": 3.9543, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193471998469565e-05, + "loss": 3.9687, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192633403718513e-05, + "loss": 3.9577, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191794808967461e-05, + "loss": 3.9587, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.190957852096782e-05, + "loss": 3.9683, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.19011925734573e-05, + "loss": 3.9596, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189280662594678e-05, + "loss": 3.9727, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188442067843626e-05, + "loss": 3.9688, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1876034730925734e-05, + "loss": 3.9667, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186766516221895e-05, + "loss": 3.9635, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.185927921470843e-05, + "loss": 3.9566, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185090964600164e-05, + "loss": 3.9687, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.1842523698491126e-05, + "loss": 3.9635, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.1834137750980606e-05, + "loss": 3.9763, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.1825751803470086e-05, + "loss": 3.9703, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181736585595956e-05, + "loss": 3.9584, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1808996287252775e-05, + "loss": 3.9569, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1800610339742255e-05, + "loss": 3.95, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1792224392231735e-05, + "loss": 3.9654, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178383844472121e-05, + "loss": 3.9686, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177545249721069e-05, + "loss": 3.9665, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1767082928503904e-05, + "loss": 3.9629, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175869698099338e-05, + "loss": 3.9574, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1750311033482863e-05, + "loss": 3.9542, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174192508597234e-05, + "loss": 3.9619, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173353913846182e-05, + "loss": 3.9694, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.17251531909513e-05, + "loss": 3.9586, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171676724344078e-05, + "loss": 3.9494, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170838129593026e-05, + "loss": 3.9523, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170001172722347e-05, + "loss": 3.9637, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169162577971295e-05, + "loss": 3.9634, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168323983220243e-05, + "loss": 3.9676, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167485388469191e-05, + "loss": 3.9656, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166646793718139e-05, + "loss": 3.9571, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165808198967087e-05, + "loss": 3.961, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164971242096408e-05, + "loss": 3.964, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164132647345356e-05, + "loss": 3.9708, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163294052594304e-05, + "loss": 3.9497, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162455457843253e-05, + "loss": 3.9599, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161616863092201e-05, + "loss": 3.9491, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160778268341149e-05, + "loss": 3.9557, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.159939673590097e-05, + "loss": 3.966, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159102716719418e-05, + "loss": 3.9545, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158264121968366e-05, + "loss": 3.9601, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157425527217314e-05, + "loss": 3.9481, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156586932466262e-05, + "loss": 3.9525, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155748337715209e-05, + "loss": 3.9596, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.154909742964157e-05, + "loss": 3.9702, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154071148213105e-05, + "loss": 3.9526, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153232553462053e-05, + "loss": 3.9492, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152393958711001e-05, + "loss": 3.9504, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1515553639599496e-05, + "loss": 3.9588, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1507167692088976e-05, + "loss": 3.9637, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1498798123382185e-05, + "loss": 3.9604, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1490412175871665e-05, + "loss": 3.9519, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1482042607164874e-05, + "loss": 3.9645, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1473656659654354e-05, + "loss": 3.9577, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1465270712143834e-05, + "loss": 3.9635, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1456884764633314e-05, + "loss": 3.9507, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1448498817122794e-05, + "loss": 3.9656, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1440112869612274e-05, + "loss": 3.9512, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1431726922101754e-05, + "loss": 3.963, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1423340974591234e-05, + "loss": 3.9562, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141497140588445e-05, + "loss": 3.9502, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140658545837393e-05, + "loss": 3.9638, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139821588966714e-05, + "loss": 3.9646, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.138982994215662e-05, + "loss": 3.9574, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.13814439946461e-05, + "loss": 3.9705, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137305804713558e-05, + "loss": 3.9508, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136467209962506e-05, + "loss": 3.9473, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135628615211454e-05, + "loss": 3.9596, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134790020460402e-05, + "loss": 3.9618, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.13395142570935e-05, + "loss": 3.9803, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133114468838671e-05, + "loss": 3.9571, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132275874087619e-05, + "loss": 3.958, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131437279336567e-05, + "loss": 3.9534, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130598684585515e-05, + "loss": 3.9602, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.1297617277148364e-05, + "loss": 3.9583, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1289231329637844e-05, + "loss": 3.965, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1280845382127324e-05, + "loss": 3.9692, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127247581342053e-05, + "loss": 3.9556, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126408986591001e-05, + "loss": 3.9563, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.074672698974609, + "eval_runtime": 542.6262, + "eval_samples_per_second": 703.23, + "eval_steps_per_second": 21.976, + "step": 1144785 + }, + { + "epoch": 0.0, + "learning_rate": 3.125570391839949e-05, + "loss": 3.914, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124731797088897e-05, + "loss": 3.9759, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123893202337845e-05, + "loss": 3.9634, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1230546075867926e-05, + "loss": 3.9556, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1222160128357406e-05, + "loss": 3.9621, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1213774180846886e-05, + "loss": 3.9541, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120538823333637e-05, + "loss": 3.9566, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119700228582585e-05, + "loss": 3.9464, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118861633831533e-05, + "loss": 3.9598, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118023039080481e-05, + "loss": 3.9561, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117186082209802e-05, + "loss": 3.957, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.11634748745875e-05, + "loss": 3.9645, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115508892707698e-05, + "loss": 3.9586, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114670297956646e-05, + "loss": 3.959, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113831703205594e-05, + "loss": 3.9538, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.112993108454542e-05, + "loss": 3.9502, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.11215451370349e-05, + "loss": 3.9347, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111315918952438e-05, + "loss": 3.954, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110477324201386e-05, + "loss": 3.9542, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109638729450334e-05, + "loss": 3.9611, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108800134699282e-05, + "loss": 3.9695, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.10796153994823e-05, + "loss": 3.9626, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107122945197178e-05, + "loss": 3.948, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106284350446126e-05, + "loss": 3.9637, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105447393575447e-05, + "loss": 3.9519, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1046104367047686e-05, + "loss": 3.9523, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1037718419537166e-05, + "loss": 3.9529, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.102933247202664e-05, + "loss": 3.9594, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102094652451612e-05, + "loss": 3.9455, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.10125605770056e-05, + "loss": 3.9551, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100417462949508e-05, + "loss": 3.945, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099578868198456e-05, + "loss": 3.9472, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098740273447404e-05, + "loss": 3.9647, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.097901678696352e-05, + "loss": 3.954, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0970630839453005e-05, + "loss": 3.9516, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0962244891942485e-05, + "loss": 3.9579, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0953875323235694e-05, + "loss": 3.9573, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0945489375725174e-05, + "loss": 3.9556, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0937103428214654e-05, + "loss": 3.9541, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0928717480704134e-05, + "loss": 3.9623, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0920331533193614e-05, + "loss": 3.9505, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0911945585683094e-05, + "loss": 3.9481, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.09035760169763e-05, + "loss": 3.9465, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089519006946578e-05, + "loss": 3.9621, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088680412195526e-05, + "loss": 3.9596, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087841817444474e-05, + "loss": 3.9564, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087003222693422e-05, + "loss": 3.9508, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.08616462794237e-05, + "loss": 3.9619, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085326033191318e-05, + "loss": 3.9571, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084487438440266e-05, + "loss": 3.9428, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9472, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9471, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.081973292067483e-05, + "loss": 3.9584, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081136335196805e-05, + "loss": 3.9492, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080297740445753e-05, + "loss": 3.9633, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0794591456947e-05, + "loss": 3.9314, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078620550943648e-05, + "loss": 3.9532, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077781956192596e-05, + "loss": 3.9523, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.076943361441544e-05, + "loss": 3.9585, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0761064045708657e-05, + "loss": 3.9536, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0752678098198137e-05, + "loss": 3.9501, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0744292150687617e-05, + "loss": 3.9464, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0735906203177096e-05, + "loss": 3.954, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0727520255666576e-05, + "loss": 3.9438, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0719134308156056e-05, + "loss": 3.9561, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0710748360645536e-05, + "loss": 3.9571, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0702378791938745e-05, + "loss": 3.9447, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0694009223231955e-05, + "loss": 3.9415, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0685623275721434e-05, + "loss": 3.9599, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0677237328210914e-05, + "loss": 3.9457, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0668851380700394e-05, + "loss": 3.9447, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066046543318988e-05, + "loss": 3.9561, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065207948567936e-05, + "loss": 3.9458, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064369353816884e-05, + "loss": 3.9566, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063530759065832e-05, + "loss": 3.9577, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.06269216431478e-05, + "loss": 3.9546, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.061855207444101e-05, + "loss": 3.9508, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061016612693049e-05, + "loss": 3.9457, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060178017941997e-05, + "loss": 3.954, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059339423190945e-05, + "loss": 3.9539, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058500828439893e-05, + "loss": 3.9638, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057662233688841e-05, + "loss": 3.9588, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056823638937789e-05, + "loss": 3.9444, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.05598668206711e-05, + "loss": 3.9431, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055148087316058e-05, + "loss": 3.9373, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054309492565006e-05, + "loss": 3.9506, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0534708978139546e-05, + "loss": 3.954, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0526339409432755e-05, + "loss": 3.9557, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0517953461922235e-05, + "loss": 3.9507, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0509567514411715e-05, + "loss": 3.9475, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0501181566901188e-05, + "loss": 3.9456, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0492795619390668e-05, + "loss": 3.95, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0484409671880148e-05, + "loss": 3.9544, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0476023724369628e-05, + "loss": 3.9439, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046763777685911e-05, + "loss": 3.9388, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.045925182934859e-05, + "loss": 3.9417, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.04508822606418e-05, + "loss": 3.953, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044249631313128e-05, + "loss": 3.9504, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043411036562076e-05, + "loss": 3.957, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042572441811024e-05, + "loss": 3.9516, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041733847059972e-05, + "loss": 3.9482, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0408968901892932e-05, + "loss": 3.9526, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0400582954382412e-05, + "loss": 3.9475, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0392197006871892e-05, + "loss": 3.9567, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.03838274381651e-05, + "loss": 3.9391, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037544149065458e-05, + "loss": 3.9498, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036705554314406e-05, + "loss": 3.9399, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0358669595633545e-05, + "loss": 3.9398, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0350283648123024e-05, + "loss": 3.9556, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0341897700612504e-05, + "loss": 3.9421, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0333511753101984e-05, + "loss": 3.9509, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0325125805591464e-05, + "loss": 3.9374, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0316756236884673e-05, + "loss": 3.9395, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0308370289374153e-05, + "loss": 3.9459, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0299984341863637e-05, + "loss": 3.9557, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0291598394353117e-05, + "loss": 3.9427, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0283228825646326e-05, + "loss": 3.9322, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0274842878135806e-05, + "loss": 3.9411, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0266456930625286e-05, + "loss": 3.9494, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0258070983114766e-05, + "loss": 3.9495, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0249685035604246e-05, + "loss": 3.9547, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024129908809373e-05, + "loss": 3.9364, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0232913140583202e-05, + "loss": 3.9555, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0224527193072682e-05, + "loss": 3.9437, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0216157624365898e-05, + "loss": 3.9509, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0207771676855378e-05, + "loss": 3.9384, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0199385729344855e-05, + "loss": 3.9541, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0190999781834334e-05, + "loss": 3.9386, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182613834323814e-05, + "loss": 3.9529, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0174244265617024e-05, + "loss": 3.9423, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016587469691024e-05, + "loss": 3.9437, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015748874939972e-05, + "loss": 3.9519, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.01491028018892e-05, + "loss": 3.9528, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0140716854378676e-05, + "loss": 3.9475, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0132330906868156e-05, + "loss": 3.9575, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0123944959357636e-05, + "loss": 3.9395, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115559011847116e-05, + "loss": 3.938, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0107173064336596e-05, + "loss": 3.9458, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0098803495629808e-05, + "loss": 3.9495, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0090417548119288e-05, + "loss": 3.9625, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0082031600608768e-05, + "loss": 3.9503, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0073645653098248e-05, + "loss": 3.9449, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0065259705587728e-05, + "loss": 3.9427, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0056890136880937e-05, + "loss": 3.9481, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004852056817415e-05, + "loss": 3.9472, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004013462066363e-05, + "loss": 3.9523, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003174867315311e-05, + "loss": 3.9566, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002336272564259e-05, + "loss": 3.9446, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001497677813207e-05, + "loss": 3.9442, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 4.067862033843994, + "eval_runtime": 560.3654, + "eval_samples_per_second": 680.968, + "eval_steps_per_second": 21.281, + "step": 1221104 + }, + { + "epoch": 1.0, + "learning_rate": 3.000659083062155e-05, + "loss": 3.9466, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999820488311103e-05, + "loss": 3.9638, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9989818935600513e-05, + "loss": 3.9505, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998146574569745e-05, + "loss": 3.9437, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997307979818693e-05, + "loss": 3.9492, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.996469385067641e-05, + "loss": 3.9404, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.995630790316589e-05, + "loss": 3.9453, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9947921955655374e-05, + "loss": 3.9396, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9939536008144854e-05, + "loss": 3.9424, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9931150060634334e-05, + "loss": 3.9446, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9922796870731272e-05, + "loss": 3.9479, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9914410923220752e-05, + "loss": 3.9525, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9906024975710236e-05, + "loss": 3.9452, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9897639028199716e-05, + "loss": 3.9464, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9889253080689195e-05, + "loss": 3.9424, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9880867133178675e-05, + "loss": 3.9368, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9872481185668155e-05, + "loss": 3.9279, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9864095238157635e-05, + "loss": 3.9419, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9855709290647115e-05, + "loss": 3.9422, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9847323343136595e-05, + "loss": 3.9497, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9838953774429808e-05, + "loss": 3.9566, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9830567826919288e-05, + "loss": 3.9473, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9822181879408768e-05, + "loss": 3.9404, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9813795931898248e-05, + "loss": 3.9523, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9805409984387728e-05, + "loss": 3.9439, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9797024036877208e-05, + "loss": 3.9425, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9788638089366684e-05, + "loss": 3.94, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9780252141856164e-05, + "loss": 3.95, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977188257314938e-05, + "loss": 3.9331, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976349662563886e-05, + "loss": 3.9472, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9755110678128333e-05, + "loss": 3.9291, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9746724730617813e-05, + "loss": 3.9344, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.973835516191103e-05, + "loss": 3.9522, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.972996921440051e-05, + "loss": 3.9441, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9721583266889985e-05, + "loss": 3.9426, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.97132136981832e-05, + "loss": 3.9415, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.970482775067268e-05, + "loss": 3.9462, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9696441803162154e-05, + "loss": 3.9477, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9688055855651638e-05, + "loss": 3.9429, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9679669908141118e-05, + "loss": 3.9493, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9671283960630598e-05, + "loss": 3.9373, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9662914391923807e-05, + "loss": 3.9449, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9654528444413287e-05, + "loss": 3.9319, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9646142496902767e-05, + "loss": 3.9499, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9637756549392247e-05, + "loss": 3.9457, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.962937060188173e-05, + "loss": 3.9449, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962098465437121e-05, + "loss": 3.9411, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961261508566442e-05, + "loss": 3.9482, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9604245516957628e-05, + "loss": 3.9476, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9595859569447108e-05, + "loss": 3.934, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958747362193659e-05, + "loss": 3.9389, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.957908767442607e-05, + "loss": 3.9344, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957070172691555e-05, + "loss": 3.9495, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956231577940503e-05, + "loss": 3.9339, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955392983189451e-05, + "loss": 3.9509, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954554388438399e-05, + "loss": 3.9271, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.95371743156772e-05, + "loss": 3.9426, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9528788368166684e-05, + "loss": 3.9392, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9520402420656164e-05, + "loss": 3.9472, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9512016473145644e-05, + "loss": 3.9426, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9503630525635123e-05, + "loss": 3.9451, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9495260956928333e-05, + "loss": 3.9311, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9486875009417813e-05, + "loss": 3.9404, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9478489061907292e-05, + "loss": 3.9344, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9470103114396776e-05, + "loss": 3.9454, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9461717166886256e-05, + "loss": 3.9462, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9453331219375736e-05, + "loss": 3.9376, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9444945271865216e-05, + "loss": 3.9259, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9436575703158425e-05, + "loss": 3.945, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9428189755647905e-05, + "loss": 3.9367, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9419803808137385e-05, + "loss": 3.934, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9411417860626868e-05, + "loss": 3.9429, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9403031913116348e-05, + "loss": 3.9364, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.939464596560582e-05, + "loss": 3.9431, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.93862600180953e-05, + "loss": 3.9476, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937787407058478e-05, + "loss": 3.9426, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9369504501877994e-05, + "loss": 3.9433, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9361118554367474e-05, + "loss": 3.9341, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9352732606856954e-05, + "loss": 3.9439, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.934436303815017e-05, + "loss": 3.945, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9335977090639643e-05, + "loss": 3.9509, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9327591143129123e-05, + "loss": 3.9475, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9319205195618606e-05, + "loss": 3.938, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9310819248108086e-05, + "loss": 3.9276, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9302433300597566e-05, + "loss": 3.9326, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9294047353087046e-05, + "loss": 3.9377, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9285661405576526e-05, + "loss": 3.9424, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9277291836869735e-05, + "loss": 3.9463, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9268905889359215e-05, + "loss": 3.9414, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9260519941848698e-05, + "loss": 3.9328, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9252133994338178e-05, + "loss": 3.9376, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9243764425631387e-05, + "loss": 3.9352, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9235378478120867e-05, + "loss": 3.9474, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9226992530610347e-05, + "loss": 3.9385, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.921862296190356e-05, + "loss": 3.9265, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.921023701439304e-05, + "loss": 3.9302, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920185106688252e-05, + "loss": 3.9426, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9193465119372e-05, + "loss": 3.9408, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918507917186148e-05, + "loss": 3.9446, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917669322435096e-05, + "loss": 3.9402, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916830727684044e-05, + "loss": 3.937, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.915992132932992e-05, + "loss": 3.9383, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.91515353818194e-05, + "loss": 3.9411, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914316581311261e-05, + "loss": 3.9462, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913477986560209e-05, + "loss": 3.9281, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912639391809157e-05, + "loss": 3.9401, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911800797058105e-05, + "loss": 3.9244, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.910962202307053e-05, + "loss": 3.9349, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910125245436374e-05, + "loss": 3.9415, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9092882885656953e-05, + "loss": 3.934, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9084496938146433e-05, + "loss": 3.9411, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9076127369439642e-05, + "loss": 3.9268, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9067741421929122e-05, + "loss": 3.9291, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9059355474418602e-05, + "loss": 3.9343, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9050969526908085e-05, + "loss": 3.9505, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9042583579397565e-05, + "loss": 3.9286, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9034197631887045e-05, + "loss": 3.9262, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9025811684376525e-05, + "loss": 3.9305, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9017425736866005e-05, + "loss": 3.9405, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.900903978935548e-05, + "loss": 3.9347, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9000653841844962e-05, + "loss": 3.9388, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899226789433444e-05, + "loss": 3.9328, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.898389832562765e-05, + "loss": 3.9437, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897551237811713e-05, + "loss": 3.9343, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896712643060661e-05, + "loss": 3.9356, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.895874048309609e-05, + "loss": 3.9328, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.895035453558557e-05, + "loss": 3.9422, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8941968588075054e-05, + "loss": 3.926, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8933582640564534e-05, + "loss": 3.9407, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8925213071857743e-05, + "loss": 3.9338, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8916827124347223e-05, + "loss": 3.9289, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8908441176836703e-05, + "loss": 3.9428, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8900055229326183e-05, + "loss": 3.9392, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8891669281815663e-05, + "loss": 3.9401, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8883299713108875e-05, + "loss": 3.9443, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8874913765598355e-05, + "loss": 3.9308, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8866527818087835e-05, + "loss": 3.9295, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8858141870577315e-05, + "loss": 3.9329, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8849755923066795e-05, + "loss": 3.9428, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8841369975556275e-05, + "loss": 3.9467, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8832984028045755e-05, + "loss": 3.9421, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8824614459338968e-05, + "loss": 3.9356, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8816228511828447e-05, + "loss": 3.9347, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8807842564317927e-05, + "loss": 3.9409, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8799456616807407e-05, + "loss": 3.9378, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8791070669296887e-05, + "loss": 3.9371, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.87827011005901e-05, + "loss": 3.9462, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877431515307958e-05, + "loss": 3.94, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876592920556906e-05, + "loss": 3.9316, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875754325805854e-05, + "loss": 3.9348, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 4.063434600830078, + "eval_runtime": 549.497, + "eval_samples_per_second": 694.437, + "eval_steps_per_second": 21.702, + "step": 1297423 + }, + { + "epoch": 0.0, + "learning_rate": 2.8749157310548013e-05, + "loss": 3.9423, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8740771363037493e-05, + "loss": 3.9375, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8732385415526976e-05, + "loss": 3.9324, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8723999468016456e-05, + "loss": 3.9373, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8715613520505936e-05, + "loss": 3.9331, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8707227572995416e-05, + "loss": 3.9407, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8698841625484896e-05, + "loss": 3.9318, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8690455677974376e-05, + "loss": 3.9188, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8682069730463856e-05, + "loss": 3.9298, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8673683782953336e-05, + "loss": 3.9426, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8665297835442816e-05, + "loss": 3.9328, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8656911887932296e-05, + "loss": 3.9379, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.864852594042178e-05, + "loss": 3.9367, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8640139992911252e-05, + "loss": 3.9432, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8631754045400732e-05, + "loss": 3.921, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8623368097890212e-05, + "loss": 3.9456, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8614982150379692e-05, + "loss": 3.932, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8606596202869172e-05, + "loss": 3.9272, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8598210255358655e-05, + "loss": 3.9464, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8589824307848135e-05, + "loss": 3.9416, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8581454739141344e-05, + "loss": 3.9468, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8573085170434554e-05, + "loss": 3.9272, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8564699222924034e-05, + "loss": 3.9356, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8556313275413517e-05, + "loss": 3.9332, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8547927327902997e-05, + "loss": 3.9339, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8539541380392477e-05, + "loss": 3.9205, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8531155432881957e-05, + "loss": 3.9383, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8522769485371437e-05, + "loss": 3.9349, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8514383537860917e-05, + "loss": 3.9378, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8505997590350397e-05, + "loss": 3.9386, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849762802164361e-05, + "loss": 3.9324, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8489258452936818e-05, + "loss": 3.9346, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8480872505426298e-05, + "loss": 3.9469, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8472486557915778e-05, + "loss": 3.9321, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8464100610405258e-05, + "loss": 