diff --git "a/checkpoint-1221104/trainer_state.json" "b/checkpoint-1221104/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1221104/trainer_state.json" @@ -0,0 +1,14457 @@ +{ + "best_metric": 4.067862033843994, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/3/checkpoints/checkpoint-1221104", + "epoch": 0.025000278439663435, + "eval_steps": 10, + "global_step": 1221104, + "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 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 4.699033815479655e+17, + "trial_name": null, + "trial_params": null +}