3.9405, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8455714662894738e-05, + "loss": 3.9312, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8447328715384218e-05, + "loss": 3.94, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.84389427678737e-05, + "loss": 3.9311, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843055682036318e-05, + "loss": 3.95, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842220363046012e-05, + "loss": 3.9475, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.84138176829496e-05, + "loss": 3.9264, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840543173543908e-05, + "loss": 3.9353, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8397045787928563e-05, + "loss": 3.9336, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8388659840418043e-05, + "loss": 3.9323, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8380273892907523e-05, + "loss": 3.9264, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8371904324200732e-05, + "loss": 3.9324, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8363518376690212e-05, + "loss": 3.9346, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835513242917969e-05, + "loss": 3.9455, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834674648166917e-05, + "loss": 3.9406, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8338360534158655e-05, + "loss": 3.9094, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8329974586648135e-05, + "loss": 3.9381, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8321588639137615e-05, + "loss": 3.9295, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8313202691627088e-05, + "loss": 3.9138, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8304816744116568e-05, + "loss": 3.9315, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8296447175409784e-05, + "loss": 3.9272, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8288061227899264e-05, + "loss": 3.9397, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8279691659192476e-05, + "loss": 3.9218, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8271305711681956e-05, + "loss": 3.9281, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8262919764171436e-05, + "loss": 3.9331, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8254533816660916e-05, + "loss": 3.9202, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8246147869150393e-05, + "loss": 3.9359, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8237761921639873e-05, + "loss": 3.9173, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8229375974129353e-05, + "loss": 3.9324, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8220990026618833e-05, + "loss": 3.9387, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8212604079108313e-05, + "loss": 3.9352, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8204234510401522e-05, + "loss": 3.929, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8195848562891e-05, + "loss": 3.933, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818746261538048e-05, + "loss": 3.9414, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8179076667869965e-05, + "loss": 3.9396, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8170707099163174e-05, + "loss": 3.9369, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8162321151652654e-05, + "loss": 3.9325, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8153935204142134e-05, + "loss": 3.9313, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8145565635435343e-05, + "loss": 3.9272, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8137179687924826e-05, + "loss": 3.9381, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8128793740414306e-05, + "loss": 3.935, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8120407792903786e-05, + "loss": 3.9346, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8112021845393266e-05, + "loss": 3.9322, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8103652276686475e-05, + "loss": 3.9371, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8095266329175955e-05, + "loss": 3.9337, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8086880381665435e-05, + "loss": 3.9363, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.807849443415492e-05, + "loss": 3.9229, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.80701084866444e-05, + "loss": 3.9356, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8061738917937608e-05, + "loss": 3.9286, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8053352970427088e-05, + "loss": 3.9261, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8044967022916568e-05, + "loss": 3.9335, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8036581075406048e-05, + "loss": 3.9308, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802821150669926e-05, + "loss": 3.9382, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.801982555918874e-05, + "loss": 3.9317, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.801145599048195e-05, + "loss": 3.9274, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800307004297143e-05, + "loss": 3.9326, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799468409546091e-05, + "loss": 3.9365, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798629814795039e-05, + "loss": 3.9304, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7977912200439872e-05, + "loss": 3.9193, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7969526252929352e-05, + "loss": 3.9281, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7961140305418832e-05, + "loss": 3.9304, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7952754357908312e-05, + "loss": 3.9344, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7944368410397792e-05, + "loss": 3.9226, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7935998841691e-05, + "loss": 3.9165, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792761289418048e-05, + "loss": 3.9251, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7919226946669965e-05, + "loss": 3.9243, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7910840999159444e-05, + "loss": 3.9337, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7902455051648924e-05, + "loss": 3.9295, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7894069104138398e-05, + "loss": 3.9307, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7885683156627878e-05, + "loss": 3.9238, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7877297209117358e-05, + "loss": 3.924, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7868927640410573e-05, + "loss": 3.9349, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786054169290005e-05, + "loss": 3.9281, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7852172124193266e-05, + "loss": 3.9211, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7843786176682746e-05, + "loss": 3.921, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783540022917222e-05, + "loss": 3.9296, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7827014281661702e-05, + "loss": 3.9336, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7818628334151182e-05, + "loss": 3.9237, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7810242386640662e-05, + "loss": 3.9282, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7801856439130142e-05, + "loss": 3.9195, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7793470491619622e-05, + "loss": 3.9296, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7785084544109102e-05, + "loss": 3.9215, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777671497540231e-05, + "loss": 3.9302, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7768329027891795e-05, + "loss": 3.9377, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7759943080381274e-05, + "loss": 3.9257, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7751557132870754e-05, + "loss": 3.9266, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7743187564163964e-05, + "loss": 3.9384, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7734801616653443e-05, + "loss": 3.9297, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7726432047946656e-05, + "loss": 3.9286, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7718046100436136e-05, + "loss": 3.9293, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7709660152925616e-05, + "loss": 3.9205, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7701274205415096e-05, + "loss": 3.9232, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7692888257904576e-05, + "loss": 3.918, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7684502310394056e-05, + "loss": 3.9305, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7676132741687265e-05, + "loss": 3.9133, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7667746794176748e-05, + "loss": 3.9446, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7659360846666228e-05, + "loss": 3.9165, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7650974899155708e-05, + "loss": 3.932, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7642588951645188e-05, + "loss": 3.9283, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7634203004134668e-05, + "loss": 3.9273, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7625817056624148e-05, + "loss": 3.928, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7617431109113628e-05, + "loss": 3.9313, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7609045161603108e-05, + "loss": 3.9298, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760067559289632e-05, + "loss": 3.9287, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.75922896453858e-05, + "loss": 3.9337, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758390369787528e-05, + "loss": 3.9278, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757553412916849e-05, + "loss": 3.9251, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756714818165797e-05, + "loss": 3.9335, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.755876223414745e-05, + "loss": 3.922, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755037628663693e-05, + "loss": 3.9331, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7541990339126406e-05, + "loss": 3.9381, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7533604391615886e-05, + "loss": 3.9329, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7525218444105366e-05, + "loss": 3.9423, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751684887539858e-05, + "loss": 3.9215, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7508462927888058e-05, + "loss": 3.9245, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 4.057143688201904, + "eval_runtime": 291.2642, + "eval_samples_per_second": 1310.12, + "eval_steps_per_second": 40.942, + "step": 1373743 + }, + { + "epoch": 1.0, + "learning_rate": 2.7500076980377538e-05, + "loss": 3.9337, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7491707411670754e-05, + "loss": 3.9246, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7483321464160234e-05, + "loss": 3.9224, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7474935516649707e-05, + "loss": 3.9251, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7466549569139187e-05, + "loss": 3.9311, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7458163621628667e-05, + "loss": 3.927, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.744977767411815e-05, + "loss": 3.9265, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744139172660763e-05, + "loss": 3.905, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743300577909711e-05, + "loss": 3.923, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742461983158659e-05, + "loss": 3.9279, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741623388407607e-05, + "loss": 3.9232, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740784793656555e-05, + "loss": 3.9245, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.739946198905503e-05, + "loss": 3.9291, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.739107604154451e-05, + "loss": 3.9301, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7382706472837723e-05, + "loss": 3.9143, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7374320525327203e-05, + "loss": 3.9319, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736595095662041e-05, + "loss": 3.9243, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735756500910989e-05, + "loss": 3.9231, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.734917906159937e-05, + "loss": 3.9369, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734079311408885e-05, + "loss": 3.927, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7332407166578335e-05, + "loss": 3.9385, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7324021219067815e-05, + "loss": 3.9182, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7315651650361024e-05, + "loss": 3.9259, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7307265702850504e-05, + "loss": 3.9246, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7298879755339984e-05, + "loss": 3.9217, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7290493807829464e-05, + "loss": 3.9132, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7282107860318944e-05, + "loss": 3.9275, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.727372191280842e-05, + "loss": 3.9227, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.72653359652979e-05, + "loss": 3.9321, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725695001778738e-05, + "loss": 3.9215, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.724856407027686e-05, + "loss": 3.924, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7240210880373805e-05, + "loss": 3.9273, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.723182493286329e-05, + "loss": 3.9315, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722343898535277e-05, + "loss": 3.9259, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721505303784224e-05, + "loss": 3.9267, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720666709033172e-05, + "loss": 3.924, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.71982811428212e-05, + "loss": 3.9287, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.718989519531068e-05, + "loss": 3.9242, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7181509247800165e-05, + "loss": 3.9339, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7173139679093374e-05, + "loss": 3.9385, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7164753731582854e-05, + "loss": 3.919, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7156367784072334e-05, + "loss": 3.9269, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7147998215365543e-05, + "loss": 3.9238, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7139612267855026e-05, + "loss": 3.9213, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7131226320344506e-05, + "loss": 3.9193, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7122840372833986e-05, + "loss": 3.9226, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7114454425323466e-05, + "loss": 3.9232, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7106068477812946e-05, + "loss": 3.9356, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7097682530302426e-05, + "loss": 3.9267, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7089296582791906e-05, + "loss": 3.9059, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7080927014085115e-05, + "loss": 3.9226, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.70725410665746e-05, + "loss": 3.9227, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.706415511906408e-05, + "loss": 3.9033, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705576917155356e-05, + "loss": 3.9234, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7047399602846767e-05, + "loss": 3.9147, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7039013655336247e-05, + "loss": 3.9325, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7030627707825727e-05, + "loss": 3.9093, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7022241760315207e-05, + "loss": 3.9202, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701387219160842e-05, + "loss": 3.9264, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.70054862440979e-05, + "loss": 3.9088, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699710029658738e-05, + "loss": 3.9252, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.698871434907686e-05, + "loss": 3.9105, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698034478037007e-05, + "loss": 3.9169, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6971958832859552e-05, + "loss": 3.9319, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6963572885349032e-05, + "loss": 3.9258, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6955186937838512e-05, + "loss": 3.9211, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6946800990327992e-05, + "loss": 3.924, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6938415042817472e-05, + "loss": 3.9292, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6930029095306952e-05, + "loss": 3.9352, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692165952660016e-05, + "loss": 3.9248, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6913273579089644e-05, + "loss": 3.9238, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6904887631579124e-05, + "loss": 3.9254, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6896501684068604e-05, + "loss": 3.9138, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6888115736558077e-05, + "loss": 3.9301, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6879729789047557e-05, + "loss": 3.9235, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6871343841537037e-05, + "loss": 3.9224, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686295789402652e-05, + "loss": 3.929, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685458832531973e-05, + "loss": 3.9229, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684620237780921e-05, + "loss": 3.9238, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.683781643029869e-05, + "loss": 3.9282, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.68294468615919e-05, + "loss": 3.9173, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6821060914081382e-05, + "loss": 3.9219, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6812674966570862e-05, + "loss": 3.922, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6804289019060342e-05, + "loss": 3.9177, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6795903071549822e-05, + "loss": 3.919, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678753350284303e-05, + "loss": 3.9274, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.677914755533251e-05, + "loss": 3.9251, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677076160782199e-05, + "loss": 3.9192, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6762392039115203e-05, + "loss": 3.9203, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6754006091604683e-05, + "loss": 3.9204, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6745620144094163e-05, + "loss": 3.9276, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6737234196583643e-05, + "loss": 3.9226, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6728848249073123e-05, + "loss": 3.9085, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6720462301562603e-05, + "loss": 3.9213, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6712076354052083e-05, + "loss": 3.9172, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6703690406541567e-05, + "loss": 3.9259, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6695304459031047e-05, + "loss": 3.9165, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6686934890324256e-05, + "loss": 3.905, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6678548942813736e-05, + "loss": 3.9177, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6670162995303216e-05, + "loss": 3.9169, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6661777047792695e-05, + "loss": 3.9215, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6653391100282175e-05, + "loss": 3.9225, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664500515277166e-05, + "loss": 3.9232, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663661920526114e-05, + "loss": 3.9146, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.662823325775062e-05, + "loss": 3.9124, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6619863689043828e-05, + "loss": 3.9221, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6611477741533308e-05, + "loss": 3.9172, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660310817282652e-05, + "loss": 3.9171, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6594722225316e-05, + "loss": 3.9065, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658633627780548e-05, + "loss": 3.9254, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.657795033029496e-05, + "loss": 3.9217, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.656956438278444e-05, + "loss": 3.9155, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6561178435273913e-05, + "loss": 3.9213, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6552792487763397e-05, + "loss": 3.9109, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6544406540252877e-05, + "loss": 3.9175, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6536036971546092e-05, + "loss": 3.9146, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6527651024035566e-05, + "loss": 3.9215, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6519265076525046e-05, + "loss": 3.9275, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6510879129014525e-05, + "loss": 3.9144, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6502493181504005e-05, + "loss": 3.9184, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6494123612797218e-05, + "loss": 3.9332, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6485737665286698e-05, + "loss": 3.9165, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6477368096579914e-05, + "loss": 3.9218, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6468998527873123e-05, + "loss": 3.9211, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6460612580362603e-05, + "loss": 3.9123, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6452226632852083e-05, + "loss": 3.9085, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6443840685341563e-05, + "loss": 3.9088, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643545473783104e-05, + "loss": 3.9213, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642706879032052e-05, + "loss": 3.9013, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.641868284281e-05, + "loss": 3.935, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641029689529948e-05, + "loss": 3.9082, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.640191094778896e-05, + "loss": 3.9209, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639352500027844e-05, + "loss": 3.9177, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6385139052767922e-05, + "loss": 3.9234, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6376753105257402e-05, + "loss": 3.9195, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.636838353655061e-05, + "loss": 3.9231, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.635999758904009e-05, + "loss": 3.9217, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635161164152957e-05, + "loss": 3.919, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634322569401905e-05, + "loss": 3.9254, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633483974650853e-05, + "loss": 3.918, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6326470177801744e-05, + "loss": 3.9176, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6318084230291224e-05, + "loss": 3.9225, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6309731040388162e-05, + "loss": 3.9167, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6301345092877645e-05, + "loss": 3.927, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6292959145367125e-05, + "loss": 3.9286, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6284573197856605e-05, + "loss": 3.9202, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6276187250346085e-05, + "loss": 3.9327, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6267801302835565e-05, + "loss": 3.9097, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6259415355325045e-05, + "loss": 3.9172, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 4.053548336029053, + "eval_runtime": 290.8672, + "eval_samples_per_second": 1311.908, + "eval_steps_per_second": 40.998, + "step": 1450063 + }, + { + "epoch": 0.0, + "learning_rate": 2.6251029407814525e-05, + "loss": 3.9161, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6242643460304005e-05, + "loss": 3.9211, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6234257512793485e-05, + "loss": 3.9233, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6225871565282968e-05, + "loss": 3.9226, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217485617772448e-05, + "loss": 3.9295, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.620909967026192e-05, + "loss": 3.9093, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.62007137227514e-05, + "loss": 3.9164, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619232777524088e-05, + "loss": 3.9086, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618394182773036e-05, + "loss": 3.9267, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6175555880219845e-05, + "loss": 3.9158, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6167169932709325e-05, + "loss": 3.9269, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6158783985198805e-05, + "loss": 3.9262, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6150414416492014e-05, + "loss": 3.9086, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6142028468981494e-05, + "loss": 3.9133, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6133642521470974e-05, + "loss": 3.906, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6125256573960454e-05, + "loss": 3.9087, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6116870626449937e-05, + "loss": 3.9165, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6108484678939417e-05, + "loss": 3.9144, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6100098731428897e-05, + "loss": 3.9142, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6091712783918377e-05, + "loss": 3.935, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6083326836407857e-05, + "loss": 3.9163, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6074940888897337e-05, + "loss": 3.9199, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6066554941386813e-05, + "loss": 3.9235, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6058168993876293e-05, + "loss": 3.9218, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.604979942516951e-05, + "loss": 3.9114, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604141347765899e-05, + "loss": 3.9033, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6033027530148462e-05, + "loss": 3.9225, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6024657961441678e-05, + "loss": 3.9076, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6016272013931158e-05, + "loss": 3.9084, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6007886066420638e-05, + "loss": 3.9175, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.5999500118910115e-05, + "loss": 3.9118, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5991114171399594e-05, + "loss": 3.9223, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5982728223889074e-05, + "loss": 3.9168, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5974342276378554e-05, + "loss": 3.9088, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5965972707671763e-05, + "loss": 3.9222, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5957586760161247e-05, + "loss": 3.9302, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5949200812650727e-05, + "loss": 3.9048, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5940814865140207e-05, + "loss": 3.9212, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5932428917629687e-05, + "loss": 3.9057, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5924042970119167e-05, + "loss": 3.9137, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915657022608647e-05, + "loss": 3.9121, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907271075098127e-05, + "loss": 3.925, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5898917885195068e-05, + "loss": 3.9188, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5890531937684548e-05, + "loss": 3.914, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5882145990174028e-05, + "loss": 3.9192, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5873760042663508e-05, + "loss": 3.9101, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5865374095152988e-05, + "loss": 3.9265, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5856988147642468e-05, + "loss": 3.9022, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5848602200131948e-05, + "loss": 3.906, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584021625262143e-05, + "loss": 3.9231, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583184668391464e-05, + "loss": 3.9185, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582346073640412e-05, + "loss": 3.9162, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.58150747888936e-05, + "loss": 3.9077, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580668884138308e-05, + "loss": 3.9175, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.579830289387256e-05, + "loss": 3.9015, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.578991694636204e-05, + "loss": 3.9216, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781530998851523e-05, + "loss": 3.9154, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773145051340997e-05, + "loss": 3.9258, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5764775482634213e-05, + "loss": 3.9179, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5756389535123692e-05, + "loss": 3.9105, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5748003587613172e-05, + "loss": 3.9063, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5739634018906385e-05, + "loss": 3.9216, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731248071395865e-05, + "loss": 3.9039, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5722862123885345e-05, + "loss": 3.9108, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714476176374825e-05, + "loss": 3.9171, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5706090228864298e-05, + "loss": 3.9155, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5697704281353778e-05, + "loss": 3.9012, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.568931833384326e-05, + "loss": 3.9019, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568093238633274e-05, + "loss": 3.904, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567254643882222e-05, + "loss": 3.9254, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566417687011543e-05, + "loss": 3.9225, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565579092260491e-05, + "loss": 3.91, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564740497509439e-05, + "loss": 3.918, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.563901902758387e-05, + "loss": 3.9142, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5630649458877083e-05, + "loss": 3.9218, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.56222798901703e-05, + "loss": 3.9053, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561389394265977e-05, + "loss": 3.923, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560550799514925e-05, + "loss": 3.9122, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559712204763873e-05, + "loss": 3.9188, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5588736100128215e-05, + "loss": 3.9097, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5580350152617695e-05, + "loss": 3.9174, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5571964205107175e-05, + "loss": 3.9188, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5563578257596655e-05, + "loss": 3.9181, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5555192310086135e-05, + "loss": 3.9038, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5546822741379344e-05, + "loss": 3.9129, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5538436793868824e-05, + "loss": 3.9129, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5530050846358307e-05, + "loss": 3.9156, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5521664898847787e-05, + "loss": 3.9168, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5513295330140996e-05, + "loss": 3.9032, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5504909382630476e-05, + "loss": 3.9167, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5496523435119956e-05, + "loss": 3.9078, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5488137487609436e-05, + "loss": 3.9194, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.547976791890265e-05, + "loss": 3.9003, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547138197139213e-05, + "loss": 3.9153, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546299602388161e-05, + "loss": 3.9227, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454626455174818e-05, + "loss": 3.9108, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446240507664298e-05, + "loss": 3.895, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5437854560153777e-05, + "loss": 3.9114, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5429468612643257e-05, + "loss": 3.9127, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542108266513274e-05, + "loss": 3.921, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541269671762222e-05, + "loss": 3.9155, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54043107701117e-05, + "loss": 3.9043, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539594120140491e-05, + "loss": 3.9062, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538755525389439e-05, + "loss": 3.9176, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.537916930638387e-05, + "loss": 3.8987, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537078335887335e-05, + "loss": 3.9082, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5362397411362833e-05, + "loss": 3.9123, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5354011463852306e-05, + "loss": 3.918, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5345625516341786e-05, + "loss": 3.8953, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5337239568831266e-05, + "loss": 3.9105, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5328870000124482e-05, + "loss": 3.9058, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532048405261396e-05, + "loss": 3.9085, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312114483907174e-05, + "loss": 3.9096, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303728536396654e-05, + "loss": 3.9043, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295342588886134e-05, + "loss": 3.9189, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5286956641375607e-05, + "loss": 3.9125, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278570693865087e-05, + "loss": 3.9043, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527018474635457e-05, + "loss": 3.9105, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526181517764778e-05, + "loss": 3.9119, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525342923013726e-05, + "loss": 3.9136, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524504328262674e-05, + "loss": 3.8952, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523665733511622e-05, + "loss": 3.9198, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.52282713876057e-05, + "loss": 3.9089, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.521988544009518e-05, + "loss": 3.9133, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5211499492584663e-05, + "loss": 3.9093, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5203113545074143e-05, + "loss": 3.9133, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5194727597563623e-05, + "loss": 3.9031, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518637440766056e-05, + "loss": 3.9058, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5178004838953777e-05, + "loss": 3.8983, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5169618891443254e-05, + "loss": 3.9212, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5161232943932734e-05, + "loss": 3.9157, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5152846996422214e-05, + "loss": 3.9135, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5144461048911693e-05, + "loss": 3.9022, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5136075101401173e-05, + "loss": 3.9169, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5127689153890653e-05, + "loss": 3.9185, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5119303206380133e-05, + "loss": 3.9067, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5110917258869617e-05, + "loss": 3.9103, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5102531311359097e-05, + "loss": 3.9153, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5094145363848577e-05, + "loss": 3.9125, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5085759416338057e-05, + "loss": 3.9176, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077389847631266e-05, + "loss": 3.9034, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5069020278924478e-05, + "loss": 3.9143, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5060634331413958e-05, + "loss": 3.91, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5052248383903438e-05, + "loss": 3.9065, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5043862436392918e-05, + "loss": 3.9247, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5035476488882398e-05, + "loss": 3.9041, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5027090541371878e-05, + "loss": 3.9141, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5018704593861358e-05, + "loss": 3.9132, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501033502515457e-05, + "loss": 3.9145, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 4.049020290374756, + "eval_runtime": 282.1921, + "eval_samples_per_second": 1352.238, + "eval_steps_per_second": 42.258, + "step": 1526383 + }, + { + "epoch": 1.0, + "learning_rate": 2.500194907764405e-05, + "loss": 3.9093, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499357950893726e-05, + "loss": 3.9119, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498519356142674e-05, + "loss": 3.9176, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497680761391622e-05, + "loss": 3.914, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.49684216664057e-05, + "loss": 3.9206, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496003571889518e-05, + "loss": 3.9006, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.495164977138466e-05, + "loss": 3.9113, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494328020267787e-05, + "loss": 3.8961, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4934894255167348e-05, + "loss": 3.9212, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4926508307656828e-05, + "loss": 3.9085, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918122360146308e-05, + "loss": 3.9139, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909752791439524e-05, + "loss": 3.9127, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901383222732733e-05, + "loss": 3.9103, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4892997275222213e-05, + "loss": 3.8994, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4884611327711693e-05, + "loss": 3.9031, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4876225380201173e-05, + "loss": 3.8992, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.486783943269065e-05, + "loss": 3.9075, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4859453485180133e-05, + "loss": 3.905, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4851067537669613e-05, + "loss": 3.9022, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4842681590159093e-05, + "loss": 3.9297, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4834295642648573e-05, + "loss": 3.9046, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4825909695138053e-05, + "loss": 3.9137, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481752374762753e-05, + "loss": 3.9175, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.480913780011701e-05, + "loss": 3.9107, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4800768231410225e-05, + "loss": 3.9055, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792382283899705e-05, + "loss": 3.8976, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4784012715192914e-05, + "loss": 3.9152, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4775626767682394e-05, + "loss": 3.8947, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4767240820171874e-05, + "loss": 3.9031, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4758854872661354e-05, + "loss": 3.9038, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4750501682758296e-05, + "loss": 3.9037, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4742115735247776e-05, + "loss": 3.9163, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4733729787737256e-05, + "loss": 3.909, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4725343840226736e-05, + "loss": 3.9021, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4716974271519948e-05, + "loss": 3.9119, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4708588324009428e-05, + "loss": 3.9215, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4700202376498908e-05, + "loss": 3.899, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4691816428988388e-05, + "loss": 3.9117, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4683430481477868e-05, + "loss": 3.8971, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4675044533967348e-05, + "loss": 3.911, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4666658586456828e-05, + "loss": 3.8998, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4658272638946304e-05, + "loss": 3.9198, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4649886691435788e-05, + "loss": 3.9123, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4641500743925268e-05, + "loss": 3.9045, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4633114796414748e-05, + "loss": 3.9134, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4624728848904228e-05, + "loss": 3.9026, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4616342901393707e-05, + "loss": 3.9142, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4607956953883184e-05, + "loss": 3.898, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4599587385176397e-05, + "loss": 3.8952, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459120143766588e-05, + "loss": 3.9154, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458281549015536e-05, + "loss": 3.9086, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4574429542644836e-05, + "loss": 3.9094, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4566043595134316e-05, + "loss": 3.9003, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4557657647623796e-05, + "loss": 3.9085, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4549271700113276e-05, + "loss": 3.8978, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4540885752602756e-05, + "loss": 3.9122, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.453251618389597e-05, + "loss": 3.907, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.452413023638545e-05, + "loss": 3.9166, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.451574428887493e-05, + "loss": 3.9132, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.450735834136441e-05, + "loss": 3.904, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.449897239385389e-05, + "loss": 3.9009, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4490602825147098e-05, + "loss": 3.9115, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448223325644031e-05, + "loss": 3.8963, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.447384730892979e-05, + "loss": 3.9046, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446546136141927e-05, + "loss": 3.9079, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445707541390875e-05, + "loss": 3.9104, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.444868946639823e-05, + "loss": 3.8931, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.444030351888771e-05, + "loss": 3.8968, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.443191757137719e-05, + "loss": 3.8939, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442353162386667e-05, + "loss": 3.918, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4415162055159882e-05, + "loss": 3.9082, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4406776107649362e-05, + "loss": 3.9059, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.439840653894257e-05, + "loss": 3.9107, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.439002059143205e-05, + "loss": 3.9028, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381634643921535e-05, + "loss": 3.9188, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373265075214744e-05, + "loss": 3.8945, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4364879127704224e-05, + "loss": 3.9163, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4356493180193704e-05, + "loss": 3.9113, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4348107232683184e-05, + "loss": 3.9055, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4339721285172664e-05, + "loss": 3.9091, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4331335337662143e-05, + "loss": 3.9052, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4322949390151623e-05, + "loss": 3.9128, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4314563442641103e-05, + "loss": 3.9071, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306177495130583e-05, + "loss": 3.8962, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4297791547620063e-05, + "loss": 3.9085, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4289405600109543e-05, + "loss": 3.8981, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428101965259902e-05, + "loss": 3.9128, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4272666462695965e-05, + "loss": 3.9072, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4264280515185445e-05, + "loss": 3.8953, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4255894567674925e-05, + "loss": 3.9092, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4247508620164405e-05, + "loss": 3.9015, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4239139051457617e-05, + "loss": 3.909, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4230753103947097e-05, + "loss": 3.8935, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4222367156436577e-05, + "loss": 3.908, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4213981208926057e-05, + "loss": 3.9163, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4205595261415537e-05, + "loss": 3.9009, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4197209313905017e-05, + "loss": 3.8904, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4188823366394494e-05, + "loss": 3.9052, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4180437418883974e-05, + "loss": 3.9012, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417206785017719e-05, + "loss": 3.916, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.41636982814704e-05, + "loss": 3.906, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415531233395988e-05, + "loss": 3.9015, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414692638644936e-05, + "loss": 3.8962, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.413854043893884e-05, + "loss": 3.914, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4130154491428318e-05, + "loss": 3.8869, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4121768543917798e-05, + "loss": 3.9, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411339897521101e-05, + "loss": 3.9024, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410501302770049e-05, + "loss": 3.9095, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4096627080189967e-05, + "loss": 3.887, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088241132679447e-05, + "loss": 3.9071, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4079855185168927e-05, + "loss": 3.896, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.407146923765841e-05, + "loss": 3.9016, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406308329014789e-05, + "loss": 3.9007, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405469734263737e-05, + "loss": 3.8954, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404632777393058e-05, + "loss": 3.9123, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.403794182642006e-05, + "loss": 3.9075, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4029572257713272e-05, + "loss": 3.8981, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021186310202752e-05, + "loss": 3.9017, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4012800362692232e-05, + "loss": 3.9021, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4004414415181712e-05, + "loss": 3.9054, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3996028467671192e-05, + "loss": 3.887, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3987642520160672e-05, + "loss": 3.9118, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.397925657265015e-05, + "loss": 3.9003, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3970870625139628e-05, + "loss": 3.9052, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3962501056432844e-05, + "loss": 3.8967, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395411510892232e-05, + "loss": 3.9098, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.39457291614118e-05, + "loss": 3.8987, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393734321390128e-05, + "loss": 3.8981, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3928973645194493e-05, + "loss": 3.8898, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3920604076487706e-05, + "loss": 3.9132, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3912218128977186e-05, + "loss": 3.9053, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903832181466665e-05, + "loss": 3.9065, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3895446233956145e-05, + "loss": 3.8972, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3887060286445622e-05, + "loss": 3.9103, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3878674338935102e-05, + "loss": 3.9115, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3870288391424582e-05, + "loss": 3.9008, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3861902443914065e-05, + "loss": 3.9004, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3853532875207274e-05, + "loss": 3.9077, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3845146927696754e-05, + "loss": 3.9086, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3836777358989967e-05, + "loss": 3.9098, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3828391411479443e-05, + "loss": 3.8968, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3820005463968927e-05, + "loss": 3.9067, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3811619516458407e-05, + "loss": 3.9011, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3803233568947887e-05, + "loss": 3.9032, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3794847621437367e-05, + "loss": 3.9106, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786461673926847e-05, + "loss": 3.9, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3778075726416327e-05, + "loss": 3.9079, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769706157709536e-05, + "loss": 3.9003, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761336589002748e-05, + "loss": 3.9112, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 4.04701566696167, + "eval_runtime": 282.1669, + "eval_samples_per_second": 1352.359, + "eval_steps_per_second": 42.262, + "step": 1602703 + }, + { + "epoch": 2.0, + "learning_rate": 2.3752950641492228e-05, + "loss": 3.903, + "step": 1603072 + }, + { + "epoch": 2.0, + "learning_rate": 2.3744564693981708e-05, + "loss": 3.9054, + "step": 1603584 + }, + { + "epoch": 2.0, + "learning_rate": 2.3736178746471188e-05, + "loss": 3.908, + "step": 1604096 + }, + { + "epoch": 2.0, + "learning_rate": 2.3727792798960668e-05, + "loss": 3.9065, + "step": 1604608 + }, + { + "epoch": 2.0, + "learning_rate": 2.3719406851450148e-05, + "loss": 3.9134, + "step": 1605120 + }, + { + "epoch": 2.0, + "learning_rate": 2.3711020903939628e-05, + "loss": 3.8952, + "step": 1605632 + }, + { + "epoch": 2.0, + "learning_rate": 2.3702634956429108e-05, + "loss": 3.9009, + "step": 1606144 + }, + { + "epoch": 2.0, + "learning_rate": 2.369426538772232e-05, + "loss": 3.8905, + "step": 1606656 + }, + { + "epoch": 2.0, + "learning_rate": 2.36858794402118e-05, + "loss": 3.9112, + "step": 1607168 + }, + { + "epoch": 2.0, + "learning_rate": 2.3677493492701277e-05, + "loss": 3.9045, + "step": 1607680 + }, + { + "epoch": 2.0, + "learning_rate": 2.3669107545190757e-05, + "loss": 3.9074, + "step": 1608192 + }, + { + "epoch": 2.0, + "learning_rate": 2.3660721597680237e-05, + "loss": 3.9031, + "step": 1608704 + }, + { + "epoch": 2.0, + "learning_rate": 2.3652368407777182e-05, + "loss": 3.9, + "step": 1609216 + }, + { + "epoch": 2.0, + "learning_rate": 2.364398246026666e-05, + "loss": 3.8968, + "step": 1609728 + }, + { + "epoch": 2.0, + "learning_rate": 2.363559651275614e-05, + "loss": 3.9004, + "step": 1610240 + }, + { + "epoch": 2.0, + "learning_rate": 2.362721056524562e-05, + "loss": 3.886, + "step": 1610752 + }, + { + "epoch": 2.0, + "learning_rate": 2.3618824617735098e-05, + "loss": 3.9016, + "step": 1611264 + }, + { + "epoch": 2.0, + "learning_rate": 2.3610455049028314e-05, + "loss": 3.8964, + "step": 1611776 + }, + { + "epoch": 2.0, + "learning_rate": 2.3602069101517794e-05, + "loss": 3.8941, + "step": 1612288 + }, + { + "epoch": 2.0, + "learning_rate": 2.3593683154007274e-05, + "loss": 3.9269, + "step": 1612800 + }, + { + "epoch": 2.0, + "learning_rate": 2.358529720649675e-05, + "loss": 3.8982, + "step": 1613312 + }, + { + "epoch": 2.0, + "learning_rate": 2.357691125898623e-05, + "loss": 3.9064, + "step": 1613824 + }, + { + "epoch": 2.0, + "learning_rate": 2.356852531147571e-05, + "loss": 3.9066, + "step": 1614336 + }, + { + "epoch": 2.0, + "learning_rate": 2.356013936396519e-05, + "loss": 3.9054, + "step": 1614848 + }, + { + "epoch": 2.0, + "learning_rate": 2.3551753416454674e-05, + "loss": 3.8971, + "step": 1615360 + }, + { + "epoch": 2.0, + "learning_rate": 2.3543367468944154e-05, + "loss": 3.8942, + "step": 1615872 + }, + { + "epoch": 2.0, + "learning_rate": 2.3534997900237363e-05, + "loss": 3.9043, + "step": 1616384 + }, + { + "epoch": 2.0, + "learning_rate": 2.3526628331530572e-05, + "loss": 3.8881, + "step": 1616896 + }, + { + "epoch": 2.0, + "learning_rate": 2.3518242384020052e-05, + "loss": 3.8969, + "step": 1617408 + }, + { + "epoch": 2.0, + "learning_rate": 2.3509856436509535e-05, + "loss": 3.8927, + "step": 1617920 + }, + { + "epoch": 2.01, + "learning_rate": 2.3501470488999015e-05, + "loss": 3.8998, + "step": 1618432 + }, + { + "epoch": 2.01, + "learning_rate": 2.3493084541488495e-05, + "loss": 3.9044, + "step": 1618944 + }, + { + "epoch": 2.01, + "learning_rate": 2.3484714972781704e-05, + "loss": 3.9015, + "step": 1619456 + }, + { + "epoch": 2.01, + "learning_rate": 2.3476329025271184e-05, + "loss": 3.8986, + "step": 1619968 + }, + { + "epoch": 2.01, + "learning_rate": 2.3467959456564397e-05, + "loss": 3.9025, + "step": 1620480 + }, + { + "epoch": 2.01, + "learning_rate": 2.3459573509053877e-05, + "loss": 3.9095, + "step": 1620992 + }, + { + "epoch": 2.01, + "learning_rate": 2.3451187561543357e-05, + "loss": 3.8941, + "step": 1621504 + }, + { + "epoch": 2.01, + "learning_rate": 2.3442801614032836e-05, + "loss": 3.9055, + "step": 1622016 + }, + { + "epoch": 2.01, + "learning_rate": 2.3434415666522316e-05, + "loss": 3.8896, + "step": 1622528 + }, + { + "epoch": 2.01, + "learning_rate": 2.3426029719011796e-05, + "loss": 3.905, + "step": 1623040 + }, + { + "epoch": 2.01, + "learning_rate": 2.3417643771501276e-05, + "loss": 3.89, + "step": 1623552 + }, + { + "epoch": 2.01, + "learning_rate": 2.3409257823990753e-05, + "loss": 3.9145, + "step": 1624064 + }, + { + "epoch": 2.01, + "learning_rate": 2.3400871876480236e-05, + "loss": 3.9038, + "step": 1624576 + }, + { + "epoch": 2.01, + "learning_rate": 2.339250230777345e-05, + "loss": 3.899, + "step": 1625088 + }, + { + "epoch": 2.01, + "learning_rate": 2.3384116360262925e-05, + "loss": 3.9062, + "step": 1625600 + }, + { + "epoch": 2.01, + "learning_rate": 2.3375730412752405e-05, + "loss": 3.8991, + "step": 1626112 + }, + { + "epoch": 2.01, + "learning_rate": 2.3367360844045618e-05, + "loss": 3.9068, + "step": 1626624 + }, + { + "epoch": 2.01, + "learning_rate": 2.3358974896535098e-05, + "loss": 3.8904, + "step": 1627136 + }, + { + "epoch": 2.01, + "learning_rate": 2.3350588949024578e-05, + "loss": 3.8861, + "step": 1627648 + }, + { + "epoch": 2.01, + "learning_rate": 2.3342203001514058e-05, + "loss": 3.9114, + "step": 1628160 + }, + { + "epoch": 2.01, + "learning_rate": 2.3333817054003538e-05, + "loss": 3.9016, + "step": 1628672 + }, + { + "epoch": 2.01, + "learning_rate": 2.3325431106493018e-05, + "loss": 3.9057, + "step": 1629184 + }, + { + "epoch": 2.01, + "learning_rate": 2.3317045158982497e-05, + "loss": 3.8943, + "step": 1629696 + }, + { + "epoch": 2.01, + "learning_rate": 2.3308659211471977e-05, + "loss": 3.897, + "step": 1630208 + }, + { + "epoch": 2.01, + "learning_rate": 2.330028964276519e-05, + "loss": 3.8898, + "step": 1630720 + }, + { + "epoch": 2.01, + "learning_rate": 2.329190369525467e-05, + "loss": 3.9035, + "step": 1631232 + }, + { + "epoch": 2.01, + "learning_rate": 2.328351774774415e-05, + "loss": 3.8987, + "step": 1631744 + }, + { + "epoch": 2.01, + "learning_rate": 2.327513180023363e-05, + "loss": 3.9096, + "step": 1632256 + }, + { + "epoch": 2.01, + "learning_rate": 2.3266745852723106e-05, + "loss": 3.9038, + "step": 1632768 + }, + { + "epoch": 2.01, + "learning_rate": 2.3258359905212586e-05, + "loss": 3.8956, + "step": 1633280 + }, + { + "epoch": 2.01, + "learning_rate": 2.3249973957702066e-05, + "loss": 3.8957, + "step": 1633792 + }, + { + "epoch": 2.01, + "learning_rate": 2.3241588010191546e-05, + "loss": 3.9052, + "step": 1634304 + }, + { + "epoch": 2.01, + "learning_rate": 2.323323482028849e-05, + "loss": 3.8894, + "step": 1634816 + }, + { + "epoch": 2.01, + "learning_rate": 2.322484887277797e-05, + "loss": 3.8982, + "step": 1635328 + }, + { + "epoch": 2.01, + "learning_rate": 2.321646292526745e-05, + "loss": 3.8974, + "step": 1635840 + }, + { + "epoch": 2.01, + "learning_rate": 2.320807697775693e-05, + "loss": 3.9044, + "step": 1636352 + }, + { + "epoch": 2.01, + "learning_rate": 2.3199691030246408e-05, + "loss": 3.8858, + "step": 1636864 + }, + { + "epoch": 2.01, + "learning_rate": 2.3191337840343353e-05, + "loss": 3.8899, + "step": 1637376 + }, + { + "epoch": 2.01, + "learning_rate": 2.3182951892832833e-05, + "loss": 3.8857, + "step": 1637888 + }, + { + "epoch": 2.01, + "learning_rate": 2.3174565945322313e-05, + "loss": 3.9073, + "step": 1638400 + }, + { + "epoch": 2.01, + "learning_rate": 2.3166179997811793e-05, + "loss": 3.9016, + "step": 1638912 + }, + { + "epoch": 2.01, + "learning_rate": 2.3157794050301272e-05, + "loss": 3.9013, + "step": 1639424 + }, + { + "epoch": 2.01, + "learning_rate": 2.3149408102790752e-05, + "loss": 3.9004, + "step": 1639936 + }, + { + "epoch": 2.01, + "learning_rate": 2.3141022155280232e-05, + "loss": 3.8959, + "step": 1640448 + }, + { + "epoch": 2.01, + "learning_rate": 2.3132636207769712e-05, + "loss": 3.9127, + "step": 1640960 + }, + { + "epoch": 2.01, + "learning_rate": 2.3124266639062925e-05, + "loss": 3.8872, + "step": 1641472 + }, + { + "epoch": 2.01, + "learning_rate": 2.3115880691552405e-05, + "loss": 3.9076, + "step": 1641984 + }, + { + "epoch": 2.01, + "learning_rate": 2.310749474404188e-05, + "loss": 3.9003, + "step": 1642496 + }, + { + "epoch": 2.01, + "learning_rate": 2.309910879653136e-05, + "loss": 3.9001, + "step": 1643008 + }, + { + "epoch": 2.01, + "learning_rate": 2.3090722849020845e-05, + "loss": 3.9058, + "step": 1643520 + }, + { + "epoch": 2.01, + "learning_rate": 2.3082353280314054e-05, + "loss": 3.8994, + "step": 1644032 + }, + { + "epoch": 2.01, + "learning_rate": 2.3073967332803534e-05, + "loss": 3.9025, + "step": 1644544 + }, + { + "epoch": 2.01, + "learning_rate": 2.3065581385293014e-05, + "loss": 3.9042, + "step": 1645056 + }, + { + "epoch": 2.01, + "learning_rate": 2.3057195437782494e-05, + "loss": 3.8868, + "step": 1645568 + }, + { + "epoch": 2.01, + "learning_rate": 2.3048825869075706e-05, + "loss": 3.9044, + "step": 1646080 + }, + { + "epoch": 2.01, + "learning_rate": 2.3040439921565186e-05, + "loss": 3.8951, + "step": 1646592 + }, + { + "epoch": 2.01, + "learning_rate": 2.3032053974054666e-05, + "loss": 3.9044, + "step": 1647104 + }, + { + "epoch": 2.01, + "learning_rate": 2.3023668026544146e-05, + "loss": 3.9011, + "step": 1647616 + }, + { + "epoch": 2.01, + "learning_rate": 2.3015282079033626e-05, + "loss": 3.8898, + "step": 1648128 + }, + { + "epoch": 2.02, + "learning_rate": 2.3006896131523106e-05, + "loss": 3.9001, + "step": 1648640 + }, + { + "epoch": 2.02, + "learning_rate": 2.2998526562816315e-05, + "loss": 3.8986, + "step": 1649152 + }, + { + "epoch": 2.02, + "learning_rate": 2.29901406153058e-05, + "loss": 3.9006, + "step": 1649664 + }, + { + "epoch": 2.02, + "learning_rate": 2.2981754667795278e-05, + "loss": 3.8841, + "step": 1650176 + }, + { + "epoch": 2.02, + "learning_rate": 2.2973368720284758e-05, + "loss": 3.9027, + "step": 1650688 + }, + { + "epoch": 2.02, + "learning_rate": 2.2964982772774235e-05, + "loss": 3.9126, + "step": 1651200 + }, + { + "epoch": 2.02, + "learning_rate": 2.2956596825263715e-05, + "loss": 3.8939, + "step": 1651712 + }, + { + "epoch": 2.02, + "learning_rate": 2.2948210877753195e-05, + "loss": 3.8824, + "step": 1652224 + }, + { + "epoch": 2.02, + "learning_rate": 2.2939824930242675e-05, + "loss": 3.8984, + "step": 1652736 + }, + { + "epoch": 2.02, + "learning_rate": 2.2931455361535887e-05, + "loss": 3.8953, + "step": 1653248 + }, + { + "epoch": 2.02, + "learning_rate": 2.2923069414025367e-05, + "loss": 3.9068, + "step": 1653760 + }, + { + "epoch": 2.02, + "learning_rate": 2.2914683466514847e-05, + "loss": 3.9036, + "step": 1654272 + }, + { + "epoch": 2.02, + "learning_rate": 2.290631389780806e-05, + "loss": 3.8913, + "step": 1654784 + }, + { + "epoch": 2.02, + "learning_rate": 2.289794432910127e-05, + "loss": 3.8949, + "step": 1655296 + }, + { + "epoch": 2.02, + "learning_rate": 2.2889558381590752e-05, + "loss": 3.9014, + "step": 1655808 + }, + { + "epoch": 2.02, + "learning_rate": 2.2881172434080232e-05, + "loss": 3.8805, + "step": 1656320 + }, + { + "epoch": 2.02, + "learning_rate": 2.287278648656971e-05, + "loss": 3.895, + "step": 1656832 + }, + { + "epoch": 2.02, + "learning_rate": 2.286440053905919e-05, + "loss": 3.8946, + "step": 1657344 + }, + { + "epoch": 2.02, + "learning_rate": 2.285601459154867e-05, + "loss": 3.9027, + "step": 1657856 + }, + { + "epoch": 2.02, + "learning_rate": 2.284762864403815e-05, + "loss": 3.8809, + "step": 1658368 + }, + { + "epoch": 2.02, + "learning_rate": 2.283925907533136e-05, + "loss": 3.8982, + "step": 1658880 + }, + { + "epoch": 2.02, + "learning_rate": 2.283087312782084e-05, + "loss": 3.8907, + "step": 1659392 + }, + { + "epoch": 2.02, + "learning_rate": 2.282248718031032e-05, + "loss": 3.8938, + "step": 1659904 + }, + { + "epoch": 2.02, + "learning_rate": 2.28141012327998e-05, + "loss": 3.8976, + "step": 1660416 + }, + { + "epoch": 2.02, + "learning_rate": 2.280571528528928e-05, + "loss": 3.8873, + "step": 1660928 + }, + { + "epoch": 2.02, + "learning_rate": 2.279732933777876e-05, + "loss": 3.8998, + "step": 1661440 + }, + { + "epoch": 2.02, + "learning_rate": 2.2788943390268237e-05, + "loss": 3.9029, + "step": 1661952 + }, + { + "epoch": 2.02, + "learning_rate": 2.278055744275772e-05, + "loss": 3.8886, + "step": 1662464 + }, + { + "epoch": 2.02, + "learning_rate": 2.27721714952472e-05, + "loss": 3.9025, + "step": 1662976 + }, + { + "epoch": 2.02, + "learning_rate": 2.276378554773668e-05, + "loss": 3.8889, + "step": 1663488 + }, + { + "epoch": 2.02, + "learning_rate": 2.275539960022616e-05, + "loss": 3.9037, + "step": 1664000 + }, + { + "epoch": 2.02, + "learning_rate": 2.274701365271564e-05, + "loss": 3.8845, + "step": 1664512 + }, + { + "epoch": 2.02, + "learning_rate": 2.273864408400885e-05, + "loss": 3.9044, + "step": 1665024 + }, + { + "epoch": 2.02, + "learning_rate": 2.2730274515302062e-05, + "loss": 3.8866, + "step": 1665536 + }, + { + "epoch": 2.02, + "learning_rate": 2.2721888567791542e-05, + "loss": 3.8979, + "step": 1666048 + }, + { + "epoch": 2.02, + "learning_rate": 2.2713502620281022e-05, + "loss": 3.8909, + "step": 1666560 + }, + { + "epoch": 2.02, + "learning_rate": 2.2705116672770502e-05, + "loss": 3.9025, + "step": 1667072 + }, + { + "epoch": 2.02, + "learning_rate": 2.2696730725259982e-05, + "loss": 3.8905, + "step": 1667584 + }, + { + "epoch": 2.02, + "learning_rate": 2.268836115655319e-05, + "loss": 3.897, + "step": 1668096 + }, + { + "epoch": 2.02, + "learning_rate": 2.2679975209042674e-05, + "loss": 3.8781, + "step": 1668608 + }, + { + "epoch": 2.02, + "learning_rate": 2.2671589261532154e-05, + "loss": 3.9127, + "step": 1669120 + }, + { + "epoch": 2.02, + "learning_rate": 2.2663203314021634e-05, + "loss": 3.8942, + "step": 1669632 + }, + { + "epoch": 2.02, + "learning_rate": 2.2654833745314843e-05, + "loss": 3.9028, + "step": 1670144 + }, + { + "epoch": 2.02, + "learning_rate": 2.2646447797804323e-05, + "loss": 3.8864, + "step": 1670656 + }, + { + "epoch": 2.02, + "learning_rate": 2.2638061850293803e-05, + "loss": 3.9053, + "step": 1671168 + }, + { + "epoch": 2.02, + "learning_rate": 2.2629675902783283e-05, + "loss": 3.9028, + "step": 1671680 + }, + { + "epoch": 2.02, + "learning_rate": 2.2621306334076496e-05, + "loss": 3.8924, + "step": 1672192 + }, + { + "epoch": 2.02, + "learning_rate": 2.2612920386565976e-05, + "loss": 3.8935, + "step": 1672704 + }, + { + "epoch": 2.02, + "learning_rate": 2.2604534439055456e-05, + "loss": 3.9024, + "step": 1673216 + }, + { + "epoch": 2.02, + "learning_rate": 2.2596148491544935e-05, + "loss": 3.9008, + "step": 1673728 + }, + { + "epoch": 2.02, + "learning_rate": 2.2587762544034415e-05, + "loss": 3.9062, + "step": 1674240 + }, + { + "epoch": 2.02, + "learning_rate": 2.2579376596523892e-05, + "loss": 3.8839, + "step": 1674752 + }, + { + "epoch": 2.02, + "learning_rate": 2.2571007027817108e-05, + "loss": 3.9004, + "step": 1675264 + }, + { + "epoch": 2.02, + "learning_rate": 2.2562621080306588e-05, + "loss": 3.8924, + "step": 1675776 + }, + { + "epoch": 2.02, + "learning_rate": 2.2554235132796068e-05, + "loss": 3.9009, + "step": 1676288 + }, + { + "epoch": 2.02, + "learning_rate": 2.2545849185285544e-05, + "loss": 3.9026, + "step": 1676800 + }, + { + "epoch": 2.02, + "learning_rate": 2.2537463237775024e-05, + "loss": 3.8871, + "step": 1677312 + }, + { + "epoch": 2.02, + "learning_rate": 2.2529077290264504e-05, + "loss": 3.906, + "step": 1677824 + }, + { + "epoch": 2.02, + "learning_rate": 2.2520691342753984e-05, + "loss": 3.8962, + "step": 1678336 + }, + { + "epoch": 2.02, + "learning_rate": 2.2512305395243468e-05, + "loss": 3.9002, + "step": 1678848 + }, + { + "epoch": 2.03, + "eval_loss": 4.044652938842773, + "eval_runtime": 283.5364, + "eval_samples_per_second": 1345.827, + "eval_steps_per_second": 42.058, + "step": 1679023 + }, + { + "epoch": 0.0, + "learning_rate": 2.2503919447732948e-05, + "loss": 3.8918, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2495533500222427e-05, + "loss": 3.9004, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2487147552711904e-05, + "loss": 3.9022, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2478761605201384e-05, + "loss": 3.8987, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2470375657690864e-05, + "loss": 3.9056, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2461989710180344e-05, + "loss": 3.8926, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2453603762669824e-05, + "loss": 3.8891, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2445217815159307e-05, + "loss": 3.8862, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2436831867648784e-05, + "loss": 3.9027, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2428445920138264e-05, + "loss": 3.8994, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2420059972627744e-05, + "loss": 3.8973, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2411674025117224e-05, + "loss": 3.8991, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2403304456410433e-05, + "loss": 3.8884, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2394918508899916e-05, + "loss": 3.8897, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2386532561389396e-05, + "loss": 3.8934, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2378146613878876e-05, + "loss": 3.8818, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369760666368356e-05, + "loss": 3.896, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361374718857836e-05, + "loss": 3.8841, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2352988771347316e-05, + "loss": 3.889, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2344602823836792e-05, + "loss": 3.924, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2336233255130008e-05, + "loss": 3.8913, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2327847307619488e-05, + "loss": 3.8972, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2319461360108965e-05, + "loss": 3.9, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2311075412598445e-05, + "loss": 3.9012, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302689465087925e-05, + "loss": 3.8851, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2294303517577405e-05, + "loss": 3.8931, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2285917570066885e-05, + "loss": 3.8961, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2277531622556368e-05, + "loss": 3.8815, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2269162053849577e-05, + "loss": 3.891, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260776106339057e-05, + "loss": 3.8862, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252390158828537e-05, + "loss": 3.8938, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2244004211318017e-05, + "loss": 3.9014, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223563464261123e-05, + "loss": 3.8945, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222726507390444e-05, + "loss": 3.8934, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.221889550519765e-05, + "loss": 3.8939, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221050955768713e-05, + "loss": 3.9013, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220212361017661e-05, + "loss": 3.8872, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219373766266609e-05, + "loss": 3.9023, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218535171515557e-05, + "loss": 3.8784, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217696576764505e-05, + "loss": 3.9006, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.216857982013453e-05, + "loss": 3.8802, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216019387262401e-05, + "loss": 3.9091, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215182430391722e-05, + "loss": 3.8974, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2143454735210432e-05, + "loss": 3.8943, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2135068787699912e-05, + "loss": 3.8961, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126682840189392e-05, + "loss": 3.8936, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2118296892678872e-05, + "loss": 3.8969, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2109910945168352e-05, + "loss": 3.8873, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210154137646156e-05, + "loss": 3.8745, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2093155428951045e-05, + "loss": 3.9086, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084769481440524e-05, + "loss": 3.8934, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076383533930004e-05, + "loss": 3.9021, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2067997586419484e-05, + "loss": 3.8848, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2059611638908964e-05, + "loss": 3.8943, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205122569139844e-05, + "loss": 3.8826, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204283974388792e-05, + "loss": 3.8988, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.20344537963774e-05, + "loss": 3.8911, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2026067848866884e-05, + "loss": 3.9047, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017681901356364e-05, + "loss": 3.8983, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009312332649573e-05, + "loss": 3.8853, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2000926385139053e-05, + "loss": 3.8916, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1992540437628533e-05, + "loss": 3.8984, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1984154490118013e-05, + "loss": 3.8815, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1975768542607493e-05, + "loss": 3.8904, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1967415352704438e-05, + "loss": 3.8922, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1959029405193915e-05, + "loss": 3.9026, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950643457683395e-05, + "loss": 3.8749, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1942257510172875e-05, + "loss": 3.8837, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1933887941466087e-05, + "loss": 3.8812, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1925501993955567e-05, + "loss": 3.8949, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1917116046445047e-05, + "loss": 3.8966, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1908730098934527e-05, + "loss": 3.8947, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1900344151424007e-05, + "loss": 3.8946, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1891958203913487e-05, + "loss": 3.8883, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1883572256402967e-05, + "loss": 3.9085, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187520268769618e-05, + "loss": 3.8827, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186681674018566e-05, + "loss": 3.898, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.185843079267514e-05, + "loss": 3.8932, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185004484516462e-05, + "loss": 3.8929, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841658897654096e-05, + "loss": 3.8998, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833272950143576e-05, + "loss": 3.8915, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1824887002633056e-05, + "loss": 3.8935, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181650105512254e-05, + "loss": 3.8997, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.180811510761202e-05, + "loss": 3.8819, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.17997291601015e-05, + "loss": 3.8965, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791359591394708e-05, + "loss": 3.8901, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1782973643884188e-05, + "loss": 3.8973, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774587696373668e-05, + "loss": 3.8903, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766201748863148e-05, + "loss": 3.8846, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.175781580135263e-05, + "loss": 3.8914, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.174944623264584e-05, + "loss": 3.8938, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174106028513532e-05, + "loss": 3.8936, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.17326743376248e-05, + "loss": 3.8805, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1724288390114277e-05, + "loss": 3.895, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1715902442603757e-05, + "loss": 3.9058, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170751649509324e-05, + "loss": 3.8897, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.169913054758272e-05, + "loss": 3.8713, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.16907446000722e-05, + "loss": 3.8904, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168235865256168e-05, + "loss": 3.8908, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167397270505116e-05, + "loss": 3.8965, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.16656195151481e-05, + "loss": 3.8997, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165723356763758e-05, + "loss": 3.8865, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.164884762012706e-05, + "loss": 3.8839, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164046167261654e-05, + "loss": 3.8981, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163207572510602e-05, + "loss": 3.8758, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162370615639923e-05, + "loss": 3.8893, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1615336587692446e-05, + "loss": 3.884, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1606950640181926e-05, + "loss": 3.9005, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598564692671403e-05, + "loss": 3.8759, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1590178745160883e-05, + "loss": 3.8888, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581792797650363e-05, + "loss": 3.8857, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1573406850139843e-05, + "loss": 3.8856, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1565020902629323e-05, + "loss": 3.8898, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1556634955118803e-05, + "loss": 3.8824, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1548249007608283e-05, + "loss": 3.8937, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539863060097762e-05, + "loss": 3.8958, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531493491390975e-05, + "loss": 3.8832, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1523107543880455e-05, + "loss": 3.8985, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151472159636993e-05, + "loss": 3.8822, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150633564885941e-05, + "loss": 3.895, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1497949701348895e-05, + "loss": 3.8806, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489563753838375e-05, + "loss": 3.891, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1481177806327855e-05, + "loss": 3.8805, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472808237621064e-05, + "loss": 3.8914, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1464422290110544e-05, + "loss": 3.8896, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1456036342600024e-05, + "loss": 3.8913, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1447650395089504e-05, + "loss": 3.8827, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1439264447578987e-05, + "loss": 3.8932, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1430894878872196e-05, + "loss": 3.8722, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1422508931361676e-05, + "loss": 3.9013, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1414122983851156e-05, + "loss": 3.8884, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1405737036340636e-05, + "loss": 3.8934, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1397351088830116e-05, + "loss": 3.8823, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1388965141319596e-05, + "loss": 3.902, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138059557261281e-05, + "loss": 3.8951, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137220962510229e-05, + "loss": 3.885, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1363823677591765e-05, + "loss": 3.89, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1355437730081245e-05, + "loss": 3.8953, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1347051782570725e-05, + "loss": 3.8926, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1338665835060205e-05, + "loss": 3.9059, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1330279887549688e-05, + "loss": 3.8763, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1321893940039168e-05, + "loss": 3.8955, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313524371332377e-05, + "loss": 3.8844, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1305138423821857e-05, + "loss": 3.8958, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1296752476311337e-05, + "loss": 3.8904, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.128838290760455e-05, + "loss": 3.8807, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.127999696009403e-05, + "loss": 3.9015, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127161101258351e-05, + "loss": 3.8896, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126322506507299e-05, + "loss": 3.8944, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 4.042142868041992, + "eval_runtime": 283.0635, + "eval_samples_per_second": 1348.076, + "eval_steps_per_second": 42.128, + "step": 1755343 + }, + { + "epoch": 1.0, + "learning_rate": 2.125483911756247e-05, + "loss": 3.8886, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.124646954885568e-05, + "loss": 3.89, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.123808360134516e-05, + "loss": 3.8943, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.122971403263837e-05, + "loss": 3.8944, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122132808512785e-05, + "loss": 3.8981, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121294213761733e-05, + "loss": 3.8883, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120455619010681e-05, + "loss": 3.8816, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119617024259629e-05, + "loss": 3.8796, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.118778429508577e-05, + "loss": 3.8964, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.117939834757525e-05, + "loss": 3.8932, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117101240006473e-05, + "loss": 3.8877, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116262645255421e-05, + "loss": 3.8949, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115425688384742e-05, + "loss": 3.8847, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.11458709363369e-05, + "loss": 3.8849, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113748498882638e-05, + "loss": 3.8856, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1129099041315863e-05, + "loss": 3.8788, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120713093805343e-05, + "loss": 3.8868, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112343525098552e-05, + "loss": 3.8786, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1103957577588032e-05, + "loss": 3.8806, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1095571630077512e-05, + "loss": 3.916, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1087185682566992e-05, + "loss": 3.8857, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078799735056472e-05, + "loss": 3.8902, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070413787545952e-05, + "loss": 3.8931, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106202784003543e-05, + "loss": 3.896, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.105364189252491e-05, + "loss": 3.8765, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104527232381812e-05, + "loss": 3.8868, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.10368863763076e-05, + "loss": 3.8878, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.102850042879708e-05, + "loss": 3.8798, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1020114481286564e-05, + "loss": 3.8788, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1011744912579773e-05, + "loss": 3.8786, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003375343872986e-05, + "loss": 3.89, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0994989396362466e-05, + "loss": 3.894, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0986603448851945e-05, + "loss": 3.8882, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0978217501341425e-05, + "loss": 3.8827, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0969847932634638e-05, + "loss": 3.8904, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0961461985124118e-05, + "loss": 3.8933, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0953076037613594e-05, + "loss": 3.8826, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0944690090103074e-05, + "loss": 3.8946, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0936304142592554e-05, + "loss": 3.8739, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0927918195082034e-05, + "loss": 3.8918, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0919548626375247e-05, + "loss": 3.8754, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0911162678864727e-05, + "loss": 3.9016, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0902776731354207e-05, + "loss": 3.8903, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894390783843687e-05, + "loss": 3.8886, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0886004836333167e-05, + "loss": 3.8896, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0877618888822647e-05, + "loss": 3.8857, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0869232941312127e-05, + "loss": 3.8922, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0860846993801606e-05, + "loss": 3.8831, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085247742509482e-05, + "loss": 3.8636, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.08440914775843e-05, + "loss": 3.9027, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0835721908877508e-05, + "loss": 3.8833, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0827335961366988e-05, + "loss": 3.899, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.08189663926602e-05, + "loss": 3.88, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081058044514968e-05, + "loss": 3.8852, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080219449763916e-05, + "loss": 3.8764, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079380855012864e-05, + "loss": 3.8932, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078542260261812e-05, + "loss": 3.8872, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.07770366551076e-05, + "loss": 3.8935, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.076865070759708e-05, + "loss": 3.897, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0760281138890293e-05, + "loss": 3.8795, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0751895191379773e-05, + "loss": 3.8808, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074350924386925e-05, + "loss": 3.8966, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073512329635873e-05, + "loss": 3.8747, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072675372765194e-05, + "loss": 3.8826, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718367780141425e-05, + "loss": 3.8834, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.07099818326309e-05, + "loss": 3.8952, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.070159588512038e-05, + "loss": 3.8717, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.069320993760986e-05, + "loss": 3.8726, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.068482399009934e-05, + "loss": 3.8755, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067643804258882e-05, + "loss": 3.8852, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.06680520950783e-05, + "loss": 3.8903, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.065966614756778e-05, + "loss": 3.8894, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.065128020005726e-05, + "loss": 3.8868, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.064289425254674e-05, + "loss": 3.8805, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.063450830503622e-05, + "loss": 3.9041, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062613873632943e-05, + "loss": 3.8733, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.061775278881891e-05, + "loss": 3.8949, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.060936684130839e-05, + "loss": 3.8887, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0600980893797874e-05, + "loss": 3.8832, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592594946287353e-05, + "loss": 3.8935, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584208998776833e-05, + "loss": 3.8887, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0575823051266313e-05, + "loss": 3.8864, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056743710375579e-05, + "loss": 3.893, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0559067535049002e-05, + "loss": 3.8757, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550681587538482e-05, + "loss": 3.8876, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542295640027966e-05, + "loss": 3.8858, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0533909692517442e-05, + "loss": 3.8918, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525556502614384e-05, + "loss": 3.8826, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0517170555103864e-05, + "loss": 3.8774, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0508784607593344e-05, + "loss": 3.8806, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0500398660082827e-05, + "loss": 3.8913, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0492012712572307e-05, + "loss": 3.8869, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483643143865516e-05, + "loss": 3.8725, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475257196354996e-05, + "loss": 3.8912, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466871248844476e-05, + "loss": 3.8929, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458485301333956e-05, + "loss": 3.8869, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0450099353823436e-05, + "loss": 3.8697, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0441713406312916e-05, + "loss": 3.882, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433327458802396e-05, + "loss": 3.8792, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0424941511291876e-05, + "loss": 3.896, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416571942585085e-05, + "loss": 3.8908, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0408202373878298e-05, + "loss": 3.8795, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.039981642636778e-05, + "loss": 3.8824, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039143047885726e-05, + "loss": 3.8875, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0383044531346737e-05, + "loss": 3.8715, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0374658583836217e-05, + "loss": 3.8815, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036628901512943e-05, + "loss": 3.8753, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.035790306761891e-05, + "loss": 3.895, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.034951712010839e-05, + "loss": 3.8686, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034113117259787e-05, + "loss": 3.8789, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0332761603891082e-05, + "loss": 3.8787, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032437565638056e-05, + "loss": 3.8889, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031598970887004e-05, + "loss": 3.8755, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.030762014016325e-05, + "loss": 3.8768, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299234192652735e-05, + "loss": 3.8877, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.029084824514221e-05, + "loss": 3.8888, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028246229763169e-05, + "loss": 3.8772, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027407635012117e-05, + "loss": 3.8929, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026569040261065e-05, + "loss": 3.8783, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025730445510013e-05, + "loss": 3.88, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.024891850758961e-05, + "loss": 3.8807, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024053256007909e-05, + "loss": 3.8817, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023214661256857e-05, + "loss": 3.8756, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022376066505805e-05, + "loss": 3.8839, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021537471754753e-05, + "loss": 3.884, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020700514884074e-05, + "loss": 3.8849, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.019861920133022e-05, + "loss": 3.8751, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190249632623436e-05, + "loss": 3.8822, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0181863685112916e-05, + "loss": 3.8695, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173477737602392e-05, + "loss": 3.895, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0165091790091872e-05, + "loss": 3.8816, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0156705842581352e-05, + "loss": 3.886, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0148319895070832e-05, + "loss": 3.8756, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0139933947560312e-05, + "loss": 3.8949, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0131564378853524e-05, + "loss": 3.8893, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0123178431343004e-05, + "loss": 3.8783, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114792483832484e-05, + "loss": 3.8842, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0106406536321964e-05, + "loss": 3.8874, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0098036967615173e-05, + "loss": 3.8857, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0089651020104657e-05, + "loss": 3.9007, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081265072594137e-05, + "loss": 3.8691, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072879125083617e-05, + "loss": 3.8903, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064493177573097e-05, + "loss": 3.8819, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0056107230062573e-05, + "loss": 3.8878, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047737661355786e-05, + "loss": 3.8818, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0039351713845266e-05, + "loss": 3.8806, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0030965766334746e-05, + "loss": 3.8906, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0022579818824226e-05, + "loss": 3.8864, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0014193871313705e-05, + "loss": 3.885, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 4.040116310119629, + "eval_runtime": 291.6604, + "eval_samples_per_second": 1308.34, + "eval_steps_per_second": 40.887, + "step": 1831663 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005807923803185e-05, + "loss": 3.8884, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997421976292665e-05, + "loss": 3.8814, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9989036028782145e-05, + "loss": 3.8869, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980650081271625e-05, + "loss": 3.8886, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972264133761105e-05, + "loss": 3.8948, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9963878186250585e-05, + "loss": 3.8757, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955492238740065e-05, + "loss": 3.8759, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9947106291229545e-05, + "loss": 3.8765, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938720343719025e-05, + "loss": 3.8861, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930334396208505e-05, + "loss": 3.8909, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9921948448697985e-05, + "loss": 3.8769, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991356250118746e-05, + "loss": 3.8874, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9905192932480677e-05, + "loss": 3.8819, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896806984970157e-05, + "loss": 3.8759, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888421037459634e-05, + "loss": 3.8814, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9880035089949114e-05, + "loss": 3.8693, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871649142438594e-05, + "loss": 3.8821, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863263194928074e-05, + "loss": 3.8729, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9854877247417554e-05, + "loss": 3.8744, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9846491299907037e-05, + "loss": 3.9069, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9838105352396517e-05, + "loss": 3.883, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829719404885994e-05, + "loss": 3.8806, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9821333457375474e-05, + "loss": 3.8857, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9812947509864954e-05, + "loss": 3.8897, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.98045943199619e-05, + "loss": 3.8697, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979620837245138e-05, + "loss": 3.88, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.978782242494086e-05, + "loss": 3.8827, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.977943647743034e-05, + "loss": 3.8748, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9771050529919815e-05, + "loss": 3.8714, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762664582409295e-05, + "loss": 3.8774, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9754278634898775e-05, + "loss": 3.8795, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974590906619199e-05, + "loss": 3.8893, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9737523118681467e-05, + "loss": 3.8818, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9729137171170947e-05, + "loss": 3.8774, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972076760246416e-05, + "loss": 3.8824, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9712381654953636e-05, + "loss": 3.8844, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970399570744312e-05, + "loss": 3.8801, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.96956097599326e-05, + "loss": 3.8835, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968722381242208e-05, + "loss": 3.8681, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.967883786491156e-05, + "loss": 3.8845, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967045191740104e-05, + "loss": 3.8721, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966206596989052e-05, + "loss": 3.8936, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965369640118373e-05, + "loss": 3.8859, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964531045367321e-05, + "loss": 3.88, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9636924506162692e-05, + "loss": 3.8867, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9628538558652172e-05, + "loss": 3.8783, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962015261114165e-05, + "loss": 3.8879, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961176666363113e-05, + "loss": 3.8762, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960338071612061e-05, + "loss": 3.8522, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9594994768610088e-05, + "loss": 3.8961, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9586608821099568e-05, + "loss": 3.8795, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.957823925239278e-05, + "loss": 3.8937, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.956985330488226e-05, + "loss": 3.8723, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956146735737174e-05, + "loss": 3.8794, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955308140986122e-05, + "loss": 3.8685, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954471184115443e-05, + "loss": 3.8852, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9536325893643913e-05, + "loss": 3.8842, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9527939946133393e-05, + "loss": 3.8845, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9519553998622873e-05, + "loss": 3.8938, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9511168051112353e-05, + "loss": 3.8746, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950278210360183e-05, + "loss": 3.8698, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949439615609131e-05, + "loss": 3.8925, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948601020858079e-05, + "loss": 3.873, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9477657018677734e-05, + "loss": 3.8742, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469271071167214e-05, + "loss": 3.8775, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9460885123656694e-05, + "loss": 3.8852, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9452499176146174e-05, + "loss": 3.8695, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944411322863565e-05, + "loss": 3.8714, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943572728112513e-05, + "loss": 3.8653, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9427357712418347e-05, + "loss": 3.8778, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9418971764907827e-05, + "loss": 3.8861, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410585817397303e-05, + "loss": 3.8827, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402199869886783e-05, + "loss": 3.8788, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393813922376263e-05, + "loss": 3.8775, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385427974865743e-05, + "loss": 3.896, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9377058406158956e-05, + "loss": 3.8686, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368672458648435e-05, + "loss": 3.8873, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360286511137915e-05, + "loss": 3.8829, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9351900563627395e-05, + "loss": 3.8731, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343530994920604e-05, + "loss": 3.8899, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9335145047410084e-05, + "loss": 3.8825, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9326759099899568e-05, + "loss": 3.8788, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9318373152389048e-05, + "loss": 3.8863, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9309987204878528e-05, + "loss": 3.8741, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301601257368004e-05, + "loss": 3.875, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293231688661217e-05, + "loss": 3.8806, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284845741150697e-05, + "loss": 3.8859, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276459793640177e-05, + "loss": 3.8745, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9268073846129657e-05, + "loss": 3.8771, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9259687898619137e-05, + "loss": 3.8724, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9251301951108617e-05, + "loss": 3.8848, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9242916003598096e-05, + "loss": 3.8816, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9234530056087576e-05, + "loss": 3.8664, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9226160487380786e-05, + "loss": 3.8828, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921777453987027e-05, + "loss": 3.8875, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.920938859235975e-05, + "loss": 3.8783, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920100264484923e-05, + "loss": 3.8641, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9192633076142438e-05, + "loss": 3.8758, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9184247128631918e-05, + "loss": 3.8711, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917587755992513e-05, + "loss": 3.8904, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.916749161241461e-05, + "loss": 3.8845, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.915910566490409e-05, + "loss": 3.8783, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915071971739357e-05, + "loss": 3.8739, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914233376988305e-05, + "loss": 3.8779, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913396420117626e-05, + "loss": 3.8695, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912557825366574e-05, + "loss": 3.8732, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9117192306155223e-05, + "loss": 3.8686, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9108806358644702e-05, + "loss": 3.887, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9100420411134182e-05, + "loss": 3.8647, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909203446362366e-05, + "loss": 3.8718, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908364851611314e-05, + "loss": 3.8727, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907526256860262e-05, + "loss": 3.8787, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906689299989583e-05, + "loss": 3.8751, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.905850705238531e-05, + "loss": 3.8696, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.905012110487479e-05, + "loss": 3.8809, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9041751536168004e-05, + "loss": 3.8832, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9033365588657484e-05, + "loss": 3.8695, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902497964114696e-05, + "loss": 3.8817, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901659369363644e-05, + "loss": 3.8741, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9008207746125924e-05, + "loss": 3.8773, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999821798615404e-05, + "loss": 3.8737, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991435851104884e-05, + "loss": 3.8758, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8983049903594363e-05, + "loss": 3.8704, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974680334887573e-05, + "loss": 3.8802, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8966294387377053e-05, + "loss": 3.8833, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8957924818670265e-05, + "loss": 3.8771, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949538871159745e-05, + "loss": 3.8697, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8941152923649225e-05, + "loss": 3.8774, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932783354942434e-05, + "loss": 3.8608, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8924397407431914e-05, + "loss": 3.8914, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8916011459921394e-05, + "loss": 3.8704, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8907625512410877e-05, + "loss": 3.8825, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899239564900357e-05, + "loss": 3.8715, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890853617389837e-05, + "loss": 3.89, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882467669879314e-05, + "loss": 3.8806, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8874081722368794e-05, + "loss": 3.8764, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865695774858274e-05, + "loss": 3.879, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857326206151486e-05, + "loss": 3.8786, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8848940258640966e-05, + "loss": 3.8821, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840554311130446e-05, + "loss": 3.8921, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8832168363619926e-05, + "loss": 3.8616, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823782416109406e-05, + "loss": 3.8877, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815412847402615e-05, + "loss": 3.8709, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.88070268998921e-05, + "loss": 3.881, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.879864095238158e-05, + "loss": 3.8766, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.879025500487106e-05, + "loss": 3.8735, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781869057360538e-05, + "loss": 3.8818, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773483109850018e-05, + "loss": 3.884, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8765113541143227e-05, + "loss": 3.8777, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 4.037905693054199, + "eval_runtime": 309.2137, + "eval_samples_per_second": 1234.069, + "eval_steps_per_second": 38.566, + "step": 1907983 + }, + { + "epoch": 1.0, + "learning_rate": 1.8756727593632707e-05, + "loss": 3.8773, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8748341646122187e-05, + "loss": 3.8767, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.873995569861167e-05, + "loss": 3.8833, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8731602508708612e-05, + "loss": 3.8794, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.872321656119809e-05, + "loss": 3.8852, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.871483061368757e-05, + "loss": 3.8748, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870644466617705e-05, + "loss": 3.8688, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8698058718666532e-05, + "loss": 3.8732, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8689672771156012e-05, + "loss": 3.8798, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8681286823645492e-05, + "loss": 3.887, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.867290087613497e-05, + "loss": 3.8739, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866451492862445e-05, + "loss": 3.8808, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.865614535991766e-05, + "loss": 3.8785, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.864775941240714e-05, + "loss": 3.8697, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.863937346489662e-05, + "loss": 3.8727, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.86309875173861e-05, + "loss": 3.8643, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8622617948679313e-05, + "loss": 3.872, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861423200116879e-05, + "loss": 3.8687, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860584605365827e-05, + "loss": 3.8726, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8597460106147753e-05, + "loss": 3.8952, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8589074158637233e-05, + "loss": 3.8811, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8580704589930442e-05, + "loss": 3.8772, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8572318642419922e-05, + "loss": 3.8799, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8563932694909402e-05, + "loss": 3.8851, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8555546747398882e-05, + "loss": 3.8629, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8547160799888362e-05, + "loss": 3.8732, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8538774852377845e-05, + "loss": 3.8791, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8530388904867325e-05, + "loss": 3.8641, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8522002957356802e-05, + "loss": 3.869, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8513633388650014e-05, + "loss": 3.8702, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8505247441139494e-05, + "loss": 3.8734, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8496877872432707e-05, + "loss": 3.8844, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8488491924922187e-05, + "loss": 3.8763, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8480105977411667e-05, + "loss": 3.8772, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8471736408704876e-05, + "loss": 3.8732, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463350461194356e-05, + "loss": 3.8779, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8454964513683836e-05, + "loss": 3.8787, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8446578566173316e-05, + "loss": 3.8748, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8438192618662796e-05, + "loss": 3.8622, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8429806671152276e-05, + "loss": 3.8782, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8421420723641756e-05, + "loss": 3.8685, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8413034776131236e-05, + "loss": 3.8848, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404648828620716e-05, + "loss": 3.8818, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8396262881110195e-05, + "loss": 3.8737, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8387893312403408e-05, + "loss": 3.8822, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8379507364892888e-05, + "loss": 3.8707, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8371121417382368e-05, + "loss": 3.8844, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8362751848675577e-05, + "loss": 3.8715, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8354365901165057e-05, + "loss": 3.8454, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8345979953654537e-05, + "loss": 3.8906, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8337594006144017e-05, + "loss": 3.8759, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.83292080586335e-05, + "loss": 3.8838, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.832082211112298e-05, + "loss": 3.8705, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8312436163612457e-05, + "loss": 3.8697, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830406659490567e-05, + "loss": 3.8616, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829568064739515e-05, + "loss": 3.8784, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287294699884626e-05, + "loss": 3.877, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.827890875237411e-05, + "loss": 3.8764, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.827052280486359e-05, + "loss": 3.8902, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.82621532361568e-05, + "loss": 3.8713, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8253767288646278e-05, + "loss": 3.8665, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8245381341135758e-05, + "loss": 3.8861, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8236995393625238e-05, + "loss": 3.8649, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8228609446114718e-05, + "loss": 3.8632, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.822023987740793e-05, + "loss": 3.8775, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821185392989741e-05, + "loss": 3.8811, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.820346798238689e-05, + "loss": 3.8648, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819508203487637e-05, + "loss": 3.8634, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818669608736585e-05, + "loss": 3.8614, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.817831013985533e-05, + "loss": 3.8707, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.816992419234481e-05, + "loss": 3.8828, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8161554623638023e-05, + "loss": 3.8715, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8153168676127503e-05, + "loss": 3.8762, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814479910742071e-05, + "loss": 3.8691, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813641315991019e-05, + "loss": 3.8947, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.812802721239967e-05, + "loss": 3.8635, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8119641264889155e-05, + "loss": 3.8828, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8111255317378635e-05, + "loss": 3.8745, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810286936986811e-05, + "loss": 3.8722, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809448342235759e-05, + "loss": 3.8793, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808609747484707e-05, + "loss": 3.8798, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.807772790614028e-05, + "loss": 3.8762, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8069341958629764e-05, + "loss": 3.8766, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8060956011119244e-05, + "loss": 3.872, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052570063608724e-05, + "loss": 3.8708, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8044184116098204e-05, + "loss": 3.8773, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8035798168587684e-05, + "loss": 3.8763, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8027412221077164e-05, + "loss": 3.8689, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.801902627356664e-05, + "loss": 3.8707, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8010656704859856e-05, + "loss": 3.8669, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8002287136153065e-05, + "loss": 3.8787, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7993901188642545e-05, + "loss": 3.8736, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7985515241132025e-05, + "loss": 3.8609, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7977129293621505e-05, + "loss": 3.8786, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7968759724914717e-05, + "loss": 3.8804, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7960373777404197e-05, + "loss": 3.8764, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7951987829893677e-05, + "loss": 3.8571, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943601882383157e-05, + "loss": 3.8691, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7935215934872637e-05, + "loss": 3.8686, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7926829987362114e-05, + "loss": 3.8805, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7918444039851594e-05, + "loss": 3.8786, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7910058092341074e-05, + "loss": 3.8747, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7901688523634286e-05, + "loss": 3.8717, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7893302576123766e-05, + "loss": 3.8698, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7884916628613246e-05, + "loss": 3.8646, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876530681102726e-05, + "loss": 3.8685, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.786816111239594e-05, + "loss": 3.8649, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.785977516488542e-05, + "loss": 3.8771, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.78513892173749e-05, + "loss": 3.8654, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.784300326986438e-05, + "loss": 3.8604, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783461732235386e-05, + "loss": 3.8698, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782623137484334e-05, + "loss": 3.8677, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.781784542733282e-05, + "loss": 3.8683, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7809459479822295e-05, + "loss": 3.8632, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7801073532311778e-05, + "loss": 3.8787, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779272034240872e-05, + "loss": 3.879, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.77843343948982e-05, + "loss": 3.8652, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777594844738768e-05, + "loss": 3.8747, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.776756249987716e-05, + "loss": 3.8677, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.775917655236664e-05, + "loss": 3.8727, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7750806983659852e-05, + "loss": 3.8715, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7742421036149332e-05, + "loss": 3.8665, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7734035088638812e-05, + "loss": 3.8685, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7725649141128292e-05, + "loss": 3.8672, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771726319361777e-05, + "loss": 3.8788, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.770887724610725e-05, + "loss": 3.8689, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7700491298596732e-05, + "loss": 3.866, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7692138108693674e-05, + "loss": 3.8724, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7683752161183154e-05, + "loss": 3.8564, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7675366213672633e-05, + "loss": 3.8845, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7666980266162113e-05, + "loss": 3.8635, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7658594318651593e-05, + "loss": 3.8819, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7650208371141073e-05, + "loss": 3.8624, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7641822423630553e-05, + "loss": 3.8811, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7633436476120033e-05, + "loss": 3.8766, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7625050528609513e-05, + "loss": 3.868, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7616680959902722e-05, + "loss": 3.8735, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7608295012392202e-05, + "loss": 3.8735, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7599909064881686e-05, + "loss": 3.8769, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7591523117371166e-05, + "loss": 3.8888, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7583153548664375e-05, + "loss": 3.8548, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7574767601153855e-05, + "loss": 3.876, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7566398032447064e-05, + "loss": 3.8692, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7558012084936547e-05, + "loss": 3.8776, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7549626137426027e-05, + "loss": 3.8716, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7541240189915507e-05, + "loss": 3.8732, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7532854242404987e-05, + "loss": 3.872, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7524484673698196e-05, + "loss": 3.8779, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7516098726187676e-05, + "loss": 3.8724, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 4.035691738128662, + "eval_runtime": 309.7321, + "eval_samples_per_second": 1232.004, + "eval_steps_per_second": 38.501, + "step": 1984303 + }, + { + "epoch": 2.0, + "learning_rate": 1.7507712778677156e-05, + "loss": 3.8716, + "step": 1984512 + }, + { + "epoch": 2.0, + "learning_rate": 1.7499326831166636e-05, + "loss": 3.8716, + "step": 1985024 + }, + { + "epoch": 2.0, + "learning_rate": 1.749094088365612e-05, + "loss": 3.8744, + "step": 1985536 + }, + { + "epoch": 2.0, + "learning_rate": 1.748257131494933e-05, + "loss": 3.8749, + "step": 1986048 + }, + { + "epoch": 2.0, + "learning_rate": 1.7474201746242537e-05, + "loss": 3.8797, + "step": 1986560 + }, + { + "epoch": 2.0, + "learning_rate": 1.7465815798732017e-05, + "loss": 3.8671, + "step": 1987072 + }, + { + "epoch": 2.0, + "learning_rate": 1.7457446230025233e-05, + "loss": 3.8677, + "step": 1987584 + }, + { + "epoch": 2.0, + "learning_rate": 1.744906028251471e-05, + "loss": 3.8684, + "step": 1988096 + }, + { + "epoch": 2.0, + "learning_rate": 1.744067433500419e-05, + "loss": 3.8717, + "step": 1988608 + }, + { + "epoch": 2.0, + "learning_rate": 1.743228838749367e-05, + "loss": 3.8832, + "step": 1989120 + }, + { + "epoch": 2.0, + "learning_rate": 1.742390243998315e-05, + "loss": 3.8678, + "step": 1989632 + }, + { + "epoch": 2.0, + "learning_rate": 1.741551649247263e-05, + "loss": 3.8718, + "step": 1990144 + }, + { + "epoch": 2.0, + "learning_rate": 1.7407146923765842e-05, + "loss": 3.8766, + "step": 1990656 + }, + { + "epoch": 2.0, + "learning_rate": 1.7398760976255322e-05, + "loss": 3.8641, + "step": 1991168 + }, + { + "epoch": 2.0, + "learning_rate": 1.7390375028744802e-05, + "loss": 3.8712, + "step": 1991680 + }, + { + "epoch": 2.0, + "learning_rate": 1.7381989081234282e-05, + "loss": 3.8598, + "step": 1992192 + }, + { + "epoch": 2.0, + "learning_rate": 1.7373603133723762e-05, + "loss": 3.8632, + "step": 1992704 + }, + { + "epoch": 2.0, + "learning_rate": 1.7365217186213242e-05, + "loss": 3.8669, + "step": 1993216 + }, + { + "epoch": 2.0, + "learning_rate": 1.735683123870272e-05, + "loss": 3.8644, + "step": 1993728 + }, + { + "epoch": 2.0, + "learning_rate": 1.7348445291192202e-05, + "loss": 3.8851, + "step": 1994240 + }, + { + "epoch": 2.0, + "learning_rate": 1.7340059343681682e-05, + "loss": 3.8792, + "step": 1994752 + }, + { + "epoch": 2.0, + "learning_rate": 1.7331673396171162e-05, + "loss": 3.8726, + "step": 1995264 + }, + { + "epoch": 2.0, + "learning_rate": 1.732328744866064e-05, + "loss": 3.8735, + "step": 1995776 + }, + { + "epoch": 2.0, + "learning_rate": 1.731490150115012e-05, + "loss": 3.876, + "step": 1996288 + }, + { + "epoch": 2.0, + "learning_rate": 1.730653193244333e-05, + "loss": 3.8587, + "step": 1996800 + }, + { + "epoch": 2.0, + "learning_rate": 1.729814598493281e-05, + "loss": 3.871, + "step": 1997312 + }, + { + "epoch": 2.0, + "learning_rate": 1.7289760037422294e-05, + "loss": 3.8718, + "step": 1997824 + }, + { + "epoch": 2.0, + "learning_rate": 1.7281374089911774e-05, + "loss": 3.8555, + "step": 1998336 + }, + { + "epoch": 2.0, + "learning_rate": 1.727298814240125e-05, + "loss": 3.8636, + "step": 1998848 + }, + { + "epoch": 2.0, + "learning_rate": 1.726460219489073e-05, + "loss": 3.8643, + "step": 1999360 + }, + { + "epoch": 2.01, + "learning_rate": 1.725621624738021e-05, + "loss": 3.8743, + "step": 1999872 + }, + { + "epoch": 2.01, + "learning_rate": 1.724783029986969e-05, + "loss": 3.8731, + "step": 2000384 + }, + { + "epoch": 2.01, + "learning_rate": 1.7239460731162903e-05, + "loss": 3.8682, + "step": 2000896 + }, + { + "epoch": 2.01, + "learning_rate": 1.7231074783652383e-05, + "loss": 3.8773, + "step": 2001408 + }, + { + "epoch": 2.01, + "learning_rate": 1.7222705214945595e-05, + "loss": 3.8641, + "step": 2001920 + }, + { + "epoch": 2.01, + "learning_rate": 1.7214319267435072e-05, + "loss": 3.876, + "step": 2002432 + }, + { + "epoch": 2.01, + "learning_rate": 1.7205933319924552e-05, + "loss": 3.8765, + "step": 2002944 + }, + { + "epoch": 2.01, + "learning_rate": 1.7197547372414032e-05, + "loss": 3.8645, + "step": 2003456 + }, + { + "epoch": 2.01, + "learning_rate": 1.7189161424903512e-05, + "loss": 3.8585, + "step": 2003968 + }, + { + "epoch": 2.01, + "learning_rate": 1.7180775477392995e-05, + "loss": 3.8695, + "step": 2004480 + }, + { + "epoch": 2.01, + "learning_rate": 1.7172389529882475e-05, + "loss": 3.8637, + "step": 2004992 + }, + { + "epoch": 2.01, + "learning_rate": 1.7164003582371955e-05, + "loss": 3.8781, + "step": 2005504 + }, + { + "epoch": 2.01, + "learning_rate": 1.715561763486143e-05, + "loss": 3.8723, + "step": 2006016 + }, + { + "epoch": 2.01, + "learning_rate": 1.7147248066154644e-05, + "loss": 3.8728, + "step": 2006528 + }, + { + "epoch": 2.01, + "learning_rate": 1.713889487625159e-05, + "loss": 3.8732, + "step": 2007040 + }, + { + "epoch": 2.01, + "learning_rate": 1.713050892874107e-05, + "loss": 3.8657, + "step": 2007552 + }, + { + "epoch": 2.01, + "learning_rate": 1.7122122981230546e-05, + "loss": 3.8771, + "step": 2008064 + }, + { + "epoch": 2.01, + "learning_rate": 1.7113737033720026e-05, + "loss": 3.8725, + "step": 2008576 + }, + { + "epoch": 2.01, + "learning_rate": 1.7105351086209506e-05, + "loss": 3.8428, + "step": 2009088 + }, + { + "epoch": 2.01, + "learning_rate": 1.7096965138698985e-05, + "loss": 3.8803, + "step": 2009600 + }, + { + "epoch": 2.01, + "learning_rate": 1.7088579191188465e-05, + "loss": 3.8688, + "step": 2010112 + }, + { + "epoch": 2.01, + "learning_rate": 1.708019324367795e-05, + "loss": 3.8798, + "step": 2010624 + }, + { + "epoch": 2.01, + "learning_rate": 1.707180729616743e-05, + "loss": 3.87, + "step": 2011136 + }, + { + "epoch": 2.01, + "learning_rate": 1.7063421348656905e-05, + "loss": 3.866, + "step": 2011648 + }, + { + "epoch": 2.01, + "learning_rate": 1.7055035401146385e-05, + "loss": 3.8558, + "step": 2012160 + }, + { + "epoch": 2.01, + "learning_rate": 1.7046649453635865e-05, + "loss": 3.8729, + "step": 2012672 + }, + { + "epoch": 2.01, + "learning_rate": 1.7038279884929078e-05, + "loss": 3.873, + "step": 2013184 + }, + { + "epoch": 2.01, + "learning_rate": 1.7029893937418558e-05, + "loss": 3.8694, + "step": 2013696 + }, + { + "epoch": 2.01, + "learning_rate": 1.7021507989908038e-05, + "loss": 3.8878, + "step": 2014208 + }, + { + "epoch": 2.01, + "learning_rate": 1.701313842120125e-05, + "loss": 3.8678, + "step": 2014720 + }, + { + "epoch": 2.01, + "learning_rate": 1.7004752473690727e-05, + "loss": 3.8544, + "step": 2015232 + }, + { + "epoch": 2.01, + "learning_rate": 1.6996366526180207e-05, + "loss": 3.884, + "step": 2015744 + }, + { + "epoch": 2.01, + "learning_rate": 1.6987980578669687e-05, + "loss": 3.8609, + "step": 2016256 + }, + { + "epoch": 2.01, + "learning_rate": 1.6979594631159167e-05, + "loss": 3.8576, + "step": 2016768 + }, + { + "epoch": 2.01, + "learning_rate": 1.697120868364865e-05, + "loss": 3.8754, + "step": 2017280 + }, + { + "epoch": 2.01, + "learning_rate": 1.696283911494186e-05, + "loss": 3.8721, + "step": 2017792 + }, + { + "epoch": 2.01, + "learning_rate": 1.695445316743134e-05, + "loss": 3.8613, + "step": 2018304 + }, + { + "epoch": 2.01, + "learning_rate": 1.694606721992082e-05, + "loss": 3.8603, + "step": 2018816 + }, + { + "epoch": 2.01, + "learning_rate": 1.69376812724103e-05, + "loss": 3.8581, + "step": 2019328 + }, + { + "epoch": 2.01, + "learning_rate": 1.692929532489978e-05, + "loss": 3.8618, + "step": 2019840 + }, + { + "epoch": 2.01, + "learning_rate": 1.692090937738926e-05, + "loss": 3.8781, + "step": 2020352 + }, + { + "epoch": 2.01, + "learning_rate": 1.691252342987874e-05, + "loss": 3.8689, + "step": 2020864 + }, + { + "epoch": 2.01, + "learning_rate": 1.690415386117195e-05, + "loss": 3.8697, + "step": 2021376 + }, + { + "epoch": 2.01, + "learning_rate": 1.689576791366143e-05, + "loss": 3.8665, + "step": 2021888 + }, + { + "epoch": 2.01, + "learning_rate": 1.6887381966150908e-05, + "loss": 3.8839, + "step": 2022400 + }, + { + "epoch": 2.01, + "learning_rate": 1.687901239744412e-05, + "loss": 3.8624, + "step": 2022912 + }, + { + "epoch": 2.01, + "learning_rate": 1.6870626449933604e-05, + "loss": 3.8774, + "step": 2023424 + }, + { + "epoch": 2.01, + "learning_rate": 1.6862240502423083e-05, + "loss": 3.8691, + "step": 2023936 + }, + { + "epoch": 2.01, + "learning_rate": 1.685385455491256e-05, + "loss": 3.866, + "step": 2024448 + }, + { + "epoch": 2.01, + "learning_rate": 1.684546860740204e-05, + "loss": 3.8736, + "step": 2024960 + }, + { + "epoch": 2.01, + "learning_rate": 1.683708265989152e-05, + "loss": 3.8736, + "step": 2025472 + }, + { + "epoch": 2.01, + "learning_rate": 1.6828696712381e-05, + "loss": 3.8684, + "step": 2025984 + }, + { + "epoch": 2.01, + "learning_rate": 1.682031076487048e-05, + "loss": 3.8779, + "step": 2026496 + }, + { + "epoch": 2.01, + "learning_rate": 1.681192481735996e-05, + "loss": 3.8623, + "step": 2027008 + }, + { + "epoch": 2.01, + "learning_rate": 1.680353886984944e-05, + "loss": 3.8661, + "step": 2027520 + }, + { + "epoch": 2.01, + "learning_rate": 1.6795169301142652e-05, + "loss": 3.8698, + "step": 2028032 + }, + { + "epoch": 2.01, + "learning_rate": 1.6786783353632132e-05, + "loss": 3.8712, + "step": 2028544 + }, + { + "epoch": 2.01, + "learning_rate": 1.6778397406121612e-05, + "loss": 3.8648, + "step": 2029056 + }, + { + "epoch": 2.01, + "learning_rate": 1.677001145861109e-05, + "loss": 3.8659, + "step": 2029568 + }, + { + "epoch": 2.01, + "learning_rate": 1.6761625511100572e-05, + "loss": 3.8643, + "step": 2030080 + }, + { + "epoch": 2.02, + "learning_rate": 1.6753239563590052e-05, + "loss": 3.8696, + "step": 2030592 + }, + { + "epoch": 2.02, + "learning_rate": 1.6744853616079532e-05, + "loss": 3.8734, + "step": 2031104 + }, + { + "epoch": 2.02, + "learning_rate": 1.673648404737274e-05, + "loss": 3.8548, + "step": 2031616 + }, + { + "epoch": 2.02, + "learning_rate": 1.672809809986222e-05, + "loss": 3.874, + "step": 2032128 + }, + { + "epoch": 2.02, + "learning_rate": 1.67197121523517e-05, + "loss": 3.871, + "step": 2032640 + }, + { + "epoch": 2.02, + "learning_rate": 1.671132620484118e-05, + "loss": 3.8753, + "step": 2033152 + }, + { + "epoch": 2.02, + "learning_rate": 1.670294025733066e-05, + "loss": 3.8478, + "step": 2033664 + }, + { + "epoch": 2.02, + "learning_rate": 1.6694570688623873e-05, + "loss": 3.8674, + "step": 2034176 + }, + { + "epoch": 2.02, + "learning_rate": 1.6686184741113353e-05, + "loss": 3.862, + "step": 2034688 + }, + { + "epoch": 2.02, + "learning_rate": 1.6677798793602833e-05, + "loss": 3.8777, + "step": 2035200 + }, + { + "epoch": 2.02, + "learning_rate": 1.6669412846092313e-05, + "loss": 3.8722, + "step": 2035712 + }, + { + "epoch": 2.02, + "learning_rate": 1.6661026898581793e-05, + "loss": 3.8696, + "step": 2036224 + }, + { + "epoch": 2.02, + "learning_rate": 1.6652640951071273e-05, + "loss": 3.8661, + "step": 2036736 + }, + { + "epoch": 2.02, + "learning_rate": 1.6644271382364486e-05, + "loss": 3.8642, + "step": 2037248 + }, + { + "epoch": 2.02, + "learning_rate": 1.6635885434853966e-05, + "loss": 3.8598, + "step": 2037760 + }, + { + "epoch": 2.02, + "learning_rate": 1.6627499487343446e-05, + "loss": 3.8645, + "step": 2038272 + }, + { + "epoch": 2.02, + "learning_rate": 1.6619129918636655e-05, + "loss": 3.8616, + "step": 2038784 + }, + { + "epoch": 2.02, + "learning_rate": 1.6610743971126135e-05, + "loss": 3.8716, + "step": 2039296 + }, + { + "epoch": 2.02, + "learning_rate": 1.6602358023615615e-05, + "loss": 3.8576, + "step": 2039808 + }, + { + "epoch": 2.02, + "learning_rate": 1.6593972076105095e-05, + "loss": 3.8595, + "step": 2040320 + }, + { + "epoch": 2.02, + "learning_rate": 1.6585586128594575e-05, + "loss": 3.8627, + "step": 2040832 + }, + { + "epoch": 2.02, + "learning_rate": 1.6577216559887787e-05, + "loss": 3.8648, + "step": 2041344 + }, + { + "epoch": 2.02, + "learning_rate": 1.6568830612377267e-05, + "loss": 3.8655, + "step": 2041856 + }, + { + "epoch": 2.02, + "learning_rate": 1.6560444664866744e-05, + "loss": 3.858, + "step": 2042368 + }, + { + "epoch": 2.02, + "learning_rate": 1.6552058717356227e-05, + "loss": 3.8742, + "step": 2042880 + }, + { + "epoch": 2.02, + "learning_rate": 1.6543672769845707e-05, + "loss": 3.8727, + "step": 2043392 + }, + { + "epoch": 2.02, + "learning_rate": 1.6535286822335187e-05, + "loss": 3.8609, + "step": 2043904 + }, + { + "epoch": 2.02, + "learning_rate": 1.6526900874824667e-05, + "loss": 3.8697, + "step": 2044416 + }, + { + "epoch": 2.02, + "learning_rate": 1.6518514927314147e-05, + "loss": 3.8646, + "step": 2044928 + }, + { + "epoch": 2.02, + "learning_rate": 1.6510145358607356e-05, + "loss": 3.8673, + "step": 2045440 + }, + { + "epoch": 2.02, + "learning_rate": 1.6501759411096836e-05, + "loss": 3.8663, + "step": 2045952 + }, + { + "epoch": 2.02, + "learning_rate": 1.6493389842390048e-05, + "loss": 3.8614, + "step": 2046464 + }, + { + "epoch": 2.02, + "learning_rate": 1.6485003894879528e-05, + "loss": 3.867, + "step": 2046976 + }, + { + "epoch": 2.02, + "learning_rate": 1.6476617947369008e-05, + "loss": 3.8643, + "step": 2047488 + }, + { + "epoch": 2.02, + "learning_rate": 1.6468231999858488e-05, + "loss": 3.8707, + "step": 2048000 + }, + { + "epoch": 2.02, + "learning_rate": 1.6459846052347968e-05, + "loss": 3.8651, + "step": 2048512 + }, + { + "epoch": 2.02, + "learning_rate": 1.6451460104837448e-05, + "loss": 3.8586, + "step": 2049024 + }, + { + "epoch": 2.02, + "learning_rate": 1.6443074157326928e-05, + "loss": 3.8683, + "step": 2049536 + }, + { + "epoch": 2.02, + "learning_rate": 1.6434688209816408e-05, + "loss": 3.8529, + "step": 2050048 + }, + { + "epoch": 2.02, + "learning_rate": 1.6426302262305888e-05, + "loss": 3.8796, + "step": 2050560 + }, + { + "epoch": 2.02, + "learning_rate": 1.6417916314795368e-05, + "loss": 3.8597, + "step": 2051072 + }, + { + "epoch": 2.02, + "learning_rate": 1.6409530367284848e-05, + "loss": 3.8783, + "step": 2051584 + }, + { + "epoch": 2.02, + "learning_rate": 1.6401144419774328e-05, + "loss": 3.8576, + "step": 2052096 + }, + { + "epoch": 2.02, + "learning_rate": 1.6392774851067537e-05, + "loss": 3.8756, + "step": 2052608 + }, + { + "epoch": 2.02, + "learning_rate": 1.638438890355702e-05, + "loss": 3.8761, + "step": 2053120 + }, + { + "epoch": 2.02, + "learning_rate": 1.637601933485023e-05, + "loss": 3.8597, + "step": 2053632 + }, + { + "epoch": 2.02, + "learning_rate": 1.636763338733971e-05, + "loss": 3.8678, + "step": 2054144 + }, + { + "epoch": 2.02, + "learning_rate": 1.635924743982919e-05, + "loss": 3.8685, + "step": 2054656 + }, + { + "epoch": 2.02, + "learning_rate": 1.635086149231867e-05, + "loss": 3.8721, + "step": 2055168 + }, + { + "epoch": 2.02, + "learning_rate": 1.634247554480815e-05, + "loss": 3.8785, + "step": 2055680 + }, + { + "epoch": 2.02, + "learning_rate": 1.633408959729763e-05, + "loss": 3.8581, + "step": 2056192 + }, + { + "epoch": 2.02, + "learning_rate": 1.632572002859084e-05, + "loss": 3.8698, + "step": 2056704 + }, + { + "epoch": 2.02, + "learning_rate": 1.631733408108032e-05, + "loss": 3.8658, + "step": 2057216 + }, + { + "epoch": 2.02, + "learning_rate": 1.63089481335698e-05, + "loss": 3.8738, + "step": 2057728 + }, + { + "epoch": 2.02, + "learning_rate": 1.6300562186059278e-05, + "loss": 3.8631, + "step": 2058240 + }, + { + "epoch": 2.02, + "learning_rate": 1.6292176238548758e-05, + "loss": 3.8729, + "step": 2058752 + }, + { + "epoch": 2.02, + "learning_rate": 1.6283790291038238e-05, + "loss": 3.8652, + "step": 2059264 + }, + { + "epoch": 2.02, + "learning_rate": 1.627540434352772e-05, + "loss": 3.8711, + "step": 2059776 + }, + { + "epoch": 2.02, + "learning_rate": 1.626703477482093e-05, + "loss": 3.8686, + "step": 2060288 + }, + { + "epoch": 2.03, + "eval_loss": 4.034547328948975, + "eval_runtime": 311.5943, + "eval_samples_per_second": 1224.64, + "eval_steps_per_second": 38.271, + "step": 2060623 + }, + { + "epoch": 0.0, + "learning_rate": 1.625864882731041e-05, + "loss": 3.8624, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625026287979989e-05, + "loss": 3.8674, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624187693228937e-05, + "loss": 3.8707, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623349098477885e-05, + "loss": 3.8718, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622510503726833e-05, + "loss": 3.8789, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6216719089757813e-05, + "loss": 3.863, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.620833314224729e-05, + "loss": 3.8639, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.619994719473677e-05, + "loss": 3.8643, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619156124722625e-05, + "loss": 3.8669, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618317529971573e-05, + "loss": 3.8738, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617478935220521e-05, + "loss": 3.8614, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6166419783498422e-05, + "loss": 3.8658, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6158050214791635e-05, + "loss": 3.8745, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.614966426728111e-05, + "loss": 3.858, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614127831977059e-05, + "loss": 3.8636, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613289237226007e-05, + "loss": 3.8561, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612450642474955e-05, + "loss": 3.8567, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.611612047723903e-05, + "loss": 3.862, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6107734529728515e-05, + "loss": 3.8618, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6099348582217995e-05, + "loss": 3.8772, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609096263470747e-05, + "loss": 3.8778, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608257668719695e-05, + "loss": 3.8668, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607419073968643e-05, + "loss": 3.8727, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.606580479217591e-05, + "loss": 3.8701, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.605741884466539e-05, + "loss": 3.8576, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6049032897154874e-05, + "loss": 3.8674, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604064694964435e-05, + "loss": 3.8657, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603226100213383e-05, + "loss": 3.8535, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602387505462331e-05, + "loss": 3.8588, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601548910711279e-05, + "loss": 3.8582, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6007119538406e-05, + "loss": 3.8662, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.5998733590895483e-05, + "loss": 3.8675, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5990347643384963e-05, + "loss": 3.8657, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5981961695874443e-05, + "loss": 3.8689, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5973592127167652e-05, + "loss": 3.8584, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5965206179657132e-05, + "loss": 3.8714, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5956836610950345e-05, + "loss": 3.8734, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5948450663439825e-05, + "loss": 3.8585, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5940064715929304e-05, + "loss": 3.8581, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5931678768418784e-05, + "loss": 3.8628, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5923292820908264e-05, + "loss": 3.8617, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5914906873397744e-05, + "loss": 3.8737, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5906520925887224e-05, + "loss": 3.8681, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5898134978376704e-05, + "loss": 3.8694, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5889765409669917e-05, + "loss": 3.87, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5881379462159397e-05, + "loss": 3.8671, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5872993514648877e-05, + "loss": 3.8682, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5864607567138357e-05, + "loss": 3.8661, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5856237998431566e-05, + "loss": 3.8399, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5847852050921046e-05, + "loss": 3.8747, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.583946610341053e-05, + "loss": 3.8611, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5831080155900006e-05, + "loss": 3.8751, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5822694208389486e-05, + "loss": 3.8652, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5814324639682698e-05, + "loss": 3.8582, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5805938692172178e-05, + "loss": 3.8569, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5797552744661655e-05, + "loss": 3.8642, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5789166797151138e-05, + "loss": 3.8742, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5780780849640618e-05, + "loss": 3.8601, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577241128093383e-05, + "loss": 3.8835, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5764025333423307e-05, + "loss": 3.8684, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5755639385912787e-05, + "loss": 3.8442, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5747253438402267e-05, + "loss": 3.8797, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5738867490891747e-05, + "loss": 3.857, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573048154338123e-05, + "loss": 3.8541, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572209559587071e-05, + "loss": 3.8701, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5713709648360187e-05, + "loss": 3.8664, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5705323700849667e-05, + "loss": 3.8548, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.569695413214288e-05, + "loss": 3.8593, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.568856818463236e-05, + "loss": 3.8468, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568018223712184e-05, + "loss": 3.8627, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567181266841505e-05, + "loss": 3.8723, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566342672090453e-05, + "loss": 3.8638, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5655040773394008e-05, + "loss": 3.8658, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5646654825883488e-05, + "loss": 3.8589, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5638268878372968e-05, + "loss": 3.8791, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5629899309666184e-05, + "loss": 3.8627, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562151336215566e-05, + "loss": 3.8727, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561312741464514e-05, + "loss": 3.861, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560474146713462e-05, + "loss": 3.8627, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.55963555196241e-05, + "loss": 3.8677, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.558796957211358e-05, + "loss": 3.8716, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.557958362460306e-05, + "loss": 3.8619, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557119767709254e-05, + "loss": 3.8774, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556281172958202e-05, + "loss": 3.8543, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5554442160875233e-05, + "loss": 3.8605, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5546056213364712e-05, + "loss": 3.864, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.553768664465792e-05, + "loss": 3.8721, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.55293006971474e-05, + "loss": 3.8608, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5520914749636885e-05, + "loss": 3.8619, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5512528802126365e-05, + "loss": 3.8611, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550414285461584e-05, + "loss": 3.8629, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5495773285909054e-05, + "loss": 3.8657, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5487387338398534e-05, + "loss": 3.8533, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5479001390888014e-05, + "loss": 3.8675, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5470615443377494e-05, + "loss": 3.871, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5462229495866974e-05, + "loss": 3.8704, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5453843548356454e-05, + "loss": 3.8471, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5445473979649663e-05, + "loss": 3.8608, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5437088032139143e-05, + "loss": 3.8577, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5428702084628623e-05, + "loss": 3.872, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5420316137118103e-05, + "loss": 3.8727, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5411930189607586e-05, + "loss": 3.8601, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5403560620900795e-05, + "loss": 3.8603, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5395174673390275e-05, + "loss": 3.8651, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5386788725879755e-05, + "loss": 3.8523, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5378402778369235e-05, + "loss": 3.8591, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5370033209662447e-05, + "loss": 3.8597, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5361647262151927e-05, + "loss": 3.8654, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5353261314641407e-05, + "loss": 3.8558, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5344875367130887e-05, + "loss": 3.8513, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5336489419620367e-05, + "loss": 3.8572, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5328119850913576e-05, + "loss": 3.8563, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5319733903403056e-05, + "loss": 3.867, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531134795589254e-05, + "loss": 3.8564, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530296200838202e-05, + "loss": 3.8656, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5294576060871496e-05, + "loss": 3.8655, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5286190113360976e-05, + "loss": 3.8596, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5277804165850456e-05, + "loss": 3.8659, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5269418218339936e-05, + "loss": 3.8594, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526104864963315e-05, + "loss": 3.8627, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5252662702122627e-05, + "loss": 3.8587, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5244276754612108e-05, + "loss": 3.8557, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5235890807101588e-05, + "loss": 3.8631, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227504859591068e-05, + "loss": 3.8581, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5219135290884279e-05, + "loss": 3.8679, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5210749343373759e-05, + "loss": 3.862, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5202363395863239e-05, + "loss": 3.8553, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.519399382715645e-05, + "loss": 3.8558, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.518560787964593e-05, + "loss": 3.8531, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.517722193213541e-05, + "loss": 3.8725, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5168835984624891e-05, + "loss": 3.8588, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.51604664159181e-05, + "loss": 3.8694, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515208046840758e-05, + "loss": 3.8542, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5143694520897062e-05, + "loss": 3.8711, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5135308573386542e-05, + "loss": 3.8719, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5126922625876022e-05, + "loss": 3.8576, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.51185366783655e-05, + "loss": 3.8628, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5110167109658713e-05, + "loss": 3.8609, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5101781162148193e-05, + "loss": 3.8731, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5093395214637673e-05, + "loss": 3.87, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5085009267127151e-05, + "loss": 3.8577, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5076623319616631e-05, + "loss": 3.8588, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.506823737210611e-05, + "loss": 3.8675, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5059851424595592e-05, + "loss": 3.8698, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5051465477085072e-05, + "loss": 3.8557, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5043095908378283e-05, + "loss": 3.8697, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5034709960867763e-05, + "loss": 3.86, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5026324013357243e-05, + "loss": 3.8689, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5017938065846723e-05, + "loss": 3.8636, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 4.032954692840576, + "eval_runtime": 315.7897, + "eval_samples_per_second": 1208.371, + "eval_steps_per_second": 37.762, + "step": 2136943 + }, + { + "epoch": 1.0, + "learning_rate": 1.5009568497139934e-05, + "loss": 3.8589, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5001182549629414e-05, + "loss": 3.8632, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4992796602118894e-05, + "loss": 3.866, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4984427033412105e-05, + "loss": 3.8672, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4976041085901585e-05, + "loss": 3.8731, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4967655138391064e-05, + "loss": 3.8566, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4959269190880546e-05, + "loss": 3.8611, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4950883243370026e-05, + "loss": 3.8598, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4942513674663237e-05, + "loss": 3.863, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4934127727152717e-05, + "loss": 3.863, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4925741779642197e-05, + "loss": 3.862, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4917355832131677e-05, + "loss": 3.8628, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4908986263424888e-05, + "loss": 3.8727, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4900600315914367e-05, + "loss": 3.853, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4892214368403847e-05, + "loss": 3.8559, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4883828420893327e-05, + "loss": 3.8527, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4875442473382806e-05, + "loss": 3.8505, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4867056525872286e-05, + "loss": 3.8608, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4858670578361766e-05, + "loss": 3.8554, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4850284630851247e-05, + "loss": 3.871, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4841915062144456e-05, + "loss": 3.8741, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4833529114633938e-05, + "loss": 3.8626, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4825143167123418e-05, + "loss": 3.8648, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4816757219612898e-05, + "loss": 3.867, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4808387650906109e-05, + "loss": 3.8497, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4800001703395589e-05, + "loss": 3.8684, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4791615755885069e-05, + "loss": 3.8567, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.478324618717828e-05, + "loss": 3.8492, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.477486023966776e-05, + "loss": 3.8603, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.476647429215724e-05, + "loss": 3.8518, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.475808834464672e-05, + "loss": 3.8599, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.474971877593993e-05, + "loss": 3.8632, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.474133282842941e-05, + "loss": 3.8673, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4732946880918892e-05, + "loss": 3.8615, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4724560933408372e-05, + "loss": 3.8542, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471619136470158e-05, + "loss": 3.8681, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4707805417191062e-05, + "loss": 3.872, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4699419469680542e-05, + "loss": 3.8584, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4691033522170022e-05, + "loss": 3.8526, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4682647574659502e-05, + "loss": 3.8571, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4674261627148982e-05, + "loss": 3.8532, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.466587567963846e-05, + "loss": 3.8691, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.465748973212794e-05, + "loss": 3.8627, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.464910378461742e-05, + "loss": 3.8704, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4640717837106902e-05, + "loss": 3.8595, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4632331889596382e-05, + "loss": 3.8606, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4623962320889593e-05, + "loss": 3.8675, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4615576373379073e-05, + "loss": 3.8633, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4607206804672283e-05, + "loss": 3.8367, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4598820857161763e-05, + "loss": 3.8687, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4590434909651243e-05, + "loss": 3.8579, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4582048962140723e-05, + "loss": 3.8731, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4573663014630203e-05, + "loss": 3.8564, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4565277067119685e-05, + "loss": 3.8595, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4556891119609165e-05, + "loss": 3.8477, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4548521550902374e-05, + "loss": 3.8557, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4540135603391856e-05, + "loss": 3.8741, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4531749655881336e-05, + "loss": 3.8567, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4523363708370812e-05, + "loss": 3.8747, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4514977760860294e-05, + "loss": 3.8619, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4506591813349774e-05, + "loss": 3.841, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4498205865839254e-05, + "loss": 3.8749, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4489819918328734e-05, + "loss": 3.8546, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4481450349621944e-05, + "loss": 3.8512, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4473064402111424e-05, + "loss": 3.8637, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4464678454600904e-05, + "loss": 3.861, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4456292507090386e-05, + "loss": 3.8522, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4447906559579866e-05, + "loss": 3.8526, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4439536990873077e-05, + "loss": 3.8445, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4431151043362557e-05, + "loss": 3.8608, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4422765095852037e-05, + "loss": 3.8642, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4414379148341517e-05, + "loss": 3.8589, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4406009579634727e-05, + "loss": 3.8645, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4397623632124207e-05, + "loss": 3.853, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4389237684613687e-05, + "loss": 3.8701, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4380868115906898e-05, + "loss": 3.861, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4372482168396378e-05, + "loss": 3.8673, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4364096220885858e-05, + "loss": 3.8556, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.435571027337534e-05, + "loss": 3.8589, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4347324325864816e-05, + "loss": 3.8645, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4338938378354296e-05, + "loss": 3.8662, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4330552430843778e-05, + "loss": 3.8601, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4322166483333258e-05, + "loss": 3.8704, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4313780535822738e-05, + "loss": 3.8525, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4305410967115949e-05, + "loss": 3.8573, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4297025019605429e-05, + "loss": 3.8571, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4288639072094908e-05, + "loss": 3.8689, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4280253124584388e-05, + "loss": 3.8538, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.42718835558776e-05, + "loss": 3.8604, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.426349760836708e-05, + "loss": 3.8573, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425511166085656e-05, + "loss": 3.8566, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.424672571334604e-05, + "loss": 3.8648, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.423835614463925e-05, + "loss": 3.8498, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4229970197128732e-05, + "loss": 3.8617, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422160062842194e-05, + "loss": 3.8652, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421321468091142e-05, + "loss": 3.8699, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4204828733400902e-05, + "loss": 3.839, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4196442785890382e-05, + "loss": 3.8575, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4188056838379862e-05, + "loss": 3.852, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4179670890869342e-05, + "loss": 3.866, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4171301322162553e-05, + "loss": 3.871, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4162915374652033e-05, + "loss": 3.8582, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4154529427141513e-05, + "loss": 3.8569, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4146143479630994e-05, + "loss": 3.8565, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4137757532120471e-05, + "loss": 3.8525, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4129371584609951e-05, + "loss": 3.8556, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4121002015903165e-05, + "loss": 3.856, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4112616068392645e-05, + "loss": 3.858, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4104230120882123e-05, + "loss": 3.8555, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4095844173371603e-05, + "loss": 3.8488, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4087458225861083e-05, + "loss": 3.8513, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4079072278350563e-05, + "loss": 3.8526, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4070686330840043e-05, + "loss": 3.8608, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4062300383329525e-05, + "loss": 3.849, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4053914435819005e-05, + "loss": 3.8622, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4045544867112214e-05, + "loss": 3.859, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4037158919601696e-05, + "loss": 3.8611, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4028772972091176e-05, + "loss": 3.8601, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4020387024580652e-05, + "loss": 3.8534, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4012017455873866e-05, + "loss": 3.8598, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4003631508363346e-05, + "loss": 3.8553, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3995245560852826e-05, + "loss": 3.8508, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3986859613342304e-05, + "loss": 3.8598, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3978473665831784e-05, + "loss": 3.8557, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3970087718321264e-05, + "loss": 3.8598, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3961701770810744e-05, + "loss": 3.8564, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3953315823300226e-05, + "loss": 3.8491, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3944962633397168e-05, + "loss": 3.8547, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.393657668588665e-05, + "loss": 3.8506, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3928190738376126e-05, + "loss": 3.8625, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3919837548473069e-05, + "loss": 3.8595, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3911451600962549e-05, + "loss": 3.8644, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3903065653452029e-05, + "loss": 3.8521, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.389467970594151e-05, + "loss": 3.8634, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.388629375843099e-05, + "loss": 3.8659, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.387790781092047e-05, + "loss": 3.8561, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3869521863409949e-05, + "loss": 3.8543, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3861135915899429e-05, + "loss": 3.8606, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3852749968388909e-05, + "loss": 3.8676, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3844364020878389e-05, + "loss": 3.8666, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.383597807336787e-05, + "loss": 3.8541, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.382759212585735e-05, + "loss": 3.8512, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.381920617834683e-05, + "loss": 3.86, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3810820230836309e-05, + "loss": 3.8652, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3802450662129521e-05, + "loss": 3.8526, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3794064714619001e-05, + "loss": 3.8678, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3785678767108481e-05, + "loss": 3.8541, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.377729281959796e-05, + "loss": 3.8654, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3768923250891172e-05, + "loss": 3.8617, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 4.031688213348389, + "eval_runtime": 322.1816, + "eval_samples_per_second": 1184.397, + "eval_steps_per_second": 37.013, + "step": 2213263 + }, + { + "epoch": 2.0, + "learning_rate": 1.3760537303380652e-05, + "loss": 3.8562, + "step": 2213376 + }, + { + "epoch": 2.0, + "learning_rate": 1.375215135587013e-05, + "loss": 3.8568, + "step": 2213888 + }, + { + "epoch": 2.0, + "learning_rate": 1.374376540835961e-05, + "loss": 3.8574, + "step": 2214400 + }, + { + "epoch": 2.0, + "learning_rate": 1.373537946084909e-05, + "loss": 3.8671, + "step": 2214912 + }, + { + "epoch": 2.0, + "learning_rate": 1.3727009892142304e-05, + "loss": 3.8669, + "step": 2215424 + }, + { + "epoch": 2.0, + "learning_rate": 1.371862394463178e-05, + "loss": 3.8574, + "step": 2215936 + }, + { + "epoch": 2.0, + "learning_rate": 1.3710254375924995e-05, + "loss": 3.8535, + "step": 2216448 + }, + { + "epoch": 2.0, + "learning_rate": 1.3701868428414475e-05, + "loss": 3.8564, + "step": 2216960 + }, + { + "epoch": 2.0, + "learning_rate": 1.3693482480903955e-05, + "loss": 3.8576, + "step": 2217472 + }, + { + "epoch": 2.0, + "learning_rate": 1.3685096533393433e-05, + "loss": 3.8616, + "step": 2217984 + }, + { + "epoch": 2.0, + "learning_rate": 1.3676710585882913e-05, + "loss": 3.8589, + "step": 2218496 + }, + { + "epoch": 2.0, + "learning_rate": 1.3668324638372393e-05, + "loss": 3.8602, + "step": 2219008 + }, + { + "epoch": 2.0, + "learning_rate": 1.3659955069665604e-05, + "loss": 3.8679, + "step": 2219520 + }, + { + "epoch": 2.0, + "learning_rate": 1.3651569122155084e-05, + "loss": 3.8471, + "step": 2220032 + }, + { + "epoch": 2.0, + "learning_rate": 1.3643183174644564e-05, + "loss": 3.8542, + "step": 2220544 + }, + { + "epoch": 2.0, + "learning_rate": 1.3634797227134043e-05, + "loss": 3.8498, + "step": 2221056 + }, + { + "epoch": 2.0, + "learning_rate": 1.3626411279623525e-05, + "loss": 3.8446, + "step": 2221568 + }, + { + "epoch": 2.0, + "learning_rate": 1.3618025332113005e-05, + "loss": 3.8581, + "step": 2222080 + }, + { + "epoch": 2.0, + "learning_rate": 1.3609639384602485e-05, + "loss": 3.852, + "step": 2222592 + }, + { + "epoch": 2.0, + "learning_rate": 1.3601253437091963e-05, + "loss": 3.8637, + "step": 2223104 + }, + { + "epoch": 2.0, + "learning_rate": 1.3592867489581443e-05, + "loss": 3.8727, + "step": 2223616 + }, + { + "epoch": 2.0, + "learning_rate": 1.3584497920874656e-05, + "loss": 3.858, + "step": 2224128 + }, + { + "epoch": 2.0, + "learning_rate": 1.3576111973364136e-05, + "loss": 3.8625, + "step": 2224640 + }, + { + "epoch": 2.0, + "learning_rate": 1.3567726025853614e-05, + "loss": 3.863, + "step": 2225152 + }, + { + "epoch": 2.0, + "learning_rate": 1.3559340078343094e-05, + "loss": 3.8449, + "step": 2225664 + }, + { + "epoch": 2.0, + "learning_rate": 1.3550954130832574e-05, + "loss": 3.862, + "step": 2226176 + }, + { + "epoch": 2.0, + "learning_rate": 1.3542568183322056e-05, + "loss": 3.852, + "step": 2226688 + }, + { + "epoch": 2.0, + "learning_rate": 1.3534182235811535e-05, + "loss": 3.8493, + "step": 2227200 + }, + { + "epoch": 2.0, + "learning_rate": 1.3525796288301015e-05, + "loss": 3.8543, + "step": 2227712 + }, + { + "epoch": 2.0, + "learning_rate": 1.3517426719594226e-05, + "loss": 3.8477, + "step": 2228224 + }, + { + "epoch": 2.01, + "learning_rate": 1.3509040772083706e-05, + "loss": 3.8535, + "step": 2228736 + }, + { + "epoch": 2.01, + "learning_rate": 1.3500654824573186e-05, + "loss": 3.8571, + "step": 2229248 + }, + { + "epoch": 2.01, + "learning_rate": 1.3492268877062666e-05, + "loss": 3.8644, + "step": 2229760 + }, + { + "epoch": 2.01, + "learning_rate": 1.3483882929552144e-05, + "loss": 3.8582, + "step": 2230272 + }, + { + "epoch": 2.01, + "learning_rate": 1.3475496982041624e-05, + "loss": 3.8493, + "step": 2230784 + }, + { + "epoch": 2.01, + "learning_rate": 1.3467127413334837e-05, + "loss": 3.856, + "step": 2231296 + }, + { + "epoch": 2.01, + "learning_rate": 1.3458741465824318e-05, + "loss": 3.8715, + "step": 2231808 + }, + { + "epoch": 2.01, + "learning_rate": 1.3450355518313795e-05, + "loss": 3.8517, + "step": 2232320 + }, + { + "epoch": 2.01, + "learning_rate": 1.3441969570803275e-05, + "loss": 3.8511, + "step": 2232832 + }, + { + "epoch": 2.01, + "learning_rate": 1.3433583623292757e-05, + "loss": 3.8525, + "step": 2233344 + }, + { + "epoch": 2.01, + "learning_rate": 1.3425214054585966e-05, + "loss": 3.8558, + "step": 2233856 + }, + { + "epoch": 2.01, + "learning_rate": 1.3416828107075446e-05, + "loss": 3.858, + "step": 2234368 + }, + { + "epoch": 2.01, + "learning_rate": 1.340845853836866e-05, + "loss": 3.8599, + "step": 2234880 + }, + { + "epoch": 2.01, + "learning_rate": 1.340007259085814e-05, + "loss": 3.8654, + "step": 2235392 + }, + { + "epoch": 2.01, + "learning_rate": 1.3391686643347618e-05, + "loss": 3.8564, + "step": 2235904 + }, + { + "epoch": 2.01, + "learning_rate": 1.3383300695837098e-05, + "loss": 3.8556, + "step": 2236416 + }, + { + "epoch": 2.01, + "learning_rate": 1.3374914748326578e-05, + "loss": 3.8591, + "step": 2236928 + }, + { + "epoch": 2.01, + "learning_rate": 1.3366528800816058e-05, + "loss": 3.8602, + "step": 2237440 + }, + { + "epoch": 2.01, + "learning_rate": 1.3358142853305538e-05, + "loss": 3.834, + "step": 2237952 + }, + { + "epoch": 2.01, + "learning_rate": 1.334975690579502e-05, + "loss": 3.862, + "step": 2238464 + }, + { + "epoch": 2.01, + "learning_rate": 1.3341387337088229e-05, + "loss": 3.8565, + "step": 2238976 + }, + { + "epoch": 2.01, + "learning_rate": 1.333300138957771e-05, + "loss": 3.8666, + "step": 2239488 + }, + { + "epoch": 2.01, + "learning_rate": 1.332461544206719e-05, + "loss": 3.8536, + "step": 2240000 + }, + { + "epoch": 2.01, + "learning_rate": 1.331622949455667e-05, + "loss": 3.8537, + "step": 2240512 + }, + { + "epoch": 2.01, + "learning_rate": 1.3307843547046148e-05, + "loss": 3.8457, + "step": 2241024 + }, + { + "epoch": 2.01, + "learning_rate": 1.3299457599535628e-05, + "loss": 3.8515, + "step": 2241536 + }, + { + "epoch": 2.01, + "learning_rate": 1.3291071652025108e-05, + "loss": 3.8709, + "step": 2242048 + }, + { + "epoch": 2.01, + "learning_rate": 1.3282702083318321e-05, + "loss": 3.8515, + "step": 2242560 + }, + { + "epoch": 2.01, + "learning_rate": 1.3274316135807799e-05, + "loss": 3.8724, + "step": 2243072 + }, + { + "epoch": 2.01, + "learning_rate": 1.3265930188297279e-05, + "loss": 3.8556, + "step": 2243584 + }, + { + "epoch": 2.01, + "learning_rate": 1.3257544240786759e-05, + "loss": 3.8404, + "step": 2244096 + }, + { + "epoch": 2.01, + "learning_rate": 1.3249158293276239e-05, + "loss": 3.8737, + "step": 2244608 + }, + { + "epoch": 2.01, + "learning_rate": 1.324077234576572e-05, + "loss": 3.8499, + "step": 2245120 + }, + { + "epoch": 2.01, + "learning_rate": 1.323240277705893e-05, + "loss": 3.8434, + "step": 2245632 + }, + { + "epoch": 2.01, + "learning_rate": 1.3224016829548411e-05, + "loss": 3.8561, + "step": 2246144 + }, + { + "epoch": 2.01, + "learning_rate": 1.3215630882037891e-05, + "loss": 3.8597, + "step": 2246656 + }, + { + "epoch": 2.01, + "learning_rate": 1.3207244934527371e-05, + "loss": 3.8456, + "step": 2247168 + }, + { + "epoch": 2.01, + "learning_rate": 1.3198858987016851e-05, + "loss": 3.852, + "step": 2247680 + }, + { + "epoch": 2.01, + "learning_rate": 1.319047303950633e-05, + "loss": 3.8438, + "step": 2248192 + }, + { + "epoch": 2.01, + "learning_rate": 1.318208709199581e-05, + "loss": 3.8477, + "step": 2248704 + }, + { + "epoch": 2.01, + "learning_rate": 1.317370114448529e-05, + "loss": 3.8644, + "step": 2249216 + }, + { + "epoch": 2.01, + "learning_rate": 1.3165331575778504e-05, + "loss": 3.8564, + "step": 2249728 + }, + { + "epoch": 2.01, + "learning_rate": 1.315694562826798e-05, + "loss": 3.8555, + "step": 2250240 + }, + { + "epoch": 2.01, + "learning_rate": 1.314855968075746e-05, + "loss": 3.8488, + "step": 2250752 + }, + { + "epoch": 2.01, + "learning_rate": 1.3140173733246942e-05, + "loss": 3.869, + "step": 2251264 + }, + { + "epoch": 2.01, + "learning_rate": 1.3131836922147616e-05, + "loss": 3.8553, + "step": 2251776 + }, + { + "epoch": 2.01, + "learning_rate": 1.3123450974637094e-05, + "loss": 3.8631, + "step": 2252288 + }, + { + "epoch": 2.01, + "learning_rate": 1.3115065027126574e-05, + "loss": 3.8525, + "step": 2252800 + }, + { + "epoch": 2.01, + "learning_rate": 1.3106679079616054e-05, + "loss": 3.8559, + "step": 2253312 + }, + { + "epoch": 2.01, + "learning_rate": 1.3098293132105536e-05, + "loss": 3.8592, + "step": 2253824 + }, + { + "epoch": 2.01, + "learning_rate": 1.3089907184595016e-05, + "loss": 3.8613, + "step": 2254336 + }, + { + "epoch": 2.01, + "learning_rate": 1.3081521237084496e-05, + "loss": 3.8557, + "step": 2254848 + }, + { + "epoch": 2.01, + "learning_rate": 1.3073135289573976e-05, + "loss": 3.8652, + "step": 2255360 + }, + { + "epoch": 2.01, + "learning_rate": 1.3064749342063454e-05, + "loss": 3.8477, + "step": 2255872 + }, + { + "epoch": 2.01, + "learning_rate": 1.3056379773356666e-05, + "loss": 3.8505, + "step": 2256384 + }, + { + "epoch": 2.01, + "learning_rate": 1.3047993825846146e-05, + "loss": 3.8558, + "step": 2256896 + }, + { + "epoch": 2.01, + "learning_rate": 1.3039607878335625e-05, + "loss": 3.862, + "step": 2257408 + }, + { + "epoch": 2.01, + "learning_rate": 1.3031221930825105e-05, + "loss": 3.8548, + "step": 2257920 + }, + { + "epoch": 2.01, + "learning_rate": 1.3022835983314584e-05, + "loss": 3.8522, + "step": 2258432 + }, + { + "epoch": 2.01, + "learning_rate": 1.3014466414607799e-05, + "loss": 3.85, + "step": 2258944 + }, + { + "epoch": 2.02, + "learning_rate": 1.3006080467097275e-05, + "loss": 3.8589, + "step": 2259456 + }, + { + "epoch": 2.02, + "learning_rate": 1.2997694519586757e-05, + "loss": 3.8528, + "step": 2259968 + }, + { + "epoch": 2.02, + "learning_rate": 1.298932495087997e-05, + "loss": 3.8534, + "step": 2260480 + }, + { + "epoch": 2.02, + "learning_rate": 1.298093900336945e-05, + "loss": 3.8561, + "step": 2260992 + }, + { + "epoch": 2.02, + "learning_rate": 1.2972553055858928e-05, + "loss": 3.8613, + "step": 2261504 + }, + { + "epoch": 2.02, + "learning_rate": 1.2964167108348408e-05, + "loss": 3.8659, + "step": 2262016 + }, + { + "epoch": 2.02, + "learning_rate": 1.2955781160837887e-05, + "loss": 3.8366, + "step": 2262528 + }, + { + "epoch": 2.02, + "learning_rate": 1.2947395213327367e-05, + "loss": 3.8506, + "step": 2263040 + }, + { + "epoch": 2.02, + "learning_rate": 1.2939025644620578e-05, + "loss": 3.8466, + "step": 2263552 + }, + { + "epoch": 2.02, + "learning_rate": 1.2930639697110058e-05, + "loss": 3.8648, + "step": 2264064 + }, + { + "epoch": 2.02, + "learning_rate": 1.2922253749599538e-05, + "loss": 3.8622, + "step": 2264576 + }, + { + "epoch": 2.02, + "learning_rate": 1.291386780208902e-05, + "loss": 3.8551, + "step": 2265088 + }, + { + "epoch": 2.02, + "learning_rate": 1.29054818545785e-05, + "loss": 3.8509, + "step": 2265600 + }, + { + "epoch": 2.02, + "learning_rate": 1.289709590706798e-05, + "loss": 3.8582, + "step": 2266112 + }, + { + "epoch": 2.02, + "learning_rate": 1.2888709959557458e-05, + "loss": 3.8501, + "step": 2266624 + }, + { + "epoch": 2.02, + "learning_rate": 1.288034039085067e-05, + "loss": 3.8489, + "step": 2267136 + }, + { + "epoch": 2.02, + "learning_rate": 1.2871970822143881e-05, + "loss": 3.8502, + "step": 2267648 + }, + { + "epoch": 2.02, + "learning_rate": 1.2863584874633361e-05, + "loss": 3.856, + "step": 2268160 + }, + { + "epoch": 2.02, + "learning_rate": 1.2855198927122841e-05, + "loss": 3.8515, + "step": 2268672 + }, + { + "epoch": 2.02, + "learning_rate": 1.2846812979612321e-05, + "loss": 3.8426, + "step": 2269184 + }, + { + "epoch": 2.02, + "learning_rate": 1.2838427032101801e-05, + "loss": 3.8482, + "step": 2269696 + }, + { + "epoch": 2.02, + "learning_rate": 1.283004108459128e-05, + "loss": 3.8437, + "step": 2270208 + }, + { + "epoch": 2.02, + "learning_rate": 1.282165513708076e-05, + "loss": 3.8594, + "step": 2270720 + }, + { + "epoch": 2.02, + "learning_rate": 1.281326918957024e-05, + "loss": 3.8472, + "step": 2271232 + }, + { + "epoch": 2.02, + "learning_rate": 1.2804883242059721e-05, + "loss": 3.8561, + "step": 2271744 + }, + { + "epoch": 2.02, + "learning_rate": 1.27964972945492e-05, + "loss": 3.8561, + "step": 2272256 + }, + { + "epoch": 2.02, + "learning_rate": 1.278811134703868e-05, + "loss": 3.8557, + "step": 2272768 + }, + { + "epoch": 2.02, + "learning_rate": 1.277972539952816e-05, + "loss": 3.8527, + "step": 2273280 + }, + { + "epoch": 2.02, + "learning_rate": 1.2771339452017639e-05, + "loss": 3.8495, + "step": 2273792 + }, + { + "epoch": 2.02, + "learning_rate": 1.2762953504507119e-05, + "loss": 3.86, + "step": 2274304 + }, + { + "epoch": 2.02, + "learning_rate": 1.2754583935800331e-05, + "loss": 3.8511, + "step": 2274816 + }, + { + "epoch": 2.02, + "learning_rate": 1.274619798828981e-05, + "loss": 3.8447, + "step": 2275328 + }, + { + "epoch": 2.02, + "learning_rate": 1.273781204077929e-05, + "loss": 3.855, + "step": 2275840 + }, + { + "epoch": 2.02, + "learning_rate": 1.272942609326877e-05, + "loss": 3.8521, + "step": 2276352 + }, + { + "epoch": 2.02, + "learning_rate": 1.2721040145758251e-05, + "loss": 3.8538, + "step": 2276864 + }, + { + "epoch": 2.02, + "learning_rate": 1.2712654198247731e-05, + "loss": 3.85, + "step": 2277376 + }, + { + "epoch": 2.02, + "learning_rate": 1.2704268250737211e-05, + "loss": 3.8489, + "step": 2277888 + }, + { + "epoch": 2.02, + "learning_rate": 1.2695898682030422e-05, + "loss": 3.8549, + "step": 2278400 + }, + { + "epoch": 2.02, + "learning_rate": 1.2687512734519902e-05, + "loss": 3.848, + "step": 2278912 + }, + { + "epoch": 2.02, + "learning_rate": 1.2679143165813113e-05, + "loss": 3.8501, + "step": 2279424 + }, + { + "epoch": 2.02, + "learning_rate": 1.2670757218302593e-05, + "loss": 3.8581, + "step": 2279936 + }, + { + "epoch": 2.02, + "learning_rate": 1.2662371270792073e-05, + "loss": 3.8633, + "step": 2280448 + }, + { + "epoch": 2.02, + "learning_rate": 1.2653985323281553e-05, + "loss": 3.8469, + "step": 2280960 + }, + { + "epoch": 2.02, + "learning_rate": 1.2645599375771033e-05, + "loss": 3.8528, + "step": 2281472 + }, + { + "epoch": 2.02, + "learning_rate": 1.2637213428260514e-05, + "loss": 3.8654, + "step": 2281984 + }, + { + "epoch": 2.02, + "learning_rate": 1.262882748074999e-05, + "loss": 3.8528, + "step": 2282496 + }, + { + "epoch": 2.02, + "learning_rate": 1.262044153323947e-05, + "loss": 3.8495, + "step": 2283008 + }, + { + "epoch": 2.02, + "learning_rate": 1.2612055585728952e-05, + "loss": 3.8547, + "step": 2283520 + }, + { + "epoch": 2.02, + "learning_rate": 1.2603669638218432e-05, + "loss": 3.8652, + "step": 2284032 + }, + { + "epoch": 2.02, + "learning_rate": 1.2595283690707912e-05, + "loss": 3.8659, + "step": 2284544 + }, + { + "epoch": 2.02, + "learning_rate": 1.2586897743197392e-05, + "loss": 3.8506, + "step": 2285056 + }, + { + "epoch": 2.02, + "learning_rate": 1.2578528174490603e-05, + "loss": 3.8465, + "step": 2285568 + }, + { + "epoch": 2.02, + "learning_rate": 1.2570142226980083e-05, + "loss": 3.8561, + "step": 2286080 + }, + { + "epoch": 2.02, + "learning_rate": 1.2561756279469563e-05, + "loss": 3.8596, + "step": 2286592 + }, + { + "epoch": 2.02, + "learning_rate": 1.2553370331959045e-05, + "loss": 3.8465, + "step": 2287104 + }, + { + "epoch": 2.02, + "learning_rate": 1.2545000763252254e-05, + "loss": 3.8668, + "step": 2287616 + }, + { + "epoch": 2.02, + "learning_rate": 1.2536614815741735e-05, + "loss": 3.848, + "step": 2288128 + }, + { + "epoch": 2.02, + "learning_rate": 1.2528228868231215e-05, + "loss": 3.8619, + "step": 2288640 + }, + { + "epoch": 2.02, + "learning_rate": 1.2519842920720695e-05, + "loss": 3.8563, + "step": 2289152 + }, + { + "epoch": 2.03, + "eval_loss": 4.030135631561279, + "eval_runtime": 302.6505, + "eval_samples_per_second": 1260.83, + "eval_steps_per_second": 39.402, + "step": 2289583 + }, + { + "epoch": 0.0, + "learning_rate": 1.2511473352013906e-05, + "loss": 3.8853, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2503087404503386e-05, + "loss": 3.8501, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2494701456992864e-05, + "loss": 3.8528, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2486315509482344e-05, + "loss": 3.8607, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2477929561971826e-05, + "loss": 3.8584, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2469543614461306e-05, + "loss": 3.8564, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2461157666950784e-05, + "loss": 3.8485, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2452771719440266e-05, + "loss": 3.8507, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2444385771929746e-05, + "loss": 3.8524, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2435999824419224e-05, + "loss": 3.8609, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2427613876908704e-05, + "loss": 3.8513, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2419227929398186e-05, + "loss": 3.8605, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2410858360691396e-05, + "loss": 3.8658, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2402472413180875e-05, + "loss": 3.8409, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2394086465670356e-05, + "loss": 3.8522, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2385700518159836e-05, + "loss": 3.8427, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2377330949453047e-05, + "loss": 3.8372, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2368945001942527e-05, + "loss": 3.8566, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2360559054432007e-05, + "loss": 3.8449, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2352173106921487e-05, + "loss": 3.859, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2343787159410967e-05, + "loss": 3.8693, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2335401211900447e-05, + "loss": 3.8503, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2327015264389927e-05, + "loss": 3.8635, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2318629316879405e-05, + "loss": 3.8592, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2310243369368887e-05, + "loss": 3.8407, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2301890179465828e-05, + "loss": 3.8575, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.229350423195531e-05, + "loss": 3.8481, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2285118284444788e-05, + "loss": 3.845, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2276732336934268e-05, + "loss": 3.8519, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.226836276822748e-05, + "loss": 3.8437, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.225997682071696e-05, + "loss": 3.8472, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2251590873206439e-05, + "loss": 3.858, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.224320492569592e-05, + "loss": 3.8621, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.22348189781854e-05, + "loss": 3.8497, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2226433030674879e-05, + "loss": 3.8492, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2218063461968091e-05, + "loss": 3.8512, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2209677514457571e-05, + "loss": 3.8692, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2201291566947051e-05, + "loss": 3.8452, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.219290561943653e-05, + "loss": 3.8478, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2184519671926011e-05, + "loss": 3.8508, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2176133724415491e-05, + "loss": 3.8496, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.216774777690497e-05, + "loss": 3.8522, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.215936182939445e-05, + "loss": 3.8549, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.215097588188393e-05, + "loss": 3.8612, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2142589934373409e-05, + "loss": 3.8561, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2134203986862889e-05, + "loss": 3.8505, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.212581803935237e-05, + "loss": 3.8511, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2117448470645581e-05, + "loss": 3.8576, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.210906252313506e-05, + "loss": 3.8305, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2100692954428272e-05, + "loss": 3.8557, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2092307006917752e-05, + "loss": 3.8542, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2083921059407232e-05, + "loss": 3.8636, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2075535111896712e-05, + "loss": 3.8474, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2067149164386192e-05, + "loss": 3.8467, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2058763216875672e-05, + "loss": 3.8474, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2050393648168883e-05, + "loss": 3.8441, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2042007700658363e-05, + "loss": 3.8652, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2033621753147843e-05, + "loss": 3.8506, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2025235805637323e-05, + "loss": 3.8687, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2016849858126803e-05, + "loss": 3.8504, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2008463910616283e-05, + "loss": 3.8379, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2000077963105763e-05, + "loss": 3.8675, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1991692015595242e-05, + "loss": 3.845, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1983322446888453e-05, + "loss": 3.842, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1974936499377933e-05, + "loss": 3.8512, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1966550551867413e-05, + "loss": 3.8558, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1958164604356893e-05, + "loss": 3.8434, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1949795035650106e-05, + "loss": 3.85, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1941425466943316e-05, + "loss": 3.8384, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1933039519432795e-05, + "loss": 3.8431, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1924653571922276e-05, + "loss": 3.8619, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1916267624411756e-05, + "loss": 3.855, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1907881676901236e-05, + "loss": 3.8513, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1899495729390715e-05, + "loss": 3.847, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1891109781880196e-05, + "loss": 3.8619, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1882723834369676e-05, + "loss": 3.8514, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1874354265662887e-05, + "loss": 3.8599, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1865968318152367e-05, + "loss": 3.8483, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1857582370641847e-05, + "loss": 3.8524, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1849196423131327e-05, + "loss": 3.857, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1840810475620807e-05, + "loss": 3.8544, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1832424528110287e-05, + "loss": 3.8546, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1824054959403497e-05, + "loss": 3.8606, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181568539069671e-05, + "loss": 3.8545, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1807299443186188e-05, + "loss": 3.8423, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1798913495675668e-05, + "loss": 3.8523, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.179052754816515e-05, + "loss": 3.8588, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1782141600654628e-05, + "loss": 3.8483, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1773755653144108e-05, + "loss": 3.8506, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1765369705633588e-05, + "loss": 3.8439, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1756983758123068e-05, + "loss": 3.8528, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1748597810612548e-05, + "loss": 3.8505, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.174022824190576e-05, + "loss": 3.8493, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.173184229439524e-05, + "loss": 3.8548, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1723456346884719e-05, + "loss": 3.8519, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1715070399374199e-05, + "loss": 3.8654, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.170668445186368e-05, + "loss": 3.8303, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1698298504353158e-05, + "loss": 3.8492, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1689912556842638e-05, + "loss": 3.8444, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1681526609332118e-05, + "loss": 3.8554, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.16731406618216e-05, + "loss": 3.8625, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1664771093114809e-05, + "loss": 3.8484, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1656401524408022e-05, + "loss": 3.8455, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1648015576897502e-05, + "loss": 3.8539, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1639629629386982e-05, + "loss": 3.8449, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1631243681876461e-05, + "loss": 3.8452, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1622874113169672e-05, + "loss": 3.8447, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1614488165659152e-05, + "loss": 3.8483, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1606102218148632e-05, + "loss": 3.8493, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1597716270638112e-05, + "loss": 3.8427, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1589330323127592e-05, + "loss": 3.8488, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1580944375617072e-05, + "loss": 3.8338, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1572558428106552e-05, + "loss": 3.8577, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1564172480596032e-05, + "loss": 3.8432, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1555786533085512e-05, + "loss": 3.8485, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1547416964378723e-05, + "loss": 3.8525, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1539031016868203e-05, + "loss": 3.8559, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1530645069357683e-05, + "loss": 3.8466, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1522259121847163e-05, + "loss": 3.8493, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1513889553140373e-05, + "loss": 3.8555, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1505503605629853e-05, + "loss": 3.8428, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1497117658119335e-05, + "loss": 3.8402, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1488731710608813e-05, + "loss": 3.8528, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1480345763098293e-05, + "loss": 3.851, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1471959815587773e-05, + "loss": 3.8512, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1463573868077253e-05, + "loss": 3.8445, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1455187920566733e-05, + "loss": 3.8478, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1446834730663676e-05, + "loss": 3.8474, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1438448783153156e-05, + "loss": 3.8436, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1430062835642635e-05, + "loss": 3.8416, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1421676888132116e-05, + "loss": 3.8583, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1413290940621596e-05, + "loss": 3.8581, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1404921371914807e-05, + "loss": 3.8462, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1396535424404287e-05, + "loss": 3.8459, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1388149476893767e-05, + "loss": 3.861, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1379763529383247e-05, + "loss": 3.852, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1371377581872727e-05, + "loss": 3.8447, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1362991634362207e-05, + "loss": 3.8517, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1354605686851687e-05, + "loss": 3.8631, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1346219739341167e-05, + "loss": 3.8575, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1337850170634377e-05, + "loss": 3.8488, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1329480601927588e-05, + "loss": 3.8421, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.132109465441707e-05, + "loss": 3.8546, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.131270870690655e-05, + "loss": 3.8549, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1304322759396028e-05, + "loss": 3.8436, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1295936811885508e-05, + "loss": 3.8643, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.128755086437499e-05, + "loss": 3.846, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1279164916864468e-05, + "loss": 3.8584, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1270778969353948e-05, + "loss": 3.8527, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 4.028681755065918, + "eval_runtime": 289.1191, + "eval_samples_per_second": 1319.84, + "eval_steps_per_second": 41.246, + "step": 2365903 + }, + { + "epoch": 1.0, + "learning_rate": 1.126240940064716e-05, + "loss": 3.851, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.125402345313664e-05, + "loss": 3.8462, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1245637505626119e-05, + "loss": 3.849, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.12372515581156e-05, + "loss": 3.8602, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.122886561060508e-05, + "loss": 3.8555, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1220479663094559e-05, + "loss": 3.8505, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1212093715584038e-05, + "loss": 3.8502, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1203724146877251e-05, + "loss": 3.85, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1195354578170462e-05, + "loss": 3.8486, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1186968630659942e-05, + "loss": 3.8564, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1178582683149422e-05, + "loss": 3.8472, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1170196735638902e-05, + "loss": 3.856, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1161843545735845e-05, + "loss": 3.8611, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1153457598225323e-05, + "loss": 3.8378, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1145071650714805e-05, + "loss": 3.8502, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1136685703204285e-05, + "loss": 3.8387, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1128299755693763e-05, + "loss": 3.8377, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1119913808183243e-05, + "loss": 3.8509, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1111527860672725e-05, + "loss": 3.8437, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1103141913162205e-05, + "loss": 3.8502, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1094755965651683e-05, + "loss": 3.866, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1086370018141163e-05, + "loss": 3.8476, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1077984070630644e-05, + "loss": 3.8569, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1069598123120123e-05, + "loss": 3.8565, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1061212175609603e-05, + "loss": 3.8448, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1052842606902815e-05, + "loss": 3.8538, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1044456659392295e-05, + "loss": 3.8384, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1036070711881773e-05, + "loss": 3.85, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1027684764371255e-05, + "loss": 3.8442, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1019298816860735e-05, + "loss": 3.8387, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1010912869350213e-05, + "loss": 3.8474, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1002543300643426e-05, + "loss": 3.8458, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0994157353132906e-05, + "loss": 3.8601, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0985771405622384e-05, + "loss": 3.851, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0977385458111866e-05, + "loss": 3.8395, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0969015889405076e-05, + "loss": 3.8455, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0960629941894556e-05, + "loss": 3.866, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0952243994384036e-05, + "loss": 3.8406, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0943858046873516e-05, + "loss": 3.8452, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0935472099362996e-05, + "loss": 3.8467, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0927086151852475e-05, + "loss": 3.843, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0918700204341956e-05, + "loss": 3.8492, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0910314256831436e-05, + "loss": 3.8557, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0901928309320916e-05, + "loss": 3.8576, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0893542361810394e-05, + "loss": 3.8518, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0885156414299876e-05, + "loss": 3.8486, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0876770466789356e-05, + "loss": 3.8456, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0868400898082567e-05, + "loss": 3.8592, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0860031329375778e-05, + "loss": 3.8266, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0851645381865257e-05, + "loss": 3.8484, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0843259434354739e-05, + "loss": 3.8533, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0834873486844217e-05, + "loss": 3.8608, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0826487539333697e-05, + "loss": 3.8485, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0818101591823177e-05, + "loss": 3.8374, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0809715644312657e-05, + "loss": 3.8481, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0801346075605868e-05, + "loss": 3.837, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0792960128095348e-05, + "loss": 3.8647, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.078457418058483e-05, + "loss": 3.8452, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0776188233074308e-05, + "loss": 3.8645, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0767802285563788e-05, + "loss": 3.8462, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0759416338053268e-05, + "loss": 3.8374, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0751030390542748e-05, + "loss": 3.8603, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0742660821835959e-05, + "loss": 3.8397, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.073427487432544e-05, + "loss": 3.8423, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.072588892681492e-05, + "loss": 3.8457, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0717502979304398e-05, + "loss": 3.855, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0709117031793878e-05, + "loss": 3.8385, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.070073108428336e-05, + "loss": 3.8452, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0692345136772838e-05, + "loss": 3.8354, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0683959189262318e-05, + "loss": 3.8411, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.067558962055553e-05, + "loss": 3.8586, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.066720367304501e-05, + "loss": 3.8535, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0658834104338221e-05, + "loss": 3.8467, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0650448156827701e-05, + "loss": 3.8462, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0642062209317181e-05, + "loss": 3.8578, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0633676261806661e-05, + "loss": 3.8473, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0625306693099872e-05, + "loss": 3.8537, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0616920745589352e-05, + "loss": 3.8487, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0608534798078832e-05, + "loss": 3.8469, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0600148850568312e-05, + "loss": 3.8564, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0591762903057792e-05, + "loss": 3.8494, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0583376955547272e-05, + "loss": 3.8481, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0574991008036752e-05, + "loss": 3.859, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0566605060526232e-05, + "loss": 3.8547, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0558235491819443e-05, + "loss": 3.8327, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.0549849544308924e-05, + "loss": 3.8488, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0541463596798403e-05, + "loss": 3.8536, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0533077649287882e-05, + "loss": 3.848, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0524708080581095e-05, + "loss": 3.8475, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0516322133070575e-05, + "loss": 3.8443, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0507936185560053e-05, + "loss": 3.8467, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0499550238049533e-05, + "loss": 3.8432, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0491197048146476e-05, + "loss": 3.8509, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0482811100635956e-05, + "loss": 3.8466, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0474425153125436e-05, + "loss": 3.8468, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0466039205614916e-05, + "loss": 3.8671, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0457653258104396e-05, + "loss": 3.8272, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0449267310593876e-05, + "loss": 3.8461, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0440881363083356e-05, + "loss": 3.8444, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0432495415572836e-05, + "loss": 3.8523, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0424125846866049e-05, + "loss": 3.8596, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0415739899355527e-05, + "loss": 3.8499, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0407353951845007e-05, + "loss": 3.8401, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0398968004334487e-05, + "loss": 3.8466, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0390598435627698e-05, + "loss": 3.8472, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0382212488117178e-05, + "loss": 3.8409, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.037382654060666e-05, + "loss": 3.842, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.036544059309614e-05, + "loss": 3.8469, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0357054645585617e-05, + "loss": 3.85, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0348668698075097e-05, + "loss": 3.8355, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0340282750564579e-05, + "loss": 3.8456, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0331896803054057e-05, + "loss": 3.8338, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0323527234347268e-05, + "loss": 3.8532, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.031515766564048e-05, + "loss": 3.8413, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.030677171812996e-05, + "loss": 3.8447, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.029838577061944e-05, + "loss": 3.848, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.028999982310892e-05, + "loss": 3.8509, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.02816138755984e-05, + "loss": 3.8463, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0273227928087879e-05, + "loss": 3.8453, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0264858359381091e-05, + "loss": 3.8511, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0256472411870571e-05, + "loss": 3.8405, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0248086464360051e-05, + "loss": 3.8363, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.0239700516849531e-05, + "loss": 3.8481, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0231330948142742e-05, + "loss": 3.8484, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0222945000632222e-05, + "loss": 3.8511, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0214559053121703e-05, + "loss": 3.8386, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0206173105611182e-05, + "loss": 3.8476, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0197803536904394e-05, + "loss": 3.8438, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0189417589393874e-05, + "loss": 3.8398, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0181031641883352e-05, + "loss": 3.8348, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0172645694372832e-05, + "loss": 3.8575, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0164259746862314e-05, + "loss": 3.8557, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0155873799351794e-05, + "loss": 3.8445, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0147487851841272e-05, + "loss": 3.8447, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0139101904330752e-05, + "loss": 3.8513, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0130732335623965e-05, + "loss": 3.8511, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0122346388113443e-05, + "loss": 3.8439, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0113976819406655e-05, + "loss": 3.8476, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0105590871896135e-05, + "loss": 3.8614, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0097204924385615e-05, + "loss": 3.8509, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0088818976875095e-05, + "loss": 3.8434, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0080449408168306e-05, + "loss": 3.8409, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0072063460657786e-05, + "loss": 3.8518, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0063677513147268e-05, + "loss": 3.8492, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0055291565636746e-05, + "loss": 3.8373, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0046921996929957e-05, + "loss": 3.8614, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0038536049419438e-05, + "loss": 3.8487, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0030150101908917e-05, + "loss": 3.8528, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0021764154398397e-05, + "loss": 3.8468, + "step": 2441728 + }, + { + "epoch": 1.03, + "eval_loss": 4.028616428375244, + "eval_runtime": 291.8727, + "eval_samples_per_second": 1307.389, + "eval_steps_per_second": 40.857, + "step": 2442223 + }, + { + "epoch": 2.0, + "learning_rate": 1.0013378206887877e-05, + "loss": 3.8486, + "step": 2442240 + }, + { + "epoch": 2.0, + "learning_rate": 1.0004992259377358e-05, + "loss": 3.8425, + "step": 2442752 + }, + { + "epoch": 2.0, + "learning_rate": 9.996606311866836e-06, + "loss": 3.8475, + "step": 2443264 + }, + { + "epoch": 2.0, + "learning_rate": 9.988220364356316e-06, + "loss": 3.858, + "step": 2443776 + }, + { + "epoch": 2.0, + "learning_rate": 9.979834416845796e-06, + "loss": 3.8532, + "step": 2444288 + }, + { + "epoch": 2.0, + "learning_rate": 9.971448469335276e-06, + "loss": 3.8507, + "step": 2444800 + }, + { + "epoch": 2.0, + "learning_rate": 9.963062521824756e-06, + "loss": 3.8417, + "step": 2445312 + }, + { + "epoch": 2.0, + "learning_rate": 9.954676574314236e-06, + "loss": 3.8466, + "step": 2445824 + }, + { + "epoch": 2.0, + "learning_rate": 9.94632338441118e-06, + "loss": 3.8423, + "step": 2446336 + }, + { + "epoch": 2.0, + "learning_rate": 9.93793743690066e-06, + "loss": 3.8581, + "step": 2446848 + }, + { + "epoch": 2.0, + "learning_rate": 9.92955148939014e-06, + "loss": 3.8436, + "step": 2447360 + }, + { + "epoch": 2.0, + "learning_rate": 9.92116554187962e-06, + "loss": 3.8536, + "step": 2447872 + }, + { + "epoch": 2.0, + "learning_rate": 9.912812351976563e-06, + "loss": 3.8571, + "step": 2448384 + }, + { + "epoch": 2.0, + "learning_rate": 9.904426404466041e-06, + "loss": 3.8382, + "step": 2448896 + }, + { + "epoch": 2.0, + "learning_rate": 9.896040456955521e-06, + "loss": 3.8443, + "step": 2449408 + }, + { + "epoch": 2.0, + "learning_rate": 9.887654509445003e-06, + "loss": 3.8335, + "step": 2449920 + }, + { + "epoch": 2.0, + "learning_rate": 9.87926856193448e-06, + "loss": 3.8337, + "step": 2450432 + }, + { + "epoch": 2.0, + "learning_rate": 9.87088261442396e-06, + "loss": 3.8473, + "step": 2450944 + }, + { + "epoch": 2.0, + "learning_rate": 9.86249666691344e-06, + "loss": 3.8419, + "step": 2451456 + }, + { + "epoch": 2.0, + "learning_rate": 9.854110719402922e-06, + "loss": 3.844, + "step": 2451968 + }, + { + "epoch": 2.0, + "learning_rate": 9.8457247718924e-06, + "loss": 3.8657, + "step": 2452480 + }, + { + "epoch": 2.0, + "learning_rate": 9.83733882438188e-06, + "loss": 3.8457, + "step": 2452992 + }, + { + "epoch": 2.0, + "learning_rate": 9.828969255675093e-06, + "loss": 3.8534, + "step": 2453504 + }, + { + "epoch": 2.0, + "learning_rate": 9.820583308164571e-06, + "loss": 3.8498, + "step": 2454016 + }, + { + "epoch": 2.0, + "learning_rate": 9.812197360654051e-06, + "loss": 3.8448, + "step": 2454528 + }, + { + "epoch": 2.0, + "learning_rate": 9.803811413143533e-06, + "loss": 3.847, + "step": 2455040 + }, + { + "epoch": 2.0, + "learning_rate": 9.795425465633013e-06, + "loss": 3.8335, + "step": 2455552 + }, + { + "epoch": 2.0, + "learning_rate": 9.787039518122491e-06, + "loss": 3.8481, + "step": 2456064 + }, + { + "epoch": 2.0, + "learning_rate": 9.778669949415704e-06, + "loss": 3.842, + "step": 2456576 + }, + { + "epoch": 2.0, + "learning_rate": 9.770300380708914e-06, + "loss": 3.835, + "step": 2457088 + }, + { + "epoch": 2.01, + "learning_rate": 9.761914433198394e-06, + "loss": 3.8482, + "step": 2457600 + }, + { + "epoch": 2.01, + "learning_rate": 9.753528485687874e-06, + "loss": 3.8403, + "step": 2458112 + }, + { + "epoch": 2.01, + "learning_rate": 9.745142538177354e-06, + "loss": 3.8524, + "step": 2458624 + }, + { + "epoch": 2.01, + "learning_rate": 9.736756590666834e-06, + "loss": 3.8527, + "step": 2459136 + }, + { + "epoch": 2.01, + "learning_rate": 9.728370643156314e-06, + "loss": 3.8415, + "step": 2459648 + }, + { + "epoch": 2.01, + "learning_rate": 9.720001074449525e-06, + "loss": 3.8443, + "step": 2460160 + }, + { + "epoch": 2.01, + "learning_rate": 9.711615126939005e-06, + "loss": 3.8634, + "step": 2460672 + }, + { + "epoch": 2.01, + "learning_rate": 9.703229179428485e-06, + "loss": 3.8365, + "step": 2461184 + }, + { + "epoch": 2.01, + "learning_rate": 9.694843231917965e-06, + "loss": 3.843, + "step": 2461696 + }, + { + "epoch": 2.01, + "learning_rate": 9.686457284407445e-06, + "loss": 3.8457, + "step": 2462208 + }, + { + "epoch": 2.01, + "learning_rate": 9.678071336896925e-06, + "loss": 3.8372, + "step": 2462720 + }, + { + "epoch": 2.01, + "learning_rate": 9.669685389386405e-06, + "loss": 3.8467, + "step": 2463232 + }, + { + "epoch": 2.01, + "learning_rate": 9.661299441875885e-06, + "loss": 3.8561, + "step": 2463744 + }, + { + "epoch": 2.01, + "learning_rate": 9.652913494365365e-06, + "loss": 3.8504, + "step": 2464256 + }, + { + "epoch": 2.01, + "learning_rate": 9.644543925658575e-06, + "loss": 3.8429, + "step": 2464768 + }, + { + "epoch": 2.01, + "learning_rate": 9.636157978148055e-06, + "loss": 3.8511, + "step": 2465280 + }, + { + "epoch": 2.01, + "learning_rate": 9.627772030637535e-06, + "loss": 3.8389, + "step": 2465792 + }, + { + "epoch": 2.01, + "learning_rate": 9.619386083127015e-06, + "loss": 3.8567, + "step": 2466304 + }, + { + "epoch": 2.01, + "learning_rate": 9.611016514420226e-06, + "loss": 3.8255, + "step": 2466816 + }, + { + "epoch": 2.01, + "learning_rate": 9.602630566909706e-06, + "loss": 3.8458, + "step": 2467328 + }, + { + "epoch": 2.01, + "learning_rate": 9.594244619399188e-06, + "loss": 3.8556, + "step": 2467840 + }, + { + "epoch": 2.01, + "learning_rate": 9.585858671888666e-06, + "loss": 3.851, + "step": 2468352 + }, + { + "epoch": 2.01, + "learning_rate": 9.577489103181877e-06, + "loss": 3.847, + "step": 2468864 + }, + { + "epoch": 2.01, + "learning_rate": 9.56911953447509e-06, + "loss": 3.8348, + "step": 2469376 + }, + { + "epoch": 2.01, + "learning_rate": 9.56073358696457e-06, + "loss": 3.8488, + "step": 2469888 + }, + { + "epoch": 2.01, + "learning_rate": 9.55234763945405e-06, + "loss": 3.8318, + "step": 2470400 + }, + { + "epoch": 2.01, + "learning_rate": 9.543961691943529e-06, + "loss": 3.863, + "step": 2470912 + }, + { + "epoch": 2.01, + "learning_rate": 9.535575744433009e-06, + "loss": 3.8403, + "step": 2471424 + }, + { + "epoch": 2.01, + "learning_rate": 9.527189796922489e-06, + "loss": 3.8617, + "step": 2471936 + }, + { + "epoch": 2.01, + "learning_rate": 9.518803849411969e-06, + "loss": 3.842, + "step": 2472448 + }, + { + "epoch": 2.01, + "learning_rate": 9.510417901901449e-06, + "loss": 3.8385, + "step": 2472960 + }, + { + "epoch": 2.01, + "learning_rate": 9.502031954390929e-06, + "loss": 3.851, + "step": 2473472 + }, + { + "epoch": 2.01, + "learning_rate": 9.493646006880407e-06, + "loss": 3.8404, + "step": 2473984 + }, + { + "epoch": 2.01, + "learning_rate": 9.485260059369889e-06, + "loss": 3.8408, + "step": 2474496 + }, + { + "epoch": 2.01, + "learning_rate": 9.476874111859369e-06, + "loss": 3.841, + "step": 2475008 + }, + { + "epoch": 2.01, + "learning_rate": 9.46850454315258e-06, + "loss": 3.8502, + "step": 2475520 + }, + { + "epoch": 2.01, + "learning_rate": 9.46011859564206e-06, + "loss": 3.8384, + "step": 2476032 + }, + { + "epoch": 2.01, + "learning_rate": 9.45173264813154e-06, + "loss": 3.8434, + "step": 2476544 + }, + { + "epoch": 2.01, + "learning_rate": 9.44334670062102e-06, + "loss": 3.8313, + "step": 2477056 + }, + { + "epoch": 2.01, + "learning_rate": 9.43497713191423e-06, + "loss": 3.8362, + "step": 2477568 + }, + { + "epoch": 2.01, + "learning_rate": 9.42659118440371e-06, + "loss": 3.854, + "step": 2478080 + }, + { + "epoch": 2.01, + "learning_rate": 9.418221615696923e-06, + "loss": 3.8544, + "step": 2478592 + }, + { + "epoch": 2.01, + "learning_rate": 9.409852046990133e-06, + "loss": 3.8421, + "step": 2479104 + }, + { + "epoch": 2.01, + "learning_rate": 9.401466099479612e-06, + "loss": 3.8441, + "step": 2479616 + }, + { + "epoch": 2.01, + "learning_rate": 9.393080151969093e-06, + "loss": 3.851, + "step": 2480128 + }, + { + "epoch": 2.01, + "learning_rate": 9.384694204458573e-06, + "loss": 3.8465, + "step": 2480640 + }, + { + "epoch": 2.01, + "learning_rate": 9.376324635751784e-06, + "loss": 3.8477, + "step": 2481152 + }, + { + "epoch": 2.01, + "learning_rate": 9.367938688241264e-06, + "loss": 3.8462, + "step": 2481664 + }, + { + "epoch": 2.01, + "learning_rate": 9.359552740730744e-06, + "loss": 3.8479, + "step": 2482176 + }, + { + "epoch": 2.01, + "learning_rate": 9.351166793220224e-06, + "loss": 3.8525, + "step": 2482688 + }, + { + "epoch": 2.01, + "learning_rate": 9.342780845709704e-06, + "loss": 3.8482, + "step": 2483200 + }, + { + "epoch": 2.01, + "learning_rate": 9.334394898199184e-06, + "loss": 3.8476, + "step": 2483712 + }, + { + "epoch": 2.01, + "learning_rate": 9.326008950688664e-06, + "loss": 3.8588, + "step": 2484224 + }, + { + "epoch": 2.01, + "learning_rate": 9.317623003178144e-06, + "loss": 3.8459, + "step": 2484736 + }, + { + "epoch": 2.01, + "learning_rate": 9.309237055667624e-06, + "loss": 3.8286, + "step": 2485248 + }, + { + "epoch": 2.01, + "learning_rate": 9.300851108157104e-06, + "loss": 3.8503, + "step": 2485760 + }, + { + "epoch": 2.01, + "learning_rate": 9.292465160646584e-06, + "loss": 3.848, + "step": 2486272 + }, + { + "epoch": 2.01, + "learning_rate": 9.284079213136062e-06, + "loss": 3.845, + "step": 2486784 + }, + { + "epoch": 2.01, + "learning_rate": 9.275693265625544e-06, + "loss": 3.8465, + "step": 2487296 + }, + { + "epoch": 2.01, + "learning_rate": 9.267323696918754e-06, + "loss": 3.8373, + "step": 2487808 + }, + { + "epoch": 2.02, + "learning_rate": 9.258937749408234e-06, + "loss": 3.8481, + "step": 2488320 + }, + { + "epoch": 2.02, + "learning_rate": 9.250551801897714e-06, + "loss": 3.8411, + "step": 2488832 + }, + { + "epoch": 2.02, + "learning_rate": 9.242165854387194e-06, + "loss": 3.8456, + "step": 2489344 + }, + { + "epoch": 2.02, + "learning_rate": 9.233779906876674e-06, + "loss": 3.8463, + "step": 2489856 + }, + { + "epoch": 2.02, + "learning_rate": 9.225393959366154e-06, + "loss": 3.8409, + "step": 2490368 + }, + { + "epoch": 2.02, + "learning_rate": 9.217008011855634e-06, + "loss": 3.8593, + "step": 2490880 + }, + { + "epoch": 2.02, + "learning_rate": 9.208622064345114e-06, + "loss": 3.8349, + "step": 2491392 + }, + { + "epoch": 2.02, + "learning_rate": 9.200252495638327e-06, + "loss": 3.8329, + "step": 2491904 + }, + { + "epoch": 2.02, + "learning_rate": 9.191866548127805e-06, + "loss": 3.846, + "step": 2492416 + }, + { + "epoch": 2.02, + "learning_rate": 9.183480600617285e-06, + "loss": 3.8478, + "step": 2492928 + }, + { + "epoch": 2.02, + "learning_rate": 9.175111031910497e-06, + "loss": 3.8573, + "step": 2493440 + }, + { + "epoch": 2.02, + "learning_rate": 9.166725084399976e-06, + "loss": 3.8465, + "step": 2493952 + }, + { + "epoch": 2.02, + "learning_rate": 9.158339136889455e-06, + "loss": 3.8359, + "step": 2494464 + }, + { + "epoch": 2.02, + "learning_rate": 9.149953189378935e-06, + "loss": 3.8446, + "step": 2494976 + }, + { + "epoch": 2.02, + "learning_rate": 9.141567241868415e-06, + "loss": 3.8469, + "step": 2495488 + }, + { + "epoch": 2.02, + "learning_rate": 9.133181294357895e-06, + "loss": 3.8351, + "step": 2496000 + }, + { + "epoch": 2.02, + "learning_rate": 9.124811725651108e-06, + "loss": 3.84, + "step": 2496512 + }, + { + "epoch": 2.02, + "learning_rate": 9.116425778140588e-06, + "loss": 3.8438, + "step": 2497024 + }, + { + "epoch": 2.02, + "learning_rate": 9.108039830630066e-06, + "loss": 3.8468, + "step": 2497536 + }, + { + "epoch": 2.02, + "learning_rate": 9.099653883119546e-06, + "loss": 3.8344, + "step": 2498048 + }, + { + "epoch": 2.02, + "learning_rate": 9.091267935609028e-06, + "loss": 3.8369, + "step": 2498560 + }, + { + "epoch": 2.02, + "learning_rate": 9.082898366902238e-06, + "loss": 3.8349, + "step": 2499072 + }, + { + "epoch": 2.02, + "learning_rate": 9.074512419391717e-06, + "loss": 3.8487, + "step": 2499584 + }, + { + "epoch": 2.02, + "learning_rate": 9.066126471881198e-06, + "loss": 3.8378, + "step": 2500096 + }, + { + "epoch": 2.02, + "learning_rate": 9.057740524370678e-06, + "loss": 3.8406, + "step": 2500608 + }, + { + "epoch": 2.02, + "learning_rate": 9.049354576860157e-06, + "loss": 3.8444, + "step": 2501120 + }, + { + "epoch": 2.02, + "learning_rate": 9.040968629349637e-06, + "loss": 3.8518, + "step": 2501632 + }, + { + "epoch": 2.02, + "learning_rate": 9.032599060642849e-06, + "loss": 3.8383, + "step": 2502144 + }, + { + "epoch": 2.02, + "learning_rate": 9.024213113132329e-06, + "loss": 3.8436, + "step": 2502656 + }, + { + "epoch": 2.02, + "learning_rate": 9.015827165621809e-06, + "loss": 3.8451, + "step": 2503168 + }, + { + "epoch": 2.02, + "learning_rate": 9.007441218111289e-06, + "loss": 3.843, + "step": 2503680 + }, + { + "epoch": 2.02, + "learning_rate": 8.999055270600769e-06, + "loss": 3.8292, + "step": 2504192 + }, + { + "epoch": 2.02, + "learning_rate": 8.990669323090247e-06, + "loss": 3.8478, + "step": 2504704 + }, + { + "epoch": 2.02, + "learning_rate": 8.98229975438346e-06, + "loss": 3.842, + "step": 2505216 + }, + { + "epoch": 2.02, + "learning_rate": 8.97391380687294e-06, + "loss": 3.8509, + "step": 2505728 + }, + { + "epoch": 2.02, + "learning_rate": 8.96552785936242e-06, + "loss": 3.8351, + "step": 2506240 + }, + { + "epoch": 2.02, + "learning_rate": 8.9571419118519e-06, + "loss": 3.8433, + "step": 2506752 + }, + { + "epoch": 2.02, + "learning_rate": 8.94875596434138e-06, + "loss": 3.8374, + "step": 2507264 + }, + { + "epoch": 2.02, + "learning_rate": 8.94038639563459e-06, + "loss": 3.8394, + "step": 2507776 + }, + { + "epoch": 2.02, + "learning_rate": 8.93200044812407e-06, + "loss": 3.8311, + "step": 2508288 + }, + { + "epoch": 2.02, + "learning_rate": 8.923630879417281e-06, + "loss": 3.853, + "step": 2508800 + }, + { + "epoch": 2.02, + "learning_rate": 8.915244931906763e-06, + "loss": 3.8526, + "step": 2509312 + }, + { + "epoch": 2.02, + "learning_rate": 8.906858984396243e-06, + "loss": 3.8441, + "step": 2509824 + }, + { + "epoch": 2.02, + "learning_rate": 8.89847303688572e-06, + "loss": 3.8361, + "step": 2510336 + }, + { + "epoch": 2.02, + "learning_rate": 8.8900870893752e-06, + "loss": 3.8506, + "step": 2510848 + }, + { + "epoch": 2.02, + "learning_rate": 8.881701141864682e-06, + "loss": 3.8474, + "step": 2511360 + }, + { + "epoch": 2.02, + "learning_rate": 8.87331519435416e-06, + "loss": 3.8415, + "step": 2511872 + }, + { + "epoch": 2.02, + "learning_rate": 8.86492924684364e-06, + "loss": 3.8447, + "step": 2512384 + }, + { + "epoch": 2.02, + "learning_rate": 8.85654329933312e-06, + "loss": 3.8562, + "step": 2512896 + }, + { + "epoch": 2.02, + "learning_rate": 8.848173730626333e-06, + "loss": 3.8479, + "step": 2513408 + }, + { + "epoch": 2.02, + "learning_rate": 8.839787783115811e-06, + "loss": 3.8434, + "step": 2513920 + }, + { + "epoch": 2.02, + "learning_rate": 8.831401835605293e-06, + "loss": 3.8392, + "step": 2514432 + }, + { + "epoch": 2.02, + "learning_rate": 8.823015888094773e-06, + "loss": 3.8467, + "step": 2514944 + }, + { + "epoch": 2.02, + "learning_rate": 8.814629940584251e-06, + "loss": 3.8465, + "step": 2515456 + }, + { + "epoch": 2.02, + "learning_rate": 8.806243993073731e-06, + "loss": 3.837, + "step": 2515968 + }, + { + "epoch": 2.02, + "learning_rate": 8.797858045563213e-06, + "loss": 3.8592, + "step": 2516480 + }, + { + "epoch": 2.02, + "learning_rate": 8.789488476856424e-06, + "loss": 3.8425, + "step": 2516992 + }, + { + "epoch": 2.02, + "learning_rate": 8.781102529345902e-06, + "loss": 3.8501, + "step": 2517504 + }, + { + "epoch": 2.02, + "learning_rate": 8.772716581835383e-06, + "loss": 3.8478, + "step": 2518016 + }, + { + "epoch": 2.02, + "learning_rate": 8.764347013128594e-06, + "loss": 3.8424, + "step": 2518528 + }, + { + "epoch": 2.03, + "eval_loss": 4.02719783782959, + "eval_runtime": 295.9801, + "eval_samples_per_second": 1289.246, + "eval_steps_per_second": 40.29, + "step": 2518543 + }, + { + "epoch": 0.0, + "learning_rate": 8.755961065618074e-06, + "loss": 3.8424, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.747575118107554e-06, + "loss": 3.8461, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.739189170597034e-06, + "loss": 3.8543, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.730803223086514e-06, + "loss": 3.8462, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.722417275575994e-06, + "loss": 3.8502, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.714031328065474e-06, + "loss": 3.8374, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.705645380554954e-06, + "loss": 3.8463, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.697259433044432e-06, + "loss": 3.8386, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.688873485533914e-06, + "loss": 3.8573, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.680487538023394e-06, + "loss": 3.8365, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.672101590512874e-06, + "loss": 3.8539, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.663748400609815e-06, + "loss": 3.8558, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.655362453099295e-06, + "loss": 3.8343, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.646976505588775e-06, + "loss": 3.8407, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.638590558078257e-06, + "loss": 3.8303, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.630204610567735e-06, + "loss": 3.8359, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.621818663057215e-06, + "loss": 3.8418, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.613432715546695e-06, + "loss": 3.8394, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.605046768036175e-06, + "loss": 3.8403, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.596660820525655e-06, + "loss": 3.8645, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.588274873015135e-06, + "loss": 3.8417, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.579888925504615e-06, + "loss": 3.8475, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.571502977994095e-06, + "loss": 3.8509, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.563117030483575e-06, + "loss": 3.8415, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.554731082973053e-06, + "loss": 3.8433, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.546345135462535e-06, + "loss": 3.829, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.537959187952015e-06, + "loss": 3.8417, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.529589619245226e-06, + "loss": 3.8449, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.521203671734705e-06, + "loss": 3.8307, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.512817724224185e-06, + "loss": 3.8439, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.504448155517398e-06, + "loss": 3.8376, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.496062208006878e-06, + "loss": 3.8524, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.487676260496356e-06, + "loss": 3.8451, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.479290312985836e-06, + "loss": 3.8353, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.470920744279049e-06, + "loss": 3.8432, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.462534796768527e-06, + "loss": 3.8585, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.454148849258007e-06, + "loss": 3.8292, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.445762901747488e-06, + "loss": 3.8431, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.437376954236968e-06, + "loss": 3.8416, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.428991006726447e-06, + "loss": 3.8361, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.420605059215927e-06, + "loss": 3.8428, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.412219111705408e-06, + "loss": 3.8524, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.403833164194887e-06, + "loss": 3.848, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.39547997429183e-06, + "loss": 3.8397, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.38709402678131e-06, + "loss": 3.852, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.37870807927079e-06, + "loss": 3.8391, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.37032213176027e-06, + "loss": 3.8465, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.36193618424975e-06, + "loss": 3.8249, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.35355023673923e-06, + "loss": 3.839, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.34516428922871e-06, + "loss": 3.8518, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.33677834171819e-06, + "loss": 3.8502, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.32839239420767e-06, + "loss": 3.8422, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.32002282550088e-06, + "loss": 3.8331, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.31163687799036e-06, + "loss": 3.8453, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.30325093047984e-06, + "loss": 3.8307, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.29486498296932e-06, + "loss": 3.8555, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.2864790354588e-06, + "loss": 3.8392, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.27809308794828e-06, + "loss": 3.8586, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.269723519241491e-06, + "loss": 3.8426, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.261337571730973e-06, + "loss": 3.8378, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.25295162422045e-06, + "loss": 3.841, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.24456567670993e-06, + "loss": 3.8452, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.23617972919941e-06, + "loss": 3.8376, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.22779378168889e-06, + "loss": 3.8336, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.21940783417837e-06, + "loss": 3.8512, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.211038265471583e-06, + "loss": 3.8361, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.202652317961063e-06, + "loss": 3.833, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.194266370450541e-06, + "loss": 3.8311, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.185880422940021e-06, + "loss": 3.8334, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.177494475429503e-06, + "loss": 3.855, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.169108527918981e-06, + "loss": 3.8475, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.160722580408461e-06, + "loss": 3.8416, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.152353011701674e-06, + "loss": 3.8411, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.143967064191154e-06, + "loss": 3.8469, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.135581116680632e-06, + "loss": 3.843, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.127211547973844e-06, + "loss": 3.8434, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.118825600463324e-06, + "loss": 3.8458, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.110439652952804e-06, + "loss": 3.8437, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.102053705442284e-06, + "loss": 3.8509, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.093667757931764e-06, + "loss": 3.8411, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.085281810421244e-06, + "loss": 3.8477, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.076895862910722e-06, + "loss": 3.8493, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.068509915400204e-06, + "loss": 3.8454, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.060123967889684e-06, + "loss": 3.8268, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.051738020379162e-06, + "loss": 3.8457, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.043368451672375e-06, + "loss": 3.843, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.034982504161855e-06, + "loss": 3.8452, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.026596556651335e-06, + "loss": 3.8433, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.018210609140815e-06, + "loss": 3.8352, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.009824661630295e-06, + "loss": 3.8427, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.001438714119774e-06, + "loss": 3.8376, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.993052766609253e-06, + "loss": 3.8468, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.984683197902465e-06, + "loss": 3.8376, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.976297250391945e-06, + "loss": 3.8414, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.967911302881425e-06, + "loss": 3.8532, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.959525355370905e-06, + "loss": 3.8392, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.951139407860385e-06, + "loss": 3.8256, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.942753460349865e-06, + "loss": 3.8445, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.934367512839343e-06, + "loss": 3.8444, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.925997944132556e-06, + "loss": 3.8547, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.917611996622036e-06, + "loss": 3.8385, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.909226049111516e-06, + "loss": 3.8363, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.900840101600996e-06, + "loss": 3.8374, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.892454154090476e-06, + "loss": 3.846, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.884084585383688e-06, + "loss": 3.8304, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.875715016676899e-06, + "loss": 3.8361, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.867329069166377e-06, + "loss": 3.8438, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.858943121655859e-06, + "loss": 3.8456, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.850557174145339e-06, + "loss": 3.8321, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.842171226634817e-06, + "loss": 3.8343, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.833785279124297e-06, + "loss": 3.8341, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.825399331613779e-06, + "loss": 3.8458, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.817013384103257e-06, + "loss": 3.838, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.808627436592737e-06, + "loss": 3.8353, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.80025786788595e-06, + "loss": 3.8464, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.79187192037543e-06, + "loss": 3.8468, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78350235166864e-06, + "loss": 3.835, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.77511640415812e-06, + "loss": 3.8407, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.7667304566476e-06, + "loss": 3.8419, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.75834450913708e-06, + "loss": 3.8407, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.74995856162656e-06, + "loss": 3.8271, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.74158899291977e-06, + "loss": 3.8468, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.73320304540925e-06, + "loss": 3.8395, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.72481709789873e-06, + "loss": 3.845, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.71643115038821e-06, + "loss": 3.8342, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.70804520287769e-06, + "loss": 3.8417, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.69965925536717e-06, + "loss": 3.8332, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.69127330785665e-06, + "loss": 3.8389, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.68288736034613e-06, + "loss": 3.8231, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.67450141283561e-06, + "loss": 3.8533, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.66611546532509e-06, + "loss": 3.8496, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.65772951781457e-06, + "loss": 3.8432, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.649359949107781e-06, + "loss": 3.8302, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.640974001597263e-06, + "loss": 3.8538, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.632588054086741e-06, + "loss": 3.8443, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.624202106576221e-06, + "loss": 3.8416, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.615816159065702e-06, + "loss": 3.8365, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.607430211555181e-06, + "loss": 3.8528, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.599044264044661e-06, + "loss": 3.8419, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.590658316534141e-06, + "loss": 3.8447, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.582288747827352e-06, + "loss": 3.8332, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.573902800316831e-06, + "loss": 3.8441, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.565516852806312e-06, + "loss": 3.845, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.557130905295792e-06, + "loss": 3.8371, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.548761336589002e-06, + "loss": 3.8565, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.540391767882215e-06, + "loss": 3.8387, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.5320058203716946e-06, + "loss": 3.8425, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.5236198728611745e-06, + "loss": 3.8447, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.515233925350654e-06, + "loss": 3.8413, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 4.026799201965332, + "eval_runtime": 291.1612, + "eval_samples_per_second": 1310.583, + "eval_steps_per_second": 40.957, + "step": 2594863 + }, + { + "epoch": 1.0, + "learning_rate": 7.5068479778401344e-06, + "loss": 3.8372, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.498462030329614e-06, + "loss": 3.8442, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.4900760828190935e-06, + "loss": 3.8479, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.4816901353085734e-06, + "loss": 3.8476, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.473304187798054e-06, + "loss": 3.8491, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.464918240287534e-06, + "loss": 3.831, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.456532292777013e-06, + "loss": 3.8398, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.448162724070225e-06, + "loss": 3.8361, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.439776776559705e-06, + "loss": 3.8502, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.431390829049184e-06, + "loss": 3.8383, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.423004881538664e-06, + "loss": 3.8484, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.414635312831876e-06, + "loss": 3.8481, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.406265744125087e-06, + "loss": 3.835, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.397879796614566e-06, + "loss": 3.8393, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.389493849104047e-06, + "loss": 3.8283, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.381107901593527e-06, + "loss": 3.8352, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.372738332886739e-06, + "loss": 3.8374, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.364352385376218e-06, + "loss": 3.8361, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.355966437865698e-06, + "loss": 3.8375, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.347580490355179e-06, + "loss": 3.8602, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.339194542844658e-06, + "loss": 3.8418, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.330824974137869e-06, + "loss": 3.8431, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.322439026627349e-06, + "loss": 3.8474, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.314053079116829e-06, + "loss": 3.8403, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.305667131606308e-06, + "loss": 3.8398, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.297281184095789e-06, + "loss": 3.8293, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.288895236585269e-06, + "loss": 3.8387, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.280509289074748e-06, + "loss": 3.8376, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.272123341564228e-06, + "loss": 3.8278, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.263737394053709e-06, + "loss": 3.8437, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.255367825346921e-06, + "loss": 3.836, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.246981877836399e-06, + "loss": 3.8502, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.2386123091296105e-06, + "loss": 3.8423, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.230226361619091e-06, + "loss": 3.829, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.221856792912303e-06, + "loss": 3.844, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.213470845401782e-06, + "loss": 3.8558, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.205084897891262e-06, + "loss": 3.8282, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.196698950380743e-06, + "loss": 3.8391, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.188313002870221e-06, + "loss": 3.8343, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.179927055359702e-06, + "loss": 3.8342, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.171541107849182e-06, + "loss": 3.8397, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.163155160338661e-06, + "loss": 3.8513, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.154769212828141e-06, + "loss": 3.8448, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.146383265317622e-06, + "loss": 3.837, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.137997317807102e-06, + "loss": 3.8472, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.129611370296581e-06, + "loss": 3.8354, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.121225422786061e-06, + "loss": 3.8475, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.1128394752755416e-06, + "loss": 3.8266, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.104453527765021e-06, + "loss": 3.833, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.096067580254501e-06, + "loss": 3.8491, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.087698011547712e-06, + "loss": 3.8476, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.079312064037193e-06, + "loss": 3.8388, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.070926116526671e-06, + "loss": 3.8307, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.062540169016152e-06, + "loss": 3.8444, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.054170600309364e-06, + "loss": 3.8246, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.045784652798843e-06, + "loss": 3.8512, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.037398705288323e-06, + "loss": 3.8394, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.029012757777803e-06, + "loss": 3.8532, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.0206431890710144e-06, + "loss": 3.8405, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.0122572415604935e-06, + "loss": 3.8342, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.003871294049974e-06, + "loss": 3.8378, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.995485346539454e-06, + "loss": 3.844, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.987115777832666e-06, + "loss": 3.8338, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.978729830322145e-06, + "loss": 3.8314, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.970343882811625e-06, + "loss": 3.8457, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.961957935301106e-06, + "loss": 3.8375, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.953588366594316e-06, + "loss": 3.828, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.945218797887527e-06, + "loss": 3.8308, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.936832850377007e-06, + "loss": 3.8281, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.928446902866488e-06, + "loss": 3.851, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.920060955355967e-06, + "loss": 3.8467, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.911675007845447e-06, + "loss": 3.8375, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.903305439138659e-06, + "loss": 3.8398, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.89491949162814e-06, + "loss": 3.842, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.886533544117618e-06, + "loss": 3.841, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.8781639754108295e-06, + "loss": 3.8408, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.86977802790031e-06, + "loss": 3.8446, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.8613920803897895e-06, + "loss": 3.8398, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.853006132879269e-06, + "loss": 3.8496, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.844620185368749e-06, + "loss": 3.8376, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.8362342378582285e-06, + "loss": 3.8436, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.827848290347709e-06, + "loss": 3.8438, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.819462342837189e-06, + "loss": 3.8439, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.811076395326669e-06, + "loss": 3.8289, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.80270682661988e-06, + "loss": 3.8413, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.79432087910936e-06, + "loss": 3.839, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.785934931598841e-06, + "loss": 3.8433, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.777548984088319e-06, + "loss": 3.8448, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.769179415381531e-06, + "loss": 3.8269, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.7607934678710114e-06, + "loss": 3.8394, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.752407520360491e-06, + "loss": 3.8348, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.7440215728499705e-06, + "loss": 3.8459, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.735635625339451e-06, + "loss": 3.8281, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.727249677828931e-06, + "loss": 3.8388, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.71886373031841e-06, + "loss": 3.8505, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.71047778280789e-06, + "loss": 3.8373, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.702091835297371e-06, + "loss": 3.8236, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.693722266590583e-06, + "loss": 3.8395, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.685336319080061e-06, + "loss": 3.8431, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.676966750373273e-06, + "loss": 3.846, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.6685808028627535e-06, + "loss": 3.8408, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.660194855352233e-06, + "loss": 3.8335, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.6518089078417125e-06, + "loss": 3.8336, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.6434229603311925e-06, + "loss": 3.8466, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.635037012820673e-06, + "loss": 3.8245, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.626667444113883e-06, + "loss": 3.833, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.618281496603364e-06, + "loss": 3.842, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.609895549092844e-06, + "loss": 3.8447, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.601509601582325e-06, + "loss": 3.8232, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.593123654071803e-06, + "loss": 3.8373, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.584737706561284e-06, + "loss": 3.8246, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.576351759050764e-06, + "loss": 3.8421, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.567982190343975e-06, + "loss": 3.8344, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.5595962428334546e-06, + "loss": 3.8316, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.5512102953229345e-06, + "loss": 3.8455, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.542824347812415e-06, + "loss": 3.8454, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.534454779105625e-06, + "loss": 3.8307, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.526068831595106e-06, + "loss": 3.8391, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.517682884084586e-06, + "loss": 3.8373, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.509296936574065e-06, + "loss": 3.8398, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.500927367867277e-06, + "loss": 3.8221, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.492541420356757e-06, + "loss": 3.8458, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.4841554728462375e-06, + "loss": 3.8369, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.475769525335716e-06, + "loss": 3.8413, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.467383577825197e-06, + "loss": 3.8338, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.4589976303146765e-06, + "loss": 3.8401, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.450628061607888e-06, + "loss": 3.8287, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.442242114097367e-06, + "loss": 3.8363, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.433856166586848e-06, + "loss": 3.8227, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.42548659788006e-06, + "loss": 3.8511, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.417100650369538e-06, + "loss": 3.8438, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.408714702859019e-06, + "loss": 3.8413, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.400328755348499e-06, + "loss": 3.8286, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.3919428078379796e-06, + "loss": 3.8491, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.383556860327458e-06, + "loss": 3.8459, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.375170912816939e-06, + "loss": 3.836, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.3667849653064186e-06, + "loss": 3.8381, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.358415396599629e-06, + "loss": 3.8469, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.350029449089109e-06, + "loss": 3.8401, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.341643501578589e-06, + "loss": 3.8449, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.33325755406807e-06, + "loss": 3.8301, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.324871606557549e-06, + "loss": 3.8433, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.316485659047029e-06, + "loss": 3.839, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.308116090340241e-06, + "loss": 3.8353, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.29973014282972e-06, + "loss": 3.8519, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.2913441953192e-06, + "loss": 3.8371, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.282958247808681e-06, + "loss": 3.8405, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.274572300298161e-06, + "loss": 3.8417, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.266202731591371e-06, + "loss": 3.8364, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 4.026012897491455, + "eval_runtime": 279.4647, + "eval_samples_per_second": 1365.435, + "eval_steps_per_second": 42.671, + "step": 2671183 + }, + { + "epoch": 2.0, + "learning_rate": 6.257816784080851e-06, + "loss": 3.8391, + "step": 2671616 + }, + { + "epoch": 2.0, + "learning_rate": 6.249430836570331e-06, + "loss": 3.8404, + "step": 2672128 + }, + { + "epoch": 2.0, + "learning_rate": 6.241044889059811e-06, + "loss": 3.8443, + "step": 2672640 + }, + { + "epoch": 2.0, + "learning_rate": 6.232675320353022e-06, + "loss": 3.8445, + "step": 2673152 + }, + { + "epoch": 2.0, + "learning_rate": 6.224289372842503e-06, + "loss": 3.8482, + "step": 2673664 + }, + { + "epoch": 2.0, + "learning_rate": 6.215903425331982e-06, + "loss": 3.8298, + "step": 2674176 + }, + { + "epoch": 2.0, + "learning_rate": 6.207517477821463e-06, + "loss": 3.8381, + "step": 2674688 + }, + { + "epoch": 2.0, + "learning_rate": 6.1991479091146736e-06, + "loss": 3.83, + "step": 2675200 + }, + { + "epoch": 2.0, + "learning_rate": 6.190778340407885e-06, + "loss": 3.8484, + "step": 2675712 + }, + { + "epoch": 2.0, + "learning_rate": 6.182392392897364e-06, + "loss": 3.8372, + "step": 2676224 + }, + { + "epoch": 2.0, + "learning_rate": 6.174006445386845e-06, + "loss": 3.8468, + "step": 2676736 + }, + { + "epoch": 2.0, + "learning_rate": 6.165620497876324e-06, + "loss": 3.8459, + "step": 2677248 + }, + { + "epoch": 2.0, + "learning_rate": 6.157250929169537e-06, + "loss": 3.8321, + "step": 2677760 + }, + { + "epoch": 2.0, + "learning_rate": 6.148864981659016e-06, + "loss": 3.833, + "step": 2678272 + }, + { + "epoch": 2.0, + "learning_rate": 6.140479034148496e-06, + "loss": 3.828, + "step": 2678784 + }, + { + "epoch": 2.0, + "learning_rate": 6.132093086637976e-06, + "loss": 3.8284, + "step": 2679296 + }, + { + "epoch": 2.0, + "learning_rate": 6.123707139127456e-06, + "loss": 3.8359, + "step": 2679808 + }, + { + "epoch": 2.0, + "learning_rate": 6.115321191616936e-06, + "loss": 3.8332, + "step": 2680320 + }, + { + "epoch": 2.0, + "learning_rate": 6.106935244106416e-06, + "loss": 3.8349, + "step": 2680832 + }, + { + "epoch": 2.0, + "learning_rate": 6.098549296595895e-06, + "loss": 3.8551, + "step": 2681344 + }, + { + "epoch": 2.0, + "learning_rate": 6.0901633490853755e-06, + "loss": 3.8377, + "step": 2681856 + }, + { + "epoch": 2.0, + "learning_rate": 6.081777401574855e-06, + "loss": 3.8395, + "step": 2682368 + }, + { + "epoch": 2.0, + "learning_rate": 6.073391454064335e-06, + "loss": 3.8444, + "step": 2682880 + }, + { + "epoch": 2.0, + "learning_rate": 6.0650055065538145e-06, + "loss": 3.8425, + "step": 2683392 + }, + { + "epoch": 2.0, + "learning_rate": 6.056635937847026e-06, + "loss": 3.833, + "step": 2683904 + }, + { + "epoch": 2.0, + "learning_rate": 6.048249990336506e-06, + "loss": 3.826, + "step": 2684416 + }, + { + "epoch": 2.0, + "learning_rate": 6.039864042825986e-06, + "loss": 3.8434, + "step": 2684928 + }, + { + "epoch": 2.0, + "learning_rate": 6.031478095315466e-06, + "loss": 3.8293, + "step": 2685440 + }, + { + "epoch": 2.0, + "learning_rate": 6.023092147804946e-06, + "loss": 3.8301, + "step": 2685952 + }, + { + "epoch": 2.01, + "learning_rate": 6.014722579098158e-06, + "loss": 3.8398, + "step": 2686464 + }, + { + "epoch": 2.01, + "learning_rate": 6.006336631587637e-06, + "loss": 3.8339, + "step": 2686976 + }, + { + "epoch": 2.01, + "learning_rate": 5.9979506840771175e-06, + "loss": 3.8435, + "step": 2687488 + }, + { + "epoch": 2.01, + "learning_rate": 5.989564736566597e-06, + "loss": 3.8394, + "step": 2688000 + }, + { + "epoch": 2.01, + "learning_rate": 5.981178789056077e-06, + "loss": 3.83, + "step": 2688512 + }, + { + "epoch": 2.01, + "learning_rate": 5.97282559915302e-06, + "loss": 3.8431, + "step": 2689024 + }, + { + "epoch": 2.01, + "learning_rate": 5.9644396516425e-06, + "loss": 3.8503, + "step": 2689536 + }, + { + "epoch": 2.01, + "learning_rate": 5.95605370413198e-06, + "loss": 3.8265, + "step": 2690048 + }, + { + "epoch": 2.01, + "learning_rate": 5.947667756621459e-06, + "loss": 3.8424, + "step": 2690560 + }, + { + "epoch": 2.01, + "learning_rate": 5.93928180911094e-06, + "loss": 3.8272, + "step": 2691072 + }, + { + "epoch": 2.01, + "learning_rate": 5.930895861600419e-06, + "loss": 3.8367, + "step": 2691584 + }, + { + "epoch": 2.01, + "learning_rate": 5.922509914089899e-06, + "loss": 3.8344, + "step": 2692096 + }, + { + "epoch": 2.01, + "learning_rate": 5.914123966579379e-06, + "loss": 3.8479, + "step": 2692608 + }, + { + "epoch": 2.01, + "learning_rate": 5.905738019068859e-06, + "loss": 3.8402, + "step": 2693120 + }, + { + "epoch": 2.01, + "learning_rate": 5.89736845036207e-06, + "loss": 3.8371, + "step": 2693632 + }, + { + "epoch": 2.01, + "learning_rate": 5.8889825028515495e-06, + "loss": 3.8417, + "step": 2694144 + }, + { + "epoch": 2.01, + "learning_rate": 5.88059655534103e-06, + "loss": 3.8329, + "step": 2694656 + }, + { + "epoch": 2.01, + "learning_rate": 5.872210607830509e-06, + "loss": 3.8486, + "step": 2695168 + }, + { + "epoch": 2.01, + "learning_rate": 5.863824660319989e-06, + "loss": 3.8239, + "step": 2695680 + }, + { + "epoch": 2.01, + "learning_rate": 5.855438712809469e-06, + "loss": 3.8284, + "step": 2696192 + }, + { + "epoch": 2.01, + "learning_rate": 5.847069144102681e-06, + "loss": 3.8454, + "step": 2696704 + }, + { + "epoch": 2.01, + "learning_rate": 5.8386995753958926e-06, + "loss": 3.8415, + "step": 2697216 + }, + { + "epoch": 2.01, + "learning_rate": 5.830313627885372e-06, + "loss": 3.8387, + "step": 2697728 + }, + { + "epoch": 2.01, + "learning_rate": 5.8219276803748525e-06, + "loss": 3.8286, + "step": 2698240 + }, + { + "epoch": 2.01, + "learning_rate": 5.8135417328643316e-06, + "loss": 3.8405, + "step": 2698752 + }, + { + "epoch": 2.01, + "learning_rate": 5.805155785353812e-06, + "loss": 3.8251, + "step": 2699264 + }, + { + "epoch": 2.01, + "learning_rate": 5.7967698378432915e-06, + "loss": 3.8445, + "step": 2699776 + }, + { + "epoch": 2.01, + "learning_rate": 5.7883838903327714e-06, + "loss": 3.8394, + "step": 2700288 + }, + { + "epoch": 2.01, + "learning_rate": 5.779997942822251e-06, + "loss": 3.8498, + "step": 2700800 + }, + { + "epoch": 2.01, + "learning_rate": 5.771611995311731e-06, + "loss": 3.842, + "step": 2701312 + }, + { + "epoch": 2.01, + "learning_rate": 5.763242426604943e-06, + "loss": 3.8358, + "step": 2701824 + }, + { + "epoch": 2.01, + "learning_rate": 5.754856479094423e-06, + "loss": 3.8303, + "step": 2702336 + }, + { + "epoch": 2.01, + "learning_rate": 5.746470531583903e-06, + "loss": 3.8455, + "step": 2702848 + }, + { + "epoch": 2.01, + "learning_rate": 5.738084584073383e-06, + "loss": 3.8282, + "step": 2703360 + }, + { + "epoch": 2.01, + "learning_rate": 5.729698636562862e-06, + "loss": 3.8336, + "step": 2703872 + }, + { + "epoch": 2.01, + "learning_rate": 5.721329067856074e-06, + "loss": 3.8397, + "step": 2704384 + }, + { + "epoch": 2.01, + "learning_rate": 5.712959499149285e-06, + "loss": 3.837, + "step": 2704896 + }, + { + "epoch": 2.01, + "learning_rate": 5.704573551638765e-06, + "loss": 3.8246, + "step": 2705408 + }, + { + "epoch": 2.01, + "learning_rate": 5.696187604128244e-06, + "loss": 3.8263, + "step": 2705920 + }, + { + "epoch": 2.01, + "learning_rate": 5.687801656617725e-06, + "loss": 3.8265, + "step": 2706432 + }, + { + "epoch": 2.01, + "learning_rate": 5.679415709107205e-06, + "loss": 3.8469, + "step": 2706944 + }, + { + "epoch": 2.01, + "learning_rate": 5.671029761596685e-06, + "loss": 3.8434, + "step": 2707456 + }, + { + "epoch": 2.01, + "learning_rate": 5.662643814086165e-06, + "loss": 3.8342, + "step": 2707968 + }, + { + "epoch": 2.01, + "learning_rate": 5.654257866575644e-06, + "loss": 3.8402, + "step": 2708480 + }, + { + "epoch": 2.01, + "learning_rate": 5.645871919065125e-06, + "loss": 3.8368, + "step": 2708992 + }, + { + "epoch": 2.01, + "learning_rate": 5.637485971554604e-06, + "loss": 3.8462, + "step": 2709504 + }, + { + "epoch": 2.01, + "learning_rate": 5.629132781651547e-06, + "loss": 3.83, + "step": 2710016 + }, + { + "epoch": 2.01, + "learning_rate": 5.620746834141026e-06, + "loss": 3.8471, + "step": 2710528 + }, + { + "epoch": 2.01, + "learning_rate": 5.612360886630507e-06, + "loss": 3.8374, + "step": 2711040 + }, + { + "epoch": 2.01, + "learning_rate": 5.603974939119986e-06, + "loss": 3.8429, + "step": 2711552 + }, + { + "epoch": 2.01, + "learning_rate": 5.595588991609467e-06, + "loss": 3.8331, + "step": 2712064 + }, + { + "epoch": 2.01, + "learning_rate": 5.587203044098946e-06, + "loss": 3.8413, + "step": 2712576 + }, + { + "epoch": 2.01, + "learning_rate": 5.578817096588426e-06, + "loss": 3.8431, + "step": 2713088 + }, + { + "epoch": 2.01, + "learning_rate": 5.570431149077906e-06, + "loss": 3.8425, + "step": 2713600 + }, + { + "epoch": 2.01, + "learning_rate": 5.562045201567386e-06, + "loss": 3.8263, + "step": 2714112 + }, + { + "epoch": 2.01, + "learning_rate": 5.553659254056866e-06, + "loss": 3.8374, + "step": 2714624 + }, + { + "epoch": 2.01, + "learning_rate": 5.545273306546346e-06, + "loss": 3.837, + "step": 2715136 + }, + { + "epoch": 2.01, + "learning_rate": 5.536903737839558e-06, + "loss": 3.8409, + "step": 2715648 + }, + { + "epoch": 2.01, + "learning_rate": 5.528517790329038e-06, + "loss": 3.8422, + "step": 2716160 + }, + { + "epoch": 2.01, + "learning_rate": 5.520131842818517e-06, + "loss": 3.8272, + "step": 2716672 + }, + { + "epoch": 2.02, + "learning_rate": 5.5117458953079975e-06, + "loss": 3.8398, + "step": 2717184 + }, + { + "epoch": 2.02, + "learning_rate": 5.503376326601208e-06, + "loss": 3.8306, + "step": 2717696 + }, + { + "epoch": 2.02, + "learning_rate": 5.494990379090688e-06, + "loss": 3.8447, + "step": 2718208 + }, + { + "epoch": 2.02, + "learning_rate": 5.486604431580168e-06, + "loss": 3.8244, + "step": 2718720 + }, + { + "epoch": 2.02, + "learning_rate": 5.478218484069648e-06, + "loss": 3.8417, + "step": 2719232 + }, + { + "epoch": 2.02, + "learning_rate": 5.469832536559128e-06, + "loss": 3.847, + "step": 2719744 + }, + { + "epoch": 2.02, + "learning_rate": 5.461446589048608e-06, + "loss": 3.8366, + "step": 2720256 + }, + { + "epoch": 2.02, + "learning_rate": 5.453060641538088e-06, + "loss": 3.8195, + "step": 2720768 + }, + { + "epoch": 2.02, + "learning_rate": 5.444674694027568e-06, + "loss": 3.8365, + "step": 2721280 + }, + { + "epoch": 2.02, + "learning_rate": 5.436288746517048e-06, + "loss": 3.8377, + "step": 2721792 + }, + { + "epoch": 2.02, + "learning_rate": 5.427919177810259e-06, + "loss": 3.8464, + "step": 2722304 + }, + { + "epoch": 2.02, + "learning_rate": 5.41954960910347e-06, + "loss": 3.8407, + "step": 2722816 + }, + { + "epoch": 2.02, + "learning_rate": 5.41116366159295e-06, + "loss": 3.8298, + "step": 2723328 + }, + { + "epoch": 2.02, + "learning_rate": 5.40277771408243e-06, + "loss": 3.8332, + "step": 2723840 + }, + { + "epoch": 2.02, + "learning_rate": 5.39439176657191e-06, + "loss": 3.8415, + "step": 2724352 + }, + { + "epoch": 2.02, + "learning_rate": 5.386005819061389e-06, + "loss": 3.8231, + "step": 2724864 + }, + { + "epoch": 2.02, + "learning_rate": 5.37761987155087e-06, + "loss": 3.835, + "step": 2725376 + }, + { + "epoch": 2.02, + "learning_rate": 5.369250302844081e-06, + "loss": 3.8356, + "step": 2725888 + }, + { + "epoch": 2.02, + "learning_rate": 5.360864355333562e-06, + "loss": 3.8414, + "step": 2726400 + }, + { + "epoch": 2.02, + "learning_rate": 5.3524947866267725e-06, + "loss": 3.8185, + "step": 2726912 + }, + { + "epoch": 2.02, + "learning_rate": 5.3441088391162525e-06, + "loss": 3.8356, + "step": 2727424 + }, + { + "epoch": 2.02, + "learning_rate": 5.3357228916057325e-06, + "loss": 3.8282, + "step": 2727936 + }, + { + "epoch": 2.02, + "learning_rate": 5.3273369440952116e-06, + "loss": 3.834, + "step": 2728448 + }, + { + "epoch": 2.02, + "learning_rate": 5.318950996584692e-06, + "loss": 3.8338, + "step": 2728960 + }, + { + "epoch": 2.02, + "learning_rate": 5.3105650490741715e-06, + "loss": 3.8284, + "step": 2729472 + }, + { + "epoch": 2.02, + "learning_rate": 5.302179101563652e-06, + "loss": 3.8457, + "step": 2729984 + }, + { + "epoch": 2.02, + "learning_rate": 5.293793154053131e-06, + "loss": 3.8384, + "step": 2730496 + }, + { + "epoch": 2.02, + "learning_rate": 5.285423585346343e-06, + "loss": 3.8304, + "step": 2731008 + }, + { + "epoch": 2.02, + "learning_rate": 5.277037637835823e-06, + "loss": 3.836, + "step": 2731520 + }, + { + "epoch": 2.02, + "learning_rate": 5.268651690325303e-06, + "loss": 3.8395, + "step": 2732032 + }, + { + "epoch": 2.02, + "learning_rate": 5.260265742814783e-06, + "loss": 3.8359, + "step": 2732544 + }, + { + "epoch": 2.02, + "learning_rate": 5.251896174107994e-06, + "loss": 3.8189, + "step": 2733056 + }, + { + "epoch": 2.02, + "learning_rate": 5.243526605401205e-06, + "loss": 3.8438, + "step": 2733568 + }, + { + "epoch": 2.02, + "learning_rate": 5.235140657890685e-06, + "loss": 3.8333, + "step": 2734080 + }, + { + "epoch": 2.02, + "learning_rate": 5.226754710380165e-06, + "loss": 3.8371, + "step": 2734592 + }, + { + "epoch": 2.02, + "learning_rate": 5.218368762869645e-06, + "loss": 3.8332, + "step": 2735104 + }, + { + "epoch": 2.02, + "learning_rate": 5.209982815359125e-06, + "loss": 3.8396, + "step": 2735616 + }, + { + "epoch": 2.02, + "learning_rate": 5.201596867848605e-06, + "loss": 3.8294, + "step": 2736128 + }, + { + "epoch": 2.02, + "learning_rate": 5.193210920338085e-06, + "loss": 3.8286, + "step": 2736640 + }, + { + "epoch": 2.02, + "learning_rate": 5.184841351631297e-06, + "loss": 3.8231, + "step": 2737152 + }, + { + "epoch": 2.02, + "learning_rate": 5.176455404120776e-06, + "loss": 3.8468, + "step": 2737664 + }, + { + "epoch": 2.02, + "learning_rate": 5.168069456610257e-06, + "loss": 3.8413, + "step": 2738176 + }, + { + "epoch": 2.02, + "learning_rate": 5.159683509099736e-06, + "loss": 3.8395, + "step": 2738688 + }, + { + "epoch": 2.02, + "learning_rate": 5.1512975615892165e-06, + "loss": 3.8287, + "step": 2739200 + }, + { + "epoch": 2.02, + "learning_rate": 5.142911614078696e-06, + "loss": 3.8406, + "step": 2739712 + }, + { + "epoch": 2.02, + "learning_rate": 5.134525666568176e-06, + "loss": 3.8441, + "step": 2740224 + }, + { + "epoch": 2.02, + "learning_rate": 5.1261397190576555e-06, + "loss": 3.8313, + "step": 2740736 + }, + { + "epoch": 2.02, + "learning_rate": 5.1177537715471355e-06, + "loss": 3.8374, + "step": 2741248 + }, + { + "epoch": 2.02, + "learning_rate": 5.1093678240366154e-06, + "loss": 3.8417, + "step": 2741760 + }, + { + "epoch": 2.02, + "learning_rate": 5.100998255329826e-06, + "loss": 3.8396, + "step": 2742272 + }, + { + "epoch": 2.02, + "learning_rate": 5.092612307819307e-06, + "loss": 3.8437, + "step": 2742784 + }, + { + "epoch": 2.02, + "learning_rate": 5.084226360308786e-06, + "loss": 3.8287, + "step": 2743296 + }, + { + "epoch": 2.02, + "learning_rate": 5.075840412798266e-06, + "loss": 3.8388, + "step": 2743808 + }, + { + "epoch": 2.02, + "learning_rate": 5.067454465287746e-06, + "loss": 3.8371, + "step": 2744320 + }, + { + "epoch": 2.02, + "learning_rate": 5.059068517777226e-06, + "loss": 3.8321, + "step": 2744832 + }, + { + "epoch": 2.02, + "learning_rate": 5.050682570266707e-06, + "loss": 3.8508, + "step": 2745344 + }, + { + "epoch": 2.02, + "learning_rate": 5.042313001559918e-06, + "loss": 3.8326, + "step": 2745856 + }, + { + "epoch": 2.02, + "learning_rate": 5.0339270540493976e-06, + "loss": 3.8392, + "step": 2746368 + }, + { + "epoch": 2.02, + "learning_rate": 5.0255411065388775e-06, + "loss": 3.8374, + "step": 2746880 + }, + { + "epoch": 2.02, + "learning_rate": 5.017155159028357e-06, + "loss": 3.8379, + "step": 2747392 + }, + { + "epoch": 2.03, + "eval_loss": 4.026063919067383, + "eval_runtime": 279.2649, + "eval_samples_per_second": 1366.412, + "eval_steps_per_second": 42.701, + "step": 2747503 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0577794817386625e+18, + "trial_name": null, + "trial_params": null +}